From 39116103a7345927fa99644d08bc0cc9d45fea6f Mon Sep 17 00:00:00 2001 From: Zejiang Tang Date: Fri, 14 Aug 2020 10:40:24 +0800 Subject: [PATCH 001/645] MIPS: ftrace: Remove redundant #ifdef CONFIG_DYNAMIC_FTRACE There exists redundant #ifdef CONFIG_DYNAMIC_FTRACE in ftrace.c, remove it. Signed-off-by: Zejiang Tang Reviewed-by: Steven Rostedt (VMware) Signed-off-by: Thomas Bogendoerfer --- arch/mips/kernel/ftrace.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/arch/mips/kernel/ftrace.c b/arch/mips/kernel/ftrace.c index 2625232bfe52..f57e68f40a34 100644 --- a/arch/mips/kernel/ftrace.c +++ b/arch/mips/kernel/ftrace.c @@ -37,10 +37,6 @@ void arch_ftrace_update_code(int command) ftrace_modify_all_code(command); } -#endif - -#ifdef CONFIG_DYNAMIC_FTRACE - #define JAL 0x0c000000 /* jump & link: ip --> ra, jump to target */ #define ADDR_MASK 0x03ffffff /* op_code|addr : 31...26|25 ....0 */ #define JUMP_RANGE_MASK ((1UL << 28) - 1) From 6937dff24424eab9eeaa9674dbf715d9f6d57ae1 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Fri, 14 Aug 2020 18:31:30 +0800 Subject: [PATCH 002/645] MIPS: Loongson: Use default CONFIG_FRAME_WARN as 2048 for Loongson64 to fix build warnings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit After commit 70b838292bef ("MIPS: Update default config file for Loongson-3"), CONFIG_VHOST_SCSI and CONFIG_VHOST are set when use loongson3_defconfig, and then there exists the following two build warnings related with these two configs: CC [M] drivers/vhost/scsi.o drivers/vhost/scsi.c: In function ‘vhost_scsi_flush’: drivers/vhost/scsi.c:1374:1: warning: the frame size of 1040 bytes is larger than 1024 bytes [-Wframe-larger-than=] } ^ LD [M] drivers/vhost/vhost_scsi.o CC [M] drivers/vhost/vsock.o LD [M] drivers/vhost/vhost_vsock.o CC [M] drivers/vhost/vhost.o drivers/vhost/vhost.c: In function ‘log_used’: drivers/vhost/vhost.c:1896:1: warning: the frame size of 1040 bytes is larger than 1024 bytes [-Wframe-larger-than=] } ^ CONFIG_FRAME_WARN=2048 can fix it, since the default CONFIG_FRAME_WARN for 64BIT is 2048, just delete the CONFIG_FRAME_WARN line in defconfig. config FRAME_WARN int "Warn for stack frames larger than" range 0 8192 default 2048 if GCC_PLUGIN_LATENT_ENTROPY default 1280 if (!64BIT && PARISC) default 1024 if (!64BIT && !PARISC) default 2048 if 64BIT Signed-off-by: Tiezhu Yang Signed-off-by: Thomas Bogendoerfer --- arch/mips/configs/loongson3_defconfig | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/mips/configs/loongson3_defconfig b/arch/mips/configs/loongson3_defconfig index a65b08de4098..a5005c8cee8a 100644 --- a/arch/mips/configs/loongson3_defconfig +++ b/arch/mips/configs/loongson3_defconfig @@ -403,7 +403,6 @@ CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_DEFLATE=m CONFIG_PRINTK_TIME=y -CONFIG_FRAME_WARN=1024 CONFIG_STRIP_ASM_SYMS=y CONFIG_MAGIC_SYSRQ=y # CONFIG_SCHED_DEBUG is not set From 58c9e24721c4a84eb5a6db3c1d54dba97e97b3f7 Mon Sep 17 00:00:00 2001 From: Aleksander Jan Bajkowski Date: Mon, 10 Aug 2020 20:09:46 +0200 Subject: [PATCH 003/645] MIPS: lantiq: add missing GPHY clock aliases for ar10 and grx390 Add missing GPHY clock aliases for ar10 (xrx300) and grx390 (xrx330). PMU in ar10 and grx390 differs from vr9. Ar10 has 3 and grx390 has 4 built-in GPHY compared to vr9 which has 2. Corespondings PMU bit: GPHY0 -> bit 29 GPHY1 -> bit 30 GPHY2 -> bit 31 GPHY3 -> bit 26 Tested on D-Link DWR-966 with OpenWRT. Signed-off-by: Aleksander Jan Bajkowski Cc: linux-mips@vger.kernel.org Cc: john@phrozen.org Cc: hauke@hauke-m.de Cc: tsbogend@alpha.franken.de Acked-by: Hauke Mehrtens Signed-off-by: Thomas Bogendoerfer --- arch/mips/lantiq/xway/sysctrl.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/arch/mips/lantiq/xway/sysctrl.c b/arch/mips/lantiq/xway/sysctrl.c index b10342018d19..917fac1636b7 100644 --- a/arch/mips/lantiq/xway/sysctrl.c +++ b/arch/mips/lantiq/xway/sysctrl.c @@ -112,11 +112,15 @@ static u32 pmu_clk_cr_b[] = { #define PMU_PPE_DP BIT(23) #define PMU_PPE_DPLUS BIT(24) #define PMU_USB1_P BIT(26) +#define PMU_GPHY3 BIT(26) /* grx390 */ #define PMU_USB1 BIT(27) #define PMU_SWITCH BIT(28) #define PMU_PPE_TOP BIT(29) +#define PMU_GPHY0 BIT(29) /* ar10, xrx390 */ #define PMU_GPHY BIT(30) +#define PMU_GPHY1 BIT(30) /* ar10, xrx390 */ #define PMU_PCIE_CLK BIT(31) +#define PMU_GPHY2 BIT(31) /* ar10, xrx390 */ #define PMU1_PCIE_PHY BIT(0) /* vr9-specific,moved in ar10/grx390 */ #define PMU1_PCIE_CTL BIT(1) @@ -465,6 +469,9 @@ void __init ltq_soc_init(void) if (of_machine_is_compatible("lantiq,grx390") || of_machine_is_compatible("lantiq,ar10")) { + clkdev_add_pmu("1e108000.switch", "gphy0", 0, 0, PMU_GPHY0); + clkdev_add_pmu("1e108000.switch", "gphy1", 0, 0, PMU_GPHY1); + clkdev_add_pmu("1e108000.switch", "gphy2", 0, 0, PMU_GPHY2); clkdev_add_pmu("1f203018.usb2-phy", "phy", 1, 2, PMU_ANALOG_USB0_P); clkdev_add_pmu("1f203034.usb2-phy", "phy", 1, 2, PMU_ANALOG_USB1_P); /* rc 0 */ @@ -496,6 +503,7 @@ void __init ltq_soc_init(void) } else if (of_machine_is_compatible("lantiq,grx390")) { clkdev_add_static(ltq_grx390_cpu_hz(), ltq_grx390_fpi_hz(), ltq_grx390_fpi_hz(), ltq_grx390_pp32_hz()); + clkdev_add_pmu("1e108000.switch", "gphy3", 0, 0, PMU_GPHY3); clkdev_add_pmu("1e101000.usb", "otg", 1, 0, PMU_USB0); clkdev_add_pmu("1e106000.usb", "otg", 1, 0, PMU_USB1); /* rc 2 */ @@ -514,8 +522,6 @@ void __init ltq_soc_init(void) clkdev_add_pmu("1e10b308.eth", NULL, 0, 0, PMU_SWITCH | PMU_PPE_DP | PMU_PPE_TC); clkdev_add_pmu("1da00000.usif", "NULL", 1, 0, PMU_USIF); - clkdev_add_pmu("1e108000.switch", "gphy0", 0, 0, PMU_GPHY); - clkdev_add_pmu("1e108000.switch", "gphy1", 0, 0, PMU_GPHY); clkdev_add_pmu("1e103100.deu", NULL, 1, 0, PMU_DEU); clkdev_add_pmu("1e116000.mei", "afe", 1, 2, PMU_ANALOG_DSL_AFE); clkdev_add_pmu("1e116000.mei", "dfe", 1, 0, PMU_DFE); From 7e914be75fc2198cfa5fffdd55a8f4ce463778e1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C3=81lvaro=20Fern=C3=A1ndez=20Rojas?= Date: Wed, 12 Aug 2020 09:52:31 +0200 Subject: [PATCH 004/645] MIPS: BCM63xx: remove duplicated new lines MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are 3 duplicated new lines, let's remove them. Signed-off-by: Álvaro Fernández Rojas Acked-by: Florian Fainelli Reviewed-by: Philippe Mathieu-Daudé Signed-off-by: Thomas Bogendoerfer --- arch/mips/bcm63xx/boards/board_bcm963xx.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/mips/bcm63xx/boards/board_bcm963xx.c b/arch/mips/bcm63xx/boards/board_bcm963xx.c index 230bf27c1fb8..744aa16bab12 100644 --- a/arch/mips/bcm63xx/boards/board_bcm963xx.c +++ b/arch/mips/bcm63xx/boards/board_bcm963xx.c @@ -32,7 +32,6 @@ #include - #define HCS_OFFSET_128K 0x20000 static struct board_info board; @@ -337,7 +336,6 @@ static struct board_info __initdata board_96348gw_11 = { .force_duplex_full = 1, }, - .has_ohci0 = 1, .has_pccard = 1, .has_ehci0 = 1, @@ -580,7 +578,6 @@ static struct board_info __initdata board_96358vw2 = { .force_duplex_full = 1, }, - .has_ohci0 = 1, .has_pccard = 1, .has_ehci0 = 1, From 3879e1dafcc30e60c3d5ea4ae4d3ae8ea02a76a8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C3=81lvaro=20Fern=C3=A1ndez=20Rojas?= Date: Wed, 12 Aug 2020 09:52:32 +0200 Subject: [PATCH 005/645] MIPS: BCM63xx: remove EHCI from BCM6348 boards MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There's no EHCI controller on BCM6348. Signed-off-by: Álvaro Fernández Rojas Acked-by: Florian Fainelli Reviewed-by: Philippe Mathieu-Daudé Signed-off-by: Thomas Bogendoerfer --- arch/mips/bcm63xx/boards/board_bcm963xx.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/mips/bcm63xx/boards/board_bcm963xx.c b/arch/mips/bcm63xx/boards/board_bcm963xx.c index 744aa16bab12..45f1bc437245 100644 --- a/arch/mips/bcm63xx/boards/board_bcm963xx.c +++ b/arch/mips/bcm63xx/boards/board_bcm963xx.c @@ -285,7 +285,6 @@ static struct board_info __initdata board_96348gw_10 = { .has_ohci0 = 1, .has_pccard = 1, - .has_ehci0 = 1, .leds = { { @@ -338,7 +337,6 @@ static struct board_info __initdata board_96348gw_11 = { .has_ohci0 = 1, .has_pccard = 1, - .has_ehci0 = 1, .leds = { { @@ -441,7 +439,6 @@ static struct board_info __initdata board_FAST2404 = { .has_ohci0 = 1, .has_pccard = 1, - .has_ehci0 = 1, }; static struct board_info __initdata board_rta1025w_16 = { From f5e8983e44b403f1bef85dff96e34d1b1ab318c7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C3=81lvaro=20Fern=C3=A1ndez=20Rojas?= Date: Wed, 12 Aug 2020 09:52:33 +0200 Subject: [PATCH 006/645] MIPS: BCM63xx: enable EHCI for DWV-S0 board MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit BCM6358 SoCs have OHCI and EHCI controllers that share the same USB ports. Therefore, the board should also have EHCI enabled. Signed-off-by: Álvaro Fernández Rojas Acked-by: Florian Fainelli Reviewed-by: Philippe Mathieu-Daudé Signed-off-by: Thomas Bogendoerfer --- arch/mips/bcm63xx/boards/board_bcm963xx.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/mips/bcm63xx/boards/board_bcm963xx.c b/arch/mips/bcm63xx/boards/board_bcm963xx.c index 45f1bc437245..ac9570b66f37 100644 --- a/arch/mips/bcm63xx/boards/board_bcm963xx.c +++ b/arch/mips/bcm63xx/boards/board_bcm963xx.c @@ -645,6 +645,7 @@ static struct board_info __initdata board_DWVS0 = { }, .has_ohci0 = 1, + .has_ehci0 = 1, }; #endif /* CONFIG_BCM63XX_CPU_6358 */ From a5fb3b4518bc0e53ebc61580dd64196be32db165 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C3=81lvaro=20Fern=C3=A1ndez=20Rojas?= Date: Wed, 12 Aug 2020 09:52:34 +0200 Subject: [PATCH 007/645] MIPS: BCM63xx: refactor board declarations MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Current board declarations are a mess. Let's put some order and make them follow the same structure. Signed-off-by: Álvaro Fernández Rojas Acked-by: Florian Fainelli Reviewed-by: Philippe Mathieu-Daudé Signed-off-by: Thomas Bogendoerfer --- arch/mips/bcm63xx/boards/board_bcm963xx.c | 667 +++++++++++----------- 1 file changed, 331 insertions(+), 336 deletions(-) diff --git a/arch/mips/bcm63xx/boards/board_bcm963xx.c b/arch/mips/bcm63xx/boards/board_bcm963xx.c index ac9570b66f37..fa0acf003a46 100644 --- a/arch/mips/bcm63xx/boards/board_bcm963xx.c +++ b/arch/mips/bcm63xx/boards/board_bcm963xx.c @@ -41,30 +41,28 @@ static struct board_info board; */ #ifdef CONFIG_BCM63XX_CPU_3368 static struct board_info __initdata board_cvg834g = { - .name = "CVG834G_E15R3921", - .expected_cpu_id = 0x3368, + .name = "CVG834G_E15R3921", + .expected_cpu_id = 0x3368, - .has_uart0 = 1, - .has_uart1 = 1, - - .has_enet0 = 1, - .has_pci = 1, + .ephy_reset_gpio = 36, + .ephy_reset_gpio_flags = GPIOF_INIT_HIGH, + .has_pci = 1, + .has_uart0 = 1, + .has_uart1 = 1, + .has_enet0 = 1, .enet0 = { - .has_phy = 1, - .use_internal_phy = 1, + .has_phy = 1, + .use_internal_phy = 1, }, .leds = { { - .name = "CVG834G:green:power", - .gpio = 37, + .name = "CVG834G:green:power", + .gpio = 37, .default_trigger= "default-on", }, }, - - .ephy_reset_gpio = 36, - .ephy_reset_gpio_flags = GPIOF_INIT_HIGH, }; #endif /* CONFIG_BCM63XX_CPU_3368 */ @@ -73,44 +71,44 @@ static struct board_info __initdata board_cvg834g = { */ #ifdef CONFIG_BCM63XX_CPU_6328 static struct board_info __initdata board_96328avng = { - .name = "96328avng", - .expected_cpu_id = 0x6328, + .name = "96328avng", + .expected_cpu_id = 0x6328, - .has_uart0 = 1, - .has_pci = 1, - .has_usbd = 0, + .has_pci = 1, + .has_uart0 = 1, + .has_usbd = 0, .usbd = { - .use_fullspeed = 0, - .port_no = 0, + .use_fullspeed = 0, + .port_no = 0, }, .leds = { { - .name = "96328avng::ppp-fail", - .gpio = 2, - .active_low = 1, + .name = "96328avng::ppp-fail", + .gpio = 2, + .active_low = 1, }, { - .name = "96328avng::power", - .gpio = 4, - .active_low = 1, + .name = "96328avng::power", + .gpio = 4, + .active_low = 1, .default_trigger = "default-on", }, { - .name = "96328avng::power-fail", - .gpio = 8, - .active_low = 1, + .name = "96328avng::power-fail", + .gpio = 8, + .active_low = 1, }, { - .name = "96328avng::wps", - .gpio = 9, - .active_low = 1, + .name = "96328avng::wps", + .gpio = 9, + .active_low = 1, }, { - .name = "96328avng::ppp", - .gpio = 11, - .active_low = 1, + .name = "96328avng::ppp", + .gpio = 11, + .active_low = 1, }, }, }; @@ -121,85 +119,86 @@ static struct board_info __initdata board_96328avng = { */ #ifdef CONFIG_BCM63XX_CPU_6338 static struct board_info __initdata board_96338gw = { - .name = "96338GW", - .expected_cpu_id = 0x6338, + .name = "96338GW", + .expected_cpu_id = 0x6338, - .has_uart0 = 1, - .has_enet0 = 1, + .has_ohci0 = 1, + .has_uart0 = 1, + + .has_enet0 = 1, .enet0 = { - .force_speed_100 = 1, - .force_duplex_full = 1, + .force_speed_100 = 1, + .force_duplex_full = 1, }, - .has_ohci0 = 1, - .leds = { { - .name = "adsl", - .gpio = 3, - .active_low = 1, + .name = "adsl", + .gpio = 3, + .active_low = 1, }, { - .name = "ses", - .gpio = 5, - .active_low = 1, + .name = "ses", + .gpio = 5, + .active_low = 1, }, { - .name = "ppp-fail", - .gpio = 4, - .active_low = 1, + .name = "ppp-fail", + .gpio = 4, + .active_low = 1, }, { - .name = "power", - .gpio = 0, - .active_low = 1, + .name = "power", + .gpio = 0, + .active_low = 1, .default_trigger = "default-on", }, { - .name = "stop", - .gpio = 1, - .active_low = 1, + .name = "stop", + .gpio = 1, + .active_low = 1, } }, }; static struct board_info __initdata board_96338w = { - .name = "96338W", - .expected_cpu_id = 0x6338, + .name = "96338W", + .expected_cpu_id = 0x6338, - .has_uart0 = 1, - .has_enet0 = 1, + .has_uart0 = 1, + + .has_enet0 = 1, .enet0 = { - .force_speed_100 = 1, - .force_duplex_full = 1, + .force_speed_100 = 1, + .force_duplex_full = 1, }, .leds = { { - .name = "adsl", - .gpio = 3, - .active_low = 1, + .name = "adsl", + .gpio = 3, + .active_low = 1, }, { - .name = "ses", - .gpio = 5, - .active_low = 1, + .name = "ses", + .gpio = 5, + .active_low = 1, }, { - .name = "ppp-fail", - .gpio = 4, - .active_low = 1, + .name = "ppp-fail", + .gpio = 4, + .active_low = 1, }, { - .name = "power", - .gpio = 0, - .active_low = 1, + .name = "power", + .gpio = 0, + .active_low = 1, .default_trigger = "default-on", }, { - .name = "stop", - .gpio = 1, - .active_low = 1, + .name = "stop", + .gpio = 1, + .active_low = 1, }, }, }; @@ -210,10 +209,10 @@ static struct board_info __initdata board_96338w = { */ #ifdef CONFIG_BCM63XX_CPU_6345 static struct board_info __initdata board_96345gw2 = { - .name = "96345GW2", - .expected_cpu_id = 0x6345, + .name = "96345GW2", + .expected_cpu_id = 0x6345, - .has_uart0 = 1, + .has_uart0 = 1, }; #endif /* CONFIG_BCM63XX_CPU_6345 */ @@ -222,282 +221,282 @@ static struct board_info __initdata board_96345gw2 = { */ #ifdef CONFIG_BCM63XX_CPU_6348 static struct board_info __initdata board_96348r = { - .name = "96348R", - .expected_cpu_id = 0x6348, + .name = "96348R", + .expected_cpu_id = 0x6348, - .has_uart0 = 1, - .has_enet0 = 1, - .has_pci = 1, + .has_pci = 1, + .has_uart0 = 1, + .has_enet0 = 1, .enet0 = { - .has_phy = 1, - .use_internal_phy = 1, + .has_phy = 1, + .use_internal_phy = 1, }, .leds = { { - .name = "adsl-fail", - .gpio = 2, - .active_low = 1, + .name = "adsl-fail", + .gpio = 2, + .active_low = 1, }, { - .name = "ppp", - .gpio = 3, - .active_low = 1, + .name = "ppp", + .gpio = 3, + .active_low = 1, }, { - .name = "ppp-fail", - .gpio = 4, - .active_low = 1, + .name = "ppp-fail", + .gpio = 4, + .active_low = 1, }, { - .name = "power", - .gpio = 0, - .active_low = 1, + .name = "power", + .gpio = 0, + .active_low = 1, .default_trigger = "default-on", }, { - .name = "stop", - .gpio = 1, - .active_low = 1, + .name = "stop", + .gpio = 1, + .active_low = 1, }, }, }; static struct board_info __initdata board_96348gw_10 = { - .name = "96348GW-10", - .expected_cpu_id = 0x6348, + .name = "96348GW-10", + .expected_cpu_id = 0x6348, - .has_uart0 = 1, - .has_enet0 = 1, - .has_enet1 = 1, - .has_pci = 1, + .has_ohci0 = 1, + .has_pccard = 1, + .has_pci = 1, + .has_uart0 = 1, + .has_enet0 = 1, .enet0 = { - .has_phy = 1, - .use_internal_phy = 1, - }, - .enet1 = { - .force_speed_100 = 1, - .force_duplex_full = 1, + .has_phy = 1, + .use_internal_phy = 1, }, - .has_ohci0 = 1, - .has_pccard = 1, + .has_enet1 = 1, + .enet1 = { + .force_speed_100 = 1, + .force_duplex_full = 1, + }, .leds = { { - .name = "adsl-fail", - .gpio = 2, - .active_low = 1, + .name = "adsl-fail", + .gpio = 2, + .active_low = 1, }, { - .name = "ppp", - .gpio = 3, - .active_low = 1, + .name = "ppp", + .gpio = 3, + .active_low = 1, }, { - .name = "ppp-fail", - .gpio = 4, - .active_low = 1, + .name = "ppp-fail", + .gpio = 4, + .active_low = 1, }, { - .name = "power", - .gpio = 0, - .active_low = 1, + .name = "power", + .gpio = 0, + .active_low = 1, .default_trigger = "default-on", }, { - .name = "stop", - .gpio = 1, - .active_low = 1, + .name = "stop", + .gpio = 1, + .active_low = 1, }, }, }; static struct board_info __initdata board_96348gw_11 = { - .name = "96348GW-11", - .expected_cpu_id = 0x6348, - - .has_uart0 = 1, - .has_enet0 = 1, - .has_enet1 = 1, - .has_pci = 1, - - .enet0 = { - .has_phy = 1, - .use_internal_phy = 1, - }, - - .enet1 = { - .force_speed_100 = 1, - .force_duplex_full = 1, - }, + .name = "96348GW-11", + .expected_cpu_id = 0x6348, .has_ohci0 = 1, .has_pccard = 1, + .has_pci = 1, + .has_uart0 = 1, + + .has_enet0 = 1, + .enet0 = { + .has_phy = 1, + .use_internal_phy = 1, + }, + + .has_enet1 = 1, + .enet1 = { + .force_speed_100 = 1, + .force_duplex_full = 1, + }, .leds = { { - .name = "adsl-fail", - .gpio = 2, - .active_low = 1, + .name = "adsl-fail", + .gpio = 2, + .active_low = 1, }, { - .name = "ppp", - .gpio = 3, - .active_low = 1, + .name = "ppp", + .gpio = 3, + .active_low = 1, }, { - .name = "ppp-fail", - .gpio = 4, - .active_low = 1, + .name = "ppp-fail", + .gpio = 4, + .active_low = 1, }, { - .name = "power", - .gpio = 0, - .active_low = 1, + .name = "power", + .gpio = 0, + .active_low = 1, .default_trigger = "default-on", }, { - .name = "stop", - .gpio = 1, - .active_low = 1, + .name = "stop", + .gpio = 1, + .active_low = 1, }, }, }; static struct board_info __initdata board_96348gw = { - .name = "96348GW", - .expected_cpu_id = 0x6348, - - .has_uart0 = 1, - .has_enet0 = 1, - .has_enet1 = 1, - .has_pci = 1, - - .enet0 = { - .has_phy = 1, - .use_internal_phy = 1, - }, - .enet1 = { - .force_speed_100 = 1, - .force_duplex_full = 1, - }, + .name = "96348GW", + .expected_cpu_id = 0x6348, .has_ohci0 = 1, + .has_pci = 1, + .has_uart0 = 1, + + .has_enet0 = 1, + .enet0 = { + .has_phy = 1, + .use_internal_phy = 1, + }, + + .has_enet1 = 1, + .enet1 = { + .force_speed_100 = 1, + .force_duplex_full = 1, + }, .leds = { { - .name = "adsl-fail", - .gpio = 2, - .active_low = 1, + .name = "adsl-fail", + .gpio = 2, + .active_low = 1, }, { - .name = "ppp", - .gpio = 3, - .active_low = 1, + .name = "ppp", + .gpio = 3, + .active_low = 1, }, { - .name = "ppp-fail", - .gpio = 4, - .active_low = 1, + .name = "ppp-fail", + .gpio = 4, + .active_low = 1, }, { - .name = "power", - .gpio = 0, - .active_low = 1, + .name = "power", + .gpio = 0, + .active_low = 1, .default_trigger = "default-on", }, { - .name = "stop", - .gpio = 1, - .active_low = 1, + .name = "stop", + .gpio = 1, + .active_low = 1, }, }, }; static struct board_info __initdata board_FAST2404 = { - .name = "F@ST2404", - .expected_cpu_id = 0x6348, + .name = "F@ST2404", + .expected_cpu_id = 0x6348, - .has_uart0 = 1, - .has_enet0 = 1, - .has_enet1 = 1, - .has_pci = 1, + .has_ohci0 = 1, + .has_pccard = 1, + .has_pci = 1, + .has_uart0 = 1, + .has_enet0 = 1, .enet0 = { - .has_phy = 1, - .use_internal_phy = 1, + .has_phy = 1, + .use_internal_phy = 1, }, + .has_enet1 = 1, .enet1 = { - .force_speed_100 = 1, - .force_duplex_full = 1, + .force_speed_100 = 1, + .force_duplex_full = 1, }, - - .has_ohci0 = 1, - .has_pccard = 1, }; static struct board_info __initdata board_rta1025w_16 = { - .name = "RTA1025W_16", - .expected_cpu_id = 0x6348, + .name = "RTA1025W_16", + .expected_cpu_id = 0x6348, - .has_enet0 = 1, - .has_enet1 = 1, - .has_pci = 1, + .has_pci = 1, + .has_enet0 = 1, .enet0 = { - .has_phy = 1, - .use_internal_phy = 1, + .has_phy = 1, + .use_internal_phy = 1, }, + + .has_enet1 = 1, .enet1 = { - .force_speed_100 = 1, - .force_duplex_full = 1, + .force_speed_100 = 1, + .force_duplex_full = 1, }, }; static struct board_info __initdata board_DV201AMR = { - .name = "DV201AMR", - .expected_cpu_id = 0x6348, + .name = "DV201AMR", + .expected_cpu_id = 0x6348, - .has_uart0 = 1, - .has_pci = 1, - .has_ohci0 = 1, + .has_ohci0 = 1, + .has_pci = 1, + .has_uart0 = 1, - .has_enet0 = 1, - .has_enet1 = 1, + .has_enet0 = 1, .enet0 = { - .has_phy = 1, - .use_internal_phy = 1, + .has_phy = 1, + .use_internal_phy = 1, }, + + .has_enet1 = 1, .enet1 = { - .force_speed_100 = 1, - .force_duplex_full = 1, + .force_speed_100 = 1, + .force_duplex_full = 1, }, }; static struct board_info __initdata board_96348gw_a = { - .name = "96348GW-A", - .expected_cpu_id = 0x6348, - - .has_uart0 = 1, - .has_enet0 = 1, - .has_enet1 = 1, - .has_pci = 1, - - .enet0 = { - .has_phy = 1, - .use_internal_phy = 1, - }, - .enet1 = { - .force_speed_100 = 1, - .force_duplex_full = 1, - }, + .name = "96348GW-A", + .expected_cpu_id = 0x6348, .has_ohci0 = 1, + .has_pci = 1, + .has_uart0 = 1, + + .has_enet0 = 1, + .enet0 = { + .has_phy = 1, + .use_internal_phy = 1, + }, + + .has_enet1 = 1, + .enet1 = { + .force_speed_100 = 1, + .force_duplex_full = 1, + }, }; #endif /* CONFIG_BCM63XX_CPU_6348 */ @@ -506,146 +505,142 @@ static struct board_info __initdata board_96348gw_a = { */ #ifdef CONFIG_BCM63XX_CPU_6358 static struct board_info __initdata board_96358vw = { - .name = "96358VW", - .expected_cpu_id = 0x6358, - - .has_uart0 = 1, - .has_enet0 = 1, - .has_enet1 = 1, - .has_pci = 1, - - .enet0 = { - .has_phy = 1, - .use_internal_phy = 1, - }, - - .enet1 = { - .force_speed_100 = 1, - .force_duplex_full = 1, - }, + .name = "96358VW", + .expected_cpu_id = 0x6358, + .has_ehci0 = 1, .has_ohci0 = 1, .has_pccard = 1, - .has_ehci0 = 1, + .has_pci = 1, + .has_uart0 = 1, + + .has_enet0 = 1, + .enet0 = { + .has_phy = 1, + .use_internal_phy = 1, + }, + + .has_enet1 = 1, + .enet1 = { + .force_speed_100 = 1, + .force_duplex_full = 1, + }, .leds = { { - .name = "adsl-fail", - .gpio = 15, - .active_low = 1, + .name = "adsl-fail", + .gpio = 15, + .active_low = 1, }, { - .name = "ppp", - .gpio = 22, - .active_low = 1, + .name = "ppp", + .gpio = 22, + .active_low = 1, }, { - .name = "ppp-fail", - .gpio = 23, - .active_low = 1, + .name = "ppp-fail", + .gpio = 23, + .active_low = 1, }, { - .name = "power", - .gpio = 4, + .name = "power", + .gpio = 4, .default_trigger = "default-on", }, { - .name = "stop", - .gpio = 5, + .name = "stop", + .gpio = 5, }, }, }; static struct board_info __initdata board_96358vw2 = { - .name = "96358VW2", - .expected_cpu_id = 0x6358, - - .has_uart0 = 1, - .has_enet0 = 1, - .has_enet1 = 1, - .has_pci = 1, - - .enet0 = { - .has_phy = 1, - .use_internal_phy = 1, - }, - - .enet1 = { - .force_speed_100 = 1, - .force_duplex_full = 1, - }, + .name = "96358VW2", + .expected_cpu_id = 0x6358, + .has_ehci0 = 1, .has_ohci0 = 1, .has_pccard = 1, - .has_ehci0 = 1, + .has_pci = 1, + .has_uart0 = 1, + + .has_enet0 = 1, + .enet0 = { + .has_phy = 1, + .use_internal_phy = 1, + }, + + .has_enet1 = 1, + .enet1 = { + .force_speed_100 = 1, + .force_duplex_full = 1, + }, .leds = { { - .name = "adsl", - .gpio = 22, - .active_low = 1, + .name = "adsl", + .gpio = 22, + .active_low = 1, }, { - .name = "ppp-fail", - .gpio = 23, + .name = "ppp-fail", + .gpio = 23, }, { - .name = "power", - .gpio = 5, - .active_low = 1, + .name = "power", + .gpio = 5, + .active_low = 1, .default_trigger = "default-on", }, { - .name = "stop", - .gpio = 4, - .active_low = 1, + .name = "stop", + .gpio = 4, + .active_low = 1, }, }, }; static struct board_info __initdata board_AGPFS0 = { - .name = "AGPF-S0", - .expected_cpu_id = 0x6358, + .name = "AGPF-S0", + .expected_cpu_id = 0x6358, - .has_uart0 = 1, - .has_enet0 = 1, - .has_enet1 = 1, - .has_pci = 1, - - .enet0 = { - .has_phy = 1, - .use_internal_phy = 1, - }, - - .enet1 = { - .force_speed_100 = 1, - .force_duplex_full = 1, - }, - - .has_ohci0 = 1, .has_ehci0 = 1, + .has_ohci0 = 1, + .has_pci = 1, + .has_uart0 = 1, + + .has_enet0 = 1, + .enet0 = { + .has_phy = 1, + .use_internal_phy = 1, + }, + + .has_enet1 = 1, + .enet1 = { + .force_speed_100 = 1, + .force_duplex_full = 1, + }, }; static struct board_info __initdata board_DWVS0 = { - .name = "DWV-S0", - .expected_cpu_id = 0x6358, + .name = "DWV-S0", + .expected_cpu_id = 0x6358, - .has_enet0 = 1, - .has_enet1 = 1, - .has_pci = 1, + .has_ehci0 = 1, + .has_ohci0 = 1, + .has_pci = 1, + .has_enet0 = 1, .enet0 = { - .has_phy = 1, - .use_internal_phy = 1, + .has_phy = 1, + .use_internal_phy = 1, }, + .has_enet1 = 1, .enet1 = { - .force_speed_100 = 1, - .force_duplex_full = 1, + .force_speed_100 = 1, + .force_duplex_full = 1, }, - - .has_ohci0 = 1, - .has_ehci0 = 1, }; #endif /* CONFIG_BCM63XX_CPU_6358 */ From 08b5666db72273d2054a2a48961c6c33f9d697b2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C3=81lvaro=20Fern=C3=A1ndez=20Rojas?= Date: Wed, 12 Aug 2020 09:52:35 +0200 Subject: [PATCH 008/645] MIPS: BCM63xx: switch to SPDX license identifier MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Use SPDX license indentifier instead of local reference to COPYING. Signed-off-by: Álvaro Fernández Rojas Acked-by: Florian Fainelli Signed-off-by: Thomas Bogendoerfer --- arch/mips/bcm63xx/boards/board_bcm963xx.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/arch/mips/bcm63xx/boards/board_bcm963xx.c b/arch/mips/bcm63xx/boards/board_bcm963xx.c index fa0acf003a46..01aff80a5967 100644 --- a/arch/mips/bcm63xx/boards/board_bcm963xx.c +++ b/arch/mips/bcm63xx/boards/board_bcm963xx.c @@ -1,8 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0-only /* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * * Copyright (C) 2008 Maxime Bizon * Copyright (C) 2008 Florian Fainelli */ From d92aabca4df182763cd541d342f2d55f8c0a827c Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Sat, 25 Jul 2020 21:15:20 -0700 Subject: [PATCH 009/645] firmware: bcm47xx_sprom: Fix -Wmissing-prototypes warnings bcm47xx_sprom.h did not include a prototype for bcm47xx_fill_sprom() therefore add one, and make sure we do include that header to fix -Wmissing-prototypes warnings. Reported-by: kernel test robot Signed-off-by: Florian Fainelli Signed-off-by: Thomas Bogendoerfer --- drivers/firmware/broadcom/bcm47xx_sprom.c | 1 + include/linux/bcm47xx_sprom.h | 10 ++++++++++ 2 files changed, 11 insertions(+) diff --git a/drivers/firmware/broadcom/bcm47xx_sprom.c b/drivers/firmware/broadcom/bcm47xx_sprom.c index 4787f86c8ac1..14fbcd11657c 100644 --- a/drivers/firmware/broadcom/bcm47xx_sprom.c +++ b/drivers/firmware/broadcom/bcm47xx_sprom.c @@ -27,6 +27,7 @@ */ #include +#include #include #include #include diff --git a/include/linux/bcm47xx_sprom.h b/include/linux/bcm47xx_sprom.h index b0f4424f34fc..f8254fd53e15 100644 --- a/include/linux/bcm47xx_sprom.h +++ b/include/linux/bcm47xx_sprom.h @@ -9,9 +9,19 @@ #include #include +struct ssb_sprom; + #ifdef CONFIG_BCM47XX_SPROM +void bcm47xx_fill_sprom(struct ssb_sprom *sprom, const char *prefix, + bool fallback); int bcm47xx_sprom_register_fallbacks(void); #else +static inline void bcm47xx_fill_sprom(struct ssb_sprom *sprom, + const char *prefix, + bool fallback) +{ +} + static inline int bcm47xx_sprom_register_fallbacks(void) { return -ENOTSUPP; From 07989ee3abad9ffba5560f7434cfb02a5f74033e Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Sat, 25 Jul 2020 21:15:21 -0700 Subject: [PATCH 010/645] MIPS: BCM47xx: Include bcm47xx_sprom.h Now that bcm47xx_sprom.h contains a prototype for bcm47xx_fill_sprom, include that header file directly from bcm47xx.h. Signed-off-by: Florian Fainelli Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/mach-bcm47xx/bcm47xx.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/arch/mips/include/asm/mach-bcm47xx/bcm47xx.h b/arch/mips/include/asm/mach-bcm47xx/bcm47xx.h index d7f1ef246d5c..93817bfb7fb2 100644 --- a/arch/mips/include/asm/mach-bcm47xx/bcm47xx.h +++ b/arch/mips/include/asm/mach-bcm47xx/bcm47xx.h @@ -10,6 +10,7 @@ #include #include #include +#include enum bcm47xx_bus_type { #ifdef CONFIG_BCM47XX_SSB @@ -32,9 +33,6 @@ union bcm47xx_bus { extern union bcm47xx_bus bcm47xx_bus; extern enum bcm47xx_bus_type bcm47xx_bus_type; -void bcm47xx_fill_sprom(struct ssb_sprom *sprom, const char *prefix, - bool fallback); - void bcm47xx_set_system_type(u16 chip_id); #endif /* __ASM_BCM47XX_H */ From 725ac66ed278f5cea418251e35ca1e289d497c6f Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Sat, 22 Aug 2020 10:02:51 +0200 Subject: [PATCH 011/645] MIPS: Paravirt: remove remaining pieces of paravirt Commit 35546aeede8e ("MIPS: Retire kvm paravirt") removed kvm paravirt support, but missed arch/mips/include/mach-paravirt. Remove it as well. Signed-off-by: Thomas Bogendoerfer --- .../asm/mach-paravirt/cpu-feature-overrides.h | 35 ------------- arch/mips/include/asm/mach-paravirt/irq.h | 19 ------- .../asm/mach-paravirt/kernel-entry-init.h | 52 ------------------- 3 files changed, 106 deletions(-) delete mode 100644 arch/mips/include/asm/mach-paravirt/cpu-feature-overrides.h delete mode 100644 arch/mips/include/asm/mach-paravirt/irq.h delete mode 100644 arch/mips/include/asm/mach-paravirt/kernel-entry-init.h diff --git a/arch/mips/include/asm/mach-paravirt/cpu-feature-overrides.h b/arch/mips/include/asm/mach-paravirt/cpu-feature-overrides.h deleted file mode 100644 index 23ecf816daa7..000000000000 --- a/arch/mips/include/asm/mach-paravirt/cpu-feature-overrides.h +++ /dev/null @@ -1,35 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2013 Cavium, Inc. - */ -#ifndef __ASM_MACH_PARAVIRT_CPU_FEATURE_OVERRIDES_H -#define __ASM_MACH_PARAVIRT_CPU_FEATURE_OVERRIDES_H - -#define cpu_has_4kex 1 -#define cpu_has_3k_cache 0 -#define cpu_has_tx39_cache 0 -#define cpu_has_counter 1 -#define cpu_has_llsc 1 -/* - * We Disable LL/SC on non SMP systems as it is faster to disable - * interrupts for atomic access than a LL/SC. - */ -#ifdef CONFIG_SMP -# define kernel_uses_llsc 1 -#else -# define kernel_uses_llsc 0 -#endif - -#ifdef CONFIG_CPU_CAVIUM_OCTEON -#define cpu_dcache_line_size() 128 -#define cpu_icache_line_size() 128 -#define cpu_has_octeon_cache 1 -#define cpu_has_4k_cache 0 -#else -#define cpu_has_4k_cache 1 -#endif - -#endif /* __ASM_MACH_PARAVIRT_CPU_FEATURE_OVERRIDES_H */ diff --git a/arch/mips/include/asm/mach-paravirt/irq.h b/arch/mips/include/asm/mach-paravirt/irq.h deleted file mode 100644 index 9b4d35eca977..000000000000 --- a/arch/mips/include/asm/mach-paravirt/irq.h +++ /dev/null @@ -1,19 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2013 Cavium, Inc. - */ -#ifndef __ASM_MACH_PARAVIRT_IRQ_H__ -#define __ASM_MACH_PARAVIRT_IRQ_H__ - -#define NR_IRQS 64 -#define MIPS_CPU_IRQ_BASE 1 - -#define MIPS_IRQ_PCIA (MIPS_CPU_IRQ_BASE + 8) - -#define MIPS_IRQ_MBOX0 (MIPS_CPU_IRQ_BASE + 32) -#define MIPS_IRQ_MBOX1 (MIPS_CPU_IRQ_BASE + 33) - -#endif /* __ASM_MACH_PARAVIRT_IRQ_H__ */ diff --git a/arch/mips/include/asm/mach-paravirt/kernel-entry-init.h b/arch/mips/include/asm/mach-paravirt/kernel-entry-init.h deleted file mode 100644 index c9f5769dfc8f..000000000000 --- a/arch/mips/include/asm/mach-paravirt/kernel-entry-init.h +++ /dev/null @@ -1,52 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2013 Cavium, Inc - */ -#ifndef __ASM_MACH_PARAVIRT_KERNEL_ENTRY_H -#define __ASM_MACH_PARAVIRT_KERNEL_ENTRY_H - -#define CP0_EBASE $15, 1 - - .macro kernel_entry_setup -#ifdef CONFIG_SMP - mfc0 t0, CP0_EBASE - andi t0, t0, 0x3ff # CPUNum - beqz t0, 1f - # CPUs other than zero goto smp_bootstrap - j smp_bootstrap -#endif /* CONFIG_SMP */ - -1: - .endm - -/* - * Do SMP slave processor setup necessary before we can safely execute - * C code. - */ - .macro smp_slave_setup - mfc0 t0, CP0_EBASE - andi t0, t0, 0x3ff # CPUNum - slti t1, t0, NR_CPUS - bnez t1, 1f -2: - di - wait - b 2b # Unknown CPU, loop forever. -1: - PTR_LA t1, paravirt_smp_sp - PTR_SLL t0, PTR_SCALESHIFT - PTR_ADDU t1, t1, t0 -3: - PTR_L sp, 0(t1) - beqz sp, 3b # Spin until told to proceed. - - PTR_LA t1, paravirt_smp_gp - PTR_ADDU t1, t1, t0 - sync - PTR_L gp, 0(t1) - .endm - -#endif /* __ASM_MACH_PARAVIRT_KERNEL_ENTRY_H */ From 625326ea9c84872c71f90b97a9def3c01db9100f Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Sat, 22 Aug 2020 10:04:27 +0200 Subject: [PATCH 012/645] MIPS: Remove PNX833x alias NXP_STB22x Remove another unused MIPS platform. Signed-off-by: Thomas Bogendoerfer --- arch/mips/Kbuild.platforms | 1 - arch/mips/Kconfig | 30 -- arch/mips/configs/pnx8335_stb225_defconfig | 77 ----- arch/mips/include/asm/mach-pnx833x/gpio.h | 159 --------- .../include/asm/mach-pnx833x/irq-mapping.h | 112 ------- arch/mips/include/asm/mach-pnx833x/irq.h | 40 --- arch/mips/include/asm/mach-pnx833x/pnx833x.h | 189 ----------- arch/mips/include/asm/mipsregs.h | 12 - arch/mips/pnx833x/Makefile | 4 - arch/mips/pnx833x/Platform | 4 - arch/mips/pnx833x/common/Makefile | 2 - arch/mips/pnx833x/common/interrupts.c | 303 ------------------ arch/mips/pnx833x/common/platform.c | 224 ------------- arch/mips/pnx833x/common/prom.c | 51 --- arch/mips/pnx833x/common/reset.c | 31 -- arch/mips/pnx833x/common/setup.c | 48 --- arch/mips/pnx833x/stb22x/Makefile | 2 - arch/mips/pnx833x/stb22x/board.c | 120 ------- 18 files changed, 1409 deletions(-) delete mode 100644 arch/mips/configs/pnx8335_stb225_defconfig delete mode 100644 arch/mips/include/asm/mach-pnx833x/gpio.h delete mode 100644 arch/mips/include/asm/mach-pnx833x/irq-mapping.h delete mode 100644 arch/mips/include/asm/mach-pnx833x/irq.h delete mode 100644 arch/mips/include/asm/mach-pnx833x/pnx833x.h delete mode 100644 arch/mips/pnx833x/Makefile delete mode 100644 arch/mips/pnx833x/Platform delete mode 100644 arch/mips/pnx833x/common/Makefile delete mode 100644 arch/mips/pnx833x/common/interrupts.c delete mode 100644 arch/mips/pnx833x/common/platform.c delete mode 100644 arch/mips/pnx833x/common/prom.c delete mode 100644 arch/mips/pnx833x/common/reset.c delete mode 100644 arch/mips/pnx833x/common/setup.c delete mode 100644 arch/mips/pnx833x/stb22x/Makefile delete mode 100644 arch/mips/pnx833x/stb22x/board.c diff --git a/arch/mips/Kbuild.platforms b/arch/mips/Kbuild.platforms index a13c4cf6e608..af336a274a7a 100644 --- a/arch/mips/Kbuild.platforms +++ b/arch/mips/Kbuild.platforms @@ -22,7 +22,6 @@ platform-$(CONFIG_MIPS_MALTA) += mti-malta/ platform-$(CONFIG_NLM_COMMON) += netlogic/ platform-$(CONFIG_PIC32MZDA) += pic32/ platform-$(CONFIG_MACH_PISTACHIO) += pistachio/ -platform-$(CONFIG_SOC_PNX833X) += pnx833x/ platform-$(CONFIG_RALINK) += ralink/ platform-$(CONFIG_MIKROTIK_RB532) += rb532/ platform-$(CONFIG_SGI_IP22) += sgi-ip22/ diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index c95fa3a2484c..99220e7e465e 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -589,19 +589,6 @@ config MACH_VR41XX select SYS_SUPPORTS_MIPS16 select GPIOLIB -config NXP_STB220 - bool "NXP STB220 board" - select SOC_PNX833X - help - Support for NXP Semiconductors STB220 Development Board. - -config NXP_STB225 - bool "NXP 225 board" - select SOC_PNX833X - select SOC_PNX8335 - help - Support for NXP Semiconductors STB225 Development Board. - config RALINK bool "Ralink based machines" select CEVT_R4K @@ -1266,23 +1253,6 @@ config PCI_XTALK_BRIDGE config NO_EXCEPT_FILL bool -config SOC_PNX833X - bool - select CEVT_R4K - select CSRC_R4K - select IRQ_MIPS_CPU - select DMA_NONCOHERENT - select SYS_HAS_CPU_MIPS32_R2 - select SYS_SUPPORTS_32BIT_KERNEL - select SYS_SUPPORTS_LITTLE_ENDIAN - select SYS_SUPPORTS_BIG_ENDIAN - select SYS_SUPPORTS_MIPS16 - select CPU_MIPSR2_IRQ_VI - -config SOC_PNX8335 - bool - select SOC_PNX833X - config MIPS_SPRAM bool diff --git a/arch/mips/configs/pnx8335_stb225_defconfig b/arch/mips/configs/pnx8335_stb225_defconfig deleted file mode 100644 index d06db6b87959..000000000000 --- a/arch/mips/configs/pnx8335_stb225_defconfig +++ /dev/null @@ -1,77 +0,0 @@ -# CONFIG_LOCALVERSION_AUTO is not set -# CONFIG_SWAP is not set -CONFIG_SYSVIPC=y -CONFIG_NO_HZ=y -CONFIG_HIGH_RES_TIMERS=y -CONFIG_PREEMPT_VOLUNTARY=y -CONFIG_LOG_BUF_SHIFT=14 -CONFIG_EXPERT=y -CONFIG_SLAB=y -CONFIG_NXP_STB225=y -CONFIG_CPU_LITTLE_ENDIAN=y -CONFIG_HZ_128=y -# CONFIG_SECCOMP is not set -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -# CONFIG_BLK_DEV_BSG is not set -CONFIG_NET=y -CONFIG_PACKET=y -CONFIG_UNIX=y -CONFIG_INET=y -CONFIG_IP_MULTICAST=y -CONFIG_IP_PNP=y -CONFIG_IP_PNP_DHCP=y -CONFIG_INET_AH=y -# CONFIG_IPV6 is not set -CONFIG_MTD=y -CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_BLOCK=y -CONFIG_MTD_CFI=y -CONFIG_MTD_CFI_ADV_OPTIONS=y -CONFIG_MTD_CFI_LE_BYTE_SWAP=y -CONFIG_MTD_CFI_GEOMETRY=y -CONFIG_MTD_CFI_AMDSTD=y -CONFIG_MTD_PHYSMAP=y -CONFIG_BLK_DEV_LOOP=y -CONFIG_BLK_DEV_SD=y -# CONFIG_SCSI_LOWLEVEL is not set -CONFIG_ATA=y -CONFIG_NETDEVICES=y -CONFIG_INPUT_EVDEV=m -CONFIG_INPUT_EVBUG=m -# CONFIG_INPUT_KEYBOARD is not set -# CONFIG_INPUT_MOUSE is not set -# CONFIG_VT_CONSOLE is not set -# CONFIG_LEGACY_PTYS is not set -CONFIG_SERIAL_PNX8XXX=y -CONFIG_SERIAL_PNX8XXX_CONSOLE=y -CONFIG_HW_RANDOM=y -CONFIG_I2C=y -CONFIG_I2C_CHARDEV=y -# CONFIG_HWMON is not set -CONFIG_FB=y -# CONFIG_VGA_CONSOLE is not set -CONFIG_SOUND=m -CONFIG_SND=m -CONFIG_SND_VERBOSE_PRINTK=y -CONFIG_SND_DEBUG=y -CONFIG_SND_SEQUENCER=m -CONFIG_EXT2_FS=m -# CONFIG_DNOTIFY is not set -CONFIG_MSDOS_FS=m -CONFIG_VFAT_FS=m -CONFIG_TMPFS=y -CONFIG_JFFS2_FS=y -CONFIG_CRAMFS=y -CONFIG_NFS_FS=y -CONFIG_ROOT_NFS=y -CONFIG_NFSD=m -CONFIG_NFSD_V3=y -CONFIG_NLS=y -CONFIG_NLS_CODEPAGE_437=m -CONFIG_NLS_CODEPAGE_850=m -CONFIG_NLS_CODEPAGE_932=m -CONFIG_NLS_ASCII=m -CONFIG_NLS_ISO8859_1=m -CONFIG_NLS_ISO8859_15=m -CONFIG_NLS_UTF8=m diff --git a/arch/mips/include/asm/mach-pnx833x/gpio.h b/arch/mips/include/asm/mach-pnx833x/gpio.h deleted file mode 100644 index 85b5b8e26118..000000000000 --- a/arch/mips/include/asm/mach-pnx833x/gpio.h +++ /dev/null @@ -1,159 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * gpio.h: GPIO Support for PNX833X. - * - * Copyright 2008 NXP Semiconductors - * Chris Steel - * Daniel Laird - */ -#ifndef __ASM_MIPS_MACH_PNX833X_GPIO_H -#define __ASM_MIPS_MACH_PNX833X_GPIO_H - -/* BIG FAT WARNING: races danger! - No protections exist here. Current users are only early init code, - when locking is not needed because no concurrency yet exists there, - and GPIO IRQ dispatcher, which does locking. - However, if many uses will ever happen, proper locking will be needed - - including locking between different uses -*/ - -#include - -#define SET_REG_BIT(reg, bit) do { (reg |= (1 << (bit))); } while (0) -#define CLEAR_REG_BIT(reg, bit) do { (reg &= ~(1 << (bit))); } while (0) - -/* Initialize GPIO to a known state */ -static inline void pnx833x_gpio_init(void) -{ - PNX833X_PIO_DIR = 0; - PNX833X_PIO_DIR2 = 0; - PNX833X_PIO_SEL = 0; - PNX833X_PIO_SEL2 = 0; - PNX833X_PIO_INT_EDGE = 0; - PNX833X_PIO_INT_HI = 0; - PNX833X_PIO_INT_LO = 0; - - /* clear any GPIO interrupt requests */ - PNX833X_PIO_INT_CLEAR = 0xffff; - PNX833X_PIO_INT_CLEAR = 0; - PNX833X_PIO_INT_ENABLE = 0; -} - -/* Select GPIO direction for a pin */ -static inline void pnx833x_gpio_select_input(unsigned int pin) -{ - if (pin < 32) - CLEAR_REG_BIT(PNX833X_PIO_DIR, pin); - else - CLEAR_REG_BIT(PNX833X_PIO_DIR2, pin & 31); -} -static inline void pnx833x_gpio_select_output(unsigned int pin) -{ - if (pin < 32) - SET_REG_BIT(PNX833X_PIO_DIR, pin); - else - SET_REG_BIT(PNX833X_PIO_DIR2, pin & 31); -} - -/* Select GPIO or alternate function for a pin */ -static inline void pnx833x_gpio_select_function_io(unsigned int pin) -{ - if (pin < 32) - CLEAR_REG_BIT(PNX833X_PIO_SEL, pin); - else - CLEAR_REG_BIT(PNX833X_PIO_SEL2, pin & 31); -} -static inline void pnx833x_gpio_select_function_alt(unsigned int pin) -{ - if (pin < 32) - SET_REG_BIT(PNX833X_PIO_SEL, pin); - else - SET_REG_BIT(PNX833X_PIO_SEL2, pin & 31); -} - -/* Read GPIO pin */ -static inline int pnx833x_gpio_read(unsigned int pin) -{ - if (pin < 32) - return (PNX833X_PIO_IN >> pin) & 1; - else - return (PNX833X_PIO_IN2 >> (pin & 31)) & 1; -} - -/* Write GPIO pin */ -static inline void pnx833x_gpio_write(unsigned int val, unsigned int pin) -{ - if (pin < 32) { - if (val) - SET_REG_BIT(PNX833X_PIO_OUT, pin); - else - CLEAR_REG_BIT(PNX833X_PIO_OUT, pin); - } else { - if (val) - SET_REG_BIT(PNX833X_PIO_OUT2, pin & 31); - else - CLEAR_REG_BIT(PNX833X_PIO_OUT2, pin & 31); - } -} - -/* Configure GPIO interrupt */ -#define GPIO_INT_NONE 0 -#define GPIO_INT_LEVEL_LOW 1 -#define GPIO_INT_LEVEL_HIGH 2 -#define GPIO_INT_EDGE_RISING 3 -#define GPIO_INT_EDGE_FALLING 4 -#define GPIO_INT_EDGE_BOTH 5 -static inline void pnx833x_gpio_setup_irq(int when, unsigned int pin) -{ - switch (when) { - case GPIO_INT_LEVEL_LOW: - CLEAR_REG_BIT(PNX833X_PIO_INT_EDGE, pin); - CLEAR_REG_BIT(PNX833X_PIO_INT_HI, pin); - SET_REG_BIT(PNX833X_PIO_INT_LO, pin); - break; - case GPIO_INT_LEVEL_HIGH: - CLEAR_REG_BIT(PNX833X_PIO_INT_EDGE, pin); - SET_REG_BIT(PNX833X_PIO_INT_HI, pin); - CLEAR_REG_BIT(PNX833X_PIO_INT_LO, pin); - break; - case GPIO_INT_EDGE_RISING: - SET_REG_BIT(PNX833X_PIO_INT_EDGE, pin); - SET_REG_BIT(PNX833X_PIO_INT_HI, pin); - CLEAR_REG_BIT(PNX833X_PIO_INT_LO, pin); - break; - case GPIO_INT_EDGE_FALLING: - SET_REG_BIT(PNX833X_PIO_INT_EDGE, pin); - CLEAR_REG_BIT(PNX833X_PIO_INT_HI, pin); - SET_REG_BIT(PNX833X_PIO_INT_LO, pin); - break; - case GPIO_INT_EDGE_BOTH: - SET_REG_BIT(PNX833X_PIO_INT_EDGE, pin); - SET_REG_BIT(PNX833X_PIO_INT_HI, pin); - SET_REG_BIT(PNX833X_PIO_INT_LO, pin); - break; - default: - CLEAR_REG_BIT(PNX833X_PIO_INT_EDGE, pin); - CLEAR_REG_BIT(PNX833X_PIO_INT_HI, pin); - CLEAR_REG_BIT(PNX833X_PIO_INT_LO, pin); - break; - } -} - -/* Enable/disable GPIO interrupt */ -static inline void pnx833x_gpio_enable_irq(unsigned int pin) -{ - SET_REG_BIT(PNX833X_PIO_INT_ENABLE, pin); -} -static inline void pnx833x_gpio_disable_irq(unsigned int pin) -{ - CLEAR_REG_BIT(PNX833X_PIO_INT_ENABLE, pin); -} - -/* Clear GPIO interrupt request */ -static inline void pnx833x_gpio_clear_irq(unsigned int pin) -{ - SET_REG_BIT(PNX833X_PIO_INT_CLEAR, pin); - CLEAR_REG_BIT(PNX833X_PIO_INT_CLEAR, pin); -} - -#endif diff --git a/arch/mips/include/asm/mach-pnx833x/irq-mapping.h b/arch/mips/include/asm/mach-pnx833x/irq-mapping.h deleted file mode 100644 index 32d8063c1bbc..000000000000 --- a/arch/mips/include/asm/mach-pnx833x/irq-mapping.h +++ /dev/null @@ -1,112 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ - -/* - * irq.h: IRQ mappings for PNX833X. - * - * Copyright 2008 NXP Semiconductors - * Chris Steel - * Daniel Laird - */ - -#ifndef __ASM_MIPS_MACH_PNX833X_IRQ_MAPPING_H -#define __ASM_MIPS_MACH_PNX833X_IRQ_MAPPING_H -/* - * The "IRQ numbers" are completely virtual. - * - * In PNX8330/1, we have 48 interrupt lines, numbered from 1 to 48. - * Let's use numbers 1..48 for PIC interrupts, number 0 for timer interrupt, - * numbers 49..64 for (virtual) GPIO interrupts. - * - * In PNX8335, we have 57 interrupt lines, numbered from 1 to 57, - * connected to PIC, which uses core hardware interrupt 2, and also - * a timer interrupt through hardware interrupt 5. - * Let's use numbers 1..64 for PIC interrupts, number 0 for timer interrupt, - * numbers 65..80 for (virtual) GPIO interrupts. - * - */ -#include - -#define PNX833X_TIMER_IRQ (MIPS_CPU_IRQ_BASE + 7) - -/* Interrupts supported by PIC */ -#define PNX833X_PIC_I2C0_INT (PNX833X_PIC_IRQ_BASE + 1) -#define PNX833X_PIC_I2C1_INT (PNX833X_PIC_IRQ_BASE + 2) -#define PNX833X_PIC_UART0_INT (PNX833X_PIC_IRQ_BASE + 3) -#define PNX833X_PIC_UART1_INT (PNX833X_PIC_IRQ_BASE + 4) -#define PNX833X_PIC_TS_IN0_DV_INT (PNX833X_PIC_IRQ_BASE + 5) -#define PNX833X_PIC_TS_IN0_DMA_INT (PNX833X_PIC_IRQ_BASE + 6) -#define PNX833X_PIC_GPIO_INT (PNX833X_PIC_IRQ_BASE + 7) -#define PNX833X_PIC_AUDIO_DEC_INT (PNX833X_PIC_IRQ_BASE + 8) -#define PNX833X_PIC_VIDEO_DEC_INT (PNX833X_PIC_IRQ_BASE + 9) -#define PNX833X_PIC_CONFIG_INT (PNX833X_PIC_IRQ_BASE + 10) -#define PNX833X_PIC_AOI_INT (PNX833X_PIC_IRQ_BASE + 11) -#define PNX833X_PIC_SYNC_INT (PNX833X_PIC_IRQ_BASE + 12) -#define PNX8330_PIC_SPU_INT (PNX833X_PIC_IRQ_BASE + 13) -#define PNX8335_PIC_SATA_INT (PNX833X_PIC_IRQ_BASE + 13) -#define PNX833X_PIC_OSD_INT (PNX833X_PIC_IRQ_BASE + 14) -#define PNX833X_PIC_DISP1_INT (PNX833X_PIC_IRQ_BASE + 15) -#define PNX833X_PIC_DEINTERLACER_INT (PNX833X_PIC_IRQ_BASE + 16) -#define PNX833X_PIC_DISPLAY2_INT (PNX833X_PIC_IRQ_BASE + 17) -#define PNX833X_PIC_VC_INT (PNX833X_PIC_IRQ_BASE + 18) -#define PNX833X_PIC_SC_INT (PNX833X_PIC_IRQ_BASE + 19) -#define PNX833X_PIC_IDE_INT (PNX833X_PIC_IRQ_BASE + 20) -#define PNX833X_PIC_IDE_DMA_INT (PNX833X_PIC_IRQ_BASE + 21) -#define PNX833X_PIC_TS_IN1_DV_INT (PNX833X_PIC_IRQ_BASE + 22) -#define PNX833X_PIC_TS_IN1_DMA_INT (PNX833X_PIC_IRQ_BASE + 23) -#define PNX833X_PIC_SGDX_DMA_INT (PNX833X_PIC_IRQ_BASE + 24) -#define PNX833X_PIC_TS_OUT_INT (PNX833X_PIC_IRQ_BASE + 25) -#define PNX833X_PIC_IR_INT (PNX833X_PIC_IRQ_BASE + 26) -#define PNX833X_PIC_VMSP1_INT (PNX833X_PIC_IRQ_BASE + 27) -#define PNX833X_PIC_VMSP2_INT (PNX833X_PIC_IRQ_BASE + 28) -#define PNX833X_PIC_PIBC_INT (PNX833X_PIC_IRQ_BASE + 29) -#define PNX833X_PIC_TS_IN0_TRD_INT (PNX833X_PIC_IRQ_BASE + 30) -#define PNX833X_PIC_SGDX_TPD_INT (PNX833X_PIC_IRQ_BASE + 31) -#define PNX833X_PIC_USB_INT (PNX833X_PIC_IRQ_BASE + 32) -#define PNX833X_PIC_TS_IN1_TRD_INT (PNX833X_PIC_IRQ_BASE + 33) -#define PNX833X_PIC_CLOCK_INT (PNX833X_PIC_IRQ_BASE + 34) -#define PNX833X_PIC_SGDX_PARSER_INT (PNX833X_PIC_IRQ_BASE + 35) -#define PNX833X_PIC_VMSP_DMA_INT (PNX833X_PIC_IRQ_BASE + 36) - -#if defined(CONFIG_SOC_PNX8335) -#define PNX8335_PIC_MIU_INT (PNX833X_PIC_IRQ_BASE + 37) -#define PNX8335_PIC_AVCHIP_IRQ_INT (PNX833X_PIC_IRQ_BASE + 38) -#define PNX8335_PIC_SYNC_HD_INT (PNX833X_PIC_IRQ_BASE + 39) -#define PNX8335_PIC_DISP_HD_INT (PNX833X_PIC_IRQ_BASE + 40) -#define PNX8335_PIC_DISP_SCALER_INT (PNX833X_PIC_IRQ_BASE + 41) -#define PNX8335_PIC_OSD_HD1_INT (PNX833X_PIC_IRQ_BASE + 42) -#define PNX8335_PIC_DTL_WRITER_Y_INT (PNX833X_PIC_IRQ_BASE + 43) -#define PNX8335_PIC_DTL_WRITER_C_INT (PNX833X_PIC_IRQ_BASE + 44) -#define PNX8335_PIC_DTL_EMULATOR_Y_IR_INT (PNX833X_PIC_IRQ_BASE + 45) -#define PNX8335_PIC_DTL_EMULATOR_C_IR_INT (PNX833X_PIC_IRQ_BASE + 46) -#define PNX8335_PIC_DENC_TTX_INT (PNX833X_PIC_IRQ_BASE + 47) -#define PNX8335_PIC_MMI_SIF0_INT (PNX833X_PIC_IRQ_BASE + 48) -#define PNX8335_PIC_MMI_SIF1_INT (PNX833X_PIC_IRQ_BASE + 49) -#define PNX8335_PIC_MMI_CDMMU_INT (PNX833X_PIC_IRQ_BASE + 50) -#define PNX8335_PIC_PIBCS_INT (PNX833X_PIC_IRQ_BASE + 51) -#define PNX8335_PIC_ETHERNET_INT (PNX833X_PIC_IRQ_BASE + 52) -#define PNX8335_PIC_VMSP1_0_INT (PNX833X_PIC_IRQ_BASE + 53) -#define PNX8335_PIC_VMSP1_1_INT (PNX833X_PIC_IRQ_BASE + 54) -#define PNX8335_PIC_VMSP1_DMA_INT (PNX833X_PIC_IRQ_BASE + 55) -#define PNX8335_PIC_TDGR_DE_INT (PNX833X_PIC_IRQ_BASE + 56) -#define PNX8335_PIC_IR1_IRQ_INT (PNX833X_PIC_IRQ_BASE + 57) -#endif - -/* GPIO interrupts */ -#define PNX833X_GPIO_0_INT (PNX833X_GPIO_IRQ_BASE + 0) -#define PNX833X_GPIO_1_INT (PNX833X_GPIO_IRQ_BASE + 1) -#define PNX833X_GPIO_2_INT (PNX833X_GPIO_IRQ_BASE + 2) -#define PNX833X_GPIO_3_INT (PNX833X_GPIO_IRQ_BASE + 3) -#define PNX833X_GPIO_4_INT (PNX833X_GPIO_IRQ_BASE + 4) -#define PNX833X_GPIO_5_INT (PNX833X_GPIO_IRQ_BASE + 5) -#define PNX833X_GPIO_6_INT (PNX833X_GPIO_IRQ_BASE + 6) -#define PNX833X_GPIO_7_INT (PNX833X_GPIO_IRQ_BASE + 7) -#define PNX833X_GPIO_8_INT (PNX833X_GPIO_IRQ_BASE + 8) -#define PNX833X_GPIO_9_INT (PNX833X_GPIO_IRQ_BASE + 9) -#define PNX833X_GPIO_10_INT (PNX833X_GPIO_IRQ_BASE + 10) -#define PNX833X_GPIO_11_INT (PNX833X_GPIO_IRQ_BASE + 11) -#define PNX833X_GPIO_12_INT (PNX833X_GPIO_IRQ_BASE + 12) -#define PNX833X_GPIO_13_INT (PNX833X_GPIO_IRQ_BASE + 13) -#define PNX833X_GPIO_14_INT (PNX833X_GPIO_IRQ_BASE + 14) -#define PNX833X_GPIO_15_INT (PNX833X_GPIO_IRQ_BASE + 15) - -#endif diff --git a/arch/mips/include/asm/mach-pnx833x/irq.h b/arch/mips/include/asm/mach-pnx833x/irq.h deleted file mode 100644 index b7a6dab5b9f7..000000000000 --- a/arch/mips/include/asm/mach-pnx833x/irq.h +++ /dev/null @@ -1,40 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * irq.h: IRQ mappings for PNX833X. - * - * Copyright 2008 NXP Semiconductors - * Chris Steel - * Daniel Laird - */ - -#ifndef __ASM_MIPS_MACH_PNX833X_IRQ_H -#define __ASM_MIPS_MACH_PNX833X_IRQ_H -/* - * The "IRQ numbers" are completely virtual. - * - * In PNX8330/1, we have 48 interrupt lines, numbered from 1 to 48. - * Let's use numbers 1..48 for PIC interrupts, number 0 for timer interrupt, - * numbers 49..64 for (virtual) GPIO interrupts. - * - * In PNX8335, we have 57 interrupt lines, numbered from 1 to 57, - * connected to PIC, which uses core hardware interrupt 2, and also - * a timer interrupt through hardware interrupt 5. - * Let's use numbers 1..64 for PIC interrupts, number 0 for timer interrupt, - * numbers 65..80 for (virtual) GPIO interrupts. - * - */ -#if defined(CONFIG_SOC_PNX8335) - #define PNX833X_PIC_NUM_IRQ 58 -#else - #define PNX833X_PIC_NUM_IRQ 37 -#endif - -#define MIPS_CPU_NUM_IRQ 8 -#define PNX833X_GPIO_NUM_IRQ 16 - -#define MIPS_CPU_IRQ_BASE 0 -#define PNX833X_PIC_IRQ_BASE (MIPS_CPU_IRQ_BASE + MIPS_CPU_NUM_IRQ) -#define PNX833X_GPIO_IRQ_BASE (PNX833X_PIC_IRQ_BASE + PNX833X_PIC_NUM_IRQ) -#define NR_IRQS (MIPS_CPU_NUM_IRQ + PNX833X_PIC_NUM_IRQ + PNX833X_GPIO_NUM_IRQ) - -#endif diff --git a/arch/mips/include/asm/mach-pnx833x/pnx833x.h b/arch/mips/include/asm/mach-pnx833x/pnx833x.h deleted file mode 100644 index 00bb67a36386..000000000000 --- a/arch/mips/include/asm/mach-pnx833x/pnx833x.h +++ /dev/null @@ -1,189 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * pnx833x.h: Register mappings for PNX833X. - * - * Copyright 2008 NXP Semiconductors - * Chris Steel - * Daniel Laird - */ -#ifndef __ASM_MIPS_MACH_PNX833X_PNX833X_H -#define __ASM_MIPS_MACH_PNX833X_PNX833X_H - -/* All regs are accessed in KSEG1 */ -#define PNX833X_BASE (0xa0000000ul + 0x17E00000ul) - -#define PNX833X_REG(offs) (*((volatile unsigned long *)(PNX833X_BASE + offs))) - -/* Registers are named exactly as in PNX833X docs, just with PNX833X_ prefix */ - -/* Read access to multibit fields */ -#define PNX833X_BIT(val, reg, field) ((val) & PNX833X_##reg##_##field) -#define PNX833X_REGBIT(reg, field) PNX833X_BIT(PNX833X_##reg, reg, field) - -/* Use PNX833X_FIELD to extract a field from val */ -#define PNX_FIELD(cpu, val, reg, field) \ - (((val) & PNX##cpu##_##reg##_##field##_MASK) >> \ - PNX##cpu##_##reg##_##field##_SHIFT) -#define PNX833X_FIELD(val, reg, field) PNX_FIELD(833X, val, reg, field) -#define PNX8330_FIELD(val, reg, field) PNX_FIELD(8330, val, reg, field) -#define PNX8335_FIELD(val, reg, field) PNX_FIELD(8335, val, reg, field) - -/* Use PNX833X_REGFIELD to extract a field from a register */ -#define PNX833X_REGFIELD(reg, field) PNX833X_FIELD(PNX833X_##reg, reg, field) -#define PNX8330_REGFIELD(reg, field) PNX8330_FIELD(PNX8330_##reg, reg, field) -#define PNX8335_REGFIELD(reg, field) PNX8335_FIELD(PNX8335_##reg, reg, field) - - -#define PNX_WRITEFIELD(cpu, val, reg, field) \ - (PNX##cpu##_##reg = (PNX##cpu##_##reg & ~(PNX##cpu##_##reg##_##field##_MASK)) | \ - ((val) << PNX##cpu##_##reg##_##field##_SHIFT)) -#define PNX833X_WRITEFIELD(val, reg, field) \ - PNX_WRITEFIELD(833X, val, reg, field) -#define PNX8330_WRITEFIELD(val, reg, field) \ - PNX_WRITEFIELD(8330, val, reg, field) -#define PNX8335_WRITEFIELD(val, reg, field) \ - PNX_WRITEFIELD(8335, val, reg, field) - - -/* Macros to detect CPU type */ - -#define PNX833X_CONFIG_MODULE_ID PNX833X_REG(0x7FFC) -#define PNX833X_CONFIG_MODULE_ID_MAJREV_MASK 0x0000f000 -#define PNX833X_CONFIG_MODULE_ID_MAJREV_SHIFT 12 -#define PNX8330_CONFIG_MODULE_MAJREV 4 -#define PNX8335_CONFIG_MODULE_MAJREV 5 -#define CPU_IS_PNX8330 (PNX833X_REGFIELD(CONFIG_MODULE_ID, MAJREV) == \ - PNX8330_CONFIG_MODULE_MAJREV) -#define CPU_IS_PNX8335 (PNX833X_REGFIELD(CONFIG_MODULE_ID, MAJREV) == \ - PNX8335_CONFIG_MODULE_MAJREV) - - - -#define PNX833X_RESET_CONTROL PNX833X_REG(0x8004) -#define PNX833X_RESET_CONTROL_2 PNX833X_REG(0x8014) - -#define PNX833X_PIC_REG(offs) PNX833X_REG(0x01000 + (offs)) -#define PNX833X_PIC_INT_PRIORITY PNX833X_PIC_REG(0x0) -#define PNX833X_PIC_INT_SRC PNX833X_PIC_REG(0x4) -#define PNX833X_PIC_INT_SRC_INT_SRC_MASK 0x00000FF8ul /* bits 11:3 */ -#define PNX833X_PIC_INT_SRC_INT_SRC_SHIFT 3 -#define PNX833X_PIC_INT_REG(irq) PNX833X_PIC_REG(0x10 + 4*(irq)) - -#define PNX833X_CLOCK_CPUCP_CTL PNX833X_REG(0x9228) -#define PNX833X_CLOCK_CPUCP_CTL_EXIT_RESET 0x00000002ul /* bit 1 */ -#define PNX833X_CLOCK_CPUCP_CTL_DIV_CLOCK_MASK 0x00000018ul /* bits 4:3 */ -#define PNX833X_CLOCK_CPUCP_CTL_DIV_CLOCK_SHIFT 3 - -#define PNX8335_CLOCK_PLL_CPU_CTL PNX833X_REG(0x9020) -#define PNX8335_CLOCK_PLL_CPU_CTL_FREQ_MASK 0x1f -#define PNX8335_CLOCK_PLL_CPU_CTL_FREQ_SHIFT 0 - -#define PNX833X_CONFIG_MUX PNX833X_REG(0x7004) -#define PNX833X_CONFIG_MUX_IDE_MUX 0x00000080 /* bit 7 */ - -#define PNX8330_CONFIG_POLYFUSE_7 PNX833X_REG(0x7040) -#define PNX8330_CONFIG_POLYFUSE_7_BOOT_MODE_MASK 0x00180000 -#define PNX8330_CONFIG_POLYFUSE_7_BOOT_MODE_SHIFT 19 - -#define PNX833X_PIO_IN PNX833X_REG(0xF000) -#define PNX833X_PIO_OUT PNX833X_REG(0xF004) -#define PNX833X_PIO_DIR PNX833X_REG(0xF008) -#define PNX833X_PIO_SEL PNX833X_REG(0xF014) -#define PNX833X_PIO_INT_EDGE PNX833X_REG(0xF020) -#define PNX833X_PIO_INT_HI PNX833X_REG(0xF024) -#define PNX833X_PIO_INT_LO PNX833X_REG(0xF028) -#define PNX833X_PIO_INT_STATUS PNX833X_REG(0xFFE0) -#define PNX833X_PIO_INT_ENABLE PNX833X_REG(0xFFE4) -#define PNX833X_PIO_INT_CLEAR PNX833X_REG(0xFFE8) -#define PNX833X_PIO_IN2 PNX833X_REG(0xF05C) -#define PNX833X_PIO_OUT2 PNX833X_REG(0xF060) -#define PNX833X_PIO_DIR2 PNX833X_REG(0xF064) -#define PNX833X_PIO_SEL2 PNX833X_REG(0xF068) - -#define PNX833X_UART0_PORTS_START (PNX833X_BASE + 0xB000) -#define PNX833X_UART0_PORTS_END (PNX833X_BASE + 0xBFFF) -#define PNX833X_UART1_PORTS_START (PNX833X_BASE + 0xC000) -#define PNX833X_UART1_PORTS_END (PNX833X_BASE + 0xCFFF) - -#define PNX833X_USB_PORTS_START (PNX833X_BASE + 0x19000) -#define PNX833X_USB_PORTS_END (PNX833X_BASE + 0x19FFF) - -#define PNX833X_CONFIG_USB PNX833X_REG(0x7008) - -#define PNX833X_I2C0_PORTS_START (PNX833X_BASE + 0xD000) -#define PNX833X_I2C0_PORTS_END (PNX833X_BASE + 0xDFFF) -#define PNX833X_I2C1_PORTS_START (PNX833X_BASE + 0xE000) -#define PNX833X_I2C1_PORTS_END (PNX833X_BASE + 0xEFFF) - -#define PNX833X_IDE_PORTS_START (PNX833X_BASE + 0x1A000) -#define PNX833X_IDE_PORTS_END (PNX833X_BASE + 0x1AFFF) -#define PNX833X_IDE_MODULE_ID PNX833X_REG(0x1AFFC) - -#define PNX833X_IDE_MODULE_ID_MODULE_ID_MASK 0xFFFF0000 -#define PNX833X_IDE_MODULE_ID_MODULE_ID_SHIFT 16 -#define PNX833X_IDE_MODULE_ID_VALUE 0xA009 - - -#define PNX833X_MIU_SEL0 PNX833X_REG(0x2004) -#define PNX833X_MIU_SEL0_TIMING PNX833X_REG(0x2008) -#define PNX833X_MIU_SEL1 PNX833X_REG(0x200C) -#define PNX833X_MIU_SEL1_TIMING PNX833X_REG(0x2010) -#define PNX833X_MIU_SEL2 PNX833X_REG(0x2014) -#define PNX833X_MIU_SEL2_TIMING PNX833X_REG(0x2018) -#define PNX833X_MIU_SEL3 PNX833X_REG(0x201C) -#define PNX833X_MIU_SEL3_TIMING PNX833X_REG(0x2020) - -#define PNX833X_MIU_SEL0_SPI_MODE_ENABLE_MASK (1 << 14) -#define PNX833X_MIU_SEL0_SPI_MODE_ENABLE_SHIFT 14 - -#define PNX833X_MIU_SEL0_BURST_MODE_ENABLE_MASK (1 << 7) -#define PNX833X_MIU_SEL0_BURST_MODE_ENABLE_SHIFT 7 - -#define PNX833X_MIU_SEL0_BURST_PAGE_LEN_MASK (0xF << 9) -#define PNX833X_MIU_SEL0_BURST_PAGE_LEN_SHIFT 9 - -#define PNX833X_MIU_CONFIG_SPI PNX833X_REG(0x2000) - -#define PNX833X_MIU_CONFIG_SPI_OPCODE_MASK (0xFF << 3) -#define PNX833X_MIU_CONFIG_SPI_OPCODE_SHIFT 3 - -#define PNX833X_MIU_CONFIG_SPI_DATA_ENABLE_MASK (1 << 2) -#define PNX833X_MIU_CONFIG_SPI_DATA_ENABLE_SHIFT 2 - -#define PNX833X_MIU_CONFIG_SPI_ADDR_ENABLE_MASK (1 << 1) -#define PNX833X_MIU_CONFIG_SPI_ADDR_ENABLE_SHIFT 1 - -#define PNX833X_MIU_CONFIG_SPI_SYNC_MASK (1 << 0) -#define PNX833X_MIU_CONFIG_SPI_SYNC_SHIFT 0 - -#define PNX833X_WRITE_CONFIG_SPI(opcode, data_enable, addr_enable, sync) \ - (PNX833X_MIU_CONFIG_SPI = \ - ((opcode) << PNX833X_MIU_CONFIG_SPI_OPCODE_SHIFT) | \ - ((data_enable) << PNX833X_MIU_CONFIG_SPI_DATA_ENABLE_SHIFT) | \ - ((addr_enable) << PNX833X_MIU_CONFIG_SPI_ADDR_ENABLE_SHIFT) | \ - ((sync) << PNX833X_MIU_CONFIG_SPI_SYNC_SHIFT)) - -#define PNX8335_IP3902_PORTS_START (PNX833X_BASE + 0x2F000) -#define PNX8335_IP3902_PORTS_END (PNX833X_BASE + 0x2FFFF) -#define PNX8335_IP3902_MODULE_ID PNX833X_REG(0x2FFFC) - -#define PNX8335_IP3902_MODULE_ID_MODULE_ID_MASK 0xFFFF0000 -#define PNX8335_IP3902_MODULE_ID_MODULE_ID_SHIFT 16 -#define PNX8335_IP3902_MODULE_ID_VALUE 0x3902 - - /* I/O location(gets remapped)*/ -#define PNX8335_NAND_BASE 0x18000000 -/* I/O location with CLE high */ -#define PNX8335_NAND_CLE_MASK 0x00100000 -/* I/O location with ALE high */ -#define PNX8335_NAND_ALE_MASK 0x00010000 - -#define PNX8335_SATA_PORTS_START (PNX833X_BASE + 0x2E000) -#define PNX8335_SATA_PORTS_END (PNX833X_BASE + 0x2EFFF) -#define PNX8335_SATA_MODULE_ID PNX833X_REG(0x2EFFC) - -#define PNX8335_SATA_MODULE_ID_MODULE_ID_MASK 0xFFFF0000 -#define PNX8335_SATA_MODULE_ID_MODULE_ID_SHIFT 16 -#define PNX8335_SATA_MODULE_ID_VALUE 0xA099 - -#endif diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h index 4ddc12e4444a..1a03fdc2c74a 100644 --- a/arch/mips/include/asm/mipsregs.h +++ b/arch/mips/include/asm/mipsregs.h @@ -1706,12 +1706,6 @@ do { \ #define read_c0_count() __read_32bit_c0_register($9, 0) #define write_c0_count(val) __write_32bit_c0_register($9, 0, val) -#define read_c0_count2() __read_32bit_c0_register($9, 6) /* pnx8550 */ -#define write_c0_count2(val) __write_32bit_c0_register($9, 6, val) - -#define read_c0_count3() __read_32bit_c0_register($9, 7) /* pnx8550 */ -#define write_c0_count3(val) __write_32bit_c0_register($9, 7, val) - #define read_c0_entryhi() __read_ulong_c0_register($10, 0) #define write_c0_entryhi(val) __write_ulong_c0_register($10, 0, val) @@ -1730,12 +1724,6 @@ do { \ #define read_c0_guestctl0ext() __read_32bit_c0_register($11, 4) #define write_c0_guestctl0ext(val) __write_32bit_c0_register($11, 4, val) -#define read_c0_compare2() __read_32bit_c0_register($11, 6) /* pnx8550 */ -#define write_c0_compare2(val) __write_32bit_c0_register($11, 6, val) - -#define read_c0_compare3() __read_32bit_c0_register($11, 7) /* pnx8550 */ -#define write_c0_compare3(val) __write_32bit_c0_register($11, 7, val) - #define read_c0_status() __read_32bit_c0_register($12, 0) #define write_c0_status(val) __write_32bit_c0_register($12, 0, val) diff --git a/arch/mips/pnx833x/Makefile b/arch/mips/pnx833x/Makefile deleted file mode 100644 index 927268a58237..000000000000 --- a/arch/mips/pnx833x/Makefile +++ /dev/null @@ -1,4 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -obj-$(CONFIG_SOC_PNX833X) += common/ -obj-$(CONFIG_NXP_STB220) += stb22x/ -obj-$(CONFIG_NXP_STB225) += stb22x/ diff --git a/arch/mips/pnx833x/Platform b/arch/mips/pnx833x/Platform deleted file mode 100644 index e5286a49fc3e..000000000000 --- a/arch/mips/pnx833x/Platform +++ /dev/null @@ -1,4 +0,0 @@ -# NXP STB225 -cflags-$(CONFIG_SOC_PNX833X) += -I$(srctree)/arch/mips/include/asm/mach-pnx833x -load-$(CONFIG_NXP_STB220) += 0xffffffff80001000 -load-$(CONFIG_NXP_STB225) += 0xffffffff80001000 diff --git a/arch/mips/pnx833x/common/Makefile b/arch/mips/pnx833x/common/Makefile deleted file mode 100644 index 9b4d394112b0..000000000000 --- a/arch/mips/pnx833x/common/Makefile +++ /dev/null @@ -1,2 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -obj-y := interrupts.o platform.o prom.o setup.o reset.o diff --git a/arch/mips/pnx833x/common/interrupts.c b/arch/mips/pnx833x/common/interrupts.c deleted file mode 100644 index 2fbbabcac386..000000000000 --- a/arch/mips/pnx833x/common/interrupts.c +++ /dev/null @@ -1,303 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * interrupts.c: Interrupt mappings for PNX833X. - * - * Copyright 2008 NXP Semiconductors - * Chris Steel - * Daniel Laird - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -static int mips_cpu_timer_irq; - -static const unsigned int irq_prio[PNX833X_PIC_NUM_IRQ] = -{ - 0, /* unused */ - 4, /* PNX833X_PIC_I2C0_INT 1 */ - 4, /* PNX833X_PIC_I2C1_INT 2 */ - 1, /* PNX833X_PIC_UART0_INT 3 */ - 1, /* PNX833X_PIC_UART1_INT 4 */ - 6, /* PNX833X_PIC_TS_IN0_DV_INT 5 */ - 6, /* PNX833X_PIC_TS_IN0_DMA_INT 6 */ - 7, /* PNX833X_PIC_GPIO_INT 7 */ - 4, /* PNX833X_PIC_AUDIO_DEC_INT 8 */ - 5, /* PNX833X_PIC_VIDEO_DEC_INT 9 */ - 4, /* PNX833X_PIC_CONFIG_INT 10 */ - 4, /* PNX833X_PIC_AOI_INT 11 */ - 9, /* PNX833X_PIC_SYNC_INT 12 */ - 9, /* PNX8335_PIC_SATA_INT 13 */ - 4, /* PNX833X_PIC_OSD_INT 14 */ - 9, /* PNX833X_PIC_DISP1_INT 15 */ - 4, /* PNX833X_PIC_DEINTERLACER_INT 16 */ - 9, /* PNX833X_PIC_DISPLAY2_INT 17 */ - 4, /* PNX833X_PIC_VC_INT 18 */ - 4, /* PNX833X_PIC_SC_INT 19 */ - 9, /* PNX833X_PIC_IDE_INT 20 */ - 9, /* PNX833X_PIC_IDE_DMA_INT 21 */ - 6, /* PNX833X_PIC_TS_IN1_DV_INT 22 */ - 6, /* PNX833X_PIC_TS_IN1_DMA_INT 23 */ - 4, /* PNX833X_PIC_SGDX_DMA_INT 24 */ - 4, /* PNX833X_PIC_TS_OUT_INT 25 */ - 4, /* PNX833X_PIC_IR_INT 26 */ - 3, /* PNX833X_PIC_VMSP1_INT 27 */ - 3, /* PNX833X_PIC_VMSP2_INT 28 */ - 4, /* PNX833X_PIC_PIBC_INT 29 */ - 4, /* PNX833X_PIC_TS_IN0_TRD_INT 30 */ - 4, /* PNX833X_PIC_SGDX_TPD_INT 31 */ - 5, /* PNX833X_PIC_USB_INT 32 */ - 4, /* PNX833X_PIC_TS_IN1_TRD_INT 33 */ - 4, /* PNX833X_PIC_CLOCK_INT 34 */ - 4, /* PNX833X_PIC_SGDX_PARSER_INT 35 */ - 4, /* PNX833X_PIC_VMSP_DMA_INT 36 */ -#if defined(CONFIG_SOC_PNX8335) - 4, /* PNX8335_PIC_MIU_INT 37 */ - 4, /* PNX8335_PIC_AVCHIP_IRQ_INT 38 */ - 9, /* PNX8335_PIC_SYNC_HD_INT 39 */ - 9, /* PNX8335_PIC_DISP_HD_INT 40 */ - 9, /* PNX8335_PIC_DISP_SCALER_INT 41 */ - 4, /* PNX8335_PIC_OSD_HD1_INT 42 */ - 4, /* PNX8335_PIC_DTL_WRITER_Y_INT 43 */ - 4, /* PNX8335_PIC_DTL_WRITER_C_INT 44 */ - 4, /* PNX8335_PIC_DTL_EMULATOR_Y_IR_INT 45 */ - 4, /* PNX8335_PIC_DTL_EMULATOR_C_IR_INT 46 */ - 4, /* PNX8335_PIC_DENC_TTX_INT 47 */ - 4, /* PNX8335_PIC_MMI_SIF0_INT 48 */ - 4, /* PNX8335_PIC_MMI_SIF1_INT 49 */ - 4, /* PNX8335_PIC_MMI_CDMMU_INT 50 */ - 4, /* PNX8335_PIC_PIBCS_INT 51 */ - 12, /* PNX8335_PIC_ETHERNET_INT 52 */ - 3, /* PNX8335_PIC_VMSP1_0_INT 53 */ - 3, /* PNX8335_PIC_VMSP1_1_INT 54 */ - 4, /* PNX8335_PIC_VMSP1_DMA_INT 55 */ - 4, /* PNX8335_PIC_TDGR_DE_INT 56 */ - 4, /* PNX8335_PIC_IR1_IRQ_INT 57 */ -#endif -}; - -static void pnx833x_timer_dispatch(void) -{ - do_IRQ(mips_cpu_timer_irq); -} - -static void pic_dispatch(void) -{ - unsigned int irq = PNX833X_REGFIELD(PIC_INT_SRC, INT_SRC); - - if ((irq >= 1) && (irq < (PNX833X_PIC_NUM_IRQ))) { - unsigned long priority = PNX833X_PIC_INT_PRIORITY; - PNX833X_PIC_INT_PRIORITY = irq_prio[irq]; - - if (irq == PNX833X_PIC_GPIO_INT) { - unsigned long mask = PNX833X_PIO_INT_STATUS & PNX833X_PIO_INT_ENABLE; - int pin; - while ((pin = ffs(mask & 0xffff))) { - pin -= 1; - do_IRQ(PNX833X_GPIO_IRQ_BASE + pin); - mask &= ~(1 << pin); - } - } else { - do_IRQ(irq + PNX833X_PIC_IRQ_BASE); - } - - PNX833X_PIC_INT_PRIORITY = priority; - } else { - printk(KERN_ERR "plat_irq_dispatch: unexpected irq %u\n", irq); - } -} - -asmlinkage void plat_irq_dispatch(void) -{ - unsigned int pending = read_c0_status() & read_c0_cause(); - - if (pending & STATUSF_IP4) - pic_dispatch(); - else if (pending & STATUSF_IP7) - do_IRQ(PNX833X_TIMER_IRQ); - else - spurious_interrupt(); -} - -static inline void pnx833x_hard_enable_pic_irq(unsigned int irq) -{ - /* Currently we do this by setting IRQ priority to 1. - If priority support is being implemented, 1 should be repalced - by a better value. */ - PNX833X_PIC_INT_REG(irq) = irq_prio[irq]; -} - -static inline void pnx833x_hard_disable_pic_irq(unsigned int irq) -{ - /* Disable IRQ by writing setting it's priority to 0 */ - PNX833X_PIC_INT_REG(irq) = 0; -} - -static DEFINE_RAW_SPINLOCK(pnx833x_irq_lock); - -static unsigned int pnx833x_startup_pic_irq(unsigned int irq) -{ - unsigned long flags; - unsigned int pic_irq = irq - PNX833X_PIC_IRQ_BASE; - - raw_spin_lock_irqsave(&pnx833x_irq_lock, flags); - pnx833x_hard_enable_pic_irq(pic_irq); - raw_spin_unlock_irqrestore(&pnx833x_irq_lock, flags); - return 0; -} - -static void pnx833x_enable_pic_irq(struct irq_data *d) -{ - unsigned long flags; - unsigned int pic_irq = d->irq - PNX833X_PIC_IRQ_BASE; - - raw_spin_lock_irqsave(&pnx833x_irq_lock, flags); - pnx833x_hard_enable_pic_irq(pic_irq); - raw_spin_unlock_irqrestore(&pnx833x_irq_lock, flags); -} - -static void pnx833x_disable_pic_irq(struct irq_data *d) -{ - unsigned long flags; - unsigned int pic_irq = d->irq - PNX833X_PIC_IRQ_BASE; - - raw_spin_lock_irqsave(&pnx833x_irq_lock, flags); - pnx833x_hard_disable_pic_irq(pic_irq); - raw_spin_unlock_irqrestore(&pnx833x_irq_lock, flags); -} - -static DEFINE_RAW_SPINLOCK(pnx833x_gpio_pnx833x_irq_lock); - -static void pnx833x_enable_gpio_irq(struct irq_data *d) -{ - int pin = d->irq - PNX833X_GPIO_IRQ_BASE; - unsigned long flags; - raw_spin_lock_irqsave(&pnx833x_gpio_pnx833x_irq_lock, flags); - pnx833x_gpio_enable_irq(pin); - raw_spin_unlock_irqrestore(&pnx833x_gpio_pnx833x_irq_lock, flags); -} - -static void pnx833x_disable_gpio_irq(struct irq_data *d) -{ - int pin = d->irq - PNX833X_GPIO_IRQ_BASE; - unsigned long flags; - raw_spin_lock_irqsave(&pnx833x_gpio_pnx833x_irq_lock, flags); - pnx833x_gpio_disable_irq(pin); - raw_spin_unlock_irqrestore(&pnx833x_gpio_pnx833x_irq_lock, flags); -} - -static int pnx833x_set_type_gpio_irq(struct irq_data *d, unsigned int flow_type) -{ - int pin = d->irq - PNX833X_GPIO_IRQ_BASE; - int gpio_mode; - - switch (flow_type) { - case IRQ_TYPE_EDGE_RISING: - gpio_mode = GPIO_INT_EDGE_RISING; - break; - case IRQ_TYPE_EDGE_FALLING: - gpio_mode = GPIO_INT_EDGE_FALLING; - break; - case IRQ_TYPE_EDGE_BOTH: - gpio_mode = GPIO_INT_EDGE_BOTH; - break; - case IRQ_TYPE_LEVEL_HIGH: - gpio_mode = GPIO_INT_LEVEL_HIGH; - break; - case IRQ_TYPE_LEVEL_LOW: - gpio_mode = GPIO_INT_LEVEL_LOW; - break; - default: - gpio_mode = GPIO_INT_NONE; - break; - } - - pnx833x_gpio_setup_irq(gpio_mode, pin); - - return 0; -} - -static struct irq_chip pnx833x_pic_irq_type = { - .name = "PNX-PIC", - .irq_enable = pnx833x_enable_pic_irq, - .irq_disable = pnx833x_disable_pic_irq, -}; - -static struct irq_chip pnx833x_gpio_irq_type = { - .name = "PNX-GPIO", - .irq_enable = pnx833x_enable_gpio_irq, - .irq_disable = pnx833x_disable_gpio_irq, - .irq_set_type = pnx833x_set_type_gpio_irq, -}; - -void __init arch_init_irq(void) -{ - unsigned int irq; - - /* setup standard internal cpu irqs */ - mips_cpu_irq_init(); - - /* Set IRQ information in irq_desc */ - for (irq = PNX833X_PIC_IRQ_BASE; irq < (PNX833X_PIC_IRQ_BASE + PNX833X_PIC_NUM_IRQ); irq++) { - pnx833x_hard_disable_pic_irq(irq); - irq_set_chip_and_handler(irq, &pnx833x_pic_irq_type, - handle_simple_irq); - } - - for (irq = PNX833X_GPIO_IRQ_BASE; irq < (PNX833X_GPIO_IRQ_BASE + PNX833X_GPIO_NUM_IRQ); irq++) - irq_set_chip_and_handler(irq, &pnx833x_gpio_irq_type, - handle_simple_irq); - - /* Set PIC priority limiter register to 0 */ - PNX833X_PIC_INT_PRIORITY = 0; - - /* Setup GPIO IRQ dispatching */ - pnx833x_startup_pic_irq(PNX833X_PIC_GPIO_INT); - - /* Enable PIC IRQs (HWIRQ2) */ - if (cpu_has_vint) - set_vi_handler(4, pic_dispatch); - - write_c0_status(read_c0_status() | IE_IRQ2); -} - -unsigned int get_c0_compare_int(void) -{ - if (cpu_has_vint) - set_vi_handler(cp0_compare_irq, pnx833x_timer_dispatch); - - mips_cpu_timer_irq = MIPS_CPU_IRQ_BASE + cp0_compare_irq; - return mips_cpu_timer_irq; -} - -void __init plat_time_init(void) -{ - /* calculate mips_hpt_frequency based on PNX833X_CLOCK_CPUCP_CTL reg */ - - extern unsigned long mips_hpt_frequency; - unsigned long reg = PNX833X_CLOCK_CPUCP_CTL; - - if (!(PNX833X_BIT(reg, CLOCK_CPUCP_CTL, EXIT_RESET))) { - /* Functional clock is disabled so use crystal frequency */ - mips_hpt_frequency = 25; - } else { -#if defined(CONFIG_SOC_PNX8335) - /* Functional clock is enabled, so get clock multiplier */ - mips_hpt_frequency = 90 + (10 * PNX8335_REGFIELD(CLOCK_PLL_CPU_CTL, FREQ)); -#else - static const unsigned long int freq[4] = {240, 160, 120, 80}; - mips_hpt_frequency = freq[PNX833X_FIELD(reg, CLOCK_CPUCP_CTL, DIV_CLOCK)]; -#endif - } - - printk(KERN_INFO "CPU clock is %ld MHz\n", mips_hpt_frequency); - - mips_hpt_frequency *= 500000; -} diff --git a/arch/mips/pnx833x/common/platform.c b/arch/mips/pnx833x/common/platform.c deleted file mode 100644 index 5fa0373f1c9e..000000000000 --- a/arch/mips/pnx833x/common/platform.c +++ /dev/null @@ -1,224 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * platform.c: platform support for PNX833X. - * - * Copyright 2008 NXP Semiconductors - * Chris Steel - * Daniel Laird - * - * Based on software written by: - * Nikita Youshchenko , based on PNX8550 code. - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include - -static u64 uart_dmamask = DMA_BIT_MASK(32); - -static struct resource pnx833x_uart_resources[] = { - [0] = { - .start = PNX833X_UART0_PORTS_START, - .end = PNX833X_UART0_PORTS_END, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = PNX833X_PIC_UART0_INT, - .end = PNX833X_PIC_UART0_INT, - .flags = IORESOURCE_IRQ, - }, - [2] = { - .start = PNX833X_UART1_PORTS_START, - .end = PNX833X_UART1_PORTS_END, - .flags = IORESOURCE_MEM, - }, - [3] = { - .start = PNX833X_PIC_UART1_INT, - .end = PNX833X_PIC_UART1_INT, - .flags = IORESOURCE_IRQ, - }, -}; - -struct pnx8xxx_port pnx8xxx_ports[] = { - [0] = { - .port = { - .type = PORT_PNX8XXX, - .iotype = UPIO_MEM, - .membase = (void __iomem *)PNX833X_UART0_PORTS_START, - .mapbase = PNX833X_UART0_PORTS_START, - .irq = PNX833X_PIC_UART0_INT, - .uartclk = 3692300, - .fifosize = 16, - .flags = UPF_BOOT_AUTOCONF, - .line = 0, - }, - }, - [1] = { - .port = { - .type = PORT_PNX8XXX, - .iotype = UPIO_MEM, - .membase = (void __iomem *)PNX833X_UART1_PORTS_START, - .mapbase = PNX833X_UART1_PORTS_START, - .irq = PNX833X_PIC_UART1_INT, - .uartclk = 3692300, - .fifosize = 16, - .flags = UPF_BOOT_AUTOCONF, - .line = 1, - }, - }, -}; - -static struct platform_device pnx833x_uart_device = { - .name = "pnx8xxx-uart", - .id = -1, - .dev = { - .dma_mask = &uart_dmamask, - .coherent_dma_mask = DMA_BIT_MASK(32), - .platform_data = pnx8xxx_ports, - }, - .num_resources = ARRAY_SIZE(pnx833x_uart_resources), - .resource = pnx833x_uart_resources, -}; - -static u64 ehci_dmamask = DMA_BIT_MASK(32); - -static struct resource pnx833x_usb_ehci_resources[] = { - [0] = { - .start = PNX833X_USB_PORTS_START, - .end = PNX833X_USB_PORTS_END, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = PNX833X_PIC_USB_INT, - .end = PNX833X_PIC_USB_INT, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct platform_device pnx833x_usb_ehci_device = { - .name = "pnx833x-ehci", - .id = -1, - .dev = { - .dma_mask = &ehci_dmamask, - .coherent_dma_mask = DMA_BIT_MASK(32), - }, - .num_resources = ARRAY_SIZE(pnx833x_usb_ehci_resources), - .resource = pnx833x_usb_ehci_resources, -}; - -static u64 ethernet_dmamask = DMA_BIT_MASK(32); - -static struct resource pnx833x_ethernet_resources[] = { - [0] = { - .start = PNX8335_IP3902_PORTS_START, - .end = PNX8335_IP3902_PORTS_END, - .flags = IORESOURCE_MEM, - }, -#ifdef CONFIG_SOC_PNX8335 - [1] = { - .start = PNX8335_PIC_ETHERNET_INT, - .end = PNX8335_PIC_ETHERNET_INT, - .flags = IORESOURCE_IRQ, - }, -#endif -}; - -static struct platform_device pnx833x_ethernet_device = { - .name = "ip3902-eth", - .id = -1, - .dev = { - .dma_mask = ðernet_dmamask, - .coherent_dma_mask = DMA_BIT_MASK(32), - }, - .num_resources = ARRAY_SIZE(pnx833x_ethernet_resources), - .resource = pnx833x_ethernet_resources, -}; - -static struct resource pnx833x_sata_resources[] = { - [0] = { - .start = PNX8335_SATA_PORTS_START, - .end = PNX8335_SATA_PORTS_END, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = PNX8335_PIC_SATA_INT, - .end = PNX8335_PIC_SATA_INT, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct platform_device pnx833x_sata_device = { - .name = "pnx833x-sata", - .id = -1, - .num_resources = ARRAY_SIZE(pnx833x_sata_resources), - .resource = pnx833x_sata_resources, -}; - -static void -pnx833x_flash_nand_cmd_ctrl(struct nand_chip *this, int cmd, unsigned int ctrl) -{ - unsigned long nandaddr = (unsigned long)this->legacy.IO_ADDR_W; - - if (cmd == NAND_CMD_NONE) - return; - - if (ctrl & NAND_CLE) - writeb(cmd, (void __iomem *)(nandaddr + PNX8335_NAND_CLE_MASK)); - else - writeb(cmd, (void __iomem *)(nandaddr + PNX8335_NAND_ALE_MASK)); -} - -static struct platform_nand_data pnx833x_flash_nand_data = { - .chip = { - .nr_chips = 1, - .chip_delay = 25, - }, - .ctrl = { - .cmd_ctrl = pnx833x_flash_nand_cmd_ctrl - } -}; - -/* - * Set start to be the correct address (PNX8335_NAND_BASE with no 0xb!!), - * 12 bytes more seems to be the standard that allows for NAND access. - */ -static struct resource pnx833x_flash_nand_resource = { - .start = PNX8335_NAND_BASE, - .end = PNX8335_NAND_BASE + 12, - .flags = IORESOURCE_MEM, -}; - -static struct platform_device pnx833x_flash_nand = { - .name = "gen_nand", - .id = -1, - .num_resources = 1, - .resource = &pnx833x_flash_nand_resource, - .dev = { - .platform_data = &pnx833x_flash_nand_data, - }, -}; - -static struct platform_device *pnx833x_platform_devices[] __initdata = { - &pnx833x_uart_device, - &pnx833x_usb_ehci_device, - &pnx833x_ethernet_device, - &pnx833x_sata_device, - &pnx833x_flash_nand, -}; - -static int __init pnx833x_platform_init(void) -{ - return platform_add_devices(pnx833x_platform_devices, - ARRAY_SIZE(pnx833x_platform_devices)); -} - -arch_initcall(pnx833x_platform_init); diff --git a/arch/mips/pnx833x/common/prom.c b/arch/mips/pnx833x/common/prom.c deleted file mode 100644 index 12733ef25782..000000000000 --- a/arch/mips/pnx833x/common/prom.c +++ /dev/null @@ -1,51 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * prom.c: - * - * Copyright 2008 NXP Semiconductors - * Chris Steel - * Daniel Laird - * - * Based on software written by: - * Nikita Youshchenko , based on PNX8550 code. - */ -#include -#include -#include - -void __init prom_init_cmdline(void) -{ - int argc = fw_arg0; - char **argv = (char **)fw_arg1; - char *c = &(arcs_cmdline[0]); - int i; - - for (i = 1; i < argc; i++) { - strcpy(c, argv[i]); - c += strlen(argv[i]); - if (i < argc-1) - *c++ = ' '; - } - *c = 0; -} - -char __init *prom_getenv(char *envname) -{ - extern char **prom_envp; - char **env = prom_envp; - int i; - - i = strlen(envname); - - while (*env) { - if (strncmp(envname, *env, i) == 0 && *(*env+i) == '=') - return *env + i + 1; - env++; - } - - return 0; -} - -void __init prom_free_prom_memory(void) -{ -} diff --git a/arch/mips/pnx833x/common/reset.c b/arch/mips/pnx833x/common/reset.c deleted file mode 100644 index b48e83bf912b..000000000000 --- a/arch/mips/pnx833x/common/reset.c +++ /dev/null @@ -1,31 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * reset.c: reset support for PNX833X. - * - * Copyright 2008 NXP Semiconductors - * Chris Steel - * Daniel Laird - * - * Based on software written by: - * Nikita Youshchenko , based on PNX8550 code. - */ -#include -#include - -void pnx833x_machine_restart(char *command) -{ - PNX833X_RESET_CONTROL_2 = 0; - PNX833X_RESET_CONTROL = 0; -} - -void pnx833x_machine_halt(void) -{ - while (1) - __asm__ __volatile__ ("wait"); - -} - -void pnx833x_machine_power_off(void) -{ - pnx833x_machine_halt(); -} diff --git a/arch/mips/pnx833x/common/setup.c b/arch/mips/pnx833x/common/setup.c deleted file mode 100644 index abf68d92ce4a..000000000000 --- a/arch/mips/pnx833x/common/setup.c +++ /dev/null @@ -1,48 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * setup.c: Setup PNX833X Soc. - * - * Copyright 2008 NXP Semiconductors - * Chris Steel - * Daniel Laird - * - * Based on software written by: - * Nikita Youshchenko , based on PNX8550 code. - */ -#include -#include -#include -#include -#include -#include -#include -#include - -extern void pnx833x_board_setup(void); -extern void pnx833x_machine_restart(char *); -extern void pnx833x_machine_halt(void); -extern void pnx833x_machine_power_off(void); - -int __init plat_mem_setup(void) -{ - /* set mips clock to 320MHz */ -#if defined(CONFIG_SOC_PNX8335) - PNX8335_WRITEFIELD(0x17, CLOCK_PLL_CPU_CTL, FREQ); -#endif - pnx833x_gpio_init(); /* so it will be ready in board_setup() */ - - pnx833x_board_setup(); - - _machine_restart = pnx833x_machine_restart; - _machine_halt = pnx833x_machine_halt; - pm_power_off = pnx833x_machine_power_off; - - /* IO/MEM resources. */ - set_io_port_base(KSEG1); - ioport_resource.start = 0; - ioport_resource.end = ~0; - iomem_resource.start = 0; - iomem_resource.end = ~0; - - return 0; -} diff --git a/arch/mips/pnx833x/stb22x/Makefile b/arch/mips/pnx833x/stb22x/Makefile deleted file mode 100644 index 7c5ddf36b735..000000000000 --- a/arch/mips/pnx833x/stb22x/Makefile +++ /dev/null @@ -1,2 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -obj-y := board.o diff --git a/arch/mips/pnx833x/stb22x/board.c b/arch/mips/pnx833x/stb22x/board.c deleted file mode 100644 index 93d8e7b73427..000000000000 --- a/arch/mips/pnx833x/stb22x/board.c +++ /dev/null @@ -1,120 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * board.c: STB225 board support. - * - * Copyright 2008 NXP Semiconductors - * Chris Steel - * Daniel Laird - * - * Based on software written by: - * Nikita Youshchenko , based on PNX8550 code. - */ -#include -#include -#include -#include -#include - -/* endianess twiddlers */ -#define PNX8335_DEBUG0 0x4400 -#define PNX8335_DEBUG1 0x4404 -#define PNX8335_DEBUG2 0x4408 -#define PNX8335_DEBUG3 0x440c -#define PNX8335_DEBUG4 0x4410 -#define PNX8335_DEBUG5 0x4414 -#define PNX8335_DEBUG6 0x4418 -#define PNX8335_DEBUG7 0x441c - -int prom_argc; -char **prom_argv, **prom_envp; - -extern void prom_init_cmdline(void); -extern char *prom_getenv(char *envname); - -const char *get_system_type(void) -{ - return "NXP STB22x"; -} - -static inline unsigned long env_or_default(char *env, unsigned long dfl) -{ - char *str = prom_getenv(env); - return str ? simple_strtol(str, 0, 0) : dfl; -} - -void __init prom_init(void) -{ - unsigned long memsize; - - prom_argc = fw_arg0; - prom_argv = (char **)fw_arg1; - prom_envp = (char **)fw_arg2; - - prom_init_cmdline(); - - memsize = env_or_default("memsize", 0x02000000); - add_memory_region(0, memsize, BOOT_MEM_RAM); -} - -void __init pnx833x_board_setup(void) -{ - pnx833x_gpio_select_function_alt(4); - pnx833x_gpio_select_output(4); - pnx833x_gpio_select_function_alt(5); - pnx833x_gpio_select_input(5); - pnx833x_gpio_select_function_alt(6); - pnx833x_gpio_select_input(6); - pnx833x_gpio_select_function_alt(7); - pnx833x_gpio_select_output(7); - - pnx833x_gpio_select_function_alt(25); - pnx833x_gpio_select_function_alt(26); - - pnx833x_gpio_select_function_alt(27); - pnx833x_gpio_select_function_alt(28); - pnx833x_gpio_select_function_alt(29); - pnx833x_gpio_select_function_alt(30); - pnx833x_gpio_select_function_alt(31); - pnx833x_gpio_select_function_alt(32); - pnx833x_gpio_select_function_alt(33); - -#if IS_ENABLED(CONFIG_MTD_NAND_PLATFORM) - /* Setup MIU for NAND access on CS0... - * - * (it seems that we must also configure CS1 for reliable operation, - * otherwise the first read ID command will fail if it's read as 4 bytes - * but pass if it's read as 1 word.) - */ - - /* Setup MIU CS0 & CS1 timing */ - PNX833X_MIU_SEL0 = 0; - PNX833X_MIU_SEL1 = 0; - PNX833X_MIU_SEL0_TIMING = 0x50003081; - PNX833X_MIU_SEL1_TIMING = 0x50003081; - - /* Setup GPIO 00 for use as MIU CS1 (CS0 is not multiplexed, so does not need this) */ - pnx833x_gpio_select_function_alt(0); - - /* Setup GPIO 04 to input NAND read/busy signal */ - pnx833x_gpio_select_function_io(4); - pnx833x_gpio_select_input(4); - - /* Setup GPIO 05 to disable NAND write protect */ - pnx833x_gpio_select_function_io(5); - pnx833x_gpio_select_output(5); - pnx833x_gpio_write(1, 5); - -#elif IS_ENABLED(CONFIG_MTD_CFI) - - /* Set up MIU for 16-bit NOR access on CS0 and CS1... */ - - /* Setup MIU CS0 & CS1 timing */ - PNX833X_MIU_SEL0 = 1; - PNX833X_MIU_SEL1 = 1; - PNX833X_MIU_SEL0_TIMING = 0x6A08D082; - PNX833X_MIU_SEL1_TIMING = 0x6A08D082; - - /* Setup GPIO 00 for use as MIU CS1 (CS0 is not multiplexed, so does not need this) */ - pnx833x_gpio_select_function_alt(0); -#endif -} From 67c3e59443f5fc77be39e2ce0db75fbfa78c7965 Mon Sep 17 00:00:00 2001 From: Nicholas Mc Guire Date: Mon, 2 Jul 2018 11:08:16 +0200 Subject: [PATCH 013/645] powerpc/pseries: Fix missing of_node_put() in rng_init() The call to of_find_compatible_node() returns a node pointer with refcount incremented thus it must be explicitly decremented here before returning. Fixes: a489043f4626 ("powerpc/pseries: Implement arch_get_random_long() based on H_RANDOM") Signed-off-by: Nicholas Mc Guire Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/1530522496-14816-1-git-send-email-hofrat@osadl.org --- arch/powerpc/platforms/pseries/rng.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/platforms/pseries/rng.c b/arch/powerpc/platforms/pseries/rng.c index bbb97169bf63..6268545947b8 100644 --- a/arch/powerpc/platforms/pseries/rng.c +++ b/arch/powerpc/platforms/pseries/rng.c @@ -36,6 +36,7 @@ static __init int rng_init(void) ppc_md.get_random_seed = pseries_get_random_long; + of_node_put(dn); return 0; } machine_subsys_initcall(pseries, rng_init); From d3e669f31ec35856f5e85df9224ede5bdbf1bc7b Mon Sep 17 00:00:00 2001 From: Nicholas Mc Guire Date: Wed, 4 Jul 2018 10:03:27 +0200 Subject: [PATCH 014/645] powerpc/icp-hv: Fix missing of_node_put() in success path Both of_find_compatible_node() and of_find_node_by_type() will return a refcounted node on success - thus for the success path the node must be explicitly released with a of_node_put(). Fixes: 0b05ac6e2480 ("powerpc/xics: Rewrite XICS driver") Signed-off-by: Nicholas Mc Guire Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/1530691407-3991-1-git-send-email-hofrat@osadl.org --- arch/powerpc/sysdev/xics/icp-hv.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/sysdev/xics/icp-hv.c b/arch/powerpc/sysdev/xics/icp-hv.c index ad8117148ea3..21b9d1bf39ff 100644 --- a/arch/powerpc/sysdev/xics/icp-hv.c +++ b/arch/powerpc/sysdev/xics/icp-hv.c @@ -174,6 +174,7 @@ int icp_hv_init(void) icp_ops = &icp_hv_ops; + of_node_put(np); return 0; } From 1e89da5ef9c28c673e86048c89ef9495618d987d Mon Sep 17 00:00:00 2001 From: Frederic Barrat Date: Fri, 3 Apr 2020 17:38:35 +0200 Subject: [PATCH 015/645] scsi: cxlflash: Access interrupt trigger page from xive directly MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit xive is already mapping the trigger page in kernel space and it can be accessed through standard APIs, so let's reuse it and simplify the code. Signed-off-by: Frederic Barrat Reviewed-by: Cédric Le Goater Acked-by: Matthew R. Ochs Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200403153838.29224-2-fbarrat@linux.ibm.com --- drivers/scsi/cxlflash/ocxl_hw.c | 18 ++++++++---------- drivers/scsi/cxlflash/ocxl_hw.h | 1 - 2 files changed, 8 insertions(+), 11 deletions(-) diff --git a/drivers/scsi/cxlflash/ocxl_hw.c b/drivers/scsi/cxlflash/ocxl_hw.c index 7018cd802569..d6eec434a607 100644 --- a/drivers/scsi/cxlflash/ocxl_hw.c +++ b/drivers/scsi/cxlflash/ocxl_hw.c @@ -15,7 +15,8 @@ #include #include #include - +#include +#include #include #include @@ -180,7 +181,7 @@ static int afu_map_irq(u64 flags, struct ocxlflash_context *ctx, int num, struct ocxl_hw_afu *afu = ctx->hw_afu; struct device *dev = afu->dev; struct ocxlflash_irqs *irq; - void __iomem *vtrig; + struct xive_irq_data *xd; u32 virq; int rc = 0; @@ -204,15 +205,15 @@ static int afu_map_irq(u64 flags, struct ocxlflash_context *ctx, int num, goto err1; } - vtrig = ioremap(irq->ptrig, PAGE_SIZE); - if (unlikely(!vtrig)) { - dev_err(dev, "%s: Trigger page mapping failed\n", __func__); - rc = -ENOMEM; + xd = irq_get_handler_data(virq); + if (unlikely(!xd)) { + dev_err(dev, "%s: Can't get interrupt data\n", __func__); + rc = -ENXIO; goto err2; } irq->virq = virq; - irq->vtrig = vtrig; + irq->vtrig = xd->trig_mmio; out: return rc; err2: @@ -259,8 +260,6 @@ static void afu_unmap_irq(u64 flags, struct ocxlflash_context *ctx, int num, } irq = &ctx->irqs[num]; - if (irq->vtrig) - iounmap(irq->vtrig); if (irq_find_mapping(NULL, irq->hwirq)) { free_irq(irq->virq, cookie); @@ -648,7 +647,6 @@ static int alloc_afu_irqs(struct ocxlflash_context *ctx, int num) } irqs[i].hwirq = hwirq; - irqs[i].ptrig = addr; } ctx->irqs = irqs; diff --git a/drivers/scsi/cxlflash/ocxl_hw.h b/drivers/scsi/cxlflash/ocxl_hw.h index fc6ad4f985de..f2fe88816bea 100644 --- a/drivers/scsi/cxlflash/ocxl_hw.h +++ b/drivers/scsi/cxlflash/ocxl_hw.h @@ -13,7 +13,6 @@ struct ocxlflash_irqs { int hwirq; u32 virq; - u64 ptrig; void __iomem *vtrig; }; From ad857d47df6a1adc9798558701dd5426643b859f Mon Sep 17 00:00:00 2001 From: Frederic Barrat Date: Fri, 3 Apr 2020 17:38:36 +0200 Subject: [PATCH 016/645] ocxl: Access interrupt trigger page from xive directly MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We can access the trigger page through standard APIs so let's use it and avoid saving it when allocating the interrupt. It will also allow to simplify allocation in a later patch. Signed-off-by: Frederic Barrat Reviewed-by: Cédric Le Goater Reviewed-by: Greg Kurz Acked-by: Andrew Donnellan Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200403153838.29224-3-fbarrat@linux.ibm.com --- drivers/misc/ocxl/afu_irq.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/misc/ocxl/afu_irq.c b/drivers/misc/ocxl/afu_irq.c index 70f8f1c3929d..b30ec0ef7be7 100644 --- a/drivers/misc/ocxl/afu_irq.c +++ b/drivers/misc/ocxl/afu_irq.c @@ -2,6 +2,7 @@ // Copyright 2017 IBM Corp. #include #include +#include #include "ocxl_internal.h" #include "trace.h" @@ -196,13 +197,16 @@ void ocxl_afu_irq_free_all(struct ocxl_context *ctx) u64 ocxl_afu_irq_get_addr(struct ocxl_context *ctx, int irq_id) { + struct xive_irq_data *xd; struct afu_irq *irq; u64 addr = 0; mutex_lock(&ctx->irq_lock); irq = idr_find(&ctx->irq_idr, irq_id); - if (irq) - addr = irq->trigger_page; + if (irq) { + xd = irq_get_handler_data(irq->virq); + addr = xd ? xd->trig_page : 0; + } mutex_unlock(&ctx->irq_lock); return addr; } From dde6f18a8779dcd88d9fd5d6336032fee7e07fcd Mon Sep 17 00:00:00 2001 From: Frederic Barrat Date: Fri, 3 Apr 2020 17:38:37 +0200 Subject: [PATCH 017/645] ocxl: Don't return trigger page when allocating an interrupt MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Existing users of ocxl_link_irq_alloc() have been converted to obtain the trigger page of an interrupt through xive directly, we therefore have no need to return the trigger page when allocating an interrupt. It also allows ocxl to use the xive native interface to allocate interrupts, instead of its custom service. Signed-off-by: Frederic Barrat Reviewed-by: Cédric Le Goater Reviewed-by: Greg Kurz Acked-by: Andrew Donnellan Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200403153838.29224-4-fbarrat@linux.ibm.com --- drivers/misc/ocxl/Kconfig | 2 +- drivers/misc/ocxl/afu_irq.c | 4 +--- drivers/misc/ocxl/link.c | 15 +++++++-------- drivers/scsi/cxlflash/ocxl_hw.c | 3 +-- include/misc/ocxl.h | 8 +------- 5 files changed, 11 insertions(+), 21 deletions(-) diff --git a/drivers/misc/ocxl/Kconfig b/drivers/misc/ocxl/Kconfig index 6551007a066c..0d815b2a40b3 100644 --- a/drivers/misc/ocxl/Kconfig +++ b/drivers/misc/ocxl/Kconfig @@ -9,7 +9,7 @@ config OCXL_BASE config OCXL tristate "OpenCAPI coherent accelerator support" - depends on PPC_POWERNV && PCI && EEH + depends on PPC_POWERNV && PCI && EEH && PPC_XIVE_NATIVE select OCXL_BASE select HOTPLUG_PCI_POWERNV default m diff --git a/drivers/misc/ocxl/afu_irq.c b/drivers/misc/ocxl/afu_irq.c index b30ec0ef7be7..ecdcfae025b7 100644 --- a/drivers/misc/ocxl/afu_irq.c +++ b/drivers/misc/ocxl/afu_irq.c @@ -11,7 +11,6 @@ struct afu_irq { int hw_irq; unsigned int virq; char *name; - u64 trigger_page; irqreturn_t (*handler)(void *private); void (*free_private)(void *private); void *private; @@ -125,8 +124,7 @@ int ocxl_afu_irq_alloc(struct ocxl_context *ctx, int *irq_id) goto err_unlock; } - rc = ocxl_link_irq_alloc(ctx->afu->fn->link, &irq->hw_irq, - &irq->trigger_page); + rc = ocxl_link_irq_alloc(ctx->afu->fn->link, &irq->hw_irq); if (rc) goto err_idr; diff --git a/drivers/misc/ocxl/link.c b/drivers/misc/ocxl/link.c index 58d111afd9f6..fd73d3bc0eb6 100644 --- a/drivers/misc/ocxl/link.c +++ b/drivers/misc/ocxl/link.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include "ocxl_internal.h" #include "trace.h" @@ -682,23 +683,21 @@ unlock: } EXPORT_SYMBOL_GPL(ocxl_link_remove_pe); -int ocxl_link_irq_alloc(void *link_handle, int *hw_irq, u64 *trigger_addr) +int ocxl_link_irq_alloc(void *link_handle, int *hw_irq) { struct ocxl_link *link = (struct ocxl_link *) link_handle; - int rc, irq; - u64 addr; + int irq; if (atomic_dec_if_positive(&link->irq_available) < 0) return -ENOSPC; - rc = pnv_ocxl_alloc_xive_irq(&irq, &addr); - if (rc) { + irq = xive_native_alloc_irq(); + if (!irq) { atomic_inc(&link->irq_available); - return rc; + return -ENXIO; } *hw_irq = irq; - *trigger_addr = addr; return 0; } EXPORT_SYMBOL_GPL(ocxl_link_irq_alloc); @@ -707,7 +706,7 @@ void ocxl_link_free_irq(void *link_handle, int hw_irq) { struct ocxl_link *link = (struct ocxl_link *) link_handle; - pnv_ocxl_free_xive_irq(hw_irq); + xive_native_free_irq(hw_irq); atomic_inc(&link->irq_available); } EXPORT_SYMBOL_GPL(ocxl_link_free_irq); diff --git a/drivers/scsi/cxlflash/ocxl_hw.c b/drivers/scsi/cxlflash/ocxl_hw.c index d6eec434a607..e4e0d767b98e 100644 --- a/drivers/scsi/cxlflash/ocxl_hw.c +++ b/drivers/scsi/cxlflash/ocxl_hw.c @@ -614,7 +614,6 @@ static int alloc_afu_irqs(struct ocxlflash_context *ctx, int num) struct ocxl_hw_afu *afu = ctx->hw_afu; struct device *dev = afu->dev; struct ocxlflash_irqs *irqs; - u64 addr; int rc = 0; int hwirq; int i; @@ -639,7 +638,7 @@ static int alloc_afu_irqs(struct ocxlflash_context *ctx, int num) } for (i = 0; i < num; i++) { - rc = ocxl_link_irq_alloc(afu->link_token, &hwirq, &addr); + rc = ocxl_link_irq_alloc(afu->link_token, &hwirq); if (unlikely(rc)) { dev_err(dev, "%s: ocxl_link_irq_alloc failed rc=%d\n", __func__, rc); diff --git a/include/misc/ocxl.h b/include/misc/ocxl.h index 357ef1aadbc0..e013736e275d 100644 --- a/include/misc/ocxl.h +++ b/include/misc/ocxl.h @@ -460,14 +460,8 @@ int ocxl_link_remove_pe(void *link_handle, int pasid); * Allocate an AFU interrupt associated to the link. * * 'hw_irq' is the hardware interrupt number - * 'obj_handle' is the 64-bit object handle to be passed to the AFU to - * trigger the interrupt. - * On P9, 'obj_handle' is an address, which, if written, triggers the - * interrupt. It is an MMIO address which needs to be remapped (one - * page). */ -int ocxl_link_irq_alloc(void *link_handle, int *hw_irq, - u64 *obj_handle); +int ocxl_link_irq_alloc(void *link_handle, int *hw_irq); /* * Free a previously allocated AFU interrupt From 374f6178f3483dcad151fc14b2fad92ed6652f07 Mon Sep 17 00:00:00 2001 From: Frederic Barrat Date: Fri, 3 Apr 2020 17:38:38 +0200 Subject: [PATCH 018/645] ocxl: Remove custom service to allocate interrupts MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We now allocate interrupts through xive directly. Signed-off-by: Frederic Barrat Reviewed-by: Cédric Le Goater Reviewed-by: Greg Kurz Acked-by: Andrew Donnellan Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200403153838.29224-5-fbarrat@linux.ibm.com --- arch/powerpc/include/asm/pnv-ocxl.h | 3 --- arch/powerpc/platforms/powernv/ocxl.c | 30 --------------------------- 2 files changed, 33 deletions(-) diff --git a/arch/powerpc/include/asm/pnv-ocxl.h b/arch/powerpc/include/asm/pnv-ocxl.h index ee79d2cd9fb6..d37ededca3ee 100644 --- a/arch/powerpc/include/asm/pnv-ocxl.h +++ b/arch/powerpc/include/asm/pnv-ocxl.h @@ -28,7 +28,4 @@ int pnv_ocxl_spa_setup(struct pci_dev *dev, void *spa_mem, int PE_mask, void **p void pnv_ocxl_spa_release(void *platform_data); int pnv_ocxl_spa_remove_pe_from_cache(void *platform_data, int pe_handle); -int pnv_ocxl_alloc_xive_irq(u32 *irq, u64 *trigger_addr); -void pnv_ocxl_free_xive_irq(u32 irq); - #endif /* _ASM_PNV_OCXL_H */ diff --git a/arch/powerpc/platforms/powernv/ocxl.c b/arch/powerpc/platforms/powernv/ocxl.c index 8c65aacda9c8..ecdad219d704 100644 --- a/arch/powerpc/platforms/powernv/ocxl.c +++ b/arch/powerpc/platforms/powernv/ocxl.c @@ -2,7 +2,6 @@ // Copyright 2017 IBM Corp. #include #include -#include #include #include "pci.h" @@ -484,32 +483,3 @@ int pnv_ocxl_spa_remove_pe_from_cache(void *platform_data, int pe_handle) return rc; } EXPORT_SYMBOL_GPL(pnv_ocxl_spa_remove_pe_from_cache); - -int pnv_ocxl_alloc_xive_irq(u32 *irq, u64 *trigger_addr) -{ - __be64 flags, trigger_page; - s64 rc; - u32 hwirq; - - hwirq = xive_native_alloc_irq(); - if (!hwirq) - return -ENOENT; - - rc = opal_xive_get_irq_info(hwirq, &flags, NULL, &trigger_page, NULL, - NULL); - if (rc || !trigger_page) { - xive_native_free_irq(hwirq); - return -ENOENT; - } - *irq = hwirq; - *trigger_addr = be64_to_cpu(trigger_page); - return 0; - -} -EXPORT_SYMBOL_GPL(pnv_ocxl_alloc_xive_irq); - -void pnv_ocxl_free_xive_irq(u32 irq) -{ - xive_native_free_irq(irq); -} -EXPORT_SYMBOL_GPL(pnv_ocxl_free_xive_irq); From 40ac790d99c6dd16b367d5c2339e446a5f1b0593 Mon Sep 17 00:00:00 2001 From: Frederic Barrat Date: Tue, 7 Apr 2020 13:56:01 +0200 Subject: [PATCH 019/645] cxl: Rework error message for incompatible slots Improve the error message shown if a capi adapter is plugged on a capi-incompatible slot directly under the PHB (no intermediate switch). Fixes: 5632874311db ("cxl: Add support for POWER9 DD2") Cc: stable@vger.kernel.org # 4.14+ Signed-off-by: Frederic Barrat Reviewed-by: Andrew Donnellan Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200407115601.25453-1-fbarrat@linux.ibm.com --- drivers/misc/cxl/pci.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c index 25a9dd9c0c1b..2ba899f5659f 100644 --- a/drivers/misc/cxl/pci.c +++ b/drivers/misc/cxl/pci.c @@ -393,8 +393,8 @@ int cxl_calc_capp_routing(struct pci_dev *dev, u64 *chipid, *capp_unit_id = get_capp_unit_id(np, *phb_index); of_node_put(np); if (!*capp_unit_id) { - pr_err("cxl: invalid capp unit id (phb_index: %d)\n", - *phb_index); + pr_err("cxl: No capp unit found for PHB[%lld,%d]. Make sure the adapter is on a capi-compatible slot\n", + *chipid, *phb_index); return -ENODEV; } From 8c7614d648037b0776e0b76cb62911be3b059ea4 Mon Sep 17 00:00:00 2001 From: Biwen Li Date: Wed, 27 May 2020 11:42:27 +0800 Subject: [PATCH 020/645] powerpc/dts/t4240rdb: remove interrupts property Since the interrupt pin for RTC DS1374 is not connected to the CPU on T4240RDB, remove the interrupt property from the device tree. This also fix the following warning for hwclock.util-linux: $ hwclock.util-linux hwclock.util-linux: select() to /dev/rtc0 to wait for clock tick timed out Signed-off-by: Biwen Li Acked-by: Li Yang Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200527034228.23793-1-biwen.li@oss.nxp.com --- arch/powerpc/boot/dts/fsl/t4240rdb.dts | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/powerpc/boot/dts/fsl/t4240rdb.dts b/arch/powerpc/boot/dts/fsl/t4240rdb.dts index a56a705d41f7..145896f2eef6 100644 --- a/arch/powerpc/boot/dts/fsl/t4240rdb.dts +++ b/arch/powerpc/boot/dts/fsl/t4240rdb.dts @@ -144,7 +144,6 @@ rtc@68 { compatible = "dallas,ds1374"; reg = <0x68>; - interrupts = <0x1 0x1 0 0>; }; }; From 843dc8ee23d1b353fa9cc24da3e52be0111d5931 Mon Sep 17 00:00:00 2001 From: Biwen Li Date: Wed, 27 May 2020 11:42:28 +0800 Subject: [PATCH 021/645] powerc/dtc/t1024rdb: remove interrupts property Since the interrupt pin for RTC DS1339 is not connected to the CPU on T1024RDB, remove the interrupt property from the device tree. This also fix the following warning for hwclock.util-linux: $ hwclock.util-linux hwclock.util-linux: select() to /dev/rtc0 to wait for clock tick timed out Signed-off-by: Biwen Li Acked-by: Li Yang Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200527034228.23793-2-biwen.li@oss.nxp.com --- arch/powerpc/boot/dts/fsl/t1024rdb.dts | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/powerpc/boot/dts/fsl/t1024rdb.dts b/arch/powerpc/boot/dts/fsl/t1024rdb.dts index 73a645324bc1..dbcd31cc35dc 100644 --- a/arch/powerpc/boot/dts/fsl/t1024rdb.dts +++ b/arch/powerpc/boot/dts/fsl/t1024rdb.dts @@ -161,7 +161,6 @@ rtc@68 { compatible = "dallas,ds1339"; reg = <0x68>; - interrupts = <0x1 0x1 0 0>; }; }; From 738e6cad0ace88edec8f4ffa082749ad5df26409 Mon Sep 17 00:00:00 2001 From: zhengbin Date: Tue, 19 Nov 2019 14:14:30 +0800 Subject: [PATCH 022/645] powerpc/fadump: Remove set but not used variable 'elf' Fix gcc '-Wunused-but-set-variable' warning: arch/powerpc/kernel/fadump.c: In function fadump_update_elfcore_header: arch/powerpc/kernel/fadump.c:790:17: warning: variable elf set but not used [-Wunused-but-set-variable] It is introduced by commit ebaeb5ae2437 ("fadump: Convert firmware-assisted cpu state dump data into elf notes."), but never used, so remove it. Reported-by: Hulk Robot Signed-off-by: zhengbin Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/1574144074-142032-2-git-send-email-zhengbin13@huawei.com --- arch/powerpc/kernel/fadump.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index 10ebb4bf71ad..d192067a112c 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -754,10 +754,8 @@ u32 *fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs) void fadump_update_elfcore_header(char *bufp) { - struct elfhdr *elf; struct elf_phdr *phdr; - elf = (struct elfhdr *)bufp; bufp += sizeof(struct elfhdr); /* First note is a place holder for cpu notes info. */ From ef23cf9a89a7aec19a29d548d1e219d436b23b6e Mon Sep 17 00:00:00 2001 From: zhengbin Date: Tue, 19 Nov 2019 14:14:31 +0800 Subject: [PATCH 023/645] powerpc/perf: Remove set but not used variable 'target' Fix gcc '-Wunused-but-set-variable' warning: arch/powerpc/perf/imc-pmu.c: In function trace_imc_event_init: arch/powerpc/perf/imc-pmu.c:1292:22: warning: variable target set but not used [-Wunused-but-set-variable] It is introduced by commit 012ae244845f ("powerpc/perf: Trace imc PMU functions"), but never used, so remove it. Reported-by: Hulk Robot Signed-off-by: zhengbin Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/1574144074-142032-3-git-send-email-zhengbin13@huawei.com --- arch/powerpc/perf/imc-pmu.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index a45d694a5d5d..00bb186caed9 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -1426,8 +1426,6 @@ static void trace_imc_event_del(struct perf_event *event, int flags) static int trace_imc_event_init(struct perf_event *event) { - struct task_struct *target; - if (event->attr.type != event->pmu->type) return -ENOENT; @@ -1458,7 +1456,6 @@ static int trace_imc_event_init(struct perf_event *event) mutex_unlock(&imc_global_refc.lock); event->hw.idx = -1; - target = event->hw.target; event->pmu->task_ctx_nr = perf_hw_context; event->destroy = reset_global_refc; From 18102e4bcc47f5b5ac70e2e4461d022c1ee6df24 Mon Sep 17 00:00:00 2001 From: zhengbin Date: Tue, 19 Nov 2019 14:14:34 +0800 Subject: [PATCH 024/645] powerpc/powernv: Remove set but not used variable 'parent' Fix gcc '-Wunused-but-set-variable' warning: arch/powerpc/platforms/powernv/pci-ioda.c: In function pnv_ioda_configure_pe: arch/powerpc/platforms/powernv/pci-ioda.c:867:18: warning: variable parent set but not used [-Wunused-but-set-variable] It is not used since commit b131a8425c34 ("powerpc/powernv: Set PELTV for compound PEs") Reported-by: Hulk Robot Signed-off-by: zhengbin Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/1574144074-142032-6-git-send-email-zhengbin13@huawei.com --- arch/powerpc/platforms/powernv/pci-ioda.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 023a4f987bb2..2b4ceb5e6ce4 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -894,7 +894,6 @@ int pnv_ioda_deconfigure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) { - struct pci_dev *parent; uint8_t bcomp, dcomp, fcomp; long rc, rid_end, rid; @@ -904,7 +903,6 @@ int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) dcomp = OPAL_IGNORE_RID_DEVICE_NUMBER; fcomp = OPAL_IGNORE_RID_FUNCTION_NUMBER; - parent = pe->pbus->self; if (pe->flags & PNV_IODA_PE_BUS_ALL) count = resource_size(&pe->pbus->busn_res); else @@ -925,12 +923,6 @@ int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) } rid_end = pe->rid + (count << 8); } else { -#ifdef CONFIG_PCI_IOV - if (pe->flags & PNV_IODA_PE_VF) - parent = pe->parent_dev; - else -#endif /* CONFIG_PCI_IOV */ - parent = pe->pdev->bus->self; bcomp = OpalPciBusAll; dcomp = OPAL_COMPARE_RID_DEVICE_NUMBER; fcomp = OPAL_COMPARE_RID_FUNCTION_NUMBER; From ccaea15296f9773abd43aaa17ee4b88848e4a505 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Fri, 31 Jul 2020 17:04:59 +0530 Subject: [PATCH 025/645] powerpc/vmemmap: Fix memory leak with vmemmap list allocation failures. If we fail to allocate vmemmap list, we don't keep track of allocated vmemmap block buf. Hence on section deactivate we skip vmemmap block buf free. This results in memory leak. Signed-off-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200731113500.248306-1-aneesh.kumar@linux.ibm.com --- arch/powerpc/mm/init_64.c | 35 ++++++++++++++++++++++++++++------- 1 file changed, 28 insertions(+), 7 deletions(-) diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 02e127fa5777..41b7da84030e 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -162,16 +162,16 @@ static __meminit struct vmemmap_backing * vmemmap_list_alloc(int node) return next++; } -static __meminit void vmemmap_list_populate(unsigned long phys, - unsigned long start, - int node) +static __meminit int vmemmap_list_populate(unsigned long phys, + unsigned long start, + int node) { struct vmemmap_backing *vmem_back; vmem_back = vmemmap_list_alloc(node); if (unlikely(!vmem_back)) { - WARN_ON(1); - return; + pr_debug("vmemap list allocation failed\n"); + return -ENOMEM; } vmem_back->phys = phys; @@ -179,6 +179,7 @@ static __meminit void vmemmap_list_populate(unsigned long phys, vmem_back->list = vmemmap_list; vmemmap_list = vmem_back; + return 0; } static bool altmap_cross_boundary(struct vmem_altmap *altmap, unsigned long start, @@ -199,6 +200,7 @@ static bool altmap_cross_boundary(struct vmem_altmap *altmap, unsigned long star int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap) { + bool altmap_alloc; unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift; /* Align to the page size of the linear mapping. */ @@ -228,13 +230,32 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, p = vmemmap_alloc_block_buf(page_size, node, altmap); if (!p) pr_debug("altmap block allocation failed, falling back to system memory"); + else + altmap_alloc = true; } - if (!p) + if (!p) { p = vmemmap_alloc_block_buf(page_size, node, NULL); + altmap_alloc = false; + } if (!p) return -ENOMEM; - vmemmap_list_populate(__pa(p), start, node); + if (vmemmap_list_populate(__pa(p), start, node)) { + /* + * If we don't populate vmemap list, we don't have + * the ability to free the allocated vmemmap + * pages in section_deactivate. Hence free them + * here. + */ + int nr_pfns = page_size >> PAGE_SHIFT; + unsigned long page_order = get_order(page_size); + + if (altmap_alloc) + vmem_altmap_free(altmap, nr_pfns); + else + free_pages((unsigned long)p, page_order); + return -ENOMEM; + } pr_debug(" * %016lx..%016lx allocated at %p\n", start, start + page_size, p); From 1c0a7ac0ec63ee626f669c9a4e278f6ae1dbfcf2 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Fri, 31 Jul 2020 17:05:00 +0530 Subject: [PATCH 026/645] powerpc/vmemmap: Don't warn if we don't find a mapping vmemmap list entry Now that we are handling vmemmap list allocation failure correctly, don't WARN in section deactivate when we don't find a mapping vmemmap list entry. Signed-off-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200731113500.248306-2-aneesh.kumar@linux.ibm.com --- arch/powerpc/mm/init_64.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 41b7da84030e..a8618f7d00a3 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -285,10 +285,8 @@ static unsigned long vmemmap_list_free(unsigned long start) vmem_back_prev = vmem_back; } - if (unlikely(!vmem_back)) { - WARN_ON(1); + if (unlikely(!vmem_back)) return 0; - } /* remove it from vmemmap_list */ if (vmem_back == vmemmap_list) /* remove head */ From 346427e668163e85cbbe14e4d9a2ddd49df1536c Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 4 Aug 2020 18:43:16 +0100 Subject: [PATCH 027/645] powerpc/oprofile: fix spelling mistake "contex" -> "context" There is a spelling mistake in a pr_debug message. Fix it. Signed-off-by: Colin Ian King Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200804174316.402425-1-colin.king@canonical.com --- arch/powerpc/oprofile/cell/spu_task_sync.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/oprofile/cell/spu_task_sync.c b/arch/powerpc/oprofile/cell/spu_task_sync.c index df59d0bb121f..489f993100d5 100644 --- a/arch/powerpc/oprofile/cell/spu_task_sync.c +++ b/arch/powerpc/oprofile/cell/spu_task_sync.c @@ -572,7 +572,7 @@ void spu_sync_buffer(int spu_num, unsigned int *samples, * samples are recorded. * No big deal -- so we just drop a few samples. */ - pr_debug("SPU_PROF: No cached SPU contex " + pr_debug("SPU_PROF: No cached SPU context " "for SPU #%d. Dropping samples.\n", spu_num); goto out; } From f6bac19cf65c5be21d14a0c9684c8f560f2096dd Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Tue, 4 Aug 2020 10:54:05 +1000 Subject: [PATCH 028/645] powerpc/powernv/smp: Fix spurious DBG() warning MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When building with W=1 we get the following warning: arch/powerpc/platforms/powernv/smp.c: In function ‘pnv_smp_cpu_kill_self’: arch/powerpc/platforms/powernv/smp.c:276:16: error: suggest braces around empty body in an ‘if’ statement [-Werror=empty-body] 276 | cpu, srr1); | ^ cc1: all warnings being treated as errors The full context is this block: if (srr1 && !generic_check_cpu_restart(cpu)) DBG("CPU%d Unexpected exit while offline srr1=%lx!\n", cpu, srr1); When building with DEBUG undefined DBG() expands to nothing and GCC emits the warning due to the lack of braces around an empty statement. Signed-off-by: Oliver O'Halloran Reviewed-by: Joel Stanley Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200804005410.146094-2-oohall@gmail.com --- arch/powerpc/platforms/powernv/smp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index b2ba3e95bda7..bbf361f23ae8 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -43,7 +43,7 @@ #include #define DBG(fmt...) udbg_printf(fmt) #else -#define DBG(fmt...) +#define DBG(fmt...) do { } while (0) #endif static void pnv_smp_setup_cpu(int cpu) From 8471c1dd93de9a2278d41c527b76291e4ace8f1c Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Tue, 4 Aug 2020 10:54:06 +1000 Subject: [PATCH 029/645] powerpc/powernv: Include asm/powernv.h from the local powernv.h The asm/powernv.h header provides prototypes for functions which need to be called by non-powernv platform code. Also include it in the powernv.h that's local to the platform directory to squash some warnings about non-static functions missing prototypes. Also include powernv.h since from opal-memcons.c since it has the prototypes for the memcons wrangling functions which are used for the opal and ultravisor msglog. Signed-off-by: Oliver O'Halloran Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200804005410.146094-3-oohall@gmail.com --- arch/powerpc/platforms/powernv/opal-msglog.c | 2 ++ arch/powerpc/platforms/powernv/powernv.h | 7 +++++++ 2 files changed, 9 insertions(+) diff --git a/arch/powerpc/platforms/powernv/opal-msglog.c b/arch/powerpc/platforms/powernv/opal-msglog.c index d26da19a611f..d3b6e135c18b 100644 --- a/arch/powerpc/platforms/powernv/opal-msglog.c +++ b/arch/powerpc/platforms/powernv/opal-msglog.c @@ -12,6 +12,8 @@ #include #include +#include "powernv.h" + /* OPAL in-memory console. Defined in OPAL source at core/console.c */ struct memcons { __be64 magic; diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h index 1aa51c4fa904..11df4e16a1cc 100644 --- a/arch/powerpc/platforms/powernv/powernv.h +++ b/arch/powerpc/platforms/powernv/powernv.h @@ -2,6 +2,13 @@ #ifndef _POWERNV_H #define _POWERNV_H +/* + * There's various hacks scattered throughout the generic powerpc arch code + * that needs to call into powernv platform stuff. The prototypes for those + * functions are in asm/powernv.h + */ +#include + #ifdef CONFIG_SMP extern void pnv_smp_init(void); #else From 3b70464aa78917e88c1d4bfc2100c344c0eda8e0 Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Tue, 4 Aug 2020 10:54:07 +1000 Subject: [PATCH 030/645] powerpc/powernv: Staticify functions without prototypes There's a few scattered in the powernv platform. Signed-off-by: Oliver O'Halloran Reviewed-by: Joel Stanley Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200804005410.146094-4-oohall@gmail.com --- arch/powerpc/platforms/powernv/eeh-powernv.c | 4 ++-- arch/powerpc/platforms/powernv/rng.c | 2 +- arch/powerpc/platforms/powernv/vas-window.c | 9 ++++----- 3 files changed, 7 insertions(+), 8 deletions(-) diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index 9af8c3b98853..663bd69ac51b 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -38,7 +38,7 @@ static int eeh_event_irq = -EINVAL; -void pnv_pcibios_bus_add_device(struct pci_dev *pdev) +static void pnv_pcibios_bus_add_device(struct pci_dev *pdev) { dev_dbg(&pdev->dev, "EEH: Setting up device\n"); eeh_probe_device(pdev); @@ -190,7 +190,7 @@ PNV_EEH_DBGFS_ENTRY(inbB, 0xE10); #endif /* CONFIG_DEBUG_FS */ -void pnv_eeh_enable_phbs(void) +static void pnv_eeh_enable_phbs(void) { struct pci_controller *hose; struct pnv_phb *phb; diff --git a/arch/powerpc/platforms/powernv/rng.c b/arch/powerpc/platforms/powernv/rng.c index 8035caf6e297..72c25295c1c2 100644 --- a/arch/powerpc/platforms/powernv/rng.c +++ b/arch/powerpc/platforms/powernv/rng.c @@ -65,7 +65,7 @@ int powernv_get_random_real_mode(unsigned long *v) return 1; } -int powernv_get_random_darn(unsigned long *v) +static int powernv_get_random_darn(unsigned long *v) { unsigned long val; diff --git a/arch/powerpc/platforms/powernv/vas-window.c b/arch/powerpc/platforms/powernv/vas-window.c index 6434f9cb5aed..5f5fe63a3d1c 100644 --- a/arch/powerpc/platforms/powernv/vas-window.c +++ b/arch/powerpc/platforms/powernv/vas-window.c @@ -186,7 +186,7 @@ static void unmap_winctx_mmio_bars(struct vas_window *window) * OS/User Window Context (UWC) MMIO Base Address Region for the given window. * Map these bus addresses and save the mapped kernel addresses in @window. */ -int map_winctx_mmio_bars(struct vas_window *window) +static int map_winctx_mmio_bars(struct vas_window *window) { int len; u64 start; @@ -214,7 +214,7 @@ int map_winctx_mmio_bars(struct vas_window *window) * registers are not sequential. And, we can only write to offsets * with valid registers. */ -void reset_window_regs(struct vas_window *window) +static void reset_window_regs(struct vas_window *window) { write_hvwc_reg(window, VREG(LPID), 0ULL); write_hvwc_reg(window, VREG(PID), 0ULL); @@ -357,7 +357,8 @@ static void init_rsvd_tx_buf_count(struct vas_window *txwin, * as a one-time task? That could work for NX but what about other * receivers? Let the receivers tell us the rx-fifo buffers for now. */ -int init_winctx_regs(struct vas_window *window, struct vas_winctx *winctx) +static void init_winctx_regs(struct vas_window *window, + struct vas_winctx *winctx) { u64 val; int fifo_size; @@ -499,8 +500,6 @@ int init_winctx_regs(struct vas_window *window, struct vas_winctx *winctx) val = SET_FIELD(VAS_WINCTL_NX_WIN, val, winctx->nx_win); val = SET_FIELD(VAS_WINCTL_OPEN, val, 1); write_hvwc_reg(window, VREG(WINCTL), val); - - return 0; } static void vas_release_window_id(struct ida *ida, int winid) From fb248c3121af713f31736af359608491544cfc23 Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Tue, 4 Aug 2020 10:54:08 +1000 Subject: [PATCH 031/645] powerpc/powernv: Fix spurious kerneldoc warnings in opal-prd.c Comments opening with /** are parsed by kerneldoc and this causes the following warning to be printed: arch/powerpc/platforms/powernv/opal-prd.c:31: warning: cannot understand function prototype: 'struct opal_prd_msg_queue_item ' opal_prd_mesg_queue_item is an internal data structure so there's no real need for it to be documented at all. Fix up the comment to squash the warning. Signed-off-by: Oliver O'Halloran Reviewed-by: Joel Stanley Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200804005410.146094-5-oohall@gmail.com --- arch/powerpc/platforms/powernv/opal-prd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/platforms/powernv/opal-prd.c b/arch/powerpc/platforms/powernv/opal-prd.c index 45f4223a790f..deddaebf8c14 100644 --- a/arch/powerpc/platforms/powernv/opal-prd.c +++ b/arch/powerpc/platforms/powernv/opal-prd.c @@ -24,7 +24,7 @@ #include -/** +/* * The msg member must be at the end of the struct, as it's followed by the * message data. */ From 3ced132a055c4e5046d21732393ae6848ff309e0 Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Tue, 4 Aug 2020 10:54:10 +1000 Subject: [PATCH 032/645] powerpc/nx: Don't pack struct coprocessor_request_block MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Building with W=1 results in the following warning: In file included from arch/powerpc/platforms/powernv/vas-fault.c:16: ./arch/powerpc/include/asm/icswx.h:159:1: error: alignment 1 of ‘struct coprocessor_request_block’ is less than 16 [-Werror=packed-not-aligned] 159 | } __packed; | ^ ./arch/powerpc/include/asm/icswx.h:159:1: error: alignment 1 of ‘struct coprocessor_request_block’ is less than 16 [-Werror=packed-not-aligned] ./arch/powerpc/include/asm/icswx.h:159:1: error: alignment 1 of ‘struct coprocessor_request_block’ is less than 16 [-Werror=packed-not-aligned] ./arch/powerpc/include/asm/icswx.h:159:1: error: alignment 1 of ‘struct coprocessor_request_block’ is less than 16 [-Werror=packed-not-aligned] cc1: all warnings being treated as errors This happens because coprocessor_request_block includes several sub-structures with an alignment specified using the __aligned(XX) attribute. The problem comes from coprocessor_request_block having the __packed attribute. Packing the structure causes the preferred alignment of the nested structures to be ignored and we get the warnings as a result. This isn't a problem in practice since the struct is defined with explicit padding in the form of reserved fields, but we'd like to get rid of the spurious warnings. The simplest solution is to remove the packed attribute and use a BUILD_BUG_ON() to ensure the struct is the correct (expected by HW) size compile time. Also add a __aligned(128) to the request block structure since Book4 for P8 suggests the HW requires it to be aligned to a 128 byte boundary. There's a similar requirement for P9 since the COPY and PASTE instructions used to invoke VAS/NX accelerators operates on a cache line boundary. Signed-off-by: Oliver O'Halloran Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200804005410.146094-7-oohall@gmail.com --- arch/powerpc/include/asm/icswx.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/include/asm/icswx.h b/arch/powerpc/include/asm/icswx.h index b0c70a35fd0e..f6599ccb3012 100644 --- a/arch/powerpc/include/asm/icswx.h +++ b/arch/powerpc/include/asm/icswx.h @@ -156,8 +156,7 @@ struct coprocessor_request_block { u8 reserved[32]; struct coprocessor_status_block csb; -} __packed; - +} __aligned(128); /* RFC02167 Initiate Coprocessor Instructions document * Chapter 8.2.1.1.1 RS @@ -188,6 +187,9 @@ static inline int icswx(__be32 ccw, struct coprocessor_request_block *crb) __be64 ccw_reg = ccw; u32 cr; + /* NB: the same structures are used by VAS-NX */ + BUILD_BUG_ON(sizeof(*crb) != 128); + __asm__ __volatile__( PPC_ICSWX(%1,0,%2) "\n" "mfcr %0\n" From 5bdd89ad341959750df3955b7fa28410a7abcebe Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Tue, 25 Aug 2020 11:09:04 +0200 Subject: [PATCH 033/645] MIPS: SGI-IP27: No need for kmalloc.h SGI-IP27 is always cache coherent so we can use generic kmalloc.h and remove the ip27 specific one. Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/mach-ip27/kmalloc.h | 8 -------- 1 file changed, 8 deletions(-) delete mode 100644 arch/mips/include/asm/mach-ip27/kmalloc.h diff --git a/arch/mips/include/asm/mach-ip27/kmalloc.h b/arch/mips/include/asm/mach-ip27/kmalloc.h deleted file mode 100644 index 82c23ce2afa7..000000000000 --- a/arch/mips/include/asm/mach-ip27/kmalloc.h +++ /dev/null @@ -1,8 +0,0 @@ -#ifndef __ASM_MACH_IP27_KMALLOC_H -#define __ASM_MACH_IP27_KMALLOC_H - -/* - * All happy, no need to define ARCH_DMA_MINALIGN - */ - -#endif /* __ASM_MACH_IP27_KMALLOC_H */ From 942b14fb3e58fd994cf23cb67da0e5998e995b61 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Tue, 25 Aug 2020 11:09:05 +0200 Subject: [PATCH 034/645] MIPS: Loongson2ef: Remove specific mc146818rtc.h Loonson2ef's mc146818rtc.h is the same as the generic one -> remove it. Signed-off-by: Thomas Bogendoerfer Acked-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer --- .../asm/mach-loongson2ef/mc146818rtc.h | 36 ------------------- 1 file changed, 36 deletions(-) delete mode 100644 arch/mips/include/asm/mach-loongson2ef/mc146818rtc.h diff --git a/arch/mips/include/asm/mach-loongson2ef/mc146818rtc.h b/arch/mips/include/asm/mach-loongson2ef/mc146818rtc.h deleted file mode 100644 index 00d602629a55..000000000000 --- a/arch/mips/include/asm/mach-loongson2ef/mc146818rtc.h +++ /dev/null @@ -1,36 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 1998, 2001, 03, 07 by Ralf Baechle (ralf@linux-mips.org) - * - * RTC routines for PC style attached Dallas chip. - */ -#ifndef __ASM_MACH_LOONGSON2EF_MC146818RTC_H -#define __ASM_MACH_LOONGSON2EF_MC146818RTC_H - -#include - -#define RTC_PORT(x) (0x70 + (x)) -#define RTC_IRQ 8 - -static inline unsigned char CMOS_READ(unsigned long addr) -{ - outb_p(addr, RTC_PORT(0)); - return inb_p(RTC_PORT(1)); -} - -static inline void CMOS_WRITE(unsigned char data, unsigned long addr) -{ - outb_p(addr, RTC_PORT(0)); - outb_p(data, RTC_PORT(1)); -} - -#define RTC_ALWAYS_BCD 0 - -#ifndef mc146818_decode_year -#define mc146818_decode_year(year) ((year) < 70 ? (year) + 2000 : (year) + 1970) -#endif - -#endif /* __ASM_MACH_LOONGSON2EF_MC146818RTC_H */ From 518c0afb55ee3642b044a5238c66354c7b935974 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Tue, 25 Aug 2020 11:09:06 +0200 Subject: [PATCH 035/645] MIPS: Remove unused header file m48t37.h No users -> remove it. Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/m48t37.h | 36 ---------------------------------- 1 file changed, 36 deletions(-) delete mode 100644 arch/mips/include/asm/m48t37.h diff --git a/arch/mips/include/asm/m48t37.h b/arch/mips/include/asm/m48t37.h deleted file mode 100644 index 3687a02e692b..000000000000 --- a/arch/mips/include/asm/m48t37.h +++ /dev/null @@ -1,36 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Registers for the SGS-Thomson M48T37 Timekeeper RAM chip - */ -#ifndef _ASM_M48T37_H -#define _ASM_M48T37_H - -#include - -extern spinlock_t rtc_lock; - -struct m48t37_rtc { - volatile u8 pad[0x7ff0]; /* NVRAM */ - volatile u8 flags; - volatile u8 century; - volatile u8 alarm_sec; - volatile u8 alarm_min; - volatile u8 alarm_hour; - volatile u8 alarm_data; - volatile u8 interrupts; - volatile u8 watchdog; - volatile u8 control; - volatile u8 sec; - volatile u8 min; - volatile u8 hour; - volatile u8 day; - volatile u8 date; - volatile u8 month; - volatile u8 year; -}; - -#define M48T37_RTC_SET 0x80 -#define M48T37_RTC_STOPPED 0x80 -#define M48T37_RTC_READ 0x40 - -#endif /* _ASM_M48T37_H */ From aa9c45db018fadd8d15611ba403d4a8e7c6521a9 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Tue, 25 Aug 2020 11:09:07 +0200 Subject: [PATCH 036/645] MIPS: SGI-IP32: No need to include mc14818*.h Nothing needs the includes in ip32-setup.c. Signed-off-by: Thomas Bogendoerfer --- arch/mips/sgi-ip32/ip32-setup.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/mips/sgi-ip32/ip32-setup.c b/arch/mips/sgi-ip32/ip32-setup.c index 3abd1465ec02..8019dae1721a 100644 --- a/arch/mips/sgi-ip32/ip32-setup.c +++ b/arch/mips/sgi-ip32/ip32-setup.c @@ -12,12 +12,10 @@ #include #include #include -#include #include #include #include -#include #include #include #include From b064904c509decf9e038f29f903a2304851a913b Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 11 Aug 2020 11:16:51 +0200 Subject: [PATCH 037/645] s390/checksum: provide csum_ipv6_magic() This implementation needs only ~30% of the time to calculate the checksum compared to the generic variant. In addition the compiler also generates only ~30% of the instructions compared to the generic variant (on z14, compiled with march=z196). Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/checksum.h | 24 ++++++++++++++++++++++-- 1 file changed, 22 insertions(+), 2 deletions(-) diff --git a/arch/s390/include/asm/checksum.h b/arch/s390/include/asm/checksum.h index 6d01c96aeb5c..f4b42db5d007 100644 --- a/arch/s390/include/asm/checksum.h +++ b/arch/s390/include/asm/checksum.h @@ -13,6 +13,7 @@ #define _S390_CHECKSUM_H #include +#include /* * computes the checksum of a memory block at buff, length len, @@ -115,6 +116,25 @@ static inline __sum16 ip_compute_csum(const void *buff, int len) return csum_fold(csum_partial(buff, len, 0)); } +#define _HAVE_ARCH_IPV6_CSUM +static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr, + const struct in6_addr *daddr, + __u32 len, __u8 proto, __wsum csum) +{ + __u64 sum = (__force __u64)csum; + + sum += (__force __u32)saddr->s6_addr32[0]; + sum += (__force __u32)saddr->s6_addr32[1]; + sum += (__force __u32)saddr->s6_addr32[2]; + sum += (__force __u32)saddr->s6_addr32[3]; + sum += (__force __u32)daddr->s6_addr32[0]; + sum += (__force __u32)daddr->s6_addr32[1]; + sum += (__force __u32)daddr->s6_addr32[2]; + sum += (__force __u32)daddr->s6_addr32[3]; + sum += len; + sum += proto; + sum += (sum >> 32) | (sum << 32); + return csum_fold((__force __wsum)(sum >> 32)); +} + #endif /* _S390_CHECKSUM_H */ - - From bb4644b14accb05663847277002e3efa9fa3cd3b Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 11 Aug 2020 15:30:30 +0200 Subject: [PATCH 038/645] s390/checksum: rewrite csum_tcpudp_nofold() Rewrite csum_tcpudp_nofold() so that the generated code will not contain branches. The old implementation was also optimized for machines which came with "add logical with carry" instructions, however the compiler doesn't generate them anymore. This is most likely because those instructions are slower. However with the old code the compiler generates a lot of branches, which isn't too helpful usually. Therefore rewrite the code. In a tight loop this doesn't make any difference since the branch prediction unit does its job. Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/checksum.h | 22 +++++++--------------- 1 file changed, 7 insertions(+), 15 deletions(-) diff --git a/arch/s390/include/asm/checksum.h b/arch/s390/include/asm/checksum.h index f4b42db5d007..961c25c5124b 100644 --- a/arch/s390/include/asm/checksum.h +++ b/arch/s390/include/asm/checksum.h @@ -73,25 +73,17 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) * computes the checksum of the TCP/UDP pseudo-header * returns a 32-bit checksum */ -static inline __wsum -csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, - __wsum sum) +static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len, + __u8 proto, __wsum sum) { - __u32 csum = (__force __u32)sum; + __u64 csum = (__force __u64)sum; csum += (__force __u32)saddr; - if (csum < (__force __u32)saddr) - csum++; - csum += (__force __u32)daddr; - if (csum < (__force __u32)daddr) - csum++; - - csum += len + proto; - if (csum < len + proto) - csum++; - - return (__force __wsum)csum; + csum += len; + csum += proto; + csum += (csum >> 32) | (csum << 32); + return (__force __wsum)(csum >> 32); } /* From 614b4f5d0fa3f622cfcc899491d8a3e6af3d4dc5 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 11 Aug 2020 16:36:26 +0200 Subject: [PATCH 039/645] s390/checksum: make ip_fast_csum() faster Convert ip_fast_csum() so it doesn't call csum_partial(), but instead open code the checksum calculation. The problem with csum_partial() is that it makes use of the cksm instruction, which has high startup costs and therefore is only very fast if used on larger memory regions. IPv4 headers however are small in size (5-16 32-bit words). The open coded variant calculates the checksum in ~30% of the time compared to the old variant (z14, march=z196). Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/checksum.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/arch/s390/include/asm/checksum.h b/arch/s390/include/asm/checksum.h index 961c25c5124b..8bc6bed4715b 100644 --- a/arch/s390/include/asm/checksum.h +++ b/arch/s390/include/asm/checksum.h @@ -66,7 +66,18 @@ static inline __sum16 csum_fold(__wsum sum) */ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) { - return csum_fold(csum_partial(iph, ihl*4, 0)); + __u64 csum = 0; + __u32 *ptr = (u32 *)iph; + + csum += *ptr++; + csum += *ptr++; + csum += *ptr++; + csum += *ptr++; + ihl -= 4; + while (ihl--) + csum += *ptr++; + csum += (csum >> 32) | (csum << 32); + return csum_fold((__force __wsum)(csum >> 32)); } /* From 612ad0785dd5161dc311b10bd26038553a378386 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 11 Aug 2020 16:37:33 +0200 Subject: [PATCH 040/645] s390/checksum: have consistent calculations Use "|" instead of "+" within csum_fold() for consistency reasons, like in the rest of the file. Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/checksum.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/include/asm/checksum.h b/arch/s390/include/asm/checksum.h index 8bc6bed4715b..de97ae691060 100644 --- a/arch/s390/include/asm/checksum.h +++ b/arch/s390/include/asm/checksum.h @@ -54,7 +54,7 @@ static inline __sum16 csum_fold(__wsum sum) { u32 csum = (__force u32) sum; - csum += (csum >> 16) + (csum << 16); + csum += (csum >> 16) | (csum << 16); csum >>= 16; return (__force __sum16) ~csum; } From 98ad45fb58c14ebef6da27f91905e5b8fcff8686 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 11 Aug 2020 16:41:27 +0200 Subject: [PATCH 041/645] s390/checksum: coding style changes Add some coding style changes which hopefully make the code look a bit less odd. Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/checksum.h | 50 ++++++++++++++------------------ 1 file changed, 22 insertions(+), 28 deletions(-) diff --git a/arch/s390/include/asm/checksum.h b/arch/s390/include/asm/checksum.h index de97ae691060..c401a5fd3ad2 100644 --- a/arch/s390/include/asm/checksum.h +++ b/arch/s390/include/asm/checksum.h @@ -16,19 +16,18 @@ #include /* - * computes the checksum of a memory block at buff, length len, - * and adds in "sum" (32-bit) + * Computes the checksum of a memory block at buff, length len, + * and adds in "sum" (32-bit). * - * returns a 32-bit number suitable for feeding into itself - * or csum_tcpudp_magic + * Returns a 32-bit number suitable for feeding into itself + * or csum_tcpudp_magic. * - * this function must be called with even lengths, except - * for the last fragment, which may be odd + * This function must be called with even lengths, except + * for the last fragment, which may be odd. * - * it's best to have buff aligned on a 32-bit boundary + * It's best to have buff aligned on a 32-bit boundary. */ -static inline __wsum -csum_partial(const void *buff, int len, __wsum sum) +static inline __wsum csum_partial(const void *buff, int len, __wsum sum) { register unsigned long reg2 asm("2") = (unsigned long) buff; register unsigned long reg3 asm("3") = (unsigned long) len; @@ -40,15 +39,15 @@ csum_partial(const void *buff, int len, __wsum sum) return sum; } -static inline __wsum -csum_partial_copy_nocheck (const void *src, void *dst, int len, __wsum sum) +static inline __wsum csum_partial_copy_nocheck(const void *src, void *dst, + int len, __wsum sum) { - memcpy(dst,src,len); + memcpy(dst, src, len); return csum_partial(dst, len, sum); } /* - * Fold a partial checksum without adding pseudo headers + * Fold a partial checksum without adding pseudo headers. */ static inline __sum16 csum_fold(__wsum sum) { @@ -60,9 +59,8 @@ static inline __sum16 csum_fold(__wsum sum) } /* - * This is a version of ip_compute_csum() optimized for IP headers, - * which always checksum on 4 octet boundaries. - * + * This is a version of ip_compute_csum() optimized for IP headers, + * which always checksums on 4 octet boundaries. */ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) { @@ -81,8 +79,8 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) } /* - * computes the checksum of the TCP/UDP pseudo-header - * returns a 32-bit checksum + * Computes the checksum of the TCP/UDP pseudo-header. + * Returns a 32-bit checksum. */ static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __wsum sum) @@ -98,22 +96,18 @@ static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len, } /* - * computes the checksum of the TCP/UDP pseudo-header - * returns a 16-bit checksum, already complemented + * Computes the checksum of the TCP/UDP pseudo-header. + * Returns a 16-bit checksum, already complemented. */ - -static inline __sum16 -csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, - __wsum sum) +static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len, + __u8 proto, __wsum sum) { - return csum_fold(csum_tcpudp_nofold(saddr,daddr,len,proto,sum)); + return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum)); } /* - * this routine is used for miscellaneous IP-like checksums, mainly - * in icmp.c + * Used for miscellaneous IP-like checksums, mainly icmp. */ - static inline __sum16 ip_compute_csum(const void *buff, int len) { return csum_fold(csum_partial(buff, len, 0)); From 4bff8cb5450287e246d365b719148b2d9364c292 Mon Sep 17 00:00:00 2001 From: Sven Schnelle Date: Tue, 28 Apr 2020 09:52:23 +0200 Subject: [PATCH 042/645] s390: convert to GENERIC_VDSO Convert s390 to generic vDSO. There are a few special things on s390: - vDSO can be called without a stack frame - glibc did this in the past. So we need to allocate a stackframe on our own. - The former assembly code used stcke to get the TOD clock and applied time steering to it. We need to do the same in the new code. This is done in the architecture specific __arch_get_hw_counter function. The steering information is stored in an architecure specific area in the vDSO data. - CPUCLOCK_VIRT is now handled with a syscall fallback, which might be slower/less accurate than the old implementation. The getcpu() function stays as an assembly function because there is no generic implementation and the code is just a few lines. Performance number from my system do 100 mio gettimeofday() calls: Plain syscall: 8.6s Generic VDSO: 1.3s old ASM VDSO: 1s So it's a bit slower but still much faster than syscalls. Signed-off-by: Sven Schnelle Reviewed-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/Kconfig | 3 + arch/s390/include/asm/clocksource.h | 7 + arch/s390/include/asm/vdso.h | 25 +-- arch/s390/include/asm/vdso/clocksource.h | 8 + arch/s390/include/asm/vdso/data.h | 13 ++ arch/s390/include/asm/vdso/gettimeofday.h | 71 +++++++++ arch/s390/include/asm/vdso/processor.h | 7 + arch/s390/include/asm/vdso/vdso.h | 0 arch/s390/include/asm/vdso/vsyscall.h | 26 ++++ arch/s390/kernel/asm-offsets.c | 20 --- arch/s390/kernel/entry.S | 6 - arch/s390/kernel/setup.c | 1 - arch/s390/kernel/time.c | 66 ++------ arch/s390/kernel/vdso.c | 29 +--- arch/s390/kernel/vdso64/Makefile | 19 ++- arch/s390/kernel/vdso64/clock_getres.S | 50 ------ arch/s390/kernel/vdso64/clock_gettime.S | 163 -------------------- arch/s390/kernel/vdso64/gettimeofday.S | 71 --------- arch/s390/kernel/vdso64/vdso64_generic.c | 18 +++ arch/s390/kernel/vdso64/vdso_user_wrapper.S | 38 +++++ 20 files changed, 221 insertions(+), 420 deletions(-) create mode 100644 arch/s390/include/asm/clocksource.h create mode 100644 arch/s390/include/asm/vdso/clocksource.h create mode 100644 arch/s390/include/asm/vdso/data.h create mode 100644 arch/s390/include/asm/vdso/gettimeofday.h create mode 100644 arch/s390/include/asm/vdso/processor.h create mode 100644 arch/s390/include/asm/vdso/vdso.h create mode 100644 arch/s390/include/asm/vdso/vsyscall.h delete mode 100644 arch/s390/kernel/vdso64/clock_getres.S delete mode 100644 arch/s390/kernel/vdso64/clock_gettime.S delete mode 100644 arch/s390/kernel/vdso64/gettimeofday.S create mode 100644 arch/s390/kernel/vdso64/vdso64_generic.c create mode 100644 arch/s390/kernel/vdso64/vdso_user_wrapper.S diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 3d86e12e8e3c..8a6121f93709 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -73,6 +73,7 @@ config S390 select ARCH_HAS_STRICT_MODULE_RWX select ARCH_HAS_SYSCALL_WRAPPER select ARCH_HAS_UBSAN_SANITIZE_ALL + select ARCH_HAS_VDSO_DATA select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_INLINE_READ_LOCK select ARCH_INLINE_READ_LOCK_BH @@ -118,6 +119,7 @@ config S390 select GENERIC_CPU_AUTOPROBE select GENERIC_CPU_VULNERABILITIES select GENERIC_FIND_FIRST_BIT + select GENERIC_GETTIMEOFDAY select GENERIC_SMP_IDLE_THREAD select GENERIC_TIME_VSYSCALL select HAVE_ALIGNED_STRUCT_PAGE if SLUB @@ -149,6 +151,7 @@ config S390 select HAVE_FUNCTION_TRACER select HAVE_FUTEX_CMPXCHG if FUTEX select HAVE_GCC_PLUGINS + select HAVE_GENERIC_VDSO select HAVE_KERNEL_BZIP2 select HAVE_KERNEL_GZIP select HAVE_KERNEL_LZ4 diff --git a/arch/s390/include/asm/clocksource.h b/arch/s390/include/asm/clocksource.h new file mode 100644 index 000000000000..03434369fce4 --- /dev/null +++ b/arch/s390/include/asm/clocksource.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* s390-specific clocksource additions */ + +#ifndef _ASM_S390_CLOCKSOURCE_H +#define _ASM_S390_CLOCKSOURCE_H + +#endif /* _ASM_S390_CLOCKSOURCE_H */ diff --git a/arch/s390/include/asm/vdso.h b/arch/s390/include/asm/vdso.h index 0cd085cdeb4f..82f86b3c394b 100644 --- a/arch/s390/include/asm/vdso.h +++ b/arch/s390/include/asm/vdso.h @@ -2,6 +2,8 @@ #ifndef __S390_VDSO_H__ #define __S390_VDSO_H__ +#include + /* Default link addresses for the vDSOs */ #define VDSO32_LBASE 0 #define VDSO64_LBASE 0 @@ -18,30 +20,7 @@ * itself and may change without notice. */ -struct vdso_data { - __u64 tb_update_count; /* Timebase atomicity ctr 0x00 */ - __u64 xtime_tod_stamp; /* TOD clock for xtime 0x08 */ - __u64 xtime_clock_sec; /* Kernel time 0x10 */ - __u64 xtime_clock_nsec; /* 0x18 */ - __u64 xtime_coarse_sec; /* Coarse kernel time 0x20 */ - __u64 xtime_coarse_nsec; /* 0x28 */ - __u64 wtom_clock_sec; /* Wall to monotonic clock 0x30 */ - __u64 wtom_clock_nsec; /* 0x38 */ - __u64 wtom_coarse_sec; /* Coarse wall to monotonic 0x40 */ - __u64 wtom_coarse_nsec; /* 0x48 */ - __u32 tz_minuteswest; /* Minutes west of Greenwich 0x50 */ - __u32 tz_dsttime; /* Type of dst correction 0x54 */ - __u32 ectg_available; /* ECTG instruction present 0x58 */ - __u32 tk_mult; /* Mult. used for xtime_nsec 0x5c */ - __u32 tk_shift; /* Shift used for xtime_nsec 0x60 */ - __u32 ts_dir; /* TOD steering direction 0x64 */ - __u64 ts_end; /* TOD steering end 0x68 */ - __u32 hrtimer_res; /* hrtimer resolution 0x70 */ -}; - struct vdso_per_cpu_data { - __u64 ectg_timer_base; - __u64 ectg_user_time; /* * Note: node_id and cpu_nr must be at adjacent memory locations. * VDSO userspace must read both values with a single instruction. diff --git a/arch/s390/include/asm/vdso/clocksource.h b/arch/s390/include/asm/vdso/clocksource.h new file mode 100644 index 000000000000..a93eda0ce7bb --- /dev/null +++ b/arch/s390/include/asm/vdso/clocksource.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_VDSO_CLOCKSOURCE_H +#define __ASM_VDSO_CLOCKSOURCE_H + +#define VDSO_ARCH_CLOCKMODES \ + VDSO_CLOCKMODE_TOD + +#endif /* __ASM_VDSO_CLOCKSOURCE_H */ diff --git a/arch/s390/include/asm/vdso/data.h b/arch/s390/include/asm/vdso/data.h new file mode 100644 index 000000000000..7b3cdb4a5f48 --- /dev/null +++ b/arch/s390/include/asm/vdso/data.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __S390_ASM_VDSO_DATA_H +#define __S390_ASM_VDSO_DATA_H + +#include +#include + +struct arch_vdso_data { + __u64 tod_steering_delta; + __u64 tod_steering_end; +}; + +#endif /* __S390_ASM_VDSO_DATA_H */ diff --git a/arch/s390/include/asm/vdso/gettimeofday.h b/arch/s390/include/asm/vdso/gettimeofday.h new file mode 100644 index 000000000000..bf123065ad3b --- /dev/null +++ b/arch/s390/include/asm/vdso/gettimeofday.h @@ -0,0 +1,71 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef ASM_VDSO_GETTIMEOFDAY_H +#define ASM_VDSO_GETTIMEOFDAY_H + +#define VDSO_HAS_TIME 1 + +#define VDSO_HAS_CLOCK_GETRES 1 + +#include +#include +#include +#include + +#define vdso_calc_delta __arch_vdso_calc_delta +static __always_inline u64 __arch_vdso_calc_delta(u64 cycles, u64 last, u64 mask, u32 mult) +{ + return (cycles - last) * mult; +} + +static __always_inline const struct vdso_data *__arch_get_vdso_data(void) +{ + return _vdso_data; +} + +static inline u64 __arch_get_hw_counter(s32 clock_mode, const struct vdso_data *vd) +{ + const struct vdso_data *vdso = __arch_get_vdso_data(); + u64 adj, now; + + now = get_tod_clock(); + adj = vdso->arch_data.tod_steering_end - now; + if (unlikely((s64) adj > 0)) + now += (vdso->arch_data.tod_steering_delta < 0) ? (adj >> 15) : -(adj >> 15); + return now; +} + +static __always_inline +long clock_gettime_fallback(clockid_t clkid, struct __kernel_timespec *ts) +{ + register unsigned long r1 __asm__("r1") = __NR_clock_gettime; + register unsigned long r2 __asm__("r2") = (unsigned long)clkid; + register void *r3 __asm__("r3") = ts; + + asm ("svc 0\n" : "+d" (r2) : "d" (r1), "d" (r3) : "cc", "memory"); + return r2; +} + +static __always_inline +long gettimeofday_fallback(register struct __kernel_old_timeval *tv, + register struct timezone *tz) +{ + register unsigned long r1 __asm__("r1") = __NR_gettimeofday; + register unsigned long r2 __asm__("r2") = (unsigned long)tv; + register void *r3 __asm__("r3") = tz; + + asm ("svc 0\n" : "+d" (r2) : "d" (r1), "d" (r3) : "cc", "memory"); + return r2; +} + +static __always_inline +long clock_getres_fallback(clockid_t clkid, struct __kernel_timespec *ts) +{ + register unsigned long r1 __asm__("r1") = __NR_clock_getres; + register unsigned long r2 __asm__("r2") = (unsigned long)clkid; + register void *r3 __asm__("r3") = ts; + + asm ("svc 0\n" : "+d" (r2) : "d" (r1), "d" (r3) : "cc", "memory"); + return r2; +} + +#endif diff --git a/arch/s390/include/asm/vdso/processor.h b/arch/s390/include/asm/vdso/processor.h new file mode 100644 index 000000000000..cfcc3e117c4c --- /dev/null +++ b/arch/s390/include/asm/vdso/processor.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __ASM_VDSO_PROCESSOR_H +#define __ASM_VDSO_PROCESSOR_H + +#define cpu_relax() barrier() + +#endif /* __ASM_VDSO_PROCESSOR_H */ diff --git a/arch/s390/include/asm/vdso/vdso.h b/arch/s390/include/asm/vdso/vdso.h new file mode 100644 index 000000000000..e69de29bb2d1 diff --git a/arch/s390/include/asm/vdso/vsyscall.h b/arch/s390/include/asm/vdso/vsyscall.h new file mode 100644 index 000000000000..6c67c08cefdd --- /dev/null +++ b/arch/s390/include/asm/vdso/vsyscall.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_VDSO_VSYSCALL_H +#define __ASM_VDSO_VSYSCALL_H + +#ifndef __ASSEMBLY__ + +#include +#include +#include +#include +/* + * Update the vDSO data page to keep in sync with kernel timekeeping. + */ + +static __always_inline struct vdso_data *__s390_get_k_vdso_data(void) +{ + return vdso_data; +} +#define __arch_get_k_vdso_data __s390_get_k_vdso_data + +/* The asm-generic header needs to be included after the definitions above */ +#include + +#endif /* !__ASSEMBLY__ */ + +#endif /* __ASM_VDSO_VSYSCALL_H */ diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index 5d8cc1864566..ece58f2217cb 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -59,26 +59,6 @@ int main(void) OFFSET(__SF_SIE_REASON, stack_frame, empty1[2]); OFFSET(__SF_SIE_FLAGS, stack_frame, empty1[3]); BLANK(); - /* timeval/timezone offsets for use by vdso */ - OFFSET(__VDSO_UPD_COUNT, vdso_data, tb_update_count); - OFFSET(__VDSO_XTIME_STAMP, vdso_data, xtime_tod_stamp); - OFFSET(__VDSO_XTIME_SEC, vdso_data, xtime_clock_sec); - OFFSET(__VDSO_XTIME_NSEC, vdso_data, xtime_clock_nsec); - OFFSET(__VDSO_XTIME_CRS_SEC, vdso_data, xtime_coarse_sec); - OFFSET(__VDSO_XTIME_CRS_NSEC, vdso_data, xtime_coarse_nsec); - OFFSET(__VDSO_WTOM_SEC, vdso_data, wtom_clock_sec); - OFFSET(__VDSO_WTOM_NSEC, vdso_data, wtom_clock_nsec); - OFFSET(__VDSO_WTOM_CRS_SEC, vdso_data, wtom_coarse_sec); - OFFSET(__VDSO_WTOM_CRS_NSEC, vdso_data, wtom_coarse_nsec); - OFFSET(__VDSO_TIMEZONE, vdso_data, tz_minuteswest); - OFFSET(__VDSO_ECTG_OK, vdso_data, ectg_available); - OFFSET(__VDSO_TK_MULT, vdso_data, tk_mult); - OFFSET(__VDSO_TK_SHIFT, vdso_data, tk_shift); - OFFSET(__VDSO_TS_DIR, vdso_data, ts_dir); - OFFSET(__VDSO_TS_END, vdso_data, ts_end); - OFFSET(__VDSO_CLOCK_REALTIME_RES, vdso_data, hrtimer_res); - OFFSET(__VDSO_ECTG_BASE, vdso_per_cpu_data, ectg_timer_base); - OFFSET(__VDSO_ECTG_USER, vdso_per_cpu_data, ectg_user_time); OFFSET(__VDSO_GETCPU_VAL, vdso_per_cpu_data, getcpu_val); BLANK(); /* constants used by the vdso */ diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 23edf196d3dc..86235919c2d1 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -435,10 +435,8 @@ ENTRY(system_call) jz .Lsysc_skip_fpu brasl %r14,load_fpu_regs .Lsysc_skip_fpu: - lg %r14,__LC_VDSO_PER_CPU mvc __LC_RETURN_PSW(16),__PT_PSW(%r11) stpt __LC_EXIT_TIMER - mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER lmg %r0,%r15,__PT_R0(%r11) b __LC_RETURN_LPSWE @@ -797,13 +795,11 @@ ENTRY(io_int_handler) TRACE_IRQS_ON 0: #endif - lg %r14,__LC_VDSO_PER_CPU mvc __LC_RETURN_PSW(16),__PT_PSW(%r11) tm __PT_PSW+1(%r11),0x01 # returning to user ? jno .Lio_exit_kernel BPEXIT __TI_flags(%r12),_TIF_ISOLATE_BP stpt __LC_EXIT_TIMER - mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER .Lio_exit_kernel: lmg %r0,%r15,__PT_R0(%r11) b __LC_RETURN_LPSWE @@ -1213,14 +1209,12 @@ ENTRY(mcck_int_handler) brasl %r14,s390_handle_mcck TRACE_IRQS_ON .Lmcck_return: - lg %r14,__LC_VDSO_PER_CPU lmg %r0,%r10,__PT_R0(%r11) mvc __LC_RETURN_MCCK_PSW(16),__PT_PSW(%r11) # move return PSW tm __LC_RETURN_MCCK_PSW+1,0x01 # returning to user ? jno 0f BPEXIT __TI_flags(%r12),_TIF_ISOLATE_BP stpt __LC_EXIT_TIMER - mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER 0: lmg %r11,%r15,__PT_R11(%r11) b __LC_RETURN_MCCK_LPSWE diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index e600f6953d7c..dfa45027cb47 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -402,7 +402,6 @@ static void __init setup_lowcore_dat_off(void) memcpy(lc->alt_stfle_fac_list, S390_lowcore.alt_stfle_fac_list, sizeof(lc->alt_stfle_fac_list)); nmi_alloc_boot_cpu(lc); - vdso_alloc_boot_cpu(lc); lc->sync_enter_timer = S390_lowcore.sync_enter_timer; lc->async_enter_timer = S390_lowcore.async_enter_timer; lc->exit_timer = S390_lowcore.exit_timer; diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index 513e59d08a55..bc806e1547d6 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -41,6 +41,9 @@ #include #include #include +#include +#include +#include #include #include #include @@ -84,7 +87,7 @@ void __init time_early_init(void) /* Initialize TOD steering parameters */ tod_steering_end = *(unsigned long long *) &tod_clock_base[1]; - vdso_data->ts_end = tod_steering_end; + vdso_data->arch_data.tod_steering_end = tod_steering_end; if (!test_facility(28)) return; @@ -257,6 +260,7 @@ static struct clocksource clocksource_tod = { .mult = 1000, .shift = 12, .flags = CLOCK_SOURCE_IS_CONTINUOUS, + .vdso_clock_mode = VDSO_CLOCKMODE_TOD, }; struct clocksource * __init clocksource_default_clock(void) @@ -264,56 +268,6 @@ struct clocksource * __init clocksource_default_clock(void) return &clocksource_tod; } -void update_vsyscall(struct timekeeper *tk) -{ - u64 nsecps; - - if (tk->tkr_mono.clock != &clocksource_tod) - return; - - /* Make userspace gettimeofday spin until we're done. */ - ++vdso_data->tb_update_count; - smp_wmb(); - vdso_data->xtime_tod_stamp = tk->tkr_mono.cycle_last; - vdso_data->xtime_clock_sec = tk->xtime_sec; - vdso_data->xtime_clock_nsec = tk->tkr_mono.xtime_nsec; - vdso_data->wtom_clock_sec = - tk->xtime_sec + tk->wall_to_monotonic.tv_sec; - vdso_data->wtom_clock_nsec = tk->tkr_mono.xtime_nsec + - + ((u64) tk->wall_to_monotonic.tv_nsec << tk->tkr_mono.shift); - nsecps = (u64) NSEC_PER_SEC << tk->tkr_mono.shift; - while (vdso_data->wtom_clock_nsec >= nsecps) { - vdso_data->wtom_clock_nsec -= nsecps; - vdso_data->wtom_clock_sec++; - } - - vdso_data->xtime_coarse_sec = tk->xtime_sec; - vdso_data->xtime_coarse_nsec = - (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); - vdso_data->wtom_coarse_sec = - vdso_data->xtime_coarse_sec + tk->wall_to_monotonic.tv_sec; - vdso_data->wtom_coarse_nsec = - vdso_data->xtime_coarse_nsec + tk->wall_to_monotonic.tv_nsec; - while (vdso_data->wtom_coarse_nsec >= NSEC_PER_SEC) { - vdso_data->wtom_coarse_nsec -= NSEC_PER_SEC; - vdso_data->wtom_coarse_sec++; - } - - vdso_data->tk_mult = tk->tkr_mono.mult; - vdso_data->tk_shift = tk->tkr_mono.shift; - vdso_data->hrtimer_res = hrtimer_resolution; - smp_wmb(); - ++vdso_data->tb_update_count; -} - -extern struct timezone sys_tz; - -void update_vsyscall_tz(void) -{ - vdso_data->tz_minuteswest = sys_tz.tz_minuteswest; - vdso_data->tz_dsttime = sys_tz.tz_dsttime; -} - /* * Initialize the TOD clock and the CPU timer of * the boot cpu. @@ -431,7 +385,6 @@ static void clock_sync_global(unsigned long long delta) /* Epoch overflow */ tod_clock_base[0]++; /* Adjust TOD steering parameters. */ - vdso_data->tb_update_count++; now = get_tod_clock(); adj = tod_steering_end - now; if (unlikely((s64) adj >= 0)) @@ -443,9 +396,8 @@ static void clock_sync_global(unsigned long long delta) panic("TOD clock sync offset %lli is too large to drift\n", tod_steering_delta); tod_steering_end = now + (abs(tod_steering_delta) << 15); - vdso_data->ts_dir = (tod_steering_delta < 0) ? 0 : 1; - vdso_data->ts_end = tod_steering_end; - vdso_data->tb_update_count++; + vdso_data->arch_data.tod_steering_end = tod_steering_end; + /* Update LPAR offset. */ if (ptff_query(PTFF_QTO) && ptff(&qto, sizeof(qto), PTFF_QTO) == 0) lpar_offset = qto.tod_epoch_difference; @@ -586,7 +538,7 @@ void stp_queue_work(void) static int stp_sync_clock(void *data) { struct clock_sync_data *sync = data; - unsigned long long clock_delta; + unsigned long long clock_delta, flags; static int first; int rc; @@ -599,6 +551,7 @@ static int stp_sync_clock(void *data) if (stp_info.todoff[0] || stp_info.todoff[1] || stp_info.todoff[2] || stp_info.todoff[3] || stp_info.tmd != 2) { + flags = vdso_update_begin(); rc = chsc_sstpc(stp_page, STP_OP_SYNC, 0, &clock_delta); if (rc == 0) { @@ -609,6 +562,7 @@ static int stp_sync_clock(void *data) if (rc == 0 && stp_info.tmd != 2) rc = -EAGAIN; } + vdso_update_end(flags); } sync->in_sync = rc ? -EAGAIN : 1; xchg(&first, 0); diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c index c4baefaa6e34..f9da5b149141 100644 --- a/arch/s390/kernel/vdso.c +++ b/arch/s390/kernel/vdso.c @@ -20,6 +20,8 @@ #include #include #include +#include +#include #include #include #include @@ -96,35 +98,12 @@ static union { struct vdso_data data; u8 page[PAGE_SIZE]; } vdso_data_store __page_aligned_data; -struct vdso_data *vdso_data = &vdso_data_store.data; - -/* - * Setup vdso data page. - */ -static void __init vdso_init_data(struct vdso_data *vd) -{ - vd->ectg_available = test_facility(31); -} - +struct vdso_data *vdso_data = (struct vdso_data *)&vdso_data_store.data; /* * Allocate/free per cpu vdso data. */ #define SEGMENT_ORDER 2 -/* - * The initial vdso_data structure for the boot CPU. Eventually - * it is replaced with a properly allocated structure in vdso_init. - * This is necessary because a valid S390_lowcore.vdso_per_cpu_data - * pointer is required to be able to return from an interrupt or - * program check. See the exit paths in entry.S. - */ -struct vdso_data boot_vdso_data __initdata; - -void __init vdso_alloc_boot_cpu(struct lowcore *lowcore) -{ - lowcore->vdso_per_cpu_data = (unsigned long) &boot_vdso_data; -} - int vdso_alloc_per_cpu(struct lowcore *lowcore) { unsigned long segment_table, page_table, page_frame; @@ -246,8 +225,6 @@ static int __init vdso_init(void) { int i; - vdso_init_data(vdso_data); - /* Calculate the size of the 64 bit vDSO */ vdso64_pages = ((&vdso64_end - &vdso64_start + PAGE_SIZE - 1) >> PAGE_SHIFT) + 1; diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile index 4a66a1cb919b..f1c0570780d1 100644 --- a/arch/s390/kernel/vdso64/Makefile +++ b/arch/s390/kernel/vdso64/Makefile @@ -1,14 +1,20 @@ # SPDX-License-Identifier: GPL-2.0 -# List of files in the vdso, has to be asm only for now +# List of files in the vdso KCOV_INSTRUMENT := n +ARCH_REL_TYPE_ABS := R_390_COPY|R_390_GLOB_DAT|R_390_JMP_SLOT|R_390_RELATIVE +ARCH_REL_TYPE_ABS += R_390_GOT|R_390_PLT -obj-vdso64 = gettimeofday.o clock_getres.o clock_gettime.o note.o getcpu.o +include $(srctree)/lib/vdso/Makefile +obj-vdso64 = vdso_user_wrapper.o note.o getcpu.o +obj-cvdso64 = vdso64_generic.o +CFLAGS_REMOVE_vdso64_generic.o = -pg $(CC_FLAGS_FTRACE) $(CC_FLAGS_EXPOLINE) # Build rules -targets := $(obj-vdso64) vdso64.so vdso64.so.dbg +targets := $(obj-vdso64) $(obj-cvdso64) vdso64.so vdso64.so.dbg obj-vdso64 := $(addprefix $(obj)/, $(obj-vdso64)) +obj-cvdso64 := $(addprefix $(obj)/, $(obj-cvdso64)) KBUILD_AFLAGS += -DBUILD_VDSO KBUILD_CFLAGS += -DBUILD_VDSO @@ -37,7 +43,7 @@ KASAN_SANITIZE := n $(obj)/vdso64_wrapper.o : $(obj)/vdso64.so # link rule for the .so file, .lds has to be first -$(obj)/vdso64.so.dbg: $(obj)/vdso64.lds $(obj-vdso64) FORCE +$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) $(obj-cvdso64) FORCE $(call if_changed,ld) # strip rule for the .so file @@ -49,9 +55,14 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE $(obj-vdso64): %.o: %.S FORCE $(call if_changed_dep,vdso64as) +$(obj-cvdso64): %.o: %.c FORCE + $(call if_changed_dep,vdso64cc) + # actual build commands quiet_cmd_vdso64as = VDSO64A $@ cmd_vdso64as = $(CC) $(a_flags) -c -o $@ $< +quiet_cmd_vdso64cc = VDSO64C $@ + cmd_vdso64cc = $(CC) $(c_flags) -c -o $@ $< # install commands for the unstripped file quiet_cmd_vdso_install = INSTALL $@ diff --git a/arch/s390/kernel/vdso64/clock_getres.S b/arch/s390/kernel/vdso64/clock_getres.S deleted file mode 100644 index 0c79caa32b59..000000000000 --- a/arch/s390/kernel/vdso64/clock_getres.S +++ /dev/null @@ -1,50 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Userland implementation of clock_getres() for 64 bits processes in a - * s390 kernel for use in the vDSO - * - * Copyright IBM Corp. 2008 - * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) - */ -#include -#include -#include -#include - - .text - .align 4 - .globl __kernel_clock_getres - .type __kernel_clock_getres,@function -__kernel_clock_getres: - CFI_STARTPROC - larl %r1,3f - lg %r0,0(%r1) - cghi %r2,__CLOCK_REALTIME_COARSE - je 0f - cghi %r2,__CLOCK_MONOTONIC_COARSE - je 0f - larl %r1,_vdso_data - llgf %r0,__VDSO_CLOCK_REALTIME_RES(%r1) - cghi %r2,__CLOCK_REALTIME - je 0f - cghi %r2,__CLOCK_MONOTONIC - je 0f - cghi %r2,__CLOCK_THREAD_CPUTIME_ID - je 0f - cghi %r2,-2 /* Per-thread CPUCLOCK with PID=0, VIRT=1 */ - jne 2f - larl %r5,_vdso_data - icm %r0,15,__LC_ECTG_OK(%r5) - jz 2f -0: ltgr %r3,%r3 - jz 1f /* res == NULL */ - xc 0(8,%r3),0(%r3) /* set tp->tv_sec to zero */ - stg %r0,8(%r3) /* store tp->tv_usec */ -1: lghi %r2,0 - br %r14 -2: lghi %r1,__NR_clock_getres /* fallback to svc */ - svc 0 - br %r14 - CFI_ENDPROC -3: .quad __CLOCK_COARSE_RES - .size __kernel_clock_getres,.-__kernel_clock_getres diff --git a/arch/s390/kernel/vdso64/clock_gettime.S b/arch/s390/kernel/vdso64/clock_gettime.S deleted file mode 100644 index 9d2ee79b90f2..000000000000 --- a/arch/s390/kernel/vdso64/clock_gettime.S +++ /dev/null @@ -1,163 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Userland implementation of clock_gettime() for 64 bits processes in a - * s390 kernel for use in the vDSO - * - * Copyright IBM Corp. 2008 - * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) - */ -#include -#include -#include -#include -#include - - .text - .align 4 - .globl __kernel_clock_gettime - .type __kernel_clock_gettime,@function -__kernel_clock_gettime: - CFI_STARTPROC - aghi %r15,-16 - CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD+16 - CFI_VAL_OFFSET 15, -STACK_FRAME_OVERHEAD - larl %r5,_vdso_data - cghi %r2,__CLOCK_REALTIME_COARSE - je 4f - cghi %r2,__CLOCK_REALTIME - je 5f - cghi %r2,-3 /* Per-thread CPUCLOCK with PID=0, VIRT=1 */ - je 9f - cghi %r2,__CLOCK_MONOTONIC_COARSE - je 3f - cghi %r2,__CLOCK_MONOTONIC - jne 12f - - /* CLOCK_MONOTONIC */ -0: lg %r4,__VDSO_UPD_COUNT(%r5) /* load update counter */ - tmll %r4,0x0001 /* pending update ? loop */ - jnz 0b - stcke 0(%r15) /* Store TOD clock */ - lgf %r2,__VDSO_TK_SHIFT(%r5) /* Timekeeper shift */ - lg %r0,__VDSO_WTOM_SEC(%r5) - lg %r1,1(%r15) - sg %r1,__VDSO_XTIME_STAMP(%r5) /* TOD - cycle_last */ - msgf %r1,__VDSO_TK_MULT(%r5) /* * tk->mult */ - alg %r1,__VDSO_WTOM_NSEC(%r5) - srlg %r1,%r1,0(%r2) /* >> tk->shift */ - clg %r4,__VDSO_UPD_COUNT(%r5) /* check update counter */ - jne 0b - larl %r5,13f -1: clg %r1,0(%r5) - jl 2f - slg %r1,0(%r5) - aghi %r0,1 - j 1b -2: stg %r0,0(%r3) /* store tp->tv_sec */ - stg %r1,8(%r3) /* store tp->tv_nsec */ - lghi %r2,0 - aghi %r15,16 - CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD - CFI_RESTORE 15 - br %r14 - - /* CLOCK_MONOTONIC_COARSE */ - CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD+16 - CFI_VAL_OFFSET 15, -STACK_FRAME_OVERHEAD -3: lg %r4,__VDSO_UPD_COUNT(%r5) /* load update counter */ - tmll %r4,0x0001 /* pending update ? loop */ - jnz 3b - lg %r0,__VDSO_WTOM_CRS_SEC(%r5) - lg %r1,__VDSO_WTOM_CRS_NSEC(%r5) - clg %r4,__VDSO_UPD_COUNT(%r5) /* check update counter */ - jne 3b - j 2b - - /* CLOCK_REALTIME_COARSE */ -4: lg %r4,__VDSO_UPD_COUNT(%r5) /* load update counter */ - tmll %r4,0x0001 /* pending update ? loop */ - jnz 4b - lg %r0,__VDSO_XTIME_CRS_SEC(%r5) - lg %r1,__VDSO_XTIME_CRS_NSEC(%r5) - clg %r4,__VDSO_UPD_COUNT(%r5) /* check update counter */ - jne 4b - j 7f - - /* CLOCK_REALTIME */ -5: lg %r4,__VDSO_UPD_COUNT(%r5) /* load update counter */ - tmll %r4,0x0001 /* pending update ? loop */ - jnz 5b - stcke 0(%r15) /* Store TOD clock */ - lg %r1,1(%r15) - lg %r0,__VDSO_TS_END(%r5) /* TOD steering end time */ - slgr %r0,%r1 /* now - ts_steering_end */ - ltgr %r0,%r0 /* past end of steering ? */ - jm 17f - srlg %r0,%r0,15 /* 1 per 2^16 */ - tm __VDSO_TS_DIR+3(%r5),0x01 /* steering direction? */ - jz 18f - lcgr %r0,%r0 /* negative TOD offset */ -18: algr %r1,%r0 /* add steering offset */ -17: lgf %r2,__VDSO_TK_SHIFT(%r5) /* Timekeeper shift */ - sg %r1,__VDSO_XTIME_STAMP(%r5) /* TOD - cycle_last */ - msgf %r1,__VDSO_TK_MULT(%r5) /* * tk->mult */ - alg %r1,__VDSO_XTIME_NSEC(%r5) /* + tk->xtime_nsec */ - srlg %r1,%r1,0(%r2) /* >> tk->shift */ - lg %r0,__VDSO_XTIME_SEC(%r5) /* tk->xtime_sec */ - clg %r4,__VDSO_UPD_COUNT(%r5) /* check update counter */ - jne 5b - larl %r5,13f -6: clg %r1,0(%r5) - jl 7f - slg %r1,0(%r5) - aghi %r0,1 - j 6b -7: stg %r0,0(%r3) /* store tp->tv_sec */ - stg %r1,8(%r3) /* store tp->tv_nsec */ - lghi %r2,0 - aghi %r15,16 - CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD - CFI_RESTORE 15 - br %r14 - - /* CPUCLOCK_VIRT for this thread */ - CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD+16 - CFI_VAL_OFFSET 15, -STACK_FRAME_OVERHEAD -9: lghi %r4,0 - icm %r0,15,__VDSO_ECTG_OK(%r5) - jz 12f - sacf 256 /* Magic ectg instruction */ - .insn ssf,0xc80100000000,__VDSO_ECTG_BASE(4),__VDSO_ECTG_USER(4),4 - sacf 0 - algr %r1,%r0 /* r1 = cputime as TOD value */ - mghi %r1,1000 /* convert to nanoseconds */ - srlg %r1,%r1,12 /* r1 = cputime in nanosec */ - lgr %r4,%r1 - larl %r5,13f - srlg %r1,%r1,9 /* divide by 1000000000 */ - mlg %r0,8(%r5) - srlg %r0,%r0,11 /* r0 = tv_sec */ - stg %r0,0(%r3) - msg %r0,0(%r5) /* calculate tv_nsec */ - slgr %r4,%r0 /* r4 = tv_nsec */ - stg %r4,8(%r3) - lghi %r2,0 - aghi %r15,16 - CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD - CFI_RESTORE 15 - br %r14 - - /* Fallback to system call */ - CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD+16 - CFI_VAL_OFFSET 15, -STACK_FRAME_OVERHEAD -12: lghi %r1,__NR_clock_gettime - svc 0 - aghi %r15,16 - CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD - CFI_RESTORE 15 - br %r14 - CFI_ENDPROC - -13: .quad 1000000000 -14: .quad 19342813113834067 - .size __kernel_clock_gettime,.-__kernel_clock_gettime diff --git a/arch/s390/kernel/vdso64/gettimeofday.S b/arch/s390/kernel/vdso64/gettimeofday.S deleted file mode 100644 index aebe10dc7c99..000000000000 --- a/arch/s390/kernel/vdso64/gettimeofday.S +++ /dev/null @@ -1,71 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Userland implementation of gettimeofday() for 64 bits processes in a - * s390 kernel for use in the vDSO - * - * Copyright IBM Corp. 2008 - * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) - */ -#include -#include -#include -#include -#include - - .text - .align 4 - .globl __kernel_gettimeofday - .type __kernel_gettimeofday,@function -__kernel_gettimeofday: - CFI_STARTPROC - aghi %r15,-16 - CFI_ADJUST_CFA_OFFSET 16 - CFI_VAL_OFFSET 15, -STACK_FRAME_OVERHEAD - larl %r5,_vdso_data -0: ltgr %r3,%r3 /* check if tz is NULL */ - je 1f - mvc 0(8,%r3),__VDSO_TIMEZONE(%r5) -1: ltgr %r2,%r2 /* check if tv is NULL */ - je 4f - lg %r4,__VDSO_UPD_COUNT(%r5) /* load update counter */ - tmll %r4,0x0001 /* pending update ? loop */ - jnz 0b - stcke 0(%r15) /* Store TOD clock */ - lg %r1,1(%r15) - lg %r0,__VDSO_TS_END(%r5) /* TOD steering end time */ - slgr %r0,%r1 /* now - ts_steering_end */ - ltgr %r0,%r0 /* past end of steering ? */ - jm 6f - srlg %r0,%r0,15 /* 1 per 2^16 */ - tm __VDSO_TS_DIR+3(%r5),0x01 /* steering direction? */ - jz 7f - lcgr %r0,%r0 /* negative TOD offset */ -7: algr %r1,%r0 /* add steering offset */ -6: sg %r1,__VDSO_XTIME_STAMP(%r5) /* TOD - cycle_last */ - msgf %r1,__VDSO_TK_MULT(%r5) /* * tk->mult */ - alg %r1,__VDSO_XTIME_NSEC(%r5) /* + tk->xtime_nsec */ - lg %r0,__VDSO_XTIME_SEC(%r5) /* tk->xtime_sec */ - clg %r4,__VDSO_UPD_COUNT(%r5) /* check update counter */ - jne 0b - lgf %r5,__VDSO_TK_SHIFT(%r5) /* Timekeeper shift */ - srlg %r1,%r1,0(%r5) /* >> tk->shift */ - larl %r5,5f -2: clg %r1,0(%r5) - jl 3f - slg %r1,0(%r5) - aghi %r0,1 - j 2b -3: stg %r0,0(%r2) /* store tv->tv_sec */ - slgr %r0,%r0 /* tv_nsec -> tv_usec */ - ml %r0,8(%r5) - srlg %r0,%r0,6 - stg %r0,8(%r2) /* store tv->tv_usec */ -4: lghi %r2,0 - aghi %r15,16 - CFI_ADJUST_CFA_OFFSET -16 - CFI_RESTORE 15 - br %r14 - CFI_ENDPROC -5: .quad 1000000000 - .long 274877907 - .size __kernel_gettimeofday,.-__kernel_gettimeofday diff --git a/arch/s390/kernel/vdso64/vdso64_generic.c b/arch/s390/kernel/vdso64/vdso64_generic.c new file mode 100644 index 000000000000..a8cef7e4d137 --- /dev/null +++ b/arch/s390/kernel/vdso64/vdso64_generic.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "../../../../lib/vdso/gettimeofday.c" + +int __s390_vdso_gettimeofday(struct __kernel_old_timeval *tv, + struct timezone *tz) +{ + return __cvdso_gettimeofday(tv, tz); +} + +int __s390_vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts) +{ + return __cvdso_clock_gettime(clock, ts); +} + +int __s390_vdso_clock_getres(clockid_t clock, struct __kernel_timespec *ts) +{ + return __cvdso_clock_getres(clock, ts); +} diff --git a/arch/s390/kernel/vdso64/vdso_user_wrapper.S b/arch/s390/kernel/vdso64/vdso_user_wrapper.S new file mode 100644 index 000000000000..a775d7e52872 --- /dev/null +++ b/arch/s390/kernel/vdso64/vdso_user_wrapper.S @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include +#include +#include +#include +#include + +#define WRAPPER_FRAME_SIZE (STACK_FRAME_OVERHEAD+8) + +/* + * Older glibc version called vdso without allocating a stackframe. This wrapper + * is just used to allocate a stackframe. See + * https://sourceware.org/git/?p=glibc.git;a=commit;h=478593e6374f3818da39332260dc453cb19cfa1e + * for details. + */ +.macro vdso_func func + .globl __kernel_\func + .type __kernel_\func,@function + .align 8 +__kernel_\func: + CFI_STARTPROC + aghi %r15,-WRAPPER_FRAME_SIZE + CFI_DEF_CFA_OFFSET (STACK_FRAME_OVERHEAD + WRAPPER_FRAME_SIZE) + CFI_VAL_OFFSET 15, -STACK_FRAME_OVERHEAD + stg %r14,STACK_FRAME_OVERHEAD(%r15) + brasl %r14,__s390_vdso_\func + lg %r14,STACK_FRAME_OVERHEAD(%r15) + aghi %r15,WRAPPER_FRAME_SIZE + CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD + CFI_RESTORE 15 + br %r14 + CFI_ENDPROC + .size __kernel_\func,.-__kernel_\func +.endm + +vdso_func gettimeofday +vdso_func clock_getres +vdso_func clock_gettime From b51ba4fe2e134b631f9c8f45423707aab71449b5 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Thu, 6 Aug 2020 06:01:42 +0000 Subject: [PATCH 043/645] powerpc/32s: Fix assembler warning about r0 The assembler says: arch/powerpc/kernel/head_32.S:1095: Warning: invalid register expression It's objecting to the use of r0 as the RA argument. That's because when RA = 0 the literal value 0 is used, rather than the content of r0, making the use of r0 in the source potentially confusing. Fix it to use a literal 0, the generated code is identical. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/2b69ac8e1cddff6f808fc7415907179eab4aae9e.1596693679.git.christophe.leroy@csgroup.eu --- arch/powerpc/kernel/head_32.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index f3ab94d73936..5624db0e09a1 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -1092,7 +1092,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) */ lis r5, abatron_pteptrs@h ori r5, r5, abatron_pteptrs@l - stw r5, 0xf0(r0) /* This much match your Abatron config */ + stw r5, 0xf0(0) /* This much match your Abatron config */ lis r6, swapper_pg_dir@h ori r6, r6, swapper_pg_dir@l tophys(r5, r5) From 7db0a07273e8f581d0b3e8a102d3d9dd99f43528 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 6 Aug 2020 11:29:01 +0100 Subject: [PATCH 044/645] macintosh: windfarm: remove detatch debug containing spelling mistakes There are spelling mistakes in two debug messages. As recommended by Wolfram Sang, these can be removed as there is plenty of debug in the driver core. Signed-off-by: Colin Ian King Reviewed-by: Wolfram Sang Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200806102901.44988-1-colin.king@canonical.com --- drivers/macintosh/windfarm_lm75_sensor.c | 2 -- drivers/macintosh/windfarm_lm87_sensor.c | 2 -- 2 files changed, 4 deletions(-) diff --git a/drivers/macintosh/windfarm_lm75_sensor.c b/drivers/macintosh/windfarm_lm75_sensor.c index 1e5fa09845e7..29f48c2028b6 100644 --- a/drivers/macintosh/windfarm_lm75_sensor.c +++ b/drivers/macintosh/windfarm_lm75_sensor.c @@ -152,8 +152,6 @@ static int wf_lm75_remove(struct i2c_client *client) { struct wf_lm75_sensor *lm = i2c_get_clientdata(client); - DBG("wf_lm75: i2c detatch called for %s\n", lm->sens.name); - /* Mark client detached */ lm->i2c = NULL; diff --git a/drivers/macintosh/windfarm_lm87_sensor.c b/drivers/macintosh/windfarm_lm87_sensor.c index d011899c0a8a..9fab0b47cd3d 100644 --- a/drivers/macintosh/windfarm_lm87_sensor.c +++ b/drivers/macintosh/windfarm_lm87_sensor.c @@ -149,8 +149,6 @@ static int wf_lm87_remove(struct i2c_client *client) { struct wf_lm87_sensor *lm = i2c_get_clientdata(client); - DBG("wf_lm87: i2c detatch called for %s\n", lm->sens.name); - /* Mark client detached */ lm->i2c = NULL; From 169b9afee572853522901b7cbf34842c0494a887 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Thu, 6 Aug 2020 12:19:06 +0000 Subject: [PATCH 045/645] powerpc/hwirq: Remove stale forward irq_chip declaration Since commit identified below, the forward declaration of struct irq_chip is useless (was struct hw_interrupt_type at that time) Remove it, together with the associated comment. Fixes: c0ad90a32fb6 ("[PATCH] genirq: add ->retrigger() irq op to consolidate hw_irq_resend()") Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/fbe58d27cf128d5fe581e4510ded8701858f268e.1596716328.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/hw_irq.h | 6 ------ 1 file changed, 6 deletions(-) diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index 3a0db7b0b46e..538698facb80 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -372,12 +372,6 @@ static inline void may_hard_irq_enable(void) { } #define ARCH_IRQ_INIT_FLAGS IRQ_NOREQUEST -/* - * interrupt-retrigger: should we handle this via lost interrupts and IPIs - * or should we not care like we do now ? --BenH. - */ -struct irq_chip; - #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_HW_IRQ_H */ From b134cfc3e3276ccd5d29e39de5c848a45b08e410 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Thu, 6 Aug 2020 12:19:46 +0000 Subject: [PATCH 046/645] powerpc/irq: Drop forward declaration of struct irqaction Since the commit identified below, the forward declaration of struct irqaction is useless. Drop it. Fixes: b709c0832824 ("ppc64: move stack switching up in interrupt processing") Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/e0bcdabac45fcd26c02d7df273bd4a5827c6033d.1596716375.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/irq.h | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h index 814dfab7e392..4f983ca4030a 100644 --- a/arch/powerpc/include/asm/irq.h +++ b/arch/powerpc/include/asm/irq.h @@ -35,7 +35,6 @@ static __inline__ int irq_canonicalize(int irq) extern int distribute_irqs; -struct irqaction; struct pt_regs; #define __ARCH_HAS_DO_SOFTIRQ From 63442de4301188129e1fcff144fbfb966ad5eb19 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Thu, 6 Aug 2020 12:20:34 +0000 Subject: [PATCH 047/645] powerpc/fpu: Drop cvt_fd() and cvt_df() Those two functions have been unused since commit identified below. Drop them. Fixes: 31bfdb036f12 ("powerpc: Use instruction emulation infrastructure to handle alignment faults") Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/d5641ada199b8dd2af16ad00a66084cf974f2704.1596716418.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/processor.h | 2 -- arch/powerpc/kernel/fpu.S | 15 --------------- 2 files changed, 17 deletions(-) diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index ed0d633ab5aa..2d68dbe56601 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -439,8 +439,6 @@ extern void flush_instruction_cache(void); extern void hard_reset_now(void); extern void poweroff_now(void); extern int fix_alignment(struct pt_regs *); -extern void cvt_fd(float *from, double *to); -extern void cvt_df(double *from, float *to); extern void _nmask_and_or_msr(unsigned long nmask, unsigned long or_val); #ifdef CONFIG_PPC64 diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S index 4ae39db70044..825893d4cb59 100644 --- a/arch/powerpc/kernel/fpu.S +++ b/arch/powerpc/kernel/fpu.S @@ -134,18 +134,3 @@ _GLOBAL(save_fpu) mffs fr0 stfd fr0,FPSTATE_FPSCR(r6) blr - -/* - * These are used in the alignment trap handler when emulating - * single-precision loads and stores. - */ - -_GLOBAL(cvt_fd) - lfs 0,0(r3) - stfd 0,0(r4) - blr - -_GLOBAL(cvt_df) - lfd 0,0(r3) - stfs 0,0(r4) - blr From 82eb1792426f8a171cdaa6cfccb63c39f55bc9bd Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Thu, 6 Aug 2020 12:20:35 +0000 Subject: [PATCH 048/645] powerpc: drop hard_reset_now() and poweroff_now() declaration Those function have never existed. Drop their declaration. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/edcdd72a36495d25213c0256c8022367458e0d19.1596716418.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/processor.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 2d68dbe56601..8184eb357f10 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -436,8 +436,6 @@ extern void power9_idle_type(unsigned long stop_psscr_val, unsigned long stop_psscr_mask); extern void flush_instruction_cache(void); -extern void hard_reset_now(void); -extern void poweroff_now(void); extern int fix_alignment(struct pt_regs *); extern void _nmask_and_or_msr(unsigned long nmask, unsigned long or_val); From 59562b5c33d6ff3685509ed58b2ed3c5b5712704 Mon Sep 17 00:00:00 2001 From: Scott Cheloha Date: Mon, 27 Jul 2020 13:46:04 -0500 Subject: [PATCH 049/645] powerpc/perf: consolidate GPCI hcall structs into asm/hvcall.h The H_GetPerformanceCounterInfo (GPCI) hypercall input/output structs are useful to modules outside of perf/, so move them into asm/hvcall.h to live alongside the other powerpc hypercall structs. Leave the perf-specific GPCI stuff in perf/hv-gpci.h. Signed-off-by: Scott Cheloha Acked-by: Nathan Lynch Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200727184605.2945095-1-cheloha@linux.ibm.com --- arch/powerpc/include/asm/hvcall.h | 36 +++++++++++++++++++++++++++++++ arch/powerpc/perf/hv-gpci.c | 9 -------- arch/powerpc/perf/hv-gpci.h | 27 ----------------------- 3 files changed, 36 insertions(+), 36 deletions(-) diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index fbb377055471..e8f116a425f9 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -560,6 +560,42 @@ struct hv_guest_state { /* Latest version of hv_guest_state structure */ #define HV_GUEST_STATE_VERSION 1 +/* + * From the document "H_GetPerformanceCounterInfo Interface" v1.07 + * + * H_GET_PERF_COUNTER_INFO argument + */ +struct hv_get_perf_counter_info_params { + __be32 counter_request; /* I */ + __be32 starting_index; /* IO */ + __be16 secondary_index; /* IO */ + __be16 returned_values; /* O */ + __be32 detail_rc; /* O, only needed when called via *_norets() */ + + /* + * O, size each of counter_value element in bytes, only set for version + * >= 0x3 + */ + __be16 cv_element_size; + + /* I, 0 (zero) for versions < 0x3 */ + __u8 counter_info_version_in; + + /* O, 0 (zero) if version < 0x3. Must be set to 0 when making hcall */ + __u8 counter_info_version_out; + __u8 reserved[0xC]; + __u8 counter_value[]; +} __packed; + +#define HGPCI_REQ_BUFFER_SIZE 4096 +#define HGPCI_MAX_DATA_BYTES \ + (HGPCI_REQ_BUFFER_SIZE - sizeof(struct hv_get_perf_counter_info_params)) + +struct hv_gpci_request_buffer { + struct hv_get_perf_counter_info_params params; + uint8_t bytes[HGPCI_MAX_DATA_BYTES]; +} __packed; + #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_HVCALL_H */ diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c index 6884d16ec19b..1667315b82e9 100644 --- a/arch/powerpc/perf/hv-gpci.c +++ b/arch/powerpc/perf/hv-gpci.c @@ -123,17 +123,8 @@ static const struct attribute_group *attr_groups[] = { NULL, }; -#define HGPCI_REQ_BUFFER_SIZE 4096 -#define HGPCI_MAX_DATA_BYTES \ - (HGPCI_REQ_BUFFER_SIZE - sizeof(struct hv_get_perf_counter_info_params)) - static DEFINE_PER_CPU(char, hv_gpci_reqb[HGPCI_REQ_BUFFER_SIZE]) __aligned(sizeof(uint64_t)); -struct hv_gpci_request_buffer { - struct hv_get_perf_counter_info_params params; - uint8_t bytes[HGPCI_MAX_DATA_BYTES]; -} __packed; - static unsigned long single_gpci_request(u32 req, u32 starting_index, u16 secondary_index, u8 version_in, u32 offset, u8 length, u64 *value) diff --git a/arch/powerpc/perf/hv-gpci.h b/arch/powerpc/perf/hv-gpci.h index a3053eda5dcc..4d108262bed7 100644 --- a/arch/powerpc/perf/hv-gpci.h +++ b/arch/powerpc/perf/hv-gpci.h @@ -2,33 +2,6 @@ #ifndef LINUX_POWERPC_PERF_HV_GPCI_H_ #define LINUX_POWERPC_PERF_HV_GPCI_H_ -#include - -/* From the document "H_GetPerformanceCounterInfo Interface" v1.07 */ - -/* H_GET_PERF_COUNTER_INFO argument */ -struct hv_get_perf_counter_info_params { - __be32 counter_request; /* I */ - __be32 starting_index; /* IO */ - __be16 secondary_index; /* IO */ - __be16 returned_values; /* O */ - __be32 detail_rc; /* O, only needed when called via *_norets() */ - - /* - * O, size each of counter_value element in bytes, only set for version - * >= 0x3 - */ - __be16 cv_element_size; - - /* I, 0 (zero) for versions < 0x3 */ - __u8 counter_info_version_in; - - /* O, 0 (zero) if version < 0x3. Must be set to 0 when making hcall */ - __u8 counter_info_version_out; - __u8 reserved[0xC]; - __u8 counter_value[]; -} __packed; - /* * counter info version => fw version/reference (spec version) * From 5d1bc776428f34941a6237afb9454061b5b5e1e1 Mon Sep 17 00:00:00 2001 From: Scott Cheloha Date: Mon, 27 Jul 2020 13:46:05 -0500 Subject: [PATCH 050/645] powerpc/pseries: new lparcfg key/value pair: partition_affinity_score The H_GetPerformanceCounterInfo (GPCI) PHYP hypercall has a subcall, Affinity_Domain_Info_By_Partition, which returns, among other things, a "partition affinity score" for a given LPAR. This score, a value on [0-100], represents the processor-memory affinity for the LPAR in question. A score of 0 indicates the worst possible affinity while a score of 100 indicates perfect affinity. The score can be used to reason about performance. This patch adds the score for the local LPAR to the lparcfg procfile under a new 'partition_affinity_score' key. Signed-off-by: Scott Cheloha Reviewed-by: Tyrel Datwyler Acked-by: Nathan Lynch Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200727184605.2945095-2-cheloha@linux.ibm.com --- arch/powerpc/platforms/pseries/lparcfg.c | 35 ++++++++++++++++++++++++ 1 file changed, 35 insertions(+) diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c index b8d28ab88178..e278390ab28d 100644 --- a/arch/powerpc/platforms/pseries/lparcfg.c +++ b/arch/powerpc/platforms/pseries/lparcfg.c @@ -136,6 +136,39 @@ static unsigned int h_get_ppp(struct hvcall_ppp_data *ppp_data) return rc; } +static void show_gpci_data(struct seq_file *m) +{ + struct hv_gpci_request_buffer *buf; + unsigned int affinity_score; + long ret; + + buf = kmalloc(sizeof(*buf), GFP_KERNEL); + if (buf == NULL) + return; + + /* + * Show the local LPAR's affinity score. + * + * 0xB1 selects the Affinity_Domain_Info_By_Partition subcall. + * The score is at byte 0xB in the output buffer. + */ + memset(&buf->params, 0, sizeof(buf->params)); + buf->params.counter_request = cpu_to_be32(0xB1); + buf->params.starting_index = cpu_to_be32(-1); /* local LPAR */ + buf->params.counter_info_version_in = 0x5; /* v5+ for score */ + ret = plpar_hcall_norets(H_GET_PERF_COUNTER_INFO, virt_to_phys(buf), + sizeof(*buf)); + if (ret != H_SUCCESS) { + pr_debug("hcall failed: H_GET_PERF_COUNTER_INFO: %ld, %x\n", + ret, be32_to_cpu(buf->params.detail_rc)); + goto out; + } + affinity_score = buf->bytes[0xB]; + seq_printf(m, "partition_affinity_score=%u\n", affinity_score); +out: + kfree(buf); +} + static unsigned h_pic(unsigned long *pool_idle_time, unsigned long *num_procs) { @@ -487,6 +520,8 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v) partition_active_processors * 100); } + show_gpci_data(m); + seq_printf(m, "partition_active_processors=%d\n", partition_active_processors); From 6c9100ea39d209e1625ba0fe06134192d9c4752a Mon Sep 17 00:00:00 2001 From: Stephen Kitt Date: Fri, 7 Aug 2020 17:27:13 +0200 Subject: [PATCH 051/645] powerpc: Use simple i2c probe function The i2c probe functions here don't use the id information provided in their second argument, so the single-parameter i2c probe function ("probe_new") can be used instead. This avoids scanning the identifier tables during probes. Signed-off-by: Stephen Kitt Acked-by: Wolfram Sang Reviewed-by: Luca Ceresoli Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200807152713.381588-1-steve@sk2.org --- arch/powerpc/platforms/44x/ppc476.c | 5 ++--- arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c | 4 ++-- 2 files changed, 4 insertions(+), 5 deletions(-) diff --git a/arch/powerpc/platforms/44x/ppc476.c b/arch/powerpc/platforms/44x/ppc476.c index cba83eee685c..07f7e3ce67b5 100644 --- a/arch/powerpc/platforms/44x/ppc476.c +++ b/arch/powerpc/platforms/44x/ppc476.c @@ -86,8 +86,7 @@ static void __noreturn avr_reset_system(char *cmd) avr_halt_system(AVR_PWRCTL_RESET); } -static int avr_probe(struct i2c_client *client, - const struct i2c_device_id *id) +static int avr_probe(struct i2c_client *client) { avr_i2c_client = client; ppc_md.restart = avr_reset_system; @@ -104,7 +103,7 @@ static struct i2c_driver avr_driver = { .driver = { .name = "akebono-avr", }, - .probe = avr_probe, + .probe_new = avr_probe, .id_table = avr_id, }; diff --git a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c index 0967bdfb1691..409481016928 100644 --- a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c +++ b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c @@ -142,7 +142,7 @@ static int mcu_gpiochip_remove(struct mcu *mcu) return 0; } -static int mcu_probe(struct i2c_client *client, const struct i2c_device_id *id) +static int mcu_probe(struct i2c_client *client) { struct mcu *mcu; int ret; @@ -221,7 +221,7 @@ static struct i2c_driver mcu_driver = { .name = "mcu-mpc8349emitx", .of_match_table = mcu_of_match_table, }, - .probe = mcu_probe, + .probe_new = mcu_probe, .remove = mcu_remove, .id_table = mcu_ids, }; From e53281bc21f061f96c9004f534bc3e807d70cb73 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 14 Aug 2020 06:54:49 +0000 Subject: [PATCH 052/645] powerpc: Drop _nmask_and_or_msr() _nmask_and_or_msr() is only used at two places to set MSR_IP. The SYNC is unnecessary as the users are not PowerPC 601. Can be easily writen in C. Do it, and drop _nmask_and_or_msr() Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/c2d2b8dfb8dd677026b26dffc8d31070c38a6b89.1597388079.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/processor.h | 1 - arch/powerpc/kernel/misc_32.S | 13 ------------- arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c | 3 ++- arch/powerpc/platforms/embedded6xx/storcenter.c | 3 ++- 4 files changed, 4 insertions(+), 16 deletions(-) diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 8184eb357f10..8c7ad14d68de 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -437,7 +437,6 @@ extern void power9_idle_type(unsigned long stop_psscr_val, extern void flush_instruction_cache(void); extern int fix_alignment(struct pt_regs *); -extern void _nmask_and_or_msr(unsigned long nmask, unsigned long or_val); #ifdef CONFIG_PPC64 /* diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index b24f866fef81..8d9cb5df580e 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -215,19 +215,6 @@ _GLOBAL(low_choose_7447a_dfs) #endif /* CONFIG_CPU_FREQ_PMAC && CONFIG_PPC_BOOK3S_32 */ -/* - * complement mask on the msr then "or" some values on. - * _nmask_and_or_msr(nmask, value_to_or) - */ -_GLOBAL(_nmask_and_or_msr) - mfmsr r0 /* Get current msr */ - andc r0,r0,r3 /* And off the bits set in r3 (first parm) */ - or r0,r0,r4 /* Or on the bits in r4 (second parm) */ - SYNC /* Some chip revs have problems here... */ - mtmsr r0 /* Update machine state */ - isync - blr /* Done */ - #ifdef CONFIG_40x /* diff --git a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c index 15437abe1f6d..b95c3380d2b5 100644 --- a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c +++ b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c @@ -147,7 +147,8 @@ static void __noreturn mpc7448_hpc2_restart(char *cmd) local_irq_disable(); /* Set exception prefix high - to the firmware */ - _nmask_and_or_msr(0, MSR_IP); + mtmsr(mfmsr() | MSR_IP); + isync(); for (;;) ; /* Spin until reset happens */ } diff --git a/arch/powerpc/platforms/embedded6xx/storcenter.c b/arch/powerpc/platforms/embedded6xx/storcenter.c index ed1914dd34bb..e346ddcef45e 100644 --- a/arch/powerpc/platforms/embedded6xx/storcenter.c +++ b/arch/powerpc/platforms/embedded6xx/storcenter.c @@ -101,7 +101,8 @@ static void __noreturn storcenter_restart(char *cmd) local_irq_disable(); /* Set exception prefix high - to the firmware */ - _nmask_and_or_msr(0, MSR_IP); + mtmsr(mfmsr() | MSR_IP); + isync(); /* Wait for reset to happen */ for (;;) ; From 9d6792ffe140240ae54c881cc4183f9acc24b4df Mon Sep 17 00:00:00 2001 From: Nathan Lynch Date: Thu, 13 Aug 2020 10:11:31 -0500 Subject: [PATCH 053/645] powerpc/pseries: explicitly reschedule during drmem_lmb list traversal The drmem lmb list can have hundreds of thousands of entries, and unfortunately lookups take the form of linear searches. As long as this is the case, traversals have the potential to monopolize the CPU and provoke lockup reports, workqueue stalls, and the like unless they explicitly yield. Rather than placing cond_resched() calls within various for_each_drmem_lmb() loop blocks in the code, put it in the iteration expression of the loop macro itself so users can't omit it. Introduce a drmem_lmb_next() iteration helper function which calls cond_resched() at a regular interval during array traversal. Each iteration of the loop in DLPAR code paths can involve around ten RTAS calls which can each take up to 250us, so this ensures the check is performed at worst every few milliseconds. Fixes: 6c6ea53725b3 ("powerpc/mm: Separate ibm, dynamic-memory data from DT format") Signed-off-by: Nathan Lynch Reviewed-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200813151131.2070161-1-nathanl@linux.ibm.com --- arch/powerpc/include/asm/drmem.h | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/include/asm/drmem.h b/arch/powerpc/include/asm/drmem.h index 17ccc6474ab6..6fb928605ed1 100644 --- a/arch/powerpc/include/asm/drmem.h +++ b/arch/powerpc/include/asm/drmem.h @@ -8,6 +8,8 @@ #ifndef _ASM_POWERPC_LMB_H #define _ASM_POWERPC_LMB_H +#include + struct drmem_lmb { u64 base_addr; u32 drc_index; @@ -26,8 +28,22 @@ struct drmem_lmb_info { extern struct drmem_lmb_info *drmem_info; +static inline struct drmem_lmb *drmem_lmb_next(struct drmem_lmb *lmb, + const struct drmem_lmb *start) +{ + /* + * DLPAR code paths can take several milliseconds per element + * when interacting with firmware. Ensure that we don't + * unfairly monopolize the CPU. + */ + if (((++lmb - start) % 16) == 0) + cond_resched(); + + return lmb; +} + #define for_each_drmem_lmb_in_range(lmb, start, end) \ - for ((lmb) = (start); (lmb) < (end); (lmb)++) + for ((lmb) = (start); (lmb) < (end); lmb = drmem_lmb_next(lmb, start)) #define for_each_drmem_lmb(lmb) \ for_each_drmem_lmb_in_range((lmb), \ From e426ab39f41045a4c163031272b2f48d944b69c0 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 14 Aug 2020 05:56:24 +0000 Subject: [PATCH 054/645] powerpc: Remove flush_instruction_cache for book3s/32 The only callers of flush_instruction_cache() are: arch/powerpc/kernel/swsusp_booke.S: bl flush_instruction_cache arch/powerpc/mm/nohash/40x.c: flush_instruction_cache(); arch/powerpc/mm/nohash/44x.c: flush_instruction_cache(); arch/powerpc/mm/nohash/fsl_booke.c: flush_instruction_cache(); arch/powerpc/platforms/44x/machine_check.c: flush_instruction_cache(); arch/powerpc/platforms/44x/machine_check.c: flush_instruction_cache(); This function is not used by book3s/32, drop it. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/50098f49877cea0f46730a9df82dcabf84160e4b.1597384512.git.christophe.leroy@csgroup.eu --- arch/powerpc/kernel/misc_32.S | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 8d9cb5df580e..aa860b8d1dcc 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -258,9 +258,8 @@ _ASM_NOKPROBE_SYMBOL(real_writeb) /* * Flush instruction cache. - * This is a no-op on the 601. */ -#ifndef CONFIG_PPC_8xx +#if !defined(CONFIG_PPC_8xx) && !defined(CONFIG_PPC_BOOK3S_32) _GLOBAL(flush_instruction_cache) #if defined(CONFIG_4xx) lis r3, KERNELBASE@h @@ -277,18 +276,11 @@ _GLOBAL(flush_instruction_cache) mfspr r3,SPRN_L1CSR1 ori r3,r3,L1CSR1_ICFI|L1CSR1_ICLFR mtspr SPRN_L1CSR1,r3 -#elif defined(CONFIG_PPC_BOOK3S_601) - blr /* for 601, do nothing */ -#else - /* 603/604 processor - use invalidate-all bit in HID0 */ - mfspr r3,SPRN_HID0 - ori r3,r3,HID0_ICFI - mtspr SPRN_HID0,r3 #endif /* CONFIG_4xx */ isync blr EXPORT_SYMBOL(flush_instruction_cache) -#endif /* CONFIG_PPC_8xx */ +#endif /* * Copy a whole page. We use the dcbz instruction on the destination From f663f3312051402d32952c44d156a20c0b854753 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 14 Aug 2020 05:56:25 +0000 Subject: [PATCH 055/645] powerpc: Move flush_instruction_cache() prototype in asm/cacheflush.h flush_instruction_cache() belongs to the cache flushing function family. Move its prototype in asm/cacheflush.h Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/993445b5227e8ca2f0e38bcc9ea3dfea6e865920.1597384512.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/cacheflush.h | 2 ++ arch/powerpc/include/asm/processor.h | 1 - arch/powerpc/platforms/44x/machine_check.c | 1 + 3 files changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h index 54764c6e922d..481877879fec 100644 --- a/arch/powerpc/include/asm/cacheflush.h +++ b/arch/powerpc/include/asm/cacheflush.h @@ -98,6 +98,8 @@ static inline void invalidate_dcache_range(unsigned long start, mb(); /* sync */ } +void flush_instruction_cache(void); + #include #endif /* _ASM_POWERPC_CACHEFLUSH_H */ diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 8c7ad14d68de..36a71cd41f37 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -435,7 +435,6 @@ extern void power7_idle_type(unsigned long type); extern void power9_idle_type(unsigned long stop_psscr_val, unsigned long stop_psscr_mask); -extern void flush_instruction_cache(void); extern int fix_alignment(struct pt_regs *); #ifdef CONFIG_PPC64 diff --git a/arch/powerpc/platforms/44x/machine_check.c b/arch/powerpc/platforms/44x/machine_check.c index 90ad6ac529d2..a5c898bb9bab 100644 --- a/arch/powerpc/platforms/44x/machine_check.c +++ b/arch/powerpc/platforms/44x/machine_check.c @@ -7,6 +7,7 @@ #include #include +#include int machine_check_440A(struct pt_regs *regs) { From de39b19452e784de5f90ae899851ab29a29bb42c Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 14 Aug 2020 05:56:26 +0000 Subject: [PATCH 056/645] powerpc: Rewrite 4xx flush_cache_instruction() in C Nothing prevents flush_cache_instruction() from being writen in C. Do it to improve readability and maintainability. This function is very small and isn't called from assembly, make it static inline in asm/cacheflush.h Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/93d93fc69b4b3ad3ceba2fc0756333c0c0245bb7.1597384512.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/cacheflush.h | 8 ++++++++ arch/powerpc/kernel/misc_32.S | 7 +------ 2 files changed, 9 insertions(+), 6 deletions(-) diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h index 481877879fec..138e46d8c04e 100644 --- a/arch/powerpc/include/asm/cacheflush.h +++ b/arch/powerpc/include/asm/cacheflush.h @@ -98,7 +98,15 @@ static inline void invalidate_dcache_range(unsigned long start, mb(); /* sync */ } +#ifdef CONFIG_4xx +static inline void flush_instruction_cache(void) +{ + iccci((void *)KERNELBASE); + isync(); +} +#else void flush_instruction_cache(void); +#endif #include diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index aa860b8d1dcc..9e8f730fe04d 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -259,12 +259,8 @@ _ASM_NOKPROBE_SYMBOL(real_writeb) /* * Flush instruction cache. */ -#if !defined(CONFIG_PPC_8xx) && !defined(CONFIG_PPC_BOOK3S_32) +#ifdef CONFIG_FSL_BOOKE _GLOBAL(flush_instruction_cache) -#if defined(CONFIG_4xx) - lis r3, KERNELBASE@h - iccci 0,r3 -#elif defined(CONFIG_FSL_BOOKE) #ifdef CONFIG_E200 mfspr r3,SPRN_L1CSR0 ori r3,r3,L1CSR0_CFI|L1CSR0_CLFC @@ -276,7 +272,6 @@ _GLOBAL(flush_instruction_cache) mfspr r3,SPRN_L1CSR1 ori r3,r3,L1CSR1_ICFI|L1CSR1_ICLFR mtspr SPRN_L1CSR1,r3 -#endif /* CONFIG_4xx */ isync blr EXPORT_SYMBOL(flush_instruction_cache) From 704dfe931df951895dea98bd1d9cacbb601b6451 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 14 Aug 2020 05:56:27 +0000 Subject: [PATCH 057/645] powerpc: Rewrite FSL_BOOKE flush_cache_instruction() in C Nothing prevents flush_cache_instruction() from being writen in C. Do it to improve readability and maintainability. This function is only use by low level callers, it is not intended to be used by module. Don't export it. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/f989eff8296800c427622c0985384148404e4f0b.1597384512.git.christophe.leroy@csgroup.eu --- arch/powerpc/kernel/misc_32.S | 22 ---------------------- arch/powerpc/mm/nohash/fsl_booke.c | 16 ++++++++++++++++ 2 files changed, 16 insertions(+), 22 deletions(-) diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 9e8f730fe04d..717e658b90fd 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -255,28 +255,6 @@ _ASM_NOKPROBE_SYMBOL(real_writeb) #endif /* CONFIG_40x */ - -/* - * Flush instruction cache. - */ -#ifdef CONFIG_FSL_BOOKE -_GLOBAL(flush_instruction_cache) -#ifdef CONFIG_E200 - mfspr r3,SPRN_L1CSR0 - ori r3,r3,L1CSR0_CFI|L1CSR0_CLFC - /* msync; isync recommended here */ - mtspr SPRN_L1CSR0,r3 - isync - blr -#endif - mfspr r3,SPRN_L1CSR1 - ori r3,r3,L1CSR1_ICFI|L1CSR1_ICLFR - mtspr SPRN_L1CSR1,r3 - isync - blr -EXPORT_SYMBOL(flush_instruction_cache) -#endif - /* * Copy a whole page. We use the dcbz instruction on the destination * to reduce memory traffic (it eliminates the unnecessary reads of diff --git a/arch/powerpc/mm/nohash/fsl_booke.c b/arch/powerpc/mm/nohash/fsl_booke.c index 0c294827d6e5..36bda962d3b3 100644 --- a/arch/powerpc/mm/nohash/fsl_booke.c +++ b/arch/powerpc/mm/nohash/fsl_booke.c @@ -219,6 +219,22 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top) return tlbcam_addrs[tlbcam_index - 1].limit - PAGE_OFFSET + 1; } +void flush_instruction_cache(void) +{ + unsigned long tmp; + + if (IS_ENABLED(CONFIG_E200)) { + tmp = mfspr(SPRN_L1CSR0); + tmp |= L1CSR0_CFI | L1CSR0_CLFC; + mtspr(SPRN_L1CSR0, tmp); + } else { + tmp = mfspr(SPRN_L1CSR1); + tmp |= L1CSR1_ICFI | L1CSR1_ICLFR; + mtspr(SPRN_L1CSR1, tmp); + } + isync(); +} + /* * MMU_init_hw does the chip-specific initialization of the MMU hardware. */ From e5e179aa3a39c818db8fbc2dce8d2cd24adaf657 Mon Sep 17 00:00:00 2001 From: Scott Cheloha Date: Mon, 10 Aug 2020 20:51:15 -0500 Subject: [PATCH 058/645] pseries/drmem: don't cache node id in drmem_lmb struct At memory hot-remove time we can retrieve an LMB's nid from its corresponding memory_block. There is no need to store the nid in multiple locations. Note that lmb_to_memblock() uses find_memory_block() to get the corresponding memory_block. As find_memory_block() runs in sub-linear time this approach is negligibly slower than what we do at present. In exchange for this lookup at hot-remove time we no longer need to call memory_add_physaddr_to_nid() during drmem_init() for each LMB. On powerpc, memory_add_physaddr_to_nid() is a linear search, so this spares us an O(n^2) initialization during boot. On systems with many LMBs that initialization overhead is palpable and disruptive. For example, on a box with 249854 LMBs we're seeing drmem_init() take upwards of 30 seconds to complete: [ 53.721639] drmem: initializing drmem v2 [ 80.604346] watchdog: BUG: soft lockup - CPU#65 stuck for 23s! [swapper/0:1] [ 80.604377] Modules linked in: [ 80.604389] CPU: 65 PID: 1 Comm: swapper/0 Not tainted 5.6.0-rc2+ #4 [ 80.604397] NIP: c0000000000a4980 LR: c0000000000a4940 CTR: 0000000000000000 [ 80.604407] REGS: c0002dbff8493830 TRAP: 0901 Not tainted (5.6.0-rc2+) [ 80.604412] MSR: 8000000002009033 CR: 44000248 XER: 0000000d [ 80.604431] CFAR: c0000000000a4a38 IRQMASK: 0 [ 80.604431] GPR00: c0000000000a4940 c0002dbff8493ac0 c000000001904400 c0003cfffffede30 [ 80.604431] GPR04: 0000000000000000 c000000000f4095a 000000000000002f 0000000010000000 [ 80.604431] GPR08: c0000bf7ecdb7fb8 c0000bf7ecc2d3c8 0000000000000008 c00c0002fdfb2001 [ 80.604431] GPR12: 0000000000000000 c00000001e8ec200 [ 80.604477] NIP [c0000000000a4980] hot_add_scn_to_nid+0xa0/0x3e0 [ 80.604486] LR [c0000000000a4940] hot_add_scn_to_nid+0x60/0x3e0 [ 80.604492] Call Trace: [ 80.604498] [c0002dbff8493ac0] [c0000000000a4940] hot_add_scn_to_nid+0x60/0x3e0 (unreliable) [ 80.604509] [c0002dbff8493b20] [c000000000087c10] memory_add_physaddr_to_nid+0x20/0x60 [ 80.604521] [c0002dbff8493b40] [c0000000010d4880] drmem_init+0x25c/0x2f0 [ 80.604530] [c0002dbff8493c10] [c000000000010154] do_one_initcall+0x64/0x2c0 [ 80.604540] [c0002dbff8493ce0] [c0000000010c4aa0] kernel_init_freeable+0x2d8/0x3a0 [ 80.604550] [c0002dbff8493db0] [c000000000010824] kernel_init+0x2c/0x148 [ 80.604560] [c0002dbff8493e20] [c00000000000b648] ret_from_kernel_thread+0x5c/0x74 [ 80.604567] Instruction dump: [ 80.604574] 392918e8 e9490000 e90a000a e92a0000 80ea000c 1d080018 3908ffe8 7d094214 [ 80.604586] 7fa94040 419d00dc e9490010 714a0088 <2faa0008> 409e00ac e9490000 7fbe5040 [ 89.047390] drmem: 249854 LMB(s) With a patched kernel on the same machine we're no longer seeing the soft lockup. drmem_init() now completes in negligible time, even when the LMB count is large. Fixes: b2d3b5ee66f2 ("powerpc/pseries: Track LMB nid instead of using device tree") Signed-off-by: Scott Cheloha Reviewed-by: Nathan Lynch Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200811015115.63677-1-cheloha@linux.ibm.com --- arch/powerpc/include/asm/drmem.h | 21 ---------------- arch/powerpc/mm/drmem.c | 6 +---- .../platforms/pseries/hotplug-memory.c | 24 ++++++++++++------- 3 files changed, 17 insertions(+), 34 deletions(-) diff --git a/arch/powerpc/include/asm/drmem.h b/arch/powerpc/include/asm/drmem.h index 6fb928605ed1..030a19d92213 100644 --- a/arch/powerpc/include/asm/drmem.h +++ b/arch/powerpc/include/asm/drmem.h @@ -15,9 +15,6 @@ struct drmem_lmb { u32 drc_index; u32 aa_index; u32 flags; -#ifdef CONFIG_MEMORY_HOTPLUG - int nid; -#endif }; struct drmem_lmb_info { @@ -121,22 +118,4 @@ static inline void invalidate_lmb_associativity_index(struct drmem_lmb *lmb) lmb->aa_index = 0xffffffff; } -#ifdef CONFIG_MEMORY_HOTPLUG -static inline void lmb_set_nid(struct drmem_lmb *lmb) -{ - lmb->nid = memory_add_physaddr_to_nid(lmb->base_addr); -} -static inline void lmb_clear_nid(struct drmem_lmb *lmb) -{ - lmb->nid = -1; -} -#else -static inline void lmb_set_nid(struct drmem_lmb *lmb) -{ -} -static inline void lmb_clear_nid(struct drmem_lmb *lmb) -{ -} -#endif - #endif /* _ASM_POWERPC_LMB_H */ diff --git a/arch/powerpc/mm/drmem.c b/arch/powerpc/mm/drmem.c index b2eeea39684c..9af3832c9d8d 100644 --- a/arch/powerpc/mm/drmem.c +++ b/arch/powerpc/mm/drmem.c @@ -389,10 +389,8 @@ static void __init init_drmem_v1_lmbs(const __be32 *prop) if (!drmem_info->lmbs) return; - for_each_drmem_lmb(lmb) { + for_each_drmem_lmb(lmb) read_drconf_v1_cell(lmb, &prop); - lmb_set_nid(lmb); - } } static void __init init_drmem_v2_lmbs(const __be32 *prop) @@ -437,8 +435,6 @@ static void __init init_drmem_v2_lmbs(const __be32 *prop) lmb->aa_index = dr_cell.aa_index; lmb->flags = dr_cell.flags; - - lmb_set_nid(lmb); } } } diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 5d545b78111f..0ea976d1cac4 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -354,25 +354,32 @@ static int dlpar_add_lmb(struct drmem_lmb *); static int dlpar_remove_lmb(struct drmem_lmb *lmb) { + struct memory_block *mem_block; unsigned long block_sz; int rc; if (!lmb_is_removable(lmb)) return -EINVAL; + mem_block = lmb_to_memblock(lmb); + if (mem_block == NULL) + return -EINVAL; + rc = dlpar_offline_lmb(lmb); - if (rc) + if (rc) { + put_device(&mem_block->dev); return rc; + } block_sz = pseries_memory_block_size(); - __remove_memory(lmb->nid, lmb->base_addr, block_sz); + __remove_memory(mem_block->nid, lmb->base_addr, block_sz); + put_device(&mem_block->dev); /* Update memory regions for memory remove */ memblock_remove(lmb->base_addr, block_sz); invalidate_lmb_associativity_index(lmb); - lmb_clear_nid(lmb); lmb->flags &= ~DRCONF_MEM_ASSIGNED; return 0; @@ -591,7 +598,7 @@ static int dlpar_memory_remove_by_ic(u32 lmbs_to_remove, u32 drc_index) static int dlpar_add_lmb(struct drmem_lmb *lmb) { unsigned long block_sz; - int rc; + int nid, rc; if (lmb->flags & DRCONF_MEM_ASSIGNED) return -EINVAL; @@ -602,11 +609,13 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb) return rc; } - lmb_set_nid(lmb); block_sz = memory_block_size_bytes(); + /* Find the node id for this address. */ + nid = memory_add_physaddr_to_nid(lmb->base_addr); + /* Add the memory */ - rc = __add_memory(lmb->nid, lmb->base_addr, block_sz); + rc = __add_memory(nid, lmb->base_addr, block_sz); if (rc) { invalidate_lmb_associativity_index(lmb); return rc; @@ -614,9 +623,8 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb) rc = dlpar_online_lmb(lmb); if (rc) { - __remove_memory(lmb->nid, lmb->base_addr, block_sz); + __remove_memory(nid, lmb->base_addr, block_sz); invalidate_lmb_associativity_index(lmb); - lmb_clear_nid(lmb); } else { lmb->flags |= DRCONF_MEM_ASSIGNED; } From d9de6b0da85c9f51734f7648f6e860b89f94c801 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Wed, 12 Aug 2020 00:04:28 +1000 Subject: [PATCH 059/645] powerpc: unrel_branch_check.sh: fix shellcheck complaints No functional change Signed-off-by: Stephen Rothwell Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200811140435.20957-2-sfr@canb.auug.org.au --- arch/powerpc/tools/unrel_branch_check.sh | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/arch/powerpc/tools/unrel_branch_check.sh b/arch/powerpc/tools/unrel_branch_check.sh index 6e6a30aea3ed..4c1e04ba5081 100755 --- a/arch/powerpc/tools/unrel_branch_check.sh +++ b/arch/powerpc/tools/unrel_branch_check.sh @@ -1,3 +1,4 @@ +#!/bin/bash # Copyright © 2016 IBM Corporation # # This program is free software; you can redistribute it and/or @@ -26,7 +27,7 @@ awk '{print $1}' BRANCHES=$( $objdump -R "$vmlinux" -D --start-address=0xc000000000000000 \ - --stop-address=${end_intr} | + --stop-address="$end_intr" | grep -e "^c[0-9a-f]*:[[:space:]]*\([0-9a-f][0-9a-f][[:space:]]\)\{4\}[[:space:]]*b" | grep -v '\<__start_initialization_multiplatform>' | grep -v -e 'b.\?.\?ctr' | @@ -40,12 +41,12 @@ awk '{ print $1 ":" $6 ":0x" $7 ":" $8 " "}' for tuple in $BRANCHES do - from=`echo $tuple | cut -d':' -f1` - branch=`echo $tuple | cut -d':' -f2` - to=`echo $tuple | cut -d':' -f3 | sed 's/cr[0-7],//'` - sym=`echo $tuple | cut -d':' -f4` + from=$(echo "$tuple" | cut -d':' -f1) + branch=$(echo "$tuple" | cut -d':' -f2) + to=$(echo "$tuple" | cut -d':' -f3 | sed 's/cr[0-7],//') + sym=$(echo "$tuple" | cut -d':' -f4) - if (( $to > $end_intr )) + if (( to > end_intr )) then if [ -z "$bad_branches" ]; then echo "WARNING: Unrelocated relative branches" From 20ff8ec182160df86571a8af5773ff1e52837d73 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Wed, 12 Aug 2020 00:04:29 +1000 Subject: [PATCH 060/645] powerpc: unrel_branch_check.sh: simplify and combine some executions Also some minor style changes. There should still be no change in behaviour. Signed-off-by: Stephen Rothwell Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200811140435.20957-3-sfr@canb.auug.org.au --- arch/powerpc/tools/unrel_branch_check.sh | 25 +++++++++++------------- 1 file changed, 11 insertions(+), 14 deletions(-) diff --git a/arch/powerpc/tools/unrel_branch_check.sh b/arch/powerpc/tools/unrel_branch_check.sh index 4c1e04ba5081..d735e3875b5e 100755 --- a/arch/powerpc/tools/unrel_branch_check.sh +++ b/arch/powerpc/tools/unrel_branch_check.sh @@ -17,37 +17,34 @@ objdump="$1" vmlinux="$2" #__end_interrupts should be located within the first 64K +kstart=0xc000000000000000 +printf -v kend '0x%x' $(( kstart + 0x10000 )) end_intr=0x$( -$objdump -R "$vmlinux" -d --start-address=0xc000000000000000 \ - --stop-address=0xc000000000010000 | -grep '\<__end_interrupts>:' | -awk '{print $1}' +$objdump -R -d --start-address="$kstart" --stop-address="$kend" "$vmlinux" | +awk '$2 == "<__end_interrupts>:" { print $1 }' ) BRANCHES=$( -$objdump -R "$vmlinux" -D --start-address=0xc000000000000000 \ - --stop-address="$end_intr" | +$objdump -R -D --start-address="$kstart" --stop-address="$end_intr" "$vmlinux" | grep -e "^c[0-9a-f]*:[[:space:]]*\([0-9a-f][0-9a-f][[:space:]]\)\{4\}[[:space:]]*b" | -grep -v '\<__start_initialization_multiplatform>' | -grep -v -e 'b.\?.\?ctr' | -grep -v -e 'b.\?.\?lr' | -sed -e 's/\bbt.\?[[:space:]]*[[:digit:]][[:digit:]]*,/beq/' \ +sed -e '/\<__start_initialization_multiplatform>/d' \ + -e '/b.\?.\?ctr/d' \ + -e '/b.\?.\?lr/d' \ + -e 's/\bbt.\?[[:space:]]*[[:digit:]][[:digit:]]*,/beq/' \ -e 's/\bbf.\?[[:space:]]*[[:digit:]][[:digit:]]*,/bne/' \ -e 's/[[:space:]]0x/ /' \ -e 's/://' | awk '{ print $1 ":" $6 ":0x" $7 ":" $8 " "}' ) -for tuple in $BRANCHES -do +for tuple in $BRANCHES; do from=$(echo "$tuple" | cut -d':' -f1) branch=$(echo "$tuple" | cut -d':' -f2) to=$(echo "$tuple" | cut -d':' -f3 | sed 's/cr[0-7],//') sym=$(echo "$tuple" | cut -d':' -f4) - if (( to > end_intr )) - then + if (( to > end_intr )); then if [ -z "$bad_branches" ]; then echo "WARNING: Unrelocated relative branches" bad_branches="yes" From 4e71106c343c625c0bf72a65b244e35e7d2cd037 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Wed, 12 Aug 2020 00:04:30 +1000 Subject: [PATCH 061/645] powerpc: unrel_branch_check.sh: simplify objdump's asm output We don't use the raw hex instruction dump, so elide it and adjust the following expressions. Also use \s instead of [[:space:]] everywhere. Signed-off-by: Stephen Rothwell Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200811140435.20957-4-sfr@canb.auug.org.au --- arch/powerpc/tools/unrel_branch_check.sh | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/powerpc/tools/unrel_branch_check.sh b/arch/powerpc/tools/unrel_branch_check.sh index d735e3875b5e..7e936e2cf70d 100755 --- a/arch/powerpc/tools/unrel_branch_check.sh +++ b/arch/powerpc/tools/unrel_branch_check.sh @@ -26,16 +26,16 @@ awk '$2 == "<__end_interrupts>:" { print $1 }' ) BRANCHES=$( -$objdump -R -D --start-address="$kstart" --stop-address="$end_intr" "$vmlinux" | -grep -e "^c[0-9a-f]*:[[:space:]]*\([0-9a-f][0-9a-f][[:space:]]\)\{4\}[[:space:]]*b" | +$objdump -R -D --no-show-raw-insn --start-address="$kstart" --stop-address="$end_intr" "$vmlinux" | +grep -e "^c[0-9a-f]*:\s*b" | sed -e '/\<__start_initialization_multiplatform>/d' \ -e '/b.\?.\?ctr/d' \ -e '/b.\?.\?lr/d' \ - -e 's/\bbt.\?[[:space:]]*[[:digit:]][[:digit:]]*,/beq/' \ - -e 's/\bbf.\?[[:space:]]*[[:digit:]][[:digit:]]*,/bne/' \ - -e 's/[[:space:]]0x/ /' \ + -e 's/\bbt.\?\s*[[:digit:]][[:digit:]]*,/beq/' \ + -e 's/\bbf.\?\s*[[:digit:]][[:digit:]]*,/bne/' \ + -e 's/\s0x/ /' \ -e 's/://' | -awk '{ print $1 ":" $6 ":0x" $7 ":" $8 " "}' +awk '{ print $1 ":" $2 ":0x" $3 ":" $4 " "}' ) for tuple in $BRANCHES; do From 3d97abbc9f6fe90973551f3e3eef47ffef863114 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Wed, 12 Aug 2020 00:04:31 +1000 Subject: [PATCH 062/645] powerpc: unrel_branch_check.sh: convert grep | sed | awk to just sed Also start using sed -E and make all the separate expressions into a single one with comments. Pull the stripping of condition registers back into the sed command. Signed-off-by: Stephen Rothwell Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200811140435.20957-5-sfr@canb.auug.org.au --- arch/powerpc/tools/unrel_branch_check.sh | 30 ++++++++++++++++-------- 1 file changed, 20 insertions(+), 10 deletions(-) diff --git a/arch/powerpc/tools/unrel_branch_check.sh b/arch/powerpc/tools/unrel_branch_check.sh index 7e936e2cf70d..dc82289b2252 100755 --- a/arch/powerpc/tools/unrel_branch_check.sh +++ b/arch/powerpc/tools/unrel_branch_check.sh @@ -27,21 +27,31 @@ awk '$2 == "<__end_interrupts>:" { print $1 }' BRANCHES=$( $objdump -R -D --no-show-raw-insn --start-address="$kstart" --stop-address="$end_intr" "$vmlinux" | -grep -e "^c[0-9a-f]*:\s*b" | -sed -e '/\<__start_initialization_multiplatform>/d' \ - -e '/b.\?.\?ctr/d' \ - -e '/b.\?.\?lr/d' \ - -e 's/\bbt.\?\s*[[:digit:]][[:digit:]]*,/beq/' \ - -e 's/\bbf.\?\s*[[:digit:]][[:digit:]]*,/bne/' \ - -e 's/\s0x/ /' \ - -e 's/://' | -awk '{ print $1 ":" $2 ":0x" $3 ":" $4 " "}' +sed -E -n ' +# match lines that start with a kernel address +/^c[0-9a-f]*:\s*b/ { + # drop a target that we do not care about + /\<__start_initialization_multiplatform>/d + # drop branches via ctr or lr + /\ end_intr )); then From b84eaab6ede6477484edc043456cf7d7cfc7f8b3 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Wed, 12 Aug 2020 00:04:32 +1000 Subject: [PATCH 063/645] powerpc: unrel_branch_check.sh: simplify and tidy up the final loop Signed-off-by: Stephen Rothwell Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200811140435.20957-6-sfr@canb.auug.org.au --- arch/powerpc/tools/unrel_branch_check.sh | 26 +++++++++--------------- 1 file changed, 10 insertions(+), 16 deletions(-) diff --git a/arch/powerpc/tools/unrel_branch_check.sh b/arch/powerpc/tools/unrel_branch_check.sh index dc82289b2252..54ebd05615d4 100755 --- a/arch/powerpc/tools/unrel_branch_check.sh +++ b/arch/powerpc/tools/unrel_branch_check.sh @@ -25,7 +25,6 @@ $objdump -R -d --start-address="$kstart" --stop-address="$kend" "$vmlinux" | awk '$2 == "<__end_interrupts>:" { print $1 }' ) -BRANCHES=$( $objdump -R -D --no-show-raw-insn --start-address="$kstart" --stop-address="$end_intr" "$vmlinux" | sed -E -n ' # match lines that start with a kernel address @@ -45,24 +44,19 @@ sed -E -n ' # strip out condition registers s/:0xcr[0-7],/:0x/ p -}' -) - -for tuple in $BRANCHES; do - from=$(echo "$tuple" | cut -d':' -f1) - branch=$(echo "$tuple" | cut -d':' -f2) - to=$(echo "$tuple" | cut -d':' -f3) - sym=$(echo "$tuple" | cut -d':' -f4) +}' | { +all_good=true +while IFS=: read -r from branch to sym; do if (( to > end_intr )); then - if [ -z "$bad_branches" ]; then - echo "WARNING: Unrelocated relative branches" - bad_branches="yes" + if $all_good; then + printf '%s\n' 'WARNING: Unrelocated relative branches' + all_good=false fi - echo "$from $branch-> $to $sym" + printf '%s %s-> %s %s\n' "$from" "$branch" "$to" "$sym" fi done -if [ -z "$bad_branches" ]; then - exit 0 -fi +$all_good + +} From 3745ae63b405b09c86718f95d96c4b2d2827b087 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Wed, 12 Aug 2020 00:04:33 +1000 Subject: [PATCH 064/645] powerpc: unrel_branch_check.sh: fix up the file header Signed-off-by: Stephen Rothwell Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200811140435.20957-7-sfr@canb.auug.org.au --- arch/powerpc/tools/unrel_branch_check.sh | 15 ++++----------- 1 file changed, 4 insertions(+), 11 deletions(-) diff --git a/arch/powerpc/tools/unrel_branch_check.sh b/arch/powerpc/tools/unrel_branch_check.sh index 54ebd05615d4..4489f16a443c 100755 --- a/arch/powerpc/tools/unrel_branch_check.sh +++ b/arch/powerpc/tools/unrel_branch_check.sh @@ -1,16 +1,9 @@ #!/bin/bash -# Copyright © 2016 IBM Corporation +# SPDX-License-Identifier: GPL-2.0+ +# Copyright © 2016,2020 IBM Corporation # -# This program is free software; you can redistribute it and/or -# modify it under the terms of the GNU General Public License -# as published by the Free Software Foundation; either version -# 2 of the License, or (at your option) any later version. -# -# This script checks the relocations of a vmlinux for "suspicious" -# branches from unrelocated code (head_64.S code). - -# Turn this on if you want more debug output: -# set -x +# This script checks the unrelocated code of a vmlinux for "suspicious" +# branches to relocated code (head_64.S code). # Have Kbuild supply the path to objdump so we handle cross compilation. objdump="$1" From af13a2244d59c4d63a25abd8257cbaef9d9ffebc Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Wed, 12 Aug 2020 00:04:34 +1000 Subject: [PATCH 065/645] powerpc: unrel_branch_check.sh: exit silently for early errors If we can't find the address of __end_interrupts, then we still exit successfully as that is the current behaviour. Signed-off-by: Stephen Rothwell Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200811140435.20957-8-sfr@canb.auug.org.au --- arch/powerpc/tools/unrel_branch_check.sh | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/tools/unrel_branch_check.sh b/arch/powerpc/tools/unrel_branch_check.sh index 4489f16a443c..70da90270c78 100755 --- a/arch/powerpc/tools/unrel_branch_check.sh +++ b/arch/powerpc/tools/unrel_branch_check.sh @@ -14,9 +14,12 @@ kstart=0xc000000000000000 printf -v kend '0x%x' $(( kstart + 0x10000 )) end_intr=0x$( -$objdump -R -d --start-address="$kstart" --stop-address="$kend" "$vmlinux" | +$objdump -R -d --start-address="$kstart" --stop-address="$kend" "$vmlinux" 2>/dev/null | awk '$2 == "<__end_interrupts>:" { print $1 }' ) +if [ "$end_intr" = "0x" ]; then + exit 0 +fi $objdump -R -D --no-show-raw-insn --start-address="$kstart" --stop-address="$end_intr" "$vmlinux" | sed -E -n ' From b71dca9891b330d5c2d3ff5d41704aa6f64f8e32 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Wed, 12 Aug 2020 18:10:35 +1000 Subject: [PATCH 066/645] powerpc: unrel_branch_check.sh: use nm to find symbol value This is considerably faster then parsing the objdump asm output. It will also make the enabling of llvm-objdump a little easier. Signed-off-by: Stephen Rothwell Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200812081036.7969-2-sfr@canb.auug.org.au --- arch/powerpc/Makefile.postlink | 2 +- arch/powerpc/tools/unrel_branch_check.sh | 13 +++++-------- 2 files changed, 6 insertions(+), 9 deletions(-) diff --git a/arch/powerpc/Makefile.postlink b/arch/powerpc/Makefile.postlink index 2268396ff4bb..a6c77f4d32b2 100644 --- a/arch/powerpc/Makefile.postlink +++ b/arch/powerpc/Makefile.postlink @@ -18,7 +18,7 @@ quiet_cmd_relocs_check = CHKREL $@ ifdef CONFIG_PPC_BOOK3S_64 cmd_relocs_check = \ $(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/relocs_check.sh "$(OBJDUMP)" "$(NM)" "$@" ; \ - $(BASH) $(srctree)/arch/powerpc/tools/unrel_branch_check.sh "$(OBJDUMP)" "$@" + $(BASH) $(srctree)/arch/powerpc/tools/unrel_branch_check.sh "$(OBJDUMP)" "$(NM)" "$@" else cmd_relocs_check = \ $(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/relocs_check.sh "$(OBJDUMP)" "$(NM)" "$@" diff --git a/arch/powerpc/tools/unrel_branch_check.sh b/arch/powerpc/tools/unrel_branch_check.sh index 70da90270c78..0369eb2e7e4b 100755 --- a/arch/powerpc/tools/unrel_branch_check.sh +++ b/arch/powerpc/tools/unrel_branch_check.sh @@ -5,18 +5,15 @@ # This script checks the unrelocated code of a vmlinux for "suspicious" # branches to relocated code (head_64.S code). -# Have Kbuild supply the path to objdump so we handle cross compilation. +# Have Kbuild supply the path to objdump and nm so we handle cross compilation. objdump="$1" -vmlinux="$2" +nm="$2" +vmlinux="$3" -#__end_interrupts should be located within the first 64K kstart=0xc000000000000000 -printf -v kend '0x%x' $(( kstart + 0x10000 )) -end_intr=0x$( -$objdump -R -d --start-address="$kstart" --stop-address="$kend" "$vmlinux" 2>/dev/null | -awk '$2 == "<__end_interrupts>:" { print $1 }' -) +end_intr=0x$($nm -p "$vmlinux" | + sed -E -n '/\s+[[:alpha:]]\s+__end_interrupts\s*$/{s///p;q}') if [ "$end_intr" = "0x" ]; then exit 0 fi From 6b1992bcdee8b86a74362192d4d8906731918bcc Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Wed, 12 Aug 2020 18:10:36 +1000 Subject: [PATCH 067/645] powerpc: unrel_branch_check.sh: enable the use of llvm-objdump v9, 10 or 11 Currently, using llvm-objtool, this script just silently succeeds without actually do the intended checking. So this updates it to work properly. Firstly, llvm-objdump does not add target symbol names to the end of branches in its asm output, so we have to drop the branch to __start_initialization_multiplatform using its address. Secondly, v9 and 10 specify branch targets as .+, so we convert those to actual addresses. Thirdly, v10 and 11 error out on a vmlinux if given the -R option complaining that it is "not a dynamic object". The -R does not make any difference to the asm output, so remove it. Lastly, v11 produces asm that is very similar to Gnu objtool (at least as far as branches are concerned), so no further changes are necessary to make it work. Signed-off-by: Stephen Rothwell Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200812081036.7969-3-sfr@canb.auug.org.au --- arch/powerpc/tools/unrel_branch_check.sh | 34 ++++++++++++++++++++---- 1 file changed, 29 insertions(+), 5 deletions(-) diff --git a/arch/powerpc/tools/unrel_branch_check.sh b/arch/powerpc/tools/unrel_branch_check.sh index 0369eb2e7e4b..8301efee1e6c 100755 --- a/arch/powerpc/tools/unrel_branch_check.sh +++ b/arch/powerpc/tools/unrel_branch_check.sh @@ -18,12 +18,16 @@ if [ "$end_intr" = "0x" ]; then exit 0 fi -$objdump -R -D --no-show-raw-insn --start-address="$kstart" --stop-address="$end_intr" "$vmlinux" | +# we know that there is a correct branch to +# __start_initialization_multiplatform, so find its address +# so we can exclude it. +sim=0x$($nm -p "$vmlinux" | + sed -E -n '/\s+[[:alpha:]]\s+__start_initialization_multiplatform\s*$/{s///p;q}') + +$objdump -D --no-show-raw-insn --start-address="$kstart" --stop-address="$end_intr" "$vmlinux" | sed -E -n ' # match lines that start with a kernel address /^c[0-9a-f]*:\s*b/ { - # drop a target that we do not care about - /\<__start_initialization_multiplatform>/d # drop branches via ctr or lr /\= 0x2000000 )); then + to=$(( to - 0x4000000 )) + fi + elif (( to >= 0x8000 )); then + to=$(( to - 0x10000 )) + fi + printf -v to '0x%x' $(( "0x$from" + to )) + ;; + *) printf 'Unkown branch format\n' + ;; + esac + if [ "$to" = "$sim" ]; then + continue + fi if (( to > end_intr )); then if $all_good; then printf '%s\n' 'WARNING: Unrelocated relative branches' From 76d46a1e2fe2c35f24c07b7cc8a41afbf98b349e Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 14 Aug 2020 05:49:29 +0000 Subject: [PATCH 068/645] powerpc: Remove flush_instruction_cache() on 8xx flush_instruction_cache() is never used on 8xx, remove it. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/245cabd8f291facac8c8c5fd370e361a69e02860.1597384145.git.christophe.leroy@csgroup.eu --- arch/powerpc/mm/nohash/8xx.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/arch/powerpc/mm/nohash/8xx.c b/arch/powerpc/mm/nohash/8xx.c index d2b37146ae6c..231ca95f9ffb 100644 --- a/arch/powerpc/mm/nohash/8xx.c +++ b/arch/powerpc/mm/nohash/8xx.c @@ -244,13 +244,6 @@ void set_context(unsigned long id, pgd_t *pgd) mb(); } -void flush_instruction_cache(void) -{ - isync(); - mtspr(SPRN_IC_CST, IDC_INVALL); - isync(); -} - #ifdef CONFIG_PPC_KUEP void __init setup_kuep(bool disabled) { From c20beffeec3cb6f6f52d9aef27f91a3f453a91f4 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Wed, 12 Aug 2020 12:25:16 +0000 Subject: [PATCH 069/645] powerpc/uaccess: Use flexible addressing with __put_user()/__get_user() At the time being, __put_user()/__get_user() and friends only use D-form addressing, with 0 offset. Ex: lwz reg1, 0(reg2) Give the compiler the opportunity to use other adressing modes whenever possible, to get more optimised code. Hereunder is a small exemple: struct test { u32 item1; u16 item2; u8 item3; u64 item4; }; int set_test_user(struct test __user *from, struct test __user *to) { int err; u32 item1; u16 item2; u8 item3; u64 item4; err = __get_user(item1, &from->item1); err |= __get_user(item2, &from->item2); err |= __get_user(item3, &from->item3); err |= __get_user(item4, &from->item4); err |= __put_user(item1, &to->item1); err |= __put_user(item2, &to->item2); err |= __put_user(item3, &to->item3); err |= __put_user(item4, &to->item4); return err; } Before the patch: 00000df0 : df0: 94 21 ff f0 stwu r1,-16(r1) df4: 39 40 00 00 li r10,0 df8: 93 c1 00 08 stw r30,8(r1) dfc: 93 e1 00 0c stw r31,12(r1) e00: 7d 49 53 78 mr r9,r10 e04: 80 a3 00 00 lwz r5,0(r3) e08: 38 e3 00 04 addi r7,r3,4 e0c: 7d 46 53 78 mr r6,r10 e10: a0 e7 00 00 lhz r7,0(r7) e14: 7d 29 33 78 or r9,r9,r6 e18: 39 03 00 06 addi r8,r3,6 e1c: 7d 46 53 78 mr r6,r10 e20: 89 08 00 00 lbz r8,0(r8) e24: 7d 29 33 78 or r9,r9,r6 e28: 38 63 00 08 addi r3,r3,8 e2c: 7d 46 53 78 mr r6,r10 e30: 83 c3 00 00 lwz r30,0(r3) e34: 83 e3 00 04 lwz r31,4(r3) e38: 7d 29 33 78 or r9,r9,r6 e3c: 7d 43 53 78 mr r3,r10 e40: 90 a4 00 00 stw r5,0(r4) e44: 7d 29 1b 78 or r9,r9,r3 e48: 38 c4 00 04 addi r6,r4,4 e4c: 7d 43 53 78 mr r3,r10 e50: b0 e6 00 00 sth r7,0(r6) e54: 7d 29 1b 78 or r9,r9,r3 e58: 38 e4 00 06 addi r7,r4,6 e5c: 7d 43 53 78 mr r3,r10 e60: 99 07 00 00 stb r8,0(r7) e64: 7d 23 1b 78 or r3,r9,r3 e68: 38 84 00 08 addi r4,r4,8 e6c: 93 c4 00 00 stw r30,0(r4) e70: 93 e4 00 04 stw r31,4(r4) e74: 7c 63 53 78 or r3,r3,r10 e78: 83 c1 00 08 lwz r30,8(r1) e7c: 83 e1 00 0c lwz r31,12(r1) e80: 38 21 00 10 addi r1,r1,16 e84: 4e 80 00 20 blr After the patch: 00000dbc : dbc: 39 40 00 00 li r10,0 dc0: 7d 49 53 78 mr r9,r10 dc4: 80 03 00 00 lwz r0,0(r3) dc8: 7d 48 53 78 mr r8,r10 dcc: a1 63 00 04 lhz r11,4(r3) dd0: 7d 29 43 78 or r9,r9,r8 dd4: 7d 48 53 78 mr r8,r10 dd8: 88 a3 00 06 lbz r5,6(r3) ddc: 7d 29 43 78 or r9,r9,r8 de0: 7d 48 53 78 mr r8,r10 de4: 80 c3 00 08 lwz r6,8(r3) de8: 80 e3 00 0c lwz r7,12(r3) dec: 7d 29 43 78 or r9,r9,r8 df0: 7d 43 53 78 mr r3,r10 df4: 90 04 00 00 stw r0,0(r4) df8: 7d 29 1b 78 or r9,r9,r3 dfc: 7d 43 53 78 mr r3,r10 e00: b1 64 00 04 sth r11,4(r4) e04: 7d 29 1b 78 or r9,r9,r3 e08: 7d 43 53 78 mr r3,r10 e0c: 98 a4 00 06 stb r5,6(r4) e10: 7d 23 1b 78 or r3,r9,r3 e14: 90 c4 00 08 stw r6,8(r4) e18: 90 e4 00 0c stw r7,12(r4) e1c: 7c 63 53 78 or r3,r3,r10 e20: 4e 80 00 20 blr Signed-off-by: Christophe Leroy Reviewed-by: Segher Boessenkool Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/c27bc4e598daf3bbb225de7a1f5c52121cf1e279.1597235091.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/uaccess.h | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 00699903f1ef..b1d5e8b66b31 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -158,7 +158,7 @@ extern long __put_user_bad(void); */ #define __put_user_asm(x, addr, err, op) \ __asm__ __volatile__( \ - "1: " op " %1,0(%2) # put_user\n" \ + "1: " op "%X2 %1,%2 # put_user\n" \ "2:\n" \ ".section .fixup,\"ax\"\n" \ "3: li %0,%3\n" \ @@ -166,7 +166,7 @@ extern long __put_user_bad(void); ".previous\n" \ EX_TABLE(1b, 3b) \ : "=r" (err) \ - : "r" (x), "b" (addr), "i" (-EFAULT), "0" (err)) + : "r" (x), "m" (*addr), "i" (-EFAULT), "0" (err)) #ifdef __powerpc64__ #define __put_user_asm2(x, ptr, retval) \ @@ -174,8 +174,8 @@ extern long __put_user_bad(void); #else /* __powerpc64__ */ #define __put_user_asm2(x, addr, err) \ __asm__ __volatile__( \ - "1: stw %1,0(%2)\n" \ - "2: stw %1+1,4(%2)\n" \ + "1: stw%X2 %1,%2\n" \ + "2: stw%X2 %L1,%L2\n" \ "3:\n" \ ".section .fixup,\"ax\"\n" \ "4: li %0,%3\n" \ @@ -184,7 +184,7 @@ extern long __put_user_bad(void); EX_TABLE(1b, 4b) \ EX_TABLE(2b, 4b) \ : "=r" (err) \ - : "r" (x), "b" (addr), "i" (-EFAULT), "0" (err)) + : "r" (x), "m" (*addr), "i" (-EFAULT), "0" (err)) #endif /* __powerpc64__ */ #define __put_user_size_allowed(x, ptr, size, retval) \ @@ -316,7 +316,7 @@ extern long __get_user_bad(void); #define __get_user_asm(x, addr, err, op) \ __asm__ __volatile__( \ - "1: "op" %1,0(%2) # get_user\n" \ + "1: "op"%X2 %1, %2 # get_user\n" \ "2:\n" \ ".section .fixup,\"ax\"\n" \ "3: li %0,%3\n" \ @@ -325,7 +325,7 @@ extern long __get_user_bad(void); ".previous\n" \ EX_TABLE(1b, 3b) \ : "=r" (err), "=r" (x) \ - : "b" (addr), "i" (-EFAULT), "0" (err)) + : "m" (*addr), "i" (-EFAULT), "0" (err)) #ifdef __powerpc64__ #define __get_user_asm2(x, addr, err) \ @@ -333,8 +333,8 @@ extern long __get_user_bad(void); #else /* __powerpc64__ */ #define __get_user_asm2(x, addr, err) \ __asm__ __volatile__( \ - "1: lwz %1,0(%2)\n" \ - "2: lwz %1+1,4(%2)\n" \ + "1: lwz%X2 %1, %2\n" \ + "2: lwz%X2 %L1, %L2\n" \ "3:\n" \ ".section .fixup,\"ax\"\n" \ "4: li %0,%3\n" \ @@ -345,7 +345,7 @@ extern long __get_user_bad(void); EX_TABLE(1b, 4b) \ EX_TABLE(2b, 4b) \ : "=r" (err), "=&r" (x) \ - : "b" (addr), "i" (-EFAULT), "0" (err)) + : "m" (*addr), "i" (-EFAULT), "0" (err)) #endif /* __powerpc64__ */ #define __get_user_size_allowed(x, ptr, size, retval) \ @@ -355,10 +355,10 @@ do { \ if (size > sizeof(x)) \ (x) = __get_user_bad(); \ switch (size) { \ - case 1: __get_user_asm(x, ptr, retval, "lbz"); break; \ - case 2: __get_user_asm(x, ptr, retval, "lhz"); break; \ - case 4: __get_user_asm(x, ptr, retval, "lwz"); break; \ - case 8: __get_user_asm2(x, ptr, retval); break; \ + case 1: __get_user_asm(x, (u8 __user *)ptr, retval, "lbz"); break; \ + case 2: __get_user_asm(x, (u16 __user *)ptr, retval, "lhz"); break; \ + case 4: __get_user_asm(x, (u32 __user *)ptr, retval, "lwz"); break; \ + case 8: __get_user_asm2(x, (u64 __user *)ptr, retval); break; \ default: (x) = __get_user_bad(); \ } \ } while (0) From 1c4dd334df3a0627ff57b35612057e2b497e373b Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Tue, 1 Sep 2020 16:26:50 +0200 Subject: [PATCH 070/645] lib: decompress_unzstd: Limit output size The zstd decompression code, as it is right now, will most likely fail on 32-bit systems, as the default output buffer size causes the buffer's end address to overflow. Address this issue by setting a sane default to the default output size, with a value that won't overflow the buffer's end address. Signed-off-by: Paul Cercueil Reviewed-by: Nick Terrell Signed-off-by: Thomas Bogendoerfer --- lib/decompress_unzstd.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/lib/decompress_unzstd.c b/lib/decompress_unzstd.c index 0ad2c15479ed..790abc472f5b 100644 --- a/lib/decompress_unzstd.c +++ b/lib/decompress_unzstd.c @@ -178,8 +178,13 @@ static int INIT __unzstd(unsigned char *in_buf, long in_len, int err; size_t ret; + /* + * ZSTD decompression code won't be happy if the buffer size is so big + * that its end address overflows. When the size is not provided, make + * it as big as possible without having the end address overflow. + */ if (out_len == 0) - out_len = LONG_MAX; /* no limit */ + out_len = UINTPTR_MAX - (uintptr_t)out_buf; if (fill == NULL && flush == NULL) /* From a510b616131f85215ba156ed67e5ed1c0701f80f Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Tue, 1 Sep 2020 16:26:51 +0200 Subject: [PATCH 071/645] MIPS: Add support for ZSTD-compressed kernels Add support for self-extracting kernels with a ZSTD compression. Tested on a kernel for the GCW-Zero, it allows to reduce the size of the kernel file from 4.1 MiB with gzip to 3.5 MiB with ZSTD, and boots just as fast. Compressed kernels are now also compiled with -D__DISABLE_EXPORTS in order to disable the EXPORT_SYMBOL() macros inside of lib/zstd/decompress.c. Signed-off-by: Paul Cercueil Signed-off-by: Thomas Bogendoerfer --- arch/mips/Kconfig | 1 + arch/mips/boot/compressed/Makefile | 3 ++- arch/mips/boot/compressed/decompress.c | 4 ++++ arch/mips/boot/compressed/string.c | 17 +++++++++++++++++ 4 files changed, 24 insertions(+), 1 deletion(-) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 99220e7e465e..a35dd02fc82c 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -1860,6 +1860,7 @@ config SYS_SUPPORTS_ZBOOT select HAVE_KERNEL_LZMA select HAVE_KERNEL_LZO select HAVE_KERNEL_XZ + select HAVE_KERNEL_ZSTD config SYS_SUPPORTS_ZBOOT_UART16550 bool diff --git a/arch/mips/boot/compressed/Makefile b/arch/mips/boot/compressed/Makefile index 6e56caef69f0..9a9ba77b745e 100644 --- a/arch/mips/boot/compressed/Makefile +++ b/arch/mips/boot/compressed/Makefile @@ -22,7 +22,7 @@ KBUILD_CFLAGS := $(filter-out -pg, $(KBUILD_CFLAGS)) KBUILD_CFLAGS := $(filter-out -fstack-protector, $(KBUILD_CFLAGS)) -KBUILD_CFLAGS := $(KBUILD_CFLAGS) -D__KERNEL__ \ +KBUILD_CFLAGS := $(KBUILD_CFLAGS) -D__KERNEL__ -D__DISABLE_EXPORTS \ -DBOOT_HEAP_SIZE=$(BOOT_HEAP_SIZE) -D"VMLINUX_LOAD_ADDRESS_ULL=$(VMLINUX_LOAD_ADDRESS)ull" KBUILD_AFLAGS := $(KBUILD_AFLAGS) -D__ASSEMBLY__ \ @@ -70,6 +70,7 @@ tool_$(CONFIG_KERNEL_LZ4) = lz4 tool_$(CONFIG_KERNEL_LZMA) = lzma tool_$(CONFIG_KERNEL_LZO) = lzo tool_$(CONFIG_KERNEL_XZ) = xzkern +tool_$(CONFIG_KERNEL_ZSTD) = zstd22 targets += vmlinux.bin.z $(obj)/vmlinux.bin.z: $(obj)/vmlinux.bin FORCE diff --git a/arch/mips/boot/compressed/decompress.c b/arch/mips/boot/compressed/decompress.c index 88f5d637b1c4..c61c641674e6 100644 --- a/arch/mips/boot/compressed/decompress.c +++ b/arch/mips/boot/compressed/decompress.c @@ -72,6 +72,10 @@ void error(char *x) #include "../../../../lib/decompress_unxz.c" #endif +#ifdef CONFIG_KERNEL_ZSTD +#include "../../../../lib/decompress_unzstd.c" +#endif + const unsigned long __stack_chk_guard = 0x000a0dff; void __stack_chk_fail(void) diff --git a/arch/mips/boot/compressed/string.c b/arch/mips/boot/compressed/string.c index 43beecc3587c..0b593b709228 100644 --- a/arch/mips/boot/compressed/string.c +++ b/arch/mips/boot/compressed/string.c @@ -5,6 +5,7 @@ * Very small subset of simple string routines */ +#include #include void *memcpy(void *dest, const void *src, size_t n) @@ -27,3 +28,19 @@ void *memset(void *s, int c, size_t n) ss[i] = c; return s; } + +void * __weak memmove(void *dest, const void *src, size_t n) +{ + unsigned int i; + const char *s = src; + char *d = dest; + + if ((uintptr_t)dest < (uintptr_t)src) { + for (i = 0; i < n; i++) + d[i] = s[i]; + } else { + for (i = n; i > 0; i--) + d[i - 1] = s[i - 1]; + } + return dest; +} From f0100c7f1aac7f10eb249c494de5016fcf8c0652 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Mon, 31 Aug 2020 13:14:02 -0700 Subject: [PATCH 072/645] MIPS: Use rcu to lookup a task in mipsmt_sys_sched_setaffinity() The call simply looks up the corresponding task (without iterating the tasklist), which is safe under rcu instead of the tasklist_lock. In addition, the setaffinity counter part already does this. Signed-off-by: Davidlohr Bueso Signed-off-by: Thomas Bogendoerfer --- arch/mips/kernel/mips-mt-fpaff.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/mips/kernel/mips-mt-fpaff.c b/arch/mips/kernel/mips-mt-fpaff.c index 1a08428eedcf..6c590ef27648 100644 --- a/arch/mips/kernel/mips-mt-fpaff.c +++ b/arch/mips/kernel/mips-mt-fpaff.c @@ -167,7 +167,7 @@ asmlinkage long mipsmt_sys_sched_getaffinity(pid_t pid, unsigned int len, return -EINVAL; get_online_cpus(); - read_lock(&tasklist_lock); + rcu_read_lock(); retval = -ESRCH; p = find_process_by_pid(pid); @@ -181,7 +181,7 @@ asmlinkage long mipsmt_sys_sched_getaffinity(pid_t pid, unsigned int len, cpumask_and(&mask, &allowed, cpu_active_mask); out_unlock: - read_unlock(&tasklist_lock); + rcu_read_unlock(); put_online_cpus(); if (retval) return retval; From af07fabdd2869ee67ecf42264b3341ede0f49b63 Mon Sep 17 00:00:00 2001 From: Jinyang He Date: Fri, 28 Aug 2020 09:53:03 +0800 Subject: [PATCH 073/645] MIPS: p5600: Discard UCA config selection Commit 2a5984360b01 ("MIPS: Drop CPU_SUPPORTS_UNCACHED_ACCELERATED") removed UCA config, but left the selection unused, delete it. Signed-off-by: Jinyang He Signed-off-by: Thomas Bogendoerfer --- arch/mips/Kconfig | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index a35dd02fc82c..5f4c2d43c073 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -1589,7 +1589,6 @@ config CPU_P5600 select CPU_SUPPORTS_32BIT_KERNEL select CPU_SUPPORTS_HIGHMEM select CPU_SUPPORTS_MSA - select CPU_SUPPORTS_UNCACHED_ACCELERATED select CPU_SUPPORTS_CPUFREQ select CPU_MIPSR2_IRQ_VI select CPU_MIPSR2_IRQ_EI From 263cdc37c18c976f05c3f5b90be515c72bf3d754 Mon Sep 17 00:00:00 2001 From: Jinyang He Date: Fri, 4 Sep 2020 18:29:51 +0800 Subject: [PATCH 074/645] MIPS: Loongson64: Remove unused loongson_reboot. Commit 1bdb7b76705a ("MIPS: Loongson64: Cleanup unused code") left the loongson_reboot unused, delete it. Signed-off-by: Jinyang He Signed-off-by: Thomas Bogendoerfer --- arch/mips/loongson64/reset.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/arch/mips/loongson64/reset.c b/arch/mips/loongson64/reset.c index bc7671079f0c..3bb8a1ed9348 100644 --- a/arch/mips/loongson64/reset.c +++ b/arch/mips/loongson64/reset.c @@ -15,11 +15,6 @@ #include #include -static inline void loongson_reboot(void) -{ - ((void (*)(void))ioremap(LOONGSON_BOOT_BASE, 4)) (); -} - static void loongson_restart(char *command) { From 8c2ede45edbea7e970ea6bd171fc6afbec0761b3 Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Fri, 4 Sep 2020 14:36:47 +0200 Subject: [PATCH 075/645] MIPS: dts/ingenic: Cleanup qi_lb60.dts Cleanup a bit the Device Tree file: 1. Respect the number of cells in GPIO descriptors and keyboard matrix; 2. Use 'ecc-engine' instead of deprecated 'ingenic,bch-controller' property; 3. The NAND's rb-gpios is actually active high; 3. The FRE/FWE pins must be configured in the proper mode for the NAND to work if it was not already done by the bootloader. Signed-off-by: Paul Cercueil Signed-off-by: Thomas Bogendoerfer --- arch/mips/boot/dts/ingenic/qi_lb60.dts | 133 ++++++++++++------------- 1 file changed, 66 insertions(+), 67 deletions(-) diff --git a/arch/mips/boot/dts/ingenic/qi_lb60.dts b/arch/mips/boot/dts/ingenic/qi_lb60.dts index bf298268f1a1..ba0218971572 100644 --- a/arch/mips/boot/dts/ingenic/qi_lb60.dts +++ b/arch/mips/boot/dts/ingenic/qi_lb60.dts @@ -109,74 +109,73 @@ debounce-delay-ms = <10>; wakeup-source; - row-gpios = <&gpd 18 0 &gpd 19 0 &gpd 20 0 &gpd 21 0 - &gpd 22 0 &gpd 23 0 &gpd 24 0 &gpd 26 0>; - col-gpios = <&gpc 10 0 &gpc 11 0 &gpc 12 0 &gpc 13 0 - &gpc 14 0 &gpc 15 0 &gpc 16 0 &gpc 17 0>; + row-gpios = <&gpd 18 0>, <&gpd 19 0>, <&gpd 20 0>, <&gpd 21 0>, + <&gpd 22 0>, <&gpd 23 0>, <&gpd 24 0>, <&gpd 26 0>; + col-gpios = <&gpc 10 0>, <&gpc 11 0>, <&gpc 12 0>, <&gpc 13 0>, + <&gpc 14 0>, <&gpc 15 0>, <&gpc 16 0>, <&gpc 17 0>; gpio-activelow; - linux,keymap = < - MATRIX_KEY(0, 0, KEY_F1) /* S2 */ - MATRIX_KEY(0, 1, KEY_F2) /* S3 */ - MATRIX_KEY(0, 2, KEY_F3) /* S4 */ - MATRIX_KEY(0, 3, KEY_F4) /* S5 */ - MATRIX_KEY(0, 4, KEY_F5) /* S6 */ - MATRIX_KEY(0, 5, KEY_F6) /* S7 */ - MATRIX_KEY(0, 6, KEY_F7) /* S8 */ + linux,keymap = + , /* S2 */ + , /* S3 */ + , /* S4 */ + , /* S5 */ + , /* S6 */ + , /* S7 */ + , /* S8 */ - MATRIX_KEY(1, 0, KEY_Q) /* S10 */ - MATRIX_KEY(1, 1, KEY_W) /* S11 */ - MATRIX_KEY(1, 2, KEY_E) /* S12 */ - MATRIX_KEY(1, 3, KEY_R) /* S13 */ - MATRIX_KEY(1, 4, KEY_T) /* S14 */ - MATRIX_KEY(1, 5, KEY_Y) /* S15 */ - MATRIX_KEY(1, 6, KEY_U) /* S16 */ - MATRIX_KEY(1, 7, KEY_I) /* S17 */ - MATRIX_KEY(2, 0, KEY_A) /* S18 */ - MATRIX_KEY(2, 1, KEY_S) /* S19 */ - MATRIX_KEY(2, 2, KEY_D) /* S20 */ - MATRIX_KEY(2, 3, KEY_F) /* S21 */ - MATRIX_KEY(2, 4, KEY_G) /* S22 */ - MATRIX_KEY(2, 5, KEY_H) /* S23 */ - MATRIX_KEY(2, 6, KEY_J) /* S24 */ - MATRIX_KEY(2, 7, KEY_K) /* S25 */ - MATRIX_KEY(3, 0, KEY_ESC) /* S26 */ - MATRIX_KEY(3, 1, KEY_Z) /* S27 */ - MATRIX_KEY(3, 2, KEY_X) /* S28 */ - MATRIX_KEY(3, 3, KEY_C) /* S29 */ - MATRIX_KEY(3, 4, KEY_V) /* S30 */ - MATRIX_KEY(3, 5, KEY_B) /* S31 */ - MATRIX_KEY(3, 6, KEY_N) /* S32 */ - MATRIX_KEY(3, 7, KEY_M) /* S33 */ - MATRIX_KEY(4, 0, KEY_TAB) /* S34 */ - MATRIX_KEY(4, 1, KEY_CAPSLOCK) /* S35 */ - MATRIX_KEY(4, 2, KEY_BACKSLASH) /* S36 */ - MATRIX_KEY(4, 3, KEY_APOSTROPHE) /* S37 */ - MATRIX_KEY(4, 4, KEY_COMMA) /* S38 */ - MATRIX_KEY(4, 5, KEY_DOT) /* S39 */ - MATRIX_KEY(4, 6, KEY_SLASH) /* S40 */ - MATRIX_KEY(4, 7, KEY_UP) /* S41 */ - MATRIX_KEY(5, 0, KEY_O) /* S42 */ - MATRIX_KEY(5, 1, KEY_L) /* S43 */ - MATRIX_KEY(5, 2, KEY_EQUAL) /* S44 */ - MATRIX_KEY(5, 3, KEY_QI_UPRED) /* S45 */ - MATRIX_KEY(5, 4, KEY_SPACE) /* S46 */ - MATRIX_KEY(5, 5, KEY_QI_QI) /* S47 */ - MATRIX_KEY(5, 6, KEY_RIGHTCTRL) /* S48 */ - MATRIX_KEY(5, 7, KEY_LEFT) /* S49 */ - MATRIX_KEY(6, 0, KEY_F8) /* S50 */ - MATRIX_KEY(6, 1, KEY_P) /* S51 */ - MATRIX_KEY(6, 2, KEY_BACKSPACE)/* S52 */ - MATRIX_KEY(6, 3, KEY_ENTER) /* S53 */ - MATRIX_KEY(6, 4, KEY_QI_VOLUP) /* S54 */ - MATRIX_KEY(6, 5, KEY_QI_VOLDOWN) /* S55 */ - MATRIX_KEY(6, 6, KEY_DOWN) /* S56 */ - MATRIX_KEY(6, 7, KEY_RIGHT) /* S57 */ + , /* S10 */ + , /* S11 */ + , /* S12 */ + , /* S13 */ + , /* S14 */ + , /* S15 */ + , /* S16 */ + , /* S17 */ + , /* S18 */ + , /* S19 */ + , /* S20 */ + , /* S21 */ + , /* S22 */ + , /* S23 */ + , /* S24 */ + , /* S25 */ + , /* S26 */ + , /* S27 */ + , /* S28 */ + , /* S29 */ + , /* S30 */ + , /* S31 */ + , /* S32 */ + , /* S33 */ + , /* S34 */ + , /* S35 */ + , /* S36 */ + , /* S37 */ + , /* S38 */ + , /* S39 */ + , /* S40 */ + , /* S41 */ + , /* S42 */ + , /* S43 */ + , /* S44 */ + , /* S45 */ + , /* S46 */ + , /* S47 */ + , /* S48 */ + , /* S49 */ + , /* S50 */ + , /* S51 */ + ,/* S52 */ + , /* S53 */ + , /* S54 */ + , /* S55 */ + , /* S56 */ + , /* S57 */ - MATRIX_KEY(7, 0, KEY_LEFTSHIFT) /* S58 */ - MATRIX_KEY(7, 1, KEY_LEFTALT) /* S59 */ - MATRIX_KEY(7, 2, KEY_QI_FN) /* S60 */ - >; + , /* S58 */ + , /* S59 */ + ; /* S60 */ }; spi { @@ -261,12 +260,12 @@ #address-cells = <1>; #size-cells = <0>; - ingenic,bch-controller = <&ecc>; + ecc-engine = <&ecc>; pinctrl-names = "default"; pinctrl-0 = <&pins_nemc>; - rb-gpios = <&gpc 30 GPIO_ACTIVE_LOW>; + rb-gpios = <&gpc 30 GPIO_ACTIVE_HIGH>; nand@1 { reg = <1>; @@ -324,7 +323,7 @@ pins_nemc: nemc { function = "nand"; - groups = "nand-cs1"; + groups = "nand-fre-fwe", "nand-cs1"; }; pins_uart0: uart0 { From 802b83627f54d63d3d95d0285ec9a5d80be434c0 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Mon, 24 Aug 2020 18:32:43 +0200 Subject: [PATCH 076/645] MIPS: Convert R4600_V1_INDEX_ICACHEOP into a config option Use a new config option to enable R4600 V1 index I-cacheop workaround and remove define from different war.h files. Signed-off-by: Thomas Bogendoerfer --- arch/mips/Kconfig | 8 ++++++++ arch/mips/include/asm/mach-cavium-octeon/war.h | 1 - arch/mips/include/asm/mach-generic/war.h | 1 - arch/mips/include/asm/mach-ip22/war.h | 1 - arch/mips/include/asm/mach-ip27/war.h | 1 - arch/mips/include/asm/mach-ip28/war.h | 1 - arch/mips/include/asm/mach-ip30/war.h | 1 - arch/mips/include/asm/mach-ip32/war.h | 1 - arch/mips/include/asm/mach-malta/war.h | 1 - arch/mips/include/asm/mach-rc32434/war.h | 1 - arch/mips/include/asm/mach-rm/war.h | 1 - arch/mips/include/asm/mach-sibyte/war.h | 1 - arch/mips/include/asm/mach-tx49xx/war.h | 1 - arch/mips/include/asm/war.h | 10 ---------- arch/mips/mm/c-r4k.c | 6 ++++-- 15 files changed, 12 insertions(+), 24 deletions(-) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 5f4c2d43c073..595916e504a3 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -638,6 +638,7 @@ config SGI_IP22 select SYS_SUPPORTS_32BIT_KERNEL select SYS_SUPPORTS_64BIT_KERNEL select SYS_SUPPORTS_BIG_ENDIAN + select WAR_R4600_V1_INDEX_ICACHEOP select MIPS_L1_CACHE_SHIFT_7 help This are the SGI Indy, Challenge S and Indigo2, as well as certain @@ -2607,6 +2608,13 @@ config MIPS_ASID_BITS_VARIABLE config MIPS_CRC_SUPPORT bool +# R4600 erratum. Due to the lack of errata information the exact +# technical details aren't known. I've experimentally found that disabling +# interrupts during indexed I-cache flushes seems to be sufficient to deal +# with the issue. +config WAR_R4600_V1_INDEX_ICACHEOP + bool + # # - Highmem only makes sense for the 32-bit kernel. # - The current highmem code will only work properly on physically indexed diff --git a/arch/mips/include/asm/mach-cavium-octeon/war.h b/arch/mips/include/asm/mach-cavium-octeon/war.h index 2421411b7636..1e01e2f20086 100644 --- a/arch/mips/include/asm/mach-cavium-octeon/war.h +++ b/arch/mips/include/asm/mach-cavium-octeon/war.h @@ -9,7 +9,6 @@ #ifndef __ASM_MIPS_MACH_CAVIUM_OCTEON_WAR_H #define __ASM_MIPS_MACH_CAVIUM_OCTEON_WAR_H -#define R4600_V1_INDEX_ICACHEOP_WAR 0 #define R4600_V1_HIT_CACHEOP_WAR 0 #define R4600_V2_HIT_CACHEOP_WAR 0 #define BCM1250_M3_WAR 0 diff --git a/arch/mips/include/asm/mach-generic/war.h b/arch/mips/include/asm/mach-generic/war.h index f0f4a35d0870..7614a1545d1c 100644 --- a/arch/mips/include/asm/mach-generic/war.h +++ b/arch/mips/include/asm/mach-generic/war.h @@ -8,7 +8,6 @@ #ifndef __ASM_MACH_GENERIC_WAR_H #define __ASM_MACH_GENERIC_WAR_H -#define R4600_V1_INDEX_ICACHEOP_WAR 0 #define R4600_V1_HIT_CACHEOP_WAR 0 #define R4600_V2_HIT_CACHEOP_WAR 0 #define BCM1250_M3_WAR 0 diff --git a/arch/mips/include/asm/mach-ip22/war.h b/arch/mips/include/asm/mach-ip22/war.h index b48eb4ac362d..3424c1e8a24f 100644 --- a/arch/mips/include/asm/mach-ip22/war.h +++ b/arch/mips/include/asm/mach-ip22/war.h @@ -12,7 +12,6 @@ * R4600 CPU modules for the Indy come with both V1.7 and V2.0 processors. */ -#define R4600_V1_INDEX_ICACHEOP_WAR 1 #define R4600_V1_HIT_CACHEOP_WAR 1 #define R4600_V2_HIT_CACHEOP_WAR 1 #define BCM1250_M3_WAR 0 diff --git a/arch/mips/include/asm/mach-ip27/war.h b/arch/mips/include/asm/mach-ip27/war.h index ef3efce0094a..5a91a7564fb9 100644 --- a/arch/mips/include/asm/mach-ip27/war.h +++ b/arch/mips/include/asm/mach-ip27/war.h @@ -8,7 +8,6 @@ #ifndef __ASM_MIPS_MACH_IP27_WAR_H #define __ASM_MIPS_MACH_IP27_WAR_H -#define R4600_V1_INDEX_ICACHEOP_WAR 0 #define R4600_V1_HIT_CACHEOP_WAR 0 #define R4600_V2_HIT_CACHEOP_WAR 0 #define BCM1250_M3_WAR 0 diff --git a/arch/mips/include/asm/mach-ip28/war.h b/arch/mips/include/asm/mach-ip28/war.h index 61cd67354829..0dc70d59909e 100644 --- a/arch/mips/include/asm/mach-ip28/war.h +++ b/arch/mips/include/asm/mach-ip28/war.h @@ -8,7 +8,6 @@ #ifndef __ASM_MIPS_MACH_IP28_WAR_H #define __ASM_MIPS_MACH_IP28_WAR_H -#define R4600_V1_INDEX_ICACHEOP_WAR 0 #define R4600_V1_HIT_CACHEOP_WAR 0 #define R4600_V2_HIT_CACHEOP_WAR 0 #define BCM1250_M3_WAR 0 diff --git a/arch/mips/include/asm/mach-ip30/war.h b/arch/mips/include/asm/mach-ip30/war.h index a1fa0c1f5300..9f5c3305674c 100644 --- a/arch/mips/include/asm/mach-ip30/war.h +++ b/arch/mips/include/asm/mach-ip30/war.h @@ -5,7 +5,6 @@ #ifndef __ASM_MIPS_MACH_IP30_WAR_H #define __ASM_MIPS_MACH_IP30_WAR_H -#define R4600_V1_INDEX_ICACHEOP_WAR 0 #define R4600_V1_HIT_CACHEOP_WAR 0 #define R4600_V2_HIT_CACHEOP_WAR 0 #define BCM1250_M3_WAR 0 diff --git a/arch/mips/include/asm/mach-ip32/war.h b/arch/mips/include/asm/mach-ip32/war.h index e77b9d1b6c96..ac933b9119bb 100644 --- a/arch/mips/include/asm/mach-ip32/war.h +++ b/arch/mips/include/asm/mach-ip32/war.h @@ -8,7 +8,6 @@ #ifndef __ASM_MIPS_MACH_IP32_WAR_H #define __ASM_MIPS_MACH_IP32_WAR_H -#define R4600_V1_INDEX_ICACHEOP_WAR 0 #define R4600_V1_HIT_CACHEOP_WAR 0 #define R4600_V2_HIT_CACHEOP_WAR 0 #define BCM1250_M3_WAR 0 diff --git a/arch/mips/include/asm/mach-malta/war.h b/arch/mips/include/asm/mach-malta/war.h index d62d2ffe515e..12c6393b6f31 100644 --- a/arch/mips/include/asm/mach-malta/war.h +++ b/arch/mips/include/asm/mach-malta/war.h @@ -8,7 +8,6 @@ #ifndef __ASM_MIPS_MACH_MIPS_WAR_H #define __ASM_MIPS_MACH_MIPS_WAR_H -#define R4600_V1_INDEX_ICACHEOP_WAR 0 #define R4600_V1_HIT_CACHEOP_WAR 0 #define R4600_V2_HIT_CACHEOP_WAR 0 #define BCM1250_M3_WAR 0 diff --git a/arch/mips/include/asm/mach-rc32434/war.h b/arch/mips/include/asm/mach-rc32434/war.h index af430d26f713..62e04bea61b3 100644 --- a/arch/mips/include/asm/mach-rc32434/war.h +++ b/arch/mips/include/asm/mach-rc32434/war.h @@ -8,7 +8,6 @@ #ifndef __ASM_MIPS_MACH_MIPS_WAR_H #define __ASM_MIPS_MACH_MIPS_WAR_H -#define R4600_V1_INDEX_ICACHEOP_WAR 0 #define R4600_V1_HIT_CACHEOP_WAR 0 #define R4600_V2_HIT_CACHEOP_WAR 0 #define BCM1250_M3_WAR 0 diff --git a/arch/mips/include/asm/mach-rm/war.h b/arch/mips/include/asm/mach-rm/war.h index eca16d167c2f..fe3c17f38650 100644 --- a/arch/mips/include/asm/mach-rm/war.h +++ b/arch/mips/include/asm/mach-rm/war.h @@ -12,7 +12,6 @@ * The RM200C seems to have been shipped only with V2.0 R4600s */ -#define R4600_V1_INDEX_ICACHEOP_WAR 0 #define R4600_V1_HIT_CACHEOP_WAR 0 #define R4600_V2_HIT_CACHEOP_WAR 1 #define BCM1250_M3_WAR 0 diff --git a/arch/mips/include/asm/mach-sibyte/war.h b/arch/mips/include/asm/mach-sibyte/war.h index 4755b6116807..d34f3c1d6741 100644 --- a/arch/mips/include/asm/mach-sibyte/war.h +++ b/arch/mips/include/asm/mach-sibyte/war.h @@ -8,7 +8,6 @@ #ifndef __ASM_MIPS_MACH_SIBYTE_WAR_H #define __ASM_MIPS_MACH_SIBYTE_WAR_H -#define R4600_V1_INDEX_ICACHEOP_WAR 0 #define R4600_V1_HIT_CACHEOP_WAR 0 #define R4600_V2_HIT_CACHEOP_WAR 0 diff --git a/arch/mips/include/asm/mach-tx49xx/war.h b/arch/mips/include/asm/mach-tx49xx/war.h index 445abb4eb769..eb0375da266a 100644 --- a/arch/mips/include/asm/mach-tx49xx/war.h +++ b/arch/mips/include/asm/mach-tx49xx/war.h @@ -8,7 +8,6 @@ #ifndef __ASM_MIPS_MACH_TX49XX_WAR_H #define __ASM_MIPS_MACH_TX49XX_WAR_H -#define R4600_V1_INDEX_ICACHEOP_WAR 0 #define R4600_V1_HIT_CACHEOP_WAR 0 #define R4600_V2_HIT_CACHEOP_WAR 0 #define BCM1250_M3_WAR 0 diff --git a/arch/mips/include/asm/war.h b/arch/mips/include/asm/war.h index e43f800e662d..3c8923692fca 100644 --- a/arch/mips/include/asm/war.h +++ b/arch/mips/include/asm/war.h @@ -72,16 +72,6 @@ #define DADDI_WAR 0 #endif -/* - * Another R4600 erratum. Due to the lack of errata information the exact - * technical details aren't known. I've experimentally found that disabling - * interrupts during indexed I-cache flushes seems to be sufficient to deal - * with the issue. - */ -#ifndef R4600_V1_INDEX_ICACHEOP_WAR -#error Check setting of R4600_V1_INDEX_ICACHEOP_WAR for your platform -#endif - /* * Pleasures of the R4600 V1.x. Cite from the IDT R4600 V1.7 errata: * diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index fc5a6d25f74f..bf454da84a9b 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -366,7 +366,8 @@ static void r4k_blast_icache_page_indexed_setup(void) else if (ic_lsize == 16) r4k_blast_icache_page_indexed = blast_icache16_page_indexed; else if (ic_lsize == 32) { - if (R4600_V1_INDEX_ICACHEOP_WAR && cpu_is_r4600_v1_x()) + if (IS_ENABLED(CONFIG_WAR_R4600_V1_INDEX_ICACHEOP) && + cpu_is_r4600_v1_x()) r4k_blast_icache_page_indexed = blast_icache32_r4600_v1_page_indexed; else if (TX49XX_ICACHE_INDEX_INV_WAR) @@ -394,7 +395,8 @@ static void r4k_blast_icache_setup(void) else if (ic_lsize == 16) r4k_blast_icache = blast_icache16; else if (ic_lsize == 32) { - if (R4600_V1_INDEX_ICACHEOP_WAR && cpu_is_r4600_v1_x()) + if (IS_ENABLED(CONFIG_WAR_R4600_V1_INDEX_ICACHEOP) && + cpu_is_r4600_v1_x()) r4k_blast_icache = blast_r4600_v1_icache32; else if (TX49XX_ICACHE_INDEX_INV_WAR) r4k_blast_icache = tx49_blast_icache32; From 5e5b6527128cea50f12a7064bf61b130b3a2739a Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Mon, 24 Aug 2020 18:32:44 +0200 Subject: [PATCH 077/645] MIPS: Convert R4600_V1_HIT_CACHEOP into a config option Use a new config option to enable R4600 V1 cacheop hit workaround and remove define from the different war.h files. Signed-off-by: Thomas Bogendoerfer --- arch/mips/Kconfig | 28 +++++++++++++++++ .../mips/include/asm/mach-cavium-octeon/war.h | 1 - arch/mips/include/asm/mach-generic/war.h | 1 - arch/mips/include/asm/mach-ip22/war.h | 1 - arch/mips/include/asm/mach-ip27/war.h | 1 - arch/mips/include/asm/mach-ip28/war.h | 1 - arch/mips/include/asm/mach-ip30/war.h | 1 - arch/mips/include/asm/mach-ip32/war.h | 1 - arch/mips/include/asm/mach-malta/war.h | 1 - arch/mips/include/asm/mach-rc32434/war.h | 1 - arch/mips/include/asm/mach-rm/war.h | 1 - arch/mips/include/asm/mach-sibyte/war.h | 1 - arch/mips/include/asm/mach-tx49xx/war.h | 1 - arch/mips/include/asm/war.h | 31 ------------------- arch/mips/mm/c-r4k.c | 2 +- arch/mips/mm/page.c | 6 ++-- 16 files changed, 33 insertions(+), 46 deletions(-) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 595916e504a3..714cd81a779c 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -639,6 +639,7 @@ config SGI_IP22 select SYS_SUPPORTS_64BIT_KERNEL select SYS_SUPPORTS_BIG_ENDIAN select WAR_R4600_V1_INDEX_ICACHEOP + select WAR_R4600_V1_HIT_CACHEOP select MIPS_L1_CACHE_SHIFT_7 help This are the SGI Indy, Challenge S and Indigo2, as well as certain @@ -2615,6 +2616,33 @@ config MIPS_CRC_SUPPORT config WAR_R4600_V1_INDEX_ICACHEOP bool +# Pleasures of the R4600 V1.x. Cite from the IDT R4600 V1.7 errata: +# +# 18. The CACHE instructions Hit_Writeback_Invalidate_D, Hit_Writeback_D, +# Hit_Invalidate_D and Create_Dirty_Excl_D should only be +# executed if there is no other dcache activity. If the dcache is +# accessed for another instruction immeidately preceding when these +# cache instructions are executing, it is possible that the dcache +# tag match outputs used by these cache instructions will be +# incorrect. These cache instructions should be preceded by at least +# four instructions that are not any kind of load or store +# instruction. +# +# This is not allowed: lw +# nop +# nop +# nop +# cache Hit_Writeback_Invalidate_D +# +# This is allowed: lw +# nop +# nop +# nop +# nop +# cache Hit_Writeback_Invalidate_D +config WAR_R4600_V1_HIT_CACHEOP + bool + # # - Highmem only makes sense for the 32-bit kernel. # - The current highmem code will only work properly on physically indexed diff --git a/arch/mips/include/asm/mach-cavium-octeon/war.h b/arch/mips/include/asm/mach-cavium-octeon/war.h index 1e01e2f20086..915ce0352c20 100644 --- a/arch/mips/include/asm/mach-cavium-octeon/war.h +++ b/arch/mips/include/asm/mach-cavium-octeon/war.h @@ -9,7 +9,6 @@ #ifndef __ASM_MIPS_MACH_CAVIUM_OCTEON_WAR_H #define __ASM_MIPS_MACH_CAVIUM_OCTEON_WAR_H -#define R4600_V1_HIT_CACHEOP_WAR 0 #define R4600_V2_HIT_CACHEOP_WAR 0 #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 diff --git a/arch/mips/include/asm/mach-generic/war.h b/arch/mips/include/asm/mach-generic/war.h index 7614a1545d1c..44d14be2e1e5 100644 --- a/arch/mips/include/asm/mach-generic/war.h +++ b/arch/mips/include/asm/mach-generic/war.h @@ -8,7 +8,6 @@ #ifndef __ASM_MACH_GENERIC_WAR_H #define __ASM_MACH_GENERIC_WAR_H -#define R4600_V1_HIT_CACHEOP_WAR 0 #define R4600_V2_HIT_CACHEOP_WAR 0 #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 diff --git a/arch/mips/include/asm/mach-ip22/war.h b/arch/mips/include/asm/mach-ip22/war.h index 3424c1e8a24f..9154c54d428a 100644 --- a/arch/mips/include/asm/mach-ip22/war.h +++ b/arch/mips/include/asm/mach-ip22/war.h @@ -12,7 +12,6 @@ * R4600 CPU modules for the Indy come with both V1.7 and V2.0 processors. */ -#define R4600_V1_HIT_CACHEOP_WAR 1 #define R4600_V2_HIT_CACHEOP_WAR 1 #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 diff --git a/arch/mips/include/asm/mach-ip27/war.h b/arch/mips/include/asm/mach-ip27/war.h index 5a91a7564fb9..e7c070c85b7c 100644 --- a/arch/mips/include/asm/mach-ip27/war.h +++ b/arch/mips/include/asm/mach-ip27/war.h @@ -8,7 +8,6 @@ #ifndef __ASM_MIPS_MACH_IP27_WAR_H #define __ASM_MIPS_MACH_IP27_WAR_H -#define R4600_V1_HIT_CACHEOP_WAR 0 #define R4600_V2_HIT_CACHEOP_WAR 0 #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 diff --git a/arch/mips/include/asm/mach-ip28/war.h b/arch/mips/include/asm/mach-ip28/war.h index 0dc70d59909e..22d9f78bf552 100644 --- a/arch/mips/include/asm/mach-ip28/war.h +++ b/arch/mips/include/asm/mach-ip28/war.h @@ -8,7 +8,6 @@ #ifndef __ASM_MIPS_MACH_IP28_WAR_H #define __ASM_MIPS_MACH_IP28_WAR_H -#define R4600_V1_HIT_CACHEOP_WAR 0 #define R4600_V2_HIT_CACHEOP_WAR 0 #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 diff --git a/arch/mips/include/asm/mach-ip30/war.h b/arch/mips/include/asm/mach-ip30/war.h index 9f5c3305674c..1400b030982e 100644 --- a/arch/mips/include/asm/mach-ip30/war.h +++ b/arch/mips/include/asm/mach-ip30/war.h @@ -5,7 +5,6 @@ #ifndef __ASM_MIPS_MACH_IP30_WAR_H #define __ASM_MIPS_MACH_IP30_WAR_H -#define R4600_V1_HIT_CACHEOP_WAR 0 #define R4600_V2_HIT_CACHEOP_WAR 0 #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 diff --git a/arch/mips/include/asm/mach-ip32/war.h b/arch/mips/include/asm/mach-ip32/war.h index ac933b9119bb..f91f4eddce8f 100644 --- a/arch/mips/include/asm/mach-ip32/war.h +++ b/arch/mips/include/asm/mach-ip32/war.h @@ -8,7 +8,6 @@ #ifndef __ASM_MIPS_MACH_IP32_WAR_H #define __ASM_MIPS_MACH_IP32_WAR_H -#define R4600_V1_HIT_CACHEOP_WAR 0 #define R4600_V2_HIT_CACHEOP_WAR 0 #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 diff --git a/arch/mips/include/asm/mach-malta/war.h b/arch/mips/include/asm/mach-malta/war.h index 12c6393b6f31..a4d5d0926e81 100644 --- a/arch/mips/include/asm/mach-malta/war.h +++ b/arch/mips/include/asm/mach-malta/war.h @@ -8,7 +8,6 @@ #ifndef __ASM_MIPS_MACH_MIPS_WAR_H #define __ASM_MIPS_MACH_MIPS_WAR_H -#define R4600_V1_HIT_CACHEOP_WAR 0 #define R4600_V2_HIT_CACHEOP_WAR 0 #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 diff --git a/arch/mips/include/asm/mach-rc32434/war.h b/arch/mips/include/asm/mach-rc32434/war.h index 62e04bea61b3..82ce2d313eed 100644 --- a/arch/mips/include/asm/mach-rc32434/war.h +++ b/arch/mips/include/asm/mach-rc32434/war.h @@ -8,7 +8,6 @@ #ifndef __ASM_MIPS_MACH_MIPS_WAR_H #define __ASM_MIPS_MACH_MIPS_WAR_H -#define R4600_V1_HIT_CACHEOP_WAR 0 #define R4600_V2_HIT_CACHEOP_WAR 0 #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 diff --git a/arch/mips/include/asm/mach-rm/war.h b/arch/mips/include/asm/mach-rm/war.h index fe3c17f38650..192ec3358ad0 100644 --- a/arch/mips/include/asm/mach-rm/war.h +++ b/arch/mips/include/asm/mach-rm/war.h @@ -12,7 +12,6 @@ * The RM200C seems to have been shipped only with V2.0 R4600s */ -#define R4600_V1_HIT_CACHEOP_WAR 0 #define R4600_V2_HIT_CACHEOP_WAR 1 #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 diff --git a/arch/mips/include/asm/mach-sibyte/war.h b/arch/mips/include/asm/mach-sibyte/war.h index d34f3c1d6741..bf793d36c890 100644 --- a/arch/mips/include/asm/mach-sibyte/war.h +++ b/arch/mips/include/asm/mach-sibyte/war.h @@ -8,7 +8,6 @@ #ifndef __ASM_MIPS_MACH_SIBYTE_WAR_H #define __ASM_MIPS_MACH_SIBYTE_WAR_H -#define R4600_V1_HIT_CACHEOP_WAR 0 #define R4600_V2_HIT_CACHEOP_WAR 0 #if defined(CONFIG_SB1_PASS_2_WORKAROUNDS) diff --git a/arch/mips/include/asm/mach-tx49xx/war.h b/arch/mips/include/asm/mach-tx49xx/war.h index eb0375da266a..7da1a3ea54c7 100644 --- a/arch/mips/include/asm/mach-tx49xx/war.h +++ b/arch/mips/include/asm/mach-tx49xx/war.h @@ -8,7 +8,6 @@ #ifndef __ASM_MIPS_MACH_TX49XX_WAR_H #define __ASM_MIPS_MACH_TX49XX_WAR_H -#define R4600_V1_HIT_CACHEOP_WAR 0 #define R4600_V2_HIT_CACHEOP_WAR 0 #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 diff --git a/arch/mips/include/asm/war.h b/arch/mips/include/asm/war.h index 3c8923692fca..d336a0e57093 100644 --- a/arch/mips/include/asm/war.h +++ b/arch/mips/include/asm/war.h @@ -72,37 +72,6 @@ #define DADDI_WAR 0 #endif -/* - * Pleasures of the R4600 V1.x. Cite from the IDT R4600 V1.7 errata: - * - * 18. The CACHE instructions Hit_Writeback_Invalidate_D, Hit_Writeback_D, - * Hit_Invalidate_D and Create_Dirty_Excl_D should only be - * executed if there is no other dcache activity. If the dcache is - * accessed for another instruction immeidately preceding when these - * cache instructions are executing, it is possible that the dcache - * tag match outputs used by these cache instructions will be - * incorrect. These cache instructions should be preceded by at least - * four instructions that are not any kind of load or store - * instruction. - * - * This is not allowed: lw - * nop - * nop - * nop - * cache Hit_Writeback_Invalidate_D - * - * This is allowed: lw - * nop - * nop - * nop - * nop - * cache Hit_Writeback_Invalidate_D - */ -#ifndef R4600_V1_HIT_CACHEOP_WAR -#error Check setting of R4600_V1_HIT_CACHEOP_WAR for your platform -#endif - - /* * Writeback and invalidate the primary cache dcache before DMA. * diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index bf454da84a9b..814a295a2df2 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -132,7 +132,7 @@ struct bcache_ops *bcops = &no_sc_ops; do { \ if (R4600_V2_HIT_CACHEOP_WAR && cpu_is_r4600_v2_x()) \ *(volatile unsigned long *)CKSEG1; \ - if (R4600_V1_HIT_CACHEOP_WAR) \ + if (IS_ENABLED(CONFIG_WAR_R4600_V1_HIT_CACHEOP)) \ __asm__ __volatile__("nop;nop;nop;nop"); \ } while (0) diff --git a/arch/mips/mm/page.c b/arch/mips/mm/page.c index cd805b005509..ecad11f5c67c 100644 --- a/arch/mips/mm/page.c +++ b/arch/mips/mm/page.c @@ -250,7 +250,8 @@ static inline void build_clear_pref(u32 **buf, int off) if (cpu_has_cache_cdex_s) { uasm_i_cache(buf, Create_Dirty_Excl_SD, off, A0); } else if (cpu_has_cache_cdex_p) { - if (R4600_V1_HIT_CACHEOP_WAR && cpu_is_r4600_v1_x()) { + if (IS_ENABLED(CONFIG_WAR_R4600_V1_HIT_CACHEOP) && + cpu_is_r4600_v1_x()) { uasm_i_nop(buf); uasm_i_nop(buf); uasm_i_nop(buf); @@ -402,7 +403,8 @@ static inline void build_copy_store_pref(u32 **buf, int off) if (cpu_has_cache_cdex_s) { uasm_i_cache(buf, Create_Dirty_Excl_SD, off, A0); } else if (cpu_has_cache_cdex_p) { - if (R4600_V1_HIT_CACHEOP_WAR && cpu_is_r4600_v1_x()) { + if (IS_ENABLED(CONFIG_WAR_R4600_V1_HIT_CACHEOP) && + cpu_is_r4600_v1_x()) { uasm_i_nop(buf); uasm_i_nop(buf); uasm_i_nop(buf); From 44def3426e4ac5a2dbdb5c8304397f4daa38eb2f Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Mon, 24 Aug 2020 18:32:45 +0200 Subject: [PATCH 078/645] MIPS: Convert R4600_V2_HIT_CACHEOP into a config option Use a new config option to enable R4600 V2 cacheop hit workaround and remove define from different war.h files. Signed-off-by: Thomas Bogendoerfer --- arch/mips/Kconfig | 14 ++++++++++++++ arch/mips/include/asm/mach-cavium-octeon/war.h | 1 - arch/mips/include/asm/mach-generic/war.h | 1 - arch/mips/include/asm/mach-ip22/war.h | 5 ----- arch/mips/include/asm/mach-ip27/war.h | 1 - arch/mips/include/asm/mach-ip28/war.h | 1 - arch/mips/include/asm/mach-ip30/war.h | 1 - arch/mips/include/asm/mach-ip32/war.h | 1 - arch/mips/include/asm/mach-malta/war.h | 1 - arch/mips/include/asm/mach-rc32434/war.h | 1 - arch/mips/include/asm/mach-rm/war.h | 5 ----- arch/mips/include/asm/mach-sibyte/war.h | 2 -- arch/mips/include/asm/mach-tx49xx/war.h | 1 - arch/mips/include/asm/war.h | 15 --------------- arch/mips/mm/c-r4k.c | 3 ++- arch/mips/mm/page.c | 10 ++++++---- 16 files changed, 22 insertions(+), 41 deletions(-) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 714cd81a779c..e4198c5c2aa8 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -640,6 +640,7 @@ config SGI_IP22 select SYS_SUPPORTS_BIG_ENDIAN select WAR_R4600_V1_INDEX_ICACHEOP select WAR_R4600_V1_HIT_CACHEOP + select WAR_R4600_V2_HIT_CACHEOP select MIPS_L1_CACHE_SHIFT_7 help This are the SGI Indy, Challenge S and Indigo2, as well as certain @@ -877,6 +878,7 @@ config SNI_RM select SYS_SUPPORTS_BIG_ENDIAN select SYS_SUPPORTS_HIGHMEM select SYS_SUPPORTS_LITTLE_ENDIAN + select WAR_R4600_V2_HIT_CACHEOP help The SNI RM200/300/400 are MIPS-based machines manufactured by Siemens Nixdorf Informationssysteme (SNI), parent company of Pyramid @@ -2643,6 +2645,18 @@ config WAR_R4600_V1_INDEX_ICACHEOP config WAR_R4600_V1_HIT_CACHEOP bool +# Writeback and invalidate the primary cache dcache before DMA. +# +# R4600 v2.0 bug: "The CACHE instructions Hit_Writeback_Inv_D, +# Hit_Writeback_D, Hit_Invalidate_D and Create_Dirty_Exclusive_D will only +# operate correctly if the internal data cache refill buffer is empty. These +# CACHE instructions should be separated from any potential data cache miss +# by a load instruction to an uncached address to empty the response buffer." +# (Revision 2.0 device errata from IDT available on https://www.idt.com/ +# in .pdf format.) +config WAR_R4600_V2_HIT_CACHEOP + bool + # # - Highmem only makes sense for the 32-bit kernel. # - The current highmem code will only work properly on physically indexed diff --git a/arch/mips/include/asm/mach-cavium-octeon/war.h b/arch/mips/include/asm/mach-cavium-octeon/war.h index 915ce0352c20..4bc396d0fdd9 100644 --- a/arch/mips/include/asm/mach-cavium-octeon/war.h +++ b/arch/mips/include/asm/mach-cavium-octeon/war.h @@ -9,7 +9,6 @@ #ifndef __ASM_MIPS_MACH_CAVIUM_OCTEON_WAR_H #define __ASM_MIPS_MACH_CAVIUM_OCTEON_WAR_H -#define R4600_V2_HIT_CACHEOP_WAR 0 #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 #define MIPS4K_ICACHE_REFILL_WAR 0 diff --git a/arch/mips/include/asm/mach-generic/war.h b/arch/mips/include/asm/mach-generic/war.h index 44d14be2e1e5..4d46a880b832 100644 --- a/arch/mips/include/asm/mach-generic/war.h +++ b/arch/mips/include/asm/mach-generic/war.h @@ -8,7 +8,6 @@ #ifndef __ASM_MACH_GENERIC_WAR_H #define __ASM_MACH_GENERIC_WAR_H -#define R4600_V2_HIT_CACHEOP_WAR 0 #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 #define MIPS4K_ICACHE_REFILL_WAR 0 diff --git a/arch/mips/include/asm/mach-ip22/war.h b/arch/mips/include/asm/mach-ip22/war.h index 9154c54d428a..a5a1c41df74e 100644 --- a/arch/mips/include/asm/mach-ip22/war.h +++ b/arch/mips/include/asm/mach-ip22/war.h @@ -8,11 +8,6 @@ #ifndef __ASM_MIPS_MACH_IP22_WAR_H #define __ASM_MIPS_MACH_IP22_WAR_H -/* - * R4600 CPU modules for the Indy come with both V1.7 and V2.0 processors. - */ - -#define R4600_V2_HIT_CACHEOP_WAR 1 #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 #define MIPS4K_ICACHE_REFILL_WAR 0 diff --git a/arch/mips/include/asm/mach-ip27/war.h b/arch/mips/include/asm/mach-ip27/war.h index e7c070c85b7c..5891d506cffd 100644 --- a/arch/mips/include/asm/mach-ip27/war.h +++ b/arch/mips/include/asm/mach-ip27/war.h @@ -8,7 +8,6 @@ #ifndef __ASM_MIPS_MACH_IP27_WAR_H #define __ASM_MIPS_MACH_IP27_WAR_H -#define R4600_V2_HIT_CACHEOP_WAR 0 #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 #define MIPS4K_ICACHE_REFILL_WAR 0 diff --git a/arch/mips/include/asm/mach-ip28/war.h b/arch/mips/include/asm/mach-ip28/war.h index 22d9f78bf552..346fc567ebb3 100644 --- a/arch/mips/include/asm/mach-ip28/war.h +++ b/arch/mips/include/asm/mach-ip28/war.h @@ -8,7 +8,6 @@ #ifndef __ASM_MIPS_MACH_IP28_WAR_H #define __ASM_MIPS_MACH_IP28_WAR_H -#define R4600_V2_HIT_CACHEOP_WAR 0 #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 #define MIPS4K_ICACHE_REFILL_WAR 0 diff --git a/arch/mips/include/asm/mach-ip30/war.h b/arch/mips/include/asm/mach-ip30/war.h index 1400b030982e..f887a0a53e18 100644 --- a/arch/mips/include/asm/mach-ip30/war.h +++ b/arch/mips/include/asm/mach-ip30/war.h @@ -5,7 +5,6 @@ #ifndef __ASM_MIPS_MACH_IP30_WAR_H #define __ASM_MIPS_MACH_IP30_WAR_H -#define R4600_V2_HIT_CACHEOP_WAR 0 #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 #define MIPS4K_ICACHE_REFILL_WAR 0 diff --git a/arch/mips/include/asm/mach-ip32/war.h b/arch/mips/include/asm/mach-ip32/war.h index f91f4eddce8f..980dbd34355c 100644 --- a/arch/mips/include/asm/mach-ip32/war.h +++ b/arch/mips/include/asm/mach-ip32/war.h @@ -8,7 +8,6 @@ #ifndef __ASM_MIPS_MACH_IP32_WAR_H #define __ASM_MIPS_MACH_IP32_WAR_H -#define R4600_V2_HIT_CACHEOP_WAR 0 #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 #define MIPS4K_ICACHE_REFILL_WAR 0 diff --git a/arch/mips/include/asm/mach-malta/war.h b/arch/mips/include/asm/mach-malta/war.h index a4d5d0926e81..29f56803e3e5 100644 --- a/arch/mips/include/asm/mach-malta/war.h +++ b/arch/mips/include/asm/mach-malta/war.h @@ -8,7 +8,6 @@ #ifndef __ASM_MIPS_MACH_MIPS_WAR_H #define __ASM_MIPS_MACH_MIPS_WAR_H -#define R4600_V2_HIT_CACHEOP_WAR 0 #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 #define MIPS4K_ICACHE_REFILL_WAR 1 diff --git a/arch/mips/include/asm/mach-rc32434/war.h b/arch/mips/include/asm/mach-rc32434/war.h index 82ce2d313eed..749787bb6c8e 100644 --- a/arch/mips/include/asm/mach-rc32434/war.h +++ b/arch/mips/include/asm/mach-rc32434/war.h @@ -8,7 +8,6 @@ #ifndef __ASM_MIPS_MACH_MIPS_WAR_H #define __ASM_MIPS_MACH_MIPS_WAR_H -#define R4600_V2_HIT_CACHEOP_WAR 0 #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 #define MIPS4K_ICACHE_REFILL_WAR 1 diff --git a/arch/mips/include/asm/mach-rm/war.h b/arch/mips/include/asm/mach-rm/war.h index 192ec3358ad0..aded634ccb01 100644 --- a/arch/mips/include/asm/mach-rm/war.h +++ b/arch/mips/include/asm/mach-rm/war.h @@ -8,11 +8,6 @@ #ifndef __ASM_MIPS_MACH_RM_WAR_H #define __ASM_MIPS_MACH_RM_WAR_H -/* - * The RM200C seems to have been shipped only with V2.0 R4600s - */ - -#define R4600_V2_HIT_CACHEOP_WAR 1 #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 #define MIPS4K_ICACHE_REFILL_WAR 0 diff --git a/arch/mips/include/asm/mach-sibyte/war.h b/arch/mips/include/asm/mach-sibyte/war.h index bf793d36c890..78fd2ad4930b 100644 --- a/arch/mips/include/asm/mach-sibyte/war.h +++ b/arch/mips/include/asm/mach-sibyte/war.h @@ -8,8 +8,6 @@ #ifndef __ASM_MIPS_MACH_SIBYTE_WAR_H #define __ASM_MIPS_MACH_SIBYTE_WAR_H -#define R4600_V2_HIT_CACHEOP_WAR 0 - #if defined(CONFIG_SB1_PASS_2_WORKAROUNDS) #ifndef __ASSEMBLY__ diff --git a/arch/mips/include/asm/mach-tx49xx/war.h b/arch/mips/include/asm/mach-tx49xx/war.h index 7da1a3ea54c7..0b1666e0391a 100644 --- a/arch/mips/include/asm/mach-tx49xx/war.h +++ b/arch/mips/include/asm/mach-tx49xx/war.h @@ -8,7 +8,6 @@ #ifndef __ASM_MIPS_MACH_TX49XX_WAR_H #define __ASM_MIPS_MACH_TX49XX_WAR_H -#define R4600_V2_HIT_CACHEOP_WAR 0 #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 #define MIPS4K_ICACHE_REFILL_WAR 0 diff --git a/arch/mips/include/asm/war.h b/arch/mips/include/asm/war.h index d336a0e57093..37092c2c68e1 100644 --- a/arch/mips/include/asm/war.h +++ b/arch/mips/include/asm/war.h @@ -72,21 +72,6 @@ #define DADDI_WAR 0 #endif -/* - * Writeback and invalidate the primary cache dcache before DMA. - * - * R4600 v2.0 bug: "The CACHE instructions Hit_Writeback_Inv_D, - * Hit_Writeback_D, Hit_Invalidate_D and Create_Dirty_Exclusive_D will only - * operate correctly if the internal data cache refill buffer is empty. These - * CACHE instructions should be separated from any potential data cache miss - * by a load instruction to an uncached address to empty the response buffer." - * (Revision 2.0 device errata from IDT available on https://www.idt.com/ - * in .pdf format.) - */ -#ifndef R4600_V2_HIT_CACHEOP_WAR -#error Check setting of R4600_V2_HIT_CACHEOP_WAR for your platform -#endif - /* * Workaround for the Sibyte M3 errata the text of which can be found at * diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index 814a295a2df2..df09a3653c4f 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -130,7 +130,8 @@ struct bcache_ops *bcops = &no_sc_ops; #define R4600_HIT_CACHEOP_WAR_IMPL \ do { \ - if (R4600_V2_HIT_CACHEOP_WAR && cpu_is_r4600_v2_x()) \ + if (IS_ENABLED(CONFIG_WAR_R4600_V2_HIT_CACHEOP) && \ + cpu_is_r4600_v2_x()) \ *(volatile unsigned long *)CKSEG1; \ if (IS_ENABLED(CONFIG_WAR_R4600_V1_HIT_CACHEOP)) \ __asm__ __volatile__("nop;nop;nop;nop"); \ diff --git a/arch/mips/mm/page.c b/arch/mips/mm/page.c index ecad11f5c67c..504bc4047c4c 100644 --- a/arch/mips/mm/page.c +++ b/arch/mips/mm/page.c @@ -258,7 +258,8 @@ static inline void build_clear_pref(u32 **buf, int off) uasm_i_nop(buf); } - if (R4600_V2_HIT_CACHEOP_WAR && cpu_is_r4600_v2_x()) + if (IS_ENABLED(CONFIG_WAR_R4600_V2_HIT_CACHEOP) && + cpu_is_r4600_v2_x()) uasm_i_lw(buf, ZERO, ZERO, AT); uasm_i_cache(buf, Create_Dirty_Excl_D, off, A0); @@ -303,7 +304,7 @@ void build_clear_page(void) else uasm_i_ori(&buf, A2, A0, off); - if (R4600_V2_HIT_CACHEOP_WAR && cpu_is_r4600_v2_x()) + if (IS_ENABLED(CONFIG_WAR_R4600_V2_HIT_CACHEOP) && cpu_is_r4600_v2_x()) uasm_i_lui(&buf, AT, uasm_rel_hi(0xa0000000)); off = cache_line_size ? min(8, pref_bias_clear_store / cache_line_size) @@ -411,7 +412,8 @@ static inline void build_copy_store_pref(u32 **buf, int off) uasm_i_nop(buf); } - if (R4600_V2_HIT_CACHEOP_WAR && cpu_is_r4600_v2_x()) + if (IS_ENABLED(CONFIG_WAR_R4600_V2_HIT_CACHEOP) && + cpu_is_r4600_v2_x()) uasm_i_lw(buf, ZERO, ZERO, AT); uasm_i_cache(buf, Create_Dirty_Excl_D, off, A0); @@ -455,7 +457,7 @@ void build_copy_page(void) else uasm_i_ori(&buf, A2, A0, off); - if (R4600_V2_HIT_CACHEOP_WAR && cpu_is_r4600_v2_x()) + if (IS_ENABLED(CONFIG_WAR_R4600_V2_HIT_CACHEOP) && cpu_is_r4600_v2_x()) uasm_i_lui(&buf, AT, uasm_rel_hi(0xa0000000)); off = cache_line_size ? min(8, pref_bias_copy_load / cache_line_size) * From 142439b0520a239bc10cf6c87d7773644c5dfe04 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Mon, 24 Aug 2020 18:32:46 +0200 Subject: [PATCH 079/645] MIPS: Remove MIPS4K_ICACHE_REFILL_WAR and MIPS_CACHE_SYNC_WAR Neither MIPS4K_ICACHE_REFILL_WAR nor MIPS_CACHE_SYNC_WAR are implemented, so removing defines for it won't change anything. Signed-off-by: Thomas Bogendoerfer --- .../mips/include/asm/mach-cavium-octeon/war.h | 2 -- arch/mips/include/asm/mach-generic/war.h | 2 -- arch/mips/include/asm/mach-ip22/war.h | 2 -- arch/mips/include/asm/mach-ip27/war.h | 2 -- arch/mips/include/asm/mach-ip28/war.h | 2 -- arch/mips/include/asm/mach-ip30/war.h | 2 -- arch/mips/include/asm/mach-ip32/war.h | 2 -- arch/mips/include/asm/mach-malta/war.h | 2 -- arch/mips/include/asm/mach-rc32434/war.h | 2 -- arch/mips/include/asm/mach-rm/war.h | 2 -- arch/mips/include/asm/mach-sibyte/war.h | 2 -- arch/mips/include/asm/mach-tx49xx/war.h | 2 -- arch/mips/include/asm/war.h | 35 ------------------- 13 files changed, 59 deletions(-) diff --git a/arch/mips/include/asm/mach-cavium-octeon/war.h b/arch/mips/include/asm/mach-cavium-octeon/war.h index 4bc396d0fdd9..5826fbf4d3a2 100644 --- a/arch/mips/include/asm/mach-cavium-octeon/war.h +++ b/arch/mips/include/asm/mach-cavium-octeon/war.h @@ -11,8 +11,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define MIPS4K_ICACHE_REFILL_WAR 0 -#define MIPS_CACHE_SYNC_WAR 0 #define TX49XX_ICACHE_INDEX_INV_WAR 0 #define ICACHE_REFILLS_WORKAROUND_WAR 0 #define R10000_LLSC_WAR 0 diff --git a/arch/mips/include/asm/mach-generic/war.h b/arch/mips/include/asm/mach-generic/war.h index 4d46a880b832..11b1f5e41af0 100644 --- a/arch/mips/include/asm/mach-generic/war.h +++ b/arch/mips/include/asm/mach-generic/war.h @@ -10,8 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define MIPS4K_ICACHE_REFILL_WAR 0 -#define MIPS_CACHE_SYNC_WAR 0 #define TX49XX_ICACHE_INDEX_INV_WAR 0 #define ICACHE_REFILLS_WORKAROUND_WAR 0 #define R10000_LLSC_WAR 0 diff --git a/arch/mips/include/asm/mach-ip22/war.h b/arch/mips/include/asm/mach-ip22/war.h index a5a1c41df74e..e47a7e186ed2 100644 --- a/arch/mips/include/asm/mach-ip22/war.h +++ b/arch/mips/include/asm/mach-ip22/war.h @@ -10,8 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define MIPS4K_ICACHE_REFILL_WAR 0 -#define MIPS_CACHE_SYNC_WAR 0 #define TX49XX_ICACHE_INDEX_INV_WAR 0 #define ICACHE_REFILLS_WORKAROUND_WAR 0 #define R10000_LLSC_WAR 0 diff --git a/arch/mips/include/asm/mach-ip27/war.h b/arch/mips/include/asm/mach-ip27/war.h index 5891d506cffd..f3c5cc8ff2bc 100644 --- a/arch/mips/include/asm/mach-ip27/war.h +++ b/arch/mips/include/asm/mach-ip27/war.h @@ -10,8 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define MIPS4K_ICACHE_REFILL_WAR 0 -#define MIPS_CACHE_SYNC_WAR 0 #define TX49XX_ICACHE_INDEX_INV_WAR 0 #define ICACHE_REFILLS_WORKAROUND_WAR 0 #define R10000_LLSC_WAR 1 diff --git a/arch/mips/include/asm/mach-ip28/war.h b/arch/mips/include/asm/mach-ip28/war.h index 346fc567ebb3..f867697a1793 100644 --- a/arch/mips/include/asm/mach-ip28/war.h +++ b/arch/mips/include/asm/mach-ip28/war.h @@ -10,8 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define MIPS4K_ICACHE_REFILL_WAR 0 -#define MIPS_CACHE_SYNC_WAR 0 #define TX49XX_ICACHE_INDEX_INV_WAR 0 #define ICACHE_REFILLS_WORKAROUND_WAR 0 #define R10000_LLSC_WAR 1 diff --git a/arch/mips/include/asm/mach-ip30/war.h b/arch/mips/include/asm/mach-ip30/war.h index f887a0a53e18..acda1ee3fb62 100644 --- a/arch/mips/include/asm/mach-ip30/war.h +++ b/arch/mips/include/asm/mach-ip30/war.h @@ -7,8 +7,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define MIPS4K_ICACHE_REFILL_WAR 0 -#define MIPS_CACHE_SYNC_WAR 0 #define TX49XX_ICACHE_INDEX_INV_WAR 0 #define ICACHE_REFILLS_WORKAROUND_WAR 0 #ifdef CONFIG_CPU_R10000 diff --git a/arch/mips/include/asm/mach-ip32/war.h b/arch/mips/include/asm/mach-ip32/war.h index 980dbd34355c..ca381798f6ab 100644 --- a/arch/mips/include/asm/mach-ip32/war.h +++ b/arch/mips/include/asm/mach-ip32/war.h @@ -10,8 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define MIPS4K_ICACHE_REFILL_WAR 0 -#define MIPS_CACHE_SYNC_WAR 0 #define TX49XX_ICACHE_INDEX_INV_WAR 0 #define ICACHE_REFILLS_WORKAROUND_WAR 1 #define R10000_LLSC_WAR 0 diff --git a/arch/mips/include/asm/mach-malta/war.h b/arch/mips/include/asm/mach-malta/war.h index 29f56803e3e5..d22ca4a3ec72 100644 --- a/arch/mips/include/asm/mach-malta/war.h +++ b/arch/mips/include/asm/mach-malta/war.h @@ -10,8 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define MIPS4K_ICACHE_REFILL_WAR 1 -#define MIPS_CACHE_SYNC_WAR 1 #define TX49XX_ICACHE_INDEX_INV_WAR 0 #define ICACHE_REFILLS_WORKAROUND_WAR 1 #define R10000_LLSC_WAR 0 diff --git a/arch/mips/include/asm/mach-rc32434/war.h b/arch/mips/include/asm/mach-rc32434/war.h index 749787bb6c8e..fccf25dcc26f 100644 --- a/arch/mips/include/asm/mach-rc32434/war.h +++ b/arch/mips/include/asm/mach-rc32434/war.h @@ -10,8 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define MIPS4K_ICACHE_REFILL_WAR 1 -#define MIPS_CACHE_SYNC_WAR 0 #define TX49XX_ICACHE_INDEX_INV_WAR 0 #define ICACHE_REFILLS_WORKAROUND_WAR 0 #define R10000_LLSC_WAR 0 diff --git a/arch/mips/include/asm/mach-rm/war.h b/arch/mips/include/asm/mach-rm/war.h index aded634ccb01..556e0223e60b 100644 --- a/arch/mips/include/asm/mach-rm/war.h +++ b/arch/mips/include/asm/mach-rm/war.h @@ -10,8 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define MIPS4K_ICACHE_REFILL_WAR 0 -#define MIPS_CACHE_SYNC_WAR 0 #define TX49XX_ICACHE_INDEX_INV_WAR 0 #define ICACHE_REFILLS_WORKAROUND_WAR 0 #define R10000_LLSC_WAR 0 diff --git a/arch/mips/include/asm/mach-sibyte/war.h b/arch/mips/include/asm/mach-sibyte/war.h index 78fd2ad4930b..0e18f0753407 100644 --- a/arch/mips/include/asm/mach-sibyte/war.h +++ b/arch/mips/include/asm/mach-sibyte/war.h @@ -24,8 +24,6 @@ extern int sb1250_m3_workaround_needed(void); #endif -#define MIPS4K_ICACHE_REFILL_WAR 0 -#define MIPS_CACHE_SYNC_WAR 0 #define TX49XX_ICACHE_INDEX_INV_WAR 0 #define ICACHE_REFILLS_WORKAROUND_WAR 0 #define R10000_LLSC_WAR 0 diff --git a/arch/mips/include/asm/mach-tx49xx/war.h b/arch/mips/include/asm/mach-tx49xx/war.h index 0b1666e0391a..7019ddc4c68d 100644 --- a/arch/mips/include/asm/mach-tx49xx/war.h +++ b/arch/mips/include/asm/mach-tx49xx/war.h @@ -10,8 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define MIPS4K_ICACHE_REFILL_WAR 0 -#define MIPS_CACHE_SYNC_WAR 0 #define TX49XX_ICACHE_INDEX_INV_WAR 1 #define ICACHE_REFILLS_WORKAROUND_WAR 0 #define R10000_LLSC_WAR 0 diff --git a/arch/mips/include/asm/war.h b/arch/mips/include/asm/war.h index 37092c2c68e1..590bf2b16b33 100644 --- a/arch/mips/include/asm/war.h +++ b/arch/mips/include/asm/war.h @@ -93,41 +93,6 @@ #error Check setting of SIBYTE_1956_WAR for your platform #endif -/* - * Fill buffers not flushed on CACHE instructions - * - * Hit_Invalidate_I cacheops invalidate an icache line but the refill - * for that line can get stale data from the fill buffer instead of - * accessing memory if the previous icache miss was also to that line. - * - * Workaround: generate an icache refill from a different line - * - * Affects: - * MIPS 4K RTL revision <3.0, PRID revision <4 - */ -#ifndef MIPS4K_ICACHE_REFILL_WAR -#error Check setting of MIPS4K_ICACHE_REFILL_WAR for your platform -#endif - -/* - * Missing implicit forced flush of evictions caused by CACHE - * instruction - * - * Evictions caused by a CACHE instructions are not forced on to the - * bus. The BIU gives higher priority to fetches than to the data from - * the eviction buffer and no collision detection is performed between - * fetches and pending data from the eviction buffer. - * - * Workaround: Execute a SYNC instruction after the cache instruction - * - * Affects: - * MIPS 5Kc,5Kf RTL revision <2.3, PRID revision <8 - * MIPS 20Kc RTL revision <4.0, PRID revision Date: Mon, 24 Aug 2020 18:32:47 +0200 Subject: [PATCH 080/645] MIPS: Convert TX49XX_ICACHE_INDEX_INV into a config option Use a new config option to enable TX49XX I-cache index invalidate workaround and remove define from different war.h files. Signed-off-by: Thomas Bogendoerfer --- arch/mips/Kconfig | 9 +++++++++ arch/mips/include/asm/mach-cavium-octeon/war.h | 1 - arch/mips/include/asm/mach-generic/war.h | 1 - arch/mips/include/asm/mach-ip22/war.h | 1 - arch/mips/include/asm/mach-ip27/war.h | 1 - arch/mips/include/asm/mach-ip28/war.h | 1 - arch/mips/include/asm/mach-ip30/war.h | 1 - arch/mips/include/asm/mach-ip32/war.h | 1 - arch/mips/include/asm/mach-malta/war.h | 1 - arch/mips/include/asm/mach-rc32434/war.h | 1 - arch/mips/include/asm/mach-rm/war.h | 1 - arch/mips/include/asm/mach-sibyte/war.h | 1 - arch/mips/include/asm/mach-tx49xx/war.h | 1 - arch/mips/include/asm/war.h | 11 ----------- arch/mips/mm/c-r4k.c | 6 +++--- 15 files changed, 12 insertions(+), 26 deletions(-) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index e4198c5c2aa8..04a413d52b26 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -890,6 +890,7 @@ config MACH_TX39XX config MACH_TX49XX bool "Toshiba TX49 series based machines" + select WAR_TX49XX_ICACHE_INDEX_INV config MIKROTIK_RB532 bool "Mikrotik RB532 boards" @@ -2657,6 +2658,14 @@ config WAR_R4600_V1_HIT_CACHEOP config WAR_R4600_V2_HIT_CACHEOP bool +# From TX49/H2 manual: "If the instruction (i.e. CACHE) is issued for +# the line which this instruction itself exists, the following +# operation is not guaranteed." +# +# Workaround: do two phase flushing for Index_Invalidate_I +config WAR_TX49XX_ICACHE_INDEX_INV + bool + # # - Highmem only makes sense for the 32-bit kernel. # - The current highmem code will only work properly on physically indexed diff --git a/arch/mips/include/asm/mach-cavium-octeon/war.h b/arch/mips/include/asm/mach-cavium-octeon/war.h index 5826fbf4d3a2..1cb30485dc94 100644 --- a/arch/mips/include/asm/mach-cavium-octeon/war.h +++ b/arch/mips/include/asm/mach-cavium-octeon/war.h @@ -11,7 +11,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define TX49XX_ICACHE_INDEX_INV_WAR 0 #define ICACHE_REFILLS_WORKAROUND_WAR 0 #define R10000_LLSC_WAR 0 #define MIPS34K_MISSED_ITLB_WAR 0 diff --git a/arch/mips/include/asm/mach-generic/war.h b/arch/mips/include/asm/mach-generic/war.h index 11b1f5e41af0..79530836cc79 100644 --- a/arch/mips/include/asm/mach-generic/war.h +++ b/arch/mips/include/asm/mach-generic/war.h @@ -10,7 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define TX49XX_ICACHE_INDEX_INV_WAR 0 #define ICACHE_REFILLS_WORKAROUND_WAR 0 #define R10000_LLSC_WAR 0 #define MIPS34K_MISSED_ITLB_WAR 0 diff --git a/arch/mips/include/asm/mach-ip22/war.h b/arch/mips/include/asm/mach-ip22/war.h index e47a7e186ed2..35286ba3ec57 100644 --- a/arch/mips/include/asm/mach-ip22/war.h +++ b/arch/mips/include/asm/mach-ip22/war.h @@ -10,7 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define TX49XX_ICACHE_INDEX_INV_WAR 0 #define ICACHE_REFILLS_WORKAROUND_WAR 0 #define R10000_LLSC_WAR 0 #define MIPS34K_MISSED_ITLB_WAR 0 diff --git a/arch/mips/include/asm/mach-ip27/war.h b/arch/mips/include/asm/mach-ip27/war.h index f3c5cc8ff2bc..a18293c16ade 100644 --- a/arch/mips/include/asm/mach-ip27/war.h +++ b/arch/mips/include/asm/mach-ip27/war.h @@ -10,7 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define TX49XX_ICACHE_INDEX_INV_WAR 0 #define ICACHE_REFILLS_WORKAROUND_WAR 0 #define R10000_LLSC_WAR 1 #define MIPS34K_MISSED_ITLB_WAR 0 diff --git a/arch/mips/include/asm/mach-ip28/war.h b/arch/mips/include/asm/mach-ip28/war.h index f867697a1793..1a6092e5c7b3 100644 --- a/arch/mips/include/asm/mach-ip28/war.h +++ b/arch/mips/include/asm/mach-ip28/war.h @@ -10,7 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define TX49XX_ICACHE_INDEX_INV_WAR 0 #define ICACHE_REFILLS_WORKAROUND_WAR 0 #define R10000_LLSC_WAR 1 #define MIPS34K_MISSED_ITLB_WAR 0 diff --git a/arch/mips/include/asm/mach-ip30/war.h b/arch/mips/include/asm/mach-ip30/war.h index acda1ee3fb62..031c7b9c5236 100644 --- a/arch/mips/include/asm/mach-ip30/war.h +++ b/arch/mips/include/asm/mach-ip30/war.h @@ -7,7 +7,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define TX49XX_ICACHE_INDEX_INV_WAR 0 #define ICACHE_REFILLS_WORKAROUND_WAR 0 #ifdef CONFIG_CPU_R10000 #define R10000_LLSC_WAR 1 diff --git a/arch/mips/include/asm/mach-ip32/war.h b/arch/mips/include/asm/mach-ip32/war.h index ca381798f6ab..25552158fa3a 100644 --- a/arch/mips/include/asm/mach-ip32/war.h +++ b/arch/mips/include/asm/mach-ip32/war.h @@ -10,7 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define TX49XX_ICACHE_INDEX_INV_WAR 0 #define ICACHE_REFILLS_WORKAROUND_WAR 1 #define R10000_LLSC_WAR 0 #define MIPS34K_MISSED_ITLB_WAR 0 diff --git a/arch/mips/include/asm/mach-malta/war.h b/arch/mips/include/asm/mach-malta/war.h index d22ca4a3ec72..9b0803537bce 100644 --- a/arch/mips/include/asm/mach-malta/war.h +++ b/arch/mips/include/asm/mach-malta/war.h @@ -10,7 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define TX49XX_ICACHE_INDEX_INV_WAR 0 #define ICACHE_REFILLS_WORKAROUND_WAR 1 #define R10000_LLSC_WAR 0 #define MIPS34K_MISSED_ITLB_WAR 0 diff --git a/arch/mips/include/asm/mach-rc32434/war.h b/arch/mips/include/asm/mach-rc32434/war.h index fccf25dcc26f..924b51b9a340 100644 --- a/arch/mips/include/asm/mach-rc32434/war.h +++ b/arch/mips/include/asm/mach-rc32434/war.h @@ -10,7 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define TX49XX_ICACHE_INDEX_INV_WAR 0 #define ICACHE_REFILLS_WORKAROUND_WAR 0 #define R10000_LLSC_WAR 0 #define MIPS34K_MISSED_ITLB_WAR 0 diff --git a/arch/mips/include/asm/mach-rm/war.h b/arch/mips/include/asm/mach-rm/war.h index 556e0223e60b..0536972b24c8 100644 --- a/arch/mips/include/asm/mach-rm/war.h +++ b/arch/mips/include/asm/mach-rm/war.h @@ -10,7 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define TX49XX_ICACHE_INDEX_INV_WAR 0 #define ICACHE_REFILLS_WORKAROUND_WAR 0 #define R10000_LLSC_WAR 0 #define MIPS34K_MISSED_ITLB_WAR 0 diff --git a/arch/mips/include/asm/mach-sibyte/war.h b/arch/mips/include/asm/mach-sibyte/war.h index 0e18f0753407..9e006fdcf38a 100644 --- a/arch/mips/include/asm/mach-sibyte/war.h +++ b/arch/mips/include/asm/mach-sibyte/war.h @@ -24,7 +24,6 @@ extern int sb1250_m3_workaround_needed(void); #endif -#define TX49XX_ICACHE_INDEX_INV_WAR 0 #define ICACHE_REFILLS_WORKAROUND_WAR 0 #define R10000_LLSC_WAR 0 #define MIPS34K_MISSED_ITLB_WAR 0 diff --git a/arch/mips/include/asm/mach-tx49xx/war.h b/arch/mips/include/asm/mach-tx49xx/war.h index 7019ddc4c68d..9293c5f9ffb2 100644 --- a/arch/mips/include/asm/mach-tx49xx/war.h +++ b/arch/mips/include/asm/mach-tx49xx/war.h @@ -10,7 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define TX49XX_ICACHE_INDEX_INV_WAR 1 #define ICACHE_REFILLS_WORKAROUND_WAR 0 #define R10000_LLSC_WAR 0 #define MIPS34K_MISSED_ITLB_WAR 0 diff --git a/arch/mips/include/asm/war.h b/arch/mips/include/asm/war.h index 590bf2b16b33..7a69641de57b 100644 --- a/arch/mips/include/asm/war.h +++ b/arch/mips/include/asm/war.h @@ -93,17 +93,6 @@ #error Check setting of SIBYTE_1956_WAR for your platform #endif -/* - * From TX49/H2 manual: "If the instruction (i.e. CACHE) is issued for - * the line which this instruction itself exists, the following - * operation is not guaranteed." - * - * Workaround: do two phase flushing for Index_Invalidate_I - */ -#ifndef TX49XX_ICACHE_INDEX_INV_WAR -#error Check setting of TX49XX_ICACHE_INDEX_INV_WAR for your platform -#endif - /* * The RM7000 processors and the E9000 cores have a bug (though PMC-Sierra * opposes it being called that) where invalid instructions in the same diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index df09a3653c4f..4b12081f9843 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -239,7 +239,7 @@ static void r4k_blast_dcache_setup(void) r4k_blast_dcache = blast_dcache128; } -/* force code alignment (used for TX49XX_ICACHE_INDEX_INV_WAR) */ +/* force code alignment (used for CONFIG_WAR_TX49XX_ICACHE_INDEX_INV) */ #define JUMP_TO_ALIGN(order) \ __asm__ __volatile__( \ "b\t1f\n\t" \ @@ -371,7 +371,7 @@ static void r4k_blast_icache_page_indexed_setup(void) cpu_is_r4600_v1_x()) r4k_blast_icache_page_indexed = blast_icache32_r4600_v1_page_indexed; - else if (TX49XX_ICACHE_INDEX_INV_WAR) + else if (IS_ENABLED(CONFIG_WAR_TX49XX_ICACHE_INDEX_INV)) r4k_blast_icache_page_indexed = tx49_blast_icache32_page_indexed; else if (current_cpu_type() == CPU_LOONGSON2EF) @@ -399,7 +399,7 @@ static void r4k_blast_icache_setup(void) if (IS_ENABLED(CONFIG_WAR_R4600_V1_INDEX_ICACHEOP) && cpu_is_r4600_v1_x()) r4k_blast_icache = blast_r4600_v1_icache32; - else if (TX49XX_ICACHE_INDEX_INV_WAR) + else if (IS_ENABLED(CONFIG_WAR_TX49XX_ICACHE_INDEX_INV)) r4k_blast_icache = tx49_blast_icache32; else if (current_cpu_type() == CPU_LOONGSON2EF) r4k_blast_icache = loongson2_blast_icache32; From 886ee1363a3ad2b890959f07cffe8d91d995b93a Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Mon, 24 Aug 2020 18:32:48 +0200 Subject: [PATCH 081/645] MIPS: Convert ICACHE_REFILLS_WORKAROUND_WAR into a config option Use a new config option to enable I-cache refill workaround and remove define from different war.h files. Signed-off-by: Thomas Bogendoerfer --- arch/mips/Kconfig | 9 +++++++++ arch/mips/include/asm/mach-cavium-octeon/war.h | 1 - arch/mips/include/asm/mach-generic/war.h | 1 - arch/mips/include/asm/mach-ip22/war.h | 1 - arch/mips/include/asm/mach-ip27/war.h | 1 - arch/mips/include/asm/mach-ip28/war.h | 1 - arch/mips/include/asm/mach-ip30/war.h | 1 - arch/mips/include/asm/mach-ip32/war.h | 1 - arch/mips/include/asm/mach-malta/war.h | 1 - arch/mips/include/asm/mach-rc32434/war.h | 1 - arch/mips/include/asm/mach-rm/war.h | 1 - arch/mips/include/asm/mach-sibyte/war.h | 1 - arch/mips/include/asm/mach-tx49xx/war.h | 1 - arch/mips/include/asm/war.h | 10 ---------- arch/mips/kernel/signal.c | 8 +++++++- 15 files changed, 16 insertions(+), 23 deletions(-) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 04a413d52b26..5df92ae935d4 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -568,6 +568,7 @@ config MIPS_MALTA select SYS_SUPPORTS_VPE_LOADER select SYS_SUPPORTS_ZBOOT select USE_OF + select WAR_ICACHE_REFILLS select ZONE_DMA32 if 64BIT help This enables support for the MIPS Technologies Malta evaluation @@ -756,6 +757,7 @@ config SGI_IP32 select SYS_HAS_CPU_NEVADA select SYS_SUPPORTS_64BIT_KERNEL select SYS_SUPPORTS_BIG_ENDIAN + select WAR_ICACHE_REFILLS help If you want this kernel to run on SGI O2 workstation, say Y here. @@ -2666,6 +2668,13 @@ config WAR_R4600_V2_HIT_CACHEOP config WAR_TX49XX_ICACHE_INDEX_INV bool +# The RM7000 processors and the E9000 cores have a bug (though PMC-Sierra +# opposes it being called that) where invalid instructions in the same +# I-cache line worth of instructions being fetched may case spurious +# exceptions. +config WAR_ICACHE_REFILLS + bool + # # - Highmem only makes sense for the 32-bit kernel. # - The current highmem code will only work properly on physically indexed diff --git a/arch/mips/include/asm/mach-cavium-octeon/war.h b/arch/mips/include/asm/mach-cavium-octeon/war.h index 1cb30485dc94..1061917152c6 100644 --- a/arch/mips/include/asm/mach-cavium-octeon/war.h +++ b/arch/mips/include/asm/mach-cavium-octeon/war.h @@ -11,7 +11,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define ICACHE_REFILLS_WORKAROUND_WAR 0 #define R10000_LLSC_WAR 0 #define MIPS34K_MISSED_ITLB_WAR 0 diff --git a/arch/mips/include/asm/mach-generic/war.h b/arch/mips/include/asm/mach-generic/war.h index 79530836cc79..966f40aedf16 100644 --- a/arch/mips/include/asm/mach-generic/war.h +++ b/arch/mips/include/asm/mach-generic/war.h @@ -10,7 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define ICACHE_REFILLS_WORKAROUND_WAR 0 #define R10000_LLSC_WAR 0 #define MIPS34K_MISSED_ITLB_WAR 0 diff --git a/arch/mips/include/asm/mach-ip22/war.h b/arch/mips/include/asm/mach-ip22/war.h index 35286ba3ec57..99f6531e5b9b 100644 --- a/arch/mips/include/asm/mach-ip22/war.h +++ b/arch/mips/include/asm/mach-ip22/war.h @@ -10,7 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define ICACHE_REFILLS_WORKAROUND_WAR 0 #define R10000_LLSC_WAR 0 #define MIPS34K_MISSED_ITLB_WAR 0 diff --git a/arch/mips/include/asm/mach-ip27/war.h b/arch/mips/include/asm/mach-ip27/war.h index a18293c16ade..d8dfa7258bea 100644 --- a/arch/mips/include/asm/mach-ip27/war.h +++ b/arch/mips/include/asm/mach-ip27/war.h @@ -10,7 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define ICACHE_REFILLS_WORKAROUND_WAR 0 #define R10000_LLSC_WAR 1 #define MIPS34K_MISSED_ITLB_WAR 0 diff --git a/arch/mips/include/asm/mach-ip28/war.h b/arch/mips/include/asm/mach-ip28/war.h index 1a6092e5c7b3..f252df761ec8 100644 --- a/arch/mips/include/asm/mach-ip28/war.h +++ b/arch/mips/include/asm/mach-ip28/war.h @@ -10,7 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define ICACHE_REFILLS_WORKAROUND_WAR 0 #define R10000_LLSC_WAR 1 #define MIPS34K_MISSED_ITLB_WAR 0 diff --git a/arch/mips/include/asm/mach-ip30/war.h b/arch/mips/include/asm/mach-ip30/war.h index 031c7b9c5236..58ff9ca345b7 100644 --- a/arch/mips/include/asm/mach-ip30/war.h +++ b/arch/mips/include/asm/mach-ip30/war.h @@ -7,7 +7,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define ICACHE_REFILLS_WORKAROUND_WAR 0 #ifdef CONFIG_CPU_R10000 #define R10000_LLSC_WAR 1 #else diff --git a/arch/mips/include/asm/mach-ip32/war.h b/arch/mips/include/asm/mach-ip32/war.h index 25552158fa3a..ca3efe457ae0 100644 --- a/arch/mips/include/asm/mach-ip32/war.h +++ b/arch/mips/include/asm/mach-ip32/war.h @@ -10,7 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define ICACHE_REFILLS_WORKAROUND_WAR 1 #define R10000_LLSC_WAR 0 #define MIPS34K_MISSED_ITLB_WAR 0 diff --git a/arch/mips/include/asm/mach-malta/war.h b/arch/mips/include/asm/mach-malta/war.h index 9b0803537bce..b7827eb09375 100644 --- a/arch/mips/include/asm/mach-malta/war.h +++ b/arch/mips/include/asm/mach-malta/war.h @@ -10,7 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define ICACHE_REFILLS_WORKAROUND_WAR 1 #define R10000_LLSC_WAR 0 #define MIPS34K_MISSED_ITLB_WAR 0 diff --git a/arch/mips/include/asm/mach-rc32434/war.h b/arch/mips/include/asm/mach-rc32434/war.h index 924b51b9a340..b7827eb09375 100644 --- a/arch/mips/include/asm/mach-rc32434/war.h +++ b/arch/mips/include/asm/mach-rc32434/war.h @@ -10,7 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define ICACHE_REFILLS_WORKAROUND_WAR 0 #define R10000_LLSC_WAR 0 #define MIPS34K_MISSED_ITLB_WAR 0 diff --git a/arch/mips/include/asm/mach-rm/war.h b/arch/mips/include/asm/mach-rm/war.h index 0536972b24c8..fe04d059dd0c 100644 --- a/arch/mips/include/asm/mach-rm/war.h +++ b/arch/mips/include/asm/mach-rm/war.h @@ -10,7 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define ICACHE_REFILLS_WORKAROUND_WAR 0 #define R10000_LLSC_WAR 0 #define MIPS34K_MISSED_ITLB_WAR 0 diff --git a/arch/mips/include/asm/mach-sibyte/war.h b/arch/mips/include/asm/mach-sibyte/war.h index 9e006fdcf38a..7c376f6eee9b 100644 --- a/arch/mips/include/asm/mach-sibyte/war.h +++ b/arch/mips/include/asm/mach-sibyte/war.h @@ -24,7 +24,6 @@ extern int sb1250_m3_workaround_needed(void); #endif -#define ICACHE_REFILLS_WORKAROUND_WAR 0 #define R10000_LLSC_WAR 0 #define MIPS34K_MISSED_ITLB_WAR 0 diff --git a/arch/mips/include/asm/mach-tx49xx/war.h b/arch/mips/include/asm/mach-tx49xx/war.h index 9293c5f9ffb2..5768889c20a7 100644 --- a/arch/mips/include/asm/mach-tx49xx/war.h +++ b/arch/mips/include/asm/mach-tx49xx/war.h @@ -10,7 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define ICACHE_REFILLS_WORKAROUND_WAR 0 #define R10000_LLSC_WAR 0 #define MIPS34K_MISSED_ITLB_WAR 0 diff --git a/arch/mips/include/asm/war.h b/arch/mips/include/asm/war.h index 7a69641de57b..a0942821d67d 100644 --- a/arch/mips/include/asm/war.h +++ b/arch/mips/include/asm/war.h @@ -93,16 +93,6 @@ #error Check setting of SIBYTE_1956_WAR for your platform #endif -/* - * The RM7000 processors and the E9000 cores have a bug (though PMC-Sierra - * opposes it being called that) where invalid instructions in the same - * I-cache line worth of instructions being fetched may case spurious - * exceptions. - */ -#ifndef ICACHE_REFILLS_WORKAROUND_WAR -#error Check setting of ICACHE_REFILLS_WORKAROUND_WAR for your platform -#endif - /* * On the R10000 up to version 2.6 (not sure about 2.7) there is a bug that * may cause ll / sc and lld / scd sequences to execute non-atomically. diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c index a0262729cd4c..f44265025281 100644 --- a/arch/mips/kernel/signal.c +++ b/arch/mips/kernel/signal.c @@ -545,6 +545,12 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc) return err ?: protected_restore_fp_context(sc); } +#ifdef CONFIG_WAR_ICACHE_REFILLS +#define SIGMASK ~(cpu_icache_line_size()-1) +#else +#define SIGMASK ALMASK +#endif + void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, size_t frame_size) { @@ -565,7 +571,7 @@ void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, sp = sigsp(sp, ksig); - return (void __user *)((sp - frame_size) & (ICACHE_REFILLS_WORKAROUND_WAR ? ~(cpu_icache_line_size()-1) : ALMASK)); + return (void __user *)((sp - frame_size) & SIGMASK); } /* From 256ec489f1c7726f0db9ffee88ba7cdc317806cd Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Mon, 24 Aug 2020 18:32:49 +0200 Subject: [PATCH 082/645] MIPS: Convert R10000_LLSC_WAR info a config option Use a new config option to enabel R1000_LLSC workaound and remove define from different war.h files. Signed-off-by: Thomas Bogendoerfer --- arch/mips/Kconfig | 8 ++++++++ arch/mips/include/asm/futex.h | 4 ++-- arch/mips/include/asm/llsc.h | 2 +- arch/mips/include/asm/local.h | 4 ++-- arch/mips/include/asm/mach-cavium-octeon/war.h | 1 - arch/mips/include/asm/mach-generic/war.h | 1 - arch/mips/include/asm/mach-ip22/war.h | 1 - arch/mips/include/asm/mach-ip27/war.h | 1 - arch/mips/include/asm/mach-ip28/war.h | 1 - arch/mips/include/asm/mach-ip30/war.h | 5 ----- arch/mips/include/asm/mach-ip32/war.h | 1 - arch/mips/include/asm/mach-malta/war.h | 1 - arch/mips/include/asm/mach-rc32434/war.h | 1 - arch/mips/include/asm/mach-rm/war.h | 1 - arch/mips/include/asm/mach-sibyte/war.h | 1 - arch/mips/include/asm/mach-tx49xx/war.h | 1 - arch/mips/include/asm/war.h | 8 -------- arch/mips/kernel/syscall.c | 2 +- arch/mips/mm/tlbex.c | 2 +- 19 files changed, 15 insertions(+), 31 deletions(-) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 5df92ae935d4..87ef000d1aec 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -669,6 +669,7 @@ config SGI_IP27 select SYS_SUPPORTS_BIG_ENDIAN select SYS_SUPPORTS_NUMA select SYS_SUPPORTS_SMP + select WAR_R10000_LLSC select MIPS_L1_CACHE_SHIFT_7 select NUMA help @@ -704,6 +705,7 @@ config SGI_IP28 select SYS_HAS_EARLY_PRINTK select SYS_SUPPORTS_64BIT_KERNEL select SYS_SUPPORTS_BIG_ENDIAN + select WAR_R10000_LLSC select MIPS_L1_CACHE_SHIFT_7 help This is the SGI Indigo2 with R10000 processor. To compile a Linux @@ -730,6 +732,7 @@ config SGI_IP30 select SYS_SUPPORTS_64BIT_KERNEL select SYS_SUPPORTS_BIG_ENDIAN select SYS_SUPPORTS_SMP + select WAR_R10000_LLSC select MIPS_L1_CACHE_SHIFT_7 select ARC_MEMORY help @@ -2675,6 +2678,11 @@ config WAR_TX49XX_ICACHE_INDEX_INV config WAR_ICACHE_REFILLS bool +# On the R10000 up to version 2.6 (not sure about 2.7) there is a bug that +# may cause ll / sc and lld / scd sequences to execute non-atomically. +config WAR_R10000_LLSC + bool + # # - Highmem only makes sense for the 32-bit kernel. # - The current highmem code will only work properly on physically indexed diff --git a/arch/mips/include/asm/futex.h b/arch/mips/include/asm/futex.h index 2bf8f6014579..d85248404c52 100644 --- a/arch/mips/include/asm/futex.h +++ b/arch/mips/include/asm/futex.h @@ -21,7 +21,7 @@ #define __futex_atomic_op(insn, ret, oldval, uaddr, oparg) \ { \ - if (cpu_has_llsc && R10000_LLSC_WAR) { \ + if (cpu_has_llsc && IS_ENABLED(CONFIG_WAR_R10000_LLSC)) { \ __asm__ __volatile__( \ " .set push \n" \ " .set noat \n" \ @@ -133,7 +133,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, if (!access_ok(uaddr, sizeof(u32))) return -EFAULT; - if (cpu_has_llsc && R10000_LLSC_WAR) { + if (cpu_has_llsc && IS_ENABLED(CONFIG_WAR_R10000_LLSC)) { __asm__ __volatile__( "# futex_atomic_cmpxchg_inatomic \n" " .set push \n" diff --git a/arch/mips/include/asm/llsc.h b/arch/mips/include/asm/llsc.h index c49738bc3bda..ec09fe5d6d6c 100644 --- a/arch/mips/include/asm/llsc.h +++ b/arch/mips/include/asm/llsc.h @@ -28,7 +28,7 @@ * works around a bug present in R10000 CPUs prior to revision 3.0 that could * cause ll-sc sequences to execute non-atomically. */ -#if R10000_LLSC_WAR +#ifdef CONFIG_WAR_R10000_LLSC # define __SC_BEQZ "beqzl " #elif MIPS_ISA_REV >= 6 # define __SC_BEQZ "beqzc " diff --git a/arch/mips/include/asm/local.h b/arch/mips/include/asm/local.h index fef0fda8f82f..ecda7295ddcd 100644 --- a/arch/mips/include/asm/local.h +++ b/arch/mips/include/asm/local.h @@ -31,7 +31,7 @@ static __inline__ long local_add_return(long i, local_t * l) { unsigned long result; - if (kernel_uses_llsc && R10000_LLSC_WAR) { + if (kernel_uses_llsc && IS_ENABLED(CONFIG_WAR_R10000_LLSC)) { unsigned long temp; __asm__ __volatile__( @@ -80,7 +80,7 @@ static __inline__ long local_sub_return(long i, local_t * l) { unsigned long result; - if (kernel_uses_llsc && R10000_LLSC_WAR) { + if (kernel_uses_llsc && IS_ENABLED(CONFIG_WAR_R10000_LLSC)) { unsigned long temp; __asm__ __volatile__( diff --git a/arch/mips/include/asm/mach-cavium-octeon/war.h b/arch/mips/include/asm/mach-cavium-octeon/war.h index 1061917152c6..52be3785e3e2 100644 --- a/arch/mips/include/asm/mach-cavium-octeon/war.h +++ b/arch/mips/include/asm/mach-cavium-octeon/war.h @@ -11,7 +11,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define R10000_LLSC_WAR 0 #define MIPS34K_MISSED_ITLB_WAR 0 #define CAVIUM_OCTEON_DCACHE_PREFETCH_WAR \ diff --git a/arch/mips/include/asm/mach-generic/war.h b/arch/mips/include/asm/mach-generic/war.h index 966f40aedf16..2229c8377288 100644 --- a/arch/mips/include/asm/mach-generic/war.h +++ b/arch/mips/include/asm/mach-generic/war.h @@ -10,7 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define R10000_LLSC_WAR 0 #define MIPS34K_MISSED_ITLB_WAR 0 #endif /* __ASM_MACH_GENERIC_WAR_H */ diff --git a/arch/mips/include/asm/mach-ip22/war.h b/arch/mips/include/asm/mach-ip22/war.h index 99f6531e5b9b..f10efe589f93 100644 --- a/arch/mips/include/asm/mach-ip22/war.h +++ b/arch/mips/include/asm/mach-ip22/war.h @@ -10,7 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define R10000_LLSC_WAR 0 #define MIPS34K_MISSED_ITLB_WAR 0 #endif /* __ASM_MIPS_MACH_IP22_WAR_H */ diff --git a/arch/mips/include/asm/mach-ip27/war.h b/arch/mips/include/asm/mach-ip27/war.h index d8dfa7258bea..0a07cf6731c0 100644 --- a/arch/mips/include/asm/mach-ip27/war.h +++ b/arch/mips/include/asm/mach-ip27/war.h @@ -10,7 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define R10000_LLSC_WAR 1 #define MIPS34K_MISSED_ITLB_WAR 0 #endif /* __ASM_MIPS_MACH_IP27_WAR_H */ diff --git a/arch/mips/include/asm/mach-ip28/war.h b/arch/mips/include/asm/mach-ip28/war.h index f252df761ec8..9fdc6425c22c 100644 --- a/arch/mips/include/asm/mach-ip28/war.h +++ b/arch/mips/include/asm/mach-ip28/war.h @@ -10,7 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define R10000_LLSC_WAR 1 #define MIPS34K_MISSED_ITLB_WAR 0 #endif /* __ASM_MIPS_MACH_IP28_WAR_H */ diff --git a/arch/mips/include/asm/mach-ip30/war.h b/arch/mips/include/asm/mach-ip30/war.h index 58ff9ca345b7..8a8ec5578083 100644 --- a/arch/mips/include/asm/mach-ip30/war.h +++ b/arch/mips/include/asm/mach-ip30/war.h @@ -7,11 +7,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#ifdef CONFIG_CPU_R10000 -#define R10000_LLSC_WAR 1 -#else -#define R10000_LLSC_WAR 0 -#endif #define MIPS34K_MISSED_ITLB_WAR 0 #endif /* __ASM_MIPS_MACH_IP30_WAR_H */ diff --git a/arch/mips/include/asm/mach-ip32/war.h b/arch/mips/include/asm/mach-ip32/war.h index ca3efe457ae0..9e8c0c2a4c26 100644 --- a/arch/mips/include/asm/mach-ip32/war.h +++ b/arch/mips/include/asm/mach-ip32/war.h @@ -10,7 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define R10000_LLSC_WAR 0 #define MIPS34K_MISSED_ITLB_WAR 0 #endif /* __ASM_MIPS_MACH_IP32_WAR_H */ diff --git a/arch/mips/include/asm/mach-malta/war.h b/arch/mips/include/asm/mach-malta/war.h index b7827eb09375..76f7de21b7dd 100644 --- a/arch/mips/include/asm/mach-malta/war.h +++ b/arch/mips/include/asm/mach-malta/war.h @@ -10,7 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define R10000_LLSC_WAR 0 #define MIPS34K_MISSED_ITLB_WAR 0 #endif /* __ASM_MIPS_MACH_MIPS_WAR_H */ diff --git a/arch/mips/include/asm/mach-rc32434/war.h b/arch/mips/include/asm/mach-rc32434/war.h index b7827eb09375..76f7de21b7dd 100644 --- a/arch/mips/include/asm/mach-rc32434/war.h +++ b/arch/mips/include/asm/mach-rc32434/war.h @@ -10,7 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define R10000_LLSC_WAR 0 #define MIPS34K_MISSED_ITLB_WAR 0 #endif /* __ASM_MIPS_MACH_MIPS_WAR_H */ diff --git a/arch/mips/include/asm/mach-rm/war.h b/arch/mips/include/asm/mach-rm/war.h index fe04d059dd0c..dcb80b558321 100644 --- a/arch/mips/include/asm/mach-rm/war.h +++ b/arch/mips/include/asm/mach-rm/war.h @@ -10,7 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define R10000_LLSC_WAR 0 #define MIPS34K_MISSED_ITLB_WAR 0 #endif /* __ASM_MIPS_MACH_RM_WAR_H */ diff --git a/arch/mips/include/asm/mach-sibyte/war.h b/arch/mips/include/asm/mach-sibyte/war.h index 7c376f6eee9b..0cf25eea846f 100644 --- a/arch/mips/include/asm/mach-sibyte/war.h +++ b/arch/mips/include/asm/mach-sibyte/war.h @@ -24,7 +24,6 @@ extern int sb1250_m3_workaround_needed(void); #endif -#define R10000_LLSC_WAR 0 #define MIPS34K_MISSED_ITLB_WAR 0 #endif /* __ASM_MIPS_MACH_SIBYTE_WAR_H */ diff --git a/arch/mips/include/asm/mach-tx49xx/war.h b/arch/mips/include/asm/mach-tx49xx/war.h index 5768889c20a7..8e572d7d2b6e 100644 --- a/arch/mips/include/asm/mach-tx49xx/war.h +++ b/arch/mips/include/asm/mach-tx49xx/war.h @@ -10,7 +10,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define R10000_LLSC_WAR 0 #define MIPS34K_MISSED_ITLB_WAR 0 #endif /* __ASM_MIPS_MACH_TX49XX_WAR_H */ diff --git a/arch/mips/include/asm/war.h b/arch/mips/include/asm/war.h index a0942821d67d..d405ecb78cbd 100644 --- a/arch/mips/include/asm/war.h +++ b/arch/mips/include/asm/war.h @@ -93,14 +93,6 @@ #error Check setting of SIBYTE_1956_WAR for your platform #endif -/* - * On the R10000 up to version 2.6 (not sure about 2.7) there is a bug that - * may cause ll / sc and lld / scd sequences to execute non-atomically. - */ -#ifndef R10000_LLSC_WAR -#error Check setting of R10000_LLSC_WAR for your platform -#endif - /* * 34K core erratum: "Problems Executing the TLBR Instruction" */ diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c index c333e5788664..2afa3eef486a 100644 --- a/arch/mips/kernel/syscall.c +++ b/arch/mips/kernel/syscall.c @@ -106,7 +106,7 @@ static inline int mips_atomic_set(unsigned long addr, unsigned long new) if (unlikely(!access_ok((const void __user *)addr, 4))) return -EINVAL; - if (cpu_has_llsc && R10000_LLSC_WAR) { + if (cpu_has_llsc && IS_ENABLED(CONFIG_WAR_R10000_LLSC)) { __asm__ __volatile__ ( " .set push \n" " .set arch=r4000 \n" diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index 14f8ba93367f..e931eb06af57 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -90,7 +90,7 @@ static inline int __maybe_unused bcm1250_m3_war(void) static inline int __maybe_unused r10000_llsc_war(void) { - return R10000_LLSC_WAR; + return IS_ENABLED(CONFIG_WAR_R10000_LLSC); } static int use_bbit_insns(void) From a7fbed988f31d3bf92415226fdf2ffd54606ad93 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Mon, 24 Aug 2020 18:32:50 +0200 Subject: [PATCH 083/645] MIPS: Convert MIPS34K_MISSED_ITLB_WAR into a config option Use a new config option to enable MIPS 34K ITLB workaround and remove define from different war.h files. Signed-off-by: Thomas Bogendoerfer --- arch/mips/Kconfig | 4 ++++ arch/mips/include/asm/mach-cavium-octeon/war.h | 1 - arch/mips/include/asm/mach-generic/war.h | 1 - arch/mips/include/asm/mach-ip22/war.h | 1 - arch/mips/include/asm/mach-ip27/war.h | 1 - arch/mips/include/asm/mach-ip28/war.h | 1 - arch/mips/include/asm/mach-ip30/war.h | 1 - arch/mips/include/asm/mach-ip32/war.h | 1 - arch/mips/include/asm/mach-malta/war.h | 1 - arch/mips/include/asm/mach-rc32434/war.h | 1 - arch/mips/include/asm/mach-rm/war.h | 1 - arch/mips/include/asm/mach-sibyte/war.h | 2 -- arch/mips/include/asm/mach-tx49xx/war.h | 1 - arch/mips/include/asm/mipsregs.h | 4 ++-- arch/mips/include/asm/war.h | 7 ------- 15 files changed, 6 insertions(+), 22 deletions(-) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 87ef000d1aec..632fe8fe68c4 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -2683,6 +2683,10 @@ config WAR_ICACHE_REFILLS config WAR_R10000_LLSC bool +# 34K core erratum: "Problems Executing the TLBR Instruction" +config WAR_MIPS34K_MISSED_ITLB + bool + # # - Highmem only makes sense for the 32-bit kernel. # - The current highmem code will only work properly on physically indexed diff --git a/arch/mips/include/asm/mach-cavium-octeon/war.h b/arch/mips/include/asm/mach-cavium-octeon/war.h index 52be3785e3e2..9aa4ea5522a9 100644 --- a/arch/mips/include/asm/mach-cavium-octeon/war.h +++ b/arch/mips/include/asm/mach-cavium-octeon/war.h @@ -11,7 +11,6 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define MIPS34K_MISSED_ITLB_WAR 0 #define CAVIUM_OCTEON_DCACHE_PREFETCH_WAR \ OCTEON_IS_MODEL(OCTEON_CN6XXX) diff --git a/arch/mips/include/asm/mach-generic/war.h b/arch/mips/include/asm/mach-generic/war.h index 2229c8377288..4f25636661d5 100644 --- a/arch/mips/include/asm/mach-generic/war.h +++ b/arch/mips/include/asm/mach-generic/war.h @@ -10,6 +10,5 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define MIPS34K_MISSED_ITLB_WAR 0 #endif /* __ASM_MACH_GENERIC_WAR_H */ diff --git a/arch/mips/include/asm/mach-ip22/war.h b/arch/mips/include/asm/mach-ip22/war.h index f10efe589f93..09169cfbf932 100644 --- a/arch/mips/include/asm/mach-ip22/war.h +++ b/arch/mips/include/asm/mach-ip22/war.h @@ -10,6 +10,5 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define MIPS34K_MISSED_ITLB_WAR 0 #endif /* __ASM_MIPS_MACH_IP22_WAR_H */ diff --git a/arch/mips/include/asm/mach-ip27/war.h b/arch/mips/include/asm/mach-ip27/war.h index 0a07cf6731c0..1c81d5464235 100644 --- a/arch/mips/include/asm/mach-ip27/war.h +++ b/arch/mips/include/asm/mach-ip27/war.h @@ -10,6 +10,5 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define MIPS34K_MISSED_ITLB_WAR 0 #endif /* __ASM_MIPS_MACH_IP27_WAR_H */ diff --git a/arch/mips/include/asm/mach-ip28/war.h b/arch/mips/include/asm/mach-ip28/war.h index 9fdc6425c22c..ff66adbaaae5 100644 --- a/arch/mips/include/asm/mach-ip28/war.h +++ b/arch/mips/include/asm/mach-ip28/war.h @@ -10,6 +10,5 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define MIPS34K_MISSED_ITLB_WAR 0 #endif /* __ASM_MIPS_MACH_IP28_WAR_H */ diff --git a/arch/mips/include/asm/mach-ip30/war.h b/arch/mips/include/asm/mach-ip30/war.h index 8a8ec5578083..b00469a39835 100644 --- a/arch/mips/include/asm/mach-ip30/war.h +++ b/arch/mips/include/asm/mach-ip30/war.h @@ -7,6 +7,5 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define MIPS34K_MISSED_ITLB_WAR 0 #endif /* __ASM_MIPS_MACH_IP30_WAR_H */ diff --git a/arch/mips/include/asm/mach-ip32/war.h b/arch/mips/include/asm/mach-ip32/war.h index 9e8c0c2a4c26..c57a9cd2e50b 100644 --- a/arch/mips/include/asm/mach-ip32/war.h +++ b/arch/mips/include/asm/mach-ip32/war.h @@ -10,6 +10,5 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define MIPS34K_MISSED_ITLB_WAR 0 #endif /* __ASM_MIPS_MACH_IP32_WAR_H */ diff --git a/arch/mips/include/asm/mach-malta/war.h b/arch/mips/include/asm/mach-malta/war.h index 76f7de21b7dd..73c9e6d84a8f 100644 --- a/arch/mips/include/asm/mach-malta/war.h +++ b/arch/mips/include/asm/mach-malta/war.h @@ -10,6 +10,5 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define MIPS34K_MISSED_ITLB_WAR 0 #endif /* __ASM_MIPS_MACH_MIPS_WAR_H */ diff --git a/arch/mips/include/asm/mach-rc32434/war.h b/arch/mips/include/asm/mach-rc32434/war.h index 76f7de21b7dd..73c9e6d84a8f 100644 --- a/arch/mips/include/asm/mach-rc32434/war.h +++ b/arch/mips/include/asm/mach-rc32434/war.h @@ -10,6 +10,5 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define MIPS34K_MISSED_ITLB_WAR 0 #endif /* __ASM_MIPS_MACH_MIPS_WAR_H */ diff --git a/arch/mips/include/asm/mach-rm/war.h b/arch/mips/include/asm/mach-rm/war.h index dcb80b558321..c396a31706ac 100644 --- a/arch/mips/include/asm/mach-rm/war.h +++ b/arch/mips/include/asm/mach-rm/war.h @@ -10,6 +10,5 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define MIPS34K_MISSED_ITLB_WAR 0 #endif /* __ASM_MIPS_MACH_RM_WAR_H */ diff --git a/arch/mips/include/asm/mach-sibyte/war.h b/arch/mips/include/asm/mach-sibyte/war.h index 0cf25eea846f..fa9bbc228dd7 100644 --- a/arch/mips/include/asm/mach-sibyte/war.h +++ b/arch/mips/include/asm/mach-sibyte/war.h @@ -24,6 +24,4 @@ extern int sb1250_m3_workaround_needed(void); #endif -#define MIPS34K_MISSED_ITLB_WAR 0 - #endif /* __ASM_MIPS_MACH_SIBYTE_WAR_H */ diff --git a/arch/mips/include/asm/mach-tx49xx/war.h b/arch/mips/include/asm/mach-tx49xx/war.h index 8e572d7d2b6e..7213d9334f3f 100644 --- a/arch/mips/include/asm/mach-tx49xx/war.h +++ b/arch/mips/include/asm/mach-tx49xx/war.h @@ -10,6 +10,5 @@ #define BCM1250_M3_WAR 0 #define SIBYTE_1956_WAR 0 -#define MIPS34K_MISSED_ITLB_WAR 0 #endif /* __ASM_MIPS_MACH_TX49XX_WAR_H */ diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h index 1a03fdc2c74a..3a7379b8f31c 100644 --- a/arch/mips/include/asm/mipsregs.h +++ b/arch/mips/include/asm/mipsregs.h @@ -2716,7 +2716,7 @@ static inline void tlb_probe(void) static inline void tlb_read(void) { -#if MIPS34K_MISSED_ITLB_WAR +#ifdef CONFIG_WAR_MIPS34K_MISSED_ITLB int res = 0; __asm__ __volatile__( @@ -2738,7 +2738,7 @@ static inline void tlb_read(void) "tlbr\n\t" ".set reorder"); -#if MIPS34K_MISSED_ITLB_WAR +#ifdef CONFIG_WAR_MIPS34K_MISSED_ITLB if ((res & _ULCAST_(1))) __asm__ __volatile__( " .set push \n" diff --git a/arch/mips/include/asm/war.h b/arch/mips/include/asm/war.h index d405ecb78cbd..4f4d37b3dd07 100644 --- a/arch/mips/include/asm/war.h +++ b/arch/mips/include/asm/war.h @@ -93,11 +93,4 @@ #error Check setting of SIBYTE_1956_WAR for your platform #endif -/* - * 34K core erratum: "Problems Executing the TLBR Instruction" - */ -#ifndef MIPS34K_MISSED_ITLB_WAR -#error Check setting of MIPS34K_MISSED_ITLB_WAR for your platform -#endif - #endif /* _ASM_WAR_H */ From 43df4eb2fc9511e09c66252c3fec4f8933a77c73 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Mon, 24 Aug 2020 18:32:51 +0200 Subject: [PATCH 084/645] MIPS: Replace SIBYTE_1956_WAR by CONFIG_SB1_PASS_2_WORKAROUNDS SB1250 uart bug is related to PASS 2 workarounds. Use config CONFIG_SB1_PASS_2_WORKAROUNDS directly and get rid of SIBYTE_1956_WAR. Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/mach-cavium-octeon/war.h | 1 - arch/mips/include/asm/mach-generic/war.h | 1 - arch/mips/include/asm/mach-ip22/war.h | 1 - arch/mips/include/asm/mach-ip27/war.h | 1 - arch/mips/include/asm/mach-ip28/war.h | 1 - arch/mips/include/asm/mach-ip30/war.h | 1 - arch/mips/include/asm/mach-ip32/war.h | 1 - arch/mips/include/asm/mach-malta/war.h | 1 - arch/mips/include/asm/mach-rc32434/war.h | 1 - arch/mips/include/asm/mach-rm/war.h | 1 - arch/mips/include/asm/mach-sibyte/war.h | 2 -- arch/mips/include/asm/mach-tx49xx/war.h | 1 - arch/mips/include/asm/war.h | 7 ------- drivers/tty/serial/sb1250-duart.c | 9 ++++----- 14 files changed, 4 insertions(+), 25 deletions(-) diff --git a/arch/mips/include/asm/mach-cavium-octeon/war.h b/arch/mips/include/asm/mach-cavium-octeon/war.h index 9aa4ea5522a9..0a2bf6b7af94 100644 --- a/arch/mips/include/asm/mach-cavium-octeon/war.h +++ b/arch/mips/include/asm/mach-cavium-octeon/war.h @@ -10,7 +10,6 @@ #define __ASM_MIPS_MACH_CAVIUM_OCTEON_WAR_H #define BCM1250_M3_WAR 0 -#define SIBYTE_1956_WAR 0 #define CAVIUM_OCTEON_DCACHE_PREFETCH_WAR \ OCTEON_IS_MODEL(OCTEON_CN6XXX) diff --git a/arch/mips/include/asm/mach-generic/war.h b/arch/mips/include/asm/mach-generic/war.h index 4f25636661d5..6b7de91435e3 100644 --- a/arch/mips/include/asm/mach-generic/war.h +++ b/arch/mips/include/asm/mach-generic/war.h @@ -9,6 +9,5 @@ #define __ASM_MACH_GENERIC_WAR_H #define BCM1250_M3_WAR 0 -#define SIBYTE_1956_WAR 0 #endif /* __ASM_MACH_GENERIC_WAR_H */ diff --git a/arch/mips/include/asm/mach-ip22/war.h b/arch/mips/include/asm/mach-ip22/war.h index 09169cfbf932..70de6a5008d3 100644 --- a/arch/mips/include/asm/mach-ip22/war.h +++ b/arch/mips/include/asm/mach-ip22/war.h @@ -9,6 +9,5 @@ #define __ASM_MIPS_MACH_IP22_WAR_H #define BCM1250_M3_WAR 0 -#define SIBYTE_1956_WAR 0 #endif /* __ASM_MIPS_MACH_IP22_WAR_H */ diff --git a/arch/mips/include/asm/mach-ip27/war.h b/arch/mips/include/asm/mach-ip27/war.h index 1c81d5464235..5b01e8fe245f 100644 --- a/arch/mips/include/asm/mach-ip27/war.h +++ b/arch/mips/include/asm/mach-ip27/war.h @@ -9,6 +9,5 @@ #define __ASM_MIPS_MACH_IP27_WAR_H #define BCM1250_M3_WAR 0 -#define SIBYTE_1956_WAR 0 #endif /* __ASM_MIPS_MACH_IP27_WAR_H */ diff --git a/arch/mips/include/asm/mach-ip28/war.h b/arch/mips/include/asm/mach-ip28/war.h index ff66adbaaae5..ba4267e2d34d 100644 --- a/arch/mips/include/asm/mach-ip28/war.h +++ b/arch/mips/include/asm/mach-ip28/war.h @@ -9,6 +9,5 @@ #define __ASM_MIPS_MACH_IP28_WAR_H #define BCM1250_M3_WAR 0 -#define SIBYTE_1956_WAR 0 #endif /* __ASM_MIPS_MACH_IP28_WAR_H */ diff --git a/arch/mips/include/asm/mach-ip30/war.h b/arch/mips/include/asm/mach-ip30/war.h index b00469a39835..f404e22b7798 100644 --- a/arch/mips/include/asm/mach-ip30/war.h +++ b/arch/mips/include/asm/mach-ip30/war.h @@ -6,6 +6,5 @@ #define __ASM_MIPS_MACH_IP30_WAR_H #define BCM1250_M3_WAR 0 -#define SIBYTE_1956_WAR 0 #endif /* __ASM_MIPS_MACH_IP30_WAR_H */ diff --git a/arch/mips/include/asm/mach-ip32/war.h b/arch/mips/include/asm/mach-ip32/war.h index c57a9cd2e50b..01475db746ec 100644 --- a/arch/mips/include/asm/mach-ip32/war.h +++ b/arch/mips/include/asm/mach-ip32/war.h @@ -9,6 +9,5 @@ #define __ASM_MIPS_MACH_IP32_WAR_H #define BCM1250_M3_WAR 0 -#define SIBYTE_1956_WAR 0 #endif /* __ASM_MIPS_MACH_IP32_WAR_H */ diff --git a/arch/mips/include/asm/mach-malta/war.h b/arch/mips/include/asm/mach-malta/war.h index 73c9e6d84a8f..68b204ff59a6 100644 --- a/arch/mips/include/asm/mach-malta/war.h +++ b/arch/mips/include/asm/mach-malta/war.h @@ -9,6 +9,5 @@ #define __ASM_MIPS_MACH_MIPS_WAR_H #define BCM1250_M3_WAR 0 -#define SIBYTE_1956_WAR 0 #endif /* __ASM_MIPS_MACH_MIPS_WAR_H */ diff --git a/arch/mips/include/asm/mach-rc32434/war.h b/arch/mips/include/asm/mach-rc32434/war.h index 73c9e6d84a8f..68b204ff59a6 100644 --- a/arch/mips/include/asm/mach-rc32434/war.h +++ b/arch/mips/include/asm/mach-rc32434/war.h @@ -9,6 +9,5 @@ #define __ASM_MIPS_MACH_MIPS_WAR_H #define BCM1250_M3_WAR 0 -#define SIBYTE_1956_WAR 0 #endif /* __ASM_MIPS_MACH_MIPS_WAR_H */ diff --git a/arch/mips/include/asm/mach-rm/war.h b/arch/mips/include/asm/mach-rm/war.h index c396a31706ac..093a3894ae41 100644 --- a/arch/mips/include/asm/mach-rm/war.h +++ b/arch/mips/include/asm/mach-rm/war.h @@ -9,6 +9,5 @@ #define __ASM_MIPS_MACH_RM_WAR_H #define BCM1250_M3_WAR 0 -#define SIBYTE_1956_WAR 0 #endif /* __ASM_MIPS_MACH_RM_WAR_H */ diff --git a/arch/mips/include/asm/mach-sibyte/war.h b/arch/mips/include/asm/mach-sibyte/war.h index fa9bbc228dd7..71eff5bc3f53 100644 --- a/arch/mips/include/asm/mach-sibyte/war.h +++ b/arch/mips/include/asm/mach-sibyte/war.h @@ -15,12 +15,10 @@ extern int sb1250_m3_workaround_needed(void); #endif #define BCM1250_M3_WAR sb1250_m3_workaround_needed() -#define SIBYTE_1956_WAR 1 #else #define BCM1250_M3_WAR 0 -#define SIBYTE_1956_WAR 0 #endif diff --git a/arch/mips/include/asm/mach-tx49xx/war.h b/arch/mips/include/asm/mach-tx49xx/war.h index 7213d9334f3f..0dc2beb5bf5a 100644 --- a/arch/mips/include/asm/mach-tx49xx/war.h +++ b/arch/mips/include/asm/mach-tx49xx/war.h @@ -9,6 +9,5 @@ #define __ASM_MIPS_MACH_TX49XX_WAR_H #define BCM1250_M3_WAR 0 -#define SIBYTE_1956_WAR 0 #endif /* __ASM_MIPS_MACH_TX49XX_WAR_H */ diff --git a/arch/mips/include/asm/war.h b/arch/mips/include/asm/war.h index 4f4d37b3dd07..2ce5cd61a072 100644 --- a/arch/mips/include/asm/war.h +++ b/arch/mips/include/asm/war.h @@ -86,11 +86,4 @@ #error Check setting of BCM1250_M3_WAR for your platform #endif -/* - * This is a DUART workaround related to glitches around register accesses - */ -#ifndef SIBYTE_1956_WAR -#error Check setting of SIBYTE_1956_WAR for your platform -#endif - #endif /* _ASM_WAR_H */ diff --git a/drivers/tty/serial/sb1250-duart.c b/drivers/tty/serial/sb1250-duart.c index bd5e7e9938ce..22c7bc90b104 100644 --- a/drivers/tty/serial/sb1250-duart.c +++ b/drivers/tty/serial/sb1250-duart.c @@ -35,7 +35,6 @@ #include #include -#include #include #include @@ -157,7 +156,7 @@ static unsigned char read_sbdchn(struct sbd_port *sport, int reg) unsigned char retval; retval = __read_sbdchn(sport, reg); - if (SIBYTE_1956_WAR) + if (IS_ENABLED(CONFIG_SB1_PASS_2_WORKAROUNDS)) __war_sbd1956(sport); return retval; } @@ -167,7 +166,7 @@ static unsigned char read_sbdshr(struct sbd_port *sport, int reg) unsigned char retval; retval = __read_sbdshr(sport, reg); - if (SIBYTE_1956_WAR) + if (IS_ENABLED(CONFIG_SB1_PASS_2_WORKAROUNDS)) __war_sbd1956(sport); return retval; } @@ -175,14 +174,14 @@ static unsigned char read_sbdshr(struct sbd_port *sport, int reg) static void write_sbdchn(struct sbd_port *sport, int reg, unsigned int value) { __write_sbdchn(sport, reg, value); - if (SIBYTE_1956_WAR) + if (IS_ENABLED(CONFIG_SB1_PASS_2_WORKAROUNDS)) __war_sbd1956(sport); } static void write_sbdshr(struct sbd_port *sport, int reg, unsigned int value) { __write_sbdshr(sport, reg, value); - if (SIBYTE_1956_WAR) + if (IS_ENABLED(CONFIG_SB1_PASS_2_WORKAROUNDS)) __war_sbd1956(sport); } From ab5743079b8e3d3d4309664903f6b1f579168a56 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Mon, 24 Aug 2020 18:32:52 +0200 Subject: [PATCH 085/645] MIPS: Get rid of BCM1250_M3_WAR BCM1250_M3_WAR is depending on CONFIG_CONFIG_SB1_PASS_2_WORKAROUNDS. So using this option directly lets and remove define. Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/mach-cavium-octeon/war.h | 2 -- arch/mips/include/asm/mach-generic/war.h | 2 -- arch/mips/include/asm/mach-ip22/war.h | 2 -- arch/mips/include/asm/mach-ip27/war.h | 2 -- arch/mips/include/asm/mach-ip28/war.h | 2 -- arch/mips/include/asm/mach-ip30/war.h | 2 -- arch/mips/include/asm/mach-ip32/war.h | 2 -- arch/mips/include/asm/mach-malta/war.h | 2 -- arch/mips/include/asm/mach-rc32434/war.h | 2 -- arch/mips/include/asm/mach-rm/war.h | 2 -- arch/mips/include/asm/mach-sibyte/war.h | 14 -------------- arch/mips/include/asm/mach-tx49xx/war.h | 2 -- arch/mips/include/asm/war.h | 14 -------------- arch/mips/mm/tlbex.c | 6 +++++- 14 files changed, 5 insertions(+), 51 deletions(-) diff --git a/arch/mips/include/asm/mach-cavium-octeon/war.h b/arch/mips/include/asm/mach-cavium-octeon/war.h index 0a2bf6b7af94..616de70e697c 100644 --- a/arch/mips/include/asm/mach-cavium-octeon/war.h +++ b/arch/mips/include/asm/mach-cavium-octeon/war.h @@ -9,8 +9,6 @@ #ifndef __ASM_MIPS_MACH_CAVIUM_OCTEON_WAR_H #define __ASM_MIPS_MACH_CAVIUM_OCTEON_WAR_H -#define BCM1250_M3_WAR 0 - #define CAVIUM_OCTEON_DCACHE_PREFETCH_WAR \ OCTEON_IS_MODEL(OCTEON_CN6XXX) diff --git a/arch/mips/include/asm/mach-generic/war.h b/arch/mips/include/asm/mach-generic/war.h index 6b7de91435e3..94796ad7e7de 100644 --- a/arch/mips/include/asm/mach-generic/war.h +++ b/arch/mips/include/asm/mach-generic/war.h @@ -8,6 +8,4 @@ #ifndef __ASM_MACH_GENERIC_WAR_H #define __ASM_MACH_GENERIC_WAR_H -#define BCM1250_M3_WAR 0 - #endif /* __ASM_MACH_GENERIC_WAR_H */ diff --git a/arch/mips/include/asm/mach-ip22/war.h b/arch/mips/include/asm/mach-ip22/war.h index 70de6a5008d3..12cf05dd46d3 100644 --- a/arch/mips/include/asm/mach-ip22/war.h +++ b/arch/mips/include/asm/mach-ip22/war.h @@ -8,6 +8,4 @@ #ifndef __ASM_MIPS_MACH_IP22_WAR_H #define __ASM_MIPS_MACH_IP22_WAR_H -#define BCM1250_M3_WAR 0 - #endif /* __ASM_MIPS_MACH_IP22_WAR_H */ diff --git a/arch/mips/include/asm/mach-ip27/war.h b/arch/mips/include/asm/mach-ip27/war.h index 5b01e8fe245f..0852fe64594d 100644 --- a/arch/mips/include/asm/mach-ip27/war.h +++ b/arch/mips/include/asm/mach-ip27/war.h @@ -8,6 +8,4 @@ #ifndef __ASM_MIPS_MACH_IP27_WAR_H #define __ASM_MIPS_MACH_IP27_WAR_H -#define BCM1250_M3_WAR 0 - #endif /* __ASM_MIPS_MACH_IP27_WAR_H */ diff --git a/arch/mips/include/asm/mach-ip28/war.h b/arch/mips/include/asm/mach-ip28/war.h index ba4267e2d34d..32796925700a 100644 --- a/arch/mips/include/asm/mach-ip28/war.h +++ b/arch/mips/include/asm/mach-ip28/war.h @@ -8,6 +8,4 @@ #ifndef __ASM_MIPS_MACH_IP28_WAR_H #define __ASM_MIPS_MACH_IP28_WAR_H -#define BCM1250_M3_WAR 0 - #endif /* __ASM_MIPS_MACH_IP28_WAR_H */ diff --git a/arch/mips/include/asm/mach-ip30/war.h b/arch/mips/include/asm/mach-ip30/war.h index f404e22b7798..ea77545f5128 100644 --- a/arch/mips/include/asm/mach-ip30/war.h +++ b/arch/mips/include/asm/mach-ip30/war.h @@ -5,6 +5,4 @@ #ifndef __ASM_MIPS_MACH_IP30_WAR_H #define __ASM_MIPS_MACH_IP30_WAR_H -#define BCM1250_M3_WAR 0 - #endif /* __ASM_MIPS_MACH_IP30_WAR_H */ diff --git a/arch/mips/include/asm/mach-ip32/war.h b/arch/mips/include/asm/mach-ip32/war.h index 01475db746ec..3e81408795b4 100644 --- a/arch/mips/include/asm/mach-ip32/war.h +++ b/arch/mips/include/asm/mach-ip32/war.h @@ -8,6 +8,4 @@ #ifndef __ASM_MIPS_MACH_IP32_WAR_H #define __ASM_MIPS_MACH_IP32_WAR_H -#define BCM1250_M3_WAR 0 - #endif /* __ASM_MIPS_MACH_IP32_WAR_H */ diff --git a/arch/mips/include/asm/mach-malta/war.h b/arch/mips/include/asm/mach-malta/war.h index 68b204ff59a6..0f5401c0e888 100644 --- a/arch/mips/include/asm/mach-malta/war.h +++ b/arch/mips/include/asm/mach-malta/war.h @@ -8,6 +8,4 @@ #ifndef __ASM_MIPS_MACH_MIPS_WAR_H #define __ASM_MIPS_MACH_MIPS_WAR_H -#define BCM1250_M3_WAR 0 - #endif /* __ASM_MIPS_MACH_MIPS_WAR_H */ diff --git a/arch/mips/include/asm/mach-rc32434/war.h b/arch/mips/include/asm/mach-rc32434/war.h index 68b204ff59a6..0f5401c0e888 100644 --- a/arch/mips/include/asm/mach-rc32434/war.h +++ b/arch/mips/include/asm/mach-rc32434/war.h @@ -8,6 +8,4 @@ #ifndef __ASM_MIPS_MACH_MIPS_WAR_H #define __ASM_MIPS_MACH_MIPS_WAR_H -#define BCM1250_M3_WAR 0 - #endif /* __ASM_MIPS_MACH_MIPS_WAR_H */ diff --git a/arch/mips/include/asm/mach-rm/war.h b/arch/mips/include/asm/mach-rm/war.h index 093a3894ae41..723c9de79ea1 100644 --- a/arch/mips/include/asm/mach-rm/war.h +++ b/arch/mips/include/asm/mach-rm/war.h @@ -8,6 +8,4 @@ #ifndef __ASM_MIPS_MACH_RM_WAR_H #define __ASM_MIPS_MACH_RM_WAR_H -#define BCM1250_M3_WAR 0 - #endif /* __ASM_MIPS_MACH_RM_WAR_H */ diff --git a/arch/mips/include/asm/mach-sibyte/war.h b/arch/mips/include/asm/mach-sibyte/war.h index 71eff5bc3f53..157eca1be328 100644 --- a/arch/mips/include/asm/mach-sibyte/war.h +++ b/arch/mips/include/asm/mach-sibyte/war.h @@ -8,18 +8,4 @@ #ifndef __ASM_MIPS_MACH_SIBYTE_WAR_H #define __ASM_MIPS_MACH_SIBYTE_WAR_H -#if defined(CONFIG_SB1_PASS_2_WORKAROUNDS) - -#ifndef __ASSEMBLY__ -extern int sb1250_m3_workaround_needed(void); -#endif - -#define BCM1250_M3_WAR sb1250_m3_workaround_needed() - -#else - -#define BCM1250_M3_WAR 0 - -#endif - #endif /* __ASM_MIPS_MACH_SIBYTE_WAR_H */ diff --git a/arch/mips/include/asm/mach-tx49xx/war.h b/arch/mips/include/asm/mach-tx49xx/war.h index 0dc2beb5bf5a..edf50e2bbb34 100644 --- a/arch/mips/include/asm/mach-tx49xx/war.h +++ b/arch/mips/include/asm/mach-tx49xx/war.h @@ -8,6 +8,4 @@ #ifndef __ASM_MIPS_MACH_TX49XX_WAR_H #define __ASM_MIPS_MACH_TX49XX_WAR_H -#define BCM1250_M3_WAR 0 - #endif /* __ASM_MIPS_MACH_TX49XX_WAR_H */ diff --git a/arch/mips/include/asm/war.h b/arch/mips/include/asm/war.h index 2ce5cd61a072..c20c04855089 100644 --- a/arch/mips/include/asm/war.h +++ b/arch/mips/include/asm/war.h @@ -72,18 +72,4 @@ #define DADDI_WAR 0 #endif -/* - * Workaround for the Sibyte M3 errata the text of which can be found at - * - * http://sibyte.broadcom.com/hw/bcm1250/docs/pass2errata.txt - * - * This will enable the use of a special TLB refill handler which does a - * consistency check on the information in c0_badvaddr and c0_entryhi and - * will just return and take the exception again if the information was - * found to be inconsistent. - */ -#ifndef BCM1250_M3_WAR -#error Check setting of BCM1250_M3_WAR for your platform -#endif - #endif /* _ASM_WAR_H */ diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index e931eb06af57..a7521b8f7658 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -83,9 +83,13 @@ static inline int r4k_250MHZhwbug(void) return 0; } +extern int sb1250_m3_workaround_needed(void); + static inline int __maybe_unused bcm1250_m3_war(void) { - return BCM1250_M3_WAR; + if (IS_ENABLED(CONFIG_SB1_PASS_2_WORKAROUNDS)) + return sb1250_m3_workaround_needed(); + return 0; } static inline int __maybe_unused r10000_llsc_war(void) From 8e7291d603a3fa8f0d16feb825629c669f36c49e Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Mon, 24 Aug 2020 18:32:53 +0200 Subject: [PATCH 086/645] MIPS: Get rid of CAVIUM_OCTEON_DCACHE_PREFETCH_WAR CAVIUM_OCTEON_DCACHE_PREFETCH_WAR is a check for Octeon model CN6XXXX. By using the version check we can remove the define. Signed-off-by: Thomas Bogendoerfer --- arch/mips/cavium-octeon/setup.c | 2 +- arch/mips/include/asm/mach-cavium-octeon/war.h | 3 --- arch/mips/mm/uasm.c | 2 +- 3 files changed, 2 insertions(+), 5 deletions(-) diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c index 4f34d92b52f9..8a357cb068c2 100644 --- a/arch/mips/cavium-octeon/setup.c +++ b/arch/mips/cavium-octeon/setup.c @@ -1126,7 +1126,7 @@ EXPORT_SYMBOL(prom_putchar); void __init prom_free_prom_memory(void) { - if (CAVIUM_OCTEON_DCACHE_PREFETCH_WAR) { + if (OCTEON_IS_MODEL(OCTEON_CN6XXX)) { /* Check for presence of Core-14449 fix. */ u32 insn; u32 *foo; diff --git a/arch/mips/include/asm/mach-cavium-octeon/war.h b/arch/mips/include/asm/mach-cavium-octeon/war.h index 616de70e697c..ba6df0a186e9 100644 --- a/arch/mips/include/asm/mach-cavium-octeon/war.h +++ b/arch/mips/include/asm/mach-cavium-octeon/war.h @@ -9,7 +9,4 @@ #ifndef __ASM_MIPS_MACH_CAVIUM_OCTEON_WAR_H #define __ASM_MIPS_MACH_CAVIUM_OCTEON_WAR_H -#define CAVIUM_OCTEON_DCACHE_PREFETCH_WAR \ - OCTEON_IS_MODEL(OCTEON_CN6XXX) - #endif /* __ASM_MIPS_MACH_CAVIUM_OCTEON_WAR_H */ diff --git a/arch/mips/mm/uasm.c b/arch/mips/mm/uasm.c index c56f129c9a4b..81dd226d6b6b 100644 --- a/arch/mips/mm/uasm.c +++ b/arch/mips/mm/uasm.c @@ -394,7 +394,7 @@ I_u2u1u3(_lddir) void uasm_i_pref(u32 **buf, unsigned int a, signed int b, unsigned int c) { - if (CAVIUM_OCTEON_DCACHE_PREFETCH_WAR && a <= 24 && a != 5) + if (OCTEON_IS_MODEL(OCTEON_CN6XXX) && a <= 24 && a != 5) /* * As per erratum Core-14449, replace prefetches 0-4, * 6-24 with 'pref 28'. From 601637e42df045ca2d1a9324d56765f044d46866 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Mon, 24 Aug 2020 18:32:54 +0200 Subject: [PATCH 087/645] MIPS: Remove mach-*/war.h After conversion of all WAR defines we can now remove all mach-*/war.h files. Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/mach-cavium-octeon/war.h | 12 ------------ arch/mips/include/asm/mach-generic/war.h | 11 ----------- arch/mips/include/asm/mach-ip22/war.h | 11 ----------- arch/mips/include/asm/mach-ip27/war.h | 11 ----------- arch/mips/include/asm/mach-ip28/war.h | 11 ----------- arch/mips/include/asm/mach-ip30/war.h | 8 -------- arch/mips/include/asm/mach-ip32/war.h | 11 ----------- arch/mips/include/asm/mach-malta/war.h | 11 ----------- arch/mips/include/asm/mach-rc32434/war.h | 11 ----------- arch/mips/include/asm/mach-rm/war.h | 11 ----------- arch/mips/include/asm/mach-sibyte/war.h | 11 ----------- arch/mips/include/asm/mach-tx49xx/war.h | 11 ----------- arch/mips/include/asm/war.h | 2 -- 13 files changed, 132 deletions(-) delete mode 100644 arch/mips/include/asm/mach-cavium-octeon/war.h delete mode 100644 arch/mips/include/asm/mach-generic/war.h delete mode 100644 arch/mips/include/asm/mach-ip22/war.h delete mode 100644 arch/mips/include/asm/mach-ip27/war.h delete mode 100644 arch/mips/include/asm/mach-ip28/war.h delete mode 100644 arch/mips/include/asm/mach-ip30/war.h delete mode 100644 arch/mips/include/asm/mach-ip32/war.h delete mode 100644 arch/mips/include/asm/mach-malta/war.h delete mode 100644 arch/mips/include/asm/mach-rc32434/war.h delete mode 100644 arch/mips/include/asm/mach-rm/war.h delete mode 100644 arch/mips/include/asm/mach-sibyte/war.h delete mode 100644 arch/mips/include/asm/mach-tx49xx/war.h diff --git a/arch/mips/include/asm/mach-cavium-octeon/war.h b/arch/mips/include/asm/mach-cavium-octeon/war.h deleted file mode 100644 index ba6df0a186e9..000000000000 --- a/arch/mips/include/asm/mach-cavium-octeon/war.h +++ /dev/null @@ -1,12 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2002, 2004, 2007 by Ralf Baechle - * Copyright (C) 2008 Cavium Networks - */ -#ifndef __ASM_MIPS_MACH_CAVIUM_OCTEON_WAR_H -#define __ASM_MIPS_MACH_CAVIUM_OCTEON_WAR_H - -#endif /* __ASM_MIPS_MACH_CAVIUM_OCTEON_WAR_H */ diff --git a/arch/mips/include/asm/mach-generic/war.h b/arch/mips/include/asm/mach-generic/war.h deleted file mode 100644 index 94796ad7e7de..000000000000 --- a/arch/mips/include/asm/mach-generic/war.h +++ /dev/null @@ -1,11 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2002, 2004, 2007 by Ralf Baechle - */ -#ifndef __ASM_MACH_GENERIC_WAR_H -#define __ASM_MACH_GENERIC_WAR_H - -#endif /* __ASM_MACH_GENERIC_WAR_H */ diff --git a/arch/mips/include/asm/mach-ip22/war.h b/arch/mips/include/asm/mach-ip22/war.h deleted file mode 100644 index 12cf05dd46d3..000000000000 --- a/arch/mips/include/asm/mach-ip22/war.h +++ /dev/null @@ -1,11 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2002, 2004, 2007 by Ralf Baechle - */ -#ifndef __ASM_MIPS_MACH_IP22_WAR_H -#define __ASM_MIPS_MACH_IP22_WAR_H - -#endif /* __ASM_MIPS_MACH_IP22_WAR_H */ diff --git a/arch/mips/include/asm/mach-ip27/war.h b/arch/mips/include/asm/mach-ip27/war.h deleted file mode 100644 index 0852fe64594d..000000000000 --- a/arch/mips/include/asm/mach-ip27/war.h +++ /dev/null @@ -1,11 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2002, 2004, 2007 by Ralf Baechle - */ -#ifndef __ASM_MIPS_MACH_IP27_WAR_H -#define __ASM_MIPS_MACH_IP27_WAR_H - -#endif /* __ASM_MIPS_MACH_IP27_WAR_H */ diff --git a/arch/mips/include/asm/mach-ip28/war.h b/arch/mips/include/asm/mach-ip28/war.h deleted file mode 100644 index 32796925700a..000000000000 --- a/arch/mips/include/asm/mach-ip28/war.h +++ /dev/null @@ -1,11 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2002, 2004, 2007 by Ralf Baechle - */ -#ifndef __ASM_MIPS_MACH_IP28_WAR_H -#define __ASM_MIPS_MACH_IP28_WAR_H - -#endif /* __ASM_MIPS_MACH_IP28_WAR_H */ diff --git a/arch/mips/include/asm/mach-ip30/war.h b/arch/mips/include/asm/mach-ip30/war.h deleted file mode 100644 index ea77545f5128..000000000000 --- a/arch/mips/include/asm/mach-ip30/war.h +++ /dev/null @@ -1,8 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (C) 2002, 2004, 2007 by Ralf Baechle - */ -#ifndef __ASM_MIPS_MACH_IP30_WAR_H -#define __ASM_MIPS_MACH_IP30_WAR_H - -#endif /* __ASM_MIPS_MACH_IP30_WAR_H */ diff --git a/arch/mips/include/asm/mach-ip32/war.h b/arch/mips/include/asm/mach-ip32/war.h deleted file mode 100644 index 3e81408795b4..000000000000 --- a/arch/mips/include/asm/mach-ip32/war.h +++ /dev/null @@ -1,11 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2002, 2004, 2007 by Ralf Baechle - */ -#ifndef __ASM_MIPS_MACH_IP32_WAR_H -#define __ASM_MIPS_MACH_IP32_WAR_H - -#endif /* __ASM_MIPS_MACH_IP32_WAR_H */ diff --git a/arch/mips/include/asm/mach-malta/war.h b/arch/mips/include/asm/mach-malta/war.h deleted file mode 100644 index 0f5401c0e888..000000000000 --- a/arch/mips/include/asm/mach-malta/war.h +++ /dev/null @@ -1,11 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2002, 2004, 2007 by Ralf Baechle - */ -#ifndef __ASM_MIPS_MACH_MIPS_WAR_H -#define __ASM_MIPS_MACH_MIPS_WAR_H - -#endif /* __ASM_MIPS_MACH_MIPS_WAR_H */ diff --git a/arch/mips/include/asm/mach-rc32434/war.h b/arch/mips/include/asm/mach-rc32434/war.h deleted file mode 100644 index 0f5401c0e888..000000000000 --- a/arch/mips/include/asm/mach-rc32434/war.h +++ /dev/null @@ -1,11 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2002, 2004, 2007 by Ralf Baechle - */ -#ifndef __ASM_MIPS_MACH_MIPS_WAR_H -#define __ASM_MIPS_MACH_MIPS_WAR_H - -#endif /* __ASM_MIPS_MACH_MIPS_WAR_H */ diff --git a/arch/mips/include/asm/mach-rm/war.h b/arch/mips/include/asm/mach-rm/war.h deleted file mode 100644 index 723c9de79ea1..000000000000 --- a/arch/mips/include/asm/mach-rm/war.h +++ /dev/null @@ -1,11 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2002, 2004, 2007 by Ralf Baechle - */ -#ifndef __ASM_MIPS_MACH_RM_WAR_H -#define __ASM_MIPS_MACH_RM_WAR_H - -#endif /* __ASM_MIPS_MACH_RM_WAR_H */ diff --git a/arch/mips/include/asm/mach-sibyte/war.h b/arch/mips/include/asm/mach-sibyte/war.h deleted file mode 100644 index 157eca1be328..000000000000 --- a/arch/mips/include/asm/mach-sibyte/war.h +++ /dev/null @@ -1,11 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2002, 2004, 2007 by Ralf Baechle - */ -#ifndef __ASM_MIPS_MACH_SIBYTE_WAR_H -#define __ASM_MIPS_MACH_SIBYTE_WAR_H - -#endif /* __ASM_MIPS_MACH_SIBYTE_WAR_H */ diff --git a/arch/mips/include/asm/mach-tx49xx/war.h b/arch/mips/include/asm/mach-tx49xx/war.h deleted file mode 100644 index edf50e2bbb34..000000000000 --- a/arch/mips/include/asm/mach-tx49xx/war.h +++ /dev/null @@ -1,11 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2002, 2004, 2007 by Ralf Baechle - */ -#ifndef __ASM_MIPS_MACH_TX49XX_WAR_H -#define __ASM_MIPS_MACH_TX49XX_WAR_H - -#endif /* __ASM_MIPS_MACH_TX49XX_WAR_H */ diff --git a/arch/mips/include/asm/war.h b/arch/mips/include/asm/war.h index c20c04855089..21443f096238 100644 --- a/arch/mips/include/asm/war.h +++ b/arch/mips/include/asm/war.h @@ -9,8 +9,6 @@ #ifndef _ASM_WAR_H #define _ASM_WAR_H -#include - /* * Work around certain R4000 CPU errata (as implemented by GCC): * From 2f279eeb68b8eda43a95255db701b4faaeedbe0f Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Wed, 12 Aug 2020 12:25:17 +0000 Subject: [PATCH 088/645] powerpc/uaccess: Add pre-update addressing to __get_user_asm() and __put_user_asm() Enable pre-update addressing mode in __get_user_asm() and __put_user_asm() Signed-off-by: Christophe Leroy Reviewed-by: Segher Boessenkool Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/13041c7df39e89ddf574ea0cdc6dedfdd9734140.1597235091.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/uaccess.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index b1d5e8b66b31..7c2427f237e1 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -158,7 +158,7 @@ extern long __put_user_bad(void); */ #define __put_user_asm(x, addr, err, op) \ __asm__ __volatile__( \ - "1: " op "%X2 %1,%2 # put_user\n" \ + "1: " op "%U2%X2 %1,%2 # put_user\n" \ "2:\n" \ ".section .fixup,\"ax\"\n" \ "3: li %0,%3\n" \ @@ -166,7 +166,7 @@ extern long __put_user_bad(void); ".previous\n" \ EX_TABLE(1b, 3b) \ : "=r" (err) \ - : "r" (x), "m" (*addr), "i" (-EFAULT), "0" (err)) + : "r" (x), "m<>" (*addr), "i" (-EFAULT), "0" (err)) #ifdef __powerpc64__ #define __put_user_asm2(x, ptr, retval) \ @@ -316,7 +316,7 @@ extern long __get_user_bad(void); #define __get_user_asm(x, addr, err, op) \ __asm__ __volatile__( \ - "1: "op"%X2 %1, %2 # get_user\n" \ + "1: "op"%U2%X2 %1, %2 # get_user\n" \ "2:\n" \ ".section .fixup,\"ax\"\n" \ "3: li %0,%3\n" \ @@ -325,7 +325,7 @@ extern long __get_user_bad(void); ".previous\n" \ EX_TABLE(1b, 3b) \ : "=r" (err), "=r" (x) \ - : "m" (*addr), "i" (-EFAULT), "0" (err)) + : "m<>" (*addr), "i" (-EFAULT), "0" (err)) #ifdef __powerpc64__ #define __get_user_asm2(x, addr, err) \ From 353bce211e00d183344f464ba1ee0e1ffb0e2a6c Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 17 Aug 2020 05:46:39 +0000 Subject: [PATCH 089/645] powerpc/process: Remove unnecessary #ifdef CONFIG_FUNCTION_GRAPH_TRACER ftrace_graph_ret_addr() is always defined and returns 'ip' when CONFIG_FUNCTION GRAPH_TRACER is not set. So the #ifdef is not needed, remove it. Signed-off-by: Christophe Leroy Acked-by: Naveen N. Rao Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/9d11143d4e27ba8274369a926968756917584868.1597643153.git.christophe.leroy@csgroup.eu --- arch/powerpc/kernel/process.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 016bd831908e..febe9f7cda2f 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -2096,10 +2096,8 @@ void show_stack(struct task_struct *tsk, unsigned long *stack, unsigned long sp, ip, lr, newsp; int count = 0; int firstframe = 1; -#ifdef CONFIG_FUNCTION_GRAPH_TRACER unsigned long ret_addr; int ftrace_idx = 0; -#endif if (tsk == NULL) tsk = current; @@ -2127,12 +2125,10 @@ void show_stack(struct task_struct *tsk, unsigned long *stack, if (!firstframe || ip != lr) { printk("%s["REG"] ["REG"] %pS", loglvl, sp, ip, (void *)ip); -#ifdef CONFIG_FUNCTION_GRAPH_TRACER ret_addr = ftrace_graph_ret_addr(current, &ftrace_idx, ip, stack); if (ret_addr != ip) pr_cont(" (%pS)", (void *)ret_addr); -#endif if (firstframe) pr_cont(" (unreliable)"); pr_cont("\n"); From 10bf59d923c2766ec8d6f0243481c865c7db9979 Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Tue, 18 Aug 2020 14:45:57 +1000 Subject: [PATCH 090/645] powerpc/pseries/eeh: Fix dumb linebreaks These annoy me every time I see them. Why are they here? They're not even needed for 80cols compliance. Signed-off-by: Oliver O'Halloran Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200818044557.135497-1-oohall@gmail.com --- arch/powerpc/platforms/pseries/eeh_pseries.c | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index cb2d9a970b7b..1db74cec72bc 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -161,8 +161,7 @@ static int pseries_eeh_phb_reset(struct pci_controller *phb, int config_addr, in BUID_LO(phb->buid), option); /* If fundamental-reset not supported, try hot-reset */ - if (option == EEH_RESET_FUNDAMENTAL && - ret == -8) { + if (option == EEH_RESET_FUNDAMENTAL && ret == -8) { option = EEH_RESET_HOT; ret = rtas_call(ibm_set_slot_reset, 4, 1, NULL, config_addr, BUID_HI(phb->buid), @@ -170,8 +169,7 @@ static int pseries_eeh_phb_reset(struct pci_controller *phb, int config_addr, in } /* We need reset hold or settlement delay */ - if (option == EEH_RESET_FUNDAMENTAL || - option == EEH_RESET_HOT) + if (option == EEH_RESET_FUNDAMENTAL || option == EEH_RESET_HOT) msleep(EEH_PE_RST_HOLD_TIME); else msleep(EEH_PE_RST_SETTLE_TIME); @@ -621,8 +619,7 @@ static int pseries_eeh_set_option(struct eeh_pe *pe, int option) /* Not support */ return 0; default: - pr_err("%s: Invalid option %d\n", - __func__, option); + pr_err("%s: Invalid option %d\n", __func__, option); return -EINVAL; } @@ -954,8 +951,7 @@ static int pseries_notify_resume(struct eeh_dev *edev) if (!edev) return -EEXIST; - if (rtas_token("ibm,open-sriov-allow-unfreeze") - == RTAS_UNKNOWN_SERVICE) + if (rtas_token("ibm,open-sriov-allow-unfreeze") == RTAS_UNKNOWN_SERVICE) return -EINVAL; if (edev->pdev->is_physfn || edev->pdev->is_virtfn) From c0176429b7b07893a5c1fd38baff055c919ba9e3 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Thu, 13 Aug 2020 11:34:43 +1000 Subject: [PATCH 091/645] selftests/powerpc: Fix TM tests when CPU 0 is offline Several of the TM tests fail spuriously if CPU 0 is offline, because they blindly try to affinitise to CPU 0. Fix them by picking any online CPU and using that instead. Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200813013445.686464-1-mpe@ellerman.id.au --- tools/testing/selftests/powerpc/tm/tm-poison.c | 11 +++++++---- tools/testing/selftests/powerpc/tm/tm-trap.c | 10 ++++++---- tools/testing/selftests/powerpc/tm/tm-unavailable.c | 9 ++++++--- 3 files changed, 19 insertions(+), 11 deletions(-) diff --git a/tools/testing/selftests/powerpc/tm/tm-poison.c b/tools/testing/selftests/powerpc/tm/tm-poison.c index 977558497c16..29e5f26af7b9 100644 --- a/tools/testing/selftests/powerpc/tm/tm-poison.c +++ b/tools/testing/selftests/powerpc/tm/tm-poison.c @@ -26,7 +26,7 @@ int tm_poison_test(void) { - int pid; + int cpu, pid; cpu_set_t cpuset; uint64_t poison = 0xdeadbeefc0dec0fe; uint64_t unknown = 0; @@ -35,10 +35,13 @@ int tm_poison_test(void) SKIP_IF(!have_htm()); - /* Attach both Child and Parent to CPU 0 */ + cpu = pick_online_cpu(); + FAIL_IF(cpu < 0); + + // Attach both Child and Parent to the same CPU CPU_ZERO(&cpuset); - CPU_SET(0, &cpuset); - sched_setaffinity(0, sizeof(cpuset), &cpuset); + CPU_SET(cpu, &cpuset); + FAIL_IF(sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0); pid = fork(); if (!pid) { diff --git a/tools/testing/selftests/powerpc/tm/tm-trap.c b/tools/testing/selftests/powerpc/tm/tm-trap.c index 601f0c1d450d..c75960af8018 100644 --- a/tools/testing/selftests/powerpc/tm/tm-trap.c +++ b/tools/testing/selftests/powerpc/tm/tm-trap.c @@ -247,8 +247,7 @@ void *pong(void *not_used) int tm_trap_test(void) { uint16_t k = 1; - - int rc; + int cpu, rc; pthread_attr_t attr; cpu_set_t cpuset; @@ -267,9 +266,12 @@ int tm_trap_test(void) usr1_sa.sa_sigaction = usr1_signal_handler; sigaction(SIGUSR1, &usr1_sa, NULL); - /* Set only CPU 0 in the mask. Both threads will be bound to cpu 0. */ + cpu = pick_online_cpu(); + FAIL_IF(cpu < 0); + + // Set only one CPU in the mask. Both threads will be bound to that CPU. CPU_ZERO(&cpuset); - CPU_SET(0, &cpuset); + CPU_SET(cpu, &cpuset); /* Init pthread attribute */ rc = pthread_attr_init(&attr); diff --git a/tools/testing/selftests/powerpc/tm/tm-unavailable.c b/tools/testing/selftests/powerpc/tm/tm-unavailable.c index 2ca2fccb0a3e..a1348a5f721a 100644 --- a/tools/testing/selftests/powerpc/tm/tm-unavailable.c +++ b/tools/testing/selftests/powerpc/tm/tm-unavailable.c @@ -338,16 +338,19 @@ void test_fp_vec(int fp, int vec, pthread_attr_t *attr) int tm_unavailable_test(void) { - int rc, exception; /* FP = 0, VEC = 1, VSX = 2 */ + int cpu, rc, exception; /* FP = 0, VEC = 1, VSX = 2 */ pthread_t t1; pthread_attr_t attr; cpu_set_t cpuset; SKIP_IF(!have_htm()); - /* Set only CPU 0 in the mask. Both threads will be bound to CPU 0. */ + cpu = pick_online_cpu(); + FAIL_IF(cpu < 0); + + // Set only one CPU in the mask. Both threads will be bound to that CPU. CPU_ZERO(&cpuset); - CPU_SET(0, &cpuset); + CPU_SET(cpu, &cpuset); /* Init pthread attribute. */ rc = pthread_attr_init(&attr); From 769628710c33b18ede837bb488e1d24084b35592 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Thu, 13 Aug 2020 11:34:44 +1000 Subject: [PATCH 092/645] selftests/powerpc: Don't use setaffinity in tm-tmspr This test tries to set affinity to CPUs that don't exist, especially if the set of online CPUs doesn't start at 0. But there's no real reason for it to use setaffinity in the first place, it's just trying to create lots of threads to cause contention. So drop the setaffinity entirely. Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200813013445.686464-2-mpe@ellerman.id.au --- tools/testing/selftests/powerpc/tm/tm-tmspr.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/tools/testing/selftests/powerpc/tm/tm-tmspr.c b/tools/testing/selftests/powerpc/tm/tm-tmspr.c index 17becf3dcee4..2ff329e2fca9 100644 --- a/tools/testing/selftests/powerpc/tm/tm-tmspr.c +++ b/tools/testing/selftests/powerpc/tm/tm-tmspr.c @@ -38,14 +38,8 @@ int passed = 1; void tfiar_tfhar(void *in) { - int i, cpu; unsigned long tfhar, tfhar_rd, tfiar, tfiar_rd; - cpu_set_t cpuset; - - CPU_ZERO(&cpuset); - cpu = (unsigned long)in >> 1; - CPU_SET(cpu, &cpuset); - sched_setaffinity(0, sizeof(cpuset), &cpuset); + int i; /* TFIAR: Last bit has to be high so userspace can read register */ tfiar = ((unsigned long)in) + 1; From b5a646a681f5d67ea5190a71d6e84a91efe63b7a Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Thu, 13 Aug 2020 11:34:45 +1000 Subject: [PATCH 093/645] selftests/powerpc: Run tm-tmspr test for longer This test creates some threads, which write to TM SPRs, and then makes sure the registers maintain the correct values across context switches and contention with other threads. But currently the test finishes almost instantaneously, which reduces the chance of it hitting an interesting condition. So increase the number of loops, so it runs a bit longer, though still less than 2s on a Power8. Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200813013445.686464-3-mpe@ellerman.id.au --- tools/testing/selftests/powerpc/tm/tm-tmspr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/powerpc/tm/tm-tmspr.c b/tools/testing/selftests/powerpc/tm/tm-tmspr.c index 2ff329e2fca9..794d574db784 100644 --- a/tools/testing/selftests/powerpc/tm/tm-tmspr.c +++ b/tools/testing/selftests/powerpc/tm/tm-tmspr.c @@ -33,7 +33,7 @@ #include "utils.h" #include "tm.h" -int num_loops = 10000; +int num_loops = 1000000; int passed = 1; void tfiar_tfhar(void *in) From 34c103342be3f9397e656da7c5cc86e97b91f514 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 19 Aug 2020 11:57:19 +1000 Subject: [PATCH 094/645] selftests/powerpc: Make using_hash_mmu() work on Cell & PowerMac These platforms don't show the MMU in /proc/cpuinfo, but they always use hash, so teach using_hash_mmu() that. Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200819015727.1977134-1-mpe@ellerman.id.au --- tools/testing/selftests/powerpc/utils.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/powerpc/utils.c b/tools/testing/selftests/powerpc/utils.c index 18b6a773d5c7..638ffacc90aa 100644 --- a/tools/testing/selftests/powerpc/utils.c +++ b/tools/testing/selftests/powerpc/utils.c @@ -318,7 +318,9 @@ int using_hash_mmu(bool *using_hash) rc = 0; while (fgets(line, sizeof(line), f) != NULL) { - if (strcmp(line, "MMU : Hash\n") == 0) { + if (!strcmp(line, "MMU : Hash\n") || + !strcmp(line, "platform : Cell\n") || + !strcmp(line, "platform : PowerMac\n")) { *using_hash = true; goto out; } From 17c98a541dc9bb1162877af41cddbdca043f9a59 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 19 Aug 2020 11:57:20 +1000 Subject: [PATCH 095/645] selftests/powerpc: Give the bad_accesses test longer to run On older systems this test takes longer to run (duh), give it five minutes which is long enough on a G5 970FX @ 1.6GHz. Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200819015727.1977134-2-mpe@ellerman.id.au --- tools/testing/selftests/powerpc/mm/bad_accesses.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/powerpc/mm/bad_accesses.c b/tools/testing/selftests/powerpc/mm/bad_accesses.c index a864ed7e2008..fd747b2ffcfc 100644 --- a/tools/testing/selftests/powerpc/mm/bad_accesses.c +++ b/tools/testing/selftests/powerpc/mm/bad_accesses.c @@ -139,5 +139,6 @@ static int test(void) int main(void) { + test_harness_set_timeout(300); return test_harness(test, "bad_accesses"); } From d89002397cfb2b65267d6688fe671ee1cf7c5f0d Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 19 Aug 2020 11:57:21 +1000 Subject: [PATCH 096/645] selftests/powerpc: Move set_dscr() into rfi_flush.c This version of set_dscr() was added for the RFI flush test, and is fairly specific to it. It also clashes with the version of set_dscr() in dscr/dscr.h. So move it into the RFI flush test where it's used. Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200819015727.1977134-3-mpe@ellerman.id.au --- .../testing/selftests/powerpc/include/utils.h | 1 - .../selftests/powerpc/security/rfi_flush.c | 35 +++++++++++++++++++ tools/testing/selftests/powerpc/utils.c | 35 ------------------- 3 files changed, 35 insertions(+), 36 deletions(-) diff --git a/tools/testing/selftests/powerpc/include/utils.h b/tools/testing/selftests/powerpc/include/utils.h index 71d2924f5b8b..bba400d1bb90 100644 --- a/tools/testing/selftests/powerpc/include/utils.h +++ b/tools/testing/selftests/powerpc/include/utils.h @@ -35,7 +35,6 @@ int pick_online_cpu(void); int read_debugfs_file(char *debugfs_file, int *result); int write_debugfs_file(char *debugfs_file, int result); int read_sysfs_file(char *debugfs_file, char *result, size_t result_size); -void set_dscr(unsigned long val); int perf_event_open_counter(unsigned int type, unsigned long config, int group_fd); int perf_event_enable(int fd); diff --git a/tools/testing/selftests/powerpc/security/rfi_flush.c b/tools/testing/selftests/powerpc/security/rfi_flush.c index 0a7d0afb26b8..fd37ff9b1c45 100644 --- a/tools/testing/selftests/powerpc/security/rfi_flush.c +++ b/tools/testing/selftests/powerpc/security/rfi_flush.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -41,6 +42,40 @@ static void syscall_loop(char *p, unsigned long iterations, } } +static void sigill_handler(int signr, siginfo_t *info, void *unused) +{ + static int warned = 0; + ucontext_t *ctx = (ucontext_t *)unused; + unsigned long *pc = &UCONTEXT_NIA(ctx); + + /* mtspr 3,RS to check for move to DSCR below */ + if ((*((unsigned int *)*pc) & 0xfc1fffff) == 0x7c0303a6) { + if (!warned++) + printf("WARNING: Skipping over dscr setup. Consider running 'ppc64_cpu --dscr=1' manually.\n"); + *pc += 4; + } else { + printf("SIGILL at %p\n", pc); + abort(); + } +} + +static void set_dscr(unsigned long val) +{ + static int init = 0; + struct sigaction sa; + + if (!init) { + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = sigill_handler; + sa.sa_flags = SA_SIGINFO; + if (sigaction(SIGILL, &sa, NULL)) + perror("sigill_handler"); + init = 1; + } + + asm volatile("mtspr %1,%0" : : "r" (val), "i" (SPRN_DSCR)); +} + int rfi_flush_test(void) { char *p; diff --git a/tools/testing/selftests/powerpc/utils.c b/tools/testing/selftests/powerpc/utils.c index 638ffacc90aa..1f36ee1a909a 100644 --- a/tools/testing/selftests/powerpc/utils.c +++ b/tools/testing/selftests/powerpc/utils.c @@ -10,7 +10,6 @@ #include #include #include -#include #include #include #include @@ -273,40 +272,6 @@ int perf_event_reset(int fd) return 0; } -static void sigill_handler(int signr, siginfo_t *info, void *unused) -{ - static int warned = 0; - ucontext_t *ctx = (ucontext_t *)unused; - unsigned long *pc = &UCONTEXT_NIA(ctx); - - /* mtspr 3,RS to check for move to DSCR below */ - if ((*((unsigned int *)*pc) & 0xfc1fffff) == 0x7c0303a6) { - if (!warned++) - printf("WARNING: Skipping over dscr setup. Consider running 'ppc64_cpu --dscr=1' manually.\n"); - *pc += 4; - } else { - printf("SIGILL at %p\n", pc); - abort(); - } -} - -void set_dscr(unsigned long val) -{ - static int init = 0; - struct sigaction sa; - - if (!init) { - memset(&sa, 0, sizeof(sa)); - sa.sa_sigaction = sigill_handler; - sa.sa_flags = SA_SIGINFO; - if (sigaction(SIGILL, &sa, NULL)) - perror("sigill_handler"); - init = 1; - } - - asm volatile("mtspr %1,%0" : : "r" (val), "i" (SPRN_DSCR)); -} - int using_hash_mmu(bool *using_hash) { char line[128]; From 178282a054dced1a08a9683d41ac08cbace2b2fe Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 19 Aug 2020 11:57:22 +1000 Subject: [PATCH 097/645] selftests/powerpc: Include asm/cputable.h from utils.h utils.h provides have_hwcap() and have_hwcap2() which check for a feature bit. Those bits are defined in asm/cputable.h, so include it in utils.h so users of utils.h don't have to do it manually. Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200819015727.1977134-4-mpe@ellerman.id.au --- tools/testing/selftests/powerpc/alignment/alignment_handler.c | 2 -- tools/testing/selftests/powerpc/include/utils.h | 1 + tools/testing/selftests/powerpc/pmu/count_stcx_fail.c | 1 - tools/testing/selftests/powerpc/pmu/per_event_excludes.c | 2 -- tools/testing/selftests/powerpc/stringloops/memcmp.c | 2 +- tools/testing/selftests/powerpc/tm/tm.h | 3 +-- 6 files changed, 3 insertions(+), 8 deletions(-) diff --git a/tools/testing/selftests/powerpc/alignment/alignment_handler.c b/tools/testing/selftests/powerpc/alignment/alignment_handler.c index 55ef15184057..e4063eba4a5b 100644 --- a/tools/testing/selftests/powerpc/alignment/alignment_handler.c +++ b/tools/testing/selftests/powerpc/alignment/alignment_handler.c @@ -55,8 +55,6 @@ #include #include -#include - #include "utils.h" #include "instructions.h" diff --git a/tools/testing/selftests/powerpc/include/utils.h b/tools/testing/selftests/powerpc/include/utils.h index bba400d1bb90..052b5a775dc2 100644 --- a/tools/testing/selftests/powerpc/include/utils.h +++ b/tools/testing/selftests/powerpc/include/utils.h @@ -12,6 +12,7 @@ #include #include #include +#include #include "reg.h" /* Avoid headaches with PRI?64 - just use %ll? always */ diff --git a/tools/testing/selftests/powerpc/pmu/count_stcx_fail.c b/tools/testing/selftests/powerpc/pmu/count_stcx_fail.c index 2980abca31e0..2070a1e2b3a5 100644 --- a/tools/testing/selftests/powerpc/pmu/count_stcx_fail.c +++ b/tools/testing/selftests/powerpc/pmu/count_stcx_fail.c @@ -9,7 +9,6 @@ #include #include #include -#include #include "event.h" #include "utils.h" diff --git a/tools/testing/selftests/powerpc/pmu/per_event_excludes.c b/tools/testing/selftests/powerpc/pmu/per_event_excludes.c index 2d37942bf72b..ad32a09a6540 100644 --- a/tools/testing/selftests/powerpc/pmu/per_event_excludes.c +++ b/tools/testing/selftests/powerpc/pmu/per_event_excludes.c @@ -12,8 +12,6 @@ #include #include -#include - #include "event.h" #include "lib.h" #include "utils.h" diff --git a/tools/testing/selftests/powerpc/stringloops/memcmp.c b/tools/testing/selftests/powerpc/stringloops/memcmp.c index 979df3d98368..cb2f18855c8d 100644 --- a/tools/testing/selftests/powerpc/stringloops/memcmp.c +++ b/tools/testing/selftests/powerpc/stringloops/memcmp.c @@ -4,7 +4,7 @@ #include #include #include -#include + #include "utils.h" #define SIZE 256 diff --git a/tools/testing/selftests/powerpc/tm/tm.h b/tools/testing/selftests/powerpc/tm/tm.h index c402464b038f..c5a1e5c163fc 100644 --- a/tools/testing/selftests/powerpc/tm/tm.h +++ b/tools/testing/selftests/powerpc/tm/tm.h @@ -6,9 +6,8 @@ #ifndef _SELFTESTS_POWERPC_TM_TM_H #define _SELFTESTS_POWERPC_TM_TM_H -#include -#include #include +#include #include "utils.h" From 4c3c3c502575556c4bc1b401235e641863b1bce6 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 19 Aug 2020 11:57:23 +1000 Subject: [PATCH 098/645] selftests/powerpc: Don't run DSCR tests on old systems The DSCR tests fail on systems that don't have DSCR, so check for the DSCR in hwcap and skip if it's not present. Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200819015727.1977134-5-mpe@ellerman.id.au --- tools/testing/selftests/powerpc/dscr/Makefile | 2 +- tools/testing/selftests/powerpc/dscr/dscr_default_test.c | 2 ++ tools/testing/selftests/powerpc/dscr/dscr_explicit_test.c | 2 ++ tools/testing/selftests/powerpc/dscr/dscr_inherit_exec_test.c | 2 ++ tools/testing/selftests/powerpc/dscr/dscr_inherit_test.c | 2 ++ tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c | 2 ++ tools/testing/selftests/powerpc/dscr/dscr_sysfs_thread_test.c | 2 ++ tools/testing/selftests/powerpc/dscr/dscr_user_test.c | 2 ++ 8 files changed, 15 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/powerpc/dscr/Makefile b/tools/testing/selftests/powerpc/dscr/Makefile index cfa6eedcb66c..845db6273a1b 100644 --- a/tools/testing/selftests/powerpc/dscr/Makefile +++ b/tools/testing/selftests/powerpc/dscr/Makefile @@ -10,4 +10,4 @@ include ../../lib.mk $(OUTPUT)/dscr_default_test: LDLIBS += -lpthread -$(TEST_GEN_PROGS): ../harness.c +$(TEST_GEN_PROGS): ../harness.c ../utils.c diff --git a/tools/testing/selftests/powerpc/dscr/dscr_default_test.c b/tools/testing/selftests/powerpc/dscr/dscr_default_test.c index 288a4e2ad156..e76611e608af 100644 --- a/tools/testing/selftests/powerpc/dscr/dscr_default_test.c +++ b/tools/testing/selftests/powerpc/dscr/dscr_default_test.c @@ -63,6 +63,8 @@ int dscr_default(void) unsigned long i, *status[THREADS]; unsigned long orig_dscr_default; + SKIP_IF(!have_hwcap2(PPC_FEATURE2_DSCR)); + orig_dscr_default = get_default_dscr(); /* Initial DSCR default */ diff --git a/tools/testing/selftests/powerpc/dscr/dscr_explicit_test.c b/tools/testing/selftests/powerpc/dscr/dscr_explicit_test.c index aefcd8d8759b..32fcf2b324b1 100644 --- a/tools/testing/selftests/powerpc/dscr/dscr_explicit_test.c +++ b/tools/testing/selftests/powerpc/dscr/dscr_explicit_test.c @@ -21,6 +21,8 @@ int dscr_explicit(void) { unsigned long i, dscr = 0; + SKIP_IF(!have_hwcap2(PPC_FEATURE2_DSCR)); + srand(getpid()); set_dscr(dscr); diff --git a/tools/testing/selftests/powerpc/dscr/dscr_inherit_exec_test.c b/tools/testing/selftests/powerpc/dscr/dscr_inherit_exec_test.c index 7c1cb46397c6..c6a81b2d6b91 100644 --- a/tools/testing/selftests/powerpc/dscr/dscr_inherit_exec_test.c +++ b/tools/testing/selftests/powerpc/dscr/dscr_inherit_exec_test.c @@ -44,6 +44,8 @@ int dscr_inherit_exec(void) unsigned long i, dscr = 0; pid_t pid; + SKIP_IF(!have_hwcap2(PPC_FEATURE2_DSCR)); + for (i = 0; i < COUNT; i++) { dscr++; if (dscr > DSCR_MAX) diff --git a/tools/testing/selftests/powerpc/dscr/dscr_inherit_test.c b/tools/testing/selftests/powerpc/dscr/dscr_inherit_test.c index 04297a69ab59..f9dfd3d3c2d5 100644 --- a/tools/testing/selftests/powerpc/dscr/dscr_inherit_test.c +++ b/tools/testing/selftests/powerpc/dscr/dscr_inherit_test.c @@ -22,6 +22,8 @@ int dscr_inherit(void) unsigned long i, dscr = 0; pid_t pid; + SKIP_IF(!have_hwcap2(PPC_FEATURE2_DSCR)); + srand(getpid()); set_dscr(dscr); diff --git a/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c b/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c index 02f6b4efde14..fbbdffdb2e5d 100644 --- a/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c +++ b/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c @@ -77,6 +77,8 @@ int dscr_sysfs(void) unsigned long orig_dscr_default; int i, j; + SKIP_IF(!have_hwcap2(PPC_FEATURE2_DSCR)); + orig_dscr_default = get_default_dscr(); for (i = 0; i < COUNT; i++) { for (j = 0; j < DSCR_MAX; j++) { diff --git a/tools/testing/selftests/powerpc/dscr/dscr_sysfs_thread_test.c b/tools/testing/selftests/powerpc/dscr/dscr_sysfs_thread_test.c index 37be2c25f277..191ed126f118 100644 --- a/tools/testing/selftests/powerpc/dscr/dscr_sysfs_thread_test.c +++ b/tools/testing/selftests/powerpc/dscr/dscr_sysfs_thread_test.c @@ -56,6 +56,8 @@ int dscr_sysfs_thread(void) unsigned long orig_dscr_default; int i, j; + SKIP_IF(!have_hwcap2(PPC_FEATURE2_DSCR)); + orig_dscr_default = get_default_dscr(); for (i = 0; i < COUNT; i++) { for (j = 0; j < DSCR_MAX; j++) { diff --git a/tools/testing/selftests/powerpc/dscr/dscr_user_test.c b/tools/testing/selftests/powerpc/dscr/dscr_user_test.c index eaf785d11eed..e09072446dd3 100644 --- a/tools/testing/selftests/powerpc/dscr/dscr_user_test.c +++ b/tools/testing/selftests/powerpc/dscr/dscr_user_test.c @@ -36,6 +36,8 @@ int dscr_user(void) { int i; + SKIP_IF(!have_hwcap2(PPC_FEATURE2_DSCR)); + check_dscr(""); for (i = 0; i < COUNT; i++) { From 3a31518a242dcb262b008d3bb5d4b1cf50cf4026 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 19 Aug 2020 11:57:24 +1000 Subject: [PATCH 099/645] selftests/powerpc: Skip security tests on older CPUs Both these tests use PMU events that only work on newer CPUs, so skip them on older CPUs. Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200819015727.1977134-6-mpe@ellerman.id.au --- tools/testing/selftests/powerpc/security/rfi_flush.c | 3 +++ tools/testing/selftests/powerpc/security/spectre_v2.c | 3 +++ 2 files changed, 6 insertions(+) diff --git a/tools/testing/selftests/powerpc/security/rfi_flush.c b/tools/testing/selftests/powerpc/security/rfi_flush.c index fd37ff9b1c45..93a65bd1f231 100644 --- a/tools/testing/selftests/powerpc/security/rfi_flush.c +++ b/tools/testing/selftests/powerpc/security/rfi_flush.c @@ -89,6 +89,9 @@ int rfi_flush_test(void) SKIP_IF(geteuid() != 0); + // The PMU event we use only works on Power7 or later + SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06)); + if (read_debugfs_file("powerpc/rfi_flush", &rfi_flush_org)) { perror("Unable to read powerpc/rfi_flush debugfs file"); SKIP_IF(1); diff --git a/tools/testing/selftests/powerpc/security/spectre_v2.c b/tools/testing/selftests/powerpc/security/spectre_v2.c index c8d82b784102..adc2b7294e5f 100644 --- a/tools/testing/selftests/powerpc/security/spectre_v2.c +++ b/tools/testing/selftests/powerpc/security/spectre_v2.c @@ -134,6 +134,9 @@ int spectre_v2_test(void) s64 miss_percent; bool is_p9; + // The PMU events we use only work on Power8 or later + SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_2_07)); + state = get_sysfs_state(); if (state == UNKNOWN) { printf("Error: couldn't determine spectre_v2 mitigation state?\n"); From 4871a10b7b5f6b0632bff229884dad1cb1e8dc37 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 19 Aug 2020 11:57:25 +1000 Subject: [PATCH 100/645] selftests/powerpc: Skip L3 bank test on older CPUs This is a test of specific piece of logic in isa207-common.c, which is only used on Power8 or later. So skip it on older CPUs. Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200819015727.1977134-7-mpe@ellerman.id.au --- tools/testing/selftests/powerpc/pmu/l3_bank_test.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/testing/selftests/powerpc/pmu/l3_bank_test.c b/tools/testing/selftests/powerpc/pmu/l3_bank_test.c index a96d512a18c4..a5dfa9bf3b9f 100644 --- a/tools/testing/selftests/powerpc/pmu/l3_bank_test.c +++ b/tools/testing/selftests/powerpc/pmu/l3_bank_test.c @@ -20,6 +20,9 @@ static int l3_bank_test(void) char *p; int i; + // The L3 bank logic is only used on Power8 or later + SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_2_07)); + p = malloc(MALLOC_SIZE); FAIL_IF(!p); From 09275d717d1b2d7d5ed91f2140bb34246514a1b4 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 19 Aug 2020 11:57:26 +1000 Subject: [PATCH 101/645] selftests/powerpc: Don't touch VMX/VSX on older CPUs If we're running on a CPU without VMX/VSX then don't touch them. This is fragile, the compiler could spill a VMX/VSX register and break the test anyway. But in practice it seems to work, ie. the test runs to completion on a system without VSX with this change. Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200819015727.1977134-8-mpe@ellerman.id.au --- tools/testing/selftests/powerpc/benchmarks/context_switch.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/tools/testing/selftests/powerpc/benchmarks/context_switch.c b/tools/testing/selftests/powerpc/benchmarks/context_switch.c index d50cc05df495..96554e2794d1 100644 --- a/tools/testing/selftests/powerpc/benchmarks/context_switch.c +++ b/tools/testing/selftests/powerpc/benchmarks/context_switch.c @@ -481,6 +481,12 @@ int main(int argc, char *argv[]) else printf("futex"); + if (!have_hwcap(PPC_FEATURE_HAS_ALTIVEC)) + touch_altivec = 0; + + if (!have_hwcap(PPC_FEATURE_HAS_VSX)) + touch_vector = 0; + printf(" on cpus %d/%d touching FP:%s altivec:%s vector:%s vdso:%s\n", cpu1, cpu2, touch_fp ? "yes" : "no", touch_altivec ? "yes" : "no", touch_vector ? "yes" : "no", touch_vdso ? "yes" : "no"); From 003d6f5fd2cc3b529f3e6c529bc4bb0792930212 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 19 Aug 2020 11:57:27 +1000 Subject: [PATCH 102/645] selftests/powerpc: Properly handle failure in switch_endian_test On older CPUs the switch_endian() syscall doesn't work. Currently that causes the switch_endian_test to just crash. Instead detect the failure and properly exit with a failure message. Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200819015727.1977134-9-mpe@ellerman.id.au --- .../switch_endian/switch_endian_test.S | 23 +++++++++++++++---- 1 file changed, 19 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/powerpc/switch_endian/switch_endian_test.S b/tools/testing/selftests/powerpc/switch_endian/switch_endian_test.S index cc4930467235..7887f78cf072 100644 --- a/tools/testing/selftests/powerpc/switch_endian/switch_endian_test.S +++ b/tools/testing/selftests/powerpc/switch_endian/switch_endian_test.S @@ -3,9 +3,13 @@ .data .balign 8 -message: +success_message: .ascii "success: switch_endian_test\n\0" + .balign 8 +failure_message: + .ascii "failure: switch_endian_test\n\0" + .section ".toc" .balign 8 pattern: @@ -64,6 +68,9 @@ FUNC_START(_start) li r0, __NR_switch_endian sc + tdi 0, 0, 0x48 // b +8 if the endian was switched + b .Lfail // exit if endian didn't switch + #include "check-reversed.S" /* Flip back, r0 already has the switch syscall number */ @@ -71,12 +78,20 @@ FUNC_START(_start) #include "check.S" + ld r4, success_message@got(%r2) + li r5, 28 // strlen(success_message) + li r14, 0 // exit status +.Lout: li r0, __NR_write li r3, 1 /* stdout */ - ld r4, message@got(%r2) - li r5, 28 /* strlen(message3) */ sc li r0, __NR_exit - li r3, 0 + mr r3, r14 sc b . + +.Lfail: + ld r4, failure_message@got(%r2) + li r5, 28 // strlen(failure_message) + li r14, 1 + b .Lout From 529d2bd56ada4b8a4904909042792879868208cd Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 19 Aug 2020 11:57:04 +1000 Subject: [PATCH 103/645] powerpc/64: Remove unused generic_secondary_thread_init() The last caller was removed in 2014 in commit fb5a515704d7 ("powerpc: Remove platforms/wsp and associated pieces"). As Jordan noticed even though there are no callers, the code above in fsl_secondary_thread_init() falls through into generic_secondary_thread_init(). So we can remove the _GLOBAL but not the body of the function. However because fsl_secondary_thread_init() is inside #ifdef CONFIG_PPC_BOOK3E, we can never reach the body of generic_secondary_thread_init() unless CONFIG_PPC_BOOK3E is enabled, so we can wrap the whole thing in a single #ifdef. Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200819015704.1976364-1-mpe@ellerman.id.au --- arch/powerpc/include/asm/smp.h | 1 - arch/powerpc/kernel/head_64.S | 7 ++----- 2 files changed, 2 insertions(+), 6 deletions(-) diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index 49a25e2400f2..81a49566ccd8 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -243,7 +243,6 @@ extern void arch_send_call_function_ipi_mask(const struct cpumask *mask); * 64-bit but defining them all here doesn't harm */ extern void generic_secondary_smp_init(void); -extern void generic_secondary_thread_init(void); extern unsigned long __secondary_hold_spinloop; extern unsigned long __secondary_hold_acknowledge; extern char __secondary_hold; diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 0e05a9a47a4b..1510b2a56669 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -300,9 +300,6 @@ _GLOBAL(fsl_secondary_thread_init) rlwimi r3, r3, 30, 2, 30 mtspr SPRN_PIR, r3 1: -#endif - -_GLOBAL(generic_secondary_thread_init) mr r24,r3 /* turn on 64-bit mode */ @@ -312,13 +309,13 @@ _GLOBAL(generic_secondary_thread_init) bl relative_toc tovirt(r2,r2) -#ifdef CONFIG_PPC_BOOK3E /* Book3E initialization */ mr r3,r24 bl book3e_secondary_thread_init -#endif b generic_secondary_common_init +#endif /* CONFIG_PPC_BOOK3E */ + /* * On pSeries and most other platforms, secondary processors spin * in the following code. From 364b236a0b6e86439b9025d961da8602db23d5bf Mon Sep 17 00:00:00 2001 From: Jordan Niethe Date: Tue, 25 Aug 2020 13:51:47 +1000 Subject: [PATCH 104/645] powerpc/boot: Update Makefile comment for 64bit wrapper As of commit 147c05168fc8 ("powerpc/boot: Add support for 64bit little endian wrapper") the comment in the Makefile is misleading. The wrapper packaging 64bit kernel may built as a 32 or 64 bit elf. Update the comment to reflect this. Signed-off-by: Jordan Niethe Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200825035147.3239-1-jniethe5@gmail.com --- arch/powerpc/boot/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index b88fd27a45f0..f8ce6d2dde7b 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -7,7 +7,7 @@ # Based on coffboot by Paul Mackerras # Simplified for ppc64 by Todd Inglett # -# NOTE: this code is built for 32 bit in ELF32 format even though +# NOTE: this code may be built for 32 bit in ELF32 format even though # it packages a 64 bit kernel. We do this to simplify the # bootloader and increase compatibility with OpenFirmware. # From db96221a683342fd4775fd820a4d5376cd2f2ed0 Mon Sep 17 00:00:00 2001 From: Jordan Niethe Date: Mon, 24 Aug 2020 23:12:31 +1000 Subject: [PATCH 105/645] selftests/powerpc: Fix prefixes in alignment_handler signal handler The signal handler in the alignment handler self test has the ability to jump over the instruction that triggered the signal. It does this by incrementing the PT_NIP in the user context by 4. If it were a prefixed instruction this will mean that the suffix is then executed which is incorrect. Instead check if the major opcode indicates a prefixed instruction (e.g. it is 1) and if so increment PT_NIP by 8. If ISA v3.1 is not available treat it as a word instruction even if the major opcode is 1. Fixes: 620a6473df36 ("selftests/powerpc: Add prefixed loads/stores to alignment_handler test") Signed-off-by: Jordan Niethe [mpe: Fix 32-bit build, rename haveprefixes to prefixes_enabled] Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200824131231.14008-1-jniethe5@gmail.com --- .../selftests/powerpc/alignment/alignment_handler.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/powerpc/alignment/alignment_handler.c b/tools/testing/selftests/powerpc/alignment/alignment_handler.c index e4063eba4a5b..2a0503bc7e49 100644 --- a/tools/testing/selftests/powerpc/alignment/alignment_handler.c +++ b/tools/testing/selftests/powerpc/alignment/alignment_handler.c @@ -62,6 +62,7 @@ int bufsize; int debug; int testing; volatile int gotsig; +bool prefixes_enabled; char *cipath = "/dev/fb0"; long cioffset; @@ -75,7 +76,12 @@ void sighandler(int sig, siginfo_t *info, void *ctx) } gotsig = sig; #ifdef __powerpc64__ - ucp->uc_mcontext.gp_regs[PT_NIP] += 4; + if (prefixes_enabled) { + u32 inst = *(u32 *)ucp->uc_mcontext.gp_regs[PT_NIP]; + ucp->uc_mcontext.gp_regs[PT_NIP] += ((inst >> 26 == 1) ? 8 : 4); + } else { + ucp->uc_mcontext.gp_regs[PT_NIP] += 4; + } #else ucp->uc_mcontext.uc_regs->gregs[PT_NIP] += 4; #endif @@ -646,6 +652,8 @@ int main(int argc, char *argv[]) exit(1); } + prefixes_enabled = have_hwcap2(PPC_FEATURE2_ARCH_3_1); + rc |= test_harness(test_alignment_handler_vsx_206, "test_alignment_handler_vsx_206"); rc |= test_harness(test_alignment_handler_vsx_207, From 0fb4871bcc8997acbb8edf14b301fc150101d6c0 Mon Sep 17 00:00:00 2001 From: Russell Currey Date: Fri, 28 Aug 2020 12:05:42 +1000 Subject: [PATCH 106/645] powerpc/tools: Remove 90 line limit in checkpatch script As of commit bdc48fa11e46, scripts/checkpatch.pl now has a default line length warning of 100 characters. The powerpc wrapper script was using a length of 90 instead of 80 in order to make checkpatch less restrictive, but now it's making it more restrictive instead. I think it makes sense to just use the default value now. Signed-off-by: Russell Currey Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200828020542.393022-1-ruscur@russell.cc --- arch/powerpc/tools/checkpatch.sh | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/powerpc/tools/checkpatch.sh b/arch/powerpc/tools/checkpatch.sh index 3ce5c093b19d..91c04802ec31 100755 --- a/arch/powerpc/tools/checkpatch.sh +++ b/arch/powerpc/tools/checkpatch.sh @@ -9,7 +9,6 @@ script_base=$(realpath $(dirname $0)) exec $script_base/../../../scripts/checkpatch.pl \ --subjective \ --no-summary \ - --max-line-length=90 \ --show-types \ --ignore ARCH_INCLUDE_LINUX \ --ignore BIT_MACRO \ From 51a1588154cb1ddc4fe8fa786324dca398f1a458 Mon Sep 17 00:00:00 2001 From: Jordan Niethe Date: Thu, 27 Aug 2020 14:05:56 +1000 Subject: [PATCH 107/645] powerpc: Update documentation of ISA versions for Power10 Update the CPU to ISA Version Mapping document to include Power10 and ISA v3.1. Signed-off-by: Jordan Niethe [mpe: Make sure ISA reference is unique] Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200827040556.1783-1-jniethe5@gmail.com --- Documentation/powerpc/isa-versions.rst | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/Documentation/powerpc/isa-versions.rst b/Documentation/powerpc/isa-versions.rst index a363d8c1603c..dfcb1097dce4 100644 --- a/Documentation/powerpc/isa-versions.rst +++ b/Documentation/powerpc/isa-versions.rst @@ -7,6 +7,7 @@ Mapping of some CPU versions to relevant ISA versions. ========= ==================================================================== CPU Architecture version ========= ==================================================================== +Power10 Power ISA v3.1 Power9 Power ISA v3.0B Power8 Power ISA v2.07 Power7 Power ISA v2.06 @@ -32,6 +33,7 @@ Key Features ========== ================== CPU VMX (aka. Altivec) ========== ================== +Power10 Yes Power9 Yes Power8 Yes Power7 Yes @@ -47,6 +49,7 @@ PPC970 Yes ========== ==== CPU VSX ========== ==== +Power10 Yes Power9 Yes Power8 Yes Power7 Yes @@ -62,6 +65,7 @@ PPC970 No ========== ==================================== CPU Transactional Memory ========== ==================================== +Power10 No (* see Power ISA v3.1, "Appendix A. Notes on the Removal of Transactional Memory from the Architecture") Power9 Yes (* see transactional_memory.txt) Power8 Yes Power7 No From cac3e629086f1b2e31c87a6c9b0130d29843ae86 Mon Sep 17 00:00:00 2001 From: Leonardo Bras Date: Wed, 5 Aug 2020 00:04:52 -0300 Subject: [PATCH 108/645] powerpc/pseries/iommu: Create defines for operations in ibm, ddw-applicable Create defines to help handling ibm,ddw-applicable values, avoiding confusion about the index of given operations. Signed-off-by: Leonardo Bras Tested-by: David Dai Reviewed-by: Alexey Kardashevskiy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200805030455.123024-2-leobras.c@gmail.com --- arch/powerpc/platforms/pseries/iommu.c | 43 ++++++++++++++++---------- 1 file changed, 26 insertions(+), 17 deletions(-) diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 6d47b4a3ce39..ac0d6376bdad 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -39,6 +39,14 @@ #include "pseries.h" +enum { + DDW_QUERY_PE_DMA_WIN = 0, + DDW_CREATE_PE_DMA_WIN = 1, + DDW_REMOVE_PE_DMA_WIN = 2, + + DDW_APPLICABLE_SIZE +}; + static struct iommu_table_group *iommu_pseries_alloc_group(int node) { struct iommu_table_group *table_group; @@ -771,12 +779,12 @@ static void remove_ddw(struct device_node *np, bool remove_prop) { struct dynamic_dma_window_prop *dwp; struct property *win64; - u32 ddw_avail[3]; + u32 ddw_avail[DDW_APPLICABLE_SIZE]; u64 liobn; int ret = 0; ret = of_property_read_u32_array(np, "ibm,ddw-applicable", - &ddw_avail[0], 3); + &ddw_avail[0], DDW_APPLICABLE_SIZE); win64 = of_find_property(np, DIRECT64_PROPNAME, NULL); if (!win64) @@ -798,15 +806,15 @@ static void remove_ddw(struct device_node *np, bool remove_prop) pr_debug("%pOF successfully cleared tces in window.\n", np); - ret = rtas_call(ddw_avail[2], 1, 1, NULL, liobn); + ret = rtas_call(ddw_avail[DDW_REMOVE_PE_DMA_WIN], 1, 1, NULL, liobn); if (ret) pr_warn("%pOF: failed to remove direct window: rtas returned " "%d to ibm,remove-pe-dma-window(%x) %llx\n", - np, ret, ddw_avail[2], liobn); + np, ret, ddw_avail[DDW_REMOVE_PE_DMA_WIN], liobn); else pr_debug("%pOF: successfully removed direct window: rtas returned " "%d to ibm,remove-pe-dma-window(%x) %llx\n", - np, ret, ddw_avail[2], liobn); + np, ret, ddw_avail[DDW_REMOVE_PE_DMA_WIN], liobn); delprop: if (remove_prop) @@ -889,11 +897,11 @@ static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail, buid = pdn->phb->buid; cfg_addr = ((pdn->busno << 16) | (pdn->devfn << 8)); - ret = rtas_call(ddw_avail[0], 3, 5, (u32 *)query, - cfg_addr, BUID_HI(buid), BUID_LO(buid)); + ret = rtas_call(ddw_avail[DDW_QUERY_PE_DMA_WIN], 3, 5, (u32 *)query, + cfg_addr, BUID_HI(buid), BUID_LO(buid)); dev_info(&dev->dev, "ibm,query-pe-dma-windows(%x) %x %x %x" - " returned %d\n", ddw_avail[0], cfg_addr, BUID_HI(buid), - BUID_LO(buid), ret); + " returned %d\n", ddw_avail[DDW_QUERY_PE_DMA_WIN], cfg_addr, + BUID_HI(buid), BUID_LO(buid), ret); return ret; } @@ -920,15 +928,16 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail, do { /* extra outputs are LIOBN and dma-addr (hi, lo) */ - ret = rtas_call(ddw_avail[1], 5, 4, (u32 *)create, - cfg_addr, BUID_HI(buid), BUID_LO(buid), - page_shift, window_shift); + ret = rtas_call(ddw_avail[DDW_CREATE_PE_DMA_WIN], 5, 4, + (u32 *)create, cfg_addr, BUID_HI(buid), + BUID_LO(buid), page_shift, window_shift); } while (rtas_busy_delay(ret)); dev_info(&dev->dev, "ibm,create-pe-dma-window(%x) %x %x %x %x %x returned %d " - "(liobn = 0x%x starting addr = %x %x)\n", ddw_avail[1], - cfg_addr, BUID_HI(buid), BUID_LO(buid), page_shift, - window_shift, ret, create->liobn, create->addr_hi, create->addr_lo); + "(liobn = 0x%x starting addr = %x %x)\n", + ddw_avail[DDW_CREATE_PE_DMA_WIN], cfg_addr, BUID_HI(buid), + BUID_LO(buid), page_shift, window_shift, ret, create->liobn, + create->addr_hi, create->addr_lo); return ret; } @@ -996,7 +1005,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) int page_shift; u64 dma_addr, max_addr; struct device_node *dn; - u32 ddw_avail[3]; + u32 ddw_avail[DDW_APPLICABLE_SIZE]; struct direct_window *window; struct property *win64; struct dynamic_dma_window_prop *ddwprop; @@ -1029,7 +1038,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) * the property is actually in the parent, not the PE */ ret = of_property_read_u32_array(pdn, "ibm,ddw-applicable", - &ddw_avail[0], 3); + &ddw_avail[0], DDW_APPLICABLE_SIZE); if (ret) goto out_failed; From 80f0251231131d164eddab78d2b6c1b8e37d0093 Mon Sep 17 00:00:00 2001 From: Leonardo Bras Date: Wed, 5 Aug 2020 00:04:53 -0300 Subject: [PATCH 109/645] powerpc/pseries/iommu: Update call to ibm, query-pe-dma-windows >From LoPAR level 2.8, "ibm,ddw-extensions" index 3 can make the number of outputs from "ibm,query-pe-dma-windows" go from 5 to 6. This change of output size is meant to expand the address size of largest_available_block PE TCE from 32-bit to 64-bit, which ends up shifting page_size and migration_capable. This ends up requiring the update of ddw_query_response->largest_available_block from u32 to u64, and manually assigning the values from the buffer into this struct, according to output size. Also, a routine was created for helping reading the ddw extensions as suggested by LoPAR: First reading the size of the extension array from index 0, checking if the property exists, and then returning it's value. Signed-off-by: Leonardo Bras Tested-by: David Dai Reviewed-by: Alexey Kardashevskiy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200805030455.123024-3-leobras.c@gmail.com --- arch/powerpc/platforms/pseries/iommu.c | 91 +++++++++++++++++++++++--- 1 file changed, 81 insertions(+), 10 deletions(-) diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index ac0d6376bdad..1a933c4e8bba 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -47,6 +47,12 @@ enum { DDW_APPLICABLE_SIZE }; +enum { + DDW_EXT_SIZE = 0, + DDW_EXT_RESET_DMA_WIN = 1, + DDW_EXT_QUERY_OUT_SIZE = 2 +}; + static struct iommu_table_group *iommu_pseries_alloc_group(int node) { struct iommu_table_group *table_group; @@ -342,7 +348,7 @@ struct direct_window { /* Dynamic DMA Window support */ struct ddw_query_response { u32 windows_available; - u32 largest_available_block; + u64 largest_available_block; u32 page_size; u32 migration_capable; }; @@ -877,14 +883,62 @@ static int find_existing_ddw_windows(void) } machine_arch_initcall(pseries, find_existing_ddw_windows); +/** + * ddw_read_ext - Get the value of an DDW extension + * @np: device node from which the extension value is to be read. + * @extnum: index number of the extension. + * @value: pointer to return value, modified when extension is available. + * + * Checks if "ibm,ddw-extensions" exists for this node, and get the value + * on index 'extnum'. + * It can be used only to check if a property exists, passing value == NULL. + * + * Returns: + * 0 if extension successfully read + * -EINVAL if the "ibm,ddw-extensions" does not exist, + * -ENODATA if "ibm,ddw-extensions" does not have a value, and + * -EOVERFLOW if "ibm,ddw-extensions" does not contain this extension. + */ +static inline int ddw_read_ext(const struct device_node *np, int extnum, + u32 *value) +{ + static const char propname[] = "ibm,ddw-extensions"; + u32 count; + int ret; + + ret = of_property_read_u32_index(np, propname, DDW_EXT_SIZE, &count); + if (ret) + return ret; + + if (count < extnum) + return -EOVERFLOW; + + if (!value) + value = &count; + + return of_property_read_u32_index(np, propname, extnum, value); +} + static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail, - struct ddw_query_response *query) + struct ddw_query_response *query, + struct device_node *parent) { struct device_node *dn; struct pci_dn *pdn; - u32 cfg_addr; + u32 cfg_addr, ext_query, query_out[5]; u64 buid; - int ret; + int ret, out_sz; + + /* + * From LoPAR level 2.8, "ibm,ddw-extensions" index 3 can rule how many + * output parameters ibm,query-pe-dma-windows will have, ranging from + * 5 to 6. + */ + ret = ddw_read_ext(parent, DDW_EXT_QUERY_OUT_SIZE, &ext_query); + if (!ret && ext_query == 1) + out_sz = 6; + else + out_sz = 5; /* * Get the config address and phb buid of the PE window. @@ -897,11 +951,28 @@ static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail, buid = pdn->phb->buid; cfg_addr = ((pdn->busno << 16) | (pdn->devfn << 8)); - ret = rtas_call(ddw_avail[DDW_QUERY_PE_DMA_WIN], 3, 5, (u32 *)query, + ret = rtas_call(ddw_avail[DDW_QUERY_PE_DMA_WIN], 3, out_sz, query_out, cfg_addr, BUID_HI(buid), BUID_LO(buid)); - dev_info(&dev->dev, "ibm,query-pe-dma-windows(%x) %x %x %x" - " returned %d\n", ddw_avail[DDW_QUERY_PE_DMA_WIN], cfg_addr, - BUID_HI(buid), BUID_LO(buid), ret); + dev_info(&dev->dev, "ibm,query-pe-dma-windows(%x) %x %x %x returned %d\n", + ddw_avail[DDW_QUERY_PE_DMA_WIN], cfg_addr, BUID_HI(buid), + BUID_LO(buid), ret); + + switch (out_sz) { + case 5: + query->windows_available = query_out[0]; + query->largest_available_block = query_out[1]; + query->page_size = query_out[2]; + query->migration_capable = query_out[3]; + break; + case 6: + query->windows_available = query_out[0]; + query->largest_available_block = ((u64)query_out[1] << 32) | + query_out[2]; + query->page_size = query_out[3]; + query->migration_capable = query_out[4]; + break; + } + return ret; } @@ -1049,7 +1120,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) * of page sizes: supported and supported for migrate-dma. */ dn = pci_device_to_OF_node(dev); - ret = query_ddw(dev, ddw_avail, &query); + ret = query_ddw(dev, ddw_avail, &query, pdn); if (ret != 0) goto out_failed; @@ -1077,7 +1148,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) /* check largest block * page size > max memory hotplug addr */ max_addr = ddw_memory_hotplug_max(); if (query.largest_available_block < (max_addr >> page_shift)) { - dev_dbg(&dev->dev, "can't map partition max 0x%llx with %u " + dev_dbg(&dev->dev, "can't map partition max 0x%llx with %llu " "%llu-sized pages\n", max_addr, query.largest_available_block, 1ULL << page_shift); goto out_failed; From 74d0b3994e147a2b503170b5e02f1d07dc086586 Mon Sep 17 00:00:00 2001 From: Leonardo Bras Date: Wed, 5 Aug 2020 00:04:54 -0300 Subject: [PATCH 110/645] powerpc/pseries/iommu: Move window-removing part of remove_ddw into remove_dma_window Move the window-removing part of remove_ddw into a new function (remove_dma_window), so it can be used to remove other DMA windows. It's useful for removing DMA windows that don't create DIRECT64_PROPNAME property, like the default DMA window from the device, which uses "ibm,dma-window". Signed-off-by: Leonardo Bras Tested-by: David Dai Reviewed-by: Alexey Kardashevskiy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200805030455.123024-4-leobras.c@gmail.com --- arch/powerpc/platforms/pseries/iommu.c | 45 +++++++++++++++----------- 1 file changed, 27 insertions(+), 18 deletions(-) diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 1a933c4e8bba..4e33147825cc 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -781,25 +781,14 @@ static int __init disable_ddw_setup(char *str) early_param("disable_ddw", disable_ddw_setup); -static void remove_ddw(struct device_node *np, bool remove_prop) +static void remove_dma_window(struct device_node *np, u32 *ddw_avail, + struct property *win) { struct dynamic_dma_window_prop *dwp; - struct property *win64; - u32 ddw_avail[DDW_APPLICABLE_SIZE]; u64 liobn; - int ret = 0; + int ret; - ret = of_property_read_u32_array(np, "ibm,ddw-applicable", - &ddw_avail[0], DDW_APPLICABLE_SIZE); - - win64 = of_find_property(np, DIRECT64_PROPNAME, NULL); - if (!win64) - return; - - if (ret || win64->length < sizeof(*dwp)) - goto delprop; - - dwp = win64->value; + dwp = win->value; liobn = (u64)be32_to_cpu(dwp->liobn); /* clear the whole window, note the arg is in kernel pages */ @@ -821,10 +810,30 @@ static void remove_ddw(struct device_node *np, bool remove_prop) pr_debug("%pOF: successfully removed direct window: rtas returned " "%d to ibm,remove-pe-dma-window(%x) %llx\n", np, ret, ddw_avail[DDW_REMOVE_PE_DMA_WIN], liobn); +} -delprop: - if (remove_prop) - ret = of_remove_property(np, win64); +static void remove_ddw(struct device_node *np, bool remove_prop) +{ + struct property *win; + u32 ddw_avail[DDW_APPLICABLE_SIZE]; + int ret = 0; + + ret = of_property_read_u32_array(np, "ibm,ddw-applicable", + &ddw_avail[0], DDW_APPLICABLE_SIZE); + if (ret) + return; + + win = of_find_property(np, DIRECT64_PROPNAME, NULL); + if (!win) + return; + + if (win->length >= sizeof(struct dynamic_dma_window_prop)) + remove_dma_window(np, ddw_avail, win); + + if (!remove_prop) + return; + + ret = of_remove_property(np, win); if (ret) pr_warn("%pOF: failed to remove direct window property: %d\n", np, ret); From 8c0d51592f6f0123953633d1ecf21e843fce0bfd Mon Sep 17 00:00:00 2001 From: Leonardo Bras Date: Wed, 5 Aug 2020 00:04:55 -0300 Subject: [PATCH 111/645] powerpc/pseries/iommu: Allow bigger 64bit window by removing default DMA window On LoPAR "DMA Window Manipulation Calls", it's recommended to remove the default DMA window for the device, before attempting to configure a DDW, in order to make the maximum resources available for the next DDW to be created. This is a requirement for using DDW on devices in which hypervisor allows only one DMA window. If setting up a new DDW fails anywhere after the removal of this default DMA window, it's needed to restore the default DMA window. For this, an implementation of ibm,reset-pe-dma-windows rtas call is needed: Platforms supporting the DDW option starting with LoPAR level 2.7 implement ibm,ddw-extensions. The first extension available (index 2) carries the token for ibm,reset-pe-dma-windows rtas call, which is used to restore the default DMA window for a device, if it has been deleted. It does so by resetting the TCE table allocation for the PE to it's boot time value, available in "ibm,dma-window" device tree node. Signed-off-by: Leonardo Bras Tested-by: David Dai Reviewed-by: Alexey Kardashevskiy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200805030455.123024-5-leobras.c@gmail.com --- arch/powerpc/platforms/pseries/iommu.c | 73 +++++++++++++++++++++++--- 1 file changed, 66 insertions(+), 7 deletions(-) diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 4e33147825cc..e4198700ed1a 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -1066,6 +1066,38 @@ static phys_addr_t ddw_memory_hotplug_max(void) return max_addr; } +/* + * Platforms supporting the DDW option starting with LoPAR level 2.7 implement + * ibm,ddw-extensions, which carries the rtas token for + * ibm,reset-pe-dma-windows. + * That rtas-call can be used to restore the default DMA window for the device. + */ +static void reset_dma_window(struct pci_dev *dev, struct device_node *par_dn) +{ + int ret; + u32 cfg_addr, reset_dma_win; + u64 buid; + struct device_node *dn; + struct pci_dn *pdn; + + ret = ddw_read_ext(par_dn, DDW_EXT_RESET_DMA_WIN, &reset_dma_win); + if (ret) + return; + + dn = pci_device_to_OF_node(dev); + pdn = PCI_DN(dn); + buid = pdn->phb->buid; + cfg_addr = (pdn->busno << 16) | (pdn->devfn << 8); + + ret = rtas_call(reset_dma_win, 3, 1, NULL, cfg_addr, BUID_HI(buid), + BUID_LO(buid)); + if (ret) + dev_info(&dev->dev, + "ibm,reset-pe-dma-windows(%x) %x %x %x returned %d ", + reset_dma_win, cfg_addr, BUID_HI(buid), BUID_LO(buid), + ret); +} + /* * If the PE supports dynamic dma windows, and there is space for a table * that can map all pages in a linear offset, then setup such a table, @@ -1090,6 +1122,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) struct property *win64; struct dynamic_dma_window_prop *ddwprop; struct failed_ddw_pdn *fpdn; + bool default_win_removed = false; mutex_lock(&direct_window_init_mutex); @@ -1133,14 +1166,38 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) if (ret != 0) goto out_failed; + /* + * If there is no window available, remove the default DMA window, + * if it's present. This will make all the resources available to the + * new DDW window. + * If anything fails after this, we need to restore it, so also check + * for extensions presence. + */ if (query.windows_available == 0) { - /* - * no additional windows are available for this device. - * We might be able to reallocate the existing window, - * trading in for a larger page size. - */ - dev_dbg(&dev->dev, "no free dynamic windows"); - goto out_failed; + struct property *default_win; + int reset_win_ext; + + default_win = of_find_property(pdn, "ibm,dma-window", NULL); + if (!default_win) + goto out_failed; + + reset_win_ext = ddw_read_ext(pdn, DDW_EXT_RESET_DMA_WIN, NULL); + if (reset_win_ext) + goto out_failed; + + remove_dma_window(pdn, ddw_avail, default_win); + default_win_removed = true; + + /* Query again, to check if the window is available */ + ret = query_ddw(dev, ddw_avail, &query, pdn); + if (ret != 0) + goto out_failed; + + if (query.windows_available == 0) { + /* no windows are available for this device. */ + dev_dbg(&dev->dev, "no free dynamic windows"); + goto out_failed; + } } if (query.page_size & 4) { page_shift = 24; /* 16MB */ @@ -1231,6 +1288,8 @@ out_free_prop: kfree(win64); out_failed: + if (default_win_removed) + reset_dma_window(dev, pdn); fpdn = kzalloc(sizeof(*fpdn), GFP_KERNEL); if (!fpdn) From 8f55984f530d7275531e17f36ea29229c2c410dd Mon Sep 17 00:00:00 2001 From: Joel Stanley Date: Thu, 1 Aug 2019 14:46:30 +0930 Subject: [PATCH 112/645] powerpc/powernv: Print helpful message when cores guarded Often the firmware will guard out cores after a crash. This often undesirable, and is not immediately noticeable. This adds an informative message when a CPU device tree nodes are marked bad in the device tree. Signed-off-by: Joel Stanley [mpe: Use an eye-catcher that's less likely to get us in trouble] Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20190801051630.5804-1-joel@jms.id.au --- arch/powerpc/platforms/powernv/setup.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index 7fcb88623081..9acaa0f131b9 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -130,6 +130,28 @@ static void pnv_setup_rfi_flush(void) setup_count_cache_flush(); } +static void __init pnv_check_guarded_cores(void) +{ + struct device_node *dn; + int bad_count = 0; + + for_each_node_by_type(dn, "cpu") { + if (of_property_match_string(dn, "status", "bad") >= 0) + bad_count++; + }; + + if (bad_count) { + printk(" _ _______________\n"); + pr_cont(" | | / \\\n"); + pr_cont(" | | | WARNING! |\n"); + pr_cont(" | | | |\n"); + pr_cont(" | | | It looks like |\n"); + pr_cont(" |_| | you have %*d |\n", 3, bad_count); + pr_cont(" _ | guarded cores |\n"); + pr_cont(" (_) \\_______________/\n"); + } +} + static void __init pnv_setup_arch(void) { set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT); @@ -150,6 +172,8 @@ static void __init pnv_setup_arch(void) /* Enable NAP mode */ powersave_nap = 1; + pnv_check_guarded_cores(); + /* XXX PMCS */ } From a02f6d42357acf6e5de6ffc728e6e77faf3ad217 Mon Sep 17 00:00:00 2001 From: Joel Stanley Date: Wed, 2 Sep 2020 09:30:11 +0930 Subject: [PATCH 113/645] powerpc: Warn about use of smt_snooze_delay It's not done anything for a long time. Save the percpu variable, and emit a warning to remind users to not expect it to do anything. This uses pr_warn_once instead of pr_warn_ratelimit as testing 'ppc64_cpu --smt=off' on a 24 core / 4 SMT system showed the warning to be noisy, as the online/offline loop is slow. Fixes: 3fa8cad82b94 ("powerpc/pseries/cpuidle: smt-snooze-delay cleanup.") Cc: stable@vger.kernel.org # v3.14 Signed-off-by: Joel Stanley Acked-by: Gautham R. Shenoy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200902000012.3440389-1-joel@jms.id.au --- arch/powerpc/kernel/sysfs.c | 42 +++++++++++++++---------------------- 1 file changed, 17 insertions(+), 25 deletions(-) diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 46b4ebc33db7..5dea98fa2f93 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -32,29 +32,27 @@ static DEFINE_PER_CPU(struct cpu, cpu_devices); -/* - * SMT snooze delay stuff, 64-bit only for now - */ - #ifdef CONFIG_PPC64 -/* Time in microseconds we delay before sleeping in the idle loop */ -static DEFINE_PER_CPU(long, smt_snooze_delay) = { 100 }; +/* + * Snooze delay has not been hooked up since 3fa8cad82b94 ("powerpc/pseries/cpuidle: + * smt-snooze-delay cleanup.") and has been broken even longer. As was foretold in + * 2014: + * + * "ppc64_util currently utilises it. Once we fix ppc64_util, propose to clean + * up the kernel code." + * + * powerpc-utils stopped using it as of 1.3.8. At some point in the future this + * code should be removed. + */ static ssize_t store_smt_snooze_delay(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct cpu *cpu = container_of(dev, struct cpu, dev); - ssize_t ret; - long snooze; - - ret = sscanf(buf, "%ld", &snooze); - if (ret != 1) - return -EINVAL; - - per_cpu(smt_snooze_delay, cpu->dev.id) = snooze; + pr_warn_once("%s (%d) stored to unsupported smt_snooze_delay, which has no effect.\n", + current->comm, current->pid); return count; } @@ -62,9 +60,9 @@ static ssize_t show_smt_snooze_delay(struct device *dev, struct device_attribute *attr, char *buf) { - struct cpu *cpu = container_of(dev, struct cpu, dev); - - return sprintf(buf, "%ld\n", per_cpu(smt_snooze_delay, cpu->dev.id)); + pr_warn_once("%s (%d) read from unsupported smt_snooze_delay\n", + current->comm, current->pid); + return sprintf(buf, "100\n"); } static DEVICE_ATTR(smt_snooze_delay, 0644, show_smt_snooze_delay, @@ -72,16 +70,10 @@ static DEVICE_ATTR(smt_snooze_delay, 0644, show_smt_snooze_delay, static int __init setup_smt_snooze_delay(char *str) { - unsigned int cpu; - long snooze; - if (!cpu_has_feature(CPU_FTR_SMT)) return 1; - snooze = simple_strtol(str, NULL, 10); - for_each_possible_cpu(cpu) - per_cpu(smt_snooze_delay, cpu) = snooze; - + pr_warn("smt-snooze-delay command line option has no effect\n"); return 1; } __setup("smt-snooze-delay=", setup_smt_snooze_delay); From dc462267d2d7aacffc3c1d99b02d7a7c59db7c66 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Tue, 25 Aug 2020 17:55:35 +1000 Subject: [PATCH 114/645] powerpc/64s: handle ISA v3.1 local copy-paste context switches The ISA v3.1 the copy-paste facility has a new memory move functionality which allows the copy buffer to be pasted to domestic memory (RAM) as opposed to foreign memory (accelerator). This means the POWER9 trick of avoiding the cp_abort on context switch if the process had not mapped foreign memory does not work on POWER10. Do the cp_abort unconditionally there. KVM must also cp_abort on guest exit to prevent copy buffer state leaking between contexts. Signed-off-by: Nicholas Piggin Acked-by: Paul Mackerras Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200825075535.224536-1-npiggin@gmail.com --- arch/powerpc/kernel/process.c | 16 +++++++++------- arch/powerpc/kvm/book3s_hv.c | 7 +++++++ arch/powerpc/kvm/book3s_hv_rmhandlers.S | 8 ++++++++ 3 files changed, 24 insertions(+), 7 deletions(-) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index febe9f7cda2f..2a6fadde58b4 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1250,15 +1250,17 @@ struct task_struct *__switch_to(struct task_struct *prev, restore_math(current->thread.regs); /* - * The copy-paste buffer can only store into foreign real - * addresses, so unprivileged processes can not see the - * data or use it in any way unless they have foreign real - * mappings. If the new process has the foreign real address - * mappings, we must issue a cp_abort to clear any state and - * prevent snooping, corruption or a covert channel. + * On POWER9 the copy-paste buffer can only paste into + * foreign real addresses, so unprivileged processes can not + * see the data or use it in any way unless they have + * foreign real mappings. If the new process has the foreign + * real address mappings, we must issue a cp_abort to clear + * any state and prevent snooping, corruption or a covert + * channel. ISA v3.1 supports paste into local memory. */ if (current->mm && - atomic_read(¤t->mm->context.vas_windows)) + (cpu_has_feature(CPU_FTR_ARCH_31) || + atomic_read(¤t->mm->context.vas_windows))) asm volatile(PPC_CP_ABORT); } #endif /* CONFIG_PPC_BOOK3S_64 */ diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 4ba06a2a306c..3bd3118c7633 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -3530,6 +3530,13 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit, */ asm volatile("eieio; tlbsync; ptesync"); + /* + * cp_abort is required if the processor supports local copy-paste + * to clear the copy buffer that was under control of the guest. + */ + if (cpu_has_feature(CPU_FTR_ARCH_31)) + asm volatile(PPC_CP_ABORT); + mtspr(SPRN_LPID, vcpu->kvm->arch.host_lpid); /* restore host LPID */ isync(); diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 799d6d0f4ead..cd9995ee8441 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1830,6 +1830,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_P9_RADIX_PREFETCH_BUG) 2: #endif /* CONFIG_PPC_RADIX_MMU */ + /* + * cp_abort is required if the processor supports local copy-paste + * to clear the copy buffer that was under control of the guest. + */ +BEGIN_FTR_SECTION + PPC_CP_ABORT +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31) + /* * POWER7/POWER8 guest -> host partition switch code. * We don't have to lock against tlbies but we do From fcdb84cc5b31c2f4e333051f467264f5821bc61a Mon Sep 17 00:00:00 2001 From: Cengiz Can Date: Tue, 30 Jun 2020 11:29:23 +0300 Subject: [PATCH 115/645] kdb: remove unnecessary null check of dbg_io_ops `kdb_msg_write` operates on a global `struct kgdb_io *` called `dbg_io_ops`. It's initialized in `debug_core.c` and checked throughout the debug flow. There's a null check in `kdb_msg_write` which triggers static analyzers and gives the (almost entirely wrong) impression that it can be null. Coverity scanner caught this as CID 1465042. I have removed the unnecessary null check and eliminated false-positive forward null dereference warning. Signed-off-by: Cengiz Can Link: https://lore.kernel.org/r/20200630082922.28672-1-cengiz@kernel.wtf Reviewed-by: Sumit Garg Reviewed-by: Douglas Anderson Tested-by: Douglas Anderson Signed-off-by: Daniel Thompson --- kernel/debug/kdb/kdb_io.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c index 9d847ab851db..e7835ca88e16 100644 --- a/kernel/debug/kdb/kdb_io.c +++ b/kernel/debug/kdb/kdb_io.c @@ -545,18 +545,18 @@ static int kdb_search_string(char *searched, char *searchfor) static void kdb_msg_write(const char *msg, int msg_len) { struct console *c; + const char *cp; + int len; if (msg_len == 0) return; - if (dbg_io_ops) { - const char *cp = msg; - int len = msg_len; + cp = msg; + len = msg_len; - while (len--) { - dbg_io_ops->write_char(*cp); - cp++; - } + while (len--) { + dbg_io_ops->write_char(*cp); + cp++; } for_each_console(c) { From b18b099e04f450cdc77bec72acefcde7042bd1f3 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Tue, 30 Jun 2020 15:14:38 -0700 Subject: [PATCH 116/645] kgdb: Make "kgdbcon" work properly with "kgdb_earlycon" On my system the kernel processes the "kgdb_earlycon" parameter before the "kgdbcon" parameter. When we setup "kgdb_earlycon" we'll end up in kgdb_register_callbacks() and "kgdb_use_con" won't have been set yet so we'll never get around to starting "kgdbcon". Let's remedy this by detecting that the IO module was already registered when setting "kgdb_use_con" and registering the console then. As part of this, to avoid pre-declaring things, move the handling of the "kgdbcon" further down in the file. Signed-off-by: Douglas Anderson Link: https://lore.kernel.org/r/20200630151422.1.I4aa062751ff5e281f5116655c976dff545c09a46@changeid Signed-off-by: Daniel Thompson --- kernel/debug/debug_core.c | 22 ++++++++++++++-------- 1 file changed, 14 insertions(+), 8 deletions(-) diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index b16dbc1bf056..404d6d47a11d 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -94,14 +94,6 @@ int dbg_switch_cpu; /* Use kdb or gdbserver mode */ int dbg_kdb_mode = 1; -static int __init opt_kgdb_con(char *str) -{ - kgdb_use_con = 1; - return 0; -} - -early_param("kgdbcon", opt_kgdb_con); - module_param(kgdb_use_con, int, 0644); module_param(kgdbreboot, int, 0644); @@ -920,6 +912,20 @@ static struct console kgdbcons = { .index = -1, }; +static int __init opt_kgdb_con(char *str) +{ + kgdb_use_con = 1; + + if (kgdb_io_module_registered && !kgdb_con_registered) { + register_console(&kgdbcons); + kgdb_con_registered = 1; + } + + return 0; +} + +early_param("kgdbcon", opt_kgdb_con); + #ifdef CONFIG_MAGIC_SYSRQ static void sysrq_handle_dbg(int key) { From ece4ceaf2eba1c0da9d6b62bc59a43be6b456548 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Mon, 7 Sep 2020 13:32:06 -0700 Subject: [PATCH 117/645] kdb: Use newer api for tasklist scanning This kills using the do_each_thread/while_each_thread combo to iterate all threads and uses for_each_process_thread() instead, maintaining semantics. while_each_thread() is ultimately racy and deprecated; although in this particular case there is no concurrency so it doesn't matter. Still lets trivially get rid of two more users. Acked-by: Oleg Nesterov Signed-off-by: Davidlohr Bueso Link: https://lore.kernel.org/r/20200907203206.21293-1-dave@stgolabs.net Signed-off-by: Daniel Thompson --- kernel/debug/gdbstub.c | 4 ++-- kernel/debug/kdb/kdb_bt.c | 4 ++-- kernel/debug/kdb/kdb_main.c | 8 ++++---- kernel/debug/kdb/kdb_private.h | 4 ---- 4 files changed, 8 insertions(+), 12 deletions(-) diff --git a/kernel/debug/gdbstub.c b/kernel/debug/gdbstub.c index cc3c43dfec44..b52ebff09ac8 100644 --- a/kernel/debug/gdbstub.c +++ b/kernel/debug/gdbstub.c @@ -725,7 +725,7 @@ static void gdb_cmd_query(struct kgdb_state *ks) } } - do_each_thread(g, p) { + for_each_process_thread(g, p) { if (i >= ks->thr_query && !finished) { int_to_threadref(thref, p->pid); ptr = pack_threadid(ptr, thref); @@ -735,7 +735,7 @@ static void gdb_cmd_query(struct kgdb_state *ks) finished = 1; } i++; - } while_each_thread(g, p); + } *(--ptr) = '\0'; break; diff --git a/kernel/debug/kdb/kdb_bt.c b/kernel/debug/kdb/kdb_bt.c index 18e03aba2cfc..1f9f0e47aeda 100644 --- a/kernel/debug/kdb/kdb_bt.c +++ b/kernel/debug/kdb/kdb_bt.c @@ -149,14 +149,14 @@ kdb_bt(int argc, const char **argv) return 0; } /* Now the inactive tasks */ - kdb_do_each_thread(g, p) { + for_each_process_thread(g, p) { if (KDB_FLAG(CMD_INTERRUPT)) return 0; if (task_curr(p)) continue; if (kdb_bt1(p, mask, btaprompt)) return 0; - } kdb_while_each_thread(g, p); + } } else if (strcmp(argv[0], "btp") == 0) { struct task_struct *p; unsigned long pid; diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 5c7949061671..930ac1b25ec7 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -2299,10 +2299,10 @@ void kdb_ps_suppressed(void) if (kdb_task_state(p, mask_I)) ++idle; } - kdb_do_each_thread(g, p) { + for_each_process_thread(g, p) { if (kdb_task_state(p, mask_M)) ++daemon; - } kdb_while_each_thread(g, p); + } if (idle || daemon) { if (idle) kdb_printf("%d idle process%s (state I)%s\n", @@ -2370,12 +2370,12 @@ static int kdb_ps(int argc, const char **argv) } kdb_printf("\n"); /* Now the real tasks */ - kdb_do_each_thread(g, p) { + for_each_process_thread(g, p) { if (KDB_FLAG(CMD_INTERRUPT)) return 0; if (kdb_task_state(p, mask)) kdb_ps1(p); - } kdb_while_each_thread(g, p); + } return 0; } diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h index 2e296e4a234c..a4281fb99299 100644 --- a/kernel/debug/kdb/kdb_private.h +++ b/kernel/debug/kdb/kdb_private.h @@ -230,10 +230,6 @@ extern struct task_struct *kdb_curr_task(int); #define kdb_task_has_cpu(p) (task_curr(p)) -/* Simplify coexistence with NPTL */ -#define kdb_do_each_thread(g, p) do_each_thread(g, p) -#define kdb_while_each_thread(g, p) while_each_thread(g, p) - #define GFP_KDB (in_interrupt() ? GFP_ATOMIC : GFP_KERNEL) extern void *debug_kmalloc(size_t size, gfp_t flags); From e16c33e290792c9b71b952dc915e5f7dfc9d4409 Mon Sep 17 00:00:00 2001 From: Youling Tang Date: Fri, 7 Aug 2020 17:44:40 +0800 Subject: [PATCH 118/645] kernel/debug: Fix spelling mistake in debug_core.c Fix typo: "notifiter" --> "notifier" "overriden" --> "overridden" Signed-off-by: Youling Tang Link: https://lore.kernel.org/r/1596793480-22559-1-git-send-email-tangyouling@loongson.cn Signed-off-by: Daniel Thompson --- kernel/debug/debug_core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index 404d6d47a11d..165e5b0c2083 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -80,7 +80,7 @@ static int exception_level; struct kgdb_io *dbg_io_ops; static DEFINE_SPINLOCK(kgdb_registration_lock); -/* Action for the reboot notifiter, a global allow kdb to change it */ +/* Action for the reboot notifier, a global allow kdb to change it */ static int kgdbreboot; /* kgdb console driver is loaded */ static int kgdb_con_registered; @@ -155,7 +155,7 @@ early_param("nokgdbroundup", opt_nokgdbroundup); /* * Weak aliases for breakpoint management, - * can be overriden by architectures when needed: + * can be overridden by architectures when needed: */ int __weak kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt) { From 4bf3ec384edf0bf893ec7bd62ccebb635b02efd9 Mon Sep 17 00:00:00 2001 From: Sven Schnelle Date: Mon, 7 Sep 2020 17:45:37 +0200 Subject: [PATCH 119/645] s390: disable branch profiling for vdso When branch profiling is enabled, if () gets annotated with code to instrument the hit/miss ratio. This doesn't work for VDSO as we can't access kernel code. Add -DDISABLE_BRANCH_PROFILING to fix this. Reported-by: Thomas Richter Signed-off-by: Sven Schnelle Reviewed-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/vdso64/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile index f1c0570780d1..3d3303283181 100644 --- a/arch/s390/kernel/vdso64/Makefile +++ b/arch/s390/kernel/vdso64/Makefile @@ -17,7 +17,7 @@ obj-vdso64 := $(addprefix $(obj)/, $(obj-vdso64)) obj-cvdso64 := $(addprefix $(obj)/, $(obj-cvdso64)) KBUILD_AFLAGS += -DBUILD_VDSO -KBUILD_CFLAGS += -DBUILD_VDSO +KBUILD_CFLAGS += -DBUILD_VDSO -DDISABLE_BRANCH_PROFILING KBUILD_AFLAGS_64 := $(filter-out -m64,$(KBUILD_AFLAGS)) KBUILD_AFLAGS_64 += -m64 -s From 309f98dbc66cb183a84781e2b19595f044a2d6e4 Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Thu, 6 Feb 2020 17:52:03 +0100 Subject: [PATCH 120/645] s390/qdio: make qdio_handle_aobs() more robust When processing a PENDING buffer with no attached aob, the current code would get stuck on this buffer (as the 'continue' causes us to not advance the buffer index) and process it repeatedly until the loop terminates eventually. Luckily this should never happen - the HW must not use the PENDING state when no aob was provided. But we can still make this code path less fragile and protect against buggy devices. Signed-off-by: Julian Wiedmann Signed-off-by: Vasily Gorbik --- drivers/s390/cio/qdio_main.c | 42 +++++++++++++++++------------------- 1 file changed, 20 insertions(+), 22 deletions(-) diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c index 4fab8bba2cdd..0ed8c680cae4 100644 --- a/drivers/s390/cio/qdio_main.c +++ b/drivers/s390/cio/qdio_main.c @@ -531,26 +531,6 @@ static inline int qdio_inbound_q_done(struct qdio_q *q, unsigned int start) return 1; } -static inline void qdio_handle_aobs(struct qdio_q *q, int start, int count) -{ - unsigned char state = 0; - int j, b = start; - - for (j = 0; j < count; ++j) { - get_buf_state(q, b, &state, 0); - if (state == SLSB_P_OUTPUT_PENDING) { - struct qaob *aob = q->u.out.aobs[b]; - if (aob == NULL) - continue; - - q->u.out.sbal_state[b].flags |= - QDIO_OUTBUF_STATE_FLAG_PENDING; - q->u.out.aobs[b] = NULL; - } - b = next_buf(b); - } -} - static inline unsigned long qdio_aob_for_buffer(struct qdio_output_q *q, int bufnr) { @@ -640,6 +620,19 @@ void qdio_inbound_processing(unsigned long data) __qdio_inbound_processing(q); } +static void qdio_check_pending(struct qdio_q *q, unsigned int index) +{ + unsigned char state; + + if (get_buf_state(q, index, &state, 0) > 0 && + state == SLSB_P_OUTPUT_PENDING && + q->u.out.aobs[index]) { + q->u.out.sbal_state[index].flags |= + QDIO_OUTBUF_STATE_FLAG_PENDING; + q->u.out.aobs[index] = NULL; + } +} + static int get_outbound_buffer_frontier(struct qdio_q *q, unsigned int start) { unsigned char state = 0; @@ -712,8 +705,13 @@ static inline int qdio_outbound_q_moved(struct qdio_q *q, unsigned int start) if (count) { DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "out moved:%1d", q->nr); - if (q->u.out.use_cq) - qdio_handle_aobs(q, start, count); + + if (q->u.out.use_cq) { + unsigned int i; + + for (i = 0; i < count; i++) + qdio_check_pending(q, QDIO_BUFNR(start + i)); + } } return count; From 4d4a3caaf36246520d61c17a9fd86ce3893f6595 Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Wed, 19 Feb 2020 11:15:30 +0100 Subject: [PATCH 121/645] s390/qdio: clean up QDR setup __qdio_allocate_fill_qdr() is meant to set up one specific queue descriptor in the QDR. But for this simple task, it gets passed a bunch of global structs and offsets - and then navigates through the structs to find its actual operands. Clean up all the complicated pointer chasing & index calculation, and just pass a descriptor and its associated queue struct. While at it also add some virt_to_phys() translations, to clarify that addresses in the QDR are meant to be absolute. Signed-off-by: Julian Wiedmann Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/qdio.h | 8 ++++---- drivers/s390/cio/qdio_setup.c | 31 ++++++++++++------------------- 2 files changed, 16 insertions(+), 23 deletions(-) diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h index e69dbf438f99..60012fc11bac 100644 --- a/arch/s390/include/asm/qdio.h +++ b/arch/s390/include/asm/qdio.h @@ -26,9 +26,9 @@ /** * struct qdesfmt0 - queue descriptor, format 0 - * @sliba: storage list information block address - * @sla: storage list address - * @slsba: storage list state block address + * @sliba: absolute address of storage list information block + * @sla: absolute address of storage list + * @slsba: absolute address of storage list state block * @akey: access key for SLIB * @bkey: access key for SL * @ckey: access key for SBALs @@ -56,7 +56,7 @@ struct qdesfmt0 { * @oqdcnt: output queue descriptor count * @iqdsz: input queue descriptor size * @oqdsz: output queue descriptor size - * @qiba: queue information block address + * @qiba: absolute address of queue information block * @qkey: queue information block key * @qdf0: queue descriptions */ diff --git a/drivers/s390/cio/qdio_setup.c b/drivers/s390/cio/qdio_setup.c index 2c5cc6ec668e..42e1c0949309 100644 --- a/drivers/s390/cio/qdio_setup.c +++ b/drivers/s390/cio/qdio_setup.c @@ -403,28 +403,22 @@ void qdio_free_async_data(struct qdio_irq *irq_ptr) } } -static void __qdio_allocate_fill_qdr(struct qdio_irq *irq_ptr, - struct qdio_q **irq_ptr_qs, - int i, int nr) +static void qdio_fill_qdr_desc(struct qdesfmt0 *desc, struct qdio_q *queue) { - irq_ptr->qdr->qdf0[i + nr].sliba = - (unsigned long)irq_ptr_qs[i]->slib; + desc->sliba = virt_to_phys(queue->slib); + desc->sla = virt_to_phys(queue->sl); + desc->slsba = virt_to_phys(&queue->slsb); - irq_ptr->qdr->qdf0[i + nr].sla = - (unsigned long)irq_ptr_qs[i]->sl; - - irq_ptr->qdr->qdf0[i + nr].slsba = - (unsigned long)&irq_ptr_qs[i]->slsb.val[0]; - - irq_ptr->qdr->qdf0[i + nr].akey = PAGE_DEFAULT_KEY >> 4; - irq_ptr->qdr->qdf0[i + nr].bkey = PAGE_DEFAULT_KEY >> 4; - irq_ptr->qdr->qdf0[i + nr].ckey = PAGE_DEFAULT_KEY >> 4; - irq_ptr->qdr->qdf0[i + nr].dkey = PAGE_DEFAULT_KEY >> 4; + desc->akey = PAGE_DEFAULT_KEY >> 4; + desc->bkey = PAGE_DEFAULT_KEY >> 4; + desc->ckey = PAGE_DEFAULT_KEY >> 4; + desc->dkey = PAGE_DEFAULT_KEY >> 4; } static void setup_qdr(struct qdio_irq *irq_ptr, struct qdio_initialize *qdio_init) { + struct qdesfmt0 *desc = &irq_ptr->qdr->qdf0[0]; int i; irq_ptr->qdr->qfmt = qdio_init->q_format; @@ -433,15 +427,14 @@ static void setup_qdr(struct qdio_irq *irq_ptr, irq_ptr->qdr->oqdcnt = qdio_init->no_output_qs; irq_ptr->qdr->iqdsz = sizeof(struct qdesfmt0) / 4; /* size in words */ irq_ptr->qdr->oqdsz = sizeof(struct qdesfmt0) / 4; - irq_ptr->qdr->qiba = (unsigned long)&irq_ptr->qib; + irq_ptr->qdr->qiba = virt_to_phys(&irq_ptr->qib); irq_ptr->qdr->qkey = PAGE_DEFAULT_KEY >> 4; for (i = 0; i < qdio_init->no_input_qs; i++) - __qdio_allocate_fill_qdr(irq_ptr, irq_ptr->input_qs, i, 0); + qdio_fill_qdr_desc(desc++, irq_ptr->input_qs[i]); for (i = 0; i < qdio_init->no_output_qs; i++) - __qdio_allocate_fill_qdr(irq_ptr, irq_ptr->output_qs, i, - qdio_init->no_input_qs); + qdio_fill_qdr_desc(desc++, irq_ptr->output_qs[i]); } static void setup_qib(struct qdio_irq *irq_ptr, From b02002cc4c0f8a2340d07690f58cae0c04ba2325 Mon Sep 17 00:00:00 2001 From: Niklas Schnelle Date: Mon, 13 Jul 2020 14:12:49 +0200 Subject: [PATCH 122/645] s390/pci: Implement ioremap_wc/prot() with MIO With our current support for the new MIO PCI instructions, write combining/write back MMIO memory can be obtained via the pci_iomap_wc() and pci_iomap_wc_range() functions. This is achieved by using the write back address for a specific bar as provided in clp_store_query_pci_fn() These functions are however not widely used and instead drivers often rely on ioremap_wc() and ioremap_prot(), which on other platforms enable write combining using a PTE flag set through the pgrprot value. While we do not have a write combining flag in the low order flag bits of the PTE like x86_64 does, with MIO support, there is a write back bit in the physical address (bit 1 on z15) and thus also the PTE. Which bit is used to toggle write back and whether it is available at all, is however not fixed in the architecture. Instead we get this information from the CLP Store Logical Processor Characteristics for PCI command. When the write back bit is not provided we fall back to the existing behavior. Signed-off-by: Niklas Schnelle Reviewed-by: Pierre Morel Reviewed-by: Gerald Schaefer Signed-off-by: Vasily Gorbik --- .../features/vm/ioremap_prot/arch-support.txt | 2 +- arch/s390/include/asm/clp.h | 3 ++ arch/s390/include/asm/io.h | 8 +++++ arch/s390/include/asm/pci.h | 1 + arch/s390/include/asm/pci_clp.h | 19 ++++++++++ arch/s390/include/asm/pgtable.h | 9 ++++- arch/s390/include/asm/setup.h | 3 ++ arch/s390/kernel/setup.c | 6 ++++ arch/s390/mm/pgtable.c | 20 +++++++++++ arch/s390/pci/pci.c | 30 ++++++++++++++-- arch/s390/pci/pci_clp.c | 36 ++++++++++++++++++- 11 files changed, 132 insertions(+), 5 deletions(-) diff --git a/Documentation/features/vm/ioremap_prot/arch-support.txt b/Documentation/features/vm/ioremap_prot/arch-support.txt index 1cb7406cd858..b5fb37c28cc6 100644 --- a/Documentation/features/vm/ioremap_prot/arch-support.txt +++ b/Documentation/features/vm/ioremap_prot/arch-support.txt @@ -24,7 +24,7 @@ | parisc: | TODO | | powerpc: | ok | | riscv: | TODO | - | s390: | TODO | + | s390: | ok | | sh: | ok | | sparc: | TODO | | um: | TODO | diff --git a/arch/s390/include/asm/clp.h b/arch/s390/include/asm/clp.h index 3925b0f085b7..10919eeb7533 100644 --- a/arch/s390/include/asm/clp.h +++ b/arch/s390/include/asm/clp.h @@ -5,6 +5,9 @@ /* CLP common request & response block size */ #define CLP_BLK_SIZE PAGE_SIZE +/* Call Logical Processor - Command Code */ +#define CLP_SLPC 0x0001 + #define CLP_LPS_BASE 0 #define CLP_LPS_PCI 2 diff --git a/arch/s390/include/asm/io.h b/arch/s390/include/asm/io.h index da014e4f8113..28664ee0abc1 100644 --- a/arch/s390/include/asm/io.h +++ b/arch/s390/include/asm/io.h @@ -12,6 +12,7 @@ #include #include +#include #include #define xlate_dev_mem_ptr xlate_dev_mem_ptr @@ -26,7 +27,10 @@ void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr); #define IO_SPACE_LIMIT 0 +void __iomem *ioremap_prot(phys_addr_t addr, size_t size, unsigned long prot); void __iomem *ioremap(phys_addr_t addr, size_t size); +void __iomem *ioremap_wc(phys_addr_t addr, size_t size); +void __iomem *ioremap_wt(phys_addr_t addr, size_t size); void iounmap(volatile void __iomem *addr); static inline void __iomem *ioport_map(unsigned long port, unsigned int nr) @@ -52,6 +56,10 @@ static inline void ioport_unmap(void __iomem *p) #define pci_iomap_wc pci_iomap_wc #define pci_iomap_wc_range pci_iomap_wc_range +#define ioremap ioremap +#define ioremap_wt ioremap_wt +#define ioremap_wc ioremap_wc + #define memcpy_fromio(dst, src, count) zpci_memcpy_fromio(dst, src, count) #define memcpy_toio(dst, src, count) zpci_memcpy_toio(dst, src, count) #define memset_io(dst, val, count) zpci_memset_io(dst, val, count) diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index 99b92c3e46b0..8015b9301533 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -208,6 +208,7 @@ int zpci_unregister_ioat(struct zpci_dev *, u8); void zpci_remove_reserved_devices(void); /* CLP */ +int clp_setup_writeback_mio(void); int clp_scan_pci_devices(void); int clp_rescan_pci_devices(void); int clp_rescan_pci_devices_simple(u32 *fid); diff --git a/arch/s390/include/asm/pci_clp.h b/arch/s390/include/asm/pci_clp.h index eb51272dd2cc..1f4b666e85ee 100644 --- a/arch/s390/include/asm/pci_clp.h +++ b/arch/s390/include/asm/pci_clp.h @@ -7,6 +7,7 @@ /* * Call Logical Processor - Command Codes */ +#define CLP_SLPC 0x0001 #define CLP_LIST_PCI 0x0002 #define CLP_QUERY_PCI_FN 0x0003 #define CLP_QUERY_PCI_FNGRP 0x0004 @@ -51,6 +52,19 @@ struct clp_fh_list_entry { extern bool zpci_unique_uid; +struct clp_rsp_slpc_pci { + struct clp_rsp_hdr hdr; + u32 reserved2[4]; + u32 lpif[8]; + u32 reserved3[4]; + u32 vwb : 1; + u32 : 1; + u32 mio_wb : 6; + u32 : 24; + u32 reserved5[3]; + u32 lpic[8]; +} __packed; + /* List PCI functions request */ struct clp_req_list_pci { struct clp_req_hdr hdr; @@ -172,6 +186,11 @@ struct clp_rsp_set_pci { } __packed; /* Combined request/response block structures used by clp insn */ +struct clp_req_rsp_slpc_pci { + struct clp_req_slpc request; + struct clp_rsp_slpc_pci response; +} __packed; + struct clp_req_rsp_list_pci { struct clp_req_list_pci request; struct clp_rsp_list_pci response; diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 7eb01a5459cd..e9244b9fb504 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1186,6 +1186,12 @@ void gmap_pmdp_invalidate(struct mm_struct *mm, unsigned long vmaddr); void gmap_pmdp_idte_local(struct mm_struct *mm, unsigned long vmaddr); void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr); +#define pgprot_writecombine pgprot_writecombine +pgprot_t pgprot_writecombine(pgprot_t prot); + +#define pgprot_writethrough pgprot_writethrough +pgprot_t pgprot_writethrough(pgprot_t prot); + /* * Certain architectures need to do special things when PTEs * within a page table are directly modified. Thus, the following @@ -1209,7 +1215,8 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, static inline pte_t mk_pte_phys(unsigned long physpage, pgprot_t pgprot) { pte_t __pte; - pte_val(__pte) = physpage + pgprot_val(pgprot); + + pte_val(__pte) = physpage | pgprot_val(pgprot); if (!MACHINE_HAS_NX) pte_val(__pte) &= ~_PAGE_NOEXEC; return pte_mkyoung(__pte); diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h index 534f212753d6..7b104f156e34 100644 --- a/arch/s390/include/asm/setup.h +++ b/arch/s390/include/asm/setup.h @@ -94,6 +94,9 @@ extern unsigned long vmalloc_size; extern unsigned long max_physmem_end; extern unsigned long __swsusp_reset_dma; +/* The Write Back bit position in the physaddr is given by the SLPC PCI */ +extern unsigned long mio_wb_bit_mask; + #define MACHINE_IS_VM (S390_lowcore.machine_flags & MACHINE_FLAG_VM) #define MACHINE_IS_KVM (S390_lowcore.machine_flags & MACHINE_FLAG_KVM) #define MACHINE_IS_LPAR (S390_lowcore.machine_flags & MACHINE_FLAG_LPAR) diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index dfa45027cb47..efd12221ecb4 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -127,6 +127,12 @@ unsigned long MODULES_END; struct lowcore *lowcore_ptr[NR_CPUS]; EXPORT_SYMBOL(lowcore_ptr); +/* + * The Write Back bit position in the physaddr is given by the SLPC PCI. + * Leaving the mask zero always uses write through which is safe + */ +unsigned long mio_wb_bit_mask __ro_after_init; + /* * This is set up by the setup-routine at boot-time * for S390 need to find out, what we have to setup diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 0d25f743b270..18205f851c24 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -24,6 +24,26 @@ #include #include +pgprot_t pgprot_writecombine(pgprot_t prot) +{ + /* + * mio_wb_bit_mask may be set on a different CPU, but it is only set + * once at init and only read afterwards. + */ + return __pgprot(pgprot_val(prot) | mio_wb_bit_mask); +} +EXPORT_SYMBOL_GPL(pgprot_writecombine); + +pgprot_t pgprot_writethrough(pgprot_t prot) +{ + /* + * mio_wb_bit_mask may be set on a different CPU, but it is only set + * once at init and only read afterwards. + */ + return __pgprot(pgprot_val(prot) & ~mio_wb_bit_mask); +} +EXPORT_SYMBOL_GPL(pgprot_writethrough); + static inline void ptep_ipte_local(struct mm_struct *mm, unsigned long addr, pte_t *ptep, int nodat) { diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 4b62d6b55024..fdbb99c4569d 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -226,7 +226,7 @@ void __iowrite64_copy(void __iomem *to, const void *from, size_t count) zpci_memcpy_toio(to, from, count); } -void __iomem *ioremap(phys_addr_t addr, size_t size) +static void __iomem *__ioremap(phys_addr_t addr, size_t size, pgprot_t prot) { unsigned long offset, vaddr; struct vm_struct *area; @@ -247,14 +247,37 @@ void __iomem *ioremap(phys_addr_t addr, size_t size) return NULL; vaddr = (unsigned long) area->addr; - if (ioremap_page_range(vaddr, vaddr + size, addr, PAGE_KERNEL)) { + if (ioremap_page_range(vaddr, vaddr + size, addr, prot)) { free_vm_area(area); return NULL; } return (void __iomem *) ((unsigned long) area->addr + offset); } + +void __iomem *ioremap_prot(phys_addr_t addr, size_t size, unsigned long prot) +{ + return __ioremap(addr, size, __pgprot(prot)); +} +EXPORT_SYMBOL(ioremap_prot); + +void __iomem *ioremap(phys_addr_t addr, size_t size) +{ + return __ioremap(addr, size, PAGE_KERNEL); +} EXPORT_SYMBOL(ioremap); +void __iomem *ioremap_wc(phys_addr_t addr, size_t size) +{ + return __ioremap(addr, size, pgprot_writecombine(PAGE_KERNEL)); +} +EXPORT_SYMBOL(ioremap_wc); + +void __iomem *ioremap_wt(phys_addr_t addr, size_t size) +{ + return __ioremap(addr, size, pgprot_writethrough(PAGE_KERNEL)); +} +EXPORT_SYMBOL(ioremap_wt); + void iounmap(volatile void __iomem *addr) { if (static_branch_likely(&have_mio)) @@ -784,6 +807,9 @@ static int zpci_mem_init(void) if (!zpci_iomap_bitmap) goto error_iomap_bitmap; + if (static_branch_likely(&have_mio)) + clp_setup_writeback_mio(); + return 0; error_iomap_bitmap: kfree(zpci_iomap_start); diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c index 7e735f41a0a6..51807945ca00 100644 --- a/arch/s390/pci/pci_clp.c +++ b/arch/s390/pci/pci_clp.c @@ -292,6 +292,40 @@ static int clp_set_pci_fn(struct zpci_dev *zdev, u8 nr_dma_as, u8 command) return rc; } +int clp_setup_writeback_mio(void) +{ + struct clp_req_rsp_slpc_pci *rrb; + u8 wb_bit_pos; + int rc; + + rrb = clp_alloc_block(GFP_KERNEL); + if (!rrb) + return -ENOMEM; + + memset(rrb, 0, sizeof(*rrb)); + rrb->request.hdr.len = sizeof(rrb->request); + rrb->request.hdr.cmd = CLP_SLPC; + rrb->response.hdr.len = sizeof(rrb->response); + + rc = clp_req(rrb, CLP_LPS_PCI); + if (!rc && rrb->response.hdr.rsp == CLP_RC_OK) { + if (rrb->response.vwb) { + wb_bit_pos = rrb->response.mio_wb; + set_bit_inv(wb_bit_pos, &mio_wb_bit_mask); + zpci_dbg(3, "wb bit: %d\n", wb_bit_pos); + } else { + zpci_dbg(3, "wb bit: n.a.\n"); + } + + } else { + zpci_err("SLPC PCI:\n"); + zpci_err_clp(rrb->response.hdr.rsp, rc); + rc = -EIO; + } + clp_free_block(rrb); + return rc; +} + int clp_enable_fh(struct zpci_dev *zdev, u8 nr_dma_as) { int rc; @@ -495,7 +529,7 @@ static int clp_base_command(struct clp_req *req, struct clp_req_hdr *lpcb) } } -static int clp_pci_slpc(struct clp_req *req, struct clp_req_rsp_slpc *lpcb) +static int clp_pci_slpc(struct clp_req *req, struct clp_req_rsp_slpc_pci *lpcb) { unsigned long limit = PAGE_SIZE - sizeof(lpcb->request); From 180a4c42e541cabe478c3f6e6c986a6b61744407 Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Mon, 24 Aug 2020 17:32:52 +0300 Subject: [PATCH 123/645] s390/qdio: always use dev_name() for device name in QIB Passing a custom name from the device driver is nice - but in practice it's only zfcp who has been using this. So we might as well hard-code a naming scheme in the qdio layer, so that qeth also benefits from it. Signed-off-by: Julian Wiedmann Reviewed-by: Steffen Maier Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/qdio.h | 2 -- drivers/s390/cio/qdio_main.c | 1 - drivers/s390/cio/qdio_setup.c | 5 ++++- drivers/s390/scsi/zfcp_qdio.c | 2 -- 4 files changed, 4 insertions(+), 6 deletions(-) diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h index 60012fc11bac..19e84c95d1e7 100644 --- a/arch/s390/include/asm/qdio.h +++ b/arch/s390/include/asm/qdio.h @@ -327,7 +327,6 @@ typedef void qdio_handler_t(struct ccw_device *, unsigned int, int, * struct qdio_initialize - qdio initialization data * @q_format: queue format * @qdr_ac: feature flags to set - * @adapter_name: name for the adapter * @qib_param_field_format: format for qib_parm_field * @qib_param_field: pointer to 128 bytes or NULL, if no param field * @qib_rflags: rflags to set @@ -347,7 +346,6 @@ typedef void qdio_handler_t(struct ccw_device *, unsigned int, int, struct qdio_initialize { unsigned char q_format; unsigned char qdr_ac; - unsigned char adapter_name[8]; unsigned int qib_param_field_format; unsigned char *qib_param_field; unsigned char qib_rflags; diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c index 0ed8c680cae4..f9a31c7819ae 100644 --- a/drivers/s390/cio/qdio_main.c +++ b/drivers/s390/cio/qdio_main.c @@ -1219,7 +1219,6 @@ static void qdio_trace_init_data(struct qdio_irq *irq, struct qdio_initialize *data) { DBF_DEV_EVENT(DBF_ERR, irq, "qfmt:%1u", data->q_format); - DBF_DEV_HEX(irq, data->adapter_name, 8, DBF_ERR); DBF_DEV_EVENT(DBF_ERR, irq, "qpff%4x", data->qib_param_field_format); DBF_DEV_HEX(irq, &data->qib_param_field, sizeof(void *), DBF_ERR); DBF_DEV_HEX(irq, &data->input_slib_elements, sizeof(void *), DBF_ERR); diff --git a/drivers/s390/cio/qdio_setup.c b/drivers/s390/cio/qdio_setup.c index 42e1c0949309..a5b2e16b7aa8 100644 --- a/drivers/s390/cio/qdio_setup.c +++ b/drivers/s390/cio/qdio_setup.c @@ -9,6 +9,8 @@ #include #include #include + +#include #include #include "cio.h" @@ -452,7 +454,8 @@ static void setup_qib(struct qdio_irq *irq_ptr, if (init_data->no_output_qs) irq_ptr->qib.osliba = (unsigned long)(irq_ptr->output_qs[0]->slib); - memcpy(irq_ptr->qib.ebcnam, init_data->adapter_name, 8); + memcpy(irq_ptr->qib.ebcnam, dev_name(&irq_ptr->cdev->dev), 8); + ASCEBC(irq_ptr->qib.ebcnam, 8); } int qdio_setup_irq(struct qdio_irq *irq_ptr, struct qdio_initialize *init_data) diff --git a/drivers/s390/scsi/zfcp_qdio.c b/drivers/s390/scsi/zfcp_qdio.c index e78d65bd46b1..a8a514074084 100644 --- a/drivers/s390/scsi/zfcp_qdio.c +++ b/drivers/s390/scsi/zfcp_qdio.c @@ -380,8 +380,6 @@ int zfcp_qdio_open(struct zfcp_qdio *qdio) &qdio->adapter->status); init_data.q_format = QDIO_ZFCP_QFMT; - memcpy(init_data.adapter_name, dev_name(&cdev->dev), 8); - ASCEBC(init_data.adapter_name, 8); init_data.qib_rflags = QIB_RFLAGS_ENABLE_DATA_DIV; if (enable_multibuffer) init_data.qdr_ac |= QDR_AC_MULTI_BUFFER_ENABLE; From 0d574ad33e5b70383b4cee81024fcb8763aac591 Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Wed, 9 Sep 2020 12:02:46 +0200 Subject: [PATCH 124/645] s390/zcrypt: simplify cca_findcard2 loop code Instead of two times go through the list of available AP devices (which may be up to 256 * 256 entries) this patch reworks the code do only run through once. The price is instead of reporting all possible devices to the caller only the first 256 devices are collected. However, having to choose from 256 AP devices is plenty of resources and should fulfill the caller's requirements. On the other side the loop code is much simplier and more easy to maintain. Signed-off-by: Harald Freudenberger Reviewed-by: Ingo Franzki Signed-off-by: Vasily Gorbik --- drivers/s390/crypto/zcrypt_ccamisc.c | 121 +++++++++++++-------------- 1 file changed, 58 insertions(+), 63 deletions(-) diff --git a/drivers/s390/crypto/zcrypt_ccamisc.c b/drivers/s390/crypto/zcrypt_ccamisc.c index 3f5b61351cde..5fafda6663ed 100644 --- a/drivers/s390/crypto/zcrypt_ccamisc.c +++ b/drivers/s390/crypto/zcrypt_ccamisc.c @@ -1685,12 +1685,10 @@ int cca_findcard2(u32 **apqns, u32 *nr_apqns, u16 cardnr, u16 domain, int minhwtype, u64 cur_mkvp, u64 old_mkvp, int verify) { struct zcrypt_device_status_ext *device_status; - int i, n, card, dom, curmatch, oldmatch, rc = 0; + u32 *_apqns = NULL, _nr_apqns = 0; + int i, card, dom, curmatch, oldmatch, rc = 0; struct cca_info ci; - *apqns = NULL; - *nr_apqns = 0; - /* fetch status of all crypto cards */ device_status = kmalloc_array(MAX_ZDEV_ENTRIES_EXT, sizeof(struct zcrypt_device_status_ext), @@ -1699,67 +1697,64 @@ int cca_findcard2(u32 **apqns, u32 *nr_apqns, u16 cardnr, u16 domain, return -ENOMEM; zcrypt_device_status_mask_ext(device_status); - /* loop two times: first gather eligible apqns, then store them */ - while (1) { - n = 0; - /* walk through all the crypto cards */ - for (i = 0; i < MAX_ZDEV_ENTRIES_EXT; i++) { - card = AP_QID_CARD(device_status[i].qid); - dom = AP_QID_QUEUE(device_status[i].qid); - /* check online state */ - if (!device_status[i].online) + /* allocate 1k space for up to 256 apqns */ + _apqns = kmalloc_array(256, sizeof(u32), GFP_KERNEL); + if (!_apqns) { + kvfree(device_status); + return -ENOMEM; + } + + /* walk through all the crypto apqnss */ + for (i = 0; i < MAX_ZDEV_ENTRIES_EXT; i++) { + card = AP_QID_CARD(device_status[i].qid); + dom = AP_QID_QUEUE(device_status[i].qid); + /* check online state */ + if (!device_status[i].online) + continue; + /* check for cca functions */ + if (!(device_status[i].functions & 0x04)) + continue; + /* check cardnr */ + if (cardnr != 0xFFFF && card != cardnr) + continue; + /* check domain */ + if (domain != 0xFFFF && dom != domain) + continue; + /* get cca info on this apqn */ + if (cca_get_info(card, dom, &ci, verify)) + continue; + /* current master key needs to be valid */ + if (ci.cur_mk_state != '2') + continue; + /* check min hardware type */ + if (minhwtype > 0 && minhwtype > ci.hwtype) + continue; + if (cur_mkvp || old_mkvp) { + /* check mkvps */ + curmatch = oldmatch = 0; + if (cur_mkvp && cur_mkvp == ci.cur_mkvp) + curmatch = 1; + if (old_mkvp && ci.old_mk_state == '2' && + old_mkvp == ci.old_mkvp) + oldmatch = 1; + if ((cur_mkvp || old_mkvp) && + (curmatch + oldmatch < 1)) continue; - /* check for cca functions */ - if (!(device_status[i].functions & 0x04)) - continue; - /* check cardnr */ - if (cardnr != 0xFFFF && card != cardnr) - continue; - /* check domain */ - if (domain != 0xFFFF && dom != domain) - continue; - /* get cca info on this apqn */ - if (cca_get_info(card, dom, &ci, verify)) - continue; - /* current master key needs to be valid */ - if (ci.cur_mk_state != '2') - continue; - /* check min hardware type */ - if (minhwtype > 0 && minhwtype > ci.hwtype) - continue; - if (cur_mkvp || old_mkvp) { - /* check mkvps */ - curmatch = oldmatch = 0; - if (cur_mkvp && cur_mkvp == ci.cur_mkvp) - curmatch = 1; - if (old_mkvp && ci.old_mk_state == '2' && - old_mkvp == ci.old_mkvp) - oldmatch = 1; - if ((cur_mkvp || old_mkvp) && - (curmatch + oldmatch < 1)) - continue; - } - /* apqn passed all filtering criterons */ - if (*apqns && n < *nr_apqns) - (*apqns)[n] = (((u16)card) << 16) | ((u16) dom); - n++; } - /* loop 2nd time: array has been filled */ - if (*apqns) - break; - /* loop 1st time: have # of eligible apqns in n */ - if (!n) { - rc = -ENODEV; /* no eligible apqns found */ - break; - } - *nr_apqns = n; - /* allocate array to store n apqns into */ - *apqns = kmalloc_array(n, sizeof(u32), GFP_KERNEL); - if (!*apqns) { - rc = -ENOMEM; - break; - } - verify = 0; + /* apqn passed all filtering criterons, add to the array */ + if (_nr_apqns < 256) + _apqns[_nr_apqns++] = (((u16)card) << 16) | ((u16) dom); + } + + /* nothing found ? */ + if (!_nr_apqns) { + kfree(_apqns); + rc = -ENODEV; + } else { + /* no re-allocation, simple return the _apqns array */ + *apqns = _apqns; + *nr_apqns = _nr_apqns; + rc = 0; } kfree(device_status); From 9d719d39aab41d3b8b6f259574dc29a27f60e66c Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Fri, 4 Sep 2020 17:41:27 +0200 Subject: [PATCH 125/645] s390/mm,ptdump: convert to generic page table dumper Make use of generic ptdump infrastructure. Reviewed-by: Vasily Gorbik Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/Kconfig | 1 + arch/s390/Kconfig.debug | 12 -- arch/s390/configs/debug_defconfig | 2 +- arch/s390/configs/defconfig | 2 +- arch/s390/mm/Makefile | 2 +- arch/s390/mm/dump_pagetables.c | 233 ++++++------------------------ 6 files changed, 51 insertions(+), 201 deletions(-) diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 8a6121f93709..85bf121211d1 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -120,6 +120,7 @@ config S390 select GENERIC_CPU_VULNERABILITIES select GENERIC_FIND_FIRST_BIT select GENERIC_GETTIMEOFDAY + select GENERIC_PTDUMP select GENERIC_SMP_IDLE_THREAD select GENERIC_TIME_VSYSCALL select HAVE_ALIGNED_STRUCT_PAGE if SLUB diff --git a/arch/s390/Kconfig.debug b/arch/s390/Kconfig.debug index 761fe2b0b2f6..ab48b694ade8 100644 --- a/arch/s390/Kconfig.debug +++ b/arch/s390/Kconfig.debug @@ -3,17 +3,5 @@ config TRACE_IRQFLAGS_SUPPORT def_bool y -config S390_PTDUMP - bool "Export kernel pagetable layout to userspace via debugfs" - depends on DEBUG_KERNEL - select DEBUG_FS - help - Say Y here if you want to show the kernel pagetable layout in a - debugfs file. This information is only useful for kernel developers - who are working in architecture specific areas of the kernel. - It is probably not a good idea to enable this feature in a production - kernel. - If in doubt, say "N" - config EARLY_PRINTK def_bool y diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 0cf9a82326a8..f79eafb597cb 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -774,6 +774,7 @@ CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_PAGEALLOC=y CONFIG_PAGE_OWNER=y CONFIG_DEBUG_RODATA_TEST=y +CONFIG_PTDUMP_DEBUGFS=y CONFIG_DEBUG_OBJECTS=y CONFIG_DEBUG_OBJECTS_SELFTEST=y CONFIG_DEBUG_OBJECTS_FREE=y @@ -819,7 +820,6 @@ CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y CONFIG_BLK_DEV_IO_TRACE=y CONFIG_HIST_TRIGGERS=y -CONFIG_S390_PTDUMP=y CONFIG_NOTIFIER_ERROR_INJECTION=m CONFIG_NETDEV_NOTIFIER_ERROR_INJECT=m CONFIG_FAULT_INJECTION=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 5df9759e8ff6..9593cc8a9efd 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -758,6 +758,7 @@ CONFIG_GDB_SCRIPTS=y CONFIG_FRAME_WARN=1024 CONFIG_DEBUG_SECTION_MISMATCH=y CONFIG_MAGIC_SYSRQ=y +CONFIG_PTDUMP_DEBUGFS=y CONFIG_DEBUG_MEMORY_INIT=y CONFIG_PANIC_ON_OOPS=y CONFIG_TEST_LOCKUP=m @@ -772,7 +773,6 @@ CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y CONFIG_BLK_DEV_IO_TRACE=y CONFIG_HIST_TRIGGERS=y -CONFIG_S390_PTDUMP=y CONFIG_LKDTM=m CONFIG_PERCPU_TEST=m CONFIG_ATOMIC64_SELFTEST=y diff --git a/arch/s390/mm/Makefile b/arch/s390/mm/Makefile index 3175413186b9..8ab9daeeace3 100644 --- a/arch/s390/mm/Makefile +++ b/arch/s390/mm/Makefile @@ -8,7 +8,7 @@ obj-y += page-states.o pageattr.o pgtable.o pgalloc.o obj-$(CONFIG_CMM) += cmm.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o -obj-$(CONFIG_S390_PTDUMP) += dump_pagetables.o +obj-$(CONFIG_PTDUMP_DEBUGFS) += dump_pagetables.o obj-$(CONFIG_PGSTE) += gmap.o KASAN_SANITIZE_kasan_init.o := n diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c index c2ac9b8ae612..93a29e2f13d4 100644 --- a/arch/s390/mm/dump_pagetables.c +++ b/arch/s390/mm/dump_pagetables.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 +#include #include #include -#include #include #include #include @@ -42,10 +42,11 @@ static struct addr_marker address_markers[] = { }; struct pg_state { + struct ptdump_state ptdump; + struct seq_file *seq; int level; unsigned int current_prot; unsigned long start_address; - unsigned long current_address; const struct addr_marker *marker; }; @@ -63,215 +64,75 @@ static void print_prot(struct seq_file *m, unsigned int pr, int level) seq_puts(m, (pr & _PAGE_NOEXEC) ? "NX\n" : "X\n"); } -static void note_page(struct seq_file *m, struct pg_state *st, - unsigned int new_prot, int level) +static void note_page(struct ptdump_state *pt_st, unsigned long addr, int level, u64 val) { - static const char units[] = "KMGTPE"; int width = sizeof(unsigned long) * 2; + static const char units[] = "KMGTPE"; const char *unit = units; - unsigned int prot, cur; unsigned long delta; + struct pg_state *st; + struct seq_file *m; + unsigned int prot; - /* - * If we have a "break" in the series, we need to flush the state - * that we have now. "break" is either changing perms, levels or - * address space marker. - */ - prot = new_prot; - cur = st->current_prot; - - if (!st->level) { - /* First entry */ - st->current_prot = new_prot; - st->level = level; - st->marker = address_markers; + st = container_of(pt_st, struct pg_state, ptdump); + m = st->seq; + prot = val & (_PAGE_PROTECT | _PAGE_NOEXEC); + if (level == 4 && (val & _PAGE_INVALID)) + prot = _PAGE_INVALID; + /* For pmd_none() & friends val gets passed as zero. */ + if (level != 4 && !val) + prot = _PAGE_INVALID; + /* Final flush from generic code. */ + if (level == -1) + addr = max_addr; + if (st->level == -1) { seq_printf(m, "---[ %s ]---\n", st->marker->name); - } else if (prot != cur || level != st->level || - st->current_address >= st->marker[1].start_address) { - /* Print the actual finished series */ + st->start_address = addr; + st->current_prot = prot; + st->level = level; + } else if (prot != st->current_prot || level != st->level || + addr >= st->marker[1].start_address) { seq_printf(m, "0x%0*lx-0x%0*lx ", width, st->start_address, - width, st->current_address); - delta = (st->current_address - st->start_address) >> 10; + width, addr); + delta = (addr - st->start_address) >> 10; while (!(delta & 0x3ff) && unit[1]) { delta >>= 10; unit++; } seq_printf(m, "%9lu%c ", delta, *unit); print_prot(m, st->current_prot, st->level); - while (st->current_address >= st->marker[1].start_address) { + while (addr >= st->marker[1].start_address) { st->marker++; seq_printf(m, "---[ %s ]---\n", st->marker->name); } - st->start_address = st->current_address; - st->current_prot = new_prot; + st->start_address = addr; + st->current_prot = prot; st->level = level; } } -#ifdef CONFIG_KASAN -static void note_kasan_early_shadow_page(struct seq_file *m, - struct pg_state *st) -{ - unsigned int prot; - - prot = pte_val(*kasan_early_shadow_pte) & - (_PAGE_PROTECT | _PAGE_INVALID | _PAGE_NOEXEC); - note_page(m, st, prot, 4); -} -#endif - -/* - * The actual page table walker functions. In order to keep the - * implementation of print_prot() short, we only check and pass - * _PAGE_INVALID and _PAGE_PROTECT flags to note_page() if a region, - * segment or page table entry is invalid or read-only. - * After all it's just a hint that the current level being walked - * contains an invalid or read-only entry. - */ -static void walk_pte_level(struct seq_file *m, struct pg_state *st, - pmd_t *pmd, unsigned long addr) -{ - unsigned int prot; - pte_t *pte; - int i; - - for (i = 0; i < PTRS_PER_PTE && addr < max_addr; i++) { - st->current_address = addr; - pte = pte_offset_kernel(pmd, addr); - prot = pte_val(*pte) & - (_PAGE_PROTECT | _PAGE_INVALID | _PAGE_NOEXEC); - note_page(m, st, prot, 4); - addr += PAGE_SIZE; - } -} - -static void walk_pmd_level(struct seq_file *m, struct pg_state *st, - pud_t *pud, unsigned long addr) -{ - unsigned int prot; - pmd_t *pmd; - int i; - -#ifdef CONFIG_KASAN - if ((pud_val(*pud) & PAGE_MASK) == __pa(kasan_early_shadow_pmd)) { - note_kasan_early_shadow_page(m, st); - return; - } -#endif - - pmd = pmd_offset(pud, addr); - for (i = 0; i < PTRS_PER_PMD && addr < max_addr; i++, pmd++) { - st->current_address = addr; - if (!pmd_none(*pmd)) { - if (pmd_large(*pmd)) { - prot = pmd_val(*pmd) & - (_SEGMENT_ENTRY_PROTECT | - _SEGMENT_ENTRY_NOEXEC); - note_page(m, st, prot, 3); - } else - walk_pte_level(m, st, pmd, addr); - } else - note_page(m, st, _PAGE_INVALID, 3); - addr += PMD_SIZE; - } -} - -static void walk_pud_level(struct seq_file *m, struct pg_state *st, - p4d_t *p4d, unsigned long addr) -{ - unsigned int prot; - pud_t *pud; - int i; - -#ifdef CONFIG_KASAN - if ((p4d_val(*p4d) & PAGE_MASK) == __pa(kasan_early_shadow_pud)) { - note_kasan_early_shadow_page(m, st); - return; - } -#endif - - pud = pud_offset(p4d, addr); - for (i = 0; i < PTRS_PER_PUD && addr < max_addr; i++, pud++) { - st->current_address = addr; - if (!pud_none(*pud)) - if (pud_large(*pud)) { - prot = pud_val(*pud) & - (_REGION_ENTRY_PROTECT | - _REGION_ENTRY_NOEXEC); - note_page(m, st, prot, 2); - } else - walk_pmd_level(m, st, pud, addr); - else - note_page(m, st, _PAGE_INVALID, 2); - addr += PUD_SIZE; - } -} - -static void walk_p4d_level(struct seq_file *m, struct pg_state *st, - pgd_t *pgd, unsigned long addr) -{ - p4d_t *p4d; - int i; - -#ifdef CONFIG_KASAN - if ((pgd_val(*pgd) & PAGE_MASK) == __pa(kasan_early_shadow_p4d)) { - note_kasan_early_shadow_page(m, st); - return; - } -#endif - - p4d = p4d_offset(pgd, addr); - for (i = 0; i < PTRS_PER_P4D && addr < max_addr; i++, p4d++) { - st->current_address = addr; - if (!p4d_none(*p4d)) - walk_pud_level(m, st, p4d, addr); - else - note_page(m, st, _PAGE_INVALID, 2); - addr += P4D_SIZE; - } -} - -static void walk_pgd_level(struct seq_file *m) -{ - unsigned long addr = 0; - struct pg_state st; - pgd_t *pgd; - int i; - - memset(&st, 0, sizeof(st)); - for (i = 0; i < PTRS_PER_PGD && addr < max_addr; i++) { - st.current_address = addr; - pgd = pgd_offset_k(addr); - if (!pgd_none(*pgd)) - walk_p4d_level(m, &st, pgd, addr); - else - note_page(m, &st, _PAGE_INVALID, 1); - addr += PGDIR_SIZE; - cond_resched(); - } - /* Flush out the last page */ - st.current_address = max_addr; - note_page(m, &st, 0, 0); -} - static int ptdump_show(struct seq_file *m, void *v) { - walk_pgd_level(m); + struct pg_state st = { + .ptdump = { + .note_page = note_page, + .range = (struct ptdump_range[]) { + {.start = 0, .end = max_addr}, + {.start = 0, .end = 0}, + } + }, + .seq = m, + .level = -1, + .current_prot = 0, + .start_address = 0, + .marker = address_markers, + }; + + ptdump_walk_pgd(&st.ptdump, &init_mm, NULL); return 0; } - -static int ptdump_open(struct inode *inode, struct file *filp) -{ - return single_open(filp, ptdump_show, NULL); -} - -static const struct file_operations ptdump_fops = { - .open = ptdump_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(ptdump); static int pt_dump_init(void) { From 36c2733c439caa424fe2b7dded870913dcb868ac Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 7 Sep 2020 17:11:36 +0200 Subject: [PATCH 126/645] s390/mm,ptdump: hold memory hotplug lock while walking for kernel page table dump This is the s390 variant of commit bf2b59f60ee1 ("arm64/mm: Hold memory hotplug lock while walking for kernel page table dump"). Right now this doesn't fix any real bug, however as soon as kvm patches get merged which make use of memory remove we might end up dereferencing/accessing freed page tables. Therefore fix this potential bug already now. Reviewed-by: Vasily Gorbik Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/mm/dump_pagetables.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c index 93a29e2f13d4..3c5e4055a3d2 100644 --- a/arch/s390/mm/dump_pagetables.c +++ b/arch/s390/mm/dump_pagetables.c @@ -129,7 +129,9 @@ static int ptdump_show(struct seq_file *m, void *v) .marker = address_markers, }; + get_online_mems(); ptdump_walk_pgd(&st.ptdump, &init_mm, NULL); + put_online_mems(); return 0; } DEFINE_SHOW_ATTRIBUTE(ptdump); From da1694ad9e8d13484c8b4ecaabde0bd7b958442a Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 7 Sep 2020 17:20:05 +0200 Subject: [PATCH 127/645] s390/mm,ptdump: hold cpa mutex while walking for kernel page table dump This is currently only preventing that outdated information is provided to user space. A concurrent split of huge/large pages does modify the kernel page tables, however either the huge/large mapping is reported or the split area is being walked. This "fixes" also only a potential future bug, since split pages could also be merged again if page permissions are the same for larger memory areas. Reviewed-by: Vasily Gorbik Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/set_memory.h | 4 ++++ arch/s390/mm/dump_pagetables.c | 3 +++ arch/s390/mm/pageattr.c | 2 +- 3 files changed, 8 insertions(+), 1 deletion(-) diff --git a/arch/s390/include/asm/set_memory.h b/arch/s390/include/asm/set_memory.h index c59a83536c70..a22a5a81811c 100644 --- a/arch/s390/include/asm/set_memory.h +++ b/arch/s390/include/asm/set_memory.h @@ -2,6 +2,10 @@ #ifndef _ASMS390_SET_MEMORY_H #define _ASMS390_SET_MEMORY_H +#include + +extern struct mutex cpa_mutex; + #define SET_MEMORY_RO 1UL #define SET_MEMORY_RW 2UL #define SET_MEMORY_NX 4UL diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c index 3c5e4055a3d2..09c7179cb17d 100644 --- a/arch/s390/mm/dump_pagetables.c +++ b/arch/s390/mm/dump_pagetables.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#include #include #include #include @@ -130,7 +131,9 @@ static int ptdump_show(struct seq_file *m, void *v) }; get_online_mems(); + mutex_lock(&cpa_mutex); ptdump_walk_pgd(&st.ptdump, &init_mm, NULL); + mutex_unlock(&cpa_mutex); put_online_mems(); return 0; } diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c index c5c52ec2b46f..ed8e5b3575d5 100644 --- a/arch/s390/mm/pageattr.c +++ b/arch/s390/mm/pageattr.c @@ -278,7 +278,7 @@ static int walk_p4d_level(pgd_t *pgd, unsigned long addr, unsigned long end, return rc; } -static DEFINE_MUTEX(cpa_mutex); +DEFINE_MUTEX(cpa_mutex); static int change_page_attr(unsigned long addr, unsigned long end, unsigned long flags) From abb95b7550f88bfb77081601f80662a259f2d143 Mon Sep 17 00:00:00 2001 From: Niklas Schnelle Date: Mon, 17 Aug 2020 10:29:23 +0200 Subject: [PATCH 128/645] s390/pci: consolidate SR-IOV specific code currently we have multiple #ifdef CONFIG_PCI_IOV blocks spread over different compliation units and headers, all dealing with SR-IOV specific behavior. This violates the style guide which discourages conditionally compiled code blocks and hinders maintainability by speading SR-IOV functionality over many files. Let's move all of this into a conditionally compiled pci_iov.c file and local header and prefix SR-IOV specific functions with zpci_iov_*. Reviewed-by: Matthew Rosato Signed-off-by: Niklas Schnelle Signed-off-by: Vasily Gorbik --- arch/s390/pci/Makefile | 1 + arch/s390/pci/pci.c | 23 ++-------- arch/s390/pci/pci_bus.c | 66 +--------------------------- arch/s390/pci/pci_bus.h | 12 ----- arch/s390/pci/pci_iov.c | 97 +++++++++++++++++++++++++++++++++++++++++ arch/s390/pci/pci_iov.h | 30 +++++++++++++ 6 files changed, 133 insertions(+), 96 deletions(-) create mode 100644 arch/s390/pci/pci_iov.c create mode 100644 arch/s390/pci/pci_iov.h diff --git a/arch/s390/pci/Makefile b/arch/s390/pci/Makefile index b4e3c84772a1..bf557a1b789c 100644 --- a/arch/s390/pci/Makefile +++ b/arch/s390/pci/Makefile @@ -6,3 +6,4 @@ obj-$(CONFIG_PCI) += pci.o pci_irq.o pci_dma.o pci_clp.o pci_sysfs.o \ pci_event.o pci_debug.o pci_insn.o pci_mmio.o \ pci_bus.o +obj-$(CONFIG_PCI_IOV) += pci_iov.o diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index fdbb99c4569d..e432318f6937 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -37,6 +37,7 @@ #include #include "pci_bus.h" +#include "pci_iov.h" /* list of all detected zpci devices */ static LIST_HEAD(zpci_list); @@ -413,15 +414,6 @@ static struct pci_ops pci_root_ops = { .write = pci_write, }; -#ifdef CONFIG_PCI_IOV -static struct resource iov_res = { - .name = "PCI IOV res", - .start = 0, - .end = -1, - .flags = IORESOURCE_MEM, -}; -#endif - static void zpci_map_resources(struct pci_dev *pdev) { struct zpci_dev *zdev = to_zpci(pdev); @@ -442,16 +434,7 @@ static void zpci_map_resources(struct pci_dev *pdev) pdev->resource[i].end = pdev->resource[i].start + len - 1; } -#ifdef CONFIG_PCI_IOV - for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { - int bar = i + PCI_IOV_RESOURCES; - - len = pci_resource_len(pdev, bar); - if (!len) - continue; - pdev->resource[bar].parent = &iov_res; - } -#endif + zpci_iov_map_resources(pdev); } static void zpci_unmap_resources(struct pci_dev *pdev) @@ -703,7 +686,7 @@ void zpci_remove_device(struct zpci_dev *zdev) pdev = pci_get_slot(zbus->bus, zdev->devfn); if (pdev) { if (pdev->is_virtfn) - return zpci_remove_virtfn(pdev, zdev->vfn); + return zpci_iov_remove_virtfn(pdev, zdev->vfn); pci_stop_and_remove_bus_device_locked(pdev); } } diff --git a/arch/s390/pci/pci_bus.c b/arch/s390/pci/pci_bus.c index 5967f3014156..0c0db7c3a404 100644 --- a/arch/s390/pci/pci_bus.c +++ b/arch/s390/pci/pci_bus.c @@ -24,6 +24,7 @@ #include #include "pci_bus.h" +#include "pci_iov.h" static LIST_HEAD(zbus_list); static DEFINE_SPINLOCK(zbus_list_lock); @@ -126,69 +127,6 @@ static struct zpci_bus *zpci_bus_alloc(int pchid) return zbus; } -#ifdef CONFIG_PCI_IOV -static int zpci_bus_link_virtfn(struct pci_dev *pdev, - struct pci_dev *virtfn, int vfid) -{ - int rc; - - rc = pci_iov_sysfs_link(pdev, virtfn, vfid); - if (rc) - return rc; - - virtfn->is_virtfn = 1; - virtfn->multifunction = 0; - virtfn->physfn = pci_dev_get(pdev); - - return 0; -} - -static int zpci_bus_setup_virtfn(struct zpci_bus *zbus, - struct pci_dev *virtfn, int vfn) -{ - int i, cand_devfn; - struct zpci_dev *zdev; - struct pci_dev *pdev; - int vfid = vfn - 1; /* Linux' vfid's start at 0 vfn at 1*/ - int rc = 0; - - if (!zbus->multifunction) - return 0; - - /* If the parent PF for the given VF is also configured in the - * instance, it must be on the same zbus. - * We can then identify the parent PF by checking what - * devfn the VF would have if it belonged to that PF using the PF's - * stride and offset. Only if this candidate devfn matches the - * actual devfn will we link both functions. - */ - for (i = 0; i < ZPCI_FUNCTIONS_PER_BUS; i++) { - zdev = zbus->function[i]; - if (zdev && zdev->is_physfn) { - pdev = pci_get_slot(zbus->bus, zdev->devfn); - if (!pdev) - continue; - cand_devfn = pci_iov_virtfn_devfn(pdev, vfid); - if (cand_devfn == virtfn->devfn) { - rc = zpci_bus_link_virtfn(pdev, virtfn, vfid); - /* balance pci_get_slot() */ - pci_dev_put(pdev); - break; - } - /* balance pci_get_slot() */ - pci_dev_put(pdev); - } - } - return rc; -} -#else -static inline int zpci_bus_setup_virtfn(struct zpci_bus *zbus, - struct pci_dev *virtfn, int vfn) -{ - return 0; -} -#endif - void pcibios_bus_add_device(struct pci_dev *pdev) { struct zpci_dev *zdev = to_zpci(pdev); @@ -198,7 +136,7 @@ void pcibios_bus_add_device(struct pci_dev *pdev) * perform PF/VF linking. */ if (zdev->vfn) - zpci_bus_setup_virtfn(zdev->zbus, pdev, zdev->vfn); + zpci_iov_setup_virtfn(zdev->zbus, pdev, zdev->vfn); } diff --git a/arch/s390/pci/pci_bus.h b/arch/s390/pci/pci_bus.h index 4972433df458..8d19723ed5c0 100644 --- a/arch/s390/pci/pci_bus.h +++ b/arch/s390/pci/pci_bus.h @@ -30,15 +30,3 @@ static inline struct zpci_dev *get_zdev_by_bus(struct pci_bus *bus, return (devfn >= ZPCI_FUNCTIONS_PER_BUS) ? NULL : zbus->function[devfn]; } -#ifdef CONFIG_PCI_IOV -static inline void zpci_remove_virtfn(struct pci_dev *pdev, int vfn) -{ - - pci_lock_rescan_remove(); - /* Linux' vfid's start at 0 vfn at 1 */ - pci_iov_remove_virtfn(pdev->physfn, vfn - 1); - pci_unlock_rescan_remove(); -} -#else /* CONFIG_PCI_IOV */ -static inline void zpci_remove_virtfn(struct pci_dev *pdev, int vfn) {} -#endif /* CONFIG_PCI_IOV */ diff --git a/arch/s390/pci/pci_iov.c b/arch/s390/pci/pci_iov.c new file mode 100644 index 000000000000..35fca14ebb35 --- /dev/null +++ b/arch/s390/pci/pci_iov.c @@ -0,0 +1,97 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright IBM Corp. 2020 + * + * Author(s): + * Niklas Schnelle + * + */ + +#define KMSG_COMPONENT "zpci" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + +#include +#include + +static struct resource iov_res = { + .name = "PCI IOV res", + .start = 0, + .end = -1, + .flags = IORESOURCE_MEM, +}; + +void zpci_iov_map_resources(struct pci_dev *pdev) +{ + resource_size_t len; + int i; + + for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { + int bar = i + PCI_IOV_RESOURCES; + + len = pci_resource_len(pdev, bar); + if (!len) + continue; + pdev->resource[bar].parent = &iov_res; + } +} + +void zpci_iov_remove_virtfn(struct pci_dev *pdev, int vfn) +{ + pci_lock_rescan_remove(); + /* Linux' vfid's start at 0 vfn at 1 */ + pci_iov_remove_virtfn(pdev->physfn, vfn - 1); + pci_unlock_rescan_remove(); +} + +static int zpci_iov_link_virtfn(struct pci_dev *pdev, struct pci_dev *virtfn, int vfid) +{ + int rc; + + rc = pci_iov_sysfs_link(pdev, virtfn, vfid); + if (rc) + return rc; + + virtfn->is_virtfn = 1; + virtfn->multifunction = 0; + virtfn->physfn = pci_dev_get(pdev); + + return 0; +} + +int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn) +{ + int i, cand_devfn; + struct zpci_dev *zdev; + struct pci_dev *pdev; + int vfid = vfn - 1; /* Linux' vfid's start at 0 vfn at 1*/ + int rc = 0; + + if (!zbus->multifunction) + return 0; + + /* If the parent PF for the given VF is also configured in the + * instance, it must be on the same zbus. + * We can then identify the parent PF by checking what + * devfn the VF would have if it belonged to that PF using the PF's + * stride and offset. Only if this candidate devfn matches the + * actual devfn will we link both functions. + */ + for (i = 0; i < ZPCI_FUNCTIONS_PER_BUS; i++) { + zdev = zbus->function[i]; + if (zdev && zdev->is_physfn) { + pdev = pci_get_slot(zbus->bus, zdev->devfn); + if (!pdev) + continue; + cand_devfn = pci_iov_virtfn_devfn(pdev, vfid); + if (cand_devfn == virtfn->devfn) { + rc = zpci_iov_link_virtfn(pdev, virtfn, vfid); + /* balance pci_get_slot() */ + pci_dev_put(pdev); + break; + } + /* balance pci_get_slot() */ + pci_dev_put(pdev); + } + } + return rc; +} diff --git a/arch/s390/pci/pci_iov.h b/arch/s390/pci/pci_iov.h new file mode 100644 index 000000000000..b2c828003bad --- /dev/null +++ b/arch/s390/pci/pci_iov.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright IBM Corp. 2020 + * + * Author(s): + * Niklas Schnelle + * + */ + +#ifndef __S390_PCI_IOV_H +#define __S390_PCI_IOV_H + +#ifdef CONFIG_PCI_IOV +void zpci_iov_remove_virtfn(struct pci_dev *pdev, int vfn); + +void zpci_iov_map_resources(struct pci_dev *pdev); + +int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn); + +#else /* CONFIG_PCI_IOV */ +static inline void zpci_iov_remove_virtfn(struct pci_dev *pdev, int vfn) {} + +static inline void zpci_iov_map_resources(struct pci_dev *pdev) {} + +static inline int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn) +{ + return 0; +} +#endif /* CONFIG_PCI_IOV */ +#endif /* __S390_PCI_IOV_h */ From 2bce60b5032fe3ca225a36b80f6df90938f0ead6 Mon Sep 17 00:00:00 2001 From: Niklas Schnelle Date: Fri, 21 Aug 2020 10:26:40 +0200 Subject: [PATCH 129/645] s390/pci: remove unused function zpci_rescan() the only caller of this was removed as part of the suspend/resume removal so no need to keep this function around. Reviewed-by: Matthew Rosato Signed-off-by: Niklas Schnelle Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/pci.h | 2 -- arch/s390/pci/pci.c | 6 ------ 2 files changed, 8 deletions(-) diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index 8015b9301533..140cb6bc8e1c 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -233,12 +233,10 @@ static inline bool zpci_use_mio(struct zpci_dev *zdev) /* Error handling and recovery */ void zpci_event_error(void *); void zpci_event_availability(void *); -void zpci_rescan(void); bool zpci_is_enabled(void); #else /* CONFIG_PCI */ static inline void zpci_event_error(void *e) {} static inline void zpci_event_availability(void *e) {} -static inline void zpci_rescan(void) {} #endif /* CONFIG_PCI */ #ifdef CONFIG_HOTPLUG_PCI_S390 diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index e432318f6937..0ff48c51cd0e 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -890,9 +890,3 @@ out: return rc; } subsys_initcall_sync(pci_base_init); - -void zpci_rescan(void) -{ - if (zpci_is_enabled()) - clp_rescan_pci_devices_simple(NULL); -} From 809fcfaf9238052f03e8002f6dad156a7fb6cd5e Mon Sep 17 00:00:00 2001 From: Niklas Schnelle Date: Fri, 21 Aug 2020 11:01:54 +0200 Subject: [PATCH 130/645] s390/pci: remove clp_rescan_pci_devices() there is only one call site of clp_rescan_pci_devices() and all the function does is call zpci_remove_reserved_devices() followed by a duplicating clp_scan_pci_devices(). So inline the single call as a call to zpci_remove_reserved_devices() and clp_scan_pci_devices() and remove the function. Reviewed-by: Matthew Rosato Signed-off-by: Niklas Schnelle Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/pci.h | 1 - arch/s390/pci/pci_clp.c | 17 ----------------- arch/s390/pci/pci_event.c | 3 ++- 3 files changed, 2 insertions(+), 19 deletions(-) diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index 140cb6bc8e1c..430f694163c1 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -210,7 +210,6 @@ void zpci_remove_reserved_devices(void); /* CLP */ int clp_setup_writeback_mio(void); int clp_scan_pci_devices(void); -int clp_rescan_pci_devices(void); int clp_rescan_pci_devices_simple(u32 *fid); int clp_add_pci_device(u32, u32, int); int clp_enable_fh(struct zpci_dev *, u8); diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c index 51807945ca00..6aabfb131c1e 100644 --- a/arch/s390/pci/pci_clp.c +++ b/arch/s390/pci/pci_clp.c @@ -441,23 +441,6 @@ int clp_scan_pci_devices(void) return rc; } -int clp_rescan_pci_devices(void) -{ - struct clp_req_rsp_list_pci *rrb; - int rc; - - zpci_remove_reserved_devices(); - - rrb = clp_alloc_block(GFP_KERNEL); - if (!rrb) - return -ENOMEM; - - rc = clp_list_pci(rrb, NULL, __clp_add); - - clp_free_block(rrb); - return rc; -} - /* Rescan PCI functions and refresh function handles. If fid is non-NULL only * refresh the handle of the function matching @fid */ diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index 9a3a291cad43..e67cc2f6e169 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -150,7 +150,8 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) } break; case 0x0306: /* 0x308 or 0x302 for multiple devices */ - clp_rescan_pci_devices(); + zpci_remove_reserved_devices(); + clp_scan_pci_devices(); break; case 0x0308: /* Standby -> Reserved */ if (!zdev) From c3b2c9064e76fa3952c99982f11a98e0327f3dbe Mon Sep 17 00:00:00 2001 From: Niklas Schnelle Date: Fri, 21 Aug 2020 11:16:48 +0200 Subject: [PATCH 131/645] s390/pci: remove clp_rescan_pci_devices_simple() clp_rescan_pci_devices_simple() is neither simpler than clp_scan_pci_devices() nor does it really scan PCI devices, in particular it will neither add newly discovered devices nor remove those which disappeared. Instead it only refreshes PCI function handles and also has just a single callsite in the same translation unit left which in fact only refreshes one specific function handle identified by a FID. Clarify this by renaming the function and its helper to clp_refresh_fh() respectvely __clp_refresh_fh() and make it take a fid directly which saves us dealing with the NULL case which updated all function handles but is not used anymore. Furthermore since the only callsite is in the same translation unit make it static. Reviewed-by: Matthew Rosato Signed-off-by: Niklas Schnelle Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/pci.h | 1 - arch/s390/pci/pci_clp.c | 44 ++++++++++++++++++------------------- 2 files changed, 21 insertions(+), 24 deletions(-) diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index 430f694163c1..178a24e0af5f 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -210,7 +210,6 @@ void zpci_remove_reserved_devices(void); /* CLP */ int clp_setup_writeback_mio(void); int clp_scan_pci_devices(void); -int clp_rescan_pci_devices_simple(u32 *fid); int clp_add_pci_device(u32, u32, int); int clp_enable_fh(struct zpci_dev *, u8); int clp_disable_fh(struct zpci_dev *); diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c index 6aabfb131c1e..5a34a1359dc5 100644 --- a/arch/s390/pci/pci_clp.c +++ b/arch/s390/pci/pci_clp.c @@ -244,6 +244,7 @@ error: return rc; } +static int clp_refresh_fh(u32 fid); /* * Enable/Disable a given PCI function and update its function handle if * necessary @@ -286,7 +287,7 @@ static int clp_set_pci_fn(struct zpci_dev *zdev, u8 nr_dma_as, u8 command) } else if (!rc && rrb->response.hdr.rsp == CLP_RC_SETPCIFN_ALRDY && rrb->response.fh == 0) { /* Function is already in desired state - update handle */ - rc = clp_rescan_pci_devices_simple(&fid); + rc = clp_refresh_fh(fid); } clp_free_block(rrb); return rc; @@ -408,24 +409,6 @@ static void __clp_add(struct clp_fh_list_entry *entry, void *data) clp_add_pci_device(entry->fid, entry->fh, entry->config_state); } -static void __clp_update(struct clp_fh_list_entry *entry, void *data) -{ - struct zpci_dev *zdev; - u32 *fid = data; - - if (!entry->vendor_id) - return; - - if (fid && *fid != entry->fid) - return; - - zdev = get_zdev_by_fid(entry->fid); - if (!zdev) - return; - - zdev->fh = entry->fh; -} - int clp_scan_pci_devices(void) { struct clp_req_rsp_list_pci *rrb; @@ -441,10 +424,25 @@ int clp_scan_pci_devices(void) return rc; } -/* Rescan PCI functions and refresh function handles. If fid is non-NULL only - * refresh the handle of the function matching @fid +static void __clp_refresh_fh(struct clp_fh_list_entry *entry, void *data) +{ + struct zpci_dev *zdev; + u32 fid = *((u32 *)data); + + if (!entry->vendor_id || fid != entry->fid) + return; + + zdev = get_zdev_by_fid(fid); + if (!zdev) + return; + + zdev->fh = entry->fh; +} + +/* + * Refresh the function handle of the function matching @fid */ -int clp_rescan_pci_devices_simple(u32 *fid) +static int clp_refresh_fh(u32 fid) { struct clp_req_rsp_list_pci *rrb; int rc; @@ -453,7 +451,7 @@ int clp_rescan_pci_devices_simple(u32 *fid) if (!rrb) return -ENOMEM; - rc = clp_list_pci(rrb, fid, __clp_update); + rc = clp_list_pci(rrb, &fid, __clp_refresh_fh); clp_free_block(rrb); return rc; From 6c6687a444cfa62548e080a52e6c2d5d41577a73 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Thu, 10 Sep 2020 16:48:35 +0200 Subject: [PATCH 132/645] s390/kprobes: make insn pages read-only Make sure that kprobe insn pages are not writable anymore. Tested-by: Vasily Gorbik Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/kprobes.c | 57 ++++++++++++++++++++++++++------------ 1 file changed, 39 insertions(+), 18 deletions(-) diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index d2a71d872638..b34fa4eef742 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -7,6 +7,7 @@ * s390 port, used ppc64 as template. Mike Grundy */ +#include #include #include #include @@ -32,17 +33,33 @@ DEFINE_INSN_CACHE_OPS(s390_insn); static int insn_page_in_use; static char insn_page[PAGE_SIZE] __aligned(PAGE_SIZE); +void *alloc_insn_page(void) +{ + void *page; + + page = module_alloc(PAGE_SIZE); + if (!page) + return NULL; + __set_memory((unsigned long) page, 1, SET_MEMORY_RO | SET_MEMORY_X); + return page; +} + +void free_insn_page(void *page) +{ + module_memfree(page); +} + static void *alloc_s390_insn_page(void) { if (xchg(&insn_page_in_use, 1) == 1) return NULL; - set_memory_x((unsigned long) &insn_page, 1); + __set_memory((unsigned long) &insn_page, 1, SET_MEMORY_RO | SET_MEMORY_X); return &insn_page; } static void free_s390_insn_page(void *page) { - set_memory_nx((unsigned long) page, 1); + __set_memory((unsigned long) page, 1, SET_MEMORY_RW | SET_MEMORY_NX); xchg(&insn_page_in_use, 0); } @@ -56,25 +73,29 @@ struct kprobe_insn_cache kprobe_s390_insn_slots = { static void copy_instruction(struct kprobe *p) { + kprobe_opcode_t insn[MAX_INSN_SIZE]; s64 disp, new_disp; u64 addr, new_addr; + unsigned int len; - memcpy(p->ainsn.insn, p->addr, insn_length(*p->addr >> 8)); - p->opcode = p->ainsn.insn[0]; - if (!probe_is_insn_relative_long(p->ainsn.insn)) - return; - /* - * For pc-relative instructions in RIL-b or RIL-c format patch the - * RI2 displacement field. We have already made sure that the insn - * slot for the patched instruction is within the same 2GB area - * as the original instruction (either kernel image or module area). - * Therefore the new displacement will always fit. - */ - disp = *(s32 *)&p->ainsn.insn[1]; - addr = (u64)(unsigned long)p->addr; - new_addr = (u64)(unsigned long)p->ainsn.insn; - new_disp = ((addr + (disp * 2)) - new_addr) / 2; - *(s32 *)&p->ainsn.insn[1] = new_disp; + len = insn_length(*p->addr >> 8); + memcpy(&insn, p->addr, len); + p->opcode = insn[0]; + if (probe_is_insn_relative_long(&insn[0])) { + /* + * For pc-relative instructions in RIL-b or RIL-c format patch + * the RI2 displacement field. We have already made sure that + * the insn slot for the patched instruction is within the same + * 2GB area as the original instruction (either kernel image or + * module area). Therefore the new displacement will always fit. + */ + disp = *(s32 *)&insn[1]; + addr = (u64)(unsigned long)p->addr; + new_addr = (u64)(unsigned long)p->ainsn.insn; + new_disp = ((addr + (disp * 2)) - new_addr) / 2; + *(s32 *)&insn[1] = new_disp; + } + s390_kernel_write(p->ainsn.insn, &insn, len); } NOKPROBE_SYMBOL(copy_instruction); From 6bf9a639e76e1da8eb1ed29e037e900106e1dff4 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Wed, 9 Sep 2020 11:14:52 +0200 Subject: [PATCH 133/645] s390/mm,ptdump: make page table dumping seq_file optional s390 version of ae5d1cf358a5 ("arm64: dump: Make the page table dumping seq_file optional"). Tested-by: Vasily Gorbik Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/mm/dump_pagetables.c | 36 ++++++++++++++++++++++++---------- 1 file changed, 26 insertions(+), 10 deletions(-) diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c index 09c7179cb17d..b7401a2f93f3 100644 --- a/arch/s390/mm/dump_pagetables.c +++ b/arch/s390/mm/dump_pagetables.c @@ -51,18 +51,34 @@ struct pg_state { const struct addr_marker *marker; }; +#define pt_dump_seq_printf(m, fmt, args...) \ +({ \ + struct seq_file *__m = (m); \ + \ + if (__m) \ + seq_printf(__m, fmt, ##args); \ +}) + +#define pt_dump_seq_puts(m, fmt) \ +({ \ + struct seq_file *__m = (m); \ + \ + if (__m) \ + seq_printf(__m, fmt); \ +}) + static void print_prot(struct seq_file *m, unsigned int pr, int level) { static const char * const level_name[] = { "ASCE", "PGD", "PUD", "PMD", "PTE" }; - seq_printf(m, "%s ", level_name[level]); + pt_dump_seq_printf(m, "%s ", level_name[level]); if (pr & _PAGE_INVALID) { - seq_printf(m, "I\n"); + pt_dump_seq_printf(m, "I\n"); return; } - seq_puts(m, (pr & _PAGE_PROTECT) ? "RO " : "RW "); - seq_puts(m, (pr & _PAGE_NOEXEC) ? "NX\n" : "X\n"); + pt_dump_seq_puts(m, (pr & _PAGE_PROTECT) ? "RO " : "RW "); + pt_dump_seq_puts(m, (pr & _PAGE_NOEXEC) ? "NX\n" : "X\n"); } static void note_page(struct ptdump_state *pt_st, unsigned long addr, int level, u64 val) @@ -87,25 +103,25 @@ static void note_page(struct ptdump_state *pt_st, unsigned long addr, int level, if (level == -1) addr = max_addr; if (st->level == -1) { - seq_printf(m, "---[ %s ]---\n", st->marker->name); + pt_dump_seq_printf(m, "---[ %s ]---\n", st->marker->name); st->start_address = addr; st->current_prot = prot; st->level = level; } else if (prot != st->current_prot || level != st->level || addr >= st->marker[1].start_address) { - seq_printf(m, "0x%0*lx-0x%0*lx ", - width, st->start_address, - width, addr); + pt_dump_seq_printf(m, "0x%0*lx-0x%0*lx ", + width, st->start_address, + width, addr); delta = (addr - st->start_address) >> 10; while (!(delta & 0x3ff) && unit[1]) { delta >>= 10; unit++; } - seq_printf(m, "%9lu%c ", delta, *unit); + pt_dump_seq_printf(m, "%9lu%c ", delta, *unit); print_prot(m, st->current_prot, st->level); while (addr >= st->marker[1].start_address) { st->marker++; - seq_printf(m, "---[ %s ]---\n", st->marker->name); + pt_dump_seq_printf(m, "---[ %s ]---\n", st->marker->name); } st->start_address = addr; st->current_prot = prot; From 08c8e685c7c9223f9c4ad6365e02bebd3f106480 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Wed, 9 Sep 2020 17:10:29 +0200 Subject: [PATCH 134/645] s390: add ARCH_HAS_DEBUG_WX support Checks the whole kernel address space for W+X mappings. Note that currently the first lowcore page unfortunately has to be mapped W+X. Therefore this not reported as an insecure mapping. For the very same reason the wording is also different to other architectures if the test passes: On s390 it is "no unexpected W+X pages found" instead of "no W+X pages found". Tested-by: Vasily Gorbik Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/Kconfig | 1 + arch/s390/configs/debug_defconfig | 1 + arch/s390/configs/defconfig | 1 + arch/s390/include/asm/ptdump.h | 14 +++++++ arch/s390/mm/Makefile | 2 +- arch/s390/mm/dump_pagetables.c | 64 ++++++++++++++++++++++++++++++- arch/s390/mm/init.c | 2 + 7 files changed, 83 insertions(+), 2 deletions(-) create mode 100644 arch/s390/include/asm/ptdump.h diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 85bf121211d1..2052b39b8459 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -60,6 +60,7 @@ config S390 def_bool y select ARCH_BINFMT_ELF_STATE select ARCH_HAS_DEBUG_VM_PGTABLE + select ARCH_HAS_DEBUG_WX select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FORTIFY_SOURCE diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index f79eafb597cb..901723e4ed63 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -774,6 +774,7 @@ CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_PAGEALLOC=y CONFIG_PAGE_OWNER=y CONFIG_DEBUG_RODATA_TEST=y +CONFIG_DEBUG_WX=y CONFIG_PTDUMP_DEBUGFS=y CONFIG_DEBUG_OBJECTS=y CONFIG_DEBUG_OBJECTS_SELFTEST=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 9593cc8a9efd..87da48c85130 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -758,6 +758,7 @@ CONFIG_GDB_SCRIPTS=y CONFIG_FRAME_WARN=1024 CONFIG_DEBUG_SECTION_MISMATCH=y CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_WX=y CONFIG_PTDUMP_DEBUGFS=y CONFIG_DEBUG_MEMORY_INIT=y CONFIG_PANIC_ON_OOPS=y diff --git a/arch/s390/include/asm/ptdump.h b/arch/s390/include/asm/ptdump.h new file mode 100644 index 000000000000..f960b2896606 --- /dev/null +++ b/arch/s390/include/asm/ptdump.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _ASM_S390_PTDUMP_H +#define _ASM_S390_PTDUMP_H + +void ptdump_check_wx(void); + +static inline void debug_checkwx(void) +{ + if (IS_ENABLED(CONFIG_DEBUG_WX)) + ptdump_check_wx(); +} + +#endif /* _ASM_S390_PTDUMP_H */ diff --git a/arch/s390/mm/Makefile b/arch/s390/mm/Makefile index 8ab9daeeace3..cd67e94c16aa 100644 --- a/arch/s390/mm/Makefile +++ b/arch/s390/mm/Makefile @@ -8,7 +8,7 @@ obj-y += page-states.o pageattr.o pgtable.o pgalloc.o obj-$(CONFIG_CMM) += cmm.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o -obj-$(CONFIG_PTDUMP_DEBUGFS) += dump_pagetables.o +obj-$(CONFIG_PTDUMP_CORE) += dump_pagetables.o obj-$(CONFIG_PGSTE) += gmap.o KASAN_SANITIZE_kasan_init.o := n diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c index b7401a2f93f3..4b27c1a533de 100644 --- a/arch/s390/mm/dump_pagetables.c +++ b/arch/s390/mm/dump_pagetables.c @@ -5,6 +5,7 @@ #include #include #include +#include #include #include @@ -47,6 +48,8 @@ struct pg_state { struct seq_file *seq; int level; unsigned int current_prot; + bool check_wx; + unsigned long wx_pages; unsigned long start_address; const struct addr_marker *marker; }; @@ -81,6 +84,26 @@ static void print_prot(struct seq_file *m, unsigned int pr, int level) pt_dump_seq_puts(m, (pr & _PAGE_NOEXEC) ? "NX\n" : "X\n"); } +static void note_prot_wx(struct pg_state *st, unsigned long addr) +{ +#ifdef CONFIG_DEBUG_WX + if (!st->check_wx) + return; + if (st->current_prot & _PAGE_INVALID) + return; + if (st->current_prot & _PAGE_PROTECT) + return; + if (st->current_prot & _PAGE_NOEXEC) + return; + /* The first lowcore page is currently still W+X. */ + if (addr == PAGE_SIZE) + return; + WARN_ONCE(1, "s390/mm: Found insecure W+X mapping at address %pS\n", + (void *)st->start_address); + st->wx_pages += (addr - st->start_address) / PAGE_SIZE; +#endif /* CONFIG_DEBUG_WX */ +} + static void note_page(struct ptdump_state *pt_st, unsigned long addr, int level, u64 val) { int width = sizeof(unsigned long) * 2; @@ -109,6 +132,7 @@ static void note_page(struct ptdump_state *pt_st, unsigned long addr, int level, st->level = level; } else if (prot != st->current_prot || level != st->level || addr >= st->marker[1].start_address) { + note_prot_wx(st, addr); pt_dump_seq_printf(m, "0x%0*lx-0x%0*lx ", width, st->start_address, width, addr); @@ -129,6 +153,40 @@ static void note_page(struct ptdump_state *pt_st, unsigned long addr, int level, } } +#ifdef CONFIG_DEBUG_WX +void ptdump_check_wx(void) +{ + struct pg_state st = { + .ptdump = { + .note_page = note_page, + .range = (struct ptdump_range[]) { + {.start = 0, .end = max_addr}, + {.start = 0, .end = 0}, + } + }, + .seq = NULL, + .level = -1, + .current_prot = 0, + .check_wx = true, + .wx_pages = 0, + .start_address = 0, + .marker = (struct addr_marker[]) { + { .start_address = 0, .name = NULL}, + { .start_address = -1, .name = NULL}, + }, + }; + + if (!MACHINE_HAS_NX) + return; + ptdump_walk_pgd(&st.ptdump, &init_mm, NULL); + if (st.wx_pages) + pr_warn("Checked W+X mappings: FAILED, %lu W+X pages found\n", st.wx_pages); + else + pr_info("Checked W+X mappings: passed, no unexpected W+X pages found\n"); +} +#endif /* CONFIG_DEBUG_WX */ + +#ifdef CONFIG_PTDUMP_DEBUGFS static int ptdump_show(struct seq_file *m, void *v) { struct pg_state st = { @@ -142,6 +200,8 @@ static int ptdump_show(struct seq_file *m, void *v) .seq = m, .level = -1, .current_prot = 0, + .check_wx = false, + .wx_pages = 0, .start_address = 0, .marker = address_markers, }; @@ -154,6 +214,7 @@ static int ptdump_show(struct seq_file *m, void *v) return 0; } DEFINE_SHOW_ATTRIBUTE(ptdump); +#endif /* CONFIG_PTDUMP_DEBUGFS */ static int pt_dump_init(void) { @@ -167,7 +228,8 @@ static int pt_dump_init(void) address_markers[MODULES_NR].start_address = MODULES_VADDR; address_markers[VMEMMAP_NR].start_address = (unsigned long) vmemmap; address_markers[VMALLOC_NR].start_address = VMALLOC_START; - debugfs_create_file("kernel_page_tables", 0400, NULL, NULL, &ptdump_fops); + if (IS_ENABLED(CONFIG_PTDUMP_DEBUGFS)) + debugfs_create_file("kernel_page_tables", 0400, NULL, NULL, &ptdump_fops); return 0; } device_initcall(pt_dump_init); diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index 0d282081dc1f..d3ddb4361361 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -34,6 +34,7 @@ #include #include #include +#include #include #include #include @@ -129,6 +130,7 @@ void mark_rodata_ro(void) set_memory_ro((unsigned long)__start_ro_after_init, size >> PAGE_SHIFT); pr_info("Write protected read-only-after-init data: %luk\n", size >> 10); + debug_checkwx(); } int set_memory_encrypted(unsigned long addr, int numpages) From d411e3c6744925f08a2c8682559ce77090144fa2 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Thu, 10 Sep 2020 22:25:13 +0200 Subject: [PATCH 135/645] s390/kasan: make shadow memory noexec ARCH_HAS_DEBUG_WX feature support brought attention to the fact that currently initial kasan shadow memory mapped without noexec flag. So fix that. Temporary initial identity mapping is still created without noexec, but it is replaced by properly set up paging later. Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/mm/kasan_init.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/arch/s390/mm/kasan_init.c b/arch/s390/mm/kasan_init.c index 99dd1c63a065..1a27a7143349 100644 --- a/arch/s390/mm/kasan_init.c +++ b/arch/s390/mm/kasan_init.c @@ -99,8 +99,12 @@ static void __init kasan_early_vmemmap_populate(unsigned long address, pgt_prot_zero = pgprot_val(PAGE_KERNEL_RO); if (!has_nx) pgt_prot_zero &= ~_PAGE_NOEXEC; - pgt_prot = pgprot_val(PAGE_KERNEL_EXEC); - sgt_prot = pgprot_val(SEGMENT_KERNEL_EXEC); + pgt_prot = pgprot_val(PAGE_KERNEL); + sgt_prot = pgprot_val(SEGMENT_KERNEL); + if (!has_nx || mode == POPULATE_ONE2ONE) { + pgt_prot &= ~_PAGE_NOEXEC; + sgt_prot &= ~_SEGMENT_ENTRY_NOEXEC; + } while (address < end) { pg_dir = pgd_offset_k(address); From e670e64af1d46571be3d9b1177024d9c8520087c Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Fri, 11 Sep 2020 12:51:59 +0200 Subject: [PATCH 136/645] s390/mm,ptdump: add couple of additional markers Signed-off-by: Vasily Gorbik [hca@linux.ibm.com: add more markers, rename some markers] Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/pgtable.h | 1 + arch/s390/kernel/setup.c | 2 ++ arch/s390/mm/dump_pagetables.c | 26 +++++++++++++++++++++----- 3 files changed, 24 insertions(+), 5 deletions(-) diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index e9244b9fb504..d87b83a77aff 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -89,6 +89,7 @@ extern unsigned long VMALLOC_START; extern unsigned long VMALLOC_END; #define VMALLOC_DEFAULT_SIZE ((128UL << 30) - MODULES_LEN) extern struct page *vmemmap; +extern unsigned long vmemmap_size; #define VMEM_MAX_PHYS ((unsigned long) vmemmap) diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index efd12221ecb4..f04252cb6004 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -119,6 +119,7 @@ EXPORT_SYMBOL(VMALLOC_END); struct page *vmemmap; EXPORT_SYMBOL(vmemmap); +unsigned long vmemmap_size; unsigned long MODULES_VADDR; unsigned long MODULES_END; @@ -589,6 +590,7 @@ static void __init setup_memory_end(void) memory_end = min(memory_end, KASAN_SHADOW_START); vmemmap = max(vmemmap, (struct page *)KASAN_SHADOW_END); #endif + vmemmap_size = SECTION_ALIGN_UP(memory_end / PAGE_SIZE) * sizeof(struct page); max_pfn = max_low_pfn = PFN_DOWN(memory_end); memblock_remove(memory_end, ULONG_MAX); diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c index 4b27c1a533de..052223c92fb1 100644 --- a/arch/s390/mm/dump_pagetables.c +++ b/arch/s390/mm/dump_pagetables.c @@ -17,29 +17,41 @@ struct addr_marker { }; enum address_markers_idx { - IDENTITY_NR = 0, + IDENTITY_BEFORE_NR = 0, + IDENTITY_BEFORE_END_NR, KERNEL_START_NR, KERNEL_END_NR, + IDENTITY_AFTER_NR, + IDENTITY_AFTER_END_NR, #ifdef CONFIG_KASAN KASAN_SHADOW_START_NR, KASAN_SHADOW_END_NR, #endif VMEMMAP_NR, + VMEMMAP_END_NR, VMALLOC_NR, + VMALLOC_END_NR, MODULES_NR, + MODULES_END_NR, }; static struct addr_marker address_markers[] = { - [IDENTITY_NR] = {0, "Identity Mapping"}, + [IDENTITY_BEFORE_NR] = {0, "Identity Mapping Start"}, + [IDENTITY_BEFORE_END_NR] = {(unsigned long)_stext, "Identity Mapping End"}, [KERNEL_START_NR] = {(unsigned long)_stext, "Kernel Image Start"}, [KERNEL_END_NR] = {(unsigned long)_end, "Kernel Image End"}, + [IDENTITY_AFTER_NR] = {(unsigned long)_end, "Identity Mapping Start"}, + [IDENTITY_AFTER_END_NR] = {0, "Identity Mapping End"}, #ifdef CONFIG_KASAN [KASAN_SHADOW_START_NR] = {KASAN_SHADOW_START, "Kasan Shadow Start"}, [KASAN_SHADOW_END_NR] = {KASAN_SHADOW_END, "Kasan Shadow End"}, #endif - [VMEMMAP_NR] = {0, "vmemmap Area"}, - [VMALLOC_NR] = {0, "vmalloc Area"}, - [MODULES_NR] = {0, "Modules Area"}, + [VMEMMAP_NR] = {0, "vmemmap Area Start"}, + [VMEMMAP_END_NR] = {0, "vmemmap Area End"}, + [VMALLOC_NR] = {0, "vmalloc Area Start"}, + [VMALLOC_END_NR] = {0, "vmalloc Area End"}, + [MODULES_NR] = {0, "Modules Area Start"}, + [MODULES_END_NR] = {0, "Modules Area End"}, { -1, NULL } }; @@ -225,9 +237,13 @@ static int pt_dump_init(void) */ max_addr = (S390_lowcore.kernel_asce & _REGION_ENTRY_TYPE_MASK) >> 2; max_addr = 1UL << (max_addr * 11 + 31); + address_markers[IDENTITY_AFTER_END_NR].start_address = memory_end; address_markers[MODULES_NR].start_address = MODULES_VADDR; + address_markers[MODULES_END_NR].start_address = MODULES_END; address_markers[VMEMMAP_NR].start_address = (unsigned long) vmemmap; + address_markers[VMEMMAP_END_NR].start_address = (unsigned long)vmemmap + vmemmap_size; address_markers[VMALLOC_NR].start_address = VMALLOC_START; + address_markers[VMALLOC_END_NR].start_address = VMALLOC_END; if (IS_ENABLED(CONFIG_PTDUMP_DEBUGFS)) debugfs_create_file("kernel_page_tables", 0400, NULL, NULL, &ptdump_fops); return 0; From 1a80b54d1ce1556bba6a8d8cd9384d6a9dcb641a Mon Sep 17 00:00:00 2001 From: Janosch Frank Date: Mon, 7 Sep 2020 08:46:59 -0400 Subject: [PATCH 137/645] s390/uv: add destroy page call We don't need to export pages if we destroy the VM configuration afterwards anyway. Instead we can destroy the page which will zero it and then make it accessible to the host. Destroying is about twice as fast as the export. Signed-off-by: Janosch Frank Reviewed-by: Claudio Imbrenda Reviewed-by: Thomas Huth Reviewed-by: Cornelia Huck Link: https://lore.kernel.org/kvm/20200907124700.10374-2-frankja@linux.ibm.com/ Signed-off-by: Janosch Frank Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/uv.h | 7 +++++++ arch/s390/kernel/uv.c | 20 ++++++++++++++++++++ arch/s390/mm/gmap.c | 2 +- 3 files changed, 28 insertions(+), 1 deletion(-) diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h index cff4b4c99b75..0325fc0469b7 100644 --- a/arch/s390/include/asm/uv.h +++ b/arch/s390/include/asm/uv.h @@ -33,6 +33,7 @@ #define UVC_CMD_DESTROY_SEC_CPU 0x0121 #define UVC_CMD_CONV_TO_SEC_STOR 0x0200 #define UVC_CMD_CONV_FROM_SEC_STOR 0x0201 +#define UVC_CMD_DESTR_SEC_STOR 0x0202 #define UVC_CMD_SET_SEC_CONF_PARAMS 0x0300 #define UVC_CMD_UNPACK_IMG 0x0301 #define UVC_CMD_VERIFY_IMG 0x0302 @@ -344,6 +345,7 @@ static inline int is_prot_virt_host(void) } int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb); +int uv_destroy_page(unsigned long paddr); int uv_convert_from_secure(unsigned long paddr); int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr); @@ -354,6 +356,11 @@ void adjust_to_uv_max(unsigned long *vmax); static inline void setup_uv(void) {} static inline void adjust_to_uv_max(unsigned long *vmax) {} +static inline int uv_destroy_page(unsigned long paddr) +{ + return 0; +} + static inline int uv_convert_from_secure(unsigned long paddr) { return 0; diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c index c296e5c8dbf9..d3399b8a9b23 100644 --- a/arch/s390/kernel/uv.c +++ b/arch/s390/kernel/uv.c @@ -118,6 +118,26 @@ static int uv_pin_shared(unsigned long paddr) return 0; } +/* + * Requests the Ultravisor to destroy a guest page and make it + * accessible to the host. The destroy clears the page instead of + * exporting. + * + * @paddr: Absolute host address of page to be destroyed + */ +int uv_destroy_page(unsigned long paddr) +{ + struct uv_cb_cfs uvcb = { + .header.cmd = UVC_CMD_DESTR_SEC_STOR, + .header.len = sizeof(uvcb), + .paddr = paddr + }; + + if (uv_call(0, (u64)&uvcb)) + return -EINVAL; + return 0; +} + /* * Requests the Ultravisor to encrypt a guest page and make it * accessible to the host for paging (export). diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index 373542ca1113..cfb0017f33a7 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -2679,7 +2679,7 @@ static int __s390_reset_acc(pte_t *ptep, unsigned long addr, pte_t pte = READ_ONCE(*ptep); if (pte_present(pte)) - WARN_ON_ONCE(uv_convert_from_secure(pte_val(pte) & PAGE_MASK)); + WARN_ON_ONCE(uv_destroy_page(pte_val(pte) & PAGE_MASK)); return 0; } From 231b232df8f67e7d37af01259c21f2a131c3911e Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Thu, 27 Aug 2020 23:17:13 +1000 Subject: [PATCH 138/645] powerpc/64: Make VDSO32 track COMPAT on 64-bit When we added the VDSO32 kconfig symbol, which controls building of the 32-bit VDSO, we made it depend on CPU_BIG_ENDIAN (for 64-bit). That was because back then COMPAT was always enabled for 64-bit, so depending on it would have left the 32-bit VDSO always enabled, which we didn't want. But since then we have made COMPAT selectable, and off by default for ppc64le, so VDSO32 should really depend on that. For most people this makes no difference, none of the defconfigs change, it's only if someone is building ppc64le with COMPAT=y, they will now also get VDSO32. If they've enabled COMPAT in order to run 32-bit binaries they presumably also want the 32-bit VDSO. Signed-off-by: Michael Ellerman Reviewed-by: Christophe Leroy Link: https://lore.kernel.org/r/20200908125850.407939-1-mpe@ellerman.id.au --- arch/powerpc/platforms/Kconfig.cputype | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 1dc9d3c81872..e74ec220b5d6 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -490,13 +490,12 @@ endmenu config VDSO32 def_bool y - depends on PPC32 || CPU_BIG_ENDIAN + depends on PPC32 || COMPAT help This symbol controls whether we build the 32-bit VDSO. We obviously want to do that if we're building a 32-bit kernel. If we're building - a 64-bit kernel then we only want a 32-bit VDSO if we're building for - big endian. That is because the only little endian configuration we - support is ppc64le which is 64-bit only. + a 64-bit kernel then we only want a 32-bit VDSO if we're also enabling + COMPAT. choice prompt "Endianness selection" From eae9eec476d13fad9af6da1f44a054ee02b7b161 Mon Sep 17 00:00:00 2001 From: Thiago Jung Bauermann Date: Tue, 18 Aug 2020 19:11:26 -0300 Subject: [PATCH 139/645] powerpc/pseries/svm: Allocate SWIOTLB buffer anywhere in memory POWER secure guests (i.e., guests which use the Protected Execution Facility) need to use SWIOTLB to be able to do I/O with the hypervisor, but they don't need the SWIOTLB memory to be in low addresses since the hypervisor doesn't have any addressing limitation. This solves a SWIOTLB initialization problem we are seeing in secure guests with 128 GB of RAM: they are configured with 4 GB of crashkernel reserved memory, which leaves no space for SWIOTLB in low addresses. To do this, we use mostly the same code as swiotlb_init(), but allocate the buffer using memblock_alloc() instead of memblock_alloc_low(). Fixes: 2efbc58f157a ("powerpc/pseries/svm: Force SWIOTLB for secure guests") Signed-off-by: Thiago Jung Bauermann Reviewed-by: Konrad Rzeszutek Wilk Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200818221126.391073-1-bauerman@linux.ibm.com --- arch/powerpc/include/asm/svm.h | 4 ++++ arch/powerpc/mm/mem.c | 6 +++++- arch/powerpc/platforms/pseries/svm.c | 26 ++++++++++++++++++++++++++ 3 files changed, 35 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/include/asm/svm.h b/arch/powerpc/include/asm/svm.h index 85580b30aba4..7546402d796a 100644 --- a/arch/powerpc/include/asm/svm.h +++ b/arch/powerpc/include/asm/svm.h @@ -15,6 +15,8 @@ static inline bool is_secure_guest(void) return mfmsr() & MSR_S; } +void __init svm_swiotlb_init(void); + void dtl_cache_ctor(void *addr); #define get_dtl_cache_ctor() (is_secure_guest() ? dtl_cache_ctor : NULL) @@ -25,6 +27,8 @@ static inline bool is_secure_guest(void) return false; } +static inline void svm_swiotlb_init(void) {} + #define get_dtl_cache_ctor() NULL #endif /* CONFIG_PPC_SVM */ diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 42e25874f5a8..ddc32cc1b6cf 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -49,6 +49,7 @@ #include #include #include +#include #include @@ -282,7 +283,10 @@ void __init mem_init(void) * back to to-down. */ memblock_set_bottom_up(true); - swiotlb_init(0); + if (is_secure_guest()) + svm_swiotlb_init(); + else + swiotlb_init(0); #endif high_memory = (void *) __va(max_low_pfn * PAGE_SIZE); diff --git a/arch/powerpc/platforms/pseries/svm.c b/arch/powerpc/platforms/pseries/svm.c index e6d7a344d9f2..7b739cc7a8a9 100644 --- a/arch/powerpc/platforms/pseries/svm.c +++ b/arch/powerpc/platforms/pseries/svm.c @@ -7,6 +7,7 @@ */ #include +#include #include #include #include @@ -35,6 +36,31 @@ static int __init init_svm(void) } machine_early_initcall(pseries, init_svm); +/* + * Initialize SWIOTLB. Essentially the same as swiotlb_init(), except that it + * can allocate the buffer anywhere in memory. Since the hypervisor doesn't have + * any addressing limitation, we don't need to allocate it in low addresses. + */ +void __init svm_swiotlb_init(void) +{ + unsigned char *vstart; + unsigned long bytes, io_tlb_nslabs; + + io_tlb_nslabs = (swiotlb_size_or_default() >> IO_TLB_SHIFT); + io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE); + + bytes = io_tlb_nslabs << IO_TLB_SHIFT; + + vstart = memblock_alloc(PAGE_ALIGN(bytes), PAGE_SIZE); + if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, false)) + return; + + if (io_tlb_start) + memblock_free_early(io_tlb_start, + PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); + panic("SVM: Cannot allocate SWIOTLB buffer"); +} + int set_memory_encrypted(unsigned long addr, int numpages) { if (!PAGE_ALIGNED(addr)) From 4759c11ed20454b7b36db4ec15f7d5aa1519af4a Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Wed, 2 Sep 2020 09:59:38 +0530 Subject: [PATCH 140/645] powerpc/watchpoint: Fix quadword instruction handling on p10 predecessors On p10 predecessors, watchpoint with quadword access is compared at quadword length. If the watch range is doubleword or less than that in a first half of quadword aligned 16 bytes, and if there is any unaligned quadword access which will access only the 2nd half, the handler should consider it as extraneous and emulate/single-step it before continuing. Fixes: 74c6881019b7 ("powerpc/watchpoint: Prepare handler to handle more than one watchpoint") Reported-by: Pedro Miraglia Franco de Carvalho Signed-off-by: Ravi Bangoria Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200902042945.129369-2-ravi.bangoria@linux.ibm.com --- arch/powerpc/include/asm/hw_breakpoint.h | 1 + arch/powerpc/kernel/hw_breakpoint.c | 12 ++++++++++-- 2 files changed, 11 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h index db206a7f38e2..9b68eafebf43 100644 --- a/arch/powerpc/include/asm/hw_breakpoint.h +++ b/arch/powerpc/include/asm/hw_breakpoint.h @@ -42,6 +42,7 @@ struct arch_hw_breakpoint { #else #define HW_BREAKPOINT_SIZE 0x8 #endif +#define HW_BREAKPOINT_SIZE_QUADWORD 0x10 #define DABR_MAX_LEN 8 #define DAWR_MAX_LEN 512 diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index 1f4a1efa0074..9f7df1c37233 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -520,9 +520,17 @@ static bool ea_hw_range_overlaps(unsigned long ea, int size, struct arch_hw_breakpoint *info) { unsigned long hw_start_addr, hw_end_addr; + unsigned long align_size = HW_BREAKPOINT_SIZE; - hw_start_addr = ALIGN_DOWN(info->address, HW_BREAKPOINT_SIZE); - hw_end_addr = ALIGN(info->address + info->len, HW_BREAKPOINT_SIZE); + /* + * On p10 predecessors, quadword is handle differently then + * other instructions. + */ + if (!cpu_has_feature(CPU_FTR_ARCH_31) && size == 16) + align_size = HW_BREAKPOINT_SIZE_QUADWORD; + + hw_start_addr = ALIGN_DOWN(info->address, align_size); + hw_end_addr = ALIGN(info->address + info->len, align_size); return ((ea < hw_end_addr) && (ea + size > hw_start_addr)); } From 4441eb02333a9b46a0d919aa7a6d3b137b5f2562 Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Wed, 2 Sep 2020 09:59:39 +0530 Subject: [PATCH 141/645] powerpc/watchpoint: Fix handling of vector instructions Vector load/store instructions are special because they are always aligned. Thus unaligned EA needs to be aligned down before comparing it with watch ranges. Otherwise we might consider valid event as invalid. Fixes: 74c6881019b7 ("powerpc/watchpoint: Prepare handler to handle more than one watchpoint") Signed-off-by: Ravi Bangoria Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200902042945.129369-3-ravi.bangoria@linux.ibm.com --- arch/powerpc/kernel/hw_breakpoint.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index 9f7df1c37233..f6b24838ca3c 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -644,6 +644,8 @@ static void get_instr_detail(struct pt_regs *regs, struct ppc_inst *instr, if (*type == CACHEOP) { *size = cache_op_size(); *ea &= ~(*size - 1); + } else if (*type == LOAD_VMX || *type == STORE_VMX) { + *ea &= ~(*size - 1); } } From 9b6b7c680cc20971444d9f836e49fc98848bcd0a Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Wed, 2 Sep 2020 09:59:40 +0530 Subject: [PATCH 142/645] powerpc/watchpoint/ptrace: Fix SETHWDEBUG when CONFIG_HAVE_HW_BREAKPOINT=N When kernel is compiled with CONFIG_HAVE_HW_BREAKPOINT=N, user can still create watchpoint using PPC_PTRACE_SETHWDEBUG, with limited functionalities. But, such watchpoints are never firing because of the missing privilege settings. Fix that. It's safe to set HW_BRK_TYPE_PRIV_ALL because we don't really leak any kernel address in signal info. Setting HW_BRK_TYPE_PRIV_ALL will also help to find scenarios when kernel accesses user memory. Reported-by: Pedro Miraglia Franco de Carvalho Suggested-by: Pedro Miraglia Franco de Carvalho Signed-off-by: Ravi Bangoria Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200902042945.129369-4-ravi.bangoria@linux.ibm.com --- arch/powerpc/kernel/ptrace/ptrace-noadv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/ptrace/ptrace-noadv.c b/arch/powerpc/kernel/ptrace/ptrace-noadv.c index 697c7e4b5877..57a0ab822334 100644 --- a/arch/powerpc/kernel/ptrace/ptrace-noadv.c +++ b/arch/powerpc/kernel/ptrace/ptrace-noadv.c @@ -217,7 +217,7 @@ long ppc_set_hwdebug(struct task_struct *child, struct ppc_hw_breakpoint *bp_inf return -EIO; brk.address = ALIGN_DOWN(bp_info->addr, HW_BREAKPOINT_SIZE); - brk.type = HW_BRK_TYPE_TRANSLATE; + brk.type = HW_BRK_TYPE_TRANSLATE | HW_BRK_TYPE_PRIV_ALL; brk.len = DABR_MAX_LEN; if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ) brk.type |= HW_BRK_TYPE_READ; From edc8dd99b29e4d705c45e2a3a6c01b096ee056db Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Wed, 2 Sep 2020 09:59:41 +0530 Subject: [PATCH 143/645] powerpc/watchpoint: Move DAWR detection logic outside of hw_breakpoint.c Power10 hw has multiple DAWRs but hw doesn't tell which DAWR caused the exception. So we have a sw logic to detect that in hw_breakpoint.c. But hw_breakpoint.c gets compiled only with CONFIG_HAVE_HW_BREAKPOINT=Y. Move DAWR detection logic outside of hw_breakpoint.c so that it can be reused when CONFIG_HAVE_HW_BREAKPOINT is not set. Signed-off-by: Ravi Bangoria Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200902042945.129369-5-ravi.bangoria@linux.ibm.com --- arch/powerpc/include/asm/hw_breakpoint.h | 8 + arch/powerpc/kernel/Makefile | 3 +- arch/powerpc/kernel/hw_breakpoint.c | 159 +---------------- .../kernel/hw_breakpoint_constraints.c | 162 ++++++++++++++++++ 4 files changed, 174 insertions(+), 158 deletions(-) create mode 100644 arch/powerpc/kernel/hw_breakpoint_constraints.c diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h index 9b68eafebf43..81872c420476 100644 --- a/arch/powerpc/include/asm/hw_breakpoint.h +++ b/arch/powerpc/include/asm/hw_breakpoint.h @@ -10,6 +10,7 @@ #define _PPC_BOOK3S_64_HW_BREAKPOINT_H #include +#include #ifdef __KERNEL__ struct arch_hw_breakpoint { @@ -52,6 +53,13 @@ static inline int nr_wp_slots(void) return cpu_has_feature(CPU_FTR_DAWR1) ? 2 : 1; } +bool wp_check_constraints(struct pt_regs *regs, struct ppc_inst instr, + unsigned long ea, int type, int size, + struct arch_hw_breakpoint *info); + +void wp_get_instr_detail(struct pt_regs *regs, struct ppc_inst *instr, + int *type, int *size, unsigned long *ea); + #ifdef CONFIG_HAVE_HW_BREAKPOINT #include #include diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index cbf41fb4ee89..a5550c2b24c4 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -45,7 +45,8 @@ obj-y := cputable.o syscalls.o \ signal.o sysfs.o cacheinfo.o time.o \ prom.o traps.o setup-common.o \ udbg.o misc.o io.o misc_$(BITS).o \ - of_platform.o prom_parse.o firmware.o + of_platform.o prom_parse.o firmware.o \ + hw_breakpoint_constraints.o obj-y += ptrace/ obj-$(CONFIG_PPC64) += setup_64.o \ paca.o nvram_64.o note.o syscall_64.o diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index f6b24838ca3c..f4e8f21046f5 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -494,161 +494,6 @@ reset: } } -static bool dar_in_user_range(unsigned long dar, struct arch_hw_breakpoint *info) -{ - return ((info->address <= dar) && (dar - info->address < info->len)); -} - -static bool ea_user_range_overlaps(unsigned long ea, int size, - struct arch_hw_breakpoint *info) -{ - return ((ea < info->address + info->len) && - (ea + size > info->address)); -} - -static bool dar_in_hw_range(unsigned long dar, struct arch_hw_breakpoint *info) -{ - unsigned long hw_start_addr, hw_end_addr; - - hw_start_addr = ALIGN_DOWN(info->address, HW_BREAKPOINT_SIZE); - hw_end_addr = ALIGN(info->address + info->len, HW_BREAKPOINT_SIZE); - - return ((hw_start_addr <= dar) && (hw_end_addr > dar)); -} - -static bool ea_hw_range_overlaps(unsigned long ea, int size, - struct arch_hw_breakpoint *info) -{ - unsigned long hw_start_addr, hw_end_addr; - unsigned long align_size = HW_BREAKPOINT_SIZE; - - /* - * On p10 predecessors, quadword is handle differently then - * other instructions. - */ - if (!cpu_has_feature(CPU_FTR_ARCH_31) && size == 16) - align_size = HW_BREAKPOINT_SIZE_QUADWORD; - - hw_start_addr = ALIGN_DOWN(info->address, align_size); - hw_end_addr = ALIGN(info->address + info->len, align_size); - - return ((ea < hw_end_addr) && (ea + size > hw_start_addr)); -} - -/* - * If hw has multiple DAWR registers, we also need to check all - * dawrx constraint bits to confirm this is _really_ a valid event. - * If type is UNKNOWN, but privilege level matches, consider it as - * a positive match. - */ -static bool check_dawrx_constraints(struct pt_regs *regs, int type, - struct arch_hw_breakpoint *info) -{ - if (OP_IS_LOAD(type) && !(info->type & HW_BRK_TYPE_READ)) - return false; - - /* - * The Cache Management instructions other than dcbz never - * cause a match. i.e. if type is CACHEOP, the instruction - * is dcbz, and dcbz is treated as Store. - */ - if ((OP_IS_STORE(type) || type == CACHEOP) && !(info->type & HW_BRK_TYPE_WRITE)) - return false; - - if (is_kernel_addr(regs->nip) && !(info->type & HW_BRK_TYPE_KERNEL)) - return false; - - if (user_mode(regs) && !(info->type & HW_BRK_TYPE_USER)) - return false; - - return true; -} - -/* - * Return true if the event is valid wrt dawr configuration, - * including extraneous exception. Otherwise return false. - */ -static bool check_constraints(struct pt_regs *regs, struct ppc_inst instr, - unsigned long ea, int type, int size, - struct arch_hw_breakpoint *info) -{ - bool in_user_range = dar_in_user_range(regs->dar, info); - bool dawrx_constraints; - - /* - * 8xx supports only one breakpoint and thus we can - * unconditionally return true. - */ - if (IS_ENABLED(CONFIG_PPC_8xx)) { - if (!in_user_range) - info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ; - return true; - } - - if (unlikely(ppc_inst_equal(instr, ppc_inst(0)))) { - if (cpu_has_feature(CPU_FTR_ARCH_31) && - !dar_in_hw_range(regs->dar, info)) - return false; - - return true; - } - - dawrx_constraints = check_dawrx_constraints(regs, type, info); - - if (type == UNKNOWN) { - if (cpu_has_feature(CPU_FTR_ARCH_31) && - !dar_in_hw_range(regs->dar, info)) - return false; - - return dawrx_constraints; - } - - if (ea_user_range_overlaps(ea, size, info)) - return dawrx_constraints; - - if (ea_hw_range_overlaps(ea, size, info)) { - if (dawrx_constraints) { - info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ; - return true; - } - } - return false; -} - -static int cache_op_size(void) -{ -#ifdef __powerpc64__ - return ppc64_caches.l1d.block_size; -#else - return L1_CACHE_BYTES; -#endif -} - -static void get_instr_detail(struct pt_regs *regs, struct ppc_inst *instr, - int *type, int *size, unsigned long *ea) -{ - struct instruction_op op; - - if (__get_user_instr_inatomic(*instr, (void __user *)regs->nip)) - return; - - analyse_instr(&op, regs, *instr); - *type = GETTYPE(op.type); - *ea = op.ea; -#ifdef __powerpc64__ - if (!(regs->msr & MSR_64BIT)) - *ea &= 0xffffffffUL; -#endif - - *size = GETSIZE(op.type); - if (*type == CACHEOP) { - *size = cache_op_size(); - *ea &= ~(*size - 1); - } else if (*type == LOAD_VMX || *type == STORE_VMX) { - *ea &= ~(*size - 1); - } -} - static bool is_larx_stcx_instr(int type) { return type == LARX || type == STCX; @@ -732,7 +577,7 @@ int hw_breakpoint_handler(struct die_args *args) rcu_read_lock(); if (!IS_ENABLED(CONFIG_PPC_8xx)) - get_instr_detail(regs, &instr, &type, &size, &ea); + wp_get_instr_detail(regs, &instr, &type, &size, &ea); for (i = 0; i < nr_wp_slots(); i++) { bp[i] = __this_cpu_read(bp_per_reg[i]); @@ -742,7 +587,7 @@ int hw_breakpoint_handler(struct die_args *args) info[i] = counter_arch_bp(bp[i]); info[i]->type &= ~HW_BRK_TYPE_EXTRANEOUS_IRQ; - if (check_constraints(regs, instr, ea, type, size, info[i])) { + if (wp_check_constraints(regs, instr, ea, type, size, info[i])) { if (!IS_ENABLED(CONFIG_PPC_8xx) && ppc_inst_equal(instr, ppc_inst(0))) { handler_error(bp[i], info[i]); diff --git a/arch/powerpc/kernel/hw_breakpoint_constraints.c b/arch/powerpc/kernel/hw_breakpoint_constraints.c new file mode 100644 index 000000000000..867ee4aa026a --- /dev/null +++ b/arch/powerpc/kernel/hw_breakpoint_constraints.c @@ -0,0 +1,162 @@ +// SPDX-License-Identifier: GPL-2.0+ +#include +#include +#include +#include +#include +#include + +static bool dar_in_user_range(unsigned long dar, struct arch_hw_breakpoint *info) +{ + return ((info->address <= dar) && (dar - info->address < info->len)); +} + +static bool ea_user_range_overlaps(unsigned long ea, int size, + struct arch_hw_breakpoint *info) +{ + return ((ea < info->address + info->len) && + (ea + size > info->address)); +} + +static bool dar_in_hw_range(unsigned long dar, struct arch_hw_breakpoint *info) +{ + unsigned long hw_start_addr, hw_end_addr; + + hw_start_addr = ALIGN_DOWN(info->address, HW_BREAKPOINT_SIZE); + hw_end_addr = ALIGN(info->address + info->len, HW_BREAKPOINT_SIZE); + + return ((hw_start_addr <= dar) && (hw_end_addr > dar)); +} + +static bool ea_hw_range_overlaps(unsigned long ea, int size, + struct arch_hw_breakpoint *info) +{ + unsigned long hw_start_addr, hw_end_addr; + unsigned long align_size = HW_BREAKPOINT_SIZE; + + /* + * On p10 predecessors, quadword is handle differently then + * other instructions. + */ + if (!cpu_has_feature(CPU_FTR_ARCH_31) && size == 16) + align_size = HW_BREAKPOINT_SIZE_QUADWORD; + + hw_start_addr = ALIGN_DOWN(info->address, align_size); + hw_end_addr = ALIGN(info->address + info->len, align_size); + + return ((ea < hw_end_addr) && (ea + size > hw_start_addr)); +} + +/* + * If hw has multiple DAWR registers, we also need to check all + * dawrx constraint bits to confirm this is _really_ a valid event. + * If type is UNKNOWN, but privilege level matches, consider it as + * a positive match. + */ +static bool check_dawrx_constraints(struct pt_regs *regs, int type, + struct arch_hw_breakpoint *info) +{ + if (OP_IS_LOAD(type) && !(info->type & HW_BRK_TYPE_READ)) + return false; + + /* + * The Cache Management instructions other than dcbz never + * cause a match. i.e. if type is CACHEOP, the instruction + * is dcbz, and dcbz is treated as Store. + */ + if ((OP_IS_STORE(type) || type == CACHEOP) && !(info->type & HW_BRK_TYPE_WRITE)) + return false; + + if (is_kernel_addr(regs->nip) && !(info->type & HW_BRK_TYPE_KERNEL)) + return false; + + if (user_mode(regs) && !(info->type & HW_BRK_TYPE_USER)) + return false; + + return true; +} + +/* + * Return true if the event is valid wrt dawr configuration, + * including extraneous exception. Otherwise return false. + */ +bool wp_check_constraints(struct pt_regs *regs, struct ppc_inst instr, + unsigned long ea, int type, int size, + struct arch_hw_breakpoint *info) +{ + bool in_user_range = dar_in_user_range(regs->dar, info); + bool dawrx_constraints; + + /* + * 8xx supports only one breakpoint and thus we can + * unconditionally return true. + */ + if (IS_ENABLED(CONFIG_PPC_8xx)) { + if (!in_user_range) + info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ; + return true; + } + + if (unlikely(ppc_inst_equal(instr, ppc_inst(0)))) { + if (cpu_has_feature(CPU_FTR_ARCH_31) && + !dar_in_hw_range(regs->dar, info)) + return false; + + return true; + } + + dawrx_constraints = check_dawrx_constraints(regs, type, info); + + if (type == UNKNOWN) { + if (cpu_has_feature(CPU_FTR_ARCH_31) && + !dar_in_hw_range(regs->dar, info)) + return false; + + return dawrx_constraints; + } + + if (ea_user_range_overlaps(ea, size, info)) + return dawrx_constraints; + + if (ea_hw_range_overlaps(ea, size, info)) { + if (dawrx_constraints) { + info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ; + return true; + } + } + return false; +} + +static int cache_op_size(void) +{ +#ifdef __powerpc64__ + return ppc64_caches.l1d.block_size; +#else + return L1_CACHE_BYTES; +#endif +} + +void wp_get_instr_detail(struct pt_regs *regs, struct ppc_inst *instr, + int *type, int *size, unsigned long *ea) +{ + struct instruction_op op; + + if (__get_user_instr_inatomic(*instr, (void __user *)regs->nip)) + return; + + analyse_instr(&op, regs, *instr); + *type = GETTYPE(op.type); + *ea = op.ea; +#ifdef __powerpc64__ + if (!(regs->msr & MSR_64BIT)) + *ea &= 0xffffffffUL; +#endif + + *size = GETSIZE(op.type); + if (*type == CACHEOP) { + *size = cache_op_size(); + *ea &= ~(*size - 1); + } else if (*type == LOAD_VMX || *type == STORE_VMX) { + *ea &= ~(*size - 1); + } +} From 5b905d77987de065bdd3a2906816b5f143df087b Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Wed, 2 Sep 2020 09:59:42 +0530 Subject: [PATCH 144/645] powerpc/watchpoint: Fix exception handling for CONFIG_HAVE_HW_BREAKPOINT=N On powerpc, ptrace watchpoint works in one-shot mode. i.e. kernel disables event every time it fires and user has to re-enable it. Also, in case of ptrace watchpoint, kernel notifies ptrace user before executing instruction. With CONFIG_HAVE_HW_BREAKPOINT=N, kernel is missing to disable ptrace event and thus it's causing infinite loop of exceptions. This is especially harmful when user watches on a data which is also read/written by kernel, eg syscall parameters. In such case, infinite exceptions happens in kernel mode which causes soft-lockup. Fixes: 9422de3e953d ("powerpc: Hardware breakpoints rewrite to handle non DABR breakpoint registers") Reported-by: Pedro Miraglia Franco de Carvalho Signed-off-by: Ravi Bangoria Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200902042945.129369-6-ravi.bangoria@linux.ibm.com --- arch/powerpc/include/asm/hw_breakpoint.h | 3 ++ arch/powerpc/kernel/process.c | 48 +++++++++++++++++++++++ arch/powerpc/kernel/ptrace/ptrace-noadv.c | 4 +- 3 files changed, 54 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h index 81872c420476..abebfbee5b1c 100644 --- a/arch/powerpc/include/asm/hw_breakpoint.h +++ b/arch/powerpc/include/asm/hw_breakpoint.h @@ -18,6 +18,7 @@ struct arch_hw_breakpoint { u16 type; u16 len; /* length of the target data symbol */ u16 hw_len; /* length programmed in hw */ + u8 flags; }; /* Note: Don't change the first 6 bits below as they are in the same order @@ -37,6 +38,8 @@ struct arch_hw_breakpoint { #define HW_BRK_TYPE_PRIV_ALL (HW_BRK_TYPE_USER | HW_BRK_TYPE_KERNEL | \ HW_BRK_TYPE_HYP) +#define HW_BRK_FLAG_DISABLED 0x1 + /* Minimum granularity */ #ifdef CONFIG_PPC_8xx #define HW_BREAKPOINT_SIZE 0x4 diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 142680e885ad..483e36a42617 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -642,6 +642,44 @@ void do_send_trap(struct pt_regs *regs, unsigned long address, (void __user *)address); } #else /* !CONFIG_PPC_ADV_DEBUG_REGS */ + +static void do_break_handler(struct pt_regs *regs) +{ + struct arch_hw_breakpoint null_brk = {0}; + struct arch_hw_breakpoint *info; + struct ppc_inst instr = ppc_inst(0); + int type = 0; + int size = 0; + unsigned long ea; + int i; + + /* + * If underneath hw supports only one watchpoint, we know it + * caused exception. 8xx also falls into this category. + */ + if (nr_wp_slots() == 1) { + __set_breakpoint(0, &null_brk); + current->thread.hw_brk[0] = null_brk; + current->thread.hw_brk[0].flags |= HW_BRK_FLAG_DISABLED; + return; + } + + /* Otherwise findout which DAWR caused exception and disable it. */ + wp_get_instr_detail(regs, &instr, &type, &size, &ea); + + for (i = 0; i < nr_wp_slots(); i++) { + info = ¤t->thread.hw_brk[i]; + if (!info->address) + continue; + + if (wp_check_constraints(regs, instr, ea, type, size, info)) { + __set_breakpoint(i, &null_brk); + current->thread.hw_brk[i] = null_brk; + current->thread.hw_brk[i].flags |= HW_BRK_FLAG_DISABLED; + } + } +} + void do_break (struct pt_regs *regs, unsigned long address, unsigned long error_code) { @@ -653,6 +691,16 @@ void do_break (struct pt_regs *regs, unsigned long address, if (debugger_break_match(regs)) return; + /* + * We reach here only when watchpoint exception is generated by ptrace + * event (or hw is buggy!). Now if CONFIG_HAVE_HW_BREAKPOINT is set, + * watchpoint is already handled by hw_breakpoint_handler() so we don't + * have to do anything. But when CONFIG_HAVE_HW_BREAKPOINT is not set, + * we need to manually handle the watchpoint here. + */ + if (!IS_ENABLED(CONFIG_HAVE_HW_BREAKPOINT)) + do_break_handler(regs); + /* Deliver the signal to userspace */ force_sig_fault(SIGTRAP, TRAP_HWBKPT, (void __user *)address); } diff --git a/arch/powerpc/kernel/ptrace/ptrace-noadv.c b/arch/powerpc/kernel/ptrace/ptrace-noadv.c index 57a0ab822334..c9122ed91340 100644 --- a/arch/powerpc/kernel/ptrace/ptrace-noadv.c +++ b/arch/powerpc/kernel/ptrace/ptrace-noadv.c @@ -286,11 +286,13 @@ long ppc_del_hwdebug(struct task_struct *child, long data) } return ret; #else /* CONFIG_HAVE_HW_BREAKPOINT */ - if (child->thread.hw_brk[data - 1].address == 0) + if (!(child->thread.hw_brk[data - 1].flags & HW_BRK_FLAG_DISABLED) && + child->thread.hw_brk[data - 1].address == 0) return -ENOENT; child->thread.hw_brk[data - 1].address = 0; child->thread.hw_brk[data - 1].type = 0; + child->thread.hw_brk[data - 1].flags = 0; #endif /* CONFIG_HAVE_HW_BREAKPOINT */ return 0; From 58da5984d2ea6d95f3f9d9e8dd9f7e1b0dddfb3c Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Wed, 2 Sep 2020 09:59:43 +0530 Subject: [PATCH 145/645] powerpc/watchpoint: Add hw_len wherever missing There are couple of places where we set len but not hw_len. For ptrace/perf watchpoints, when CONFIG_HAVE_HW_BREAKPOINT=Y, hw_len will be calculated and set internally while parsing watchpoint. But when CONFIG_HAVE_HW_BREAKPOINT=N, we need to manually set 'hw_len'. Similarly for xmon as well, hw_len needs to be set directly. Fixes: b57aeab811db ("powerpc/watchpoint: Fix length calculation for unaligned target") Signed-off-by: Ravi Bangoria Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200902042945.129369-7-ravi.bangoria@linux.ibm.com --- arch/powerpc/kernel/ptrace/ptrace-noadv.c | 1 + arch/powerpc/xmon/xmon.c | 1 + 2 files changed, 2 insertions(+) diff --git a/arch/powerpc/kernel/ptrace/ptrace-noadv.c b/arch/powerpc/kernel/ptrace/ptrace-noadv.c index c9122ed91340..48c52426af80 100644 --- a/arch/powerpc/kernel/ptrace/ptrace-noadv.c +++ b/arch/powerpc/kernel/ptrace/ptrace-noadv.c @@ -219,6 +219,7 @@ long ppc_set_hwdebug(struct task_struct *child, struct ppc_hw_breakpoint *bp_inf brk.address = ALIGN_DOWN(bp_info->addr, HW_BREAKPOINT_SIZE); brk.type = HW_BRK_TYPE_TRANSLATE | HW_BRK_TYPE_PRIV_ALL; brk.len = DABR_MAX_LEN; + brk.hw_len = DABR_MAX_LEN; if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ) brk.type |= HW_BRK_TYPE_READ; if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE) diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index df7bca00f5ec..55c43a6c9111 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -969,6 +969,7 @@ static void insert_cpu_bpts(void) brk.address = dabr[i].address; brk.type = (dabr[i].enabled & HW_BRK_TYPE_DABR) | HW_BRK_TYPE_PRIV_ALL; brk.len = 8; + brk.hw_len = 8; __set_breakpoint(i, &brk); } } From fa725cc53d353110f39a9e5b9f60d6acb2c7ff49 Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Wed, 2 Sep 2020 09:59:44 +0530 Subject: [PATCH 146/645] powerpc/watchpoint/ptrace: Introduce PPC_DEBUG_FEATURE_DATA_BP_ARCH_31 PPC_DEBUG_FEATURE_DATA_BP_ARCH_31 can be used to determine whether we are running on an ISA 3.1 compliant machine. Which is needed to determine DAR behaviour, 512 byte boundary limit etc. This was requested by Pedro Miraglia Franco de Carvalho for extending watchpoint features in gdb. Note that availability of 2nd DAWR is independent of this flag and should be checked using ppc_debug_info->num_data_bps. Signed-off-by: Ravi Bangoria Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200902042945.129369-8-ravi.bangoria@linux.ibm.com --- Documentation/powerpc/ptrace.rst | 1 + arch/powerpc/include/uapi/asm/ptrace.h | 1 + arch/powerpc/kernel/ptrace/ptrace-noadv.c | 2 ++ 3 files changed, 4 insertions(+) diff --git a/Documentation/powerpc/ptrace.rst b/Documentation/powerpc/ptrace.rst index 864d4b6dddd1..77725d69eb4a 100644 --- a/Documentation/powerpc/ptrace.rst +++ b/Documentation/powerpc/ptrace.rst @@ -46,6 +46,7 @@ features will have bits indicating whether there is support for:: #define PPC_DEBUG_FEATURE_DATA_BP_RANGE 0x4 #define PPC_DEBUG_FEATURE_DATA_BP_MASK 0x8 #define PPC_DEBUG_FEATURE_DATA_BP_DAWR 0x10 + #define PPC_DEBUG_FEATURE_DATA_BP_ARCH_31 0x20 2. PTRACE_SETHWDEBUG diff --git a/arch/powerpc/include/uapi/asm/ptrace.h b/arch/powerpc/include/uapi/asm/ptrace.h index f5f1ccc740fc..7004cfea3f5f 100644 --- a/arch/powerpc/include/uapi/asm/ptrace.h +++ b/arch/powerpc/include/uapi/asm/ptrace.h @@ -222,6 +222,7 @@ struct ppc_debug_info { #define PPC_DEBUG_FEATURE_DATA_BP_RANGE 0x0000000000000004 #define PPC_DEBUG_FEATURE_DATA_BP_MASK 0x0000000000000008 #define PPC_DEBUG_FEATURE_DATA_BP_DAWR 0x0000000000000010 +#define PPC_DEBUG_FEATURE_DATA_BP_ARCH_31 0x0000000000000020 #ifndef __ASSEMBLY__ diff --git a/arch/powerpc/kernel/ptrace/ptrace-noadv.c b/arch/powerpc/kernel/ptrace/ptrace-noadv.c index 48c52426af80..aa36fcad36cd 100644 --- a/arch/powerpc/kernel/ptrace/ptrace-noadv.c +++ b/arch/powerpc/kernel/ptrace/ptrace-noadv.c @@ -57,6 +57,8 @@ void ppc_gethwdinfo(struct ppc_debug_info *dbginfo) } else { dbginfo->features = 0; } + if (cpu_has_feature(CPU_FTR_ARCH_31)) + dbginfo->features |= PPC_DEBUG_FEATURE_DATA_BP_ARCH_31; } int ptrace_get_debugreg(struct task_struct *child, unsigned long addr, From ac234524056da4e0c081f682da3ea25cdaab737a Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Wed, 2 Sep 2020 09:59:45 +0530 Subject: [PATCH 147/645] selftests/powerpc: Tests for kernel accessing user memory Introduce tests to cover simple scenarios where user is watching memory which can be accessed by kernel as well. We also support _MODE_EXACT with _SETHWDEBUG interface. Move those testcases outside of _BP_RANGE condition. This will help to test _MODE_EXACT scenarios when CONFIG_HAVE_HW_BREAKPOINT is not set, eg: $ ./ptrace-hwbreak ... PTRACE_SET_DEBUGREG, Kernel Access Userspace, len: 8: Ok PPC_PTRACE_SETHWDEBUG, MODE_EXACT, WO, len: 1: Ok PPC_PTRACE_SETHWDEBUG, MODE_EXACT, RO, len: 1: Ok PPC_PTRACE_SETHWDEBUG, MODE_EXACT, RW, len: 1: Ok PPC_PTRACE_SETHWDEBUG, MODE_EXACT, Kernel Access Userspace, len: 1: Ok success: ptrace-hwbreak Suggested-by: Pedro Miraglia Franco de Carvalho Signed-off-by: Ravi Bangoria Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200902042945.129369-9-ravi.bangoria@linux.ibm.com --- .../selftests/powerpc/ptrace/ptrace-hwbreak.c | 48 ++++++++++++++++++- 1 file changed, 46 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-hwbreak.c b/tools/testing/selftests/powerpc/ptrace/ptrace-hwbreak.c index fc477dfe86a2..2e0d86e0687e 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace-hwbreak.c +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-hwbreak.c @@ -20,6 +20,8 @@ #include #include #include +#include +#include #include "ptrace.h" #define SPRN_PVR 0x11F @@ -44,6 +46,7 @@ struct gstruct { }; static volatile struct gstruct gstruct __attribute__((aligned(512))); +static volatile char cwd[PATH_MAX] __attribute__((aligned(8))); static void get_dbginfo(pid_t child_pid, struct ppc_debug_info *dbginfo) { @@ -138,6 +141,9 @@ static void test_workload(void) write_var(len); } + /* PTRACE_SET_DEBUGREG, Kernel Access Userspace test */ + syscall(__NR_getcwd, &cwd, PATH_MAX); + /* PPC_PTRACE_SETHWDEBUG, MODE_EXACT, WO test */ write_var(1); @@ -150,6 +156,9 @@ static void test_workload(void) else read_var(1); + /* PPC_PTRACE_SETHWDEBUG, MODE_EXACT, Kernel Access Userspace test */ + syscall(__NR_getcwd, &cwd, PATH_MAX); + /* PPC_PTRACE_SETHWDEBUG, MODE_RANGE, DW ALIGNED, WO test */ gstruct.a[rand() % A_LEN] = 'a'; @@ -293,6 +302,24 @@ static int test_set_debugreg(pid_t child_pid) return 0; } +static int test_set_debugreg_kernel_userspace(pid_t child_pid) +{ + unsigned long wp_addr = (unsigned long)cwd; + char *name = "PTRACE_SET_DEBUGREG"; + + /* PTRACE_SET_DEBUGREG, Kernel Access Userspace test */ + wp_addr &= ~0x7UL; + wp_addr |= (1Ul << DABR_READ_SHIFT); + wp_addr |= (1UL << DABR_WRITE_SHIFT); + wp_addr |= (1UL << DABR_TRANSLATION_SHIFT); + ptrace_set_debugreg(child_pid, wp_addr); + ptrace(PTRACE_CONT, child_pid, NULL, 0); + check_success(child_pid, name, "Kernel Access Userspace", wp_addr, 8); + + ptrace_set_debugreg(child_pid, 0); + return 0; +} + static void get_ppc_hw_breakpoint(struct ppc_hw_breakpoint *info, int type, unsigned long addr, int len) { @@ -338,6 +365,22 @@ static void test_sethwdebug_exact(pid_t child_pid) ptrace_delhwdebug(child_pid, wh); } +static void test_sethwdebug_exact_kernel_userspace(pid_t child_pid) +{ + struct ppc_hw_breakpoint info; + unsigned long wp_addr = (unsigned long)&cwd; + char *name = "PPC_PTRACE_SETHWDEBUG, MODE_EXACT"; + int len = 1; /* hardcoded in kernel */ + int wh; + + /* PPC_PTRACE_SETHWDEBUG, MODE_EXACT, Kernel Access Userspace test */ + get_ppc_hw_breakpoint(&info, PPC_BREAKPOINT_TRIGGER_WRITE, wp_addr, 0); + wh = ptrace_sethwdebug(child_pid, &info); + ptrace(PTRACE_CONT, child_pid, NULL, 0); + check_success(child_pid, name, "Kernel Access Userspace", wp_addr, len); + ptrace_delhwdebug(child_pid, wh); +} + static void test_sethwdebug_range_aligned(pid_t child_pid) { struct ppc_hw_breakpoint info; @@ -452,9 +495,10 @@ static void run_tests(pid_t child_pid, struct ppc_debug_info *dbginfo, bool dawr) { test_set_debugreg(child_pid); + test_set_debugreg_kernel_userspace(child_pid); + test_sethwdebug_exact(child_pid); + test_sethwdebug_exact_kernel_userspace(child_pid); if (dbginfo->features & PPC_DEBUG_FEATURE_DATA_BP_RANGE) { - test_sethwdebug_exact(child_pid); - test_sethwdebug_range_aligned(child_pid); if (dawr || is_8xx) { test_sethwdebug_range_unaligned(child_pid); From 2a32abac8860aa1c3a1fc99973ce67179575b36c Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Mon, 8 Jun 2020 12:39:01 +0530 Subject: [PATCH 148/645] powerpc/percpu: Update percpu bootmem allocator This update the ppc64 version to be closer to x86/sparc. Signed-off-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200608070904.387440-1-aneesh.kumar@linux.ibm.com --- arch/powerpc/kernel/setup_64.c | 45 ++++++++++++++++++++++++++++------ 1 file changed, 37 insertions(+), 8 deletions(-) diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 6be430107c6f..55bbbf89ea82 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -756,17 +756,46 @@ void __init emergency_stack_init(void) } #ifdef CONFIG_SMP -#define PCPU_DYN_SIZE () - -static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align) +/** + * pcpu_alloc_bootmem - NUMA friendly alloc_bootmem wrapper for percpu + * @cpu: cpu to allocate for + * @size: size allocation in bytes + * @align: alignment + * + * Allocate @size bytes aligned at @align for cpu @cpu. This wrapper + * does the right thing for NUMA regardless of the current + * configuration. + * + * RETURNS: + * Pointer to the allocated area on success, NULL on failure. + */ +static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size, + size_t align) { - return memblock_alloc_try_nid(size, align, __pa(MAX_DMA_ADDRESS), - MEMBLOCK_ALLOC_ACCESSIBLE, - early_cpu_to_node(cpu)); + const unsigned long goal = __pa(MAX_DMA_ADDRESS); +#ifdef CONFIG_NEED_MULTIPLE_NODES + int node = early_cpu_to_node(cpu); + void *ptr; + if (!node_online(node) || !NODE_DATA(node)) { + ptr = memblock_alloc_from(size, align, goal); + pr_info("cpu %d has no node %d or node-local memory\n", + cpu, node); + pr_debug("per cpu data for cpu%d %lu bytes at %016lx\n", + cpu, size, __pa(ptr)); + } else { + ptr = memblock_alloc_try_nid(size, align, goal, + MEMBLOCK_ALLOC_ACCESSIBLE, node); + pr_debug("per cpu data for cpu%d %lu bytes on node%d at " + "%016lx\n", cpu, size, node, __pa(ptr)); + } + return ptr; +#else + return memblock_alloc_from(size, align, goal); +#endif } -static void __init pcpu_fc_free(void *ptr, size_t size) +static void __init pcpu_free_bootmem(void *ptr, size_t size) { memblock_free(__pa(ptr), size); } @@ -801,7 +830,7 @@ void __init setup_per_cpu_areas(void) atom_size = 1 << 20; rc = pcpu_embed_first_chunk(0, dyn_size, atom_size, pcpu_cpu_distance, - pcpu_fc_alloc, pcpu_fc_free); + pcpu_alloc_bootmem, pcpu_free_bootmem); if (rc < 0) panic("cannot initialize percpu area (err=%d)", rc); From eb553f16973ade990d05946af9ae191394712c8a Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Mon, 8 Jun 2020 12:39:02 +0530 Subject: [PATCH 149/645] powerpc/64/mm: implement page mapping percpu first chunk allocator Implement page mapping percpu first chunk allocator as a fallback to the embedding allocator. With 4K hash translation we limit our page table range to 64TB and commit: 0034d395f89d ("powerpc/mm/hash64: Map all the kernel regions in the same 0xc range") moved all kernel mapping to that 64TB range. In-order to support sparse memory layout we need to increase our linear mapping space and reduce other mappings. With such a layout percpu embedded first chunk allocator will fail because of small vmalloc range. Add a fallback to page mapping percpu first chunk allocator for such failures. The below dmesg output can be observed in such case. percpu: max_distance=0x1ffffef00000 too large for vmalloc space 0x10000000000 PERCPU: auto allocator failed (-22), falling back to page size percpu: 40 4K pages/cpu s148816 r0 d15024 Signed-off-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200608070904.387440-2-aneesh.kumar@linux.ibm.com --- arch/powerpc/Kconfig | 5 ++- arch/powerpc/kernel/setup_64.c | 62 ++++++++++++++++++++++++++++++++-- 2 files changed, 63 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 787e829b6f25..4b33477dafb8 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -59,7 +59,10 @@ config HAVE_SETUP_PER_CPU_AREA def_bool PPC64 config NEED_PER_CPU_EMBED_FIRST_CHUNK - def_bool PPC64 + def_bool y if PPC64 + +config NEED_PER_CPU_PAGE_FIRST_CHUNK + def_bool y if PPC64 config NR_IRQS int "Number of virtual interrupt numbers" diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 55bbbf89ea82..bb9cab3641d7 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -66,6 +66,7 @@ #include #include #include +#include #include "setup.h" @@ -811,13 +812,58 @@ static int pcpu_cpu_distance(unsigned int from, unsigned int to) unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; EXPORT_SYMBOL(__per_cpu_offset); +static void __init pcpu_populate_pte(unsigned long addr) +{ + pgd_t *pgd = pgd_offset_k(addr); + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + + p4d = p4d_offset(pgd, addr); + if (p4d_none(*p4d)) { + pud_t *new; + + new = memblock_alloc(PUD_TABLE_SIZE, PUD_TABLE_SIZE); + if (!new) + goto err_alloc; + p4d_populate(&init_mm, p4d, new); + } + + pud = pud_offset(p4d, addr); + if (pud_none(*pud)) { + pmd_t *new; + + new = memblock_alloc(PMD_TABLE_SIZE, PMD_TABLE_SIZE); + if (!new) + goto err_alloc; + pud_populate(&init_mm, pud, new); + } + + pmd = pmd_offset(pud, addr); + if (!pmd_present(*pmd)) { + pte_t *new; + + new = memblock_alloc(PTE_TABLE_SIZE, PTE_TABLE_SIZE); + if (!new) + goto err_alloc; + pmd_populate_kernel(&init_mm, pmd, new); + } + + return; + +err_alloc: + panic("%s: Failed to allocate %lu bytes align=%lx from=%lx\n", + __func__, PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); +} + + void __init setup_per_cpu_areas(void) { const size_t dyn_size = PERCPU_MODULE_RESERVE + PERCPU_DYNAMIC_RESERVE; size_t atom_size; unsigned long delta; unsigned int cpu; - int rc; + int rc = -EINVAL; /* * Linear mapping is one of 4K, 1M and 16M. For 4K, no need @@ -829,8 +875,18 @@ void __init setup_per_cpu_areas(void) else atom_size = 1 << 20; - rc = pcpu_embed_first_chunk(0, dyn_size, atom_size, pcpu_cpu_distance, - pcpu_alloc_bootmem, pcpu_free_bootmem); + if (pcpu_chosen_fc != PCPU_FC_PAGE) { + rc = pcpu_embed_first_chunk(0, dyn_size, atom_size, pcpu_cpu_distance, + pcpu_alloc_bootmem, pcpu_free_bootmem); + if (rc) + pr_warn("PERCPU: %s allocator failed (%d), " + "falling back to page size\n", + pcpu_fc_names[pcpu_chosen_fc], rc); + } + + if (rc < 0) + rc = pcpu_page_first_chunk(0, pcpu_alloc_bootmem, pcpu_free_bootmem, + pcpu_populate_pte); if (rc < 0) panic("cannot initialize percpu area (err=%d)", rc); From 7746406baa3bc9e23fdd7b7da2f04d86e25ab837 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Mon, 8 Jun 2020 12:39:03 +0530 Subject: [PATCH 150/645] powerpc/book3s64/hash/4k: Support large linear mapping range with 4K With commit: 0034d395f89d ("powerpc/mm/hash64: Map all the kernel regions in the same 0xc range"), we now split the 64TB address range into 4 contexts each of 16TB. That implies we can do only 16TB linear mapping. On some systems, eg. Power9, memory attached to nodes > 0 will appear above 16TB in the linear mapping. This resulted in kernel crash when we boot such systems in hash translation mode with 4K PAGE_SIZE. This patch updates the kernel mapping such that we now start supporting upto 61TB of memory with 4K. The kernel mapping now looks like below 4K PAGE_SIZE and hash translation. vmalloc start = 0xc0003d0000000000 IO start = 0xc0003e0000000000 vmemmap start = 0xc0003f0000000000 Our MAX_PHYSMEM_BITS for 4K is still 64TB even though we can only map 61TB. We prevent bolt mapping anything outside 61TB range by checking against H_VMALLOC_START. Fixes: 0034d395f89d ("powerpc/mm/hash64: Map all the kernel regions in the same 0xc range") Reported-by: Cameron Berkenpas Signed-off-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200608070904.387440-3-aneesh.kumar@linux.ibm.com --- arch/powerpc/include/asm/book3s/64/hash-4k.h | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h index 082b98808701..b3ca542f871e 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-4k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h @@ -13,20 +13,19 @@ */ #define MAX_EA_BITS_PER_CONTEXT 46 -#define REGION_SHIFT (MAX_EA_BITS_PER_CONTEXT - 2) /* - * Our page table limit us to 64TB. Hence for the kernel mapping, - * each MAP area is limited to 16 TB. - * The four map areas are: linear mapping, vmap, IO and vmemmap + * Our page table limit us to 64TB. For 64TB physical memory, we only need 64GB + * of vmemmap space. To better support sparse memory layout, we use 61TB + * linear map range, 1TB of vmalloc, 1TB of I/O and 1TB of vmememmap. */ +#define REGION_SHIFT (40) #define H_KERN_MAP_SIZE (ASM_CONST(1) << REGION_SHIFT) /* - * Define the address range of the kernel non-linear virtual area - * 16TB + * Define the address range of the kernel non-linear virtual area (61TB) */ -#define H_KERN_VIRT_START ASM_CONST(0xc000100000000000) +#define H_KERN_VIRT_START ASM_CONST(0xc0003d0000000000) #ifndef __ASSEMBLY__ #define H_PTE_TABLE_SIZE (sizeof(pte_t) << H_PTE_INDEX_SIZE) From b32d5d7e920a364287f6206af2d20179978a617d Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Mon, 8 Jun 2020 12:39:04 +0530 Subject: [PATCH 151/645] powerpc/mm/book3s: Split radix and hash MAX_PHYSMEM limit MAX_PHYSMEM #define is used along with sparsemem to determine the SECTION_SHIFT value. Powerpc also uses the same value to limit the max memory enabled on the system. With 4K PAGE_SIZE and hash translation mode, we want to limit the max memory enabled to 64TB due to page table size restrictions. However, with radix translation, we don't have these restrictions. Hence split the radix and hash MA_PHYSMEM limit and use different limit for each of them. Signed-off-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200608070904.387440-4-aneesh.kumar@linux.ibm.com --- arch/powerpc/include/asm/book3s/64/hash-4k.h | 5 +++++ arch/powerpc/include/asm/book3s/64/hash-64k.h | 13 +++++++++++++ arch/powerpc/include/asm/book3s/64/mmu-hash.h | 4 ++-- arch/powerpc/include/asm/book3s/64/mmu.h | 15 --------------- arch/powerpc/include/asm/book3s/64/pgtable.h | 7 +++++++ arch/powerpc/include/asm/book3s/64/radix.h | 16 ++++++++++++++++ arch/powerpc/kernel/prom.c | 5 +++++ arch/powerpc/mm/book3s64/slb.c | 4 ++-- 8 files changed, 50 insertions(+), 19 deletions(-) diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h index b3ca542f871e..b6ac4f86c87b 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-4k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h @@ -22,6 +22,11 @@ #define REGION_SHIFT (40) #define H_KERN_MAP_SIZE (ASM_CONST(1) << REGION_SHIFT) +/* + * Limits the linear mapping range + */ +#define H_MAX_PHYSMEM_BITS 46 + /* * Define the address range of the kernel non-linear virtual area (61TB) */ diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h index f20de1149ebe..338e62fbea0b 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-64k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h @@ -7,6 +7,19 @@ #define H_PUD_INDEX_SIZE 10 // size: 8B << 10 = 8KB, maps 2^10 x 16GB = 16TB #define H_PGD_INDEX_SIZE 8 // size: 8B << 8 = 2KB, maps 2^8 x 16TB = 4PB +/* + * If we store section details in page->flags we can't increase the MAX_PHYSMEM_BITS + * if we increase SECTIONS_WIDTH we will not store node details in page->flags and + * page_to_nid does a page->section->node lookup + * Hence only increase for VMEMMAP. Further depending on SPARSEMEM_EXTREME reduce + * memory requirements with large number of sections. + * 51 bits is the max physical real address on POWER9 + */ +#if defined(CONFIG_SPARSEMEM_VMEMMAP) && defined(CONFIG_SPARSEMEM_EXTREME) +#define H_MAX_PHYSMEM_BITS 51 +#else +#define H_MAX_PHYSMEM_BITS 46 +#endif /* * Each context is 512TB size. SLB miss for first context/default context diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h index 93d18da5e7ec..683a9c7d1b03 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h +++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h @@ -577,8 +577,8 @@ extern void slb_set_size(u16 size); * For vmalloc and memmap, we use just one context with 512TB. With 64 byte * struct page size, we need ony 32 TB in memmap for 2PB (51 bits (MAX_PHYSMEM_BITS)). */ -#if (MAX_PHYSMEM_BITS > MAX_EA_BITS_PER_CONTEXT) -#define MAX_KERNEL_CTX_CNT (1UL << (MAX_PHYSMEM_BITS - MAX_EA_BITS_PER_CONTEXT)) +#if (H_MAX_PHYSMEM_BITS > MAX_EA_BITS_PER_CONTEXT) +#define MAX_KERNEL_CTX_CNT (1UL << (H_MAX_PHYSMEM_BITS - MAX_EA_BITS_PER_CONTEXT)) #else #define MAX_KERNEL_CTX_CNT 1 #endif diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h index b392384a3b15..ddc414ab3c4d 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu.h +++ b/arch/powerpc/include/asm/book3s/64/mmu.h @@ -27,21 +27,6 @@ struct mmu_psize_def { extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT]; #endif /* __ASSEMBLY__ */ -/* - * If we store section details in page->flags we can't increase the MAX_PHYSMEM_BITS - * if we increase SECTIONS_WIDTH we will not store node details in page->flags and - * page_to_nid does a page->section->node lookup - * Hence only increase for VMEMMAP. Further depending on SPARSEMEM_EXTREME reduce - * memory requirements with large number of sections. - * 51 bits is the max physical real address on POWER9 - */ -#if defined(CONFIG_SPARSEMEM_VMEMMAP) && defined(CONFIG_SPARSEMEM_EXTREME) && \ - defined(CONFIG_PPC_64K_PAGES) -#define MAX_PHYSMEM_BITS 51 -#else -#define MAX_PHYSMEM_BITS 46 -#endif - /* 64-bit classic hash table MMU */ #include diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 495fc0ccb453..76880c7066fa 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -294,6 +294,13 @@ extern unsigned long pci_io_base; #include #include +#if H_MAX_PHYSMEM_BITS > R_MAX_PHYSMEM_BITS +#define MAX_PHYSMEM_BITS H_MAX_PHYSMEM_BITS +#else +#define MAX_PHYSMEM_BITS R_MAX_PHYSMEM_BITS +#endif + + #ifdef CONFIG_PPC_64K_PAGES #include #else diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h index 0cba794c4fb8..c7813dc628fc 100644 --- a/arch/powerpc/include/asm/book3s/64/radix.h +++ b/arch/powerpc/include/asm/book3s/64/radix.h @@ -91,6 +91,22 @@ * +------------------------------+ Kernel linear (0xc.....) */ + +/* + * If we store section details in page->flags we can't increase the MAX_PHYSMEM_BITS + * if we increase SECTIONS_WIDTH we will not store node details in page->flags and + * page_to_nid does a page->section->node lookup + * Hence only increase for VMEMMAP. Further depending on SPARSEMEM_EXTREME reduce + * memory requirements with large number of sections. + * 51 bits is the max physical real address on POWER9 + */ + +#if defined(CONFIG_SPARSEMEM_VMEMMAP) && defined(CONFIG_SPARSEMEM_EXTREME) +#define R_MAX_PHYSMEM_BITS 51 +#else +#define R_MAX_PHYSMEM_BITS 46 +#endif + #define RADIX_KERN_VIRT_START ASM_CONST(0xc008000000000000) /* * 49 = MAX_EA_BITS_PER_CONTEXT (hash specific). To make sure we pick diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index d8a2fb87ba0c..c1545f22c077 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -776,6 +776,11 @@ void __init early_init_devtree(void *params) limit = ALIGN(memory_limit ?: memblock_phys_mem_size(), PAGE_SIZE); memblock_enforce_memory_limit(limit); +#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_4K_PAGES) + if (!early_radix_enabled()) + memblock_cap_memory_range(0, 1UL << (H_MAX_PHYSMEM_BITS)); +#endif + memblock_allow_resize(); memblock_dump_all(); diff --git a/arch/powerpc/mm/book3s64/slb.c b/arch/powerpc/mm/book3s64/slb.c index 156c38f89511..c30fcbfa0e32 100644 --- a/arch/powerpc/mm/book3s64/slb.c +++ b/arch/powerpc/mm/book3s64/slb.c @@ -765,8 +765,8 @@ static long slb_allocate_kernel(unsigned long ea, unsigned long id) if (id == LINEAR_MAP_REGION_ID) { - /* We only support upto MAX_PHYSMEM_BITS */ - if ((ea & EA_MASK) > (1UL << MAX_PHYSMEM_BITS)) + /* We only support upto H_MAX_PHYSMEM_BITS */ + if ((ea & EA_MASK) > (1UL << H_MAX_PHYSMEM_BITS)) return -EFAULT; flags = SLB_VSID_KERNEL | mmu_psize_defs[mmu_linear_psize].sllp; From 66943005cc41f48e4d05614e8f76c0ca1812f0fd Mon Sep 17 00:00:00 2001 From: Finn Thain Date: Sat, 5 Sep 2020 09:02:20 +1000 Subject: [PATCH 152/645] powerpc/tau: Use appropriate temperature sample interval According to the MPC750 Users Manual, the SITV value in Thermal Management Register 3 is 13 bits long. The present code calculates the SITV value as 60 * 500 cycles. This would overflow to give 10 us on a 500 MHz CPU rather than the intended 60 us. (But according to the Microprocessor Datasheet, there is also a factor of 266 that has to be applied to this value on certain parts i.e. speed sort above 266 MHz.) Always use the maximum cycle count, as recommended by the Datasheet. Fixes: 1da177e4c3f41 ("Linux-2.6.12-rc2") Signed-off-by: Finn Thain Tested-by: Stan Johnson Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/896f542e5f0f1d6cf8218524c2b67d79f3d69b3c.1599260540.git.fthain@telegraphics.com.au --- arch/powerpc/include/asm/reg.h | 2 +- arch/powerpc/kernel/tau_6xx.c | 12 ++++-------- 2 files changed, 5 insertions(+), 9 deletions(-) diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 88fb88491fe9..5647006ed373 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -817,7 +817,7 @@ #define THRM1_TIN (1 << 31) #define THRM1_TIV (1 << 30) #define THRM1_THRES(x) ((x&0x7f)<<23) -#define THRM3_SITV(x) ((x&0x3fff)<<1) +#define THRM3_SITV(x) ((x & 0x1fff) << 1) #define THRM1_TID (1<<2) #define THRM1_TIE (1<<1) #define THRM1_V (1<<0) diff --git a/arch/powerpc/kernel/tau_6xx.c b/arch/powerpc/kernel/tau_6xx.c index e2ab8a111b69..976d5bc1b517 100644 --- a/arch/powerpc/kernel/tau_6xx.c +++ b/arch/powerpc/kernel/tau_6xx.c @@ -178,15 +178,11 @@ static void tau_timeout(void * info) * complex sleep code needs to be added. One mtspr every time * tau_timeout is called is probably not a big deal. * - * Enable thermal sensor and set up sample interval timer - * need 20 us to do the compare.. until a nice 'cpu_speed' function - * call is implemented, just assume a 500 mhz clock. It doesn't really - * matter if we take too long for a compare since it's all interrupt - * driven anyway. - * - * use a extra long time.. (60 us @ 500 mhz) + * The "PowerPC 740 and PowerPC 750 Microprocessor Datasheet" + * recommends that "the maximum value be set in THRM3 under all + * conditions." */ - mtspr(SPRN_THRM3, THRM3_SITV(500*60) | THRM3_E); + mtspr(SPRN_THRM3, THRM3_SITV(0x1fff) | THRM3_E); local_irq_restore(flags); } From b1c6a0a10bfaf36ec82fde6f621da72407fa60a1 Mon Sep 17 00:00:00 2001 From: Finn Thain Date: Sat, 5 Sep 2020 09:02:20 +1000 Subject: [PATCH 153/645] powerpc/tau: Convert from timer to workqueue Since commit 19dbdcb8039cf ("smp: Warn on function calls from softirq context") the Thermal Assist Unit driver causes a warning like the following when CONFIG_SMP is enabled. ------------[ cut here ]------------ WARNING: CPU: 0 PID: 0 at kernel/smp.c:428 smp_call_function_many_cond+0xf4/0x38c Modules linked in: CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.7.0-pmac #3 NIP: c00b37a8 LR: c00b3abc CTR: c001218c REGS: c0799c60 TRAP: 0700 Not tainted (5.7.0-pmac) MSR: 00029032 CR: 42000224 XER: 00000000 GPR00: c00b3abc c0799d18 c076e300 c079ef5c c0011fec 00000000 00000000 00000000 GPR08: 00000100 00000100 00008000 ffffffff 42000224 00000000 c079d040 c079d044 GPR16: 00000001 00000000 00000004 c0799da0 c079f054 c07a0000 c07a0000 00000000 GPR24: c0011fec 00000000 c079ef5c c079ef5c 00000000 00000000 00000000 00000000 NIP [c00b37a8] smp_call_function_many_cond+0xf4/0x38c LR [c00b3abc] on_each_cpu+0x38/0x68 Call Trace: [c0799d18] [ffffffff] 0xffffffff (unreliable) [c0799d68] [c00b3abc] on_each_cpu+0x38/0x68 [c0799d88] [c0096704] call_timer_fn.isra.26+0x20/0x7c [c0799d98] [c0096b40] run_timer_softirq+0x1d4/0x3fc [c0799df8] [c05b4368] __do_softirq+0x118/0x240 [c0799e58] [c0039c44] irq_exit+0xc4/0xcc [c0799e68] [c000ade8] timer_interrupt+0x1b0/0x230 [c0799ea8] [c0013520] ret_from_except+0x0/0x14 --- interrupt: 901 at arch_cpu_idle+0x24/0x6c LR = arch_cpu_idle+0x24/0x6c [c0799f70] [00000001] 0x1 (unreliable) [c0799f80] [c0060990] do_idle+0xd8/0x17c [c0799fa0] [c0060ba8] cpu_startup_entry+0x24/0x28 [c0799fb0] [c072d220] start_kernel+0x434/0x44c [c0799ff0] [00003860] 0x3860 Instruction dump: 8129f204 2f890000 40beff98 3d20c07a 8929eec4 2f890000 40beff88 0fe00000 81220000 552805de 550802ef 4182ff84 <0fe00000> 3860ffff 7f65db78 7f44d378 ---[ end trace 34a886e47819c2eb ]--- Don't call on_each_cpu() from a timer callback, call it from a worker thread instead. Fixes: 1da177e4c3f41 ("Linux-2.6.12-rc2") Tested-by: Stan Johnson Signed-off-by: Finn Thain Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/bb61650bea4f4c91fb8e24b9a6f130a1438651a7.1599260540.git.fthain@telegraphics.com.au --- arch/powerpc/kernel/tau_6xx.c | 38 +++++++++++++++++------------------ 1 file changed, 18 insertions(+), 20 deletions(-) diff --git a/arch/powerpc/kernel/tau_6xx.c b/arch/powerpc/kernel/tau_6xx.c index 976d5bc1b517..268205cc347d 100644 --- a/arch/powerpc/kernel/tau_6xx.c +++ b/arch/powerpc/kernel/tau_6xx.c @@ -13,13 +13,14 @@ */ #include -#include #include #include #include #include #include #include +#include +#include #include #include @@ -39,8 +40,6 @@ static struct tau_temp unsigned char grew; } tau[NR_CPUS]; -struct timer_list tau_timer; - #undef DEBUG /* TODO: put these in a /proc interface, with some sanity checks, and maybe @@ -50,7 +49,7 @@ struct timer_list tau_timer; #define step_size 2 /* step size when temp goes out of range */ #define window_expand 1 /* expand the window by this much */ /* configurable values for shrinking the window */ -#define shrink_timer 2*HZ /* period between shrinking the window */ +#define shrink_timer 2000 /* period between shrinking the window */ #define min_window 2 /* minimum window size, degrees C */ static void set_thresholds(unsigned long cpu) @@ -187,14 +186,18 @@ static void tau_timeout(void * info) local_irq_restore(flags); } -static void tau_timeout_smp(struct timer_list *unused) -{ +static struct workqueue_struct *tau_workq; - /* schedule ourselves to be run again */ - mod_timer(&tau_timer, jiffies + shrink_timer) ; +static void tau_work_func(struct work_struct *work) +{ + msleep(shrink_timer); on_each_cpu(tau_timeout, NULL, 0); + /* schedule ourselves to be run again */ + queue_work(tau_workq, work); } +DECLARE_WORK(tau_work, tau_work_func); + /* * setup the TAU * @@ -227,21 +230,16 @@ static int __init TAU_init(void) return 1; } - - /* first, set up the window shrinking timer */ - timer_setup(&tau_timer, tau_timeout_smp, 0); - tau_timer.expires = jiffies + shrink_timer; - add_timer(&tau_timer); + tau_workq = alloc_workqueue("tau", WQ_UNBOUND, 1, 0); + if (!tau_workq) + return -ENOMEM; on_each_cpu(TAU_init_smp, NULL, 0); - printk("Thermal assist unit "); -#ifdef CONFIG_TAU_INT - printk("using interrupts, "); -#else - printk("using timers, "); -#endif - printk("shrink_timer: %d jiffies\n", shrink_timer); + queue_work(tau_workq, &tau_work); + + pr_info("Thermal assist unit using %s, shrink_timer: %d ms\n", + IS_ENABLED(CONFIG_TAU_INT) ? "interrupts" : "workqueue", shrink_timer); tau_initialized = 1; return 0; From 420ab2bc7544d978a5d0762ee736412fe9c796ab Mon Sep 17 00:00:00 2001 From: Finn Thain Date: Sat, 5 Sep 2020 09:02:20 +1000 Subject: [PATCH 154/645] powerpc/tau: Remove duplicated set_thresholds() call The commentary at the call site seems to disagree with the code. The conditional prevents calling set_thresholds() via the exception handler, which appears to crash. Perhaps that's because it immediately triggers another TAU exception. Anyway, calling set_thresholds() from TAUupdate() is redundant because tau_timeout() does so. Fixes: 1da177e4c3f41 ("Linux-2.6.12-rc2") Signed-off-by: Finn Thain Tested-by: Stan Johnson Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/d7c7ee33232cf72a6a6bbb6ef05838b2e2b113c0.1599260540.git.fthain@telegraphics.com.au --- arch/powerpc/kernel/tau_6xx.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/arch/powerpc/kernel/tau_6xx.c b/arch/powerpc/kernel/tau_6xx.c index 268205cc347d..b8d7e7d498e0 100644 --- a/arch/powerpc/kernel/tau_6xx.c +++ b/arch/powerpc/kernel/tau_6xx.c @@ -110,11 +110,6 @@ static void TAUupdate(int cpu) #ifdef DEBUG printk("grew = %d\n", tau[cpu].grew); #endif - -#ifndef CONFIG_TAU_INT /* tau_timeout will do this if not using interrupts */ - set_thresholds(cpu); -#endif - } #ifdef CONFIG_TAU_INT From 5e3119e15fed5b9a9a7e528665ff098a4a8dbdbc Mon Sep 17 00:00:00 2001 From: Finn Thain Date: Sat, 5 Sep 2020 09:02:20 +1000 Subject: [PATCH 155/645] powerpc/tau: Check processor type before enabling TAU interrupt According to Freescale's documentation, MPC74XX processors have an erratum that prevents the TAU interrupt from working, so don't try to use it when running on those processors. Fixes: 1da177e4c3f41 ("Linux-2.6.12-rc2") Signed-off-by: Finn Thain Tested-by: Stan Johnson Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/c281611544768e758bd58fe812cf702a5bd2d042.1599260540.git.fthain@telegraphics.com.au --- arch/powerpc/kernel/tau_6xx.c | 33 ++++++++++++++------------------- arch/powerpc/platforms/Kconfig | 5 ++--- 2 files changed, 16 insertions(+), 22 deletions(-) diff --git a/arch/powerpc/kernel/tau_6xx.c b/arch/powerpc/kernel/tau_6xx.c index b8d7e7d498e0..614b5b272d9c 100644 --- a/arch/powerpc/kernel/tau_6xx.c +++ b/arch/powerpc/kernel/tau_6xx.c @@ -40,6 +40,8 @@ static struct tau_temp unsigned char grew; } tau[NR_CPUS]; +static bool tau_int_enable; + #undef DEBUG /* TODO: put these in a /proc interface, with some sanity checks, and maybe @@ -54,22 +56,13 @@ static struct tau_temp static void set_thresholds(unsigned long cpu) { -#ifdef CONFIG_TAU_INT - /* - * setup THRM1, - * threshold, valid bit, enable interrupts, interrupt when below threshold - */ - mtspr(SPRN_THRM1, THRM1_THRES(tau[cpu].low) | THRM1_V | THRM1_TIE | THRM1_TID); + u32 maybe_tie = tau_int_enable ? THRM1_TIE : 0; - /* setup THRM2, - * threshold, valid bit, enable interrupts, interrupt when above threshold - */ - mtspr (SPRN_THRM2, THRM1_THRES(tau[cpu].high) | THRM1_V | THRM1_TIE); -#else - /* same thing but don't enable interrupts */ - mtspr(SPRN_THRM1, THRM1_THRES(tau[cpu].low) | THRM1_V | THRM1_TID); - mtspr(SPRN_THRM2, THRM1_THRES(tau[cpu].high) | THRM1_V); -#endif + /* setup THRM1, threshold, valid bit, interrupt when below threshold */ + mtspr(SPRN_THRM1, THRM1_THRES(tau[cpu].low) | THRM1_V | maybe_tie | THRM1_TID); + + /* setup THRM2, threshold, valid bit, interrupt when above threshold */ + mtspr(SPRN_THRM2, THRM1_THRES(tau[cpu].high) | THRM1_V | maybe_tie); } static void TAUupdate(int cpu) @@ -142,9 +135,8 @@ static void tau_timeout(void * info) local_irq_save(flags); cpu = smp_processor_id(); -#ifndef CONFIG_TAU_INT - TAUupdate(cpu); -#endif + if (!tau_int_enable) + TAUupdate(cpu); size = tau[cpu].high - tau[cpu].low; if (size > min_window && ! tau[cpu].grew) { @@ -225,6 +217,9 @@ static int __init TAU_init(void) return 1; } + tau_int_enable = IS_ENABLED(CONFIG_TAU_INT) && + !strcmp(cur_cpu_spec->platform, "ppc750"); + tau_workq = alloc_workqueue("tau", WQ_UNBOUND, 1, 0); if (!tau_workq) return -ENOMEM; @@ -234,7 +229,7 @@ static int __init TAU_init(void) queue_work(tau_workq, &tau_work); pr_info("Thermal assist unit using %s, shrink_timer: %d ms\n", - IS_ENABLED(CONFIG_TAU_INT) ? "interrupts" : "workqueue", shrink_timer); + tau_int_enable ? "interrupts" : "workqueue", shrink_timer); tau_initialized = 1; return 0; diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index fb7515b4fa9c..9fe36f0b54c1 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -223,9 +223,8 @@ config TAU temperature within 2-4 degrees Celsius. This option shows the current on-die temperature in /proc/cpuinfo if the cpu supports it. - Unfortunately, on some chip revisions, this sensor is very inaccurate - and in many cases, does not work at all, so don't assume the cpu - temp is actually what /proc/cpuinfo says it is. + Unfortunately, this sensor is very inaccurate when uncalibrated, so + don't assume the cpu temp is actually what /proc/cpuinfo says it is. config TAU_INT bool "Interrupt driven TAU driver (DANGEROUS)" From e63d6fb5637e92725cf143559672a34b706bca4f Mon Sep 17 00:00:00 2001 From: Finn Thain Date: Sat, 5 Sep 2020 09:02:20 +1000 Subject: [PATCH 156/645] powerpc/tau: Disable TAU between measurements Enabling CONFIG_TAU_INT causes random crashes: Unrecoverable exception 1700 at c0009414 (msr=1000) Oops: Unrecoverable exception, sig: 6 [#1] BE PAGE_SIZE=4K MMU=Hash SMP NR_CPUS=2 PowerMac Modules linked in: CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.7.0-pmac-00043-gd5f545e1a8593 #5 NIP: c0009414 LR: c0009414 CTR: c00116fc REGS: c0799eb8 TRAP: 1700 Not tainted (5.7.0-pmac-00043-gd5f545e1a8593) MSR: 00001000 CR: 22000228 XER: 00000100 GPR00: 00000000 c0799f70 c076e300 00800000 0291c0ac 00e00000 c076e300 00049032 GPR08: 00000001 c00116fc 00000000 dfbd3200 ffffffff 007f80a8 00000000 00000000 GPR16: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 c075ce04 GPR24: c075ce04 dfff8880 c07b0000 c075ce04 00080000 00000001 c079ef98 c079ef5c NIP [c0009414] arch_cpu_idle+0x24/0x6c LR [c0009414] arch_cpu_idle+0x24/0x6c Call Trace: [c0799f70] [00000001] 0x1 (unreliable) [c0799f80] [c0060990] do_idle+0xd8/0x17c [c0799fa0] [c0060ba4] cpu_startup_entry+0x20/0x28 [c0799fb0] [c072d220] start_kernel+0x434/0x44c [c0799ff0] [00003860] 0x3860 Instruction dump: XXXXXXXX XXXXXXXX XXXXXXXX 3d20c07b XXXXXXXX XXXXXXXX XXXXXXXX 7c0802a6 XXXXXXXX XXXXXXXX XXXXXXXX 4e800421 XXXXXXXX XXXXXXXX XXXXXXXX 7d2000a6 ---[ end trace 3a0c9b5cb216db6b ]--- Resolve this problem by disabling each THRMn comparator when handling the associated THRMn interrupt and by disabling the TAU entirely when updating THRMn thresholds. Fixes: 1da177e4c3f41 ("Linux-2.6.12-rc2") Signed-off-by: Finn Thain Tested-by: Stan Johnson Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/5a0ba3dc5612c7aac596727331284a3676c08472.1599260540.git.fthain@telegraphics.com.au --- arch/powerpc/kernel/tau_6xx.c | 71 +++++++++++++--------------------- arch/powerpc/platforms/Kconfig | 9 +---- 2 files changed, 29 insertions(+), 51 deletions(-) diff --git a/arch/powerpc/kernel/tau_6xx.c b/arch/powerpc/kernel/tau_6xx.c index 614b5b272d9c..0b4694b8d248 100644 --- a/arch/powerpc/kernel/tau_6xx.c +++ b/arch/powerpc/kernel/tau_6xx.c @@ -42,8 +42,6 @@ static struct tau_temp static bool tau_int_enable; -#undef DEBUG - /* TODO: put these in a /proc interface, with some sanity checks, and maybe * dynamic adjustment to minimize # of interrupts */ /* configurable values for step size and how much to expand the window when @@ -67,42 +65,33 @@ static void set_thresholds(unsigned long cpu) static void TAUupdate(int cpu) { - unsigned thrm; - -#ifdef DEBUG - printk("TAUupdate "); -#endif + u32 thrm; + u32 bits = THRM1_TIV | THRM1_TIN | THRM1_V; /* if both thresholds are crossed, the step_sizes cancel out * and the window winds up getting expanded twice. */ - if((thrm = mfspr(SPRN_THRM1)) & THRM1_TIV){ /* is valid? */ - if(thrm & THRM1_TIN){ /* crossed low threshold */ - if (tau[cpu].low >= step_size){ - tau[cpu].low -= step_size; - tau[cpu].high -= (step_size - window_expand); - } - tau[cpu].grew = 1; -#ifdef DEBUG - printk("low threshold crossed "); -#endif - } - } - if((thrm = mfspr(SPRN_THRM2)) & THRM1_TIV){ /* is valid? */ - if(thrm & THRM1_TIN){ /* crossed high threshold */ - if (tau[cpu].high <= 127-step_size){ - tau[cpu].low += (step_size - window_expand); - tau[cpu].high += step_size; - } - tau[cpu].grew = 1; -#ifdef DEBUG - printk("high threshold crossed "); -#endif - } - } + thrm = mfspr(SPRN_THRM1); + if ((thrm & bits) == bits) { + mtspr(SPRN_THRM1, 0); -#ifdef DEBUG - printk("grew = %d\n", tau[cpu].grew); -#endif + if (tau[cpu].low >= step_size) { + tau[cpu].low -= step_size; + tau[cpu].high -= (step_size - window_expand); + } + tau[cpu].grew = 1; + pr_debug("%s: low threshold crossed\n", __func__); + } + thrm = mfspr(SPRN_THRM2); + if ((thrm & bits) == bits) { + mtspr(SPRN_THRM2, 0); + + if (tau[cpu].high <= 127 - step_size) { + tau[cpu].low += (step_size - window_expand); + tau[cpu].high += step_size; + } + tau[cpu].grew = 1; + pr_debug("%s: high threshold crossed\n", __func__); + } } #ifdef CONFIG_TAU_INT @@ -127,17 +116,17 @@ void TAUException(struct pt_regs * regs) static void tau_timeout(void * info) { int cpu; - unsigned long flags; int size; int shrink; - /* disabling interrupts *should* be okay */ - local_irq_save(flags); cpu = smp_processor_id(); if (!tau_int_enable) TAUupdate(cpu); + /* Stop thermal sensor comparisons and interrupts */ + mtspr(SPRN_THRM3, 0); + size = tau[cpu].high - tau[cpu].low; if (size > min_window && ! tau[cpu].grew) { /* do an exponential shrink of half the amount currently over size */ @@ -159,18 +148,12 @@ static void tau_timeout(void * info) set_thresholds(cpu); - /* - * Do the enable every time, since otherwise a bunch of (relatively) - * complex sleep code needs to be added. One mtspr every time - * tau_timeout is called is probably not a big deal. - * + /* Restart thermal sensor comparisons and interrupts. * The "PowerPC 740 and PowerPC 750 Microprocessor Datasheet" * recommends that "the maximum value be set in THRM3 under all * conditions." */ mtspr(SPRN_THRM3, THRM3_SITV(0x1fff) | THRM3_E); - - local_irq_restore(flags); } static struct workqueue_struct *tau_workq; diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index 9fe36f0b54c1..b439b027a42f 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -227,7 +227,7 @@ config TAU don't assume the cpu temp is actually what /proc/cpuinfo says it is. config TAU_INT - bool "Interrupt driven TAU driver (DANGEROUS)" + bool "Interrupt driven TAU driver (EXPERIMENTAL)" depends on TAU help The TAU supports an interrupt driven mode which causes an interrupt @@ -235,12 +235,7 @@ config TAU_INT to get notified the temp has exceeded a range. With this option off, a timer is used to re-check the temperature periodically. - However, on some cpus it appears that the TAU interrupt hardware - is buggy and can cause a situation which would lead unexplained hard - lockups. - - Unless you are extending the TAU driver, or enjoy kernel/hardware - debugging, leave this option off. + If in doubt, say N here. config TAU_AVERAGE bool "Average high and low temp" From 542db12a9c42d1ce70c45091765e02f74c129f43 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 31 Aug 2020 07:58:19 +0000 Subject: [PATCH 157/645] powerpc: Fix random segfault when freeing hugetlb range The following random segfault is observed from time to time with map_hugetlb selftest: root@localhost:~# ./map_hugetlb 1 19 524288 kB hugepages Mapping 1 Mbytes Segmentation fault [ 31.219972] map_hugetlb[365]: segfault (11) at 117 nip 77974f8c lr 779a6834 code 1 in ld-2.23.so[77966000+21000] [ 31.220192] map_hugetlb[365]: code: 9421ffc0 480318d1 93410028 90010044 9361002c 93810030 93a10034 93c10038 [ 31.220307] map_hugetlb[365]: code: 93e1003c 93210024 8123007c 81430038 <80e90004> 814a0004 7f443a14 813a0004 [ 31.221911] BUG: Bad rss-counter state mm:(ptrval) type:MM_FILEPAGES val:33 [ 31.229362] BUG: Bad rss-counter state mm:(ptrval) type:MM_ANONPAGES val:5 This fault is due to hugetlb_free_pgd_range() freeing page tables that are also used by regular pages. As explain in the comment at the beginning of hugetlb_free_pgd_range(), the verification done in free_pgd_range() on floor and ceiling is not done here, which means hugetlb_free_pte_range() can free outside the expected range. As the verification cannot be done in hugetlb_free_pgd_range(), it must be done in hugetlb_free_pte_range(). Fixes: b250c8c08c79 ("powerpc/8xx: Manage 512k huge pages as standard pages.") Cc: stable@vger.kernel.org Signed-off-by: Christophe Leroy Reviewed-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/f0cb2a5477cd87d1eaadb128042e20aeb2bc2859.1598860677.git.christophe.leroy@csgroup.eu --- arch/powerpc/mm/hugetlbpage.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 26292544630f..e7ae2a2c4545 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -330,10 +330,24 @@ static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshif get_hugepd_cache_index(pdshift - shift)); } -static void hugetlb_free_pte_range(struct mmu_gather *tlb, pmd_t *pmd, unsigned long addr) +static void hugetlb_free_pte_range(struct mmu_gather *tlb, pmd_t *pmd, + unsigned long addr, unsigned long end, + unsigned long floor, unsigned long ceiling) { + unsigned long start = addr; pgtable_t token = pmd_pgtable(*pmd); + start &= PMD_MASK; + if (start < floor) + return; + if (ceiling) { + ceiling &= PMD_MASK; + if (!ceiling) + return; + } + if (end - 1 > ceiling - 1) + return; + pmd_clear(pmd); pte_free_tlb(tlb, token, addr); mm_dec_nr_ptes(tlb->mm); @@ -363,7 +377,7 @@ static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud, */ WARN_ON(!IS_ENABLED(CONFIG_PPC_8xx)); - hugetlb_free_pte_range(tlb, pmd, addr); + hugetlb_free_pte_range(tlb, pmd, addr, end, floor, ceiling); continue; } From 175a99991511fed16108dcb823f0af8e72325a1f Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 31 Aug 2020 08:30:43 +0000 Subject: [PATCH 158/645] powerpc/8xx: Refactor calculation of number of entries per PTE in page tables On 8xx, the number of entries occupied by a PTE in the page tables depends on the size of the page. At the time being, this calculation is done in two places: in pte_update() and in set_huge_pte_at() Refactor this calculation into a helper called number_of_cells_per_pte(). For the time being, the val param is unused. It will be used by following patch. Instead of opencoding is_hugepd(), use hugepd_ok() with a forward declaration. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/f6ea2483c2c389567b007945948f704d18cfaeea.1598862623.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/nohash/32/pgtable.h | 18 ++++++++++++------ arch/powerpc/mm/pgtable.c | 6 ++++-- 2 files changed, 16 insertions(+), 8 deletions(-) diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index b9e134d0f03a..80bbc21b87f0 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -227,6 +227,17 @@ static inline void pmd_clear(pmd_t *pmdp) */ #ifdef CONFIG_PPC_8xx static pmd_t *pmd_off(struct mm_struct *mm, unsigned long addr); +static int hugepd_ok(hugepd_t hpd); + +static int number_of_cells_per_pte(pmd_t *pmd, pte_basic_t val, int huge) +{ + if (!huge) + return PAGE_SIZE / SZ_4K; + else if (hugepd_ok(*((hugepd_t *)pmd))) + return 1; + else + return SZ_512K / SZ_4K; +} static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p, unsigned long clr, unsigned long set, int huge) @@ -237,12 +248,7 @@ static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, p int num, i; pmd_t *pmd = pmd_off(mm, addr); - if (!huge) - num = PAGE_SIZE / SZ_4K; - else if ((pmd_val(*pmd) & _PMD_PAGE_MASK) != _PMD_PAGE_8M) - num = SZ_512K / SZ_4K; - else - num = 1; + num = number_of_cells_per_pte(pmd, new, huge); for (i = 0; i < num; i++, entry++, new += SZ_4K) *entry = new; diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c index 9c0547d77af3..2dcad640b869 100644 --- a/arch/powerpc/mm/pgtable.c +++ b/arch/powerpc/mm/pgtable.c @@ -266,8 +266,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_ pmd_t *pmd = pmd_off(mm, addr); pte_basic_t val; pte_basic_t *entry = &ptep->pte; - int num = is_hugepd(*((hugepd_t *)pmd)) ? 1 : SZ_512K / SZ_4K; - int i; + int num, i; /* * Make sure hardware valid bit is not set. We don't do @@ -280,6 +279,9 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_ pte = set_pte_filter(pte); val = pte_val(pte); + + num = number_of_cells_per_pte(pmd, val, 1); + for (i = 0; i < num; i++, entry++, val += SZ_4K) *entry = val; } From e47168f3d1b14af5281cf50c59561d59d28201f9 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 31 Aug 2020 08:30:44 +0000 Subject: [PATCH 159/645] powerpc/8xx: Support 16k hugepages with 4k pages The 8xx has 4 page sizes: 4k, 16k, 512k and 8M 4k and 16k can be selected at build time as standard page sizes, and 512k and 8M are hugepages. When 4k standard pages are selected, 16k pages are not available. Allow 16k pages as hugepages when 4k pages are used. To allow that, implement arch_make_huge_pte() which receives the necessary arguments to allow setting the PTE in accordance with the page size: - 512 k pages must have _PAGE_HUGE and _PAGE_SPS. They are set by pte_mkhuge(). arch_make_huge_pte() does nothing. - 16 k pages must have only _PAGE_SPS. arch_make_huge_pte() clears _PAGE_HUGE. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/a518abc29266a708dfbccc8fce9ae6694fe4c2c6.1598862623.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h | 14 ++++++++++++++ arch/powerpc/include/asm/nohash/32/pgtable.h | 2 ++ arch/powerpc/mm/hugetlbpage.c | 2 +- arch/powerpc/mm/nohash/tlb.c | 4 ---- arch/powerpc/mm/ptdump/8xx.c | 5 +++++ include/uapi/asm-generic/hugetlb_encode.h | 1 + include/uapi/linux/mman.h | 1 + 7 files changed, 24 insertions(+), 5 deletions(-) diff --git a/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h b/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h index e752a5807a59..39be9aea86db 100644 --- a/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h @@ -65,4 +65,18 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, pte_update(mm, addr, ptep, clr, set, 1); } +#ifdef CONFIG_PPC_4K_PAGES +static inline pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma, + struct page *page, int writable) +{ + size_t size = huge_page_size(hstate_vma(vma)); + + if (size == SZ_16K) + return __pte(pte_val(entry) & ~_PAGE_HUGE); + else + return entry; +} +#define arch_make_huge_pte arch_make_huge_pte +#endif + #endif /* _ASM_POWERPC_NOHASH_32_HUGETLB_8XX_H */ diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index 80bbc21b87f0..ee2243ba96cf 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -235,6 +235,8 @@ static int number_of_cells_per_pte(pmd_t *pmd, pte_basic_t val, int huge) return PAGE_SIZE / SZ_4K; else if (hugepd_ok(*((hugepd_t *)pmd))) return 1; + else if (IS_ENABLED(CONFIG_PPC_4K_PAGES) && !(val & _PAGE_HUGE)) + return SZ_16K / SZ_4K; else return SZ_512K / SZ_4K; } diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index e7ae2a2c4545..36c3800769fb 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -180,7 +180,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz if (!hpdp) return NULL; - if (IS_ENABLED(CONFIG_PPC_8xx) && sz == SZ_512K) + if (IS_ENABLED(CONFIG_PPC_8xx) && pshift < PMD_SHIFT) return pte_alloc_map(mm, (pmd_t *)hpdp, addr); BUG_ON(!hugepd_none(*hpdp) && !hugepd_ok(*hpdp)); diff --git a/arch/powerpc/mm/nohash/tlb.c b/arch/powerpc/mm/nohash/tlb.c index 14514585db98..5872f69141d5 100644 --- a/arch/powerpc/mm/nohash/tlb.c +++ b/arch/powerpc/mm/nohash/tlb.c @@ -83,16 +83,12 @@ struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = { }; #elif defined(CONFIG_PPC_8xx) struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = { - /* we only manage 4k and 16k pages as normal pages */ -#ifdef CONFIG_PPC_4K_PAGES [MMU_PAGE_4K] = { .shift = 12, }, -#else [MMU_PAGE_16K] = { .shift = 14, }, -#endif [MMU_PAGE_512K] = { .shift = 19, }, diff --git a/arch/powerpc/mm/ptdump/8xx.c b/arch/powerpc/mm/ptdump/8xx.c index 8a797dcbf475..86da2a669680 100644 --- a/arch/powerpc/mm/ptdump/8xx.c +++ b/arch/powerpc/mm/ptdump/8xx.c @@ -11,8 +11,13 @@ static const struct flag_info flag_array[] = { { +#ifdef CONFIG_PPC_16K_PAGES .mask = _PAGE_HUGE, .val = _PAGE_HUGE, +#else + .mask = _PAGE_SPS, + .val = _PAGE_SPS, +#endif .set = "huge", .clear = " ", }, { diff --git a/include/uapi/asm-generic/hugetlb_encode.h b/include/uapi/asm-generic/hugetlb_encode.h index b0f8e87235bd..4f3d5aaa11f5 100644 --- a/include/uapi/asm-generic/hugetlb_encode.h +++ b/include/uapi/asm-generic/hugetlb_encode.h @@ -20,6 +20,7 @@ #define HUGETLB_FLAG_ENCODE_SHIFT 26 #define HUGETLB_FLAG_ENCODE_MASK 0x3f +#define HUGETLB_FLAG_ENCODE_16KB (14 << HUGETLB_FLAG_ENCODE_SHIFT) #define HUGETLB_FLAG_ENCODE_64KB (16 << HUGETLB_FLAG_ENCODE_SHIFT) #define HUGETLB_FLAG_ENCODE_512KB (19 << HUGETLB_FLAG_ENCODE_SHIFT) #define HUGETLB_FLAG_ENCODE_1MB (20 << HUGETLB_FLAG_ENCODE_SHIFT) diff --git a/include/uapi/linux/mman.h b/include/uapi/linux/mman.h index 923cc162609c..f55bc680b5b0 100644 --- a/include/uapi/linux/mman.h +++ b/include/uapi/linux/mman.h @@ -27,6 +27,7 @@ #define MAP_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT #define MAP_HUGE_MASK HUGETLB_FLAG_ENCODE_MASK +#define MAP_HUGE_16KB HUGETLB_FLAG_ENCODE_16KB #define MAP_HUGE_64KB HUGETLB_FLAG_ENCODE_64KB #define MAP_HUGE_512KB HUGETLB_FLAG_ENCODE_512KB #define MAP_HUGE_1MB HUGETLB_FLAG_ENCODE_1MB From fcf1f26895a4f14618b0dc04e0801b123c55e4a3 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 4 Sep 2020 10:46:47 +0000 Subject: [PATCH 160/645] powerpc/uaccess: Add pre-update addressing to __put_user_asm_goto() Enable pre-update addressing mode in __put_user_asm_goto() Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/346f65d677adb11865f7762c25a1ca3c64404ba5.1599216023.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/uaccess.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 7c2427f237e1..a5cfe867fbdc 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -254,7 +254,7 @@ do { \ "1: " op "%U1%X1 %0,%1 # put_user\n" \ EX_TABLE(1b, %l2) \ : \ - : "r" (x), "m" (*addr) \ + : "r" (x), "m<>" (*addr) \ : \ : label) From ee0a49a6870ea75e25b4d4984c1bb6b3b7c65f2b Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 4 Sep 2020 11:01:30 +0000 Subject: [PATCH 161/645] powerpc/uaccess: Switch __put_user_size_allowed() to __put_user_asm_goto() __put_user_asm_goto() provides more flexibility to GCC and avoids using a local variable to tell if the write succeeded or not. GCC can then avoid implementing a cmp in the fast path. See the difference for a small function like the PPC64 version of save_general_regs() in arch/powerpc/kernel/signal_32.c: Before the patch (unreachable nop removed): 0000000000000c10 <.save_general_regs>: c10: 39 20 00 2c li r9,44 c14: 39 40 00 00 li r10,0 c18: 7d 29 03 a6 mtctr r9 c1c: 38 c0 00 00 li r6,0 c20: 48 00 00 14 b c34 <.save_general_regs+0x24> c30: 42 40 00 40 bdz c70 <.save_general_regs+0x60> c34: 28 2a 00 27 cmpldi r10,39 c38: 7c c8 33 78 mr r8,r6 c3c: 79 47 1f 24 rldicr r7,r10,3,60 c40: 39 20 00 01 li r9,1 c44: 41 82 00 0c beq c50 <.save_general_regs+0x40> c48: 7d 23 38 2a ldx r9,r3,r7 c4c: 79 29 00 20 clrldi r9,r9,32 c50: 91 24 00 00 stw r9,0(r4) c54: 2c 28 00 00 cmpdi r8,0 c58: 39 4a 00 01 addi r10,r10,1 c5c: 38 84 00 04 addi r4,r4,4 c60: 41 82 ff d0 beq c30 <.save_general_regs+0x20> c64: 38 60 ff f2 li r3,-14 c68: 4e 80 00 20 blr c70: 38 60 00 00 li r3,0 c74: 4e 80 00 20 blr 0000000000000000 <.fixup>: cc: 39 00 ff f2 li r8,-14 d0: 48 00 00 00 b d0 <.fixup+0xd0> d0: R_PPC64_REL24 .text+0xc54 After the patch: 0000000000001490 <.save_general_regs>: 1490: 39 20 00 2c li r9,44 1494: 39 40 00 00 li r10,0 1498: 7d 29 03 a6 mtctr r9 149c: 60 00 00 00 nop 14a0: 28 2a 00 27 cmpldi r10,39 14a4: 79 48 1f 24 rldicr r8,r10,3,60 14a8: 39 20 00 01 li r9,1 14ac: 41 82 00 0c beq 14b8 <.save_general_regs+0x28> 14b0: 7d 23 40 2a ldx r9,r3,r8 14b4: 79 29 00 20 clrldi r9,r9,32 14b8: 91 24 00 00 stw r9,0(r4) 14bc: 39 4a 00 01 addi r10,r10,1 14c0: 38 84 00 04 addi r4,r4,4 14c4: 42 00 ff dc bdnz 14a0 <.save_general_regs+0x10> 14c8: 38 60 00 00 li r3,0 14cc: 4e 80 00 20 blr 14d0: 38 60 ff f2 li r3,-14 14d4: 4e 80 00 20 blr Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/94ba5a5138f99522e1562dbcdb38d31aa790dc89.1599216721.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/uaccess.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index a5cfe867fbdc..96d1c144f92b 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -189,14 +189,14 @@ extern long __put_user_bad(void); #define __put_user_size_allowed(x, ptr, size, retval) \ do { \ + __label__ __pu_failed; \ + \ retval = 0; \ - switch (size) { \ - case 1: __put_user_asm(x, ptr, retval, "stb"); break; \ - case 2: __put_user_asm(x, ptr, retval, "sth"); break; \ - case 4: __put_user_asm(x, ptr, retval, "stw"); break; \ - case 8: __put_user_asm2(x, ptr, retval); break; \ - default: __put_user_bad(); \ - } \ + __put_user_size_goto(x, ptr, size, __pu_failed); \ + break; \ + \ +__pu_failed: \ + retval = -EFAULT; \ } while (0) #define __put_user_size(x, ptr, size, retval) \ From e64ac41ab0c510b3f85199a585eb886cad92fb19 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 4 Sep 2020 11:01:31 +0000 Subject: [PATCH 162/645] powerpc/uaccess: Switch __patch_instruction() to __put_user_asm_goto() __patch_instruction() is the only user of __put_user_asm() outside of asm/uaccess.h Switch to the new __put_user_asm_goto() to enable retirement of __put_user_asm() in a later patch. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/b9745b122f4a9ae72cef445c61320022ab8b77b7.1599216721.git.christophe.leroy@csgroup.eu --- arch/powerpc/lib/code-patching.c | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c index 8c3934ea6220..2333625b5e31 100644 --- a/arch/powerpc/lib/code-patching.c +++ b/arch/powerpc/lib/code-patching.c @@ -21,21 +21,18 @@ static int __patch_instruction(struct ppc_inst *exec_addr, struct ppc_inst instr, struct ppc_inst *patch_addr) { - int err = 0; - - if (!ppc_inst_prefixed(instr)) { - __put_user_asm(ppc_inst_val(instr), patch_addr, err, "stw"); - } else { - __put_user_asm(ppc_inst_as_u64(instr), patch_addr, err, "std"); - } - - if (err) - return err; + if (!ppc_inst_prefixed(instr)) + __put_user_asm_goto(ppc_inst_val(instr), patch_addr, failed, "stw"); + else + __put_user_asm_goto(ppc_inst_as_u64(instr), patch_addr, failed, "std"); asm ("dcbst 0, %0; sync; icbi 0,%1; sync; isync" :: "r" (patch_addr), "r" (exec_addr)); return 0; + +failed: + return -EFAULT; } int raw_patch_instruction(struct ppc_inst *addr, struct ppc_inst instr) From 7fdf966bed155b214f4f1f9b67825a40b2e9b998 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 4 Sep 2020 11:01:32 +0000 Subject: [PATCH 163/645] powerpc/uaccess: Remove __put_user_asm() and __put_user_asm2() __put_user_asm() and __put_user_asm2() are not used anymore. Remove them. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/d66c4a372738d2fbd81f433ca86e4295871ace6a.1599216721.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/uaccess.h | 41 ++++-------------------------- 1 file changed, 5 insertions(+), 36 deletions(-) diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 96d1c144f92b..26781b044932 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -151,42 +151,6 @@ static inline int __access_ok(unsigned long addr, unsigned long size, extern long __put_user_bad(void); -/* - * We don't tell gcc that we are accessing memory, but this is OK - * because we do not write to any memory gcc knows about, so there - * are no aliasing issues. - */ -#define __put_user_asm(x, addr, err, op) \ - __asm__ __volatile__( \ - "1: " op "%U2%X2 %1,%2 # put_user\n" \ - "2:\n" \ - ".section .fixup,\"ax\"\n" \ - "3: li %0,%3\n" \ - " b 2b\n" \ - ".previous\n" \ - EX_TABLE(1b, 3b) \ - : "=r" (err) \ - : "r" (x), "m<>" (*addr), "i" (-EFAULT), "0" (err)) - -#ifdef __powerpc64__ -#define __put_user_asm2(x, ptr, retval) \ - __put_user_asm(x, ptr, retval, "std") -#else /* __powerpc64__ */ -#define __put_user_asm2(x, addr, err) \ - __asm__ __volatile__( \ - "1: stw%X2 %1,%2\n" \ - "2: stw%X2 %L1,%L2\n" \ - "3:\n" \ - ".section .fixup,\"ax\"\n" \ - "4: li %0,%3\n" \ - " b 3b\n" \ - ".previous\n" \ - EX_TABLE(1b, 4b) \ - EX_TABLE(2b, 4b) \ - : "=r" (err) \ - : "r" (x), "m" (*addr), "i" (-EFAULT), "0" (err)) -#endif /* __powerpc64__ */ - #define __put_user_size_allowed(x, ptr, size, retval) \ do { \ __label__ __pu_failed; \ @@ -249,6 +213,11 @@ do { \ }) +/* + * We don't tell gcc that we are accessing memory, but this is OK + * because we do not write to any memory gcc knows about, so there + * are no aliasing issues. + */ #define __put_user_asm_goto(x, addr, label, op) \ asm volatile goto( \ "1: " op "%U1%X1 %0,%1 # put_user\n" \ From c118c7303ad528be8ff2aea8cd1ee15452c763f0 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 7 Sep 2020 13:42:09 +0000 Subject: [PATCH 164/645] powerpc/32: Fix vmap stack - Do not activate MMU before reading task struct We need r1 to be properly set before activating MMU, so reading task_struct->stack must be done with MMU off. This means we need an additional register to play with MSR bits while r11 now points to the stack. For that, move r10 back to CR (As is already done for hash MMU) and use r10. We still don't have r1 correct yet when we activate MMU. It is done in following patch. Fixes: 028474876f47 ("powerpc/32: prepare for CONFIG_VMAP_STACK") Cc: stable@vger.kernel.org Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/a027d447022a006c9c4958ac734128e577a3c5c1.1599486108.git.christophe.leroy@csgroup.eu --- arch/powerpc/kernel/head_32.S | 6 ------ arch/powerpc/kernel/head_32.h | 31 ++++++------------------------- 2 files changed, 6 insertions(+), 31 deletions(-) diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index 5624db0e09a1..b0e184f795c0 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -274,14 +274,8 @@ __secondary_hold_acknowledge: DO_KVM 0x200 MachineCheck: EXCEPTION_PROLOG_0 -#ifdef CONFIG_VMAP_STACK - li r11, MSR_KERNEL & ~(MSR_IR | MSR_RI) /* can take DTLB miss */ - mtmsr r11 - isync -#endif #ifdef CONFIG_PPC_CHRP mfspr r11, SPRN_SPRG_THREAD - tovirt_vmstack r11, r11 lwz r11, RTAS_SP(r11) cmpwi cr1, r11, 0 bne cr1, 7f diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h index 9abec6cd099c..21effebb9277 100644 --- a/arch/powerpc/kernel/head_32.h +++ b/arch/powerpc/kernel/head_32.h @@ -39,24 +39,13 @@ .endm .macro EXCEPTION_PROLOG_1 for_rtas=0 -#ifdef CONFIG_VMAP_STACK - .ifeq \for_rtas - li r11, MSR_KERNEL & ~(MSR_IR | MSR_RI) /* can take DTLB miss */ - mtmsr r11 - isync - .endif subi r11, r1, INT_FRAME_SIZE /* use r1 if kernel */ -#else - tophys(r11,r1) /* use tophys(r1) if kernel */ - subi r11, r11, INT_FRAME_SIZE /* alloc exc. frame */ -#endif beq 1f mfspr r11,SPRN_SPRG_THREAD - tovirt_vmstack r11, r11 lwz r11,TASK_STACK-THREAD(r11) addi r11, r11, THREAD_SIZE - INT_FRAME_SIZE - tophys_novmstack r11, r11 1: + tophys_novmstack r11, r11 #ifdef CONFIG_VMAP_STACK mtcrf 0x7f, r11 bt 32 - THREAD_ALIGN_SHIFT, stack_overflow @@ -64,12 +53,11 @@ .endm .macro EXCEPTION_PROLOG_2 handle_dar_dsisr=0 -#if defined(CONFIG_VMAP_STACK) && defined(CONFIG_PPC_BOOK3S) -BEGIN_MMU_FTR_SECTION +#ifdef CONFIG_VMAP_STACK mtcr r10 -FTR_SECTION_ELSE - stw r10, _CCR(r11) -ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_HPTE_TABLE) + li r10, MSR_KERNEL & ~(MSR_IR | MSR_RI) /* can take DTLB miss */ + mtmsr r10 + isync #else stw r10,_CCR(r11) /* save registers */ #endif @@ -77,11 +65,9 @@ ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_HPTE_TABLE) stw r12,GPR12(r11) stw r9,GPR9(r11) stw r10,GPR10(r11) -#if defined(CONFIG_VMAP_STACK) && defined(CONFIG_PPC_BOOK3S) -BEGIN_MMU_FTR_SECTION +#ifdef CONFIG_VMAP_STACK mfcr r10 stw r10, _CCR(r11) -END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) #endif mfspr r12,SPRN_SPRG_SCRATCH1 stw r12,GPR11(r11) @@ -97,11 +83,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) stw r10, _DSISR(r11) .endif lwz r9, SRR1(r12) -#if defined(CONFIG_VMAP_STACK) && defined(CONFIG_PPC_BOOK3S) -BEGIN_MMU_FTR_SECTION andi. r10, r9, MSR_PR -END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) -#endif lwz r12, SRR0(r12) #else mfspr r12,SPRN_SRR0 @@ -328,7 +310,6 @@ label: #ifdef CONFIG_VMAP_STACK #ifdef CONFIG_SMP mfspr r11, SPRN_SPRG_THREAD - tovirt(r11, r11) lwz r11, TASK_CPU - THREAD(r11) slwi r11, r11, 3 addis r11, r11, emergency_ctx@ha From da7bb43ab9da39bcfed0d146ce94e1f0cbae4ca0 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 7 Sep 2020 13:42:10 +0000 Subject: [PATCH 165/645] powerpc/32: Fix vmap stack - Properly set r1 before activating MMU We need r1 to be properly set before activating MMU, otherwise any new exception taken while saving registers into the stack in exception prologs will use the user stack, which is wrong and will even lockup or crash when KUAP is selected. Do that by switching the meaning of r11 and r1 until we have saved r1 to the stack: copy r1 into r11 and setup the new stack pointer in r1. To avoid complicating and impacting all generic and specific prolog code (and more), copy back r1 into r11 once r11 is save onto the stack. We could get rid of copying r1 back and forth at the cost of rewriting everything to use r1 instead of r11 all the way when CONFIG_VMAP_STACK is set, but the effort is probably not worth it. Fixes: 028474876f47 ("powerpc/32: prepare for CONFIG_VMAP_STACK") Cc: stable@vger.kernel.org Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/8f85e8752ac5af602db7237ef53d634f4f3d3892.1599486108.git.christophe.leroy@csgroup.eu --- arch/powerpc/kernel/head_32.h | 43 +++++++++++++++++++++++------------ 1 file changed, 29 insertions(+), 14 deletions(-) diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h index 21effebb9277..cc36998c5541 100644 --- a/arch/powerpc/kernel/head_32.h +++ b/arch/powerpc/kernel/head_32.h @@ -39,15 +39,24 @@ .endm .macro EXCEPTION_PROLOG_1 for_rtas=0 +#ifdef CONFIG_VMAP_STACK + mr r11, r1 + subi r1, r1, INT_FRAME_SIZE /* use r1 if kernel */ + beq 1f + mfspr r1,SPRN_SPRG_THREAD + lwz r1,TASK_STACK-THREAD(r1) + addi r1, r1, THREAD_SIZE - INT_FRAME_SIZE +#else subi r11, r1, INT_FRAME_SIZE /* use r1 if kernel */ beq 1f mfspr r11,SPRN_SPRG_THREAD lwz r11,TASK_STACK-THREAD(r11) addi r11, r11, THREAD_SIZE - INT_FRAME_SIZE +#endif 1: tophys_novmstack r11, r11 #ifdef CONFIG_VMAP_STACK - mtcrf 0x7f, r11 + mtcrf 0x7f, r1 bt 32 - THREAD_ALIGN_SHIFT, stack_overflow #endif .endm @@ -62,6 +71,15 @@ stw r10,_CCR(r11) /* save registers */ #endif mfspr r10, SPRN_SPRG_SCRATCH0 +#ifdef CONFIG_VMAP_STACK + stw r11,GPR1(r1) + stw r11,0(r1) + mr r11, r1 +#else + stw r1,GPR1(r11) + stw r1,0(r11) + tovirt(r1, r11) /* set new kernel sp */ +#endif stw r12,GPR12(r11) stw r9,GPR9(r11) stw r10,GPR10(r11) @@ -89,9 +107,6 @@ mfspr r12,SPRN_SRR0 mfspr r9,SPRN_SRR1 #endif - stw r1,GPR1(r11) - stw r1,0(r11) - tovirt_novmstack r1, r11 /* set new kernel sp */ #ifdef CONFIG_40x rlwinm r9,r9,0,14,12 /* clear MSR_WE (necessary?) */ #else @@ -309,19 +324,19 @@ label: .macro vmap_stack_overflow_exception #ifdef CONFIG_VMAP_STACK #ifdef CONFIG_SMP - mfspr r11, SPRN_SPRG_THREAD - lwz r11, TASK_CPU - THREAD(r11) - slwi r11, r11, 3 - addis r11, r11, emergency_ctx@ha + mfspr r1, SPRN_SPRG_THREAD + lwz r1, TASK_CPU - THREAD(r1) + slwi r1, r1, 3 + addis r1, r1, emergency_ctx@ha #else - lis r11, emergency_ctx@ha + lis r1, emergency_ctx@ha #endif - lwz r11, emergency_ctx@l(r11) - cmpwi cr1, r11, 0 + lwz r1, emergency_ctx@l(r1) + cmpwi cr1, r1, 0 bne cr1, 1f - lis r11, init_thread_union@ha - addi r11, r11, init_thread_union@l -1: addi r11, r11, THREAD_SIZE - INT_FRAME_SIZE + lis r1, init_thread_union@ha + addi r1, r1, init_thread_union@l +1: addi r1, r1, THREAD_SIZE - INT_FRAME_SIZE EXCEPTION_PROLOG_2 SAVE_NVGPRS(r11) addi r3, r1, STACK_FRAME_OVERHEAD From 04d476bfbb06426fef2985c8e53578bb04596a6f Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 17 Aug 2020 05:46:41 +0000 Subject: [PATCH 166/645] powerpc/process: Replace an #ifdef CONFIG_PPC_47x by IS_ENABLED() isync() is always defined, no need for an #ifdef. Replace it by IS_ENABLED(CONFIG_PPC_47x). Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/ac8da0e3baa91dda805e1e492fd65aecd90c1fb5.1597643156.git.christophe.leroy@csgroup.eu --- arch/powerpc/kernel/process.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 483e36a42617..59dde9a6d3a0 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -831,9 +831,8 @@ static void switch_hw_breakpoint(struct task_struct *new) static inline int __set_dabr(unsigned long dabr, unsigned long dabrx) { mtspr(SPRN_DAC1, dabr); -#ifdef CONFIG_PPC_47x - isync(); -#endif + if (IS_ENABLED(CONFIG_PPC_47x)) + isync(); return 0; } #elif defined(CONFIG_PPC_BOOK3S) From bfac2799301c19d81122af04a8a3ad5ecae3737e Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 17 Aug 2020 05:46:42 +0000 Subject: [PATCH 167/645] powerpc/process: Replace an #ifdef CONFIG_PPC_BOOK3S_64 by IS_ENABLED() This #ifdef CONFIG_PPC_BOOK3S_64 calls preload_new_slb_context() when radix is not enabled. radix_enabled() is always defined, and the prototype for preload_new_slb_context() is always present, so the #ifdef is unneeded. Replace it by IS_ENABLED(). Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/d31506ca9bac9def68cf7424eded63fdc4fb6660.1597643167.git.christophe.leroy@csgroup.eu --- arch/powerpc/kernel/process.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 59dde9a6d3a0..47c401246c40 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1780,10 +1780,8 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) #ifdef CONFIG_PPC64 unsigned long load_addr = regs->gpr[2]; /* saved by ELF_PLAT_INIT */ -#ifdef CONFIG_PPC_BOOK3S_64 - if (!radix_enabled()) + if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && !radix_enabled()) preload_new_slb_context(start, sp); -#endif #endif /* From 2ec42996f5b12826466300a755413577b6913206 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 17 Aug 2020 05:46:43 +0000 Subject: [PATCH 168/645] powerpc/process: Replace an #if defined(CONFIG_4xx) || defined(CONFIG_BOOKE) by IS_ENABLED() The #if defined(CONFIG_4xx) || defined(CONFIG_BOOKE) encloses some printk which can be compiled in all cases. Replace by IS_ENABLED(). Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/a1b6ef3d657c8f249193442f56868fc358ea5b6c.1597643160.git.christophe.leroy@csgroup.eu --- arch/powerpc/kernel/process.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 47c401246c40..4c20136dbdf6 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1502,12 +1502,13 @@ void show_regs(struct pt_regs * regs) trap = TRAP(regs); if (!trap_is_syscall(regs) && cpu_has_feature(CPU_FTR_CFAR)) pr_cont("CFAR: "REG" ", regs->orig_gpr3); - if (trap == 0x200 || trap == 0x300 || trap == 0x600) -#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE) - pr_cont("DEAR: "REG" ESR: "REG" ", regs->dar, regs->dsisr); -#else - pr_cont("DAR: "REG" DSISR: %08lx ", regs->dar, regs->dsisr); -#endif + if (trap == 0x200 || trap == 0x300 || trap == 0x600) { + if (IS_ENABLED(CONFIG_4xx) || IS_ENABLED(CONFIG_BOOKE)) + pr_cont("DEAR: "REG" ESR: "REG" ", regs->dar, regs->dsisr); + else + pr_cont("DAR: "REG" DSISR: %08lx ", regs->dar, regs->dsisr); + } + #ifdef CONFIG_PPC64 pr_cont("IRQMASK: %lx ", regs->softe); #endif From 8f020c7ca300fd60374f0347814c92ea513c24da Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 17 Aug 2020 05:46:44 +0000 Subject: [PATCH 169/645] powerpc/process: Replace #ifdef CONFIG_KALLSYMS by IS_ENABLED() The #ifdef CONFIG_KALLSYMS encloses some printk which can compile in all cases. Replace by IS_ENABLED(). Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/2d89732a9062b2cf2651728804e4b8f6c9b9358e.1597643164.git.christophe.leroy@csgroup.eu --- arch/powerpc/kernel/process.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 4c20136dbdf6..743afa368849 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1525,14 +1525,14 @@ void show_regs(struct pt_regs * regs) break; } pr_cont("\n"); -#ifdef CONFIG_KALLSYMS /* * Lookup NIP late so we have the best change of getting the * above info out without failing */ - printk("NIP ["REG"] %pS\n", regs->nip, (void *)regs->nip); - printk("LR ["REG"] %pS\n", regs->link, (void *)regs->link); -#endif + if (IS_ENABLED(CONFIG_KALLSYMS)) { + printk("NIP ["REG"] %pS\n", regs->nip, (void *)regs->nip); + printk("LR ["REG"] %pS\n", regs->link, (void *)regs->link); + } show_stack(current, (unsigned long *) regs->gpr[1], KERN_DEFAULT); if (!user_mode(regs)) show_instructions(regs); From 60d62bfd24efce1a595d259100b8a4e7a489e834 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 17 Aug 2020 05:46:45 +0000 Subject: [PATCH 170/645] powerpc/process: Tag an #endif to help locate the matching #ifdef. That #endif is more than 100 lines after the matching #ifdef, and there are several #ifdef/#else/#endif inbetween. Tag it as /* CONFIG_PPC_BOOK3S_64 */ to help locate the matching #ifdef. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/3612a8f8aaca16de3fc414a7e66293319d6e213c.1597643147.git.christophe.leroy@csgroup.eu --- arch/powerpc/kernel/process.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 743afa368849..3bc671df5b51 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -581,7 +581,7 @@ void notrace restore_math(struct pt_regs *regs) regs->msr |= new_msr | fpexc_mode; } } -#endif +#endif /* CONFIG_PPC_BOOK3S_64 */ static void save_all(struct task_struct *tsk) { From 80739c2bd29133715d6828e333649a55095f4747 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 17 Aug 2020 05:47:55 +0000 Subject: [PATCH 171/645] powerpc/process: Remove useless #ifdef CONFIG_VSX cpu_has_feature(CPU_FTR_VSX) returns false when CONFIG_VSX is not set. There is no need to enclose the test in an #ifdef CONFIG_VSX. Remove it. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/0eb61cf0dc66d781d47deb2228498cd61d03a754.1597643221.git.christophe.leroy@csgroup.eu --- arch/powerpc/kernel/process.c | 13 +------------ 1 file changed, 1 insertion(+), 12 deletions(-) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 3bc671df5b51..fb079f11a6df 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -124,10 +124,8 @@ unsigned long notrace msr_check_and_set(unsigned long bits) newmsr = oldmsr | bits; -#ifdef CONFIG_VSX if (cpu_has_feature(CPU_FTR_VSX) && (bits & MSR_FP)) newmsr |= MSR_VSX; -#endif if (oldmsr != newmsr) mtmsr_isync(newmsr); @@ -144,10 +142,8 @@ void notrace __msr_check_and_clear(unsigned long bits) newmsr = oldmsr & ~bits; -#ifdef CONFIG_VSX if (cpu_has_feature(CPU_FTR_VSX) && (bits & MSR_FP)) newmsr &= ~MSR_VSX; -#endif if (oldmsr != newmsr) mtmsr_isync(newmsr); @@ -162,10 +158,8 @@ static void __giveup_fpu(struct task_struct *tsk) save_fpu(tsk); msr = tsk->thread.regs->msr; msr &= ~(MSR_FP|MSR_FE0|MSR_FE1); -#ifdef CONFIG_VSX if (cpu_has_feature(CPU_FTR_VSX)) msr &= ~MSR_VSX; -#endif tsk->thread.regs->msr = msr; } @@ -245,10 +239,8 @@ static void __giveup_altivec(struct task_struct *tsk) save_altivec(tsk); msr = tsk->thread.regs->msr; msr &= ~MSR_VEC; -#ifdef CONFIG_VSX if (cpu_has_feature(CPU_FTR_VSX)) msr &= ~MSR_VSX; -#endif tsk->thread.regs->msr = msr; } @@ -421,10 +413,8 @@ static int __init init_msr_all_available(void) if (cpu_has_feature(CPU_FTR_ALTIVEC)) msr_all_available |= MSR_VEC; #endif -#ifdef CONFIG_VSX if (cpu_has_feature(CPU_FTR_VSX)) msr_all_available |= MSR_VSX; -#endif #ifdef CONFIG_SPE if (cpu_has_feature(CPU_FTR_SPE)) msr_all_available |= MSR_SPE; @@ -509,19 +499,18 @@ static bool should_restore_altivec(void) { return false; } static void do_restore_altivec(void) { } #endif /* CONFIG_ALTIVEC */ -#ifdef CONFIG_VSX static bool should_restore_vsx(void) { if (cpu_has_feature(CPU_FTR_VSX)) return true; return false; } +#ifdef CONFIG_VSX static void do_restore_vsx(void) { current->thread.used_vsr = 1; } #else -static bool should_restore_vsx(void) { return false; } static void do_restore_vsx(void) { } #endif /* CONFIG_VSX */ From e3667ee427e224f9951eb3940a97477285548134 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 17 Aug 2020 05:47:56 +0000 Subject: [PATCH 172/645] powerpc/process: Remove useless #ifdef CONFIG_ALTIVEC cpu_has_feature(CPU_FTR_ALTIVEC) returns false when CONFIG_ALTIVEC is not set. There is no need to enclose the test in an #ifdef CONFIG_ALTIVEC. Remove it. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/03ba6b52344ca7c336df2bc6e3d31d736c804ae2.1597643221.git.christophe.leroy@csgroup.eu --- arch/powerpc/kernel/process.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index fb079f11a6df..52019b6962ba 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -409,10 +409,8 @@ static int __init init_msr_all_available(void) #ifdef CONFIG_PPC_FPU msr_all_available |= MSR_FP; #endif -#ifdef CONFIG_ALTIVEC if (cpu_has_feature(CPU_FTR_ALTIVEC)) msr_all_available |= MSR_VEC; -#endif if (cpu_has_feature(CPU_FTR_VSX)) msr_all_available |= MSR_VSX; #ifdef CONFIG_SPE @@ -446,10 +444,8 @@ void giveup_all(struct task_struct *tsk) if (usermsr & MSR_FP) __giveup_fpu(tsk); #endif -#ifdef CONFIG_ALTIVEC if (usermsr & MSR_VEC) __giveup_altivec(tsk); -#endif #ifdef CONFIG_SPE if (usermsr & MSR_SPE) __giveup_spe(tsk); From 532ed1900d37a47c821718a0d8d28eb05b2c4d28 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 17 Aug 2020 05:47:57 +0000 Subject: [PATCH 173/645] powerpc/process: Remove useless #ifdef CONFIG_SPE cpu_has_feature(CPU_FTR_SPE) returns false when CONFIG_SPE is not set. There is no need to enclose the test in an #ifdef CONFIG_SPE. Remove it. CPU_FTR_SPE only exists on 32 bits. Define it as 0 on 64 bits. We have a couple of places like: #ifdef CONFIG_SPE if (cpu_has_feature(CPU_FTR_SPE)) { do_something_that_requires_CONFIG_SPE } else { return -EINVAL; } #else return -EINVAL; #endif Replace them by a cleaner version: if (cpu_has_feature(CPU_FTR_SPE)) { #ifdef CONFIG_SPE do_something_that_requires_CONFIG_SPE #endif } else { return -EINVAL; } When CONFIG_SPE is not set, this resolves to an unconditional return of -EINVAL Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/698df8387555765b70ea42e4a7fa48141c309c1f.1597643221.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/cputable.h | 1 + arch/powerpc/kernel/process.c | 21 +++++++-------------- 2 files changed, 8 insertions(+), 14 deletions(-) diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index 32a15dc49e8c..8ca5885bd5b9 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -170,6 +170,7 @@ static inline void cpu_feature_keys_init(void) { } #else /* CONFIG_PPC32 */ /* Define these to 0 for the sake of tests in common code */ #define CPU_FTR_PPC_LE (0) +#define CPU_FTR_SPE (0) #endif /* diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 52019b6962ba..348d4355bc00 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -413,10 +413,8 @@ static int __init init_msr_all_available(void) msr_all_available |= MSR_VEC; if (cpu_has_feature(CPU_FTR_VSX)) msr_all_available |= MSR_VSX; -#ifdef CONFIG_SPE if (cpu_has_feature(CPU_FTR_SPE)) msr_all_available |= MSR_SPE; -#endif return 0; } @@ -446,10 +444,8 @@ void giveup_all(struct task_struct *tsk) #endif if (usermsr & MSR_VEC) __giveup_altivec(tsk); -#ifdef CONFIG_SPE if (usermsr & MSR_SPE) __giveup_spe(tsk); -#endif msr_check_and_clear(msr_all_available); } @@ -1899,7 +1895,6 @@ int set_fpexc_mode(struct task_struct *tsk, unsigned int val) * fpexc_mode. fpexc_mode is also used for setting FP exception * mode (asyn, precise, disabled) for 'Classic' FP. */ if (val & PR_FP_EXC_SW_ENABLE) { -#ifdef CONFIG_SPE if (cpu_has_feature(CPU_FTR_SPE)) { /* * When the sticky exception bits are set @@ -1913,16 +1908,15 @@ int set_fpexc_mode(struct task_struct *tsk, unsigned int val) * anyway to restore the prctl settings from * the saved environment. */ +#ifdef CONFIG_SPE tsk->thread.spefscr_last = mfspr(SPRN_SPEFSCR); tsk->thread.fpexc_mode = val & (PR_FP_EXC_SW_ENABLE | PR_FP_ALL_EXCEPT); +#endif return 0; } else { return -EINVAL; } -#else - return -EINVAL; -#endif } /* on a CONFIG_SPE this does not hurt us. The bits that @@ -1943,8 +1937,7 @@ int get_fpexc_mode(struct task_struct *tsk, unsigned long adr) { unsigned int val; - if (tsk->thread.fpexc_mode & PR_FP_EXC_SW_ENABLE) -#ifdef CONFIG_SPE + if (tsk->thread.fpexc_mode & PR_FP_EXC_SW_ENABLE) { if (cpu_has_feature(CPU_FTR_SPE)) { /* * When the sticky exception bits are set @@ -1958,15 +1951,15 @@ int get_fpexc_mode(struct task_struct *tsk, unsigned long adr) * anyway to restore the prctl settings from * the saved environment. */ +#ifdef CONFIG_SPE tsk->thread.spefscr_last = mfspr(SPRN_SPEFSCR); val = tsk->thread.fpexc_mode; +#endif } else return -EINVAL; -#else - return -EINVAL; -#endif - else + } else { val = __unpack_fe01(tsk->thread.fpexc_mode); + } return put_user(val, (unsigned int __user *) adr); } From c83c192a6fbb1d4db4144c40296ed059f5eca384 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 17 Aug 2020 05:47:58 +0000 Subject: [PATCH 174/645] powerpc/process: Remove useless #ifdef CONFIG_PPC_FPU Add a stub for __giveup_fpu() when CONFIG_PPC_FPU is not selected, as done for CONFIG_SPE and CONFIG_ALTIVEC. This allows to remove some #ifdef CONFIG_PPC_FPU. Also change one to IS_ENABLED(). Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/69c8b7954ceeccc6b849e52e1fa41b3a0f10f6c1.1597643221.git.christophe.leroy@csgroup.eu --- arch/powerpc/kernel/process.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 348d4355bc00..14d5189b17d8 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -229,6 +229,8 @@ void enable_kernel_fp(void) } } EXPORT_SYMBOL(enable_kernel_fp); +#else +static inline void __giveup_fpu(struct task_struct *tsk) { } #endif /* CONFIG_PPC_FPU */ #ifdef CONFIG_ALTIVEC @@ -406,9 +408,8 @@ static unsigned long msr_all_available; static int __init init_msr_all_available(void) { -#ifdef CONFIG_PPC_FPU - msr_all_available |= MSR_FP; -#endif + if (IS_ENABLED(CONFIG_PPC_FPU)) + msr_all_available |= MSR_FP; if (cpu_has_feature(CPU_FTR_ALTIVEC)) msr_all_available |= MSR_VEC; if (cpu_has_feature(CPU_FTR_VSX)) @@ -438,10 +439,8 @@ void giveup_all(struct task_struct *tsk) WARN_ON((usermsr & MSR_VSX) && !((usermsr & MSR_FP) && (usermsr & MSR_VEC))); -#ifdef CONFIG_PPC_FPU if (usermsr & MSR_FP) __giveup_fpu(tsk); -#endif if (usermsr & MSR_VEC) __giveup_altivec(tsk); if (usermsr & MSR_SPE) From 2c637d2df4ee4830e9d3eb2bd5412250522ce96e Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 11 Sep 2020 10:29:15 +0000 Subject: [PATCH 175/645] powerpc/powermac: Fix low_sleep_handler with KUAP and KUEP low_sleep_handler() has an hardcoded restore of segment registers that doesn't take KUAP and KUEP into account. Use head_32's load_segment_registers() routine instead. Fixes: a68c31fc01ef ("powerpc/32s: Implement Kernel Userspace Access Protection") Fixes: 31ed2b13c48d ("powerpc/32s: Implement Kernel Userspace Execution Prevention.") Cc: stable@vger.kernel.org Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/21b05f7298c1b18f73e6e5b4cd5005aafa24b6da.1599820109.git.christophe.leroy@csgroup.eu --- arch/powerpc/kernel/head_32.S | 2 +- arch/powerpc/platforms/powermac/sleep.S | 9 +-------- 2 files changed, 2 insertions(+), 9 deletions(-) diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index b0e184f795c0..2bd0aa3a4cc7 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -996,7 +996,7 @@ BEGIN_MMU_FTR_SECTION END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) blr -load_segment_registers: +_GLOBAL(load_segment_registers) li r0, NUM_USER_SEGMENTS /* load up user segment register values */ mtctr r0 /* for context 0 */ li r3, 0 /* Kp = 0, Ks = 0, VSID = 0 */ diff --git a/arch/powerpc/platforms/powermac/sleep.S b/arch/powerpc/platforms/powermac/sleep.S index f9a680fdd9c4..51bfdfe85058 100644 --- a/arch/powerpc/platforms/powermac/sleep.S +++ b/arch/powerpc/platforms/powermac/sleep.S @@ -294,14 +294,7 @@ grackle_wake_up: * we do any r1 memory access as we are not sure they * are in a sane state above the first 256Mb region */ - li r0,16 /* load up segment register values */ - mtctr r0 /* for context 0 */ - lis r3,0x2000 /* Ku = 1, VSID = 0 */ - li r4,0 -3: mtsrin r3,r4 - addi r3,r3,0x111 /* increment VSID */ - addis r4,r4,0x1000 /* address of next segment */ - bdnz 3b + bl load_segment_registers sync isync From 4c42dc5c69a8f24c467a6c997909d2f1d4efdc7f Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 11 Sep 2020 05:05:38 +0000 Subject: [PATCH 176/645] powerpc/kasan: Fix CONFIG_KASAN_VMALLOC for 8xx Before the commit identified below, pages tables allocation was performed after the allocation of final shadow area for linear memory. But that commit switched the order, leading to page tables being already allocated at the time 8xx kasan_init_shadow_8M() is called. Due to this, kasan_init_shadow_8M() doesn't map the needed shadow entries because there are already page tables. kasan_init_shadow_8M() installs huge PMD entries instead of page tables. We could at that time free the page tables, but there is no point in creating page tables that get freed before being used. Only book3s/32 hash needs early allocation of page tables. For other variants, we can keep the initial order and create remaining page tables after the allocation of final shadow memory for linear mem. Move back the allocation of shadow page tables for CONFIG_KASAN_VMALLOC into kasan_init() after the loop which creates final shadow memory for linear mem. Fixes: 41ea93cf7ba4 ("powerpc/kasan: Fix shadow pages allocation failure") Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/8ae4554357da4882612644a74387ae05525b2aaa.1599800716.git.christophe.leroy@csgroup.eu --- arch/powerpc/mm/kasan/kasan_init_32.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/mm/kasan/kasan_init_32.c b/arch/powerpc/mm/kasan/kasan_init_32.c index fb294046e00e..929716ea21e9 100644 --- a/arch/powerpc/mm/kasan/kasan_init_32.c +++ b/arch/powerpc/mm/kasan/kasan_init_32.c @@ -127,8 +127,7 @@ void __init kasan_mmu_init(void) { int ret; - if (early_mmu_has_feature(MMU_FTR_HPTE_TABLE) || - IS_ENABLED(CONFIG_KASAN_VMALLOC)) { + if (early_mmu_has_feature(MMU_FTR_HPTE_TABLE)) { ret = kasan_init_shadow_page_tables(KASAN_SHADOW_START, KASAN_SHADOW_END); if (ret) @@ -139,11 +138,11 @@ void __init kasan_mmu_init(void) void __init kasan_init(void) { struct memblock_region *reg; + int ret; for_each_memblock(memory, reg) { phys_addr_t base = reg->base; phys_addr_t top = min(base + reg->size, total_lowmem); - int ret; if (base >= top) continue; @@ -153,6 +152,13 @@ void __init kasan_init(void) panic("kasan: kasan_init_region() failed"); } + if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) { + ret = kasan_init_shadow_page_tables(KASAN_SHADOW_START, KASAN_SHADOW_END); + + if (ret) + panic("kasan: kasan_init_shadow_page_tables() failed"); + } + kasan_remap_early_shadow_ro(); clear_page(kasan_early_shadow_page); From bbc4f40b5322b3e0b8678619f1c613dadc811669 Mon Sep 17 00:00:00 2001 From: Jason Yan Date: Fri, 11 Sep 2020 10:01:21 +0800 Subject: [PATCH 177/645] powerpc/ps3: make two symbols static This addresses the following sparse warning: arch/powerpc/platforms/ps3/spu.c:451:33: warning: symbol 'spu_management_ps3_ops' was not declared. Should it be static? arch/powerpc/platforms/ps3/spu.c:592:28: warning: symbol 'spu_priv1_ps3_ops' was not declared. Should it be static? Reported-by: Hulk Robot Signed-off-by: Jason Yan Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200911020121.1464585-1-yanaijie@huawei.com --- arch/powerpc/platforms/ps3/spu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/platforms/ps3/spu.c b/arch/powerpc/platforms/ps3/spu.c index 1193c294b8d0..0c252478e556 100644 --- a/arch/powerpc/platforms/ps3/spu.c +++ b/arch/powerpc/platforms/ps3/spu.c @@ -448,7 +448,7 @@ static void ps3_disable_spu(struct spu_context *ctx) ctx->ops->runcntl_stop(ctx); } -const struct spu_management_ops spu_management_ps3_ops = { +static const struct spu_management_ops spu_management_ps3_ops = { .enumerate_spus = ps3_enumerate_spus, .create_spu = ps3_create_spu, .destroy_spu = ps3_destroy_spu, @@ -589,7 +589,7 @@ static u64 resource_allocation_enable_get(struct spu *spu) return 0; /* No support. */ } -const struct spu_priv1_ops spu_priv1_ps3_ops = { +static const struct spu_priv1_ops spu_priv1_ps3_ops = { .int_mask_and = int_mask_and, .int_mask_or = int_mask_or, .int_mask_set = int_mask_set, From 79b123cdf9cf0d4a1620baa8c611962626323a08 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Mon, 7 Sep 2020 12:55:39 +0530 Subject: [PATCH 178/645] powerepc/book3s64/hash: Align start/end address correctly with bolt mapping This ensures we don't do a partial mapping of memory. With nvdimm, when creating namespaces with size not aligned to 16MB, the kernel ends up partially mapping the pages. This can result in kernel adding multiple hash page table entries for the same range. A new namespace will result in create_section_mapping() with start and end overlapping an already existing bolted hash page table entry. commit: 6acd7d5ef264 ("libnvdimm/namespace: Enforce memremap_compat_align()") made sure that we always create namespaces aligned to 16MB. But we can do better by avoiding mapping pages that are not aligned. This helps to catch access to these partially mapped pages early. Signed-off-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200907072539.67310-1-aneesh.kumar@linux.ibm.com --- arch/powerpc/mm/book3s64/hash_utils.c | 12 +++++++++--- arch/powerpc/mm/book3s64/radix_pgtable.c | 1 + 2 files changed, 10 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c index c663e7ba801f..7185bc43b24f 100644 --- a/arch/powerpc/mm/book3s64/hash_utils.c +++ b/arch/powerpc/mm/book3s64/hash_utils.c @@ -260,8 +260,12 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend, DBG("htab_bolt_mapping(%lx..%lx -> %lx (%lx,%d,%d)\n", vstart, vend, pstart, prot, psize, ssize); - for (vaddr = vstart, paddr = pstart; vaddr < vend; - vaddr += step, paddr += step) { + /* Carefully map only the possible range */ + vaddr = ALIGN(vstart, step); + paddr = ALIGN(pstart, step); + vend = ALIGN_DOWN(vend, step); + + for (; vaddr < vend; vaddr += step, paddr += step) { unsigned long hash, hpteg; unsigned long vsid = get_kernel_vsid(vaddr, ssize); unsigned long vpn = hpt_vpn(vaddr, vsid, ssize); @@ -343,7 +347,9 @@ int htab_remove_mapping(unsigned long vstart, unsigned long vend, if (!mmu_hash_ops.hpte_removebolted) return -ENODEV; - for (vaddr = vstart; vaddr < vend; vaddr += step) { + /* Unmap the full range specificied */ + vaddr = ALIGN_DOWN(vstart, step); + for (;vaddr < vend; vaddr += step) { rc = mmu_hash_ops.hpte_removebolted(vaddr, psize, ssize); if (rc == -ENOENT) { ret = -ENOENT; diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index d5f0c10d752a..5c8adeb8c955 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -276,6 +276,7 @@ static int __meminit create_physical_mapping(unsigned long start, int psize; start = ALIGN(start, PAGE_SIZE); + end = ALIGN_DOWN(end, PAGE_SIZE); for (addr = start; addr < end; addr += mapping_size) { unsigned long gap, previous_size; int rc; From ffd2961bb41f797eb00b58e019b707555197275e Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Wed, 19 Aug 2020 19:47:00 +1000 Subject: [PATCH 179/645] powerpc/powernv/idle: add a basic stop 0-3 driver for POWER10 This driver does not restore stop > 3 state, so it limits itself to states which do not lose full state or TB. The POWER10 SPRs are sufficiently different from P9 that it seems easier to split out the P10 code. The POWER10 deep sleep code (e.g., the BHRB restore) has been taken out, but it can be re-added when stop > 3 support is added. Signed-off-by: Nicholas Piggin Tested-by: Pratik Rajesh Sampat Tested-by: Vaidyanathan Srinivasan Reviewed-by: Pratik Rajesh Sampat Reviewed-by: Gautham R. Shenoy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200819094700.493399-1-npiggin@gmail.com --- arch/powerpc/include/asm/machdep.h | 2 - arch/powerpc/include/asm/processor.h | 2 +- arch/powerpc/include/asm/reg.h | 1 + arch/powerpc/platforms/powernv/idle.c | 302 ++++++++++++++++++-------- drivers/cpuidle/cpuidle-powernv.c | 2 +- 5 files changed, 212 insertions(+), 97 deletions(-) diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index a90b892f0bfe..5082cd496190 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -222,8 +222,6 @@ struct machdep_calls { extern void e500_idle(void); extern void power4_idle(void); -extern void power7_idle(void); -extern void power9_idle(void); extern void ppc6xx_idle(void); extern void book3e_idle(void); diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 36a71cd41f37..22ffe85a91b8 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -432,7 +432,7 @@ enum idle_boot_override {IDLE_NO_OVERRIDE = 0, IDLE_POWERSAVE_OFF}; extern int powersave_nap; /* set if nap mode can be used in idle loop */ extern void power7_idle_type(unsigned long type); -extern void power9_idle_type(unsigned long stop_psscr_val, +extern void arch300_idle_type(unsigned long stop_psscr_val, unsigned long stop_psscr_mask); extern int fix_alignment(struct pt_regs *); diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 5647006ed373..d25c357a873c 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -1353,6 +1353,7 @@ #define PVR_POWER8NVL 0x004C #define PVR_POWER8 0x004D #define PVR_POWER9 0x004E +#define PVR_POWER10 0x0080 #define PVR_BE 0x0070 #define PVR_PA6T 0x0090 diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c index 345ab062b21a..1ed7c5286487 100644 --- a/arch/powerpc/platforms/powernv/idle.c +++ b/arch/powerpc/platforms/powernv/idle.c @@ -565,7 +565,7 @@ void power7_idle_type(unsigned long type) irq_set_pending_from_srr1(srr1); } -void power7_idle(void) +static void power7_idle(void) { if (!powersave_nap) return; @@ -659,20 +659,6 @@ static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on) mmcr0 = mfspr(SPRN_MMCR0); } - if (cpu_has_feature(CPU_FTR_ARCH_31)) { - /* - * POWER10 uses MMCRA (BHRBRD) as BHRB disable bit. - * If the user hasn't asked for the BHRB to be - * written, the value of MMCRA[BHRBRD] is 1. - * On wakeup from stop, MMCRA[BHRBD] will be 0, - * since it is previleged resource and will be lost. - * Thus, if we do not save and restore the MMCRA[BHRBD], - * hardware will be needlessly writing to the BHRB - * in problem mode. - */ - mmcra = mfspr(SPRN_MMCRA); - } - if ((psscr & PSSCR_RL_MASK) >= deep_spr_loss_state) { sprs.lpcr = mfspr(SPRN_LPCR); sprs.hfscr = mfspr(SPRN_HFSCR); @@ -735,10 +721,6 @@ static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on) mtspr(SPRN_MMCR0, mmcr0); } - /* Reload MMCRA to restore BHRB disable bit for POWER10 */ - if (cpu_has_feature(CPU_FTR_ARCH_31)) - mtspr(SPRN_MMCRA, mmcra); - /* * DD2.2 and earlier need to set then clear bit 60 in MMCRA * to ensure the PMU starts running. @@ -823,73 +805,6 @@ out: return srr1; } -#ifdef CONFIG_HOTPLUG_CPU -static unsigned long power9_offline_stop(unsigned long psscr) -{ - unsigned long srr1; - -#ifndef CONFIG_KVM_BOOK3S_HV_POSSIBLE - __ppc64_runlatch_off(); - srr1 = power9_idle_stop(psscr, true); - __ppc64_runlatch_on(); -#else - /* - * Tell KVM we're entering idle. - * This does not have to be done in real mode because the P9 MMU - * is independent per-thread. Some steppings share radix/hash mode - * between threads, but in that case KVM has a barrier sync in real - * mode before and after switching between radix and hash. - * - * kvm_start_guest must still be called in real mode though, hence - * the false argument. - */ - local_paca->kvm_hstate.hwthread_state = KVM_HWTHREAD_IN_IDLE; - - __ppc64_runlatch_off(); - srr1 = power9_idle_stop(psscr, false); - __ppc64_runlatch_on(); - - local_paca->kvm_hstate.hwthread_state = KVM_HWTHREAD_IN_KERNEL; - /* Order setting hwthread_state vs. testing hwthread_req */ - smp_mb(); - if (local_paca->kvm_hstate.hwthread_req) - srr1 = idle_kvm_start_guest(srr1); - mtmsr(MSR_KERNEL); -#endif - - return srr1; -} -#endif - -void power9_idle_type(unsigned long stop_psscr_val, - unsigned long stop_psscr_mask) -{ - unsigned long psscr; - unsigned long srr1; - - if (!prep_irq_for_idle_irqsoff()) - return; - - psscr = mfspr(SPRN_PSSCR); - psscr = (psscr & ~stop_psscr_mask) | stop_psscr_val; - - __ppc64_runlatch_off(); - srr1 = power9_idle_stop(psscr, true); - __ppc64_runlatch_on(); - - fini_irq_for_idle_irqsoff(); - - irq_set_pending_from_srr1(srr1); -} - -/* - * Used for ppc_md.power_save which needs a function with no parameters - */ -void power9_idle(void) -{ - power9_idle_type(pnv_default_stop_val, pnv_default_stop_mask); -} - #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE /* * This is used in working around bugs in thread reconfiguration @@ -962,6 +877,198 @@ void pnv_power9_force_smt4_release(void) EXPORT_SYMBOL_GPL(pnv_power9_force_smt4_release); #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ +struct p10_sprs { + /* + * SPRs that get lost in shallow states: + * + * P10 loses CR, LR, CTR, FPSCR, VSCR, XER, TAR, SPRG2, and HSPRG1 + * isa300 idle routines restore CR, LR. + * CTR is volatile + * idle thread doesn't use FP or VEC + * kernel doesn't use TAR + * HSPRG1 is only live in HV interrupt entry + * SPRG2 is only live in KVM guests, KVM handles it. + */ +}; + +static unsigned long power10_idle_stop(unsigned long psscr, bool mmu_on) +{ + int cpu = raw_smp_processor_id(); + int first = cpu_first_thread_sibling(cpu); + unsigned long *state = &paca_ptrs[first]->idle_state; + unsigned long core_thread_mask = (1UL << threads_per_core) - 1; + unsigned long srr1; + unsigned long pls; +// struct p10_sprs sprs = {}; /* avoid false used-uninitialised */ + bool sprs_saved = false; + + if (!(psscr & (PSSCR_EC|PSSCR_ESL))) { + /* EC=ESL=0 case */ + + BUG_ON(!mmu_on); + + /* + * Wake synchronously. SRESET via xscom may still cause + * a 0x100 powersave wakeup with SRR1 reason! + */ + srr1 = isa300_idle_stop_noloss(psscr); /* go idle */ + if (likely(!srr1)) + return 0; + + /* + * Registers not saved, can't recover! + * This would be a hardware bug + */ + BUG_ON((srr1 & SRR1_WAKESTATE) != SRR1_WS_NOLOSS); + + goto out; + } + + /* EC=ESL=1 case */ + if ((psscr & PSSCR_RL_MASK) >= deep_spr_loss_state) { + /* XXX: save SPRs for deep state loss here. */ + + sprs_saved = true; + + atomic_start_thread_idle(); + } + + srr1 = isa300_idle_stop_mayloss(psscr); /* go idle */ + + psscr = mfspr(SPRN_PSSCR); + + WARN_ON_ONCE(!srr1); + WARN_ON_ONCE(mfmsr() & (MSR_IR|MSR_DR)); + + if (unlikely((srr1 & SRR1_WAKEMASK_P8) == SRR1_WAKEHMI)) + hmi_exception_realmode(NULL); + + /* + * On POWER10, SRR1 bits do not match exactly as expected. + * SRR1_WS_GPRLOSS (10b) can also result in SPR loss, so + * just always test PSSCR for SPR/TB state loss. + */ + pls = (psscr & PSSCR_PLS) >> PSSCR_PLS_SHIFT; + if (likely(pls < deep_spr_loss_state)) { + if (sprs_saved) + atomic_stop_thread_idle(); + goto out; + } + + /* HV state loss */ + BUG_ON(!sprs_saved); + + atomic_lock_thread_idle(); + + if ((*state & core_thread_mask) != 0) + goto core_woken; + + /* XXX: restore per-core SPRs here */ + + if (pls >= pnv_first_tb_loss_level) { + /* TB loss */ + if (opal_resync_timebase() != OPAL_SUCCESS) + BUG(); + } + + /* + * isync after restoring shared SPRs and before unlocking. Unlock + * only contains hwsync which does not necessarily do the right + * thing for SPRs. + */ + isync(); + +core_woken: + atomic_unlock_and_stop_thread_idle(); + + /* XXX: restore per-thread SPRs here */ + + if (!radix_enabled()) + __slb_restore_bolted_realmode(); + +out: + if (mmu_on) + mtmsr(MSR_KERNEL); + + return srr1; +} + +#ifdef CONFIG_HOTPLUG_CPU +static unsigned long arch300_offline_stop(unsigned long psscr) +{ + unsigned long srr1; + +#ifndef CONFIG_KVM_BOOK3S_HV_POSSIBLE + __ppc64_runlatch_off(); + if (cpu_has_feature(CPU_FTR_ARCH_31)) + srr1 = power10_idle_stop(psscr, true); + else + srr1 = power9_idle_stop(psscr, true); + __ppc64_runlatch_on(); +#else + /* + * Tell KVM we're entering idle. + * This does not have to be done in real mode because the P9 MMU + * is independent per-thread. Some steppings share radix/hash mode + * between threads, but in that case KVM has a barrier sync in real + * mode before and after switching between radix and hash. + * + * kvm_start_guest must still be called in real mode though, hence + * the false argument. + */ + local_paca->kvm_hstate.hwthread_state = KVM_HWTHREAD_IN_IDLE; + + __ppc64_runlatch_off(); + if (cpu_has_feature(CPU_FTR_ARCH_31)) + srr1 = power10_idle_stop(psscr, false); + else + srr1 = power9_idle_stop(psscr, false); + __ppc64_runlatch_on(); + + local_paca->kvm_hstate.hwthread_state = KVM_HWTHREAD_IN_KERNEL; + /* Order setting hwthread_state vs. testing hwthread_req */ + smp_mb(); + if (local_paca->kvm_hstate.hwthread_req) + srr1 = idle_kvm_start_guest(srr1); + mtmsr(MSR_KERNEL); +#endif + + return srr1; +} +#endif + +void arch300_idle_type(unsigned long stop_psscr_val, + unsigned long stop_psscr_mask) +{ + unsigned long psscr; + unsigned long srr1; + + if (!prep_irq_for_idle_irqsoff()) + return; + + psscr = mfspr(SPRN_PSSCR); + psscr = (psscr & ~stop_psscr_mask) | stop_psscr_val; + + __ppc64_runlatch_off(); + if (cpu_has_feature(CPU_FTR_ARCH_31)) + srr1 = power10_idle_stop(psscr, true); + else + srr1 = power9_idle_stop(psscr, true); + __ppc64_runlatch_on(); + + fini_irq_for_idle_irqsoff(); + + irq_set_pending_from_srr1(srr1); +} + +/* + * Used for ppc_md.power_save which needs a function with no parameters + */ +static void arch300_idle(void) +{ + arch300_idle_type(pnv_default_stop_val, pnv_default_stop_mask); +} + #ifdef CONFIG_HOTPLUG_CPU void pnv_program_cpu_hotplug_lpcr(unsigned int cpu, u64 lpcr_val) @@ -995,7 +1102,7 @@ unsigned long pnv_cpu_offline(unsigned int cpu) psscr = mfspr(SPRN_PSSCR); psscr = (psscr & ~pnv_deepest_stop_psscr_mask) | pnv_deepest_stop_psscr_val; - srr1 = power9_offline_stop(psscr); + srr1 = arch300_offline_stop(psscr); } else if (cpu_has_feature(CPU_FTR_ARCH_206) && power7_offline_type) { srr1 = power7_offline(); } else { @@ -1093,11 +1200,15 @@ int validate_psscr_val_mask(u64 *psscr_val, u64 *psscr_mask, u32 flags) * @dt_idle_states: Number of idle state entries * Returns 0 on success */ -static void __init pnv_power9_idle_init(void) +static void __init pnv_arch300_idle_init(void) { u64 max_residency_ns = 0; int i; + /* stop is not really architected, we only have p9,p10 drivers */ + if (!pvr_version_is(PVR_POWER10) && !pvr_version_is(PVR_POWER9)) + return; + /* * pnv_deepest_stop_{val,mask} should be set to values corresponding to * the deepest stop state. @@ -1112,6 +1223,11 @@ static void __init pnv_power9_idle_init(void) struct pnv_idle_states_t *state = &pnv_idle_states[i]; u64 psscr_rl = state->psscr_val & PSSCR_RL_MASK; + /* No deep loss driver implemented for POWER10 yet */ + if (pvr_version_is(PVR_POWER10) && + state->flags & (OPAL_PM_TIMEBASE_STOP|OPAL_PM_LOSE_FULL_CONTEXT)) + continue; + if ((state->flags & OPAL_PM_TIMEBASE_STOP) && (pnv_first_tb_loss_level > psscr_rl)) pnv_first_tb_loss_level = psscr_rl; @@ -1162,7 +1278,7 @@ static void __init pnv_power9_idle_init(void) if (unlikely(!default_stop_found)) { pr_warn("cpuidle-powernv: No suitable default stop state found. Disabling platform idle.\n"); } else { - ppc_md.power_save = power9_idle; + ppc_md.power_save = arch300_idle; pr_info("cpuidle-powernv: Default stop: psscr = 0x%016llx,mask=0x%016llx\n", pnv_default_stop_val, pnv_default_stop_mask); } @@ -1224,7 +1340,7 @@ static void __init pnv_probe_idle_states(void) } if (cpu_has_feature(CPU_FTR_ARCH_300)) - pnv_power9_idle_init(); + pnv_arch300_idle_init(); for (i = 0; i < nr_pnv_idle_states; i++) supported_cpuidle_states |= pnv_idle_states[i].flags; @@ -1295,7 +1411,7 @@ static int pnv_parse_cpuidle_dt(void) for (i = 0; i < nr_idle_states; i++) pnv_idle_states[i].residency_ns = temp_u32[i]; - /* For power9 */ + /* For power9 and later */ if (cpu_has_feature(CPU_FTR_ARCH_300)) { /* Read pm_crtl_val */ if (of_property_read_u64_array(np, "ibm,cpu-idle-state-psscr", @@ -1358,8 +1474,8 @@ static int __init pnv_init_idle_states(void) if (!cpu_has_feature(CPU_FTR_ARCH_300)) { /* P7/P8 nap */ p->thread_idle_state = PNV_THREAD_RUNNING; - } else { - /* P9 stop */ + } else if (pvr_version_is(PVR_POWER9)) { + /* P9 stop workarounds */ #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE p->requested_psscr = 0; atomic_set(&p->dont_stop, 0); diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c index addaa6e6718b..c32c600b3cf8 100644 --- a/drivers/cpuidle/cpuidle-powernv.c +++ b/drivers/cpuidle/cpuidle-powernv.c @@ -141,7 +141,7 @@ static int stop_loop(struct cpuidle_device *dev, struct cpuidle_driver *drv, int index) { - power9_idle_type(stop_psscr_table[index].val, + arch300_idle_type(stop_psscr_table[index].val, stop_psscr_table[index].mask); return index; } From 3a3181e16fbde752007759f8759d25e0ff1fc425 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= Date: Fri, 7 Aug 2020 12:18:54 +0200 Subject: [PATCH 180/645] powerpc/pci: unmap legacy INTx interrupts when a PHB is removed MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When a passthrough IO adapter is removed from a pseries machine using hash MMU and the XIVE interrupt mode, the POWER hypervisor expects the guest OS to clear all page table entries related to the adapter. If some are still present, the RTAS call which isolates the PCI slot returns error 9001 "valid outstanding translations" and the removal of the IO adapter fails. This is because when the PHBs are scanned, Linux maps automatically the INTx interrupts in the Linux interrupt number space but these are never removed. To solve this problem, we introduce a PPC platform specific pcibios_remove_bus() routine which clears all interrupt mappings when the bus is removed. This also clears the associated page table entries of the ESB pages when using XIVE. For this purpose, we record the logical interrupt numbers of the mapped interrupt under the PHB structure and let pcibios_remove_bus() do the clean up. Since some PCI adapters, like GPUs, use the "interrupt-map" property to describe interrupt mappings other than the legacy INTx interrupts, we can not restrict the size of the mapping array to PCI_NUM_INTX. The number of interrupt mappings is computed from the "interrupt-map" property and the mapping array is allocated accordingly. Signed-off-by: Cédric Le Goater Reviewed-by: Alexey Kardashevskiy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200807101854.844619-1-clg@kaod.org --- arch/powerpc/include/asm/pci-bridge.h | 6 ++ arch/powerpc/kernel/pci-common.c | 114 ++++++++++++++++++++++++++ 2 files changed, 120 insertions(+) diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index d2a2a14e56f9..d21e070352dc 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -48,6 +48,9 @@ struct pci_controller_ops { /* * Structure of a PCI controller (host bridge) + * + * @irq_count: number of interrupt mappings + * @irq_map: interrupt mappings */ struct pci_controller { struct pci_bus *bus; @@ -127,6 +130,9 @@ struct pci_controller { void *private_data; struct npu *npu; + + unsigned int irq_count; + unsigned int *irq_map; }; /* These are used for config access before all the PCI probing diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index be108616a721..deb831f0ae13 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -353,6 +353,115 @@ struct pci_controller *pci_find_controller_for_domain(int domain_nr) return NULL; } +/* + * Assumption is made on the interrupt parent. All interrupt-map + * entries are considered to have the same parent. + */ +static int pcibios_irq_map_count(struct pci_controller *phb) +{ + const __be32 *imap; + int imaplen; + struct device_node *parent; + u32 intsize, addrsize, parintsize, paraddrsize; + + if (of_property_read_u32(phb->dn, "#interrupt-cells", &intsize)) + return 0; + if (of_property_read_u32(phb->dn, "#address-cells", &addrsize)) + return 0; + + imap = of_get_property(phb->dn, "interrupt-map", &imaplen); + if (!imap) { + pr_debug("%pOF : no interrupt-map\n", phb->dn); + return 0; + } + imaplen /= sizeof(u32); + pr_debug("%pOF : imaplen=%d\n", phb->dn, imaplen); + + if (imaplen < (addrsize + intsize + 1)) + return 0; + + imap += intsize + addrsize; + parent = of_find_node_by_phandle(be32_to_cpup(imap)); + if (!parent) { + pr_debug("%pOF : no imap parent found !\n", phb->dn); + return 0; + } + + if (of_property_read_u32(parent, "#interrupt-cells", &parintsize)) { + pr_debug("%pOF : parent lacks #interrupt-cells!\n", phb->dn); + return 0; + } + + if (of_property_read_u32(parent, "#address-cells", ¶ddrsize)) + paraddrsize = 0; + + return imaplen / (addrsize + intsize + 1 + paraddrsize + parintsize); +} + +static void pcibios_irq_map_init(struct pci_controller *phb) +{ + phb->irq_count = pcibios_irq_map_count(phb); + if (phb->irq_count < PCI_NUM_INTX) + phb->irq_count = PCI_NUM_INTX; + + pr_debug("%pOF : interrupt map #%d\n", phb->dn, phb->irq_count); + + phb->irq_map = kcalloc(phb->irq_count, sizeof(unsigned int), + GFP_KERNEL); +} + +static void pci_irq_map_register(struct pci_dev *pdev, unsigned int virq) +{ + struct pci_controller *phb = pci_bus_to_host(pdev->bus); + int i; + + if (!phb->irq_map) + return; + + for (i = 0; i < phb->irq_count; i++) { + /* + * Look for an empty or an equivalent slot, as INTx + * interrupts can be shared between adapters. + */ + if (phb->irq_map[i] == virq || !phb->irq_map[i]) { + phb->irq_map[i] = virq; + break; + } + } + + if (i == phb->irq_count) + pr_err("PCI:%s all platform interrupts mapped\n", + pci_name(pdev)); +} + +/* + * Clearing the mapped interrupts will also clear the underlying + * mappings of the ESB pages of the interrupts when under XIVE. It is + * a requirement of PowerVM to clear all memory mappings before + * removing a PHB. + */ +static void pci_irq_map_dispose(struct pci_bus *bus) +{ + struct pci_controller *phb = pci_bus_to_host(bus); + int i; + + if (!phb->irq_map) + return; + + pr_debug("PCI: Clearing interrupt mappings for PHB %04x:%02x...\n", + pci_domain_nr(bus), bus->number); + for (i = 0; i < phb->irq_count; i++) + irq_dispose_mapping(phb->irq_map[i]); + + kfree(phb->irq_map); +} + +void pcibios_remove_bus(struct pci_bus *bus) +{ + pci_irq_map_dispose(bus); +} +EXPORT_SYMBOL_GPL(pcibios_remove_bus); + /* * Reads the interrupt pin to determine if interrupt is use by card. * If the interrupt is used, then gets the interrupt line from the @@ -401,6 +510,8 @@ static int pci_read_irq_line(struct pci_dev *pci_dev) pci_dev->irq = virq; + /* Record all interrut mappings for later removal of a PHB */ + pci_irq_map_register(pci_dev, virq); return 0; } @@ -1554,6 +1665,9 @@ void pcibios_scan_phb(struct pci_controller *hose) pr_debug("PCI: Scanning PHB %pOF\n", node); + /* Allocate interrupt mappings array */ + pcibios_irq_map_init(hose); + /* Get some IO space for the new PHB */ pcibios_setup_phb_io_space(hose); From 8f7e57e8e29c4fc788811dd4db96126272b8df91 Mon Sep 17 00:00:00 2001 From: Qinglang Miao Date: Mon, 14 Sep 2020 14:14:11 +0800 Subject: [PATCH 181/645] macintosh: windfarm: use for_each_child_of_node() macro Use for_each_child_of_node() macro instead of open coding it. Signed-off-by: Qinglang Miao Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200914061411.3356-1-miaoqinglang@huawei.com --- drivers/macintosh/windfarm_smu_sat.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/macintosh/windfarm_smu_sat.c b/drivers/macintosh/windfarm_smu_sat.c index cb75dc035616..e46e1153a0b4 100644 --- a/drivers/macintosh/windfarm_smu_sat.c +++ b/drivers/macintosh/windfarm_smu_sat.c @@ -216,8 +216,7 @@ static int wf_sat_probe(struct i2c_client *client, vsens[0] = vsens[1] = -1; isens[0] = isens[1] = -1; - child = NULL; - while ((child = of_get_next_child(dev, child)) != NULL) { + for_each_child_of_node(dev, child) { reg = of_get_property(child, "reg", NULL); loc = of_get_property(child, "location", NULL); if (reg == NULL || loc == NULL) From d53c3dfb23c45f7d4f910c3a3ca84bf0a99c6143 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Mon, 14 Sep 2020 14:52:16 +1000 Subject: [PATCH 182/645] mm: fix exec activate_mm vs TLB shootdown and lazy tlb switching race Reading and modifying current->mm and current->active_mm and switching mm should be done with irqs off, to prevent races seeing an intermediate state. This is similar to commit 38cf307c1f20 ("mm: fix kthread_use_mm() vs TLB invalidate"). At exec-time when the new mm is activated, the old one should usually be single-threaded and no longer used, unless something else is holding an mm_users reference (which may be possible). Absent other mm_users, there is also a race with preemption and lazy tlb switching. Consider the kernel_execve case where the current thread is using a lazy tlb active mm: call_usermodehelper() kernel_execve() old_mm = current->mm; active_mm = current->active_mm; *** preempt *** --------------------> schedule() prev->active_mm = NULL; mmdrop(prev active_mm); ... <-------------------- schedule() current->mm = mm; current->active_mm = mm; if (!old_mm) mmdrop(active_mm); If we switch back to the kernel thread from a different mm, there is a double free of the old active_mm, and a missing free of the new one. Closing this race only requires interrupts to be disabled while ->mm and ->active_mm are being switched, but the TLB problem requires also holding interrupts off over activate_mm. Unfortunately not all archs can do that yet, e.g., arm defers the switch if irqs are disabled and expects finish_arch_post_lock_switch() to be called to complete the flush; um takes a blocking lock in activate_mm(). So as a first step, disable interrupts across the mm/active_mm updates to close the lazy tlb preempt race, and provide an arch option to extend that to activate_mm which allows architectures doing IPI based TLB shootdowns to close the second race. This is a bit ugly, but in the interest of fixing the bug and backporting before all architectures are converted this is a compromise. Signed-off-by: Nicholas Piggin Acked-by: Peter Zijlstra (Intel) Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200914045219.3736466-2-npiggin@gmail.com --- arch/Kconfig | 7 +++++++ fs/exec.c | 17 +++++++++++++++-- 2 files changed, 22 insertions(+), 2 deletions(-) diff --git a/arch/Kconfig b/arch/Kconfig index af14a567b493..94821e3f94d1 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -414,6 +414,13 @@ config MMU_GATHER_NO_GATHER bool depends on MMU_GATHER_TABLE_FREE +config ARCH_WANT_IRQS_OFF_ACTIVATE_MM + bool + help + Temporary select until all architectures can be converted to have + irqs disabled over activate_mm. Architectures that do IPI based TLB + shootdowns should enable this. + config ARCH_HAVE_NMI_SAFE_CMPXCHG bool diff --git a/fs/exec.c b/fs/exec.c index a91003e28eaa..d4fb18baf1fb 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1130,11 +1130,24 @@ static int exec_mmap(struct mm_struct *mm) } task_lock(tsk); - active_mm = tsk->active_mm; membarrier_exec_mmap(mm); - tsk->mm = mm; + + local_irq_disable(); + active_mm = tsk->active_mm; tsk->active_mm = mm; + tsk->mm = mm; + /* + * This prevents preemption while active_mm is being loaded and + * it and mm are being updated, which could cause problems for + * lazy tlb mm refcounting when these are updated by context + * switches. Not all architectures can handle irqs off over + * activate_mm yet. + */ + if (!IS_ENABLED(CONFIG_ARCH_WANT_IRQS_OFF_ACTIVATE_MM)) + local_irq_enable(); activate_mm(active_mm, mm); + if (IS_ENABLED(CONFIG_ARCH_WANT_IRQS_OFF_ACTIVATE_MM)) + local_irq_enable(); tsk->mm->vmacache_seqnum = 0; vmacache_flush(tsk); task_unlock(tsk); From 66acd46080bd9e5ad2be4b0eb1d498d5145d058e Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Mon, 14 Sep 2020 14:52:17 +1000 Subject: [PATCH 183/645] powerpc: select ARCH_WANT_IRQS_OFF_ACTIVATE_MM powerpc uses IPIs in some situations to switch a kernel thread away from a lazy tlb mm, which is subject to the TLB flushing race described in the changelog introducing ARCH_WANT_IRQS_OFF_ACTIVATE_MM. Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200914045219.3736466-3-npiggin@gmail.com --- arch/powerpc/Kconfig | 1 + arch/powerpc/include/asm/mmu_context.h | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 1f48bbfb3ce9..65cb32211574 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -149,6 +149,7 @@ config PPC select ARCH_USE_QUEUED_RWLOCKS if PPC_QUEUED_SPINLOCKS select ARCH_USE_QUEUED_SPINLOCKS if PPC_QUEUED_SPINLOCKS select ARCH_WANT_IPC_PARSE_VERSION + select ARCH_WANT_IRQS_OFF_ACTIVATE_MM select ARCH_WEAK_RELEASE_ACQUIRE select BINFMT_ELF select BUILDTIME_TABLE_SORT diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index 7f3658a97384..e02aa793420b 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -244,7 +244,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, */ static inline void activate_mm(struct mm_struct *prev, struct mm_struct *next) { - switch_mm(prev, next, current); + switch_mm_irqs_off(prev, next, current); } /* We don't currently use enter_lazy_tlb() for anything */ From bafb056ce27940c9994ea905336aa8f27b4f7275 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Mon, 14 Sep 2020 14:52:18 +1000 Subject: [PATCH 184/645] sparc64: remove mm_cpumask clearing to fix kthread_use_mm race The de facto (and apparently uncommented) standard for using an mm had, thanks to this code in sparc if nothing else, been that you must have a reference on mm_users *and that reference must have been obtained with mmget()*, i.e., from a thread with a reference to mm_users that had used the mm. The introduction of mmget_not_zero() in commit d2005e3f41d4 ("userfaultfd: don't pin the user memory in userfaultfd_file_create()") allowed mm_count holders to aoperate on user mappings asynchronously from the actual threads using the mm, but they were not to load those mappings into their TLB (i.e., walking vmas and page tables is okay, kthread_use_mm() is not). io_uring 2b188cc1bb857 ("Add io_uring IO interface") added code which does a kthread_use_mm() from a mmget_not_zero() refcount. The problem with this is code which previously assumed mm == current->mm and mm->mm_users == 1 implies the mm will remain single-threaded at least until this thread creates another mm_users reference, has now broken. arch/sparc/kernel/smp_64.c: if (atomic_read(&mm->mm_users) == 1) { cpumask_copy(mm_cpumask(mm), cpumask_of(cpu)); goto local_flush_and_out; } vs fs/io_uring.c if (unlikely(!(ctx->flags & IORING_SETUP_SQPOLL) || !mmget_not_zero(ctx->sqo_mm))) return -EFAULT; kthread_use_mm(ctx->sqo_mm); mmget_not_zero() could come in right after the mm_users == 1 test, then kthread_use_mm() which sets its CPU in the mm_cpumask. That update could be lost if cpumask_copy() occurs afterward. I propose we fix this by allowing mmget_not_zero() to be a first-class reference, and not have this obscure undocumented and unchecked restriction. The basic fix for sparc64 is to remove its mm_cpumask clearing code. The optimisation could be effectively restored by sending IPIs to mm_cpumask members and having them remove themselves from mm_cpumask. This is more tricky so I leave it as an exercise for someone with a sparc64 SMP. powerpc has a (currently similarly broken) example. Signed-off-by: Nicholas Piggin Acked-by: David S. Miller Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200914045219.3736466-4-npiggin@gmail.com --- arch/sparc/kernel/smp_64.c | 65 ++++++++------------------------------ 1 file changed, 14 insertions(+), 51 deletions(-) diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index e286e2badc8a..e38d8bf454e8 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -1039,38 +1039,9 @@ void smp_fetch_global_pmu(void) * are flush_tlb_*() routines, and these run after flush_cache_*() * which performs the flushw. * - * The SMP TLB coherency scheme we use works as follows: - * - * 1) mm->cpu_vm_mask is a bit mask of which cpus an address - * space has (potentially) executed on, this is the heuristic - * we use to avoid doing cross calls. - * - * Also, for flushing from kswapd and also for clones, we - * use cpu_vm_mask as the list of cpus to make run the TLB. - * - * 2) TLB context numbers are shared globally across all processors - * in the system, this allows us to play several games to avoid - * cross calls. - * - * One invariant is that when a cpu switches to a process, and - * that processes tsk->active_mm->cpu_vm_mask does not have the - * current cpu's bit set, that tlb context is flushed locally. - * - * If the address space is non-shared (ie. mm->count == 1) we avoid - * cross calls when we want to flush the currently running process's - * tlb state. This is done by clearing all cpu bits except the current - * processor's in current->mm->cpu_vm_mask and performing the - * flush locally only. This will force any subsequent cpus which run - * this task to flush the context from the local tlb if the process - * migrates to another cpu (again). - * - * 3) For shared address spaces (threads) and swapping we bite the - * bullet for most cases and perform the cross call (but only to - * the cpus listed in cpu_vm_mask). - * - * The performance gain from "optimizing" away the cross call for threads is - * questionable (in theory the big win for threads is the massive sharing of - * address space state across processors). + * mm->cpu_vm_mask is a bit mask of which cpus an address + * space has (potentially) executed on, this is the heuristic + * we use to limit cross calls. */ /* This currently is only used by the hugetlb arch pre-fault @@ -1080,18 +1051,13 @@ void smp_fetch_global_pmu(void) void smp_flush_tlb_mm(struct mm_struct *mm) { u32 ctx = CTX_HWBITS(mm->context); - int cpu = get_cpu(); - if (atomic_read(&mm->mm_users) == 1) { - cpumask_copy(mm_cpumask(mm), cpumask_of(cpu)); - goto local_flush_and_out; - } + get_cpu(); smp_cross_call_masked(&xcall_flush_tlb_mm, ctx, 0, 0, mm_cpumask(mm)); -local_flush_and_out: __flush_tlb_mm(ctx, SECONDARY_CONTEXT); put_cpu(); @@ -1114,17 +1080,15 @@ void smp_flush_tlb_pending(struct mm_struct *mm, unsigned long nr, unsigned long { u32 ctx = CTX_HWBITS(mm->context); struct tlb_pending_info info; - int cpu = get_cpu(); + + get_cpu(); info.ctx = ctx; info.nr = nr; info.vaddrs = vaddrs; - if (mm == current->mm && atomic_read(&mm->mm_users) == 1) - cpumask_copy(mm_cpumask(mm), cpumask_of(cpu)); - else - smp_call_function_many(mm_cpumask(mm), tlb_pending_func, - &info, 1); + smp_call_function_many(mm_cpumask(mm), tlb_pending_func, + &info, 1); __flush_tlb_pending(ctx, nr, vaddrs); @@ -1134,14 +1098,13 @@ void smp_flush_tlb_pending(struct mm_struct *mm, unsigned long nr, unsigned long void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr) { unsigned long context = CTX_HWBITS(mm->context); - int cpu = get_cpu(); - if (mm == current->mm && atomic_read(&mm->mm_users) == 1) - cpumask_copy(mm_cpumask(mm), cpumask_of(cpu)); - else - smp_cross_call_masked(&xcall_flush_tlb_page, - context, vaddr, 0, - mm_cpumask(mm)); + get_cpu(); + + smp_cross_call_masked(&xcall_flush_tlb_page, + context, vaddr, 0, + mm_cpumask(mm)); + __flush_tlb_page(context, vaddr); put_cpu(); From a665eec0a22e11cdde708c1c256a465ebe768047 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Mon, 14 Sep 2020 14:52:19 +1000 Subject: [PATCH 185/645] powerpc/64s/radix: Fix mm_cpumask trimming race vs kthread_use_mm Commit 0cef77c7798a7 ("powerpc/64s/radix: flush remote CPUs out of single-threaded mm_cpumask") added a mechanism to trim the mm_cpumask of a process under certain conditions. One of the assumptions is that mm_users would not be incremented via a reference outside the process context with mmget_not_zero() then go on to kthread_use_mm() via that reference. That invariant was broken by io_uring code (see previous sparc64 fix), but I'll point Fixes: to the original powerpc commit because we are changing that assumption going forward, so this will make backports match up. Fix this by no longer relying on that assumption, but by having each CPU check the mm is not being used, and clearing their own bit from the mask only if it hasn't been switched-to by the time the IPI is processed. This relies on commit 38cf307c1f20 ("mm: fix kthread_use_mm() vs TLB invalidate") and ARCH_WANT_IRQS_OFF_ACTIVATE_MM to disable irqs over mm switch sequences. Fixes: 0cef77c7798a7 ("powerpc/64s/radix: flush remote CPUs out of single-threaded mm_cpumask") Signed-off-by: Nicholas Piggin Reviewed-by: Michael Ellerman Depends-on: 38cf307c1f20 ("mm: fix kthread_use_mm() vs TLB invalidate") Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200914045219.3736466-5-npiggin@gmail.com --- arch/powerpc/include/asm/tlb.h | 13 ------------- arch/powerpc/mm/book3s64/radix_tlb.c | 23 ++++++++++++++++------- 2 files changed, 16 insertions(+), 20 deletions(-) diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h index fbc6f3002f23..d97f061fecac 100644 --- a/arch/powerpc/include/asm/tlb.h +++ b/arch/powerpc/include/asm/tlb.h @@ -66,19 +66,6 @@ static inline int mm_is_thread_local(struct mm_struct *mm) return false; return cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm)); } -static inline void mm_reset_thread_local(struct mm_struct *mm) -{ - WARN_ON(atomic_read(&mm->context.copros) > 0); - /* - * It's possible for mm_access to take a reference on mm_users to - * access the remote mm from another thread, but it's not allowed - * to set mm_cpumask, so mm_users may be > 1 here. - */ - WARN_ON(current->mm != mm); - atomic_set(&mm->context.active_cpus, 1); - cpumask_clear(mm_cpumask(mm)); - cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm)); -} #else /* CONFIG_PPC_BOOK3S_64 */ static inline int mm_is_thread_local(struct mm_struct *mm) { diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c index 0d233763441f..143b4fd396f0 100644 --- a/arch/powerpc/mm/book3s64/radix_tlb.c +++ b/arch/powerpc/mm/book3s64/radix_tlb.c @@ -645,19 +645,29 @@ static void do_exit_flush_lazy_tlb(void *arg) struct mm_struct *mm = arg; unsigned long pid = mm->context.id; + /* + * A kthread could have done a mmget_not_zero() after the flushing CPU + * checked mm_is_singlethreaded, and be in the process of + * kthread_use_mm when interrupted here. In that case, current->mm will + * be set to mm, because kthread_use_mm() setting ->mm and switching to + * the mm is done with interrupts off. + */ if (current->mm == mm) - return; /* Local CPU */ + goto out_flush; if (current->active_mm == mm) { - /* - * Must be a kernel thread because sender is single-threaded. - */ - BUG_ON(current->mm); + WARN_ON_ONCE(current->mm != NULL); + /* Is a kernel thread and is using mm as the lazy tlb */ mmgrab(&init_mm); - switch_mm(mm, &init_mm, current); current->active_mm = &init_mm; + switch_mm_irqs_off(mm, &init_mm, current); mmdrop(mm); } + + atomic_dec(&mm->context.active_cpus); + cpumask_clear_cpu(smp_processor_id(), mm_cpumask(mm)); + +out_flush: _tlbiel_pid(pid, RIC_FLUSH_ALL); } @@ -672,7 +682,6 @@ static void exit_flush_lazy_tlbs(struct mm_struct *mm) */ smp_call_function_many(mm_cpumask(mm), do_exit_flush_lazy_tlb, (void *)mm, 1); - mm_reset_thread_local(mm); } void radix__flush_tlb_mm(struct mm_struct *mm) From ca78ef2f08ccfa29b711d644964cdf9d7ace15e5 Mon Sep 17 00:00:00 2001 From: Vaibhav Jain Date: Sat, 12 Sep 2020 13:44:51 +0530 Subject: [PATCH 186/645] powerpc/papr_scm: Fix warning triggered by perf_stats_show() A warning is reported by the kernel in case perf_stats_show() returns an error code. The warning is of the form below: papr_scm ibm,persistent-memory:ibm,pmemory@44100001: Failed to query performance stats, Err:-10 dev_attr_show: perf_stats_show+0x0/0x1c0 [papr_scm] returned bad count fill_read_buffer: dev_attr_show+0x0/0xb0 returned bad count On investigation it looks like that the compiler is silently truncating the return value of drc_pmem_query_stats() from 'long' to 'int', since the variable used to store the return code 'rc' is an 'int'. This truncated value is then returned back as a 'ssize_t' back from perf_stats_show() to 'dev_attr_show()' which thinks of it as a large unsigned number and triggers this warning.. To fix this we update the type of variable 'rc' from 'int' to 'ssize_t' that prevents the compiler from truncating the return value of drc_pmem_query_stats() and returning correct signed value back from perf_stats_show(). Fixes: 2d02bf835e57 ("powerpc/papr_scm: Fetch nvdimm performance stats from PHYP") Signed-off-by: Vaibhav Jain Reviewed-by: Ira Weiny Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200912081451.66225-1-vaibhav@linux.ibm.com --- arch/powerpc/platforms/pseries/papr_scm.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index a88a707a608a..5493bc847bd0 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -785,7 +785,8 @@ static int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc, static ssize_t perf_stats_show(struct device *dev, struct device_attribute *attr, char *buf) { - int index, rc; + int index; + ssize_t rc; struct seq_buf s; struct papr_scm_perf_stat *stat; struct papr_scm_perf_stats *stats; @@ -820,7 +821,7 @@ static ssize_t perf_stats_show(struct device *dev, free_stats: kfree(stats); - return rc ? rc : seq_buf_used(&s); + return rc ? rc : (ssize_t)seq_buf_used(&s); } DEVICE_ATTR_ADMIN_RO(perf_stats); From 3db8715ec9dc1d32ecafc67af9fb96508c98efe5 Mon Sep 17 00:00:00 2001 From: Wang Wensheng Date: Mon, 14 Sep 2020 12:26:15 +0000 Subject: [PATCH 187/645] drivers/macintosh/smu.c: Fix undeclared symbol warning Make kernel with `C=2`: drivers/macintosh/smu.c:1018:30: warning: symbol '__smu_get_sdb_partition' was not declared. Should it be static? Reported-by: Hulk Robot Signed-off-by: Wang Wensheng Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200914122615.65669-1-wangwensheng4@huawei.com --- drivers/macintosh/smu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/macintosh/smu.c b/drivers/macintosh/smu.c index 23f1f41c8602..ca2a0bc5c33e 100644 --- a/drivers/macintosh/smu.c +++ b/drivers/macintosh/smu.c @@ -1015,7 +1015,7 @@ static struct smu_sdbp_header *smu_create_sdb_partition(int id) /* Note: Only allowed to return error code in pointers (using ERR_PTR) * when interruptible is 1 */ -const struct smu_sdbp_header *__smu_get_sdb_partition(int id, +static const struct smu_sdbp_header *__smu_get_sdb_partition(int id, unsigned int *size, int interruptible) { char pname[32]; From 3babbe447d76ac2919ec4d0eb3b0adfb22f5b03c Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Fri, 7 Aug 2020 13:15:16 +0530 Subject: [PATCH 188/645] sched/topology: Allow archs to override cpu_smt_mask cpu_smt_mask tracks topology_sibling_cpumask. This would be good for most architectures. One of the users of cpu_smt_mask(), would be to identify idle-cores. On Power9, a pair of SMT4 cores can be presented by the firmware as a SMT8 core for backward compatibility reasons. powerpc allows LPARs to be live migrated from Power8 to Power9. Do note Power8 had only SMT8 cores. Existing software which has been developed/configured for Power8 would expect to see SMT8 core. Maintaining the illusion of SMT8 core is a requirement to make that work. In order to maintain above userspace backward compatibility with previous versions of processor, Power9 onwards there is option to the firmware to advertise a pair of SMT4 cores as a fused cores aka SMT8 core. On Power9 this pair shares the L2 cache as well. However, from the scheduler's point of view, a core should be determined by SMT4, since its a completely independent unit of compute. Hence allow powerpc architecture to override the default cpu_smt_mask() to point to the SMT4 cores in a SMT8 mode. This will ensure the scheduler is always given the right information. Acked-by: Peter Zijlstra (Intel) Signed-off-by: Srikar Dronamraju Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200807074517.27957-1-srikar@linux.vnet.ibm.com --- include/linux/topology.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/topology.h b/include/linux/topology.h index 608fa4aadf0e..ad03df1cc266 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -198,7 +198,7 @@ static inline int cpu_to_mem(int cpu) #define topology_die_cpumask(cpu) cpumask_of(cpu) #endif -#ifdef CONFIG_SCHED_SMT +#if defined(CONFIG_SCHED_SMT) && !defined(cpu_smt_mask) static inline const struct cpumask *cpu_smt_mask(int cpu) { return topology_sibling_cpumask(cpu); From f3232321db58480804f80d59aeb651a5c859a200 Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Fri, 7 Aug 2020 13:15:17 +0530 Subject: [PATCH 189/645] powerpc/topology: Override cpu_smt_mask On Power9, a pair of SMT4 cores can be presented by the firmware as a SMT8 core for backward compatibility reasons, with the fusion of two SMT4 cores. Powerpc allows LPARs to be live migrated from Power8 to Power9. Existing software developed/configured for Power8, expects to see a SMT8 core. In order to maintain userspace backward compatibility (with Power8 chips in case of Power9) in enterprise Linux systems, the topology_sibling_cpumask has to be set to SMT8 core. cpu_smt_mask() should generally point to the cpu mask of the SMT4 core. Hence override the default cpu_smt_mask() to be powerpc specific allowing for better scheduling behaviour on Power. schbench (latency measured in usecs, so lesser is better) Without patch With patch Latency percentiles (usec) Latency percentiles (usec) 50.0000th: 34 50.0000th: 38 75.0000th: 47 75.0000th: 52 90.0000th: 54 90.0000th: 60 95.0000th: 57 95.0000th: 64 *99.0000th: 62 *99.0000th: 72 99.5000th: 65 99.5000th: 75 99.9000th: 76 99.9000th: 3452 min=0, max=9205 min=0, max=9344 schbench (With Cede disabled) Without patch With patch Latency percentiles (usec) Latency percentiles (usec) 50.0000th: 20 50.0000th: 21 75.0000th: 28 75.0000th: 29 90.0000th: 33 90.0000th: 34 95.0000th: 35 95.0000th: 37 *99.0000th: 40 *99.0000th: 40 99.5000th: 48 99.5000th: 42 99.9000th: 94 99.9000th: 79 min=0, max=791 min=0, max=791 perf bench sched pipe usec/ops : lesser is better Without patch N Min Max Median Avg Stddev 101 5.095113 5.595269 5.204842 5.2298776 0.10762713 5.10 - 5.15 : ################################################## 23% (24) 5.15 - 5.20 : ############################################# 21% (22) 5.20 - 5.25 : ################################################## 23% (24) 5.25 - 5.30 : ######################### 11% (12) 5.30 - 5.35 : ########## 4% (5) 5.35 - 5.40 : ######## 3% (4) 5.40 - 5.45 : ######## 3% (4) 5.45 - 5.50 : #### 1% (2) 5.50 - 5.55 : ## 0% (1) 5.55 - 5.60 : #### 1% (2) With patch N Min Max Median Avg Stddev 101 5.134675 8.524719 5.207658 5.2780985 0.34911969 5.1 - 5.5 : ################################################## 94% (95) 5.5 - 5.8 : ## 3% (4) 5.8 - 6.2 : 0% (1) 6.2 - 6.5 : 6.5 - 6.8 : 6.8 - 7.2 : 7.2 - 7.5 : 7.5 - 7.8 : 7.8 - 8.2 : 8.2 - 8.5 : perf bench sched pipe (cede disabled) usec/ops : lesser is better Without patch N Min Max Median Avg Stddev 101 7.884227 12.576538 7.956474 8.0170722 0.46159054 7.9 - 8.4 : ################################################## 99% (100) 8.4 - 8.8 : 8.8 - 9.3 : 9.3 - 9.8 : 9.8 - 10.2 : 10.2 - 10.7 : 10.7 - 11.2 : 11.2 - 11.6 : 11.6 - 12.1 : 12.1 - 12.6 : With patch N Min Max Median Avg Stddev 101 7.956021 8.217284 8.015615 8.0283866 0.049844967 7.96 - 7.98 : ###################### 12% (13) 7.98 - 8.01 : ################################################## 28% (29) 8.01 - 8.03 : #################################### 20% (21) 8.03 - 8.06 : ######################### 14% (15) 8.06 - 8.09 : ###################### 12% (13) 8.09 - 8.11 : ###### 3% (4) 8.11 - 8.14 : ### 1% (2) 8.14 - 8.17 : ### 1% (2) 8.17 - 8.19 : 8.19 - 8.22 : # 0% (1) Observations: With the patch, the initial run/iteration takes a slight longer time. This can be attributed to the fact that now we pick a CPU from a idle core which could be sleep mode. Once we remove the cede, state the numbers improve in favour of the patch. ebizzy: transactions per second (higher is better) without patch N Min Max Median Avg Stddev 100 1018433 1304470 1193208 1182315.7 60018.733 1018433 - 1047037 : ###### 3% (3) 1047037 - 1075640 : ######## 4% (4) 1075640 - 1104244 : ######## 4% (4) 1104244 - 1132848 : ############### 7% (7) 1132848 - 1161452 : #################################### 17% (17) 1161452 - 1190055 : ########################## 12% (12) 1190055 - 1218659 : ############################################# 21% (21) 1218659 - 1247263 : ################################################## 23% (23) 1247263 - 1275866 : ######## 4% (4) 1275866 - 1304470 : ######## 4% (4) with patch N Min Max Median Avg Stddev 100 967014 1292938 1208819 1185281.8 69815.851 967014 - 999606 : ## 1% (1) 999606 - 1032199 : ## 1% (1) 1032199 - 1064791 : ############ 6% (6) 1064791 - 1097384 : ########## 5% (5) 1097384 - 1129976 : ################## 9% (9) 1129976 - 1162568 : #################### 10% (10) 1162568 - 1195161 : ########################## 13% (13) 1195161 - 1227753 : ############################################ 22% (22) 1227753 - 1260346 : ################################################## 25% (25) 1260346 - 1292938 : ############## 7% (7) Observations: Not much changes, ebizzy is not much impacted. Signed-off-by: Srikar Dronamraju Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200807074517.27957-2-srikar@linux.vnet.ibm.com --- arch/powerpc/include/asm/cputhreads.h | 1 - arch/powerpc/include/asm/smp.h | 13 +++++++++++++ 2 files changed, 13 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h index deb99fd6e060..98c8bd155bf9 100644 --- a/arch/powerpc/include/asm/cputhreads.h +++ b/arch/powerpc/include/asm/cputhreads.h @@ -23,7 +23,6 @@ extern int threads_per_core; extern int threads_per_subcore; extern int threads_shift; -extern bool has_big_cores; extern cpumask_t threads_core_mask; #else #define threads_per_core 1 diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index 81a49566ccd8..b727f5f7b8f9 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -135,6 +135,19 @@ static inline struct cpumask *cpu_smallcore_mask(int cpu) extern int cpu_to_core_id(int cpu); +extern bool has_big_cores; + +#define cpu_smt_mask cpu_smt_mask +#ifdef CONFIG_SCHED_SMT +static inline const struct cpumask *cpu_smt_mask(int cpu) +{ + if (has_big_cores) + return per_cpu(cpu_smallcore_map, cpu); + + return per_cpu(cpu_sibling_map, cpu); +} +#endif /* CONFIG_SCHED_SMT */ + /* Since OpenPIC has only 4 IPIs, we use slightly different message numbers. * * Make sure this matches openpic_request_IPIs in open_pic.c, or what shows up From 67df77845c181166d4bc324cbb0382f7e81c7631 Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Mon, 17 Aug 2020 11:22:57 +0530 Subject: [PATCH 190/645] powerpc/numa: Restrict possible nodes based on platform As per draft LoPAPR (Revision 2.9_pre7), section B.5.3 "Run Time Abstraction Services (RTAS) Node" available at: https://openpowerfoundation.org/wp-content/uploads/2020/07/LoPAR-20200611.pdf ... there are 2 device tree properties: "ibm,max-associativity-domains" which defines the maximum number of domains that the firmware i.e PowerVM can support. and: "ibm,current-associativity-domains" which defines the maximum number of domains that the current platform can support. The value of "ibm,max-associativity-domains" is always greater than or equal to "ibm,current-associativity-domains" property. If the latter property is not available, use "ibm,max-associativity-domain" as a fallback. In this yet to be released LoPAPR, "ibm,current-associativity-domains" is mentioned in page 833 / B.5.3 which is covered under under "Appendix B. System Binding" section Currently powerpc uses the "ibm,max-associativity-domains" property while setting the possible number of nodes. This is currently set at 32. However the possible number of nodes for a platform may be significantly less. Hence set the possible number of nodes based on "ibm,current-associativity-domains" property. Nathan Lynch had raised a valid concern that post LPM (Live Partition Migration), a user could DLPAR add processors and memory after LPM with "new" associativity properties: https://lore.kernel.org/linuxppc-dev/871rljfet9.fsf@linux.ibm.com/t/#u He also pointed out that "ibm,max-associativity-domains" has the same contents on all currently available PowerVM systems, unlike "ibm,current-associativity-domains" and hence may be better able to handle the new NUMA associativity properties. However with the recent commit dbce45628085 ("powerpc/numa: Limit possible nodes to within num_possible_nodes"), all new NUMA associativity properties are capped to initially set nr_node_ids. Hence this commit should be safe with any new DLPAR add post LPM. $ lsprop /proc/device-tree/rtas/ibm,*associ*-domains /proc/device-tree/rtas/ibm,current-associativity-domains 00000005 00000001 00000002 00000002 00000002 00000010 /proc/device-tree/rtas/ibm,max-associativity-domains 00000005 00000001 00000008 00000020 00000020 00000100 $ cat /sys/devices/system/node/possible ##Before patch 0-31 $ cat /sys/devices/system/node/possible ##After patch 0-1 Note the maximum nodes this platform can support is only 2 but the possible nodes is set to 32. This is important because lot of kernel and user space code allocate structures for all possible nodes leading to a lot of memory that is allocated but not used. I ran a simple experiment to create and destroy 100 memory cgroups on boot on a 8 node machine (Power8 Alpine). Before patch: free -k at boot total used free shared buff/cache available Mem: 523498176 4106816 518820608 22272 570752 516606720 Swap: 4194240 0 4194240 free -k after creating 100 memory cgroups total used free shared buff/cache available Mem: 523498176 4628416 518246464 22336 623296 516058688 Swap: 4194240 0 4194240 free -k after destroying 100 memory cgroups total used free shared buff/cache available Mem: 523498176 4697408 518173760 22400 627008 515987904 Swap: 4194240 0 4194240 After patch: free -k at boot total used free shared buff/cache available Mem: 523498176 3969472 518933888 22272 594816 516731776 Swap: 4194240 0 4194240 free -k after creating 100 memory cgroups total used free shared buff/cache available Mem: 523498176 4181888 518676096 22208 640192 516496448 Swap: 4194240 0 4194240 free -k after destroying 100 memory cgroups total used free shared buff/cache available Mem: 523498176 4232320 518619904 22272 645952 516443264 Swap: 4194240 0 4194240 Observations: Fixed kernel takes 137344 kb (4106816-3969472) less to boot. Fixed kernel takes 309184 kb (4628416-4181888-137344) less to create 100 memcgs. Signed-off-by: Srikar Dronamraju [mpe: Reformat change log a bit for readability] Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200817055257.110873-1-srikar@linux.vnet.ibm.com --- arch/powerpc/mm/numa.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 1f61fa2148b5..5ddc83ba20f4 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -900,10 +900,19 @@ static void __init find_possible_nodes(void) if (!rtas) return; - if (of_property_read_u32_index(rtas, - "ibm,max-associativity-domains", + if (of_property_read_u32_index(rtas, "ibm,current-associativity-domains", + min_common_depth, &numnodes)) { + /* + * ibm,current-associativity-domains is a fairly recent + * property. If it doesn't exist, then fallback on + * ibm,max-associativity-domains. Current denotes what the + * platform can support compared to max which denotes what the + * Hypervisor can support. + */ + if (of_property_read_u32_index(rtas, "ibm,max-associativity-domains", min_common_depth, &numnodes)) - goto out; + goto out; + } for (i = 0; i < numnodes; i++) { if (!node_possible(i)) From a874f1005ef5dfe53dfd8cda59a6600e89986ecd Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Tue, 18 Aug 2020 13:41:02 +0530 Subject: [PATCH 191/645] powerpc/numa: Set numa_node for all possible cpus A Powerpc system with multiple possible nodes and with CONFIG_NUMA enabled always used to have a node 0, even if node 0 does not any cpus or memory attached to it. As per PAPR, node affinity of a cpu is only available once its present / online. For all cpus that are possible but not present, cpu_to_node() would point to node 0. To ensure a cpuless, memoryless dummy node is not online, powerpc need to make sure all possible but not present cpu_to_node are set to a proper node. Signed-off-by: Srikar Dronamraju Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200818081104.57888-2-srikar@linux.vnet.ibm.com --- arch/powerpc/mm/numa.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 5ddc83ba20f4..f63e1a41402f 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -507,6 +507,11 @@ static int numa_setup_cpu(unsigned long lcpu) int fcpu = cpu_first_thread_sibling(lcpu); int nid = NUMA_NO_NODE; + if (!cpu_present(lcpu)) { + set_cpu_numa_node(lcpu, first_online_node); + return first_online_node; + } + /* * If a valid cpu-to-node mapping is already available, use it * directly instead of querying the firmware, since it represents @@ -944,8 +949,17 @@ void __init mem_topology_setup(void) reset_numa_cpu_lookup_table(); - for_each_present_cpu(cpu) + for_each_possible_cpu(cpu) { + /* + * Powerpc with CONFIG_NUMA always used to have a node 0, + * even if it was memoryless or cpuless. For all cpus that + * are possible but not present, cpu_to_node() would point + * to node 0. To remove a cpuless, memoryless dummy node, + * powerpc need to make sure all possible but not present + * cpu_to_node are set to a proper node. + */ numa_setup_cpu(cpu); + } } void __init initmem_init(void) From 6398eaa268168b528dd1d3d0e70e61e9c13bea23 Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Tue, 18 Aug 2020 13:41:03 +0530 Subject: [PATCH 192/645] powerpc/numa: Prefer node id queried from vphn Node id queried from the static device tree may not be correct. For example: it may always show 0 on a shared processor. Hence prefer the node id queried from vphn and fallback on the device tree based node id if vphn query fails. Signed-off-by: Srikar Dronamraju Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200818081104.57888-3-srikar@linux.vnet.ibm.com --- arch/powerpc/mm/numa.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index f63e1a41402f..9f0127cfb978 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -728,21 +728,22 @@ static int __init parse_numa_properties(void) */ for_each_present_cpu(i) { struct device_node *cpu; - int nid; - - cpu = of_get_cpu_node(i, NULL); - BUG_ON(!cpu); - nid = of_node_to_nid_single(cpu); - of_node_put(cpu); + int nid = vphn_get_nid(i); /* * Don't fall back to default_nid yet -- we will plug * cpus into nodes once the memory scan has discovered * the topology. */ - if (nid < 0) - continue; - node_set_online(nid); + if (nid == NUMA_NO_NODE) { + cpu = of_get_cpu_node(i, NULL); + BUG_ON(!cpu); + nid = of_node_to_nid_single(cpu); + of_node_put(cpu); + } + + if (likely(nid > 0)) + node_set_online(nid); } get_n_mem_cells(&n_mem_addr_cells, &n_mem_size_cells); From e75130f20b1f48e04ccc806aea01f0a361f9cb6b Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Tue, 18 Aug 2020 13:41:04 +0530 Subject: [PATCH 193/645] powerpc/numa: Offline memoryless cpuless node 0 Currently Linux kernel with CONFIG_NUMA on a system with multiple possible nodes, marks node 0 as online at boot. However in practice, there are systems which have node 0 as memoryless and cpuless. This can cause numa_balancing to be enabled on systems with only one node with memory and CPUs. The existence of this dummy node which is cpuless and memoryless node can confuse users/scripts looking at output of lscpu / numactl. By marking, node 0 as offline, lets stop assuming that node 0 is always online. If node 0 has CPU or memory that are online, node 0 will again be set as online. v5.8 available: 2 nodes (0,2) node 0 cpus: node 0 size: 0 MB node 0 free: 0 MB node 2 cpus: 0 1 2 3 4 5 6 7 node 2 size: 32625 MB node 2 free: 31490 MB node distances: node 0 2 0: 10 20 2: 20 10 proc and sys files ------------------ /sys/devices/system/node/online: 0,2 /proc/sys/kernel/numa_balancing: 1 /sys/devices/system/node/has_cpu: 2 /sys/devices/system/node/has_memory: 2 /sys/devices/system/node/has_normal_memory: 2 /sys/devices/system/node/possible: 0-31 v5.8 + patch ------------------ available: 1 nodes (2) node 2 cpus: 0 1 2 3 4 5 6 7 node 2 size: 32625 MB node 2 free: 31487 MB node distances: node 2 2: 10 proc and sys files ------------------ /sys/devices/system/node/online: 2 /proc/sys/kernel/numa_balancing: 0 /sys/devices/system/node/has_cpu: 2 /sys/devices/system/node/has_memory: 2 /sys/devices/system/node/has_normal_memory: 2 /sys/devices/system/node/possible: 0-31 Example of a node with online CPUs/memory on node 0. (Same o/p with and without patch) numactl -H available: 4 nodes (0-3) node 0 cpus: 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 node 0 size: 32482 MB node 0 free: 22994 MB node 1 cpus: 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 node 1 size: 0 MB node 1 free: 0 MB node 2 cpus: 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 node 2 size: 0 MB node 2 free: 0 MB node 3 cpus: 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 node 3 size: 0 MB node 3 free: 0 MB node distances: node 0 1 2 3 0: 10 20 40 40 1: 20 10 40 40 2: 40 40 10 20 3: 40 40 20 10 Note: On Powerpc, cpu_to_node of possible but not present cpus would previously return 0. Hence this commit depends on commit ("powerpc/numa: Set numa_node for all possible cpus") and commit ("powerpc/numa: Prefer node id queried from vphn"). Without the 2 commits, Powerpc system might crash. 1. User space applications like Numactl, lscpu, that parse the sysfs tend to believe there is an extra online node. This tends to confuse users and applications. Other user space applications start believing that system was not able to use all the resources (i.e missing resources) or the system was not setup correctly. 2. Also existence of dummy node also leads to inconsistent information. The number of online nodes is inconsistent with the information in the device-tree and resource-dump 3. When the dummy node is present, single node non-Numa systems end up showing up as NUMA systems and numa_balancing gets enabled. This will mean we take the hit from the unnecessary numa hinting faults. Signed-off-by: Srikar Dronamraju Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200818081104.57888-4-srikar@linux.vnet.ibm.com --- arch/powerpc/mm/numa.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 9f0127cfb978..481951ac3e55 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -933,6 +933,16 @@ void __init mem_topology_setup(void) { int cpu; + /* + * Linux/mm assumes node 0 to be online at boot. However this is not + * true on PowerPC, where node 0 is similar to any other node, it + * could be cpuless, memoryless node. So force node 0 to be offline + * for now. This will prevent cpuless, memoryless node 0 showing up + * unnecessarily as online. If a node has cpus or memory that need + * to be online, then node will anyway be marked online. + */ + node_set_offline(0); + if (parse_numa_properties()) setup_nonnuma(); From 980d5f9ab36b6cfe473a8371a7e11bd168c9e630 Mon Sep 17 00:00:00 2001 From: Alexander Egorenkov Date: Wed, 2 Sep 2020 16:52:06 +0200 Subject: [PATCH 194/645] s390/boot: enable .bss section for compressed kernel - Support static uninitialized variables in compressed kernel. - Remove chkbss script - Get rid of workarounds for not having .bss section Signed-off-by: Alexander Egorenkov Reviewed-by: Vasily Gorbik Signed-off-by: Vasily Gorbik --- arch/s390/boot/Makefile | 4 ---- arch/s390/boot/compressed/Makefile | 4 ---- arch/s390/boot/compressed/decompressor.c | 1 - arch/s390/boot/compressed/vmlinux.lds.S | 22 +++++++++++++--------- arch/s390/boot/head.S | 6 ++++++ arch/s390/boot/ipl_parm.c | 4 ++-- arch/s390/boot/startup.c | 3 +++ arch/s390/kernel/setup.c | 2 +- arch/s390/scripts/Makefile.chkbss | 20 -------------------- 9 files changed, 25 insertions(+), 41 deletions(-) delete mode 100644 arch/s390/scripts/Makefile.chkbss diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile index 45b33b83de08..41a64b8dce25 100644 --- a/arch/s390/boot/Makefile +++ b/arch/s390/boot/Makefile @@ -73,7 +73,3 @@ $(obj)/startup.a: $(OBJECTS) FORCE install: sh -x $(srctree)/$(obj)/install.sh $(KERNELRELEASE) $(obj)/bzImage \ System.map "$(INSTALL_PATH)" - -chkbss := $(obj-y) -chkbss-target := startup.a -include $(srctree)/arch/s390/scripts/Makefile.chkbss diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile index fa529c5b4486..b235ed95a3d8 100644 --- a/arch/s390/boot/compressed/Makefile +++ b/arch/s390/boot/compressed/Makefile @@ -62,7 +62,3 @@ $(obj)/vmlinux.bin.xz: $(vmlinux.bin.all-y) FORCE OBJCOPYFLAGS_piggy.o := -I binary -O elf64-s390 -B s390:64-bit --rename-section .data=.vmlinux.bin.compressed $(obj)/piggy.o: $(obj)/vmlinux.bin$(suffix-y) FORCE $(call if_changed,objcopy) - -chkbss := $(filter-out piggy.o info.o, $(obj-y)) -chkbss-target := vmlinux.bin -include $(srctree)/arch/s390/scripts/Makefile.chkbss diff --git a/arch/s390/boot/compressed/decompressor.c b/arch/s390/boot/compressed/decompressor.c index 368fd372c875..3061b11c4d27 100644 --- a/arch/s390/boot/compressed/decompressor.c +++ b/arch/s390/boot/compressed/decompressor.c @@ -16,7 +16,6 @@ * gzip declarations */ #define STATIC static -#define STATIC_RW_DATA static __section(.data) #undef memset #undef memcpy diff --git a/arch/s390/boot/compressed/vmlinux.lds.S b/arch/s390/boot/compressed/vmlinux.lds.S index 44561b2c3712..9427e2cd0c15 100644 --- a/arch/s390/boot/compressed/vmlinux.lds.S +++ b/arch/s390/boot/compressed/vmlinux.lds.S @@ -58,6 +58,19 @@ SECTIONS BOOT_DATA BOOT_DATA_PRESERVED + /* + * This is the BSS section of the decompressor and not of the decompressed Linux kernel. + * It will consume place in the decompressor's image. + */ + . = ALIGN(8); + .bss : { + _bss = . ; + *(.bss) + *(.bss.*) + *(COMMON) + _ebss = .; + } + /* * uncompressed image info used by the decompressor it should match * struct vmlinux_info. It comes from .vmlinux.info section of @@ -81,15 +94,6 @@ SECTIONS FILL(0xff); . = ALIGN(4096); } - . = ALIGN(256); - .bss : { - _bss = . ; - *(.bss) - *(.bss.*) - *(COMMON) - . = ALIGN(8); /* For convenience during zeroing */ - _ebss = .; - } _end = .; /* Sections to be discarded */ diff --git a/arch/s390/boot/head.S b/arch/s390/boot/head.S index dae10961d072..fd78755d996d 100644 --- a/arch/s390/boot/head.S +++ b/arch/s390/boot/head.S @@ -313,6 +313,12 @@ ENTRY(startup_kdump) spt 6f-.LPG0(%r13) mvc __LC_LAST_UPDATE_TIMER(8),6f-.LPG0(%r13) l %r15,.Lstack-.LPG0(%r13) + // Clear decompressor's BSS section + larl %r2,_bss + slgr %r3,%r3 + larl %r4,_ebss + slgr %r4,%r2 + brasl %r14,memset brasl %r14,verify_facilities brasl %r14,startup_kernel diff --git a/arch/s390/boot/ipl_parm.c b/arch/s390/boot/ipl_parm.c index 8e222a666025..ae230ebd6420 100644 --- a/arch/s390/boot/ipl_parm.c +++ b/arch/s390/boot/ipl_parm.c @@ -21,7 +21,7 @@ unsigned long __bootdata(memory_end); int __bootdata(memory_end_set); int __bootdata(noexec_disabled); -int kaslr_enabled __section(.data); +int kaslr_enabled; static inline int __diag308(unsigned long subcode, void *addr) { @@ -209,7 +209,7 @@ static void modify_fac_list(char *str) check_cleared_facilities(); } -static char command_line_buf[COMMAND_LINE_SIZE] __section(.data); +static char command_line_buf[COMMAND_LINE_SIZE]; void parse_boot_command_line(void) { char *param, *val; diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index 3b3a11f95269..81835483169b 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -120,6 +120,9 @@ static void handle_relocs(unsigned long offset) } } +/* + * This function clears the BSS section of the decompressed Linux kernel and NOT the decompressor's. + */ static void clear_bss_section(void) { memset((void *)vmlinux.default_lma + vmlinux.image_size, 0, vmlinux.bss_size); diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index f04252cb6004..047793902ce6 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -307,7 +307,7 @@ void machine_power_off(void) void (*pm_power_off)(void) = machine_power_off; EXPORT_SYMBOL_GPL(pm_power_off); -void *restart_stack __section(.data); +void *restart_stack; unsigned long stack_alloc(void) { diff --git a/arch/s390/scripts/Makefile.chkbss b/arch/s390/scripts/Makefile.chkbss deleted file mode 100644 index f4f4c2c6dee9..000000000000 --- a/arch/s390/scripts/Makefile.chkbss +++ /dev/null @@ -1,20 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 - -chkbss-target ?= built-in.a -$(obj)/$(chkbss-target): chkbss - -chkbss-files := $(addsuffix .chkbss, $(chkbss)) -clean-files += $(chkbss-files) - -PHONY += chkbss -chkbss: $(addprefix $(obj)/, $(chkbss-files)) - -quiet_cmd_chkbss = CHKBSS $< - cmd_chkbss = \ - if ! $(OBJSIZE) --common $< | $(AWK) 'END { if ($$3) exit 1 }'; then \ - echo "error: $< .bss section is not empty" >&2; exit 1; \ - fi; \ - touch $@; - -$(obj)/%.o.chkbss: $(obj)/%.o - $(call cmd,chkbss) From 48111b4838480d1357783f4231c351bb2ba2d27d Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 15 Sep 2020 12:52:36 +0200 Subject: [PATCH 195/645] s390/mm,ptdump: add proper ifdefs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Use ifdefs instead of IS_ENABLED() to avoid compile error for !PTDUMP_DEBUGFS: arch/s390/mm/dump_pagetables.c: In function ‘pt_dump_init’: arch/s390/mm/dump_pagetables.c:248:64: error: ‘ptdump_fops’ undeclared (first use in this function); did you mean ‘pidfd_fops’? debugfs_create_file("kernel_page_tables", 0400, NULL, NULL, &ptdump_fops); Reported-by: Julian Wiedmann Fixes: 08c8e685c7c9 ("s390: add ARCH_HAS_DEBUG_WX support") Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/mm/dump_pagetables.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c index 052223c92fb1..0356ac6d7dad 100644 --- a/arch/s390/mm/dump_pagetables.c +++ b/arch/s390/mm/dump_pagetables.c @@ -244,8 +244,9 @@ static int pt_dump_init(void) address_markers[VMEMMAP_END_NR].start_address = (unsigned long)vmemmap + vmemmap_size; address_markers[VMALLOC_NR].start_address = VMALLOC_START; address_markers[VMALLOC_END_NR].start_address = VMALLOC_END; - if (IS_ENABLED(CONFIG_PTDUMP_DEBUGFS)) - debugfs_create_file("kernel_page_tables", 0400, NULL, NULL, &ptdump_fops); +#ifdef CONFIG_PTDUMP_DEBUGFS + debugfs_create_file("kernel_page_tables", 0400, NULL, NULL, &ptdump_fops); +#endif /* CONFIG_PTDUMP_DEBUGFS */ return 0; } device_initcall(pt_dump_init); From 4904e1941ee334bf1f90e4017a37f7c8a52b685c Mon Sep 17 00:00:00 2001 From: Niklas Schnelle Date: Tue, 15 Sep 2020 10:42:41 +0200 Subject: [PATCH 196/645] s390/pci: add missing pci_iov.h include this fixes a missing prototype compiler warning spotted by the kernel test robot. Fixes: abb95b7550f8 ("s390/pci: consolidate SR-IOV specific code") Reported-by: kernel test robot Signed-off-by: Niklas Schnelle Signed-off-by: Vasily Gorbik --- arch/s390/pci/pci_iov.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/s390/pci/pci_iov.c b/arch/s390/pci/pci_iov.c index 35fca14ebb35..ead062bf2b41 100644 --- a/arch/s390/pci/pci_iov.c +++ b/arch/s390/pci/pci_iov.c @@ -13,6 +13,8 @@ #include #include +#include "pci_iov.h" + static struct resource iov_res = { .name = "PCI IOV res", .start = 0, From ee4b2ce6d1e3baa412148a7b0889f6643749c665 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Thu, 10 Sep 2020 22:51:17 +0200 Subject: [PATCH 197/645] s390/mm,ptdump: sort markers Kasan configuration options and size of physical memory present could affect kernel memory layout. In particular vmemmap, vmalloc and modules might come before kasan shadow or after it. To make ptdump correctly output markers in the right order markers have to be sorted. To preserve the original order of markers with the same start address avoid using sort() from lib/sort.c (which is not stable sorting algorithm) and sort markers in place. Reviewed-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/mm/dump_pagetables.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c index 0356ac6d7dad..8f9ff7e7187d 100644 --- a/arch/s390/mm/dump_pagetables.c +++ b/arch/s390/mm/dump_pagetables.c @@ -228,6 +228,24 @@ static int ptdump_show(struct seq_file *m, void *v) DEFINE_SHOW_ATTRIBUTE(ptdump); #endif /* CONFIG_PTDUMP_DEBUGFS */ +/* + * Heapsort from lib/sort.c is not a stable sorting algorithm, do a simple + * insertion sort to preserve the original order of markers with the same + * start address. + */ +static void sort_address_markers(void) +{ + struct addr_marker tmp; + int i, j; + + for (i = 1; i < ARRAY_SIZE(address_markers) - 1; i++) { + tmp = address_markers[i]; + for (j = i - 1; j >= 0 && address_markers[j].start_address > tmp.start_address; j--) + address_markers[j + 1] = address_markers[j]; + address_markers[j + 1] = tmp; + } +} + static int pt_dump_init(void) { /* @@ -244,6 +262,7 @@ static int pt_dump_init(void) address_markers[VMEMMAP_END_NR].start_address = (unsigned long)vmemmap + vmemmap_size; address_markers[VMALLOC_NR].start_address = VMALLOC_START; address_markers[VMALLOC_END_NR].start_address = VMALLOC_END; + sort_address_markers(); #ifdef CONFIG_PTDUMP_DEBUGFS debugfs_create_file("kernel_page_tables", 0400, NULL, NULL, &ptdump_fops); #endif /* CONFIG_PTDUMP_DEBUGFS */ From 8f78657c291f9e5ec26a2a9187938b374629d176 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Thu, 10 Sep 2020 22:54:58 +0200 Subject: [PATCH 198/645] s390/kasan: avoid unnecessary moving of vmemmap Currently vmemmap area is unconditionally moved beyond Kasan shadow memory. When Kasan is not enabled vmemmap area position is calculated in setup_memory_end() and depends on limiting factors like ultravisor secure storage limit. Try to follow the same logic with Kasan enabled as well and avoid unnecessary vmemmap area position changes unless it really intersects with Kasan shadow. Reviewed-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/setup.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 047793902ce6..d63b08bacdf9 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -586,11 +586,15 @@ static void __init setup_memory_end(void) /* Take care that memory_end is set and <= vmemmap */ memory_end = min(memory_end ?: max_physmem_end, (unsigned long)vmemmap); #ifdef CONFIG_KASAN - /* fit in kasan shadow memory region between 1:1 and vmemmap */ memory_end = min(memory_end, KASAN_SHADOW_START); - vmemmap = max(vmemmap, (struct page *)KASAN_SHADOW_END); #endif vmemmap_size = SECTION_ALIGN_UP(memory_end / PAGE_SIZE) * sizeof(struct page); +#ifdef CONFIG_KASAN + /* move vmemmap above kasan shadow only if stands in a way */ + if (KASAN_SHADOW_END > (unsigned long)vmemmap && + (unsigned long)vmemmap + vmemmap_size > KASAN_SHADOW_START) + vmemmap = max(vmemmap, (struct page *)KASAN_SHADOW_END); +#endif max_pfn = max_low_pfn = PFN_DOWN(memory_end); memblock_remove(memory_end, ULONG_MAX); From 1d6671ae46e52e383bc6eea8d33bdd32ae61b323 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Fri, 11 Sep 2020 11:38:21 +0200 Subject: [PATCH 199/645] s390/protvirt: parse prot_virt option in the decompressor To make early kernel address space layout definition possible parse prot_virt option in the decompressor and pass it to the uncompressed kernel. This enables kasan to take ultravisor secure storage limit into consideration and pre-define vmalloc position correctly. Signed-off-by: Vasily Gorbik --- arch/s390/boot/ipl_parm.c | 8 ++++++++ arch/s390/boot/uv.c | 3 +++ arch/s390/kernel/setup.c | 3 +-- arch/s390/kernel/uv.c | 40 ++++++++++++++++----------------------- 4 files changed, 28 insertions(+), 26 deletions(-) diff --git a/arch/s390/boot/ipl_parm.c b/arch/s390/boot/ipl_parm.c index ae230ebd6420..92ebc4a58fe2 100644 --- a/arch/s390/boot/ipl_parm.c +++ b/arch/s390/boot/ipl_parm.c @@ -254,6 +254,14 @@ void parse_boot_command_line(void) if (!strcmp(param, "nokaslr")) kaslr_enabled = 0; + +#if IS_ENABLED(CONFIG_KVM) + if (!strcmp(param, "prot_virt")) { + rc = kstrtobool(val, &enabled); + if (!rc && enabled) + prot_virt_host = 1; + } +#endif } } diff --git a/arch/s390/boot/uv.c b/arch/s390/boot/uv.c index f887a479cdc7..a15c033f53ca 100644 --- a/arch/s390/boot/uv.c +++ b/arch/s390/boot/uv.c @@ -7,6 +7,9 @@ #ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST int __bootdata_preserved(prot_virt_guest); #endif +#if IS_ENABLED(CONFIG_KVM) +int __bootdata_preserved(prot_virt_host); +#endif struct uv_info __bootdata_preserved(uv_info); void uv_query_info(void) diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index d63b08bacdf9..dd3fa7039cb0 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -1137,8 +1137,7 @@ void __init setup_arch(char **cmdline_p) free_mem_detect_info(); remove_oldmem(); - if (is_prot_virt_host()) - setup_uv(); + setup_uv(); setup_memory_end(); setup_memory(); dma_contiguous_reserve(memory_end); diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c index d3399b8a9b23..4233245737bd 100644 --- a/arch/s390/kernel/uv.c +++ b/arch/s390/kernel/uv.c @@ -26,33 +26,10 @@ int __bootdata_preserved(prot_virt_guest); struct uv_info __bootdata_preserved(uv_info); #if IS_ENABLED(CONFIG_KVM) -int prot_virt_host; +int __bootdata_preserved(prot_virt_host); EXPORT_SYMBOL(prot_virt_host); EXPORT_SYMBOL(uv_info); -static int __init prot_virt_setup(char *val) -{ - bool enabled; - int rc; - - rc = kstrtobool(val, &enabled); - if (!rc && enabled) - prot_virt_host = 1; - - if (is_prot_virt_guest() && prot_virt_host) { - prot_virt_host = 0; - pr_warn("Protected virtualization not available in protected guests."); - } - - if (prot_virt_host && !test_facility(158)) { - prot_virt_host = 0; - pr_warn("Protected virtualization not supported by the hardware."); - } - - return rc; -} -early_param("prot_virt", prot_virt_setup); - static int __init uv_init(unsigned long stor_base, unsigned long stor_len) { struct uv_cb_init uvcb = { @@ -74,6 +51,21 @@ void __init setup_uv(void) { unsigned long uv_stor_base; + if (!is_prot_virt_host()) + return; + + if (is_prot_virt_guest()) { + prot_virt_host = 0; + pr_warn("Protected virtualization not available in protected guests."); + return; + } + + if (!test_facility(158)) { + prot_virt_host = 0; + pr_warn("Protected virtualization not supported by the hardware."); + return; + } + uv_stor_base = (unsigned long)memblock_alloc_try_nid( uv_info.uv_base_stor_len, SZ_1M, SZ_2G, MEMBLOCK_ALLOC_ACCESSIBLE, NUMA_NO_NODE); From c2314cb2dd4140cb14b79a8139be34459777f421 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Fri, 11 Sep 2020 11:40:21 +0200 Subject: [PATCH 200/645] s390/protvirt: support ultravisor without secure storage limit Avoid potential crash due to lack of secure storage limit. Check that max_sec_stor_addr is not 0 before adjusting vmalloc position. Signed-off-by: Vasily Gorbik --- arch/s390/kernel/uv.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c index 4233245737bd..1a166a1119c0 100644 --- a/arch/s390/kernel/uv.c +++ b/arch/s390/kernel/uv.c @@ -90,7 +90,8 @@ fail: void adjust_to_uv_max(unsigned long *vmax) { - *vmax = min_t(unsigned long, *vmax, uv_info.max_sec_stor_addr); + if (uv_info.max_sec_stor_addr) + *vmax = min_t(unsigned long, *vmax, uv_info.max_sec_stor_addr); } /* From c360c9a238d1754b1ee8f1c3368ef36794e1daab Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Fri, 11 Sep 2020 11:44:47 +0200 Subject: [PATCH 201/645] s390/kasan: support protvirt with 4-level paging Currently the kernel crashes in Kasan instrumentation code if CONFIG_KASAN_S390_4_LEVEL_PAGING is used on protected virtualization capable machine where the ultravisor imposes addressing limitations on the host and those limitations are lower then KASAN_SHADOW_OFFSET. The problem is that Kasan has to know in advance where vmalloc/modules areas would be. With protected virtualization enabled vmalloc/modules areas are moved down to the ultravisor secure storage limit while kasan still expects them at the very end of 4-level paging address space. To fix that make Kasan recognize when protected virtualization is enabled and predefine vmalloc/modules areas position which are compliant with ultravisor secure storage limit. Kasan shadow itself stays in place and might reside above that ultravisor secure storage limit. One slight difference compaired to a kernel without Kasan enabled is that vmalloc/modules areas position is not reverted to default if ultravisor initialization fails. It would still be below the ultravisor secure storage limit. Kernel layout with kasan, 4-level paging and protected virtualization enabled (ultravisor secure storage limit is at 0x0000800000000000): ---[ vmemmap Area Start ]--- 0x0000400000000000-0x0000400080000000 ---[ vmemmap Area End ]--- ---[ vmalloc Area Start ]--- 0x00007fe000000000-0x00007fff80000000 ---[ vmalloc Area End ]--- ---[ Modules Area Start ]--- 0x00007fff80000000-0x0000800000000000 ---[ Modules Area End ]--- ---[ Kasan Shadow Start ]--- 0x0018000000000000-0x001c000000000000 ---[ Kasan Shadow End ]--- 0x001c000000000000-0x0020000000000000 1P PGD I Kernel layout with kasan, 4-level paging and protected virtualization disabled/unsupported: ---[ vmemmap Area Start ]--- 0x0000400000000000-0x0000400060000000 ---[ vmemmap Area End ]--- ---[ Kasan Shadow Start ]--- 0x0018000000000000-0x001c000000000000 ---[ Kasan Shadow End ]--- ---[ vmalloc Area Start ]--- 0x001fffe000000000-0x001fffff80000000 ---[ vmalloc Area End ]--- ---[ Modules Area Start ]--- 0x001fffff80000000-0x0020000000000000 ---[ Modules Area End ]--- Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/kasan.h | 1 + arch/s390/kernel/setup.c | 23 +++++++++------------- arch/s390/kernel/uv.c | 3 +++ arch/s390/mm/kasan_init.c | 36 +++++++++++++++++++++++++++++------ 4 files changed, 43 insertions(+), 20 deletions(-) diff --git a/arch/s390/include/asm/kasan.h b/arch/s390/include/asm/kasan.h index 89d6886040c8..e9bf486de136 100644 --- a/arch/s390/include/asm/kasan.h +++ b/arch/s390/include/asm/kasan.h @@ -19,6 +19,7 @@ extern void kasan_early_init(void); extern void kasan_copy_shadow(pgd_t *dst); extern void kasan_free_early_identity(void); +extern unsigned long kasan_vmax; #else static inline void kasan_early_init(void) { } static inline void kasan_copy_shadow(pgd_t *dst) { } diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index dd3fa7039cb0..ae2f4d946048 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -552,22 +552,17 @@ static void __init setup_memory_end(void) unsigned long vmax, tmp; /* Choose kernel address space layout: 3 or 4 levels. */ - if (IS_ENABLED(CONFIG_KASAN)) { - vmax = IS_ENABLED(CONFIG_KASAN_S390_4_LEVEL_PAGING) - ? _REGION1_SIZE - : _REGION2_SIZE; - } else { - tmp = (memory_end ?: max_physmem_end) / PAGE_SIZE; - tmp = tmp * (sizeof(struct page) + PAGE_SIZE); - if (tmp + vmalloc_size + MODULES_LEN <= _REGION2_SIZE) - vmax = _REGION2_SIZE; /* 3-level kernel page table */ - else - vmax = _REGION1_SIZE; /* 4-level kernel page table */ - } - + tmp = (memory_end ?: max_physmem_end) / PAGE_SIZE; + tmp = tmp * (sizeof(struct page) + PAGE_SIZE); + if (tmp + vmalloc_size + MODULES_LEN <= _REGION2_SIZE) + vmax = _REGION2_SIZE; /* 3-level kernel page table */ + else + vmax = _REGION1_SIZE; /* 4-level kernel page table */ if (is_prot_virt_host()) adjust_to_uv_max(&vmax); - +#ifdef CONFIG_KASAN + vmax = kasan_vmax; +#endif /* module area is at the end of the kernel address space. */ MODULES_END = vmax; MODULES_VADDR = MODULES_END - MODULES_LEN; diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c index 1a166a1119c0..14bd9d58edc9 100644 --- a/arch/s390/kernel/uv.c +++ b/arch/s390/kernel/uv.c @@ -51,6 +51,9 @@ void __init setup_uv(void) { unsigned long uv_stor_base; + /* + * keep these conditions in line with kasan init code has_uv_sec_stor_limit() + */ if (!is_prot_virt_host()) return; diff --git a/arch/s390/mm/kasan_init.c b/arch/s390/mm/kasan_init.c index 1a27a7143349..5646b39c728a 100644 --- a/arch/s390/mm/kasan_init.c +++ b/arch/s390/mm/kasan_init.c @@ -11,7 +11,9 @@ #include #include #include +#include +unsigned long kasan_vmax; static unsigned long segment_pos __initdata; static unsigned long segment_low __initdata; static unsigned long pgalloc_pos __initdata; @@ -256,14 +258,31 @@ static void __init kasan_early_detect_facilities(void) } } +static bool __init has_uv_sec_stor_limit(void) +{ + /* + * keep these conditions in line with setup_uv() + */ + if (!is_prot_virt_host()) + return false; + + if (is_prot_virt_guest()) + return false; + + if (!test_facility(158)) + return false; + + return !!uv_info.max_sec_stor_addr; +} + void __init kasan_early_init(void) { unsigned long untracked_mem_end; unsigned long shadow_alloc_size; + unsigned long vmax_unlimited; unsigned long initrd_end; unsigned long asce_type; unsigned long memsize; - unsigned long vmax; unsigned long pgt_prot = pgprot_val(PAGE_KERNEL_RO); pte_t pte_z; pmd_t pmd_z = __pmd(__pa(kasan_early_shadow_pte) | _SEGMENT_ENTRY); @@ -291,7 +310,9 @@ void __init kasan_early_init(void) BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END, P4D_SIZE)); crst_table_init((unsigned long *)early_pg_dir, _REGION2_ENTRY_EMPTY); - untracked_mem_end = vmax = _REGION1_SIZE; + untracked_mem_end = kasan_vmax = vmax_unlimited = _REGION1_SIZE; + if (has_uv_sec_stor_limit()) + kasan_vmax = min(vmax_unlimited, uv_info.max_sec_stor_addr); asce_type = _ASCE_TYPE_REGION2; } else { /* 3 level paging */ @@ -299,7 +320,7 @@ void __init kasan_early_init(void) BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END, PUD_SIZE)); crst_table_init((unsigned long *)early_pg_dir, _REGION3_ENTRY_EMPTY); - untracked_mem_end = vmax = _REGION2_SIZE; + untracked_mem_end = kasan_vmax = vmax_unlimited = _REGION2_SIZE; asce_type = _ASCE_TYPE_REGION3; } @@ -369,17 +390,20 @@ void __init kasan_early_init(void) /* populate kasan shadow (for identity mapping and zero page mapping) */ kasan_early_vmemmap_populate(__sha(0), __sha(memsize), POPULATE_MAP); if (IS_ENABLED(CONFIG_MODULES)) - untracked_mem_end = vmax - MODULES_LEN; + untracked_mem_end = kasan_vmax - MODULES_LEN; if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) { - untracked_mem_end = vmax - vmalloc_size - MODULES_LEN; + untracked_mem_end = kasan_vmax - vmalloc_size - MODULES_LEN; /* shallowly populate kasan shadow for vmalloc and modules */ kasan_early_vmemmap_populate(__sha(untracked_mem_end), - __sha(vmax), POPULATE_SHALLOW); + __sha(kasan_vmax), POPULATE_SHALLOW); } /* populate kasan shadow for untracked memory */ kasan_early_vmemmap_populate(__sha(max_physmem_end), __sha(untracked_mem_end), POPULATE_ZERO_SHADOW); + kasan_early_vmemmap_populate(__sha(kasan_vmax), + __sha(vmax_unlimited), + POPULATE_ZERO_SHADOW); /* memory allocated for identity mapping structs will be freed later */ pgalloc_freeable = pgalloc_pos; /* populate identity mapping */ From d0fd24bbd27619d7b8d4da26a19a2027931ae9fc Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Mon, 10 Aug 2020 12:48:25 +0530 Subject: [PATCH 202/645] powerpc/smp: Fix a warning under !NEED_MULTIPLE_NODES Fix a build warning in a non CONFIG_NEED_MULTIPLE_NODES "error: _numa_cpu_lookup_table_ undeclared" Signed-off-by: Srikar Dronamraju Reviewed-by: Gautham R. Shenoy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200810071834.92514-2-srikar@linux.vnet.ibm.com --- arch/powerpc/kernel/smp.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 8261999c7d52..d511bf73ade9 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -861,6 +861,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus) GFP_KERNEL, cpu_to_node(cpu)); zalloc_cpumask_var_node(&per_cpu(cpu_core_map, cpu), GFP_KERNEL, cpu_to_node(cpu)); +#ifdef CONFIG_NEED_MULTIPLE_NODES /* * numa_node_id() works after this. */ @@ -869,6 +870,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus) set_cpu_numa_mem(cpu, local_memory_node(numa_cpu_lookup_table[cpu])); } +#endif } /* Init the cpumasks so the boot CPU is related to itself */ From 2ef0ca54d97f40f7621d595ac5479bd7fa076bfa Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Mon, 10 Aug 2020 12:48:26 +0530 Subject: [PATCH 203/645] powerpc/smp: Merge Power9 topology with Power topology A new sched_domain_topology_level was added just for Power9. However the same can be achieved by merging powerpc_topology with power9_topology and makes the code more simpler especially when adding a new sched domain. Signed-off-by: Srikar Dronamraju Reviewed-by: Gautham R. Shenoy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200810071834.92514-3-srikar@linux.vnet.ibm.com --- arch/powerpc/kernel/smp.c | 25 +++---------------------- 1 file changed, 3 insertions(+), 22 deletions(-) diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index d511bf73ade9..1fb98b255b4c 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -1314,7 +1314,7 @@ int setup_profiling_timer(unsigned int multiplier) } #ifdef CONFIG_SCHED_SMT -/* cpumask of CPUs with asymetric SMT dependancy */ +/* cpumask of CPUs with asymmetric SMT dependency */ static int powerpc_smt_flags(void) { int flags = SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES; @@ -1327,14 +1327,6 @@ static int powerpc_smt_flags(void) } #endif -static struct sched_domain_topology_level powerpc_topology[] = { -#ifdef CONFIG_SCHED_SMT - { cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) }, -#endif - { cpu_cpu_mask, SD_INIT_NAME(DIE) }, - { NULL, }, -}; - /* * P9 has a slightly odd architecture where pairs of cores share an L2 cache. * This topology makes it *much* cheaper to migrate tasks between adjacent cores @@ -1362,7 +1354,7 @@ static const struct cpumask *smallcore_smt_mask(int cpu) } #endif -static struct sched_domain_topology_level power9_topology[] = { +static struct sched_domain_topology_level powerpc_topology[] = { #ifdef CONFIG_SCHED_SMT { cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) }, #endif @@ -1387,21 +1379,10 @@ void __init smp_cpus_done(unsigned int max_cpus) #ifdef CONFIG_SCHED_SMT if (has_big_cores) { pr_info("Big cores detected but using small core scheduling\n"); - power9_topology[0].mask = smallcore_smt_mask; powerpc_topology[0].mask = smallcore_smt_mask; } #endif - /* - * If any CPU detects that it's sharing a cache with another CPU then - * use the deeper topology that is aware of this sharing. - */ - if (shared_caches) { - pr_info("Using shared cache scheduler topology\n"); - set_sched_topology(power9_topology); - } else { - pr_info("Using standard scheduler topology\n"); - set_sched_topology(powerpc_topology); - } + set_sched_topology(powerpc_topology); } #ifdef CONFIG_HOTPLUG_CPU From 5e93f16ae48b728775496429c6db53d0bf8cdd9b Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Mon, 10 Aug 2020 12:48:27 +0530 Subject: [PATCH 204/645] powerpc/smp: Move powerpc_topology above Just moving the powerpc_topology description above. This will help in using functions in this file and avoid declarations. No other functional changes Signed-off-by: Srikar Dronamraju Reviewed-by: Gautham R. Shenoy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200810071834.92514-4-srikar@linux.vnet.ibm.com --- arch/powerpc/kernel/smp.c | 104 +++++++++++++++++++------------------- 1 file changed, 52 insertions(+), 52 deletions(-) diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 1fb98b255b4c..b12d143c7104 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -819,6 +819,58 @@ out: return err; } +static bool shared_caches; + +#ifdef CONFIG_SCHED_SMT +/* cpumask of CPUs with asymmetric SMT dependency */ +static int powerpc_smt_flags(void) +{ + int flags = SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES; + + if (cpu_has_feature(CPU_FTR_ASYM_SMT)) { + printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n"); + flags |= SD_ASYM_PACKING; + } + return flags; +} +#endif + +/* + * P9 has a slightly odd architecture where pairs of cores share an L2 cache. + * This topology makes it *much* cheaper to migrate tasks between adjacent cores + * since the migrated task remains cache hot. We want to take advantage of this + * at the scheduler level so an extra topology level is required. + */ +static int powerpc_shared_cache_flags(void) +{ + return SD_SHARE_PKG_RESOURCES; +} + +/* + * We can't just pass cpu_l2_cache_mask() directly because + * returns a non-const pointer and the compiler barfs on that. + */ +static const struct cpumask *shared_cache_mask(int cpu) +{ + return cpu_l2_cache_mask(cpu); +} + +#ifdef CONFIG_SCHED_SMT +static const struct cpumask *smallcore_smt_mask(int cpu) +{ + return cpu_smallcore_mask(cpu); +} +#endif + +static struct sched_domain_topology_level powerpc_topology[] = { +#ifdef CONFIG_SCHED_SMT + { cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) }, +#endif + { shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE) }, + { cpu_cpu_mask, SD_INIT_NAME(DIE) }, + { NULL, }, +}; + static int init_big_cores(void) { int cpu; @@ -1248,8 +1300,6 @@ static void add_cpu_to_masks(int cpu) set_cpus_related(cpu, i, cpu_core_mask); } -static bool shared_caches; - /* Activate a secondary processor. */ void start_secondary(void *unused) { @@ -1313,56 +1363,6 @@ int setup_profiling_timer(unsigned int multiplier) return 0; } -#ifdef CONFIG_SCHED_SMT -/* cpumask of CPUs with asymmetric SMT dependency */ -static int powerpc_smt_flags(void) -{ - int flags = SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES; - - if (cpu_has_feature(CPU_FTR_ASYM_SMT)) { - printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n"); - flags |= SD_ASYM_PACKING; - } - return flags; -} -#endif - -/* - * P9 has a slightly odd architecture where pairs of cores share an L2 cache. - * This topology makes it *much* cheaper to migrate tasks between adjacent cores - * since the migrated task remains cache hot. We want to take advantage of this - * at the scheduler level so an extra topology level is required. - */ -static int powerpc_shared_cache_flags(void) -{ - return SD_SHARE_PKG_RESOURCES; -} - -/* - * We can't just pass cpu_l2_cache_mask() directly because - * returns a non-const pointer and the compiler barfs on that. - */ -static const struct cpumask *shared_cache_mask(int cpu) -{ - return cpu_l2_cache_mask(cpu); -} - -#ifdef CONFIG_SCHED_SMT -static const struct cpumask *smallcore_smt_mask(int cpu) -{ - return cpu_smallcore_mask(cpu); -} -#endif - -static struct sched_domain_topology_level powerpc_topology[] = { -#ifdef CONFIG_SCHED_SMT - { cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) }, -#endif - { shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE) }, - { cpu_cpu_mask, SD_INIT_NAME(DIE) }, - { NULL, }, -}; - void __init smp_cpus_done(unsigned int max_cpus) { /* From 3c6032a8fe99547d31b2b57715e303a67d1b0c66 Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Mon, 10 Aug 2020 12:48:28 +0530 Subject: [PATCH 205/645] powerpc/smp: Move topology fixups into a new function Move topology fixup based on the platform attributes into its own function which is called just before set_sched_topology. Signed-off-by: Srikar Dronamraju Reviewed-by: Gautham R. Shenoy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200810071834.92514-5-srikar@linux.vnet.ibm.com --- arch/powerpc/kernel/smp.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index b12d143c7104..9f4333d0748b 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -1363,6 +1363,16 @@ int setup_profiling_timer(unsigned int multiplier) return 0; } +static void fixup_topology(void) +{ +#ifdef CONFIG_SCHED_SMT + if (has_big_cores) { + pr_info("Big cores detected but using small core scheduling\n"); + powerpc_topology[0].mask = smallcore_smt_mask; + } +#endif +} + void __init smp_cpus_done(unsigned int max_cpus) { /* @@ -1376,12 +1386,7 @@ void __init smp_cpus_done(unsigned int max_cpus) dump_numa_cpu_topology(); -#ifdef CONFIG_SCHED_SMT - if (has_big_cores) { - pr_info("Big cores detected but using small core scheduling\n"); - powerpc_topology[0].mask = smallcore_smt_mask; - } -#endif + fixup_topology(); set_sched_topology(powerpc_topology); } From f6606cfdfbcda00ce8a6e63c8fc13c93e73ac059 Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Sun, 13 Sep 2020 22:40:38 +0530 Subject: [PATCH 206/645] powerpc/smp: Dont assume l2-cache to be superset of sibling Current code assumes that cpumask of cpus sharing a l2-cache mask will always be a superset of cpu_sibling_mask. Lets stop that assumption. cpu_l2_cache_mask is a superset of cpu_sibling_mask if and only if shared_caches is set. Reviewed-by: Gautham R. Shenoy Signed-off-by: Srikar Dronamraju Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200913171038.GB11808@linux.vnet.ibm.com --- arch/powerpc/kernel/smp.c | 45 ++++++++++++++++++++++++++------------- 1 file changed, 30 insertions(+), 15 deletions(-) diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 9f4333d0748b..168532e37305 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -1186,9 +1186,23 @@ static bool update_mask_by_l2(int cpu, struct cpumask *(*mask_fn)(int)) int i; l2_cache = cpu_to_l2cache(cpu); - if (!l2_cache) - return false; + if (!l2_cache) { + struct cpumask *(*sibling_mask)(int) = cpu_sibling_mask; + /* + * If no l2cache for this CPU, assume all siblings to share + * cache with this CPU. + */ + if (has_big_cores) + sibling_mask = cpu_smallcore_mask; + + for_each_cpu(i, sibling_mask(cpu)) + set_cpus_related(cpu, i, cpu_l2_cache_mask); + + return false; + } + + cpumask_set_cpu(cpu, mask_fn(cpu)); for_each_cpu(i, cpu_online_mask) { /* * when updating the marks the current CPU has not been marked @@ -1271,29 +1285,30 @@ static void add_cpu_to_masks(int cpu) * add it to it's own thread sibling mask. */ cpumask_set_cpu(cpu, cpu_sibling_mask(cpu)); + cpumask_set_cpu(cpu, cpu_core_mask(cpu)); for (i = first_thread; i < first_thread + threads_per_core; i++) if (cpu_online(i)) set_cpus_related(i, cpu, cpu_sibling_mask); add_cpu_to_smallcore_masks(cpu); - /* - * Copy the thread sibling mask into the cache sibling mask - * and mark any CPUs that share an L2 with this CPU. - */ - for_each_cpu(i, cpu_sibling_mask(cpu)) - set_cpus_related(cpu, i, cpu_l2_cache_mask); update_mask_by_l2(cpu, cpu_l2_cache_mask); - /* - * Copy the cache sibling mask into core sibling mask and mark - * any CPUs on the same chip as this CPU. - */ - for_each_cpu(i, cpu_l2_cache_mask(cpu)) - set_cpus_related(cpu, i, cpu_core_mask); + if (pkg_id == -1) { + struct cpumask *(*mask)(int) = cpu_sibling_mask; + + /* + * Copy the sibling mask into core sibling mask and + * mark any CPUs on the same chip as this CPU. + */ + if (shared_caches) + mask = cpu_l2_cache_mask; + + for_each_cpu(i, mask(cpu)) + set_cpus_related(cpu, i, cpu_core_mask); - if (pkg_id == -1) return; + } for_each_cpu(i, cpu_online_mask) if (get_physical_package_id(i) == pkg_id) From caa8e29da59926bef099b46ab6280333d583e944 Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Mon, 10 Aug 2020 12:48:30 +0530 Subject: [PATCH 207/645] powerpc/smp: Optimize start_secondary In start_secondary, even if shared_cache was already set, system does a redundant match for cpumask. This redundant check can be removed by checking if shared_cache is already set. While here, localize the sibling_mask variable to within the if condition. Signed-off-by: Srikar Dronamraju Reviewed-by: Gautham R. Shenoy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200810071834.92514-7-srikar@linux.vnet.ibm.com --- arch/powerpc/kernel/smp.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 168532e37305..016a822eb8c4 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -852,7 +852,7 @@ static int powerpc_shared_cache_flags(void) */ static const struct cpumask *shared_cache_mask(int cpu) { - return cpu_l2_cache_mask(cpu); + return per_cpu(cpu_l2_cache_map, cpu); } #ifdef CONFIG_SCHED_SMT @@ -1319,7 +1319,6 @@ static void add_cpu_to_masks(int cpu) void start_secondary(void *unused) { unsigned int cpu = smp_processor_id(); - struct cpumask *(*sibling_mask)(int) = cpu_sibling_mask; mmgrab(&init_mm); current->active_mm = &init_mm; @@ -1345,14 +1344,20 @@ void start_secondary(void *unused) /* Update topology CPU masks */ add_cpu_to_masks(cpu); - if (has_big_cores) - sibling_mask = cpu_smallcore_mask; /* * Check for any shared caches. Note that this must be done on a * per-core basis because one core in the pair might be disabled. */ - if (!cpumask_equal(cpu_l2_cache_mask(cpu), sibling_mask(cpu))) - shared_caches = true; + if (!shared_caches) { + struct cpumask *(*sibling_mask)(int) = cpu_sibling_mask; + struct cpumask *mask = cpu_l2_cache_mask(cpu); + + if (has_big_cores) + sibling_mask = cpu_smallcore_mask; + + if (cpumask_weight(mask) > cpumask_weight(sibling_mask(cpu))) + shared_caches = true; + } set_numa_node(numa_cpu_lookup_table[cpu]); set_numa_mem(local_memory_node(numa_cpu_lookup_table[cpu])); From f9f130ff2ec93c5949576bbfb168cc9530c23649 Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Mon, 10 Aug 2020 12:48:31 +0530 Subject: [PATCH 208/645] powerpc/numa: Detect support for coregroup Add support for grouping cores based on the device-tree classification. - The last domain in the associativity domains always refers to the core. - If primary reference domain happens to be the penultimate domain in the associativity domains device-tree property, then there are no coregroups. However if its not a penultimate domain, then there are coregroups. There can be more than one coregroup. For now we would be interested in the last or the smallest coregroups, i.e one sub-group per DIE. Currently there are no firmwares that are exposing this grouping. Hence allow the basis for grouping to be abstract. Once the firmware starts using this grouping, code would be added to detect the type of grouping and adjust the sd domain flags accordingly. Signed-off-by: Srikar Dronamraju Reviewed-by: Gautham R. Shenoy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200810071834.92514-8-srikar@linux.vnet.ibm.com --- arch/powerpc/include/asm/smp.h | 1 + arch/powerpc/kernel/smp.c | 1 + arch/powerpc/mm/numa.c | 34 +++++++++++++++++++++------------- 3 files changed, 23 insertions(+), 13 deletions(-) diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index b727f5f7b8f9..041f0b97c45b 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -28,6 +28,7 @@ extern int boot_cpuid; extern int spinning_secondaries; extern u32 *cpu_to_phys_id; +extern bool coregroup_enabled; extern void cpu_die(void); extern int cpu_to_chip_id(int cpu); diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 016a822eb8c4..a44b9350d2ef 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -75,6 +75,7 @@ static DEFINE_PER_CPU(int, cpu_state) = { 0 }; struct task_struct *secondary_current; bool has_big_cores; +bool coregroup_enabled; DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map); DEFINE_PER_CPU(cpumask_var_t, cpu_smallcore_map); diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 481951ac3e55..b2c44c5a81fb 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -897,7 +897,9 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn) static void __init find_possible_nodes(void) { struct device_node *rtas; - u32 numnodes, i; + const __be32 *domains; + int prop_length, max_nodes; + u32 i; if (!numa_enabled) return; @@ -906,25 +908,31 @@ static void __init find_possible_nodes(void) if (!rtas) return; - if (of_property_read_u32_index(rtas, "ibm,current-associativity-domains", - min_common_depth, &numnodes)) { - /* - * ibm,current-associativity-domains is a fairly recent - * property. If it doesn't exist, then fallback on - * ibm,max-associativity-domains. Current denotes what the - * platform can support compared to max which denotes what the - * Hypervisor can support. - */ - if (of_property_read_u32_index(rtas, "ibm,max-associativity-domains", - min_common_depth, &numnodes)) + /* + * ibm,current-associativity-domains is a fairly recent property. If + * it doesn't exist, then fallback on ibm,max-associativity-domains. + * Current denotes what the platform can support compared to max + * which denotes what the Hypervisor can support. + */ + domains = of_get_property(rtas, "ibm,current-associativity-domains", + &prop_length); + if (!domains) { + domains = of_get_property(rtas, "ibm,max-associativity-domains", + &prop_length); + if (!domains) goto out; } - for (i = 0; i < numnodes; i++) { + max_nodes = of_read_number(&domains[min_common_depth], 1); + for (i = 0; i < max_nodes; i++) { if (!node_possible(i)) node_set(i, node_possible_map); } + prop_length /= sizeof(int); + if (prop_length > min_common_depth + 2) + coregroup_enabled = 1; + out: of_node_put(rtas); } From 6e086302816b2ced602bc99641eb0189c05f018a Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Mon, 10 Aug 2020 12:48:32 +0530 Subject: [PATCH 209/645] powerpc/smp: Allocate cpumask only after searching thread group If allocated earlier and the search fails, then cpu_l1_cache_map cpumask is unnecessarily cleared. However cpu_l1_cache_map can be allocated / cleared after we search thread group. Please note CONFIG_CPUMASK_OFFSTACK is not set on Powerpc. Hence cpumask allocated by zalloc_cpumask_var_node is never freed. Signed-off-by: Srikar Dronamraju Reviewed-by: Gautham R. Shenoy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200810071834.92514-9-srikar@linux.vnet.ibm.com --- arch/powerpc/kernel/smp.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index a44b9350d2ef..41f76c8cd024 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -790,10 +790,6 @@ static int init_cpu_l1_cache_map(int cpu) if (err) goto out; - zalloc_cpumask_var_node(&per_cpu(cpu_l1_cache_map, cpu), - GFP_KERNEL, - cpu_to_node(cpu)); - cpu_group_start = get_cpu_thread_group_start(cpu, &tg); if (unlikely(cpu_group_start == -1)) { @@ -802,6 +798,9 @@ static int init_cpu_l1_cache_map(int cpu) goto out; } + zalloc_cpumask_var_node(&per_cpu(cpu_l1_cache_map, cpu), + GFP_KERNEL, cpu_to_node(cpu)); + for (i = first_thread; i < first_thread + threads_per_core; i++) { int i_group_start = get_cpu_thread_group_start(i, &tg); From 72730bfc2a2b91a525f38dfc830f598bdb95f216 Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Mon, 10 Aug 2020 12:48:33 +0530 Subject: [PATCH 210/645] powerpc/smp: Create coregroup domain Add percpu coregroup maps and masks to create coregroup domain. If a coregroup doesn't exist, the coregroup domain will be degenerated in favour of SMT/CACHE domain. Do note this patch is only creating stubs for cpu_to_coregroup_id. The actual cpu_to_coregroup_id implementation would be in a subsequent patch. Signed-off-by: Srikar Dronamraju Reviewed-by: Gautham R. Shenoy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200810071834.92514-10-srikar@linux.vnet.ibm.com --- arch/powerpc/include/asm/topology.h | 10 ++++++ arch/powerpc/kernel/smp.c | 54 ++++++++++++++++++++++++++++- arch/powerpc/mm/numa.c | 5 +++ 3 files changed, 68 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index f0b6300e7dd3..6609174918ab 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -88,12 +88,22 @@ static inline int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc) #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR) extern int find_and_online_cpu_nid(int cpu); +extern int cpu_to_coregroup_id(int cpu); #else static inline int find_and_online_cpu_nid(int cpu) { return 0; } +static inline int cpu_to_coregroup_id(int cpu) +{ +#ifdef CONFIG_SMP + return cpu_to_core_id(cpu); +#else + return 0; +#endif +} + #endif /* CONFIG_NUMA && CONFIG_PPC_SPLPAR */ #include diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 41f76c8cd024..3d96752d6570 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -81,12 +81,22 @@ DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map); DEFINE_PER_CPU(cpumask_var_t, cpu_smallcore_map); DEFINE_PER_CPU(cpumask_var_t, cpu_l2_cache_map); DEFINE_PER_CPU(cpumask_var_t, cpu_core_map); +DEFINE_PER_CPU(cpumask_var_t, cpu_coregroup_map); EXPORT_PER_CPU_SYMBOL(cpu_sibling_map); EXPORT_PER_CPU_SYMBOL(cpu_l2_cache_map); EXPORT_PER_CPU_SYMBOL(cpu_core_map); EXPORT_SYMBOL_GPL(has_big_cores); +enum { +#ifdef CONFIG_SCHED_SMT + smt_idx, +#endif + cache_idx, + mc_idx, + die_idx, +}; + #define MAX_THREAD_LIST_SIZE 8 #define THREAD_GROUP_SHARE_L1 1 struct thread_groups { @@ -862,11 +872,27 @@ static const struct cpumask *smallcore_smt_mask(int cpu) } #endif +static struct cpumask *cpu_coregroup_mask(int cpu) +{ + return per_cpu(cpu_coregroup_map, cpu); +} + +static bool has_coregroup_support(void) +{ + return coregroup_enabled; +} + +static const struct cpumask *cpu_mc_mask(int cpu) +{ + return cpu_coregroup_mask(cpu); +} + static struct sched_domain_topology_level powerpc_topology[] = { #ifdef CONFIG_SCHED_SMT { cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) }, #endif { shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE) }, + { cpu_mc_mask, SD_INIT_NAME(MC) }, { cpu_cpu_mask, SD_INIT_NAME(DIE) }, { NULL, }, }; @@ -913,6 +939,10 @@ void __init smp_prepare_cpus(unsigned int max_cpus) GFP_KERNEL, cpu_to_node(cpu)); zalloc_cpumask_var_node(&per_cpu(cpu_core_map, cpu), GFP_KERNEL, cpu_to_node(cpu)); + if (has_coregroup_support()) + zalloc_cpumask_var_node(&per_cpu(cpu_coregroup_map, cpu), + GFP_KERNEL, cpu_to_node(cpu)); + #ifdef CONFIG_NEED_MULTIPLE_NODES /* * numa_node_id() works after this. @@ -930,6 +960,9 @@ void __init smp_prepare_cpus(unsigned int max_cpus) cpumask_set_cpu(boot_cpuid, cpu_l2_cache_mask(boot_cpuid)); cpumask_set_cpu(boot_cpuid, cpu_core_mask(boot_cpuid)); + if (has_coregroup_support()) + cpumask_set_cpu(boot_cpuid, cpu_coregroup_mask(boot_cpuid)); + init_big_cores(); if (has_big_cores) { cpumask_set_cpu(boot_cpuid, @@ -1234,6 +1267,8 @@ static void remove_cpu_from_masks(int cpu) set_cpus_unrelated(cpu, i, cpu_sibling_mask); if (has_big_cores) set_cpus_unrelated(cpu, i, cpu_smallcore_mask); + if (has_coregroup_support()) + set_cpus_unrelated(cpu, i, cpu_coregroup_mask); } } #endif @@ -1294,6 +1329,20 @@ static void add_cpu_to_masks(int cpu) add_cpu_to_smallcore_masks(cpu); update_mask_by_l2(cpu, cpu_l2_cache_mask); + if (has_coregroup_support()) { + int coregroup_id = cpu_to_coregroup_id(cpu); + + cpumask_set_cpu(cpu, cpu_coregroup_mask(cpu)); + for_each_cpu_and(i, cpu_online_mask, cpu_cpu_mask(cpu)) { + int fcpu = cpu_first_thread_sibling(i); + + if (fcpu == first_thread) + set_cpus_related(cpu, i, cpu_coregroup_mask); + else if (coregroup_id == cpu_to_coregroup_id(i)) + set_cpus_related(cpu, i, cpu_coregroup_mask); + } + } + if (pkg_id == -1) { struct cpumask *(*mask)(int) = cpu_sibling_mask; @@ -1388,9 +1437,12 @@ static void fixup_topology(void) #ifdef CONFIG_SCHED_SMT if (has_big_cores) { pr_info("Big cores detected but using small core scheduling\n"); - powerpc_topology[0].mask = smallcore_smt_mask; + powerpc_topology[smt_idx].mask = smallcore_smt_mask; } #endif + + if (!has_coregroup_support()) + powerpc_topology[mc_idx].mask = powerpc_topology[cache_idx].mask; } void __init smp_cpus_done(unsigned int max_cpus) diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index b2c44c5a81fb..dfebca905acb 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1245,6 +1245,11 @@ int find_and_online_cpu_nid(int cpu) return new_nid; } +int cpu_to_coregroup_id(int cpu) +{ + return cpu_to_core_id(cpu); +} + static int topology_update_init(void) { topology_inited = 1; From fa35e868f9ddcbb7984fd5ab7f91aef924fa8543 Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Mon, 10 Aug 2020 12:48:34 +0530 Subject: [PATCH 211/645] powerpc/smp: Implement cpu_to_coregroup_id Lookup the coregroup id from the associativity array. If unable to detect the coregroup id, fallback on the core id. This way, ensure sched_domain degenerates and an extra sched domain is not created. Ideally this function should have been implemented in arch/powerpc/kernel/smp.c. However if its implemented in mm/numa.c, we don't need to find the primary domain again. If the device-tree mentions more than one coregroup, then kernel implements only the last or the smallest coregroup, which currently corresponds to the penultimate domain in the device-tree. Signed-off-by: Srikar Dronamraju Reviewed-by: Gautham R. Shenoy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200810071834.92514-11-srikar@linux.vnet.ibm.com --- arch/powerpc/mm/numa.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index dfebca905acb..b725fb66e913 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1247,6 +1247,26 @@ int find_and_online_cpu_nid(int cpu) int cpu_to_coregroup_id(int cpu) { + __be32 associativity[VPHN_ASSOC_BUFSIZE] = {0}; + int index; + + if (cpu < 0 || cpu > nr_cpu_ids) + return -1; + + if (!coregroup_enabled) + goto out; + + if (!firmware_has_feature(FW_FEATURE_VPHN)) + goto out; + + if (vphn_get_associativity(cpu, associativity)) + goto out; + + index = of_read_number(associativity, 1); + if (index > min_common_depth + 1) + return of_read_number(&associativity[index - 1], 1); + +out: return cpu_to_core_id(cpu); } From 52f72feba9dbe4fac848ae0d90bc0b85b17f91bc Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Tue, 15 Sep 2020 17:01:58 +0200 Subject: [PATCH 212/645] s390/zcrypt: remove set_fs() invocation in zcrypt device driver This patch reworks the zcrypt device driver so that the set_fs() invocation is not needed any more. Instead there is a new flag bool userspace passed through all the functions which tells if the pointer arguments are userspace or kernelspace. Together with the two new inline functions z_copy_from_user() and z_copy_to_user() which either invoke copy_from_user (userspace is true) or memcpy (userspace is false) the zcrypt dd and the AP bus now has no requirement for the set_fs() functionality any more. Signed-off-by: Harald Freudenberger Reviewed-by: Ingo Franzki Reviewed-by: Christoph Hellwig Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- drivers/s390/crypto/zcrypt_api.c | 30 +++++------ drivers/s390/crypto/zcrypt_api.h | 26 ++++++++- drivers/s390/crypto/zcrypt_ccamisc.c | 32 +++-------- drivers/s390/crypto/zcrypt_ep11misc.c | 28 ++-------- drivers/s390/crypto/zcrypt_msgtype6.c | 78 +++++++++++++-------------- drivers/s390/crypto/zcrypt_msgtype6.h | 4 +- 6 files changed, 92 insertions(+), 106 deletions(-) diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c index 4dbbfd88262c..a711728c3857 100644 --- a/drivers/s390/crypto/zcrypt_api.c +++ b/drivers/s390/crypto/zcrypt_api.c @@ -797,7 +797,7 @@ out: return rc; } -static long _zcrypt_send_cprb(struct ap_perms *perms, +static long _zcrypt_send_cprb(bool userspace, struct ap_perms *perms, struct ica_xcRB *xcRB) { struct zcrypt_card *zc, *pref_zc; @@ -813,7 +813,7 @@ static long _zcrypt_send_cprb(struct ap_perms *perms, xcRB->status = 0; ap_init_message(&ap_msg); - rc = get_cprb_fc(xcRB, &ap_msg, &func_code, &domain); + rc = get_cprb_fc(userspace, xcRB, &ap_msg, &func_code, &domain); if (rc) goto out; @@ -878,7 +878,7 @@ static long _zcrypt_send_cprb(struct ap_perms *perms, if (*domain == AUTOSEL_DOM) *domain = AP_QID_QUEUE(qid); - rc = pref_zq->ops->send_cprb(pref_zq, xcRB, &ap_msg); + rc = pref_zq->ops->send_cprb(userspace, pref_zq, xcRB, &ap_msg); spin_lock(&zcrypt_list_lock); zcrypt_drop_queue(pref_zc, pref_zq, mod, weight); @@ -893,7 +893,7 @@ out: long zcrypt_send_cprb(struct ica_xcRB *xcRB) { - return _zcrypt_send_cprb(&ap_perms, xcRB); + return _zcrypt_send_cprb(false, &ap_perms, xcRB); } EXPORT_SYMBOL(zcrypt_send_cprb); @@ -924,7 +924,7 @@ static bool is_desired_ep11_queue(unsigned int dev_qid, return false; } -static long _zcrypt_send_ep11_cprb(struct ap_perms *perms, +static long _zcrypt_send_ep11_cprb(bool userspace, struct ap_perms *perms, struct ep11_urb *xcrb) { struct zcrypt_card *zc, *pref_zc; @@ -956,7 +956,7 @@ static long _zcrypt_send_ep11_cprb(struct ap_perms *perms, } uptr = (struct ep11_target_dev __force __user *) xcrb->targets; - if (copy_from_user(targets, uptr, + if (z_copy_from_user(userspace, targets, uptr, target_num * sizeof(*targets))) { func_code = 0; rc = -EFAULT; @@ -964,7 +964,7 @@ static long _zcrypt_send_ep11_cprb(struct ap_perms *perms, } } - rc = get_ep11cprb_fc(xcrb, &ap_msg, &func_code); + rc = get_ep11cprb_fc(userspace, xcrb, &ap_msg, &func_code); if (rc) goto out_free; @@ -1015,7 +1015,7 @@ static long _zcrypt_send_ep11_cprb(struct ap_perms *perms, } qid = pref_zq->queue->qid; - rc = pref_zq->ops->send_ep11_cprb(pref_zq, xcrb, &ap_msg); + rc = pref_zq->ops->send_ep11_cprb(userspace, pref_zq, xcrb, &ap_msg); spin_lock(&zcrypt_list_lock); zcrypt_drop_queue(pref_zc, pref_zq, mod, weight); @@ -1032,7 +1032,7 @@ out: long zcrypt_send_ep11_cprb(struct ep11_urb *xcrb) { - return _zcrypt_send_ep11_cprb(&ap_perms, xcrb); + return _zcrypt_send_ep11_cprb(false, &ap_perms, xcrb); } EXPORT_SYMBOL(zcrypt_send_ep11_cprb); @@ -1353,12 +1353,12 @@ static int zsecsendcprb_ioctl(struct ap_perms *perms, unsigned long arg) if (copy_from_user(&xcRB, uxcRB, sizeof(xcRB))) return -EFAULT; do { - rc = _zcrypt_send_cprb(perms, &xcRB); + rc = _zcrypt_send_cprb(true, perms, &xcRB); } while (rc == -EAGAIN); /* on failure: retry once again after a requested rescan */ if ((rc == -ENODEV) && (zcrypt_process_rescan())) do { - rc = _zcrypt_send_cprb(perms, &xcRB); + rc = _zcrypt_send_cprb(true, perms, &xcRB); } while (rc == -EAGAIN); if (rc) ZCRYPT_DBF(DBF_DEBUG, "ioctl ZSENDCPRB rc=%d status=0x%x\n", @@ -1377,12 +1377,12 @@ static int zsendep11cprb_ioctl(struct ap_perms *perms, unsigned long arg) if (copy_from_user(&xcrb, uxcrb, sizeof(xcrb))) return -EFAULT; do { - rc = _zcrypt_send_ep11_cprb(perms, &xcrb); + rc = _zcrypt_send_ep11_cprb(true, perms, &xcrb); } while (rc == -EAGAIN); /* on failure: retry once again after a requested rescan */ if ((rc == -ENODEV) && (zcrypt_process_rescan())) do { - rc = _zcrypt_send_ep11_cprb(perms, &xcrb); + rc = _zcrypt_send_ep11_cprb(true, perms, &xcrb); } while (rc == -EAGAIN); if (rc) ZCRYPT_DBF(DBF_DEBUG, "ioctl ZSENDEP11CPRB rc=%d\n", rc); @@ -1655,12 +1655,12 @@ static long trans_xcRB32(struct ap_perms *perms, struct file *filp, xcRB64.priority_window = xcRB32.priority_window; xcRB64.status = xcRB32.status; do { - rc = _zcrypt_send_cprb(perms, &xcRB64); + rc = _zcrypt_send_cprb(true, perms, &xcRB64); } while (rc == -EAGAIN); /* on failure: retry once again after a requested rescan */ if ((rc == -ENODEV) && (zcrypt_process_rescan())) do { - rc = _zcrypt_send_cprb(perms, &xcRB64); + rc = _zcrypt_send_cprb(true, perms, &xcRB64); } while (rc == -EAGAIN); xcRB32.reply_control_blk_length = xcRB64.reply_control_blk_length; xcRB32.reply_data_length = xcRB64.reply_data_length; diff --git a/drivers/s390/crypto/zcrypt_api.h b/drivers/s390/crypto/zcrypt_api.h index 599e68bf53f7..19ddfc38e029 100644 --- a/drivers/s390/crypto/zcrypt_api.h +++ b/drivers/s390/crypto/zcrypt_api.h @@ -59,9 +59,9 @@ struct zcrypt_ops { long (*rsa_modexpo)(struct zcrypt_queue *, struct ica_rsa_modexpo *); long (*rsa_modexpo_crt)(struct zcrypt_queue *, struct ica_rsa_modexpo_crt *); - long (*send_cprb)(struct zcrypt_queue *, struct ica_xcRB *, + long (*send_cprb)(bool userspace, struct zcrypt_queue *, struct ica_xcRB *, struct ap_message *); - long (*send_ep11_cprb)(struct zcrypt_queue *, struct ep11_urb *, + long (*send_ep11_cprb)(bool userspace, struct zcrypt_queue *, struct ep11_urb *, struct ap_message *); long (*rng)(struct zcrypt_queue *, char *, struct ap_message *); struct list_head list; /* zcrypt ops list. */ @@ -145,4 +145,26 @@ void zcrypt_device_status_mask_ext(struct zcrypt_device_status_ext *devstatus); int zcrypt_device_status_ext(int card, int queue, struct zcrypt_device_status_ext *devstatus); +static inline unsigned long z_copy_from_user(bool userspace, + void *to, + const void __user *from, + unsigned long n) +{ + if (likely(userspace)) + return copy_from_user(to, from, n); + memcpy(to, (void __force *) from, n); + return 0; +} + +static inline unsigned long z_copy_to_user(bool userspace, + void __user *to, + const void *from, + unsigned long n) +{ + if (likely(userspace)) + return copy_to_user(to, from, n); + memcpy((void __force *) to, from, n); + return 0; +} + #endif /* _ZCRYPT_API_H_ */ diff --git a/drivers/s390/crypto/zcrypt_ccamisc.c b/drivers/s390/crypto/zcrypt_ccamisc.c index 5fafda6663ed..40b59a77ec0c 100644 --- a/drivers/s390/crypto/zcrypt_ccamisc.c +++ b/drivers/s390/crypto/zcrypt_ccamisc.c @@ -248,24 +248,6 @@ static inline void prep_xcrb(struct ica_xcRB *pxcrb, pxcrb->reply_control_blk_addr = (void __user *) prepcblk; } -/* - * Helper function which calls zcrypt_send_cprb with - * memory management segment adjusted to kernel space - * so that the copy_from_user called within this - * function do in fact copy from kernel space. - */ -static inline int _zcrypt_send_cprb(struct ica_xcRB *xcrb) -{ - int rc; - mm_segment_t old_fs = get_fs(); - - set_fs(KERNEL_DS); - rc = zcrypt_send_cprb(xcrb); - set_fs(old_fs); - - return rc; -} - /* * Generate (random) CCA AES DATA secure key. */ @@ -359,7 +341,7 @@ int cca_genseckey(u16 cardnr, u16 domain, prep_xcrb(&xcrb, cardnr, preqcblk, prepcblk); /* forward xcrb with request CPRB and reply CPRB to zcrypt dd */ - rc = _zcrypt_send_cprb(&xcrb); + rc = zcrypt_send_cprb(&xcrb); if (rc) { DEBUG_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, errno %d\n", __func__, (int) cardnr, (int) domain, rc); @@ -497,7 +479,7 @@ int cca_clr2seckey(u16 cardnr, u16 domain, u32 keybitsize, prep_xcrb(&xcrb, cardnr, preqcblk, prepcblk); /* forward xcrb with request CPRB and reply CPRB to zcrypt dd */ - rc = _zcrypt_send_cprb(&xcrb); + rc = zcrypt_send_cprb(&xcrb); if (rc) { DEBUG_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", __func__, (int) cardnr, (int) domain, rc); @@ -624,7 +606,7 @@ int cca_sec2protkey(u16 cardnr, u16 domain, prep_xcrb(&xcrb, cardnr, preqcblk, prepcblk); /* forward xcrb with request CPRB and reply CPRB to zcrypt dd */ - rc = _zcrypt_send_cprb(&xcrb); + rc = zcrypt_send_cprb(&xcrb); if (rc) { DEBUG_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", __func__, (int) cardnr, (int) domain, rc); @@ -850,7 +832,7 @@ int cca_gencipherkey(u16 cardnr, u16 domain, u32 keybitsize, u32 keygenflags, prep_xcrb(&xcrb, cardnr, preqcblk, prepcblk); /* forward xcrb with request CPRB and reply CPRB to zcrypt dd */ - rc = _zcrypt_send_cprb(&xcrb); + rc = zcrypt_send_cprb(&xcrb); if (rc) { DEBUG_ERR( "%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", @@ -1018,7 +1000,7 @@ static int _ip_cprb_helper(u16 cardnr, u16 domain, prep_xcrb(&xcrb, cardnr, preqcblk, prepcblk); /* forward xcrb with request CPRB and reply CPRB to zcrypt dd */ - rc = _zcrypt_send_cprb(&xcrb); + rc = zcrypt_send_cprb(&xcrb); if (rc) { DEBUG_ERR( "%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", @@ -1235,7 +1217,7 @@ int cca_cipher2protkey(u16 cardnr, u16 domain, const u8 *ckey, prep_xcrb(&xcrb, cardnr, preqcblk, prepcblk); /* forward xcrb with request CPRB and reply CPRB to zcrypt dd */ - rc = _zcrypt_send_cprb(&xcrb); + rc = zcrypt_send_cprb(&xcrb); if (rc) { DEBUG_ERR( "%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", @@ -1366,7 +1348,7 @@ int cca_query_crypto_facility(u16 cardnr, u16 domain, prep_xcrb(&xcrb, cardnr, preqcblk, prepcblk); /* forward xcrb with request CPRB and reply CPRB to zcrypt dd */ - rc = _zcrypt_send_cprb(&xcrb); + rc = zcrypt_send_cprb(&xcrb); if (rc) { DEBUG_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", __func__, (int) cardnr, (int) domain, rc); diff --git a/drivers/s390/crypto/zcrypt_ep11misc.c b/drivers/s390/crypto/zcrypt_ep11misc.c index 3c3d403abe92..60b6bec21c32 100644 --- a/drivers/s390/crypto/zcrypt_ep11misc.c +++ b/drivers/s390/crypto/zcrypt_ep11misc.c @@ -169,24 +169,6 @@ int ep11_check_aeskeyblob(debug_info_t *dbg, int dbflvl, } EXPORT_SYMBOL(ep11_check_aeskeyblob); -/* - * Helper function which calls zcrypt_send_ep11_cprb with - * memory management segment adjusted to kernel space - * so that the copy_from_user called within this - * function do in fact copy from kernel space. - */ -static inline int _zcrypt_send_ep11_cprb(struct ep11_urb *urb) -{ - int rc; - mm_segment_t old_fs = get_fs(); - - set_fs(KERNEL_DS); - rc = zcrypt_send_ep11_cprb(urb); - set_fs(old_fs); - - return rc; -} - /* * Allocate and prepare ep11 cprb plus additional payload. */ @@ -399,7 +381,7 @@ static int ep11_query_info(u16 cardnr, u16 domain, u32 query_type, req, sizeof(*req) + sizeof(*req_pl), rep, sizeof(*rep) + sizeof(*rep_pl) + buflen); - rc = _zcrypt_send_ep11_cprb(urb); + rc = zcrypt_send_ep11_cprb(urb); if (rc) { DEBUG_ERR( "%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n", @@ -637,7 +619,7 @@ int ep11_genaeskey(u16 card, u16 domain, u32 keybitsize, u32 keygenflags, req, sizeof(*req) + sizeof(*req_pl), rep, sizeof(*rep) + sizeof(*rep_pl)); - rc = _zcrypt_send_ep11_cprb(urb); + rc = zcrypt_send_ep11_cprb(urb); if (rc) { DEBUG_ERR( "%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n", @@ -757,7 +739,7 @@ static int ep11_cryptsingle(u16 card, u16 domain, req, sizeof(*req) + req_pl_size, rep, sizeof(*rep) + rep_pl_size); - rc = _zcrypt_send_ep11_cprb(urb); + rc = zcrypt_send_ep11_cprb(urb); if (rc) { DEBUG_ERR( "%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n", @@ -905,7 +887,7 @@ static int ep11_unwrapkey(u16 card, u16 domain, req, sizeof(*req) + req_pl_size, rep, sizeof(*rep) + sizeof(*rep_pl)); - rc = _zcrypt_send_ep11_cprb(urb); + rc = zcrypt_send_ep11_cprb(urb); if (rc) { DEBUG_ERR( "%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n", @@ -1033,7 +1015,7 @@ static int ep11_wrapkey(u16 card, u16 domain, req, sizeof(*req) + req_pl_size, rep, sizeof(*rep) + sizeof(*rep_pl)); - rc = _zcrypt_send_ep11_cprb(urb); + rc = zcrypt_send_ep11_cprb(urb); if (rc) { DEBUG_ERR( "%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n", diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c index d77991c74c25..3db901883a5c 100644 --- a/drivers/s390/crypto/zcrypt_msgtype6.c +++ b/drivers/s390/crypto/zcrypt_msgtype6.c @@ -388,7 +388,7 @@ struct type86_fmt2_msg { struct type86_fmt2_ext fmt2; } __packed; -static int XCRB_msg_to_type6CPRB_msgX(struct ap_message *ap_msg, +static int XCRB_msg_to_type6CPRB_msgX(bool userspace, struct ap_message *ap_msg, struct ica_xcRB *xcRB, unsigned int *fcode, unsigned short **dom) @@ -465,8 +465,8 @@ static int XCRB_msg_to_type6CPRB_msgX(struct ap_message *ap_msg, msg->hdr.FromCardLen2 = xcRB->reply_data_length; /* prepare CPRB */ - if (copy_from_user(&(msg->cprbx), xcRB->request_control_blk_addr, - xcRB->request_control_blk_length)) + if (z_copy_from_user(userspace, &(msg->cprbx), xcRB->request_control_blk_addr, + xcRB->request_control_blk_length)) return -EFAULT; if (msg->cprbx.cprb_len + sizeof(msg->hdr.function_code) > xcRB->request_control_blk_length) @@ -484,16 +484,16 @@ static int XCRB_msg_to_type6CPRB_msgX(struct ap_message *ap_msg, /* copy data block */ if (xcRB->request_data_length && - copy_from_user(req_data, xcRB->request_data_address, - xcRB->request_data_length)) + z_copy_from_user(userspace, req_data, xcRB->request_data_address, + xcRB->request_data_length)) return -EFAULT; return 0; } -static int xcrb_msg_to_type6_ep11cprb_msgx(struct ap_message *ap_msg, - struct ep11_urb *xcRB, - unsigned int *fcode) +static int xcrb_msg_to_type6_ep11cprb_msgx(bool userspace, struct ap_message *ap_msg, + struct ep11_urb *xcRB, + unsigned int *fcode) { unsigned int lfmt; static struct type6_hdr static_type6_ep11_hdr = { @@ -543,8 +543,8 @@ static int xcrb_msg_to_type6_ep11cprb_msgx(struct ap_message *ap_msg, msg->hdr.FromCardLen1 = xcRB->resp_len; /* Import CPRB data from the ioctl input parameter */ - if (copy_from_user(&(msg->cprbx.cprb_len), - (char __force __user *)xcRB->req, xcRB->req_len)) { + if (z_copy_from_user(userspace, &(msg->cprbx.cprb_len), + (char __force __user *)xcRB->req, xcRB->req_len)) { return -EFAULT; } @@ -707,7 +707,7 @@ static int convert_type86_ica(struct zcrypt_queue *zq, * * Returns 0 on success or -EINVAL, -EFAULT, -EAGAIN in case of an error. */ -static int convert_type86_xcrb(struct zcrypt_queue *zq, +static int convert_type86_xcrb(bool userspace, struct zcrypt_queue *zq, struct ap_message *reply, struct ica_xcRB *xcRB) { @@ -715,15 +715,15 @@ static int convert_type86_xcrb(struct zcrypt_queue *zq, char *data = reply->msg; /* Copy CPRB to user */ - if (copy_to_user(xcRB->reply_control_blk_addr, - data + msg->fmt2.offset1, msg->fmt2.count1)) + if (z_copy_to_user(userspace, xcRB->reply_control_blk_addr, + data + msg->fmt2.offset1, msg->fmt2.count1)) return -EFAULT; xcRB->reply_control_blk_length = msg->fmt2.count1; /* Copy data buffer to user */ if (msg->fmt2.count2) - if (copy_to_user(xcRB->reply_data_addr, - data + msg->fmt2.offset2, msg->fmt2.count2)) + if (z_copy_to_user(userspace, xcRB->reply_data_addr, + data + msg->fmt2.offset2, msg->fmt2.count2)) return -EFAULT; xcRB->reply_data_length = msg->fmt2.count2; return 0; @@ -738,7 +738,7 @@ static int convert_type86_xcrb(struct zcrypt_queue *zq, * * Returns 0 on success or -EINVAL, -EFAULT, -EAGAIN in case of an error. */ -static int convert_type86_ep11_xcrb(struct zcrypt_queue *zq, +static int convert_type86_ep11_xcrb(bool userspace, struct zcrypt_queue *zq, struct ap_message *reply, struct ep11_urb *xcRB) { @@ -749,8 +749,8 @@ static int convert_type86_ep11_xcrb(struct zcrypt_queue *zq, return -EINVAL; /* Copy response CPRB to user */ - if (copy_to_user((char __force __user *)xcRB->resp, - data + msg->fmt2.offset1, msg->fmt2.count1)) + if (z_copy_to_user(userspace, (char __force __user *)xcRB->resp, + data + msg->fmt2.offset1, msg->fmt2.count1)) return -EFAULT; xcRB->resp_len = msg->fmt2.count1; return 0; @@ -814,9 +814,9 @@ static int convert_response_ica(struct zcrypt_queue *zq, } } -static int convert_response_xcrb(struct zcrypt_queue *zq, - struct ap_message *reply, - struct ica_xcRB *xcRB) +static int convert_response_xcrb(bool userspace, struct zcrypt_queue *zq, + struct ap_message *reply, + struct ica_xcRB *xcRB) { struct type86x_reply *msg = reply->msg; @@ -831,7 +831,7 @@ static int convert_response_xcrb(struct zcrypt_queue *zq, return convert_error(zq, reply); } if (msg->cprbx.cprb_ver_id == 0x02) - return convert_type86_xcrb(zq, reply, xcRB); + return convert_type86_xcrb(userspace, zq, reply, xcRB); fallthrough; /* wrong cprb version is an unknown response */ default: /* Unknown response type, this should NEVER EVER happen */ xcRB->status = 0x0008044DL; /* HDD_InvalidParm */ @@ -848,8 +848,8 @@ static int convert_response_xcrb(struct zcrypt_queue *zq, } } -static int convert_response_ep11_xcrb(struct zcrypt_queue *zq, - struct ap_message *reply, struct ep11_urb *xcRB) +static int convert_response_ep11_xcrb(bool userspace, struct zcrypt_queue *zq, + struct ap_message *reply, struct ep11_urb *xcRB) { struct type86_ep11_reply *msg = reply->msg; @@ -861,7 +861,7 @@ static int convert_response_ep11_xcrb(struct zcrypt_queue *zq, if (msg->hdr.reply_code) return convert_error(zq, reply); if (msg->cprbx.cprb_ver_id == 0x04) - return convert_type86_ep11_xcrb(zq, reply, xcRB); + return convert_type86_ep11_xcrb(userspace, zq, reply, xcRB); fallthrough; /* wrong cprb version is an unknown resp */ default: /* Unknown response type, this should NEVER EVER happen */ zq->online = 0; @@ -1095,9 +1095,9 @@ out_free: * by the caller with ap_init_message(). Also the caller has to * make sure ap_release_message() is always called even on failure. */ -unsigned int get_cprb_fc(struct ica_xcRB *xcRB, - struct ap_message *ap_msg, - unsigned int *func_code, unsigned short **dom) +unsigned int get_cprb_fc(bool userspace, struct ica_xcRB *xcRB, + struct ap_message *ap_msg, + unsigned int *func_code, unsigned short **dom) { struct response_type resp_type = { .type = CEXXC_RESPONSE_TYPE_XCRB, @@ -1112,7 +1112,7 @@ unsigned int get_cprb_fc(struct ica_xcRB *xcRB, ap_msg->private = kmemdup(&resp_type, sizeof(resp_type), GFP_KERNEL); if (!ap_msg->private) return -ENOMEM; - return XCRB_msg_to_type6CPRB_msgX(ap_msg, xcRB, func_code, dom); + return XCRB_msg_to_type6CPRB_msgX(userspace, ap_msg, xcRB, func_code, dom); } /** @@ -1122,9 +1122,9 @@ unsigned int get_cprb_fc(struct ica_xcRB *xcRB, * CEXxC device to the request distributor * @xcRB: pointer to the send_cprb request buffer */ -static long zcrypt_msgtype6_send_cprb(struct zcrypt_queue *zq, - struct ica_xcRB *xcRB, - struct ap_message *ap_msg) +static long zcrypt_msgtype6_send_cprb(bool userspace, struct zcrypt_queue *zq, + struct ica_xcRB *xcRB, + struct ap_message *ap_msg) { int rc; struct response_type *rtype = (struct response_type *)(ap_msg->private); @@ -1135,7 +1135,7 @@ static long zcrypt_msgtype6_send_cprb(struct zcrypt_queue *zq, if (rc == 0) { rc = ap_msg->rc; if (rc == 0) - rc = convert_response_xcrb(zq, ap_msg, xcRB); + rc = convert_response_xcrb(userspace, zq, ap_msg, xcRB); } else /* Signal pending. */ ap_cancel_message(zq->queue, ap_msg); @@ -1150,9 +1150,9 @@ static long zcrypt_msgtype6_send_cprb(struct zcrypt_queue *zq, * by the caller with ap_init_message(). Also the caller has to * make sure ap_release_message() is always called even on failure. */ -unsigned int get_ep11cprb_fc(struct ep11_urb *xcrb, - struct ap_message *ap_msg, - unsigned int *func_code) +unsigned int get_ep11cprb_fc(bool userspace, struct ep11_urb *xcrb, + struct ap_message *ap_msg, + unsigned int *func_code) { struct response_type resp_type = { .type = CEXXC_RESPONSE_TYPE_EP11, @@ -1167,7 +1167,7 @@ unsigned int get_ep11cprb_fc(struct ep11_urb *xcrb, ap_msg->private = kmemdup(&resp_type, sizeof(resp_type), GFP_KERNEL); if (!ap_msg->private) return -ENOMEM; - return xcrb_msg_to_type6_ep11cprb_msgx(ap_msg, xcrb, func_code); + return xcrb_msg_to_type6_ep11cprb_msgx(userspace, ap_msg, xcrb, func_code); } /** @@ -1177,7 +1177,7 @@ unsigned int get_ep11cprb_fc(struct ep11_urb *xcrb, * CEX4P device to the request distributor * @xcRB: pointer to the ep11 user request block */ -static long zcrypt_msgtype6_send_ep11_cprb(struct zcrypt_queue *zq, +static long zcrypt_msgtype6_send_ep11_cprb(bool userspace, struct zcrypt_queue *zq, struct ep11_urb *xcrb, struct ap_message *ap_msg) { @@ -1237,7 +1237,7 @@ static long zcrypt_msgtype6_send_ep11_cprb(struct zcrypt_queue *zq, if (rc == 0) { rc = ap_msg->rc; if (rc == 0) - rc = convert_response_ep11_xcrb(zq, ap_msg, xcrb); + rc = convert_response_ep11_xcrb(userspace, zq, ap_msg, xcrb); } else /* Signal pending. */ ap_cancel_message(zq->queue, ap_msg); diff --git a/drivers/s390/crypto/zcrypt_msgtype6.h b/drivers/s390/crypto/zcrypt_msgtype6.h index 0de280a81dd4..0a0bf074206b 100644 --- a/drivers/s390/crypto/zcrypt_msgtype6.h +++ b/drivers/s390/crypto/zcrypt_msgtype6.h @@ -96,9 +96,9 @@ struct type86_fmt2_ext { unsigned int offset4; /* 0x00000000 */ } __packed; -unsigned int get_cprb_fc(struct ica_xcRB *, struct ap_message *, +unsigned int get_cprb_fc(bool userspace, struct ica_xcRB *, struct ap_message *, unsigned int *, unsigned short **); -unsigned int get_ep11cprb_fc(struct ep11_urb *, struct ap_message *, +unsigned int get_ep11cprb_fc(bool userspace, struct ep11_urb *, struct ap_message *, unsigned int *); unsigned int get_rng_fc(struct ap_message *, int *, unsigned int *); From fc3f61e1bcd5f88bfb7241bf509a3f63bab49ea8 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 14 Sep 2020 13:15:15 +0200 Subject: [PATCH 213/645] s390/dis: get rid of set_fs() usage Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/dis.c | 22 ++++++++++++++-------- 1 file changed, 14 insertions(+), 8 deletions(-) diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c index f304802ecf7b..a7eab7be4db0 100644 --- a/arch/s390/kernel/dis.c +++ b/arch/s390/kernel/dis.c @@ -482,31 +482,37 @@ static int print_insn(char *buffer, unsigned char *code, unsigned long addr) return (int) (ptr - buffer); } +static int copy_from_regs(struct pt_regs *regs, void *dst, void *src, int len) +{ + if (user_mode(regs)) { + if (copy_from_user(dst, (char __user *)src, len)) + return -EFAULT; + } else { + if (copy_from_kernel_nofault(dst, src, len)) + return -EFAULT; + } + return 0; +} + void show_code(struct pt_regs *regs) { char *mode = user_mode(regs) ? "User" : "Krnl"; unsigned char code[64]; char buffer[128], *ptr; - mm_segment_t old_fs; unsigned long addr; int start, end, opsize, hops, i; /* Get a snapshot of the 64 bytes surrounding the fault address. */ - old_fs = get_fs(); - set_fs(user_mode(regs) ? USER_DS : KERNEL_DS); for (start = 32; start && regs->psw.addr >= 34 - start; start -= 2) { addr = regs->psw.addr - 34 + start; - if (__copy_from_user(code + start - 2, - (char __user *) addr, 2)) + if (copy_from_regs(regs, code + start - 2, (void *)addr, 2)) break; } for (end = 32; end < 64; end += 2) { addr = regs->psw.addr + end - 32; - if (__copy_from_user(code + end, - (char __user *) addr, 2)) + if (copy_from_regs(regs, code + end, (void *)addr, 2)) break; } - set_fs(old_fs); /* Code snapshot useable ? */ if ((regs->psw.addr & 1) || start >= end) { printk("%s Code: Bad PSW.\n", mode); From 110a6dbb2eca6b10bf60c61a51063d7fe1e55078 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 14 Sep 2020 13:42:25 +0200 Subject: [PATCH 214/645] s390/uaccess: add HAVE_GET_KERNEL_NOFAULT support Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/uaccess.h | 111 ++++++++++++++++++++++++++++++++ 1 file changed, 111 insertions(+) diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h index f09444d6aeab..23c85801cf04 100644 --- a/arch/s390/include/asm/uaccess.h +++ b/arch/s390/include/asm/uaccess.h @@ -278,4 +278,115 @@ static inline unsigned long __must_check clear_user(void __user *to, unsigned lo int copy_to_user_real(void __user *dest, void *src, unsigned long count); void *s390_kernel_write(void *dst, const void *src, size_t size); +#define HAVE_GET_KERNEL_NOFAULT + +int __noreturn __put_kernel_bad(void); + +#define __put_kernel_asm(val, to, insn) \ +({ \ + int __rc; \ + \ + asm volatile( \ + "0: " insn " %2,%1\n" \ + "1: xr %0,%0\n" \ + "2:\n" \ + ".pushsection .fixup, \"ax\"\n" \ + "3: lhi %0,%3\n" \ + " jg 2b\n" \ + ".popsection\n" \ + EX_TABLE(0b,3b) EX_TABLE(1b,3b) \ + : "=d" (__rc), "+Q" (*(to)) \ + : "d" (val), "K" (-EFAULT) \ + : "cc"); \ + __rc; \ +}) + +#define __put_kernel_nofault(dst, src, type, err_label) \ +do { \ + u64 __x = (u64)(*((type *)(src))); \ + int __pk_err; \ + \ + switch (sizeof(type)) { \ + case 1: \ + __pk_err = __put_kernel_asm(__x, (type *)(dst), "stc"); \ + break; \ + case 2: \ + __pk_err = __put_kernel_asm(__x, (type *)(dst), "sth"); \ + break; \ + case 4: \ + __pk_err = __put_kernel_asm(__x, (type *)(dst), "st"); \ + break; \ + case 8: \ + __pk_err = __put_kernel_asm(__x, (type *)(dst), "stg"); \ + break; \ + default: \ + __pk_err = __put_kernel_bad(); \ + break; \ + } \ + if (unlikely(__pk_err)) \ + goto err_label; \ +} while (0) + +int __noreturn __get_kernel_bad(void); + +#define __get_kernel_asm(val, from, insn) \ +({ \ + int __rc; \ + \ + asm volatile( \ + "0: " insn " %1,%2\n" \ + "1: xr %0,%0\n" \ + "2:\n" \ + ".pushsection .fixup, \"ax\"\n" \ + "3: lhi %0,%3\n" \ + " jg 2b\n" \ + ".popsection\n" \ + EX_TABLE(0b,3b) EX_TABLE(1b,3b) \ + : "=d" (__rc), "+d" (val) \ + : "Q" (*(from)), "K" (-EFAULT) \ + : "cc"); \ + __rc; \ +}) + +#define __get_kernel_nofault(dst, src, type, err_label) \ +do { \ + int __gk_err; \ + \ + switch (sizeof(type)) { \ + case 1: { \ + u8 __x = 0; \ + \ + __gk_err = __get_kernel_asm(__x, (type *)(src), "ic"); \ + *((type *)(dst)) = (type)__x; \ + break; \ + }; \ + case 2: { \ + u16 __x = 0; \ + \ + __gk_err = __get_kernel_asm(__x, (type *)(src), "lh"); \ + *((type *)(dst)) = (type)__x; \ + break; \ + }; \ + case 4: { \ + u32 __x = 0; \ + \ + __gk_err = __get_kernel_asm(__x, (type *)(src), "l"); \ + *((type *)(dst)) = (type)__x; \ + break; \ + }; \ + case 8: { \ + u64 __x = 0; \ + \ + __gk_err = __get_kernel_asm(__x, (type *)(src), "lg"); \ + *((type *)(dst)) = (type)__x; \ + break; \ + }; \ + default: \ + __gk_err = __get_kernel_bad(); \ + break; \ + } \ + if (unlikely(__gk_err)) \ + goto err_label; \ +} while (0) + #endif /* __S390_UACCESS_H */ From 61f2e77489182b9b0e2fabe875e151fd46d286a1 Mon Sep 17 00:00:00 2001 From: Liu Shixin Date: Wed, 16 Sep 2020 10:50:29 +0800 Subject: [PATCH 215/645] s390/diag: convert to use DEFINE_SEQ_ATTRIBUTE macro Use DEFINE_SEQ_ATTRIBUTE macro to simplify the code. Signed-off-by: Liu Shixin Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/diag.c | 13 +------------ 1 file changed, 1 insertion(+), 12 deletions(-) diff --git a/arch/s390/kernel/diag.c b/arch/s390/kernel/diag.c index ccba63aaeb47..b8b0cd7b008f 100644 --- a/arch/s390/kernel/diag.c +++ b/arch/s390/kernel/diag.c @@ -104,18 +104,7 @@ static const struct seq_operations show_diag_stat_sops = { .show = show_diag_stat, }; -static int show_diag_stat_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &show_diag_stat_sops); -} - -static const struct file_operations show_diag_stat_fops = { - .open = show_diag_stat_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - +DEFINE_SEQ_ATTRIBUTE(show_diag_stat); static int __init show_diag_stat_init(void) { From 48175fed1deaf8f37e918f504a5cff7504c583ad Mon Sep 17 00:00:00 2001 From: Qinglang Miao Date: Wed, 16 Sep 2020 14:21:30 +0800 Subject: [PATCH 216/645] s390/ap: remove unnecessary spin_lock_init() The spinlock ap_poll_timer_lock is initialized statically. It is unnecessary to initialize by spin_lock_init(). Signed-off-by: Qinglang Miao Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- drivers/s390/crypto/ap_bus.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index 24a1940b829e..231a98c9165d 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -1575,7 +1575,6 @@ static int __init ap_module_init(void) */ if (MACHINE_IS_VM) poll_timeout = 1500000; - spin_lock_init(&ap_poll_timer_lock); hrtimer_init(&ap_poll_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); ap_poll_timer.function = ap_poll_timeout; From d208e13c6a2277d9fb71fad6a1394c70bdd7b634 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Thu, 17 Sep 2020 12:20:16 +1000 Subject: [PATCH 217/645] powerpc/process: Fix uninitialised variable error Clang, and GCC with -Wmaybe-uninitialized, can't see that val is unused in get_fpexec_mode(): arch/powerpc/kernel/process.c:1940:7: error: variable 'val' is used uninitialized whenever 'if' condition is true if (cpu_has_feature(CPU_FTR_SPE)) { ^~~~~~~~~~~~~~~~~~~~~~~~~~~~ We know that CPU_FTR_SPE will only be true iff CONFIG_SPE is also true, but the compiler doesn't. Avoid it by initialising val to zero. Reported-by: kernel test robot Fixes: 532ed1900d37 ("powerpc/process: Remove useless #ifdef CONFIG_SPE") Signed-off-by: Michael Ellerman Reviewed-by: Nick Desaulniers Tested-by: Nick Desaulniers Link: https://lore.kernel.org/r/20200917024509.3253837-1-mpe@ellerman.id.au --- arch/powerpc/kernel/process.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 14d5189b17d8..d421a2c7f822 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1934,7 +1934,7 @@ int set_fpexc_mode(struct task_struct *tsk, unsigned int val) int get_fpexc_mode(struct task_struct *tsk, unsigned long adr) { - unsigned int val; + unsigned int val = 0; if (tsk->thread.fpexc_mode & PR_FP_EXC_SW_ENABLE) { if (cpu_has_feature(CPU_FTR_SPE)) { From bda7673d64b6c2e92423363a756caa657464e096 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Thu, 17 Sep 2020 10:06:43 +0800 Subject: [PATCH 218/645] powerpc/book3s64: fix link error with CONFIG_PPC_RADIX_MMU=n Fix link error when CONFIG_PPC_RADIX_MMU is disabled: powerpc64-linux-gnu-ld: arch/powerpc/platforms/pseries/lpar.o:(.toc+0x0): undefined reference to `mmu_pid_bits' Reported-by: Hulk Robot Signed-off-by: Yang Yingliang Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200917020643.90375-1-yangyingliang@huawei.com --- arch/powerpc/platforms/pseries/lpar.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index baf24eacd268..764170fdb0f7 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -1724,6 +1724,7 @@ void __init hpte_init_pseries(void) pseries_lpar_register_process_table(0, 0, 0); } +#ifdef CONFIG_PPC_RADIX_MMU void radix_init_pseries(void) { pr_info("Using radix MMU under hypervisor\n"); @@ -1731,6 +1732,7 @@ void radix_init_pseries(void) pseries_lpar_register_process_table(__pa(process_tb), 0, PRTB_SIZE_SHIFT - 12); } +#endif #ifdef CONFIG_PPC_SMLPAR #define CMO_FREE_HINT_DEFAULT 1 From 96543e7352bded5d6d1a0e0022376ebdd6c1b8ab Mon Sep 17 00:00:00 2001 From: Liu Shixin Date: Wed, 16 Sep 2020 10:50:26 +0800 Subject: [PATCH 219/645] powerpc/pseries: convert to use DEFINE_SEQ_ATTRIBUTE macro Use DEFINE_SEQ_ATTRIBUTE macro to simplify the code. Signed-off-by: Liu Shixin Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200916025026.3992835-1-liushixin2@huawei.com --- arch/powerpc/platforms/pseries/hvCall_inst.c | 23 +++----------------- 1 file changed, 3 insertions(+), 20 deletions(-) diff --git a/arch/powerpc/platforms/pseries/hvCall_inst.c b/arch/powerpc/platforms/pseries/hvCall_inst.c index c40c62ec432e..2c59b4986ea5 100644 --- a/arch/powerpc/platforms/pseries/hvCall_inst.c +++ b/arch/powerpc/platforms/pseries/hvCall_inst.c @@ -70,31 +70,14 @@ static int hc_show(struct seq_file *m, void *p) return 0; } -static const struct seq_operations hcall_inst_seq_ops = { +static const struct seq_operations hcall_inst_sops = { .start = hc_start, .next = hc_next, .stop = hc_stop, .show = hc_show }; -static int hcall_inst_seq_open(struct inode *inode, struct file *file) -{ - int rc; - struct seq_file *seq; - - rc = seq_open(file, &hcall_inst_seq_ops); - seq = file->private_data; - seq->private = file_inode(file)->i_private; - - return rc; -} - -static const struct file_operations hcall_inst_seq_fops = { - .open = hcall_inst_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; +DEFINE_SEQ_ATTRIBUTE(hcall_inst); #define HCALL_ROOT_DIR "hcall_inst" #define CPU_NAME_BUF_SIZE 32 @@ -149,7 +132,7 @@ static int __init hcall_inst_init(void) snprintf(cpu_name_buf, CPU_NAME_BUF_SIZE, "cpu%d", cpu); debugfs_create_file(cpu_name_buf, 0444, hcall_root, per_cpu(hcall_stats, cpu), - &hcall_inst_seq_fops); + &hcall_inst_fops); } return 0; From ef1edbba52883907caf02ab85e0d00a2e4648f05 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 16 Sep 2020 21:56:36 +1000 Subject: [PATCH 220/645] powerpc/mm/64s: Fix slb_setup_new_exec() sparse warning Sparse says: symbol slb_setup_new_exec was not declared. Should it be static? No, it should have a declaration in a header, add one. Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200916115637.3100484-1-mpe@ellerman.id.au --- arch/powerpc/mm/book3s64/internal.h | 2 ++ arch/powerpc/mm/book3s64/mmu_context.c | 4 ++-- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/mm/book3s64/internal.h b/arch/powerpc/mm/book3s64/internal.h index 7eda0d30d765..c12d78ee42f5 100644 --- a/arch/powerpc/mm/book3s64/internal.h +++ b/arch/powerpc/mm/book3s64/internal.h @@ -13,4 +13,6 @@ static inline bool stress_slb(void) return static_branch_unlikely(&stress_slb_key); } +void slb_setup_new_exec(void); + #endif /* ARCH_POWERPC_MM_BOOK3S64_INTERNAL_H */ diff --git a/arch/powerpc/mm/book3s64/mmu_context.c b/arch/powerpc/mm/book3s64/mmu_context.c index 0ba30b8b935b..1c54821de7bf 100644 --- a/arch/powerpc/mm/book3s64/mmu_context.c +++ b/arch/powerpc/mm/book3s64/mmu_context.c @@ -21,6 +21,8 @@ #include #include +#include "internal.h" + static DEFINE_IDA(mmu_context_ida); static int alloc_context_id(int min_id, int max_id) @@ -48,8 +50,6 @@ int hash__alloc_context_id(void) } EXPORT_SYMBOL_GPL(hash__alloc_context_id); -void slb_setup_new_exec(void); - static int realloc_context_ids(mm_context_t *ctx) { int i, id; From d10ebe79dfae7dc59b6cf77ffa615f0b8dae21bf Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 16 Sep 2020 21:56:37 +1000 Subject: [PATCH 221/645] powerpc/perf: Add declarations to fix sparse warnings Sparse warns about all the init functions: symbol init_ppc970_pmu was not declared. Should it be static? symbol init_power5p_pmu was not declared. Should it be static? symbol init_power5_pmu was not declared. Should it be static? symbol init_power6_pmu was not declared. Should it be static? symbol init_power7_pmu was not declared. Should it be static? symbol init_power9_pmu was not declared. Should it be static? symbol init_power8_pmu was not declared. Should it be static? symbol init_generic_compat_pmu was not declared. Should it be static? They're already declared in internal.h, so just make sure all the C files include that directly or indirectly. Signed-off-by: Michael Ellerman Reviewed-by: Madhavan Srinivasan Link: https://lore.kernel.org/r/20200916115637.3100484-2-mpe@ellerman.id.au --- arch/powerpc/perf/isa207-common.h | 2 ++ arch/powerpc/perf/power10-pmu.c | 1 - arch/powerpc/perf/power5+-pmu.c | 2 ++ arch/powerpc/perf/power5-pmu.c | 2 ++ arch/powerpc/perf/power6-pmu.c | 2 ++ arch/powerpc/perf/power7-pmu.c | 2 ++ arch/powerpc/perf/ppc970-pmu.c | 2 ++ 7 files changed, 12 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/perf/isa207-common.h b/arch/powerpc/perf/isa207-common.h index 044de65e96b9..7025de5e60e7 100644 --- a/arch/powerpc/perf/isa207-common.h +++ b/arch/powerpc/perf/isa207-common.h @@ -13,6 +13,8 @@ #include #include +#include "internal.h" + #define EVENT_EBB_MASK 1ull #define EVENT_EBB_SHIFT PERF_EVENT_CONFIG_EBB_SHIFT #define EVENT_BHRB_MASK 1ull diff --git a/arch/powerpc/perf/power10-pmu.c b/arch/powerpc/perf/power10-pmu.c index 83148656b524..9dbe8f9b89b4 100644 --- a/arch/powerpc/perf/power10-pmu.c +++ b/arch/powerpc/perf/power10-pmu.c @@ -9,7 +9,6 @@ #define pr_fmt(fmt) "power10-pmu: " fmt #include "isa207-common.h" -#include "internal.h" /* * Raw event encoding for Power10: diff --git a/arch/powerpc/perf/power5+-pmu.c b/arch/powerpc/perf/power5+-pmu.c index a62b2cd7914f..3e64b4a1511f 100644 --- a/arch/powerpc/perf/power5+-pmu.c +++ b/arch/powerpc/perf/power5+-pmu.c @@ -10,6 +10,8 @@ #include #include +#include "internal.h" + /* * Bits in event code for POWER5+ (POWER5 GS) and POWER5++ (POWER5 GS DD3) */ diff --git a/arch/powerpc/perf/power5-pmu.c b/arch/powerpc/perf/power5-pmu.c index 8732b587cf71..017bb19b73fb 100644 --- a/arch/powerpc/perf/power5-pmu.c +++ b/arch/powerpc/perf/power5-pmu.c @@ -10,6 +10,8 @@ #include #include +#include "internal.h" + /* * Bits in event code for POWER5 (not POWER5++) */ diff --git a/arch/powerpc/perf/power6-pmu.c b/arch/powerpc/perf/power6-pmu.c index 0e318cf87129..189974478e9f 100644 --- a/arch/powerpc/perf/power6-pmu.c +++ b/arch/powerpc/perf/power6-pmu.c @@ -10,6 +10,8 @@ #include #include +#include "internal.h" + /* * Bits in event code for POWER6 */ diff --git a/arch/powerpc/perf/power7-pmu.c b/arch/powerpc/perf/power7-pmu.c index 5e0bf09cf077..bacfab104a1a 100644 --- a/arch/powerpc/perf/power7-pmu.c +++ b/arch/powerpc/perf/power7-pmu.c @@ -10,6 +10,8 @@ #include #include +#include "internal.h" + /* * Bits in event code for POWER7 */ diff --git a/arch/powerpc/perf/ppc970-pmu.c b/arch/powerpc/perf/ppc970-pmu.c index d35223fb112c..7d78df97f272 100644 --- a/arch/powerpc/perf/ppc970-pmu.c +++ b/arch/powerpc/perf/ppc970-pmu.c @@ -9,6 +9,8 @@ #include #include +#include "internal.h" + /* * Bits in event code for PPC970 */ From 1ea21ba231f248034e8c794aa675869ca2b97d42 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 19 Aug 2020 11:56:32 +1000 Subject: [PATCH 222/645] powerpc: Move arch_cpu_idle_dead() into smp.c arch_cpu_idle_dead() is in idle.c, which makes sense, but it's inside a CONFIG_HOTPLUG_CPU block. It would be more at home in smp.c, inside the existing CONFIG_HOTPLUG_CPU block. Note that CONFIG_HOTPLUG_CPU depends on CONFIG_SMP so even though smp.c is not built for SMP=n builds, that's fine. Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200819015634.1974478-1-mpe@ellerman.id.au --- arch/powerpc/kernel/idle.c | 8 -------- arch/powerpc/kernel/smp.c | 6 ++++++ 2 files changed, 6 insertions(+), 8 deletions(-) diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c index 422e31d2f5a2..ae0e2632393d 100644 --- a/arch/powerpc/kernel/idle.c +++ b/arch/powerpc/kernel/idle.c @@ -41,14 +41,6 @@ static int __init powersave_off(char *arg) } __setup("powersave=off", powersave_off); -#ifdef CONFIG_HOTPLUG_CPU -void arch_cpu_idle_dead(void) -{ - sched_preempt_enable_no_resched(); - cpu_die(); -} -#endif - void arch_cpu_idle(void) { ppc64_runlatch_off(); diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 3d96752d6570..24b0476c1d4f 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -1489,6 +1489,12 @@ void __cpu_die(unsigned int cpu) smp_ops->cpu_die(cpu); } +void arch_cpu_idle_dead(void) +{ + sched_preempt_enable_no_resched(); + cpu_die(); +} + void cpu_die(void) { /* From bf3c1464db883a953ad7bbed64924480b8b2b244 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 19 Aug 2020 11:56:33 +1000 Subject: [PATCH 223/645] powerpc/smp: Fold cpu_die() into its only caller Avoid the eternal confusion between cpu_die() and __cpu_die() by removing the former, folding it into its only caller. Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200819015634.1974478-2-mpe@ellerman.id.au --- arch/powerpc/include/asm/smp.h | 1 - arch/powerpc/kernel/smp.c | 4 ---- 2 files changed, 5 deletions(-) diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index 041f0b97c45b..0bf80c5b440a 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -30,7 +30,6 @@ extern int spinning_secondaries; extern u32 *cpu_to_phys_id; extern bool coregroup_enabled; -extern void cpu_die(void); extern int cpu_to_chip_id(int cpu); #ifdef CONFIG_SMP diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 24b0476c1d4f..4ae767c455b8 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -1492,11 +1492,7 @@ void __cpu_die(unsigned int cpu) void arch_cpu_idle_dead(void) { sched_preempt_enable_no_resched(); - cpu_die(); -} -void cpu_die(void) -{ /* * Disable on the down path. This will be re-enabled by * start_secondary() via start_secondary_resume() below From 39f87561454dc33efb2a3d8354d066207acac8a6 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 19 Aug 2020 11:56:34 +1000 Subject: [PATCH 224/645] powerpc/smp: Move ppc_md.cpu_die() to smp_ops.cpu_offline_self() We have smp_ops->cpu_die() and ppc_md.cpu_die(). One of them offlines the current CPU and one offlines another CPU, can you guess which is which? Also one is in smp_ops and one is in ppc_md? So rename ppc_md.cpu_die(), to cpu_offline_self(), because that's what it does. And move it into smp_ops where it belongs. Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200819015634.1974478-3-mpe@ellerman.id.au --- arch/powerpc/include/asm/machdep.h | 1 - arch/powerpc/include/asm/smp.h | 3 +++ arch/powerpc/kernel/smp.c | 4 ++-- arch/powerpc/kernel/sysfs.c | 4 +++- arch/powerpc/platforms/85xx/smp.c | 4 ++-- arch/powerpc/platforms/powermac/pmac.h | 2 +- arch/powerpc/platforms/powermac/sleep.S | 6 +++--- arch/powerpc/platforms/powermac/smp.c | 8 ++++---- arch/powerpc/platforms/powernv/smp.c | 4 ++-- arch/powerpc/platforms/pseries/hotplug-cpu.c | 6 +++--- 10 files changed, 23 insertions(+), 19 deletions(-) diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index 5082cd496190..95081078aa8a 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -65,7 +65,6 @@ struct machdep_calls { void __noreturn (*restart)(char *cmd); void __noreturn (*halt)(void); void (*panic)(char *str); - void (*cpu_die)(void); long (*time_init)(void); /* Optional, may be NULL */ diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index 0bf80c5b440a..635bdf947105 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -50,6 +50,9 @@ struct smp_ops_t { int (*cpu_disable)(void); void (*cpu_die)(unsigned int nr); int (*cpu_bootable)(unsigned int nr); +#ifdef CONFIG_HOTPLUG_CPU + void (*cpu_offline_self)(void); +#endif }; extern int smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us); diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 4ae767c455b8..58990baa5182 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -1499,8 +1499,8 @@ void arch_cpu_idle_dead(void) */ this_cpu_disable_ftrace(); - if (ppc_md.cpu_die) - ppc_md.cpu_die(); + if (smp_ops->cpu_offline_self) + smp_ops->cpu_offline_self(); /* If we return, we re-enter start_secondary */ start_secondary_resume(); diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 5dea98fa2f93..928b29e0ee83 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -1160,6 +1160,7 @@ static int __init topology_init(void) for_each_possible_cpu(cpu) { struct cpu *c = &per_cpu(cpu_devices, cpu); +#ifdef CONFIG_HOTPLUG_CPU /* * For now, we just see if the system supports making * the RTAS calls for CPU hotplug. But, there may be a @@ -1167,8 +1168,9 @@ static int __init topology_init(void) * CPU. For instance, the boot cpu might never be valid * for hotplugging. */ - if (ppc_md.cpu_die) + if (smp_ops->cpu_offline_self) c->hotpluggable = 1; +#endif if (cpu_online(cpu) || c->hotpluggable) { register_cpu(c, cpu); diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c index fda108bae95f..c6df294054fe 100644 --- a/arch/powerpc/platforms/85xx/smp.c +++ b/arch/powerpc/platforms/85xx/smp.c @@ -112,7 +112,7 @@ static void mpc85xx_take_timebase(void) local_irq_restore(flags); } -static void smp_85xx_mach_cpu_die(void) +static void smp_85xx_cpu_offline_self(void) { unsigned int cpu = smp_processor_id(); @@ -506,7 +506,7 @@ void __init mpc85xx_smp_init(void) if (qoriq_pm_ops) { smp_85xx_ops.give_timebase = mpc85xx_give_timebase; smp_85xx_ops.take_timebase = mpc85xx_take_timebase; - ppc_md.cpu_die = smp_85xx_mach_cpu_die; + smp_85xx_ops.cpu_offline_self = smp_85xx_cpu_offline_self; smp_85xx_ops.cpu_die = qoriq_cpu_kill; } #endif diff --git a/arch/powerpc/platforms/powermac/pmac.h b/arch/powerpc/platforms/powermac/pmac.h index 16a52afdb76e..0d715db434dc 100644 --- a/arch/powerpc/platforms/powermac/pmac.h +++ b/arch/powerpc/platforms/powermac/pmac.h @@ -34,7 +34,7 @@ extern void pmac_check_ht_link(void); extern void pmac_setup_smp(void); extern int psurge_secondary_virq; -extern void low_cpu_die(void) __attribute__((noreturn)); +extern void low_cpu_offline_self(void) __attribute__((noreturn)); extern int pmac_nvram_init(void); extern void pmac_pic_init(void); diff --git a/arch/powerpc/platforms/powermac/sleep.S b/arch/powerpc/platforms/powermac/sleep.S index 51bfdfe85058..7e0f8ba6e54a 100644 --- a/arch/powerpc/platforms/powermac/sleep.S +++ b/arch/powerpc/platforms/powermac/sleep.S @@ -201,8 +201,8 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) addi r3,r3,sleep_storage@l stw r5,0(r3) - .globl low_cpu_die -low_cpu_die: + .globl low_cpu_offline_self +low_cpu_offline_self: /* Flush & disable all caches */ bl flush_disable_caches @@ -244,7 +244,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_SPEC7450) mtmsr r2 isync b 1b -_ASM_NOKPROBE_SYMBOL(low_cpu_die) +_ASM_NOKPROBE_SYMBOL(low_cpu_offline_self) /* * Here is the resume code. */ diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c index eb23264910e1..a6fedcfb714f 100644 --- a/arch/powerpc/platforms/powermac/smp.c +++ b/arch/powerpc/platforms/powermac/smp.c @@ -920,7 +920,7 @@ static int smp_core99_cpu_disable(void) #ifdef CONFIG_PPC32 -static void pmac_cpu_die(void) +static void pmac_cpu_offline_self(void) { int cpu = smp_processor_id(); @@ -930,12 +930,12 @@ static void pmac_cpu_die(void) generic_set_cpu_dead(cpu); smp_wmb(); mb(); - low_cpu_die(); + low_cpu_offline_self(); } #else /* CONFIG_PPC32 */ -static void pmac_cpu_die(void) +static void pmac_cpu_offline_self(void) { int cpu = smp_processor_id(); @@ -1020,7 +1020,7 @@ void __init pmac_setup_smp(void) #endif /* CONFIG_PPC_PMAC32_PSURGE */ #ifdef CONFIG_HOTPLUG_CPU - ppc_md.cpu_die = pmac_cpu_die; + smp_ops->cpu_offline_self = pmac_cpu_offline_self; #endif } diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index bbf361f23ae8..54c4ba45c7ce 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -158,7 +158,7 @@ static void pnv_flush_interrupts(void) } } -static void pnv_smp_cpu_kill_self(void) +static void pnv_cpu_offline_self(void) { unsigned long srr1, unexpected_mask, wmask; unsigned int cpu; @@ -417,6 +417,7 @@ static struct smp_ops_t pnv_smp_ops = { #ifdef CONFIG_HOTPLUG_CPU .cpu_disable = pnv_smp_cpu_disable, .cpu_die = generic_cpu_die, + .cpu_offline_self = pnv_cpu_offline_self, #endif /* CONFIG_HOTPLUG_CPU */ }; @@ -430,7 +431,6 @@ void __init pnv_smp_init(void) smp_ops = &pnv_smp_ops; #ifdef CONFIG_HOTPLUG_CPU - ppc_md.cpu_die = pnv_smp_cpu_kill_self; #ifdef CONFIG_KEXEC_CORE crash_wake_offline = 1; #endif diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index 7a974ed6b240..f2837e33bf5d 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -55,7 +55,7 @@ static void rtas_stop_self(void) panic("Alas, I survived.\n"); } -static void pseries_mach_cpu_die(void) +static void pseries_cpu_offline_self(void) { unsigned int hwcpu = hard_smp_processor_id(); @@ -102,7 +102,7 @@ static int pseries_cpu_disable(void) * to self-destroy so that the cpu-offline thread can send the CPU_DEAD * notifications. * - * OTOH, pseries_mach_cpu_die() is called by the @cpu when it wants to + * OTOH, pseries_cpu_offline_self() is called by the @cpu when it wants to * self-destruct. */ static void pseries_cpu_die(unsigned int cpu) @@ -901,7 +901,7 @@ static int __init pseries_cpu_hotplug_init(void) return 0; } - ppc_md.cpu_die = pseries_mach_cpu_die; + smp_ops->cpu_offline_self = pseries_cpu_offline_self; smp_ops->cpu_disable = pseries_cpu_disable; smp_ops->cpu_die = pseries_cpu_die; From 6c71cfcc01685ef495ca7886471a76e73446424e Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 21 Aug 2020 20:34:07 +1000 Subject: [PATCH 225/645] powerpc/prom_init: Check display props exist before enabling btext It's possible to enable CONFIG_PPC_EARLY_DEBUG_BOOTX for a pseries kernel (maybe it shouldn't be), which is then booted with qemu/slof. But if you do that the kernel crashes in draw_byte(), with a DAR pointing somewhere near INT_MAX. Adding some debug to prom_init we see that we're not able to read the "address" property from OF, so we're just using whatever junk value was on the stack. So check the properties can be read properly from OF, if not we bail out before initialising btext, which avoids the crash. Signed-off-by: Michael Ellerman Reviewed-by: Alexey Kardashevskiy Link: https://lore.kernel.org/r/20200821103407.3362149-1-mpe@ellerman.id.au --- arch/powerpc/kernel/prom_init.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index ae7ec9903191..5090a5ab54e5 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -2422,10 +2422,19 @@ static void __init prom_check_displays(void) u32 width, height, pitch, addr; prom_printf("Setting btext !\n"); - prom_getprop(node, "width", &width, 4); - prom_getprop(node, "height", &height, 4); - prom_getprop(node, "linebytes", &pitch, 4); - prom_getprop(node, "address", &addr, 4); + + if (prom_getprop(node, "width", &width, 4) == PROM_ERROR) + return; + + if (prom_getprop(node, "height", &height, 4) == PROM_ERROR) + return; + + if (prom_getprop(node, "linebytes", &pitch, 4) == PROM_ERROR) + return; + + if (prom_getprop(node, "address", &addr, 4) == PROM_ERROR) + return; + prom_printf("W=%d H=%d LB=%d addr=0x%x\n", width, height, pitch, addr); btext_setup_display(width, height, 8, pitch, addr); From 9c826d31a73815464bd3df81e56d39b3d908ac73 Mon Sep 17 00:00:00 2001 From: Qinglang Miao Date: Wed, 16 Sep 2020 14:21:22 +0800 Subject: [PATCH 226/645] drivers/macintosh/smu.c: use for_each_child_of_node() macro Use for_each_child_of_node() macro instead of open coding it. Signed-off-by: Qinglang Miao Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200916062122.190586-1-miaoqinglang@huawei.com --- drivers/macintosh/smu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/macintosh/smu.c b/drivers/macintosh/smu.c index ca2a0bc5c33e..51b6f2aa5291 100644 --- a/drivers/macintosh/smu.c +++ b/drivers/macintosh/smu.c @@ -638,7 +638,7 @@ static void smu_expose_childs(struct work_struct *unused) { struct device_node *np; - for (np = NULL; (np = of_get_next_child(smu->of_node, np)) != NULL;) + for_each_child_of_node(smu->of_node, np) if (of_device_is_compatible(np, "smu-sensors")) of_platform_device_create(np, "smu-sensors", &smu->of_dev->dev); From acff5e6c37fa4bf8d002c917a762c4f7615f6eaf Mon Sep 17 00:00:00 2001 From: Qinglang Miao Date: Wed, 16 Sep 2020 14:21:25 +0800 Subject: [PATCH 227/645] macintosh: smu_sensors: use for_each_child_of_node() macro Use for_each_child_of_node() macro instead of open coding it. Signed-off-by: Qinglang Miao Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200916062125.190729-1-miaoqinglang@huawei.com --- drivers/macintosh/windfarm_smu_sensors.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/macintosh/windfarm_smu_sensors.c b/drivers/macintosh/windfarm_smu_sensors.c index 3e6059eaa138..c8706cfb83fd 100644 --- a/drivers/macintosh/windfarm_smu_sensors.c +++ b/drivers/macintosh/windfarm_smu_sensors.c @@ -421,8 +421,7 @@ static int __init smu_sensors_init(void) return -ENODEV; /* Look for sensors subdir */ - for (sensors = NULL; - (sensors = of_get_next_child(smu, sensors)) != NULL;) + for_each_child_of_node(smu, sensors) if (of_node_name_eq(sensors, "sensors")) break; From 1d42e07e9c249b7a032fba82b673ee8a8d6bd7b7 Mon Sep 17 00:00:00 2001 From: Qinglang Miao Date: Wed, 16 Sep 2020 14:21:38 +0800 Subject: [PATCH 228/645] serial: pmac_zilog: use for_each_child_of_node() macro Use for_each_child_of_node() macro instead of open coding it. Signed-off-by: Qinglang Miao Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200916062138.191188-1-miaoqinglang@huawei.com --- drivers/tty/serial/pmac_zilog.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/tty/serial/pmac_zilog.c b/drivers/tty/serial/pmac_zilog.c index 96e7aa479961..063484b22523 100644 --- a/drivers/tty/serial/pmac_zilog.c +++ b/drivers/tty/serial/pmac_zilog.c @@ -1644,7 +1644,7 @@ static int __init pmz_probe(void) * TODO: Add routines with proper locking to do that... */ node_a = node_b = NULL; - for (np = NULL; (np = of_get_next_child(node_p, np)) != NULL;) { + for_each_child_of_node(node_p, np) { if (of_node_name_prefix(np, "ch-a")) node_a = of_node_get(np); else if (of_node_name_prefix(np, "ch-b")) From 8ec5cb12cd957e59b0470b75d26c901aaf645bc3 Mon Sep 17 00:00:00 2001 From: Qinglang Miao Date: Wed, 16 Sep 2020 14:21:29 +0800 Subject: [PATCH 229/645] powerpc/powernv: fix wrong warning message in opalcore_config_init() The logic of the warn output is incorrect. The two args should be exchanged. Signed-off-by: Qinglang Miao Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200916062129.190864-1-miaoqinglang@huawei.com --- arch/powerpc/platforms/powernv/opal-core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/platforms/powernv/opal-core.c b/arch/powerpc/platforms/powernv/opal-core.c index 6dba3b62269f..23571f0b555a 100644 --- a/arch/powerpc/platforms/powernv/opal-core.c +++ b/arch/powerpc/platforms/powernv/opal-core.c @@ -510,7 +510,7 @@ static void __init opalcore_config_init(void) idx = be32_to_cpu(opalc_metadata->region_cnt); if (idx > MAX_PT_LOAD_CNT) { pr_warn("WARNING: OPAL regions count (%d) adjusted to limit (%d)", - MAX_PT_LOAD_CNT, idx); + idx, MAX_PT_LOAD_CNT); idx = MAX_PT_LOAD_CNT; } for (i = 0; i < idx; i++) { From 7b2aab5f22f0f7cc9e2f8672c9e65e2e88d30102 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= Date: Mon, 14 Sep 2020 23:10:01 +0200 Subject: [PATCH 230/645] powerpc/sysfs: Remove unused 'err' variable in sysfs_create_dscr_default() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This fixes a compile error with W=1. arch/powerpc/kernel/sysfs.c: In function ‘sysfs_create_dscr_default’: arch/powerpc/kernel/sysfs.c:228:7: error: variable ‘err’ set but not used [-Werror=unused-but-set-variable] int err = 0; ^~~ cc1: all warnings being treated as errors Signed-off-by: Cédric Le Goater Reviewed-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200914211007.2285999-2-clg@kaod.org --- arch/powerpc/kernel/sysfs.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 928b29e0ee83..2e08640bb3b4 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -217,14 +217,13 @@ static DEVICE_ATTR(dscr_default, 0600, static void sysfs_create_dscr_default(void) { if (cpu_has_feature(CPU_FTR_DSCR)) { - int err = 0; int cpu; dscr_default = spr_default_dscr; for_each_possible_cpu(cpu) paca_ptrs[cpu]->dscr_default = dscr_default; - err = device_create_file(cpu_subsys.dev_root, &dev_attr_dscr_default); + device_create_file(cpu_subsys.dev_root, &dev_attr_dscr_default); } } #endif /* CONFIG_PPC64 */ From 5ab187e01a5310e1f9cd2f6b192b2343b8bd14cb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= Date: Mon, 14 Sep 2020 23:10:03 +0200 Subject: [PATCH 231/645] powerpc/sstep: Remove empty if statement checking for invalid form MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The check should be performed by the caller. This fixes a compile error with W=1. ../arch/powerpc/lib/sstep.c: In function ‘mlsd_8lsd_ea’: ../arch/powerpc/lib/sstep.c:225:3: error: suggest braces around empty body in an ‘if’ statement [-Werror=empty-body] ; /* Invalid form. Should already be checked for by caller! */ ^ Signed-off-by: Cédric Le Goater Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200914211007.2285999-4-clg@kaod.org --- arch/powerpc/lib/sstep.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c index caee8cc77e19..e9dcaba9a4f8 100644 --- a/arch/powerpc/lib/sstep.c +++ b/arch/powerpc/lib/sstep.c @@ -219,10 +219,13 @@ static nokprobe_inline unsigned long mlsd_8lsd_ea(unsigned int instr, ea += regs->gpr[ra]; else if (!prefix_r && !ra) ; /* Leave ea as is */ - else if (prefix_r && !ra) + else if (prefix_r) ea += regs->nip; - else if (prefix_r && ra) - ; /* Invalid form. Should already be checked for by caller! */ + + /* + * (prefix_r && ra) is an invalid form. Should already be + * checked for by caller! + */ return ea; } From 2228f19cf90ef796c8d84f54f3a5db2dcc85c83f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= Date: Mon, 14 Sep 2020 23:10:04 +0200 Subject: [PATCH 232/645] powerpc/xive: Make debug routines static MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This fixes a compile error with W=1. CC arch/powerpc/sysdev/xive/common.o ../arch/powerpc/sysdev/xive/common.c:1568:6: error: no previous prototype for ‘xive_debug_show_cpu’ [-Werror=missing-prototypes] void xive_debug_show_cpu(struct seq_file *m, int cpu) ^~~~~~~~~~~~~~~~~~~ ../arch/powerpc/sysdev/xive/common.c:1602:6: error: no previous prototype for ‘xive_debug_show_irq’ [-Werror=missing-prototypes] void xive_debug_show_irq(struct seq_file *m, u32 hw_irq, struct irq_data *d) ^~~~~~~~~~~~~~~~~~~ Fixes: 930914b7d528 ("powerpc/xive: Add a debugfs file to dump internal XIVE state") Signed-off-by: Cédric Le Goater Reviewed-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200914211007.2285999-5-clg@kaod.org --- arch/powerpc/sysdev/xive/common.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c index f591be9f01f4..a80440af491a 100644 --- a/arch/powerpc/sysdev/xive/common.c +++ b/arch/powerpc/sysdev/xive/common.c @@ -1565,7 +1565,7 @@ static int __init xive_off(char *arg) } __setup("xive=off", xive_off); -void xive_debug_show_cpu(struct seq_file *m, int cpu) +static void xive_debug_show_cpu(struct seq_file *m, int cpu) { struct xive_cpu *xc = per_cpu(xive_cpu, cpu); @@ -1599,7 +1599,7 @@ void xive_debug_show_cpu(struct seq_file *m, int cpu) seq_puts(m, "\n"); } -void xive_debug_show_irq(struct seq_file *m, u32 hw_irq, struct irq_data *d) +static void xive_debug_show_irq(struct seq_file *m, u32 hw_irq, struct irq_data *d) { struct irq_chip *chip = irq_data_get_irq_chip(d); int rc; From ebbfeef0d8093a06ff39c60105b6650be3344cbe Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= Date: Mon, 14 Sep 2020 23:10:07 +0200 Subject: [PATCH 233/645] powerpc/32: Declare stack_overflow_exception() prototype MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This fixes a compile error with W=1. CC arch/powerpc/kernel/traps.o ../arch/powerpc/kernel/traps.c:1663:6: error: no previous prototype for ‘stack_overflow_exception’ [-Werror=missing-prototypes] void stack_overflow_exception(struct pt_regs *regs) ^~~~~~~~~~~~~~~~~~~~~~~~ Fixes: 3978eb78517c ("powerpc/32: Add early stack overflow detection with VMAP stack.") Signed-off-by: Cédric Le Goater Reviewed-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200914211007.2285999-8-clg@kaod.org --- arch/powerpc/include/asm/asm-prototypes.h | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h index de14b1a34d56..4957119604c7 100644 --- a/arch/powerpc/include/asm/asm-prototypes.h +++ b/arch/powerpc/include/asm/asm-prototypes.h @@ -67,6 +67,7 @@ void single_step_exception(struct pt_regs *regs); void program_check_exception(struct pt_regs *regs); void alignment_exception(struct pt_regs *regs); void StackOverflow(struct pt_regs *regs); +void stack_overflow_exception(struct pt_regs *regs); void kernel_fp_unavailable_exception(struct pt_regs *regs); void altivec_unavailable_exception(struct pt_regs *regs); void vsx_unavailable_exception(struct pt_regs *regs); From 38a6445cab6ba4bf6b32f28552d2a7d87dc4414a Mon Sep 17 00:00:00 2001 From: Wei Li Date: Fri, 18 Sep 2020 09:41:11 +0800 Subject: [PATCH 234/645] MIPS: Correct the header guard of r4k-timer.h Rename the header guard of r4k-timer.h from __ASM_R4K_TYPES_H to __ASM_R4K_TIMER_H what corresponding with the file name. Signed-off-by: Wei Li Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/r4k-timer.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/mips/include/asm/r4k-timer.h b/arch/mips/include/asm/r4k-timer.h index afe9e0e03fe9..6e7361629348 100644 --- a/arch/mips/include/asm/r4k-timer.h +++ b/arch/mips/include/asm/r4k-timer.h @@ -5,8 +5,8 @@ * * Copyright (C) 2008 by Ralf Baechle (ralf@linux-mips.org) */ -#ifndef __ASM_R4K_TYPES_H -#define __ASM_R4K_TYPES_H +#ifndef __ASM_R4K_TIMER_H +#define __ASM_R4K_TIMER_H #include @@ -27,4 +27,4 @@ static inline void synchronise_count_slave(int cpu) #endif -#endif /* __ASM_R4K_TYPES_H */ +#endif /* __ASM_R4K_TIMER_H */ From b0a1c2903b5f43861a78a25fe4f389d99607ae04 Mon Sep 17 00:00:00 2001 From: Zhang Qilong Date: Thu, 17 Sep 2020 15:46:22 +0800 Subject: [PATCH 235/645] MIPS: pci: use devm_platform_ioremap_resource_byname Use the devm_platform_ioremap_resource_byname() helper instead of calling platform_get_resource_byname() and devm_ioremap_resource() separately. Signed-off-by: Zhang Qilong Signed-off-by: Thomas Bogendoerfer --- arch/mips/pci/pci-ar2315.c | 5 ++--- arch/mips/pci/pci-ar71xx.c | 4 ++-- arch/mips/pci/pci-ar724x.c | 9 +++------ 3 files changed, 7 insertions(+), 11 deletions(-) diff --git a/arch/mips/pci/pci-ar2315.c b/arch/mips/pci/pci-ar2315.c index 490953f51528..d1b141e8f301 100644 --- a/arch/mips/pci/pci-ar2315.c +++ b/arch/mips/pci/pci-ar2315.c @@ -423,9 +423,8 @@ static int ar2315_pci_probe(struct platform_device *pdev) return -EINVAL; apc->irq = irq; - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, - "ar2315-pci-ctrl"); - apc->mmr_mem = devm_ioremap_resource(dev, res); + apc->mmr_mem = devm_platform_ioremap_resource_byname(pdev, + "ar2315-pci-ctrl"); if (IS_ERR(apc->mmr_mem)) return PTR_ERR(apc->mmr_mem); diff --git a/arch/mips/pci/pci-ar71xx.c b/arch/mips/pci/pci-ar71xx.c index a9f8e7c881bd..118760b3fa82 100644 --- a/arch/mips/pci/pci-ar71xx.c +++ b/arch/mips/pci/pci-ar71xx.c @@ -336,8 +336,8 @@ static int ar71xx_pci_probe(struct platform_device *pdev) if (!apc) return -ENOMEM; - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "cfg_base"); - apc->cfg_base = devm_ioremap_resource(&pdev->dev, res); + apc->cfg_base = devm_platform_ioremap_resource_byname(pdev, + "cfg_base"); if (IS_ERR(apc->cfg_base)) return PTR_ERR(apc->cfg_base); diff --git a/arch/mips/pci/pci-ar724x.c b/arch/mips/pci/pci-ar724x.c index 869d5c9a2f8d..807558b251ef 100644 --- a/arch/mips/pci/pci-ar724x.c +++ b/arch/mips/pci/pci-ar724x.c @@ -372,18 +372,15 @@ static int ar724x_pci_probe(struct platform_device *pdev) if (!apc) return -ENOMEM; - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "ctrl_base"); - apc->ctrl_base = devm_ioremap_resource(&pdev->dev, res); + apc->ctrl_base = devm_platform_ioremap_resource_byname(pdev, "ctrl_base"); if (IS_ERR(apc->ctrl_base)) return PTR_ERR(apc->ctrl_base); - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "cfg_base"); - apc->devcfg_base = devm_ioremap_resource(&pdev->dev, res); + apc->devcfg_base = devm_platform_ioremap_resource_byname(pdev, "cfg_base"); if (IS_ERR(apc->devcfg_base)) return PTR_ERR(apc->devcfg_base); - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "crp_base"); - apc->crp_base = devm_ioremap_resource(&pdev->dev, res); + apc->crp_base = devm_platform_ioremap_resource_byname(pdev, "crp_base"); if (IS_ERR(apc->crp_base)) return PTR_ERR(apc->crp_base); From 0ee69c589ec8659560910815f32c13af8587a779 Mon Sep 17 00:00:00 2001 From: Qinglang Miao Date: Wed, 16 Sep 2020 14:21:27 +0800 Subject: [PATCH 236/645] MIPS: OCTEON: use devm_platform_ioremap_resource Note that error handling on the result of a call to platform_get_resource() is unneeded when the value is passed to devm_ioremap_resource(), so remove it. Then use the helper function that wraps the calls to platform_get_resource() and devm_ioremap_resource() together. Signed-off-by: Qinglang Miao Signed-off-by: Thomas Bogendoerfer --- arch/mips/cavium-octeon/octeon-usb.c | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) diff --git a/arch/mips/cavium-octeon/octeon-usb.c b/arch/mips/cavium-octeon/octeon-usb.c index 950e6c6e8629..97f6dc31e1b4 100644 --- a/arch/mips/cavium-octeon/octeon-usb.c +++ b/arch/mips/cavium-octeon/octeon-usb.c @@ -498,7 +498,6 @@ static int __init dwc3_octeon_device_init(void) const char compat_node_name[] = "cavium,octeon-7130-usb-uctl"; struct platform_device *pdev; struct device_node *node; - struct resource *res; void __iomem *base; /* @@ -516,20 +515,13 @@ static int __init dwc3_octeon_device_init(void) if (!pdev) return -ENODEV; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (res == NULL) { - put_device(&pdev->dev); - dev_err(&pdev->dev, "No memory resources\n"); - return -ENXIO; - } - /* * The code below maps in the registers necessary for * setting up the clocks and reseting PHYs. We must * release the resources so the dwc3 subsystem doesn't * know the difference. */ - base = devm_ioremap_resource(&pdev->dev, res); + base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(base)) { put_device(&pdev->dev); return PTR_ERR(base); From 338a93a497e48cb2366314ac9e545fadbf128bb4 Mon Sep 17 00:00:00 2001 From: Youling Tang Date: Sat, 12 Sep 2020 09:54:39 +0800 Subject: [PATCH 237/645] MIPS: netlogic: Remove unused code Remove some unused code. Signed-off-by: Youling Tang Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/netlogic/psb-bootinfo.h | 15 --------------- 1 file changed, 15 deletions(-) diff --git a/arch/mips/include/asm/netlogic/psb-bootinfo.h b/arch/mips/include/asm/netlogic/psb-bootinfo.h index 6878307f0ee6..272544b55ceb 100644 --- a/arch/mips/include/asm/netlogic/psb-bootinfo.h +++ b/arch/mips/include/asm/netlogic/psb-bootinfo.h @@ -77,21 +77,6 @@ struct psb_info { uint64_t avail_mem_map; }; -enum { - NETLOGIC_IO_SPACE = 0x10, - PCIX_IO_SPACE, - PCIX_CFG_SPACE, - PCIX_MEMORY_SPACE, - HT_IO_SPACE, - HT_CFG_SPACE, - HT_MEMORY_SPACE, - SRAM_SPACE, - FLASH_CONTROLLER_SPACE -}; - -#define NLM_MAX_ARGS 64 -#define NLM_MAX_ENVS 32 - /* This is what netlboot passes and linux boot_mem_map is subtly different */ #define NLM_BOOT_MEM_MAP_MAX 32 struct nlm_boot_mem_map { From 055444c2663ba9139dec0340bf7a6b29a8a5f7f6 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Fri, 11 Sep 2020 18:26:17 +0800 Subject: [PATCH 238/645] MIPS: Loongson64: Increase NR_IRQS to 320 Modernized Loongson64 uses a hierarchical organization for interrupt controllers (INTCs), all INTC nodes (not only leaf nodes) need some IRQ numbers. This means 280 (i.e., NR_IRQS_LEGACY + NR_MIPS_CPU_IRQS + 256) is not enough to represent all interrupts, so let's increase NR_IRQS to 320 (NR_IRQS_LEGACY + NR_MIPS_CPU_IRQS + NR_MAX_CHAINED_IRQS + 256). Signed-off-by: Huacai Chen Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/mach-loongson64/irq.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/mips/include/asm/mach-loongson64/irq.h b/arch/mips/include/asm/mach-loongson64/irq.h index f5e362f79701..28b1d942a724 100644 --- a/arch/mips/include/asm/mach-loongson64/irq.h +++ b/arch/mips/include/asm/mach-loongson64/irq.h @@ -7,7 +7,8 @@ /* cpu core interrupt numbers */ #define NR_IRQS_LEGACY 16 #define NR_MIPS_CPU_IRQS 8 -#define NR_IRQS (NR_IRQS_LEGACY + NR_MIPS_CPU_IRQS + 256) +#define NR_MAX_CHAINED_IRQS 40 /* Chained IRQs means those not directly used by devices */ +#define NR_IRQS (NR_IRQS_LEGACY + NR_MIPS_CPU_IRQS + NR_MAX_CHAINED_IRQS + 256) #define MIPS_CPU_IRQ_BASE NR_IRQS_LEGACY From 7487abbe85afd02c35c283315cefc5e19c28d40f Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Sun, 6 Sep 2020 21:29:21 +0200 Subject: [PATCH 239/645] MIPS: configs: lb60: Fix defconfig not selecting correct board Since INGENIC_GENERIC_BOARD was introduced, the JZ4740_QI_LB60 option is no longer the default, so the symbol has to be selected by the defconfig, otherwise the kernel built will be for a generic Ingenic board and won't have the Device Tree blob built-in. Cc: stable@vger.kernel.org # v5.7 Fixes: 62249209a772 ("MIPS: ingenic: Default to a generic board") Signed-off-by: Paul Cercueil Signed-off-by: Thomas Bogendoerfer --- arch/mips/configs/qi_lb60_defconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/mips/configs/qi_lb60_defconfig b/arch/mips/configs/qi_lb60_defconfig index 81bfbee72b0c..9c2c183085d1 100644 --- a/arch/mips/configs/qi_lb60_defconfig +++ b/arch/mips/configs/qi_lb60_defconfig @@ -8,6 +8,7 @@ CONFIG_EMBEDDED=y # CONFIG_COMPAT_BRK is not set CONFIG_SLAB=y CONFIG_MACH_INGENIC=y +CONFIG_JZ4740_QI_LB60=y CONFIG_HZ_100=y # CONFIG_SECCOMP is not set CONFIG_MODULES=y From 95b1f6db67aea9135b018497f7ed4446a060cba2 Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Sun, 6 Sep 2020 21:29:22 +0200 Subject: [PATCH 240/645] MIPS: cpu-probe: Set Ingenic's writecombine to _CACHE_CACHABLE_WA Previously, in cpu_probe_ingenic(), c->writecombine was set to _CACHE_UNCACHED_ACCELERATED, but this macro was defined differently when CONFIG_MACH_INGENIC was set. This made it impossible to support multiple CPUs. Address this issue by setting c->writecombine to _CACHE_CACHABLE_WA directly and removing the dependency on CONFIG_MACH_INGENIC. Signed-off-by: Paul Cercueil Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/pgtable-bits.h | 5 ----- arch/mips/kernel/cpu-probe.c | 3 ++- 2 files changed, 2 insertions(+), 6 deletions(-) diff --git a/arch/mips/include/asm/pgtable-bits.h b/arch/mips/include/asm/pgtable-bits.h index e26dc41a8a68..2362842ee2b5 100644 --- a/arch/mips/include/asm/pgtable-bits.h +++ b/arch/mips/include/asm/pgtable-bits.h @@ -249,11 +249,6 @@ static inline uint64_t pte_to_entrylo(unsigned long pte_val) #define _CACHE_CACHABLE_NONCOHERENT (5<<_CACHE_SHIFT) -#elif defined(CONFIG_MACH_INGENIC) - -/* Ingenic uses the WA bit to achieve write-combine memory writes */ -#define _CACHE_UNCACHED_ACCELERATED (1<<_CACHE_SHIFT) - #endif #ifndef _CACHE_CACHABLE_NO_WA diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index e2955f1f6316..a18f3611fa5e 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -2169,8 +2169,9 @@ static inline void cpu_probe_ingenic(struct cpuinfo_mips *c, unsigned int cpu) /* XBurst®1 with MXU2.0 SIMD ISA */ case PRID_IMP_XBURST_REV2: + /* Ingenic uses the WA bit to achieve write-combine memory writes */ + c->writecombine = _CACHE_CACHABLE_WA; c->cputype = CPU_XBURST; - c->writecombine = _CACHE_UNCACHED_ACCELERATED; __cpu_name[cpu] = "Ingenic XBurst"; break; From 5ef415107dfd42a334d62a9b7be9754817df92ed Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Sun, 6 Sep 2020 21:29:23 +0200 Subject: [PATCH 241/645] MIPS: cpu-probe: Mark XBurst CPU as having vtagged caches XBurst CPUs present in Ingenic SoCs have virtually tagged caches, according to the header. Add that information to cpu_probe_ingenic(). Signed-off-by: Paul Cercueil Signed-off-by: Thomas Bogendoerfer --- arch/mips/kernel/cpu-probe.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index a18f3611fa5e..a07e66a6e063 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -2125,6 +2125,9 @@ static inline void cpu_probe_ingenic(struct cpuinfo_mips *c, unsigned int cpu) c->options &= ~MIPS_CPU_COUNTER; BUG_ON(!__builtin_constant_p(cpu_has_counter) || cpu_has_counter); + /* XBurst has virtually tagged icache */ + c->icache.flags |= MIPS_CACHE_VTAG; + switch (c->processor_id & PRID_IMP_MASK) { /* XBurst®1 with MXU1.0/MXU1.1 SIMD ISA */ From 5f5ed0ebcf84c7479c93a28c5c0e1b0b6926883b Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Sun, 6 Sep 2020 21:29:24 +0200 Subject: [PATCH 242/645] MIPS: cpu-probe: ingenic: Fix broken BUG_ON The previous code was doing: BUG_ON(!__builtin_constant_p(cpu_has_counter) || cpu_has_counter); This only worked as the "cpu_has_counter" macro was overridden in . The default "cpu_has_counter" macro is non-constant, which triggered the BUG_ON() independently of the value returned by the macro. What we want to check here, is that *if* the macro was overridden to a compile-time constant, then must be defined to zero, otherwise it's a bug. So the correct check is: BUG_ON(__builtin_constant_p(cpu_has_counter) && cpu_has_counter); Signed-off-by: Paul Cercueil Signed-off-by: Thomas Bogendoerfer --- arch/mips/kernel/cpu-probe.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index a07e66a6e063..6be23f205e74 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -2123,7 +2123,7 @@ static inline void cpu_probe_ingenic(struct cpuinfo_mips *c, unsigned int cpu) /* XBurst does not implement the CP0 counter. */ c->options &= ~MIPS_CPU_COUNTER; - BUG_ON(!__builtin_constant_p(cpu_has_counter) || cpu_has_counter); + BUG_ON(__builtin_constant_p(cpu_has_counter) && cpu_has_counter); /* XBurst has virtually tagged icache */ c->icache.flags |= MIPS_CACHE_VTAG; From c434b9f80b0923e6460031b0fd964f8b0bf3c6a6 Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Sun, 6 Sep 2020 21:29:25 +0200 Subject: [PATCH 243/645] MIPS: Kconfig: add MIPS_GENERIC_KERNEL symbol The MIPS_GENERIC symbol now won't select any other configuration option. The MIPS_GENERIC_KERNEL will select all the options that the previous MIPS_GENERIC option did select, and will select MIPS_GENERIC as well. The whole point of this, is that it now becomes possible to compile a kernel for a SoC supported by the arch/mips/generic/ code, without making that kernel generic itself. Signed-off-by: Paul Cercueil Signed-off-by: Thomas Bogendoerfer --- arch/mips/Kconfig | 8 ++++++-- arch/mips/generic/Kconfig | 2 +- 2 files changed, 7 insertions(+), 3 deletions(-) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 632fe8fe68c4..d96618c91103 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -93,14 +93,18 @@ config MIPS config MIPS_FIXUP_BIGPHYS_ADDR bool +config MIPS_GENERIC + bool + menu "Machine selection" choice prompt "System type" - default MIPS_GENERIC + default MIPS_GENERIC_KERNEL -config MIPS_GENERIC +config MIPS_GENERIC_KERNEL bool "Generic board-agnostic MIPS kernel" + select MIPS_GENERIC select BOOT_RAW select BUILTIN_DTB select CEVT_R4K diff --git a/arch/mips/generic/Kconfig b/arch/mips/generic/Kconfig index fd6019802657..5216c850b7e2 100644 --- a/arch/mips/generic/Kconfig +++ b/arch/mips/generic/Kconfig @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -if MIPS_GENERIC +if MIPS_GENERIC_KERNEL config LEGACY_BOARDS bool From 8405419942f2f012dc23b5c8817eded2d591b033 Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Sun, 6 Sep 2020 21:29:26 +0200 Subject: [PATCH 244/645] MIPS: generic: Allow boards to set system type Check for the system_type variable in the get_system_type() function. If non-NULL, return it as the system type. Signed-off-by: Paul Cercueil Signed-off-by: Thomas Bogendoerfer --- arch/mips/generic/proc.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/mips/generic/proc.c b/arch/mips/generic/proc.c index 4c992809cc3f..cce2fde219a3 100644 --- a/arch/mips/generic/proc.c +++ b/arch/mips/generic/proc.c @@ -8,11 +8,16 @@ #include +char *system_type; + const char *get_system_type(void) { const char *str; int err; + if (system_type) + return system_type; + err = of_property_read_string(of_root, "model", &str); if (!err) return str; From 13a0ea28e8c698cc0d600fdeed8da3e4d478b97e Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Sun, 6 Sep 2020 21:29:27 +0200 Subject: [PATCH 245/645] MIPS: generic: Init command line with fw_init_cmdline() The function bootcmdline_init() in arch/mips/kernel/setup.c will populate the boot_command_line string using the parameters hardcoded in the kernel, and those provided in the devicetree file. Then, it would append the content of the arcs_cmdline variable, which is filled by the board's plat_mem_setup() function. The plat_mem_setup() function for the generic MIPS board would just copy the current boot_command_line to arcs_cmdline, which is nonsense for two reasons: - the result will be appended to the boot_command_line anyway, so all it does is duplicate every single parameter on the command line; - the code did not perform at all what it's supposed to, which is to retrieve the parameters passed by the bootloader. Fix this by calling fw_init_cmdline() in plat_mem_setup(), which will properly initialize arcs_cmdline to the parameters passed by the bootloader. Signed-off-by: Paul Cercueil Signed-off-by: Thomas Bogendoerfer --- arch/mips/generic/init.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/generic/init.c b/arch/mips/generic/init.c index 805d0135a9f4..029f47ea390c 100644 --- a/arch/mips/generic/init.c +++ b/arch/mips/generic/init.c @@ -106,7 +106,7 @@ void __init plat_mem_setup(void) if (mach && mach->fixup_fdt) fdt = mach->fixup_fdt(fdt, mach_match_data); - strlcpy(arcs_cmdline, boot_command_line, COMMAND_LINE_SIZE); + fw_init_cmdline(); __dt_setup_arch((void *)fdt); } From 323690d23be14fa4b7be8bd2961810df6fe42138 Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Sun, 6 Sep 2020 21:29:28 +0200 Subject: [PATCH 246/645] MIPS: generic: Support booting with built-in or appended DTB The plat_get_fdt() checked that the kernel was booted using UHI before reading the 'fw_passed_dtb' variable. However, this variable is also set when the DT has been appended, or when it has been built into the kernel. Support these usecases by removing the UHI check. Signed-off-by: Paul Cercueil Signed-off-by: Thomas Bogendoerfer --- arch/mips/generic/init.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/arch/mips/generic/init.c b/arch/mips/generic/init.c index 029f47ea390c..66a19337d2ab 100644 --- a/arch/mips/generic/init.c +++ b/arch/mips/generic/init.c @@ -39,12 +39,11 @@ void __init *plat_get_fdt(void) /* Already set up */ return (void *)fdt; - if ((fw_arg0 == -2) && !fdt_check_header((void *)fw_passed_dtb)) { + if (fw_passed_dtb && !fdt_check_header((void *)fw_passed_dtb)) { /* - * We booted using the UHI boot protocol, so we have been - * provided with the appropriate device tree for the board. - * Make use of it & search for any machine struct based upon - * the root compatible string. + * We have been provided with the appropriate device tree for + * the board. Make use of it & search for any machine struct + * based upon the root compatible string. */ fdt = (void *)fw_passed_dtb; From c3e2ee657418f4f2bff1269c0550f8135ed0c927 Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Sun, 6 Sep 2020 21:29:29 +0200 Subject: [PATCH 247/645] MIPS: generic: Add support for zboot There is no reason we can't create compressed kernels here, so select the option SYS_SUPPORTS_ZBOOT. Signed-off-by: Paul Cercueil Signed-off-by: Thomas Bogendoerfer --- arch/mips/Kconfig | 1 + arch/mips/generic/Platform | 1 + 2 files changed, 2 insertions(+) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index d96618c91103..15430599a6ac 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -141,6 +141,7 @@ config MIPS_GENERIC_KERNEL select SYS_SUPPORTS_MULTITHREADING select SYS_SUPPORTS_RELOCATABLE select SYS_SUPPORTS_SMARTMIPS + select SYS_SUPPORTS_ZBOOT select UHI_BOOT select USB_EHCI_BIG_ENDIAN_DESC if CPU_BIG_ENDIAN select USB_EHCI_BIG_ENDIAN_MMIO if CPU_BIG_ENDIAN diff --git a/arch/mips/generic/Platform b/arch/mips/generic/Platform index 53c33cb72974..4cefecf7d14b 100644 --- a/arch/mips/generic/Platform +++ b/arch/mips/generic/Platform @@ -10,6 +10,7 @@ cflags-$(CONFIG_MIPS_GENERIC) += -I$(srctree)/arch/mips/include/asm/mach-generic load-$(CONFIG_MIPS_GENERIC) += 0xffffffff80100000 +zload-$(CONFIG_MIPS_GENERIC) += 0xffffffff81000000 all-$(CONFIG_MIPS_GENERIC) := vmlinux.gz.itb its-y := vmlinux.its.S From 02bd530f888c6d6ba4995c3afcd10f87c136f173 Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Sun, 6 Sep 2020 21:29:30 +0200 Subject: [PATCH 248/645] MIPS: generic: Increase NR_IRQS to 256 128 IRQs is not enough to support Ingenic SoCs. Signed-off-by: Paul Cercueil Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/mach-generic/irq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/include/asm/mach-generic/irq.h b/arch/mips/include/asm/mach-generic/irq.h index 72ac2c202c55..079889ced4f3 100644 --- a/arch/mips/include/asm/mach-generic/irq.h +++ b/arch/mips/include/asm/mach-generic/irq.h @@ -9,7 +9,7 @@ #define __ASM_MACH_GENERIC_IRQ_H #ifndef NR_IRQS -#define NR_IRQS 128 +#define NR_IRQS 256 #endif #ifdef CONFIG_I8259 From f0f4a753079c636d5d43a102edbde0dad1e7de51 Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Sun, 6 Sep 2020 21:29:31 +0200 Subject: [PATCH 249/645] MIPS: generic: Add support for Ingenic SoCs Add support for Ingenic SoCs in arch/mips/generic/. The Kconfig changes are here to ensure that it is possible to compile either a generic kernel that supports Ingenic SoCs, or a Ingenic-only kernel, both using the same code base, to avoid duplicated code. Signed-off-by: Paul Cercueil Signed-off-by: Thomas Bogendoerfer --- arch/mips/Kbuild.platforms | 1 - arch/mips/Kconfig | 32 +++++---- arch/mips/generic/Kconfig | 6 ++ arch/mips/generic/Makefile | 1 + arch/mips/generic/Platform | 3 + arch/mips/generic/board-ingenic.c | 108 ++++++++++++++++++++++++++++++ arch/mips/jz4740/Kconfig | 18 +++-- 7 files changed, 150 insertions(+), 19 deletions(-) create mode 100644 arch/mips/generic/board-ingenic.c diff --git a/arch/mips/Kbuild.platforms b/arch/mips/Kbuild.platforms index af336a274a7a..5483e38b5dc7 100644 --- a/arch/mips/Kbuild.platforms +++ b/arch/mips/Kbuild.platforms @@ -13,7 +13,6 @@ platform-$(CONFIG_MIPS_COBALT) += cobalt/ platform-$(CONFIG_MACH_DECSTATION) += dec/ platform-$(CONFIG_MIPS_GENERIC) += generic/ platform-$(CONFIG_MACH_JAZZ) += jazz/ -platform-$(CONFIG_MACH_INGENIC) += jz4740/ platform-$(CONFIG_LANTIQ) += lantiq/ platform-$(CONFIG_MACH_LOONGSON2EF) += loongson2ef/ platform-$(CONFIG_MACH_LOONGSON32) += loongson32/ diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 15430599a6ac..74604b867e26 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -96,6 +96,23 @@ config MIPS_FIXUP_BIGPHYS_ADDR config MIPS_GENERIC bool +config MACH_INGENIC + bool + select SYS_SUPPORTS_32BIT_KERNEL + select SYS_SUPPORTS_LITTLE_ENDIAN + select SYS_SUPPORTS_ZBOOT + select CPU_SUPPORTS_HUGEPAGES + select DMA_NONCOHERENT + select IRQ_MIPS_CPU + select PINCTRL + select GPIOLIB + select COMMON_CLK + select GENERIC_IRQ_CHIP + select BUILTIN_DTB if MIPS_NO_APPENDED_DTB + select USE_OF + select CPU_SUPPORTS_CPUFREQ + select MIPS_EXTERNAL_TIMER + menu "Machine selection" choice @@ -394,20 +411,11 @@ config MACH_JAZZ Members include the Acer PICA, MIPS Magnum 4000, MIPS Millennium and Olivetti M700-10 workstations. -config MACH_INGENIC +config MACH_INGENIC_SOC bool "Ingenic SoC based machines" - select SYS_SUPPORTS_32BIT_KERNEL - select SYS_SUPPORTS_LITTLE_ENDIAN + select MIPS_GENERIC + select MACH_INGENIC select SYS_SUPPORTS_ZBOOT_UART16550 - select CPU_SUPPORTS_HUGEPAGES - select DMA_NONCOHERENT - select IRQ_MIPS_CPU - select PINCTRL - select GPIOLIB - select COMMON_CLK - select GENERIC_IRQ_CHIP - select BUILTIN_DTB if MIPS_NO_APPENDED_DTB - select USE_OF config LANTIQ bool "Lantiq based platforms" diff --git a/arch/mips/generic/Kconfig b/arch/mips/generic/Kconfig index 5216c850b7e2..55d9aed7ced9 100644 --- a/arch/mips/generic/Kconfig +++ b/arch/mips/generic/Kconfig @@ -73,6 +73,12 @@ config FIT_IMAGE_FDT_OCELOT from Microsemi in the FIT kernel image. This requires u-boot on the platform. +config BOARD_INGENIC + bool "Support boards based on Ingenic SoCs" + select MACH_INGENIC_GENERIC + help + Enable support for boards based on Ingenic SoCs. + config VIRT_BOARD_RANCHU bool "Support Ranchu platform for Android emulator" help diff --git a/arch/mips/generic/Makefile b/arch/mips/generic/Makefile index 2384a6b09e4c..e37a59bae0a6 100644 --- a/arch/mips/generic/Makefile +++ b/arch/mips/generic/Makefile @@ -11,4 +11,5 @@ obj-y += proc.o obj-$(CONFIG_YAMON_DT_SHIM) += yamon-dt.o obj-$(CONFIG_LEGACY_BOARD_SEAD3) += board-sead3.o obj-$(CONFIG_LEGACY_BOARD_OCELOT) += board-ocelot.o +obj-$(CONFIG_MACH_INGENIC) += board-ingenic.o obj-$(CONFIG_VIRT_BOARD_RANCHU) += board-ranchu.o diff --git a/arch/mips/generic/Platform b/arch/mips/generic/Platform index 4cefecf7d14b..7d511fc28a01 100644 --- a/arch/mips/generic/Platform +++ b/arch/mips/generic/Platform @@ -8,7 +8,10 @@ # option) any later version. # +# Note: order matters, keep the asm/mach-generic include last. +cflags-$(CONFIG_MACH_INGENIC_SOC) += -I$(srctree)/arch/mips/include/asm/mach-jz4740 cflags-$(CONFIG_MIPS_GENERIC) += -I$(srctree)/arch/mips/include/asm/mach-generic + load-$(CONFIG_MIPS_GENERIC) += 0xffffffff80100000 zload-$(CONFIG_MIPS_GENERIC) += 0xffffffff81000000 all-$(CONFIG_MIPS_GENERIC) := vmlinux.gz.itb diff --git a/arch/mips/generic/board-ingenic.c b/arch/mips/generic/board-ingenic.c new file mode 100644 index 000000000000..0d7de8f9713d --- /dev/null +++ b/arch/mips/generic/board-ingenic.c @@ -0,0 +1,108 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Support for Ingenic SoCs + * + * Copyright (C) 2009-2010, Lars-Peter Clausen + * Copyright (C) 2011, Maarten ter Huurne + * Copyright (C) 2020 Paul Cercueil + */ + +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +static __init char *ingenic_get_system_type(unsigned long machtype) +{ + switch (machtype) { + case MACH_INGENIC_X1830: + return "X1830"; + case MACH_INGENIC_X1000: + return "X1000"; + case MACH_INGENIC_JZ4780: + return "JZ4780"; + case MACH_INGENIC_JZ4770: + return "JZ4770"; + case MACH_INGENIC_JZ4725B: + return "JZ4725B"; + default: + return "JZ4740"; + } +} + +static __init const void *ingenic_fixup_fdt(const void *fdt, const void *match_data) +{ + /* + * Old devicetree files for the qi,lb60 board did not have a /memory + * node. Hardcode the memory info here. + */ + if (!fdt_node_check_compatible(fdt, 0, "qi,lb60") && + fdt_path_offset(fdt, "/memory") < 0) + early_init_dt_add_memory_arch(0, SZ_32M); + + mips_machtype = (unsigned long)match_data; + system_type = ingenic_get_system_type(mips_machtype); + + return fdt; +} + +static const struct of_device_id ingenic_of_match[] __initconst = { + { .compatible = "ingenic,jz4740", .data = (void *)MACH_INGENIC_JZ4740 }, + { .compatible = "ingenic,jz4725b", .data = (void *)MACH_INGENIC_JZ4725B }, + { .compatible = "ingenic,jz4770", .data = (void *)MACH_INGENIC_JZ4770 }, + { .compatible = "ingenic,jz4780", .data = (void *)MACH_INGENIC_JZ4780 }, + { .compatible = "ingenic,x1000", .data = (void *)MACH_INGENIC_X1000 }, + { .compatible = "ingenic,x1830", .data = (void *)MACH_INGENIC_X1830 }, + {} +}; + +MIPS_MACHINE(ingenic) = { + .matches = ingenic_of_match, + .fixup_fdt = ingenic_fixup_fdt, +}; + +static void ingenic_wait_instr(void) +{ + __asm__(".set push;\n" + ".set mips3;\n" + "wait;\n" + ".set pop;\n" + ); +} + +static void ingenic_halt(void) +{ + for (;;) + ingenic_wait_instr(); +} + +static int __maybe_unused ingenic_pm_enter(suspend_state_t state) +{ + ingenic_wait_instr(); + + return 0; +} + +static const struct platform_suspend_ops ingenic_pm_ops __maybe_unused = { + .valid = suspend_valid_only_mem, + .enter = ingenic_pm_enter, +}; + +static int __init ingenic_pm_init(void) +{ + if (boot_cpu_type() == CPU_XBURST) { + if (IS_ENABLED(CONFIG_PM_SLEEP)) + suspend_set_ops(&ingenic_pm_ops); + _machine_halt = ingenic_halt; + } + + return 0; + +} +late_initcall(ingenic_pm_init); diff --git a/arch/mips/jz4740/Kconfig b/arch/mips/jz4740/Kconfig index c2a6fbf8e411..3238e16febd5 100644 --- a/arch/mips/jz4740/Kconfig +++ b/arch/mips/jz4740/Kconfig @@ -1,16 +1,22 @@ # SPDX-License-Identifier: GPL-2.0 -choice - prompt "Machine type" - depends on MACH_INGENIC - default INGENIC_GENERIC_BOARD -config INGENIC_GENERIC_BOARD - bool "Generic board" +config MACH_INGENIC_GENERIC + bool + select MACH_INGENIC select MACH_JZ4740 select MACH_JZ4770 select MACH_JZ4780 select MACH_X1000 +choice + prompt "Machine type" + depends on MACH_INGENIC_SOC + default INGENIC_GENERIC_BOARD + +config INGENIC_GENERIC_BOARD + bool "Generic board" + select MACH_INGENIC_GENERIC + config JZ4740_QI_LB60 bool "Qi Hardware Ben NanoNote" select MACH_JZ4740 From b4a30e9c7480603a02d8ad788975428b9c6dc876 Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Sun, 6 Sep 2020 21:29:32 +0200 Subject: [PATCH 250/645] MIPS: jz4740: Drop all obsolete files Support for Ingenic SoCs is now provided by the arch/mips/generic/ code, so all files in the arch/mips/jz4740/ folder can dropped, except for the Kconfig, and the cpu-feature-overrides.h header file. Signed-off-by: Paul Cercueil Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/mach-jz4740/irq.h | 13 --- arch/mips/jz4740/Makefile | 9 -- arch/mips/jz4740/Platform | 3 - arch/mips/jz4740/setup.c | 145 ------------------------ 4 files changed, 170 deletions(-) delete mode 100644 arch/mips/include/asm/mach-jz4740/irq.h delete mode 100644 arch/mips/jz4740/Makefile delete mode 100644 arch/mips/jz4740/Platform delete mode 100644 arch/mips/jz4740/setup.c diff --git a/arch/mips/include/asm/mach-jz4740/irq.h b/arch/mips/include/asm/mach-jz4740/irq.h deleted file mode 100644 index 27c543bd340f..000000000000 --- a/arch/mips/include/asm/mach-jz4740/irq.h +++ /dev/null @@ -1,13 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Copyright (C) 2009-2010, Lars-Peter Clausen - * JZ4740 IRQ definitions - */ - -#ifndef __ASM_MACH_JZ4740_IRQ_H__ -#define __ASM_MACH_JZ4740_IRQ_H__ - -#define MIPS_CPU_IRQ_BASE 0 -#define NR_IRQS 256 - -#endif diff --git a/arch/mips/jz4740/Makefile b/arch/mips/jz4740/Makefile deleted file mode 100644 index f96c0f5eca44..000000000000 --- a/arch/mips/jz4740/Makefile +++ /dev/null @@ -1,9 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -# -# Makefile for the Ingenic JZ4740. -# - -# Object file lists. -obj-y += setup.o - -CFLAGS_setup.o = -I$(src)/../../../scripts/dtc/libfdt diff --git a/arch/mips/jz4740/Platform b/arch/mips/jz4740/Platform deleted file mode 100644 index bd35d0621b13..000000000000 --- a/arch/mips/jz4740/Platform +++ /dev/null @@ -1,3 +0,0 @@ -cflags-$(CONFIG_MACH_INGENIC) += -I$(srctree)/arch/mips/include/asm/mach-jz4740 -load-$(CONFIG_MACH_INGENIC) += 0xffffffff80010000 -zload-$(CONFIG_MACH_INGENIC) += 0xffffffff81000000 diff --git a/arch/mips/jz4740/setup.c b/arch/mips/jz4740/setup.c deleted file mode 100644 index 51d906325ce6..000000000000 --- a/arch/mips/jz4740/setup.c +++ /dev/null @@ -1,145 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Copyright (C) 2009-2010, Lars-Peter Clausen - * Copyright (C) 2011, Maarten ter Huurne - * JZ4740 setup code - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include - -static unsigned long __init get_board_mach_type(const void *fdt) -{ - if (!fdt_node_check_compatible(fdt, 0, "ingenic,x2000")) - return MACH_INGENIC_X2000; - if (!fdt_node_check_compatible(fdt, 0, "ingenic,x1830")) - return MACH_INGENIC_X1830; - if (!fdt_node_check_compatible(fdt, 0, "ingenic,x1000")) - return MACH_INGENIC_X1000; - if (!fdt_node_check_compatible(fdt, 0, "ingenic,jz4780")) - return MACH_INGENIC_JZ4780; - if (!fdt_node_check_compatible(fdt, 0, "ingenic,jz4770")) - return MACH_INGENIC_JZ4770; - if (!fdt_node_check_compatible(fdt, 0, "ingenic,jz4725b")) - return MACH_INGENIC_JZ4725B; - - return MACH_INGENIC_JZ4740; -} - -void __init plat_mem_setup(void) -{ - void *dtb = (void *)fw_passed_dtb; - - __dt_setup_arch(dtb); - - /* - * Old devicetree files for the qi,lb60 board did not have a /memory - * node. Hardcode the memory info here. - */ - if (!fdt_node_check_compatible(dtb, 0, "qi,lb60") && - fdt_path_offset(dtb, "/memory") < 0) - early_init_dt_add_memory_arch(0, SZ_32M); - - mips_machtype = get_board_mach_type(dtb); -} - -void __init device_tree_init(void) -{ - if (!initial_boot_params) - return; - - unflatten_and_copy_device_tree(); -} - -const char *get_system_type(void) -{ - switch (mips_machtype) { - case MACH_INGENIC_X2000: - return "X2000"; - case MACH_INGENIC_X1830: - return "X1830"; - case MACH_INGENIC_X1000: - return "X1000"; - case MACH_INGENIC_JZ4780: - return "JZ4780"; - case MACH_INGENIC_JZ4770: - return "JZ4770"; - case MACH_INGENIC_JZ4725B: - return "JZ4725B"; - default: - return "JZ4740"; - } -} - -void __init arch_init_irq(void) -{ - irqchip_init(); -} - -void __init plat_time_init(void) -{ - of_clk_init(NULL); - timer_probe(); -} - -void __init prom_init(void) -{ - fw_init_cmdline(); -} - -void __init prom_free_prom_memory(void) -{ -} - -static void jz4740_wait_instr(void) -{ - __asm__(".set push;\n" - ".set mips3;\n" - "wait;\n" - ".set pop;\n" - ); -} - -static void jz4740_halt(void) -{ - for (;;) - jz4740_wait_instr(); -} - -static int __maybe_unused jz4740_pm_enter(suspend_state_t state) -{ - jz4740_wait_instr(); - - return 0; -} - -static const struct platform_suspend_ops jz4740_pm_ops __maybe_unused = { - .valid = suspend_valid_only_mem, - .enter = jz4740_pm_enter, -}; - -static int __init jz4740_pm_init(void) -{ - if (IS_ENABLED(CONFIG_PM_SLEEP)) - suspend_set_ops(&jz4740_pm_ops); - _machine_halt = jz4740_halt; - - return 0; - -} -late_initcall(jz4740_pm_init); From a103e9b951f9094792fd0dab0a0dcd1b3408825a Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Sun, 6 Sep 2020 21:29:33 +0200 Subject: [PATCH 251/645] MIPS: jz4740: Rename jz4740 folders to ingenic Now that all the jz4740 platform code has been removed, and we're left with only a Kconfig and the cpu-feature-overrides.h file, finalize the cleanup process by renaming the jz4740 and include/mach-jz4740 folders to ingenic and include/mach-ingenic. Signed-off-by: Paul Cercueil Signed-off-by: Thomas Bogendoerfer --- arch/mips/Kconfig | 2 +- arch/mips/generic/Platform | 2 +- .../asm/{mach-jz4740 => mach-ingenic}/cpu-feature-overrides.h | 0 arch/mips/{jz4740 => ingenic}/Kconfig | 0 4 files changed, 2 insertions(+), 2 deletions(-) rename arch/mips/include/asm/{mach-jz4740 => mach-ingenic}/cpu-feature-overrides.h (100%) rename arch/mips/{jz4740 => ingenic}/Kconfig (100%) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 74604b867e26..c08c98d654b1 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -1034,8 +1034,8 @@ source "arch/mips/bcm47xx/Kconfig" source "arch/mips/bcm63xx/Kconfig" source "arch/mips/bmips/Kconfig" source "arch/mips/generic/Kconfig" +source "arch/mips/ingenic/Kconfig" source "arch/mips/jazz/Kconfig" -source "arch/mips/jz4740/Kconfig" source "arch/mips/lantiq/Kconfig" source "arch/mips/pic32/Kconfig" source "arch/mips/pistachio/Kconfig" diff --git a/arch/mips/generic/Platform b/arch/mips/generic/Platform index 7d511fc28a01..f8ef2f9d107e 100644 --- a/arch/mips/generic/Platform +++ b/arch/mips/generic/Platform @@ -9,7 +9,7 @@ # # Note: order matters, keep the asm/mach-generic include last. -cflags-$(CONFIG_MACH_INGENIC_SOC) += -I$(srctree)/arch/mips/include/asm/mach-jz4740 +cflags-$(CONFIG_MACH_INGENIC_SOC) += -I$(srctree)/arch/mips/include/asm/mach-ingenic cflags-$(CONFIG_MIPS_GENERIC) += -I$(srctree)/arch/mips/include/asm/mach-generic load-$(CONFIG_MIPS_GENERIC) += 0xffffffff80100000 diff --git a/arch/mips/include/asm/mach-jz4740/cpu-feature-overrides.h b/arch/mips/include/asm/mach-ingenic/cpu-feature-overrides.h similarity index 100% rename from arch/mips/include/asm/mach-jz4740/cpu-feature-overrides.h rename to arch/mips/include/asm/mach-ingenic/cpu-feature-overrides.h diff --git a/arch/mips/jz4740/Kconfig b/arch/mips/ingenic/Kconfig similarity index 100% rename from arch/mips/jz4740/Kconfig rename to arch/mips/ingenic/Kconfig From 8446fd61b5e3b64cc7800f3c9fb625fdd4012b6d Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Sun, 6 Sep 2020 21:29:34 +0200 Subject: [PATCH 252/645] MIPS: configs: Regenerate configs of Ingenic boards For each board the MACH_INGENIC_SOC option was selected instead of MACH_INGENIC. Nothing else was changed in the menuconfig. Signed-off-by: Paul Cercueil Signed-off-by: Thomas Bogendoerfer --- arch/mips/configs/ci20_defconfig | 4 ++-- arch/mips/configs/cu1000-neo_defconfig | 15 ++------------- arch/mips/configs/cu1830-neo_defconfig | 15 ++------------- arch/mips/configs/gcw0_defconfig | 2 +- arch/mips/configs/qi_lb60_defconfig | 6 ++---- arch/mips/configs/rs90_defconfig | 4 ++-- 6 files changed, 11 insertions(+), 35 deletions(-) diff --git a/arch/mips/configs/ci20_defconfig b/arch/mips/configs/ci20_defconfig index 0a46199fdc3f..052c5ad0f2b1 100644 --- a/arch/mips/configs/ci20_defconfig +++ b/arch/mips/configs/ci20_defconfig @@ -22,7 +22,7 @@ CONFIG_EMBEDDED=y # CONFIG_VM_EVENT_COUNTERS is not set # CONFIG_COMPAT_BRK is not set CONFIG_SLAB=y -CONFIG_MACH_INGENIC=y +CONFIG_MACH_INGENIC_SOC=y CONFIG_JZ4780_CI20=y CONFIG_HIGHMEM=y CONFIG_HZ_100=y @@ -42,7 +42,7 @@ CONFIG_IP_PNP_DHCP=y # CONFIG_IPV6 is not set # CONFIG_WIRELESS is not set CONFIG_DEVTMPFS=y -# CONFIG_FW_LOADER is not set +CONFIG_FW_LOADER=m # CONFIG_ALLOW_DEV_COREDUMP is not set CONFIG_MTD=y CONFIG_MTD_RAW_NAND=y diff --git a/arch/mips/configs/cu1000-neo_defconfig b/arch/mips/configs/cu1000-neo_defconfig index e924c817f73d..55d0690a3ffe 100644 --- a/arch/mips/configs/cu1000-neo_defconfig +++ b/arch/mips/configs/cu1000-neo_defconfig @@ -1,5 +1,3 @@ -CONFIG_LOCALVERSION_AUTO=y -CONFIG_KERNEL_GZIP=y CONFIG_SYSVIPC=y CONFIG_NO_HZ_IDLE=y CONFIG_HIGH_RES_TIMERS=y @@ -9,7 +7,6 @@ CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_CGROUPS=y CONFIG_MEMCG=y -CONFIG_MEMCG_KMEM=y CONFIG_CGROUP_SCHED=y CONFIG_CGROUP_FREEZER=y CONFIG_CGROUP_DEVICE=y @@ -22,7 +19,7 @@ CONFIG_EMBEDDED=y # CONFIG_VM_EVENT_COUNTERS is not set # CONFIG_COMPAT_BRK is not set CONFIG_SLAB=y -CONFIG_MACH_INGENIC=y +CONFIG_MACH_INGENIC_SOC=y CONFIG_X1000_CU1000_NEO=y CONFIG_HIGHMEM=y CONFIG_HZ_100=y @@ -31,7 +28,6 @@ CONFIG_HZ_100=y # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set # CONFIG_COMPACTION is not set CONFIG_CMA=y -CONFIG_CMA_AREAS=7 CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -40,19 +36,16 @@ CONFIG_CFG80211=y CONFIG_UEVENT_HELPER=y CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y -# CONFIG_FW_LOADER is not set # CONFIG_ALLOW_DEV_COREDUMP is not set CONFIG_NETDEVICES=y CONFIG_STMMAC_ETH=y CONFIG_SMSC_PHY=y CONFIG_BRCMFMAC=y -# CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set CONFIG_VT_HW_CONSOLE_BINDING=y CONFIG_LEGACY_PTY_COUNT=2 -CONFIG_SERIAL_EARLYCON=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=3 @@ -66,8 +59,6 @@ CONFIG_GPIO_SYSFS=y CONFIG_SENSORS_ADS7828=y CONFIG_WATCHDOG=y CONFIG_JZ4740_WDT=y -# CONFIG_LCD_CLASS_DEVICE is not set -# CONFIG_BACKLIGHT_CLASS_DEVICE is not set # CONFIG_VGA_CONSOLE is not set # CONFIG_HID is not set # CONFIG_USB_SUPPORT is not set @@ -82,8 +73,6 @@ CONFIG_RTC_DRV_JZ4740=y CONFIG_DMADEVICES=y CONFIG_DMA_JZ4780=y # CONFIG_IOMMU_SUPPORT is not set -CONFIG_NVMEM=y -CONFIG_NVMEM_SYSFS=y CONFIG_EXT4_FS=y # CONFIG_DNOTIFY is not set CONFIG_AUTOFS_FS=y @@ -108,8 +97,8 @@ CONFIG_CONSOLE_LOGLEVEL_QUIET=15 CONFIG_MESSAGE_LOGLEVEL_DEFAULT=7 CONFIG_DEBUG_INFO=y CONFIG_STRIP_ASM_SYMS=y -CONFIG_DEBUG_FS=y CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_FS=y CONFIG_PANIC_ON_OOPS=y CONFIG_PANIC_TIMEOUT=10 # CONFIG_SCHED_DEBUG is not set diff --git a/arch/mips/configs/cu1830-neo_defconfig b/arch/mips/configs/cu1830-neo_defconfig index cbfb62900273..e7064851a47a 100644 --- a/arch/mips/configs/cu1830-neo_defconfig +++ b/arch/mips/configs/cu1830-neo_defconfig @@ -1,5 +1,3 @@ -CONFIG_LOCALVERSION_AUTO=y -CONFIG_KERNEL_GZIP=y CONFIG_SYSVIPC=y CONFIG_NO_HZ_IDLE=y CONFIG_HIGH_RES_TIMERS=y @@ -9,7 +7,6 @@ CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_CGROUPS=y CONFIG_MEMCG=y -CONFIG_MEMCG_KMEM=y CONFIG_CGROUP_SCHED=y CONFIG_CGROUP_FREEZER=y CONFIG_CGROUP_DEVICE=y @@ -22,7 +19,7 @@ CONFIG_EMBEDDED=y # CONFIG_VM_EVENT_COUNTERS is not set # CONFIG_COMPAT_BRK is not set CONFIG_SLAB=y -CONFIG_MACH_INGENIC=y +CONFIG_MACH_INGENIC_SOC=y CONFIG_X1830_CU1830_NEO=y CONFIG_HIGHMEM=y CONFIG_HZ_100=y @@ -31,7 +28,6 @@ CONFIG_HZ_100=y # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set # CONFIG_COMPACTION is not set CONFIG_CMA=y -CONFIG_CMA_AREAS=7 CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -40,7 +36,6 @@ CONFIG_CFG80211=y CONFIG_UEVENT_HELPER=y CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y -# CONFIG_FW_LOADER is not set # CONFIG_ALLOW_DEV_COREDUMP is not set CONFIG_MD=y CONFIG_BLK_DEV_MD=y @@ -49,13 +44,11 @@ CONFIG_NETDEVICES=y CONFIG_STMMAC_ETH=y CONFIG_ICPLUS_PHY=y CONFIG_BRCMFMAC=y -# CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set CONFIG_VT_HW_CONSOLE_BINDING=y CONFIG_LEGACY_PTY_COUNT=2 -CONFIG_SERIAL_EARLYCON=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=2 @@ -69,8 +62,6 @@ CONFIG_GPIO_SYSFS=y CONFIG_SENSORS_ADS7828=y CONFIG_WATCHDOG=y CONFIG_JZ4740_WDT=y -# CONFIG_LCD_CLASS_DEVICE is not set -# CONFIG_BACKLIGHT_CLASS_DEVICE is not set # CONFIG_VGA_CONSOLE is not set # CONFIG_HID is not set # CONFIG_USB_SUPPORT is not set @@ -85,8 +76,6 @@ CONFIG_RTC_DRV_JZ4740=y CONFIG_DMADEVICES=y CONFIG_DMA_JZ4780=y # CONFIG_IOMMU_SUPPORT is not set -CONFIG_NVMEM=y -CONFIG_NVMEM_SYSFS=y CONFIG_EXT4_FS=y # CONFIG_DNOTIFY is not set CONFIG_AUTOFS_FS=y @@ -111,8 +100,8 @@ CONFIG_CONSOLE_LOGLEVEL_QUIET=15 CONFIG_MESSAGE_LOGLEVEL_DEFAULT=7 CONFIG_DEBUG_INFO=y CONFIG_STRIP_ASM_SYMS=y -CONFIG_DEBUG_FS=y CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_FS=y CONFIG_PANIC_ON_OOPS=y CONFIG_PANIC_TIMEOUT=10 # CONFIG_SCHED_DEBUG is not set diff --git a/arch/mips/configs/gcw0_defconfig b/arch/mips/configs/gcw0_defconfig index 4994749b9eaa..7e28a4fe9d84 100644 --- a/arch/mips/configs/gcw0_defconfig +++ b/arch/mips/configs/gcw0_defconfig @@ -4,7 +4,7 @@ CONFIG_HIGH_RES_TIMERS=y CONFIG_PREEMPT_VOLUNTARY=y CONFIG_EMBEDDED=y CONFIG_PROFILING=y -CONFIG_MACH_INGENIC=y +CONFIG_MACH_INGENIC_SOC=y CONFIG_JZ4770_GCW0=y CONFIG_HIGHMEM=y # CONFIG_SECCOMP is not set diff --git a/arch/mips/configs/qi_lb60_defconfig b/arch/mips/configs/qi_lb60_defconfig index 9c2c183085d1..b4448d0876d5 100644 --- a/arch/mips/configs/qi_lb60_defconfig +++ b/arch/mips/configs/qi_lb60_defconfig @@ -7,7 +7,7 @@ CONFIG_EMBEDDED=y # CONFIG_VM_EVENT_COUNTERS is not set # CONFIG_COMPAT_BRK is not set CONFIG_SLAB=y -CONFIG_MACH_INGENIC=y +CONFIG_MACH_INGENIC_SOC=y CONFIG_JZ4740_QI_LB60=y CONFIG_HZ_100=y # CONFIG_SECCOMP is not set @@ -73,9 +73,7 @@ CONFIG_DRM=y CONFIG_DRM_FBDEV_OVERALLOC=200 CONFIG_DRM_PANEL_SIMPLE=y CONFIG_DRM_INGENIC=y -# CONFIG_LCD_CLASS_DEVICE is not set CONFIG_BACKLIGHT_CLASS_DEVICE=y -# CONFIG_BACKLIGHT_GENERIC is not set # CONFIG_VGA_CONSOLE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y @@ -171,9 +169,9 @@ CONFIG_PRINTK_TIME=y CONFIG_DEBUG_INFO=y CONFIG_STRIP_ASM_SYMS=y CONFIG_READABLE_ASM=y +CONFIG_KGDB=y CONFIG_DEBUG_KMEMLEAK=y CONFIG_DEBUG_MEMORY_INIT=y CONFIG_DEBUG_STACKOVERFLOW=y CONFIG_PANIC_ON_OOPS=y # CONFIG_FTRACE is not set -CONFIG_KGDB=y diff --git a/arch/mips/configs/rs90_defconfig b/arch/mips/configs/rs90_defconfig index de6752051ecc..dfbb9fed9a42 100644 --- a/arch/mips/configs/rs90_defconfig +++ b/arch/mips/configs/rs90_defconfig @@ -19,7 +19,7 @@ CONFIG_EMBEDDED=y # CONFIG_PERF_EVENTS is not set CONFIG_SLAB=y CONFIG_PROFILING=y -CONFIG_MACH_INGENIC=y +CONFIG_MACH_INGENIC_SOC=y CONFIG_JZ4740_RS90=y CONFIG_PAGE_SIZE_16KB=y CONFIG_HZ_100=y @@ -80,8 +80,8 @@ CONFIG_KEYBOARD_GPIO=y # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set CONFIG_LEGACY_PTY_COUNT=2 -# CONFIG_DEVMEM is not set # CONFIG_HW_RANDOM is not set +# CONFIG_DEVMEM is not set # CONFIG_I2C_COMPAT is not set # CONFIG_I2C_HELPER_AUTO is not set CONFIG_POWER_SUPPLY=y From d41afc398fbc9dfb8c40b951e97a7f0283346c6a Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Sun, 6 Sep 2020 21:29:35 +0200 Subject: [PATCH 253/645] MAINTAINERS: Update paths to Ingenic platform code Support for Ingenic chips has been moved to the generic MIPS platform. Update the paths accordingly. Signed-off-by: Paul Cercueil Signed-off-by: Thomas Bogendoerfer --- MAINTAINERS | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index deaafb617361..52ce4a1beede 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8595,8 +8595,9 @@ INGENIC JZ47xx SoCs M: Paul Cercueil S: Maintained F: arch/mips/boot/dts/ingenic/ -F: arch/mips/include/asm/mach-jz4740/ -F: arch/mips/jz4740/ +F: arch/mips/generic/board-ingenic.c +F: arch/mips/include/asm/mach-ingenic/ +F: arch/mips/ingenic/Kconfig F: drivers/clk/ingenic/ F: drivers/dma/dma-jz4780.c F: drivers/gpu/drm/ingenic/ From bcf1650c9b826602ad860f4465a3b66be611508a Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Wed, 16 Sep 2020 12:02:49 +0200 Subject: [PATCH 254/645] s390/boot: avoid unnecessary zeroing of .bss section .bss section is a part of the decompressor's image now, linker fills it with zeros already. No need do it with memset additionally. Reviewed-by: Alexander Egorenkov Signed-off-by: Vasily Gorbik --- arch/s390/boot/head.S | 6 ------ 1 file changed, 6 deletions(-) diff --git a/arch/s390/boot/head.S b/arch/s390/boot/head.S index fd78755d996d..dae10961d072 100644 --- a/arch/s390/boot/head.S +++ b/arch/s390/boot/head.S @@ -313,12 +313,6 @@ ENTRY(startup_kdump) spt 6f-.LPG0(%r13) mvc __LC_LAST_UPDATE_TIMER(8),6f-.LPG0(%r13) l %r15,.Lstack-.LPG0(%r13) - // Clear decompressor's BSS section - larl %r2,_bss - slgr %r3,%r3 - larl %r4,_ebss - slgr %r4,%r2 - brasl %r14,memset brasl %r14,verify_facilities brasl %r14,startup_kernel From 14ab622432415326ab832441ec5d19003a3b1176 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Wed, 16 Sep 2020 12:06:02 +0200 Subject: [PATCH 255/645] s390/sclp: clean up unneeded .data section usage Since commit 980d5f9ab36b ("s390/boot: enable .bss section for compressed kernel") .bss section usage is no longer restricted. .bss section is a part of the decompressor's image and is zeroed by the linker. For that reason clean up now unneeded .data section usage. Reviewed-by: Alexander Egorenkov Signed-off-by: Vasily Gorbik --- drivers/s390/char/sclp_early_core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/s390/char/sclp_early_core.c b/drivers/s390/char/sclp_early_core.c index 7737470f8498..958621326ece 100644 --- a/drivers/s390/char/sclp_early_core.c +++ b/drivers/s390/char/sclp_early_core.c @@ -17,12 +17,12 @@ static struct read_info_sccb __bootdata(sclp_info_sccb); static int __bootdata(sclp_info_sccb_valid); char *sclp_early_sccb = (char *) EARLY_SCCB_OFFSET; -int sclp_init_state __section(.data) = sclp_init_state_uninitialized; +int sclp_init_state = sclp_init_state_uninitialized; /* * Used to keep track of the size of the event masks. Qemu until version 2.11 * only supports 4 and needs a workaround. */ -bool sclp_mask_compat_mode __section(.data); +bool sclp_mask_compat_mode; void sclp_early_wait_irq(void) { From 5596c4c106baf3c915724dc0ae3ed293b4d1af55 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Fri, 18 Sep 2020 19:04:36 +0200 Subject: [PATCH 256/645] s390/sclp: remove unused sclp_early_printk_forced This reverts commit 55a5542a5462 ("s390/hibernate: fix error handling when suspend cpu != resume cpu"). It added sclp_early_printk_force() which is no longer used since commit 394216275c7d ("s390: remove broken hibernate / power management support"). No hibernate - no problem. Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/sclp.h | 3 +-- arch/s390/kernel/early_printk.c | 2 +- drivers/s390/char/sclp_early_core.c | 11 +++-------- 3 files changed, 5 insertions(+), 11 deletions(-) diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h index c563f8368b19..90f34c7e2752 100644 --- a/arch/s390/include/asm/sclp.h +++ b/arch/s390/include/asm/sclp.h @@ -114,8 +114,7 @@ int sclp_early_get_core_info(struct sclp_core_info *info); void sclp_early_get_ipl_info(struct sclp_ipl_info *info); void sclp_early_detect(void); void sclp_early_printk(const char *s); -void sclp_early_printk_force(const char *s); -void __sclp_early_printk(const char *s, unsigned int len, unsigned int force); +void __sclp_early_printk(const char *s, unsigned int len); int sclp_early_get_memsize(unsigned long *mem); int sclp_early_get_hsa_size(unsigned long *hsa_size); diff --git a/arch/s390/kernel/early_printk.c b/arch/s390/kernel/early_printk.c index 6f24d83bc5dc..d9d53f44008a 100644 --- a/arch/s390/kernel/early_printk.c +++ b/arch/s390/kernel/early_printk.c @@ -10,7 +10,7 @@ static void sclp_early_write(struct console *con, const char *s, unsigned int len) { - __sclp_early_printk(s, len, 0); + __sclp_early_printk(s, len); } static struct console sclp_early_console = { diff --git a/drivers/s390/char/sclp_early_core.c b/drivers/s390/char/sclp_early_core.c index 958621326ece..a960afa974bf 100644 --- a/drivers/s390/char/sclp_early_core.c +++ b/drivers/s390/char/sclp_early_core.c @@ -214,11 +214,11 @@ static int sclp_early_setup(int disable, int *have_linemode, int *have_vt220) * Output one or more lines of text on the SCLP console (VT220 and / * or line-mode). */ -void __sclp_early_printk(const char *str, unsigned int len, unsigned int force) +void __sclp_early_printk(const char *str, unsigned int len) { int have_linemode, have_vt220; - if (!force && sclp_init_state != sclp_init_state_uninitialized) + if (sclp_init_state != sclp_init_state_uninitialized) return; if (sclp_early_setup(0, &have_linemode, &have_vt220) != 0) return; @@ -231,12 +231,7 @@ void __sclp_early_printk(const char *str, unsigned int len, unsigned int force) void sclp_early_printk(const char *str) { - __sclp_early_printk(str, strlen(str), 0); -} - -void sclp_early_printk_force(const char *str) -{ - __sclp_early_printk(str, strlen(str), 1); + __sclp_early_printk(str, strlen(str)); } int __init sclp_early_read_info(void) From d976ae6ba04cdbe62a60fc6dc6f363da596d5622 Mon Sep 17 00:00:00 2001 From: Jason Yan Date: Fri, 11 Sep 2020 10:01:32 +0800 Subject: [PATCH 257/645] MIPS: Make setup_elfcorehdr and setup_elfcorehdr_size static This addresses the following sparse warning: arch/mips/kernel/setup.c:446:33: warning: symbol 'setup_elfcorehdr_size' was not declared. Should it be static? Reported-by: Hulk Robot Signed-off-by: Jason Yan Signed-off-by: Thomas Bogendoerfer --- arch/mips/kernel/setup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index bf5f5acab0a8..8589a34c28de 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -447,7 +447,7 @@ static int __init early_parse_memmap(char *p) early_param("memmap", early_parse_memmap); #ifdef CONFIG_PROC_VMCORE -unsigned long setup_elfcorehdr, setup_elfcorehdr_size; +static unsigned long setup_elfcorehdr, setup_elfcorehdr_size; static int __init early_parse_elfcorehdr(char *p) { struct memblock_region *mem; From 6fa573a3e307af923c3220beeba65e8f566e94c2 Mon Sep 17 00:00:00 2001 From: Pujin Shi Date: Tue, 22 Sep 2020 00:18:21 +0800 Subject: [PATCH 258/645] MIPS: kernel: include probes-common.h header in branch.c arch/mips/kernel/branch.c:876:5: error: no previous prototype for '__insn_is_compact_branch' [-Werror=missing-prototypes] Signed-off-by: Pujin Shi Signed-off-by: Pujin Shi Signed-off-by: Thomas Bogendoerfer --- arch/mips/kernel/branch.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c index fb3e203698ea..0216ff24c392 100644 --- a/arch/mips/kernel/branch.c +++ b/arch/mips/kernel/branch.c @@ -20,6 +20,8 @@ #include #include +#include "probes-common.h" + /* * Calculate and return exception PC in case of branch delay slot * for microMIPS and MIPS16e. It does not clear the ISA mode bit. From 4e43e5df5850ca8300180f422727e42a5065aaaa Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Mon, 21 Sep 2020 17:12:26 +0800 Subject: [PATCH 259/645] MIPS: context switch: Use save/restore instead of set/clear for Status.CU2 Some processors (such as Loongson-3) need to enable CU2 in kernel mode, current set/clear method will lose Status.CU2 during context switching, so use save/restore method instead. Signed-off-by: Huacai Chen Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/switch_to.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/mips/include/asm/switch_to.h b/arch/mips/include/asm/switch_to.h index 0b0a93bf83cd..a4374b4cb88f 100644 --- a/arch/mips/include/asm/switch_to.h +++ b/arch/mips/include/asm/switch_to.h @@ -117,6 +117,8 @@ do { \ __restore_dsp(next); \ } \ if (cop2_present) { \ + u32 status = read_c0_status(); \ + \ set_c0_status(ST0_CU2); \ if ((KSTK_STATUS(prev) & ST0_CU2)) { \ if (cop2_lazy_restore) \ @@ -127,7 +129,7 @@ do { \ !cop2_lazy_restore) { \ cop2_restore(next); \ } \ - clear_c0_status(ST0_CU2); \ + write_c0_status(status); \ } \ __clear_r5_hw_ll_bit(); \ __clear_software_ll_bit(); \ From 195615ecc8309082a524433cf552eda722b26c1c Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Mon, 21 Sep 2020 17:12:27 +0800 Subject: [PATCH 260/645] MIPS: Loongson-3: Enable COP2 usage in kernel Loongson-3's COP2 is Multi-Media coprocessor, it is disabled in kernel mode by default. However, gslq/gssq (16-bytes load/store instructions) overrides the instruction format of lwc2/swc2. If we wan't to use gslq/ gssq for optimization in kernel, we should enable COP2 usage in kernel. Please pay attention that in this patch we only enable COP2 in kernel, which means it will lose ST0_CU2 when a process go to user space (try to use COP2 in user space will trigger an exception and then grab COP2, which is similar to FPU). And as a result, we need to modify the context switching code because the new scheduled process doesn't contain ST0_CU2 in its THERAD_STATUS probably. For zboot, we disable gslq/gssq be generated by toolchain. Signed-off-by: Huacai Chen Signed-off-by: Thomas Bogendoerfer --- arch/mips/boot/compressed/Makefile | 5 +++++ arch/mips/include/asm/mipsregs.h | 7 +++++++ arch/mips/include/asm/stackframe.h | 6 +++--- arch/mips/kernel/head.S | 2 +- arch/mips/kernel/process.c | 4 ++-- arch/mips/kernel/traps.c | 2 +- 6 files changed, 19 insertions(+), 7 deletions(-) diff --git a/arch/mips/boot/compressed/Makefile b/arch/mips/boot/compressed/Makefile index 9a9ba77b745e..d66511825fe1 100644 --- a/arch/mips/boot/compressed/Makefile +++ b/arch/mips/boot/compressed/Makefile @@ -22,6 +22,11 @@ KBUILD_CFLAGS := $(filter-out -pg, $(KBUILD_CFLAGS)) KBUILD_CFLAGS := $(filter-out -fstack-protector, $(KBUILD_CFLAGS)) +# Disable lq/sq in zboot +ifdef CONFIG_CPU_LOONGSON64 +KBUILD_CFLAGS := $(filter-out -march=loongson3a, $(KBUILD_CFLAGS)) -march=mips64r2 +endif + KBUILD_CFLAGS := $(KBUILD_CFLAGS) -D__KERNEL__ -D__DISABLE_EXPORTS \ -DBOOT_HEAP_SIZE=$(BOOT_HEAP_SIZE) -D"VMLINUX_LOAD_ADDRESS_ULL=$(VMLINUX_LOAD_ADDRESS)ull" diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h index 3a7379b8f31c..a0e8ae5497b6 100644 --- a/arch/mips/include/asm/mipsregs.h +++ b/arch/mips/include/asm/mipsregs.h @@ -389,6 +389,13 @@ #define ST0_CU3 0x80000000 #define ST0_XX 0x80000000 /* MIPS IV naming */ +/* in-kernel enabled CUs */ +#ifdef CONFIG_CPU_LOONGSON64 +#define ST0_KERNEL_CUMASK (ST0_CU0 | ST0_CU2) +#else +#define ST0_KERNEL_CUMASK ST0_CU0 +#endif + /* * Bitfields and bit numbers in the coprocessor 0 IntCtl register. (MIPSR2) */ diff --git a/arch/mips/include/asm/stackframe.h b/arch/mips/include/asm/stackframe.h index 3e8d2aaf96af..aa430a6c68b2 100644 --- a/arch/mips/include/asm/stackframe.h +++ b/arch/mips/include/asm/stackframe.h @@ -450,7 +450,7 @@ */ .macro CLI mfc0 t0, CP0_STATUS - li t1, ST0_CU0 | STATMASK + li t1, ST0_KERNEL_CUMASK | STATMASK or t0, t1 xori t0, STATMASK mtc0 t0, CP0_STATUS @@ -463,7 +463,7 @@ */ .macro STI mfc0 t0, CP0_STATUS - li t1, ST0_CU0 | STATMASK + li t1, ST0_KERNEL_CUMASK | STATMASK or t0, t1 xori t0, STATMASK & ~1 mtc0 t0, CP0_STATUS @@ -477,7 +477,7 @@ */ .macro KMODE mfc0 t0, CP0_STATUS - li t1, ST0_CU0 | (STATMASK & ~1) + li t1, ST0_KERNEL_CUMASK | (STATMASK & ~1) #if defined(CONFIG_CPU_R3000) || defined(CONFIG_CPU_TX39XX) andi t2, t0, ST0_IEP srl t2, 2 diff --git a/arch/mips/kernel/head.S b/arch/mips/kernel/head.S index 7dd234e788e6..61b73580b877 100644 --- a/arch/mips/kernel/head.S +++ b/arch/mips/kernel/head.S @@ -35,7 +35,7 @@ .macro setup_c0_status set clr .set push mfc0 t0, CP0_STATUS - or t0, ST0_CU0|\set|0x1f|\clr + or t0, ST0_KERNEL_CUMASK|\set|0x1f|\clr xor t0, 0x1f|\clr mtc0 t0, CP0_STATUS .set noreorder diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index f5dc316a826a..b36297ee2b37 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -68,7 +68,7 @@ void start_thread(struct pt_regs * regs, unsigned long pc, unsigned long sp) unsigned long status; /* New thread loses kernel privileges. */ - status = regs->cp0_status & ~(ST0_CU0|ST0_CU1|ST0_FR|KU_MASK); + status = regs->cp0_status & ~(ST0_CU0|ST0_CU1|ST0_CU2|ST0_FR|KU_MASK); status |= KU_USER; regs->cp0_status = status; lose_fpu(0); @@ -133,7 +133,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, childregs = (struct pt_regs *) childksp - 1; /* Put the stack after the struct pt_regs. */ childksp = (unsigned long) childregs; - p->thread.cp0_status = read_c0_status() & ~(ST0_CU2|ST0_CU1); + p->thread.cp0_status = (read_c0_status() & ~(ST0_CU2|ST0_CU1)) | ST0_KERNEL_CUMASK; if (unlikely(p->flags & PF_KTHREAD)) { /* kernel thread */ unsigned long status = p->thread.cp0_status; diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 38aa07ccdbcc..14225b616119 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -2192,7 +2192,7 @@ static void configure_status(void) * flag that some firmware may have left set and the TS bit (for * IP27). Set XX for ISA IV code to work. */ - unsigned int status_set = ST0_CU0; + unsigned int status_set = ST0_KERNEL_CUMASK; #ifdef CONFIG_64BIT status_set |= ST0_FR|ST0_KX|ST0_SX|ST0_UX; #endif From bc1c969f1158485f64e360659f755d19136bb5b0 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Mon, 21 Sep 2020 17:12:28 +0800 Subject: [PATCH 261/645] MIPS: Loongson-3: Calculate ra properly when unwinding the stack Loongson-3 has 16-bytes load/store instructions: gslq and gssq. This patch calculate ra properly when unwinding the stack, if ra is saved by gssq and restored by gslq. Signed-off-by: Huacai Chen Signed-off-by: Thomas Bogendoerfer --- arch/mips/kernel/process.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index b36297ee2b37..37f05c8605c2 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -279,7 +279,21 @@ static inline int is_ra_save_ins(union mips_instruction *ip, int *poff) *poff = ip->i_format.simmediate / sizeof(ulong); return 1; } - +#ifdef CONFIG_CPU_LOONGSON64 + if ((ip->loongson3_lswc2_format.opcode == swc2_op) && + (ip->loongson3_lswc2_format.ls == 1) && + (ip->loongson3_lswc2_format.fr == 0) && + (ip->loongson3_lswc2_format.base == 29)) { + if (ip->loongson3_lswc2_format.rt == 31) { + *poff = ip->loongson3_lswc2_format.offset << 1; + return 1; + } + if (ip->loongson3_lswc2_format.rq == 31) { + *poff = (ip->loongson3_lswc2_format.offset << 1) + 1; + return 1; + } + } +#endif return 0; #endif } From 7895d662bab8827176d44326d0a7423221287ca9 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Sun, 20 Sep 2020 22:51:50 +0200 Subject: [PATCH 262/645] MIPS: SGI-IP30: Move irq bits to better header files Move HEART specific parts of mach-ip30/irq.h to asm/sgi/heart.h and IP30 specific parts to sgi-ip30/ip30-common.h. Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/mach-ip30/irq.h | 87 --------------------------- arch/mips/include/asm/sgi/heart.h | 51 ++++++++++++++++ arch/mips/sgi-ip30/ip30-common.h | 14 +++++ arch/mips/sgi-ip30/ip30-irq.c | 2 + 4 files changed, 67 insertions(+), 87 deletions(-) delete mode 100644 arch/mips/include/asm/mach-ip30/irq.h diff --git a/arch/mips/include/asm/mach-ip30/irq.h b/arch/mips/include/asm/mach-ip30/irq.h deleted file mode 100644 index 27ba899c95be..000000000000 --- a/arch/mips/include/asm/mach-ip30/irq.h +++ /dev/null @@ -1,87 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * HEART IRQ defines - * - * Copyright (C) 2009 Johannes Dickgreber - * 2014-2016 Joshua Kinard - * - */ - -#ifndef __ASM_MACH_IP30_IRQ_H -#define __ASM_MACH_IP30_IRQ_H - -/* - * HEART has 64 hardware interrupts, but use 128 to leave room for a few - * software interrupts as well (such as the CPU timer interrupt. - */ -#define NR_IRQS 128 - -extern void __init ip30_install_ipi(void); - -/* - * HEART has 64 interrupt vectors available to it, subdivided into five - * priority levels. They are numbered 0 to 63. - */ -#define HEART_NUM_IRQS 64 - -/* - * These are the five interrupt priority levels and their corresponding - * CPU IPx interrupt pins. - * - * Level 4 - Error Interrupts. - * Level 3 - HEART timer interrupt. - * Level 2 - CPU IPI, CPU debug, power putton, general device interrupts. - * Level 1 - General device interrupts. - * Level 0 - General device GFX flow control interrupts. - */ -#define HEART_L4_INT_MASK 0xfff8000000000000ULL /* IP6 */ -#define HEART_L3_INT_MASK 0x0004000000000000ULL /* IP5 */ -#define HEART_L2_INT_MASK 0x0003ffff00000000ULL /* IP4 */ -#define HEART_L1_INT_MASK 0x00000000ffff0000ULL /* IP3 */ -#define HEART_L0_INT_MASK 0x000000000000ffffULL /* IP2 */ - -/* HEART L0 Interrupts (Low Priority) */ -#define HEART_L0_INT_GENERIC 0 -#define HEART_L0_INT_FLOW_CTRL_HWTR_0 1 -#define HEART_L0_INT_FLOW_CTRL_HWTR_1 2 - -/* HEART L2 Interrupts (High Priority) */ -#define HEART_L2_INT_RESCHED_CPU_0 46 -#define HEART_L2_INT_RESCHED_CPU_1 47 -#define HEART_L2_INT_CALL_CPU_0 48 -#define HEART_L2_INT_CALL_CPU_1 49 - -/* HEART L3 Interrupts (Compare/Counter Timer) */ -#define HEART_L3_INT_TIMER 50 - -/* HEART L4 Interrupts (Errors) */ -#define HEART_L4_INT_XWID_ERR_9 51 -#define HEART_L4_INT_XWID_ERR_A 52 -#define HEART_L4_INT_XWID_ERR_B 53 -#define HEART_L4_INT_XWID_ERR_C 54 -#define HEART_L4_INT_XWID_ERR_D 55 -#define HEART_L4_INT_XWID_ERR_E 56 -#define HEART_L4_INT_XWID_ERR_F 57 -#define HEART_L4_INT_XWID_ERR_XBOW 58 -#define HEART_L4_INT_CPU_BUS_ERR_0 59 -#define HEART_L4_INT_CPU_BUS_ERR_1 60 -#define HEART_L4_INT_CPU_BUS_ERR_2 61 -#define HEART_L4_INT_CPU_BUS_ERR_3 62 -#define HEART_L4_INT_HEART_EXCP 63 - -/* - * Power Switch is wired via BaseIO BRIDGE slot #6. - * - * ACFail is wired via BaseIO BRIDGE slot #7. - */ -#define IP30_POWER_IRQ HEART_L2_INT_POWER_BTN - -#include - -#define IP30_HEART_L0_IRQ (MIPS_CPU_IRQ_BASE + 2) -#define IP30_HEART_L1_IRQ (MIPS_CPU_IRQ_BASE + 3) -#define IP30_HEART_L2_IRQ (MIPS_CPU_IRQ_BASE + 4) -#define IP30_HEART_TIMER_IRQ (MIPS_CPU_IRQ_BASE + 5) -#define IP30_HEART_ERR_IRQ (MIPS_CPU_IRQ_BASE + 6) - -#endif /* __ASM_MACH_IP30_IRQ_H */ diff --git a/arch/mips/include/asm/sgi/heart.h b/arch/mips/include/asm/sgi/heart.h index c423221b4792..0d03751955c4 100644 --- a/arch/mips/include/asm/sgi/heart.h +++ b/arch/mips/include/asm/sgi/heart.h @@ -264,6 +264,57 @@ struct ip30_heart_regs { /* 0x0ff00000 */ #define HC_NCOR_MEM_ERR BIT(1) #define HC_COR_MEM_ERR BIT(0) +/* + * HEART has 64 interrupt vectors available to it, subdivided into five + * priority levels. They are numbered 0 to 63. + */ +#define HEART_NUM_IRQS 64 + +/* + * These are the five interrupt priority levels and their corresponding + * CPU IPx interrupt pins. + * + * Level 4 - Error Interrupts. + * Level 3 - HEART timer interrupt. + * Level 2 - CPU IPI, CPU debug, power putton, general device interrupts. + * Level 1 - General device interrupts. + * Level 0 - General device GFX flow control interrupts. + */ +#define HEART_L4_INT_MASK 0xfff8000000000000ULL /* IP6 */ +#define HEART_L3_INT_MASK 0x0004000000000000ULL /* IP5 */ +#define HEART_L2_INT_MASK 0x0003ffff00000000ULL /* IP4 */ +#define HEART_L1_INT_MASK 0x00000000ffff0000ULL /* IP3 */ +#define HEART_L0_INT_MASK 0x000000000000ffffULL /* IP2 */ + +/* HEART L0 Interrupts (Low Priority) */ +#define HEART_L0_INT_GENERIC 0 +#define HEART_L0_INT_FLOW_CTRL_HWTR_0 1 +#define HEART_L0_INT_FLOW_CTRL_HWTR_1 2 + +/* HEART L2 Interrupts (High Priority) */ +#define HEART_L2_INT_RESCHED_CPU_0 46 +#define HEART_L2_INT_RESCHED_CPU_1 47 +#define HEART_L2_INT_CALL_CPU_0 48 +#define HEART_L2_INT_CALL_CPU_1 49 + +/* HEART L3 Interrupts (Compare/Counter Timer) */ +#define HEART_L3_INT_TIMER 50 + +/* HEART L4 Interrupts (Errors) */ +#define HEART_L4_INT_XWID_ERR_9 51 +#define HEART_L4_INT_XWID_ERR_A 52 +#define HEART_L4_INT_XWID_ERR_B 53 +#define HEART_L4_INT_XWID_ERR_C 54 +#define HEART_L4_INT_XWID_ERR_D 55 +#define HEART_L4_INT_XWID_ERR_E 56 +#define HEART_L4_INT_XWID_ERR_F 57 +#define HEART_L4_INT_XWID_ERR_XBOW 58 +#define HEART_L4_INT_CPU_BUS_ERR_0 59 +#define HEART_L4_INT_CPU_BUS_ERR_1 60 +#define HEART_L4_INT_CPU_BUS_ERR_2 61 +#define HEART_L4_INT_CPU_BUS_ERR_3 62 +#define HEART_L4_INT_HEART_EXCP 63 + extern struct ip30_heart_regs __iomem *heart_regs; #define heart_read ____raw_readq diff --git a/arch/mips/sgi-ip30/ip30-common.h b/arch/mips/sgi-ip30/ip30-common.h index d2bcaee712f3..7b5db24b6279 100644 --- a/arch/mips/sgi-ip30/ip30-common.h +++ b/arch/mips/sgi-ip30/ip30-common.h @@ -3,6 +3,20 @@ #ifndef __IP30_COMMON_H #define __IP30_COMMON_H +/* + * Power Switch is wired via BaseIO BRIDGE slot #6. + * + * ACFail is wired via BaseIO BRIDGE slot #7. + */ +#define IP30_POWER_IRQ HEART_L2_INT_POWER_BTN + +#define IP30_HEART_L0_IRQ (MIPS_CPU_IRQ_BASE + 2) +#define IP30_HEART_L1_IRQ (MIPS_CPU_IRQ_BASE + 3) +#define IP30_HEART_L2_IRQ (MIPS_CPU_IRQ_BASE + 4) +#define IP30_HEART_TIMER_IRQ (MIPS_CPU_IRQ_BASE + 5) +#define IP30_HEART_ERR_IRQ (MIPS_CPU_IRQ_BASE + 6) + +extern void __init ip30_install_ipi(void); extern struct plat_smp_ops ip30_smp_ops; extern void __init ip30_per_cpu_init(void); diff --git a/arch/mips/sgi-ip30/ip30-irq.c b/arch/mips/sgi-ip30/ip30-irq.c index c2ffcb920250..e8374e4c705b 100644 --- a/arch/mips/sgi-ip30/ip30-irq.c +++ b/arch/mips/sgi-ip30/ip30-irq.c @@ -14,6 +14,8 @@ #include #include +#include "ip30-common.h" + struct heart_irq_data { u64 *irq_mask; int cpu; From b123c46cf55853c0d56098c00b35943ae6f719d3 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Sun, 20 Sep 2020 23:03:46 +0200 Subject: [PATCH 263/645] MIPS: alchemy: remove unused ALCHEMY_GPIOINT_AU1300 Remove unused config option ALCHEMY_GPIOINT_AU1300 and related code. Signed-off-by: Thomas Bogendoerfer --- arch/mips/alchemy/Kconfig | 4 - .../include/asm/mach-au1x00/gpio-au1300.h | 137 ------------------ 2 files changed, 141 deletions(-) diff --git a/arch/mips/alchemy/Kconfig b/arch/mips/alchemy/Kconfig index 83b288b95b16..827256bbe6b8 100644 --- a/arch/mips/alchemy/Kconfig +++ b/arch/mips/alchemy/Kconfig @@ -3,10 +3,6 @@ config ALCHEMY_GPIOINT_AU1000 bool -# au1300-style GPIO/INT controller -config ALCHEMY_GPIOINT_AU1300 - bool - choice prompt "Machine type" depends on MIPS_ALCHEMY diff --git a/arch/mips/include/asm/mach-au1x00/gpio-au1300.h b/arch/mips/include/asm/mach-au1x00/gpio-au1300.h index d25846a1291f..d16add7ba49d 100644 --- a/arch/mips/include/asm/mach-au1x00/gpio-au1300.h +++ b/arch/mips/include/asm/mach-au1x00/gpio-au1300.h @@ -120,141 +120,4 @@ static inline int au1300_gpio_getinitlvl(unsigned int gpio) return (v >> gpio) & 1; } -/**********************************************************************/ - -/* Linux gpio framework integration. -* -* 4 use cases of Alchemy GPIOS: -*(1) GPIOLIB=y, ALCHEMY_GPIO_INDIRECT=y: -* Board must register gpiochips. -*(2) GPIOLIB=y, ALCHEMY_GPIO_INDIRECT=n: -* A gpiochip for the 75 GPIOs is registered. -* -*(3) GPIOLIB=n, ALCHEMY_GPIO_INDIRECT=y: -* the boards' gpio.h must provide the linux gpio wrapper functions, -* -*(4) GPIOLIB=n, ALCHEMY_GPIO_INDIRECT=n: -* inlinable gpio functions are provided which enable access to the -* Au1300 gpios only by using the numbers straight out of the data- -* sheets. - -* Cases 1 and 3 are intended for boards which want to provide their own -* GPIO namespace and -operations (i.e. for example you have 8 GPIOs -* which are in part provided by spare Au1300 GPIO pins and in part by -* an external FPGA but you still want them to be accessible in linux -* as gpio0-7. The board can of course use the alchemy_gpioX_* functions -* as required). -*/ - -#ifndef CONFIG_GPIOLIB - -#ifdef CONFIG_ALCHEMY_GPIOINT_AU1300 - -#ifndef CONFIG_ALCHEMY_GPIO_INDIRECT /* case (4) */ - -static inline int gpio_direction_input(unsigned int gpio) -{ - return au1300_gpio_direction_input(gpio); -} - -static inline int gpio_direction_output(unsigned int gpio, int v) -{ - return au1300_gpio_direction_output(gpio, v); -} - -static inline int gpio_get_value(unsigned int gpio) -{ - return au1300_gpio_get_value(gpio); -} - -static inline void gpio_set_value(unsigned int gpio, int v) -{ - au1300_gpio_set_value(gpio, v); -} - -static inline int gpio_get_value_cansleep(unsigned gpio) -{ - return gpio_get_value(gpio); -} - -static inline void gpio_set_value_cansleep(unsigned gpio, int value) -{ - gpio_set_value(gpio, value); -} - -static inline int gpio_is_valid(unsigned int gpio) -{ - return au1300_gpio_is_valid(gpio); -} - -static inline int gpio_cansleep(unsigned int gpio) -{ - return au1300_gpio_cansleep(gpio); -} - -static inline int gpio_to_irq(unsigned int gpio) -{ - return au1300_gpio_to_irq(gpio); -} - -static inline int irq_to_gpio(unsigned int irq) -{ - return au1300_irq_to_gpio(irq); -} - -static inline int gpio_request(unsigned int gpio, const char *label) -{ - return 0; -} - -static inline int gpio_request_one(unsigned gpio, - unsigned long flags, const char *label) -{ - return 0; -} - -static inline int gpio_request_array(struct gpio *array, size_t num) -{ - return 0; -} - -static inline void gpio_free(unsigned gpio) -{ -} - -static inline void gpio_free_array(struct gpio *array, size_t num) -{ -} - -static inline int gpio_set_debounce(unsigned gpio, unsigned debounce) -{ - return -ENOSYS; -} - -static inline void gpio_unexport(unsigned gpio) -{ -} - -static inline int gpio_export(unsigned gpio, bool direction_may_change) -{ - return -ENOSYS; -} - -static inline int gpio_sysfs_set_active_low(unsigned gpio, int value) -{ - return -ENOSYS; -} - -static inline int gpio_export_link(struct device *dev, const char *name, - unsigned gpio) -{ - return -ENOSYS; -} - -#endif /* !CONFIG_ALCHEMY_GPIO_INDIRECT */ - -#endif /* CONFIG_ALCHEMY_GPIOINT_AU1300 */ - -#endif /* CONFIG GPIOLIB */ - #endif /* _GPIO_AU1300_H_ */ From b350041e6f23a71f63f1eee6d939c846838e7e25 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Sun, 20 Sep 2020 23:03:47 +0200 Subject: [PATCH 264/645] MIPS: alchemy: remove unused ALCHEMY_GPIOINT_AU1000 Remove unused config option ALCHEMY_GPIOINT_AU1000. Signed-off-by: Thomas Bogendoerfer --- arch/mips/alchemy/Kconfig | 7 ------- 1 file changed, 7 deletions(-) diff --git a/arch/mips/alchemy/Kconfig b/arch/mips/alchemy/Kconfig index 827256bbe6b8..69734120ada1 100644 --- a/arch/mips/alchemy/Kconfig +++ b/arch/mips/alchemy/Kconfig @@ -1,8 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 -# au1000-style gpio and interrupt controllers -config ALCHEMY_GPIOINT_AU1000 - bool - choice prompt "Machine type" depends on MIPS_ALCHEMY @@ -11,7 +7,6 @@ choice config MIPS_MTX1 bool "4G Systems MTX-1 board" select HAVE_PCI - select ALCHEMY_GPIOINT_AU1000 select SYS_SUPPORTS_LITTLE_ENDIAN select SYS_HAS_EARLY_PRINTK @@ -29,13 +24,11 @@ config MIPS_DB1XXX config MIPS_XXS1500 bool "MyCable XXS1500 board" - select ALCHEMY_GPIOINT_AU1000 select SYS_SUPPORTS_LITTLE_ENDIAN select SYS_HAS_EARLY_PRINTK config MIPS_GPR bool "Trapeze ITS GPR board" - select ALCHEMY_GPIOINT_AU1000 select HAVE_PCI select SYS_SUPPORTS_LITTLE_ENDIAN select SYS_HAS_EARLY_PRINTK From 0c0938ea1d7c0619a096fa40d5bb23586b7ffb51 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Sun, 20 Sep 2020 23:08:34 +0200 Subject: [PATCH 265/645] MIPS: malta: remove unused header file Remove unused heasder file asm/mach-malta/malta-pm.h. Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/mach-malta/malta-pm.h | 33 --------------------- 1 file changed, 33 deletions(-) delete mode 100644 arch/mips/include/asm/mach-malta/malta-pm.h diff --git a/arch/mips/include/asm/mach-malta/malta-pm.h b/arch/mips/include/asm/mach-malta/malta-pm.h deleted file mode 100644 index 2a5146d79313..000000000000 --- a/arch/mips/include/asm/mach-malta/malta-pm.h +++ /dev/null @@ -1,33 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Copyright (C) 2014 Imagination Technologies - * Author: Paul Burton - */ - -#ifndef __ASM_MIPS_MACH_MALTA_PM_H__ -#define __ASM_MIPS_MACH_MALTA_PM_H__ - -#include - -#ifdef CONFIG_MIPS_MALTA_PM - -/** - * mips_pm_suspend - enter a suspend state - * @state: the state to enter, one of PIIX4_FUNC3IO_PMCNTRL_SUS_TYP_* - * - * Enters a suspend state via the Malta's PIIX4. If the state to be entered - * is one which loses context (eg. SOFF) then this function will never - * return. - */ -extern int mips_pm_suspend(unsigned state); - -#else /* !CONFIG_MIPS_MALTA_PM */ - -static inline int mips_pm_suspend(unsigned state) -{ - return -EINVAL; -} - -#endif /* !CONFIG_MIPS_MALTA_PM */ - -#endif /* __ASM_MIPS_MACH_MALTA_PM_H__ */ From 307c9926393aed6c48600bea218b9565f2292fcb Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Sun, 20 Sep 2020 23:13:42 +0200 Subject: [PATCH 266/645] MIPS: malta: remove mach-malta/malta-dtshim.h header file To clean up mach-* directories move external declaration of malta_dt_shim() to mips-boards/malta.h and remove malta-dtshim.h. Signed-off-by: Thomas Bogendoerfer --- .../include/asm/mach-malta/malta-dtshim.h | 25 ------------------- arch/mips/include/asm/mips-boards/malta.h | 2 ++ arch/mips/mti-malta/malta-setup.c | 1 - 3 files changed, 2 insertions(+), 26 deletions(-) delete mode 100644 arch/mips/include/asm/mach-malta/malta-dtshim.h diff --git a/arch/mips/include/asm/mach-malta/malta-dtshim.h b/arch/mips/include/asm/mach-malta/malta-dtshim.h deleted file mode 100644 index 7c97b710121d..000000000000 --- a/arch/mips/include/asm/mach-malta/malta-dtshim.h +++ /dev/null @@ -1,25 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Copyright (C) 2015 Imagination Technologies - * Author: Paul Burton - */ - -#ifndef __MIPS_MALTA_DTSHIM_H__ -#define __MIPS_MALTA_DTSHIM_H__ - -#include - -#ifdef CONFIG_MIPS_MALTA - -extern void __init *malta_dt_shim(void *fdt); - -#else /* !CONFIG_MIPS_MALTA */ - -static inline void *malta_dt_shim(void *fdt) -{ - return fdt; -} - -#endif /* !CONFIG_MIPS_MALTA */ - -#endif /* __MIPS_MALTA_DTSHIM_H__ */ diff --git a/arch/mips/include/asm/mips-boards/malta.h b/arch/mips/include/asm/mips-boards/malta.h index 65de4fb06096..254be3d62519 100644 --- a/arch/mips/include/asm/mips-boards/malta.h +++ b/arch/mips/include/asm/mips-boards/malta.h @@ -92,4 +92,6 @@ static inline unsigned long get_msc_port_base(unsigned long reg) #define MALTA_JMPRS_REG 0x1f000210 +extern void __init *malta_dt_shim(void *fdt); + #endif /* __ASM_MIPS_BOARDS_MALTA_H */ diff --git a/arch/mips/mti-malta/malta-setup.c b/arch/mips/mti-malta/malta-setup.c index c4ad5a9b4bc1..e1fb8b534944 100644 --- a/arch/mips/mti-malta/malta-setup.c +++ b/arch/mips/mti-malta/malta-setup.c @@ -16,7 +16,6 @@ #include #include -#include #include #include #include From c1f6b45e630a76d47506303defe111a48b651db1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E5=91=A8=E7=90=B0=E6=9D=B0=20=28Zhou=20Yanjie=29?= Date: Sat, 19 Sep 2020 19:38:59 +0800 Subject: [PATCH 267/645] MIPS: Ingenic: Add CPU nodes for Ingenic SoCs. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add 'cpus' node to the jz4725b.dtsi, jz4740.dtsi, jz4770.dtsi, jz4780.dtsi, x1000.dtsi, and x1830.dtsi files. Tested-by: H. Nikolaus Schaller Tested-by: Paul Boddie Signed-off-by: 周琰杰 (Zhou Yanjie) Reviewed-by: Paul Cercueil Signed-off-by: Thomas Bogendoerfer --- arch/mips/boot/dts/ingenic/jz4725b.dtsi | 14 ++++++++++++++ arch/mips/boot/dts/ingenic/jz4740.dtsi | 14 ++++++++++++++ arch/mips/boot/dts/ingenic/jz4770.dtsi | 15 ++++++++++++++- arch/mips/boot/dts/ingenic/jz4780.dtsi | 23 +++++++++++++++++++++++ arch/mips/boot/dts/ingenic/x1000.dtsi | 14 ++++++++++++++ arch/mips/boot/dts/ingenic/x1830.dtsi | 14 ++++++++++++++ 6 files changed, 93 insertions(+), 1 deletion(-) diff --git a/arch/mips/boot/dts/ingenic/jz4725b.dtsi b/arch/mips/boot/dts/ingenic/jz4725b.dtsi index a8fca560878d..a1f0b71c9223 100644 --- a/arch/mips/boot/dts/ingenic/jz4725b.dtsi +++ b/arch/mips/boot/dts/ingenic/jz4725b.dtsi @@ -7,6 +7,20 @@ #size-cells = <1>; compatible = "ingenic,jz4725b"; + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu0: cpu@0 { + device_type = "cpu"; + compatible = "ingenic,xburst-mxu1.0"; + reg = <0>; + + clocks = <&cgu JZ4725B_CLK_CCLK>; + clock-names = "cpu"; + }; + }; + cpuintc: interrupt-controller { #address-cells = <0>; #interrupt-cells = <1>; diff --git a/arch/mips/boot/dts/ingenic/jz4740.dtsi b/arch/mips/boot/dts/ingenic/jz4740.dtsi index 1520585c235c..eee523678ce5 100644 --- a/arch/mips/boot/dts/ingenic/jz4740.dtsi +++ b/arch/mips/boot/dts/ingenic/jz4740.dtsi @@ -7,6 +7,20 @@ #size-cells = <1>; compatible = "ingenic,jz4740"; + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu0: cpu@0 { + device_type = "cpu"; + compatible = "ingenic,xburst-mxu1.0"; + reg = <0>; + + clocks = <&cgu JZ4740_CLK_CCLK>; + clock-names = "cpu"; + }; + }; + cpuintc: interrupt-controller { #address-cells = <0>; #interrupt-cells = <1>; diff --git a/arch/mips/boot/dts/ingenic/jz4770.dtsi b/arch/mips/boot/dts/ingenic/jz4770.dtsi index fa11ac950499..018721a9eea9 100644 --- a/arch/mips/boot/dts/ingenic/jz4770.dtsi +++ b/arch/mips/boot/dts/ingenic/jz4770.dtsi @@ -1,5 +1,4 @@ // SPDX-License-Identifier: GPL-2.0 - #include #include @@ -8,6 +7,20 @@ #size-cells = <1>; compatible = "ingenic,jz4770"; + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu0: cpu@0 { + device_type = "cpu"; + compatible = "ingenic,xburst-fpu1.0-mxu1.1"; + reg = <0>; + + clocks = <&cgu JZ4770_CLK_CCLK>; + clock-names = "cpu"; + }; + }; + cpuintc: interrupt-controller { #address-cells = <0>; #interrupt-cells = <1>; diff --git a/arch/mips/boot/dts/ingenic/jz4780.dtsi b/arch/mips/boot/dts/ingenic/jz4780.dtsi index b7f409a7cf5d..dfb5a7e1bb21 100644 --- a/arch/mips/boot/dts/ingenic/jz4780.dtsi +++ b/arch/mips/boot/dts/ingenic/jz4780.dtsi @@ -8,6 +8,29 @@ #size-cells = <1>; compatible = "ingenic,jz4780"; + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu0: cpu@0 { + device_type = "cpu"; + compatible = "ingenic,xburst-fpu1.0-mxu1.1"; + reg = <0>; + + clocks = <&cgu JZ4780_CLK_CPU>; + clock-names = "cpu"; + }; + + cpu1: cpu@1 { + device_type = "cpu"; + compatible = "ingenic,xburst-fpu1.0-mxu1.1"; + reg = <1>; + + clocks = <&cgu JZ4780_CLK_CORE1>; + clock-names = "cpu"; + }; + }; + cpuintc: interrupt-controller { #address-cells = <0>; #interrupt-cells = <1>; diff --git a/arch/mips/boot/dts/ingenic/x1000.dtsi b/arch/mips/boot/dts/ingenic/x1000.dtsi index 9de9e7c2d523..1f1f896dd1f7 100644 --- a/arch/mips/boot/dts/ingenic/x1000.dtsi +++ b/arch/mips/boot/dts/ingenic/x1000.dtsi @@ -8,6 +8,20 @@ #size-cells = <1>; compatible = "ingenic,x1000", "ingenic,x1000e"; + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu0: cpu@0 { + device_type = "cpu"; + compatible = "ingenic,xburst-fpu1.0-mxu1.1"; + reg = <0>; + + clocks = <&cgu X1000_CLK_CPU>; + clock-names = "cpu"; + }; + }; + cpuintc: interrupt-controller { #address-cells = <0>; #interrupt-cells = <1>; diff --git a/arch/mips/boot/dts/ingenic/x1830.dtsi b/arch/mips/boot/dts/ingenic/x1830.dtsi index eb1214481a33..b05dac3ae308 100644 --- a/arch/mips/boot/dts/ingenic/x1830.dtsi +++ b/arch/mips/boot/dts/ingenic/x1830.dtsi @@ -8,6 +8,20 @@ #size-cells = <1>; compatible = "ingenic,x1830"; + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu0: cpu@0 { + device_type = "cpu"; + compatible = "ingenic,xburst-fpu2.0-mxu2.0"; + reg = <0>; + + clocks = <&cgu X1830_CLK_CPU>; + clock-names = "cpu"; + }; + }; + cpuintc: interrupt-controller { #address-cells = <0>; #interrupt-cells = <1>; From 5fa1f7680f2728d62561db6d4a9282c4d21f2324 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Thu, 17 Sep 2020 20:39:01 +0800 Subject: [PATCH 268/645] MIPS: Loongson64: Add UART node for LS7A PCH When I update the latest kernel on the Loongson platform used with LS7A bridge chip, the serial console has no output, this is because the machine uses LS7A UART0 instead of CPU UART0, add UART node for LS7A PCH to enhance the compatibility. Signed-off-by: Tiezhu Yang Signed-off-by: Thomas Bogendoerfer --- arch/mips/boot/dts/loongson/ls7a-pch.dtsi | 39 +++++++++++++++++++++++ 1 file changed, 39 insertions(+) diff --git a/arch/mips/boot/dts/loongson/ls7a-pch.dtsi b/arch/mips/boot/dts/loongson/ls7a-pch.dtsi index e574a062dfae..f99a7a11fded 100644 --- a/arch/mips/boot/dts/loongson/ls7a-pch.dtsi +++ b/arch/mips/boot/dts/loongson/ls7a-pch.dtsi @@ -19,6 +19,45 @@ #interrupt-cells = <2>; }; + ls7a_uart0: serial@10080000 { + compatible = "ns16550a"; + reg = <0 0x10080000 0 0x100>; + clock-frequency = <50000000>; + interrupt-parent = <&pic>; + interrupts = <8 IRQ_TYPE_LEVEL_HIGH>; + no-loopback-test; + }; + + ls7a_uart1: serial@10080100 { + status = "disabled"; + compatible = "ns16550a"; + reg = <0 0x10080100 0 0x100>; + clock-frequency = <50000000>; + interrupt-parent = <&pic>; + interrupts = <8 IRQ_TYPE_LEVEL_HIGH>; + no-loopback-test; + }; + + ls7a_uart2: serial@10080200 { + status = "disabled"; + compatible = "ns16550a"; + reg = <0 0x10080200 0 0x100>; + clock-frequency = <50000000>; + interrupt-parent = <&pic>; + interrupts = <8 IRQ_TYPE_LEVEL_HIGH>; + no-loopback-test; + }; + + ls7a_uart3: serial@10080300 { + status = "disabled"; + compatible = "ns16550a"; + reg = <0 0x10080300 0 0x100>; + clock-frequency = <50000000>; + interrupt-parent = <&pic>; + interrupts = <8 IRQ_TYPE_LEVEL_HIGH>; + no-loopback-test; + }; + pci@1a000000 { compatible = "loongson,ls7a-pci"; device_type = "pci"; From 262623961478836b0f467f9bbb9a3dd2a0c8a9be Mon Sep 17 00:00:00 2001 From: Youling Tang Date: Sat, 19 Sep 2020 09:55:46 +0800 Subject: [PATCH 269/645] MIPS: kexec: Add crashkernel=YM handling When the kernel crashkernel parameter is specified with just a size, we are supposed to allocate a region from RAM to store the crashkernel. However, MIPS merely reserves physical address zero with no checking that there is even RAM there. Fix this by lifting similar code from x86, importing it to MIPS with the MIPS specific parameters added. In the absence of any platform specific information, we allocate the crashkernel region from the first 512MB of physical memory (limited to CKSEG0 or KSEG0 address range). When X is not specified, crash_base defaults to 0 (crashkernel=YM@XM). E.g. without this patch: The environment as follows: [ 0.000000] MIPS: machine is loongson,loongson64c-4core-ls7a ... [ 0.000000] Kernel command line: root=/dev/sda2 crashkernel=96M ... The warning as follows: [ 0.000000] Invalid memory region reserved for crash kernel And the iomem as follows: 00200000-0effffff : System RAM 00200000-00b47f87 : Kernel code 00b47f88-00dfffff : Kernel data 00e60000-01f73c7f : Kernel bss 1a000000-1bffffff : pci@1a000000 ... With this patch: After increasing crash_base <= 0 handling. And the iomem as follows: 00200000-0effffff : System RAM 00200000-00b47f87 : Kernel code 00b47f88-00dfffff : Kernel data 00e60000-01f73c7f : Kernel bss 04000000-09ffffff : Crash kernel 1a000000-1bffffff : pci@1a000000 ... Signed-off-by: Youling Tang Signed-off-by: Thomas Bogendoerfer --- arch/mips/kernel/setup.c | 24 +++++++++++++++++++++--- 1 file changed, 21 insertions(+), 3 deletions(-) diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 8589a34c28de..4c04a86f075b 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -477,6 +477,11 @@ early_param("elfcorehdr", early_parse_elfcorehdr); #endif #ifdef CONFIG_KEXEC + +/* 64M alignment for crash kernel regions */ +#define CRASH_ALIGN SZ_64M +#define CRASH_ADDR_MAX SZ_512M + static void __init mips_parse_crashkernel(void) { unsigned long long total_mem; @@ -489,9 +494,22 @@ static void __init mips_parse_crashkernel(void) if (ret != 0 || crash_size <= 0) return; - if (!memblock_find_in_range(crash_base, crash_base + crash_size, crash_size, 1)) { - pr_warn("Invalid memory region reserved for crash kernel\n"); - return; + if (crash_base <= 0) { + crash_base = memblock_find_in_range(CRASH_ALIGN, CRASH_ADDR_MAX, + crash_size, CRASH_ALIGN); + if (!crash_base) { + pr_warn("crashkernel reservation failed - No suitable area found.\n"); + return; + } + } else { + unsigned long long start; + + start = memblock_find_in_range(crash_base, crash_base + crash_size, + crash_size, 1); + if (start != crash_base) { + pr_warn("Invalid memory region reserved for crash kernel\n"); + return; + } } crashk_res.start = crash_base; From 063a9966ee1555db2375fa21339199578974b725 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Wed, 23 Sep 2020 09:26:44 +0200 Subject: [PATCH 270/645] Revert "MIPS: OCTEON: use devm_platform_ioremap_resource" This reverts commit 0ee69c589ec8659560910815f32c13af8587a779. Resource is still needed later in the code, so using devm_platform_ioremap_resource is no win at all. Signed-off-by: Thomas Bogendoerfer --- arch/mips/cavium-octeon/octeon-usb.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/arch/mips/cavium-octeon/octeon-usb.c b/arch/mips/cavium-octeon/octeon-usb.c index 97f6dc31e1b4..950e6c6e8629 100644 --- a/arch/mips/cavium-octeon/octeon-usb.c +++ b/arch/mips/cavium-octeon/octeon-usb.c @@ -498,6 +498,7 @@ static int __init dwc3_octeon_device_init(void) const char compat_node_name[] = "cavium,octeon-7130-usb-uctl"; struct platform_device *pdev; struct device_node *node; + struct resource *res; void __iomem *base; /* @@ -515,13 +516,20 @@ static int __init dwc3_octeon_device_init(void) if (!pdev) return -ENODEV; + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (res == NULL) { + put_device(&pdev->dev); + dev_err(&pdev->dev, "No memory resources\n"); + return -ENXIO; + } + /* * The code below maps in the registers necessary for * setting up the clocks and reseting PHYs. We must * release the resources so the dwc3 subsystem doesn't * know the difference. */ - base = devm_platform_ioremap_resource(pdev, 0); + base = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(base)) { put_device(&pdev->dev); return PTR_ERR(base); From 32ca04bba6fd9775a0630534f3db52e27b062e6c Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Fri, 4 Sep 2020 16:11:37 +0200 Subject: [PATCH 271/645] s390/zcrypt: Support for CCA APKA master keys Support for CCA APKA (used for CCA ECC keys) master keys. The existing mkvps sysfs attribute for each queue for cards in CCA mode is extended to show the APKA master key register states and verification pattern: Improve the mkvps sysfs attribute to display the APKA master key verification patterns for old, current and new master key registers. The APKA master key is used to encrypt CCA ECC secure keys. The syntax is analog to the existing AES mk verification patterns: APKA NEW: APKA CUR: APKA OLD: with : 'empty' or 'partial' or 'full' : 'valid' or 'invalid' : 'valid' or 'invalid' , , 8 byte hex string with leading 0x MKVP means Master Key Verification Pattern and is a folded hash over the key value. Only the states 'full' and 'valid' result in displaying a useful mkvp, otherwise a mkvp of all bytes zero is shown. If for any reason the FQ fails and the (cached) information is not available, the state '-' will be shown with the mkvp value also '-'. The values shown here are the very same as the cca panel tools displays. The internal function cca_findcard2() also supports to match against the APKA master key verification patterns and the pkey kernel module which uses this function needed compatible rewrite of these invocations. Signed-off-by: Harald Freudenberger Signed-off-by: Vasily Gorbik --- drivers/s390/crypto/pkey_api.c | 18 +++--- drivers/s390/crypto/zcrypt_ccamisc.c | 85 ++++++++++++++++++---------- drivers/s390/crypto/zcrypt_ccamisc.h | 30 +++++++--- drivers/s390/crypto/zcrypt_cex2c.c | 39 +++++++++++-- drivers/s390/crypto/zcrypt_cex4.c | 39 +++++++++++-- 5 files changed, 154 insertions(+), 57 deletions(-) diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c index 5896e5282a4e..e48c13acc5da 100644 --- a/drivers/s390/crypto/pkey_api.c +++ b/drivers/s390/crypto/pkey_api.c @@ -661,13 +661,14 @@ static int pkey_verifykey2(const u8 *key, size_t keylen, *ksize = (enum pkey_key_size) t->bitsize; rc = cca_findcard2(&_apqns, &_nr_apqns, *cardnr, *domain, - ZCRYPT_CEX3C, t->mkvp, 0, 1); + ZCRYPT_CEX3C, AES_MK_SET, t->mkvp, 0, 1); if (rc == 0 && flags) *flags = PKEY_FLAGS_MATCH_CUR_MKVP; if (rc == -ENODEV) { rc = cca_findcard2(&_apqns, &_nr_apqns, *cardnr, *domain, - ZCRYPT_CEX3C, 0, t->mkvp, 1); + ZCRYPT_CEX3C, AES_MK_SET, + 0, t->mkvp, 1); if (rc == 0 && flags) *flags = PKEY_FLAGS_MATCH_ALT_MKVP; } @@ -697,13 +698,14 @@ static int pkey_verifykey2(const u8 *key, size_t keylen, } rc = cca_findcard2(&_apqns, &_nr_apqns, *cardnr, *domain, - ZCRYPT_CEX6, t->mkvp0, 0, 1); + ZCRYPT_CEX6, AES_MK_SET, t->mkvp0, 0, 1); if (rc == 0 && flags) *flags = PKEY_FLAGS_MATCH_CUR_MKVP; if (rc == -ENODEV) { rc = cca_findcard2(&_apqns, &_nr_apqns, *cardnr, *domain, - ZCRYPT_CEX6, 0, t->mkvp0, 1); + ZCRYPT_CEX6, AES_MK_SET, + 0, t->mkvp0, 1); if (rc == 0 && flags) *flags = PKEY_FLAGS_MATCH_ALT_MKVP; } @@ -863,7 +865,8 @@ static int pkey_apqns4key(const u8 *key, size_t keylen, u32 flags, return -EINVAL; } rc = cca_findcard2(&_apqns, &_nr_apqns, 0xFFFF, 0xFFFF, - minhwtype, cur_mkvp, old_mkvp, 1); + minhwtype, AES_MK_SET, + cur_mkvp, old_mkvp, 1); if (rc) goto out; } else @@ -900,7 +903,8 @@ static int pkey_apqns4keytype(enum pkey_key_type ktype, if (ktype == PKEY_TYPE_CCA_CIPHER) minhwtype = ZCRYPT_CEX6; rc = cca_findcard2(&_apqns, &_nr_apqns, 0xFFFF, 0xFFFF, - minhwtype, cur_mkvp, old_mkvp, 1); + minhwtype, AES_MK_SET, + cur_mkvp, old_mkvp, 1); if (rc) goto out; } else if (ktype == PKEY_TYPE_EP11) { @@ -1589,7 +1593,7 @@ static ssize_t pkey_ccacipher_aes_attr_read(enum pkey_key_size keybits, /* build a list of apqns able to generate an cipher key */ rc = cca_findcard2(&apqns, &nr_apqns, 0xFFFF, 0xFFFF, - ZCRYPT_CEX6, 0, 0, 0); + ZCRYPT_CEX6, 0, 0, 0, 0); if (rc) return rc; diff --git a/drivers/s390/crypto/zcrypt_ccamisc.c b/drivers/s390/crypto/zcrypt_ccamisc.c index 40b59a77ec0c..e969188a1ec4 100644 --- a/drivers/s390/crypto/zcrypt_ccamisc.c +++ b/drivers/s390/crypto/zcrypt_ccamisc.c @@ -1506,21 +1506,38 @@ static int fetch_cca_info(u16 cardnr, u16 domain, struct cca_info *ci) rarray, &rlen, varray, &vlen); if (rc == 0 && rlen >= 10*8 && vlen >= 204) { memcpy(ci->serial, rarray, 8); - ci->new_mk_state = (char) rarray[7*8]; - ci->cur_mk_state = (char) rarray[8*8]; - ci->old_mk_state = (char) rarray[9*8]; - if (ci->old_mk_state == '2') - memcpy(&ci->old_mkvp, varray + 172, 8); - if (ci->cur_mk_state == '2') - memcpy(&ci->cur_mkvp, varray + 184, 8); - if (ci->new_mk_state == '3') - memcpy(&ci->new_mkvp, varray + 196, 8); - found = 1; + ci->new_aes_mk_state = (char) rarray[7*8]; + ci->cur_aes_mk_state = (char) rarray[8*8]; + ci->old_aes_mk_state = (char) rarray[9*8]; + if (ci->old_aes_mk_state == '2') + memcpy(&ci->old_aes_mkvp, varray + 172, 8); + if (ci->cur_aes_mk_state == '2') + memcpy(&ci->cur_aes_mkvp, varray + 184, 8); + if (ci->new_aes_mk_state == '3') + memcpy(&ci->new_aes_mkvp, varray + 196, 8); + found++; + } + if (!found) + goto out; + rlen = vlen = PAGE_SIZE/2; + rc = cca_query_crypto_facility(cardnr, domain, "STATICSB", + rarray, &rlen, varray, &vlen); + if (rc == 0 && rlen >= 10*8 && vlen >= 240) { + ci->new_apka_mk_state = (char) rarray[7*8]; + ci->cur_apka_mk_state = (char) rarray[8*8]; + ci->old_apka_mk_state = (char) rarray[9*8]; + if (ci->old_apka_mk_state == '2') + memcpy(&ci->old_apka_mkvp, varray + 208, 8); + if (ci->cur_apka_mk_state == '2') + memcpy(&ci->cur_apka_mkvp, varray + 220, 8); + if (ci->new_apka_mk_state == '3') + memcpy(&ci->new_apka_mkvp, varray + 232, 8); + found++; } +out: free_page((unsigned long) pg); - - return found ? 0 : -ENOENT; + return found == 2 ? 0 : -ENOENT; } /* @@ -1574,16 +1591,16 @@ static int findcard(u64 mkvp, u16 *pcardnr, u16 *pdomain, /* enabled CCA card, check current mkvp from cache */ if (cca_info_cache_fetch(card, dom, &ci) == 0 && ci.hwtype >= minhwtype && - ci.cur_mk_state == '2' && - ci.cur_mkvp == mkvp) { + ci.cur_aes_mk_state == '2' && + ci.cur_aes_mkvp == mkvp) { if (!verify) break; /* verify: refresh card info */ if (fetch_cca_info(card, dom, &ci) == 0) { cca_info_cache_update(card, dom, &ci); if (ci.hwtype >= minhwtype && - ci.cur_mk_state == '2' && - ci.cur_mkvp == mkvp) + ci.cur_aes_mk_state == '2' && + ci.cur_aes_mkvp == mkvp) break; } } @@ -1605,12 +1622,12 @@ static int findcard(u64 mkvp, u16 *pcardnr, u16 *pdomain, if (fetch_cca_info(card, dom, &ci) == 0) { cca_info_cache_update(card, dom, &ci); if (ci.hwtype >= minhwtype && - ci.cur_mk_state == '2' && - ci.cur_mkvp == mkvp) + ci.cur_aes_mk_state == '2' && + ci.cur_aes_mkvp == mkvp) break; if (ci.hwtype >= minhwtype && - ci.old_mk_state == '2' && - ci.old_mkvp == mkvp && + ci.old_aes_mk_state == '2' && + ci.old_aes_mkvp == mkvp && oi < 0) oi = i; } @@ -1664,7 +1681,8 @@ int cca_findcard(const u8 *key, u16 *pcardnr, u16 *pdomain, int verify) EXPORT_SYMBOL(cca_findcard); int cca_findcard2(u32 **apqns, u32 *nr_apqns, u16 cardnr, u16 domain, - int minhwtype, u64 cur_mkvp, u64 old_mkvp, int verify) + int minhwtype, int mktype, u64 cur_mkvp, u64 old_mkvp, + int verify) { struct zcrypt_device_status_ext *device_status; u32 *_apqns = NULL, _nr_apqns = 0; @@ -1706,7 +1724,9 @@ int cca_findcard2(u32 **apqns, u32 *nr_apqns, u16 cardnr, u16 domain, if (cca_get_info(card, dom, &ci, verify)) continue; /* current master key needs to be valid */ - if (ci.cur_mk_state != '2') + if (mktype == AES_MK_SET && ci.cur_aes_mk_state != '2') + continue; + if (mktype == APKA_MK_SET && ci.cur_apka_mk_state != '2') continue; /* check min hardware type */ if (minhwtype > 0 && minhwtype > ci.hwtype) @@ -1714,13 +1734,20 @@ int cca_findcard2(u32 **apqns, u32 *nr_apqns, u16 cardnr, u16 domain, if (cur_mkvp || old_mkvp) { /* check mkvps */ curmatch = oldmatch = 0; - if (cur_mkvp && cur_mkvp == ci.cur_mkvp) - curmatch = 1; - if (old_mkvp && ci.old_mk_state == '2' && - old_mkvp == ci.old_mkvp) - oldmatch = 1; - if ((cur_mkvp || old_mkvp) && - (curmatch + oldmatch < 1)) + if (mktype == AES_MK_SET) { + if (cur_mkvp && cur_mkvp == ci.cur_aes_mkvp) + curmatch = 1; + if (old_mkvp && ci.old_aes_mk_state == '2' && + old_mkvp == ci.old_aes_mkvp) + oldmatch = 1; + } else { + if (cur_mkvp && cur_mkvp == ci.cur_apka_mkvp) + curmatch = 1; + if (old_mkvp && ci.old_apka_mk_state == '2' && + old_mkvp == ci.old_apka_mkvp) + oldmatch = 1; + } + if (curmatch + oldmatch < 1) continue; } /* apqn passed all filtering criterons, add to the array */ diff --git a/drivers/s390/crypto/zcrypt_ccamisc.h b/drivers/s390/crypto/zcrypt_ccamisc.h index 8b7a641671c9..4d88a1d6af21 100644 --- a/drivers/s390/crypto/zcrypt_ccamisc.h +++ b/drivers/s390/crypto/zcrypt_ccamisc.h @@ -186,6 +186,8 @@ int cca_findcard(const u8 *key, u16 *pcardnr, u16 *pdomain, int verify); * - if verify is enabled and a cur_mkvp and/or old_mkvp * value is given, then refetch the cca_info and make sure the current * cur_mkvp or old_mkvp values of the apqn are used. + * The mktype determines which set of master keys to use: + * 0 = AES_MK_SET - AES MK set, 1 = APKA MK_SET - APKA MK set * The array of apqn entries is allocated with kmalloc and returned in *apqns; * the number of apqns stored into the list is returned in *nr_apqns. One apqn * entry is simple a 32 bit value with 16 bit cardnr and 16 bit domain nr and @@ -194,18 +196,28 @@ int cca_findcard(const u8 *key, u16 *pcardnr, u16 *pdomain, int verify); * -ENODEV is returned. */ int cca_findcard2(u32 **apqns, u32 *nr_apqns, u16 cardnr, u16 domain, - int minhwtype, u64 cur_mkvp, u64 old_mkvp, int verify); + int minhwtype, int mktype, u64 cur_mkvp, u64 old_mkvp, + int verify); + +#define AES_MK_SET 0 +#define APKA_MK_SET 1 /* struct to hold info for each CCA queue */ struct cca_info { - int hwtype; /* one of the defined AP_DEVICE_TYPE_* */ - char new_mk_state; /* '1' empty, '2' partially full, '3' full */ - char cur_mk_state; /* '1' invalid, '2' valid */ - char old_mk_state; /* '1' invalid, '2' valid */ - u64 new_mkvp; /* truncated sha256 hash of new master key */ - u64 cur_mkvp; /* truncated sha256 hash of current master key */ - u64 old_mkvp; /* truncated sha256 hash of old master key */ - char serial[9]; /* serial number string (8 ascii numbers + 0x00) */ + int hwtype; /* one of the defined AP_DEVICE_TYPE_* */ + char new_aes_mk_state; /* '1' empty, '2' partially full, '3' full */ + char cur_aes_mk_state; /* '1' invalid, '2' valid */ + char old_aes_mk_state; /* '1' invalid, '2' valid */ + char new_apka_mk_state; /* '1' empty, '2' partially full, '3' full */ + char cur_apka_mk_state; /* '1' invalid, '2' valid */ + char old_apka_mk_state; /* '1' invalid, '2' valid */ + u64 new_aes_mkvp; /* truncated sha256 of new aes master key */ + u64 cur_aes_mkvp; /* truncated sha256 of current aes master key */ + u64 old_aes_mkvp; /* truncated sha256 of old aes master key */ + u64 new_apka_mkvp; /* truncated sha256 of new apka master key */ + u64 cur_apka_mkvp; /* truncated sha256 of current apka mk */ + u64 old_apka_mkvp; /* truncated sha256 of old apka mk */ + char serial[9]; /* serial number (8 ascii numbers + 0x00) */ }; /* diff --git a/drivers/s390/crypto/zcrypt_cex2c.c b/drivers/s390/crypto/zcrypt_cex2c.c index f00127a78bab..146eb9f24694 100644 --- a/drivers/s390/crypto/zcrypt_cex2c.c +++ b/drivers/s390/crypto/zcrypt_cex2c.c @@ -109,26 +109,53 @@ static ssize_t cca_mkvps_show(struct device *dev, AP_QID_QUEUE(zq->queue->qid), &ci, zq->online); - if (ci.new_mk_state >= '1' && ci.new_mk_state <= '3') + if (ci.new_aes_mk_state >= '1' && ci.new_aes_mk_state <= '3') n = scnprintf(buf, PAGE_SIZE, "AES NEW: %s 0x%016llx\n", - new_state[ci.new_mk_state - '1'], ci.new_mkvp); + new_state[ci.new_aes_mk_state - '1'], + ci.new_aes_mkvp); else n = scnprintf(buf, PAGE_SIZE, "AES NEW: - -\n"); - if (ci.cur_mk_state >= '1' && ci.cur_mk_state <= '2') + if (ci.cur_aes_mk_state >= '1' && ci.cur_aes_mk_state <= '2') n += scnprintf(buf + n, PAGE_SIZE - n, "AES CUR: %s 0x%016llx\n", - cao_state[ci.cur_mk_state - '1'], ci.cur_mkvp); + cao_state[ci.cur_aes_mk_state - '1'], + ci.cur_aes_mkvp); else n += scnprintf(buf + n, PAGE_SIZE - n, "AES CUR: - -\n"); - if (ci.old_mk_state >= '1' && ci.old_mk_state <= '2') + if (ci.old_aes_mk_state >= '1' && ci.old_aes_mk_state <= '2') n += scnprintf(buf + n, PAGE_SIZE - n, "AES OLD: %s 0x%016llx\n", - cao_state[ci.old_mk_state - '1'], ci.old_mkvp); + cao_state[ci.old_aes_mk_state - '1'], + ci.old_aes_mkvp); else n += scnprintf(buf + n, PAGE_SIZE - n, "AES OLD: - -\n"); + if (ci.new_apka_mk_state >= '1' && ci.new_apka_mk_state <= '3') + n += scnprintf(buf + n, PAGE_SIZE - n, + "APKA NEW: %s 0x%016llx\n", + new_state[ci.new_apka_mk_state - '1'], + ci.new_apka_mkvp); + else + n += scnprintf(buf + n, PAGE_SIZE - n, "APKA NEW: - -\n"); + + if (ci.cur_apka_mk_state >= '1' && ci.cur_apka_mk_state <= '2') + n += scnprintf(buf + n, PAGE_SIZE - n, + "APKA CUR: %s 0x%016llx\n", + cao_state[ci.cur_apka_mk_state - '1'], + ci.cur_apka_mkvp); + else + n += scnprintf(buf + n, PAGE_SIZE - n, "APKA CUR: - -\n"); + + if (ci.old_apka_mk_state >= '1' && ci.old_apka_mk_state <= '2') + n += scnprintf(buf + n, PAGE_SIZE - n, + "APKA OLD: %s 0x%016llx\n", + cao_state[ci.old_apka_mk_state - '1'], + ci.old_apka_mkvp); + else + n += scnprintf(buf + n, PAGE_SIZE - n, "APKA OLD: - -\n"); + return n; } diff --git a/drivers/s390/crypto/zcrypt_cex4.c b/drivers/s390/crypto/zcrypt_cex4.c index dc20d983e468..d9ebe3a3c210 100644 --- a/drivers/s390/crypto/zcrypt_cex4.c +++ b/drivers/s390/crypto/zcrypt_cex4.c @@ -121,26 +121,53 @@ static ssize_t cca_mkvps_show(struct device *dev, AP_QID_QUEUE(zq->queue->qid), &ci, zq->online); - if (ci.new_mk_state >= '1' && ci.new_mk_state <= '3') + if (ci.new_aes_mk_state >= '1' && ci.new_aes_mk_state <= '3') n = scnprintf(buf, PAGE_SIZE, "AES NEW: %s 0x%016llx\n", - new_state[ci.new_mk_state - '1'], ci.new_mkvp); + new_state[ci.new_aes_mk_state - '1'], + ci.new_aes_mkvp); else n = scnprintf(buf, PAGE_SIZE, "AES NEW: - -\n"); - if (ci.cur_mk_state >= '1' && ci.cur_mk_state <= '2') + if (ci.cur_aes_mk_state >= '1' && ci.cur_aes_mk_state <= '2') n += scnprintf(buf + n, PAGE_SIZE - n, "AES CUR: %s 0x%016llx\n", - cao_state[ci.cur_mk_state - '1'], ci.cur_mkvp); + cao_state[ci.cur_aes_mk_state - '1'], + ci.cur_aes_mkvp); else n += scnprintf(buf + n, PAGE_SIZE - n, "AES CUR: - -\n"); - if (ci.old_mk_state >= '1' && ci.old_mk_state <= '2') + if (ci.old_aes_mk_state >= '1' && ci.old_aes_mk_state <= '2') n += scnprintf(buf + n, PAGE_SIZE - n, "AES OLD: %s 0x%016llx\n", - cao_state[ci.old_mk_state - '1'], ci.old_mkvp); + cao_state[ci.old_aes_mk_state - '1'], + ci.old_aes_mkvp); else n += scnprintf(buf + n, PAGE_SIZE - n, "AES OLD: - -\n"); + if (ci.new_apka_mk_state >= '1' && ci.new_apka_mk_state <= '3') + n += scnprintf(buf + n, PAGE_SIZE - n, + "APKA NEW: %s 0x%016llx\n", + new_state[ci.new_apka_mk_state - '1'], + ci.new_apka_mkvp); + else + n += scnprintf(buf + n, PAGE_SIZE - n, "APKA NEW: - -\n"); + + if (ci.cur_apka_mk_state >= '1' && ci.cur_apka_mk_state <= '2') + n += scnprintf(buf + n, PAGE_SIZE - n, + "APKA CUR: %s 0x%016llx\n", + cao_state[ci.cur_apka_mk_state - '1'], + ci.cur_apka_mkvp); + else + n += scnprintf(buf + n, PAGE_SIZE - n, "APKA CUR: - -\n"); + + if (ci.old_apka_mk_state >= '1' && ci.old_apka_mk_state <= '2') + n += scnprintf(buf + n, PAGE_SIZE - n, + "APKA OLD: %s 0x%016llx\n", + cao_state[ci.old_apka_mk_state - '1'], + ci.old_apka_mkvp); + else + n += scnprintf(buf + n, PAGE_SIZE - n, "APKA OLD: - -\n"); + return n; } From fa6999e326fe7851ecbd572b8cb9be8e930ebf41 Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Mon, 21 Sep 2020 10:45:55 +0200 Subject: [PATCH 272/645] s390/pkey: support CCA and EP11 secure ECC private keys This patch extends the pkey kernel module to support CCA and EP11 secure ECC (private) keys as source for deriving ECC protected (private) keys. There is yet another new ioctl to support this: PKEY_KBLOB2PROTK3 can handle all the old keys plus CCA and EP11 secure ECC keys. For details see ioctl description in pkey.h. The CPACF unit currently only supports a subset of 5 different ECC curves (P-256, P-384, P-521, ED25519, ED448) and so only keys of this curve type can be transformed into protected keys. However, the pkey and the cca/ep11 low level functions do not check this but simple pass-through the key blob to the firmware onto the crypto cards. So most likely the failure will be a response carrying an error code resulting in user space errno value EIO instead of EINVAL. Deriving a protected key from an EP11 ECC secure key requires a CEX7 in EP11 mode. Deriving a protected key from an CCA ECC secure key requires a CEX7 in CCA mode. Together with this new ioctl the ioctls for querying lists of apqns (PKEY_APQNS4K and PKEY_APQNS4KT) have been extended to support EP11 and CCA ECC secure key type and key blobs. Together with this ioctl there comes a new struct ep11kblob_header which is to be prepended onto the EP11 key blob. See details in pkey.h for the fields in there. The older EP11 AES key blob with some info stored in the (unused) session field is also supported with this new ioctl. Signed-off-by: Harald Freudenberger Reviewed-by: Ingo Franzki Signed-off-by: Vasily Gorbik --- arch/s390/include/uapi/asm/pkey.h | 77 +++++-- drivers/s390/crypto/pkey_api.c | 244 +++++++++++++++++++-- drivers/s390/crypto/zcrypt_ccamisc.c | 193 +++++++++++++++++ drivers/s390/crypto/zcrypt_ccamisc.h | 44 +++- drivers/s390/crypto/zcrypt_ep11misc.c | 298 +++++++++++++++++++++----- drivers/s390/crypto/zcrypt_ep11misc.h | 63 ++++-- 6 files changed, 821 insertions(+), 98 deletions(-) diff --git a/arch/s390/include/uapi/asm/pkey.h b/arch/s390/include/uapi/asm/pkey.h index d27d7d329263..7349e96d28a0 100644 --- a/arch/s390/include/uapi/asm/pkey.h +++ b/arch/s390/include/uapi/asm/pkey.h @@ -35,12 +35,16 @@ #define PKEY_KEYTYPE_AES_128 1 #define PKEY_KEYTYPE_AES_192 2 #define PKEY_KEYTYPE_AES_256 3 +#define PKEY_KEYTYPE_ECC 4 /* the newer ioctls use a pkey_key_type enum for type information */ enum pkey_key_type { PKEY_TYPE_CCA_DATA = (__u32) 1, PKEY_TYPE_CCA_CIPHER = (__u32) 2, PKEY_TYPE_EP11 = (__u32) 3, + PKEY_TYPE_CCA_ECC = (__u32) 0x1f, + PKEY_TYPE_EP11_AES = (__u32) 6, + PKEY_TYPE_EP11_ECC = (__u32) 7, }; /* the newer ioctls use a pkey_key_size enum for key size information */ @@ -88,6 +92,20 @@ struct pkey_clrkey { __u8 clrkey[MAXCLRKEYSIZE]; /* 16, 24, or 32 byte clear key value */ }; +/* + * EP11 key blobs of type PKEY_TYPE_EP11_AES and PKEY_TYPE_EP11_ECC + * are ep11 blobs prepended by this header: + */ +struct ep11kblob_header { + __u8 type; /* always 0x00 */ + __u8 hver; /* header version, currently needs to be 0x00 */ + __u16 len; /* total length in bytes (including this header) */ + __u8 version; /* PKEY_TYPE_EP11_AES or PKEY_TYPE_EP11_ECC */ + __u8 res0; /* unused */ + __u16 bitlen; /* clear key bit len, 0 for unknown */ + __u8 res1[8]; /* unused */ +} __packed; + /* * Generate CCA AES secure key. */ @@ -304,7 +322,7 @@ struct pkey_verifykey2 { #define PKEY_VERIFYKEY2 _IOWR(PKEY_IOCTL_MAGIC, 0x17, struct pkey_verifykey2) /* - * Transform a key blob (of any type) into a protected key, version 2. + * Transform a key blob into a protected key, version 2. * There needs to be a list of apqns given with at least one entry in there. * All apqns in the list need to be exact apqns, 0xFFFF as ANY card or domain * is not supported. The implementation walks through the list of apqns and @@ -313,6 +331,8 @@ struct pkey_verifykey2 { * list is tried until success (return 0) or the end of the list is reached * (return -1 with errno ENODEV). You may use the PKEY_APQNS4K ioctl to * generate a list of apqns based on the key. + * Deriving ECC protected keys from ECC secure keys is not supported with + * this ioctl, use PKEY_KBLOB2PROTK3 for this purpose. */ struct pkey_kblob2pkey2 { __u8 __user *key; /* in: pointer to key blob */ @@ -326,17 +346,17 @@ struct pkey_kblob2pkey2 { /* * Build a list of APQNs based on a key blob given. * Is able to find out which type of secure key is given (CCA AES secure - * key, CCA AES cipher key or EP11 AES key) and tries to find all matching - * crypto cards based on the MKVP and maybe other criterias (like CCA AES - * cipher keys need a CEX5C or higher, EP11 keys with BLOB_PKEY_EXTRACTABLE - * need a CEX7 and EP11 api version 4). The list of APQNs is further filtered - * by the key's mkvp which needs to match to either the current mkvp (CCA and - * EP11) or the alternate mkvp (old mkvp, CCA adapters only) of the apqns. The - * flags argument may be used to limit the matching apqns. If the - * PKEY_FLAGS_MATCH_CUR_MKVP is given, only the current mkvp of each apqn is - * compared. Likewise with the PKEY_FLAGS_MATCH_ALT_MKVP. If both are given, it - * is assumed to return apqns where either the current or the alternate mkvp - * matches. At least one of the matching flags needs to be given. + * key, CCA AES cipher key, CCA ECC private key, EP11 AES key, EP11 ECC private + * key) and tries to find all matching crypto cards based on the MKVP and maybe + * other criterias (like CCA AES cipher keys need a CEX5C or higher, EP11 keys + * with BLOB_PKEY_EXTRACTABLE need a CEX7 and EP11 api version 4). The list of + * APQNs is further filtered by the key's mkvp which needs to match to either + * the current mkvp (CCA and EP11) or the alternate mkvp (old mkvp, CCA adapters + * only) of the apqns. The flags argument may be used to limit the matching + * apqns. If the PKEY_FLAGS_MATCH_CUR_MKVP is given, only the current mkvp of + * each apqn is compared. Likewise with the PKEY_FLAGS_MATCH_ALT_MKVP. If both + * are given, it is assumed to return apqns where either the current or the + * alternate mkvp matches. At least one of the matching flags needs to be given. * The flags argument for EP11 keys has no further action and is currently * ignored (but needs to be given as PKEY_FLAGS_MATCH_CUR_MKVP) as there is only * the wkvp from the key to match against the apqn's wkvp. @@ -365,9 +385,10 @@ struct pkey_apqns4key { * restrict the list by given master key verification patterns. * For different key types there may be different ways to match the * master key verification patterns. For CCA keys (CCA data key and CCA - * cipher key) the first 8 bytes of cur_mkvp refer to the current mkvp value - * of the apqn and the first 8 bytes of the alt_mkvp refer to the old mkvp. - * The flags argument controls if the apqns current and/or alternate mkvp + * cipher key) the first 8 bytes of cur_mkvp refer to the current AES mkvp value + * of the apqn and the first 8 bytes of the alt_mkvp refer to the old AES mkvp. + * For CCA ECC keys it is similar but the match is against the APKA current/old + * mkvp. The flags argument controls if the apqns current and/or alternate mkvp * should match. If the PKEY_FLAGS_MATCH_CUR_MKVP is given, only the current * mkvp of each apqn is compared. Likewise with the PKEY_FLAGS_MATCH_ALT_MKVP. * If both are given, it is assumed to return apqns where either the @@ -397,4 +418,30 @@ struct pkey_apqns4keytype { }; #define PKEY_APQNS4KT _IOWR(PKEY_IOCTL_MAGIC, 0x1C, struct pkey_apqns4keytype) +/* + * Transform a key blob into a protected key, version 3. + * The difference to version 2 of this ioctl is that the protected key + * buffer is now explicitly and not within a struct pkey_protkey any more. + * So this ioctl is also able to handle EP11 and CCA ECC secure keys and + * provide ECC protected keys. + * There needs to be a list of apqns given with at least one entry in there. + * All apqns in the list need to be exact apqns, 0xFFFF as ANY card or domain + * is not supported. The implementation walks through the list of apqns and + * tries to send the request to each apqn without any further checking (like + * card type or online state). If the apqn fails, simple the next one in the + * list is tried until success (return 0) or the end of the list is reached + * (return -1 with errno ENODEV). You may use the PKEY_APQNS4K ioctl to + * generate a list of apqns based on the key. + */ +struct pkey_kblob2pkey3 { + __u8 __user *key; /* in: pointer to key blob */ + __u32 keylen; /* in: key blob size */ + struct pkey_apqn __user *apqns; /* in: ptr to list of apqn targets */ + __u32 apqn_entries; /* in: # of apqn target list entries */ + __u32 pkeytype; /* out: prot key type (enum pkey_key_type) */ + __u32 pkeylen; /* in/out: size of pkey buffer/actual len of pkey */ + __u8 __user *pkey; /* in: pkey blob buffer space ptr */ +}; +#define PKEY_KBLOB2PROTK3 _IOWR(PKEY_IOCTL_MAGIC, 0x1D, struct pkey_kblob2pkey3) + #endif /* _UAPI_PKEY_H */ diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c index e48c13acc5da..99cb60ea663d 100644 --- a/drivers/s390/crypto/pkey_api.c +++ b/drivers/s390/crypto/pkey_api.c @@ -31,8 +31,9 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("IBM Corporation"); MODULE_DESCRIPTION("s390 protected key interface"); -#define KEYBLOBBUFSIZE 8192 /* key buffer size used for internal processing */ -#define MAXAPQNSINLIST 64 /* max 64 apqns within a apqn list */ +#define KEYBLOBBUFSIZE 8192 /* key buffer size used for internal processing */ +#define PROTKEYBLOBBUFSIZE 256 /* protected key buffer size used internal */ +#define MAXAPQNSINLIST 64 /* max 64 apqns within a apqn list */ /* mask of available pckmo subfunctions, fetched once at module init */ static cpacf_mask_t pckmo_functions; @@ -237,8 +238,9 @@ static int pkey_ep11key2pkey(const u8 *key, struct pkey_protkey *pkey) for (rc = -ENODEV, i = 0; i < nr_apqns; i++) { card = apqns[i] >> 16; dom = apqns[i] & 0xFFFF; - rc = ep11_key2protkey(card, dom, key, kb->head.len, - pkey->protkey, &pkey->len, &pkey->type); + pkey->len = sizeof(pkey->protkey); + rc = ep11_kblob2protkey(card, dom, key, kb->head.len, + pkey->protkey, &pkey->len, &pkey->type); if (rc == 0) break; } @@ -449,15 +451,21 @@ static int pkey_nonccatok2pkey(const u8 *key, u32 keylen, break; } case TOKVER_EP11_AES: { - if (keylen < MINEP11AESKEYBLOBSIZE) - goto out; /* check ep11 key for exportable as protected key */ - rc = ep11_check_aeskeyblob(debug_info, 3, key, 0, 1); + rc = ep11_check_aes_key(debug_info, 3, key, keylen, 1); if (rc) goto out; rc = pkey_ep11key2pkey(key, protkey); break; } + case TOKVER_EP11_AES_WITH_HEADER: + /* check ep11 key with header for exportable as protected key */ + rc = ep11_check_aes_key_with_hdr(debug_info, 3, key, keylen, 1); + if (rc) + goto out; + rc = pkey_ep11key2pkey(key + sizeof(struct ep11kblob_header), + protkey); + break; default: DEBUG_ERR("%s unknown/unsupported non-CCA token version %d\n", __func__, hdr->version); @@ -719,7 +727,7 @@ static int pkey_verifykey2(const u8 *key, size_t keylen, && hdr->version == TOKVER_EP11_AES) { struct ep11keyblob *kb = (struct ep11keyblob *)key; - rc = ep11_check_aeskeyblob(debug_info, 3, key, 0, 1); + rc = ep11_check_aes_key(debug_info, 3, key, keylen, 1); if (rc) goto out; if (ktype) @@ -780,7 +788,7 @@ static int pkey_keyblob2pkey2(const struct pkey_apqn *apqns, size_t nr_apqns, if (hdr->version == TOKVER_EP11_AES) { if (keylen < sizeof(struct ep11keyblob)) return -EINVAL; - if (ep11_check_aeskeyblob(debug_info, 3, key, 0, 1)) + if (ep11_check_aes_key(debug_info, 3, key, keylen, 1)) return -EINVAL; } else { return pkey_nonccatok2pkey(key, keylen, pkey); @@ -806,9 +814,10 @@ static int pkey_keyblob2pkey2(const struct pkey_apqn *apqns, size_t nr_apqns, else { /* EP11 AES secure key blob */ struct ep11keyblob *kb = (struct ep11keyblob *) key; - rc = ep11_key2protkey(card, dom, key, kb->head.len, - pkey->protkey, &pkey->len, - &pkey->type); + pkey->len = sizeof(pkey->protkey); + rc = ep11_kblob2protkey(card, dom, key, kb->head.len, + pkey->protkey, &pkey->len, + &pkey->type); } if (rc == 0) break; @@ -827,7 +836,27 @@ static int pkey_apqns4key(const u8 *key, size_t keylen, u32 flags, if (keylen < sizeof(struct keytoken_header) || flags == 0) return -EINVAL; - if (hdr->type == TOKTYPE_NON_CCA && hdr->version == TOKVER_EP11_AES) { + if (hdr->type == TOKTYPE_NON_CCA + && (hdr->version == TOKVER_EP11_AES_WITH_HEADER + || hdr->version == TOKVER_EP11_ECC_WITH_HEADER) + && is_ep11_keyblob(key + sizeof(struct ep11kblob_header))) { + int minhwtype = 0, api = 0; + struct ep11keyblob *kb = (struct ep11keyblob *) + (key + sizeof(struct ep11kblob_header)); + + if (flags != PKEY_FLAGS_MATCH_CUR_MKVP) + return -EINVAL; + if (kb->attr & EP11_BLOB_PKEY_EXTRACTABLE) { + minhwtype = ZCRYPT_CEX7; + api = EP11_API_V; + } + rc = ep11_findcard2(&_apqns, &_nr_apqns, 0xFFFF, 0xFFFF, + minhwtype, api, kb->wkvp); + if (rc) + goto out; + } else if (hdr->type == TOKTYPE_NON_CCA + && hdr->version == TOKVER_EP11_AES + && is_ep11_keyblob(key)) { int minhwtype = 0, api = 0; struct ep11keyblob *kb = (struct ep11keyblob *) key; @@ -869,6 +898,24 @@ static int pkey_apqns4key(const u8 *key, size_t keylen, u32 flags, cur_mkvp, old_mkvp, 1); if (rc) goto out; + } else if (hdr->type == TOKTYPE_CCA_INTERNAL_PKA) { + u64 cur_mkvp = 0, old_mkvp = 0; + struct eccprivkeytoken *t = (struct eccprivkeytoken *)key; + + if (t->secid == 0x20) { + if (flags & PKEY_FLAGS_MATCH_CUR_MKVP) + cur_mkvp = t->mkvp; + if (flags & PKEY_FLAGS_MATCH_ALT_MKVP) + old_mkvp = t->mkvp; + } else { + /* unknown cca internal 2 token type */ + return -EINVAL; + } + rc = cca_findcard2(&_apqns, &_nr_apqns, 0xFFFF, 0xFFFF, + ZCRYPT_CEX7, APKA_MK_SET, + cur_mkvp, old_mkvp, 1); + if (rc) + goto out; } else return -EINVAL; @@ -907,7 +954,22 @@ static int pkey_apqns4keytype(enum pkey_key_type ktype, cur_mkvp, old_mkvp, 1); if (rc) goto out; - } else if (ktype == PKEY_TYPE_EP11) { + } else if (ktype == PKEY_TYPE_CCA_ECC) { + u64 cur_mkvp = 0, old_mkvp = 0; + + if (flags & PKEY_FLAGS_MATCH_CUR_MKVP) + cur_mkvp = *((u64 *) cur_mkvp); + if (flags & PKEY_FLAGS_MATCH_ALT_MKVP) + old_mkvp = *((u64 *) alt_mkvp); + rc = cca_findcard2(&_apqns, &_nr_apqns, 0xFFFF, 0xFFFF, + ZCRYPT_CEX7, APKA_MK_SET, + cur_mkvp, old_mkvp, 1); + if (rc) + goto out; + + } else if (ktype == PKEY_TYPE_EP11 || + ktype == PKEY_TYPE_EP11_AES || + ktype == PKEY_TYPE_EP11_ECC) { u8 *wkvp = NULL; if (flags & PKEY_FLAGS_MATCH_CUR_MKVP) @@ -933,6 +995,111 @@ out: return rc; } +static int pkey_keyblob2pkey3(const struct pkey_apqn *apqns, size_t nr_apqns, + const u8 *key, size_t keylen, u32 *protkeytype, + u8 *protkey, u32 *protkeylen) +{ + int i, card, dom, rc; + struct keytoken_header *hdr = (struct keytoken_header *)key; + + /* check for at least one apqn given */ + if (!apqns || !nr_apqns) + return -EINVAL; + + if (keylen < sizeof(struct keytoken_header)) + return -EINVAL; + + if (hdr->type == TOKTYPE_NON_CCA + && hdr->version == TOKVER_EP11_AES_WITH_HEADER + && is_ep11_keyblob(key + sizeof(struct ep11kblob_header))) { + /* EP11 AES key blob with header */ + if (ep11_check_aes_key_with_hdr(debug_info, 3, key, keylen, 1)) + return -EINVAL; + } else if (hdr->type == TOKTYPE_NON_CCA + && hdr->version == TOKVER_EP11_ECC_WITH_HEADER + && is_ep11_keyblob(key + sizeof(struct ep11kblob_header))) { + /* EP11 ECC key blob with header */ + if (ep11_check_ecc_key_with_hdr(debug_info, 3, key, keylen, 1)) + return -EINVAL; + } else if (hdr->type == TOKTYPE_NON_CCA + && hdr->version == TOKVER_EP11_AES + && is_ep11_keyblob(key)) { + /* EP11 AES key blob with header in session field */ + if (ep11_check_aes_key(debug_info, 3, key, keylen, 1)) + return -EINVAL; + } else if (hdr->type == TOKTYPE_CCA_INTERNAL) { + if (hdr->version == TOKVER_CCA_AES) { + /* CCA AES data key */ + if (keylen != sizeof(struct secaeskeytoken)) + return -EINVAL; + if (cca_check_secaeskeytoken(debug_info, 3, key, 0)) + return -EINVAL; + } else if (hdr->version == TOKVER_CCA_VLSC) { + /* CCA AES cipher key */ + if (keylen < hdr->len || keylen > MAXCCAVLSCTOKENSIZE) + return -EINVAL; + if (cca_check_secaescipherkey(debug_info, 3, key, 0, 1)) + return -EINVAL; + } else { + DEBUG_ERR("%s unknown CCA internal token version %d\n", + __func__, hdr->version); + return -EINVAL; + } + } else if (hdr->type == TOKTYPE_CCA_INTERNAL_PKA) { + /* CCA ECC (private) key */ + if (keylen < sizeof(struct eccprivkeytoken)) + return -EINVAL; + if (cca_check_sececckeytoken(debug_info, 3, key, keylen, 1)) + return -EINVAL; + } else if (hdr->type == TOKTYPE_NON_CCA) { + struct pkey_protkey pkey; + + rc = pkey_nonccatok2pkey(key, keylen, &pkey); + if (rc) + return rc; + memcpy(protkey, pkey.protkey, pkey.len); + *protkeylen = pkey.len; + *protkeytype = pkey.type; + return 0; + } else { + DEBUG_ERR("%s unknown/unsupported blob type %d\n", + __func__, hdr->type); + return -EINVAL; + } + + /* simple try all apqns from the list */ + for (rc = -ENODEV, i = 0; rc && i < nr_apqns; i++) { + card = apqns[i].card; + dom = apqns[i].domain; + if (hdr->type == TOKTYPE_NON_CCA + && (hdr->version == TOKVER_EP11_AES_WITH_HEADER + || hdr->version == TOKVER_EP11_ECC_WITH_HEADER) + && is_ep11_keyblob(key + sizeof(struct ep11kblob_header))) + rc = ep11_kblob2protkey(card, dom, key, hdr->len, + protkey, protkeylen, protkeytype); + else if (hdr->type == TOKTYPE_NON_CCA + && hdr->version == TOKVER_EP11_AES + && is_ep11_keyblob(key)) + rc = ep11_kblob2protkey(card, dom, key, hdr->len, + protkey, protkeylen, protkeytype); + else if (hdr->type == TOKTYPE_CCA_INTERNAL && + hdr->version == TOKVER_CCA_AES) + rc = cca_sec2protkey(card, dom, key, protkey, + protkeylen, protkeytype); + else if (hdr->type == TOKTYPE_CCA_INTERNAL && + hdr->version == TOKVER_CCA_VLSC) + rc = cca_cipher2protkey(card, dom, key, protkey, + protkeylen, protkeytype); + else if (hdr->type == TOKTYPE_CCA_INTERNAL_PKA) + rc = cca_ecc2protkey(card, dom, key, protkey, + protkeylen, protkeytype); + else + return -EINVAL; + } + + return rc; +} + /* * File io functions */ @@ -1333,6 +1500,55 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, kfree(apqns); break; } + case PKEY_KBLOB2PROTK3: { + struct pkey_kblob2pkey3 __user *utp = (void __user *) arg; + struct pkey_kblob2pkey3 ktp; + struct pkey_apqn *apqns = NULL; + u32 protkeylen = PROTKEYBLOBBUFSIZE; + u8 *kkey, *protkey; + + if (copy_from_user(&ktp, utp, sizeof(ktp))) + return -EFAULT; + apqns = _copy_apqns_from_user(ktp.apqns, ktp.apqn_entries); + if (IS_ERR(apqns)) + return PTR_ERR(apqns); + kkey = _copy_key_from_user(ktp.key, ktp.keylen); + if (IS_ERR(kkey)) { + kfree(apqns); + return PTR_ERR(kkey); + } + protkey = kmalloc(protkeylen, GFP_KERNEL); + if (!protkey) { + kfree(apqns); + kfree(kkey); + return -ENOMEM; + } + rc = pkey_keyblob2pkey3(apqns, ktp.apqn_entries, kkey, + ktp.keylen, &ktp.pkeytype, + protkey, &protkeylen); + DEBUG_DBG("%s pkey_keyblob2pkey3()=%d\n", __func__, rc); + kfree(apqns); + kfree(kkey); + if (rc) { + kfree(protkey); + break; + } + if (ktp.pkey && ktp.pkeylen) { + if (protkeylen > ktp.pkeylen) { + kfree(protkey); + return -EINVAL; + } + if (copy_to_user(ktp.pkey, protkey, protkeylen)) { + kfree(protkey); + return -EFAULT; + } + } + kfree(protkey); + ktp.pkeylen = protkeylen; + if (copy_to_user(utp, &ktp, sizeof(ktp))) + return -EFAULT; + break; + } default: /* unknown/unsupported ioctl cmd */ return -ENOTTY; diff --git a/drivers/s390/crypto/zcrypt_ccamisc.c b/drivers/s390/crypto/zcrypt_ccamisc.c index e969188a1ec4..b9d293ae228c 100644 --- a/drivers/s390/crypto/zcrypt_ccamisc.c +++ b/drivers/s390/crypto/zcrypt_ccamisc.c @@ -172,6 +172,49 @@ int cca_check_secaescipherkey(debug_info_t *dbg, int dbflvl, } EXPORT_SYMBOL(cca_check_secaescipherkey); +/* + * Simple check if the token is a valid CCA secure ECC private + * key token. Returns 0 on success or errno value on failure. + */ +int cca_check_sececckeytoken(debug_info_t *dbg, int dbflvl, + const u8 *token, size_t keysize, + int checkcpacfexport) +{ + struct eccprivkeytoken *t = (struct eccprivkeytoken *) token; + +#define DBF(...) debug_sprintf_event(dbg, dbflvl, ##__VA_ARGS__) + + if (t->type != TOKTYPE_CCA_INTERNAL_PKA) { + if (dbg) + DBF("%s token check failed, type 0x%02x != 0x%02x\n", + __func__, (int) t->type, TOKTYPE_CCA_INTERNAL_PKA); + return -EINVAL; + } + if (t->len > keysize) { + if (dbg) + DBF("%s token check failed, len %d > keysize %zu\n", + __func__, (int) t->len, keysize); + return -EINVAL; + } + if (t->secid != 0x20) { + if (dbg) + DBF("%s token check failed, secid 0x%02x != 0x20\n", + __func__, (int) t->secid); + return -EINVAL; + } + if (checkcpacfexport && !(t->kutc & 0x01)) { + if (dbg) + DBF("%s token check failed, XPRTCPAC bit is 0\n", + __func__); + return -EINVAL; + } + +#undef DBF + + return 0; +} +EXPORT_SYMBOL(cca_check_sececckeytoken); + /* * Allocate consecutive memory for request CPRB, request param * block, reply CPRB and reply param block and fill in values @@ -1297,6 +1340,156 @@ out: } EXPORT_SYMBOL(cca_cipher2protkey); +/* + * Derive protected key from CCA ECC secure private key. + */ +int cca_ecc2protkey(u16 cardnr, u16 domain, const u8 *key, + u8 *protkey, u32 *protkeylen, u32 *protkeytype) +{ + int rc; + u8 *mem, *ptr; + struct CPRBX *preqcblk, *prepcblk; + struct ica_xcRB xcrb; + struct aureqparm { + u8 subfunc_code[2]; + u16 rule_array_len; + u8 rule_array[8]; + struct { + u16 len; + u16 tk_blob_len; + u16 tk_blob_tag; + u8 tk_blob[66]; + } vud; + struct { + u16 len; + u16 cca_key_token_len; + u16 cca_key_token_flags; + u8 cca_key_token[0]; + } kb; + } __packed * preqparm; + struct aurepparm { + u8 subfunc_code[2]; + u16 rule_array_len; + struct { + u16 len; + u16 sublen; + u16 tag; + struct cpacfkeyblock { + u8 version; /* version of this struct */ + u8 flags[2]; + u8 algo; + u8 form; + u8 pad1[3]; + u16 keylen; + u8 key[0]; /* the key (keylen bytes) */ + u16 keyattrlen; + u8 keyattr[32]; + u8 pad2[1]; + u8 vptype; + u8 vp[32]; /* verification pattern */ + } ckb; + } vud; + struct { + u16 len; + } kb; + } __packed * prepparm; + int keylen = ((struct eccprivkeytoken *)key)->len; + + /* get already prepared memory for 2 cprbs with param block each */ + rc = alloc_and_prep_cprbmem(PARMBSIZE, &mem, &preqcblk, &prepcblk); + if (rc) + return rc; + + /* fill request cprb struct */ + preqcblk->domain = domain; + + /* fill request cprb param block with AU request */ + preqparm = (struct aureqparm __force *) preqcblk->req_parmb; + memcpy(preqparm->subfunc_code, "AU", 2); + preqparm->rule_array_len = + sizeof(preqparm->rule_array_len) + + sizeof(preqparm->rule_array); + memcpy(preqparm->rule_array, "EXPT-SK ", 8); + /* vud, tk blob */ + preqparm->vud.len = sizeof(preqparm->vud); + preqparm->vud.tk_blob_len = sizeof(preqparm->vud.tk_blob) + + 2 * sizeof(uint16_t); + preqparm->vud.tk_blob_tag = 0x00C2; + /* kb, cca token */ + preqparm->kb.len = keylen + 3 * sizeof(uint16_t); + preqparm->kb.cca_key_token_len = keylen + 2 * sizeof(uint16_t); + memcpy(preqparm->kb.cca_key_token, key, keylen); + /* now fill length of param block into cprb */ + preqcblk->req_parml = sizeof(struct aureqparm) + keylen; + + /* fill xcrb struct */ + prep_xcrb(&xcrb, cardnr, preqcblk, prepcblk); + + /* forward xcrb with request CPRB and reply CPRB to zcrypt dd */ + rc = zcrypt_send_cprb(&xcrb); + if (rc) { + DEBUG_ERR( + "%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", + __func__, (int) cardnr, (int) domain, rc); + goto out; + } + + /* check response returncode and reasoncode */ + if (prepcblk->ccp_rtcode != 0) { + DEBUG_ERR( + "%s unwrap secure key failure, card response %d/%d\n", + __func__, + (int) prepcblk->ccp_rtcode, + (int) prepcblk->ccp_rscode); + rc = -EIO; + goto out; + } + if (prepcblk->ccp_rscode != 0) { + DEBUG_WARN( + "%s unwrap secure key warning, card response %d/%d\n", + __func__, + (int) prepcblk->ccp_rtcode, + (int) prepcblk->ccp_rscode); + } + + /* process response cprb param block */ + ptr = ((u8 *) prepcblk) + sizeof(struct CPRBX); + prepcblk->rpl_parmb = (u8 __user *) ptr; + prepparm = (struct aurepparm *) ptr; + + /* check the returned keyblock */ + if (prepparm->vud.ckb.version != 0x02) { + DEBUG_ERR("%s reply param keyblock version mismatch 0x%02x != 0x02\n", + __func__, (int) prepparm->vud.ckb.version); + rc = -EIO; + goto out; + } + if (prepparm->vud.ckb.algo != 0x81) { + DEBUG_ERR( + "%s reply param keyblock algo mismatch 0x%02x != 0x81\n", + __func__, (int) prepparm->vud.ckb.algo); + rc = -EIO; + goto out; + } + + /* copy the translated protected key */ + if (prepparm->vud.ckb.keylen > *protkeylen) { + DEBUG_ERR("%s prot keylen mismatch %d > buffersize %u\n", + __func__, prepparm->vud.ckb.keylen, *protkeylen); + rc = -EIO; + goto out; + } + memcpy(protkey, prepparm->vud.ckb.key, prepparm->vud.ckb.keylen); + *protkeylen = prepparm->vud.ckb.keylen; + if (protkeytype) + *protkeytype = PKEY_KEYTYPE_ECC; + +out: + free_cprbmem(mem, PARMBSIZE, 0); + return rc; +} +EXPORT_SYMBOL(cca_ecc2protkey); + /* * query cryptographic facility from CCA adapter */ diff --git a/drivers/s390/crypto/zcrypt_ccamisc.h b/drivers/s390/crypto/zcrypt_ccamisc.h index 4d88a1d6af21..e7105443d5cb 100644 --- a/drivers/s390/crypto/zcrypt_ccamisc.h +++ b/drivers/s390/crypto/zcrypt_ccamisc.h @@ -14,8 +14,9 @@ #include /* Key token types */ -#define TOKTYPE_NON_CCA 0x00 /* Non-CCA key token */ -#define TOKTYPE_CCA_INTERNAL 0x01 /* CCA internal key token */ +#define TOKTYPE_NON_CCA 0x00 /* Non-CCA key token */ +#define TOKTYPE_CCA_INTERNAL 0x01 /* CCA internal sym key token */ +#define TOKTYPE_CCA_INTERNAL_PKA 0x1f /* CCA internal asym key token */ /* For TOKTYPE_NON_CCA: */ #define TOKVER_PROTECTED_KEY 0x01 /* Protected key token */ @@ -93,6 +94,31 @@ struct cipherkeytoken { u8 vdata[]; /* variable part data follows */ } __packed; +/* inside view of an CCA secure ECC private key */ +struct eccprivkeytoken { + u8 type; /* 0x1f for internal asym key token */ + u8 version; /* should be 0x00 */ + u16 len; /* total key token length in bytes */ + u8 res1[4]; + u8 secid; /* 0x20 for ECC priv key section marker */ + u8 secver; /* section version */ + u16 seclen; /* section length */ + u8 wtype; /* wrapping method, 0x00 clear, 0x01 AES */ + u8 htype; /* hash method, 0x02 for SHA-256 */ + u8 res2[2]; + u8 kutc; /* key usage and translation control */ + u8 ctype; /* curve type */ + u8 kfs; /* key format and security */ + u8 ksrc; /* key source */ + u16 pbitlen; /* length of prime p in bits */ + u16 ibmadlen; /* IBM associated data length in bytes */ + u64 mkvp; /* master key verification pattern */ + u8 opk[48]; /* encrypted object protection key data */ + u16 adatalen; /* associated data length in bytes */ + u16 fseclen; /* formated section length in bytes */ + u8 more_data[]; /* more data follows */ +} __packed; + /* Some defines for the CCA AES cipherkeytoken kmf1 field */ #define KMF1_XPRT_SYM 0x8000 #define KMF1_XPRT_UASY 0x4000 @@ -122,6 +148,14 @@ int cca_check_secaescipherkey(debug_info_t *dbg, int dbflvl, const u8 *token, int keybitsize, int checkcpacfexport); +/* + * Simple check if the token is a valid CCA secure ECC private + * key token. Returns 0 on success or errno value on failure. + */ +int cca_check_sececckeytoken(debug_info_t *dbg, int dbflvl, + const u8 *token, size_t keysize, + int checkcpacfexport); + /* * Generate (random) CCA AES DATA secure key. */ @@ -158,6 +192,12 @@ int cca_cipher2protkey(u16 cardnr, u16 domain, const u8 *ckey, int cca_clr2cipherkey(u16 cardnr, u16 domain, u32 keybitsize, u32 keygenflags, const u8 *clrkey, u8 *keybuf, size_t *keybufsize); +/* + * Derive proteced key from CCA ECC secure private key. + */ +int cca_ecc2protkey(u16 cardnr, u16 domain, const u8 *key, + u8 *protkey, u32 *protkeylen, u32 *protkeytype); + /* * Query cryptographic facility from CCA adapter */ diff --git a/drivers/s390/crypto/zcrypt_ep11misc.c b/drivers/s390/crypto/zcrypt_ep11misc.c index 60b6bec21c32..9ce5a71da69b 100644 --- a/drivers/s390/crypto/zcrypt_ep11misc.c +++ b/drivers/s390/crypto/zcrypt_ep11misc.c @@ -15,6 +15,7 @@ #include #include #include +#include #include "ap_bus.h" #include "zcrypt_api.h" @@ -113,16 +114,156 @@ static void __exit card_cache_free(void) } /* - * Simple check if the key blob is a valid EP11 secure AES key. + * Simple check if the key blob is a valid EP11 AES key blob with header. */ -int ep11_check_aeskeyblob(debug_info_t *dbg, int dbflvl, - const u8 *key, int keybitsize, - int checkcpacfexport) +int ep11_check_aes_key_with_hdr(debug_info_t *dbg, int dbflvl, + const u8 *key, size_t keylen, int checkcpacfexp) +{ + struct ep11kblob_header *hdr = (struct ep11kblob_header *) key; + struct ep11keyblob *kb = (struct ep11keyblob *) (key + sizeof(*hdr)); + +#define DBF(...) debug_sprintf_event(dbg, dbflvl, ##__VA_ARGS__) + + if (keylen < sizeof(*hdr) + sizeof(*kb)) { + DBF("%s key check failed, keylen %zu < %zu\n", + __func__, keylen, sizeof(*hdr) + sizeof(*kb)); + return -EINVAL; + } + + if (hdr->type != TOKTYPE_NON_CCA) { + if (dbg) + DBF("%s key check failed, type 0x%02x != 0x%02x\n", + __func__, (int) hdr->type, TOKTYPE_NON_CCA); + return -EINVAL; + } + if (hdr->hver != 0x00) { + if (dbg) + DBF("%s key check failed, header version 0x%02x != 0x00\n", + __func__, (int) hdr->hver); + return -EINVAL; + } + if (hdr->version != TOKVER_EP11_AES_WITH_HEADER) { + if (dbg) + DBF("%s key check failed, version 0x%02x != 0x%02x\n", + __func__, (int) hdr->version, TOKVER_EP11_AES_WITH_HEADER); + return -EINVAL; + } + if (hdr->len > keylen) { + if (dbg) + DBF("%s key check failed, header len %d keylen %zu mismatch\n", + __func__, (int) hdr->len, keylen); + return -EINVAL; + } + if (hdr->len < sizeof(*hdr) + sizeof(*kb)) { + if (dbg) + DBF("%s key check failed, header len %d < %zu\n", + __func__, (int) hdr->len, sizeof(*hdr) + sizeof(*kb)); + return -EINVAL; + } + + if (kb->version != EP11_STRUCT_MAGIC) { + if (dbg) + DBF("%s key check failed, blob magic 0x%04x != 0x%04x\n", + __func__, (int) kb->version, EP11_STRUCT_MAGIC); + return -EINVAL; + } + if (checkcpacfexp && !(kb->attr & EP11_BLOB_PKEY_EXTRACTABLE)) { + if (dbg) + DBF("%s key check failed, PKEY_EXTRACTABLE is off\n", + __func__); + return -EINVAL; + } + +#undef DBF + + return 0; +} +EXPORT_SYMBOL(ep11_check_aes_key_with_hdr); + +/* + * Simple check if the key blob is a valid EP11 ECC key blob with header. + */ +int ep11_check_ecc_key_with_hdr(debug_info_t *dbg, int dbflvl, + const u8 *key, size_t keylen, int checkcpacfexp) +{ + struct ep11kblob_header *hdr = (struct ep11kblob_header *) key; + struct ep11keyblob *kb = (struct ep11keyblob *) (key + sizeof(*hdr)); + +#define DBF(...) debug_sprintf_event(dbg, dbflvl, ##__VA_ARGS__) + + if (keylen < sizeof(*hdr) + sizeof(*kb)) { + DBF("%s key check failed, keylen %zu < %zu\n", + __func__, keylen, sizeof(*hdr) + sizeof(*kb)); + return -EINVAL; + } + + if (hdr->type != TOKTYPE_NON_CCA) { + if (dbg) + DBF("%s key check failed, type 0x%02x != 0x%02x\n", + __func__, (int) hdr->type, TOKTYPE_NON_CCA); + return -EINVAL; + } + if (hdr->hver != 0x00) { + if (dbg) + DBF("%s key check failed, header version 0x%02x != 0x00\n", + __func__, (int) hdr->hver); + return -EINVAL; + } + if (hdr->version != TOKVER_EP11_ECC_WITH_HEADER) { + if (dbg) + DBF("%s key check failed, version 0x%02x != 0x%02x\n", + __func__, (int) hdr->version, TOKVER_EP11_ECC_WITH_HEADER); + return -EINVAL; + } + if (hdr->len > keylen) { + if (dbg) + DBF("%s key check failed, header len %d keylen %zu mismatch\n", + __func__, (int) hdr->len, keylen); + return -EINVAL; + } + if (hdr->len < sizeof(*hdr) + sizeof(*kb)) { + if (dbg) + DBF("%s key check failed, header len %d < %zu\n", + __func__, (int) hdr->len, sizeof(*hdr) + sizeof(*kb)); + return -EINVAL; + } + + if (kb->version != EP11_STRUCT_MAGIC) { + if (dbg) + DBF("%s key check failed, blob magic 0x%04x != 0x%04x\n", + __func__, (int) kb->version, EP11_STRUCT_MAGIC); + return -EINVAL; + } + if (checkcpacfexp && !(kb->attr & EP11_BLOB_PKEY_EXTRACTABLE)) { + if (dbg) + DBF("%s key check failed, PKEY_EXTRACTABLE is off\n", + __func__); + return -EINVAL; + } + +#undef DBF + + return 0; +} +EXPORT_SYMBOL(ep11_check_ecc_key_with_hdr); + +/* + * Simple check if the key blob is a valid EP11 AES key blob with + * the header in the session field (old style EP11 AES key). + */ +int ep11_check_aes_key(debug_info_t *dbg, int dbflvl, + const u8 *key, size_t keylen, int checkcpacfexp) { struct ep11keyblob *kb = (struct ep11keyblob *) key; #define DBF(...) debug_sprintf_event(dbg, dbflvl, ##__VA_ARGS__) + if (keylen < sizeof(*kb)) { + DBF("%s key check failed, keylen %zu < %zu\n", + __func__, keylen, sizeof(*kb)); + return -EINVAL; + } + if (kb->head.type != TOKTYPE_NON_CCA) { if (dbg) DBF("%s key check failed, type 0x%02x != 0x%02x\n", @@ -135,39 +276,37 @@ int ep11_check_aeskeyblob(debug_info_t *dbg, int dbflvl, __func__, (int) kb->head.version, TOKVER_EP11_AES); return -EINVAL; } + if (kb->head.len > keylen) { + if (dbg) + DBF("%s key check failed, header len %d keylen %zu mismatch\n", + __func__, (int) kb->head.len, keylen); + return -EINVAL; + } + if (kb->head.len < sizeof(*kb)) { + if (dbg) + DBF("%s key check failed, header len %d < %zu\n", + __func__, (int) kb->head.len, sizeof(*kb)); + return -EINVAL; + } + if (kb->version != EP11_STRUCT_MAGIC) { if (dbg) - DBF("%s key check failed, magic 0x%04x != 0x%04x\n", + DBF("%s key check failed, blob magic 0x%04x != 0x%04x\n", __func__, (int) kb->version, EP11_STRUCT_MAGIC); return -EINVAL; } - switch (kb->head.keybitlen) { - case 128: - case 192: - case 256: - break; - default: + if (checkcpacfexp && !(kb->attr & EP11_BLOB_PKEY_EXTRACTABLE)) { if (dbg) - DBF("%s key check failed, keybitlen %d invalid\n", - __func__, (int) kb->head.keybitlen); - return -EINVAL; - } - if (keybitsize > 0 && keybitsize != (int) kb->head.keybitlen) { - DBF("%s key check failed, keybitsize %d\n", - __func__, keybitsize); - return -EINVAL; - } - if (checkcpacfexport && !(kb->attr & EP11_BLOB_PKEY_EXTRACTABLE)) { - if (dbg) - DBF("%s key check failed, PKEY_EXTRACTABLE is 0\n", + DBF("%s key check failed, PKEY_EXTRACTABLE is off\n", __func__); return -EINVAL; } + #undef DBF return 0; } -EXPORT_SYMBOL(ep11_check_aeskeyblob); +EXPORT_SYMBOL(ep11_check_aes_key); /* * Allocate and prepare ep11 cprb plus additional payload. @@ -954,7 +1093,7 @@ static int ep11_wrapkey(u16 card, u16 domain, u8 data_tag; u8 data_lenfmt; u16 data_len; - u8 data[512]; + u8 data[1024]; } __packed * rep_pl; struct ep11_cprb *req = NULL, *rep = NULL; struct ep11_target_dev target; @@ -962,8 +1101,17 @@ static int ep11_wrapkey(u16 card, u16 domain, struct ep11keyblob *kb; size_t req_pl_size; int api, rc = -ENOMEM; + bool has_header = false; u8 *p; + /* maybe the session field holds a header with key info */ + kb = (struct ep11keyblob *) key; + if (kb->head.type == TOKTYPE_NON_CCA && + kb->head.version == TOKVER_EP11_AES) { + has_header = true; + keysize = kb->head.len < keysize ? kb->head.len : keysize; + } + /* request cprb and payload */ req_pl_size = sizeof(struct wk_req_pl) + (iv ? 16 : 0) + ASN1TAGLEN(keysize) + 4; @@ -989,9 +1137,10 @@ static int ep11_wrapkey(u16 card, u16 domain, /* key blob */ p += asn1tag_write(p, 0x04, key, keysize); /* maybe the key argument needs the head data cleaned out */ - kb = (struct ep11keyblob *)(p - keysize); - if (kb->head.version == TOKVER_EP11_AES) + if (has_header) { + kb = (struct ep11keyblob *)(p - keysize); memset(&kb->head, 0, sizeof(kb->head)); + } /* empty kek tag */ *p++ = 0x04; *p++ = 0; @@ -1114,12 +1263,12 @@ out: } EXPORT_SYMBOL(ep11_clr2keyblob); -int ep11_key2protkey(u16 card, u16 dom, const u8 *key, size_t keylen, - u8 *protkey, u32 *protkeylen, u32 *protkeytype) +int ep11_kblob2protkey(u16 card, u16 dom, const u8 *keyblob, size_t keybloblen, + u8 *protkey, u32 *protkeylen, u32 *protkeytype) { int rc = -EIO; u8 *wkbuf = NULL; - size_t wkbuflen = 256; + size_t wkbuflen, keylen; struct wk_info { u16 version; u8 res1[16]; @@ -1129,8 +1278,33 @@ int ep11_key2protkey(u16 card, u16 dom, const u8 *key, size_t keylen, u8 res2[8]; u8 pkey[0]; } __packed * wki; + const u8 *key; + struct ep11kblob_header *hdr; + + /* key with or without header ? */ + hdr = (struct ep11kblob_header *) keyblob; + if (hdr->type == TOKTYPE_NON_CCA + && (hdr->version == TOKVER_EP11_AES_WITH_HEADER + || hdr->version == TOKVER_EP11_ECC_WITH_HEADER) + && is_ep11_keyblob(keyblob + sizeof(struct ep11kblob_header))) { + /* EP11 AES or ECC key with header */ + key = keyblob + sizeof(struct ep11kblob_header); + keylen = hdr->len - sizeof(struct ep11kblob_header); + } else if (hdr->type == TOKTYPE_NON_CCA + && hdr->version == TOKVER_EP11_AES + && is_ep11_keyblob(keyblob)) { + /* EP11 AES key (old style) */ + key = keyblob; + keylen = hdr->len; + } else if (is_ep11_keyblob(keyblob)) { + /* raw EP11 key blob */ + key = keyblob; + keylen = keybloblen; + } else + return -EINVAL; /* alloc temp working buffer */ + wkbuflen = (keylen + AES_BLOCK_SIZE) & (~(AES_BLOCK_SIZE - 1)); wkbuf = kmalloc(wkbuflen, GFP_ATOMIC); if (!wkbuf) return -ENOMEM; @@ -1147,46 +1321,68 @@ int ep11_key2protkey(u16 card, u16 dom, const u8 *key, size_t keylen, wki = (struct wk_info *) wkbuf; /* check struct version and pkey type */ - if (wki->version != 1 || wki->pkeytype != 1) { + if (wki->version != 1 || wki->pkeytype < 1 || wki->pkeytype > 5) { DEBUG_ERR("%s wk info version %d or pkeytype %d mismatch.\n", __func__, (int) wki->version, (int) wki->pkeytype); rc = -EIO; goto out; } - /* copy the tanslated protected key */ - switch (wki->pkeysize) { - case 16+32: - /* AES 128 protected key */ - if (protkeytype) - *protkeytype = PKEY_KEYTYPE_AES_128; + /* check protected key type field */ + switch (wki->pkeytype) { + case 1: /* AES */ + switch (wki->pkeysize) { + case 16+32: + /* AES 128 protected key */ + if (protkeytype) + *protkeytype = PKEY_KEYTYPE_AES_128; + break; + case 24+32: + /* AES 192 protected key */ + if (protkeytype) + *protkeytype = PKEY_KEYTYPE_AES_192; + break; + case 32+32: + /* AES 256 protected key */ + if (protkeytype) + *protkeytype = PKEY_KEYTYPE_AES_256; + break; + default: + DEBUG_ERR("%s unknown/unsupported AES pkeysize %d\n", + __func__, (int) wki->pkeysize); + rc = -EIO; + goto out; + } break; - case 24+32: - /* AES 192 protected key */ + case 3: /* EC-P */ + case 4: /* EC-ED */ + case 5: /* EC-BP */ if (protkeytype) - *protkeytype = PKEY_KEYTYPE_AES_192; - break; - case 32+32: - /* AES 256 protected key */ - if (protkeytype) - *protkeytype = PKEY_KEYTYPE_AES_256; + *protkeytype = PKEY_KEYTYPE_ECC; break; + case 2: /* TDES */ default: - DEBUG_ERR("%s unknown/unsupported pkeysize %d\n", - __func__, (int) wki->pkeysize); + DEBUG_ERR("%s unknown/unsupported key type %d\n", + __func__, (int) wki->pkeytype); rc = -EIO; goto out; } + + /* copy the tanslated protected key */ + if (wki->pkeysize > *protkeylen) { + DEBUG_ERR("%s wk info pkeysize %llu > protkeysize %u\n", + __func__, wki->pkeysize, *protkeylen); + rc = -EINVAL; + goto out; + } memcpy(protkey, wki->pkey, wki->pkeysize); - if (protkeylen) - *protkeylen = (u32) wki->pkeysize; - rc = 0; + *protkeylen = wki->pkeysize; out: kfree(wkbuf); return rc; } -EXPORT_SYMBOL(ep11_key2protkey); +EXPORT_SYMBOL(ep11_kblob2protkey); int ep11_findcard2(u32 **apqns, u32 *nr_apqns, u16 cardnr, u16 domain, int minhwtype, int minapi, const u8 *wkvp) diff --git a/drivers/s390/crypto/zcrypt_ep11misc.h b/drivers/s390/crypto/zcrypt_ep11misc.h index e3ed5ed1de86..1e02b197c003 100644 --- a/drivers/s390/crypto/zcrypt_ep11misc.h +++ b/drivers/s390/crypto/zcrypt_ep11misc.h @@ -12,22 +12,28 @@ #include #include -#define TOKVER_EP11_AES 0x03 /* EP11 AES key blob */ - #define EP11_API_V 4 /* highest known and supported EP11 API version */ - #define EP11_STRUCT_MAGIC 0x1234 -#define EP11_BLOB_PKEY_EXTRACTABLE 0x200000 +#define EP11_BLOB_PKEY_EXTRACTABLE 0x00200000 + +/* + * Internal used values for the version field of the key header. + * Should match to the enum pkey_key_type in pkey.h. + */ +#define TOKVER_EP11_AES 0x03 /* EP11 AES key blob (old style) */ +#define TOKVER_EP11_AES_WITH_HEADER 0x06 /* EP11 AES key blob with header */ +#define TOKVER_EP11_ECC_WITH_HEADER 0x07 /* EP11 ECC key blob with header */ /* inside view of an EP11 secure key blob */ struct ep11keyblob { union { u8 session[32]; + /* only used for PKEY_TYPE_EP11: */ struct { u8 type; /* 0x00 (TOKTYPE_NON_CCA) */ u8 res0; /* unused */ u16 len; /* total length in bytes of this blob */ - u8 version; /* 0x06 (TOKVER_EP11_AES) */ + u8 version; /* 0x03 (TOKVER_EP11_AES) */ u8 res1; /* unused */ u16 keybitlen; /* clear key bit len, 0 for unknown */ } head; @@ -41,16 +47,41 @@ struct ep11keyblob { u8 mac[32]; } __packed; +/* check ep11 key magic to find out if this is an ep11 key blob */ +static inline bool is_ep11_keyblob(const u8 *key) +{ + struct ep11keyblob *kb = (struct ep11keyblob *) key; + + return (kb->version == EP11_STRUCT_MAGIC); +} + /* - * Simple check if the key blob is a valid EP11 secure AES key. - * If keybitsize is given, the bitsize of the key is also checked. + * Simple check if the key blob is a valid EP11 AES key blob with header. * If checkcpacfexport is enabled, the key is also checked for the * attributes needed to export this key for CPACF use. * Returns 0 on success or errno value on failure. */ -int ep11_check_aeskeyblob(debug_info_t *dbg, int dbflvl, - const u8 *key, int keybitsize, - int checkcpacfexport); +int ep11_check_aes_key_with_hdr(debug_info_t *dbg, int dbflvl, + const u8 *key, size_t keylen, int checkcpacfexp); + +/* + * Simple check if the key blob is a valid EP11 ECC key blob with header. + * If checkcpacfexport is enabled, the key is also checked for the + * attributes needed to export this key for CPACF use. + * Returns 0 on success or errno value on failure. + */ +int ep11_check_ecc_key_with_hdr(debug_info_t *dbg, int dbflvl, + const u8 *key, size_t keylen, int checkcpacfexp); + +/* + * Simple check if the key blob is a valid EP11 AES key blob with + * the header in the session field (old style EP11 AES key). + * If checkcpacfexport is enabled, the key is also checked for the + * attributes needed to export this key for CPACF use. + * Returns 0 on success or errno value on failure. + */ +int ep11_check_aes_key(debug_info_t *dbg, int dbflvl, + const u8 *key, size_t keylen, int checkcpacfexp); /* EP11 card info struct */ struct ep11_card_info { @@ -91,12 +122,6 @@ int ep11_genaeskey(u16 card, u16 domain, u32 keybitsize, u32 keygenflags, int ep11_clr2keyblob(u16 cardnr, u16 domain, u32 keybitsize, u32 keygenflags, const u8 *clrkey, u8 *keybuf, size_t *keybufsize); -/* - * Derive proteced key from EP11 AES secure key blob. - */ -int ep11_key2protkey(u16 cardnr, u16 domain, const u8 *key, size_t keylen, - u8 *protkey, u32 *protkeylen, u32 *protkeytype); - /* * Build a list of ep11 apqns meeting the following constrains: * - apqn is online and is in fact an EP11 apqn @@ -119,6 +144,12 @@ int ep11_key2protkey(u16 cardnr, u16 domain, const u8 *key, size_t keylen, int ep11_findcard2(u32 **apqns, u32 *nr_apqns, u16 cardnr, u16 domain, int minhwtype, int minapi, const u8 *wkvp); +/* + * Derive proteced key from EP11 key blob (AES and ECC keys). + */ +int ep11_kblob2protkey(u16 card, u16 dom, const u8 *key, size_t keylen, + u8 *protkey, u32 *protkeylen, u32 *protkeytype); + void zcrypt_ep11misc_exit(void); #endif /* _ZCRYPT_EP11MISC_H_ */ From b3bd02495cb339124f13135d51940cf48d83e5cb Mon Sep 17 00:00:00 2001 From: Sven Schnelle Date: Tue, 15 Sep 2020 08:53:50 +0200 Subject: [PATCH 273/645] s390/stp: add locking to sysfs functions The sysfs function might race with stp_work_fn. To prevent that, add the required locking. Another issue is that the sysfs functions are checking the stp_online flag, but this flag just holds the user setting whether STP is enabled. Add a flag to clock_sync_flag whether stp_info holds valid data and use that instead. Cc: stable@vger.kernel.org Signed-off-by: Sven Schnelle Reviewed-by: Alexander Egorenkov Signed-off-by: Vasily Gorbik --- arch/s390/kernel/time.c | 118 +++++++++++++++++++++++++++++----------- 1 file changed, 85 insertions(+), 33 deletions(-) diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index bc806e1547d6..bee380340bad 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -299,8 +299,9 @@ static DEFINE_PER_CPU(atomic_t, clock_sync_word); static DEFINE_MUTEX(clock_sync_mutex); static unsigned long clock_sync_flags; -#define CLOCK_SYNC_HAS_STP 0 -#define CLOCK_SYNC_STP 1 +#define CLOCK_SYNC_HAS_STP 0 +#define CLOCK_SYNC_STP 1 +#define CLOCK_SYNC_STPINFO_VALID 2 /* * The get_clock function for the physical clock. It will get the current @@ -535,6 +536,22 @@ void stp_queue_work(void) queue_work(time_sync_wq, &stp_work); } +static int __store_stpinfo(void) +{ + int rc = chsc_sstpi(stp_page, &stp_info, sizeof(struct stp_sstpi)); + + if (rc) + clear_bit(CLOCK_SYNC_STPINFO_VALID, &clock_sync_flags); + else + set_bit(CLOCK_SYNC_STPINFO_VALID, &clock_sync_flags); + return rc; +} + +static int stpinfo_valid(void) +{ + return stp_online && test_bit(CLOCK_SYNC_STPINFO_VALID, &clock_sync_flags); +} + static int stp_sync_clock(void *data) { struct clock_sync_data *sync = data; @@ -557,8 +574,7 @@ static int stp_sync_clock(void *data) if (rc == 0) { sync->clock_delta = clock_delta; clock_sync_global(clock_delta); - rc = chsc_sstpi(stp_page, &stp_info, - sizeof(struct stp_sstpi)); + rc = __store_stpinfo(); if (rc == 0 && stp_info.tmd != 2) rc = -EAGAIN; } @@ -604,7 +620,7 @@ static void stp_work_fn(struct work_struct *work) if (rc) goto out_unlock; - rc = chsc_sstpi(stp_page, &stp_info, sizeof(struct stp_sstpi)); + rc = __store_stpinfo(); if (rc || stp_info.c == 0) goto out_unlock; @@ -641,10 +657,14 @@ static ssize_t ctn_id_show(struct device *dev, struct device_attribute *attr, char *buf) { - if (!stp_online) - return -ENODATA; - return sprintf(buf, "%016llx\n", - *(unsigned long long *) stp_info.ctnid); + ssize_t ret = -ENODATA; + + mutex_lock(&stp_work_mutex); + if (stpinfo_valid()) + ret = sprintf(buf, "%016llx\n", + *(unsigned long long *) stp_info.ctnid); + mutex_unlock(&stp_work_mutex); + return ret; } static DEVICE_ATTR_RO(ctn_id); @@ -653,9 +673,13 @@ static ssize_t ctn_type_show(struct device *dev, struct device_attribute *attr, char *buf) { - if (!stp_online) - return -ENODATA; - return sprintf(buf, "%i\n", stp_info.ctn); + ssize_t ret = -ENODATA; + + mutex_lock(&stp_work_mutex); + if (stpinfo_valid()) + ret = sprintf(buf, "%i\n", stp_info.ctn); + mutex_unlock(&stp_work_mutex); + return ret; } static DEVICE_ATTR_RO(ctn_type); @@ -664,9 +688,13 @@ static ssize_t dst_offset_show(struct device *dev, struct device_attribute *attr, char *buf) { - if (!stp_online || !(stp_info.vbits & 0x2000)) - return -ENODATA; - return sprintf(buf, "%i\n", (int)(s16) stp_info.dsto); + ssize_t ret = -ENODATA; + + mutex_lock(&stp_work_mutex); + if (stpinfo_valid() && (stp_info.vbits & 0x2000)) + ret = sprintf(buf, "%i\n", (int)(s16) stp_info.dsto); + mutex_unlock(&stp_work_mutex); + return ret; } static DEVICE_ATTR_RO(dst_offset); @@ -675,9 +703,13 @@ static ssize_t leap_seconds_show(struct device *dev, struct device_attribute *attr, char *buf) { - if (!stp_online || !(stp_info.vbits & 0x8000)) - return -ENODATA; - return sprintf(buf, "%i\n", (int)(s16) stp_info.leaps); + ssize_t ret = -ENODATA; + + mutex_lock(&stp_work_mutex); + if (stpinfo_valid() && (stp_info.vbits & 0x8000)) + ret = sprintf(buf, "%i\n", (int)(s16) stp_info.leaps); + mutex_unlock(&stp_work_mutex); + return ret; } static DEVICE_ATTR_RO(leap_seconds); @@ -686,9 +718,13 @@ static ssize_t stratum_show(struct device *dev, struct device_attribute *attr, char *buf) { - if (!stp_online) - return -ENODATA; - return sprintf(buf, "%i\n", (int)(s16) stp_info.stratum); + ssize_t ret = -ENODATA; + + mutex_lock(&stp_work_mutex); + if (stpinfo_valid()) + ret = sprintf(buf, "%i\n", (int)(s16) stp_info.stratum); + mutex_unlock(&stp_work_mutex); + return ret; } static DEVICE_ATTR_RO(stratum); @@ -697,9 +733,13 @@ static ssize_t time_offset_show(struct device *dev, struct device_attribute *attr, char *buf) { - if (!stp_online || !(stp_info.vbits & 0x0800)) - return -ENODATA; - return sprintf(buf, "%i\n", (int) stp_info.tto); + ssize_t ret = -ENODATA; + + mutex_lock(&stp_work_mutex); + if (stpinfo_valid() && (stp_info.vbits & 0x0800)) + ret = sprintf(buf, "%i\n", (int) stp_info.tto); + mutex_unlock(&stp_work_mutex); + return ret; } static DEVICE_ATTR_RO(time_offset); @@ -708,9 +748,13 @@ static ssize_t time_zone_offset_show(struct device *dev, struct device_attribute *attr, char *buf) { - if (!stp_online || !(stp_info.vbits & 0x4000)) - return -ENODATA; - return sprintf(buf, "%i\n", (int)(s16) stp_info.tzo); + ssize_t ret = -ENODATA; + + mutex_lock(&stp_work_mutex); + if (stpinfo_valid() && (stp_info.vbits & 0x4000)) + ret = sprintf(buf, "%i\n", (int)(s16) stp_info.tzo); + mutex_unlock(&stp_work_mutex); + return ret; } static DEVICE_ATTR_RO(time_zone_offset); @@ -719,9 +763,13 @@ static ssize_t timing_mode_show(struct device *dev, struct device_attribute *attr, char *buf) { - if (!stp_online) - return -ENODATA; - return sprintf(buf, "%i\n", stp_info.tmd); + ssize_t ret = -ENODATA; + + mutex_lock(&stp_work_mutex); + if (stpinfo_valid()) + ret = sprintf(buf, "%i\n", stp_info.tmd); + mutex_unlock(&stp_work_mutex); + return ret; } static DEVICE_ATTR_RO(timing_mode); @@ -730,9 +778,13 @@ static ssize_t timing_state_show(struct device *dev, struct device_attribute *attr, char *buf) { - if (!stp_online) - return -ENODATA; - return sprintf(buf, "%i\n", stp_info.tst); + ssize_t ret = -ENODATA; + + mutex_lock(&stp_work_mutex); + if (stpinfo_valid()) + ret = sprintf(buf, "%i\n", stp_info.tst); + mutex_unlock(&stp_work_mutex); + return ret; } static DEVICE_ATTR_RO(timing_state); From bb7d066a091654b6d6c0b6061bda438bf36c6613 Mon Sep 17 00:00:00 2001 From: Sven Schnelle Date: Mon, 3 Aug 2020 08:50:38 +0200 Subject: [PATCH 274/645] s390/stp: use __packed Use __packed instead of __attribute__((packed)) Signed-off-by: Sven Schnelle Reviewed-by: Alexander Egorenkov Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/stp.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/s390/include/asm/stp.h b/arch/s390/include/asm/stp.h index f0ddefb06ec8..572f6f4286e2 100644 --- a/arch/s390/include/asm/stp.h +++ b/arch/s390/include/asm/stp.h @@ -6,6 +6,8 @@ #ifndef __S390_STP_H #define __S390_STP_H +#include + /* notifier for syncs */ extern struct atomic_notifier_head s390_epoch_delta_notifier; @@ -16,7 +18,7 @@ struct stp_irq_parm { unsigned int lac : 1; /* Link availability change */ unsigned int tcpc : 1; /* Time control parameter change */ unsigned int _pad2 : 15; -} __attribute__ ((packed)); +} __packed; #define STP_OP_SYNC 1 #define STP_OP_CTRL 3 @@ -42,7 +44,7 @@ struct stp_sstpi { unsigned int rsvd5; unsigned int todoff[4]; unsigned int rsvd6[48]; -} __attribute__ ((packed)); +} __packed; /* Functions needed by the machine check handler */ int stp_sync_check(void); From 4ab79ed223d2ff32ffe16cfd841e064199341c34 Mon Sep 17 00:00:00 2001 From: Sven Schnelle Date: Tue, 8 Sep 2020 10:14:00 +0200 Subject: [PATCH 275/645] s390/stp: use u32 instead of unsigned int In hardware-dependent headers using u32 is easier to read and less error-prone. Signed-off-by: Sven Schnelle Reviewed-by: Alexander Egorenkov Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/stp.h | 50 ++++++++++++++++++------------------- 1 file changed, 25 insertions(+), 25 deletions(-) diff --git a/arch/s390/include/asm/stp.h b/arch/s390/include/asm/stp.h index 572f6f4286e2..a5c0bc1e5b90 100644 --- a/arch/s390/include/asm/stp.h +++ b/arch/s390/include/asm/stp.h @@ -13,37 +13,37 @@ extern struct atomic_notifier_head s390_epoch_delta_notifier; /* STP interruption parameter */ struct stp_irq_parm { - unsigned int _pad0 : 14; - unsigned int tsc : 1; /* Timing status change */ - unsigned int lac : 1; /* Link availability change */ - unsigned int tcpc : 1; /* Time control parameter change */ - unsigned int _pad2 : 15; + u32 : 14; + u32 tsc : 1; /* Timing status change */ + u32 lac : 1; /* Link availability change */ + u32 tcpc : 1; /* Time control parameter change */ + u32 : 15; } __packed; #define STP_OP_SYNC 1 #define STP_OP_CTRL 3 struct stp_sstpi { - unsigned int rsvd0; - unsigned int rsvd1 : 8; - unsigned int stratum : 8; - unsigned int vbits : 16; - unsigned int leaps : 16; - unsigned int tmd : 4; - unsigned int ctn : 4; - unsigned int rsvd2 : 3; - unsigned int c : 1; - unsigned int tst : 4; - unsigned int tzo : 16; - unsigned int dsto : 16; - unsigned int ctrl : 16; - unsigned int rsvd3 : 16; - unsigned int tto; - unsigned int rsvd4; - unsigned int ctnid[3]; - unsigned int rsvd5; - unsigned int todoff[4]; - unsigned int rsvd6[48]; + u32 : 32; + u32 : 8; + u32 stratum : 8; + u32 vbits : 16; + u32 leaps : 16; + u32 tmd : 4; + u32 ctn : 4; + u32 : 3; + u32 c : 1; + u32 tst : 4; + u32 tzo : 16; + u32 dsto : 16; + u32 ctrl : 16; + u32 : 16; + u32 tto; + u32 : 32; + u32 ctnid[3]; + u32 : 32; + u32 todoff[4]; + u32 rsvd[48]; } __packed; /* Functions needed by the machine check handler */ From b2539aa0d7ff1e42c74a9dd8c73ec1c2771c9e5d Mon Sep 17 00:00:00 2001 From: Sven Schnelle Date: Fri, 12 Jun 2020 12:59:19 +0200 Subject: [PATCH 276/645] s390/stp: add support for leap seconds In the current implementation, leap seconds are only synchronized during the bootup process when the STP clock is synced. If the Leap second offset (LSO) changes the machine must be rebooted, which is not desired. This patch adds the required code to handle Leap second changes during runtime. If the Leap second changes, a Configuration change machine check is triggered. The STP code than schedules a Leap second insertion/deletion with do_adjtimex(). Signed-off-by: Sven Schnelle Reviewed-by: Alexander Egorenkov Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/cio.h | 1 + arch/s390/include/asm/stp.h | 46 +++++++++++++++++- arch/s390/kernel/time.c | 94 +++++++++++++++++++++++++++++++++---- drivers/s390/cio/chsc.c | 21 +++++++++ 4 files changed, 152 insertions(+), 10 deletions(-) diff --git a/arch/s390/include/asm/cio.h b/arch/s390/include/asm/cio.h index b5bfb3123cb1..953a7316b30a 100644 --- a/arch/s390/include/asm/cio.h +++ b/arch/s390/include/asm/cio.h @@ -372,6 +372,7 @@ struct gen_pool *cio_gp_dma_create(struct device *dma_dev, int nr_pages); /* Function from drivers/s390/cio/chsc.c */ int chsc_sstpc(void *page, unsigned int op, u16 ctrl, u64 *clock_delta); int chsc_sstpi(void *page, void *result, size_t size); +int chsc_stzi(void *page, void *result, size_t size); int chsc_sgib(u32 origin); #endif diff --git a/arch/s390/include/asm/stp.h b/arch/s390/include/asm/stp.h index a5c0bc1e5b90..ba07463897c1 100644 --- a/arch/s390/include/asm/stp.h +++ b/arch/s390/include/asm/stp.h @@ -25,7 +25,9 @@ struct stp_irq_parm { struct stp_sstpi { u32 : 32; - u32 : 8; + u32 tu : 1; + u32 lu : 1; + u32 : 6; u32 stratum : 8; u32 vbits : 16; u32 leaps : 16; @@ -46,6 +48,48 @@ struct stp_sstpi { u32 rsvd[48]; } __packed; +struct stp_tzib { + u32 tzan : 16; + u32 : 16; + u32 tzo : 16; + u32 dsto : 16; + u32 stn; + u32 dstn; + u64 dst_on_alg; + u64 dst_off_alg; +} __packed; + +struct stp_tcpib { + u32 atcode : 4; + u32 ntcode : 4; + u32 d : 1; + u32 : 23; + s32 tto; + struct stp_tzib atzib; + struct stp_tzib ntzib; + s32 adst_offset : 16; + s32 ndst_offset : 16; + u32 rsvd1; + u64 ntzib_update; + u64 ndsto_update; +} __packed; + +struct stp_lsoib { + u32 p : 1; + u32 : 31; + s32 also : 16; + s32 nlso : 16; + u64 nlsout; +} __packed; + +struct stp_stzi { + u32 rsvd0[3]; + u64 data_ts; + u32 rsvd1[22]; + struct stp_tcpib tcpib; + struct stp_lsoib lsoib; +} __packed; + /* Functions needed by the machine check handler */ int stp_sync_check(void); int stp_island_check(void); diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index bee380340bad..49648d574b35 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -598,6 +598,81 @@ static int stp_sync_clock(void *data) return 0; } +static int stp_clear_leap(void) +{ + struct __kernel_timex txc; + int ret; + + memset(&txc, 0, sizeof(txc)); + + ret = do_adjtimex(&txc); + if (ret < 0) + return ret; + + txc.modes = ADJ_STATUS; + txc.status &= ~(STA_INS|STA_DEL); + return do_adjtimex(&txc); +} + +static void stp_check_leap(void) +{ + struct stp_stzi stzi; + struct stp_lsoib *lsoib = &stzi.lsoib; + struct __kernel_timex txc; + int64_t timediff; + int leapdiff, ret; + + if (!stp_info.lu || !check_sync_clock()) { + /* + * Either a scheduled leap second was removed by the operator, + * or STP is out of sync. In both cases, clear the leap second + * kernel flags. + */ + if (stp_clear_leap() < 0) + pr_err("failed to clear leap second flags\n"); + return; + } + + if (chsc_stzi(stp_page, &stzi, sizeof(stzi))) { + pr_err("stzi failed\n"); + return; + } + + timediff = tod_to_ns(lsoib->nlsout - get_tod_clock()) / NSEC_PER_SEC; + leapdiff = lsoib->nlso - lsoib->also; + + if (leapdiff != 1 && leapdiff != -1) { + pr_err("Cannot schedule %d leap seconds\n", leapdiff); + return; + } + + if (timediff < 0) { + if (stp_clear_leap() < 0) + pr_err("failed to clear leap second flags\n"); + } else if (timediff < 7200) { + memset(&txc, 0, sizeof(txc)); + ret = do_adjtimex(&txc); + if (ret < 0) + return; + + txc.modes = ADJ_STATUS; + if (leapdiff > 0) + txc.status |= STA_INS; + else + txc.status |= STA_DEL; + ret = do_adjtimex(&txc); + if (ret < 0) + pr_err("failed to set leap second flags\n"); + /* arm Timer to clear leap second flags */ + mod_timer(&stp_timer, jiffies + msecs_to_jiffies(14400 * MSEC_PER_SEC)); + } else { + /* The day the leap second is scheduled for hasn't been reached. Retry + * in one hour. + */ + mod_timer(&stp_timer, jiffies + msecs_to_jiffies(3600 * MSEC_PER_SEC)); + } +} + /* * STP work. Check for the STP state and take over the clock * synchronization if the STP clock source is usable. @@ -616,7 +691,7 @@ static void stp_work_fn(struct work_struct *work) goto out_unlock; } - rc = chsc_sstpc(stp_page, STP_OP_CTRL, 0xb0e0, NULL); + rc = chsc_sstpc(stp_page, STP_OP_CTRL, 0xf0e0, NULL); if (rc) goto out_unlock; @@ -625,14 +700,13 @@ static void stp_work_fn(struct work_struct *work) goto out_unlock; /* Skip synchronization if the clock is already in sync. */ - if (check_sync_clock()) - goto out_unlock; - - memset(&stp_sync, 0, sizeof(stp_sync)); - cpus_read_lock(); - atomic_set(&stp_sync.cpus, num_online_cpus() - 1); - stop_machine_cpuslocked(stp_sync_clock, &stp_sync, cpu_online_mask); - cpus_read_unlock(); + if (!check_sync_clock()) { + memset(&stp_sync, 0, sizeof(stp_sync)); + cpus_read_lock(); + atomic_set(&stp_sync.cpus, num_online_cpus() - 1); + stop_machine_cpuslocked(stp_sync_clock, &stp_sync, cpu_online_mask); + cpus_read_unlock(); + } if (!check_sync_clock()) /* @@ -640,6 +714,8 @@ static void stp_work_fn(struct work_struct *work) * Retry after a second. */ mod_timer(&stp_timer, jiffies + msecs_to_jiffies(MSEC_PER_SEC)); + else if (stp_info.lu) + stp_check_leap(); out_unlock: mutex_unlock(&stp_work_mutex); diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c index c314e9495c1b..e612e570447a 100644 --- a/drivers/s390/cio/chsc.c +++ b/drivers/s390/cio/chsc.c @@ -1260,6 +1260,27 @@ int chsc_sstpi(void *page, void *result, size_t size) return (rr->response.code == 0x0001) ? 0 : -EIO; } +int chsc_stzi(void *page, void *result, size_t size) +{ + struct { + struct chsc_header request; + unsigned int rsvd0[3]; + struct chsc_header response; + char data[]; + } *rr; + int rc; + + memset(page, 0, PAGE_SIZE); + rr = page; + rr->request.length = 0x0010; + rr->request.code = 0x003e; + rc = chsc(rr); + if (rc) + return -EIO; + memcpy(result, &rr->data, size); + return (rr->response.code == 0x0001) ? 0 : -EIO; +} + int chsc_siosl(struct subchannel_id schid) { struct { From 4fb53dde770cc095a6e279ca9d9c72d49488cdb3 Mon Sep 17 00:00:00 2001 From: Sven Schnelle Date: Wed, 17 Jun 2020 10:58:47 +0200 Subject: [PATCH 277/645] s390/stp: add sysfs file to show scheduled leap seconds This patch introduces /sys/devices/system/stp/scheduled_leap_seconds, which will contain either 0,0 if no leap second is scheduled, or the UTC timestamp + leap second offset. Signed-off-by: Sven Schnelle Reviewed-by: Alexander Egorenkov Signed-off-by: Vasily Gorbik --- arch/s390/kernel/time.c | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index 49648d574b35..da271f8ec8d6 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -790,6 +790,34 @@ static ssize_t leap_seconds_show(struct device *dev, static DEVICE_ATTR_RO(leap_seconds); +static ssize_t leap_seconds_scheduled_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct stp_stzi stzi; + ssize_t ret; + + mutex_lock(&stp_work_mutex); + if (!stpinfo_valid() || !(stp_info.vbits & 0x8000) || !stp_info.lu) { + mutex_unlock(&stp_work_mutex); + return -ENODATA; + } + + ret = chsc_stzi(stp_page, &stzi, sizeof(stzi)); + mutex_unlock(&stp_work_mutex); + if (ret < 0) + return ret; + + if (!stzi.lsoib.p) + return sprintf(buf, "0,0\n"); + + return sprintf(buf, "%llu,%d\n", + tod_to_ns(stzi.lsoib.nlsout - TOD_UNIX_EPOCH) / NSEC_PER_SEC, + stzi.lsoib.nlso - stzi.lsoib.also); +} + +static DEVICE_ATTR_RO(leap_seconds_scheduled); + static ssize_t stratum_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -906,6 +934,7 @@ static struct device_attribute *stp_attributes[] = { &dev_attr_dst_offset, &dev_attr_leap_seconds, &dev_attr_online, + &dev_attr_leap_seconds_scheduled, &dev_attr_stratum, &dev_attr_time_offset, &dev_attr_time_zone_offset, From ad5ceb33eee128346475f5efa672e6402ae15e51 Mon Sep 17 00:00:00 2001 From: Sven Schnelle Date: Mon, 21 Sep 2020 17:23:42 +0200 Subject: [PATCH 278/645] s390/stp: unify stp_work_mutex and clock_sync_mutex No need to have two mutexes, and while at it rename it to stp_mutex. Signed-off-by: Sven Schnelle Reviewed-by: Alexander Egorenkov Signed-off-by: Vasily Gorbik --- arch/s390/kernel/time.c | 53 ++++++++++++++++++++--------------------- 1 file changed, 26 insertions(+), 27 deletions(-) diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index da271f8ec8d6..0ac30ee2c633 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -296,7 +296,7 @@ void __init time_init(void) } static DEFINE_PER_CPU(atomic_t, clock_sync_word); -static DEFINE_MUTEX(clock_sync_mutex); +static DEFINE_MUTEX(stp_mutex); static unsigned long clock_sync_flags; #define CLOCK_SYNC_HAS_STP 0 @@ -445,7 +445,6 @@ static struct stp_sstpi stp_info; static void *stp_page; static void stp_work_fn(struct work_struct *work); -static DEFINE_MUTEX(stp_work_mutex); static DECLARE_WORK(stp_work, stp_work_fn); static struct timer_list stp_timer; @@ -683,7 +682,7 @@ static void stp_work_fn(struct work_struct *work) int rc; /* prevent multiple execution. */ - mutex_lock(&stp_work_mutex); + mutex_lock(&stp_mutex); if (!stp_online) { chsc_sstpc(stp_page, STP_OP_CTRL, 0x0000, NULL); @@ -718,7 +717,7 @@ static void stp_work_fn(struct work_struct *work) stp_check_leap(); out_unlock: - mutex_unlock(&stp_work_mutex); + mutex_unlock(&stp_mutex); } /* @@ -735,11 +734,11 @@ static ssize_t ctn_id_show(struct device *dev, { ssize_t ret = -ENODATA; - mutex_lock(&stp_work_mutex); + mutex_lock(&stp_mutex); if (stpinfo_valid()) ret = sprintf(buf, "%016llx\n", *(unsigned long long *) stp_info.ctnid); - mutex_unlock(&stp_work_mutex); + mutex_unlock(&stp_mutex); return ret; } @@ -751,10 +750,10 @@ static ssize_t ctn_type_show(struct device *dev, { ssize_t ret = -ENODATA; - mutex_lock(&stp_work_mutex); + mutex_lock(&stp_mutex); if (stpinfo_valid()) ret = sprintf(buf, "%i\n", stp_info.ctn); - mutex_unlock(&stp_work_mutex); + mutex_unlock(&stp_mutex); return ret; } @@ -766,10 +765,10 @@ static ssize_t dst_offset_show(struct device *dev, { ssize_t ret = -ENODATA; - mutex_lock(&stp_work_mutex); + mutex_lock(&stp_mutex); if (stpinfo_valid() && (stp_info.vbits & 0x2000)) ret = sprintf(buf, "%i\n", (int)(s16) stp_info.dsto); - mutex_unlock(&stp_work_mutex); + mutex_unlock(&stp_mutex); return ret; } @@ -781,10 +780,10 @@ static ssize_t leap_seconds_show(struct device *dev, { ssize_t ret = -ENODATA; - mutex_lock(&stp_work_mutex); + mutex_lock(&stp_mutex); if (stpinfo_valid() && (stp_info.vbits & 0x8000)) ret = sprintf(buf, "%i\n", (int)(s16) stp_info.leaps); - mutex_unlock(&stp_work_mutex); + mutex_unlock(&stp_mutex); return ret; } @@ -797,14 +796,14 @@ static ssize_t leap_seconds_scheduled_show(struct device *dev, struct stp_stzi stzi; ssize_t ret; - mutex_lock(&stp_work_mutex); + mutex_lock(&stp_mutex); if (!stpinfo_valid() || !(stp_info.vbits & 0x8000) || !stp_info.lu) { - mutex_unlock(&stp_work_mutex); + mutex_unlock(&stp_mutex); return -ENODATA; } ret = chsc_stzi(stp_page, &stzi, sizeof(stzi)); - mutex_unlock(&stp_work_mutex); + mutex_unlock(&stp_mutex); if (ret < 0) return ret; @@ -824,10 +823,10 @@ static ssize_t stratum_show(struct device *dev, { ssize_t ret = -ENODATA; - mutex_lock(&stp_work_mutex); + mutex_lock(&stp_mutex); if (stpinfo_valid()) ret = sprintf(buf, "%i\n", (int)(s16) stp_info.stratum); - mutex_unlock(&stp_work_mutex); + mutex_unlock(&stp_mutex); return ret; } @@ -839,10 +838,10 @@ static ssize_t time_offset_show(struct device *dev, { ssize_t ret = -ENODATA; - mutex_lock(&stp_work_mutex); + mutex_lock(&stp_mutex); if (stpinfo_valid() && (stp_info.vbits & 0x0800)) ret = sprintf(buf, "%i\n", (int) stp_info.tto); - mutex_unlock(&stp_work_mutex); + mutex_unlock(&stp_mutex); return ret; } @@ -854,10 +853,10 @@ static ssize_t time_zone_offset_show(struct device *dev, { ssize_t ret = -ENODATA; - mutex_lock(&stp_work_mutex); + mutex_lock(&stp_mutex); if (stpinfo_valid() && (stp_info.vbits & 0x4000)) ret = sprintf(buf, "%i\n", (int)(s16) stp_info.tzo); - mutex_unlock(&stp_work_mutex); + mutex_unlock(&stp_mutex); return ret; } @@ -869,10 +868,10 @@ static ssize_t timing_mode_show(struct device *dev, { ssize_t ret = -ENODATA; - mutex_lock(&stp_work_mutex); + mutex_lock(&stp_mutex); if (stpinfo_valid()) ret = sprintf(buf, "%i\n", stp_info.tmd); - mutex_unlock(&stp_work_mutex); + mutex_unlock(&stp_mutex); return ret; } @@ -884,10 +883,10 @@ static ssize_t timing_state_show(struct device *dev, { ssize_t ret = -ENODATA; - mutex_lock(&stp_work_mutex); + mutex_lock(&stp_mutex); if (stpinfo_valid()) ret = sprintf(buf, "%i\n", stp_info.tst); - mutex_unlock(&stp_work_mutex); + mutex_unlock(&stp_mutex); return ret; } @@ -911,14 +910,14 @@ static ssize_t online_store(struct device *dev, return -EINVAL; if (!test_bit(CLOCK_SYNC_HAS_STP, &clock_sync_flags)) return -EOPNOTSUPP; - mutex_lock(&clock_sync_mutex); + mutex_lock(&stp_mutex); stp_online = value; if (stp_online) set_bit(CLOCK_SYNC_STP, &clock_sync_flags); else clear_bit(CLOCK_SYNC_STP, &clock_sync_flags); queue_work(time_sync_wq, &stp_work); - mutex_unlock(&clock_sync_mutex); + mutex_unlock(&stp_mutex); return count; } From 2372b506115b411c6127c94798d575e0cf5b58b6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E5=91=A8=E7=90=B0=E6=9D=B0=20=28Zhou=20Yanjie=29?= Date: Tue, 22 Sep 2020 09:24:42 +0800 Subject: [PATCH 279/645] dt-bindings: MIPS: Add X2000E based CU2000-Neo. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add bindings for Ingenic X2000E based board, prepare for later dts. Signed-off-by: 周琰杰 (Zhou Yanjie) Signed-off-by: Thomas Bogendoerfer --- Documentation/devicetree/bindings/mips/ingenic/devices.yaml | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/Documentation/devicetree/bindings/mips/ingenic/devices.yaml b/Documentation/devicetree/bindings/mips/ingenic/devices.yaml index 83c86cbe4716..dc21b4630c25 100644 --- a/Documentation/devicetree/bindings/mips/ingenic/devices.yaml +++ b/Documentation/devicetree/bindings/mips/ingenic/devices.yaml @@ -47,4 +47,9 @@ properties: items: - const: yna,cu1830-neo - const: ingenic,x1830 + + - description: YSH & ATIL General Board, CU2000 Module with Neo Backplane + items: + - const: yna,cu2000-neo + - const: ingenic,x2000e ... From a9fee3a513e560b154ccbe662faa791d5f358875 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E5=91=A8=E7=90=B0=E6=9D=B0=20=28Zhou=20Yanjie=29?= Date: Tue, 22 Sep 2020 09:24:43 +0800 Subject: [PATCH 280/645] MIPS: Ingenic: Add system type for new Ingenic SoCs. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add JZ4775, X1000E, X2000, and X2000E system type for cat /proc/cpuinfo to give out JZ4775, X1000E, X2000 and X2000E. Signed-off-by: 周琰杰 (Zhou Yanjie) Reviewed-by: Paul Cercueil Signed-off-by: Thomas Bogendoerfer --- arch/mips/generic/board-ingenic.c | 12 ++++++++++++ arch/mips/include/asm/bootinfo.h | 2 ++ 2 files changed, 14 insertions(+) diff --git a/arch/mips/generic/board-ingenic.c b/arch/mips/generic/board-ingenic.c index 0d7de8f9713d..0cec0bea13d6 100644 --- a/arch/mips/generic/board-ingenic.c +++ b/arch/mips/generic/board-ingenic.c @@ -21,12 +21,20 @@ static __init char *ingenic_get_system_type(unsigned long machtype) { switch (machtype) { + case MACH_INGENIC_X2000E: + return "X2000E"; + case MACH_INGENIC_X2000: + return "X2000"; case MACH_INGENIC_X1830: return "X1830"; + case MACH_INGENIC_X1000E: + return "X1000E"; case MACH_INGENIC_X1000: return "X1000"; case MACH_INGENIC_JZ4780: return "JZ4780"; + case MACH_INGENIC_JZ4775: + return "JZ4775"; case MACH_INGENIC_JZ4770: return "JZ4770"; case MACH_INGENIC_JZ4725B: @@ -56,9 +64,13 @@ static const struct of_device_id ingenic_of_match[] __initconst = { { .compatible = "ingenic,jz4740", .data = (void *)MACH_INGENIC_JZ4740 }, { .compatible = "ingenic,jz4725b", .data = (void *)MACH_INGENIC_JZ4725B }, { .compatible = "ingenic,jz4770", .data = (void *)MACH_INGENIC_JZ4770 }, + { .compatible = "ingenic,jz4775", .data = (void *)MACH_INGENIC_JZ4775 }, { .compatible = "ingenic,jz4780", .data = (void *)MACH_INGENIC_JZ4780 }, { .compatible = "ingenic,x1000", .data = (void *)MACH_INGENIC_X1000 }, + { .compatible = "ingenic,x1000e", .data = (void *)MACH_INGENIC_X1000E }, { .compatible = "ingenic,x1830", .data = (void *)MACH_INGENIC_X1830 }, + { .compatible = "ingenic,x2000", .data = (void *)MACH_INGENIC_X2000 }, + { .compatible = "ingenic,x2000e", .data = (void *)MACH_INGENIC_X2000E }, {} }; diff --git a/arch/mips/include/asm/bootinfo.h b/arch/mips/include/asm/bootinfo.h index 147c9327ce04..6dd173a22aeb 100644 --- a/arch/mips/include/asm/bootinfo.h +++ b/arch/mips/include/asm/bootinfo.h @@ -79,8 +79,10 @@ enum ingenic_machine_type { MACH_INGENIC_JZ4775, MACH_INGENIC_JZ4780, MACH_INGENIC_X1000, + MACH_INGENIC_X1000E, MACH_INGENIC_X1830, MACH_INGENIC_X2000, + MACH_INGENIC_X2000E, }; extern char *system_type; From a5ce852398a4efc9df4869a71ff45b9dda58882d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E5=91=A8=E7=90=B0=E6=9D=B0=20=28Zhou=20Yanjie=29?= Date: Tue, 22 Sep 2020 09:24:44 +0800 Subject: [PATCH 281/645] MIPS: Ingenic: Fix bugs when detecting L2 cache of JZ4775 and X1000E. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 1.Fix bugs when detecting ways value of JZ4775's L2 cache. 2.Fix bugs when detecting sets value and ways value of X1000E's L2 cache. Signed-off-by: 周琰杰 (Zhou Yanjie) Reviewed-by: Paul Cercueil Signed-off-by: Thomas Bogendoerfer --- arch/mips/mm/sc-mips.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/mips/mm/sc-mips.c b/arch/mips/mm/sc-mips.c index 97dc0511e63f..dd0a5becaabd 100644 --- a/arch/mips/mm/sc-mips.c +++ b/arch/mips/mm/sc-mips.c @@ -228,6 +228,7 @@ static inline int __init mips_sc_probe(void) * contradicted by all documentation. */ case MACH_INGENIC_JZ4770: + case MACH_INGENIC_JZ4775: c->scache.ways = 4; break; @@ -236,6 +237,7 @@ static inline int __init mips_sc_probe(void) * but that is contradicted by all documentation. */ case MACH_INGENIC_X1000: + case MACH_INGENIC_X1000E: c->scache.sets = 256; c->scache.ways = 4; break; From ef923a76c398157a74ec52bd3c81fb77bcdc7cdd Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Thu, 17 Sep 2020 15:35:28 +0200 Subject: [PATCH 282/645] MIPS: Increase range of CONFIG_FORCE_MAX_ZONEORDER There is nothing that prevents us from using lower maximum values. It's something that we actually want, when using bigger page sizes on devices with low RAM. Signed-off-by: Paul Cercueil Signed-off-by: Thomas Bogendoerfer --- arch/mips/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index c08c98d654b1..b557fa578e62 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -2264,7 +2264,7 @@ config FORCE_MAX_ZONEORDER default "13" if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_32KB range 12 64 if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_16KB default "12" if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_16KB - range 11 64 + range 0 64 default "11" help The kernel memory allocator divides physically contiguous memory From 925b68822397eedc3b82d8c36929cec9cee26ec1 Mon Sep 17 00:00:00 2001 From: Pujin Shi Date: Sun, 27 Sep 2020 17:22:05 +0800 Subject: [PATCH 283/645] MIPS: idle: Add prototype for function check_wait This commit adds a prototype to fix warning at W=1: arch/mips/kernel/idle.c:126:13: error: no previous prototype for 'check_wait' [-Werror=missing-prototypes] Signed-off-by: Pujin Shi Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/idle.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/mips/include/asm/idle.h b/arch/mips/include/asm/idle.h index 655a6dbc861a..0992cad9c632 100644 --- a/arch/mips/include/asm/idle.h +++ b/arch/mips/include/asm/idle.h @@ -15,6 +15,8 @@ static inline int using_rollback_handler(void) return cpu_wait == r4k_wait; } +extern void __init check_wait(void); + extern int mips_cpuidle_wait_enter(struct cpuidle_device *dev, struct cpuidle_driver *drv, int index); From f2d10ff4a903813df767a4b56b651a26b938df06 Mon Sep 17 00:00:00 2001 From: Daniel Thompson Date: Sun, 27 Sep 2020 22:15:29 +0100 Subject: [PATCH 284/645] kgdb: Honour the kprobe blocklist when setting breakpoints Currently kgdb has absolutely no safety rails in place to discourage or prevent a user from placing a breakpoint in dangerous places such as the debugger's own trap entry/exit and other places where it is not safe to take synchronous traps. Introduce a new config symbol KGDB_HONOUR_BLOCKLIST and modify the default implementation of kgdb_validate_break_address() so that we use the kprobe blocklist to prohibit instrumentation of critical functions if the config symbol is set. The config symbol dependencies are set to ensure that the blocklist will be enabled by default if we enable KGDB and are compiling for an architecture where we HAVE_KPROBES. Suggested-by: Peter Zijlstra Reviewed-by: Douglas Anderson Reviewed-by: Masami Hiramatsu Link: https://lore.kernel.org/r/20200927211531.1380577-2-daniel.thompson@linaro.org Signed-off-by: Daniel Thompson --- include/linux/kgdb.h | 18 ++++++++++++++++++ kernel/debug/debug_core.c | 4 ++++ kernel/debug/kdb/kdb_bp.c | 9 +++++++++ lib/Kconfig.kgdb | 15 +++++++++++++++ 4 files changed, 46 insertions(+) diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index 477b8b7c908f..0d6cf64c8bb1 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -16,6 +16,7 @@ #include #include #include +#include #ifdef CONFIG_HAVE_ARCH_KGDB #include #endif @@ -335,6 +336,23 @@ extern int kgdb_nmicallin(int cpu, int trapnr, void *regs, int err_code, atomic_t *snd_rdy); extern void gdbstub_exit(int status); +/* + * kgdb and kprobes both use the same (kprobe) blocklist (which makes sense + * given they are both typically hooked up to the same trap meaning on most + * architectures one cannot be used to debug the other) + * + * However on architectures where kprobes is not (yet) implemented we permit + * breakpoints everywhere rather than blocking everything by default. + */ +static inline bool kgdb_within_blocklist(unsigned long addr) +{ +#ifdef CONFIG_KGDB_HONOUR_BLOCKLIST + return within_kprobe_blacklist(addr); +#else + return false; +#endif +} + extern int kgdb_single_step; extern atomic_t kgdb_active; #define in_dbg_master() \ diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index 165e5b0c2083..6b9383fa8278 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -180,6 +180,10 @@ int __weak kgdb_validate_break_address(unsigned long addr) { struct kgdb_bkpt tmp; int err; + + if (kgdb_within_blocklist(addr)) + return -EINVAL; + /* Validate setting the breakpoint and then removing it. If the * remove fails, the kernel needs to emit a bad message because we * are deep trouble not being able to put things back the way we diff --git a/kernel/debug/kdb/kdb_bp.c b/kernel/debug/kdb/kdb_bp.c index d7ebb2c79cb8..ec4940146612 100644 --- a/kernel/debug/kdb/kdb_bp.c +++ b/kernel/debug/kdb/kdb_bp.c @@ -306,6 +306,15 @@ static int kdb_bp(int argc, const char **argv) if (!template.bp_addr) return KDB_BADINT; + /* + * This check is redundant (since the breakpoint machinery should + * be doing the same check during kdb_bp_install) but gives the + * user immediate feedback. + */ + diag = kgdb_validate_break_address(template.bp_addr); + if (diag) + return diag; + /* * Find an empty bp structure to allocate */ diff --git a/lib/Kconfig.kgdb b/lib/Kconfig.kgdb index 256f2486f9bd..05dae05b6cc9 100644 --- a/lib/Kconfig.kgdb +++ b/lib/Kconfig.kgdb @@ -24,6 +24,21 @@ menuconfig KGDB if KGDB +config KGDB_HONOUR_BLOCKLIST + bool "KGDB: use kprobe blocklist to prohibit unsafe breakpoints" + depends on HAVE_KPROBES + depends on MODULES + select KPROBES + default y + help + If set to Y the debug core will use the kprobe blocklist to + identify symbols where it is unsafe to set breakpoints. + In particular this disallows instrumentation of functions + called during debug trap handling and thus makes it very + difficult to inadvertently provoke recursive trap handling. + + If unsure, say Y. + config KGDB_SERIAL_CONSOLE tristate "KGDB: use kgdb over the serial console" select CONSOLE_POLL From 62aacabc1301364446b36a418229c12a8e7162ba Mon Sep 17 00:00:00 2001 From: Qinglang Miao Date: Mon, 21 Sep 2020 21:11:01 +0800 Subject: [PATCH 285/645] s390/3215: simplify the return expression of tty3215_open() Simplify the return expression. Link: https://lkml.kernel.org/r/20200921131101.93037-1-miaoqinglang@huawei.com Signed-off-by: Qinglang Miao Signed-off-by: Vasily Gorbik --- drivers/s390/char/con3215.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/drivers/s390/char/con3215.c b/drivers/s390/char/con3215.c index 92757f9bd010..d8acabbb1ed3 100644 --- a/drivers/s390/char/con3215.c +++ b/drivers/s390/char/con3215.c @@ -978,7 +978,6 @@ static int tty3215_install(struct tty_driver *driver, struct tty_struct *tty) static int tty3215_open(struct tty_struct *tty, struct file * filp) { struct raw3215_info *raw = tty->driver_data; - int retval; tty_port_tty_set(&raw->port, tty); @@ -986,11 +985,7 @@ static int tty3215_open(struct tty_struct *tty, struct file * filp) /* * Start up 3215 device */ - retval = raw3215_startup(raw); - if (retval) - return retval; - - return 0; + return raw3215_startup(raw); } /* From 07a699bc43d1feb2abe3d47781e2db3d08554bcc Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Wed, 23 Sep 2020 09:37:43 +0200 Subject: [PATCH 286/645] s390/kaslr: avoid mixing valid random value and an error code 0 is a valid random value. To avoid mixing it with error code 0 as an return code make get_random() take extra argument to output random value and return an error code. Reviewed-by: Philipp Rudo Reviewed-by: Alexander Egorenkov Signed-off-by: Vasily Gorbik --- arch/s390/boot/kaslr.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/s390/boot/kaslr.c b/arch/s390/boot/kaslr.c index d4442163ffa9..c8549a0474e1 100644 --- a/arch/s390/boot/kaslr.c +++ b/arch/s390/boot/kaslr.c @@ -42,7 +42,7 @@ static int check_prng(void) return PRNG_MODE_TDES; } -static unsigned long get_random(unsigned long limit) +static int get_random(unsigned long limit, unsigned long *value) { struct prng_parm prng = { /* initial parameter block for tdes mode, copied from libica */ @@ -84,9 +84,10 @@ static unsigned long get_random(unsigned long limit) (u8 *) &random, sizeof(random)); break; default: - random = 0; + return -1; } - return random % limit; + *value = random % limit; + return 0; } unsigned long get_random_base(unsigned long safe_addr) @@ -143,8 +144,7 @@ unsigned long get_random_base(unsigned long safe_addr) return 0; } - base = get_random(block_sum); - if (base == 0) + if (get_random(block_sum, &base)) return 0; if (base < safe_addr) base = safe_addr; From 5c46f2768c4bbf8e0beebea9adac1320015816b7 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Fri, 18 Sep 2020 16:02:45 +0200 Subject: [PATCH 287/645] s390/kaslr: correct and explain randomization base generation Currently there are several minor problems with randomization base generation code: 1. It might misbehave in low memory conditions. In particular there might be enough space for the kernel on [0, block_sum] but after if (base < safe_addr) base = safe_addr; it might not be enough anymore. 2. It does not correctly handle minimal address constraint. In condition if (base < safe_addr) base = safe_addr; a synthetic value is compared with an address. If we have a memory setup with memory holes due to offline memory regions, and safe_addr is close to the end of the first online memory block - we might position the kernel in invalid memory. 3. block_sum calculation logic contains off-by-one error. Let's say we have a memory block in which the kernel fits perfectly (end - start == kernel_size). In this case: if (end - start < kernel_size) continue; block_sum += end - start - kernel_size; block_sum is not increased, while it is a valid kernel position. So, address problems listed and explain algorithm used. Besides that restructuring the code makes it possible to extend kernel positioning algorithm further. Currently we pick position in between single [min, max] range (min = safe_addr, max = memory_limit). In future we can do that for multiple ranges as well (by calling count_valid_kernel_positions for each range). Reviewed-by: Philipp Rudo Reviewed-by: Alexander Egorenkov Signed-off-by: Vasily Gorbik --- arch/s390/boot/kaslr.c | 130 +++++++++++++++++++++++++++++------------ 1 file changed, 92 insertions(+), 38 deletions(-) diff --git a/arch/s390/boot/kaslr.c b/arch/s390/boot/kaslr.c index c8549a0474e1..d844a5ef9089 100644 --- a/arch/s390/boot/kaslr.c +++ b/arch/s390/boot/kaslr.c @@ -90,14 +90,95 @@ static int get_random(unsigned long limit, unsigned long *value) return 0; } +/* + * To randomize kernel base address we have to consider several facts: + * 1. physical online memory might not be continuous and have holes. mem_detect + * info contains list of online memory ranges we should consider. + * 2. we have several memory regions which are occupied and we should not + * overlap and destroy them. Currently safe_addr tells us the border below + * which all those occupied regions are. We are safe to use anything above + * safe_addr. + * 3. the upper limit might apply as well, even if memory above that limit is + * online. Currently those limitations are: + * 3.1. Limit set by "mem=" kernel command line option + * 3.2. memory reserved at the end for kasan initialization. + * 4. kernel base address must be aligned to THREAD_SIZE (kernel stack size). + * Which is required for CONFIG_CHECK_STACK. Currently THREAD_SIZE is 4 pages + * (16 pages when the kernel is built with kasan enabled) + * Assumptions: + * 1. kernel size (including .bss size) and upper memory limit are page aligned. + * 2. mem_detect memory region start is THREAD_SIZE aligned / end is PAGE_SIZE + * aligned (in practice memory configurations granularity on z/VM and LPAR + * is 1mb). + * + * To guarantee uniform distribution of kernel base address among all suitable + * addresses we generate random value just once. For that we need to build a + * continuous range in which every value would be suitable. We can build this + * range by simply counting all suitable addresses (let's call them positions) + * which would be valid as kernel base address. To count positions we iterate + * over online memory ranges. For each range which is big enough for the + * kernel image we count all suitable addresses we can put the kernel image at + * that is + * (end - start - kernel_size) / THREAD_SIZE + 1 + * Two functions count_valid_kernel_positions and position_to_address help + * to count positions in memory range given and then convert position back + * to address. + */ +static unsigned long count_valid_kernel_positions(unsigned long kernel_size, + unsigned long _min, + unsigned long _max) +{ + unsigned long start, end, pos = 0; + int i; + + for_each_mem_detect_block(i, &start, &end) { + if (_min >= end) + continue; + if (start >= _max) + break; + start = max(_min, start); + end = min(_max, end); + if (end - start < kernel_size) + continue; + pos += (end - start - kernel_size) / THREAD_SIZE + 1; + } + + return pos; +} + +static unsigned long position_to_address(unsigned long pos, unsigned long kernel_size, + unsigned long _min, unsigned long _max) +{ + unsigned long start, end; + int i; + + for_each_mem_detect_block(i, &start, &end) { + if (_min >= end) + continue; + if (start >= _max) + break; + start = max(_min, start); + end = min(_max, end); + if (end - start < kernel_size) + continue; + if ((end - start - kernel_size) / THREAD_SIZE + 1 >= pos) + return start + (pos - 1) * THREAD_SIZE; + pos -= (end - start - kernel_size) / THREAD_SIZE + 1; + } + + return 0; +} + unsigned long get_random_base(unsigned long safe_addr) { - unsigned long memory_limit = memory_end_set ? memory_end : 0; - unsigned long base, start, end, kernel_size; - unsigned long block_sum, offset; + unsigned long memory_limit = get_mem_detect_end(); + unsigned long base_pos, max_pos, kernel_size; unsigned long kasan_needs; int i; + if (memory_end_set) + memory_limit = min(memory_limit, memory_end); + if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && INITRD_START && INITRD_SIZE) { if (safe_addr < INITRD_START + INITRD_SIZE) safe_addr = INITRD_START + INITRD_SIZE; @@ -127,44 +208,17 @@ unsigned long get_random_base(unsigned long safe_addr) } kernel_size = vmlinux.image_size + vmlinux.bss_size; - block_sum = 0; - for_each_mem_detect_block(i, &start, &end) { - if (memory_limit) { - if (start >= memory_limit) - break; - if (end > memory_limit) - end = memory_limit; - } - if (end - start < kernel_size) - continue; - block_sum += end - start - kernel_size; - } - if (!block_sum) { + if (safe_addr + kernel_size > memory_limit) + return 0; + + max_pos = count_valid_kernel_positions(kernel_size, safe_addr, memory_limit); + if (!max_pos) { sclp_early_printk("KASLR disabled: not enough memory\n"); return 0; } - if (get_random(block_sum, &base)) + /* we need a value in the range [1, base_pos] inclusive */ + if (get_random(max_pos, &base_pos)) return 0; - if (base < safe_addr) - base = safe_addr; - block_sum = offset = 0; - for_each_mem_detect_block(i, &start, &end) { - if (memory_limit) { - if (start >= memory_limit) - break; - if (end > memory_limit) - end = memory_limit; - } - if (end - start < kernel_size) - continue; - block_sum += end - start - kernel_size; - if (base <= block_sum) { - base = start + base - offset; - base = ALIGN_DOWN(base, THREAD_SIZE); - break; - } - offset = block_sum; - } - return base; + return position_to_address(base_pos + 1, kernel_size, safe_addr, memory_limit); } From 1c7c83e8d2351ee3d736094115e447a5da8e5369 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Thu, 24 Sep 2020 18:29:29 +0200 Subject: [PATCH 288/645] s390: remove unused _swsusp_reset_dma Since commit 394216275c7d ("s390: remove broken hibernate / power management support") _swsusp_reset_dma is unused and could be safely removed. Reviewed-by: Sven Schnelle Signed-off-by: Vasily Gorbik --- arch/s390/boot/startup.c | 2 -- arch/s390/boot/text_dma.S | 17 ----------------- arch/s390/include/asm/setup.h | 1 - arch/s390/kernel/setup.c | 1 - 4 files changed, 21 deletions(-) diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index 81835483169b..90842936545b 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -48,8 +48,6 @@ struct diag_ops __bootdata_preserved(diag_dma_ops) = { }; static struct diag210 _diag210_tmp_dma __section(.dma.data); struct diag210 *__bootdata_preserved(__diag210_tmp_dma) = &_diag210_tmp_dma; -void _swsusp_reset_dma(void); -unsigned long __bootdata_preserved(__swsusp_reset_dma) = __pa(_swsusp_reset_dma); void error(char *x) { diff --git a/arch/s390/boot/text_dma.S b/arch/s390/boot/text_dma.S index 9715715c4c28..f7c77cd518f2 100644 --- a/arch/s390/boot/text_dma.S +++ b/arch/s390/boot/text_dma.S @@ -96,23 +96,6 @@ ENTRY(_diag0c_dma) BR_EX_DMA_r14 ENDPROC(_diag0c_dma) -/* - * void _swsusp_reset_dma(void) - */ -ENTRY(_swsusp_reset_dma) - larl %r1,restart_entry - larl %r2,.Lrestart_diag308_psw - og %r1,0(%r2) - stg %r1,0(%r0) - lghi %r0,0 - diag %r0,%r0,0x308 -restart_entry: - lhi %r1,1 - sigp %r1,%r0,SIGP_SET_ARCHITECTURE - sam64 - BR_EX_DMA_r14 -ENDPROC(_swsusp_reset_dma) - /* * void _diag308_reset_dma(void) * diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h index 7b104f156e34..396db1638417 100644 --- a/arch/s390/include/asm/setup.h +++ b/arch/s390/include/asm/setup.h @@ -92,7 +92,6 @@ extern int memory_end_set; extern unsigned long memory_end; extern unsigned long vmalloc_size; extern unsigned long max_physmem_end; -extern unsigned long __swsusp_reset_dma; /* The Write Back bit position in the physaddr is given by the SLPC PCI */ extern unsigned long mio_wb_bit_mask; diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index ae2f4d946048..c1b78aae270b 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -102,7 +102,6 @@ struct mem_detect_info __bootdata(mem_detect); struct exception_table_entry *__bootdata_preserved(__start_dma_ex_table); struct exception_table_entry *__bootdata_preserved(__stop_dma_ex_table); -unsigned long __bootdata_preserved(__swsusp_reset_dma); unsigned long __bootdata_preserved(__stext_dma); unsigned long __bootdata_preserved(__etext_dma); unsigned long __bootdata_preserved(__sdma); From 2835c2ea95d50625108e47a459e1a47f6be836ce Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Thu, 24 Sep 2020 19:07:04 +0200 Subject: [PATCH 289/645] s390/startup: avoid save_area_sync overflow Currently we overflow save_area_sync and write over save_area_async. Although this is not a real problem make startup_pgm_check_handler consistent with late pgm check handler and store [%r0,%r7] directly into gpregs_save_area. Reviewed-by: Sven Schnelle Signed-off-by: Vasily Gorbik --- arch/s390/boot/head.S | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) diff --git a/arch/s390/boot/head.S b/arch/s390/boot/head.S index dae10961d072..1a2c2b1ed964 100644 --- a/arch/s390/boot/head.S +++ b/arch/s390/boot/head.S @@ -360,22 +360,23 @@ ENTRY(startup_kdump) # the save area and does disabled wait with a faulty address. # ENTRY(startup_pgm_check_handler) - stmg %r0,%r15,__LC_SAVE_AREA_SYNC - la %r1,4095 - stctg %c0,%c15,__LC_CREGS_SAVE_AREA-4095(%r1) - mvc __LC_GPREGS_SAVE_AREA-4095(128,%r1),__LC_SAVE_AREA_SYNC - mvc __LC_PSW_SAVE_AREA-4095(16,%r1),__LC_PGM_OLD_PSW + stmg %r8,%r15,__LC_SAVE_AREA_SYNC + la %r8,4095 + stctg %c0,%c15,__LC_CREGS_SAVE_AREA-4095(%r8) + stmg %r0,%r7,__LC_GPREGS_SAVE_AREA-4095(%r8) + mvc __LC_GPREGS_SAVE_AREA-4095+64(64,%r8),__LC_SAVE_AREA_SYNC + mvc __LC_PSW_SAVE_AREA-4095(16,%r8),__LC_PGM_OLD_PSW mvc __LC_RETURN_PSW(16),__LC_PGM_OLD_PSW ni __LC_RETURN_PSW,0xfc # remove IO and EX bits ni __LC_RETURN_PSW+1,0xfb # remove MCHK bit oi __LC_RETURN_PSW+1,0x2 # set wait state bit - larl %r2,.Lold_psw_disabled_wait - stg %r2,__LC_PGM_NEW_PSW+8 - l %r15,.Ldump_info_stack-.Lold_psw_disabled_wait(%r2) + larl %r9,.Lold_psw_disabled_wait + stg %r9,__LC_PGM_NEW_PSW+8 + l %r15,.Ldump_info_stack-.Lold_psw_disabled_wait(%r9) brasl %r14,print_pgm_check_info .Lold_psw_disabled_wait: - la %r1,4095 - lmg %r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r1) + la %r8,4095 + lmg %r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r8) lpswe __LC_RETURN_PSW # disabled wait .Ldump_info_stack: .long 0x5000 + PAGE_SIZE - STACK_FRAME_OVERHEAD From ad3e6948f90ac3d71f9c03ec92009d99dfb561e9 Mon Sep 17 00:00:00 2001 From: Sven Schnelle Date: Mon, 28 Sep 2020 07:22:50 +0200 Subject: [PATCH 290/645] s390: remove cad commandline option remove the cad command line option as the instruction was never published and never used by userspace. Signed-off-by: Sven Schnelle Reviewed-by: Vasily Gorbik Acked-by: Christian Borntraeger Signed-off-by: Vasily Gorbik --- arch/s390/kernel/early.c | 13 ------------- 1 file changed, 13 deletions(-) diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index 078277231858..705844f73934 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -274,19 +274,6 @@ static int __init disable_vector_extension(char *str) } early_param("novx", disable_vector_extension); -static int __init cad_setup(char *str) -{ - bool enabled; - int rc; - - rc = kstrtobool(str, &enabled); - if (!rc && enabled && test_facility(128)) - /* Enable problem state CAD. */ - __ctl_set_bit(2, 3); - return rc; -} -early_param("cad", cad_setup); - char __bootdata(early_command_line)[COMMAND_LINE_SIZE]; static void __init setup_boot_command_line(void) { From 54530ce6a184ed8c0accc3c50b659590ec445222 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Sat, 26 Sep 2020 00:08:54 +0200 Subject: [PATCH 291/645] s390/cio: remove unused channel_subsystem_reinit Added with commit 77e844b96440 ("s390/hibernate: add early resume function") unused since commit 394216275c7d ("s390: remove broken hibernate / power management support"). Reviewed-by: Vineeth Vijayan Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/cio.h | 1 - drivers/s390/cio/css.c | 14 -------------- 2 files changed, 15 deletions(-) diff --git a/arch/s390/include/asm/cio.h b/arch/s390/include/asm/cio.h index 953a7316b30a..5c58756d6476 100644 --- a/arch/s390/include/asm/cio.h +++ b/arch/s390/include/asm/cio.h @@ -356,7 +356,6 @@ static inline u8 pathmask_to_pos(u8 mask) return 8 - ffs(mask); } -void channel_subsystem_reinit(void); extern void css_schedule_reprobe(void); extern void *cio_dma_zalloc(size_t size); diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c index aca022239b33..c17d6c99f404 100644 --- a/drivers/s390/cio/css.c +++ b/drivers/s390/cio/css.c @@ -1350,20 +1350,6 @@ static int __init channel_subsystem_init_sync(void) } subsys_initcall_sync(channel_subsystem_init_sync); -void channel_subsystem_reinit(void) -{ - struct channel_path *chp; - struct chp_id chpid; - - chsc_enable_facility(CHSC_SDA_OC_MSS); - chp_id_for_each(&chpid) { - chp = chpid_to_chp(chpid); - if (chp) - chp_update_desc(chp); - } - cmf_reactivate(); -} - #ifdef CONFIG_PROC_FS static ssize_t cio_settle_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) From 3731ac579519d6c24ad2c5ac91959586b1919b5c Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Sun, 27 Sep 2020 21:34:55 +0200 Subject: [PATCH 292/645] s390/vdso: remove orphaned declarations Remove couple of declarations which are unused since commit 4bff8cb54502 ("s390: convert to GENERIC_VDSO"). Acked-by: Sven Schnelle Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/vdso.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/s390/include/asm/vdso.h b/arch/s390/include/asm/vdso.h index 82f86b3c394b..29b44a930e71 100644 --- a/arch/s390/include/asm/vdso.h +++ b/arch/s390/include/asm/vdso.h @@ -35,9 +35,7 @@ struct vdso_per_cpu_data { }; extern struct vdso_data *vdso_data; -extern struct vdso_data boot_vdso_data; -void vdso_alloc_boot_cpu(struct lowcore *lowcore); int vdso_alloc_per_cpu(struct lowcore *lowcore); void vdso_free_per_cpu(struct lowcore *lowcore); From 86cde618e718d0d286a565bcabfce5bdfc304685 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Fri, 25 Sep 2020 22:42:30 +0200 Subject: [PATCH 293/645] s390/startup: correct "dfltcc" option parsing Currently if just "dfltcc" is passed as a kernel command line option "val" going to be NULL, this leads to reading at address 0 in strcmp(val, "off") Fix that by making sure "val" is not NULL. This does not affect option handling logic. Reviewed-by: Sven Schnelle Signed-off-by: Vasily Gorbik --- arch/s390/boot/ipl_parm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/boot/ipl_parm.c b/arch/s390/boot/ipl_parm.c index 92ebc4a58fe2..1add096e09a6 100644 --- a/arch/s390/boot/ipl_parm.c +++ b/arch/s390/boot/ipl_parm.c @@ -230,7 +230,7 @@ void parse_boot_command_line(void) if (!strcmp(param, "vmalloc") && val) vmalloc_size = round_up(memparse(val, NULL), PAGE_SIZE); - if (!strcmp(param, "dfltcc")) { + if (!strcmp(param, "dfltcc") && val) { if (!strcmp(val, "off")) zlib_dfltcc_support = ZLIB_DFLTCC_DISABLED; else if (!strcmp(val, "on")) From f980ec9e34f8b0e74ba524cfc1b7bd9ff10ee6b4 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Sat, 26 Sep 2020 00:27:25 +0200 Subject: [PATCH 294/645] s390/sclp_sdias: remove unused sclp_sdias_exit sclp_sdias cannot be built as a module, CRASH_DUMP option is a bool not a tristate. zcore_exit() has already been removed with commit cbe62fac178c ("s390: char: make zcore explicitly non-modular"). Remove orphaned sclp_sdias_exit for consistency as well. Reviewed-by: Sven Schnelle Signed-off-by: Vasily Gorbik --- drivers/s390/char/sclp.h | 2 -- drivers/s390/char/sclp_sdias.c | 6 ------ 2 files changed, 8 deletions(-) diff --git a/drivers/s390/char/sclp.h b/drivers/s390/char/sclp.h index 196333013e54..ccc2d759c575 100644 --- a/drivers/s390/char/sclp.h +++ b/drivers/s390/char/sclp.h @@ -305,9 +305,7 @@ int sclp_deactivate(void); int sclp_reactivate(void); int sclp_sync_request(sclp_cmdw_t command, void *sccb); int sclp_sync_request_timeout(sclp_cmdw_t command, void *sccb, int timeout); - int sclp_sdias_init(void); -void sclp_sdias_exit(void); enum { sclp_init_state_uninitialized, diff --git a/drivers/s390/char/sclp_sdias.c b/drivers/s390/char/sclp_sdias.c index 644b61013679..be8cad61b4cf 100644 --- a/drivers/s390/char/sclp_sdias.c +++ b/drivers/s390/char/sclp_sdias.c @@ -275,9 +275,3 @@ out: TRACE("init done\n"); return 0; } - -void __exit sclp_sdias_exit(void) -{ - debug_unregister(sdias_dbf); - sclp_unregister(&sclp_sdias_register); -} From 3372e88b094e7ed463b92dc28e1121ec44fb6fbe Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Sat, 26 Sep 2020 00:38:41 +0200 Subject: [PATCH 295/645] s390/sclp: remove orphaned sclp_set_columns and sclp_set_htab sclp_set_columns and sclp_set_htab are leftovers since commit 095761d28ae4 ("[S390] sclp_tty: remove ioctl interface."), remove them as a dead code. Reviewed-by: Sven Schnelle Signed-off-by: Vasily Gorbik --- drivers/s390/char/sclp_rw.c | 18 ------------------ drivers/s390/char/sclp_rw.h | 2 -- 2 files changed, 20 deletions(-) diff --git a/drivers/s390/char/sclp_rw.c b/drivers/s390/char/sclp_rw.c index 44594a492553..d6c84e354df5 100644 --- a/drivers/s390/char/sclp_rw.c +++ b/drivers/s390/char/sclp_rw.c @@ -336,24 +336,6 @@ sclp_chars_in_buffer(struct sclp_buffer *buffer) return count; } -/* - * sets or provides some values that influence the drivers behaviour - */ -void -sclp_set_columns(struct sclp_buffer *buffer, unsigned short columns) -{ - buffer->columns = columns; - if (buffer->current_line != NULL && - buffer->current_length > buffer->columns) - sclp_finalize_mto(buffer); -} - -void -sclp_set_htab(struct sclp_buffer *buffer, unsigned short htab) -{ - buffer->htab = htab; -} - /* * called by sclp_console_init and/or sclp_tty_init */ diff --git a/drivers/s390/char/sclp_rw.h b/drivers/s390/char/sclp_rw.h index a2eb22f67393..93d706e4935c 100644 --- a/drivers/s390/char/sclp_rw.h +++ b/drivers/s390/char/sclp_rw.h @@ -86,8 +86,6 @@ void *sclp_unmake_buffer(struct sclp_buffer *); int sclp_buffer_space(struct sclp_buffer *); int sclp_write(struct sclp_buffer *buffer, const unsigned char *, int); int sclp_emit_buffer(struct sclp_buffer *,void (*)(struct sclp_buffer *,int)); -void sclp_set_columns(struct sclp_buffer *, unsigned short); -void sclp_set_htab(struct sclp_buffer *, unsigned short); int sclp_chars_in_buffer(struct sclp_buffer *); #ifdef CONFIG_SCLP_CONSOLE From 3ca8b855b0112906caecab88f04a8786a2d40906 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Sun, 11 Aug 2019 20:23:56 +0200 Subject: [PATCH 296/645] s390/startup: add kaslr_offset to pgm check info print startup pgm check handler is active since the very beginning of kernel code execution until uncompressed kernel sets up s390_base_pgm_handler. It is useful not just for the decompressor debugging itself, but also for early code of uncompressed kernel, in particular Kasan initialization. But since there is no stack trace or symbolic representation of failing psw address it is impossible to figure out faulty code location without knowing Kaslr kernel base. So, let's add it to the startup pgm check info printed as well. Reviewed-by: Sven Schnelle Signed-off-by: Vasily Gorbik --- arch/s390/boot/pgm_check_info.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/s390/boot/pgm_check_info.c b/arch/s390/boot/pgm_check_info.c index 83b5b7915c32..d3ab20ec517e 100644 --- a/arch/s390/boot/pgm_check_info.c +++ b/arch/s390/boot/pgm_check_info.c @@ -2,6 +2,7 @@ #include #include #include +#include #include #include "boot.h" @@ -42,6 +43,13 @@ void print_pgm_check_info(void) add_str(p, "\n"); sclp_early_printk(buf); + if (kaslr_enabled) { + p = add_str(buf, "Kernel random base: "); + p = add_val_as_hex(p, __kaslr_offset); + add_str(p, "\n"); + sclp_early_printk(buf); + } + p = add_str(buf, "PSW : "); p = add_val_as_hex(p, S390_lowcore.psw_save_area.mask); p = add_str(p, " "); From 402e9228f7a6a90e4fad44b358350ae358f1bc3c Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Sun, 27 Sep 2020 22:07:40 +0200 Subject: [PATCH 297/645] s390: remove orphaned function declarations arch/s390/pci/pci_bus.h: zpci_bus_init - only declaration left after commit 05bc1be6db4b ("s390/pci: create zPCI bus") arch/s390/include/asm/gmap.h: gmap_pte_notify - only declaration left after commit 4be130a08420 ("s390/mm: add shadow gmap support") arch/s390/include/asm/pgalloc.h: rcu_table_freelist_finish - only declaration left after commit 36409f6353fc ("[S390] use generic RCU page-table freeing code") arch/s390/include/asm/tlbflush.h: smp_ptlb_all - only declaration left after commit 5a79859ae0f3 ("s390: remove 31 bit support") arch/s390/include/asm/vtimer.h: init_cpu_vtimer - only declaration left after commit b5f87f15e200 ("s390/idle: consolidate idle functions and definitions") arch/s390/include/asm/pci.h: zpci_debug_info - only declaration left after commit 386aa051fb4b ("s390/pci: remove per device debug attribute") arch/s390/include/asm/vdso.h: vdso_alloc_boot_cpu - only declaration left after commit 4bff8cb54502 ("s390: convert to GENERIC_VDSO") arch/s390/include/asm/smp.h: smp_vcpu_scheduled - only declaration left after commit 67626fadd269 ("s390: enforce CONFIG_SMP") arch/s390/kernel/entry.h: restart_call_handler - only declaration left after commit 8b646bd75908 ("[S390] rework smp code") arch/s390/kernel/entry.h: startup_init_nobss - only declaration left after commit 2e83e0eb85ca ("s390: clean .bss before running uncompressed kernel") arch/s390/kernel/entry.h: s390_early_resume - only declaration left after commit 394216275c7d ("s390: remove broken hibernate / power management support") drivers/s390/char/raw3270.h: raw3270_request_alloc_bootmem - only declaration left after commit 33403dcfcdfd ("[S390] 3270 console: convert from bootmem to slab") drivers/s390/cio/device.h: ccw_device_schedule_sch_unregister - only declaration left after commit 37de53bb5290 ("[S390] cio: introduce ccw device todos") drivers/s390/char/tape.h: tape_hotplug_event - has only declaration since recorded git history. drivers/s390/char/tape.h: tape_oper_handler - has only declaration since recorded git history. drivers/s390/char/tape.h: tape_noper_handler - has only declaration since recorded git history. drivers/s390/char/tape_std.h: tape_std_check_locate - only declaration left after commit 161beff8f40d ("s390/tape: remove tape block leftovers") drivers/s390/char/tape_std.h: tape_std_default_handler - has only declaration since recorded git history. drivers/s390/char/tape_std.h: tape_std_unexpect_uchk_handler - has only declaration since recorded git history. drivers/s390/char/tape_std.h: tape_std_irq - has only declaration since recorded git history. drivers/s390/char/tape_std.h: tape_std_error_recovery - has only declaration since recorded git history. drivers/s390/char/tape_std.h: tape_std_error_recovery_has_failed - has only declaration since recorded git history. drivers/s390/char/tape_std.h: tape_std_error_recovery_succeded - has only declaration since recorded git history. drivers/s390/char/tape_std.h: tape_std_error_recovery_do_retry - has only declaration since recorded git history. drivers/s390/char/tape_std.h: tape_std_error_recovery_read_opposite - has only declaration since recorded git history. drivers/s390/char/tape_std.h: tape_std_error_recovery_HWBUG - has only declaration since recorded git history. Reviewed-by: Sven Schnelle Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/gmap.h | 2 -- arch/s390/include/asm/pci.h | 1 - arch/s390/include/asm/pgalloc.h | 2 -- arch/s390/include/asm/smp.h | 1 - arch/s390/include/asm/tlbflush.h | 2 -- arch/s390/include/asm/vtimer.h | 2 -- arch/s390/kernel/entry.h | 3 --- arch/s390/pci/pci_bus.h | 1 - drivers/s390/char/raw3270.h | 1 - drivers/s390/char/tape.h | 3 --- drivers/s390/char/tape_std.h | 12 ------------ drivers/s390/cio/device.h | 1 - 12 files changed, 31 deletions(-) diff --git a/arch/s390/include/asm/gmap.h b/arch/s390/include/asm/gmap.h index a816fb4734b8..40264f60b0da 100644 --- a/arch/s390/include/asm/gmap.h +++ b/arch/s390/include/asm/gmap.h @@ -140,8 +140,6 @@ int gmap_shadow_page(struct gmap *sg, unsigned long saddr, pte_t pte); void gmap_register_pte_notifier(struct gmap_notifier *); void gmap_unregister_pte_notifier(struct gmap_notifier *); -void gmap_pte_notify(struct mm_struct *, unsigned long addr, pte_t *, - unsigned long bits); int gmap_mprotect_notify(struct gmap *, unsigned long start, unsigned long len, int prot); diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index 178a24e0af5f..b5380a251df2 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -279,7 +279,6 @@ int zpci_debug_init(void); void zpci_debug_exit(void); void zpci_debug_init_device(struct zpci_dev *, const char *); void zpci_debug_exit_device(struct zpci_dev *); -void zpci_debug_info(struct zpci_dev *, struct seq_file *); /* Error reporting */ int zpci_report_error(struct pci_dev *, struct zpci_report_error_header *); diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index 74a352f8c0d1..d1297d6bbdcf 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -146,8 +146,6 @@ static inline void pmd_populate(struct mm_struct *mm, #define pte_free_kernel(mm, pte) page_table_free(mm, (unsigned long *) pte) #define pte_free(mm, pte) page_table_free(mm, (unsigned long *) pte) -extern void rcu_table_freelist_finish(void); - void vmem_map_init(void); void *vmem_crst_alloc(unsigned long val); pte_t *vmem_pte_alloc(void); diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h index 7e155fb6c254..01e360004481 100644 --- a/arch/s390/include/asm/smp.h +++ b/arch/s390/include/asm/smp.h @@ -31,7 +31,6 @@ extern void smp_emergency_stop(void); extern int smp_find_processor_id(u16 address); extern int smp_store_status(int cpu); extern void smp_save_dump_cpus(void); -extern int smp_vcpu_scheduled(int cpu); extern void smp_yield_cpu(int cpu); extern void smp_cpu_set_polarization(int cpu, int val); extern int smp_cpu_get_polarization(int cpu); diff --git a/arch/s390/include/asm/tlbflush.h b/arch/s390/include/asm/tlbflush.h index acce6a08a1fa..6448bb5be10c 100644 --- a/arch/s390/include/asm/tlbflush.h +++ b/arch/s390/include/asm/tlbflush.h @@ -30,8 +30,6 @@ static inline void __tlb_flush_idte(unsigned long asce) : : "a" (opt), "a" (asce) : "cc"); } -void smp_ptlb_all(void); - /* * Flush all TLB entries on all CPUs. */ diff --git a/arch/s390/include/asm/vtimer.h b/arch/s390/include/asm/vtimer.h index 42f707d1c1e8..e601adaa6320 100644 --- a/arch/s390/include/asm/vtimer.h +++ b/arch/s390/include/asm/vtimer.h @@ -25,8 +25,6 @@ extern void add_virt_timer_periodic(struct vtimer_list *timer); extern int mod_virt_timer(struct vtimer_list *timer, u64 expires); extern int mod_virt_timer_periodic(struct vtimer_list *timer, u64 expires); extern int del_virt_timer(struct vtimer_list *timer); - -extern void init_cpu_vtimer(void); extern void vtime_init(void); #endif /* _ASM_S390_TIMER_H */ diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index faca269d5f27..412a54e6aa81 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -17,7 +17,6 @@ void ext_int_handler(void); void io_int_handler(void); void mcck_int_handler(void); void restart_int_handler(void); -void restart_call_handler(void); asmlinkage long do_syscall_trace_enter(struct pt_regs *regs); asmlinkage void do_syscall_trace_exit(struct pt_regs *regs); @@ -61,12 +60,10 @@ void do_notify_resume(struct pt_regs *regs); void __init init_IRQ(void); void do_IRQ(struct pt_regs *regs, int irq); void do_restart(void); -void __init startup_init_nobss(void); void __init startup_init(void); void die(struct pt_regs *regs, const char *str); int setup_profiling_timer(unsigned int multiplier); void __init time_init(void); -void s390_early_resume(void); unsigned long prepare_ftrace_return(unsigned long parent, unsigned long sp, unsigned long ip); struct s390_mmap_arg_struct; diff --git a/arch/s390/pci/pci_bus.h b/arch/s390/pci/pci_bus.h index 8d19723ed5c0..f8dfac0b5b71 100644 --- a/arch/s390/pci/pci_bus.h +++ b/arch/s390/pci/pci_bus.h @@ -9,7 +9,6 @@ int zpci_bus_device_register(struct zpci_dev *zdev, struct pci_ops *ops); void zpci_bus_device_unregister(struct zpci_dev *zdev); -int zpci_bus_init(void); void zpci_release_device(struct kref *kref); static inline void zpci_zdev_put(struct zpci_dev *zdev) diff --git a/drivers/s390/char/raw3270.h b/drivers/s390/char/raw3270.h index 08f36e973b43..8d979e0ee605 100644 --- a/drivers/s390/char/raw3270.h +++ b/drivers/s390/char/raw3270.h @@ -110,7 +110,6 @@ struct raw3270_request { }; struct raw3270_request *raw3270_request_alloc(size_t size); -struct raw3270_request *raw3270_request_alloc_bootmem(size_t size); void raw3270_request_free(struct raw3270_request *); void raw3270_request_reset(struct raw3270_request *); void raw3270_request_set_cmd(struct raw3270_request *, u8 cmd); diff --git a/drivers/s390/char/tape.h b/drivers/s390/char/tape.h index 8bec5f9ea92c..e2c60475dfa8 100644 --- a/drivers/s390/char/tape.h +++ b/drivers/s390/char/tape.h @@ -238,7 +238,6 @@ extern int tape_do_io(struct tape_device *, struct tape_request *); extern int tape_do_io_async(struct tape_device *, struct tape_request *); extern int tape_do_io_interruptible(struct tape_device *, struct tape_request *); extern int tape_cancel_io(struct tape_device *, struct tape_request *); -void tape_hotplug_event(struct tape_device *, int major, int action); static inline int tape_do_io_free(struct tape_device *device, struct tape_request *request) @@ -258,8 +257,6 @@ tape_do_io_async_free(struct tape_device *device, struct tape_request *request) tape_do_io_async(device, request); } -extern int tape_oper_handler(int irq, int status); -extern void tape_noper_handler(int irq, int status); extern int tape_open(struct tape_device *); extern int tape_release(struct tape_device *); extern int tape_mtop(struct tape_device *, int, int); diff --git a/drivers/s390/char/tape_std.h b/drivers/s390/char/tape_std.h index 53ec8e2870d4..dcc63ff587f9 100644 --- a/drivers/s390/char/tape_std.h +++ b/drivers/s390/char/tape_std.h @@ -101,7 +101,6 @@ struct tape_request *tape_std_read_block(struct tape_device *, size_t); void tape_std_read_backward(struct tape_device *device, struct tape_request *request); struct tape_request *tape_std_write_block(struct tape_device *, size_t); -void tape_std_check_locate(struct tape_device *, struct tape_request *); /* Some non-mtop commands. */ int tape_std_assign(struct tape_device *); @@ -131,19 +130,8 @@ int tape_std_mtunload(struct tape_device *, int); int tape_std_mtweof(struct tape_device *, int); /* Event handlers */ -void tape_std_default_handler(struct tape_device *); -void tape_std_unexpect_uchk_handler(struct tape_device *); -void tape_std_irq(struct tape_device *); void tape_std_process_eov(struct tape_device *); -// the error recovery stuff: -void tape_std_error_recovery(struct tape_device *); -void tape_std_error_recovery_has_failed(struct tape_device *,int error_id); -void tape_std_error_recovery_succeded(struct tape_device *); -void tape_std_error_recovery_do_retry(struct tape_device *); -void tape_std_error_recovery_read_opposite(struct tape_device *); -void tape_std_error_recovery_HWBUG(struct tape_device *, int condno); - /* S390 tape types */ enum s390_tape_type { tape_3480, diff --git a/drivers/s390/cio/device.h b/drivers/s390/cio/device.h index f5c427ec24b1..853b6a8ca095 100644 --- a/drivers/s390/cio/device.h +++ b/drivers/s390/cio/device.h @@ -96,7 +96,6 @@ int ccw_device_online(struct ccw_device *); int ccw_device_offline(struct ccw_device *); void ccw_device_update_sense_data(struct ccw_device *); int ccw_device_test_sense_data(struct ccw_device *); -void ccw_device_schedule_sch_unregister(struct ccw_device *); int ccw_purge_blacklisted(void); void ccw_device_sched_todo(struct ccw_device *cdev, enum cdev_todo todo); struct ccw_device *get_ccwdev_by_dev_id(struct ccw_dev_id *dev_id); From 99419c310ee0f3f9aceff8966b2eeffc03ba76a5 Mon Sep 17 00:00:00 2001 From: Pujin Shi Date: Tue, 29 Sep 2020 17:30:46 +0800 Subject: [PATCH 298/645] MIPS: process: Add prototype for function arch_dup_task_struct This commit adds a prototype to fix warning at W=1: arch/mips/kernel/process.c:95:5: error: no previous prototype for 'arch_dup_task_struct' [-Werror=missing-prototypes] Signed-off-by: Pujin Shi Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/processor.h | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h index 856e12f6063d..7834e7c0c78a 100644 --- a/arch/mips/include/asm/processor.h +++ b/arch/mips/include/asm/processor.h @@ -29,6 +29,7 @@ */ extern unsigned int vced_count, vcei_count; +extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src); #ifdef CONFIG_32BIT #ifdef CONFIG_KVM_GUEST From 047248cab16b689b2a88ded960e1fd73c30b5510 Mon Sep 17 00:00:00 2001 From: Pujin Shi Date: Tue, 29 Sep 2020 17:30:47 +0800 Subject: [PATCH 299/645] MIPS: process: include exec.h header in process.c arch/mips/kernel/process.c:696:15: error: no previous prototype for 'arch_align_stack' [-Werror=missing-prototypes] Signed-off-by: Pujin Shi Signed-off-by: Thomas Bogendoerfer --- arch/mips/kernel/process.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index 37f05c8605c2..75ebd8d7bd5d 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -52,6 +52,7 @@ #include #include #include +#include #ifdef CONFIG_HOTPLUG_CPU void arch_cpu_idle_dead(void) From 4c4197eda710d197c7474abcceb3f8789ec22a64 Mon Sep 17 00:00:00 2001 From: Daniel Thompson Date: Sun, 27 Sep 2020 22:15:30 +0100 Subject: [PATCH 300/645] kgdb: Add NOKPROBE labels on the trap handler functions Currently kgdb honours the kprobe blocklist but doesn't place its own trap handling code on the list. Add labels to discourage attempting to use kgdb to debug itself. Not every functions that executes from the trap handler needs to be marked up: relatively early in the trap handler execution (just after we bring the other CPUs to a halt) all breakpoints are replaced with the original opcodes. This patch marks up code in the debug_core that executes between trap entry and the breakpoints being deactivated and, also, code that executes between breakpoint activation and trap exit. To be clear these changes are not sufficient to make recursive trapping impossible since they do not include library calls made during kgdb's entry/exit logic. However going much further whilst we are sharing the kprobe blocklist risks reducing the capabilities of kprobe and this would be a bad trade off (especially so given kgdb's users are currently conditioned to avoid recursive traps). Reviewed-by: Douglas Anderson Link: https://lore.kernel.org/r/20200927211531.1380577-3-daniel.thompson@linaro.org Signed-off-by: Daniel Thompson --- kernel/debug/debug_core.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index 6b9383fa8278..0761cbcbdd6d 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -169,12 +169,14 @@ int __weak kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt) arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE); return err; } +NOKPROBE_SYMBOL(kgdb_arch_set_breakpoint); int __weak kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt) { return copy_to_kernel_nofault((char *)bpt->bpt_addr, (char *)bpt->saved_instr, BREAK_INSTR_SIZE); } +NOKPROBE_SYMBOL(kgdb_arch_remove_breakpoint); int __weak kgdb_validate_break_address(unsigned long addr) { @@ -204,6 +206,7 @@ unsigned long __weak kgdb_arch_pc(int exception, struct pt_regs *regs) { return instruction_pointer(regs); } +NOKPROBE_SYMBOL(kgdb_arch_pc); int __weak kgdb_arch_init(void) { @@ -214,6 +217,7 @@ int __weak kgdb_skipexception(int exception, struct pt_regs *regs) { return 0; } +NOKPROBE_SYMBOL(kgdb_skipexception); #ifdef CONFIG_SMP @@ -235,6 +239,7 @@ void __weak kgdb_call_nmi_hook(void *ignored) */ kgdb_nmicallback(raw_smp_processor_id(), get_irq_regs()); } +NOKPROBE_SYMBOL(kgdb_call_nmi_hook); void __weak kgdb_roundup_cpus(void) { @@ -268,6 +273,7 @@ void __weak kgdb_roundup_cpus(void) kgdb_info[cpu].rounding_up = false; } } +NOKPROBE_SYMBOL(kgdb_roundup_cpus); #endif @@ -294,6 +300,7 @@ static void kgdb_flush_swbreak_addr(unsigned long addr) /* Force flush instruction cache if it was outside the mm */ flush_icache_range(addr, addr + BREAK_INSTR_SIZE); } +NOKPROBE_SYMBOL(kgdb_flush_swbreak_addr); /* * SW breakpoint management: @@ -321,6 +328,7 @@ int dbg_activate_sw_breakpoints(void) } return ret; } +NOKPROBE_SYMBOL(dbg_activate_sw_breakpoints); int dbg_set_sw_break(unsigned long addr) { @@ -384,6 +392,7 @@ int dbg_deactivate_sw_breakpoints(void) } return ret; } +NOKPROBE_SYMBOL(dbg_deactivate_sw_breakpoints); int dbg_remove_sw_break(unsigned long addr) { @@ -505,6 +514,7 @@ static int kgdb_io_ready(int print_wait) } return 1; } +NOKPROBE_SYMBOL(kgdb_io_ready); static int kgdb_reenter_check(struct kgdb_state *ks) { @@ -552,6 +562,7 @@ static int kgdb_reenter_check(struct kgdb_state *ks) return 1; } +NOKPROBE_SYMBOL(kgdb_reenter_check); static void dbg_touch_watchdogs(void) { @@ -559,6 +570,7 @@ static void dbg_touch_watchdogs(void) clocksource_touch_watchdog(); rcu_cpu_stall_reset(); } +NOKPROBE_SYMBOL(dbg_touch_watchdogs); static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs, int exception_state) @@ -790,6 +802,7 @@ kgdb_restore: return kgdb_info[cpu].ret_state; } +NOKPROBE_SYMBOL(kgdb_cpu_enter); /* * kgdb_handle_exception() - main entry point from a kernel exception @@ -834,6 +847,7 @@ out: arch_kgdb_ops.enable_nmi(1); return ret; } +NOKPROBE_SYMBOL(kgdb_handle_exception); /* * GDB places a breakpoint at this function to know dynamically loaded objects. @@ -868,6 +882,7 @@ int kgdb_nmicallback(int cpu, void *regs) #endif return 1; } +NOKPROBE_SYMBOL(kgdb_nmicallback); int kgdb_nmicallin(int cpu, int trapnr, void *regs, int err_code, atomic_t *send_ready) @@ -893,6 +908,7 @@ int kgdb_nmicallin(int cpu, int trapnr, void *regs, int err_code, #endif return 1; } +NOKPROBE_SYMBOL(kgdb_nmicallin); static void kgdb_console_write(struct console *co, const char *s, unsigned count) From 771910f719651789adee8260e1a2c4c0ba161007 Mon Sep 17 00:00:00 2001 From: Daniel Thompson Date: Sun, 27 Sep 2020 22:15:31 +0100 Subject: [PATCH 301/645] kernel: debug: Centralize dbg_[de]activate_sw_breakpoints During debug trap execution we expect dbg_deactivate_sw_breakpoints() to be paired with an dbg_activate_sw_breakpoint(). Currently although the calls are paired correctly they are needlessly smeared across three different functions. Worse this also results in code to drive polled I/O being called with breakpoints activated which, in turn, needlessly increases the set of functions that will recursively trap if breakpointed. Fix this by moving the activation of breakpoints into the debug core. Reviewed-by: Douglas Anderson Link: https://lore.kernel.org/r/20200927211531.1380577-4-daniel.thompson@linaro.org Signed-off-by: Daniel Thompson --- kernel/debug/debug_core.c | 2 ++ kernel/debug/gdbstub.c | 1 - kernel/debug/kdb/kdb_debugger.c | 2 -- 3 files changed, 2 insertions(+), 3 deletions(-) diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index 0761cbcbdd6d..1e75a8923a8d 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -760,6 +760,8 @@ cpu_master_loop: } } + dbg_activate_sw_breakpoints(); + /* Call the I/O driver's post_exception routine */ if (dbg_io_ops->post_exception) dbg_io_ops->post_exception(); diff --git a/kernel/debug/gdbstub.c b/kernel/debug/gdbstub.c index b52ebff09ac8..a77df59d9ca5 100644 --- a/kernel/debug/gdbstub.c +++ b/kernel/debug/gdbstub.c @@ -1061,7 +1061,6 @@ int gdb_serial_stub(struct kgdb_state *ks) error_packet(remcom_out_buffer, -EINVAL); break; } - dbg_activate_sw_breakpoints(); fallthrough; /* to default processing */ default: default_handle: diff --git a/kernel/debug/kdb/kdb_debugger.c b/kernel/debug/kdb/kdb_debugger.c index 53a0df6e4d92..0220afda3200 100644 --- a/kernel/debug/kdb/kdb_debugger.c +++ b/kernel/debug/kdb/kdb_debugger.c @@ -147,7 +147,6 @@ int kdb_stub(struct kgdb_state *ks) return DBG_PASS_EVENT; } kdb_bp_install(ks->linux_regs); - dbg_activate_sw_breakpoints(); /* Set the exit state to a single step or a continue */ if (KDB_STATE(DOING_SS)) gdbstub_state(ks, "s"); @@ -167,7 +166,6 @@ int kdb_stub(struct kgdb_state *ks) * differently vs the gdbstub */ kgdb_single_step = 0; - dbg_deactivate_sw_breakpoints(); return DBG_SWITCH_CPU_EVENT; } return kgdb_info[ks->cpu].ret_state; From d081a6e353168f15e63eb9e9334757f20343319f Mon Sep 17 00:00:00 2001 From: Daniel Thompson Date: Wed, 9 Sep 2020 15:17:08 +0100 Subject: [PATCH 302/645] kdb: Fix pager search for multi-line strings Currently using forward search doesn't handle multi-line strings correctly. The search routine replaces line breaks with \0 during the search and, for regular searches ("help | grep Common\n"), there is code after the line has been discarded or printed to replace the break character. However during a pager search ("help\n" followed by "/Common\n") when the string is matched we will immediately return to normal output and the code that should restore the \n becomes unreachable. Fix this by restoring the replaced character when we disable the search mode and update the comment accordingly. Fixes: fb6daa7520f9d ("kdb: Provide forward search at more prompt") Link: https://lore.kernel.org/r/20200909141708.338273-1-daniel.thompson@linaro.org Reviewed-by: Douglas Anderson Signed-off-by: Daniel Thompson --- kernel/debug/kdb/kdb_io.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c index e7835ca88e16..6735ac36b718 100644 --- a/kernel/debug/kdb/kdb_io.c +++ b/kernel/debug/kdb/kdb_io.c @@ -706,12 +706,16 @@ int vkdb_printf(enum kdb_msgsrc src, const char *fmt, va_list ap) size_avail = sizeof(kdb_buffer) - len; goto kdb_print_out; } - if (kdb_grepping_flag >= KDB_GREPPING_FLAG_SEARCH) + if (kdb_grepping_flag >= KDB_GREPPING_FLAG_SEARCH) { /* * This was a interactive search (using '/' at more - * prompt) and it has completed. Clear the flag. + * prompt) and it has completed. Replace the \0 with + * its original value to ensure multi-line strings + * are handled properly, and return to normal mode. */ + *cphold = replaced_byte; kdb_grepping_flag = 0; + } /* * at this point the string is a full line and * should be printed, up to the null. From d70e38cb1deef3b2acee4cd36d33fef4c98abf28 Mon Sep 17 00:00:00 2001 From: "Jason J. Herne" Date: Tue, 17 Mar 2020 09:23:41 -0400 Subject: [PATCH 303/645] s390: nvme dump support Add the nvme dump ipl type, associated data, and sysfs entries. This allows booting into a stand alone dump environment that resides on an nvme device. Signed-off-by: Jason J. Herne Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/ipl.h | 1 + arch/s390/kernel/ipl.c | 71 ++++++++++++++++++++++++++++++++++++- 2 files changed, 71 insertions(+), 1 deletion(-) diff --git a/arch/s390/include/asm/ipl.h b/arch/s390/include/asm/ipl.h index 7d5cfdda5277..a72d195bf92d 100644 --- a/arch/s390/include/asm/ipl.h +++ b/arch/s390/include/asm/ipl.h @@ -66,6 +66,7 @@ enum ipl_type { IPL_TYPE_FCP_DUMP = 8, IPL_TYPE_NSS = 16, IPL_TYPE_NVME = 32, + IPL_TYPE_NVME_DUMP = 64, }; struct ipl_info diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 90a2a17239b0..c5f9d6f88d27 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -40,10 +40,12 @@ #define IPL_FCP_STR "fcp" #define IPL_FCP_DUMP_STR "fcp_dump" #define IPL_NVME_STR "nvme" +#define IPL_NVME_DUMP_STR "nvme_dump" #define IPL_NSS_STR "nss" #define DUMP_CCW_STR "ccw" #define DUMP_FCP_STR "fcp" +#define DUMP_NVME_STR "nvme" #define DUMP_NONE_STR "none" /* @@ -96,6 +98,8 @@ static char *ipl_type_str(enum ipl_type type) return IPL_NSS_STR; case IPL_TYPE_NVME: return IPL_NVME_STR; + case IPL_TYPE_NVME_DUMP: + return IPL_NVME_DUMP_STR; case IPL_TYPE_UNKNOWN: default: return IPL_UNKNOWN_STR; @@ -106,6 +110,7 @@ enum dump_type { DUMP_TYPE_NONE = 1, DUMP_TYPE_CCW = 2, DUMP_TYPE_FCP = 4, + DUMP_TYPE_NVME = 8, }; static char *dump_type_str(enum dump_type type) @@ -117,6 +122,8 @@ static char *dump_type_str(enum dump_type type) return DUMP_CCW_STR; case DUMP_TYPE_FCP: return DUMP_FCP_STR; + case DUMP_TYPE_NVME: + return DUMP_NVME_STR; default: return NULL; } @@ -144,6 +151,7 @@ static struct ipl_parameter_block *reipl_block_actual; static int dump_capabilities = DUMP_TYPE_NONE; static enum dump_type dump_type = DUMP_TYPE_NONE; static struct ipl_parameter_block *dump_block_fcp; +static struct ipl_parameter_block *dump_block_nvme; static struct ipl_parameter_block *dump_block_ccw; static struct sclp_ipl_info sclp_ipl_info; @@ -266,7 +274,10 @@ static __init enum ipl_type get_ipl_type(void) else return IPL_TYPE_FCP; case IPL_PBT_NVME: - return IPL_TYPE_NVME; + if (ipl_block.nvme.opt == IPL_PB0_NVME_OPT_DUMP) + return IPL_TYPE_NVME_DUMP; + else + return IPL_TYPE_NVME; } return IPL_TYPE_UNKNOWN; } @@ -324,6 +335,7 @@ static ssize_t sys_ipl_device_show(struct kobject *kobj, case IPL_TYPE_FCP_DUMP: return sprintf(page, "0.0.%04x\n", ipl_block.fcp.devno); case IPL_TYPE_NVME: + case IPL_TYPE_NVME_DUMP: return sprintf(page, "%08ux\n", ipl_block.nvme.fid); default: return 0; @@ -531,6 +543,7 @@ static int __init ipl_init(void) rc = sysfs_create_group(&ipl_kset->kobj, &ipl_fcp_attr_group); break; case IPL_TYPE_NVME: + case IPL_TYPE_NVME_DUMP: rc = sysfs_create_group(&ipl_kset->kobj, &ipl_nvme_attr_group); break; default: @@ -1109,6 +1122,7 @@ static void __reipl_run(void *unused) diag308(DIAG308_LOAD_CLEAR, NULL); break; case IPL_TYPE_FCP_DUMP: + case IPL_TYPE_NVME_DUMP: break; } disabled_wait(); @@ -1382,6 +1396,29 @@ static struct attribute_group dump_fcp_attr_group = { .attrs = dump_fcp_attrs, }; +/* NVME dump device attributes */ +DEFINE_IPL_ATTR_RW(dump_nvme, fid, "0x%08llx\n", "%llx\n", + dump_block_nvme->nvme.fid); +DEFINE_IPL_ATTR_RW(dump_nvme, nsid, "0x%08llx\n", "%llx\n", + dump_block_nvme->nvme.nsid); +DEFINE_IPL_ATTR_RW(dump_nvme, bootprog, "%lld\n", "%llx\n", + dump_block_nvme->nvme.bootprog); +DEFINE_IPL_ATTR_RW(dump_nvme, br_lba, "%lld\n", "%llx\n", + dump_block_nvme->nvme.br_lba); + +static struct attribute *dump_nvme_attrs[] = { + &sys_dump_nvme_fid_attr.attr, + &sys_dump_nvme_nsid_attr.attr, + &sys_dump_nvme_bootprog_attr.attr, + &sys_dump_nvme_br_lba_attr.attr, + NULL, +}; + +static struct attribute_group dump_nvme_attr_group = { + .name = IPL_NVME_STR, + .attrs = dump_nvme_attrs, +}; + /* CCW dump device attributes */ DEFINE_IPL_CCW_ATTR_RW(dump_ccw, device, dump_block_ccw->ccw); @@ -1423,6 +1460,8 @@ static ssize_t dump_type_store(struct kobject *kobj, rc = dump_set_type(DUMP_TYPE_CCW); else if (strncmp(buf, DUMP_FCP_STR, strlen(DUMP_FCP_STR)) == 0) rc = dump_set_type(DUMP_TYPE_FCP); + else if (strncmp(buf, DUMP_NVME_STR, strlen(DUMP_NVME_STR)) == 0) + rc = dump_set_type(DUMP_TYPE_NVME); return (rc != 0) ? rc : len; } @@ -1450,6 +1489,9 @@ static void __dump_run(void *unused) case DUMP_TYPE_FCP: diag308_dump(dump_block_fcp); break; + case DUMP_TYPE_NVME: + diag308_dump(dump_block_nvme); + break; default: break; } @@ -1506,6 +1548,29 @@ static int __init dump_fcp_init(void) return 0; } +static int __init dump_nvme_init(void) +{ + int rc; + + if (!sclp_ipl_info.has_dump) + return 0; /* LDIPL DUMP is not installed */ + dump_block_nvme = (void *) get_zeroed_page(GFP_KERNEL); + if (!dump_block_nvme) + return -ENOMEM; + rc = sysfs_create_group(&dump_kset->kobj, &dump_nvme_attr_group); + if (rc) { + free_page((unsigned long)dump_block_nvme); + return rc; + } + dump_block_nvme->hdr.len = IPL_BP_NVME_LEN; + dump_block_nvme->hdr.version = IPL_PARM_BLOCK_VERSION; + dump_block_nvme->fcp.len = IPL_BP0_NVME_LEN; + dump_block_nvme->fcp.pbt = IPL_PBT_NVME; + dump_block_nvme->fcp.opt = IPL_PB0_NVME_OPT_DUMP; + dump_capabilities |= DUMP_TYPE_NVME; + return 0; +} + static int __init dump_init(void) { int rc; @@ -1522,6 +1587,9 @@ static int __init dump_init(void) if (rc) return rc; rc = dump_fcp_init(); + if (rc) + return rc; + rc = dump_nvme_init(); if (rc) return rc; dump_set_type(DUMP_TYPE_NONE); @@ -1956,6 +2024,7 @@ void __init setup_ipl(void) ipl_info.data.fcp.lun = ipl_block.fcp.lun; break; case IPL_TYPE_NVME: + case IPL_TYPE_NVME_DUMP: ipl_info.data.nvme.fid = ipl_block.nvme.fid; ipl_info.data.nvme.nsid = ipl_block.nvme.nsid; break; From d9f12e48d08ec08ace574050a838e001e442ee38 Mon Sep 17 00:00:00 2001 From: Alexander Egorenkov Date: Tue, 29 Sep 2020 20:23:17 +0200 Subject: [PATCH 304/645] s390/ipl: support NVMe IPL kernel parameters Enable extracting of extra kernel command-line parameters from the NVMe IPL block passed by the firmware to the kernel at boot. Signed-off-by: Alexander Egorenkov Reviewed-by: Vasily Gorbik Reviewed-by: Philipp Rudo Signed-off-by: Vasily Gorbik --- arch/s390/boot/ipl_parm.c | 31 +++++++++++++++++++++++-------- 1 file changed, 23 insertions(+), 8 deletions(-) diff --git a/arch/s390/boot/ipl_parm.c b/arch/s390/boot/ipl_parm.c index 1add096e09a6..f26c34e6f1e6 100644 --- a/arch/s390/boot/ipl_parm.c +++ b/arch/s390/boot/ipl_parm.c @@ -70,30 +70,44 @@ static size_t scpdata_length(const u8 *buf, size_t count) static size_t ipl_block_get_ascii_scpdata(char *dest, size_t size, const struct ipl_parameter_block *ipb) { - size_t count; - size_t i; + const __u8 *scp_data; + __u32 scp_data_len; int has_lowercase; + size_t count = 0; + size_t i; - count = min(size - 1, scpdata_length(ipb->fcp.scp_data, - ipb->fcp.scp_data_len)); + switch (ipb->pb0_hdr.pbt) { + case IPL_PBT_FCP: + scp_data_len = ipb->fcp.scp_data_len; + scp_data = ipb->fcp.scp_data; + break; + case IPL_PBT_NVME: + scp_data_len = ipb->nvme.scp_data_len; + scp_data = ipb->nvme.scp_data; + break; + default: + goto out; + } + + count = min(size - 1, scpdata_length(scp_data, scp_data_len)); if (!count) goto out; has_lowercase = 0; for (i = 0; i < count; i++) { - if (!isascii(ipb->fcp.scp_data[i])) { + if (!isascii(scp_data[i])) { count = 0; goto out; } - if (!has_lowercase && islower(ipb->fcp.scp_data[i])) + if (!has_lowercase && islower(scp_data[i])) has_lowercase = 1; } if (has_lowercase) - memcpy(dest, ipb->fcp.scp_data, count); + memcpy(dest, scp_data, count); else for (i = 0; i < count; i++) - dest[i] = tolower(ipb->fcp.scp_data[i]); + dest[i] = tolower(scp_data[i]); out: dest[count] = '\0'; return count; @@ -115,6 +129,7 @@ static void append_ipl_block_parm(void) parm, COMMAND_LINE_SIZE - len - 1, &ipl_block); break; case IPL_PBT_FCP: + case IPL_PBT_NVME: rc = ipl_block_get_ascii_scpdata( parm, COMMAND_LINE_SIZE - len - 1, &ipl_block); break; From bd37b36832f62bf42ab66da8744191d99252a6e3 Mon Sep 17 00:00:00 2001 From: Alexander Egorenkov Date: Tue, 29 Sep 2020 20:24:55 +0200 Subject: [PATCH 305/645] s390/nvme: support firmware-assisted dump to NVMe disks From the kernel perspective NVMe dump works exactly like zFCP dump. Therefore, adapt all places where code explicitly tests only for IPL of type FCP DUMP. And also set the memory end correctly in this case. Signed-off-by: Alexander Egorenkov Reviewed-by: Vasily Gorbik Reviewed-by: Philipp Rudo Signed-off-by: Vasily Gorbik --- arch/s390/boot/ipl_parm.c | 15 ++++++++++++--- arch/s390/include/asm/ipl.h | 6 ++++++ arch/s390/kernel/crash_dump.c | 16 ++++++++-------- arch/s390/kernel/setup.c | 4 ++-- arch/s390/kernel/smp.c | 12 ++++++------ drivers/s390/char/sclp_sdias.c | 2 +- drivers/s390/char/zcore.c | 17 ++++++++++++----- 7 files changed, 47 insertions(+), 25 deletions(-) diff --git a/arch/s390/boot/ipl_parm.c b/arch/s390/boot/ipl_parm.c index f26c34e6f1e6..f94b91d72620 100644 --- a/arch/s390/boot/ipl_parm.c +++ b/arch/s390/boot/ipl_parm.c @@ -280,14 +280,23 @@ void parse_boot_command_line(void) } } +static inline bool is_ipl_block_dump(void) +{ + if (ipl_block.pb0_hdr.pbt == IPL_PBT_FCP && + ipl_block.fcp.opt == IPL_PB0_FCP_OPT_DUMP) + return true; + if (ipl_block.pb0_hdr.pbt == IPL_PBT_NVME && + ipl_block.nvme.opt == IPL_PB0_NVME_OPT_DUMP) + return true; + return false; +} + void setup_memory_end(void) { #ifdef CONFIG_CRASH_DUMP if (OLDMEM_BASE) { kaslr_enabled = 0; - } else if (ipl_block_valid && - ipl_block.pb0_hdr.pbt == IPL_PBT_FCP && - ipl_block.fcp.opt == IPL_PB0_FCP_OPT_DUMP) { + } else if (ipl_block_valid && is_ipl_block_dump()) { kaslr_enabled = 0; if (!sclp_early_get_hsa_size(&memory_end) && memory_end) memory_end_set = 1; diff --git a/arch/s390/include/asm/ipl.h b/arch/s390/include/asm/ipl.h index a72d195bf92d..a9e2c7295b35 100644 --- a/arch/s390/include/asm/ipl.h +++ b/arch/s390/include/asm/ipl.h @@ -95,6 +95,12 @@ extern struct ipl_info ipl_info; extern void setup_ipl(void); extern void set_os_info_reipl_block(void); +static inline bool is_ipl_type_dump(void) +{ + return (ipl_info.type == IPL_TYPE_FCP_DUMP) || + (ipl_info.type == IPL_TYPE_NVME_DUMP); +} + struct ipl_report { struct ipl_parameter_block *ipib; struct list_head components; diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c index c42ce348103c..205b2e2648aa 100644 --- a/arch/s390/kernel/crash_dump.c +++ b/arch/s390/kernel/crash_dump.c @@ -141,7 +141,7 @@ int copy_oldmem_kernel(void *dst, void *src, size_t count) while (count) { from = __pa(src); if (!OLDMEM_BASE && from < sclp.hsa_size) { - /* Copy from zfcpdump HSA area */ + /* Copy from zfcp/nvme dump HSA area */ len = min(count, sclp.hsa_size - from); rc = memcpy_hsa_kernel(dst, from, len); if (rc) @@ -184,7 +184,7 @@ static int copy_oldmem_user(void __user *dst, void *src, size_t count) while (count) { from = __pa(src); if (!OLDMEM_BASE && from < sclp.hsa_size) { - /* Copy from zfcpdump HSA area */ + /* Copy from zfcp/nvme dump HSA area */ len = min(count, sclp.hsa_size - from); rc = memcpy_hsa_user(dst, from, len); if (rc) @@ -258,7 +258,7 @@ static int remap_oldmem_pfn_range_kdump(struct vm_area_struct *vma, } /* - * Remap "oldmem" for zfcpdump + * Remap "oldmem" for zfcp/nvme dump * * We only map available memory above HSA size. Memory below HSA size * is read on demand using the copy_oldmem_page() function. @@ -283,7 +283,7 @@ static int remap_oldmem_pfn_range_zfcpdump(struct vm_area_struct *vma, } /* - * Remap "oldmem" for kdump or zfcpdump + * Remap "oldmem" for kdump or zfcp/nvme dump */ int remap_oldmem_pfn_range(struct vm_area_struct *vma, unsigned long from, unsigned long pfn, unsigned long size, pgprot_t prot) @@ -632,11 +632,11 @@ int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size) u32 alloc_size; u64 hdr_off; - /* If we are not in kdump or zfcpdump mode return */ - if (!OLDMEM_BASE && ipl_info.type != IPL_TYPE_FCP_DUMP) + /* If we are not in kdump or zfcp/nvme dump mode return */ + if (!OLDMEM_BASE && !is_ipl_type_dump()) return 0; - /* If we cannot get HSA size for zfcpdump return error */ - if (ipl_info.type == IPL_TYPE_FCP_DUMP && !sclp.hsa_size) + /* If we cannot get HSA size for zfcp/nvme dump return error */ + if (is_ipl_type_dump() && !sclp.hsa_size) return -ENODEV; /* For kdump, exclude previous crashkernel memory */ diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index c1b78aae270b..419a0604959f 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -251,7 +251,7 @@ static void __init conmode_default(void) #ifdef CONFIG_CRASH_DUMP static void __init setup_zfcpdump(void) { - if (ipl_info.type != IPL_TYPE_FCP_DUMP) + if (!is_ipl_type_dump()) return; if (OLDMEM_BASE) return; @@ -1175,7 +1175,7 @@ void __init setup_arch(char **cmdline_p) if (IS_ENABLED(CONFIG_EXPOLINE)) nospec_init_branches(); - /* Setup zfcpdump support */ + /* Setup zfcp/nvme dump support */ setup_zfcpdump(); /* Add system specific data to the random pool */ diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 85700bd85f98..ebfe86d097f0 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -606,14 +606,14 @@ int smp_store_status(int cpu) /* * Collect CPU state of the previous, crashed system. * There are four cases: - * 1) standard zfcp dump - * condition: OLDMEM_BASE == NULL && ipl_info.type == IPL_TYPE_FCP_DUMP + * 1) standard zfcp/nvme dump + * condition: OLDMEM_BASE == NULL && is_ipl_type_dump() == true * The state for all CPUs except the boot CPU needs to be collected * with sigp stop-and-store-status. The boot CPU state is located in * the absolute lowcore of the memory stored in the HSA. The zcore code * will copy the boot CPU state from the HSA. - * 2) stand-alone kdump for SCSI (zfcp dump with swapped memory) - * condition: OLDMEM_BASE != NULL && ipl_info.type == IPL_TYPE_FCP_DUMP + * 2) stand-alone kdump for SCSI/NVMe (zfcp/nvme dump with swapped memory) + * condition: OLDMEM_BASE != NULL && is_ipl_type_dump() == true * The state for all CPUs except the boot CPU needs to be collected * with sigp stop-and-store-status. The firmware or the boot-loader * stored the registers of the boot CPU in the absolute lowcore in the @@ -660,7 +660,7 @@ void __init smp_save_dump_cpus(void) unsigned long page; bool is_boot_cpu; - if (!(OLDMEM_BASE || ipl_info.type == IPL_TYPE_FCP_DUMP)) + if (!(OLDMEM_BASE || is_ipl_type_dump())) /* No previous system present, normal boot. */ return; /* Allocate a page as dumping area for the store status sigps */ @@ -686,7 +686,7 @@ void __init smp_save_dump_cpus(void) /* Get the vector registers */ smp_save_cpu_vxrs(sa, addr, is_boot_cpu, page); /* - * For a zfcp dump OLDMEM_BASE == NULL and the registers + * For a zfcp/nvme dump OLDMEM_BASE == NULL and the registers * of the boot CPU are stored in the HSA. To retrieve * these registers an SCLP request is required which is * done by drivers/s390/char/zcore.c:init_cpu_info() diff --git a/drivers/s390/char/sclp_sdias.c b/drivers/s390/char/sclp_sdias.c index be8cad61b4cf..215d4b4a5ff5 100644 --- a/drivers/s390/char/sclp_sdias.c +++ b/drivers/s390/char/sclp_sdias.c @@ -257,7 +257,7 @@ static int __init sclp_sdias_init_async(void) int __init sclp_sdias_init(void) { - if (ipl_info.type != IPL_TYPE_FCP_DUMP) + if (!is_ipl_type_dump()) return 0; sclp_sdias_sccb = (void *) __get_free_page(GFP_KERNEL | GFP_DMA); BUG_ON(!sclp_sdias_sccb); diff --git a/drivers/s390/char/zcore.c b/drivers/s390/char/zcore.c index d29f1b71618e..1515fdc3c1ab 100644 --- a/drivers/s390/char/zcore.c +++ b/drivers/s390/char/zcore.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-1.0+ /* * zcore module to export memory content and register sets for creating system - * dumps on SCSI disks (zfcpdump). + * dumps on SCSI/NVMe disks (zfcp/nvme dump). * * For more information please refer to Documentation/s390/zfcpdump.rst * @@ -243,7 +243,7 @@ static int __init zcore_init(void) unsigned char arch; int rc; - if (ipl_info.type != IPL_TYPE_FCP_DUMP) + if (!is_ipl_type_dump()) return -ENODATA; if (OLDMEM_BASE) return -ENODATA; @@ -252,9 +252,16 @@ static int __init zcore_init(void) debug_register_view(zcore_dbf, &debug_sprintf_view); debug_set_level(zcore_dbf, 6); - TRACE("devno: %x\n", ipl_info.data.fcp.dev_id.devno); - TRACE("wwpn: %llx\n", (unsigned long long) ipl_info.data.fcp.wwpn); - TRACE("lun: %llx\n", (unsigned long long) ipl_info.data.fcp.lun); + if (ipl_info.type == IPL_TYPE_FCP_DUMP) { + TRACE("type: fcp\n"); + TRACE("devno: %x\n", ipl_info.data.fcp.dev_id.devno); + TRACE("wwpn: %llx\n", (unsigned long long) ipl_info.data.fcp.wwpn); + TRACE("lun: %llx\n", (unsigned long long) ipl_info.data.fcp.lun); + } else if (ipl_info.type == IPL_TYPE_NVME_DUMP) { + TRACE("type: nvme\n"); + TRACE("fid: %x\n", ipl_info.data.nvme.fid); + TRACE("nsid: %x\n", ipl_info.data.nvme.nsid); + } rc = sclp_sdias_init(); if (rc) From 5627b9224b00334e4c91122ebbb8536a9a575969 Mon Sep 17 00:00:00 2001 From: Gerald Schaefer Date: Tue, 23 Jun 2020 19:10:08 +0200 Subject: [PATCH 306/645] s390/ipl: add support to control memory clearing for nvme re-IPL Re-IPL for nvme is currently done by using diag 308 with the "Load Clear" subcode, which means that all memory will be cleared. This can increase re-IPL duration considerably on very large machines. For list-directed IPL like nvme or fcp IPL, a "Load Normal" subcode was introduced with z14. The "Load Normal" diag 308 subcode allows to re-IPL without clearing memory. This patch adds a new "clear" sysfs attribute to /sys/firmware/reipl/nvme, which can be set to either "0" or "1" to disable or enable re-IPL with memory clearing. The default value is "0", which disables memory clearing. Signed-off-by: Gerald Schaefer Reviewed-by: Vasily Gorbik Tested-by: Alexander Egorenkov Signed-off-by: Vasily Gorbik --- arch/s390/kernel/ipl.c | 48 ++++++++++++++++++++++++++++++++++++------ 1 file changed, 42 insertions(+), 6 deletions(-) diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index c5f9d6f88d27..98b3aca1de8e 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -156,6 +156,7 @@ static struct ipl_parameter_block *dump_block_ccw; static struct sclp_ipl_info sclp_ipl_info; +static bool reipl_nvme_clear; static bool reipl_fcp_clear; static bool reipl_ccw_clear; @@ -886,6 +887,24 @@ static struct attribute_group reipl_nvme_attr_group = { .bin_attrs = reipl_nvme_bin_attrs }; +static ssize_t reipl_nvme_clear_show(struct kobject *kobj, + struct kobj_attribute *attr, char *page) +{ + return sprintf(page, "%u\n", reipl_nvme_clear); +} + +static ssize_t reipl_nvme_clear_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t len) +{ + if (strtobool(buf, &reipl_nvme_clear) < 0) + return -EINVAL; + return len; +} + +static struct kobj_attribute sys_reipl_nvme_clear_attr = + __ATTR(clear, 0644, reipl_nvme_clear_show, reipl_nvme_clear_store); + /* CCW reipl device attributes */ DEFINE_IPL_CCW_ATTR_RW(reipl_ccw, device, reipl_block_ccw->ccw); @@ -1112,7 +1131,10 @@ static void __reipl_run(void *unused) break; case IPL_TYPE_NVME: diag308(DIAG308_SET, reipl_block_nvme); - diag308(DIAG308_LOAD_CLEAR, NULL); + if (reipl_nvme_clear) + diag308(DIAG308_LOAD_CLEAR, NULL); + else + diag308(DIAG308_LOAD_NORMAL, NULL); break; case IPL_TYPE_NSS: diag308(DIAG308_SET, reipl_block_nss); @@ -1233,8 +1255,9 @@ static int __init reipl_fcp_init(void) &sys_reipl_fcp_clear_attr.attr); if (rc) goto out2; - } else + } else { reipl_fcp_clear = true; + } if (ipl_info.type == IPL_TYPE_FCP) { memcpy(reipl_block_fcp, &ipl_block, sizeof(ipl_block)); @@ -1280,10 +1303,16 @@ static int __init reipl_nvme_init(void) } rc = sysfs_create_group(&reipl_nvme_kset->kobj, &reipl_nvme_attr_group); - if (rc) { - kset_unregister(reipl_nvme_kset); - free_page((unsigned long) reipl_block_nvme); - return rc; + if (rc) + goto out1; + + if (test_facility(141)) { + rc = sysfs_create_file(&reipl_nvme_kset->kobj, + &sys_reipl_nvme_clear_attr.attr); + if (rc) + goto out2; + } else { + reipl_nvme_clear = true; } if (ipl_info.type == IPL_TYPE_NVME) { @@ -1304,6 +1333,13 @@ static int __init reipl_nvme_init(void) } reipl_capabilities |= IPL_TYPE_NVME; return 0; + +out2: + sysfs_remove_group(&reipl_nvme_kset->kobj, &reipl_nvme_attr_group); +out1: + kset_unregister(reipl_nvme_kset); + free_page((unsigned long) reipl_block_nvme); + return rc; } static int __init reipl_type_init(void) From 21a66717079c3d74e8573cd48743728e4a244507 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Thu, 24 Sep 2020 01:01:29 +0200 Subject: [PATCH 307/645] s390/kasan: make sure int handler always run with DAT on Since commit 998f5bbe3dbd ("s390/kasan: fix early pgm check handler execution") early pgm check handler is executed with DAT on if Kasan is enabled. Still there is a window between setup_lowcore_dat_off() and setup_lowcore_dat_on() when int handlers could be executed with DAT off under Kasan. If this happens the kernel ends up in pgm check loop due to Kasan shadow memory access attempts. With Kasan enabled paging is initialized much earlier and DAT flag has to be on at all times instrumented code is executed. Make sure int handlers are set up to be called with DAT on right away in this case. Signed-off-by: Vasily Gorbik --- arch/s390/kernel/setup.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 419a0604959f..dc4d461095cc 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -372,8 +372,12 @@ void __init arch_call_rest_init(void) static void __init setup_lowcore_dat_off(void) { + unsigned long int_psw_mask = PSW_KERNEL_BITS; struct lowcore *lc; + if (IS_ENABLED(CONFIG_KASAN)) + int_psw_mask |= PSW_MASK_DAT; + /* * Setup lowcore for boot cpu */ @@ -385,15 +389,15 @@ static void __init setup_lowcore_dat_off(void) lc->restart_psw.mask = PSW_KERNEL_BITS; lc->restart_psw.addr = (unsigned long) restart_int_handler; - lc->external_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_MCHECK; + lc->external_new_psw.mask = int_psw_mask | PSW_MASK_MCHECK; lc->external_new_psw.addr = (unsigned long) ext_int_handler; - lc->svc_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_MCHECK; + lc->svc_new_psw.mask = int_psw_mask | PSW_MASK_MCHECK; lc->svc_new_psw.addr = (unsigned long) system_call; - lc->program_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_MCHECK; + lc->program_new_psw.mask = int_psw_mask | PSW_MASK_MCHECK; lc->program_new_psw.addr = (unsigned long) pgm_check_handler; lc->mcck_new_psw.mask = PSW_KERNEL_BITS; lc->mcck_new_psw.addr = (unsigned long) mcck_int_handler; - lc->io_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_MCHECK; + lc->io_new_psw.mask = int_psw_mask | PSW_MASK_MCHECK; lc->io_new_psw.addr = (unsigned long) io_int_handler; lc->clock_comparator = clock_comparator_max; lc->nodat_stack = ((unsigned long) &init_thread_union) From 100a980c174bed82e0178766809ac664e59ca037 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Sun, 27 Sep 2020 01:34:25 +0200 Subject: [PATCH 308/645] s390: remove orphaned extern variables declarations arch/s390/kernel/entry.h: suspend_zero_pages - only declaration left after commit 394216275c7d ("s390: remove broken hibernate / power management support") arch/s390/include/asm/setup.h: vmhalt_cmd - only declaration left after commit 99ca4e582d4a ("[S390] kernel: Shutdown Actions Interface") arch/s390/include/asm/setup.h: vmpoff_cmd - only declaration left after commit 99ca4e582d4a ("[S390] kernel: Shutdown Actions Interface") Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/setup.h | 3 --- arch/s390/kernel/entry.h | 1 - 2 files changed, 4 deletions(-) diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h index 396db1638417..bdb242a1544e 100644 --- a/arch/s390/include/asm/setup.h +++ b/arch/s390/include/asm/setup.h @@ -121,9 +121,6 @@ extern unsigned int console_mode; extern unsigned int console_devno; extern unsigned int console_irq; -extern char vmhalt_cmd[]; -extern char vmpoff_cmd[]; - #define CONSOLE_IS_UNDEFINED (console_mode == 0) #define CONSOLE_IS_SCLP (console_mode == 1) #define CONSOLE_IS_3215 (console_mode == 2) diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index 412a54e6aa81..6475a885cd60 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -9,7 +9,6 @@ #include extern void *restart_stack; -extern unsigned long suspend_zero_pages; void system_call(void); void pgm_check_handler(void); From 4ec95ed312c4ce877fb04084991754cb8cd33f01 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Thu, 1 Oct 2020 02:22:54 +0200 Subject: [PATCH 309/645] s390/startup: correct early pgm check info formatting Early sclp console messages are printed in line mode on z/VM and LPAR, but under kvm newlines matter. Add a missing newline between "kernel version" and "Kernel fault". Signed-off-by: Vasily Gorbik --- arch/s390/boot/pgm_check_info.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/s390/boot/pgm_check_info.c b/arch/s390/boot/pgm_check_info.c index d3ab20ec517e..a3c9862bcede 100644 --- a/arch/s390/boot/pgm_check_info.c +++ b/arch/s390/boot/pgm_check_info.c @@ -33,7 +33,8 @@ void print_pgm_check_info(void) char *p; add_str(buf, "Linux version "); - strlcat(buf, kernel_version, sizeof(buf)); + strlcat(buf, kernel_version, sizeof(buf) - 1); + strlcat(buf, "\n", sizeof(buf)); sclp_early_printk(buf); p = add_str(buf, "Kernel fault: interruption code "); From 396c7d94c3bbe07ae00c9f694a5c731878843038 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Mon, 5 Oct 2020 11:42:19 +0200 Subject: [PATCH 310/645] MIPS: alchemy: Fix build breakage, if TOUCHSCREEN_WM97XX is disabled Only include wm97xx touchscreen probing code, if driver is enabled. Reported-by: kernel test robot Signed-off-by: Thomas Bogendoerfer --- arch/mips/alchemy/devboards/db1300.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/arch/mips/alchemy/devboards/db1300.c b/arch/mips/alchemy/devboards/db1300.c index 8ac1f56ee57d..cd72eaa1168f 100644 --- a/arch/mips/alchemy/devboards/db1300.c +++ b/arch/mips/alchemy/devboards/db1300.c @@ -731,6 +731,7 @@ static struct platform_device db1300_lcd_dev = { /**********************************************************************/ +#if IS_ENABLED(CONFIG_TOUCHSCREEN_WM97XX) static void db1300_wm97xx_irqen(struct wm97xx *wm, int enable) { if (enable) @@ -762,6 +763,12 @@ static int db1300_wm97xx_probe(struct platform_device *pdev) return wm97xx_register_mach_ops(wm, &db1300_wm97xx_ops); } +#else +static int db1300_wm97xx_probe(struct platform_device *pdev) +{ + return -ENODEV; +} +#endif static struct platform_driver db1300_wm97xx_driver = { .driver.name = "wm97xx-touch", From 026ba130a5e8861259d12fb9ae352e9ce408955d Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Mon, 5 Oct 2020 13:28:45 +0200 Subject: [PATCH 311/645] MIPS: alchemy: Share prom_init implementation All boards have the same prom_init() function. Move it to common code and delete the duplicates. Signed-off-by: Thomas Bogendoerfer --- arch/mips/alchemy/board-gpr.c | 17 ----------------- arch/mips/alchemy/board-mtx1.c | 17 ----------------- arch/mips/alchemy/board-xxs1500.c | 18 ------------------ arch/mips/alchemy/common/prom.c | 20 ++++++++++++++++++++ arch/mips/alchemy/devboards/platform.c | 17 ----------------- 5 files changed, 20 insertions(+), 69 deletions(-) diff --git a/arch/mips/alchemy/board-gpr.c b/arch/mips/alchemy/board-gpr.c index 6c47318946e4..f587c40b6d00 100644 --- a/arch/mips/alchemy/board-gpr.c +++ b/arch/mips/alchemy/board-gpr.c @@ -31,23 +31,6 @@ const char *get_system_type(void) return "GPR"; } -void __init prom_init(void) -{ - unsigned char *memsize_str; - unsigned long memsize; - - prom_argc = fw_arg0; - prom_argv = (char **)fw_arg1; - prom_envp = (char **)fw_arg2; - - prom_init_cmdline(); - - memsize_str = prom_getenv("memsize"); - if (!memsize_str || kstrtoul(memsize_str, 0, &memsize)) - memsize = 0x04000000; - add_memory_region(0, memsize, BOOT_MEM_RAM); -} - void prom_putchar(char c) { alchemy_uart_putchar(AU1000_UART0_PHYS_ADDR, c); diff --git a/arch/mips/alchemy/board-mtx1.c b/arch/mips/alchemy/board-mtx1.c index 23093535399f..68ea57511629 100644 --- a/arch/mips/alchemy/board-mtx1.c +++ b/arch/mips/alchemy/board-mtx1.c @@ -30,23 +30,6 @@ const char *get_system_type(void) return "MTX-1"; } -void __init prom_init(void) -{ - unsigned char *memsize_str; - unsigned long memsize; - - prom_argc = fw_arg0; - prom_argv = (char **)fw_arg1; - prom_envp = (char **)fw_arg2; - - prom_init_cmdline(); - - memsize_str = prom_getenv("memsize"); - if (!memsize_str || kstrtoul(memsize_str, 0, &memsize)) - memsize = 0x04000000; - add_memory_region(0, memsize, BOOT_MEM_RAM); -} - void prom_putchar(char c) { alchemy_uart_putchar(AU1000_UART0_PHYS_ADDR, c); diff --git a/arch/mips/alchemy/board-xxs1500.c b/arch/mips/alchemy/board-xxs1500.c index c67dfe1f4997..b184baa4e56a 100644 --- a/arch/mips/alchemy/board-xxs1500.c +++ b/arch/mips/alchemy/board-xxs1500.c @@ -25,24 +25,6 @@ const char *get_system_type(void) return "XXS1500"; } -void __init prom_init(void) -{ - unsigned char *memsize_str; - unsigned long memsize; - - prom_argc = fw_arg0; - prom_argv = (char **)fw_arg1; - prom_envp = (char **)fw_arg2; - - prom_init_cmdline(); - - memsize_str = prom_getenv("memsize"); - if (!memsize_str || kstrtoul(memsize_str, 0, &memsize)) - memsize = 0x04000000; - - add_memory_region(0, memsize, BOOT_MEM_RAM); -} - void prom_putchar(char c) { alchemy_uart_putchar(AU1000_UART0_PHYS_ADDR, c); diff --git a/arch/mips/alchemy/common/prom.c b/arch/mips/alchemy/common/prom.c index af312b5e33f6..cfa203064d3c 100644 --- a/arch/mips/alchemy/common/prom.c +++ b/arch/mips/alchemy/common/prom.c @@ -34,6 +34,8 @@ */ #include +#include +#include #include #include @@ -76,6 +78,24 @@ char *prom_getenv(char *envname) return NULL; } +void __init prom_init(void) +{ + unsigned char *memsize_str; + unsigned long memsize; + + prom_argc = (int)fw_arg0; + prom_argv = (char **)fw_arg1; + prom_envp = (char **)fw_arg2; + + prom_init_cmdline(); + + memsize_str = prom_getenv("memsize"); + if (!memsize_str || kstrtoul(memsize_str, 0, &memsize)) + memsize = SZ_64M; /* minimum memsize is 64MB RAM */ + + add_memory_region(0, memsize, BOOT_MEM_RAM); +} + static inline unsigned char str2hexnum(unsigned char c) { if (c >= '0' && c <= '9') diff --git a/arch/mips/alchemy/devboards/platform.c b/arch/mips/alchemy/devboards/platform.c index 8d4b65c3268a..754bdd2ca630 100644 --- a/arch/mips/alchemy/devboards/platform.c +++ b/arch/mips/alchemy/devboards/platform.c @@ -20,23 +20,6 @@ #include -void __init prom_init(void) -{ - unsigned char *memsize_str; - unsigned long memsize; - - prom_argc = (int)fw_arg0; - prom_argv = (char **)fw_arg1; - prom_envp = (char **)fw_arg2; - - prom_init_cmdline(); - memsize_str = prom_getenv("memsize"); - if (!memsize_str || kstrtoul(memsize_str, 0, &memsize)) - memsize = 64 << 20; /* all devboards have at least 64MB RAM */ - - add_memory_region(0, memsize, BOOT_MEM_RAM); -} - void prom_putchar(char c) { if (alchemy_get_cputype() == ALCHEMY_CPU_AU1300) From 9b7224836965550649357732f7f0b63a5bfcc305 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Mon, 5 Oct 2020 13:28:46 +0200 Subject: [PATCH 312/645] MIPS: pgtable: Remove used PAGE_USERIO define There are no users of PAGE_USERIO. Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/pgtable.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h index dd7a0f552cac..e5ef0fdd4838 100644 --- a/arch/mips/include/asm/pgtable.h +++ b/arch/mips/include/asm/pgtable.h @@ -37,8 +37,6 @@ struct vm_area_struct; _PAGE_GLOBAL | _page_cachable_default) #define PAGE_KERNEL_NC __pgprot(_PAGE_PRESENT | __READABLE | __WRITEABLE | \ _PAGE_GLOBAL | _CACHE_CACHABLE_NONCOHERENT) -#define PAGE_USERIO __pgprot(_PAGE_PRESENT | _PAGE_WRITE | \ - _page_cachable_default) #define PAGE_KERNEL_UNCACHED __pgprot(_PAGE_PRESENT | __READABLE | \ __WRITEABLE | _PAGE_GLOBAL | _CACHE_UNCACHED) From aea948bb80b478ddc2448f7359d574387521a52d Mon Sep 17 00:00:00 2001 From: Mahesh Salgaonkar Date: Tue, 6 Oct 2020 13:02:18 +0530 Subject: [PATCH 313/645] powerpc/powernv/elog: Fix race while processing OPAL error log event. Every error log reported by OPAL is exported to userspace through a sysfs interface and notified using kobject_uevent(). The userspace daemon (opal_errd) then reads the error log and acknowledges the error log is saved safely to disk. Once acknowledged the kernel removes the respective sysfs file entry causing respective resources to be released including kobject. However it's possible the userspace daemon may already be scanning elog entries when a new sysfs elog entry is created by the kernel. User daemon may read this new entry and ack it even before kernel can notify userspace about it through kobject_uevent() call. If that happens then we have a potential race between elog_ack_store->kobject_put() and kobject_uevent which can lead to use-after-free of a kernfs object resulting in a kernel crash. eg: BUG: Unable to handle kernel data access on read at 0x6b6b6b6b6b6b6bfb Faulting instruction address: 0xc0000000008ff2a0 Oops: Kernel access of bad area, sig: 11 [#1] LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA PowerNV CPU: 27 PID: 805 Comm: irq/29-opal-elo Not tainted 5.9.0-rc2-gcc-8.2.0-00214-g6f56a67bcbb5-dirty #363 ... NIP kobject_uevent_env+0xa0/0x910 LR elog_event+0x1f4/0x2d0 Call Trace: 0x5deadbeef0000122 (unreliable) elog_event+0x1f4/0x2d0 irq_thread_fn+0x4c/0xc0 irq_thread+0x1c0/0x2b0 kthread+0x1c4/0x1d0 ret_from_kernel_thread+0x5c/0x6c This patch fixes this race by protecting the sysfs file creation/notification by holding a reference count on kobject until we safely send kobject_uevent(). The function create_elog_obj() returns the elog object which if used by caller function will end up in use-after-free problem again. However, the return value of create_elog_obj() function isn't being used today and there is no need as well. Hence change it to return void to make this fix complete. Fixes: 774fea1a38c6 ("powerpc/powernv: Read OPAL error log and export it through sysfs") Cc: stable@vger.kernel.org # v3.15+ Reported-by: Oliver O'Halloran Signed-off-by: Mahesh Salgaonkar Signed-off-by: Aneesh Kumar K.V Reviewed-by: Oliver O'Halloran Reviewed-by: Vasant Hegde [mpe: Rework the logic to use a single return, reword comments, add oops] Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20201006122051.190176-1-mpe@ellerman.id.au --- arch/powerpc/platforms/powernv/opal-elog.c | 33 +++++++++++++++++----- 1 file changed, 26 insertions(+), 7 deletions(-) diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c index 62ef7ad995da..5e33b1fc67c2 100644 --- a/arch/powerpc/platforms/powernv/opal-elog.c +++ b/arch/powerpc/platforms/powernv/opal-elog.c @@ -179,14 +179,14 @@ static ssize_t raw_attr_read(struct file *filep, struct kobject *kobj, return count; } -static struct elog_obj *create_elog_obj(uint64_t id, size_t size, uint64_t type) +static void create_elog_obj(uint64_t id, size_t size, uint64_t type) { struct elog_obj *elog; int rc; elog = kzalloc(sizeof(*elog), GFP_KERNEL); if (!elog) - return NULL; + return; elog->kobj.kset = elog_kset; @@ -219,18 +219,37 @@ static struct elog_obj *create_elog_obj(uint64_t id, size_t size, uint64_t type) rc = kobject_add(&elog->kobj, NULL, "0x%llx", id); if (rc) { kobject_put(&elog->kobj); - return NULL; + return; } + /* + * As soon as the sysfs file for this elog is created/activated there is + * a chance the opal_errd daemon (or any userspace) might read and + * acknowledge the elog before kobject_uevent() is called. If that + * happens then there is a potential race between + * elog_ack_store->kobject_put() and kobject_uevent() which leads to a + * use-after-free of a kernfs object resulting in a kernel crash. + * + * To avoid that, we need to take a reference on behalf of the bin file, + * so that our reference remains valid while we call kobject_uevent(). + * We then drop our reference before exiting the function, leaving the + * bin file to drop the last reference (if it hasn't already). + */ + + /* Take a reference for the bin file */ + kobject_get(&elog->kobj); rc = sysfs_create_bin_file(&elog->kobj, &elog->raw_attr); - if (rc) { + if (rc == 0) { + kobject_uevent(&elog->kobj, KOBJ_ADD); + } else { + /* Drop the reference taken for the bin file */ kobject_put(&elog->kobj); - return NULL; } - kobject_uevent(&elog->kobj, KOBJ_ADD); + /* Drop our reference */ + kobject_put(&elog->kobj); - return elog; + return; } static irqreturn_t elog_event(int irq, void *data) From 9983efa83b0a98da33807ccf5c047e204fdcac4c Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Wed, 16 Sep 2020 13:02:33 +1000 Subject: [PATCH 314/645] powerpc: untangle cputable mce include Having cputable.h include mce.h means it pulls in a bunch of low level headers (e.g., synch.h) which then can't use CPU_FTR_ definitions. Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200916030234.4110379-1-npiggin@gmail.com --- arch/powerpc/include/asm/cputable.h | 5 ----- arch/powerpc/kernel/cputable.c | 1 + arch/powerpc/kernel/dt_cpu_ftrs.c | 1 + 3 files changed, 2 insertions(+), 5 deletions(-) diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index 8ca5885bd5b9..a1a300c1a20e 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -9,11 +9,6 @@ #ifndef __ASSEMBLY__ -/* - * Added to include __machine_check_early_realmode_* functions - */ -#include - /* This structure can grow, it's real size is used by head.S code * via the mkdefs mechanism. */ diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 2aa89c6b2896..b5bc2edef440 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -16,6 +16,7 @@ #include #include #include /* for PTRRELOC on ARCH=ppc */ +#include #include #include diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index f204ad79b6b5..1098863e17ee 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -17,6 +17,7 @@ #include #include +#include #include #include #include From 05504b42562066ae27ce3e7dcec37f81dea476cb Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Wed, 16 Sep 2020 13:02:34 +1000 Subject: [PATCH 315/645] powerpc/64s: Add cp_abort after tlbiel to invalidate copy-buffer address The copy buffer is implemented as a real address in the nest which is translated from EA by copy, and used for memory access by paste. This requires that it be invalidated by TLB invalidation. TLBIE does invalidate the copy buffer, but TLBIEL does not. Add cp_abort to the tlbiel sequence. Signed-off-by: Nicholas Piggin [mpe: Fixup whitespace and comment formatting] Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200916030234.4110379-2-npiggin@gmail.com --- arch/powerpc/include/asm/synch.h | 19 ++++++++++++++++++- arch/powerpc/mm/book3s64/hash_native.c | 8 ++++---- arch/powerpc/mm/book3s64/radix_tlb.c | 12 ++++++------ 3 files changed, 28 insertions(+), 11 deletions(-) diff --git a/arch/powerpc/include/asm/synch.h b/arch/powerpc/include/asm/synch.h index aca70fb43147..1d67bc8d7bc6 100644 --- a/arch/powerpc/include/asm/synch.h +++ b/arch/powerpc/include/asm/synch.h @@ -3,8 +3,9 @@ #define _ASM_POWERPC_SYNCH_H #ifdef __KERNEL__ +#include #include -#include +#include #ifndef __ASSEMBLY__ extern unsigned int __start___lwsync_fixup, __stop___lwsync_fixup; @@ -20,6 +21,22 @@ static inline void isync(void) { __asm__ __volatile__ ("isync" : : : "memory"); } + +static inline void ppc_after_tlbiel_barrier(void) +{ + asm volatile("ptesync": : :"memory"); + /* + * POWER9, POWER10 need a cp_abort after tlbiel to ensure the copy is + * invalidated correctly. If this is not done, the paste can take data + * from the physical address that was translated at copy time. + * + * POWER9 in practice does not need this, because address spaces with + * accelerators mapped will use tlbie (which does invalidate the copy) + * to invalidate translations. It's not possible to limit POWER10 this + * way due to local copy-paste. + */ + asm volatile(ASM_FTR_IFSET(PPC_CP_ABORT, "", %0) : : "i" (CPU_FTR_ARCH_31) : "memory"); +} #endif /* __ASSEMBLY__ */ #if defined(__powerpc64__) diff --git a/arch/powerpc/mm/book3s64/hash_native.c b/arch/powerpc/mm/book3s64/hash_native.c index cf20e5229ce1..0203cdf48c54 100644 --- a/arch/powerpc/mm/book3s64/hash_native.c +++ b/arch/powerpc/mm/book3s64/hash_native.c @@ -82,7 +82,7 @@ static void tlbiel_all_isa206(unsigned int num_sets, unsigned int is) for (set = 0; set < num_sets; set++) tlbiel_hash_set_isa206(set, is); - asm volatile("ptesync": : :"memory"); + ppc_after_tlbiel_barrier(); } static void tlbiel_all_isa300(unsigned int num_sets, unsigned int is) @@ -110,7 +110,7 @@ static void tlbiel_all_isa300(unsigned int num_sets, unsigned int is) */ tlbiel_hash_set_isa300(0, is, 0, 2, 1); - asm volatile("ptesync": : :"memory"); + ppc_after_tlbiel_barrier(); asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT "; isync" : : :"memory"); } @@ -303,7 +303,7 @@ static inline void tlbie(unsigned long vpn, int psize, int apsize, asm volatile("ptesync": : :"memory"); if (use_local) { __tlbiel(vpn, psize, apsize, ssize); - asm volatile("ptesync": : :"memory"); + ppc_after_tlbiel_barrier(); } else { __tlbie(vpn, psize, apsize, ssize); fixup_tlbie_vpn(vpn, psize, apsize, ssize); @@ -879,7 +879,7 @@ static void native_flush_hash_range(unsigned long number, int local) __tlbiel(vpn, psize, psize, ssize); } pte_iterate_hashed_end(); } - asm volatile("ptesync":::"memory"); + ppc_after_tlbiel_barrier(); } else { int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE); diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c index 143b4fd396f0..b487b489d4b6 100644 --- a/arch/powerpc/mm/book3s64/radix_tlb.c +++ b/arch/powerpc/mm/book3s64/radix_tlb.c @@ -65,7 +65,7 @@ static void tlbiel_all_isa300(unsigned int num_sets, unsigned int is) for (set = 1; set < num_sets; set++) tlbiel_radix_set_isa300(set, is, 0, RIC_FLUSH_TLB, 1); - asm volatile("ptesync": : :"memory"); + ppc_after_tlbiel_barrier(); } void radix__tlbiel_all(unsigned int action) @@ -296,7 +296,7 @@ static __always_inline void _tlbiel_pid(unsigned long pid, unsigned long ric) /* For PWC, only one flush is needed */ if (ric == RIC_FLUSH_PWC) { - asm volatile("ptesync": : :"memory"); + ppc_after_tlbiel_barrier(); return; } @@ -304,7 +304,7 @@ static __always_inline void _tlbiel_pid(unsigned long pid, unsigned long ric) for (set = 1; set < POWER9_TLB_SETS_RADIX ; set++) __tlbiel_pid(pid, set, RIC_FLUSH_TLB); - asm volatile("ptesync": : :"memory"); + ppc_after_tlbiel_barrier(); asm volatile(PPC_RADIX_INVALIDATE_ERAT_USER "; isync" : : :"memory"); } @@ -431,7 +431,7 @@ static __always_inline void _tlbiel_va(unsigned long va, unsigned long pid, asm volatile("ptesync": : :"memory"); __tlbiel_va(va, pid, ap, ric); - asm volatile("ptesync": : :"memory"); + ppc_after_tlbiel_barrier(); } static inline void _tlbiel_va_range(unsigned long start, unsigned long end, @@ -442,7 +442,7 @@ static inline void _tlbiel_va_range(unsigned long start, unsigned long end, if (also_pwc) __tlbiel_pid(pid, 0, RIC_FLUSH_PWC); __tlbiel_va_range(start, end, pid, page_size, psize); - asm volatile("ptesync": : :"memory"); + ppc_after_tlbiel_barrier(); } static inline void __tlbie_va_range(unsigned long start, unsigned long end, @@ -949,7 +949,7 @@ is_local: if (hflush) __tlbiel_va_range(hstart, hend, pid, PMD_SIZE, MMU_PAGE_2M); - asm volatile("ptesync": : :"memory"); + ppc_after_tlbiel_barrier(); } else if (cputlb_use_tlbie()) { asm volatile("ptesync": : :"memory"); __tlbie_va_range(start, end, pid, page_size, mmu_virtual_psize); From cdb1ea0276bd6a225aa1203b4829b8c3c0d4d069 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Tue, 25 Aug 2020 17:56:12 +1000 Subject: [PATCH 316/645] powerpc/pseries: add new branch prediction security bits for link stack The hypervisor interface has defined branch prediction security bits for handling the link stack. Wire them up. Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200825075612.224656-1-npiggin@gmail.com --- arch/powerpc/include/asm/hvcall.h | 2 ++ arch/powerpc/platforms/pseries/setup.c | 6 ++++++ 2 files changed, 8 insertions(+) diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index e8f116a425f9..c1fbccb04390 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -375,11 +375,13 @@ #define H_CPU_CHAR_THREAD_RECONFIG_CTRL (1ull << 57) // IBM bit 6 #define H_CPU_CHAR_COUNT_CACHE_DISABLED (1ull << 56) // IBM bit 7 #define H_CPU_CHAR_BCCTR_FLUSH_ASSIST (1ull << 54) // IBM bit 9 +#define H_CPU_CHAR_BCCTR_LINK_FLUSH_ASSIST (1ull << 52) // IBM bit 11 #define H_CPU_BEHAV_FAVOUR_SECURITY (1ull << 63) // IBM bit 0 #define H_CPU_BEHAV_L1D_FLUSH_PR (1ull << 62) // IBM bit 1 #define H_CPU_BEHAV_BNDS_CHK_SPEC_BAR (1ull << 61) // IBM bit 2 #define H_CPU_BEHAV_FLUSH_COUNT_CACHE (1ull << 58) // IBM bit 5 +#define H_CPU_BEHAV_FLUSH_LINK_STACK (1ull << 57) // IBM bit 6 /* Flag values used in H_REGISTER_PROC_TBL hcall */ #define PROC_TABLE_OP_MASK 0x18 diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 2f4ee0a90284..633c45ec406d 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -519,9 +519,15 @@ static void init_cpu_char_feature_flags(struct h_cpu_char_result *result) if (result->character & H_CPU_CHAR_BCCTR_FLUSH_ASSIST) security_ftr_set(SEC_FTR_BCCTR_FLUSH_ASSIST); + if (result->character & H_CPU_CHAR_BCCTR_LINK_FLUSH_ASSIST) + security_ftr_set(SEC_FTR_BCCTR_LINK_FLUSH_ASSIST); + if (result->behaviour & H_CPU_BEHAV_FLUSH_COUNT_CACHE) security_ftr_set(SEC_FTR_FLUSH_COUNT_CACHE); + if (result->behaviour & H_CPU_BEHAV_FLUSH_LINK_STACK) + security_ftr_set(SEC_FTR_FLUSH_LINK_STACK); + /* * The features below are enabled by default, so we instead look to see * if firmware has *disabled* them, and clear them if so. From 903fd31d3212ab72d564c68f6cfb5d04db68773e Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Tue, 15 Sep 2020 21:46:45 +1000 Subject: [PATCH 317/645] powerpc/64: fix irq replay missing preempt Prior to commit 3282a3da25bd ("powerpc/64: Implement soft interrupt replay in C"), replayed interrupts returned by the regular interrupt exit code, which performs preemption in case an interrupt had set need_resched. This logic was missed by the conversion. Adding preempt_disable/enable around the interrupt replay and final irq enable will reschedule if needed. Fixes: 3282a3da25bd ("powerpc/64: Implement soft interrupt replay in C") Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200915114650.3980244-1-npiggin@gmail.com --- arch/powerpc/kernel/irq.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index bf21ebd36190..77019699606a 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -368,6 +368,12 @@ notrace void arch_local_irq_restore(unsigned long mask) } } + /* + * Disable preempt here, so that the below preempt_enable will + * perform resched if required (a replayed interrupt may set + * need_resched). + */ + preempt_disable(); irq_soft_mask_set(IRQS_ALL_DISABLED); trace_hardirqs_off(); @@ -377,6 +383,7 @@ notrace void arch_local_irq_restore(unsigned long mask) trace_hardirqs_on(); irq_soft_mask_set(IRQS_ENABLED); __hard_irq_enable(); + preempt_enable(); } EXPORT_SYMBOL(arch_local_irq_restore); From 2b48e96be2f9f7151197fd25dc41487054bc6f5b Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Tue, 15 Sep 2020 21:46:46 +1000 Subject: [PATCH 318/645] powerpc/64: fix irq replay pt_regs->softe value Replayed interrupts get an "artificial" struct pt_regs constructed to pass to interrupt handler functions. This did not get the softe field set correctly, it's as though the interrupt has hit while irqs are disabled. It should be IRQS_ENABLED. This is possibly harmless, asynchronous handlers should not be testing if irqs were disabled, but it might be possible for example some code is shared with synchronous or NMI handlers, and it makes more sense if debug output looks at this. Fixes: 3282a3da25bd ("powerpc/64: Implement soft interrupt replay in C") Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200915114650.3980244-2-npiggin@gmail.com --- arch/powerpc/kernel/irq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 77019699606a..3fdad9336885 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -214,7 +214,7 @@ void replay_soft_interrupts(void) struct pt_regs regs; ppc_save_regs(®s); - regs.softe = IRQS_ALL_DISABLED; + regs.softe = IRQS_ENABLED; again: if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) From 012a9a97a8fd6c96d5ec64eb0583220490d95e73 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Tue, 15 Sep 2020 21:46:47 +1000 Subject: [PATCH 319/645] powerpc/64e: remove PACA_IRQ_EE_EDGE This is not used anywhere. Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200915114650.3980244-3-npiggin@gmail.com --- arch/powerpc/include/asm/hw_irq.h | 5 ++--- arch/powerpc/kernel/exceptions-64e.S | 1 - arch/powerpc/kernel/irq.c | 23 ----------------------- 3 files changed, 2 insertions(+), 27 deletions(-) diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index 538698facb80..2034f9590a8c 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -25,9 +25,8 @@ #define PACA_IRQ_DBELL 0x02 #define PACA_IRQ_EE 0x04 #define PACA_IRQ_DEC 0x08 /* Or FIT */ -#define PACA_IRQ_EE_EDGE 0x10 /* BookE only */ -#define PACA_IRQ_HMI 0x20 -#define PACA_IRQ_PMI 0x40 +#define PACA_IRQ_HMI 0x10 +#define PACA_IRQ_PMI 0x20 /* * Some soft-masked interrupts must be hard masked until they are replayed diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index d9ed79415100..ca444ca82b8d 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -988,7 +988,6 @@ kernel_dbg_exc: .endm masked_interrupt_book3e_0x500: - // XXX When adding support for EPR, use PACA_IRQ_EE_EDGE masked_interrupt_book3e PACA_IRQ_EE 1 masked_interrupt_book3e_0x900: diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 3fdad9336885..736a6b56e7d6 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -181,16 +181,6 @@ notrace unsigned int __check_irq_replay(void) return 0x500; } - /* - * Check if an EPR external interrupt happened this bit is typically - * set if we need to handle another "edge" interrupt from within the - * MPIC "EPR" handler. - */ - if (happened & PACA_IRQ_EE_EDGE) { - local_paca->irq_happened &= ~PACA_IRQ_EE_EDGE; - return 0x500; - } - if (happened & PACA_IRQ_DBELL) { local_paca->irq_happened &= ~PACA_IRQ_DBELL; return 0x280; @@ -270,19 +260,6 @@ again: hard_irq_disable(); } - /* - * Check if an EPR external interrupt happened this bit is typically - * set if we need to handle another "edge" interrupt from within the - * MPIC "EPR" handler. - */ - if (IS_ENABLED(CONFIG_PPC_BOOK3E) && (happened & PACA_IRQ_EE_EDGE)) { - local_paca->irq_happened &= ~PACA_IRQ_EE_EDGE; - regs.trap = 0x500; - do_IRQ(®s); - if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) - hard_irq_disable(); - } - if (IS_ENABLED(CONFIG_PPC_DOORBELL) && (happened & PACA_IRQ_DBELL)) { local_paca->irq_happened &= ~PACA_IRQ_DBELL; if (IS_ENABLED(CONFIG_PPC_BOOK3E)) From 903dd1ff453e458fc7608ee4df42a6df16d3d1a0 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Tue, 15 Sep 2020 21:46:48 +1000 Subject: [PATCH 320/645] powerpc/64e: remove 64s specific interrupt soft-mask code Since the assembly soft-masking code was moved to 64e specific, there are some 64s specific interrupt types still there. Remove them. Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200915114650.3980244-4-npiggin@gmail.com --- arch/powerpc/kernel/exceptions-64e.S | 10 ---------- arch/powerpc/kernel/irq.c | 2 +- 2 files changed, 1 insertion(+), 11 deletions(-) diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index ca444ca82b8d..f579ce46eef2 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -1302,16 +1302,6 @@ fast_exception_return: addi r3,r1,STACK_FRAME_OVERHEAD; bl do_IRQ b ret_from_except -1: cmpwi cr0,r3,0xf00 - bne 1f - addi r3,r1,STACK_FRAME_OVERHEAD; - bl performance_monitor_exception - b ret_from_except -1: cmpwi cr0,r3,0xe60 - bne 1f - addi r3,r1,STACK_FRAME_OVERHEAD; - bl handle_hmi_exception - b ret_from_except 1: cmpwi cr0,r3,0x900 bne 1f addi r3,r1,STACK_FRAME_OVERHEAD; diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 736a6b56e7d6..b725509f9073 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -113,7 +113,7 @@ static inline notrace int decrementer_check_overflow(void) #ifdef CONFIG_PPC_BOOK3E /* This is called whenever we are re-enabling interrupts - * and returns either 0 (nothing to do) or 500/900/280/a00/e80 if + * and returns either 0 (nothing to do) or 500/900/280 if * there's an EE, DEC or DBELL to generate. * * This is called in two contexts: From arch_local_irq_restore() From 455575533c7aa294d3c0284d59a77ae9a60c0537 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Tue, 15 Sep 2020 21:46:49 +1000 Subject: [PATCH 321/645] powerpc/64: make restore_interrupts 64e only This is not used by 64s. Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200915114650.3980244-5-npiggin@gmail.com --- arch/powerpc/kernel/irq.c | 37 +++++++++++++++++++------------------ 1 file changed, 19 insertions(+), 18 deletions(-) diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index b725509f9073..631e6d236c97 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -191,6 +191,25 @@ notrace unsigned int __check_irq_replay(void) return 0; } + +/* + * This is specifically called by assembly code to re-enable interrupts + * if they are currently disabled. This is typically called before + * schedule() or do_signal() when returning to userspace. We do it + * in C to avoid the burden of dealing with lockdep etc... + * + * NOTE: This is called with interrupts hard disabled but not marked + * as such in paca->irq_happened, so we need to resync this. + */ +void notrace restore_interrupts(void) +{ + if (irqs_disabled()) { + local_paca->irq_happened |= PACA_IRQ_HARD_DIS; + local_irq_enable(); + } else + __hard_irq_enable(); +} + #endif /* CONFIG_PPC_BOOK3E */ void replay_soft_interrupts(void) @@ -364,24 +383,6 @@ notrace void arch_local_irq_restore(unsigned long mask) } EXPORT_SYMBOL(arch_local_irq_restore); -/* - * This is specifically called by assembly code to re-enable interrupts - * if they are currently disabled. This is typically called before - * schedule() or do_signal() when returning to userspace. We do it - * in C to avoid the burden of dealing with lockdep etc... - * - * NOTE: This is called with interrupts hard disabled but not marked - * as such in paca->irq_happened, so we need to resync this. - */ -void notrace restore_interrupts(void) -{ - if (irqs_disabled()) { - local_paca->irq_happened |= PACA_IRQ_HARD_DIS; - local_irq_enable(); - } else - __hard_irq_enable(); -} - /* * This is a helper to use when about to go into idle low-power * when the latter has the side effect of re-enabling interrupts From 4366337490cbe5a35b50e83755be629a502ec7e2 Mon Sep 17 00:00:00 2001 From: Wang Wensheng Date: Fri, 18 Sep 2020 08:59:51 +0000 Subject: [PATCH 322/645] powerpc/papr_scm: Fix warnings about undeclared variable Build the kernel with 'make C=2': arch/powerpc/platforms/pseries/papr_scm.c:825:1: warning: symbol 'dev_attr_perf_stats' was not declared. Should it be static? Signed-off-by: Wang Wensheng Reviewed-by: Vaibhav Jain Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200918085951.44983-1-wangwensheng4@huawei.com --- arch/powerpc/platforms/pseries/papr_scm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index 5493bc847bd0..a95aa425e7d4 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -823,7 +823,7 @@ free_stats: kfree(stats); return rc ? rc : (ssize_t)seq_buf_used(&s); } -DEVICE_ATTR_ADMIN_RO(perf_stats); +static DEVICE_ATTR_ADMIN_RO(perf_stats); static ssize_t flags_show(struct device *dev, struct device_attribute *attr, char *buf) From 5c5e46dad939b2bf4df04293ab9ac68abd7c1f55 Mon Sep 17 00:00:00 2001 From: Daniel Axtens Date: Thu, 24 Sep 2020 11:49:22 +1000 Subject: [PATCH 323/645] powerpc: PPC_SECURE_BOOT should not require PowerNV In commit 61f879d97ce4 ("powerpc/pseries: Detect secure and trusted boot state of the system.") we taught the kernel how to understand the secure-boot parameters used by a pseries guest. However, CONFIG_PPC_SECURE_BOOT still requires PowerNV. I didn't catch this because pseries_le_defconfig includes support for PowerNV and so everything still worked. Indeed, most configs will. Nonetheless, technically PPC_SECURE_BOOT doesn't require PowerNV any more. The secure variables support (PPC_SECVAR_SYSFS) doesn't do anything on pSeries yet, but I don't think it's worth adding a new condition - at some stage we'll want to add a backend for pSeries anyway. Fixes: 61f879d97ce4 ("powerpc/pseries: Detect secure and trusted boot state of the system.") Signed-off-by: Daniel Axtens Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200924014922.172914-1-dja@axtens.net --- arch/powerpc/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index d02b51174fe4..fe0e6b317cc2 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -984,7 +984,7 @@ config PPC_MEM_KEYS config PPC_SECURE_BOOT prompt "Enable secure boot support" bool - depends on PPC_POWERNV + depends on PPC_POWERNV || PPC_PSERIES depends on IMA_ARCH_POLICY imply IMA_SECURE_AND_OR_TRUSTED_BOOT help From 874dc62f548f28649ac3d7e31025b1e8cec3868a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Sep 2020 06:13:10 +0200 Subject: [PATCH 324/645] powerpc: switch 85xx defconfigs from legacy ide to libata Switch the 85xx defconfigs from the soon to be removed legacy ide driver to libata. Signed-off-by: Christoph Hellwig Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200924041310.520970-1-hch@lst.de --- arch/powerpc/configs/85xx/mpc85xx_cds_defconfig | 6 +++--- arch/powerpc/configs/85xx/tqm8540_defconfig | 6 +++--- arch/powerpc/configs/85xx/tqm8541_defconfig | 6 +++--- arch/powerpc/configs/85xx/tqm8555_defconfig | 6 +++--- arch/powerpc/configs/85xx/tqm8560_defconfig | 6 +++--- 5 files changed, 15 insertions(+), 15 deletions(-) diff --git a/arch/powerpc/configs/85xx/mpc85xx_cds_defconfig b/arch/powerpc/configs/85xx/mpc85xx_cds_defconfig index 0683d8c292a8..cea72e85ed26 100644 --- a/arch/powerpc/configs/85xx/mpc85xx_cds_defconfig +++ b/arch/powerpc/configs/85xx/mpc85xx_cds_defconfig @@ -29,9 +29,9 @@ CONFIG_SYN_COOKIES=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=32768 -CONFIG_IDE=y -CONFIG_BLK_DEV_GENERIC=y -CONFIG_BLK_DEV_VIA82CXXX=y +CONFIG_ATA=y +CONFIG_ATA_GENERIC=y +CONFIG_PATA_VIA=y CONFIG_NETDEVICES=y CONFIG_GIANFAR=y CONFIG_E1000=y diff --git a/arch/powerpc/configs/85xx/tqm8540_defconfig b/arch/powerpc/configs/85xx/tqm8540_defconfig index 98982a0e82d8..bbf040aa1f9a 100644 --- a/arch/powerpc/configs/85xx/tqm8540_defconfig +++ b/arch/powerpc/configs/85xx/tqm8540_defconfig @@ -30,9 +30,9 @@ CONFIG_MTD_CFI_AMDSTD=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=32768 -CONFIG_IDE=y -CONFIG_BLK_DEV_GENERIC=y -CONFIG_BLK_DEV_VIA82CXXX=y +CONFIG_ATA=y +CONFIG_ATA_GENERIC=y +CONFIG_PATA_VIA=y CONFIG_NETDEVICES=y CONFIG_GIANFAR=y CONFIG_E100=y diff --git a/arch/powerpc/configs/85xx/tqm8541_defconfig b/arch/powerpc/configs/85xx/tqm8541_defconfig index a6e21db1dafe..523ad8dcfd9d 100644 --- a/arch/powerpc/configs/85xx/tqm8541_defconfig +++ b/arch/powerpc/configs/85xx/tqm8541_defconfig @@ -30,9 +30,9 @@ CONFIG_MTD_CFI_AMDSTD=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=32768 -CONFIG_IDE=y -CONFIG_BLK_DEV_GENERIC=y -CONFIG_BLK_DEV_VIA82CXXX=y +CONFIG_ATA=y +CONFIG_ATA_GENERIC=y +CONFIG_PATA_VIA=y CONFIG_NETDEVICES=y CONFIG_GIANFAR=y CONFIG_E100=y diff --git a/arch/powerpc/configs/85xx/tqm8555_defconfig b/arch/powerpc/configs/85xx/tqm8555_defconfig index ca1de3979474..0032ce1e8c9c 100644 --- a/arch/powerpc/configs/85xx/tqm8555_defconfig +++ b/arch/powerpc/configs/85xx/tqm8555_defconfig @@ -30,9 +30,9 @@ CONFIG_MTD_CFI_AMDSTD=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=32768 -CONFIG_IDE=y -CONFIG_BLK_DEV_GENERIC=y -CONFIG_BLK_DEV_VIA82CXXX=y +CONFIG_ATA=y +CONFIG_ATA_GENERIC=y +CONFIG_PATA_VIA=y CONFIG_NETDEVICES=y CONFIG_GIANFAR=y CONFIG_E100=y diff --git a/arch/powerpc/configs/85xx/tqm8560_defconfig b/arch/powerpc/configs/85xx/tqm8560_defconfig index ca3b8c8ef30f..a80b971f7d6e 100644 --- a/arch/powerpc/configs/85xx/tqm8560_defconfig +++ b/arch/powerpc/configs/85xx/tqm8560_defconfig @@ -30,9 +30,9 @@ CONFIG_MTD_CFI_AMDSTD=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=32768 -CONFIG_IDE=y -CONFIG_BLK_DEV_GENERIC=y -CONFIG_BLK_DEV_VIA82CXXX=y +CONFIG_ATA=y +CONFIG_ATA_GENERIC=y +CONFIG_PATA_VIA=y CONFIG_NETDEVICES=y CONFIG_GIANFAR=y CONFIG_E100=y From d125aedb404204de0579b16028096b2cc09e4deb Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Fri, 18 Sep 2020 19:30:42 +1000 Subject: [PATCH 325/645] powerpc/eeh: Rework EEH initialisation Drop the EEH register / unregister ops thing and have the platform pass the ops structure into eeh_init() directly. This takes one initcall out of the EEH setup path and it means we're only doing EEH setup on the platforms which actually support it. It's also less code and generally easier to follow. No functional changes. Signed-off-by: Oliver O'Halloran Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200918093050.37344-1-oohall@gmail.com --- arch/powerpc/include/asm/eeh.h | 3 +- arch/powerpc/kernel/eeh.c | 87 ++++---------------- arch/powerpc/platforms/powernv/eeh-powernv.c | 4 +- arch/powerpc/platforms/pseries/eeh_pseries.c | 5 +- 4 files changed, 21 insertions(+), 78 deletions(-) diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index d5f369bcd130..765bcf63edea 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -295,8 +295,7 @@ const char *eeh_pe_loc_get(struct eeh_pe *pe); struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe); void eeh_show_enabled(void); -int __init eeh_ops_register(struct eeh_ops *ops); -int __exit eeh_ops_unregister(const char *name); +int __init eeh_init(struct eeh_ops *ops); int eeh_check_failure(const volatile void __iomem *token); int eeh_dev_check_failure(struct eeh_dev *edev); void eeh_addr_cache_init(void); diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 94682382fc8c..28a0ea5d9faa 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -929,56 +929,6 @@ void eeh_save_bars(struct eeh_dev *edev) edev->config_space[1] |= PCI_COMMAND_MASTER; } -/** - * eeh_ops_register - Register platform dependent EEH operations - * @ops: platform dependent EEH operations - * - * Register the platform dependent EEH operation callback - * functions. The platform should call this function before - * any other EEH operations. - */ -int __init eeh_ops_register(struct eeh_ops *ops) -{ - if (!ops->name) { - pr_warn("%s: Invalid EEH ops name for %p\n", - __func__, ops); - return -EINVAL; - } - - if (eeh_ops && eeh_ops != ops) { - pr_warn("%s: EEH ops of platform %s already existing (%s)\n", - __func__, eeh_ops->name, ops->name); - return -EEXIST; - } - - eeh_ops = ops; - - return 0; -} - -/** - * eeh_ops_unregister - Unreigster platform dependent EEH operations - * @name: name of EEH platform operations - * - * Unregister the platform dependent EEH operation callback - * functions. - */ -int __exit eeh_ops_unregister(const char *name) -{ - if (!name || !strlen(name)) { - pr_warn("%s: Invalid EEH ops name\n", - __func__); - return -EINVAL; - } - - if (eeh_ops && !strcmp(eeh_ops->name, name)) { - eeh_ops = NULL; - return 0; - } - - return -EEXIST; -} - static int eeh_reboot_notifier(struct notifier_block *nb, unsigned long action, void *unused) { @@ -991,25 +941,22 @@ static struct notifier_block eeh_reboot_nb = { }; /** - * eeh_init - EEH initialization + * eeh_init - System wide EEH initialization * - * Initialize EEH by trying to enable it for all of the adapters in the system. - * As a side effect we can determine here if eeh is supported at all. - * Note that we leave EEH on so failed config cycles won't cause a machine - * check. If a user turns off EEH for a particular adapter they are really - * telling Linux to ignore errors. Some hardware (e.g. POWER5) won't - * grant access to a slot if EEH isn't enabled, and so we always enable - * EEH for all slots/all devices. - * - * The eeh-force-off option disables EEH checking globally, for all slots. - * Even if force-off is set, the EEH hardware is still enabled, so that - * newer systems can boot. + * It's the platform's job to call this from an arch_initcall(). */ -static int eeh_init(void) +int eeh_init(struct eeh_ops *ops) { struct pci_controller *hose, *tmp; int ret = 0; + /* the platform should only initialise EEH once */ + if (WARN_ON(eeh_ops)) + return -EEXIST; + if (WARN_ON(!ops)) + return -ENOENT; + eeh_ops = ops; + /* Register reboot notifier */ ret = register_reboot_notifier(&eeh_reboot_nb); if (ret) { @@ -1018,13 +965,13 @@ static int eeh_init(void) return ret; } - /* call platform initialization function */ - if (!eeh_ops) { - pr_warn("%s: Platform EEH operation not found\n", - __func__); - return -EEXIST; - } else if ((ret = eeh_ops->init())) + if (eeh_ops->init) + ret = eeh_ops->init(); + if (ret) { + pr_warn("%s: platform EEH init failed (%d)\n", + __func__, ret); return ret; + } /* Initialize PHB PEs */ list_for_each_entry_safe(hose, tmp, &hose_list, list_node) @@ -1036,8 +983,6 @@ static int eeh_init(void) return eeh_event_init(); } -core_initcall_sync(eeh_init); - static int eeh_device_notifier(struct notifier_block *nb, unsigned long action, void *data) { diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index 663bd69ac51b..33938f8a3fba 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -1717,7 +1717,7 @@ static int __init eeh_powernv_init(void) { int ret = -EINVAL; - ret = eeh_ops_register(&pnv_eeh_ops); + ret = eeh_init(&pnv_eeh_ops); if (!ret) pr_info("EEH: PowerNV platform initialized\n"); else @@ -1725,4 +1725,4 @@ static int __init eeh_powernv_init(void) return ret; } -machine_early_initcall(powernv, eeh_powernv_init); +machine_core_initcall_sync(powernv, eeh_powernv_init); diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index 1db74cec72bc..df32b8ccbd59 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -990,13 +990,12 @@ static int __init eeh_pseries_init(void) { int ret; - ret = eeh_ops_register(&pseries_eeh_ops); + ret = eeh_init(&pseries_eeh_ops); if (!ret) pr_info("EEH: pSeries platform initialized\n"); else pr_info("EEH: pSeries platform initialization failure (%d)\n", ret); - return ret; } -machine_early_initcall(pseries, eeh_pseries_init); +machine_core_initcall_sync(pseries, eeh_pseries_init); From 82a1ea21f1bac42eb8e3f77d5d249201855f2c85 Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Fri, 18 Sep 2020 19:30:43 +1000 Subject: [PATCH 326/645] powerpc/powernv: Stop using eeh_ops->init() Fold pnv_eeh_init() into eeh_powernv_init() rather than having eeh_init() call it via eeh_ops->init(). It's simpler and it'll let us delete eeh_ops.init. Signed-off-by: Oliver O'Halloran Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200918093050.37344-2-oohall@gmail.com --- arch/powerpc/platforms/powernv/eeh-powernv.c | 94 ++++++++++---------- 1 file changed, 45 insertions(+), 49 deletions(-) diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index 33938f8a3fba..5db92f39887a 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -44,54 +44,6 @@ static void pnv_pcibios_bus_add_device(struct pci_dev *pdev) eeh_probe_device(pdev); } -static int pnv_eeh_init(void) -{ - struct pci_controller *hose; - struct pnv_phb *phb; - int max_diag_size = PNV_PCI_DIAG_BUF_SIZE; - - if (!firmware_has_feature(FW_FEATURE_OPAL)) { - pr_warn("%s: OPAL is required !\n", - __func__); - return -EINVAL; - } - - /* Set probe mode */ - eeh_add_flag(EEH_PROBE_MODE_DEV); - - /* - * P7IOC blocks PCI config access to frozen PE, but PHB3 - * doesn't do that. So we have to selectively enable I/O - * prior to collecting error log. - */ - list_for_each_entry(hose, &hose_list, list_node) { - phb = hose->private_data; - - if (phb->model == PNV_PHB_MODEL_P7IOC) - eeh_add_flag(EEH_ENABLE_IO_FOR_LOG); - - if (phb->diag_data_size > max_diag_size) - max_diag_size = phb->diag_data_size; - - /* - * PE#0 should be regarded as valid by EEH core - * if it's not the reserved one. Currently, we - * have the reserved PE#255 and PE#127 for PHB3 - * and P7IOC separately. So we should regard - * PE#0 as valid for PHB3 and P7IOC. - */ - if (phb->ioda.reserved_pe_idx != 0) - eeh_add_flag(EEH_VALID_PE_ZERO); - - break; - } - - eeh_set_pe_aux_size(max_diag_size); - ppc_md.pcibios_bus_add_device = pnv_pcibios_bus_add_device; - - return 0; -} - static irqreturn_t pnv_eeh_event(int irq, void *data) { /* @@ -1674,7 +1626,6 @@ static int pnv_eeh_restore_config(struct eeh_dev *edev) static struct eeh_ops pnv_eeh_ops = { .name = "powernv", - .init = pnv_eeh_init, .probe = pnv_eeh_probe, .set_option = pnv_eeh_set_option, .get_state = pnv_eeh_get_state, @@ -1715,8 +1666,53 @@ DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, pnv_pci_fixup_vf_mps); */ static int __init eeh_powernv_init(void) { + int max_diag_size = PNV_PCI_DIAG_BUF_SIZE; + struct pci_controller *hose; + struct pnv_phb *phb; int ret = -EINVAL; + if (!firmware_has_feature(FW_FEATURE_OPAL)) { + pr_warn("%s: OPAL is required !\n", __func__); + return -EINVAL; + } + + /* Set probe mode */ + eeh_add_flag(EEH_PROBE_MODE_DEV); + + /* + * P7IOC blocks PCI config access to frozen PE, but PHB3 + * doesn't do that. So we have to selectively enable I/O + * prior to collecting error log. + */ + list_for_each_entry(hose, &hose_list, list_node) { + phb = hose->private_data; + + if (phb->model == PNV_PHB_MODEL_P7IOC) + eeh_add_flag(EEH_ENABLE_IO_FOR_LOG); + + if (phb->diag_data_size > max_diag_size) + max_diag_size = phb->diag_data_size; + + /* + * PE#0 should be regarded as valid by EEH core + * if it's not the reserved one. Currently, we + * have the reserved PE#255 and PE#127 for PHB3 + * and P7IOC separately. So we should regard + * PE#0 as valid for PHB3 and P7IOC. + */ + if (phb->ioda.reserved_pe_idx != 0) + eeh_add_flag(EEH_VALID_PE_ZERO); + + break; + } + + /* + * eeh_init() allocates the eeh_pe and its aux data buf so the + * size needs to be set before calling eeh_init(). + */ + eeh_set_pe_aux_size(max_diag_size); + ppc_md.pcibios_bus_add_device = pnv_pcibios_bus_add_device; + ret = eeh_init(&pnv_eeh_ops); if (!ret) pr_info("EEH: PowerNV platform initialized\n"); From 1f8fa0cd6a848ff072bffe0ee776554387128f60 Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Fri, 18 Sep 2020 19:30:44 +1000 Subject: [PATCH 327/645] powerpc/pseries: Stop using eeh_ops->init() Fold pseries_eeh_init() into eeh_pseries_init() rather than having eeh_init() call it via eeh_ops->init(). It's simpler and it'll let us delete eeh_ops.init. Signed-off-by: Oliver O'Halloran Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200918093050.37344-3-oohall@gmail.com --- arch/powerpc/platforms/pseries/eeh_pseries.c | 155 +++++++++---------- 1 file changed, 71 insertions(+), 84 deletions(-) diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index df32b8ccbd59..a3ed6a0507da 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -237,88 +237,6 @@ static unsigned char slot_errbuf[RTAS_ERROR_LOG_MAX]; static DEFINE_SPINLOCK(slot_errbuf_lock); static int eeh_error_buf_size; -/** - * pseries_eeh_init - EEH platform dependent initialization - * - * EEH platform dependent initialization on pseries. - */ -static int pseries_eeh_init(void) -{ - struct pci_controller *phb; - struct pci_dn *pdn; - int addr, config_addr; - - /* figure out EEH RTAS function call tokens */ - ibm_set_eeh_option = rtas_token("ibm,set-eeh-option"); - ibm_set_slot_reset = rtas_token("ibm,set-slot-reset"); - ibm_read_slot_reset_state2 = rtas_token("ibm,read-slot-reset-state2"); - ibm_read_slot_reset_state = rtas_token("ibm,read-slot-reset-state"); - ibm_slot_error_detail = rtas_token("ibm,slot-error-detail"); - ibm_get_config_addr_info2 = rtas_token("ibm,get-config-addr-info2"); - ibm_get_config_addr_info = rtas_token("ibm,get-config-addr-info"); - ibm_configure_pe = rtas_token("ibm,configure-pe"); - - /* - * ibm,configure-pe and ibm,configure-bridge have the same semantics, - * however ibm,configure-pe can be faster. If we can't find - * ibm,configure-pe then fall back to using ibm,configure-bridge. - */ - if (ibm_configure_pe == RTAS_UNKNOWN_SERVICE) - ibm_configure_pe = rtas_token("ibm,configure-bridge"); - - /* - * Necessary sanity check. We needn't check "get-config-addr-info" - * and its variant since the old firmware probably support address - * of domain/bus/slot/function for EEH RTAS operations. - */ - if (ibm_set_eeh_option == RTAS_UNKNOWN_SERVICE || - ibm_set_slot_reset == RTAS_UNKNOWN_SERVICE || - (ibm_read_slot_reset_state2 == RTAS_UNKNOWN_SERVICE && - ibm_read_slot_reset_state == RTAS_UNKNOWN_SERVICE) || - ibm_slot_error_detail == RTAS_UNKNOWN_SERVICE || - ibm_configure_pe == RTAS_UNKNOWN_SERVICE) { - pr_info("EEH functionality not supported\n"); - return -EINVAL; - } - - /* Initialize error log lock and size */ - spin_lock_init(&slot_errbuf_lock); - eeh_error_buf_size = rtas_token("rtas-error-log-max"); - if (eeh_error_buf_size == RTAS_UNKNOWN_SERVICE) { - pr_info("%s: unknown EEH error log size\n", - __func__); - eeh_error_buf_size = 1024; - } else if (eeh_error_buf_size > RTAS_ERROR_LOG_MAX) { - pr_info("%s: EEH error log size %d exceeds the maximal %d\n", - __func__, eeh_error_buf_size, RTAS_ERROR_LOG_MAX); - eeh_error_buf_size = RTAS_ERROR_LOG_MAX; - } - - /* Set EEH probe mode */ - eeh_add_flag(EEH_PROBE_MODE_DEVTREE | EEH_ENABLE_IO_FOR_LOG); - - /* Set EEH machine dependent code */ - ppc_md.pcibios_bus_add_device = pseries_pcibios_bus_add_device; - - if (is_kdump_kernel() || reset_devices) { - pr_info("Issue PHB reset ...\n"); - list_for_each_entry(phb, &hose_list, list_node) { - pdn = list_first_entry(&PCI_DN(phb->dn)->child_list, struct pci_dn, list); - addr = (pdn->busno << 16) | (pdn->devfn << 8); - config_addr = pseries_eeh_get_config_addr(phb, addr); - /* invalid PE config addr */ - if (config_addr == 0) - continue; - - pseries_eeh_phb_reset(phb, config_addr, EEH_RESET_FUNDAMENTAL); - pseries_eeh_phb_reset(phb, config_addr, EEH_RESET_DEACTIVATE); - pseries_eeh_phb_configure_bridge(phb, config_addr); - } - } - - return 0; -} - static int pseries_eeh_cap_start(struct pci_dn *pdn) { u32 status; @@ -963,7 +881,6 @@ static int pseries_notify_resume(struct eeh_dev *edev) static struct eeh_ops pseries_eeh_ops = { .name = "pseries", - .init = pseries_eeh_init, .probe = pseries_eeh_probe, .set_option = pseries_eeh_set_option, .get_state = pseries_eeh_get_state, @@ -988,7 +905,77 @@ static struct eeh_ops pseries_eeh_ops = { */ static int __init eeh_pseries_init(void) { - int ret; + struct pci_controller *phb; + struct pci_dn *pdn; + int ret, addr, config_addr; + + /* figure out EEH RTAS function call tokens */ + ibm_set_eeh_option = rtas_token("ibm,set-eeh-option"); + ibm_set_slot_reset = rtas_token("ibm,set-slot-reset"); + ibm_read_slot_reset_state2 = rtas_token("ibm,read-slot-reset-state2"); + ibm_read_slot_reset_state = rtas_token("ibm,read-slot-reset-state"); + ibm_slot_error_detail = rtas_token("ibm,slot-error-detail"); + ibm_get_config_addr_info2 = rtas_token("ibm,get-config-addr-info2"); + ibm_get_config_addr_info = rtas_token("ibm,get-config-addr-info"); + ibm_configure_pe = rtas_token("ibm,configure-pe"); + + /* + * ibm,configure-pe and ibm,configure-bridge have the same semantics, + * however ibm,configure-pe can be faster. If we can't find + * ibm,configure-pe then fall back to using ibm,configure-bridge. + */ + if (ibm_configure_pe == RTAS_UNKNOWN_SERVICE) + ibm_configure_pe = rtas_token("ibm,configure-bridge"); + + /* + * Necessary sanity check. We needn't check "get-config-addr-info" + * and its variant since the old firmware probably support address + * of domain/bus/slot/function for EEH RTAS operations. + */ + if (ibm_set_eeh_option == RTAS_UNKNOWN_SERVICE || + ibm_set_slot_reset == RTAS_UNKNOWN_SERVICE || + (ibm_read_slot_reset_state2 == RTAS_UNKNOWN_SERVICE && + ibm_read_slot_reset_state == RTAS_UNKNOWN_SERVICE) || + ibm_slot_error_detail == RTAS_UNKNOWN_SERVICE || + ibm_configure_pe == RTAS_UNKNOWN_SERVICE) { + pr_info("EEH functionality not supported\n"); + return -EINVAL; + } + + /* Initialize error log lock and size */ + spin_lock_init(&slot_errbuf_lock); + eeh_error_buf_size = rtas_token("rtas-error-log-max"); + if (eeh_error_buf_size == RTAS_UNKNOWN_SERVICE) { + pr_info("%s: unknown EEH error log size\n", + __func__); + eeh_error_buf_size = 1024; + } else if (eeh_error_buf_size > RTAS_ERROR_LOG_MAX) { + pr_info("%s: EEH error log size %d exceeds the maximal %d\n", + __func__, eeh_error_buf_size, RTAS_ERROR_LOG_MAX); + eeh_error_buf_size = RTAS_ERROR_LOG_MAX; + } + + /* Set EEH probe mode */ + eeh_add_flag(EEH_PROBE_MODE_DEVTREE | EEH_ENABLE_IO_FOR_LOG); + + /* Set EEH machine dependent code */ + ppc_md.pcibios_bus_add_device = pseries_pcibios_bus_add_device; + + if (is_kdump_kernel() || reset_devices) { + pr_info("Issue PHB reset ...\n"); + list_for_each_entry(phb, &hose_list, list_node) { + pdn = list_first_entry(&PCI_DN(phb->dn)->child_list, struct pci_dn, list); + addr = (pdn->busno << 16) | (pdn->devfn << 8); + config_addr = pseries_eeh_get_config_addr(phb, addr); + /* invalid PE config addr */ + if (config_addr == 0) + continue; + + pseries_eeh_phb_reset(phb, config_addr, EEH_RESET_FUNDAMENTAL); + pseries_eeh_phb_reset(phb, config_addr, EEH_RESET_DEACTIVATE); + pseries_eeh_phb_configure_bridge(phb, config_addr); + } + } ret = eeh_init(&pseries_eeh_ops); if (!ret) From 5d69e46a2104050c0a458c6bf6abba5f58f56e4c Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Fri, 18 Sep 2020 19:30:45 +1000 Subject: [PATCH 328/645] powerpc/eeh: Delete eeh_ops->init No longer used since the platforms perform their EEH initialisation before calling eeh_init(). Signed-off-by: Oliver O'Halloran Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200918093050.37344-4-oohall@gmail.com --- arch/powerpc/include/asm/eeh.h | 1 - arch/powerpc/kernel/eeh.c | 8 -------- 2 files changed, 9 deletions(-) diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index 765bcf63edea..85030c05e67e 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -216,7 +216,6 @@ enum { struct eeh_ops { char *name; - int (*init)(void); struct eeh_dev *(*probe)(struct pci_dev *pdev); int (*set_option)(struct eeh_pe *pe, int option); int (*get_state)(struct eeh_pe *pe, int *delay); diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 28a0ea5d9faa..98faf139e676 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -965,14 +965,6 @@ int eeh_init(struct eeh_ops *ops) return ret; } - if (eeh_ops->init) - ret = eeh_ops->init(); - if (ret) { - pr_warn("%s: platform EEH init failed (%d)\n", - __func__, ret); - return ret; - } - /* Initialize PHB PEs */ list_for_each_entry_safe(hose, tmp, &hose_list, list_node) eeh_phb_pe_create(hose); From 395ee2a2a15ba1c4c7c414db24dc3082ba8feab8 Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Fri, 18 Sep 2020 19:30:46 +1000 Subject: [PATCH 329/645] powerpc/eeh: Move EEH initialisation to an arch initcall The initialisation of EEH mostly happens in a core_initcall_sync initcall, followed by registering a bus notifier later on in an arch_initcall. Anything involving initcall dependecies is mostly incomprehensible unless you've spent a while staring at code so here's the full sequence: ppc_md.setup_arch <-- pci_controllers are created here ...time passes... core_initcall <-- pci_dns are created from DT nodes core_initcall_sync <-- platforms call eeh_init() postcore_initcall <-- PCI bus type is registered postcore_initcall_sync arch_initcall <-- EEH pci_bus notifier registered subsys_initcall <-- PHBs are scanned here There's no real requirement to do the EEH setup at the core_initcall_sync level. It just needs to be done after pci_dn's are created and before we start scanning PHBs. Simplify the flow a bit by moving the platform EEH inititalisation to an arch_initcall so we can fold the bus notifier registration into eeh_init(). Signed-off-by: Oliver O'Halloran Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200918093050.37344-5-oohall@gmail.com --- arch/powerpc/kernel/eeh.c | 78 ++++++++++---------- arch/powerpc/platforms/powernv/eeh-powernv.c | 2 +- arch/powerpc/platforms/pseries/eeh_pseries.c | 2 +- 3 files changed, 41 insertions(+), 41 deletions(-) diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 98faf139e676..c9e25cfce8f0 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -940,41 +940,6 @@ static struct notifier_block eeh_reboot_nb = { .notifier_call = eeh_reboot_notifier, }; -/** - * eeh_init - System wide EEH initialization - * - * It's the platform's job to call this from an arch_initcall(). - */ -int eeh_init(struct eeh_ops *ops) -{ - struct pci_controller *hose, *tmp; - int ret = 0; - - /* the platform should only initialise EEH once */ - if (WARN_ON(eeh_ops)) - return -EEXIST; - if (WARN_ON(!ops)) - return -ENOENT; - eeh_ops = ops; - - /* Register reboot notifier */ - ret = register_reboot_notifier(&eeh_reboot_nb); - if (ret) { - pr_warn("%s: Failed to register notifier (%d)\n", - __func__, ret); - return ret; - } - - /* Initialize PHB PEs */ - list_for_each_entry_safe(hose, tmp, &hose_list, list_node) - eeh_phb_pe_create(hose); - - eeh_addr_cache_init(); - - /* Initialize EEH event */ - return eeh_event_init(); -} - static int eeh_device_notifier(struct notifier_block *nb, unsigned long action, void *data) { @@ -999,12 +964,47 @@ static struct notifier_block eeh_device_nb = { .notifier_call = eeh_device_notifier, }; -static __init int eeh_set_bus_notifier(void) +/** + * eeh_init - System wide EEH initialization + * + * It's the platform's job to call this from an arch_initcall(). + */ +int eeh_init(struct eeh_ops *ops) { - bus_register_notifier(&pci_bus_type, &eeh_device_nb); - return 0; + struct pci_controller *hose, *tmp; + int ret = 0; + + /* the platform should only initialise EEH once */ + if (WARN_ON(eeh_ops)) + return -EEXIST; + if (WARN_ON(!ops)) + return -ENOENT; + eeh_ops = ops; + + /* Register reboot notifier */ + ret = register_reboot_notifier(&eeh_reboot_nb); + if (ret) { + pr_warn("%s: Failed to register reboot notifier (%d)\n", + __func__, ret); + return ret; + } + + ret = bus_register_notifier(&pci_bus_type, &eeh_device_nb); + if (ret) { + pr_warn("%s: Failed to register bus notifier (%d)\n", + __func__, ret); + return ret; + } + + /* Initialize PHB PEs */ + list_for_each_entry_safe(hose, tmp, &hose_list, list_node) + eeh_phb_pe_create(hose); + + eeh_addr_cache_init(); + + /* Initialize EEH event */ + return eeh_event_init(); } -arch_initcall(eeh_set_bus_notifier); /** * eeh_probe_device() - Perform EEH initialization for the indicated pci device diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index 5db92f39887a..b97ec796dd41 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -1721,4 +1721,4 @@ static int __init eeh_powernv_init(void) return ret; } -machine_core_initcall_sync(powernv, eeh_powernv_init); +machine_arch_initcall(powernv, eeh_powernv_init); diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index a3ed6a0507da..691b9a38b683 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -985,4 +985,4 @@ static int __init eeh_pseries_init(void) ret); return ret; } -machine_core_initcall_sync(pseries, eeh_pseries_init); +machine_arch_initcall(pseries, eeh_pseries_init); From f61c859feb5d19787c93d6b2b3d4beeca7260034 Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Fri, 18 Sep 2020 19:30:47 +1000 Subject: [PATCH 330/645] powerpc/pseries/eeh: Clean up pe_config_addr lookups De-duplicate, and fix up the comments, and make the prototype just take a pci_dn since the job of the function is to return the pe_config_addr of the PE which contains a given device. Signed-off-by: Oliver O'Halloran Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200918093050.37344-6-oohall@gmail.com --- arch/powerpc/platforms/pseries/eeh_pseries.c | 80 +++----------------- 1 file changed, 11 insertions(+), 69 deletions(-) diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index 691b9a38b683..c96ee45a4689 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -33,8 +33,6 @@ #include #include -static int pseries_eeh_get_pe_addr(struct pci_dn *pdn); - /* RTAS tokens */ static int ibm_set_eeh_option; static int ibm_set_slot_reset; @@ -86,7 +84,8 @@ void pseries_pcibios_bus_add_device(struct pci_dev *pdev) /** - * pseries_eeh_get_config_addr - Retrieve config address + * pseries_eeh_get_pe_config_addr - Find the pe_config_addr for a device + * @pdn: pci_dn of the input device * * Retrieve the assocated config address. Actually, there're 2 RTAS * function calls dedicated for the purpose. We need implement @@ -97,16 +96,17 @@ void pseries_pcibios_bus_add_device(struct pci_dev *pdev) * It's notable that zero'ed return value means invalid PE config * address. */ -static int pseries_eeh_get_config_addr(struct pci_controller *phb, int config_addr) +static int pseries_eeh_get_pe_config_addr(struct pci_dn *pdn) { + int config_addr = rtas_config_addr(pdn->busno, pdn->devfn, 0); + struct pci_controller *phb = pdn->phb; int ret = 0; int rets[3]; if (ibm_get_config_addr_info2 != RTAS_UNKNOWN_SERVICE) { /* - * First of all, we need to make sure there has one PE - * associated with the device. Otherwise, PE address is - * meaningless. + * First of all, use function 1 to determine if this device is + * part of a PE or not. ret[0] being zero indicates it's not. */ ret = rtas_call(ibm_get_config_addr_info2, 4, 2, rets, config_addr, BUID_HI(phb->buid), @@ -429,7 +429,7 @@ void pseries_eeh_init_edev(struct pci_dn *pdn) struct eeh_pe *parent; /* Retrieve PE address */ - edev->pe_config_addr = pseries_eeh_get_pe_addr(pdn); + edev->pe_config_addr = pseries_eeh_get_pe_config_addr(pdn); pe.addr = edev->pe_config_addr; /* Some older systems (Power4) allow the ibm,set-eeh-option @@ -548,64 +548,6 @@ static int pseries_eeh_set_option(struct eeh_pe *pe, int option) return ret; } -/** - * pseries_eeh_get_pe_addr - Retrieve PE address - * @pe: EEH PE - * - * Retrieve the assocated PE address. Actually, there're 2 RTAS - * function calls dedicated for the purpose. We need implement - * it through the new function and then the old one. Besides, - * you should make sure the config address is figured out from - * FDT node before calling the function. - * - * It's notable that zero'ed return value means invalid PE config - * address. - */ -static int pseries_eeh_get_pe_addr(struct pci_dn *pdn) -{ - int config_addr = rtas_config_addr(pdn->busno, pdn->devfn, 0); - unsigned long buid = pdn->phb->buid; - int ret = 0; - int rets[3]; - - if (ibm_get_config_addr_info2 != RTAS_UNKNOWN_SERVICE) { - /* - * First of all, we need to make sure there has one PE - * associated with the device. Otherwise, PE address is - * meaningless. - */ - ret = rtas_call(ibm_get_config_addr_info2, 4, 2, rets, - config_addr, BUID_HI(buid), BUID_LO(buid), 1); - if (ret || (rets[0] == 0)) - return 0; - - /* Retrieve the associated PE config address */ - ret = rtas_call(ibm_get_config_addr_info2, 4, 2, rets, - config_addr, BUID_HI(buid), BUID_LO(buid), 0); - if (ret) { - pr_warn("%s: Failed to get address for PHB#%x-PE#%x\n", - __func__, pdn->phb->global_number, config_addr); - return 0; - } - - return rets[0]; - } - - if (ibm_get_config_addr_info != RTAS_UNKNOWN_SERVICE) { - ret = rtas_call(ibm_get_config_addr_info, 4, 2, rets, - config_addr, BUID_HI(buid), BUID_LO(buid), 0); - if (ret) { - pr_warn("%s: Failed to get address for PHB#%x-PE#%x\n", - __func__, pdn->phb->global_number, config_addr); - return 0; - } - - return rets[0]; - } - - return ret; -} - /** * pseries_eeh_get_state - Retrieve PE state * @pe: EEH PE @@ -907,7 +849,7 @@ static int __init eeh_pseries_init(void) { struct pci_controller *phb; struct pci_dn *pdn; - int ret, addr, config_addr; + int ret, config_addr; /* figure out EEH RTAS function call tokens */ ibm_set_eeh_option = rtas_token("ibm,set-eeh-option"); @@ -965,8 +907,8 @@ static int __init eeh_pseries_init(void) pr_info("Issue PHB reset ...\n"); list_for_each_entry(phb, &hose_list, list_node) { pdn = list_first_entry(&PCI_DN(phb->dn)->child_list, struct pci_dn, list); - addr = (pdn->busno << 16) | (pdn->devfn << 8); - config_addr = pseries_eeh_get_config_addr(phb, addr); + config_addr = pseries_eeh_get_pe_config_addr(pdn); + /* invalid PE config addr */ if (config_addr == 0) continue; From 98ba956f6a3891b233466b8da064f17d16dc2090 Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Fri, 18 Sep 2020 19:30:48 +1000 Subject: [PATCH 331/645] powerpc/pseries/eeh: Rework device EEH PE determination The process Linux uses for determining if a device supports EEH or not appears to be at odds with what PAPR says the OS should be doing. The current flow is something like: 1. Assume pe_config_addr is equal the the device's config_addr. 2. Attempt to enable EEH on that PE 3. Verify EEH was enabled (POWER4 bug workaround) 4. Try find the pe_config_addr using the ibm,get-config-addr-info2 RTAS call. 5. If that fails walk the pci_dn tree upwards trying to find a parent device with EEH support. If we find one then add the device to that PE. The first major problem with this process is that we need the PE config address in step 2) since its needs to be passed to the ibm,set-eeh-option RTAS call when enabling EEH for th PE. We hack around this requirement in by making the assumption in 1) and delay finding the actual PE address until 4). This is fine if: a) The PCI device is the 0th function, and b) The device is on the PE's root bus. Granted, the current sequence does appear to work on most systems even when these conditions are false. At a guess PowerVM's RTAS has workarounds to accommodate Linux's quirks or the RTAS call to enable EEH is treated as no-op on most platforms since EEH is usually enabled by default. However, what is currently implemented is a bit sketch and is downright confusing since it doesn't match up with what what PAPR suggests we should be doing. This patch re-works how we handle EEH init so that we find the PE config address using the ibm,get-config-addr-info2 RTAS call first, then use the found address to finish the EEH init process. It also drops the Power4 workaround since as of commit 471d7ff8b51b ("powerpc/64s: Remove POWER4 support") the kernel does not support running on a Power4 CPU so there's no need to support the Power4 platform's quirks either. With the patch applied the sequence is now: 1. Find the pe_config_addr from the device using the RTAS call. 2. Enable the PE. 3. Insert the edev into the tree and create an eeh_pe if needed. The other change made here is ignoring unsupported devices entirely. Currently the device's BARs are saved to the eeh_dev even if the device is not part of an EEH PE. Not being part of a PE means that an EEH recovery pass will never see that device so the saving the BARs is pointless. Signed-off-by: Oliver O'Halloran Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200918093050.37344-7-oohall@gmail.com --- arch/powerpc/platforms/pseries/eeh_pseries.c | 61 ++++++++------------ 1 file changed, 24 insertions(+), 37 deletions(-) diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index c96ee45a4689..4b88b482ef16 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -355,10 +355,10 @@ static struct eeh_pe *pseries_eeh_pe_get_parent(struct eeh_dev *edev) */ void pseries_eeh_init_edev(struct pci_dn *pdn) { + struct eeh_pe pe, *parent; struct eeh_dev *edev; - struct eeh_pe pe; + int addr; u32 pcie_flags; - int enable = 0; int ret; if (WARN_ON_ONCE(!eeh_has_flag(EEH_PROBE_MODE_DEVTREE))) @@ -415,51 +415,38 @@ void pseries_eeh_init_edev(struct pci_dn *pdn) } } - /* Initialize the fake PE */ + /* first up, find the pe_config_addr for the PE containing the device */ + addr = pseries_eeh_get_pe_config_addr(pdn); + if (addr == 0) { + eeh_edev_dbg(edev, "Unable to find pe_config_addr\n"); + goto err; + } + + /* Try enable EEH on the fake PE */ memset(&pe, 0, sizeof(struct eeh_pe)); pe.phb = pdn->phb; - pe.config_addr = (pdn->busno << 16) | (pdn->devfn << 8); + pe.addr = addr; - /* Enable EEH on the device */ eeh_edev_dbg(edev, "Enabling EEH on device\n"); ret = eeh_ops->set_option(&pe, EEH_OPT_ENABLE); if (ret) { eeh_edev_dbg(edev, "EEH failed to enable on device (code %d)\n", ret); - } else { - struct eeh_pe *parent; - - /* Retrieve PE address */ - edev->pe_config_addr = pseries_eeh_get_pe_config_addr(pdn); - pe.addr = edev->pe_config_addr; - - /* Some older systems (Power4) allow the ibm,set-eeh-option - * call to succeed even on nodes where EEH is not supported. - * Verify support explicitly. - */ - ret = eeh_ops->get_state(&pe, NULL); - if (ret > 0 && ret != EEH_STATE_NOT_SUPPORT) - enable = 1; - - /* - * This device doesn't support EEH, but it may have an - * EEH parent. In this case any error on the device will - * freeze the PE of it's upstream bridge, so added it to - * the upstream PE. - */ - parent = pseries_eeh_pe_get_parent(edev); - if (parent && !enable) - edev->pe_config_addr = parent->addr; - - if (enable || parent) { - eeh_add_flag(EEH_ENABLED); - eeh_pe_tree_insert(edev, parent); - } - eeh_edev_dbg(edev, "EEH is %s on device (code %d)\n", - (enable ? "enabled" : "unsupported"), ret); + goto err; } - /* Save memory bars */ + edev->pe_config_addr = addr; + + eeh_add_flag(EEH_ENABLED); + + parent = pseries_eeh_pe_get_parent(edev); + eeh_pe_tree_insert(edev, parent); eeh_save_bars(edev); + eeh_edev_dbg(edev, "EEH enabled for device"); + + return; + +err: + eeh_edev_dbg(edev, "EEH is unsupported on device (code = %d)\n", ret); } static struct eeh_dev *pseries_eeh_probe(struct pci_dev *pdev) From 42de19d5ef71b91765266557705394e52954adb3 Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Fri, 18 Sep 2020 19:30:49 +1000 Subject: [PATCH 332/645] powerpc/pseries/eeh: Allow zero to be a valid PE configuration address There's no real reason why zero can't be a valid PE configuration address. Under qemu each sPAPR PHB (i.e. EEH supporting) has the passed-though devices on bus zero, so the PE address of bus :00 should be zero. However, all previous versions of Linux will reject that, so Qemu at least goes out of it's way to avoid it. The Qemu implementation of ibm,get-config-addr-info2 RTAS has the following comment: > /* > * We always have PE address of form "00BB0001". "BB" > * represents the bus number of PE's primary bus. > */ So qemu puts a one into the register portion of the PE's config_addr to avoid it being zero. The whole is pretty silly considering that RTAS will return a negative error code if it can't map the device's config_addr to a PE. This patch fixes Linux to treat zero as a valid PE address. This shouldn't have any real effects due to the Qemu hack mentioned above. And the fact that Linux EEH has worked historically on PowerVM means they never pass through devices on bus zero so we would never see the problem there either. Signed-off-by: Oliver O'Halloran Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200918093050.37344-8-oohall@gmail.com --- arch/powerpc/platforms/pseries/eeh_pseries.c | 38 +++++++++++--------- 1 file changed, 22 insertions(+), 16 deletions(-) diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index 4b88b482ef16..f8b546135bba 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -87,21 +87,20 @@ void pseries_pcibios_bus_add_device(struct pci_dev *pdev) * pseries_eeh_get_pe_config_addr - Find the pe_config_addr for a device * @pdn: pci_dn of the input device * - * Retrieve the assocated config address. Actually, there're 2 RTAS - * function calls dedicated for the purpose. We need implement - * it through the new function and then the old one. Besides, - * you should make sure the config address is figured out from - * FDT node before calling the function. + * The EEH RTAS calls use a tuple consisting of: (buid_hi, buid_lo, + * pe_config_addr) as a handle to a given PE. This function finds the + * pe_config_addr based on the device's config addr. * - * It's notable that zero'ed return value means invalid PE config - * address. + * Keep in mind that the pe_config_addr *might* be numerically identical to the + * device's config addr, but the two are conceptually distinct. + * + * Returns the pe_config_addr, or a negative error code. */ static int pseries_eeh_get_pe_config_addr(struct pci_dn *pdn) { int config_addr = rtas_config_addr(pdn->busno, pdn->devfn, 0); struct pci_controller *phb = pdn->phb; - int ret = 0; - int rets[3]; + int ret, rets[3]; if (ibm_get_config_addr_info2 != RTAS_UNKNOWN_SERVICE) { /* @@ -112,16 +111,16 @@ static int pseries_eeh_get_pe_config_addr(struct pci_dn *pdn) config_addr, BUID_HI(phb->buid), BUID_LO(phb->buid), 1); if (ret || (rets[0] == 0)) - return 0; + return -ENOENT; - /* Retrieve the associated PE config address */ + /* Retrieve the associated PE config address with function 0 */ ret = rtas_call(ibm_get_config_addr_info2, 4, 2, rets, config_addr, BUID_HI(phb->buid), BUID_LO(phb->buid), 0); if (ret) { pr_warn("%s: Failed to get address for PHB#%x-PE#%x\n", __func__, phb->global_number, config_addr); - return 0; + return -ENXIO; } return rets[0]; @@ -134,13 +133,20 @@ static int pseries_eeh_get_pe_config_addr(struct pci_dn *pdn) if (ret) { pr_warn("%s: Failed to get address for PHB#%x-PE#%x\n", __func__, phb->global_number, config_addr); - return 0; + return -ENXIO; } return rets[0]; } - return ret; + /* + * PAPR does describe a process for finding the pe_config_addr that was + * used before the ibm,get-config-addr-info calls were added. However, + * I haven't found *any* systems that don't have that RTAS call + * implemented. If you happen to find one that needs the old DT based + * process, patches are welcome! + */ + return -ENOENT; } /** @@ -417,7 +423,7 @@ void pseries_eeh_init_edev(struct pci_dn *pdn) /* first up, find the pe_config_addr for the PE containing the device */ addr = pseries_eeh_get_pe_config_addr(pdn); - if (addr == 0) { + if (addr < 0) { eeh_edev_dbg(edev, "Unable to find pe_config_addr\n"); goto err; } @@ -897,7 +903,7 @@ static int __init eeh_pseries_init(void) config_addr = pseries_eeh_get_pe_config_addr(pdn); /* invalid PE config addr */ - if (config_addr == 0) + if (config_addr < 0) continue; pseries_eeh_phb_reset(phb, config_addr, EEH_RESET_FUNDAMENTAL); From 35d64734b64315f2c5716c5a0a380ed1ba8fbe4a Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Fri, 18 Sep 2020 19:30:50 +1000 Subject: [PATCH 333/645] powerpc/eeh: Clean up PE addressing When support for EEH on PowerNV was added a lot of pseries specific code was made "generic" and some of the quirks of pseries EEH came along for the ride. One of the stranger quirks is eeh_pe containing two types of PE address: pe->addr and pe->config_addr. There reason for this appears to be historical baggage rather than any real requirements. On pseries EEH PEs are manipulated using RTAS calls. Each EEH RTAS call takes a "PE configuration address" as an input which is used to identify which EEH PE is being manipulated by the call. When initialising the EEH state for a device the first thing we need to do is determine the configuration address for the PE which contains the device so we can enable EEH on that PE. This process is outlined in PAPR which is the modern (i.e post-2003) FW specification for pseries. However, EEH support was first described in the pSeries RISC Platform Architecture (RPA) and although they are mostly compatible EEH is one of the areas where they are not. The major difference is that RPA doesn't actually have the concept of a PE. On RPA systems the EEH RTAS calls are done on a per-device basis using the same config_addr that would be passed to the RTAS functions to access PCI config space (e.g. ibm,read-pci-config). The config_addr is not identical since the function and config register offsets of the config_addr must be set to zero. EEH operations being done on a per-device basis doesn't make a whole lot of sense when you consider how EEH was implemented on legacy PCI systems. For legacy PCI(-X) systems EEH was implemented using special PCI-PCI bridges which contained logic to detect errors and freeze the secondary bus when one occurred. This means that the EEH enabled state is shared among all devices behind that EEH bridge. As a result there's no way to implement the per-device control required for the semantics specified by RPA. It can be made to work if we assume that a separate EEH bridge exists for each EEH capable PCI slot and there are no bridges behind those slots. However, RPA also specifies the ibm,configure-bridge RTAS call for re-initalising bridges behind EEH capable slots after they are reset due to an EEH event so that is probably not a valid assumption. This incoherence was fixed in later PAPR, which succeeded RPA. Unfortunately, since Linux EEH support seems to have been implemented based on the RPA spec some of the legacy assumptions were carried over (probably for POWER4 compatibility). The fix made in PAPR was the introduction of the "PE" concept and redefining the EEH RTAS calls (set-eeh-option, reset-slot, etc) to operate on a per-PE basis so all devices behind an EEH bride would share the same EEH state. The "config_addr" argument to the EEH RTAS calls became the "PE_config_addr" and the OS was required to use the ibm,get-config-addr-info RTAS call to find the correct PE address for the device. When support for the new interfaces was added to Linux it was implemented using something like: At probe time: pdn->eeh_config_addr = rtas_config_addr(pdn); pdn->eeh_pe_config_addr = rtas_get_config_addr_info(pdn); When performing an RTAS call: config_addr = pdn->eeh_config_addr; if (pdn->eeh_pe_config_addr) config_addr = pdn->eeh_pe_config_addr; rtas_call(..., config_addr, ...); In other words, if the ibm,get-config-addr-info RTAS call is implemented and returned a valid result we'd use that as the argument to the EEH RTAS calls. If not, Linux would fall back to using the device's config_addr. Over time these addresses have moved around going from pci_dn to eeh_dev and finally into eeh_pe. Today the users look like this: config_addr = pe->config_addr; if (pe->addr) config_addr = pe->addr; rtas_call(..., config_addr, ...); However, considering the EEH core always operates on a per-PE basis and even on pseries the only per-device operation is the initial call to ibm,set-eeh-option I'm not sure if any of this actually works on an RPA system today. It doesn't make much sense to have the fallback address in a generic structure either since the bulk of the code which reference it is in pseries anyway. The EEH core makes a token effort to support looking up a PE using the config_addr by having two arguments to eeh_pe_get(). However, a survey of all the callers to eeh_pe_get() shows that all bar one have the config_addr argument hard-coded to zero.The only caller that doesn't is in eeh_pe_tree_insert() which has: if (!eeh_has_flag(EEH_VALID_PE_ZERO) && !edev->pe_config_addr) return -EINVAL; pe = eeh_pe_get(hose, edev->pe_config_addr, edev->bdfn); The third argument (config_addr) is only used if the second (pe->addr) argument is invalid. The preceding check ensures that the call to eeh_pe_get() will never happen if edev->pe_config_addr is invalid so there is no situation where eeh_pe_get() will search for a PE based on the 3rd argument. The check also means that we'll never insert a PE into the tree where pe_config_addr is zero since EEH_VALID_PE_ZERO is never set on pseries. All the users of the fallback address on pseries never actually use the fallback and all the only caller that supplies something for the config_addr argument to eeh_pe_get() never use it either. It's all dead code. This patch removes the fallback address from eeh_pe since nothing uses it. Specificly, we do this by: 1) Removing pe->config_addr 2) Removing the EEH_VALID_PE_ZERO flag 3) Removing the fallback address argument to eeh_pe_get(). 4) Removing all the checks for pe->addr being zero in the pseries EEH code. This leaves us with PE's only being identified by what's in their pe->addr field and the EEH core relying on the platform to ensure that eeh_dev's are only inserted into the EEH tree if they're actually inside a PE. No functional changes, I hope. Signed-off-by: Oliver O'Halloran Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200918093050.37344-9-oohall@gmail.com --- arch/powerpc/include/asm/eeh.h | 4 +- arch/powerpc/kernel/eeh.c | 2 +- arch/powerpc/kernel/eeh_pe.c | 46 +++----------------- arch/powerpc/platforms/powernv/eeh-powernv.c | 16 ++----- arch/powerpc/platforms/pseries/eeh_pseries.c | 42 +++--------------- 5 files changed, 17 insertions(+), 93 deletions(-) diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index 85030c05e67e..dd6a4ac6c713 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -27,7 +27,6 @@ struct pci_dn; #define EEH_FORCE_DISABLED 0x02 /* EEH disabled */ #define EEH_PROBE_MODE_DEV 0x04 /* From PCI device */ #define EEH_PROBE_MODE_DEVTREE 0x08 /* From device tree */ -#define EEH_VALID_PE_ZERO 0x10 /* PE#0 is valid */ #define EEH_ENABLE_IO_FOR_LOG 0x20 /* Enable IO for log */ #define EEH_EARLY_DUMP_LOG 0x40 /* Dump log immediately */ @@ -280,8 +279,7 @@ int eeh_phb_pe_create(struct pci_controller *phb); int eeh_wait_state(struct eeh_pe *pe, int max_wait); struct eeh_pe *eeh_phb_pe_get(struct pci_controller *phb); struct eeh_pe *eeh_pe_next(struct eeh_pe *pe, struct eeh_pe *root); -struct eeh_pe *eeh_pe_get(struct pci_controller *phb, - int pe_no, int config_addr); +struct eeh_pe *eeh_pe_get(struct pci_controller *phb, int pe_no); int eeh_pe_tree_insert(struct eeh_dev *edev, struct eeh_pe *new_pe_parent); int eeh_pe_tree_remove(struct eeh_dev *edev); void eeh_pe_update_time_stamp(struct eeh_pe *pe); diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index c9e25cfce8f0..87de8b798b2d 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -1657,7 +1657,7 @@ static ssize_t eeh_force_recover_write(struct file *filp, return -ENODEV; /* Retrieve PE */ - pe = eeh_pe_get(hose, pe_no, 0); + pe = eeh_pe_get(hose, pe_no); if (!pe) return -ENODEV; diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index d2aaaa73fdd5..61b7d4019051 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -251,43 +251,21 @@ void eeh_pe_dev_traverse(struct eeh_pe *root, /** * __eeh_pe_get - Check the PE address - * @data: EEH PE - * @flag: EEH device * * For one particular PE, it can be identified by PE address * or tranditional BDF address. BDF address is composed of * Bus/Device/Function number. The extra data referred by flag * indicates which type of address should be used. */ -struct eeh_pe_get_flag { - int pe_no; - int config_addr; -}; - static void *__eeh_pe_get(struct eeh_pe *pe, void *flag) { - struct eeh_pe_get_flag *tmp = (struct eeh_pe_get_flag *) flag; + int *target_pe = flag; - /* Unexpected PHB PE */ + /* PHB PEs are special and should be ignored */ if (pe->type & EEH_PE_PHB) return NULL; - /* - * We prefer PE address. For most cases, we should - * have non-zero PE address - */ - if (eeh_has_flag(EEH_VALID_PE_ZERO)) { - if (tmp->pe_no == pe->addr) - return pe; - } else { - if (tmp->pe_no && - (tmp->pe_no == pe->addr)) - return pe; - } - - /* Try BDF address */ - if (tmp->config_addr && - (tmp->config_addr == pe->config_addr)) + if (*target_pe == pe->addr) return pe; return NULL; @@ -297,7 +275,6 @@ static void *__eeh_pe_get(struct eeh_pe *pe, void *flag) * eeh_pe_get - Search PE based on the given address * @phb: PCI controller * @pe_no: PE number - * @config_addr: Config address * * Search the corresponding PE based on the specified address which * is included in the eeh device. The function is used to check if @@ -306,16 +283,11 @@ static void *__eeh_pe_get(struct eeh_pe *pe, void *flag) * which is composed of PCI bus/device/function number, or unified * PE address. */ -struct eeh_pe *eeh_pe_get(struct pci_controller *phb, - int pe_no, int config_addr) +struct eeh_pe *eeh_pe_get(struct pci_controller *phb, int pe_no) { struct eeh_pe *root = eeh_phb_pe_get(phb); - struct eeh_pe_get_flag tmp = { pe_no, config_addr }; - struct eeh_pe *pe; - pe = eeh_pe_traverse(root, __eeh_pe_get, &tmp); - - return pe; + return eeh_pe_traverse(root, __eeh_pe_get, &pe_no); } /** @@ -336,19 +308,13 @@ int eeh_pe_tree_insert(struct eeh_dev *edev, struct eeh_pe *new_pe_parent) struct pci_controller *hose = edev->controller; struct eeh_pe *pe, *parent; - /* Check if the PE number is valid */ - if (!eeh_has_flag(EEH_VALID_PE_ZERO) && !edev->pe_config_addr) { - eeh_edev_err(edev, "PE#0 is invalid for this PHB!\n"); - return -EINVAL; - } - /* * Search the PE has been existing or not according * to the PE address. If that has been existing, the * PE should be composed of PCI bus and its subordinate * components. */ - pe = eeh_pe_get(hose, edev->pe_config_addr, edev->bdfn); + pe = eeh_pe_get(hose, edev->pe_config_addr); if (pe) { if (pe->type & EEH_PE_INVALID) { list_add_tail(&edev->entry, &pe->edevs); diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index b97ec796dd41..89e22c460ebf 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -87,7 +87,7 @@ static ssize_t pnv_eeh_ei_write(struct file *filp, return -EINVAL; /* Retrieve PE */ - pe = eeh_pe_get(hose, pe_no, 0); + pe = eeh_pe_get(hose, pe_no); if (!pe) return -ENODEV; @@ -306,7 +306,7 @@ static struct eeh_pe *pnv_eeh_get_upstream_pe(struct pci_dev *pdev) if (parent) { struct pnv_ioda_pe *ioda_pe = pnv_ioda_get_pe(parent); - return eeh_pe_get(phb->hose, ioda_pe->pe_number, 0); + return eeh_pe_get(phb->hose, ioda_pe->pe_number); } return NULL; @@ -1358,7 +1358,7 @@ static int pnv_eeh_get_pe(struct pci_controller *hose, } /* Find the PE according to PE# */ - dev_pe = eeh_pe_get(hose, pe_no, 0); + dev_pe = eeh_pe_get(hose, pe_no); if (!dev_pe) return -EEXIST; @@ -1693,16 +1693,6 @@ static int __init eeh_powernv_init(void) if (phb->diag_data_size > max_diag_size) max_diag_size = phb->diag_data_size; - /* - * PE#0 should be regarded as valid by EEH core - * if it's not the reserved one. Currently, we - * have the reserved PE#255 and PE#127 for PHB3 - * and P7IOC separately. So we should regard - * PE#0 as valid for PHB3 and P7IOC. - */ - if (phb->ioda.reserved_pe_idx != 0) - eeh_add_flag(EEH_VALID_PE_ZERO); - break; } diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index f8b546135bba..d8fd5f7b2143 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -509,7 +509,6 @@ EXPORT_SYMBOL_GPL(pseries_eeh_init_edev_recursive); static int pseries_eeh_set_option(struct eeh_pe *pe, int option) { int ret = 0; - int config_addr; /* * When we're enabling or disabling EEH functioality on @@ -522,9 +521,6 @@ static int pseries_eeh_set_option(struct eeh_pe *pe, int option) case EEH_OPT_ENABLE: case EEH_OPT_THAW_MMIO: case EEH_OPT_THAW_DMA: - config_addr = pe->config_addr; - if (pe->addr) - config_addr = pe->addr; break; case EEH_OPT_FREEZE_PE: /* Not support */ @@ -535,7 +531,7 @@ static int pseries_eeh_set_option(struct eeh_pe *pe, int option) } ret = rtas_call(ibm_set_eeh_option, 4, 1, NULL, - config_addr, BUID_HI(pe->phb->buid), + pe->addr, BUID_HI(pe->phb->buid), BUID_LO(pe->phb->buid), option); return ret; @@ -556,25 +552,19 @@ static int pseries_eeh_set_option(struct eeh_pe *pe, int option) */ static int pseries_eeh_get_state(struct eeh_pe *pe, int *delay) { - int config_addr; int ret; int rets[4]; int result; - /* Figure out PE config address if possible */ - config_addr = pe->config_addr; - if (pe->addr) - config_addr = pe->addr; - if (ibm_read_slot_reset_state2 != RTAS_UNKNOWN_SERVICE) { ret = rtas_call(ibm_read_slot_reset_state2, 3, 4, rets, - config_addr, BUID_HI(pe->phb->buid), + pe->addr, BUID_HI(pe->phb->buid), BUID_LO(pe->phb->buid)); } else if (ibm_read_slot_reset_state != RTAS_UNKNOWN_SERVICE) { /* Fake PE unavailable info */ rets[2] = 0; ret = rtas_call(ibm_read_slot_reset_state, 3, 3, rets, - config_addr, BUID_HI(pe->phb->buid), + pe->addr, BUID_HI(pe->phb->buid), BUID_LO(pe->phb->buid)); } else { return EEH_STATE_NOT_SUPPORT; @@ -628,14 +618,7 @@ static int pseries_eeh_get_state(struct eeh_pe *pe, int *delay) */ static int pseries_eeh_reset(struct eeh_pe *pe, int option) { - int config_addr; - - /* Figure out PE address */ - config_addr = pe->config_addr; - if (pe->addr) - config_addr = pe->addr; - - return pseries_eeh_phb_reset(pe->phb, config_addr, option); + return pseries_eeh_phb_reset(pe->phb, pe->addr, option); } /** @@ -651,19 +634,13 @@ static int pseries_eeh_reset(struct eeh_pe *pe, int option) */ static int pseries_eeh_get_log(struct eeh_pe *pe, int severity, char *drv_log, unsigned long len) { - int config_addr; unsigned long flags; int ret; spin_lock_irqsave(&slot_errbuf_lock, flags); memset(slot_errbuf, 0, eeh_error_buf_size); - /* Figure out the PE address */ - config_addr = pe->config_addr; - if (pe->addr) - config_addr = pe->addr; - - ret = rtas_call(ibm_slot_error_detail, 8, 1, NULL, config_addr, + ret = rtas_call(ibm_slot_error_detail, 8, 1, NULL, pe->addr, BUID_HI(pe->phb->buid), BUID_LO(pe->phb->buid), virt_to_phys(drv_log), len, virt_to_phys(slot_errbuf), eeh_error_buf_size, @@ -682,14 +659,7 @@ static int pseries_eeh_get_log(struct eeh_pe *pe, int severity, char *drv_log, u */ static int pseries_eeh_configure_bridge(struct eeh_pe *pe) { - int config_addr; - - /* Figure out the PE address */ - config_addr = pe->config_addr; - if (pe->addr) - config_addr = pe->addr; - - return pseries_eeh_phb_configure_bridge(pe->phb, config_addr); + return pseries_eeh_phb_configure_bridge(pe->phb, pe->addr); } /** From d0ffdee8ff01fb21085d835ee54dc8c1c4d19226 Mon Sep 17 00:00:00 2001 From: Gustavo Romero Date: Sat, 19 Sep 2020 12:00:25 -0300 Subject: [PATCH 334/645] powerpc/tm: Save and restore AMR on treclaim and trechkpt Althought AMR is stashed in the checkpoint area, currently we don't save it to the per thread checkpoint struct after a treclaim and so we don't restore it either from that struct when we trechkpt. As a consequence when the transaction is later rolled back the kernel space AMR value when the trechkpt was done appears in userspace. That commit saves and restores AMR accordingly on treclaim and trechkpt. Since AMR value is also used in kernel space in other functions, it also takes care of stashing kernel live AMR into the stack before treclaim and before trechkpt, restoring it later, just before returning from tm_reclaim and __tm_recheckpoint. Is also fixes two nonrelated comments about CR and MSR. Signed-off-by: Gustavo Romero Tested-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200919150025.9609-1-gromero@linux.ibm.com --- arch/powerpc/include/asm/processor.h | 1 + arch/powerpc/kernel/asm-offsets.c | 1 + arch/powerpc/kernel/tm.S | 35 ++++++++++++++++++++++++---- 3 files changed, 33 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 22ffe85a91b8..365290b9a24b 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -220,6 +220,7 @@ struct thread_struct { unsigned long tm_tar; unsigned long tm_ppr; unsigned long tm_dscr; + unsigned long tm_amr; /* * Checkpointed FP and VSX 0-31 register set. diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 8711c2164b45..c2722ff36e98 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -176,6 +176,7 @@ int main(void) OFFSET(THREAD_TM_TAR, thread_struct, tm_tar); OFFSET(THREAD_TM_PPR, thread_struct, tm_ppr); OFFSET(THREAD_TM_DSCR, thread_struct, tm_dscr); + OFFSET(THREAD_TM_AMR, thread_struct, tm_amr); OFFSET(PT_CKPT_REGS, thread_struct, ckpt_regs); OFFSET(THREAD_CKVRSTATE, thread_struct, ckvr_state.vr); OFFSET(THREAD_CKVRSAVE, thread_struct, ckvrsave); diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index 6ba0fdd1e7f8..2b91f233b05d 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -122,6 +122,13 @@ _GLOBAL(tm_reclaim) std r3, STK_PARAM(R3)(r1) SAVE_NVGPRS(r1) + /* + * Save kernel live AMR since it will be clobbered by treclaim + * but can be used elsewhere later in kernel space. + */ + mfspr r3, SPRN_AMR + std r3, TM_FRAME_L1(r1) + /* We need to setup MSR for VSX register save instructions. */ mfmsr r14 mr r15, r14 @@ -245,7 +252,7 @@ _GLOBAL(tm_reclaim) * but is used in signal return to 'wind back' to the abort handler. */ - /* ******************** CR,LR,CCR,MSR ********** */ + /* ***************** CTR, LR, CR, XER ********** */ mfctr r3 mflr r4 mfcr r5 @@ -256,7 +263,6 @@ _GLOBAL(tm_reclaim) std r5, _CCR(r7) std r6, _XER(r7) - /* ******************** TAR, DSCR ********** */ mfspr r3, SPRN_TAR mfspr r4, SPRN_DSCR @@ -264,6 +270,10 @@ _GLOBAL(tm_reclaim) std r3, THREAD_TM_TAR(r12) std r4, THREAD_TM_DSCR(r12) + /* ******************** AMR **************** */ + mfspr r3, SPRN_AMR + std r3, THREAD_TM_AMR(r12) + /* * MSR and flags: We don't change CRs, and we don't need to alter MSR. */ @@ -308,7 +318,9 @@ _GLOBAL(tm_reclaim) std r3, THREAD_TM_TFHAR(r12) std r4, THREAD_TM_TFIAR(r12) - /* AMR is checkpointed too, but is unsupported by Linux. */ + /* Restore kernel live AMR */ + ld r8, TM_FRAME_L1(r1) + mtspr SPRN_AMR, r8 /* Restore original MSR/IRQ state & clear TM mode */ ld r14, TM_FRAME_L0(r1) /* Orig MSR */ @@ -355,6 +367,13 @@ _GLOBAL(__tm_recheckpoint) */ SAVE_NVGPRS(r1) + /* + * Save kernel live AMR since it will be clobbered for trechkpt + * but can be used elsewhere later in kernel space. + */ + mfspr r8, SPRN_AMR + std r8, TM_FRAME_L0(r1) + /* Load complete register state from ts_ckpt* registers */ addi r7, r3, PT_CKPT_REGS /* Thread's ckpt_regs */ @@ -404,7 +423,7 @@ _GLOBAL(__tm_recheckpoint) restore_gprs: - /* ******************** CR,LR,CCR,MSR ********** */ + /* ****************** CTR, LR, XER ************* */ ld r4, _CTR(r7) ld r5, _LINK(r7) ld r8, _XER(r7) @@ -417,6 +436,10 @@ restore_gprs: ld r4, THREAD_TM_TAR(r3) mtspr SPRN_TAR, r4 + /* ******************** AMR ******************** */ + ld r4, THREAD_TM_AMR(r3) + mtspr SPRN_AMR, r4 + /* Load up the PPR and DSCR in GPRs only at this stage */ ld r5, THREAD_TM_DSCR(r3) ld r6, THREAD_TM_PPR(r3) @@ -509,6 +532,10 @@ restore_gprs: li r4, MSR_RI mtmsrd r4, 1 + /* Restore kernel live AMR */ + ld r8, TM_FRAME_L0(r1) + mtspr SPRN_AMR, r8 + REST_NVGPRS(r1) addi r1, r1, TM_FRAME_SIZE From 4bce545903fa0290e011cf118997717f0c4f4d20 Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Mon, 21 Sep 2020 15:26:43 +0530 Subject: [PATCH 335/645] powerpc/topology: Update topology_core_cpumask On Power, cpu_core_mask and cpu_cpu_mask refer to the same set of CPUs. cpu_cpu_mask is needed by scheduler, hence look at deprecating cpu_core_mask. Before deleting the cpu_core_mask, ensure its only user is moved to cpu_cpu_mask. Signed-off-by: Srikar Dronamraju Tested-by: Satheesh Rajendran Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200921095653.9701-2-srikar@linux.vnet.ibm.com --- arch/powerpc/include/asm/topology.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index 6609174918ab..e0f232533c9d 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -122,7 +122,7 @@ int get_physical_package_id(int cpu); #endif #define topology_sibling_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu)) -#define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu)) +#define topology_core_cpumask(cpu) (cpu_cpu_mask(cpu)) #define topology_core_id(cpu) (cpu_to_core_id(cpu)) #endif From 4ca234a9cbd7c3a656b34dd98c8b156f70ed7849 Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Mon, 21 Sep 2020 15:26:44 +0530 Subject: [PATCH 336/645] powerpc/smp: Stop updating cpu_core_mask Anton Blanchard reported that his 4096 vcpu KVM guest took around 30 minutes to boot. He also analyzed it to the time taken to iterate while setting the cpu_core_mask. Further analysis shows that cpu_core_mask and cpu_cpu_mask for any CPU would be equal on Power. However updating cpu_core_mask took forever to update as its a per cpu cpumask variable. Instead cpu_cpu_mask was a per NODE /per DIE cpumask that was shared by all the respective CPUs. Also cpu_cpu_mask is needed from a scheduler perspective. However cpu_core_map is an exported symbol. Hence stop updating cpu_core_map and make it point to cpu_cpu_mask. Signed-off-by: Srikar Dronamraju Tested-by: Satheesh Rajendran Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200921095653.9701-3-srikar@linux.vnet.ibm.com --- arch/powerpc/include/asm/smp.h | 5 ----- arch/powerpc/kernel/smp.c | 33 +++++++-------------------------- 2 files changed, 7 insertions(+), 31 deletions(-) diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index 635bdf947105..b2035b2f57ce 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -121,11 +121,6 @@ static inline struct cpumask *cpu_sibling_mask(int cpu) return per_cpu(cpu_sibling_map, cpu); } -static inline struct cpumask *cpu_core_mask(int cpu) -{ - return per_cpu(cpu_core_map, cpu); -} - static inline struct cpumask *cpu_l2_cache_mask(int cpu) { return per_cpu(cpu_l2_cache_map, cpu); diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 58990baa5182..bf6d4192adda 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -953,12 +953,17 @@ void __init smp_prepare_cpus(unsigned int max_cpus) local_memory_node(numa_cpu_lookup_table[cpu])); } #endif + /* + * cpu_core_map is now more updated and exists only since + * its been exported for long. It only will have a snapshot + * of cpu_cpu_mask. + */ + cpumask_copy(per_cpu(cpu_core_map, cpu), cpu_cpu_mask(cpu)); } /* Init the cpumasks so the boot CPU is related to itself */ cpumask_set_cpu(boot_cpuid, cpu_sibling_mask(boot_cpuid)); cpumask_set_cpu(boot_cpuid, cpu_l2_cache_mask(boot_cpuid)); - cpumask_set_cpu(boot_cpuid, cpu_core_mask(boot_cpuid)); if (has_coregroup_support()) cpumask_set_cpu(boot_cpuid, cpu_coregroup_mask(boot_cpuid)); @@ -1260,9 +1265,7 @@ static void remove_cpu_from_masks(int cpu) { int i; - /* NB: cpu_core_mask is a superset of the others */ - for_each_cpu(i, cpu_core_mask(cpu)) { - set_cpus_unrelated(cpu, i, cpu_core_mask); + for_each_cpu(i, cpu_cpu_mask(cpu)) { set_cpus_unrelated(cpu, i, cpu_l2_cache_mask); set_cpus_unrelated(cpu, i, cpu_sibling_mask); if (has_big_cores) @@ -1312,7 +1315,6 @@ EXPORT_SYMBOL_GPL(get_physical_package_id); static void add_cpu_to_masks(int cpu) { int first_thread = cpu_first_thread_sibling(cpu); - int pkg_id = get_physical_package_id(cpu); int i; /* @@ -1320,7 +1322,6 @@ static void add_cpu_to_masks(int cpu) * add it to it's own thread sibling mask. */ cpumask_set_cpu(cpu, cpu_sibling_mask(cpu)); - cpumask_set_cpu(cpu, cpu_core_mask(cpu)); for (i = first_thread; i < first_thread + threads_per_core; i++) if (cpu_online(i)) @@ -1342,26 +1343,6 @@ static void add_cpu_to_masks(int cpu) set_cpus_related(cpu, i, cpu_coregroup_mask); } } - - if (pkg_id == -1) { - struct cpumask *(*mask)(int) = cpu_sibling_mask; - - /* - * Copy the sibling mask into core sibling mask and - * mark any CPUs on the same chip as this CPU. - */ - if (shared_caches) - mask = cpu_l2_cache_mask; - - for_each_cpu(i, mask(cpu)) - set_cpus_related(cpu, i, cpu_core_mask); - - return; - } - - for_each_cpu(i, cpu_online_mask) - if (get_physical_package_id(i) == pkg_id) - set_cpus_related(cpu, i, cpu_core_mask); } /* Activate a secondary processor. */ From e29e9ed665eeb6f98cd88672994ecf4aaefdb943 Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Mon, 21 Sep 2020 15:26:45 +0530 Subject: [PATCH 337/645] powerpc/smp: Remove get_physical_package_id Now that cpu_core_mask has been removed and topology_core_cpumask has been updated to use cpu_cpu_mask, we no more need get_physical_package_id. Signed-off-by: Srikar Dronamraju Tested-by: Satheesh Rajendran Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200921095653.9701-4-srikar@linux.vnet.ibm.com --- arch/powerpc/include/asm/topology.h | 5 ----- arch/powerpc/kernel/smp.c | 20 -------------------- 2 files changed, 25 deletions(-) diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index e0f232533c9d..e45219f74be0 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -114,12 +114,7 @@ static inline int cpu_to_coregroup_id(int cpu) #ifdef CONFIG_PPC64 #include -#ifdef CONFIG_PPC_SPLPAR -int get_physical_package_id(int cpu); -#define topology_physical_package_id(cpu) (get_physical_package_id(cpu)) -#else #define topology_physical_package_id(cpu) (cpu_to_chip_id(cpu)) -#endif #define topology_sibling_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu)) #define topology_core_cpumask(cpu) (cpu_cpu_mask(cpu)) diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index bf6d4192adda..aecc01f0e95e 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -1292,26 +1292,6 @@ static inline void add_cpu_to_smallcore_masks(int cpu) } } -int get_physical_package_id(int cpu) -{ - int pkg_id = cpu_to_chip_id(cpu); - - /* - * If the platform is PowerNV or Guest on KVM, ibm,chip-id is - * defined. Hence we would return the chip-id as the result of - * get_physical_package_id. - */ - if (pkg_id == -1 && firmware_has_feature(FW_FEATURE_LPAR) && - IS_ENABLED(CONFIG_PPC_SPLPAR)) { - struct device_node *np = of_get_cpu_node(cpu, NULL); - pkg_id = of_node_to_nid(np); - of_node_put(np); - } - - return pkg_id; -} -EXPORT_SYMBOL_GPL(get_physical_package_id); - static void add_cpu_to_masks(int cpu) { int first_thread = cpu_first_thread_sibling(cpu); From 70edd4a7c753ba18e3e4bb9e97b6d85156cea738 Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Mon, 21 Sep 2020 15:26:46 +0530 Subject: [PATCH 338/645] powerpc/smp: Optimize remove_cpu_from_masks While offlining a CPU, system currently iterate through all the CPUs in the DIE to clear sibling, l2_cache and smallcore maps. However if there are more cores in a DIE, system can end up spending more time iterating through CPUs which are completely unrelated. Optimize this by only iterating through smaller but relevant cpumap. If shared_cache is set, cpu_l2_cache_map should be relevant else cpu_sibling_map would be relevant. Signed-off-by: Srikar Dronamraju Tested-by: Satheesh Rajendran Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200921095653.9701-5-srikar@linux.vnet.ibm.com --- arch/powerpc/kernel/smp.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index aecc01f0e95e..9cdb966f00b3 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -1263,14 +1263,21 @@ static bool update_mask_by_l2(int cpu, struct cpumask *(*mask_fn)(int)) #ifdef CONFIG_HOTPLUG_CPU static void remove_cpu_from_masks(int cpu) { + struct cpumask *(*mask_fn)(int) = cpu_sibling_mask; int i; - for_each_cpu(i, cpu_cpu_mask(cpu)) { + if (shared_caches) + mask_fn = cpu_l2_cache_mask; + + for_each_cpu(i, mask_fn(cpu)) { set_cpus_unrelated(cpu, i, cpu_l2_cache_mask); set_cpus_unrelated(cpu, i, cpu_sibling_mask); if (has_big_cores) set_cpus_unrelated(cpu, i, cpu_smallcore_mask); - if (has_coregroup_support()) + } + + if (has_coregroup_support()) { + for_each_cpu(i, cpu_coregroup_mask(cpu)) set_cpus_unrelated(cpu, i, cpu_coregroup_mask); } } From 53516d4abacfab1faaa075c1f79957abc3da358c Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Mon, 21 Sep 2020 15:26:47 +0530 Subject: [PATCH 339/645] powerpc/smp: Limit CPUs traversed to within a node. All the arch specific topology cpumasks are within a node/DIE. However when setting these per CPU cpumasks, system traverses through all the online CPUs. This is redundant. Reduce the traversal to only CPUs that are online in the node to which the CPU belongs to. Signed-off-by: Srikar Dronamraju Tested-by: Satheesh Rajendran Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200921095653.9701-6-srikar@linux.vnet.ibm.com --- arch/powerpc/kernel/smp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 9cdb966f00b3..9455af47123c 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -1241,7 +1241,7 @@ static bool update_mask_by_l2(int cpu, struct cpumask *(*mask_fn)(int)) } cpumask_set_cpu(cpu, mask_fn(cpu)); - for_each_cpu(i, cpu_online_mask) { + for_each_cpu_and(i, cpu_online_mask, cpu_cpu_mask(cpu)) { /* * when updating the marks the current CPU has not been marked * online, but we need to update the cache masks From 1f3a4181042107e32e44047e9dde990aced845b5 Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Mon, 21 Sep 2020 15:26:48 +0530 Subject: [PATCH 340/645] powerpc/smp: Stop passing mask to update_mask_by_l2 update_mask_by_l2 is called only once. But it passes cpu_l2_cache_mask as parameter. Instead of passing cpu_l2_cache_mask, use it directly in update_mask_by_l2. Signed-off-by: Srikar Dronamraju Tested-by: Satheesh Rajendran Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200921095653.9701-7-srikar@linux.vnet.ibm.com --- arch/powerpc/kernel/smp.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 9455af47123c..0e96f6687363 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -1218,7 +1218,7 @@ static struct device_node *cpu_to_l2cache(int cpu) return cache; } -static bool update_mask_by_l2(int cpu, struct cpumask *(*mask_fn)(int)) +static bool update_mask_by_l2(int cpu) { struct device_node *l2_cache, *np; int i; @@ -1240,7 +1240,7 @@ static bool update_mask_by_l2(int cpu, struct cpumask *(*mask_fn)(int)) return false; } - cpumask_set_cpu(cpu, mask_fn(cpu)); + cpumask_set_cpu(cpu, cpu_l2_cache_mask(cpu)); for_each_cpu_and(i, cpu_online_mask, cpu_cpu_mask(cpu)) { /* * when updating the marks the current CPU has not been marked @@ -1251,7 +1251,7 @@ static bool update_mask_by_l2(int cpu, struct cpumask *(*mask_fn)(int)) continue; if (np == l2_cache) - set_cpus_related(cpu, i, mask_fn); + set_cpus_related(cpu, i, cpu_l2_cache_mask); of_node_put(np); } @@ -1315,7 +1315,7 @@ static void add_cpu_to_masks(int cpu) set_cpus_related(i, cpu, cpu_sibling_mask); add_cpu_to_smallcore_masks(cpu); - update_mask_by_l2(cpu, cpu_l2_cache_mask); + update_mask_by_l2(cpu); if (has_coregroup_support()) { int coregroup_id = cpu_to_coregroup_id(cpu); From 661e3d42f99193b7fdd71467a87e48f6e597c285 Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Mon, 21 Sep 2020 15:26:49 +0530 Subject: [PATCH 341/645] powerpc/smp: Depend on cpu_l1_cache_map when adding CPUs Currently on hotplug/hotunplug, CPU iterates through all the CPUs in its core to find threads in its thread group. However this info is already captured in cpu_l1_cache_map. Hence reduce iterations and cleanup add_cpu_to_smallcore_masks function. Signed-off-by: Srikar Dronamraju Tested-by: Satheesh Rajendran Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200921095653.9701-8-srikar@linux.vnet.ibm.com --- arch/powerpc/kernel/smp.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 0e96f6687363..3a3e6bbab29c 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -1285,16 +1285,15 @@ static void remove_cpu_from_masks(int cpu) static inline void add_cpu_to_smallcore_masks(int cpu) { - struct cpumask *this_l1_cache_map = per_cpu(cpu_l1_cache_map, cpu); - int i, first_thread = cpu_first_thread_sibling(cpu); + int i; if (!has_big_cores) return; cpumask_set_cpu(cpu, cpu_smallcore_mask(cpu)); - for (i = first_thread; i < first_thread + threads_per_core; i++) { - if (cpu_online(i) && cpumask_test_cpu(i, this_l1_cache_map)) + for_each_cpu(i, per_cpu(cpu_l1_cache_map, cpu)) { + if (cpu_online(i)) set_cpus_related(i, cpu, cpu_smallcore_mask); } } From 375370a10d061d5c75c6bc5b09c5db4cc0b0fcfe Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Mon, 21 Sep 2020 15:26:50 +0530 Subject: [PATCH 342/645] powerpc/smp: Check for duplicate topologies and consolidate CACHE and COREGROUP domains are now part of default topology. However on systems that don't support CACHE or COREGROUP, these domains will eventually be degenerated. The degeneration happens per CPU. Do note the current fixup_topology() logic ensures that mask of a domain that is not supported on the current platform is set to the previous domain. Instead of waiting for the scheduler to degenerated try to consolidate based on their masks and sd_flags. This is done just before setting the scheduler topology. Signed-off-by: Srikar Dronamraju Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200921095653.9701-9-srikar@linux.vnet.ibm.com --- arch/powerpc/kernel/smp.c | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 3a3e6bbab29c..917c8598cf61 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -1401,6 +1401,8 @@ int setup_profiling_timer(unsigned int multiplier) static void fixup_topology(void) { + int i; + #ifdef CONFIG_SCHED_SMT if (has_big_cores) { pr_info("Big cores detected but using small core scheduling\n"); @@ -1410,6 +1412,30 @@ static void fixup_topology(void) if (!has_coregroup_support()) powerpc_topology[mc_idx].mask = powerpc_topology[cache_idx].mask; + + /* + * Try to consolidate topology levels here instead of + * allowing scheduler to degenerate. + * - Dont consolidate if masks are different. + * - Dont consolidate if sd_flags exists and are different. + */ + for (i = 1; i <= die_idx; i++) { + if (powerpc_topology[i].mask != powerpc_topology[i - 1].mask) + continue; + + if (powerpc_topology[i].sd_flags && powerpc_topology[i - 1].sd_flags && + powerpc_topology[i].sd_flags != powerpc_topology[i - 1].sd_flags) + continue; + + if (!powerpc_topology[i - 1].sd_flags) + powerpc_topology[i - 1].sd_flags = powerpc_topology[i].sd_flags; + + powerpc_topology[i].mask = powerpc_topology[i + 1].mask; + powerpc_topology[i].sd_flags = powerpc_topology[i + 1].sd_flags; +#ifdef CONFIG_SCHED_DEBUG + powerpc_topology[i].name = powerpc_topology[i + 1].name; +#endif + } } void __init smp_cpus_done(unsigned int max_cpus) From 3ab33d6dc3e98e83b55732049e1d1d488207bb6d Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Mon, 21 Sep 2020 15:26:51 +0530 Subject: [PATCH 343/645] powerpc/smp: Optimize update_mask_by_l2 All threads of a SMT4 core can either be part of this CPU's l2-cache mask or not related to this CPU l2-cache mask. Use this relation to reduce the number of iterations needed to find all the CPUs that share the same l2-cache. Use a temporary mask to iterate through the CPUs that may share l2_cache mask. Also instead of setting one CPU at a time into cpu_l2_cache_mask, copy the SMT4/sub mask at one shot. Signed-off-by: Srikar Dronamraju Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200921095653.9701-10-srikar@linux.vnet.ibm.com --- arch/powerpc/kernel/smp.c | 51 ++++++++++++++++++++++++++++++++++----- 1 file changed, 45 insertions(+), 6 deletions(-) diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 917c8598cf61..925251b0bb0f 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -670,6 +670,28 @@ static void set_cpus_unrelated(int i, int j, } #endif +/* + * Extends set_cpus_related. Instead of setting one CPU at a time in + * dstmask, set srcmask at oneshot. dstmask should be super set of srcmask. + */ +static void or_cpumasks_related(int i, int j, struct cpumask *(*srcmask)(int), + struct cpumask *(*dstmask)(int)) +{ + struct cpumask *mask; + int k; + + mask = srcmask(j); + for_each_cpu(k, srcmask(i)) + cpumask_or(dstmask(k), dstmask(k), mask); + + if (i == j) + return; + + mask = srcmask(i); + for_each_cpu(k, srcmask(j)) + cpumask_or(dstmask(k), dstmask(k), mask); +} + /* * parse_thread_groups: Parses the "ibm,thread-groups" device tree * property for the CPU device node @dn and stores @@ -1220,7 +1242,9 @@ static struct device_node *cpu_to_l2cache(int cpu) static bool update_mask_by_l2(int cpu) { + struct cpumask *(*submask_fn)(int) = cpu_sibling_mask; struct device_node *l2_cache, *np; + cpumask_var_t mask; int i; l2_cache = cpu_to_l2cache(cpu); @@ -1240,22 +1264,37 @@ static bool update_mask_by_l2(int cpu) return false; } - cpumask_set_cpu(cpu, cpu_l2_cache_mask(cpu)); - for_each_cpu_and(i, cpu_online_mask, cpu_cpu_mask(cpu)) { + alloc_cpumask_var_node(&mask, GFP_KERNEL, cpu_to_node(cpu)); + cpumask_and(mask, cpu_online_mask, cpu_cpu_mask(cpu)); + + if (has_big_cores) + submask_fn = cpu_smallcore_mask; + + /* Update l2-cache mask with all the CPUs that are part of submask */ + or_cpumasks_related(cpu, cpu, submask_fn, cpu_l2_cache_mask); + + /* Skip all CPUs already part of current CPU l2-cache mask */ + cpumask_andnot(mask, mask, cpu_l2_cache_mask(cpu)); + + for_each_cpu(i, mask) { /* * when updating the marks the current CPU has not been marked * online, but we need to update the cache masks */ np = cpu_to_l2cache(i); - if (!np) - continue; - if (np == l2_cache) - set_cpus_related(cpu, i, cpu_l2_cache_mask); + /* Skip all CPUs already part of current CPU l2-cache */ + if (np == l2_cache) { + or_cpumasks_related(cpu, i, submask_fn, cpu_l2_cache_mask); + cpumask_andnot(mask, mask, submask_fn(i)); + } else { + cpumask_andnot(mask, mask, cpu_l2_cache_mask(i)); + } of_node_put(np); } of_node_put(l2_cache); + free_cpumask_var(mask); return true; } From b8a97cb4599cda28bd3b3bc13042f5803b42ad65 Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Mon, 21 Sep 2020 15:26:52 +0530 Subject: [PATCH 344/645] powerpc/smp: Move coregroup mask updation to a new function Move the logic for updating the coregroup mask of a CPU to its own function. This will help in reworking the updation of coregroup mask in subsequent patch. Signed-off-by: Srikar Dronamraju Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200921095653.9701-11-srikar@linux.vnet.ibm.com --- arch/powerpc/kernel/smp.c | 32 +++++++++++++++++++------------- 1 file changed, 19 insertions(+), 13 deletions(-) diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 925251b0bb0f..45619433c43a 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -1337,6 +1337,23 @@ static inline void add_cpu_to_smallcore_masks(int cpu) } } +static void update_coregroup_mask(int cpu) +{ + int first_thread = cpu_first_thread_sibling(cpu); + int coregroup_id = cpu_to_coregroup_id(cpu); + int i; + + cpumask_set_cpu(cpu, cpu_coregroup_mask(cpu)); + for_each_cpu_and(i, cpu_online_mask, cpu_cpu_mask(cpu)) { + int fcpu = cpu_first_thread_sibling(i); + + if (fcpu == first_thread) + set_cpus_related(cpu, i, cpu_coregroup_mask); + else if (coregroup_id == cpu_to_coregroup_id(i)) + set_cpus_related(cpu, i, cpu_coregroup_mask); + } +} + static void add_cpu_to_masks(int cpu) { int first_thread = cpu_first_thread_sibling(cpu); @@ -1355,19 +1372,8 @@ static void add_cpu_to_masks(int cpu) add_cpu_to_smallcore_masks(cpu); update_mask_by_l2(cpu); - if (has_coregroup_support()) { - int coregroup_id = cpu_to_coregroup_id(cpu); - - cpumask_set_cpu(cpu, cpu_coregroup_mask(cpu)); - for_each_cpu_and(i, cpu_online_mask, cpu_cpu_mask(cpu)) { - int fcpu = cpu_first_thread_sibling(i); - - if (fcpu == first_thread) - set_cpus_related(cpu, i, cpu_coregroup_mask); - else if (coregroup_id == cpu_to_coregroup_id(i)) - set_cpus_related(cpu, i, cpu_coregroup_mask); - } - } + if (has_coregroup_support()) + update_coregroup_mask(cpu); } /* Activate a secondary processor. */ From 70a94089d7f7fa91bc1795622426b3ed017ec71a Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Mon, 21 Sep 2020 15:26:53 +0530 Subject: [PATCH 345/645] powerpc/smp: Optimize update_coregroup_mask All threads of a SMT4/SMT8 core can either be part of CPU's coregroup mask or outside the coregroup. Use this relation to reduce the number of iterations needed to find all the CPUs that share the same coregroup Use a temporary mask to iterate through the CPUs that may share coregroup mask. Also instead of setting one CPU at a time into cpu_coregroup_mask, copy the SMT4/SMT8/submask at one shot. Signed-off-by: Srikar Dronamraju Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200921095653.9701-12-srikar@linux.vnet.ibm.com --- arch/powerpc/kernel/smp.c | 30 ++++++++++++++++++++++-------- 1 file changed, 22 insertions(+), 8 deletions(-) diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 45619433c43a..0dc1b8591cc8 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -1339,19 +1339,33 @@ static inline void add_cpu_to_smallcore_masks(int cpu) static void update_coregroup_mask(int cpu) { - int first_thread = cpu_first_thread_sibling(cpu); + struct cpumask *(*submask_fn)(int) = cpu_sibling_mask; + cpumask_var_t mask; int coregroup_id = cpu_to_coregroup_id(cpu); int i; - cpumask_set_cpu(cpu, cpu_coregroup_mask(cpu)); - for_each_cpu_and(i, cpu_online_mask, cpu_cpu_mask(cpu)) { - int fcpu = cpu_first_thread_sibling(i); + alloc_cpumask_var_node(&mask, GFP_KERNEL, cpu_to_node(cpu)); + cpumask_and(mask, cpu_online_mask, cpu_cpu_mask(cpu)); - if (fcpu == first_thread) - set_cpus_related(cpu, i, cpu_coregroup_mask); - else if (coregroup_id == cpu_to_coregroup_id(i)) - set_cpus_related(cpu, i, cpu_coregroup_mask); + if (shared_caches) + submask_fn = cpu_l2_cache_mask; + + /* Update coregroup mask with all the CPUs that are part of submask */ + or_cpumasks_related(cpu, cpu, submask_fn, cpu_coregroup_mask); + + /* Skip all CPUs already part of coregroup mask */ + cpumask_andnot(mask, mask, cpu_coregroup_mask(cpu)); + + for_each_cpu(i, mask) { + /* Skip all CPUs not part of this coregroup */ + if (coregroup_id == cpu_to_coregroup_id(i)) { + or_cpumasks_related(cpu, i, submask_fn, cpu_coregroup_mask); + cpumask_andnot(mask, mask, submask_fn(i)); + } else { + cpumask_andnot(mask, mask, cpu_coregroup_mask(i)); + } } + free_cpumask_var(mask); } static void add_cpu_to_masks(int cpu) From 3b6c3adbb2fa42749c3d38cfc4d4d0b7e096bb7b Mon Sep 17 00:00:00 2001 From: Athira Rajeev Date: Mon, 21 Sep 2020 03:10:04 -0400 Subject: [PATCH 346/645] powerpc/perf: Exclude pmc5/6 from the irrelevant PMU group constraints PMU counter support functions enforces event constraints for group of events to check if all events in a group can be monitored. Incase of event codes using PMC5 and PMC6 ( 500fa and 600f4 respectively ), not all constraints are applicable, say the threshold or sample bits. But current code includes pmc5 and pmc6 in some group constraints (like IC_DC Qualifier bits) which is actually not applicable and hence results in those events not getting counted when scheduled along with group of other events. Patch fixes this by excluding PMC5/6 from constraints which are not relevant for it. Fixes: 7ffd948 ("powerpc/perf: factor out power8 pmu functions") Signed-off-by: Athira Rajeev Reviewed-by: Madhavan Srinivasan Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/1600672204-1610-1-git-send-email-atrajeev@linux.vnet.ibm.com --- arch/powerpc/perf/isa207-common.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c index 964437adec18..2848904df638 100644 --- a/arch/powerpc/perf/isa207-common.c +++ b/arch/powerpc/perf/isa207-common.c @@ -288,6 +288,15 @@ int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp) mask |= CNST_PMC_MASK(pmc); value |= CNST_PMC_VAL(pmc); + + /* + * PMC5 and PMC6 are used to count cycles and instructions and + * they do not support most of the constraint bits. Add a check + * to exclude PMC5/6 from most of the constraints except for + * EBB/BHRB. + */ + if (pmc >= 5) + goto ebb_bhrb; } if (pmc <= 4) { @@ -357,6 +366,7 @@ int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp) } } +ebb_bhrb: if (!pmc && ebb) /* EBB events must specify the PMC */ return -1; From bd59380c5ba4147dcbaad3e582b55ccfd120b764 Mon Sep 17 00:00:00 2001 From: Andrew Donnellan Date: Thu, 20 Aug 2020 14:45:12 +1000 Subject: [PATCH 347/645] powerpc/rtas: Restrict RTAS requests from userspace A number of userspace utilities depend on making calls to RTAS to retrieve information and update various things. The existing API through which we expose RTAS to userspace exposes more RTAS functionality than we actually need, through the sys_rtas syscall, which allows root (or anyone with CAP_SYS_ADMIN) to make any RTAS call they want with arbitrary arguments. Many RTAS calls take the address of a buffer as an argument, and it's up to the caller to specify the physical address of the buffer as an argument. We allocate a buffer (the "RMO buffer") in the Real Memory Area that RTAS can access, and then expose the physical address and size of this buffer in /proc/powerpc/rtas/rmo_buffer. Userspace is expected to read this address, poke at the buffer using /dev/mem, and pass an address in the RMO buffer to the RTAS call. However, there's nothing stopping the caller from specifying whatever address they want in the RTAS call, and it's easy to construct a series of RTAS calls that can overwrite arbitrary bytes (even without /dev/mem access). Additionally, there are some RTAS calls that do potentially dangerous things and for which there are no legitimate userspace use cases. In the past, this would not have been a particularly big deal as it was assumed that root could modify all system state freely, but with Secure Boot and lockdown we need to care about this. We can't fundamentally change the ABI at this point, however we can address this by implementing a filter that checks RTAS calls against a list of permitted calls and forces the caller to use addresses within the RMO buffer. The list is based off the list of calls that are used by the librtas userspace library, and has been tested with a number of existing userspace RTAS utilities. For compatibility with any applications we are not aware of that require other calls, the filter can be turned off at build time. Cc: stable@vger.kernel.org Reported-by: Daniel Axtens Signed-off-by: Andrew Donnellan Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200820044512.7543-1-ajd@linux.ibm.com --- arch/powerpc/Kconfig | 13 ++++ arch/powerpc/kernel/rtas.c | 153 +++++++++++++++++++++++++++++++++++++ 2 files changed, 166 insertions(+) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index fe0e6b317cc2..6c76caa950e1 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -1004,6 +1004,19 @@ config PPC_SECVAR_SYSFS read/write operations on these variables. Say Y if you have secure boot enabled and want to expose variables to userspace. +config PPC_RTAS_FILTER + bool "Enable filtering of RTAS syscalls" + default y + depends on PPC_RTAS + help + The RTAS syscall API has security issues that could be used to + compromise system integrity. This option enforces restrictions on the + RTAS calls and arguments passed by userspace programs to mitigate + these issues. + + Say Y unless you know what you are doing and the filter is causing + problems for you. + endmenu config ISA_DMA_API diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 806d554ce357..954f41676f69 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -992,6 +992,147 @@ struct pseries_errorlog *get_pseries_errorlog(struct rtas_error_log *log, return NULL; } +#ifdef CONFIG_PPC_RTAS_FILTER + +/* + * The sys_rtas syscall, as originally designed, allows root to pass + * arbitrary physical addresses to RTAS calls. A number of RTAS calls + * can be abused to write to arbitrary memory and do other things that + * are potentially harmful to system integrity, and thus should only + * be used inside the kernel and not exposed to userspace. + * + * All known legitimate users of the sys_rtas syscall will only ever + * pass addresses that fall within the RMO buffer, and use a known + * subset of RTAS calls. + * + * Accordingly, we filter RTAS requests to check that the call is + * permitted, and that provided pointers fall within the RMO buffer. + * The rtas_filters list contains an entry for each permitted call, + * with the indexes of the parameters which are expected to contain + * addresses and sizes of buffers allocated inside the RMO buffer. + */ +struct rtas_filter { + const char *name; + int token; + /* Indexes into the args buffer, -1 if not used */ + int buf_idx1; + int size_idx1; + int buf_idx2; + int size_idx2; + + int fixed_size; +}; + +static struct rtas_filter rtas_filters[] __ro_after_init = { + { "ibm,activate-firmware", -1, -1, -1, -1, -1 }, + { "ibm,configure-connector", -1, 0, -1, 1, -1, 4096 }, /* Special cased */ + { "display-character", -1, -1, -1, -1, -1 }, + { "ibm,display-message", -1, 0, -1, -1, -1 }, + { "ibm,errinjct", -1, 2, -1, -1, -1, 1024 }, + { "ibm,close-errinjct", -1, -1, -1, -1, -1 }, + { "ibm,open-errinct", -1, -1, -1, -1, -1 }, + { "ibm,get-config-addr-info2", -1, -1, -1, -1, -1 }, + { "ibm,get-dynamic-sensor-state", -1, 1, -1, -1, -1 }, + { "ibm,get-indices", -1, 2, 3, -1, -1 }, + { "get-power-level", -1, -1, -1, -1, -1 }, + { "get-sensor-state", -1, -1, -1, -1, -1 }, + { "ibm,get-system-parameter", -1, 1, 2, -1, -1 }, + { "get-time-of-day", -1, -1, -1, -1, -1 }, + { "ibm,get-vpd", -1, 0, -1, 1, 2 }, + { "ibm,lpar-perftools", -1, 2, 3, -1, -1 }, + { "ibm,platform-dump", -1, 4, 5, -1, -1 }, + { "ibm,read-slot-reset-state", -1, -1, -1, -1, -1 }, + { "ibm,scan-log-dump", -1, 0, 1, -1, -1 }, + { "ibm,set-dynamic-indicator", -1, 2, -1, -1, -1 }, + { "ibm,set-eeh-option", -1, -1, -1, -1, -1 }, + { "set-indicator", -1, -1, -1, -1, -1 }, + { "set-power-level", -1, -1, -1, -1, -1 }, + { "set-time-for-power-on", -1, -1, -1, -1, -1 }, + { "ibm,set-system-parameter", -1, 1, -1, -1, -1 }, + { "set-time-of-day", -1, -1, -1, -1, -1 }, + { "ibm,suspend-me", -1, -1, -1, -1, -1 }, + { "ibm,update-nodes", -1, 0, -1, -1, -1, 4096 }, + { "ibm,update-properties", -1, 0, -1, -1, -1, 4096 }, + { "ibm,physical-attestation", -1, 0, 1, -1, -1 }, +}; + +static bool in_rmo_buf(u32 base, u32 end) +{ + return base >= rtas_rmo_buf && + base < (rtas_rmo_buf + RTAS_RMOBUF_MAX) && + base <= end && + end >= rtas_rmo_buf && + end < (rtas_rmo_buf + RTAS_RMOBUF_MAX); +} + +static bool block_rtas_call(int token, int nargs, + struct rtas_args *args) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(rtas_filters); i++) { + struct rtas_filter *f = &rtas_filters[i]; + u32 base, size, end; + + if (token != f->token) + continue; + + if (f->buf_idx1 != -1) { + base = be32_to_cpu(args->args[f->buf_idx1]); + if (f->size_idx1 != -1) + size = be32_to_cpu(args->args[f->size_idx1]); + else if (f->fixed_size) + size = f->fixed_size; + else + size = 1; + + end = base + size - 1; + if (!in_rmo_buf(base, end)) + goto err; + } + + if (f->buf_idx2 != -1) { + base = be32_to_cpu(args->args[f->buf_idx2]); + if (f->size_idx2 != -1) + size = be32_to_cpu(args->args[f->size_idx2]); + else if (f->fixed_size) + size = f->fixed_size; + else + size = 1; + end = base + size - 1; + + /* + * Special case for ibm,configure-connector where the + * address can be 0 + */ + if (!strcmp(f->name, "ibm,configure-connector") && + base == 0) + return false; + + if (!in_rmo_buf(base, end)) + goto err; + } + + return false; + } + +err: + pr_err_ratelimited("sys_rtas: RTAS call blocked - exploit attempt?\n"); + pr_err_ratelimited("sys_rtas: token=0x%x, nargs=%d (called by %s)\n", + token, nargs, current->comm); + return true; +} + +#else + +static bool block_rtas_call(int token, int nargs, + struct rtas_args *args) +{ + return false; +} + +#endif /* CONFIG_PPC_RTAS_FILTER */ + /* We assume to be passed big endian arguments */ SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs) { @@ -1029,6 +1170,9 @@ SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs) args.rets = &args.args[nargs]; memset(args.rets, 0, nret * sizeof(rtas_arg_t)); + if (block_rtas_call(token, nargs, &args)) + return -EINVAL; + /* Need to handle ibm,suspend_me call specially */ if (token == ibm_suspend_me_token) { @@ -1090,6 +1234,9 @@ void __init rtas_initialize(void) unsigned long rtas_region = RTAS_INSTANTIATE_MAX; u32 base, size, entry; int no_base, no_size, no_entry; +#ifdef CONFIG_PPC_RTAS_FILTER + int i; +#endif /* Get RTAS dev node and fill up our "rtas" structure with infos * about it. @@ -1129,6 +1276,12 @@ void __init rtas_initialize(void) #ifdef CONFIG_RTAS_ERROR_LOGGING rtas_last_error_token = rtas_token("rtas-last-error"); #endif + +#ifdef CONFIG_PPC_RTAS_FILTER + for (i = 0; i < ARRAY_SIZE(rtas_filters); i++) { + rtas_filters[i].token = rtas_token(rtas_filters[i].name); + } +#endif } int __init early_init_dt_scan_rtas(unsigned long node, From dc9af82ea0614bb138705d1f5230d53b3b1dfb83 Mon Sep 17 00:00:00 2001 From: Andrew Donnellan Date: Thu, 20 Aug 2020 14:45:14 +1000 Subject: [PATCH 348/645] selftests/powerpc: Add a rtas_filter selftest Add a selftest to test the basic functionality of CONFIG_RTAS_FILTER. Signed-off-by: Andrew Donnellan [mpe: Change rmo_start/end to 32-bit to avoid build errors on ppc64] Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200820044512.7543-2-ajd@linux.ibm.com --- .../selftests/powerpc/syscalls/Makefile | 2 +- .../selftests/powerpc/syscalls/rtas_filter.c | 285 ++++++++++++++++++ 2 files changed, 286 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/powerpc/syscalls/rtas_filter.c diff --git a/tools/testing/selftests/powerpc/syscalls/Makefile b/tools/testing/selftests/powerpc/syscalls/Makefile index 01b22775ca87..b63f8459c704 100644 --- a/tools/testing/selftests/powerpc/syscalls/Makefile +++ b/tools/testing/selftests/powerpc/syscalls/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only -TEST_GEN_PROGS := ipc_unmuxed +TEST_GEN_PROGS := ipc_unmuxed rtas_filter CFLAGS += -I../../../../../usr/include diff --git a/tools/testing/selftests/powerpc/syscalls/rtas_filter.c b/tools/testing/selftests/powerpc/syscalls/rtas_filter.c new file mode 100644 index 000000000000..03b487f18d00 --- /dev/null +++ b/tools/testing/selftests/powerpc/syscalls/rtas_filter.c @@ -0,0 +1,285 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright 2005-2020 IBM Corporation. + * + * Includes code from librtas (https://github.com/ibm-power-utilities/librtas/) + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "utils.h" + +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ +#define cpu_to_be32(x) bswap_32(x) +#define be32_to_cpu(x) bswap_32(x) +#else +#define cpu_to_be32(x) (x) +#define be32_to_cpu(x) (x) +#endif + +#define RTAS_IO_ASSERT -1098 /* Unexpected I/O Error */ +#define RTAS_UNKNOWN_OP -1099 /* No Firmware Implementation of Function */ +#define BLOCK_SIZE 4096 +#define PAGE_SIZE 4096 +#define MAX_PAGES 64 + +static const char *ofdt_rtas_path = "/proc/device-tree/rtas"; + +typedef __be32 uint32_t; +struct rtas_args { + __be32 token; + __be32 nargs; + __be32 nret; + __be32 args[16]; + __be32 *rets; /* Pointer to return values in args[]. */ +}; + +struct region { + uint64_t addr; + uint32_t size; + struct region *next; +}; + +int read_entire_file(int fd, char **buf, size_t *len) +{ + size_t buf_size = 0; + size_t off = 0; + int rc; + + *buf = NULL; + do { + buf_size += BLOCK_SIZE; + if (*buf == NULL) + *buf = malloc(buf_size); + else + *buf = realloc(*buf, buf_size); + + if (*buf == NULL) + return -ENOMEM; + + rc = read(fd, *buf + off, BLOCK_SIZE); + if (rc < 0) + return -EIO; + + off += rc; + } while (rc == BLOCK_SIZE); + + if (len) + *len = off; + + return 0; +} + +static int open_prop_file(const char *prop_path, const char *prop_name, int *fd) +{ + char *path; + int len; + + /* allocate enough for two string, a slash and trailing NULL */ + len = strlen(prop_path) + strlen(prop_name) + 1 + 1; + path = malloc(len); + if (path == NULL) + return -ENOMEM; + + snprintf(path, len, "%s/%s", prop_path, prop_name); + + *fd = open(path, O_RDONLY); + free(path); + if (*fd < 0) + return -errno; + + return 0; +} + +static int get_property(const char *prop_path, const char *prop_name, + char **prop_val, size_t *prop_len) +{ + int rc, fd; + + rc = open_prop_file(prop_path, prop_name, &fd); + if (rc) + return rc; + + rc = read_entire_file(fd, prop_val, prop_len); + close(fd); + + return rc; +} + +int rtas_token(const char *call_name) +{ + char *prop_buf = NULL; + size_t len; + int rc; + + rc = get_property(ofdt_rtas_path, call_name, &prop_buf, &len); + if (rc < 0) { + rc = RTAS_UNKNOWN_OP; + goto err; + } + + rc = be32_to_cpu(*(int *)prop_buf); + +err: + free(prop_buf); + return rc; +} + +static int read_kregion_bounds(struct region *kregion) +{ + char *buf; + int fd; + int rc; + + fd = open("/proc/ppc64/rtas/rmo_buffer", O_RDONLY); + if (fd < 0) { + printf("Could not open rmo_buffer file\n"); + return RTAS_IO_ASSERT; + } + + rc = read_entire_file(fd, &buf, NULL); + close(fd); + if (rc) { + free(buf); + return rc; + } + + sscanf(buf, "%" SCNx64 " %x", &kregion->addr, &kregion->size); + free(buf); + + if (!(kregion->size && kregion->addr) || + (kregion->size > (PAGE_SIZE * MAX_PAGES))) { + printf("Unexpected kregion bounds\n"); + return RTAS_IO_ASSERT; + } + + return 0; +} + +static int rtas_call(const char *name, int nargs, + int nrets, ...) +{ + struct rtas_args args; + __be32 *rets[16]; + int i, rc, token; + va_list ap; + + va_start(ap, nrets); + + token = rtas_token(name); + if (token == RTAS_UNKNOWN_OP) { + // We don't care if the call doesn't exist + printf("call '%s' not available, skipping...", name); + rc = RTAS_UNKNOWN_OP; + goto err; + } + + args.token = cpu_to_be32(token); + args.nargs = cpu_to_be32(nargs); + args.nret = cpu_to_be32(nrets); + + for (i = 0; i < nargs; i++) + args.args[i] = (__be32) va_arg(ap, unsigned long); + + for (i = 0; i < nrets; i++) + rets[i] = (__be32 *) va_arg(ap, unsigned long); + + rc = syscall(__NR_rtas, &args); + if (rc) { + rc = -errno; + goto err; + } + + if (nrets) { + *(rets[0]) = be32_to_cpu(args.args[nargs]); + + for (i = 1; i < nrets; i++) { + *(rets[i]) = args.args[nargs + i]; + } + } + +err: + va_end(ap); + return rc; +} + +static int test(void) +{ + struct region rmo_region; + uint32_t rmo_start; + uint32_t rmo_end; + __be32 rets[1]; + int rc; + + // Test a legitimate harmless call + // Expected: call succeeds + printf("Test a permitted call, no parameters... "); + rc = rtas_call("get-time-of-day", 0, 1, rets); + printf("rc: %d\n", rc); + FAIL_IF(rc != 0 && rc != RTAS_UNKNOWN_OP); + + // Test a prohibited call + // Expected: call returns -EINVAL + printf("Test a prohibited call... "); + rc = rtas_call("nvram-fetch", 0, 1, rets); + printf("rc: %d\n", rc); + FAIL_IF(rc != -EINVAL && rc != RTAS_UNKNOWN_OP); + + // Get RMO + rc = read_kregion_bounds(&rmo_region); + if (rc) { + printf("Couldn't read RMO region bounds, skipping remaining cases\n"); + return 0; + } + rmo_start = rmo_region.addr; + rmo_end = rmo_start + rmo_region.size - 1; + printf("RMO range: %08x - %08x\n", rmo_start, rmo_end); + + // Test a permitted call, user-supplied size, buffer inside RMO + // Expected: call succeeds + printf("Test a permitted call, user-supplied size, buffer inside RMO... "); + rc = rtas_call("ibm,get-system-parameter", 3, 1, 0, cpu_to_be32(rmo_start), + cpu_to_be32(rmo_end - rmo_start + 1), rets); + printf("rc: %d\n", rc); + FAIL_IF(rc != 0 && rc != RTAS_UNKNOWN_OP); + + // Test a permitted call, user-supplied size, buffer start outside RMO + // Expected: call returns -EINVAL + printf("Test a permitted call, user-supplied size, buffer start outside RMO... "); + rc = rtas_call("ibm,get-system-parameter", 3, 1, 0, cpu_to_be32(rmo_end + 1), + cpu_to_be32(4000), rets); + printf("rc: %d\n", rc); + FAIL_IF(rc != -EINVAL && rc != RTAS_UNKNOWN_OP); + + // Test a permitted call, user-supplied size, buffer end outside RMO + // Expected: call returns -EINVAL + printf("Test a permitted call, user-supplied size, buffer end outside RMO... "); + rc = rtas_call("ibm,get-system-parameter", 3, 1, 0, cpu_to_be32(rmo_start), + cpu_to_be32(rmo_end - rmo_start + 2), rets); + printf("rc: %d\n", rc); + FAIL_IF(rc != -EINVAL && rc != RTAS_UNKNOWN_OP); + + // Test a permitted call, fixed size, buffer end outside RMO + // Expected: call returns -EINVAL + printf("Test a permitted call, fixed size, buffer end outside RMO... "); + rc = rtas_call("ibm,configure-connector", 2, 1, cpu_to_be32(rmo_end - 4000), 0, rets); + printf("rc: %d\n", rc); + FAIL_IF(rc != -EINVAL && rc != RTAS_UNKNOWN_OP); + + return 0; +} + +int main(int argc, char *argv[]) +{ + return test_harness(test, "rtas_filter"); +} From 72cdd117c449896c707fc6cfe5b90978160697d0 Mon Sep 17 00:00:00 2001 From: Scott Cheloha Date: Wed, 16 Sep 2020 09:51:22 -0500 Subject: [PATCH 349/645] pseries/hotplug-memory: hot-add: skip redundant LMB lookup During memory hot-add, dlpar_add_lmb() calls memory_add_physaddr_to_nid() to determine which node id (nid) to use when later calling __add_memory(). This is wasteful. On pseries, memory_add_physaddr_to_nid() finds an appropriate nid for a given address by looking up the LMB containing the address and then passing that LMB to of_drconf_to_nid_single() to get the nid. In dlpar_add_lmb() we get this address from the LMB itself. In short, we have a pointer to an LMB and then we are searching for that LMB *again* in order to find its nid. If we call of_drconf_to_nid_single() directly from dlpar_add_lmb() we can skip the redundant lookup. The only error handling we need to duplicate from memory_add_physaddr_to_nid() is the fallback to the default nid when drconf_to_nid_single() returns -1 (NUMA_NO_NODE) or an invalid nid. Skipping the extra lookup makes hot-add operations faster, especially on machines with many LMBs. Consider an LPAR with 126976 LMBs. In one test, hot-adding 126000 LMBs on an upatched kernel took ~3.5 hours while a patched kernel completed the same operation in ~2 hours: Unpatched (12450 seconds): Sep 9 04:06:31 ltc-brazos1 drmgr[810169]: drmgr: -c mem -a -q 126000 Sep 9 04:06:31 ltc-brazos1 kernel: pseries-hotplug-mem: Attempting to hot-add 126000 LMB(s) [...] Sep 9 07:34:01 ltc-brazos1 kernel: pseries-hotplug-mem: Memory at 20000000 (drc index 80000002) was hot-added Patched (7065 seconds): Sep 8 21:49:57 ltc-brazos1 drmgr[877703]: drmgr: -c mem -a -q 126000 Sep 8 21:49:57 ltc-brazos1 kernel: pseries-hotplug-mem: Attempting to hot-add 126000 LMB(s) [...] Sep 8 23:27:42 ltc-brazos1 kernel: pseries-hotplug-mem: Memory at 20000000 (drc index 80000002) was hot-added It should be noted that the speedup grows more substantial when hot-adding LMBs at the end of the drconf range. This is because we are skipping a linear LMB search. To see the distinction, consider smaller hot-add test on the same LPAR. A perf-stat run with 10 iterations showed that hot-adding 4096 LMBs completed less than 1 second faster on a patched kernel: Unpatched: Performance counter stats for 'drmgr -c mem -a -q 4096' (10 runs): 104,753.42 msec task-clock # 0.992 CPUs utilized ( +- 0.55% ) 4,708 context-switches # 0.045 K/sec ( +- 0.69% ) 2,444 cpu-migrations # 0.023 K/sec ( +- 1.25% ) 394 page-faults # 0.004 K/sec ( +- 0.22% ) 445,902,503,057 cycles # 4.257 GHz ( +- 0.55% ) (66.67%) 8,558,376,740 stalled-cycles-frontend # 1.92% frontend cycles idle ( +- 0.88% ) (49.99%) 300,346,181,651 stalled-cycles-backend # 67.36% backend cycles idle ( +- 0.76% ) (50.01%) 258,091,488,691 instructions # 0.58 insn per cycle # 1.16 stalled cycles per insn ( +- 0.22% ) (66.67%) 70,568,169,256 branches # 673.660 M/sec ( +- 0.17% ) (50.01%) 3,100,725,426 branch-misses # 4.39% of all branches ( +- 0.20% ) (49.99%) 105.583 +- 0.589 seconds time elapsed ( +- 0.56% ) Patched: Performance counter stats for 'drmgr -c mem -a -q 4096' (10 runs): 104,055.69 msec task-clock # 0.993 CPUs utilized ( +- 0.32% ) 4,606 context-switches # 0.044 K/sec ( +- 0.20% ) 2,463 cpu-migrations # 0.024 K/sec ( +- 0.93% ) 394 page-faults # 0.004 K/sec ( +- 0.25% ) 442,951,129,921 cycles # 4.257 GHz ( +- 0.32% ) (66.66%) 8,710,413,329 stalled-cycles-frontend # 1.97% frontend cycles idle ( +- 0.47% ) (50.06%) 299,656,905,836 stalled-cycles-backend # 67.65% backend cycles idle ( +- 0.39% ) (50.02%) 252,731,168,193 instructions # 0.57 insn per cycle # 1.19 stalled cycles per insn ( +- 0.20% ) (66.66%) 68,902,851,121 branches # 662.173 M/sec ( +- 0.13% ) (49.94%) 3,100,242,882 branch-misses # 4.50% of all branches ( +- 0.15% ) (49.98%) 104.829 +- 0.325 seconds time elapsed ( +- 0.31% ) This is consistent. An add-by-count hot-add operation adds LMBs greedily, so LMBs near the start of the drconf range are considered first. On an otherwise idle LPAR with so many LMBs we would expect to find the LMBs we need near the start of the drconf range, hence the smaller speedup. Signed-off-by: Scott Cheloha Reviewed-by: Laurent Dufour Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200916145122.3408129-1-cheloha@linux.ibm.com --- arch/powerpc/include/asm/topology.h | 3 +++ arch/powerpc/mm/numa.c | 2 +- arch/powerpc/platforms/pseries/hotplug-memory.c | 6 ++++-- 3 files changed, 8 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index e45219f74be0..8728590f514a 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -86,6 +86,9 @@ static inline int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc) #endif /* CONFIG_NUMA */ +struct drmem_lmb; +int of_drconf_to_nid_single(struct drmem_lmb *lmb); + #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR) extern int find_and_online_cpu_nid(int cpu); extern int cpu_to_coregroup_id(int cpu); diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index b725fb66e913..8335399b7509 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -430,7 +430,7 @@ static int of_get_assoc_arrays(struct assoc_arrays *aa) * This is like of_node_to_nid_single() for memory represented in the * ibm,dynamic-reconfiguration-memory node. */ -static int of_drconf_to_nid_single(struct drmem_lmb *lmb) +int of_drconf_to_nid_single(struct drmem_lmb *lmb) { struct assoc_arrays aa = { .arrays = NULL }; int default_nid = NUMA_NO_NODE; diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 0ea976d1cac4..9a533acf8ad0 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -611,8 +611,10 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb) block_sz = memory_block_size_bytes(); - /* Find the node id for this address. */ - nid = memory_add_physaddr_to_nid(lmb->base_addr); + /* Find the node id for this LMB. Fake one if necessary. */ + nid = of_drconf_to_nid_single(lmb); + if (nid < 0 || !node_possible(nid)) + nid = first_online_node; /* Add the memory */ rc = __add_memory(nid, lmb->base_addr, block_sz); From 269e583357df32d77368903214f10f43fa5d7a5f Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Wed, 7 Oct 2020 15:09:02 +1100 Subject: [PATCH 350/645] powerpc/eeh: Delete eeh_pe->config_addr The eeh_pe->config_addr field was supposed to be removed in commit 35d64734b643 ("powerpc/eeh: Clean up PE addressing") which made it largely unused. Finish the job. Signed-off-by: Oliver O'Halloran Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20201007040903.819081-1-oohall@gmail.com --- arch/powerpc/include/asm/eeh.h | 1 - arch/powerpc/kernel/eeh.c | 2 +- arch/powerpc/kernel/eeh_pe.c | 4 ++-- 3 files changed, 3 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index dd6a4ac6c713..b1a5bba2e0b9 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -73,7 +73,6 @@ struct pci_dn; struct eeh_pe { int type; /* PE type: PHB/Bus/Device */ int state; /* PE EEH dependent mode */ - int config_addr; /* Traditional PCI address */ int addr; /* PE configuration address */ struct pci_controller *phb; /* Associated PHB */ struct pci_bus *bus; /* Top PCI bus for bus PE */ diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 87de8b798b2d..0e160dffcb86 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -466,7 +466,7 @@ int eeh_dev_check_failure(struct eeh_dev *edev) return 0; } - if (!pe->addr && !pe->config_addr) { + if (!pe->addr) { eeh_stats.no_cfg_addr++; return 0; } diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index 61b7d4019051..845e024321d4 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -354,8 +354,8 @@ int eeh_pe_tree_insert(struct eeh_dev *edev, struct eeh_pe *new_pe_parent) pr_err("%s: out of memory!\n", __func__); return -ENOMEM; } - pe->addr = edev->pe_config_addr; - pe->config_addr = edev->bdfn; + + pe->addr = edev->pe_config_addr; /* * Put the new EEH PE into hierarchy tree. If the parent From 8175bd580e629dcf9cc507794da774a6b8d3a9bd Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Wed, 7 Oct 2020 15:09:03 +1100 Subject: [PATCH 351/645] powerpc/pseries/eeh: Fix use of uninitialised variable If the RTAS call to query the PE address for a device fails we jump the err: label where an error message is printed along with the return code. However, the printed return code is from the "ret" variable which isn't set at that point since we assigned the result to "addr" instead. Fix this by consistently using the "ret" variable for the result of the RTAS call helpers an dropping the "addr" local variable" Fixes: 98ba956f6a38 ("powerpc/pseries/eeh: Rework device EEH PE determination") Signed-off-by: Oliver O'Halloran Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20201007040903.819081-2-oohall@gmail.com --- arch/powerpc/platforms/pseries/eeh_pseries.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index d8fd5f7b2143..cf024fa37bda 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -363,7 +363,6 @@ void pseries_eeh_init_edev(struct pci_dn *pdn) { struct eeh_pe pe, *parent; struct eeh_dev *edev; - int addr; u32 pcie_flags; int ret; @@ -422,8 +421,8 @@ void pseries_eeh_init_edev(struct pci_dn *pdn) } /* first up, find the pe_config_addr for the PE containing the device */ - addr = pseries_eeh_get_pe_config_addr(pdn); - if (addr < 0) { + ret = pseries_eeh_get_pe_config_addr(pdn); + if (ret < 0) { eeh_edev_dbg(edev, "Unable to find pe_config_addr\n"); goto err; } @@ -431,7 +430,7 @@ void pseries_eeh_init_edev(struct pci_dn *pdn) /* Try enable EEH on the fake PE */ memset(&pe, 0, sizeof(struct eeh_pe)); pe.phb = pdn->phb; - pe.addr = addr; + pe.addr = ret; eeh_edev_dbg(edev, "Enabling EEH on device\n"); ret = eeh_ops->set_option(&pe, EEH_OPT_ENABLE); @@ -440,7 +439,7 @@ void pseries_eeh_init_edev(struct pci_dn *pdn) goto err; } - edev->pe_config_addr = addr; + edev->pe_config_addr = pe.addr; eeh_add_flag(EEH_ENABLED); From 0f9866f7e85765bbda86666df56c92f377c3bc10 Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Sat, 3 Oct 2020 13:19:39 +0530 Subject: [PATCH 352/645] powerpc/perf/hv-gpci: Fix starting index value Commit 9e9f60108423f ("powerpc/perf/{hv-gpci, hv-common}: generate requests with counters annotated") adds a framework for defining gpci counters. In this patch, they adds starting_index value as '0xffffffffffffffff'. which is wrong as starting_index is of size 32 bits. Because of this, incase we try to run hv-gpci event we get error. In power9 machine: command#: perf stat -e hv_gpci/system_tlbie_count_and_time_tlbie_instructions_issued/ -C 0 -I 1000 event syntax error: '..bie_count_and_time_tlbie_instructions_issued/' \___ value too big for format, maximum is 4294967295 This patch fix this issue and changes starting_index value to '0xffffffff' After this patch: command#: perf stat -e hv_gpci/system_tlbie_count_and_time_tlbie_instructions_issued/ -C 0 -I 1000 1.000085786 1,024 hv_gpci/system_tlbie_count_and_time_tlbie_instructions_issued/ 2.000287818 1,024 hv_gpci/system_tlbie_count_and_time_tlbie_instructions_issued/ 2.439113909 17,408 hv_gpci/system_tlbie_count_and_time_tlbie_instructions_issued/ Fixes: 9e9f60108423 ("powerpc/perf/{hv-gpci, hv-common}: generate requests with counters annotated") Signed-off-by: Kajol Jain Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20201003074943.338618-1-kjain@linux.ibm.com --- arch/powerpc/perf/hv-gpci-requests.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/perf/hv-gpci-requests.h b/arch/powerpc/perf/hv-gpci-requests.h index e608f9db12dd..8965b4463d43 100644 --- a/arch/powerpc/perf/hv-gpci-requests.h +++ b/arch/powerpc/perf/hv-gpci-requests.h @@ -95,7 +95,7 @@ REQUEST(__field(0, 8, partition_id) #define REQUEST_NAME system_performance_capabilities #define REQUEST_NUM 0x40 -#define REQUEST_IDX_KIND "starting_index=0xffffffffffffffff" +#define REQUEST_IDX_KIND "starting_index=0xffffffff" #include I(REQUEST_BEGIN) REQUEST(__field(0, 1, perf_collect_privileged) __field(0x1, 1, capability_mask) @@ -223,7 +223,7 @@ REQUEST(__field(0, 2, partition_id) #define REQUEST_NAME system_hypervisor_times #define REQUEST_NUM 0xF0 -#define REQUEST_IDX_KIND "starting_index=0xffffffffffffffff" +#define REQUEST_IDX_KIND "starting_index=0xffffffff" #include I(REQUEST_BEGIN) REQUEST(__count(0, 8, time_spent_to_dispatch_virtual_processors) __count(0x8, 8, time_spent_processing_virtual_processor_timers) @@ -234,7 +234,7 @@ REQUEST(__count(0, 8, time_spent_to_dispatch_virtual_processors) #define REQUEST_NAME system_tlbie_count_and_time #define REQUEST_NUM 0xF4 -#define REQUEST_IDX_KIND "starting_index=0xffffffffffffffff" +#define REQUEST_IDX_KIND "starting_index=0xffffffff" #include I(REQUEST_BEGIN) REQUEST(__count(0, 8, tlbie_instructions_issued) /* From 264a034099b6e3c76fae85e75329373f3652a033 Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Sat, 3 Oct 2020 13:19:40 +0530 Subject: [PATCH 353/645] Documentation/ABI: Add ABI documentation for hv-24x7 format This patch adds ABI documentation for hv-24x7 format. Signed-off-by: Kajol Jain Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20201003074943.338618-2-kjain@linux.ibm.com --- .../sysfs-bus-event_source-devices-hv_24x7 | 25 +++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7 b/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7 index e82fc37be802..2273627df190 100644 --- a/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7 +++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7 @@ -1,3 +1,28 @@ +What: /sys/bus/event_source/devices/hv_24x7/format +Date: September 2020 +Contact: Linux on PowerPC Developer List +Description: Read-only. Attribute group to describe the magic bits + that go into perf_event_attr.config for a particular pmu. + (See ABI/testing/sysfs-bus-event_source-devices-format). + + Each attribute under this group defines a bit range of the + perf_event_attr.config. All supported attributes are listed + below. + + chip = "config:16-31" + core = "config:16-31" + domain = "config:0-3" + lpar = "config:0-15" + offset = "config:32-63" + vcpu = "config:16-31" + + For example, + + PM_PB_CYC = "domain=1,offset=0x80,chip=?,lpar=0x0" + + In this event, '?' after chip specifies that + this value will be provided by user while running this event. + What: /sys/bus/event_source/devices/hv_24x7/interface/catalog Date: February 2014 Contact: Linux on PowerPC Developer List From 435387dd1f6fc03c64e3fdb4cc8737904c08a4db Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Sat, 3 Oct 2020 13:19:41 +0530 Subject: [PATCH 354/645] Documentation/ABI: Add ABI documentation for hv-gpci format This patch adds ABI documentation for hv-gpci event format. Signed-off-by: Kajol Jain Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20201003074943.338618-3-kjain@linux.ibm.com --- .../sysfs-bus-event_source-devices-hv_gpci | 31 +++++++++++++++++++ 1 file changed, 31 insertions(+) diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_gpci b/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_gpci index 3ca4e554d2f9..ed989869d116 100644 --- a/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_gpci +++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_gpci @@ -1,3 +1,34 @@ +What: /sys/bus/event_source/devices/hv_gpci/format +Date: September 2020 +Contact: Linux on PowerPC Developer List +Description: Read-only. Attribute group to describe the magic bits + that go into perf_event_attr.config for a particular pmu. + (See ABI/testing/sysfs-bus-event_source-devices-format). + + Each attribute under this group defines a bit range of the + perf_event_attr.config. All supported attributes are listed + below. + + counter_info_version = "config:16-23" + length = "config:24-31" + partition_id = "config:32-63" + request = "config:0-31" + sibling_part_id = "config:32-63" + hw_chip_id = "config:32-63" + offset = "config:32-63" + phys_processor_idx = "config:32-63" + secondary_index = "config:0-15" + starting_index = "config:32-63" + + For example, + + processor_core_utilization_instructions_completed = "request=0x94, + phys_processor_idx=?,counter_info_version=0x8, + length=8,offset=0x18" + + In this event, '?' after phys_processor_idx specifies this value + this value will be provided by user while running this event. + What: /sys/bus/event_source/devices/hv_gpci/interface/collect_privileged Date: February 2014 Contact: Linux on PowerPC Developer List From dcb5cdf60a1fbbdb3b4dd2abc562206481f09ef1 Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Sat, 3 Oct 2020 13:19:42 +0530 Subject: [PATCH 355/645] powerpc/perf/hv-gpci: Add cpu hotplug support Patch here adds cpu hotplug functions to hv_gpci pmu. A new cpuhp_state "CPUHP_AP_PERF_POWERPC_HV_GPCI_ONLINE" enum is added. The online callback function updates the cpumask only if its empty. As the primary intention of adding hotplug support is to designate a CPU to make HCALL to collect the counter data. The offline function test and clear corresponding cpu in a cpumask and update cpumask to any other active cpu. Signed-off-by: Kajol Jain Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20201003074943.338618-4-kjain@linux.ibm.com --- arch/powerpc/perf/hv-gpci.c | 46 +++++++++++++++++++++++++++++++++++++ include/linux/cpuhotplug.h | 1 + 2 files changed, 47 insertions(+) diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c index 1667315b82e9..1bca0c1a6cfe 100644 --- a/arch/powerpc/perf/hv-gpci.c +++ b/arch/powerpc/perf/hv-gpci.c @@ -48,6 +48,8 @@ EVENT_DEFINE_RANGE_FORMAT(length, config1, 24, 31); /* u32, byte offset */ EVENT_DEFINE_RANGE_FORMAT(offset, config1, 32, 63); +static cpumask_t hv_gpci_cpumask; + static struct attribute *format_attrs[] = { &format_attr_request.attr, &format_attr_starting_index.attr, @@ -266,6 +268,45 @@ static struct pmu h_gpci_pmu = { .capabilities = PERF_PMU_CAP_NO_EXCLUDE, }; +static int ppc_hv_gpci_cpu_online(unsigned int cpu) +{ + if (cpumask_empty(&hv_gpci_cpumask)) + cpumask_set_cpu(cpu, &hv_gpci_cpumask); + + return 0; +} + +static int ppc_hv_gpci_cpu_offline(unsigned int cpu) +{ + int target; + + /* Check if exiting cpu is used for collecting gpci events */ + if (!cpumask_test_and_clear_cpu(cpu, &hv_gpci_cpumask)) + return 0; + + /* Find a new cpu to collect gpci events */ + target = cpumask_last(cpu_active_mask); + + if (target < 0 || target >= nr_cpu_ids) { + pr_err("hv_gpci: CPU hotplug init failed\n"); + return -1; + } + + /* Migrate gpci events to the new target */ + cpumask_set_cpu(target, &hv_gpci_cpumask); + perf_pmu_migrate_context(&h_gpci_pmu, cpu, target); + + return 0; +} + +static int hv_gpci_cpu_hotplug_init(void) +{ + return cpuhp_setup_state(CPUHP_AP_PERF_POWERPC_HV_GPCI_ONLINE, + "perf/powerpc/hv_gcpi:online", + ppc_hv_gpci_cpu_online, + ppc_hv_gpci_cpu_offline); +} + static int hv_gpci_init(void) { int r; @@ -286,6 +327,11 @@ static int hv_gpci_init(void) return -ENODEV; } + /* init cpuhotplug */ + r = hv_gpci_cpu_hotplug_init(); + if (r) + return r; + /* sampling not supported */ h_gpci_pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT; diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 3215023d4852..5d08ed922510 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -183,6 +183,7 @@ enum cpuhp_state { CPUHP_AP_PERF_POWERPC_THREAD_IMC_ONLINE, CPUHP_AP_PERF_POWERPC_TRACE_IMC_ONLINE, CPUHP_AP_PERF_POWERPC_HV_24x7_ONLINE, + CPUHP_AP_PERF_POWERPC_HV_GPCI_ONLINE, CPUHP_AP_WATCHDOG_ONLINE, CPUHP_AP_WORKQUEUE_ONLINE, CPUHP_AP_RCUTREE_ONLINE, From 09b791d95559ef82542063333ecaa2ac9d57118e Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Sat, 3 Oct 2020 13:19:43 +0530 Subject: [PATCH 356/645] powerpc/hv-gpci: Add sysfs files inside hv-gpci device to show cpumask Patch here adds a cpumask attr to hv_gpci pmu along with ABI documentation. Primary use to expose the cpumask is for the perf tool which has the capability to parse the driver sysfs folder and understand the cpumask file. Having cpumask file will reduce the number of perf command line parameters (will avoid "-C" option in the perf tool command line). It can also notify the user which is the current cpu used to retrieve the counter data. command:# cat /sys/devices/hv_gpci/cpumask 0 Signed-off-by: Kajol Jain Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20201003074943.338618-5-kjain@linux.ibm.com --- .../sysfs-bus-event_source-devices-hv_gpci | 7 +++++++ arch/powerpc/perf/hv-gpci.c | 18 ++++++++++++++++++ 2 files changed, 25 insertions(+) diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_gpci b/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_gpci index ed989869d116..6a023b42486c 100644 --- a/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_gpci +++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_gpci @@ -72,3 +72,10 @@ Contact: Linux on PowerPC Developer List Description: A number indicating the latest version of the gpci interface that the kernel is aware of. + +What: /sys/devices/hv_gpci/cpumask +Date: October 2020 +Contact: Linux on PowerPC Developer List +Description: read only + This sysfs file exposes the cpumask which is designated to make + HCALLs to retrieve hv-gpci pmu event counter data. diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c index 1bca0c1a6cfe..d48413e28c39 100644 --- a/arch/powerpc/perf/hv-gpci.c +++ b/arch/powerpc/perf/hv-gpci.c @@ -96,7 +96,15 @@ static ssize_t kernel_version_show(struct device *dev, return sprintf(page, "0x%x\n", COUNTER_INFO_VERSION_CURRENT); } +static ssize_t cpumask_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return cpumap_print_to_pagebuf(true, buf, &hv_gpci_cpumask); +} + static DEVICE_ATTR_RO(kernel_version); +static DEVICE_ATTR_RO(cpumask); + HV_CAPS_ATTR(version, "0x%x\n"); HV_CAPS_ATTR(ga, "%d\n"); HV_CAPS_ATTR(expanded, "%d\n"); @@ -113,6 +121,15 @@ static struct attribute *interface_attrs[] = { NULL, }; +static struct attribute *cpumask_attrs[] = { + &dev_attr_cpumask.attr, + NULL, +}; + +static struct attribute_group cpumask_attr_group = { + .attrs = cpumask_attrs, +}; + static struct attribute_group interface_group = { .name = "interface", .attrs = interface_attrs, @@ -122,6 +139,7 @@ static const struct attribute_group *attr_groups[] = { &format_group, &event_group, &interface_group, + &cpumask_attr_group, NULL, }; From 91ffc519c1997520ff3435ee227d86cfaa30d037 Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Thu, 2 Jul 2020 11:10:11 +0200 Subject: [PATCH 357/645] s390/zcrypt: introduce msg tracking in zcrypt functions Introduce a new internal struct zcrypt_track with an retry counter field and a last return code field. Fill and update these fields at certain points during processing of an request/reply. This tracking info is then used to - avoid trying to resend the message forever. Now each message is tried to be send TRACK_AGAIN_MAX (currently 10) times and then the ioctl returns to userspace with errno EAGAIN. - avoid trying to resend the message on the very same card/domain. If possible (more than one APQN with same quality) don't use the very same qid as the previous attempt when again scheduling the request. This is done by adding penalty weight values when the dispatching takes place. There is a penalty TRACK_AGAIN_CARD_WEIGHT_PENALTY for using the same card as previously and another penalty define TRACK_AGAIN_QUEUE_WEIGHT_PENALTY to be considered when the same qid as the previous sent attempt is calculated. Both values make it harder to choose the very same card/domain but not impossible. For example when only one APQN is available a resend can only address the very same APQN. There are some more ideas for the future to extend the use of this tracking information. For example the last response code at NQAP and DQAP could be stored there, giving the possibility to extended tracing and debugging about requests failing to get processed properly. Signed-off-by: Harald Freudenberger Signed-off-by: Vasily Gorbik --- drivers/s390/crypto/zcrypt_api.c | 253 ++++++++++++++++++++--------- drivers/s390/crypto/zcrypt_api.h | 14 +- drivers/s390/crypto/zcrypt_cex2a.c | 6 +- drivers/s390/crypto/zcrypt_cex2c.c | 6 +- drivers/s390/crypto/zcrypt_cex4.c | 58 +++---- 5 files changed, 213 insertions(+), 124 deletions(-) diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c index a711728c3857..223e1c233278 100644 --- a/drivers/s390/crypto/zcrypt_api.c +++ b/drivers/s390/crypto/zcrypt_api.c @@ -602,13 +602,13 @@ static inline bool zcrypt_card_compare(struct zcrypt_card *zc, unsigned int pref_weight) { if (!pref_zc) - return false; + return true; weight += atomic_read(&zc->load); pref_weight += atomic_read(&pref_zc->load); if (weight == pref_weight) - return atomic64_read(&zc->card->total_request_count) > + return atomic64_read(&zc->card->total_request_count) < atomic64_read(&pref_zc->card->total_request_count); - return weight > pref_weight; + return weight < pref_weight; } static inline bool zcrypt_queue_compare(struct zcrypt_queue *zq, @@ -617,26 +617,27 @@ static inline bool zcrypt_queue_compare(struct zcrypt_queue *zq, unsigned int pref_weight) { if (!pref_zq) - return false; + return true; weight += atomic_read(&zq->load); pref_weight += atomic_read(&pref_zq->load); if (weight == pref_weight) - return zq->queue->total_request_count > + return zq->queue->total_request_count < pref_zq->queue->total_request_count; - return weight > pref_weight; + return weight < pref_weight; } /* * zcrypt ioctls. */ static long zcrypt_rsa_modexpo(struct ap_perms *perms, + struct zcrypt_track *tr, struct ica_rsa_modexpo *mex) { struct zcrypt_card *zc, *pref_zc; struct zcrypt_queue *zq, *pref_zq; - unsigned int weight = 0, pref_weight = 0; + unsigned int wgt = 0, pref_wgt = 0; unsigned int func_code; - int qid = 0, rc = -ENODEV; + int cpen, qpen, qid = 0, rc = -ENODEV; struct module *mod; trace_s390_zcrypt_req(mex, TP_ICARSAMODEXPO); @@ -673,8 +674,12 @@ static long zcrypt_rsa_modexpo(struct ap_perms *perms, if (!zcrypt_check_card(perms, zc->card->id)) continue; /* get weight index of the card device */ - weight = zc->speed_rating[func_code]; - if (zcrypt_card_compare(zc, pref_zc, weight, pref_weight)) + wgt = zc->speed_rating[func_code]; + /* penalty if this msg was previously sent via this card */ + cpen = (tr && tr->again_counter && tr->last_qid && + AP_QID_CARD(tr->last_qid) == zc->card->id) ? + TRACK_AGAIN_CARD_WEIGHT_PENALTY : 0; + if (!zcrypt_card_compare(zc, pref_zc, wgt + cpen, pref_wgt)) continue; for_each_zcrypt_queue(zq, zc) { /* check if device is online and eligible */ @@ -684,15 +689,19 @@ static long zcrypt_rsa_modexpo(struct ap_perms *perms, if (!zcrypt_check_queue(perms, AP_QID_QUEUE(zq->queue->qid))) continue; - if (zcrypt_queue_compare(zq, pref_zq, - weight, pref_weight)) + /* penalty if the msg was previously sent at this qid */ + qpen = (tr && tr->again_counter && tr->last_qid && + tr->last_qid == zq->queue->qid) ? + TRACK_AGAIN_QUEUE_WEIGHT_PENALTY : 0; + if (!zcrypt_queue_compare(zq, pref_zq, + wgt + cpen + qpen, pref_wgt)) continue; pref_zc = zc; pref_zq = zq; - pref_weight = weight; + pref_wgt = wgt + cpen + qpen; } } - pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, &mod, weight); + pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, &mod, wgt); spin_unlock(&zcrypt_list_lock); if (!pref_zq) { @@ -704,23 +713,28 @@ static long zcrypt_rsa_modexpo(struct ap_perms *perms, rc = pref_zq->ops->rsa_modexpo(pref_zq, mex); spin_lock(&zcrypt_list_lock); - zcrypt_drop_queue(pref_zc, pref_zq, mod, weight); + zcrypt_drop_queue(pref_zc, pref_zq, mod, wgt); spin_unlock(&zcrypt_list_lock); out: + if (tr) { + tr->last_rc = rc; + tr->last_qid = qid; + } trace_s390_zcrypt_rep(mex, func_code, rc, AP_QID_CARD(qid), AP_QID_QUEUE(qid)); return rc; } static long zcrypt_rsa_crt(struct ap_perms *perms, + struct zcrypt_track *tr, struct ica_rsa_modexpo_crt *crt) { struct zcrypt_card *zc, *pref_zc; struct zcrypt_queue *zq, *pref_zq; - unsigned int weight = 0, pref_weight = 0; + unsigned int wgt = 0, pref_wgt = 0; unsigned int func_code; - int qid = 0, rc = -ENODEV; + int cpen, qpen, qid = 0, rc = -ENODEV; struct module *mod; trace_s390_zcrypt_req(crt, TP_ICARSACRT); @@ -757,8 +771,12 @@ static long zcrypt_rsa_crt(struct ap_perms *perms, if (!zcrypt_check_card(perms, zc->card->id)) continue; /* get weight index of the card device */ - weight = zc->speed_rating[func_code]; - if (zcrypt_card_compare(zc, pref_zc, weight, pref_weight)) + wgt = zc->speed_rating[func_code]; + /* penalty if this msg was previously sent via this card */ + cpen = (tr && tr->again_counter && tr->last_qid && + AP_QID_CARD(tr->last_qid) == zc->card->id) ? + TRACK_AGAIN_CARD_WEIGHT_PENALTY : 0; + if (!zcrypt_card_compare(zc, pref_zc, wgt + cpen, pref_wgt)) continue; for_each_zcrypt_queue(zq, zc) { /* check if device is online and eligible */ @@ -768,15 +786,19 @@ static long zcrypt_rsa_crt(struct ap_perms *perms, if (!zcrypt_check_queue(perms, AP_QID_QUEUE(zq->queue->qid))) continue; - if (zcrypt_queue_compare(zq, pref_zq, - weight, pref_weight)) + /* penalty if the msg was previously sent at this qid */ + qpen = (tr && tr->again_counter && tr->last_qid && + tr->last_qid == zq->queue->qid) ? + TRACK_AGAIN_QUEUE_WEIGHT_PENALTY : 0; + if (!zcrypt_queue_compare(zq, pref_zq, + wgt + cpen + qpen, pref_wgt)) continue; pref_zc = zc; pref_zq = zq; - pref_weight = weight; + pref_wgt = wgt + cpen + qpen; } } - pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, &mod, weight); + pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, &mod, wgt); spin_unlock(&zcrypt_list_lock); if (!pref_zq) { @@ -788,25 +810,30 @@ static long zcrypt_rsa_crt(struct ap_perms *perms, rc = pref_zq->ops->rsa_modexpo_crt(pref_zq, crt); spin_lock(&zcrypt_list_lock); - zcrypt_drop_queue(pref_zc, pref_zq, mod, weight); + zcrypt_drop_queue(pref_zc, pref_zq, mod, wgt); spin_unlock(&zcrypt_list_lock); out: + if (tr) { + tr->last_rc = rc; + tr->last_qid = qid; + } trace_s390_zcrypt_rep(crt, func_code, rc, AP_QID_CARD(qid), AP_QID_QUEUE(qid)); return rc; } static long _zcrypt_send_cprb(bool userspace, struct ap_perms *perms, + struct zcrypt_track *tr, struct ica_xcRB *xcRB) { struct zcrypt_card *zc, *pref_zc; struct zcrypt_queue *zq, *pref_zq; struct ap_message ap_msg; - unsigned int weight = 0, pref_weight = 0; + unsigned int wgt = 0, pref_wgt = 0; unsigned int func_code; unsigned short *domain, tdom; - int qid = 0, rc = -ENODEV; + int cpen, qpen, qid = 0, rc = -ENODEV; struct module *mod; trace_s390_zcrypt_req(xcRB, TB_ZSECSENDCPRB); @@ -843,8 +870,12 @@ static long _zcrypt_send_cprb(bool userspace, struct ap_perms *perms, if (!zcrypt_check_card(perms, zc->card->id)) continue; /* get weight index of the card device */ - weight = speed_idx_cca(func_code) * zc->speed_rating[SECKEY]; - if (zcrypt_card_compare(zc, pref_zc, weight, pref_weight)) + wgt = speed_idx_cca(func_code) * zc->speed_rating[SECKEY]; + /* penalty if this msg was previously sent via this card */ + cpen = (tr && tr->again_counter && tr->last_qid && + AP_QID_CARD(tr->last_qid) == zc->card->id) ? + TRACK_AGAIN_CARD_WEIGHT_PENALTY : 0; + if (!zcrypt_card_compare(zc, pref_zc, wgt + cpen, pref_wgt)) continue; for_each_zcrypt_queue(zq, zc) { /* check if device is online and eligible */ @@ -857,15 +888,19 @@ static long _zcrypt_send_cprb(bool userspace, struct ap_perms *perms, if (!zcrypt_check_queue(perms, AP_QID_QUEUE(zq->queue->qid))) continue; - if (zcrypt_queue_compare(zq, pref_zq, - weight, pref_weight)) + /* penalty if the msg was previously sent at this qid */ + qpen = (tr && tr->again_counter && tr->last_qid && + tr->last_qid == zq->queue->qid) ? + TRACK_AGAIN_QUEUE_WEIGHT_PENALTY : 0; + if (!zcrypt_queue_compare(zq, pref_zq, + wgt + cpen + qpen, pref_wgt)) continue; pref_zc = zc; pref_zq = zq; - pref_weight = weight; + pref_wgt = wgt + cpen + qpen; } } - pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, &mod, weight); + pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, &mod, wgt); spin_unlock(&zcrypt_list_lock); if (!pref_zq) { @@ -881,11 +916,15 @@ static long _zcrypt_send_cprb(bool userspace, struct ap_perms *perms, rc = pref_zq->ops->send_cprb(userspace, pref_zq, xcRB, &ap_msg); spin_lock(&zcrypt_list_lock); - zcrypt_drop_queue(pref_zc, pref_zq, mod, weight); + zcrypt_drop_queue(pref_zc, pref_zq, mod, wgt); spin_unlock(&zcrypt_list_lock); out: ap_release_message(&ap_msg); + if (tr) { + tr->last_rc = rc; + tr->last_qid = qid; + } trace_s390_zcrypt_rep(xcRB, func_code, rc, AP_QID_CARD(qid), AP_QID_QUEUE(qid)); return rc; @@ -893,7 +932,7 @@ out: long zcrypt_send_cprb(struct ica_xcRB *xcRB) { - return _zcrypt_send_cprb(false, &ap_perms, xcRB); + return _zcrypt_send_cprb(false, &ap_perms, NULL, xcRB); } EXPORT_SYMBOL(zcrypt_send_cprb); @@ -925,16 +964,17 @@ static bool is_desired_ep11_queue(unsigned int dev_qid, } static long _zcrypt_send_ep11_cprb(bool userspace, struct ap_perms *perms, + struct zcrypt_track *tr, struct ep11_urb *xcrb) { struct zcrypt_card *zc, *pref_zc; struct zcrypt_queue *zq, *pref_zq; struct ep11_target_dev *targets; unsigned short target_num; - unsigned int weight = 0, pref_weight = 0; + unsigned int wgt = 0, pref_wgt = 0; unsigned int func_code; struct ap_message ap_msg; - int qid = 0, rc = -ENODEV; + int cpen, qpen, qid = 0, rc = -ENODEV; struct module *mod; trace_s390_zcrypt_req(xcrb, TP_ZSENDEP11CPRB); @@ -983,8 +1023,12 @@ static long _zcrypt_send_ep11_cprb(bool userspace, struct ap_perms *perms, if (!zcrypt_check_card(perms, zc->card->id)) continue; /* get weight index of the card device */ - weight = speed_idx_ep11(func_code) * zc->speed_rating[SECKEY]; - if (zcrypt_card_compare(zc, pref_zc, weight, pref_weight)) + wgt = speed_idx_ep11(func_code) * zc->speed_rating[SECKEY]; + /* penalty if this msg was previously sent via this card */ + cpen = (tr && tr->again_counter && tr->last_qid && + AP_QID_CARD(tr->last_qid) == zc->card->id) ? + TRACK_AGAIN_CARD_WEIGHT_PENALTY : 0; + if (!zcrypt_card_compare(zc, pref_zc, wgt + cpen, pref_wgt)) continue; for_each_zcrypt_queue(zq, zc) { /* check if device is online and eligible */ @@ -998,15 +1042,19 @@ static long _zcrypt_send_ep11_cprb(bool userspace, struct ap_perms *perms, if (!zcrypt_check_queue(perms, AP_QID_QUEUE(zq->queue->qid))) continue; - if (zcrypt_queue_compare(zq, pref_zq, - weight, pref_weight)) + /* penalty if the msg was previously sent at this qid */ + qpen = (tr && tr->again_counter && tr->last_qid && + tr->last_qid == zq->queue->qid) ? + TRACK_AGAIN_QUEUE_WEIGHT_PENALTY : 0; + if (!zcrypt_queue_compare(zq, pref_zq, + wgt + cpen + qpen, pref_wgt)) continue; pref_zc = zc; pref_zq = zq; - pref_weight = weight; + pref_wgt = wgt + cpen + qpen; } } - pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, &mod, weight); + pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, &mod, wgt); spin_unlock(&zcrypt_list_lock); if (!pref_zq) { @@ -1018,13 +1066,17 @@ static long _zcrypt_send_ep11_cprb(bool userspace, struct ap_perms *perms, rc = pref_zq->ops->send_ep11_cprb(userspace, pref_zq, xcrb, &ap_msg); spin_lock(&zcrypt_list_lock); - zcrypt_drop_queue(pref_zc, pref_zq, mod, weight); + zcrypt_drop_queue(pref_zc, pref_zq, mod, wgt); spin_unlock(&zcrypt_list_lock); out_free: kfree(targets); out: ap_release_message(&ap_msg); + if (tr) { + tr->last_rc = rc; + tr->last_qid = qid; + } trace_s390_zcrypt_rep(xcrb, func_code, rc, AP_QID_CARD(qid), AP_QID_QUEUE(qid)); return rc; @@ -1032,7 +1084,7 @@ out: long zcrypt_send_ep11_cprb(struct ep11_urb *xcrb) { - return _zcrypt_send_ep11_cprb(false, &ap_perms, xcrb); + return _zcrypt_send_ep11_cprb(false, &ap_perms, NULL, xcrb); } EXPORT_SYMBOL(zcrypt_send_ep11_cprb); @@ -1040,7 +1092,7 @@ static long zcrypt_rng(char *buffer) { struct zcrypt_card *zc, *pref_zc; struct zcrypt_queue *zq, *pref_zq; - unsigned int weight = 0, pref_weight = 0; + unsigned int wgt = 0, pref_wgt = 0; unsigned int func_code; struct ap_message ap_msg; unsigned int domain; @@ -1062,22 +1114,21 @@ static long zcrypt_rng(char *buffer) if (!zc->online || !(zc->card->functions & 0x10000000)) continue; /* get weight index of the card device */ - weight = zc->speed_rating[func_code]; - if (zcrypt_card_compare(zc, pref_zc, weight, pref_weight)) + wgt = zc->speed_rating[func_code]; + if (!zcrypt_card_compare(zc, pref_zc, wgt, pref_wgt)) continue; for_each_zcrypt_queue(zq, zc) { /* check if device is online and eligible */ if (!zq->online || !zq->ops->rng) continue; - if (zcrypt_queue_compare(zq, pref_zq, - weight, pref_weight)) + if (!zcrypt_queue_compare(zq, pref_zq, wgt, pref_wgt)) continue; pref_zc = zc; pref_zq = zq; - pref_weight = weight; + pref_wgt = wgt; } } - pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, &mod, weight); + pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, &mod, wgt); spin_unlock(&zcrypt_list_lock); if (!pref_zq) { @@ -1089,7 +1140,7 @@ static long zcrypt_rng(char *buffer) rc = pref_zq->ops->rng(pref_zq, buffer, &ap_msg); spin_lock(&zcrypt_list_lock); - zcrypt_drop_queue(pref_zc, pref_zq, mod, weight); + zcrypt_drop_queue(pref_zc, pref_zq, mod, wgt); spin_unlock(&zcrypt_list_lock); out: @@ -1301,19 +1352,25 @@ static int zcrypt_requestq_count(void) static int icarsamodexpo_ioctl(struct ap_perms *perms, unsigned long arg) { int rc; + struct zcrypt_track tr; struct ica_rsa_modexpo mex; struct ica_rsa_modexpo __user *umex = (void __user *) arg; + memset(&tr, 0, sizeof(tr)); if (copy_from_user(&mex, umex, sizeof(mex))) return -EFAULT; do { - rc = zcrypt_rsa_modexpo(perms, &mex); - } while (rc == -EAGAIN); + rc = zcrypt_rsa_modexpo(perms, &tr, &mex); + if (rc == -EAGAIN) + tr.again_counter++; + } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); /* on failure: retry once again after a requested rescan */ if ((rc == -ENODEV) && (zcrypt_process_rescan())) do { - rc = zcrypt_rsa_modexpo(perms, &mex); - } while (rc == -EAGAIN); + rc = zcrypt_rsa_modexpo(perms, &tr, &mex); + if (rc == -EAGAIN) + tr.again_counter++; + } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); if (rc) { ZCRYPT_DBF(DBF_DEBUG, "ioctl ICARSAMODEXPO rc=%d\n", rc); return rc; @@ -1324,19 +1381,25 @@ static int icarsamodexpo_ioctl(struct ap_perms *perms, unsigned long arg) static int icarsacrt_ioctl(struct ap_perms *perms, unsigned long arg) { int rc; + struct zcrypt_track tr; struct ica_rsa_modexpo_crt crt; struct ica_rsa_modexpo_crt __user *ucrt = (void __user *) arg; + memset(&tr, 0, sizeof(tr)); if (copy_from_user(&crt, ucrt, sizeof(crt))) return -EFAULT; do { - rc = zcrypt_rsa_crt(perms, &crt); - } while (rc == -EAGAIN); + rc = zcrypt_rsa_crt(perms, &tr, &crt); + if (rc == -EAGAIN) + tr.again_counter++; + } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); /* on failure: retry once again after a requested rescan */ if ((rc == -ENODEV) && (zcrypt_process_rescan())) do { - rc = zcrypt_rsa_crt(perms, &crt); - } while (rc == -EAGAIN); + rc = zcrypt_rsa_crt(perms, &tr, &crt); + if (rc == -EAGAIN) + tr.again_counter++; + } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); if (rc) { ZCRYPT_DBF(DBF_DEBUG, "ioctl ICARSACRT rc=%d\n", rc); return rc; @@ -1348,18 +1411,24 @@ static int zsecsendcprb_ioctl(struct ap_perms *perms, unsigned long arg) { int rc; struct ica_xcRB xcRB; + struct zcrypt_track tr; struct ica_xcRB __user *uxcRB = (void __user *) arg; + memset(&tr, 0, sizeof(tr)); if (copy_from_user(&xcRB, uxcRB, sizeof(xcRB))) return -EFAULT; do { - rc = _zcrypt_send_cprb(true, perms, &xcRB); - } while (rc == -EAGAIN); + rc = _zcrypt_send_cprb(true, perms, &tr, &xcRB); + if (rc == -EAGAIN) + tr.again_counter++; + } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); /* on failure: retry once again after a requested rescan */ if ((rc == -ENODEV) && (zcrypt_process_rescan())) do { - rc = _zcrypt_send_cprb(true, perms, &xcRB); - } while (rc == -EAGAIN); + rc = _zcrypt_send_cprb(true, perms, &tr, &xcRB); + if (rc == -EAGAIN) + tr.again_counter++; + } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); if (rc) ZCRYPT_DBF(DBF_DEBUG, "ioctl ZSENDCPRB rc=%d status=0x%x\n", rc, xcRB.status); @@ -1372,18 +1441,24 @@ static int zsendep11cprb_ioctl(struct ap_perms *perms, unsigned long arg) { int rc; struct ep11_urb xcrb; + struct zcrypt_track tr; struct ep11_urb __user *uxcrb = (void __user *)arg; + memset(&tr, 0, sizeof(tr)); if (copy_from_user(&xcrb, uxcrb, sizeof(xcrb))) return -EFAULT; do { - rc = _zcrypt_send_ep11_cprb(true, perms, &xcrb); - } while (rc == -EAGAIN); + rc = _zcrypt_send_ep11_cprb(true, perms, &tr, &xcrb); + if (rc == -EAGAIN) + tr.again_counter++; + } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); /* on failure: retry once again after a requested rescan */ if ((rc == -ENODEV) && (zcrypt_process_rescan())) do { - rc = _zcrypt_send_ep11_cprb(true, perms, &xcrb); - } while (rc == -EAGAIN); + rc = _zcrypt_send_ep11_cprb(true, perms, &tr, &xcrb); + if (rc == -EAGAIN) + tr.again_counter++; + } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); if (rc) ZCRYPT_DBF(DBF_DEBUG, "ioctl ZSENDEP11CPRB rc=%d\n", rc); if (copy_to_user(uxcrb, &xcrb, sizeof(xcrb))) @@ -1535,8 +1610,10 @@ static long trans_modexpo32(struct ap_perms *perms, struct file *filp, struct compat_ica_rsa_modexpo __user *umex32 = compat_ptr(arg); struct compat_ica_rsa_modexpo mex32; struct ica_rsa_modexpo mex64; + struct zcrypt_track tr; long rc; + memset(&tr, 0, sizeof(tr)); if (copy_from_user(&mex32, umex32, sizeof(mex32))) return -EFAULT; mex64.inputdata = compat_ptr(mex32.inputdata); @@ -1546,13 +1623,17 @@ static long trans_modexpo32(struct ap_perms *perms, struct file *filp, mex64.b_key = compat_ptr(mex32.b_key); mex64.n_modulus = compat_ptr(mex32.n_modulus); do { - rc = zcrypt_rsa_modexpo(perms, &mex64); - } while (rc == -EAGAIN); + rc = zcrypt_rsa_modexpo(perms, &tr, &mex64); + if (rc == -EAGAIN) + tr.again_counter++; + } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); /* on failure: retry once again after a requested rescan */ if ((rc == -ENODEV) && (zcrypt_process_rescan())) do { - rc = zcrypt_rsa_modexpo(perms, &mex64); - } while (rc == -EAGAIN); + rc = zcrypt_rsa_modexpo(perms, &tr, &mex64); + if (rc == -EAGAIN) + tr.again_counter++; + } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); if (rc) return rc; return put_user(mex64.outputdatalength, @@ -1577,8 +1658,10 @@ static long trans_modexpo_crt32(struct ap_perms *perms, struct file *filp, struct compat_ica_rsa_modexpo_crt __user *ucrt32 = compat_ptr(arg); struct compat_ica_rsa_modexpo_crt crt32; struct ica_rsa_modexpo_crt crt64; + struct zcrypt_track tr; long rc; + memset(&tr, 0, sizeof(tr)); if (copy_from_user(&crt32, ucrt32, sizeof(crt32))) return -EFAULT; crt64.inputdata = compat_ptr(crt32.inputdata); @@ -1591,13 +1674,17 @@ static long trans_modexpo_crt32(struct ap_perms *perms, struct file *filp, crt64.nq_prime = compat_ptr(crt32.nq_prime); crt64.u_mult_inv = compat_ptr(crt32.u_mult_inv); do { - rc = zcrypt_rsa_crt(perms, &crt64); - } while (rc == -EAGAIN); + rc = zcrypt_rsa_crt(perms, &tr, &crt64); + if (rc == -EAGAIN) + tr.again_counter++; + } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); /* on failure: retry once again after a requested rescan */ if ((rc == -ENODEV) && (zcrypt_process_rescan())) do { - rc = zcrypt_rsa_crt(perms, &crt64); - } while (rc == -EAGAIN); + rc = zcrypt_rsa_crt(perms, &tr, &crt64); + if (rc == -EAGAIN) + tr.again_counter++; + } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); if (rc) return rc; return put_user(crt64.outputdatalength, @@ -1629,9 +1716,11 @@ static long trans_xcRB32(struct ap_perms *perms, struct file *filp, { struct compat_ica_xcRB __user *uxcRB32 = compat_ptr(arg); struct compat_ica_xcRB xcRB32; + struct zcrypt_track tr; struct ica_xcRB xcRB64; long rc; + memset(&tr, 0, sizeof(tr)); if (copy_from_user(&xcRB32, uxcRB32, sizeof(xcRB32))) return -EFAULT; xcRB64.agent_ID = xcRB32.agent_ID; @@ -1655,13 +1744,17 @@ static long trans_xcRB32(struct ap_perms *perms, struct file *filp, xcRB64.priority_window = xcRB32.priority_window; xcRB64.status = xcRB32.status; do { - rc = _zcrypt_send_cprb(true, perms, &xcRB64); - } while (rc == -EAGAIN); + rc = _zcrypt_send_cprb(true, perms, &tr, &xcRB64); + if (rc == -EAGAIN) + tr.again_counter++; + } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); /* on failure: retry once again after a requested rescan */ if ((rc == -ENODEV) && (zcrypt_process_rescan())) do { - rc = _zcrypt_send_cprb(true, perms, &xcRB64); - } while (rc == -EAGAIN); + rc = _zcrypt_send_cprb(true, perms, &tr, &xcRB64); + if (rc == -EAGAIN) + tr.again_counter++; + } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); xcRB32.reply_control_blk_length = xcRB64.reply_control_blk_length; xcRB32.reply_data_length = xcRB64.reply_data_length; xcRB32.status = xcRB64.status; diff --git a/drivers/s390/crypto/zcrypt_api.h b/drivers/s390/crypto/zcrypt_api.h index 19ddfc38e029..263ed1735431 100644 --- a/drivers/s390/crypto/zcrypt_api.h +++ b/drivers/s390/crypto/zcrypt_api.h @@ -55,6 +55,18 @@ enum crypto_ops { struct zcrypt_queue; +/* struct to hold tracking information for a userspace request/response */ +struct zcrypt_track { + int again_counter; /* retry attempts counter */ + int last_qid; /* last qid used */ + int last_rc; /* last return code */ +}; + +/* defines related to message tracking */ +#define TRACK_AGAIN_MAX 10 +#define TRACK_AGAIN_CARD_WEIGHT_PENALTY 1000 +#define TRACK_AGAIN_QUEUE_WEIGHT_PENALTY 10000 + struct zcrypt_ops { long (*rsa_modexpo)(struct zcrypt_queue *, struct ica_rsa_modexpo *); long (*rsa_modexpo_crt)(struct zcrypt_queue *, @@ -82,7 +94,7 @@ struct zcrypt_card { int min_mod_size; /* Min number of bits. */ int max_mod_size; /* Max number of bits. */ int max_exp_bit_length; - int speed_rating[NUM_OPS]; /* Speed idx of crypto ops. */ + const int *speed_rating; /* Speed idx of crypto ops. */ atomic_t load; /* Utilization of the crypto device */ int request_count; /* # current requests. */ diff --git a/drivers/s390/crypto/zcrypt_cex2a.c b/drivers/s390/crypto/zcrypt_cex2a.c index b447f3e9e4a2..226a5612e855 100644 --- a/drivers/s390/crypto/zcrypt_cex2a.c +++ b/drivers/s390/crypto/zcrypt_cex2a.c @@ -94,8 +94,7 @@ static int zcrypt_cex2a_card_probe(struct ap_device *ap_dev) if (ac->ap_dev.device_type == AP_DEVICE_TYPE_CEX2A) { zc->min_mod_size = CEX2A_MIN_MOD_SIZE; zc->max_mod_size = CEX2A_MAX_MOD_SIZE; - memcpy(zc->speed_rating, CEX2A_SPEED_IDX, - sizeof(CEX2A_SPEED_IDX)); + zc->speed_rating = CEX2A_SPEED_IDX; zc->max_exp_bit_length = CEX2A_MAX_MOD_SIZE; zc->type_string = "CEX2A"; zc->user_space_type = ZCRYPT_CEX2A; @@ -108,8 +107,7 @@ static int zcrypt_cex2a_card_probe(struct ap_device *ap_dev) zc->max_mod_size = CEX3A_MAX_MOD_SIZE; zc->max_exp_bit_length = CEX3A_MAX_MOD_SIZE; } - memcpy(zc->speed_rating, CEX3A_SPEED_IDX, - sizeof(CEX3A_SPEED_IDX)); + zc->speed_rating = CEX3A_SPEED_IDX; zc->type_string = "CEX3A"; zc->user_space_type = ZCRYPT_CEX3A; } else { diff --git a/drivers/s390/crypto/zcrypt_cex2c.c b/drivers/s390/crypto/zcrypt_cex2c.c index 146eb9f24694..7a8cbdbe4408 100644 --- a/drivers/s390/crypto/zcrypt_cex2c.c +++ b/drivers/s390/crypto/zcrypt_cex2c.c @@ -266,8 +266,7 @@ static int zcrypt_cex2c_card_probe(struct ap_device *ap_dev) case AP_DEVICE_TYPE_CEX2C: zc->user_space_type = ZCRYPT_CEX2C; zc->type_string = "CEX2C"; - memcpy(zc->speed_rating, CEX2C_SPEED_IDX, - sizeof(CEX2C_SPEED_IDX)); + zc->speed_rating = CEX2C_SPEED_IDX; zc->min_mod_size = CEX2C_MIN_MOD_SIZE; zc->max_mod_size = CEX2C_MAX_MOD_SIZE; zc->max_exp_bit_length = CEX2C_MAX_MOD_SIZE; @@ -275,8 +274,7 @@ static int zcrypt_cex2c_card_probe(struct ap_device *ap_dev) case AP_DEVICE_TYPE_CEX3C: zc->user_space_type = ZCRYPT_CEX3C; zc->type_string = "CEX3C"; - memcpy(zc->speed_rating, CEX3C_SPEED_IDX, - sizeof(CEX3C_SPEED_IDX)); + zc->speed_rating = CEX3C_SPEED_IDX; zc->min_mod_size = CEX3C_MIN_MOD_SIZE; zc->max_mod_size = CEX3C_MAX_MOD_SIZE; zc->max_exp_bit_length = CEX3C_MAX_MOD_SIZE; diff --git a/drivers/s390/crypto/zcrypt_cex4.c b/drivers/s390/crypto/zcrypt_cex4.c index d9ebe3a3c210..f5195bca1d85 100644 --- a/drivers/s390/crypto/zcrypt_cex4.c +++ b/drivers/s390/crypto/zcrypt_cex4.c @@ -409,31 +409,31 @@ static int zcrypt_cex4_card_probe(struct ap_device *ap_dev) * Normalized speed ratings per crypto adapter * MEX_1k, MEX_2k, MEX_4k, CRT_1k, CRT_2k, CRT_4k, RNG, SECKEY */ - static const int CEX4A_SPEED_IDX[] = { + static const int CEX4A_SPEED_IDX[NUM_OPS] = { 14, 19, 249, 42, 228, 1458, 0, 0}; - static const int CEX5A_SPEED_IDX[] = { + static const int CEX5A_SPEED_IDX[NUM_OPS] = { 8, 9, 20, 18, 66, 458, 0, 0}; - static const int CEX6A_SPEED_IDX[] = { + static const int CEX6A_SPEED_IDX[NUM_OPS] = { 6, 9, 20, 17, 65, 438, 0, 0}; - static const int CEX7A_SPEED_IDX[] = { + static const int CEX7A_SPEED_IDX[NUM_OPS] = { 6, 8, 17, 15, 54, 362, 0, 0}; - static const int CEX4C_SPEED_IDX[] = { + static const int CEX4C_SPEED_IDX[NUM_OPS] = { 59, 69, 308, 83, 278, 2204, 209, 40}; static const int CEX5C_SPEED_IDX[] = { 24, 31, 50, 37, 90, 479, 27, 10}; - static const int CEX6C_SPEED_IDX[] = { + static const int CEX6C_SPEED_IDX[NUM_OPS] = { 16, 20, 32, 27, 77, 455, 24, 9}; - static const int CEX7C_SPEED_IDX[] = { + static const int CEX7C_SPEED_IDX[NUM_OPS] = { 14, 16, 26, 23, 64, 376, 23, 8}; - static const int CEX4P_SPEED_IDX[] = { + static const int CEX4P_SPEED_IDX[NUM_OPS] = { 0, 0, 0, 0, 0, 0, 0, 50}; - static const int CEX5P_SPEED_IDX[] = { + static const int CEX5P_SPEED_IDX[NUM_OPS] = { 0, 0, 0, 0, 0, 0, 0, 10}; - static const int CEX6P_SPEED_IDX[] = { + static const int CEX6P_SPEED_IDX[NUM_OPS] = { 0, 0, 0, 0, 0, 0, 0, 9}; - static const int CEX7P_SPEED_IDX[] = { + static const int CEX7P_SPEED_IDX[NUM_OPS] = { 0, 0, 0, 0, 0, 0, 0, 8}; struct ap_card *ac = to_ap_card(&ap_dev->device); @@ -449,26 +449,22 @@ static int zcrypt_cex4_card_probe(struct ap_device *ap_dev) if (ac->ap_dev.device_type == AP_DEVICE_TYPE_CEX4) { zc->type_string = "CEX4A"; zc->user_space_type = ZCRYPT_CEX4; - memcpy(zc->speed_rating, CEX4A_SPEED_IDX, - sizeof(CEX4A_SPEED_IDX)); + zc->speed_rating = CEX4A_SPEED_IDX; } else if (ac->ap_dev.device_type == AP_DEVICE_TYPE_CEX5) { zc->type_string = "CEX5A"; zc->user_space_type = ZCRYPT_CEX5; - memcpy(zc->speed_rating, CEX5A_SPEED_IDX, - sizeof(CEX5A_SPEED_IDX)); + zc->speed_rating = CEX5A_SPEED_IDX; } else if (ac->ap_dev.device_type == AP_DEVICE_TYPE_CEX6) { zc->type_string = "CEX6A"; zc->user_space_type = ZCRYPT_CEX6; - memcpy(zc->speed_rating, CEX6A_SPEED_IDX, - sizeof(CEX6A_SPEED_IDX)); + zc->speed_rating = CEX6A_SPEED_IDX; } else { zc->type_string = "CEX7A"; /* wrong user space type, just for compatibility * with the ZCRYPT_STATUS_MASK ioctl. */ zc->user_space_type = ZCRYPT_CEX6; - memcpy(zc->speed_rating, CEX7A_SPEED_IDX, - sizeof(CEX7A_SPEED_IDX)); + zc->speed_rating = CEX7A_SPEED_IDX; } zc->min_mod_size = CEX4A_MIN_MOD_SIZE; if (ap_test_bit(&ac->functions, AP_FUNC_MEX4K) && @@ -488,32 +484,28 @@ static int zcrypt_cex4_card_probe(struct ap_device *ap_dev) * just keep it for cca compatibility */ zc->user_space_type = ZCRYPT_CEX3C; - memcpy(zc->speed_rating, CEX4C_SPEED_IDX, - sizeof(CEX4C_SPEED_IDX)); + zc->speed_rating = CEX4C_SPEED_IDX; } else if (ac->ap_dev.device_type == AP_DEVICE_TYPE_CEX5) { zc->type_string = "CEX5C"; /* wrong user space type, must be CEX5 * just keep it for cca compatibility */ zc->user_space_type = ZCRYPT_CEX3C; - memcpy(zc->speed_rating, CEX5C_SPEED_IDX, - sizeof(CEX5C_SPEED_IDX)); + zc->speed_rating = CEX5C_SPEED_IDX; } else if (ac->ap_dev.device_type == AP_DEVICE_TYPE_CEX6) { zc->type_string = "CEX6C"; /* wrong user space type, must be CEX6 * just keep it for cca compatibility */ zc->user_space_type = ZCRYPT_CEX3C; - memcpy(zc->speed_rating, CEX6C_SPEED_IDX, - sizeof(CEX6C_SPEED_IDX)); + zc->speed_rating = CEX6C_SPEED_IDX; } else { zc->type_string = "CEX7C"; /* wrong user space type, must be CEX7 * just keep it for cca compatibility */ zc->user_space_type = ZCRYPT_CEX3C; - memcpy(zc->speed_rating, CEX7C_SPEED_IDX, - sizeof(CEX7C_SPEED_IDX)); + zc->speed_rating = CEX7C_SPEED_IDX; } zc->min_mod_size = CEX4C_MIN_MOD_SIZE; zc->max_mod_size = CEX4C_MAX_MOD_SIZE; @@ -522,26 +514,22 @@ static int zcrypt_cex4_card_probe(struct ap_device *ap_dev) if (ac->ap_dev.device_type == AP_DEVICE_TYPE_CEX4) { zc->type_string = "CEX4P"; zc->user_space_type = ZCRYPT_CEX4; - memcpy(zc->speed_rating, CEX4P_SPEED_IDX, - sizeof(CEX4P_SPEED_IDX)); + zc->speed_rating = CEX4P_SPEED_IDX; } else if (ac->ap_dev.device_type == AP_DEVICE_TYPE_CEX5) { zc->type_string = "CEX5P"; zc->user_space_type = ZCRYPT_CEX5; - memcpy(zc->speed_rating, CEX5P_SPEED_IDX, - sizeof(CEX5P_SPEED_IDX)); + zc->speed_rating = CEX5P_SPEED_IDX; } else if (ac->ap_dev.device_type == AP_DEVICE_TYPE_CEX6) { zc->type_string = "CEX6P"; zc->user_space_type = ZCRYPT_CEX6; - memcpy(zc->speed_rating, CEX6P_SPEED_IDX, - sizeof(CEX6P_SPEED_IDX)); + zc->speed_rating = CEX6P_SPEED_IDX; } else { zc->type_string = "CEX7P"; /* wrong user space type, just for compatibility * with the ZCRYPT_STATUS_MASK ioctl. */ zc->user_space_type = ZCRYPT_CEX6; - memcpy(zc->speed_rating, CEX7P_SPEED_IDX, - sizeof(CEX7P_SPEED_IDX)); + zc->speed_rating = CEX7P_SPEED_IDX; } zc->min_mod_size = CEX4C_MIN_MOD_SIZE; zc->max_mod_size = CEX4C_MAX_MOD_SIZE; From 0ae88ccf4c160e02316e054db67156230568cf49 Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Wed, 23 Sep 2020 09:18:38 +0200 Subject: [PATCH 358/645] s390/zcrypt: New config switch CONFIG_ZCRYPT_DEBUG Introduce a new config switch CONFIG_ZCRYPT_DEBUG which will be used to enable some features for debugging the zcrypt device driver and ap bus system: Another patch will use this for displaying ap card and ap queue state information via sysfs attribute. A furher patch will use this to enable some special treatment for some fields of an crypto request to be able to inject failures and so help debugging with regards to handling of failures. Signed-off-by: Harald Freudenberger Signed-off-by: Vasily Gorbik --- drivers/crypto/Kconfig | 24 ++++++++++++++++++++---- 1 file changed, 20 insertions(+), 4 deletions(-) diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig index aa3a4ed07a66..895a6d5f8b53 100644 --- a/drivers/crypto/Kconfig +++ b/drivers/crypto/Kconfig @@ -71,10 +71,26 @@ config ZCRYPT help Select this option if you want to enable support for s390 cryptographic adapters like: - + PCI-X Cryptographic Coprocessor (PCIXCC) - + Crypto Express 2,3,4 or 5 Coprocessor (CEXxC) - + Crypto Express 2,3,4 or 5 Accelerator (CEXxA) - + Crypto Express 4 or 5 EP11 Coprocessor (CEXxP) + + Crypto Express 2 up to 7 Coprocessor (CEXxC) + + Crypto Express 2 up to 7 Accelerator (CEXxA) + + Crypto Express 4 up to 7 EP11 Coprocessor (CEXxP) + +config ZCRYPT_DEBUG + bool "Enable debug features for s390 cryptographic adapters" + default n + depends on DEBUG_KERNEL + depends on ZCRYPT + help + Say 'Y' here to enable some additional debug features on the + s390 cryptographic adapters driver. + + There will be some more sysfs attributes displayed for ap cards + and queues and some flags on crypto requests are interpreted as + debugging messages to force error injection. + + Do not enable on production level kernel build. + + If unsure, say N. config ZCRYPT_MULTIDEVNODES bool "Support for multiple zcrypt device nodes" From 0b641cbd24445e56073c69dd046be488dcf1965b Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Thu, 2 Jul 2020 11:22:01 +0200 Subject: [PATCH 359/645] s390/ap: split ap queue state machine state from device state The state machine for each ap queue covered a mixture of device states and state machine (firmware queue state) states. This patch splits the device states and the state machine states into two different enums and variables. The major state is the device state with currently these values: AP_DEV_STATE_UNINITIATED - fresh and virgin, not touched AP_DEV_STATE_OPERATING - queue dev is working normal AP_DEV_STATE_SHUTDOWN - remove/unbind/shutdown in progress AP_DEV_STATE_ERROR - device is in error state only when the device state is > UNINITIATED the state machine is run. The state machine represents the states of the firmware queue: AP_SM_STATE_RESET_START - starting point, reset (RAPQ) ap queue AP_SM_STATE_RESET_WAIT - reset triggered, waiting to be finished if irqs enabled, set up irq (AQIC) AP_SM_STATE_SETIRQ_WAIT - enable irq triggered, waiting to be finished, then go to IDLE AP_SM_STATE_IDLE - queue is operational but empty AP_SM_STATE_WORKING - queue is operational, requests are stored and replies may wait for getting fetched AP_SM_STATE_QUEUE_FULL - firmware queue is full, so only replies can get fetched For debugging each ap queue shows a sysfs attribute 'states' which displays the device and state machine state and is only available when the kernel is build with CONFIG_ZCRYPT_DEBUG enabled. Signed-off-by: Harald Freudenberger Signed-off-by: Vasily Gorbik --- drivers/s390/crypto/ap_bus.c | 2 +- drivers/s390/crypto/ap_bus.h | 21 +++- drivers/s390/crypto/ap_queue.c | 155 ++++++++++++++++++------- drivers/s390/crypto/zcrypt_msgtype50.c | 8 +- drivers/s390/crypto/zcrypt_msgtype6.c | 26 +++-- 5 files changed, 155 insertions(+), 57 deletions(-) diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index 231a98c9165d..1e895fcd25cc 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -1380,7 +1380,7 @@ static void _ap_scan_bus_adapter(int id) if (dev) { if (!broken) { spin_lock_bh(&aq->lock); - broken = aq->sm_state == AP_SM_STATE_BORKED; + broken = aq->dev_state == AP_DEV_STATE_ERROR; spin_unlock_bh(&aq->lock); } if (broken) { diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h index 1ea046324e8f..2d4558b5abaf 100644 --- a/drivers/s390/crypto/ap_bus.h +++ b/drivers/s390/crypto/ap_bus.h @@ -86,15 +86,12 @@ static inline int ap_test_bit(unsigned int *ptr, unsigned int nr) * AP queue state machine states */ enum ap_sm_state { - AP_SM_STATE_RESET_START, + AP_SM_STATE_RESET_START = 0, AP_SM_STATE_RESET_WAIT, AP_SM_STATE_SETIRQ_WAIT, AP_SM_STATE_IDLE, AP_SM_STATE_WORKING, AP_SM_STATE_QUEUE_FULL, - AP_SM_STATE_REMOVE, /* about to be removed from driver */ - AP_SM_STATE_UNBOUND, /* momentary not bound to a driver */ - AP_SM_STATE_BORKED, /* broken */ NR_AP_SM_STATES }; @@ -118,6 +115,17 @@ enum ap_sm_wait { NR_AP_SM_WAIT }; +/* + * AP queue device states + */ +enum ap_dev_state { + AP_DEV_STATE_UNINITIATED = 0, /* fresh and virgin, not touched */ + AP_DEV_STATE_OPERATING, /* queue dev is working normal */ + AP_DEV_STATE_SHUTDOWN, /* remove/unbind/shutdown in progress */ + AP_DEV_STATE_ERROR, /* device is in error state */ + NR_AP_DEV_STATES +}; + struct ap_device; struct ap_message; @@ -169,10 +177,10 @@ struct ap_queue { struct ap_card *card; /* Ptr to assoc. AP card. */ spinlock_t lock; /* Per device lock. */ void *private; /* ap driver private pointer. */ + enum ap_dev_state dev_state; /* queue device state */ ap_qid_t qid; /* AP queue id. */ int interrupt; /* indicate if interrupts are enabled */ int queue_count; /* # messages currently on AP queue. */ - enum ap_sm_state sm_state; /* ap queue state machine state */ int pendingq_count; /* # requests on pendingq list. */ int requestq_count; /* # requests on requestq list. */ u64 total_request_count; /* # requests ever for this AP device.*/ @@ -181,6 +189,7 @@ struct ap_queue { struct list_head pendingq; /* List of message sent to AP queue. */ struct list_head requestq; /* List of message yet to be sent. */ struct ap_message *reply; /* Per device reply message. */ + enum ap_sm_state sm_state; /* ap queue state machine state */ }; #define to_ap_queue(x) container_of((x), struct ap_queue, ap_dev.device) @@ -234,7 +243,7 @@ int ap_recv(ap_qid_t, unsigned long long *, void *, size_t); enum ap_sm_wait ap_sm_event(struct ap_queue *aq, enum ap_sm_event event); enum ap_sm_wait ap_sm_event_loop(struct ap_queue *aq, enum ap_sm_event event); -void ap_queue_message(struct ap_queue *aq, struct ap_message *ap_msg); +int ap_queue_message(struct ap_queue *aq, struct ap_message *ap_msg); void ap_cancel_message(struct ap_queue *aq, struct ap_message *ap_msg); void ap_flush_queue(struct ap_queue *aq); diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c index 688ebebbf98c..e7ecbcc18db3 100644 --- a/drivers/s390/crypto/ap_queue.c +++ b/drivers/s390/crypto/ap_queue.c @@ -195,7 +195,7 @@ static enum ap_sm_wait ap_sm_read(struct ap_queue *aq) aq->sm_state = AP_SM_STATE_IDLE; return AP_SM_WAIT_NONE; default: - aq->sm_state = AP_SM_STATE_BORKED; + aq->dev_state = AP_DEV_STATE_ERROR; return AP_SM_WAIT_NONE; } } @@ -245,7 +245,7 @@ static enum ap_sm_wait ap_sm_write(struct ap_queue *aq) ap_msg->receive(aq, ap_msg, NULL); return AP_SM_WAIT_AGAIN; default: - aq->sm_state = AP_SM_STATE_BORKED; + aq->dev_state = AP_DEV_STATE_ERROR; return AP_SM_WAIT_NONE; } } @@ -284,7 +284,7 @@ static enum ap_sm_wait ap_sm_reset(struct ap_queue *aq) case AP_RESPONSE_DECONFIGURED: case AP_RESPONSE_CHECKSTOPPED: default: - aq->sm_state = AP_SM_STATE_BORKED; + aq->dev_state = AP_DEV_STATE_ERROR; return AP_SM_WAIT_NONE; } } @@ -323,7 +323,7 @@ static enum ap_sm_wait ap_sm_reset_wait(struct ap_queue *aq) case AP_RESPONSE_DECONFIGURED: case AP_RESPONSE_CHECKSTOPPED: default: - aq->sm_state = AP_SM_STATE_BORKED; + aq->dev_state = AP_DEV_STATE_ERROR; return AP_SM_WAIT_NONE; } } @@ -360,7 +360,7 @@ static enum ap_sm_wait ap_sm_setirq_wait(struct ap_queue *aq) case AP_RESPONSE_NO_PENDING_REPLY: return AP_SM_WAIT_TIMEOUT; default: - aq->sm_state = AP_SM_STATE_BORKED; + aq->dev_state = AP_DEV_STATE_ERROR; return AP_SM_WAIT_NONE; } } @@ -393,23 +393,14 @@ static ap_func_t *ap_jumptable[NR_AP_SM_STATES][NR_AP_SM_EVENTS] = { [AP_SM_EVENT_POLL] = ap_sm_read, [AP_SM_EVENT_TIMEOUT] = ap_sm_reset, }, - [AP_SM_STATE_REMOVE] = { - [AP_SM_EVENT_POLL] = ap_sm_nop, - [AP_SM_EVENT_TIMEOUT] = ap_sm_nop, - }, - [AP_SM_STATE_UNBOUND] = { - [AP_SM_EVENT_POLL] = ap_sm_nop, - [AP_SM_EVENT_TIMEOUT] = ap_sm_nop, - }, - [AP_SM_STATE_BORKED] = { - [AP_SM_EVENT_POLL] = ap_sm_nop, - [AP_SM_EVENT_TIMEOUT] = ap_sm_nop, - }, }; enum ap_sm_wait ap_sm_event(struct ap_queue *aq, enum ap_sm_event event) { - return ap_jumptable[aq->sm_state][event](aq); + if (aq->dev_state > AP_DEV_STATE_UNINITIATED) + return ap_jumptable[aq->sm_state][event](aq); + else + return AP_SM_WAIT_NONE; } enum ap_sm_wait ap_sm_event_loop(struct ap_queue *aq, enum ap_sm_event event) @@ -429,12 +420,20 @@ static ssize_t request_count_show(struct device *dev, char *buf) { struct ap_queue *aq = to_ap_queue(dev); + bool valid = false; u64 req_cnt; spin_lock_bh(&aq->lock); - req_cnt = aq->total_request_count; + if (aq->dev_state > AP_DEV_STATE_UNINITIATED) { + req_cnt = aq->total_request_count; + valid = true; + } spin_unlock_bh(&aq->lock); - return scnprintf(buf, PAGE_SIZE, "%llu\n", req_cnt); + + if (valid) + return scnprintf(buf, PAGE_SIZE, "%llu\n", req_cnt); + else + return scnprintf(buf, PAGE_SIZE, "-\n"); } static ssize_t request_count_store(struct device *dev, @@ -459,7 +458,8 @@ static ssize_t requestq_count_show(struct device *dev, unsigned int reqq_cnt = 0; spin_lock_bh(&aq->lock); - reqq_cnt = aq->requestq_count; + if (aq->dev_state > AP_DEV_STATE_UNINITIATED) + reqq_cnt = aq->requestq_count; spin_unlock_bh(&aq->lock); return scnprintf(buf, PAGE_SIZE, "%d\n", reqq_cnt); } @@ -473,7 +473,8 @@ static ssize_t pendingq_count_show(struct device *dev, unsigned int penq_cnt = 0; spin_lock_bh(&aq->lock); - penq_cnt = aq->pendingq_count; + if (aq->dev_state > AP_DEV_STATE_UNINITIATED) + penq_cnt = aq->pendingq_count; spin_unlock_bh(&aq->lock); return scnprintf(buf, PAGE_SIZE, "%d\n", penq_cnt); } @@ -542,12 +543,79 @@ static ssize_t interrupt_show(struct device *dev, static DEVICE_ATTR_RO(interrupt); +#ifdef CONFIG_ZCRYPT_DEBUG +static ssize_t states_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct ap_queue *aq = to_ap_queue(dev); + int rc = 0; + + spin_lock_bh(&aq->lock); + /* queue device state */ + switch (aq->dev_state) { + case AP_DEV_STATE_UNINITIATED: + rc = scnprintf(buf, PAGE_SIZE, "UNINITIATED\n"); + break; + case AP_DEV_STATE_OPERATING: + rc = scnprintf(buf, PAGE_SIZE, "OPERATING"); + break; + case AP_DEV_STATE_SHUTDOWN: + rc = scnprintf(buf, PAGE_SIZE, "SHUTDOWN"); + break; + case AP_DEV_STATE_ERROR: + rc = scnprintf(buf, PAGE_SIZE, "ERROR"); + break; + default: + rc = scnprintf(buf, PAGE_SIZE, "UNKNOWN"); + } + /* state machine state */ + if (aq->dev_state) { + switch (aq->sm_state) { + case AP_SM_STATE_RESET_START: + rc += scnprintf(buf + rc, PAGE_SIZE - rc, + " [RESET_START]\n"); + break; + case AP_SM_STATE_RESET_WAIT: + rc += scnprintf(buf + rc, PAGE_SIZE - rc, + " [RESET_WAIT]\n"); + break; + case AP_SM_STATE_SETIRQ_WAIT: + rc += scnprintf(buf + rc, PAGE_SIZE - rc, + " [SETIRQ_WAIT]\n"); + break; + case AP_SM_STATE_IDLE: + rc += scnprintf(buf + rc, PAGE_SIZE - rc, + " [IDLE]\n"); + break; + case AP_SM_STATE_WORKING: + rc += scnprintf(buf + rc, PAGE_SIZE - rc, + " [WORKING]\n"); + break; + case AP_SM_STATE_QUEUE_FULL: + rc += scnprintf(buf + rc, PAGE_SIZE - rc, + " [FULL]\n"); + break; + default: + rc += scnprintf(buf + rc, PAGE_SIZE - rc, + " [UNKNOWN]\n"); + } + } + spin_unlock_bh(&aq->lock); + + return rc; +} +static DEVICE_ATTR_RO(states); +#endif + static struct attribute *ap_queue_dev_attrs[] = { &dev_attr_request_count.attr, &dev_attr_requestq_count.attr, &dev_attr_pendingq_count.attr, &dev_attr_reset.attr, &dev_attr_interrupt.attr, +#ifdef CONFIG_ZCRYPT_DEBUG + &dev_attr_states.attr, +#endif NULL }; @@ -587,7 +655,6 @@ struct ap_queue *ap_queue_create(ap_qid_t qid, int device_type) aq->ap_dev.device.type = &ap_queue_type; aq->ap_dev.device_type = device_type; aq->qid = qid; - aq->sm_state = AP_SM_STATE_UNBOUND; aq->interrupt = AP_INTR_DISABLED; spin_lock_init(&aq->lock); INIT_LIST_HEAD(&aq->pendingq); @@ -612,22 +679,30 @@ EXPORT_SYMBOL(ap_queue_init_reply); * @aq: The AP device to queue the message to * @ap_msg: The message that is to be added */ -void ap_queue_message(struct ap_queue *aq, struct ap_message *ap_msg) +int ap_queue_message(struct ap_queue *aq, struct ap_message *ap_msg) { - /* For asynchronous message handling a valid receive-callback - * is required. - */ + int rc = 0; + + /* msg needs to have a valid receive-callback */ BUG_ON(!ap_msg->receive); spin_lock_bh(&aq->lock); - /* Queue the message. */ - list_add_tail(&ap_msg->list, &aq->requestq); - aq->requestq_count++; - aq->total_request_count++; - atomic64_inc(&aq->card->total_request_count); + + /* only allow to queue new messages if device state is ok */ + if (aq->dev_state == AP_DEV_STATE_OPERATING) { + list_add_tail(&ap_msg->list, &aq->requestq); + aq->requestq_count++; + aq->total_request_count++; + atomic64_inc(&aq->card->total_request_count); + } else + rc = -ENODEV; + /* Send/receive as many request from the queue as possible. */ ap_wait(ap_sm_event_loop(aq, AP_SM_EVENT_POLL)); + spin_unlock_bh(&aq->lock); + + return rc; } EXPORT_SYMBOL(ap_queue_message); @@ -698,8 +773,8 @@ void ap_queue_prepare_remove(struct ap_queue *aq) spin_lock_bh(&aq->lock); /* flush queue */ __ap_flush_queue(aq); - /* set REMOVE state to prevent new messages are queued in */ - aq->sm_state = AP_SM_STATE_REMOVE; + /* move queue device state to SHUTDOWN in progress */ + aq->dev_state = AP_DEV_STATE_SHUTDOWN; spin_unlock_bh(&aq->lock); del_timer_sync(&aq->timeout); } @@ -707,21 +782,21 @@ void ap_queue_prepare_remove(struct ap_queue *aq) void ap_queue_remove(struct ap_queue *aq) { /* - * all messages have been flushed and the state is - * AP_SM_STATE_REMOVE. Now reset with zero which also - * clears the irq registration and move the state - * to AP_SM_STATE_UNBOUND to signal that this queue - * is not used by any driver currently. + * all messages have been flushed and the device state + * is SHUTDOWN. Now reset with zero which also clears + * the irq registration and move the device state + * to the initial value AP_DEV_STATE_UNINITIATED. */ spin_lock_bh(&aq->lock); ap_zapq(aq->qid); - aq->sm_state = AP_SM_STATE_UNBOUND; + aq->dev_state = AP_DEV_STATE_UNINITIATED; spin_unlock_bh(&aq->lock); } void ap_queue_init_state(struct ap_queue *aq) { spin_lock_bh(&aq->lock); + aq->dev_state = AP_DEV_STATE_OPERATING; aq->sm_state = AP_SM_STATE_RESET_START; ap_wait(ap_sm_event(aq, AP_SM_EVENT_POLL)); spin_unlock_bh(&aq->lock); diff --git a/drivers/s390/crypto/zcrypt_msgtype50.c b/drivers/s390/crypto/zcrypt_msgtype50.c index 7aedc338b445..349306c2f155 100644 --- a/drivers/s390/crypto/zcrypt_msgtype50.c +++ b/drivers/s390/crypto/zcrypt_msgtype50.c @@ -471,7 +471,9 @@ static long zcrypt_cex2a_modexpo(struct zcrypt_queue *zq, if (rc) goto out_free; init_completion(&work); - ap_queue_message(zq->queue, &ap_msg); + rc = ap_queue_message(zq->queue, &ap_msg); + if (rc) + goto out_free; rc = wait_for_completion_interruptible(&work); if (rc == 0) { rc = ap_msg.rc; @@ -515,7 +517,9 @@ static long zcrypt_cex2a_modexpo_crt(struct zcrypt_queue *zq, if (rc) goto out_free; init_completion(&work); - ap_queue_message(zq->queue, &ap_msg); + rc = ap_queue_message(zq->queue, &ap_msg); + if (rc) + goto out_free; rc = wait_for_completion_interruptible(&work); if (rc == 0) { rc = ap_msg.rc; diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c index 3db901883a5c..51b9924753ee 100644 --- a/drivers/s390/crypto/zcrypt_msgtype6.c +++ b/drivers/s390/crypto/zcrypt_msgtype6.c @@ -1027,7 +1027,9 @@ static long zcrypt_msgtype6_modexpo(struct zcrypt_queue *zq, if (rc) goto out_free; init_completion(&resp_type.work); - ap_queue_message(zq->queue, &ap_msg); + rc = ap_queue_message(zq->queue, &ap_msg); + if (rc) + goto out_free; rc = wait_for_completion_interruptible(&resp_type.work); if (rc == 0) { rc = ap_msg.rc; @@ -1071,7 +1073,9 @@ static long zcrypt_msgtype6_modexpo_crt(struct zcrypt_queue *zq, if (rc) goto out_free; init_completion(&resp_type.work); - ap_queue_message(zq->queue, &ap_msg); + rc = ap_queue_message(zq->queue, &ap_msg); + if (rc) + goto out_free; rc = wait_for_completion_interruptible(&resp_type.work); if (rc == 0) { rc = ap_msg.rc; @@ -1130,7 +1134,9 @@ static long zcrypt_msgtype6_send_cprb(bool userspace, struct zcrypt_queue *zq, struct response_type *rtype = (struct response_type *)(ap_msg->private); init_completion(&rtype->work); - ap_queue_message(zq->queue, ap_msg); + rc = ap_queue_message(zq->queue, ap_msg); + if (rc) + goto out; rc = wait_for_completion_interruptible(&rtype->work); if (rc == 0) { rc = ap_msg->rc; @@ -1139,7 +1145,7 @@ static long zcrypt_msgtype6_send_cprb(bool userspace, struct zcrypt_queue *zq, } else /* Signal pending. */ ap_cancel_message(zq->queue, ap_msg); - +out: return rc; } @@ -1232,7 +1238,9 @@ static long zcrypt_msgtype6_send_ep11_cprb(bool userspace, struct zcrypt_queue * } init_completion(&rtype->work); - ap_queue_message(zq->queue, ap_msg); + rc = ap_queue_message(zq->queue, ap_msg); + if (rc) + goto out; rc = wait_for_completion_interruptible(&rtype->work); if (rc == 0) { rc = ap_msg->rc; @@ -1241,7 +1249,7 @@ static long zcrypt_msgtype6_send_ep11_cprb(bool userspace, struct zcrypt_queue * } else /* Signal pending. */ ap_cancel_message(zq->queue, ap_msg); - +out: return rc; } @@ -1293,7 +1301,9 @@ static long zcrypt_msgtype6_rng(struct zcrypt_queue *zq, msg->cprbx.domain = AP_QID_QUEUE(zq->queue->qid); init_completion(&rtype->work); - ap_queue_message(zq->queue, ap_msg); + rc = ap_queue_message(zq->queue, ap_msg); + if (rc) + goto out; rc = wait_for_completion_interruptible(&rtype->work); if (rc == 0) { rc = ap_msg->rc; @@ -1302,7 +1312,7 @@ static long zcrypt_msgtype6_rng(struct zcrypt_queue *zq, } else /* Signal pending. */ ap_cancel_message(zq->queue, ap_msg); - +out: return rc; } From 2ea2a6099ae3d1708f90f43c81a98cba3d4bb74c Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Thu, 2 Jul 2020 15:56:15 +0200 Subject: [PATCH 360/645] s390/ap: add error response code field for ap queue devices On AP instruction failures the last response code is now kept in the struct ap_queue. There is also a new sysfs attribute showing this field (enabled only on debug kernels). Also slight rework of the AP_DBF macros to get some more content into one debug feature message line. Signed-off-by: Harald Freudenberger Signed-off-by: Vasily Gorbik --- drivers/s390/crypto/ap_bus.c | 54 ++++++++++++++-------------- drivers/s390/crypto/ap_bus.h | 1 + drivers/s390/crypto/ap_debug.h | 8 +++++ drivers/s390/crypto/ap_queue.c | 64 ++++++++++++++++++++++++++++++++++ 4 files changed, 101 insertions(+), 26 deletions(-) diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index 1e895fcd25cc..6d61e89c5984 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -214,7 +214,7 @@ static inline int ap_fetch_qci_info(struct ap_config_info *info) static void __init ap_init_qci_info(void) { if (!ap_qci_available()) { - AP_DBF(DBF_INFO, "%s QCI not supported\n", __func__); + AP_DBF_INFO("%s QCI not supported\n", __func__); return; } @@ -226,18 +226,18 @@ static void __init ap_init_qci_info(void) ap_qci_info = NULL; return; } - AP_DBF(DBF_INFO, "%s successful fetched initial qci info\n", __func__); + AP_DBF_INFO("%s successful fetched initial qci info\n", __func__); if (ap_qci_info->apxa) { if (ap_qci_info->Na) { ap_max_adapter_id = ap_qci_info->Na; - AP_DBF(DBF_INFO, "%s new ap_max_adapter_id is %d\n", - __func__, ap_max_adapter_id); + AP_DBF_INFO("%s new ap_max_adapter_id is %d\n", + __func__, ap_max_adapter_id); } if (ap_qci_info->Nd) { ap_max_domain_id = ap_qci_info->Nd; - AP_DBF(DBF_INFO, "%s new ap_max_domain_id is %d\n", - __func__, ap_max_domain_id); + AP_DBF_INFO("%s new ap_max_domain_id is %d\n", + __func__, ap_max_domain_id); } } } @@ -618,8 +618,8 @@ static int __ap_revise_reserved(struct device *dev, void *dummy) drvres = to_ap_drv(dev->driver)->flags & AP_DRIVER_FLAG_DEFAULT; if (!!devres != !!drvres) { - AP_DBF(DBF_DEBUG, "reprobing queue=%02x.%04x\n", - card, queue); + AP_DBF_DBG("reprobing queue=%02x.%04x\n", + card, queue); rc = device_reprobe(dev); } } @@ -796,7 +796,7 @@ EXPORT_SYMBOL(ap_bus_force_rescan); */ void ap_bus_cfg_chg(void) { - AP_DBF(DBF_INFO, "%s config change, forcing bus rescan\n", __func__); + AP_DBF_DBG("%s config change, forcing bus rescan\n", __func__); ap_bus_force_rescan(); } @@ -947,7 +947,7 @@ static ssize_t ap_domain_store(struct bus_type *bus, ap_domain_index = domain; spin_unlock_bh(&ap_domain_lock); - AP_DBF(DBF_INFO, "stored new default domain=%d\n", domain); + AP_DBF_INFO("stored new default domain=%d\n", domain); return count; } @@ -1208,8 +1208,8 @@ static void ap_select_domain(void) } if (dom <= ap_max_domain_id) { ap_domain_index = dom; - AP_DBF(DBF_DEBUG, "%s new default domain is %d\n", - __func__, ap_domain_index); + AP_DBF_INFO("%s new default domain is %d\n", + __func__, ap_domain_index); } out: spin_unlock_bh(&ap_domain_lock); @@ -1225,8 +1225,11 @@ static int ap_get_compatible_type(ap_qid_t qid, int rawtype, unsigned int func) int comp_type = 0; /* < CEX2A is not supported */ - if (rawtype < AP_DEVICE_TYPE_CEX2A) + if (rawtype < AP_DEVICE_TYPE_CEX2A) { + AP_DBF_WARN("get_comp_type queue=%02x.%04x unsupported type %d\n", + AP_QID_CARD(qid), AP_QID_QUEUE(qid), rawtype); return 0; + } /* up to CEX7 known and fully supported */ if (rawtype <= AP_DEVICE_TYPE_CEX7) return rawtype; @@ -1248,11 +1251,12 @@ static int ap_get_compatible_type(ap_qid_t qid, int rawtype, unsigned int func) comp_type = apinfo.cat; } if (!comp_type) - AP_DBF(DBF_WARN, "queue=%02x.%04x unable to map type %d\n", - AP_QID_CARD(qid), AP_QID_QUEUE(qid), rawtype); + AP_DBF_WARN("get_comp_type queue=%02x.%04x unable to map type %d\n", + AP_QID_CARD(qid), AP_QID_QUEUE(qid), rawtype); else if (comp_type != rawtype) - AP_DBF(DBF_INFO, "queue=%02x.%04x map type %d to %d\n", - AP_QID_CARD(qid), AP_QID_QUEUE(qid), rawtype, comp_type); + AP_DBF_INFO("get_comp_type queue=%02x.%04x map type %d to %d\n", + AP_QID_CARD(qid), AP_QID_QUEUE(qid), + rawtype, comp_type); return comp_type; } @@ -1333,11 +1337,11 @@ static void _ap_scan_bus_adapter(int id) broken = true; } else if (ac->raw_hwtype != type) { /* card type has changed */ - AP_DBF(DBF_INFO, "card=%02x type changed.\n", id); + AP_DBF_INFO("card=%02x type changed.\n", id); broken = true; } else if (ac->functions != func) { /* card functions have changed */ - AP_DBF(DBF_INFO, "card=%02x functions changed.\n", id); + AP_DBF_INFO("card=%02x functions changed.\n", id); broken = true; } if (broken) { @@ -1385,9 +1389,8 @@ static void _ap_scan_bus_adapter(int id) } if (broken) { /* Remove broken device */ - AP_DBF(DBF_DEBUG, - "removing broken queue=%02x.%04x\n", - id, dom); + AP_DBF_DBG("removing broken queue=%02x.%04x\n", + id, dom); device_unregister(dev); } put_device(dev); @@ -1448,7 +1451,7 @@ static void ap_scan_bus(struct work_struct *unused) ap_fetch_qci_info(ap_qci_info); ap_select_domain(); - AP_DBF(DBF_DEBUG, "%s running\n", __func__); + AP_DBF_DBG("%s running\n", __func__); /* loop over all possible adapters */ for (id = 0; id < AP_DEVICES; id++) @@ -1463,9 +1466,8 @@ static void ap_scan_bus(struct work_struct *unused) if (dev) put_device(dev); else - AP_DBF(DBF_INFO, - "no queue device with default domain %d available\n", - ap_domain_index); + AP_DBF_INFO("no queue device with default domain %d available\n", + ap_domain_index); } mod_timer(&ap_config_timer, jiffies + ap_config_time * HZ); diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h index 2d4558b5abaf..0b66e8866a2c 100644 --- a/drivers/s390/crypto/ap_bus.h +++ b/drivers/s390/crypto/ap_bus.h @@ -190,6 +190,7 @@ struct ap_queue { struct list_head requestq; /* List of message yet to be sent. */ struct ap_message *reply; /* Per device reply message. */ enum ap_sm_state sm_state; /* ap queue state machine state */ + int last_err_rc; /* last error state response code */ }; #define to_ap_queue(x) container_of((x), struct ap_queue, ap_dev.device) diff --git a/drivers/s390/crypto/ap_debug.h b/drivers/s390/crypto/ap_debug.h index dc675eb5aef6..34b0350d0b1a 100644 --- a/drivers/s390/crypto/ap_debug.h +++ b/drivers/s390/crypto/ap_debug.h @@ -20,6 +20,14 @@ #define AP_DBF(...) \ debug_sprintf_event(ap_dbf_info, ##__VA_ARGS__) +#define AP_DBF_ERR(...) \ + debug_sprintf_event(ap_dbf_info, DBF_ERR, ##__VA_ARGS__) +#define AP_DBF_WARN(...) \ + debug_sprintf_event(ap_dbf_info, DBF_WARN, ##__VA_ARGS__) +#define AP_DBF_INFO(...) \ + debug_sprintf_event(ap_dbf_info, DBF_INFO, ##__VA_ARGS__) +#define AP_DBF_DBG(...) \ + debug_sprintf_event(ap_dbf_info, DBF_DEBUG, ##__VA_ARGS__) extern debug_info_t *ap_dbf_info; diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c index e7ecbcc18db3..69ea3d2c20ae 100644 --- a/drivers/s390/crypto/ap_queue.c +++ b/drivers/s390/crypto/ap_queue.c @@ -196,6 +196,10 @@ static enum ap_sm_wait ap_sm_read(struct ap_queue *aq) return AP_SM_WAIT_NONE; default: aq->dev_state = AP_DEV_STATE_ERROR; + aq->last_err_rc = status.response_code; + AP_DBF_WARN("%s RC 0x%02hhx on 0x%02x.%04x -> AP_DEV_STATE_ERROR\n", + __func__, status.response_code, + AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid)); return AP_SM_WAIT_NONE; } } @@ -246,6 +250,10 @@ static enum ap_sm_wait ap_sm_write(struct ap_queue *aq) return AP_SM_WAIT_AGAIN; default: aq->dev_state = AP_DEV_STATE_ERROR; + aq->last_err_rc = status.response_code; + AP_DBF_WARN("%s RC 0x%02hhx on 0x%02x.%04x -> AP_DEV_STATE_ERROR\n", + __func__, status.response_code, + AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid)); return AP_SM_WAIT_NONE; } } @@ -285,6 +293,10 @@ static enum ap_sm_wait ap_sm_reset(struct ap_queue *aq) case AP_RESPONSE_CHECKSTOPPED: default: aq->dev_state = AP_DEV_STATE_ERROR; + aq->last_err_rc = status.response_code; + AP_DBF_WARN("%s RC 0x%02hhx on 0x%02x.%04x -> AP_DEV_STATE_ERROR\n", + __func__, status.response_code, + AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid)); return AP_SM_WAIT_NONE; } } @@ -324,6 +336,10 @@ static enum ap_sm_wait ap_sm_reset_wait(struct ap_queue *aq) case AP_RESPONSE_CHECKSTOPPED: default: aq->dev_state = AP_DEV_STATE_ERROR; + aq->last_err_rc = status.response_code; + AP_DBF_WARN("%s RC 0x%02hhx on 0x%02x.%04x -> AP_DEV_STATE_ERROR\n", + __func__, status.response_code, + AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid)); return AP_SM_WAIT_NONE; } } @@ -361,6 +377,10 @@ static enum ap_sm_wait ap_sm_setirq_wait(struct ap_queue *aq) return AP_SM_WAIT_TIMEOUT; default: aq->dev_state = AP_DEV_STATE_ERROR; + aq->last_err_rc = status.response_code; + AP_DBF_WARN("%s RC 0x%02hhx on 0x%02x.%04x -> AP_DEV_STATE_ERROR\n", + __func__, status.response_code, + AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid)); return AP_SM_WAIT_NONE; } } @@ -605,6 +625,49 @@ static ssize_t states_show(struct device *dev, return rc; } static DEVICE_ATTR_RO(states); + +static ssize_t last_err_rc_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct ap_queue *aq = to_ap_queue(dev); + int rc; + + spin_lock_bh(&aq->lock); + rc = aq->last_err_rc; + spin_unlock_bh(&aq->lock); + + switch (rc) { + case AP_RESPONSE_NORMAL: + return scnprintf(buf, PAGE_SIZE, "NORMAL\n"); + case AP_RESPONSE_Q_NOT_AVAIL: + return scnprintf(buf, PAGE_SIZE, "Q_NOT_AVAIL\n"); + case AP_RESPONSE_RESET_IN_PROGRESS: + return scnprintf(buf, PAGE_SIZE, "RESET_IN_PROGRESS\n"); + case AP_RESPONSE_DECONFIGURED: + return scnprintf(buf, PAGE_SIZE, "DECONFIGURED\n"); + case AP_RESPONSE_CHECKSTOPPED: + return scnprintf(buf, PAGE_SIZE, "CHECKSTOPPED\n"); + case AP_RESPONSE_BUSY: + return scnprintf(buf, PAGE_SIZE, "BUSY\n"); + case AP_RESPONSE_INVALID_ADDRESS: + return scnprintf(buf, PAGE_SIZE, "INVALID_ADDRESS\n"); + case AP_RESPONSE_OTHERWISE_CHANGED: + return scnprintf(buf, PAGE_SIZE, "OTHERWISE_CHANGED\n"); + case AP_RESPONSE_Q_FULL: + return scnprintf(buf, PAGE_SIZE, "Q_FULL/NO_PENDING_REPLY\n"); + case AP_RESPONSE_INDEX_TOO_BIG: + return scnprintf(buf, PAGE_SIZE, "INDEX_TOO_BIG\n"); + case AP_RESPONSE_NO_FIRST_PART: + return scnprintf(buf, PAGE_SIZE, "NO_FIRST_PART\n"); + case AP_RESPONSE_MESSAGE_TOO_BIG: + return scnprintf(buf, PAGE_SIZE, "MESSAGE_TOO_BIG\n"); + case AP_RESPONSE_REQ_FAC_NOT_INST: + return scnprintf(buf, PAGE_SIZE, "REQ_FAC_NOT_INST\n"); + default: + return scnprintf(buf, PAGE_SIZE, "response code %d\n", rc); + } +} +static DEVICE_ATTR_RO(last_err_rc); #endif static struct attribute *ap_queue_dev_attrs[] = { @@ -615,6 +678,7 @@ static struct attribute *ap_queue_dev_attrs[] = { &dev_attr_interrupt.attr, #ifdef CONFIG_ZCRYPT_DEBUG &dev_attr_states.attr, + &dev_attr_last_err_rc.attr, #endif NULL }; From 4f2fcccdb547b09a4532c705078811e672fb9235 Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Thu, 2 Jul 2020 16:57:00 +0200 Subject: [PATCH 361/645] s390/ap: add card/queue deconfig state This patch adds a new config state to the ap card and queue devices. This state reflects the response code 0x03 "AP deconfigured" on TQAP invocation and is tracked with every ap bus scan. Together with this new state now a card/queue device which is 'deconfigured' is not disposed any more. However, for backward compatibility the online state now needs to take this state into account. So a card/queue is offline when the device is not configured. Furthermore a device can't get switched from offline to online state when not configured. The config state is shown in sysfs at /sys/devices/ap/cardxx/config for the card and /sys/devices/ap/cardxx/xx.yyyy/config for each queue within each card. It is a read-only attribute reflecting the negation of the 'AP deconfig' state as it is noted in the AP documents. Signed-off-by: Harald Freudenberger Signed-off-by: Vasily Gorbik --- drivers/s390/crypto/ap_bus.c | 372 +++++++++++++++++++---------- drivers/s390/crypto/ap_bus.h | 2 + drivers/s390/crypto/ap_card.c | 11 + drivers/s390/crypto/ap_queue.c | 15 ++ drivers/s390/crypto/zcrypt_api.c | 46 ++-- drivers/s390/crypto/zcrypt_card.c | 12 +- drivers/s390/crypto/zcrypt_queue.c | 11 +- 7 files changed, 323 insertions(+), 146 deletions(-) diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index 6d61e89c5984..485cbfcbf06e 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -307,7 +307,7 @@ EXPORT_SYMBOL(ap_test_config_ctrl_domain); * false otherwise. */ static bool ap_queue_info(ap_qid_t qid, int *q_type, - unsigned int *q_fac, int *q_depth) + unsigned int *q_fac, int *q_depth, bool *q_decfg) { struct ap_queue_status status; unsigned long info = 0; @@ -322,6 +322,9 @@ static bool ap_queue_info(ap_qid_t qid, int *q_type, switch (status.response_code) { case AP_RESPONSE_NORMAL: case AP_RESPONSE_RESET_IN_PROGRESS: + case AP_RESPONSE_DECONFIGURED: + case AP_RESPONSE_CHECKSTOPPED: + case AP_RESPONSE_BUSY: /* * According to the architecture in all these cases the * info should be filled. All bits 0 is not possible as @@ -332,6 +335,7 @@ static bool ap_queue_info(ap_qid_t qid, int *q_type, *q_type = (int)((info >> 24) & 0xff); *q_fac = (unsigned int)(info >> 32); *q_depth = (int)(info & 0xff); + *q_decfg = status.response_code == AP_RESPONSE_DECONFIGURED; switch (*q_type) { /* For CEX2 and CEX3 the available functions * are not reflected by the facilities bits. @@ -1290,154 +1294,278 @@ static int __match_queue_device_with_queue_id(struct device *dev, const void *da /* * Helper function for ap_scan_bus(). - * Does the scan bus job for the given adapter id. + * Remove card device and associated queue devices. */ -static void _ap_scan_bus_adapter(int id) +static inline void ap_scan_rm_card_dev_and_queue_devs(struct ap_card *ac) { - bool broken; + bus_for_each_dev(&ap_bus_type, NULL, + (void *)(long) ac->id, + __ap_queue_devices_with_id_unregister); + device_unregister(&ac->ap_dev.device); +} + +/* + * Helper function for ap_scan_bus(). + * Does the scan bus job for all the domains within + * a valid adapter given by an ap_card ptr. + */ +static inline void ap_scan_domains(struct ap_card *ac) +{ + bool decfg; ap_qid_t qid; unsigned int func; - struct ap_card *ac; struct device *dev; struct ap_queue *aq; - int rc, dom, depth, type, comp_type; - - /* check if there is a card device registered with this id */ - dev = bus_find_device(&ap_bus_type, NULL, - (void *)(long) id, - __match_card_device_with_id); - ac = dev ? to_ap_card(dev) : NULL; - if (!ap_test_config_card_id(id)) { - if (dev) { - /* Card device has been removed from configuration */ - bus_for_each_dev(&ap_bus_type, NULL, - (void *)(long) id, - __ap_queue_devices_with_id_unregister); - device_unregister(dev); - put_device(dev); - } - return; - } + int rc, dom, depth, type; /* - * This card id is enabled in the configuration. If we already have - * a card device with this id, check if type and functions are still - * the very same. Also verify that at least one queue is available. + * Go through the configuration for the domains and compare them + * to the existing queue devices. Also take care of the config + * and error state for the queue devices. */ - if (ac) { - /* find the first valid queue */ - for (dom = 0; dom < AP_DOMAINS; dom++) { - qid = AP_MKQID(id, dom); - if (ap_queue_info(qid, &type, &func, &depth)) - break; - } - broken = false; - if (dom >= AP_DOMAINS) { - /* no accessible queue on this card */ - broken = true; - } else if (ac->raw_hwtype != type) { - /* card type has changed */ - AP_DBF_INFO("card=%02x type changed.\n", id); - broken = true; - } else if (ac->functions != func) { - /* card functions have changed */ - AP_DBF_INFO("card=%02x functions changed.\n", id); - broken = true; - } - if (broken) { - /* unregister card device and associated queues */ - bus_for_each_dev(&ap_bus_type, NULL, - (void *)(long) id, - __ap_queue_devices_with_id_unregister); - device_unregister(dev); - put_device(dev); - /* go back if there is no valid queue on this card */ - if (dom >= AP_DOMAINS) - return; - ac = NULL; - } - } - /* - * Go through all possible queue ids. Check and maybe create or release - * queue devices for this card. If there exists no card device yet, - * create a card device also. - */ - for (dom = 0; dom < AP_DOMAINS; dom++) { - qid = AP_MKQID(id, dom); + for (dom = 0; dom <= ap_max_domain_id; dom++) { + qid = AP_MKQID(ac->id, dom); dev = bus_find_device(&ap_bus_type, NULL, (void *)(long) qid, __match_queue_device_with_qid); aq = dev ? to_ap_queue(dev) : NULL; if (!ap_test_config_usage_domain(dom)) { if (dev) { - /* Queue device exists but has been - * removed from configuration. - */ + AP_DBF_INFO("%s(%d,%d) not in config any more, rm queue device\n", + __func__, ac->id, dom); device_unregister(dev); put_device(dev); } continue; } - /* try to fetch infos about this queue */ - broken = !ap_queue_info(qid, &type, &func, &depth); - if (dev) { - if (!broken) { - spin_lock_bh(&aq->lock); - broken = aq->dev_state == AP_DEV_STATE_ERROR; - spin_unlock_bh(&aq->lock); - } - if (broken) { - /* Remove broken device */ - AP_DBF_DBG("removing broken queue=%02x.%04x\n", - id, dom); + /* domain is valid, get info from this APQN */ + if (!ap_queue_info(qid, &type, &func, &depth, &decfg)) { + if (aq) { + AP_DBF_INFO( + "%s(%d,%d) ap_queue_info() not successful, rm queue device\n", + __func__, ac->id, dom); device_unregister(dev); + put_device(dev); } - put_device(dev); continue; } - if (broken) - continue; - /* a new queue device is needed, check out comp type */ - comp_type = ap_get_compatible_type(qid, type, func); - if (!comp_type) - continue; - /* maybe a card device needs to be created first */ - if (!ac) { - ac = ap_card_create(id, depth, type, comp_type, func); - if (!ac) + /* if no queue device exists, create a new one */ + if (!aq) { + aq = ap_queue_create(qid, ac->ap_dev.device_type); + if (!aq) { + AP_DBF_WARN("%s(%d,%d) ap_queue_create() failed\n", + __func__, ac->id, dom); continue; - ac->ap_dev.device.bus = &ap_bus_type; - ac->ap_dev.device.parent = ap_root_device; - dev_set_name(&ac->ap_dev.device, "card%02x", id); - /* Register card device with AP bus */ - rc = device_register(&ac->ap_dev.device); - if (rc) { - put_device(&ac->ap_dev.device); - ac = NULL; - break; } - /* get it and thus adjust reference counter */ - get_device(&ac->ap_dev.device); + aq->card = ac; + aq->config = !decfg; + dev = &aq->ap_dev.device; + dev->bus = &ap_bus_type; + dev->parent = &ac->ap_dev.device; + dev_set_name(dev, "%02x.%04x", ac->id, dom); + /* register queue device */ + rc = device_register(dev); + if (rc) { + AP_DBF_WARN("%s(%d,%d) device_register() failed\n", + __func__, ac->id, dom); + goto put_dev_and_continue; + } + if (decfg) + AP_DBF_INFO("%s(%d,%d) new (decfg) queue device created\n", + __func__, ac->id, dom); + else + AP_DBF_INFO("%s(%d,%d) new queue device created\n", + __func__, ac->id, dom); + goto put_dev_and_continue; } - /* now create the new queue device */ - aq = ap_queue_create(qid, comp_type); - if (!aq) - continue; - aq->card = ac; - aq->ap_dev.device.bus = &ap_bus_type; - aq->ap_dev.device.parent = &ac->ap_dev.device; - dev_set_name(&aq->ap_dev.device, "%02x.%04x", id, dom); - /* Register queue device */ - rc = device_register(&aq->ap_dev.device); - if (rc) { - put_device(&aq->ap_dev.device); - continue; + /* Check config state on the already existing queue device */ + spin_lock_bh(&aq->lock); + if (decfg && aq->config) { + /* config off this queue device */ + aq->config = false; + if (aq->dev_state > AP_DEV_STATE_UNINITIATED) { + aq->dev_state = AP_DEV_STATE_ERROR; + aq->last_err_rc = AP_RESPONSE_DECONFIGURED; + } + spin_unlock_bh(&aq->lock); + AP_DBF_INFO("%s(%d,%d) queue device config off\n", + __func__, ac->id, dom); + /* 'receive' pending messages with -EAGAIN */ + ap_flush_queue(aq); + goto put_dev_and_continue; } - } /* end domain loop */ + if (!decfg && !aq->config) { + /* config on this queue device */ + aq->config = true; + if (aq->dev_state > AP_DEV_STATE_UNINITIATED) { + aq->dev_state = AP_DEV_STATE_OPERATING; + aq->sm_state = AP_SM_STATE_RESET_START; + } + spin_unlock_bh(&aq->lock); + AP_DBF_INFO("%s(%d,%d) queue device config on\n", + __func__, ac->id, dom); + goto put_dev_and_continue; + } + /* handle other error states */ + if (!decfg && aq->dev_state == AP_DEV_STATE_ERROR) { + spin_unlock_bh(&aq->lock); + /* 'receive' pending messages with -EAGAIN */ + ap_flush_queue(aq); + /* re-init (with reset) the queue device */ + ap_queue_init_state(aq); + AP_DBF_INFO("%s(%d,%d) queue device reinit enforced\n", + __func__, ac->id, dom); + goto put_dev_and_continue; + } + spin_unlock_bh(&aq->lock); +put_dev_and_continue: + put_device(dev); + } +} - if (ac) - put_device(&ac->ap_dev.device); +/* + * Helper function for ap_scan_bus(). + * Does the scan bus job for the given adapter id. + */ +static inline void ap_scan_adapter(int ap) +{ + bool decfg; + ap_qid_t qid; + unsigned int func; + struct device *dev; + struct ap_card *ac; + int rc, dom, depth, type, comp_type; + + /* Is there currently a card device for this adapter ? */ + dev = bus_find_device(&ap_bus_type, NULL, + (void *)(long) ap, + __match_card_device_with_id); + ac = dev ? to_ap_card(dev) : NULL; + + /* Adapter not in configuration ? */ + if (!ap_test_config_card_id(ap)) { + if (ac) { + AP_DBF_INFO("%s(%d) ap not in config any more, rm card and queue devices\n", + __func__, ap); + ap_scan_rm_card_dev_and_queue_devs(ac); + put_device(dev); + } + return; + } + + /* + * Adapter ap is valid in the current configuration. So do some checks: + * If no card device exists, build one. If a card device exists, check + * for type and functions changed. For all this we need to find a valid + * APQN first. + */ + + for (dom = 0; dom <= ap_max_domain_id; dom++) + if (ap_test_config_usage_domain(dom)) { + qid = AP_MKQID(ap, dom); + if (ap_queue_info(qid, &type, &func, &depth, &decfg)) + break; + } + if (dom > ap_max_domain_id) { + /* Could not find a valid APQN for this adapter */ + if (ac) { + AP_DBF_INFO( + "%s(%d) no type info (no APQN found), rm card and queue devices\n", + __func__, ap); + ap_scan_rm_card_dev_and_queue_devs(ac); + put_device(dev); + } else { + AP_DBF_DBG("%s(%d) no type info (no APQN found), ignored\n", + __func__, ap); + } + return; + } + if (!type) { + /* No apdater type info available, an unusable adapter */ + if (ac) { + AP_DBF_INFO("%s(%d) no valid type (0) info, rm card and queue devices\n", + __func__, ap); + ap_scan_rm_card_dev_and_queue_devs(ac); + put_device(dev); + } else { + AP_DBF_DBG("%s(%d) no valid type (0) info, ignored\n", + __func__, ap); + } + return; + } + + if (ac) { + /* Check APQN against existing card device for changes */ + if (ac->raw_hwtype != type) { + AP_DBF_INFO("%s(%d) hwtype %d changed, rm card and queue devices\n", + __func__, ap, type); + ap_scan_rm_card_dev_and_queue_devs(ac); + put_device(dev); + ac = NULL; + } else if (ac->functions != func) { + AP_DBF_INFO("%s(%d) functions 0x%08x changed, rm card and queue devices\n", + __func__, ap, type); + ap_scan_rm_card_dev_and_queue_devs(ac); + put_device(dev); + ac = NULL; + } else { + if (decfg && ac->config) { + ac->config = false; + AP_DBF_INFO("%s(%d) card device config off\n", + __func__, ap); + + } + if (!decfg && !ac->config) { + ac->config = true; + AP_DBF_INFO("%s(%d) card device config on\n", + __func__, ap); + } + } + } + + if (!ac) { + /* Build a new card device */ + comp_type = ap_get_compatible_type(qid, type, func); + if (!comp_type) { + AP_DBF_WARN("%s(%d) type %d, can't get compatibility type\n", + __func__, ap, type); + return; + } + ac = ap_card_create(ap, depth, type, comp_type, func); + if (!ac) { + AP_DBF_WARN("%s(%d) ap_card_create() failed\n", + __func__, ap); + return; + } + ac->config = !decfg; + dev = &ac->ap_dev.device; + dev->bus = &ap_bus_type; + dev->parent = ap_root_device; + dev_set_name(dev, "card%02x", ap); + /* Register the new card device with AP bus */ + rc = device_register(dev); + if (rc) { + AP_DBF_WARN("%s(%d) device_register() failed\n", + __func__, ap); + put_device(dev); + return; + } + /* get it and thus adjust reference counter */ + get_device(dev); + if (decfg) + AP_DBF_INFO("%s(%d) new (decfg) card device type=%d func=0x%08x created\n", + __func__, ap, type, func); + else + AP_DBF_INFO("%s(%d) new card device type=%d func=0x%08x created\n", + __func__, ap, type, func); + } + + /* Verify the domains and the queue devices for this card */ + ap_scan_domains(ac); + + /* release the card device */ + put_device(&ac->ap_dev.device); } /** @@ -1446,7 +1574,7 @@ static void _ap_scan_bus_adapter(int id) */ static void ap_scan_bus(struct work_struct *unused) { - int id; + int ap; ap_fetch_qci_info(ap_qci_info); ap_select_domain(); @@ -1454,8 +1582,8 @@ static void ap_scan_bus(struct work_struct *unused) AP_DBF_DBG("%s running\n", __func__); /* loop over all possible adapters */ - for (id = 0; id < AP_DEVICES; id++) - _ap_scan_bus_adapter(id); + for (ap = 0; ap <= ap_max_adapter_id; ap++) + ap_scan_adapter(ap); /* check if there is at least one queue available with default domain */ if (ap_domain_index >= 0) { diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h index 0b66e8866a2c..56c8bed7b6a1 100644 --- a/drivers/s390/crypto/ap_bus.h +++ b/drivers/s390/crypto/ap_bus.h @@ -166,6 +166,7 @@ struct ap_card { unsigned int functions; /* AP device function bitfield. */ int queue_depth; /* AP queue depth.*/ int id; /* AP card number. */ + bool config; /* configured state */ atomic64_t total_request_count; /* # requests ever for this AP device.*/ }; @@ -178,6 +179,7 @@ struct ap_queue { spinlock_t lock; /* Per device lock. */ void *private; /* ap driver private pointer. */ enum ap_dev_state dev_state; /* queue device state */ + bool config; /* configured state */ ap_qid_t qid; /* AP queue id. */ int interrupt; /* indicate if interrupts are enabled */ int queue_count; /* # messages currently on AP queue. */ diff --git a/drivers/s390/crypto/ap_card.c b/drivers/s390/crypto/ap_card.c index 6588713319ba..bf1e964b0048 100644 --- a/drivers/s390/crypto/ap_card.c +++ b/drivers/s390/crypto/ap_card.c @@ -139,6 +139,16 @@ static ssize_t modalias_show(struct device *dev, static DEVICE_ATTR_RO(modalias); +static ssize_t config_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct ap_card *ac = to_ap_card(dev); + + return scnprintf(buf, PAGE_SIZE, "%d\n", ac->config ? 1 : 0); +} + +static DEVICE_ATTR_RO(config); + static struct attribute *ap_card_dev_attrs[] = { &dev_attr_hwtype.attr, &dev_attr_raw_hwtype.attr, @@ -148,6 +158,7 @@ static struct attribute *ap_card_dev_attrs[] = { &dev_attr_requestq_count.attr, &dev_attr_pendingq_count.attr, &dev_attr_modalias.attr, + &dev_attr_config.attr, NULL }; diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c index 69ea3d2c20ae..5523338ca65d 100644 --- a/drivers/s390/crypto/ap_queue.c +++ b/drivers/s390/crypto/ap_queue.c @@ -563,6 +563,20 @@ static ssize_t interrupt_show(struct device *dev, static DEVICE_ATTR_RO(interrupt); +static ssize_t config_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct ap_queue *aq = to_ap_queue(dev); + int rc; + + spin_lock_bh(&aq->lock); + rc = scnprintf(buf, PAGE_SIZE, "%d\n", aq->config ? 1 : 0); + spin_unlock_bh(&aq->lock); + return rc; +} + +static DEVICE_ATTR_RO(config); + #ifdef CONFIG_ZCRYPT_DEBUG static ssize_t states_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -676,6 +690,7 @@ static struct attribute *ap_queue_dev_attrs[] = { &dev_attr_pendingq_count.attr, &dev_attr_reset.attr, &dev_attr_interrupt.attr, + &dev_attr_config.attr, #ifdef CONFIG_ZCRYPT_DEBUG &dev_attr_states.attr, &dev_attr_last_err_rc.attr, diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c index 223e1c233278..ab18e847cee7 100644 --- a/drivers/s390/crypto/zcrypt_api.c +++ b/drivers/s390/crypto/zcrypt_api.c @@ -663,8 +663,9 @@ static long zcrypt_rsa_modexpo(struct ap_perms *perms, pref_zq = NULL; spin_lock(&zcrypt_list_lock); for_each_zcrypt_card(zc) { - /* Check for online accelarator and CCA cards */ - if (!zc->online || !(zc->card->functions & 0x18000000)) + /* Check for useable accelarator or CCA card */ + if (!zc->online || !zc->card->config || + !(zc->card->functions & 0x18000000)) continue; /* Check for size limits */ if (zc->min_mod_size > mex->inputdatalength || @@ -682,8 +683,9 @@ static long zcrypt_rsa_modexpo(struct ap_perms *perms, if (!zcrypt_card_compare(zc, pref_zc, wgt + cpen, pref_wgt)) continue; for_each_zcrypt_queue(zq, zc) { - /* check if device is online and eligible */ - if (!zq->online || !zq->ops->rsa_modexpo) + /* check if device is useable and eligible */ + if (!zq->online || !zq->ops->rsa_modexpo || + !zq->queue->config) continue; /* check if device node has admission for this queue */ if (!zcrypt_check_queue(perms, @@ -760,8 +762,9 @@ static long zcrypt_rsa_crt(struct ap_perms *perms, pref_zq = NULL; spin_lock(&zcrypt_list_lock); for_each_zcrypt_card(zc) { - /* Check for online accelarator and CCA cards */ - if (!zc->online || !(zc->card->functions & 0x18000000)) + /* Check for useable accelarator or CCA card */ + if (!zc->online || !zc->card->config || + !(zc->card->functions & 0x18000000)) continue; /* Check for size limits */ if (zc->min_mod_size > crt->inputdatalength || @@ -779,8 +782,9 @@ static long zcrypt_rsa_crt(struct ap_perms *perms, if (!zcrypt_card_compare(zc, pref_zc, wgt + cpen, pref_wgt)) continue; for_each_zcrypt_queue(zq, zc) { - /* check if device is online and eligible */ - if (!zq->online || !zq->ops->rsa_modexpo_crt) + /* check if device is useable and eligible */ + if (!zq->online || !zq->ops->rsa_modexpo_crt || + !zq->queue->config) continue; /* check if device node has admission for this queue */ if (!zcrypt_check_queue(perms, @@ -859,8 +863,9 @@ static long _zcrypt_send_cprb(bool userspace, struct ap_perms *perms, pref_zq = NULL; spin_lock(&zcrypt_list_lock); for_each_zcrypt_card(zc) { - /* Check for online CCA cards */ - if (!zc->online || !(zc->card->functions & 0x10000000)) + /* Check for useable CCA card */ + if (!zc->online || !zc->card->config || + !(zc->card->functions & 0x10000000)) continue; /* Check for user selected CCA card */ if (xcRB->user_defined != AUTOSELECT && @@ -878,9 +883,10 @@ static long _zcrypt_send_cprb(bool userspace, struct ap_perms *perms, if (!zcrypt_card_compare(zc, pref_zc, wgt + cpen, pref_wgt)) continue; for_each_zcrypt_queue(zq, zc) { - /* check if device is online and eligible */ + /* check for device useable and eligible */ if (!zq->online || !zq->ops->send_cprb || + !zq->queue->config || (tdom != AUTOSEL_DOM && tdom != AP_QID_QUEUE(zq->queue->qid))) continue; @@ -1012,8 +1018,9 @@ static long _zcrypt_send_ep11_cprb(bool userspace, struct ap_perms *perms, pref_zq = NULL; spin_lock(&zcrypt_list_lock); for_each_zcrypt_card(zc) { - /* Check for online EP11 cards */ - if (!zc->online || !(zc->card->functions & 0x04000000)) + /* Check for useable EP11 card */ + if (!zc->online || !zc->card->config || + !(zc->card->functions & 0x04000000)) continue; /* Check for user selected EP11 card */ if (targets && @@ -1031,9 +1038,10 @@ static long _zcrypt_send_ep11_cprb(bool userspace, struct ap_perms *perms, if (!zcrypt_card_compare(zc, pref_zc, wgt + cpen, pref_wgt)) continue; for_each_zcrypt_queue(zq, zc) { - /* check if device is online and eligible */ + /* check if device is useable and eligible */ if (!zq->online || !zq->ops->send_ep11_cprb || + !zq->queue->config || (targets && !is_desired_ep11_queue(zq->queue->qid, target_num, targets))) @@ -1110,16 +1118,18 @@ static long zcrypt_rng(char *buffer) pref_zq = NULL; spin_lock(&zcrypt_list_lock); for_each_zcrypt_card(zc) { - /* Check for online CCA cards */ - if (!zc->online || !(zc->card->functions & 0x10000000)) + /* Check for useable CCA card */ + if (!zc->online || !zc->card->config || + !(zc->card->functions & 0x10000000)) continue; /* get weight index of the card device */ wgt = zc->speed_rating[func_code]; if (!zcrypt_card_compare(zc, pref_zc, wgt, pref_wgt)) continue; for_each_zcrypt_queue(zq, zc) { - /* check if device is online and eligible */ - if (!zq->online || !zq->ops->rng) + /* check if device is useable and eligible */ + if (!zq->online || !zq->ops->rng || + !zq->queue->config) continue; if (!zcrypt_queue_compare(zq, pref_zq, wgt, pref_wgt)) continue; diff --git a/drivers/s390/crypto/zcrypt_card.c b/drivers/s390/crypto/zcrypt_card.c index c53cab4b0c9e..e342eb86acd1 100644 --- a/drivers/s390/crypto/zcrypt_card.c +++ b/drivers/s390/crypto/zcrypt_card.c @@ -50,22 +50,28 @@ static ssize_t online_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct zcrypt_card *zc = to_ap_card(dev)->private; + struct ap_card *ac = to_ap_card(dev); + struct zcrypt_card *zc = ac->private; + int online = ac->config && zc->online ? 1 : 0; - return scnprintf(buf, PAGE_SIZE, "%d\n", zc->online); + return scnprintf(buf, PAGE_SIZE, "%d\n", online); } static ssize_t online_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct zcrypt_card *zc = to_ap_card(dev)->private; + struct ap_card *ac = to_ap_card(dev); + struct zcrypt_card *zc = ac->private; struct zcrypt_queue *zq; int online, id; if (sscanf(buf, "%d\n", &online) != 1 || online < 0 || online > 1) return -EINVAL; + if (online && !ac->config) + return -ENODEV; + zc->online = online; id = zc->card->id; diff --git a/drivers/s390/crypto/zcrypt_queue.c b/drivers/s390/crypto/zcrypt_queue.c index 8bae6ad159a7..3c207066313c 100644 --- a/drivers/s390/crypto/zcrypt_queue.c +++ b/drivers/s390/crypto/zcrypt_queue.c @@ -40,22 +40,27 @@ static ssize_t online_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct zcrypt_queue *zq = to_ap_queue(dev)->private; + struct ap_queue *aq = to_ap_queue(dev); + struct zcrypt_queue *zq = aq->private; + int online = aq->config && zq->online ? 1 : 0; - return scnprintf(buf, PAGE_SIZE, "%d\n", zq->online); + return scnprintf(buf, PAGE_SIZE, "%d\n", online); } static ssize_t online_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct zcrypt_queue *zq = to_ap_queue(dev)->private; + struct ap_queue *aq = to_ap_queue(dev); + struct zcrypt_queue *zq = aq->private; struct zcrypt_card *zc = zq->zcard; int online; if (sscanf(buf, "%d\n", &online) != 1 || online < 0 || online > 1) return -EINVAL; + if (online && (!aq->config || !aq->card->config)) + return -ENODEV; if (online && !zc->online) return -EINVAL; zq->online = online; From 0671cc1048744c9a6f1c896baa85966a5abc42a0 Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Mon, 27 Jul 2020 14:34:57 +0200 Subject: [PATCH 362/645] s390/sclp: Add support for SCLP AP adapter config/deconfig Add support for AP bus adapter config and deconfig to the sclp core code. The code is statically build into the kernel when ZCRYPT is configured either as module or with static support. This is the base functionality for having configure/deconfigure support in the AP bus and card code. Another patch will exploit this soon. Signed-off-by: Harald Freudenberger Suggested-by: Pierre Morel Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/sclp.h | 2 ++ drivers/s390/char/Makefile | 2 ++ drivers/s390/char/sclp.h | 2 +- drivers/s390/char/sclp_ap.c | 63 ++++++++++++++++++++++++++++++++++++ 4 files changed, 68 insertions(+), 1 deletion(-) create mode 100644 drivers/s390/char/sclp_ap.c diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h index 90f34c7e2752..a7bdd128d85b 100644 --- a/arch/s390/include/asm/sclp.h +++ b/arch/s390/include/asm/sclp.h @@ -128,6 +128,8 @@ int sclp_chp_deconfigure(struct chp_id chpid); int sclp_chp_read_info(struct sclp_chp_info *info); int sclp_pci_configure(u32 fid); int sclp_pci_deconfigure(u32 fid); +int sclp_ap_configure(u32 apid); +int sclp_ap_deconfigure(u32 apid); int sclp_pci_report(struct zpci_report_error_header *report, u32 fh, u32 fid); int memcpy_hsa_kernel(void *dest, unsigned long src, size_t count); int memcpy_hsa_user(void __user *dest, unsigned long src, size_t count); diff --git a/drivers/s390/char/Makefile b/drivers/s390/char/Makefile index 845e12ac5954..c6fdb81a068a 100644 --- a/drivers/s390/char/Makefile +++ b/drivers/s390/char/Makefile @@ -34,6 +34,8 @@ obj-$(CONFIG_SCLP_VT220_TTY) += sclp_vt220.o obj-$(CONFIG_PCI) += sclp_pci.o +obj-$(subst m,y,$(CONFIG_ZCRYPT)) += sclp_ap.o + obj-$(CONFIG_VMLOGRDR) += vmlogrdr.o obj-$(CONFIG_VMCP) += vmcp.o diff --git a/drivers/s390/char/sclp.h b/drivers/s390/char/sclp.h index ccc2d759c575..69d9cde9ff5a 100644 --- a/drivers/s390/char/sclp.h +++ b/drivers/s390/char/sclp.h @@ -229,7 +229,7 @@ static inline void sclp_fill_core_info(struct sclp_core_info *info, #define SCLP_HAS_CPU_INFO (sclp.facilities & 0x0800000000000000ULL) #define SCLP_HAS_CPU_RECONFIG (sclp.facilities & 0x0400000000000000ULL) #define SCLP_HAS_PCI_RECONFIG (sclp.facilities & 0x0000000040000000ULL) - +#define SCLP_HAS_AP_RECONFIG (sclp.facilities & 0x0000000100000000ULL) struct gds_subvector { u8 length; diff --git a/drivers/s390/char/sclp_ap.c b/drivers/s390/char/sclp_ap.c new file mode 100644 index 000000000000..0dd1ca712795 --- /dev/null +++ b/drivers/s390/char/sclp_ap.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * s390 crypto adapter related sclp functions. + * + * Copyright IBM Corp. 2020 + */ +#define KMSG_COMPONENT "sclp_cmd" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + +#include +#include +#include +#include "sclp.h" + +#define SCLP_CMDW_CONFIGURE_AP 0x001f0001 +#define SCLP_CMDW_DECONFIGURE_AP 0x001e0001 + +struct ap_cfg_sccb { + struct sccb_header header; +} __packed; + +static int do_ap_configure(sclp_cmdw_t cmd, u32 apid) +{ + struct ap_cfg_sccb *sccb; + int rc; + + if (!SCLP_HAS_AP_RECONFIG) + return -EOPNOTSUPP; + + sccb = (struct ap_cfg_sccb *) get_zeroed_page(GFP_KERNEL | GFP_DMA); + if (!sccb) + return -ENOMEM; + + sccb->header.length = PAGE_SIZE; + cmd |= (apid & 0xFF) << 8; + rc = sclp_sync_request(cmd, sccb); + if (rc) + goto out; + switch (sccb->header.response_code) { + case 0x0020: case 0x0120: case 0x0440: case 0x0450: + break; + default: + pr_warn("configure AP adapter %u failed: cmd=0x%08x response=0x%04x\n", + apid, cmd, sccb->header.response_code); + rc = -EIO; + break; + } +out: + free_page((unsigned long) sccb); + return rc; +} + +int sclp_ap_configure(u32 apid) +{ + return do_ap_configure(SCLP_CMDW_CONFIGURE_AP, apid); +} +EXPORT_SYMBOL(sclp_ap_configure); + +int sclp_ap_deconfigure(u32 apid) +{ + return do_ap_configure(SCLP_CMDW_DECONFIGURE_AP, apid); +} +EXPORT_SYMBOL(sclp_ap_deconfigure); From 5caa2af97118308c79f29cc9876aec3ed504f9b0 Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Mon, 27 Jul 2020 14:49:34 +0200 Subject: [PATCH 363/645] s390/ap: Support AP card SCLP config and deconfig operations Support SCLP AP adapter config and deconfig operations: The sysfs deconfig attribute /sys/devices/ap/cardxx/deconfig for each AP card is now read-write. Writing in a '1' triggers a synchronous SCLP request to configure the adapter, writing in a '0' sends a synchronous SCLP deconfigure request. Signed-off-by: Harald Freudenberger Signed-off-by: Vasily Gorbik --- drivers/s390/crypto/ap_card.c | 25 ++++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) diff --git a/drivers/s390/crypto/ap_card.c b/drivers/s390/crypto/ap_card.c index bf1e964b0048..d98bdd28d23e 100644 --- a/drivers/s390/crypto/ap_card.c +++ b/drivers/s390/crypto/ap_card.c @@ -12,6 +12,7 @@ #include #include #include +#include #include "ap_bus.h" @@ -147,7 +148,29 @@ static ssize_t config_show(struct device *dev, return scnprintf(buf, PAGE_SIZE, "%d\n", ac->config ? 1 : 0); } -static DEVICE_ATTR_RO(config); +static ssize_t config_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + int rc = 0, cfg; + struct ap_card *ac = to_ap_card(dev); + + if (sscanf(buf, "%d\n", &cfg) != 1 || cfg < 0 || cfg > 1) + return -EINVAL; + + if (cfg && !ac->config) + rc = sclp_ap_configure(ac->id); + else if (!cfg && ac->config) + rc = sclp_ap_deconfigure(ac->id); + if (rc) + return rc; + + ac->config = cfg ? true : false; + + return count; +} + +static DEVICE_ATTR_RW(config); static struct attribute *ap_card_dev_attrs[] = { &dev_attr_hwtype.attr, From e0332629e33d1926c93348d918aaaf451ef9a16b Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Tue, 4 Aug 2020 09:27:47 +0200 Subject: [PATCH 364/645] s390/ap/zcrypt: revisit ap and zcrypt error handling Revisit the ap queue error handling: Based on discussions and evaluatios with the firmware folk here is now a rework of the response code handling for all the AP instructions. The idea is to distinguish between failures because of some kind of invalid request where a retry does not make any sense and a failure where another attempt to send the very same request may succeed. The first case is handled by returning EINVAL to the userspace application. The second case results in retries within the zcrypt API controlled by a per message retry counter. Revisit the zcrpyt error handling: Similar here, based on discussions with the firmware people here comes a rework of the handling of all the reply codes. Main point here is that there are only very few cases left, where a zcrypt device queue is switched to offline. It should never be the case that an AP reply message is 'unknown' to the device driver as it indicates a total mismatch between device driver and crypto card firmware. In all other cases, the code distinguishes between failure because of invalid message (see above - EINVAL) or failures of the infrastructure (see above - EAGAIN). Signed-off-by: Harald Freudenberger Signed-off-by: Vasily Gorbik --- drivers/s390/crypto/ap_bus.h | 1 + drivers/s390/crypto/ap_queue.c | 8 +-- drivers/s390/crypto/zcrypt_debug.h | 8 +++ drivers/s390/crypto/zcrypt_error.h | 88 +++++++++--------------- drivers/s390/crypto/zcrypt_msgtype50.c | 50 +++++++------- drivers/s390/crypto/zcrypt_msgtype6.c | 92 +++++++++++++------------- 6 files changed, 116 insertions(+), 131 deletions(-) diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h index 56c8bed7b6a1..03fd95b5a0e8 100644 --- a/drivers/s390/crypto/ap_bus.h +++ b/drivers/s390/crypto/ap_bus.h @@ -50,6 +50,7 @@ static inline int ap_test_bit(unsigned int *ptr, unsigned int nr) #define AP_RESPONSE_NO_FIRST_PART 0x13 #define AP_RESPONSE_MESSAGE_TOO_BIG 0x15 #define AP_RESPONSE_REQ_FAC_NOT_INST 0x16 +#define AP_RESPONSE_INVALID_DOMAIN 0x42 /* * Known device types diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c index 5523338ca65d..ada37f1c7ac7 100644 --- a/drivers/s390/crypto/ap_queue.c +++ b/drivers/s390/crypto/ap_queue.c @@ -241,6 +241,9 @@ static enum ap_sm_wait ap_sm_write(struct ap_queue *aq) case AP_RESPONSE_RESET_IN_PROGRESS: aq->sm_state = AP_SM_STATE_RESET_WAIT; return AP_SM_WAIT_TIMEOUT; + case AP_RESPONSE_INVALID_DOMAIN: + AP_DBF(DBF_WARN, "AP_RESPONSE_INVALID_DOMAIN on NQAP\n"); + fallthrough; case AP_RESPONSE_MESSAGE_TOO_BIG: case AP_RESPONSE_REQ_FAC_NOT_INST: list_del_init(&ap_msg->list); @@ -286,11 +289,6 @@ static enum ap_sm_wait ap_sm_reset(struct ap_queue *aq) aq->sm_state = AP_SM_STATE_RESET_WAIT; aq->interrupt = AP_INTR_DISABLED; return AP_SM_WAIT_TIMEOUT; - case AP_RESPONSE_BUSY: - return AP_SM_WAIT_TIMEOUT; - case AP_RESPONSE_Q_NOT_AVAIL: - case AP_RESPONSE_DECONFIGURED: - case AP_RESPONSE_CHECKSTOPPED: default: aq->dev_state = AP_DEV_STATE_ERROR; aq->last_err_rc = status.response_code; diff --git a/drivers/s390/crypto/zcrypt_debug.h b/drivers/s390/crypto/zcrypt_debug.h index 241dbb5f75bf..3225489a1c41 100644 --- a/drivers/s390/crypto/zcrypt_debug.h +++ b/drivers/s390/crypto/zcrypt_debug.h @@ -21,6 +21,14 @@ #define ZCRYPT_DBF(...) \ debug_sprintf_event(zcrypt_dbf_info, ##__VA_ARGS__) +#define ZCRYPT_DBF_ERR(...) \ + debug_sprintf_event(zcrypt_dbf_info, DBF_ERR, ##__VA_ARGS__) +#define ZCRYPT_DBF_WARN(...) \ + debug_sprintf_event(zcrypt_dbf_info, DBF_WARN, ##__VA_ARGS__) +#define ZCRYPT_DBF_INFO(...) \ + debug_sprintf_event(zcrypt_dbf_info, DBF_INFO, ##__VA_ARGS__) +#define ZCRYPT_DBF_DBG(...) \ + debug_sprintf_event(zcrypt_dbf_info, DBF_DEBUG, ##__VA_ARGS__) extern debug_info_t *zcrypt_dbf_info; diff --git a/drivers/s390/crypto/zcrypt_error.h b/drivers/s390/crypto/zcrypt_error.h index 54a04f8c38ef..39e626e3a379 100644 --- a/drivers/s390/crypto/zcrypt_error.h +++ b/drivers/s390/crypto/zcrypt_error.h @@ -52,7 +52,6 @@ struct error_hdr { #define REP82_ERROR_INVALID_COMMAND 0x30 #define REP82_ERROR_MALFORMED_MSG 0x40 #define REP82_ERROR_INVALID_SPECIAL_CMD 0x41 -#define REP82_ERROR_INVALID_DOMAIN_PRECHECK 0x42 #define REP82_ERROR_RESERVED_FIELDO 0x50 /* old value */ #define REP82_ERROR_WORD_ALIGNMENT 0x60 #define REP82_ERROR_MESSAGE_LENGTH 0x80 @@ -67,7 +66,6 @@ struct error_hdr { #define REP82_ERROR_ZERO_BUFFER_LEN 0xB0 #define REP88_ERROR_MODULE_FAILURE 0x10 - #define REP88_ERROR_MESSAGE_TYPE 0x20 #define REP88_ERROR_MESSAGE_MALFORMD 0x22 #define REP88_ERROR_MESSAGE_LENGTH 0x23 @@ -85,78 +83,56 @@ static inline int convert_error(struct zcrypt_queue *zq, int queue = AP_QID_QUEUE(zq->queue->qid); switch (ehdr->reply_code) { - case REP82_ERROR_OPERAND_INVALID: - case REP82_ERROR_OPERAND_SIZE: - case REP82_ERROR_EVEN_MOD_IN_OPND: - case REP88_ERROR_MESSAGE_MALFORMD: - case REP82_ERROR_INVALID_DOMAIN_PRECHECK: - case REP82_ERROR_INVALID_DOMAIN_PENDING: - case REP82_ERROR_INVALID_SPECIAL_CMD: - case REP82_ERROR_FILTERED_BY_HYPERVISOR: - // REP88_ERROR_INVALID_KEY // '82' CEX2A - // REP88_ERROR_OPERAND // '84' CEX2A - // REP88_ERROR_OPERAND_EVEN_MOD // '85' CEX2A - /* Invalid input data. */ + case REP82_ERROR_INVALID_MSG_LEN: /* 0x23 */ + case REP82_ERROR_RESERVD_FIELD: /* 0x24 */ + case REP82_ERROR_FORMAT_FIELD: /* 0x29 */ + case REP82_ERROR_MALFORMED_MSG: /* 0x40 */ + case REP82_ERROR_INVALID_SPECIAL_CMD: /* 0x41 */ + case REP82_ERROR_MESSAGE_LENGTH: /* 0x80 */ + case REP82_ERROR_OPERAND_INVALID: /* 0x82 */ + case REP82_ERROR_OPERAND_SIZE: /* 0x84 */ + case REP82_ERROR_EVEN_MOD_IN_OPND: /* 0x85 */ + case REP82_ERROR_INVALID_DOMAIN_PENDING: /* 0x8A */ + case REP82_ERROR_FILTERED_BY_HYPERVISOR: /* 0x8B */ + case REP82_ERROR_PACKET_TRUNCATED: /* 0xA0 */ + case REP88_ERROR_MESSAGE_MALFORMD: /* 0x22 */ + case REP88_ERROR_KEY_TYPE: /* 0x34 */ + /* RY indicates malformed request */ ZCRYPT_DBF(DBF_WARN, - "device=%02x.%04x reply=0x%02x => rc=EINVAL\n", + "dev=%02x.%04x RY=0x%02x => rc=EINVAL\n", card, queue, ehdr->reply_code); return -EINVAL; - case REP82_ERROR_MESSAGE_TYPE: - // REP88_ERROR_MESSAGE_TYPE // '20' CEX2A + case REP82_ERROR_MACHINE_FAILURE: /* 0x10 */ + case REP82_ERROR_MESSAGE_TYPE: /* 0x20 */ + case REP82_ERROR_TRANSPORT_FAIL: /* 0x90 */ /* - * To sent a message of the wrong type is a bug in the - * device driver. Send error msg, disable the device - * and then repeat the request. + * Msg to wrong type or card/infrastructure failure. + * Trigger rescan of the ap bus, trigger retry request. */ atomic_set(&zcrypt_rescan_req, 1); - zq->online = 0; - pr_err("Cryptographic device %02x.%04x failed and was set offline\n", - card, queue); - ZCRYPT_DBF(DBF_ERR, - "device=%02x.%04x reply=0x%02x => online=0 rc=EAGAIN\n", - card, queue, ehdr->reply_code); - return -EAGAIN; - case REP82_ERROR_TRANSPORT_FAIL: - /* Card or infrastructure failure, disable card */ - atomic_set(&zcrypt_rescan_req, 1); - zq->online = 0; - pr_err("Cryptographic device %02x.%04x failed and was set offline\n", - card, queue); /* For type 86 response show the apfs value (failure reason) */ - if (ehdr->type == TYPE86_RSP_CODE) { + if (ehdr->reply_code == REP82_ERROR_TRANSPORT_FAIL && + ehdr->type == TYPE86_RSP_CODE) { struct { struct type86_hdr hdr; struct type86_fmt2_ext fmt2; } __packed * head = reply->msg; unsigned int apfs = *((u32 *)head->fmt2.apfs); - ZCRYPT_DBF(DBF_ERR, - "device=%02x.%04x reply=0x%02x apfs=0x%x => online=0 rc=EAGAIN\n", - card, queue, apfs, ehdr->reply_code); + ZCRYPT_DBF(DBF_WARN, + "dev=%02x.%04x RY=0x%02x apfs=0x%x => bus rescan, rc=EAGAIN\n", + card, queue, ehdr->reply_code, apfs); } else - ZCRYPT_DBF(DBF_ERR, - "device=%02x.%04x reply=0x%02x => online=0 rc=EAGAIN\n", + ZCRYPT_DBF(DBF_WARN, + "dev=%02x.%04x RY=0x%02x => bus rescan, rc=EAGAIN\n", card, queue, ehdr->reply_code); return -EAGAIN; - case REP82_ERROR_MACHINE_FAILURE: - // REP88_ERROR_MODULE_FAILURE // '10' CEX2A - /* If a card fails disable it and repeat the request. */ - atomic_set(&zcrypt_rescan_req, 1); - zq->online = 0; - pr_err("Cryptographic device %02x.%04x failed and was set offline\n", - card, queue); - ZCRYPT_DBF(DBF_ERR, - "device=%02x.%04x reply=0x%02x => online=0 rc=EAGAIN\n", + default: + /* Assume request is valid and a retry will be worth it */ + ZCRYPT_DBF(DBF_WARN, + "dev=%02x.%04x RY=0x%02x => rc=EAGAIN\n", card, queue, ehdr->reply_code); return -EAGAIN; - default: - zq->online = 0; - pr_err("Cryptographic device %02x.%04x failed and was set offline\n", - card, queue); - ZCRYPT_DBF(DBF_ERR, - "device=%02x.%04x reply=0x%02x => online=0 rc=EAGAIN\n", - card, queue, ehdr->reply_code); - return -EAGAIN; /* repeat the request on a different device. */ } } diff --git a/drivers/s390/crypto/zcrypt_msgtype50.c b/drivers/s390/crypto/zcrypt_msgtype50.c index 349306c2f155..0f7f404ed858 100644 --- a/drivers/s390/crypto/zcrypt_msgtype50.c +++ b/drivers/s390/crypto/zcrypt_msgtype50.c @@ -356,15 +356,15 @@ static int convert_type80(struct zcrypt_queue *zq, if (t80h->len < sizeof(*t80h) + outputdatalength) { /* The result is too short, the CEXxA card may not do that.. */ zq->online = 0; - pr_err("Cryptographic device %02x.%04x failed and was set offline\n", + pr_err("Crypto dev=%02x.%04x code=0x%02x => online=0 rc=EAGAIN\n", AP_QID_CARD(zq->queue->qid), - AP_QID_QUEUE(zq->queue->qid)); - ZCRYPT_DBF(DBF_ERR, - "device=%02x.%04x code=0x%02x => online=0 rc=EAGAIN\n", - AP_QID_CARD(zq->queue->qid), - AP_QID_QUEUE(zq->queue->qid), - t80h->code); - return -EAGAIN; /* repeat the request on a different device. */ + AP_QID_QUEUE(zq->queue->qid), + t80h->code); + ZCRYPT_DBF_ERR("dev=%02x.%04x code=0x%02x => online=0 rc=EAGAIN\n", + AP_QID_CARD(zq->queue->qid), + AP_QID_QUEUE(zq->queue->qid), + t80h->code); + return -EAGAIN; } if (zq->zcard->user_space_type == ZCRYPT_CEX2A) BUG_ON(t80h->len > CEX2A_MAX_RESPONSE_SIZE); @@ -376,10 +376,10 @@ static int convert_type80(struct zcrypt_queue *zq, return 0; } -static int convert_response(struct zcrypt_queue *zq, - struct ap_message *reply, - char __user *outputdata, - unsigned int outputdatalength) +static int convert_response_cex2a(struct zcrypt_queue *zq, + struct ap_message *reply, + char __user *outputdata, + unsigned int outputdatalength) { /* Response type byte is the second byte in the response. */ unsigned char rtype = ((unsigned char *) reply->msg)[1]; @@ -393,15 +393,15 @@ static int convert_response(struct zcrypt_queue *zq, outputdata, outputdatalength); default: /* Unknown response type, this should NEVER EVER happen */ zq->online = 0; - pr_err("Cryptographic device %02x.%04x failed and was set offline\n", + pr_err("Crypto dev=%02x.%04x unknown response type 0x%02x => online=0 rc=EAGAIN\n", AP_QID_CARD(zq->queue->qid), - AP_QID_QUEUE(zq->queue->qid)); - ZCRYPT_DBF(DBF_ERR, - "device=%02x.%04x rtype=0x%02x => online=0 rc=EAGAIN\n", - AP_QID_CARD(zq->queue->qid), - AP_QID_QUEUE(zq->queue->qid), - (unsigned int) rtype); - return -EAGAIN; /* repeat the request on a different device. */ + AP_QID_QUEUE(zq->queue->qid), + (int) rtype); + ZCRYPT_DBF_ERR("dev=%02x.%04x unknown response type 0x%02x => online=0 rc=EAGAIN\n", + AP_QID_CARD(zq->queue->qid), + AP_QID_QUEUE(zq->queue->qid), + (int) rtype); + return -EAGAIN; } } @@ -478,8 +478,9 @@ static long zcrypt_cex2a_modexpo(struct zcrypt_queue *zq, if (rc == 0) { rc = ap_msg.rc; if (rc == 0) - rc = convert_response(zq, &ap_msg, mex->outputdata, - mex->outputdatalength); + rc = convert_response_cex2a(zq, &ap_msg, + mex->outputdata, + mex->outputdatalength); } else /* Signal pending. */ ap_cancel_message(zq->queue, &ap_msg); @@ -524,8 +525,9 @@ static long zcrypt_cex2a_modexpo_crt(struct zcrypt_queue *zq, if (rc == 0) { rc = ap_msg.rc; if (rc == 0) - rc = convert_response(zq, &ap_msg, crt->outputdata, - crt->outputdatalength); + rc = convert_response_cex2a(zq, &ap_msg, + crt->outputdata, + crt->outputdatalength); } else /* Signal pending. */ ap_cancel_message(zq->queue, &ap_msg); diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c index 51b9924753ee..30eaa7a7aede 100644 --- a/drivers/s390/crypto/zcrypt_msgtype6.c +++ b/drivers/s390/crypto/zcrypt_msgtype6.c @@ -650,23 +650,22 @@ static int convert_type86_ica(struct zcrypt_queue *zq, (service_rc == 8 && service_rs == 72) || (service_rc == 8 && service_rs == 770) || (service_rc == 12 && service_rs == 769)) { - ZCRYPT_DBF(DBF_DEBUG, - "device=%02x.%04x rc/rs=%d/%d => rc=EINVAL\n", - AP_QID_CARD(zq->queue->qid), - AP_QID_QUEUE(zq->queue->qid), - (int) service_rc, (int) service_rs); + ZCRYPT_DBF_WARN("dev=%02x.%04x rc/rs=%d/%d => rc=EINVAL\n", + AP_QID_CARD(zq->queue->qid), + AP_QID_QUEUE(zq->queue->qid), + (int) service_rc, (int) service_rs); return -EINVAL; } zq->online = 0; - pr_err("Cryptographic device %02x.%04x failed and was set offline\n", + pr_err("Crypto dev=%02x.%04x rc/rs=%d/%d online=0 rc=EAGAIN\n", AP_QID_CARD(zq->queue->qid), - AP_QID_QUEUE(zq->queue->qid)); - ZCRYPT_DBF(DBF_ERR, - "device=%02x.%04x rc/rs=%d/%d => online=0 rc=EAGAIN\n", - AP_QID_CARD(zq->queue->qid), - AP_QID_QUEUE(zq->queue->qid), - (int) service_rc, (int) service_rs); - return -EAGAIN; /* repeat the request on a different device. */ + AP_QID_QUEUE(zq->queue->qid), + (int) service_rc, (int) service_rs); + ZCRYPT_DBF_ERR("dev=%02x.%04x rc/rs=%d/%d => online=0 rc=EAGAIN\n", + AP_QID_CARD(zq->queue->qid), + AP_QID_QUEUE(zq->queue->qid), + (int) service_rc, (int) service_rs); + return -EAGAIN; } data = msg->text; reply_len = msg->length - 2; @@ -800,17 +799,18 @@ static int convert_response_ica(struct zcrypt_queue *zq, return convert_type86_ica(zq, reply, outputdata, outputdatalength); fallthrough; /* wrong cprb version is an unknown response */ - default: /* Unknown response type, this should NEVER EVER happen */ + default: + /* Unknown response type, this should NEVER EVER happen */ zq->online = 0; - pr_err("Cryptographic device %02x.%04x failed and was set offline\n", + pr_err("Crypto dev=%02x.%04x unknown response type 0x%02x => online=0 rc=EAGAIN\n", AP_QID_CARD(zq->queue->qid), - AP_QID_QUEUE(zq->queue->qid)); - ZCRYPT_DBF(DBF_ERR, - "device=%02x.%04x rtype=0x%02x => online=0 rc=EAGAIN\n", - AP_QID_CARD(zq->queue->qid), - AP_QID_QUEUE(zq->queue->qid), - (int) msg->hdr.type); - return -EAGAIN; /* repeat the request on a different device. */ + AP_QID_QUEUE(zq->queue->qid), + (int) msg->hdr.type); + ZCRYPT_DBF_ERR("dev=%02x.%04x unknown response type 0x%02x => online=0 rc=EAGAIN\n", + AP_QID_CARD(zq->queue->qid), + AP_QID_QUEUE(zq->queue->qid), + (int) msg->hdr.type); + return -EAGAIN; } } @@ -836,15 +836,15 @@ static int convert_response_xcrb(bool userspace, struct zcrypt_queue *zq, default: /* Unknown response type, this should NEVER EVER happen */ xcRB->status = 0x0008044DL; /* HDD_InvalidParm */ zq->online = 0; - pr_err("Cryptographic device %02x.%04x failed and was set offline\n", + pr_err("Crypto dev=%02x.%04x unknown response type 0x%02x => online=0 rc=EAGAIN\n", AP_QID_CARD(zq->queue->qid), - AP_QID_QUEUE(zq->queue->qid)); - ZCRYPT_DBF(DBF_ERR, - "device=%02x.%04x rtype=0x%02x => online=0 rc=EAGAIN\n", - AP_QID_CARD(zq->queue->qid), - AP_QID_QUEUE(zq->queue->qid), - (int) msg->hdr.type); - return -EAGAIN; /* repeat the request on a different device. */ + AP_QID_QUEUE(zq->queue->qid), + (int) msg->hdr.type); + ZCRYPT_DBF_ERR("dev=%02x.%04x unknown response type 0x%02x => online=0 rc=EAGAIN\n", + AP_QID_CARD(zq->queue->qid), + AP_QID_QUEUE(zq->queue->qid), + (int) msg->hdr.type); + return -EAGAIN; } } @@ -865,15 +865,15 @@ static int convert_response_ep11_xcrb(bool userspace, struct zcrypt_queue *zq, fallthrough; /* wrong cprb version is an unknown resp */ default: /* Unknown response type, this should NEVER EVER happen */ zq->online = 0; - pr_err("Cryptographic device %02x.%04x failed and was set offline\n", + pr_err("Crypto dev=%02x.%04x unknown response type 0x%02x => online=0 rc=EAGAIN\n", AP_QID_CARD(zq->queue->qid), - AP_QID_QUEUE(zq->queue->qid)); - ZCRYPT_DBF(DBF_ERR, - "device=%02x.%04x rtype=0x%02x => online=0 rc=EAGAIN\n", - AP_QID_CARD(zq->queue->qid), - AP_QID_QUEUE(zq->queue->qid), - (int) msg->hdr.type); - return -EAGAIN; /* repeat the request on a different device. */ + AP_QID_QUEUE(zq->queue->qid), + (int) msg->hdr.type); + ZCRYPT_DBF_ERR("dev=%02x.%04x unknown response type 0x%02x => online=0 rc=EAGAIN\n", + AP_QID_CARD(zq->queue->qid), + AP_QID_QUEUE(zq->queue->qid), + (int) msg->hdr.type); + return -EAGAIN; } } @@ -895,15 +895,15 @@ static int convert_response_rng(struct zcrypt_queue *zq, fallthrough; /* wrong cprb version is an unknown response */ default: /* Unknown response type, this should NEVER EVER happen */ zq->online = 0; - pr_err("Cryptographic device %02x.%04x failed and was set offline\n", + pr_err("Crypto dev=%02x.%04x unknown response type 0x%02x => online=0 rc=EAGAIN\n", AP_QID_CARD(zq->queue->qid), - AP_QID_QUEUE(zq->queue->qid)); - ZCRYPT_DBF(DBF_ERR, - "device=%02x.%04x rtype=0x%02x => online=0 rc=EAGAIN\n", - AP_QID_CARD(zq->queue->qid), - AP_QID_QUEUE(zq->queue->qid), - (int) msg->hdr.type); - return -EAGAIN; /* repeat the request on a different device. */ + AP_QID_QUEUE(zq->queue->qid), + (int) msg->hdr.type); + ZCRYPT_DBF_ERR("dev=%02x.%04x unknown response type 0x%02x => online=0 rc=EAGAIN\n", + AP_QID_CARD(zq->queue->qid), + AP_QID_QUEUE(zq->queue->qid), + (int) msg->hdr.type); + return -EAGAIN; } } From 3730f5300b450bc89306c3ab79c254e6039d9197 Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Sat, 26 Sep 2020 22:51:38 +0200 Subject: [PATCH 365/645] s390/zcrypt: move ap_msg param one level up the call chain Move the creating and disposal of the struct ap_message one level up the call chain. The ap message was constructed in the calling functions in msgtype50 and msgtype6 but only for the ica rsa messages. For CCA and EP11 CPRBs the ap message struct is created in the zcrypt api functions. This patch moves the construction of the ap message struct into the functions zcrypt_rsa_modexpo and zcrypt_rsa_crt. So now all the 4 zcrypt api functions zcrypt_rsa_modexpo, zcrypt_rsa_crt, zcrypt_send_cprb and zcrypt_send_ep11_cprb appear and act similar. There are no functional changes coming with this patch. However, the availability of the ap_message struct has advantages which will be needed by a follow up patch. Signed-off-by: Harald Freudenberger Signed-off-by: Vasily Gorbik --- drivers/s390/crypto/zcrypt_api.c | 12 ++++- drivers/s390/crypto/zcrypt_api.h | 6 ++- drivers/s390/crypto/zcrypt_msgtype50.c | 74 +++++++++++++------------- drivers/s390/crypto/zcrypt_msgtype6.c | 62 ++++++++++----------- 4 files changed, 82 insertions(+), 72 deletions(-) diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c index ab18e847cee7..d642be65a3a0 100644 --- a/drivers/s390/crypto/zcrypt_api.c +++ b/drivers/s390/crypto/zcrypt_api.c @@ -635,6 +635,7 @@ static long zcrypt_rsa_modexpo(struct ap_perms *perms, { struct zcrypt_card *zc, *pref_zc; struct zcrypt_queue *zq, *pref_zq; + struct ap_message ap_msg; unsigned int wgt = 0, pref_wgt = 0; unsigned int func_code; int cpen, qpen, qid = 0, rc = -ENODEV; @@ -642,6 +643,8 @@ static long zcrypt_rsa_modexpo(struct ap_perms *perms, trace_s390_zcrypt_req(mex, TP_ICARSAMODEXPO); + ap_init_message(&ap_msg); + if (mex->outputdatalength < mex->inputdatalength) { func_code = 0; rc = -EINVAL; @@ -712,13 +715,14 @@ static long zcrypt_rsa_modexpo(struct ap_perms *perms, } qid = pref_zq->queue->qid; - rc = pref_zq->ops->rsa_modexpo(pref_zq, mex); + rc = pref_zq->ops->rsa_modexpo(pref_zq, mex, &ap_msg); spin_lock(&zcrypt_list_lock); zcrypt_drop_queue(pref_zc, pref_zq, mod, wgt); spin_unlock(&zcrypt_list_lock); out: + ap_release_message(&ap_msg); if (tr) { tr->last_rc = rc; tr->last_qid = qid; @@ -734,6 +738,7 @@ static long zcrypt_rsa_crt(struct ap_perms *perms, { struct zcrypt_card *zc, *pref_zc; struct zcrypt_queue *zq, *pref_zq; + struct ap_message ap_msg; unsigned int wgt = 0, pref_wgt = 0; unsigned int func_code; int cpen, qpen, qid = 0, rc = -ENODEV; @@ -741,6 +746,8 @@ static long zcrypt_rsa_crt(struct ap_perms *perms, trace_s390_zcrypt_req(crt, TP_ICARSACRT); + ap_init_message(&ap_msg); + if (crt->outputdatalength < crt->inputdatalength) { func_code = 0; rc = -EINVAL; @@ -811,13 +818,14 @@ static long zcrypt_rsa_crt(struct ap_perms *perms, } qid = pref_zq->queue->qid; - rc = pref_zq->ops->rsa_modexpo_crt(pref_zq, crt); + rc = pref_zq->ops->rsa_modexpo_crt(pref_zq, crt, &ap_msg); spin_lock(&zcrypt_list_lock); zcrypt_drop_queue(pref_zc, pref_zq, mod, wgt); spin_unlock(&zcrypt_list_lock); out: + ap_release_message(&ap_msg); if (tr) { tr->last_rc = rc; tr->last_qid = qid; diff --git a/drivers/s390/crypto/zcrypt_api.h b/drivers/s390/crypto/zcrypt_api.h index 263ed1735431..03804f03b5d0 100644 --- a/drivers/s390/crypto/zcrypt_api.h +++ b/drivers/s390/crypto/zcrypt_api.h @@ -68,9 +68,11 @@ struct zcrypt_track { #define TRACK_AGAIN_QUEUE_WEIGHT_PENALTY 10000 struct zcrypt_ops { - long (*rsa_modexpo)(struct zcrypt_queue *, struct ica_rsa_modexpo *); + long (*rsa_modexpo)(struct zcrypt_queue *, struct ica_rsa_modexpo *, + struct ap_message *); long (*rsa_modexpo_crt)(struct zcrypt_queue *, - struct ica_rsa_modexpo_crt *); + struct ica_rsa_modexpo_crt *, + struct ap_message *); long (*send_cprb)(bool userspace, struct zcrypt_queue *, struct ica_xcRB *, struct ap_message *); long (*send_ep11_cprb)(bool userspace, struct zcrypt_queue *, struct ep11_urb *, diff --git a/drivers/s390/crypto/zcrypt_msgtype50.c b/drivers/s390/crypto/zcrypt_msgtype50.c index 0f7f404ed858..c543b5959509 100644 --- a/drivers/s390/crypto/zcrypt_msgtype50.c +++ b/drivers/s390/crypto/zcrypt_msgtype50.c @@ -450,42 +450,41 @@ static atomic_t zcrypt_step = ATOMIC_INIT(0); * @mex: pointer to the modexpo request buffer */ static long zcrypt_cex2a_modexpo(struct zcrypt_queue *zq, - struct ica_rsa_modexpo *mex) + struct ica_rsa_modexpo *mex, + struct ap_message *ap_msg) { - struct ap_message ap_msg; struct completion work; int rc; - ap_init_message(&ap_msg); if (zq->zcard->user_space_type == ZCRYPT_CEX2A) - ap_msg.msg = kmalloc(MSGTYPE50_CRB2_MAX_MSG_SIZE, GFP_KERNEL); + ap_msg->msg = kmalloc(MSGTYPE50_CRB2_MAX_MSG_SIZE, GFP_KERNEL); else - ap_msg.msg = kmalloc(MSGTYPE50_CRB3_MAX_MSG_SIZE, GFP_KERNEL); - if (!ap_msg.msg) + ap_msg->msg = kmalloc(MSGTYPE50_CRB3_MAX_MSG_SIZE, GFP_KERNEL); + if (!ap_msg->msg) return -ENOMEM; - ap_msg.receive = zcrypt_cex2a_receive; - ap_msg.psmid = (((unsigned long long) current->pid) << 32) + - atomic_inc_return(&zcrypt_step); - ap_msg.private = &work; - rc = ICAMEX_msg_to_type50MEX_msg(zq, &ap_msg, mex); + ap_msg->receive = zcrypt_cex2a_receive; + ap_msg->psmid = (((unsigned long long) current->pid) << 32) + + atomic_inc_return(&zcrypt_step); + ap_msg->private = &work; + rc = ICAMEX_msg_to_type50MEX_msg(zq, ap_msg, mex); if (rc) - goto out_free; + goto out; init_completion(&work); - rc = ap_queue_message(zq->queue, &ap_msg); + rc = ap_queue_message(zq->queue, ap_msg); if (rc) - goto out_free; + goto out; rc = wait_for_completion_interruptible(&work); if (rc == 0) { - rc = ap_msg.rc; + rc = ap_msg->rc; if (rc == 0) - rc = convert_response_cex2a(zq, &ap_msg, + rc = convert_response_cex2a(zq, ap_msg, mex->outputdata, mex->outputdatalength); } else /* Signal pending. */ - ap_cancel_message(zq->queue, &ap_msg); -out_free: - kfree(ap_msg.msg); + ap_cancel_message(zq->queue, ap_msg); +out: + ap_msg->private = NULL; return rc; } @@ -497,42 +496,41 @@ out_free: * @crt: pointer to the modexpoc_crt request buffer */ static long zcrypt_cex2a_modexpo_crt(struct zcrypt_queue *zq, - struct ica_rsa_modexpo_crt *crt) + struct ica_rsa_modexpo_crt *crt, + struct ap_message *ap_msg) { - struct ap_message ap_msg; struct completion work; int rc; - ap_init_message(&ap_msg); if (zq->zcard->user_space_type == ZCRYPT_CEX2A) - ap_msg.msg = kmalloc(MSGTYPE50_CRB2_MAX_MSG_SIZE, GFP_KERNEL); + ap_msg->msg = kmalloc(MSGTYPE50_CRB2_MAX_MSG_SIZE, GFP_KERNEL); else - ap_msg.msg = kmalloc(MSGTYPE50_CRB3_MAX_MSG_SIZE, GFP_KERNEL); - if (!ap_msg.msg) + ap_msg->msg = kmalloc(MSGTYPE50_CRB3_MAX_MSG_SIZE, GFP_KERNEL); + if (!ap_msg->msg) return -ENOMEM; - ap_msg.receive = zcrypt_cex2a_receive; - ap_msg.psmid = (((unsigned long long) current->pid) << 32) + - atomic_inc_return(&zcrypt_step); - ap_msg.private = &work; - rc = ICACRT_msg_to_type50CRT_msg(zq, &ap_msg, crt); + ap_msg->receive = zcrypt_cex2a_receive; + ap_msg->psmid = (((unsigned long long) current->pid) << 32) + + atomic_inc_return(&zcrypt_step); + ap_msg->private = &work; + rc = ICACRT_msg_to_type50CRT_msg(zq, ap_msg, crt); if (rc) - goto out_free; + goto out; init_completion(&work); - rc = ap_queue_message(zq->queue, &ap_msg); + rc = ap_queue_message(zq->queue, ap_msg); if (rc) - goto out_free; + goto out; rc = wait_for_completion_interruptible(&work); if (rc == 0) { - rc = ap_msg.rc; + rc = ap_msg->rc; if (rc == 0) - rc = convert_response_cex2a(zq, &ap_msg, + rc = convert_response_cex2a(zq, ap_msg, crt->outputdata, crt->outputdatalength); } else /* Signal pending. */ - ap_cancel_message(zq->queue, &ap_msg); -out_free: - kfree(ap_msg.msg); + ap_cancel_message(zq->queue, ap_msg); +out: + ap_msg->private = NULL; return rc; } diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c index 30eaa7a7aede..aab7f0692035 100644 --- a/drivers/s390/crypto/zcrypt_msgtype6.c +++ b/drivers/s390/crypto/zcrypt_msgtype6.c @@ -1007,41 +1007,42 @@ static atomic_t zcrypt_step = ATOMIC_INIT(0); * @mex: pointer to the modexpo request buffer */ static long zcrypt_msgtype6_modexpo(struct zcrypt_queue *zq, - struct ica_rsa_modexpo *mex) + struct ica_rsa_modexpo *mex, + struct ap_message *ap_msg) { - struct ap_message ap_msg; struct response_type resp_type = { .type = CEXXC_RESPONSE_TYPE_ICA, }; int rc; - ap_init_message(&ap_msg); - ap_msg.msg = (void *) get_zeroed_page(GFP_KERNEL); - if (!ap_msg.msg) + ap_msg->msg = (void *) get_zeroed_page(GFP_KERNEL); + if (!ap_msg->msg) return -ENOMEM; - ap_msg.receive = zcrypt_msgtype6_receive; - ap_msg.psmid = (((unsigned long long) current->pid) << 32) + - atomic_inc_return(&zcrypt_step); - ap_msg.private = &resp_type; - rc = ICAMEX_msg_to_type6MEX_msgX(zq, &ap_msg, mex); + ap_msg->receive = zcrypt_msgtype6_receive; + ap_msg->psmid = (((unsigned long long) current->pid) << 32) + + atomic_inc_return(&zcrypt_step); + ap_msg->private = &resp_type; + rc = ICAMEX_msg_to_type6MEX_msgX(zq, ap_msg, mex); if (rc) goto out_free; init_completion(&resp_type.work); - rc = ap_queue_message(zq->queue, &ap_msg); + rc = ap_queue_message(zq->queue, ap_msg); if (rc) goto out_free; rc = wait_for_completion_interruptible(&resp_type.work); if (rc == 0) { - rc = ap_msg.rc; + rc = ap_msg->rc; if (rc == 0) - rc = convert_response_ica(zq, &ap_msg, + rc = convert_response_ica(zq, ap_msg, mex->outputdata, mex->outputdatalength); } else /* Signal pending. */ - ap_cancel_message(zq->queue, &ap_msg); + ap_cancel_message(zq->queue, ap_msg); out_free: - free_page((unsigned long) ap_msg.msg); + free_page((unsigned long) ap_msg->msg); + ap_msg->private = NULL; + ap_msg->msg = NULL; return rc; } @@ -1053,42 +1054,43 @@ out_free: * @crt: pointer to the modexpoc_crt request buffer */ static long zcrypt_msgtype6_modexpo_crt(struct zcrypt_queue *zq, - struct ica_rsa_modexpo_crt *crt) + struct ica_rsa_modexpo_crt *crt, + struct ap_message *ap_msg) { - struct ap_message ap_msg; struct response_type resp_type = { .type = CEXXC_RESPONSE_TYPE_ICA, }; int rc; - ap_init_message(&ap_msg); - ap_msg.msg = (void *) get_zeroed_page(GFP_KERNEL); - if (!ap_msg.msg) + ap_msg->msg = (void *) get_zeroed_page(GFP_KERNEL); + if (!ap_msg->msg) return -ENOMEM; - ap_msg.receive = zcrypt_msgtype6_receive; - ap_msg.psmid = (((unsigned long long) current->pid) << 32) + - atomic_inc_return(&zcrypt_step); - ap_msg.private = &resp_type; - rc = ICACRT_msg_to_type6CRT_msgX(zq, &ap_msg, crt); + ap_msg->receive = zcrypt_msgtype6_receive; + ap_msg->psmid = (((unsigned long long) current->pid) << 32) + + atomic_inc_return(&zcrypt_step); + ap_msg->private = &resp_type; + rc = ICACRT_msg_to_type6CRT_msgX(zq, ap_msg, crt); if (rc) goto out_free; init_completion(&resp_type.work); - rc = ap_queue_message(zq->queue, &ap_msg); + rc = ap_queue_message(zq->queue, ap_msg); if (rc) goto out_free; rc = wait_for_completion_interruptible(&resp_type.work); if (rc == 0) { - rc = ap_msg.rc; + rc = ap_msg->rc; if (rc == 0) - rc = convert_response_ica(zq, &ap_msg, + rc = convert_response_ica(zq, ap_msg, crt->outputdata, crt->outputdatalength); } else { /* Signal pending. */ - ap_cancel_message(zq->queue, &ap_msg); + ap_cancel_message(zq->queue, ap_msg); } out_free: - free_page((unsigned long) ap_msg.msg); + free_page((unsigned long) ap_msg->msg); + ap_msg->private = NULL; + ap_msg->msg = NULL; return rc; } From 27c4f6738bdc535e42dfc1295dadc78ab7582939 Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Tue, 29 Sep 2020 16:07:22 +0200 Subject: [PATCH 366/645] s390/zcrypt: Introduce Failure Injection feature Introduce a way to specify additional debug flags with an crpyto request to be able to trigger certain failures within the zcrypt device drivers and/or ap core code. This failure injection possibility is only enabled with a kernel debug build CONFIG_ZCRYPT_DEBUG) and should never be available on a regular kernel running in production environment. Details: * The ioctl(ICARSAMODEXPO) get's a struct ica_rsa_modexpo. If the leftmost bit of the 32 bit unsigned int inputdatalength field is set, the uppermost 16 bits are separated and used as debug flag value. The process is checked to have the CAP_SYS_ADMIN capability enabled or EPERM is returned. * The ioctl(ICARSACRT) get's a struct ica_rsa_modexpo_crt. If the leftmost bit of the 32 bit unsigned int inputdatalength field is set, the uppermost 16 bits are separated and used als debug flag value. The process is checked to have the CAP_SYS_ADMIN capability enabled or EPERM is returned. * The ioctl(ZSECSENDCPRB) used to send CCA CPRBs get's a struct ica_xcRB. If the leftmost bit of the 32 bit unsigned int status field is set, the uppermost 16 bits of this field are used as debug flag value. The process is checked to have the CAP_SYS_ADMIN capability enabled or EPERM is returned. * The ioctl(ZSENDEP11CPRB) used to send EP11 CPRBs get's a struct ep11_urb. If the leftmost bit of the 64 bit unsigned int req_len field is set, the uppermost 16 bits of this field are used as debug flag value. The process is checked to have the CAP_SYS_ADMIN capability enabled or EPERM is returned. So it is possible to send an additional 16 bit value to the zcrypt API to be used to carry a failure injection command which may trigger special behavior within the zcrypt API and layers below. This 16 bit value is for the rest of the test referred as 'fi command' for Failure Injection. The lower 8 bits of the fi command construct a numerical argument in the range of 1-255 and is the 'fi action' to be performed with the request or the resulting reply: * 0x00 (all requests): No failure injection action but flags may be provided which may affect the processing of the request or reply. * 0x01 (only CCA CPRBs): The CPRB's agent_ID field is set to 'FF'. This results in an reply code 0x90 (Transport-Protocol Failure). * 0x02 (only CCA CPRBs): After the APQN to send to has been chosen, the domain field within the CPRB is overwritten with value 99 to enforce an reply with RY 0x8A. * 0x03 (all requests): At NQAP invocation the invalid qid value 0xFF00 is used causing an response code of 0x01 (AP queue not valid). The upper 8 bits of the fi command may carry bit flags which may influence the processing of an request or response: * 0x01: No retry. If this bit is set, the usual loop in the zcrypt API which retries an CPRB up to 10 times when the lower layers return with EAGAIN is abandoned after the first attempt to send the CPRB. * 0x02: Toggle special. Toggles the special bit on this request. This should result in an reply code RY~0x41 and result in an ioctl failure with errno EINVAL. This failure injection possibilities may get some further extensions in the future. As of now this is a starting point for Continuous Test and Integration to trigger some failures and watch for the reaction of the ap bus and zcrypt device driver code. Signed-off-by: Harald Freudenberger Signed-off-by: Vasily Gorbik --- drivers/s390/crypto/ap_bus.h | 29 +++++++- drivers/s390/crypto/ap_queue.c | 10 ++- drivers/s390/crypto/zcrypt_api.c | 91 ++++++++++++++++++++++++++ drivers/s390/crypto/zcrypt_api.h | 3 + drivers/s390/crypto/zcrypt_msgtype50.c | 11 ++++ drivers/s390/crypto/zcrypt_msgtype6.c | 10 +++ 6 files changed, 151 insertions(+), 3 deletions(-) diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h index 03fd95b5a0e8..5029b80132aa 100644 --- a/drivers/s390/crypto/ap_bus.h +++ b/drivers/s390/crypto/ap_bus.h @@ -200,12 +200,37 @@ struct ap_queue { typedef enum ap_sm_wait (ap_func_t)(struct ap_queue *queue); +/* failure injection cmd struct */ +struct ap_fi { + union { + u16 cmd; /* fi flags + action */ + struct { + u8 flags; /* fi flags only */ + u8 action; /* fi action only */ + }; + }; +}; + +/* all currently known fi actions */ +enum ap_fi_actions { + AP_FI_ACTION_CCA_AGENT_FF = 0x01, + AP_FI_ACTION_CCA_DOM_INVAL = 0x02, + AP_FI_ACTION_NQAP_QID_INVAL = 0x03, +}; + +/* all currently known fi flags */ +enum ap_fi_flags { + AP_FI_FLAG_NO_RETRY = 0x01, + AP_FI_FLAG_TOGGLE_SPECIAL = 0x02, +}; + struct ap_message { struct list_head list; /* Request queueing. */ unsigned long long psmid; /* Message id. */ void *msg; /* Pointer to message buffer. */ unsigned int len; /* Message length. */ - u32 flags; /* Flags, see AP_MSG_FLAG_xxx */ + u16 flags; /* Flags, see AP_MSG_FLAG_xxx */ + struct ap_fi fi; /* Failure Injection cmd */ int rc; /* Return code for this message */ void *private; /* ap driver private pointer. */ /* receive is called from tasklet context */ @@ -213,7 +238,7 @@ struct ap_message { struct ap_message *); }; -#define AP_MSG_FLAG_SPECIAL (1 << 16) /* flag msg as 'special' with NQAP */ +#define AP_MSG_FLAG_SPECIAL 1 /* flag msg as 'special' with NQAP */ /** * ap_init_message() - Initialize ap_message. diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c index ada37f1c7ac7..13d4fe2c6127 100644 --- a/drivers/s390/crypto/ap_queue.c +++ b/drivers/s390/crypto/ap_queue.c @@ -214,12 +214,20 @@ static enum ap_sm_wait ap_sm_write(struct ap_queue *aq) { struct ap_queue_status status; struct ap_message *ap_msg; + ap_qid_t qid = aq->qid; if (aq->requestq_count <= 0) return AP_SM_WAIT_NONE; /* Start the next request on the queue. */ ap_msg = list_entry(aq->requestq.next, struct ap_message, list); - status = __ap_send(aq->qid, ap_msg->psmid, +#ifdef CONFIG_ZCRYPT_DEBUG + if (ap_msg->fi.action == AP_FI_ACTION_NQAP_QID_INVAL) { + AP_DBF_WARN("%s fi cmd 0x%04x: forcing invalid qid 0xFF00\n", + __func__, ap_msg->fi.cmd); + qid = 0xFF00; + } +#endif + status = __ap_send(qid, ap_msg->psmid, ap_msg->msg, ap_msg->len, ap_msg->flags & AP_MSG_FLAG_SPECIAL); switch (status.response_code) { diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c index d642be65a3a0..08bb0f60c4b0 100644 --- a/drivers/s390/crypto/zcrypt_api.c +++ b/drivers/s390/crypto/zcrypt_api.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #define CREATE_TRACE_POINTS @@ -645,6 +646,11 @@ static long zcrypt_rsa_modexpo(struct ap_perms *perms, ap_init_message(&ap_msg); +#ifdef CONFIG_ZCRYPT_DEBUG + if (tr && tr->fi.cmd) + ap_msg.fi.cmd = tr->fi.cmd; +#endif + if (mex->outputdatalength < mex->inputdatalength) { func_code = 0; rc = -EINVAL; @@ -748,6 +754,11 @@ static long zcrypt_rsa_crt(struct ap_perms *perms, ap_init_message(&ap_msg); +#ifdef CONFIG_ZCRYPT_DEBUG + if (tr && tr->fi.cmd) + ap_msg.fi.cmd = tr->fi.cmd; +#endif + if (crt->outputdatalength < crt->inputdatalength) { func_code = 0; rc = -EINVAL; @@ -852,6 +863,17 @@ static long _zcrypt_send_cprb(bool userspace, struct ap_perms *perms, xcRB->status = 0; ap_init_message(&ap_msg); + +#ifdef CONFIG_ZCRYPT_DEBUG + if (tr && tr->fi.cmd) + ap_msg.fi.cmd = tr->fi.cmd; + if (tr && tr->fi.action == AP_FI_ACTION_CCA_AGENT_FF) { + ZCRYPT_DBF_WARN("%s fi cmd 0x%04x: forcing invalid agent_ID 'FF'\n", + __func__, tr->fi.cmd); + xcRB->agent_ID = 0x4646; + } +#endif + rc = get_cprb_fc(userspace, xcRB, &ap_msg, &func_code, &domain); if (rc) goto out; @@ -927,6 +949,14 @@ static long _zcrypt_send_cprb(bool userspace, struct ap_perms *perms, if (*domain == AUTOSEL_DOM) *domain = AP_QID_QUEUE(qid); +#ifdef CONFIG_ZCRYPT_DEBUG + if (tr && tr->fi.action == AP_FI_ACTION_CCA_DOM_INVAL) { + ZCRYPT_DBF_WARN("%s fi cmd 0x%04x: forcing invalid domain\n", + __func__, tr->fi.cmd); + *domain = 99; + } +#endif + rc = pref_zq->ops->send_cprb(userspace, pref_zq, xcRB, &ap_msg); spin_lock(&zcrypt_list_lock); @@ -995,6 +1025,11 @@ static long _zcrypt_send_ep11_cprb(bool userspace, struct ap_perms *perms, ap_init_message(&ap_msg); +#ifdef CONFIG_ZCRYPT_DEBUG + if (tr && tr->fi.cmd) + ap_msg.fi.cmd = tr->fi.cmd; +#endif + target_num = (unsigned short) xcrb->targets_num; /* empty list indicates autoselect (all available targets) */ @@ -1377,10 +1412,24 @@ static int icarsamodexpo_ioctl(struct ap_perms *perms, unsigned long arg) memset(&tr, 0, sizeof(tr)); if (copy_from_user(&mex, umex, sizeof(mex))) return -EFAULT; + +#ifdef CONFIG_ZCRYPT_DEBUG + if (mex.inputdatalength & (1U << 31)) { + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + tr.fi.cmd = (u16)(mex.inputdatalength >> 16); + } + mex.inputdatalength &= 0x0000FFFF; +#endif + do { rc = zcrypt_rsa_modexpo(perms, &tr, &mex); if (rc == -EAGAIN) tr.again_counter++; +#ifdef CONFIG_ZCRYPT_DEBUG + if (rc == -EAGAIN && (tr.fi.flags & AP_FI_FLAG_NO_RETRY)) + break; +#endif } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); /* on failure: retry once again after a requested rescan */ if ((rc == -ENODEV) && (zcrypt_process_rescan())) @@ -1406,10 +1455,24 @@ static int icarsacrt_ioctl(struct ap_perms *perms, unsigned long arg) memset(&tr, 0, sizeof(tr)); if (copy_from_user(&crt, ucrt, sizeof(crt))) return -EFAULT; + +#ifdef CONFIG_ZCRYPT_DEBUG + if (crt.inputdatalength & (1U << 31)) { + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + tr.fi.cmd = (u16)(crt.inputdatalength >> 16); + } + crt.inputdatalength &= 0x0000FFFF; +#endif + do { rc = zcrypt_rsa_crt(perms, &tr, &crt); if (rc == -EAGAIN) tr.again_counter++; +#ifdef CONFIG_ZCRYPT_DEBUG + if (rc == -EAGAIN && (tr.fi.flags & AP_FI_FLAG_NO_RETRY)) + break; +#endif } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); /* on failure: retry once again after a requested rescan */ if ((rc == -ENODEV) && (zcrypt_process_rescan())) @@ -1435,10 +1498,24 @@ static int zsecsendcprb_ioctl(struct ap_perms *perms, unsigned long arg) memset(&tr, 0, sizeof(tr)); if (copy_from_user(&xcRB, uxcRB, sizeof(xcRB))) return -EFAULT; + +#ifdef CONFIG_ZCRYPT_DEBUG + if (xcRB.status & (1U << 31)) { + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + tr.fi.cmd = (u16)(xcRB.status >> 16); + } + xcRB.status &= 0x0000FFFF; +#endif + do { rc = _zcrypt_send_cprb(true, perms, &tr, &xcRB); if (rc == -EAGAIN) tr.again_counter++; +#ifdef CONFIG_ZCRYPT_DEBUG + if (rc == -EAGAIN && (tr.fi.flags & AP_FI_FLAG_NO_RETRY)) + break; +#endif } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); /* on failure: retry once again after a requested rescan */ if ((rc == -ENODEV) && (zcrypt_process_rescan())) @@ -1465,10 +1542,24 @@ static int zsendep11cprb_ioctl(struct ap_perms *perms, unsigned long arg) memset(&tr, 0, sizeof(tr)); if (copy_from_user(&xcrb, uxcrb, sizeof(xcrb))) return -EFAULT; + +#ifdef CONFIG_ZCRYPT_DEBUG + if (xcrb.req_len & (1ULL << 63)) { + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + tr.fi.cmd = (u16)(xcrb.req_len >> 48); + } + xcrb.req_len &= 0x0000FFFFFFFFFFFFULL; +#endif + do { rc = _zcrypt_send_ep11_cprb(true, perms, &tr, &xcrb); if (rc == -EAGAIN) tr.again_counter++; +#ifdef CONFIG_ZCRYPT_DEBUG + if (rc == -EAGAIN && (tr.fi.flags & AP_FI_FLAG_NO_RETRY)) + break; +#endif } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); /* on failure: retry once again after a requested rescan */ if ((rc == -ENODEV) && (zcrypt_process_rescan())) diff --git a/drivers/s390/crypto/zcrypt_api.h b/drivers/s390/crypto/zcrypt_api.h index 03804f03b5d0..51c0b8bdef50 100644 --- a/drivers/s390/crypto/zcrypt_api.h +++ b/drivers/s390/crypto/zcrypt_api.h @@ -60,6 +60,9 @@ struct zcrypt_track { int again_counter; /* retry attempts counter */ int last_qid; /* last qid used */ int last_rc; /* last return code */ +#ifdef CONFIG_ZCRYPT_DEBUG + struct ap_fi fi; /* failure injection cmd */ +#endif }; /* defines related to message tracking */ diff --git a/drivers/s390/crypto/zcrypt_msgtype50.c b/drivers/s390/crypto/zcrypt_msgtype50.c index c543b5959509..bf14ee445f89 100644 --- a/drivers/s390/crypto/zcrypt_msgtype50.c +++ b/drivers/s390/crypto/zcrypt_msgtype50.c @@ -246,6 +246,12 @@ static int ICAMEX_msg_to_type50MEX_msg(struct zcrypt_queue *zq, copy_from_user(exp, mex->b_key, mod_len) || copy_from_user(inp, mex->inputdata, mod_len)) return -EFAULT; + +#ifdef CONFIG_ZCRYPT_DEBUG + if (ap_msg->fi.flags & AP_FI_FLAG_TOGGLE_SPECIAL) + ap_msg->flags ^= AP_MSG_FLAG_SPECIAL; +#endif + return 0; } @@ -332,6 +338,11 @@ static int ICACRT_msg_to_type50CRT_msg(struct zcrypt_queue *zq, copy_from_user(inp, crt->inputdata, mod_len)) return -EFAULT; +#ifdef CONFIG_ZCRYPT_DEBUG + if (ap_msg->fi.flags & AP_FI_FLAG_TOGGLE_SPECIAL) + ap_msg->flags ^= AP_MSG_FLAG_SPECIAL; +#endif + return 0; } diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c index aab7f0692035..307f90657d1d 100644 --- a/drivers/s390/crypto/zcrypt_msgtype6.c +++ b/drivers/s390/crypto/zcrypt_msgtype6.c @@ -482,6 +482,11 @@ static int XCRB_msg_to_type6CPRB_msgX(bool userspace, struct ap_message *ap_msg, || memcmp(function_code, "AU", 2) == 0) ap_msg->flags |= AP_MSG_FLAG_SPECIAL; +#ifdef CONFIG_ZCRYPT_DEBUG + if (ap_msg->fi.flags & AP_FI_FLAG_TOGGLE_SPECIAL) + ap_msg->flags ^= AP_MSG_FLAG_SPECIAL; +#endif + /* copy data block */ if (xcRB->request_data_length && z_copy_from_user(userspace, req_data, xcRB->request_data_address, @@ -569,6 +574,11 @@ static int xcrb_msg_to_type6_ep11cprb_msgx(bool userspace, struct ap_message *ap if (msg->cprbx.flags & 0x20) ap_msg->flags |= AP_MSG_FLAG_SPECIAL; +#ifdef CONFIG_ZCRYPT_DEBUG + if (ap_msg->fi.flags & AP_FI_FLAG_TOGGLE_SPECIAL) + ap_msg->flags ^= AP_MSG_FLAG_SPECIAL; +#endif + return 0; } From 4aa32ee3c058847ff935d1a65da309b67b65354a Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Fri, 2 Oct 2020 11:16:49 +0200 Subject: [PATCH 367/645] s390/lib: fix kernel doc for memcmp() s/count/n Signed-off-by: Julian Wiedmann Acked-by: Christian Borntraeger Signed-off-by: Vasily Gorbik --- arch/s390/lib/string.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/lib/string.c b/arch/s390/lib/string.c index 0e30e6e43b0c..93b3209b94a2 100644 --- a/arch/s390/lib/string.c +++ b/arch/s390/lib/string.c @@ -333,7 +333,7 @@ EXPORT_SYMBOL(memchr); * memcmp - Compare two areas of memory * @s1: One area of memory * @s2: Another area of memory - * @count: The size of the area. + * @n: The size of the area. */ #ifdef __HAVE_ARCH_MEMCMP int memcmp(const void *s1, const void *s2, size_t n) From eefc69a09ca5b441ee136f9fb68ab5970cfc2d51 Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Fri, 2 Oct 2020 11:18:19 +0200 Subject: [PATCH 368/645] s390/sie: fix typo in SIGP code description s/ait address/at address Signed-off-by: Julian Wiedmann Acked-by: Christian Borntraeger Signed-off-by: Vasily Gorbik --- arch/s390/include/uapi/asm/sie.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/include/uapi/asm/sie.h b/arch/s390/include/uapi/asm/sie.h index 6ca1e68d7103..ede318653c87 100644 --- a/arch/s390/include/uapi/asm/sie.h +++ b/arch/s390/include/uapi/asm/sie.h @@ -29,7 +29,7 @@ { 0x13, "SIGP conditional emergency signal" }, \ { 0x15, "SIGP sense running" }, \ { 0x16, "SIGP set multithreading"}, \ - { 0x17, "SIGP store additional status ait address"} + { 0x17, "SIGP store additional status at address"} #define icpt_prog_codes \ { 0x0001, "Prog Operation" }, \ From 792254a77201453d9a77479e63dc216ad90462d2 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Wed, 7 Oct 2020 18:06:05 +1000 Subject: [PATCH 369/645] powerpc/security: Fix link stack flush instruction The inline execution path for the hardware assisted branch flush instruction failed to set CTR to the correct value before bcctr, causing a crash when the feature is enabled. Fixes: 4d24e21cc694 ("powerpc/security: Allow for processors that flush the link stack using the special bcctr") Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20201007080605.64423-1-npiggin@gmail.com --- arch/powerpc/include/asm/asm-prototypes.h | 4 ++- arch/powerpc/kernel/entry_64.S | 8 ++++-- arch/powerpc/kernel/security.c | 34 ++++++++++++++++------- 3 files changed, 33 insertions(+), 13 deletions(-) diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h index 4957119604c7..d0b832cbbec8 100644 --- a/arch/powerpc/include/asm/asm-prototypes.h +++ b/arch/powerpc/include/asm/asm-prototypes.h @@ -145,7 +145,9 @@ void _kvmppc_restore_tm_pr(struct kvm_vcpu *vcpu, u64 guest_msr); void _kvmppc_save_tm_pr(struct kvm_vcpu *vcpu, u64 guest_msr); /* Patch sites */ -extern s32 patch__call_flush_branch_caches; +extern s32 patch__call_flush_branch_caches1; +extern s32 patch__call_flush_branch_caches2; +extern s32 patch__call_flush_branch_caches3; extern s32 patch__flush_count_cache_return; extern s32 patch__flush_link_stack_return; extern s32 patch__call_kvm_flush_link_stack; diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 733e40eba4eb..2f3846192ec7 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -430,7 +430,11 @@ _ASM_NOKPROBE_SYMBOL(save_nvgprs); #define FLUSH_COUNT_CACHE \ 1: nop; \ - patch_site 1b, patch__call_flush_branch_caches + patch_site 1b, patch__call_flush_branch_caches1; \ +1: nop; \ + patch_site 1b, patch__call_flush_branch_caches2; \ +1: nop; \ + patch_site 1b, patch__call_flush_branch_caches3 .macro nops number .rept \number @@ -512,7 +516,7 @@ _GLOBAL(_switch) kuap_check_amr r9, r10 - FLUSH_COUNT_CACHE + FLUSH_COUNT_CACHE /* Clobbers r9, ctr */ /* * On SMP kernels, care must be taken because a task may be diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c index c9876aab3142..e4e1a94ccf6a 100644 --- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -430,30 +430,44 @@ device_initcall(stf_barrier_debugfs_init); static void update_branch_cache_flush(void) { + u32 *site; + #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + site = &patch__call_kvm_flush_link_stack; // This controls the branch from guest_exit_cont to kvm_flush_link_stack if (link_stack_flush_type == BRANCH_CACHE_FLUSH_NONE) { - patch_instruction_site(&patch__call_kvm_flush_link_stack, - ppc_inst(PPC_INST_NOP)); + patch_instruction_site(site, ppc_inst(PPC_INST_NOP)); } else { // Could use HW flush, but that could also flush count cache - patch_branch_site(&patch__call_kvm_flush_link_stack, - (u64)&kvm_flush_link_stack, BRANCH_SET_LINK); + patch_branch_site(site, (u64)&kvm_flush_link_stack, BRANCH_SET_LINK); } #endif + // Patch out the bcctr first, then nop the rest + site = &patch__call_flush_branch_caches3; + patch_instruction_site(site, ppc_inst(PPC_INST_NOP)); + site = &patch__call_flush_branch_caches2; + patch_instruction_site(site, ppc_inst(PPC_INST_NOP)); + site = &patch__call_flush_branch_caches1; + patch_instruction_site(site, ppc_inst(PPC_INST_NOP)); + // This controls the branch from _switch to flush_branch_caches if (count_cache_flush_type == BRANCH_CACHE_FLUSH_NONE && link_stack_flush_type == BRANCH_CACHE_FLUSH_NONE) { - patch_instruction_site(&patch__call_flush_branch_caches, - ppc_inst(PPC_INST_NOP)); + // Nothing to be done + } else if (count_cache_flush_type == BRANCH_CACHE_FLUSH_HW && link_stack_flush_type == BRANCH_CACHE_FLUSH_HW) { - patch_instruction_site(&patch__call_flush_branch_caches, - ppc_inst(PPC_INST_BCCTR_FLUSH)); + // Patch in the bcctr last + site = &patch__call_flush_branch_caches1; + patch_instruction_site(site, ppc_inst(0x39207fff)); // li r9,0x7fff + site = &patch__call_flush_branch_caches2; + patch_instruction_site(site, ppc_inst(0x7d2903a6)); // mtctr r9 + site = &patch__call_flush_branch_caches3; + patch_instruction_site(site, ppc_inst(PPC_INST_BCCTR_FLUSH)); + } else { - patch_branch_site(&patch__call_flush_branch_caches, - (u64)&flush_branch_caches, BRANCH_SET_LINK); + patch_branch_site(site, (u64)&flush_branch_caches, BRANCH_SET_LINK); // If we just need to flush the link stack, early return if (count_cache_flush_type == BRANCH_CACHE_FLUSH_NONE) { From ec72024e35dddb88a81e40071c87ceb18b5ee835 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 7 Oct 2020 17:18:33 +0530 Subject: [PATCH 370/645] powerpc/drmem: Make lmb_size 64 bit Similar to commit 89c140bbaeee ("pseries: Fix 64 bit logical memory block panic") make sure different variables tracking lmb_size are updated to be 64 bit. This was found by code audit. Cc: stable@vger.kernel.org Signed-off-by: Aneesh Kumar K.V Acked-by: Nathan Lynch Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20201007114836.282468-2-aneesh.kumar@linux.ibm.com --- arch/powerpc/include/asm/drmem.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/include/asm/drmem.h b/arch/powerpc/include/asm/drmem.h index 030a19d92213..bf2402fed3e0 100644 --- a/arch/powerpc/include/asm/drmem.h +++ b/arch/powerpc/include/asm/drmem.h @@ -20,7 +20,7 @@ struct drmem_lmb { struct drmem_lmb_info { struct drmem_lmb *lmbs; int n_lmbs; - u32 lmb_size; + u64 lmb_size; }; extern struct drmem_lmb_info *drmem_info; @@ -80,7 +80,7 @@ struct of_drconf_cell_v2 { #define DRCONF_MEM_RESERVED 0x00000080 #define DRCONF_MEM_HOTREMOVABLE 0x00000100 -static inline u32 drmem_lmb_size(void) +static inline u64 drmem_lmb_size(void) { return drmem_info->lmb_size; } From 301d2ea6572386245c5d2d2dc85c3b5a737b85ac Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 7 Oct 2020 17:18:34 +0530 Subject: [PATCH 371/645] powerpc/memhotplug: Make lmb size 64bit Similar to commit 89c140bbaeee ("pseries: Fix 64 bit logical memory block panic") make sure different variables tracking lmb_size are updated to be 64 bit. This was found by code audit. Cc: stable@vger.kernel.org Signed-off-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20201007114836.282468-3-aneesh.kumar@linux.ibm.com --- .../platforms/pseries/hotplug-memory.c | 43 +++++++++++++------ 1 file changed, 29 insertions(+), 14 deletions(-) diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 9a533acf8ad0..ca5589a1ec7f 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -277,7 +277,7 @@ static int dlpar_offline_lmb(struct drmem_lmb *lmb) return dlpar_change_lmb_state(lmb, false); } -static int pseries_remove_memblock(unsigned long base, unsigned int memblock_size) +static int pseries_remove_memblock(unsigned long base, unsigned long memblock_size) { unsigned long block_sz, start_pfn; int sections_per_block; @@ -308,10 +308,11 @@ out: static int pseries_remove_mem_node(struct device_node *np) { - const __be32 *regs; + const __be32 *prop; unsigned long base; - unsigned int lmb_size; + unsigned long lmb_size; int ret = -EINVAL; + int addr_cells, size_cells; /* * Check to see if we are actually removing memory @@ -322,12 +323,19 @@ static int pseries_remove_mem_node(struct device_node *np) /* * Find the base address and size of the memblock */ - regs = of_get_property(np, "reg", NULL); - if (!regs) + prop = of_get_property(np, "reg", NULL); + if (!prop) return ret; - base = be64_to_cpu(*(unsigned long *)regs); - lmb_size = be32_to_cpu(regs[3]); + addr_cells = of_n_addr_cells(np); + size_cells = of_n_size_cells(np); + + /* + * "reg" property represents (addr,size) tuple. + */ + base = of_read_number(prop, addr_cells); + prop += addr_cells; + lmb_size = of_read_number(prop, size_cells); pseries_remove_memblock(base, lmb_size); return 0; @@ -564,7 +572,7 @@ static int dlpar_memory_remove_by_ic(u32 lmbs_to_remove, u32 drc_index) #else static inline int pseries_remove_memblock(unsigned long base, - unsigned int memblock_size) + unsigned long memblock_size) { return -EOPNOTSUPP; } @@ -888,10 +896,11 @@ int dlpar_memory(struct pseries_hp_errorlog *hp_elog) static int pseries_add_mem_node(struct device_node *np) { - const __be32 *regs; + const __be32 *prop; unsigned long base; - unsigned int lmb_size; + unsigned long lmb_size; int ret = -EINVAL; + int addr_cells, size_cells; /* * Check to see if we are actually adding memory @@ -902,12 +911,18 @@ static int pseries_add_mem_node(struct device_node *np) /* * Find the base and size of the memblock */ - regs = of_get_property(np, "reg", NULL); - if (!regs) + prop = of_get_property(np, "reg", NULL); + if (!prop) return ret; - base = be64_to_cpu(*(unsigned long *)regs); - lmb_size = be32_to_cpu(regs[3]); + addr_cells = of_n_addr_cells(np); + size_cells = of_n_size_cells(np); + /* + * "reg" property represents (addr,size) tuple. + */ + base = of_read_number(prop, addr_cells); + prop += addr_cells; + lmb_size = of_read_number(prop, size_cells); /* * Update memory region to represent the memory add From 950805f4d90eda14325ceab56b0f00d034baa8bc Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 7 Oct 2020 17:18:35 +0530 Subject: [PATCH 372/645] powerpc/book3s64/radix: Make radix_mem_block_size 64bit Similar to commit 89c140bbaeee ("pseries: Fix 64 bit logical memory block panic") make sure different variables tracking lmb_size are updated to be 64 bit. Fixes: af9d00e93a4f ("powerpc/mm/radix: Create separate mappings for hot-plugged memory") Signed-off-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20201007114836.282468-4-aneesh.kumar@linux.ibm.com --- arch/powerpc/include/asm/book3s/64/mmu.h | 2 +- arch/powerpc/mm/book3s64/radix_pgtable.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h index ddc414ab3c4d..e0b52940e43c 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu.h +++ b/arch/powerpc/include/asm/book3s/64/mmu.h @@ -70,7 +70,7 @@ extern unsigned int mmu_base_pid; /* * memory block size used with radix translation. */ -extern unsigned int __ro_after_init radix_mem_block_size; +extern unsigned long __ro_after_init radix_mem_block_size; #define PRTB_SIZE_SHIFT (mmu_pid_bits + 4) #define PRTB_ENTRIES (1ul << mmu_pid_bits) diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index 5c8adeb8c955..78c5afe98359 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -34,7 +34,7 @@ unsigned int mmu_pid_bits; unsigned int mmu_base_pid; -unsigned int radix_mem_block_size __ro_after_init; +unsigned long radix_mem_block_size __ro_after_init; static __ref void *early_alloc_pgtable(unsigned long size, int nid, unsigned long region_start, unsigned long region_end) From fbf2f134c8c312d3166534a8bd6a1aaee6e9c7ef Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 7 Oct 2020 17:18:36 +0530 Subject: [PATCH 373/645] powerpc/lmb-size: Use addr #size-cells value when fetching lmb-size Make it consistent with other usages. Signed-off-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20201007114836.282468-5-aneesh.kumar@linux.ibm.com --- arch/powerpc/mm/book3s64/radix_pgtable.c | 7 ++++--- arch/powerpc/platforms/pseries/hotplug-memory.c | 13 +++++++++---- 2 files changed, 13 insertions(+), 7 deletions(-) diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index 78c5afe98359..f8e9eb49d46b 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -498,7 +498,7 @@ static int __init probe_memory_block_size(unsigned long node, const char *uname, depth, void *data) { unsigned long *mem_block_size = (unsigned long *)data; - const __be64 *prop; + const __be32 *prop; int len; if (depth != 1) @@ -508,13 +508,14 @@ static int __init probe_memory_block_size(unsigned long node, const char *uname, return 0; prop = of_get_flat_dt_prop(node, "ibm,lmb-size", &len); - if (!prop || len < sizeof(__be64)) + + if (!prop || len < dt_root_size_cells * sizeof(__be32)) /* * Nothing in the device tree */ *mem_block_size = MIN_MEMORY_BLOCK_SIZE; else - *mem_block_size = be64_to_cpup(prop); + *mem_block_size = of_read_number(prop, dt_root_size_cells); return 1; } diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index ca5589a1ec7f..4e18653a3804 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -30,12 +30,17 @@ unsigned long pseries_memory_block_size(void) np = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory"); if (np) { - const __be64 *size; + int len; + int size_cells; + const __be32 *prop; - size = of_get_property(np, "ibm,lmb-size", NULL); - if (size) - memblock_size = be64_to_cpup(size); + size_cells = of_n_size_cells(np); + + prop = of_get_property(np, "ibm,lmb-size", &len); + if (prop && len >= size_cells * sizeof(__be32)) + memblock_size = of_read_number(prop, size_cells); of_node_put(np); + } else if (machine_is(pseries)) { /* This fallback really only applies to pseries */ unsigned int memzero_size = 0; From 13135b461cf205941308984bd3271ec7d403dc40 Mon Sep 17 00:00:00 2001 From: Vaibhav Jain Date: Mon, 14 Sep 2020 02:49:04 +0530 Subject: [PATCH 374/645] powerpc/papr_scm: Add PAPR command family to pass-through command-set Add NVDIMM_FAMILY_PAPR to the list of valid 'dimm_family_mask' acceptable by papr_scm. This is needed as since commit 92fe2aa859f5 ("libnvdimm: Validate command family indices") libnvdimm performs a validation of 'nd_cmd_pkg.nd_family' received as part of ND_CMD_CALL processing to ensure only known command families can use the general ND_CMD_CALL pass-through functionality. Without this change the ND_CMD_CALL pass-through targeting NVDIMM_FAMILY_PAPR error out with -EINVAL. Fixes: 92fe2aa859f5 ("libnvdimm: Validate command family indices") Signed-off-by: Vaibhav Jain Reviewed-by: Ira Weiny Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200913211904.24472-1-vaibhav@linux.ibm.com --- arch/powerpc/platforms/pseries/papr_scm.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index a95aa425e7d4..835163f54244 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -898,6 +898,9 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p) p->bus_desc.of_node = p->pdev->dev.of_node; p->bus_desc.provider_name = kstrdup(p->pdev->name, GFP_KERNEL); + /* Set the dimm command family mask to accept PDSMs */ + set_bit(NVDIMM_FAMILY_PAPR, &p->bus_desc.dimm_family_mask); + if (!p->bus_desc.provider_name) return -ENOMEM; From 43fab0856eafb32d5cdb809d8225197755826128 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Tue, 6 Oct 2020 15:58:37 +0200 Subject: [PATCH 375/645] MIPS: tx49xx: move tx4939_add_memory_regions into only user tx4939_add_memory_regions() is only used in txx9/rbtx4939/prom.c. Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/txx9/tx4939.h | 1 - arch/mips/txx9/generic/setup_tx4939.c | 17 ----------------- arch/mips/txx9/rbtx4939/prom.c | 14 +++++++++++++- 3 files changed, 13 insertions(+), 19 deletions(-) diff --git a/arch/mips/include/asm/txx9/tx4939.h b/arch/mips/include/asm/txx9/tx4939.h index 00805ac6e9fc..abf980af9ef4 100644 --- a/arch/mips/include/asm/txx9/tx4939.h +++ b/arch/mips/include/asm/txx9/tx4939.h @@ -498,7 +498,6 @@ struct tx4939_vpc_desc { ((((mst) + 245/2) / 245UL * 429 * 16 + 19) / 19 / 2) void tx4939_wdt_init(void); -void tx4939_add_memory_regions(void); void tx4939_setup(void); void tx4939_time_init(unsigned int tmrnr); void tx4939_sio_init(unsigned int sclk, unsigned int cts_mask); diff --git a/arch/mips/txx9/generic/setup_tx4939.c b/arch/mips/txx9/generic/setup_tx4939.c index 360c388f4c82..bf8a3cdababf 100644 --- a/arch/mips/txx9/generic/setup_tx4939.c +++ b/arch/mips/txx9/generic/setup_tx4939.c @@ -22,7 +22,6 @@ #include #include #include -#include #include #include #include @@ -94,22 +93,6 @@ static struct resource tx4939_sdram_resource[4]; static struct resource tx4939_sram_resource; #define TX4939_SRAM_SIZE 0x800 -void __init tx4939_add_memory_regions(void) -{ - int i; - unsigned long start, size; - u64 win; - - for (i = 0; i < 4; i++) { - if (!((__u32)____raw_readq(&tx4939_ddrcptr->winen) & (1 << i))) - continue; - win = ____raw_readq(&tx4939_ddrcptr->win[i]); - start = (unsigned long)(win >> 48); - size = (((unsigned long)(win >> 32) & 0xffff) + 1) - start; - add_memory_region(start << 20, size << 20, BOOT_MEM_RAM); - } -} - void __init tx4939_setup(void) { int i; diff --git a/arch/mips/txx9/rbtx4939/prom.c b/arch/mips/txx9/rbtx4939/prom.c index bd277ecb4ad6..1dc47ce81c92 100644 --- a/arch/mips/txx9/rbtx4939/prom.c +++ b/arch/mips/txx9/rbtx4939/prom.c @@ -7,11 +7,23 @@ */ #include +#include #include #include void __init rbtx4939_prom_init(void) { - tx4939_add_memory_regions(); + unsigned long start, size; + u64 win; + int i; + + for (i = 0; i < 4; i++) { + if (!((__u32)____raw_readq(&tx4939_ddrcptr->winen) & (1 << i))) + continue; + win = ____raw_readq(&tx4939_ddrcptr->win[i]); + start = (unsigned long)(win >> 48); + size = (((unsigned long)(win >> 32) & 0xffff) + 1) - start; + add_memory_region(start << 20, size << 20, BOOT_MEM_RAM); + } txx9_sio_putchar_init(TX4939_SIO_REG(0) & 0xfffffffffULL); } From 46dd40aa376c8158b6aa17510079caf5c3af6237 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Wed, 7 Oct 2020 12:17:04 +0200 Subject: [PATCH 376/645] MIPS: SGI-IP28: disable use of ll/sc in kernel SGI-IP28 systems only use broken R10k rev 2.5 CPUs, which could lock up, if ll/sc sequences are issued in certain order. Since those systems are all non-SMP, we can disable ll/sc usage in kernel. Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/mach-ip28/cpu-feature-overrides.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/include/asm/mach-ip28/cpu-feature-overrides.h b/arch/mips/include/asm/mach-ip28/cpu-feature-overrides.h index ba8b4e30b3e2..613bbc10c1f2 100644 --- a/arch/mips/include/asm/mach-ip28/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-ip28/cpu-feature-overrides.h @@ -25,7 +25,7 @@ #define cpu_has_mcheck 0 #define cpu_has_ejtag 0 -#define cpu_has_llsc 1 +#define cpu_has_llsc 0 #define cpu_has_vtag_icache 0 #define cpu_has_dc_aliases 0 /* see probe_pcache() */ #define cpu_has_ic_fills_f_dc 0 From ca1d3443b4dd1e8f152bd6c881ddb3eb2996179a Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Tue, 29 Sep 2020 06:48:31 +0000 Subject: [PATCH 377/645] powerpc: Remove SYNC on non 6xx SYNC is usefull for Powerpc 601 only. On everything else, SYNC is empty. Remove it from code that is not made to run on 6xx. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/27951fa6c9a8f80724d1bc81a6117ac32343a55d.1601362098.git.christophe.leroy@csgroup.eu --- arch/powerpc/kernel/head_40x.S | 1 - arch/powerpc/kernel/head_booke.h | 1 - arch/powerpc/kernel/misc_64.S | 1 - 3 files changed, 3 deletions(-) diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S index 5b282d9965a5..44c9018aed1b 100644 --- a/arch/powerpc/kernel/head_40x.S +++ b/arch/powerpc/kernel/head_40x.S @@ -72,7 +72,6 @@ turn_on_mmu: lis r0,start_here@h ori r0,r0,start_here@l mtspr SPRN_SRR0,r0 - SYNC rfi /* enables MMU */ b . /* prevent prefetch past rfi */ diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h index 18f87bf9e32b..71c359d438b5 100644 --- a/arch/powerpc/kernel/head_booke.h +++ b/arch/powerpc/kernel/head_booke.h @@ -176,7 +176,6 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV) #endif mtspr SPRN_SRR1,r10 mtspr SPRN_SRR0,r11 - SYNC RFI /* jump to handler, enable MMU */ 99: b ret_from_kernel_syscall .endm diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index 7bb46ad98207..070465825c21 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -365,7 +365,6 @@ _GLOBAL(kexec_smp_wait) li r4,KEXEC_STATE_REAL_MODE stb r4,PACAKEXECSTATE(r13) - SYNC b kexec_wait From e42a64002a507bf61e57106ed5323b1854371563 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Tue, 29 Sep 2020 06:48:33 +0000 Subject: [PATCH 378/645] powerpc: Remove CONFIG_PPC601_SYNC_FIX This config option isn't in any defconfig. The very first versions of Powerpc 601 have a bug which requires additional sync before and/or after some instructions. This was more than 25 years ago and time has come to retire those buggy versions of the 601 from the kernel. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/55b46bff16705b1ae7bf0a60ccd522b1010ebf75.1601362098.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/ppc_asm.h | 6 ------ arch/powerpc/platforms/Kconfig | 15 --------------- 2 files changed, 21 deletions(-) diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index b4cc6608131c..0b9dc814b81c 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -382,15 +382,9 @@ n: #endif /* various errata or part fixups */ -#ifdef CONFIG_PPC601_SYNC_FIX -#define SYNC sync; isync -#define SYNC_601 sync -#define ISYNC_601 isync -#else #define SYNC #define SYNC_601 #define ISYNC_601 -#endif #if defined(CONFIG_PPC_CELL) || defined(CONFIG_PPC_FSL_BOOK3E) #define MFTB(dest) \ diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index b439b027a42f..7a5e8f4541e3 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -199,21 +199,6 @@ source "drivers/cpuidle/Kconfig" endmenu -config PPC601_SYNC_FIX - bool "Workarounds for PPC601 bugs" - depends on PPC_BOOK3S_601 && PPC_PMAC - default y - help - Some versions of the PPC601 (the first PowerPC chip) have bugs which - mean that extra synchronization instructions are required near - certain instructions, typically those that make major changes to the - CPU state. These extra instructions reduce performance slightly. - If you say N here, these extra instructions will not be included, - resulting in a kernel which will run faster but may not run at all - on some systems with the PPC601 chip. - - If in doubt, say Y here. - config TAU bool "On-chip CPU temperature sensor support" depends on PPC_BOOK3S_32 From d2a5cd83ee984c0e9fc172d2df9591c264261a52 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Tue, 29 Sep 2020 06:48:34 +0000 Subject: [PATCH 379/645] powerpc: Drop SYNC_601() ISYNC_601() and SYNC() Those macros are now empty at all time. Drop them. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/7990bb63fc53e460bfa94f8040184881d9e6fbc3.1601362098.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/ppc_asm.h | 4 ---- arch/powerpc/kernel/entry_32.S | 17 +---------------- arch/powerpc/kernel/fpu.S | 1 - arch/powerpc/kernel/head_32.S | 9 --------- arch/powerpc/kernel/head_32.h | 1 - arch/powerpc/kernel/l2cr_6xx.S | 3 +-- arch/powerpc/mm/book3s32/hash_low.S | 12 ------------ 7 files changed, 2 insertions(+), 45 deletions(-) diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index 0b9dc814b81c..67a421b81a50 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -382,10 +382,6 @@ n: #endif /* various errata or part fixups */ -#define SYNC -#define SYNC_601 -#define ISYNC_601 - #if defined(CONFIG_PPC_CELL) || defined(CONFIG_PPC_FSL_BOOK3E) #define MFTB(dest) \ 90: mfspr dest, SPRN_TBRL; \ diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index f4d0af8e1136..f25ea188ecd3 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -234,7 +234,6 @@ transfer_to_handler_cont: mtspr SPRN_SRR0,r11 mtspr SPRN_SRR1,r10 mtlr r9 - SYNC RFI /* jump to handler, enable MMU */ #if defined (CONFIG_PPC_BOOK3S_32) || defined(CONFIG_E500) @@ -264,7 +263,6 @@ _ASM_NOKPROBE_SYMBOL(transfer_to_handler_cont) LOAD_REG_IMMEDIATE(r0, MSR_KERNEL) mtspr SPRN_SRR0,r12 mtspr SPRN_SRR1,r0 - SYNC RFI reenable_mmu: @@ -323,7 +321,6 @@ stack_ovf: #endif mtspr SPRN_SRR0,r9 mtspr SPRN_SRR1,r10 - SYNC RFI _ASM_NOKPROBE_SYMBOL(stack_ovf) #endif @@ -411,7 +408,6 @@ ret_from_syscall: /* disable interrupts so current_thread_info()->flags can't change */ LOAD_REG_IMMEDIATE(r10,MSR_KERNEL) /* doesn't include MSR_EE */ /* Note: We don't bother telling lockdep about it */ - SYNC mtmsr r10 lwz r9,TI_FLAGS(r2) li r8,-MAX_ERRNO @@ -474,7 +470,6 @@ syscall_exit_finish: #endif mtspr SPRN_SRR0,r7 mtspr SPRN_SRR1,r8 - SYNC RFI _ASM_NOKPROBE_SYMBOL(syscall_exit_finish) #ifdef CONFIG_44x @@ -567,7 +562,6 @@ syscall_exit_work: * lockdep as we are supposed to have IRQs on at this point */ ori r10,r10,MSR_EE - SYNC mtmsr r10 /* Save NVGPRS if they're not saved already */ @@ -606,7 +600,6 @@ ret_from_kernel_syscall: #endif mtspr SPRN_SRR0, r9 mtspr SPRN_SRR1, r10 - SYNC RFI _ASM_NOKPROBE_SYMBOL(ret_from_kernel_syscall) @@ -810,7 +803,6 @@ fast_exception_return: REST_GPR(9, r11) REST_GPR(12, r11) lwz r11,GPR11(r11) - SYNC RFI _ASM_NOKPROBE_SYMBOL(fast_exception_return) @@ -872,7 +864,6 @@ ret_from_except: * from the interrupt. */ /* Note: We don't bother telling lockdep about it */ LOAD_REG_IMMEDIATE(r10,MSR_KERNEL) - SYNC /* Some chip revs have problems here... */ mtmsr r10 /* disable interrupts */ lwz r3,_MSR(r1) /* Returning to user mode? */ @@ -1035,7 +1026,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX) * exc_exit_restart below. -- paulus */ LOAD_REG_IMMEDIATE(r10,MSR_KERNEL & ~MSR_RI) - SYNC mtmsr r10 /* clear the RI bit */ .globl exc_exit_restart exc_exit_restart: @@ -1046,7 +1036,6 @@ exc_exit_restart: lwz r1,GPR1(r1) .globl exc_exit_restart_end exc_exit_restart_end: - SYNC RFI _ASM_NOKPROBE_SYMBOL(exc_exit_restart) _ASM_NOKPROBE_SYMBOL(exc_exit_restart_end) @@ -1274,7 +1263,6 @@ do_resched: /* r10 contains MSR_KERNEL here */ mfmsr r10 #endif ori r10,r10,MSR_EE - SYNC mtmsr r10 /* hard-enable interrupts */ bl schedule recheck: @@ -1283,7 +1271,6 @@ recheck: * TI_FLAGS aren't advertised. */ LOAD_REG_IMMEDIATE(r10,MSR_KERNEL) - SYNC mtmsr r10 /* disable interrupts */ lwz r9,TI_FLAGS(r2) andi. r0,r9,_TIF_NEED_RESCHED @@ -1292,7 +1279,6 @@ recheck: beq restore_user do_user_signal: /* r10 contains MSR_KERNEL here */ ori r10,r10,MSR_EE - SYNC mtmsr r10 /* hard-enable interrupts */ /* save r13-r31 in the exception frame, if not already done */ lwz r3,_TRAP(r1) @@ -1382,8 +1368,7 @@ _GLOBAL(enter_rtas) mfmsr r9 stw r9,8(r1) LOAD_REG_IMMEDIATE(r0,MSR_KERNEL) - SYNC /* disable interrupts so SRR0/1 */ - mtmsr r0 /* don't get trashed */ + mtmsr r0 /* disable interrupts so SRR0/1 don't get trashed */ li r9,MSR_KERNEL & ~(MSR_IR|MSR_DR) mtlr r6 stw r7, THREAD + RTAS_SP(r2) diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S index 825893d4cb59..3ff9a8fafa46 100644 --- a/arch/powerpc/kernel/fpu.S +++ b/arch/powerpc/kernel/fpu.S @@ -87,7 +87,6 @@ BEGIN_FTR_SECTION oris r5,r5,MSR_VSX@h END_FTR_SECTION_IFSET(CPU_FTR_VSX) #endif - SYNC MTMSRD(r5) /* enable use of fpu now */ isync /* enable use of FP after return */ diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index 2bd0aa3a4cc7..48cde60334a2 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -219,7 +219,6 @@ turn_on_mmu: lis r0,start_here@h ori r0,r0,start_here@l mtspr SPRN_SRR0,r0 - SYNC RFI /* enables MMU */ /* @@ -784,14 +783,12 @@ fast_hash_page_return: mtcr r11 lwz r11, THR11(r10) mfspr r10, SPRN_SPRG_SCRATCH0 - SYNC RFI 1: /* ISI */ mtcr r11 mfspr r11, SPRN_SPRG_SCRATCH1 mfspr r10, SPRN_SPRG_SCRATCH0 - SYNC RFI stack_overflow: @@ -882,7 +879,6 @@ __secondary_start_pmac_0: set to map the 0xf0000000 - 0xffffffff region */ mfmsr r0 rlwinm r0,r0,0,28,26 /* clear DR (0x10) */ - SYNC mtmsr r0 isync @@ -930,7 +926,6 @@ __secondary_start: ori r3,r3,start_secondary@l mtspr SPRN_SRR0,r3 mtspr SPRN_SRR1,r4 - SYNC RFI #endif /* CONFIG_SMP */ @@ -1074,7 +1069,6 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) .align 4 mtspr SPRN_SRR0,r4 mtspr SPRN_SRR1,r3 - SYNC RFI /* Load up the kernel context */ 2: bl load_up_mmu @@ -1099,7 +1093,6 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) ori r3,r3,start_kernel@l mtspr SPRN_SRR0,r3 mtspr SPRN_SRR1,r4 - SYNC RFI /* @@ -1217,7 +1210,6 @@ _ENTRY(update_bats) .align 4 mtspr SPRN_SRR0, r4 mtspr SPRN_SRR1, r3 - SYNC RFI 1: bl clear_bats lis r3, BATS@ha @@ -1237,7 +1229,6 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) mtmsr r3 mtspr SPRN_SRR0, r7 mtspr SPRN_SRR1, r6 - SYNC RFI flush_tlbs: diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h index cc36998c5541..7c767765071d 100644 --- a/arch/powerpc/kernel/head_32.h +++ b/arch/powerpc/kernel/head_32.h @@ -222,7 +222,6 @@ #endif mtspr SPRN_SRR1,r10 mtspr SPRN_SRR0,r11 - SYNC RFI /* jump to handler, enable MMU */ 99: b ret_from_kernel_syscall .endm diff --git a/arch/powerpc/kernel/l2cr_6xx.S b/arch/powerpc/kernel/l2cr_6xx.S index 5f07aa5e9851..225511d73bef 100644 --- a/arch/powerpc/kernel/l2cr_6xx.S +++ b/arch/powerpc/kernel/l2cr_6xx.S @@ -256,7 +256,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_SPEC7450) sync /* Restore MSR (restores EE and DR bits to original state) */ - SYNC mtmsr r7 isync @@ -377,7 +376,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_L3CR) 1: bdnz 1b /* Restore MSR (restores EE and DR bits to original state) */ -4: SYNC +4: mtmsr r7 isync blr diff --git a/arch/powerpc/mm/book3s32/hash_low.S b/arch/powerpc/mm/book3s32/hash_low.S index 1690d369688b..3143de6ae769 100644 --- a/arch/powerpc/mm/book3s32/hash_low.S +++ b/arch/powerpc/mm/book3s32/hash_low.S @@ -199,11 +199,9 @@ _GLOBAL(add_hash_page) * covered by a BAT). -- paulus */ mfmsr r9 - SYNC rlwinm r0,r9,0,17,15 /* clear bit 16 (MSR_EE) */ rlwinm r0,r0,0,28,26 /* clear MSR_DR */ mtmsr r0 - SYNC_601 isync #ifdef CONFIG_SMP @@ -262,7 +260,6 @@ _GLOBAL(add_hash_page) /* reenable interrupts and DR */ mtmsr r9 - SYNC_601 isync lwz r0,4(r1) @@ -506,11 +503,9 @@ _GLOBAL(flush_hash_pages) * covered by a BAT). -- paulus */ mfmsr r10 - SYNC rlwinm r0,r10,0,17,15 /* clear bit 16 (MSR_EE) */ rlwinm r0,r0,0,28,26 /* clear MSR_DR */ mtmsr r0 - SYNC_601 isync /* First find a PTE in the range that has _PAGE_HASHPTE set */ @@ -629,7 +624,6 @@ _GLOBAL(flush_hash_pages) #endif 19: mtmsr r10 - SYNC_601 isync blr EXPORT_SYMBOL(flush_hash_pages) @@ -643,11 +637,9 @@ _GLOBAL(_tlbie) lwz r8,TASK_CPU(r2) oris r8,r8,11 mfmsr r10 - SYNC rlwinm r0,r10,0,17,15 /* clear bit 16 (MSR_EE) */ rlwinm r0,r0,0,28,26 /* clear DR */ mtmsr r0 - SYNC_601 isync lis r9,mmu_hash_lock@h ori r9,r9,mmu_hash_lock@l @@ -664,7 +656,6 @@ _GLOBAL(_tlbie) li r0,0 stw r0,0(r9) /* clear mmu_hash_lock */ mtmsr r10 - SYNC_601 isync #else /* CONFIG_SMP */ tlbie r3 @@ -681,11 +672,9 @@ _GLOBAL(_tlbia) lwz r8,TASK_CPU(r2) oris r8,r8,10 mfmsr r10 - SYNC rlwinm r0,r10,0,17,15 /* clear bit 16 (MSR_EE) */ rlwinm r0,r0,0,28,26 /* clear DR */ mtmsr r0 - SYNC_601 isync lis r9,mmu_hash_lock@h ori r9,r9,mmu_hash_lock@l @@ -709,7 +698,6 @@ _GLOBAL(_tlbia) li r0,0 stw r0,0(r9) /* clear mmu_hash_lock */ mtmsr r10 - SYNC_601 isync #endif /* CONFIG_SMP */ blr From f0ed73f3fa2cdca65973659689ec9e46d99a5f60 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Tue, 29 Sep 2020 06:48:35 +0000 Subject: [PATCH 380/645] powerpc: Remove PowerPC 601 Powerpc 601 is 25 years old. It is not selected by any defconfig. It requires a lot of special handling as it deviates from the standard 6xx. Retire it. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/00a6948d659e017f8ca63437d1384222c3aede57.1601362098.git.christophe.leroy@csgroup.eu --- arch/powerpc/kernel/cputable.c | 15 --------------- arch/powerpc/platforms/Kconfig.cputype | 11 ++--------- 2 files changed, 2 insertions(+), 24 deletions(-) diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index b5bc2edef440..492c0b36aff6 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -609,21 +609,6 @@ static struct cpu_spec __initdata cpu_specs[] = { #endif /* CONFIG_PPC_BOOK3S_64 */ #ifdef CONFIG_PPC32 -#ifdef CONFIG_PPC_BOOK3S_601 - { /* 601 */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00010000, - .cpu_name = "601", - .cpu_features = CPU_FTRS_PPC601, - .cpu_user_features = COMMON_USER | PPC_FEATURE_601_INSTR | - PPC_FEATURE_UNIFIED_CACHE | PPC_FEATURE_NO_TB, - .mmu_features = MMU_FTR_HPTE_TABLE, - .icache_bsize = 32, - .dcache_bsize = 32, - .machine_check = machine_check_generic, - .platform = "ppc601", - }, -#endif /* CONFIG_PPC_BOOK3S_601 */ #ifdef CONFIG_PPC_BOOK3S_6xx { /* 603 */ .pvr_mask = 0xffff0000, diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index e74ec220b5d6..c194c4ae8bc7 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -20,7 +20,7 @@ choice depends on PPC32 help There are five families of 32 bit PowerPC chips supported. - The most common ones are the desktop and server CPUs (601, 603, + The most common ones are the desktop and server CPUs (603, 604, 740, 750, 74xx) CPUs from Freescale and IBM, with their embedded 512x/52xx/82xx/83xx/86xx counterparts. The other embedded parts, namely 4xx, 8xx, e200 (55xx) and e500 @@ -30,7 +30,7 @@ choice If unsure, select 52xx/6xx/7xx/74xx/82xx/83xx/86xx. config PPC_BOOK3S_6xx - bool "512x/52xx/6xx/7xx/74xx/82xx/83xx/86xx except 601" + bool "512x/52xx/6xx/7xx/74xx/82xx/83xx/86xx" select PPC_BOOK3S_32 select PPC_FPU select PPC_HAVE_PMU_SUPPORT @@ -38,13 +38,6 @@ config PPC_BOOK3S_6xx select PPC_HAVE_KUAP select HAVE_ARCH_VMAP_STACK if !ADB_PMU -config PPC_BOOK3S_601 - bool "PowerPC 601" - select PPC_BOOK3S_32 - select PPC_FPU - select PPC_HAVE_KUAP - select HAVE_ARCH_VMAP_STACK - config PPC_85xx bool "Freescale 85xx" select E500 From 8b14e1dff067195dca7a42321771437cb33a99e9 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Tue, 29 Sep 2020 06:48:36 +0000 Subject: [PATCH 381/645] powerpc: Remove support for PowerPC 601 PowerPC 601 has been retired. Remove all associated specific code. CPU_FTRS_PPC601 has CPU_FTR_COHERENT_ICACHE and CPU_FTR_COMMON. CPU_FTR_COMMON is already present via other CPU_FTRS. None of the remaining CPU selects CPU_FTR_COHERENT_ICACHE. So CPU_FTRS_PPC601 can be removed from the possible features, hence can be removed completely. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/60b725d55e21beec3335175c20b77903ff98284f.1601362098.git.christophe.leroy@csgroup.eu --- arch/powerpc/boot/util.S | 15 +------ arch/powerpc/include/asm/cputable.h | 12 ++--- arch/powerpc/include/asm/ppc_asm.h | 3 +- arch/powerpc/include/asm/ptrace.h | 4 -- arch/powerpc/include/asm/time.h | 2 +- arch/powerpc/include/asm/timex.h | 3 -- arch/powerpc/kernel/btext.c | 8 +--- arch/powerpc/kernel/entry_32.S | 18 -------- arch/powerpc/kernel/head_32.S | 44 ++---------------- arch/powerpc/kernel/setup_32.c | 2 +- arch/powerpc/kernel/traps.c | 4 -- arch/powerpc/kernel/vdso32/datapage.S | 2 - arch/powerpc/kernel/vdso32/vdso32.lds.S | 2 - arch/powerpc/mm/book3s32/mmu.c | 39 +++------------- arch/powerpc/mm/ptdump/bats.c | 59 ------------------------- arch/powerpc/platforms/powermac/setup.c | 2 +- arch/powerpc/platforms/powermac/smp.c | 4 -- 17 files changed, 17 insertions(+), 206 deletions(-) diff --git a/arch/powerpc/boot/util.S b/arch/powerpc/boot/util.S index f11f0589a669..d03cdb7606dc 100644 --- a/arch/powerpc/boot/util.S +++ b/arch/powerpc/boot/util.S @@ -18,7 +18,7 @@ .text -/* udelay (on non-601 processors) needs to know the period of the +/* udelay needs to know the period of the * timebase in nanoseconds. This used to be hardcoded to be 60ns * (period of 66MHz/4). Now a variable is used that is initialized to * 60 for backward compatibility, but it can be overridden as necessary @@ -37,19 +37,6 @@ timebase_period_ns: */ .globl udelay udelay: - mfspr r4,SPRN_PVR - srwi r4,r4,16 - cmpwi 0,r4,1 /* 601 ? */ - bne .Ludelay_not_601 -00: li r0,86 /* Instructions / microsecond? */ - mtctr r0 -10: addi r0,r0,0 /* NOP */ - bdnz 10b - subic. r3,r3,1 - bne 00b - blr - -.Ludelay_not_601: mulli r4,r3,1000 /* nanoseconds */ /* Change r4 to be the number of ticks using: * (nanoseconds + (timebase_period_ns - 1 )) / timebase_period_ns diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index a1a300c1a20e..93bc70d4c9a1 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -295,8 +295,6 @@ static inline void cpu_feature_keys_init(void) { } #define CPU_FTR_MAYBE_CAN_NAP 0 #endif -#define CPU_FTRS_PPC601 (CPU_FTR_COMMON | \ - CPU_FTR_COHERENT_ICACHE) #define CPU_FTRS_603 (CPU_FTR_COMMON | CPU_FTR_MAYBE_CAN_DOZE | \ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE | CPU_FTR_NOEXECUTE) #define CPU_FTRS_604 (CPU_FTR_COMMON | CPU_FTR_PPC_LE) @@ -512,10 +510,8 @@ static inline void cpu_feature_keys_init(void) { } #else enum { CPU_FTRS_POSSIBLE = -#ifdef CONFIG_PPC_BOOK3S_601 - CPU_FTRS_PPC601 | -#elif defined(CONFIG_PPC_BOOK3S_32) - CPU_FTRS_PPC601 | CPU_FTRS_603 | CPU_FTRS_604 | CPU_FTRS_740_NOTAU | +#ifdef CONFIG_PPC_BOOK3S_32 + CPU_FTRS_603 | CPU_FTRS_604 | CPU_FTRS_740_NOTAU | CPU_FTRS_740 | CPU_FTRS_750 | CPU_FTRS_750FX1 | CPU_FTRS_750FX2 | CPU_FTRS_750FX | CPU_FTRS_750GX | CPU_FTRS_7400_NOTAU | CPU_FTRS_7400 | CPU_FTRS_7450_20 | @@ -590,9 +586,7 @@ enum { #else enum { CPU_FTRS_ALWAYS = -#ifdef CONFIG_PPC_BOOK3S_601 - CPU_FTRS_PPC601 & -#elif defined(CONFIG_PPC_BOOK3S_32) +#ifdef CONFIG_PPC_BOOK3S_32 CPU_FTRS_603 & CPU_FTRS_604 & CPU_FTRS_740_NOTAU & CPU_FTRS_740 & CPU_FTRS_750 & CPU_FTRS_750FX1 & CPU_FTRS_750FX2 & CPU_FTRS_750FX & CPU_FTRS_750GX & diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index 67a421b81a50..511786f0e40d 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -401,8 +401,7 @@ END_FTR_SECTION_NESTED(CPU_FTR_CELL_TB_BUG, CPU_FTR_CELL_TB_BUG, 96) #define MFTBU(dest) mfspr dest, SPRN_TBRU #endif -/* tlbsync is not implemented on 601 */ -#if !defined(CONFIG_SMP) || defined(CONFIG_PPC_BOOK3S_601) +#ifndef CONFIG_SMP #define TLBSYNC #else #define TLBSYNC tlbsync; sync diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h index 155a197c0aa1..e2c778c176a3 100644 --- a/arch/powerpc/include/asm/ptrace.h +++ b/arch/powerpc/include/asm/ptrace.h @@ -243,11 +243,7 @@ static inline void set_trap_norestart(struct pt_regs *regs) } #define arch_has_single_step() (1) -#ifndef CONFIG_PPC_BOOK3S_601 #define arch_has_block_step() (true) -#else -#define arch_has_block_step() (false) -#endif #define ARCH_HAS_USER_SINGLE_STEP_REPORT /* diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h index cb326720a8a1..ce065589192a 100644 --- a/arch/powerpc/include/asm/time.h +++ b/arch/powerpc/include/asm/time.h @@ -39,7 +39,7 @@ struct div_result { }; /* Accessor functions for the timebase (RTC on 601) registers. */ -#define __USE_RTC() (IS_ENABLED(CONFIG_PPC_BOOK3S_601)) +#define __USE_RTC() (0) #ifdef CONFIG_PPC64 diff --git a/arch/powerpc/include/asm/timex.h b/arch/powerpc/include/asm/timex.h index 6047402b0a4d..95988870a57b 100644 --- a/arch/powerpc/include/asm/timex.h +++ b/arch/powerpc/include/asm/timex.h @@ -17,9 +17,6 @@ typedef unsigned long cycles_t; static inline cycles_t get_cycles(void) { - if (IS_ENABLED(CONFIG_PPC_BOOK3S_601)) - return 0; - return mftb(); } diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c index 02300edc6989..b609fb39dba8 100644 --- a/arch/powerpc/kernel/btext.c +++ b/arch/powerpc/kernel/btext.c @@ -95,18 +95,12 @@ void __init btext_prepare_BAT(void) boot_text_mapped = 0; return; } - if (PVR_VER(mfspr(SPRN_PVR)) != 1) { + { /* 603, 604, G3, G4, ... */ lowbits = addr & ~0xFF000000UL; addr &= 0xFF000000UL; disp_BAT[0] = vaddr | (BL_16M<<2) | 2; disp_BAT[1] = addr | (_PAGE_NO_CACHE | _PAGE_GUARDED | BPP_RW); - } else { - /* 601 */ - lowbits = addr & ~0xFF800000UL; - addr &= 0xFF800000UL; - disp_BAT[0] = vaddr | (_PAGE_NO_CACHE | PP_RWXX) | 4; - disp_BAT[1] = addr | BL_8M | 0x40; } logicalDisplayBase = (void *) (vaddr + lowbits); } diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index f25ea188ecd3..8cdc8bcde703 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -811,19 +811,11 @@ _ASM_NOKPROBE_SYMBOL(fast_exception_return) 1: lis r3,exc_exit_restart_end@ha addi r3,r3,exc_exit_restart_end@l cmplw r12,r3 -#ifdef CONFIG_PPC_BOOK3S_601 - bge 2b -#else bge 3f -#endif lis r4,exc_exit_restart@ha addi r4,r4,exc_exit_restart@l cmplw r12,r4 -#ifdef CONFIG_PPC_BOOK3S_601 - blt 2b -#else blt 3f -#endif lis r3,fee_restarts@ha tophys(r3,r3) lwz r5,fee_restarts@l(r3) @@ -840,7 +832,6 @@ fee_restarts: /* aargh, a nonrecoverable interrupt, panic */ /* aargh, we don't know which trap this is */ -/* but the 601 doesn't implement the RI bit, so assume it's OK */ 3: li r10,-1 stw r10,_TRAP(r11) @@ -1302,19 +1293,11 @@ nonrecoverable: lis r10,exc_exit_restart_end@ha addi r10,r10,exc_exit_restart_end@l cmplw r12,r10 -#ifdef CONFIG_PPC_BOOK3S_601 - bgelr -#else bge 3f -#endif lis r11,exc_exit_restart@ha addi r11,r11,exc_exit_restart@l cmplw r12,r11 -#ifdef CONFIG_PPC_BOOK3S_601 - bltlr -#else blt 3f -#endif lis r10,ee_restarts@ha lwz r12,ee_restarts@l(r10) addi r12,r12,1 @@ -1322,7 +1305,6 @@ nonrecoverable: mr r12,r11 /* restart at exc_exit_restart */ blr 3: /* OK, we can't recover, kill this process */ - /* but the 601 doesn't implement the RI bit, so assume it's OK */ lwz r3,_TRAP(r1) andi. r0,r3,1 beq 5f diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index 48cde60334a2..b14524d4534c 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -34,16 +34,6 @@ #include "head_32.h" -/* 601 only have IBAT */ -#ifdef CONFIG_PPC_BOOK3S_601 -#define LOAD_BAT(n, reg, RA, RB) \ - li RA,0; \ - mtspr SPRN_IBAT##n##U,RA; \ - lwz RA,(n*16)+0(reg); \ - lwz RB,(n*16)+4(reg); \ - mtspr SPRN_IBAT##n##U,RA; \ - mtspr SPRN_IBAT##n##L,RB -#else #define LOAD_BAT(n, reg, RA, RB) \ /* see the comment for clear_bats() -- Cort */ \ li RA,0; \ @@ -57,7 +47,6 @@ lwz RB,(n*16)+12(reg); \ mtspr SPRN_DBAT##n##U,RA; \ mtspr SPRN_DBAT##n##L,RB -#endif __HEAD .stabs "arch/powerpc/kernel/",N_SO,0,0,0f @@ -432,7 +421,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_FPU_UNAVAILABLE) SystemCall: SYSCALL_ENTRY 0xc00 -/* Single step - not used on 601 */ EXCEPTION(0xd00, SingleStep, single_step_exception, EXC_XFER_STD) EXCEPTION(0xe00, Trap_0e, unknown_exception, EXC_XFER_STD) @@ -974,8 +962,7 @@ load_up_mmu: lwz r6,_SDR1@l(r6) mtspr SPRN_SDR1,r6 -/* Load the BAT registers with the values set up by MMU_init. - MMU_init takes care of whether we're on a 601 or not. */ +/* Load the BAT registers with the values set up by MMU_init. */ lis r3,BATS@ha addi r3,r3,BATS@l tophys(r3,r3) @@ -1152,7 +1139,6 @@ EXPORT_SYMBOL(switch_mmu_context) clear_bats: li r10,0 -#ifndef CONFIG_PPC_BOOK3S_601 mtspr SPRN_DBAT0U,r10 mtspr SPRN_DBAT0L,r10 mtspr SPRN_DBAT1U,r10 @@ -1161,7 +1147,6 @@ clear_bats: mtspr SPRN_DBAT2L,r10 mtspr SPRN_DBAT3U,r10 mtspr SPRN_DBAT3L,r10 -#endif mtspr SPRN_IBAT0U,r10 mtspr SPRN_IBAT0L,r10 mtspr SPRN_IBAT1U,r10 @@ -1252,26 +1237,9 @@ mmu_off: sync RFI -/* - * On 601, we use 3 BATs to map up to 24M of RAM at _PAGE_OFFSET - * (we keep one for debugging) and on others, we use one 256M BAT. - */ +/* We use one BAT to map up to 256M of RAM at _PAGE_OFFSET */ initial_bats: lis r11,PAGE_OFFSET@h -#ifdef CONFIG_PPC_BOOK3S_601 - ori r11,r11,4 /* set up BAT registers for 601 */ - li r8,0x7f /* valid, block length = 8MB */ - mtspr SPRN_IBAT0U,r11 /* N.B. 601 has valid bit in */ - mtspr SPRN_IBAT0L,r8 /* lower BAT register */ - addis r11,r11,0x800000@h - addis r8,r8,0x800000@h - mtspr SPRN_IBAT1U,r11 - mtspr SPRN_IBAT1L,r8 - addis r11,r11,0x800000@h - addis r8,r8,0x800000@h - mtspr SPRN_IBAT2U,r11 - mtspr SPRN_IBAT2L,r8 -#else tophys(r8,r11) #ifdef CONFIG_SMP ori r8,r8,0x12 /* R/W access, M=1 */ @@ -1280,11 +1248,10 @@ initial_bats: #endif /* CONFIG_SMP */ ori r11,r11,BL_256M<<2|0x2 /* set up BAT registers for 604 */ - mtspr SPRN_DBAT0L,r8 /* N.B. 6xx (not 601) have valid */ + mtspr SPRN_DBAT0L,r8 /* N.B. 6xx have valid */ mtspr SPRN_DBAT0U,r11 /* bit in upper BAT register */ mtspr SPRN_IBAT0L,r8 mtspr SPRN_IBAT0U,r11 -#endif isync blr @@ -1302,13 +1269,8 @@ setup_disp_bat: beqlr lwz r11,0(r8) lwz r8,4(r8) -#ifndef CONFIG_PPC_BOOK3S_601 mtspr SPRN_DBAT3L,r8 mtspr SPRN_DBAT3U,r11 -#else - mtspr SPRN_IBAT3L,r8 - mtspr SPRN_IBAT3U,r11 -#endif blr #endif /* CONFIG_BOOTX_TEXT */ diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 1823706ae076..057d6b8e9bb0 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -223,6 +223,6 @@ __init void initialize_cache_info(void) dcache_bsize = cur_cpu_spec->dcache_bsize; icache_bsize = cur_cpu_spec->icache_bsize; ucache_bsize = 0; - if (IS_ENABLED(CONFIG_PPC_BOOK3S_601) || IS_ENABLED(CONFIG_E200)) + if (IS_ENABLED(CONFIG_E200)) ucache_bsize = icache_bsize = dcache_bsize; } diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index d1ebe152f210..c5f39f13e96e 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -529,9 +529,6 @@ out: * Check if the NIP corresponds to the address of a sync * instruction for which there is an entry in the exception * table. - * Note that the 601 only takes a machine check on TEA - * (transfer error ack) signal assertion, and does not - * set any of the top 16 bits of SRR1. * -- paulus. */ static inline int check_io_access(struct pt_regs *regs) @@ -796,7 +793,6 @@ int machine_check_generic(struct pt_regs *regs) case 0x80000: pr_cont("Machine check signal\n"); break; - case 0: /* for 601 */ case 0x40000: case 0x140000: /* 7450 MSS error and TEA */ pr_cont("Transfer error ack signal\n"); diff --git a/arch/powerpc/kernel/vdso32/datapage.S b/arch/powerpc/kernel/vdso32/datapage.S index 217bb630f8f9..1d23e2771dba 100644 --- a/arch/powerpc/kernel/vdso32/datapage.S +++ b/arch/powerpc/kernel/vdso32/datapage.S @@ -47,7 +47,6 @@ V_FUNCTION_END(__kernel_get_syscall_map) * * returns the timebase frequency in HZ */ -#ifndef CONFIG_PPC_BOOK3S_601 V_FUNCTION_BEGIN(__kernel_get_tbfreq) .cfi_startproc mflr r12 @@ -60,4 +59,3 @@ V_FUNCTION_BEGIN(__kernel_get_tbfreq) blr .cfi_endproc V_FUNCTION_END(__kernel_get_tbfreq) -#endif diff --git a/arch/powerpc/kernel/vdso32/vdso32.lds.S b/arch/powerpc/kernel/vdso32/vdso32.lds.S index 5206c2eb2a1d..7eadac74c7f9 100644 --- a/arch/powerpc/kernel/vdso32/vdso32.lds.S +++ b/arch/powerpc/kernel/vdso32/vdso32.lds.S @@ -144,13 +144,11 @@ VERSION __kernel_datapage_offset; __kernel_get_syscall_map; -#ifndef CONFIG_PPC_BOOK3S_601 __kernel_gettimeofday; __kernel_clock_gettime; __kernel_clock_getres; __kernel_time; __kernel_get_tbfreq; -#endif __kernel_sync_dicache; __kernel_sync_dicache_p5; __kernel_sigtramp32; diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c index d426eaf76bb0..771d607f1a3d 100644 --- a/arch/powerpc/mm/book3s32/mmu.c +++ b/arch/powerpc/mm/book3s32/mmu.c @@ -74,14 +74,7 @@ static int find_free_bat(void) { int b; - if (IS_ENABLED(CONFIG_PPC_BOOK3S_601)) { - for (b = 0; b < 4; b++) { - struct ppc_bat *bat = BATS[b]; - - if (!(bat[0].batl & 0x40)) - return b; - } - } else { + { int n = mmu_has_feature(MMU_FTR_USE_HIGH_BATS) ? 8 : 4; for (b = 0; b < n; b++) { @@ -97,7 +90,7 @@ static int find_free_bat(void) /* * This function calculates the size of the larger block usable to map the * beginning of an area based on the start address and size of that area: - * - max block size is 8M on 601 and 256 on other 6xx. + * - max block size is 256 on 6xx. * - base address must be aligned to the block size. So the maximum block size * is identified by the lowest bit set to 1 in the base address (for instance * if base is 0x16000000, max size is 0x02000000). @@ -106,7 +99,7 @@ static int find_free_bat(void) */ static unsigned int block_size(unsigned long base, unsigned long top) { - unsigned int max_size = IS_ENABLED(CONFIG_PPC_BOOK3S_601) ? SZ_8M : SZ_256M; + unsigned int max_size = SZ_256M; unsigned int base_shift = (ffs(base) - 1) & 31; unsigned int block_shift = (fls(top - base) - 1) & 31; @@ -117,7 +110,6 @@ static unsigned int block_size(unsigned long base, unsigned long top) * Set up one of the IBAT (block address translation) register pairs. * The parameters are not checked; in particular size must be a power * of 2 between 128k and 256M. - * Only for 603+ ... */ static void setibat(int index, unsigned long virt, phys_addr_t phys, unsigned int size, pgprot_t prot) @@ -214,9 +206,6 @@ void mmu_mark_initmem_nx(void) unsigned long border = (unsigned long)__init_begin - PAGE_OFFSET; unsigned long size; - if (IS_ENABLED(CONFIG_PPC_BOOK3S_601)) - return; - for (i = 0; i < nb - 1 && base < top && top - base > (128 << 10);) { size = block_size(base, top); setibat(i++, PAGE_OFFSET + base, base, size, PAGE_KERNEL_TEXT); @@ -253,9 +242,6 @@ void mmu_mark_rodata_ro(void) int nb = mmu_has_feature(MMU_FTR_USE_HIGH_BATS) ? 8 : 4; int i; - if (IS_ENABLED(CONFIG_PPC_BOOK3S_601)) - return; - for (i = 0; i < nb; i++) { struct ppc_bat *bat = BATS[i]; @@ -294,8 +280,7 @@ void __init setbat(int index, unsigned long virt, phys_addr_t phys, flags &= ~_PAGE_COHERENT; bl = (size >> 17) - 1; - if (!IS_ENABLED(CONFIG_PPC_BOOK3S_601)) { - /* 603, 604, etc. */ + { /* Do DBAT first */ wimgxpp = flags & (_PAGE_WRITETHRU | _PAGE_NO_CACHE | _PAGE_COHERENT | _PAGE_GUARDED); @@ -312,16 +297,6 @@ void __init setbat(int index, unsigned long virt, phys_addr_t phys, bat[0] = bat[1]; else bat[0].batu = bat[0].batl = 0; - } else { - /* 601 cpu */ - if (bl > BL_8M) - bl = BL_8M; - wimgxpp = flags & (_PAGE_WRITETHRU | _PAGE_NO_CACHE - | _PAGE_COHERENT); - wimgxpp |= (flags & _PAGE_RW)? - ((flags & _PAGE_USER)? PP_RWRW: PP_RWXX): PP_RXRX; - bat->batu = virt | wimgxpp | 4; /* Ks=0, Ku=1 */ - bat->batl = phys | bl | 0x40; /* V=1 */ } bat_addrs[index].start = virt; @@ -474,11 +449,7 @@ void setup_initial_memory_limit(phys_addr_t first_memblock_base, */ BUG_ON(first_memblock_base != 0); - /* 601 can only access 16MB at the moment */ - if (IS_ENABLED(CONFIG_PPC_BOOK3S_601)) - memblock_set_current_limit(min_t(u64, first_memblock_size, 0x01000000)); - else /* Anything else has 256M mapped */ - memblock_set_current_limit(min_t(u64, first_memblock_size, 0x10000000)); + memblock_set_current_limit(min_t(u64, first_memblock_size, SZ_256M)); } void __init print_system_hash_info(void) diff --git a/arch/powerpc/mm/ptdump/bats.c b/arch/powerpc/mm/ptdump/bats.c index e29b338d499f..c4c628b03cf8 100644 --- a/arch/powerpc/mm/ptdump/bats.c +++ b/arch/powerpc/mm/ptdump/bats.c @@ -12,62 +12,6 @@ #include "ptdump.h" -static char *pp_601(int k, int pp) -{ - if (pp == 0) - return k ? " " : "rwx"; - if (pp == 1) - return k ? "r x" : "rwx"; - if (pp == 2) - return "rwx"; - return "r x"; -} - -static void bat_show_601(struct seq_file *m, int idx, u32 lower, u32 upper) -{ - u32 blpi = upper & 0xfffe0000; - u32 k = (upper >> 2) & 3; - u32 pp = upper & 3; - phys_addr_t pbn = PHYS_BAT_ADDR(lower); - u32 bsm = lower & 0x3ff; - u32 size = (bsm + 1) << 17; - - seq_printf(m, "%d: ", idx); - if (!(lower & 0x40)) { - seq_puts(m, " -\n"); - return; - } - - seq_printf(m, "0x%08x-0x%08x ", blpi, blpi + size - 1); -#ifdef CONFIG_PHYS_64BIT - seq_printf(m, "0x%016llx ", pbn); -#else - seq_printf(m, "0x%08x ", pbn); -#endif - pt_dump_size(m, size); - - seq_printf(m, "Kernel %s User %s", pp_601(k & 2, pp), pp_601(k & 1, pp)); - - seq_puts(m, lower & _PAGE_WRITETHRU ? "w " : " "); - seq_puts(m, lower & _PAGE_NO_CACHE ? "i " : " "); - seq_puts(m, lower & _PAGE_COHERENT ? "m " : " "); - seq_puts(m, "\n"); -} - -#define BAT_SHOW_601(_m, _n, _l, _u) bat_show_601(_m, _n, mfspr(_l), mfspr(_u)) - -static int bats_show_601(struct seq_file *m, void *v) -{ - seq_puts(m, "---[ Block Address Translation ]---\n"); - - BAT_SHOW_601(m, 0, SPRN_IBAT0L, SPRN_IBAT0U); - BAT_SHOW_601(m, 1, SPRN_IBAT1L, SPRN_IBAT1U); - BAT_SHOW_601(m, 2, SPRN_IBAT2L, SPRN_IBAT2U); - BAT_SHOW_601(m, 3, SPRN_IBAT3L, SPRN_IBAT3U); - - return 0; -} - static void bat_show_603(struct seq_file *m, int idx, u32 lower, u32 upper, bool is_d) { u32 bepi = upper & 0xfffe0000; @@ -146,9 +90,6 @@ static int bats_show_603(struct seq_file *m, void *v) static int bats_open(struct inode *inode, struct file *file) { - if (IS_ENABLED(CONFIG_PPC_BOOK3S_601)) - return single_open(file, bats_show_601, NULL); - return single_open(file, bats_show_603, NULL); } diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c index f002b0fa69b8..2e2cc0c75d87 100644 --- a/arch/powerpc/platforms/powermac/setup.c +++ b/arch/powerpc/platforms/powermac/setup.c @@ -284,7 +284,7 @@ static void __init pmac_setup_arch(void) /* 604, G3, G4 etc. */ loops_per_jiffy = *fp / HZ; else - /* 601, 603, etc. */ + /* 603, etc. */ loops_per_jiffy = *fp / (2 * HZ); of_node_put(cpu); break; diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c index a6fedcfb714f..74ebe664b016 100644 --- a/arch/powerpc/platforms/powermac/smp.c +++ b/arch/powerpc/platforms/powermac/smp.c @@ -270,10 +270,6 @@ static void __init smp_psurge_probe(void) int i, ncpus; struct device_node *dn; - /* We don't do SMP on the PPC601 -- paulus */ - if (PVR_VER(mfspr(SPRN_PVR)) == 1) - return; - /* * The powersurge cpu board can be used in the generation * of powermacs that have a socket for an upgradeable cpu card, From 2e38ea486615bddbc7a42d002aee93a3a9e7a36f Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Tue, 29 Sep 2020 06:48:37 +0000 Subject: [PATCH 382/645] powerpc: Tidy up a bit after removal of PowerPC 601. The removal of the 601 left some standalone blocks from former if/else. Drop the { } and re-indent. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/31c4cd093963f22831bf388449056ee045533d3b.1601362098.git.christophe.leroy@csgroup.eu --- arch/powerpc/kernel/btext.c | 11 +++------ arch/powerpc/mm/book3s32/mmu.c | 45 +++++++++++++++------------------- 2 files changed, 24 insertions(+), 32 deletions(-) diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c index b609fb39dba8..c22a8e0dbc93 100644 --- a/arch/powerpc/kernel/btext.c +++ b/arch/powerpc/kernel/btext.c @@ -95,13 +95,10 @@ void __init btext_prepare_BAT(void) boot_text_mapped = 0; return; } - { - /* 603, 604, G3, G4, ... */ - lowbits = addr & ~0xFF000000UL; - addr &= 0xFF000000UL; - disp_BAT[0] = vaddr | (BL_16M<<2) | 2; - disp_BAT[1] = addr | (_PAGE_NO_CACHE | _PAGE_GUARDED | BPP_RW); - } + lowbits = addr & ~0xFF000000UL; + addr &= 0xFF000000UL; + disp_BAT[0] = vaddr | (BL_16M<<2) | 2; + disp_BAT[1] = addr | (_PAGE_NO_CACHE | _PAGE_GUARDED | BPP_RW); logicalDisplayBase = (void *) (vaddr + lowbits); } #endif diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c index 771d607f1a3d..741e4fc990c7 100644 --- a/arch/powerpc/mm/book3s32/mmu.c +++ b/arch/powerpc/mm/book3s32/mmu.c @@ -73,16 +73,13 @@ unsigned long p_block_mapped(phys_addr_t pa) static int find_free_bat(void) { int b; + int n = mmu_has_feature(MMU_FTR_USE_HIGH_BATS) ? 8 : 4; - { - int n = mmu_has_feature(MMU_FTR_USE_HIGH_BATS) ? 8 : 4; + for (b = 0; b < n; b++) { + struct ppc_bat *bat = BATS[b]; - for (b = 0; b < n; b++) { - struct ppc_bat *bat = BATS[b]; - - if (!(bat[1].batu & 3)) - return b; - } + if (!(bat[1].batu & 3)) + return b; } return -1; } @@ -280,24 +277,22 @@ void __init setbat(int index, unsigned long virt, phys_addr_t phys, flags &= ~_PAGE_COHERENT; bl = (size >> 17) - 1; - { - /* Do DBAT first */ - wimgxpp = flags & (_PAGE_WRITETHRU | _PAGE_NO_CACHE - | _PAGE_COHERENT | _PAGE_GUARDED); - wimgxpp |= (flags & _PAGE_RW)? BPP_RW: BPP_RX; - bat[1].batu = virt | (bl << 2) | 2; /* Vs=1, Vp=0 */ - bat[1].batl = BAT_PHYS_ADDR(phys) | wimgxpp; - if (flags & _PAGE_USER) - bat[1].batu |= 1; /* Vp = 1 */ - if (flags & _PAGE_GUARDED) { - /* G bit must be zero in IBATs */ - flags &= ~_PAGE_EXEC; - } - if (flags & _PAGE_EXEC) - bat[0] = bat[1]; - else - bat[0].batu = bat[0].batl = 0; + /* Do DBAT first */ + wimgxpp = flags & (_PAGE_WRITETHRU | _PAGE_NO_CACHE + | _PAGE_COHERENT | _PAGE_GUARDED); + wimgxpp |= (flags & _PAGE_RW)? BPP_RW: BPP_RX; + bat[1].batu = virt | (bl << 2) | 2; /* Vs=1, Vp=0 */ + bat[1].batl = BAT_PHYS_ADDR(phys) | wimgxpp; + if (flags & _PAGE_USER) + bat[1].batu |= 1; /* Vp = 1 */ + if (flags & _PAGE_GUARDED) { + /* G bit must be zero in IBATs */ + flags &= ~_PAGE_EXEC; } + if (flags & _PAGE_EXEC) + bat[0] = bat[1]; + else + bat[0].batu = bat[0].batl = 0; bat_addrs[index].start = virt; bat_addrs[index].limit = virt + ((bl + 1) << 17) - 1; From a4c5a355422920bcbfe3fd1f01aead2d3a2a820c Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Tue, 29 Sep 2020 06:48:38 +0000 Subject: [PATCH 383/645] powerpc: Remove __USE_RTC() Now that PowerPC 601 is gone, __USE_RTC() is never true. Remove it. That also leads to removing get_rtc() and get_rtcl() Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/4757e1ed21fe1968c761ae081d1f3d790a9673f8.1601362098.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/time.h | 28 +----------------- arch/powerpc/kernel/time.c | 52 +++++---------------------------- 2 files changed, 9 insertions(+), 71 deletions(-) diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h index ce065589192a..caf68a4bc19e 100644 --- a/arch/powerpc/include/asm/time.h +++ b/arch/powerpc/include/asm/time.h @@ -38,9 +38,6 @@ struct div_result { u64 result_low; }; -/* Accessor functions for the timebase (RTC on 601) registers. */ -#define __USE_RTC() (0) - #ifdef CONFIG_PPC64 /* For compatibility, get_tbl() is defined as get_tb() on ppc64 */ @@ -59,25 +56,6 @@ static inline unsigned int get_tbu(void) } #endif /* !CONFIG_PPC64 */ -static inline unsigned int get_rtcl(void) -{ - unsigned int rtcl; - - asm volatile("mfrtcl %0" : "=r" (rtcl)); - return rtcl; -} - -static inline u64 get_rtc(void) -{ - unsigned int hi, lo, hi2; - - do { - asm volatile("mfrtcu %0; mfrtcl %1; mfrtcu %2" - : "=r" (hi), "=r" (lo), "=r" (hi2)); - } while (hi2 != hi); - return (u64)hi * 1000000000 + lo; -} - static inline u64 get_vtb(void) { #ifdef CONFIG_PPC_BOOK3S_64 @@ -109,7 +87,7 @@ static inline u64 get_tb(void) static inline u64 get_tb_or_rtc(void) { - return __USE_RTC() ? get_rtc() : get_tb(); + return get_tb(); } static inline void set_tb(unsigned int upper, unsigned int lower) @@ -153,10 +131,6 @@ static inline void set_dec(u64 val) static inline unsigned long tb_ticks_since(unsigned long tstamp) { - if (__USE_RTC()) { - int delta = get_rtcl() - (unsigned int) tstamp; - return delta < 0 ? delta + 1000000000 : delta; - } return get_tbl() - tstamp; } diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index f85539ebb513..13c820c15d37 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -75,15 +75,6 @@ #include #include -static u64 rtc_read(struct clocksource *); -static struct clocksource clocksource_rtc = { - .name = "rtc", - .rating = 400, - .flags = CLOCK_SOURCE_IS_CONTINUOUS, - .mask = CLOCKSOURCE_MASK(64), - .read = rtc_read, -}; - static u64 timebase_read(struct clocksource *); static struct clocksource clocksource_timebase = { .name = "timebase", @@ -447,19 +438,9 @@ void vtime_flush(struct task_struct *tsk) void __delay(unsigned long loops) { unsigned long start; - int diff; spin_begin(); - if (__USE_RTC()) { - start = get_rtcl(); - do { - /* the RTCL register wraps at 1000000000 */ - diff = get_rtcl() - start; - if (diff < 0) - diff += 1000000000; - spin_cpu_relax(); - } while (diff < loops); - } else if (tb_invalid) { + if (tb_invalid) { /* * TB is in error state and isn't ticking anymore. * HMI handler was unable to recover from TB error. @@ -696,8 +677,6 @@ EXPORT_SYMBOL_GPL(tb_to_ns); */ notrace unsigned long long sched_clock(void) { - if (__USE_RTC()) - return get_rtc(); return mulhdu(get_tb() - boot_tb, tb_to_ns_scale) << tb_to_ns_shift; } @@ -847,11 +826,6 @@ void read_persistent_clock64(struct timespec64 *ts) } /* clocksource code */ -static notrace u64 rtc_read(struct clocksource *cs) -{ - return (u64)get_rtc(); -} - static notrace u64 timebase_read(struct clocksource *cs) { return (u64)get_tb(); @@ -948,12 +922,7 @@ void update_vsyscall_tz(void) static void __init clocksource_init(void) { - struct clocksource *clock; - - if (__USE_RTC()) - clock = &clocksource_rtc; - else - clock = &clocksource_timebase; + struct clocksource *clock = &clocksource_timebase; if (clocksource_register_hz(clock, tb_ticks_per_sec)) { printk(KERN_ERR "clocksource: %s is already registered\n", @@ -1071,17 +1040,12 @@ void __init time_init(void) u64 scale; unsigned shift; - if (__USE_RTC()) { - /* 601 processor: dec counts down by 128 every 128ns */ - ppc_tb_freq = 1000000000; - } else { - /* Normal PowerPC with timebase register */ - ppc_md.calibrate_decr(); - printk(KERN_DEBUG "time_init: decrementer frequency = %lu.%.6lu MHz\n", - ppc_tb_freq / 1000000, ppc_tb_freq % 1000000); - printk(KERN_DEBUG "time_init: processor frequency = %lu.%.6lu MHz\n", - ppc_proc_freq / 1000000, ppc_proc_freq % 1000000); - } + /* Normal PowerPC with timebase register */ + ppc_md.calibrate_decr(); + printk(KERN_DEBUG "time_init: decrementer frequency = %lu.%.6lu MHz\n", + ppc_tb_freq / 1000000, ppc_tb_freq % 1000000); + printk(KERN_DEBUG "time_init: processor frequency = %lu.%.6lu MHz\n", + ppc_proc_freq / 1000000, ppc_proc_freq % 1000000); tb_ticks_per_jiffy = ppc_tb_freq / HZ; tb_ticks_per_sec = ppc_tb_freq; From 6601ec1c2ba929430f5585ce7f9d9960b0e0a01d Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Tue, 29 Sep 2020 06:48:39 +0000 Subject: [PATCH 384/645] powerpc: Remove get_tb_or_rtc() 601 is gone, get_tb_or_rtc() is equivalent to get_tb(). Replace the former by the later. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/3e8a13ee83418630c753c30cb722ae682d5b2d39.1601362098.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/time.h | 5 ----- arch/powerpc/kernel/irq.c | 2 +- arch/powerpc/kernel/time.c | 6 +++--- 3 files changed, 4 insertions(+), 9 deletions(-) diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h index caf68a4bc19e..410ed72eef1c 100644 --- a/arch/powerpc/include/asm/time.h +++ b/arch/powerpc/include/asm/time.h @@ -85,11 +85,6 @@ static inline u64 get_tb(void) } #endif /* !CONFIG_PPC64 */ -static inline u64 get_tb_or_rtc(void) -{ - return get_tb(); -} - static inline void set_tb(unsigned int upper, unsigned int lower) { mtspr(SPRN_TBWL, 0); diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 631e6d236c97..7d0f7682d01d 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -104,7 +104,7 @@ static inline notrace unsigned long get_irq_happened(void) static inline notrace int decrementer_check_overflow(void) { - u64 now = get_tb_or_rtc(); + u64 now = get_tb(); u64 *next_tb = this_cpu_ptr(&decrementers_next_tb); return now >= *next_tb; diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 13c820c15d37..760ea359a7f7 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -595,7 +595,7 @@ void timer_interrupt(struct pt_regs *regs) irq_work_run(); } - now = get_tb_or_rtc(); + now = get_tb(); if (now >= *next_tb) { *next_tb = ~(u64)0; if (evt->event_handler) @@ -937,7 +937,7 @@ static void __init clocksource_init(void) static int decrementer_set_next_event(unsigned long evt, struct clock_event_device *dev) { - __this_cpu_write(decrementers_next_tb, get_tb_or_rtc() + evt); + __this_cpu_write(decrementers_next_tb, get_tb() + evt); set_dec(evt); /* We may have raced with new irq work */ @@ -1071,7 +1071,7 @@ void __init time_init(void) tb_to_ns_scale = scale; tb_to_ns_shift = shift; /* Save the current timebase to pretty up CONFIG_PRINTK_TIME */ - boot_tb = get_tb_or_rtc(); + boot_tb = get_tb(); /* If platform provided a timezone (pmac), we correct the time */ if (timezone_offset) { From 63f9d9df5ed0d4f3a2c0cd08730e1cae1edd11bf Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Thu, 1 Oct 2020 10:59:19 +0000 Subject: [PATCH 385/645] powerpc/time: Remove ifdef in get_dec() and set_dec() Move SPRN_PIT definition in reg.h. This allows to remove ifdef in get_dec() and set_dec() and makes them more readable. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/3c9a6eb0fc040868ac59be66f338d08fd017668d.1601549945.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/reg.h | 2 ++ arch/powerpc/include/asm/reg_booke.h | 1 - arch/powerpc/include/asm/time.h | 23 ++++++++++------------- 3 files changed, 12 insertions(+), 14 deletions(-) diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index d25c357a873c..788058af1d44 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -521,6 +521,8 @@ #define SPRN_TSCR 0x399 /* Thread Switch Control Register */ #define SPRN_DEC 0x016 /* Decrement Register */ +#define SPRN_PIT 0x3DB /* Programmable Interval Timer (40x/BOOKE) */ + #define SPRN_DER 0x095 /* Debug Enable Register */ #define DER_RSTE 0x40000000 /* Reset Interrupt */ #define DER_CHSTPE 0x20000000 /* Check Stop */ diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h index ff30f1076162..29a948e0c0f2 100644 --- a/arch/powerpc/include/asm/reg_booke.h +++ b/arch/powerpc/include/asm/reg_booke.h @@ -174,7 +174,6 @@ #define SPRN_L1CSR1 0x3F3 /* L1 Cache Control and Status Register 1 */ #define SPRN_MMUCSR0 0x3F4 /* MMU Control and Status Register 0 */ #define SPRN_MMUCFG 0x3F7 /* MMU Configuration Register */ -#define SPRN_PIT 0x3DB /* Programmable Interval Timer */ #define SPRN_BUCSR 0x3F5 /* Branch Unit Control and Status */ #define SPRN_L2CSR0 0x3F9 /* L2 Data Cache Control and Status Register 0 */ #define SPRN_L2CSR1 0x3FA /* L2 Data Cache Control and Status Register 1 */ diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h index 410ed72eef1c..a0c8ae4cb27c 100644 --- a/arch/powerpc/include/asm/time.h +++ b/arch/powerpc/include/asm/time.h @@ -100,11 +100,10 @@ static inline void set_tb(unsigned int upper, unsigned int lower) */ static inline u64 get_dec(void) { -#if defined(CONFIG_40x) - return (mfspr(SPRN_PIT)); -#else - return (mfspr(SPRN_DEC)); -#endif + if (IS_ENABLED(CONFIG_40x)) + return mfspr(SPRN_PIT); + + return mfspr(SPRN_DEC); } /* @@ -114,14 +113,12 @@ static inline u64 get_dec(void) */ static inline void set_dec(u64 val) { -#if defined(CONFIG_40x) - mtspr(SPRN_PIT, (u32) val); -#else -#ifndef CONFIG_BOOKE - --val; -#endif - mtspr(SPRN_DEC, val); -#endif /* not 40x */ + if (IS_ENABLED(CONFIG_40x)) + mtspr(SPRN_PIT, (u32)val); + else if (IS_ENABLED(CONFIG_BOOKE)) + mtspr(SPRN_DEC, val); + else + mtspr(SPRN_DEC, val - 1); } static inline unsigned long tb_ticks_since(unsigned long tstamp) From 69a1593abdbcf03a76367320d929a8ae7a5e3d71 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Thu, 1 Oct 2020 15:35:38 +0000 Subject: [PATCH 386/645] powerpc/32s: Setup the early hash table at all time. At the time being, an early hash table is set up when CONFIG_KASAN is selected. There is nothing wrong with setting such an early hash table all the time, even if it is not used. This is a statically allocated 256 kB table which lies in the init data section. This makes the code simpler and may in the future allow to setup early IO mappings with fixmap instead of hard coding BATs. Put create_hpte() and flush_hash_pages() in the .ref.text section in order to avoid warning for the reference to early_hash[]. This reference is removed by MMU_init_hw_patch() before init memory is freed. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/b8f8101c368b8a6451844a58d7bd7d83c14cf2aa.1601566529.git.christophe.leroy@csgroup.eu --- arch/powerpc/kernel/head_32.S | 13 +++++-------- arch/powerpc/mm/book3s32/hash_low.S | 9 +++++++-- arch/powerpc/mm/book3s32/mmu.c | 14 +++++--------- arch/powerpc/mm/kasan/kasan_init_32.c | 19 ------------------- 4 files changed, 17 insertions(+), 38 deletions(-) diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index b14524d4534c..6dc77419147e 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -155,9 +155,9 @@ __after_mmu_off: bl initial_bats bl load_segment_registers -#ifdef CONFIG_KASAN +BEGIN_MMU_FTR_SECTION bl early_hash_table -#endif +END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) #if defined(CONFIG_BOOTX_TEXT) bl setup_disp_bat #endif @@ -936,7 +936,6 @@ _ENTRY(__restore_cpu_setup) * Load stuff into the MMU. Intended to be called with * IR=0 and DR=0. */ -#ifdef CONFIG_KASAN early_hash_table: sync /* Force all PTE updates to finish */ isync @@ -947,8 +946,10 @@ early_hash_table: lis r6, early_hash - PAGE_OFFSET@h ori r6, r6, 3 /* 256kB table */ mtspr SPRN_SDR1, r6 + lis r6, early_hash@h + lis r3, Hash@ha + stw r6, Hash@l(r3) blr -#endif load_up_mmu: sync /* Force all PTE updates to finish */ @@ -1037,11 +1038,7 @@ start_here: bl machine_init bl __save_cpu_setup bl MMU_init -#ifdef CONFIG_KASAN -BEGIN_MMU_FTR_SECTION bl MMU_init_hw_patch -END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) -#endif /* * Go back to running unmapped so we can load up new values diff --git a/arch/powerpc/mm/book3s32/hash_low.S b/arch/powerpc/mm/book3s32/hash_low.S index 3143de6ae769..b2c912e517b9 100644 --- a/arch/powerpc/mm/book3s32/hash_low.S +++ b/arch/powerpc/mm/book3s32/hash_low.S @@ -15,6 +15,7 @@ */ #include +#include #include #include #include @@ -284,9 +285,9 @@ _ASM_NOKPROBE_SYMBOL(add_hash_page) * * For speed, 4 of the instructions get patched once the size and * physical address of the hash table are known. These definitions - * of Hash_base and Hash_bits below are just an example. + * of Hash_base and Hash_bits below are for the early hash table. */ -Hash_base = 0xc0180000 +Hash_base = early_hash Hash_bits = 12 /* e.g. 256kB hash table */ Hash_msk = (((1 << Hash_bits) - 1) * 64) @@ -307,6 +308,7 @@ Hash_msk = (((1 << Hash_bits) - 1) * 64) #define HASH_LEFT 31-(LG_PTEG_SIZE+Hash_bits-1) #define HASH_RIGHT 31-LG_PTEG_SIZE +__REF _GLOBAL(create_hpte) /* Convert linux-style PTE (r5) to low word of PPC-style PTE (r8) */ rlwinm r8,r5,32-9,30,30 /* _PAGE_RW -> PP msb */ @@ -473,6 +475,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT) sync /* make sure pte updates get to memory */ blr + .previous _ASM_NOKPROBE_SYMBOL(create_hpte) .section .bss @@ -493,6 +496,7 @@ htab_hash_searches: * * We assume that there is a hash table in use (Hash != 0). */ +__REF _GLOBAL(flush_hash_pages) /* * We disable interrupts here, even on UP, because we want @@ -626,6 +630,7 @@ _GLOBAL(flush_hash_pages) 19: mtmsr r10 isync blr + .previous EXPORT_SYMBOL(flush_hash_pages) _ASM_NOKPROBE_SYMBOL(flush_hash_pages) diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c index 741e4fc990c7..a59e7ec98180 100644 --- a/arch/powerpc/mm/book3s32/mmu.c +++ b/arch/powerpc/mm/book3s32/mmu.c @@ -31,6 +31,8 @@ #include +u8 __initdata early_hash[SZ_256K] __aligned(SZ_256K) = {0}; + struct hash_pte *Hash; static unsigned long Hash_size, Hash_mask; unsigned long _SDR1; @@ -395,15 +397,6 @@ void __init MMU_init_hw(void) hash_mb2 = hash_mb = 32 - LG_HPTEG_SIZE - lg_n_hpteg; if (lg_n_hpteg > 16) hash_mb2 = 16 - LG_HPTEG_SIZE; - - /* - * When KASAN is selected, there is already an early temporary hash - * table and the switch to the final hash table is done later. - */ - if (IS_ENABLED(CONFIG_KASAN)) - return; - - MMU_init_hw_patch(); } void __init MMU_init_hw_patch(void) @@ -411,6 +404,9 @@ void __init MMU_init_hw_patch(void) unsigned int hmask = Hash_mask >> (16 - LG_HPTEG_SIZE); unsigned int hash = (unsigned int)Hash - PAGE_OFFSET; + if (!mmu_has_feature(MMU_FTR_HPTE_TABLE)) + return; + if (ppc_md.progress) ppc_md.progress("hash:patch", 0x345); if (ppc_md.progress) diff --git a/arch/powerpc/mm/kasan/kasan_init_32.c b/arch/powerpc/mm/kasan/kasan_init_32.c index 929716ea21e9..59f61efc43af 100644 --- a/arch/powerpc/mm/kasan/kasan_init_32.c +++ b/arch/powerpc/mm/kasan/kasan_init_32.c @@ -174,22 +174,6 @@ void __init kasan_late_init(void) kasan_unmap_early_shadow_vmalloc(); } -#ifdef CONFIG_PPC_BOOK3S_32 -u8 __initdata early_hash[256 << 10] __aligned(256 << 10) = {0}; - -static void __init kasan_early_hash_table(void) -{ - unsigned int hash = __pa(early_hash); - - modify_instruction_site(&patch__hash_page_A0, 0xffff, hash >> 16); - modify_instruction_site(&patch__flush_hash_A0, 0xffff, hash >> 16); - - Hash = (struct hash_pte *)early_hash; -} -#else -static void __init kasan_early_hash_table(void) {} -#endif - void __init kasan_early_init(void) { unsigned long addr = KASAN_SHADOW_START; @@ -205,7 +189,4 @@ void __init kasan_early_init(void) next = pgd_addr_end(addr, end); pmd_populate_kernel(&init_mm, pmd, kasan_early_shadow_pte); } while (pmd++, addr = next, addr != end); - - if (early_mmu_has_feature(MMU_FTR_HPTE_TABLE)) - kasan_early_hash_table(); } From 533090e5a980ad80bbe0961b4ed45a9bcf55cc0c Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Tue, 6 Oct 2020 09:05:26 +0000 Subject: [PATCH 387/645] powerpc/32s: Rename head_32.S to head_book3s_32.S Unlike PPC64 which had a single head_64.S, PPC32 are multiple ones. There is the head_32.S, selected by default based on the value of BITS and overridden based on some CONFIG_ values. This leads to thinking that it may be selected by different types of PPC32 platform but indeed it ends up being selected by book3s/32 only. Make that explicit by: - Not doing any default selection based on BITS. - Renaming head_32.S to head_book3s_32.S. - Get head_book3s_32.S selected only by CONFIG_PPC_BOOK3S_32. Signed-off-by: Christophe Leroy [mpe: Fix head_$(BITS).o reference in arch/powerpc/Makefile] Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/319d379f696412681c66a987cc75e6abf8f958d2.1601975100.git.christophe.leroy@csgroup.eu --- arch/powerpc/Makefile | 3 ++- arch/powerpc/kernel/Makefile | 3 ++- arch/powerpc/kernel/{head_32.S => head_book3s_32.S} | 2 +- 3 files changed, 5 insertions(+), 3 deletions(-) rename arch/powerpc/kernel/{head_32.S => head_book3s_32.S} (99%) diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 3e8da9cf2eb9..c4f9dbd12577 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -264,7 +264,8 @@ KBUILD_CFLAGS += $(cpu-as-y) KBUILD_AFLAGS += $(aflags-y) KBUILD_CFLAGS += $(cflags-y) -head-y := arch/powerpc/kernel/head_$(BITS).o +head-$(CONFIG_PPC64) := arch/powerpc/kernel/head_64.o +head-$(CONFIG_PPC_BOOK3S_32) := arch/powerpc/kernel/head_book3s_32.o head-$(CONFIG_PPC_8xx) := arch/powerpc/kernel/head_8xx.o head-$(CONFIG_40x) := arch/powerpc/kernel/head_40x.o head-$(CONFIG_44x) := arch/powerpc/kernel/head_44x.o diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index a5550c2b24c4..bf0bf1b900d2 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -95,7 +95,8 @@ obj-$(CONFIG_PPC_FSL_BOOK3E) += cpu_setup_fsl_booke.o obj-$(CONFIG_PPC_DOORBELL) += dbell.o obj-$(CONFIG_JUMP_LABEL) += jump_label.o -extra-y := head_$(BITS).o +extra-$(CONFIG_PPC64) := head_64.o +extra-$(CONFIG_PPC_BOOK3S_32) := head_book3s_32.o extra-$(CONFIG_40x) := head_40x.o extra-$(CONFIG_44x) := head_44x.o extra-$(CONFIG_FSL_BOOKE) := head_fsl_booke.o diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_book3s_32.S similarity index 99% rename from arch/powerpc/kernel/head_32.S rename to arch/powerpc/kernel/head_book3s_32.S index 6dc77419147e..b7b554533e0d 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_book3s_32.S @@ -50,7 +50,7 @@ __HEAD .stabs "arch/powerpc/kernel/",N_SO,0,0,0f - .stabs "head_32.S",N_SO,0,0,0f + .stabs "head_book3s_32.S",N_SO,0,0,0f 0: _ENTRY(_stext); From 865418795a1dea1c2b58a5fd7b6bdcb93e0c36b8 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Tue, 6 Oct 2020 09:05:37 +0000 Subject: [PATCH 388/645] powerpc/32s: Remove #ifdef CONFIG_PPC_BOOK3S_32 in head_book3s_32.S head_book3s_32.S is only built when CONFIG_PPC_BOOK3S_32 is selected. Remove all conditions based on CONFIG_PPC_BOOK3S_32 in the file. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/1b68632425d8866d147aea9005004e4594672211.1601975100.git.christophe.leroy@csgroup.eu --- arch/powerpc/kernel/head_book3s_32.S | 15 --------------- 1 file changed, 15 deletions(-) diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S index b7b554533e0d..5eb9eedac920 100644 --- a/arch/powerpc/kernel/head_book3s_32.S +++ b/arch/powerpc/kernel/head_book3s_32.S @@ -174,10 +174,8 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) bl reloc_offset li r24,0 /* cpu# */ bl call_setup_cpu /* Call setup_cpu for this CPU */ -#ifdef CONFIG_PPC_BOOK3S_32 bl reloc_offset bl init_idle_6xx -#endif /* CONFIG_PPC_BOOK3S_32 */ /* @@ -878,10 +876,8 @@ __secondary_start: lis r3,-KERNELBASE@h mr r4,r24 bl call_setup_cpu /* Call setup_cpu for this CPU */ -#ifdef CONFIG_PPC_BOOK3S_32 lis r3,-KERNELBASE@h bl init_idle_6xx -#endif /* CONFIG_PPC_BOOK3S_32 */ /* get current's stack and current */ lis r2,secondary_current@ha @@ -921,17 +917,6 @@ __secondary_start: #include "../kvm/book3s_rmhandlers.S" #endif -/* - * Those generic dummy functions are kept for CPUs not - * included in CONFIG_PPC_BOOK3S_32 - */ -#if !defined(CONFIG_PPC_BOOK3S_32) -_ENTRY(__save_cpu_setup) - blr -_ENTRY(__restore_cpu_setup) - blr -#endif /* !defined(CONFIG_PPC_BOOK3S_32) */ - /* * Load stuff into the MMU. Intended to be called with * IR=0 and DR=0. From 15c102153e722cc6e0729764a7068c209a7469cd Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Thu, 1 Oct 2020 12:42:39 +0000 Subject: [PATCH 389/645] powerpc/time: Rename mftbl() to mftb() On PPC64, we have mftb(). On PPC32, we have mftbl() and an #define mftb() mftbl(). mftb() and mftbl() are equivalent, their purpose is to read the content of SPRN_TRBL, as returned by 'mftb' simplified instruction. binutils seems to define 'mftbl' instruction as an equivalent of 'mftb'. However in both 32 bits and 64 bits documentation, only 'mftb' is defined, and when performing a disassembly with objdump, the displayed instruction is 'mftb' No need to have two ways to do the same thing with different names, rename mftbl() to have only mftb(). Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/94dc68d3d9ef9eb549796d4b938b6ba0305a049b.1601556145.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/reg.h | 5 ++--- arch/powerpc/include/asm/time.h | 2 +- 2 files changed, 3 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 788058af1d44..c66dcdb47c44 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -1439,19 +1439,18 @@ static inline void msr_check_and_clear(unsigned long bits) #else /* __powerpc64__ */ #if defined(CONFIG_PPC_8xx) -#define mftbl() ({unsigned long rval; \ +#define mftb() ({unsigned long rval; \ asm volatile("mftbl %0" : "=r" (rval)); rval;}) #define mftbu() ({unsigned long rval; \ asm volatile("mftbu %0" : "=r" (rval)); rval;}) #else -#define mftbl() ({unsigned long rval; \ +#define mftb() ({unsigned long rval; \ asm volatile("mfspr %0, %1" : "=r" (rval) : \ "i" (SPRN_TBRL)); rval;}) #define mftbu() ({unsigned long rval; \ asm volatile("mfspr %0, %1" : "=r" (rval) : \ "i" (SPRN_TBRU)); rval;}) #endif -#define mftb() mftbl() #endif /* !__powerpc64__ */ #define mttbl(v) asm volatile("mttbl %0":: "r"(v)) diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h index a0c8ae4cb27c..6e681160981b 100644 --- a/arch/powerpc/include/asm/time.h +++ b/arch/powerpc/include/asm/time.h @@ -47,7 +47,7 @@ struct div_result { static inline unsigned long get_tbl(void) { - return mftbl(); + return mftb(); } static inline unsigned int get_tbu(void) From ff125fbcd45d1706861579dbe66e31f5b3f1e779 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Thu, 1 Oct 2020 12:42:40 +0000 Subject: [PATCH 390/645] powerpc/time: Make mftb() common to PPC32 and PPC64 No need to have two versions that are identical. CONFIG_PPC_CELL is only selected by PPC64 targets. CONFIG_E500 is the only PPC64 target selecting CONFIG_FSL_BOOK3E. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/6bf23ec744aab4ba63506a011f6a145ea35d620d.1601556145.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/reg.h | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index c66dcdb47c44..f877a576b338 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -1419,8 +1419,7 @@ static inline void msr_check_and_clear(unsigned long bits) __msr_check_and_clear(bits); } -#ifdef __powerpc64__ -#if defined(CONFIG_PPC_CELL) || defined(CONFIG_PPC_FSL_BOOK3E) +#if defined(CONFIG_PPC_CELL) || defined(CONFIG_E500) #define mftb() ({unsigned long rval; \ asm volatile( \ "90: mfspr %0, %2;\n" \ @@ -1430,28 +1429,23 @@ static inline void msr_check_and_clear(unsigned long bits) : "=r" (rval) \ : "i" (CPU_FTR_CELL_TB_BUG), "i" (SPRN_TBRL) : "cr0"); \ rval;}) +#elif defined(CONFIG_PPC_8xx) +#define mftb() ({unsigned long rval; \ + asm volatile("mftbl %0" : "=r" (rval)); rval;}) #else #define mftb() ({unsigned long rval; \ asm volatile("mfspr %0, %1" : \ "=r" (rval) : "i" (SPRN_TBRL)); rval;}) #endif /* !CONFIG_PPC_CELL */ -#else /* __powerpc64__ */ - #if defined(CONFIG_PPC_8xx) -#define mftb() ({unsigned long rval; \ - asm volatile("mftbl %0" : "=r" (rval)); rval;}) #define mftbu() ({unsigned long rval; \ asm volatile("mftbu %0" : "=r" (rval)); rval;}) #else -#define mftb() ({unsigned long rval; \ - asm volatile("mfspr %0, %1" : "=r" (rval) : \ - "i" (SPRN_TBRL)); rval;}) #define mftbu() ({unsigned long rval; \ asm volatile("mfspr %0, %1" : "=r" (rval) : \ "i" (SPRN_TBRU)); rval;}) #endif -#endif /* !__powerpc64__ */ #define mttbl(v) asm volatile("mttbl %0":: "r"(v)) #define mttbu(v) asm volatile("mttbu %0":: "r"(v)) From 942e89115b588b4b5df86930b5302a5c07b820ba Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Thu, 1 Oct 2020 12:42:41 +0000 Subject: [PATCH 391/645] powerpc/time: Avoid using get_tbl() and get_tbu() internally get_tbl() is confusing as it returns the content of TBL register on PPC32 but the concatenation of TBL and TBU on PPC64. Use mftb() instead. Do the same with get_tbu() for consistency allthough it's name is less confusing. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/41573406a4eab98838decaa91649086fef1e6119.1601556145.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/delay.h | 2 +- arch/powerpc/include/asm/time.h | 8 ++++---- arch/powerpc/kernel/time.c | 4 ++-- 3 files changed, 7 insertions(+), 7 deletions(-) diff --git a/arch/powerpc/include/asm/delay.h b/arch/powerpc/include/asm/delay.h index 66963f7d3e64..51bb8c1476c7 100644 --- a/arch/powerpc/include/asm/delay.h +++ b/arch/powerpc/include/asm/delay.h @@ -54,7 +54,7 @@ extern void udelay(unsigned long usecs); ({ \ typeof(condition) __ret; \ unsigned long __loops = tb_ticks_per_usec * timeout; \ - unsigned long __start = get_tbl(); \ + unsigned long __start = mftb(); \ \ if (delay) { \ while (!(__ret = (condition)) && \ diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h index 6e681160981b..c83116ec79c3 100644 --- a/arch/powerpc/include/asm/time.h +++ b/arch/powerpc/include/asm/time.h @@ -76,9 +76,9 @@ static inline u64 get_tb(void) unsigned int tbhi, tblo, tbhi2; do { - tbhi = get_tbu(); - tblo = get_tbl(); - tbhi2 = get_tbu(); + tbhi = mftbu(); + tblo = mftb(); + tbhi2 = mftbu(); } while (tbhi != tbhi2); return ((u64)tbhi << 32) | tblo; @@ -123,7 +123,7 @@ static inline void set_dec(u64 val) static inline unsigned long tb_ticks_since(unsigned long tstamp) { - return get_tbl() - tstamp; + return mftb() - tstamp; } #define mulhwu(x,y) \ diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 760ea359a7f7..74efe46f5532 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -448,8 +448,8 @@ void __delay(unsigned long loops) */ spin_cpu_relax(); } else { - start = get_tbl(); - while (get_tbl() - start < loops) + start = mftb(); + while (mftb() - start < loops) spin_cpu_relax(); } spin_end(); From e8d5bf30eafc37e31ce68bc7ccf1db970fe3cd04 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Thu, 1 Oct 2020 12:42:42 +0000 Subject: [PATCH 392/645] powerpc/time: Remove get_tbu() get_tbu() is redundant with mftbu() and is not used anymore. Remove it. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/1746e2d11ea90c3f45877e1fcc6c79ce96cf6b98.1601556145.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/time.h | 5 ----- 1 file changed, 5 deletions(-) diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h index c83116ec79c3..3dd2deb623da 100644 --- a/arch/powerpc/include/asm/time.h +++ b/arch/powerpc/include/asm/time.h @@ -49,11 +49,6 @@ static inline unsigned long get_tbl(void) { return mftb(); } - -static inline unsigned int get_tbu(void) -{ - return mftbu(); -} #endif /* !CONFIG_PPC64 */ static inline u64 get_vtb(void) From 1156a6285cd38e5a6987ddee3758e7954c56cb3d Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Thu, 1 Oct 2020 12:42:43 +0000 Subject: [PATCH 393/645] powerpc/time: Make get_tbl() common to PPC32 and PPC64 On PPC64, get_tbl() is defined as an alias of get_tb() which return the result of mftb(). That exactly the same as what the PPC32 version does. We don't need two versions. Remove the PPC64 definition of get_tbl() and use the PPC32 version for both. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/a8eaabb87d69534e533ebac805163e08146e05bd.1601556145.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/time.h | 7 ------- 1 file changed, 7 deletions(-) diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h index 3dd2deb623da..6ec0409d10f4 100644 --- a/arch/powerpc/include/asm/time.h +++ b/arch/powerpc/include/asm/time.h @@ -38,18 +38,11 @@ struct div_result { u64 result_low; }; -#ifdef CONFIG_PPC64 - /* For compatibility, get_tbl() is defined as get_tb() on ppc64 */ -#define get_tbl get_tb - -#else - static inline unsigned long get_tbl(void) { return mftb(); } -#endif /* !CONFIG_PPC64 */ static inline u64 get_vtb(void) { From 9686e431c683ee7b8aca0f3985c244aee3d9f30d Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Thu, 1 Oct 2020 12:42:44 +0000 Subject: [PATCH 394/645] powerpc/time: Make get_tb() common to PPC32 and PPC64 mftbu() is always defined now, so the #ifdef can be removed and replaced by an IS_ENABLED(CONFIG_PPC64) inside the PPC32 version of get_tb(). Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/47e49717d2643169ffcbe5d507f184cf49f0fe95.1601556145.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/time.h | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h index 6ec0409d10f4..2f566c1a754c 100644 --- a/arch/powerpc/include/asm/time.h +++ b/arch/powerpc/include/asm/time.h @@ -53,16 +53,13 @@ static inline u64 get_vtb(void) return 0; } -#ifdef CONFIG_PPC64 -static inline u64 get_tb(void) -{ - return mftb(); -} -#else /* CONFIG_PPC64 */ static inline u64 get_tb(void) { unsigned int tbhi, tblo, tbhi2; + if (IS_ENABLED(CONFIG_PPC64)) + return mftb(); + do { tbhi = mftbu(); tblo = mftb(); @@ -71,7 +68,6 @@ static inline u64 get_tb(void) return ((u64)tbhi << 32) | tblo; } -#endif /* !CONFIG_PPC64 */ static inline void set_tb(unsigned int upper, unsigned int lower) { From a2d0230b91f7e23ceb5d8fb6a9799f30517ec33a Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Tue, 22 Sep 2020 13:32:54 +0530 Subject: [PATCH 395/645] cpufreq: powernv: Fix frame-size-overflow in powernv_cpufreq_reboot_notifier The patch avoids allocating cpufreq_policy on stack hence fixing frame size overflow in 'powernv_cpufreq_reboot_notifier': drivers/cpufreq/powernv-cpufreq.c: In function powernv_cpufreq_reboot_notifier: drivers/cpufreq/powernv-cpufreq.c:906:1: error: the frame size of 2064 bytes is larger than 2048 bytes Fixes: cf30af76 ("cpufreq: powernv: Set the cpus to nominal frequency during reboot/kexec") Signed-off-by: Srikar Dronamraju Reviewed-by: Daniel Axtens Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200922080254.41497-1-srikar@linux.vnet.ibm.com --- drivers/cpufreq/powernv-cpufreq.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c index a9af15e994cc..e439b43c19eb 100644 --- a/drivers/cpufreq/powernv-cpufreq.c +++ b/drivers/cpufreq/powernv-cpufreq.c @@ -885,12 +885,15 @@ static int powernv_cpufreq_reboot_notifier(struct notifier_block *nb, unsigned long action, void *unused) { int cpu; - struct cpufreq_policy cpu_policy; + struct cpufreq_policy *cpu_policy; rebooting = true; for_each_online_cpu(cpu) { - cpufreq_get_policy(&cpu_policy, cpu); - powernv_cpufreq_target_index(&cpu_policy, get_nominal_index()); + cpu_policy = cpufreq_cpu_get(cpu); + if (!cpu_policy) + continue; + powernv_cpufreq_target_index(cpu_policy, get_nominal_index()); + cpufreq_cpu_put(cpu_policy); } return NOTIFY_DONE; From b61e1f3281c5a53f24f47849873463514f58c1b8 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Fri, 18 Sep 2020 10:26:19 +0200 Subject: [PATCH 396/645] s390/kprobes: move insn_page to text segment Move the in-kernel kprobes insn page to text segment. Rationale: having that page in rw data segment is suboptimal, since as soon as a kprobe is set, this will split the 1:1 kernel mapping for a single page which get new permissions. Note: there is always at least one kprobe present for the kretprobe trampoline; so the mapping will always be split into smaller 4k mappings because of this. Moving the kprobes insn page into text segment makes sure that the page is mapped RO/X in any case, and avoids that the 1:1 mapping is split. The kprobe insn_page is defined as a dummy function which is filled with "br %r14" instructions. Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/Makefile | 1 + arch/s390/kernel/entry.h | 2 ++ arch/s390/kernel/kprobes.c | 6 ++---- arch/s390/kernel/kprobes_insn_page.S | 22 ++++++++++++++++++++++ 4 files changed, 27 insertions(+), 4 deletions(-) create mode 100644 arch/s390/kernel/kprobes_insn_page.S diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index efca70970761..dd73b7f07423 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -57,6 +57,7 @@ obj-$(CONFIG_COMPAT) += $(compat-obj-y) obj-$(CONFIG_EARLY_PRINTK) += early_printk.o obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-$(CONFIG_KPROBES) += kprobes.o +obj-$(CONFIG_KPROBES) += kprobes_insn_page.o obj-$(CONFIG_FUNCTION_TRACER) += mcount.o ftrace.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_UPROBES) += uprobes.o diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index 6475a885cd60..0f7e4e9176e0 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -87,4 +87,6 @@ void set_fs_fixup(void); unsigned long stack_alloc(void); void stack_free(unsigned long stack); +extern char kprobes_insn_page[]; + #endif /* _ENTRY_H */ diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index b34fa4eef742..6574774d404e 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -22,6 +22,7 @@ #include #include #include +#include "entry.h" DEFINE_PER_CPU(struct kprobe *, current_kprobe); DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); @@ -31,7 +32,6 @@ struct kretprobe_blackpoint kretprobe_blacklist[] = { }; DEFINE_INSN_CACHE_OPS(s390_insn); static int insn_page_in_use; -static char insn_page[PAGE_SIZE] __aligned(PAGE_SIZE); void *alloc_insn_page(void) { @@ -53,13 +53,11 @@ static void *alloc_s390_insn_page(void) { if (xchg(&insn_page_in_use, 1) == 1) return NULL; - __set_memory((unsigned long) &insn_page, 1, SET_MEMORY_RO | SET_MEMORY_X); - return &insn_page; + return &kprobes_insn_page; } static void free_s390_insn_page(void *page) { - __set_memory((unsigned long) page, 1, SET_MEMORY_RW | SET_MEMORY_NX); xchg(&insn_page_in_use, 0); } diff --git a/arch/s390/kernel/kprobes_insn_page.S b/arch/s390/kernel/kprobes_insn_page.S new file mode 100644 index 000000000000..f6cb022ef8c8 --- /dev/null +++ b/arch/s390/kernel/kprobes_insn_page.S @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#include + +/* + * insn_page is a special 4k aligned dummy function for kprobes. + * It will contain all kprobed instructions that are out-of-line executed. + * The page must be within the kernel image to guarantee that the + * out-of-line instructions are within 2GB distance of their original + * location. Using a dummy function ensures that the insn_page is within + * the text section of the kernel and mapped read-only/executable from + * the beginning on, thus avoiding to split large mappings if the page + * would be in the data section instead. + */ + .section .kprobes.text, "ax" + .align 4096 +ENTRY(kprobes_insn_page) + .rept 2048 + .word 0x07fe + .endr +ENDPROC(kprobes_insn_page) + .previous From 4366dd7251259806e57251cb2d699f0863841775 Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Thu, 8 Oct 2020 08:43:09 +0200 Subject: [PATCH 397/645] s390/zcrypt: fix wrong format specifications Fixes 5 wrong format specification findings found by the kernel test robot in ap_queue.c: warning: format specifies type 'unsigned char' but the argument has type 'int' [-Wformat] __func__, status.response_code, Signed-off-by: Harald Freudenberger Reported-by: kernel test robot Fixes: 2ea2a6099ae3 ("s390/ap: add error response code field for ap queue devices") Signed-off-by: Vasily Gorbik --- drivers/s390/crypto/ap_queue.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c index 13d4fe2c6127..ecefc25eff0c 100644 --- a/drivers/s390/crypto/ap_queue.c +++ b/drivers/s390/crypto/ap_queue.c @@ -197,7 +197,7 @@ static enum ap_sm_wait ap_sm_read(struct ap_queue *aq) default: aq->dev_state = AP_DEV_STATE_ERROR; aq->last_err_rc = status.response_code; - AP_DBF_WARN("%s RC 0x%02hhx on 0x%02x.%04x -> AP_DEV_STATE_ERROR\n", + AP_DBF_WARN("%s RC 0x%02x on 0x%02x.%04x -> AP_DEV_STATE_ERROR\n", __func__, status.response_code, AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid)); return AP_SM_WAIT_NONE; @@ -262,7 +262,7 @@ static enum ap_sm_wait ap_sm_write(struct ap_queue *aq) default: aq->dev_state = AP_DEV_STATE_ERROR; aq->last_err_rc = status.response_code; - AP_DBF_WARN("%s RC 0x%02hhx on 0x%02x.%04x -> AP_DEV_STATE_ERROR\n", + AP_DBF_WARN("%s RC 0x%02x on 0x%02x.%04x -> AP_DEV_STATE_ERROR\n", __func__, status.response_code, AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid)); return AP_SM_WAIT_NONE; @@ -300,7 +300,7 @@ static enum ap_sm_wait ap_sm_reset(struct ap_queue *aq) default: aq->dev_state = AP_DEV_STATE_ERROR; aq->last_err_rc = status.response_code; - AP_DBF_WARN("%s RC 0x%02hhx on 0x%02x.%04x -> AP_DEV_STATE_ERROR\n", + AP_DBF_WARN("%s RC 0x%02x on 0x%02x.%04x -> AP_DEV_STATE_ERROR\n", __func__, status.response_code, AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid)); return AP_SM_WAIT_NONE; @@ -343,7 +343,7 @@ static enum ap_sm_wait ap_sm_reset_wait(struct ap_queue *aq) default: aq->dev_state = AP_DEV_STATE_ERROR; aq->last_err_rc = status.response_code; - AP_DBF_WARN("%s RC 0x%02hhx on 0x%02x.%04x -> AP_DEV_STATE_ERROR\n", + AP_DBF_WARN("%s RC 0x%02x on 0x%02x.%04x -> AP_DEV_STATE_ERROR\n", __func__, status.response_code, AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid)); return AP_SM_WAIT_NONE; @@ -384,7 +384,7 @@ static enum ap_sm_wait ap_sm_setirq_wait(struct ap_queue *aq) default: aq->dev_state = AP_DEV_STATE_ERROR; aq->last_err_rc = status.response_code; - AP_DBF_WARN("%s RC 0x%02hhx on 0x%02x.%04x -> AP_DEV_STATE_ERROR\n", + AP_DBF_WARN("%s RC 0x%02x on 0x%02x.%04x -> AP_DEV_STATE_ERROR\n", __func__, status.response_code, AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid)); return AP_SM_WAIT_NONE; From db5273975622af17e265d5d96b41427cde4c25b0 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Thu, 8 Oct 2020 16:28:15 +0200 Subject: [PATCH 398/645] s390/uaccess: add default cases for __put_user_fn()/__get_user_fn() Add default cases for __put_user_fn()/__get_user_fn(). This doesn't fix anything since the functions are only called with sane values. However we get rid of smatch warnings: ./arch/s390/include/asm/uaccess.h:143 __get_user_fn() error: uninitialized symbol 'rc'. Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/uaccess.h | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h index 23c85801cf04..bf47d93ff1c6 100644 --- a/arch/s390/include/asm/uaccess.h +++ b/arch/s390/include/asm/uaccess.h @@ -60,6 +60,9 @@ raw_copy_to_user(void __user *to, const void *from, unsigned long n); #define INLINE_COPY_TO_USER #endif +int __put_user_bad(void) __attribute__((noreturn)); +int __get_user_bad(void) __attribute__((noreturn)); + #ifdef CONFIG_HAVE_MARCH_Z10_FEATURES #define __put_get_user_asm(to, from, size, spec) \ @@ -109,6 +112,9 @@ static __always_inline int __put_user_fn(void *x, void __user *ptr, unsigned lon (unsigned long *)x, size, spec); break; + default: + __put_user_bad(); + break; } return rc; } @@ -139,6 +145,9 @@ static __always_inline int __get_user_fn(void *x, const void __user *ptr, unsign (unsigned long __user *)ptr, size, spec); break; + default: + __get_user_bad(); + break; } return rc; } @@ -190,8 +199,6 @@ static inline int __get_user_fn(void *x, const void __user *ptr, unsigned long s }) -int __put_user_bad(void) __attribute__((noreturn)); - #define __get_user(x, ptr) \ ({ \ int __gu_err = -EFAULT; \ @@ -238,8 +245,6 @@ int __put_user_bad(void) __attribute__((noreturn)); __get_user(x, ptr); \ }) -int __get_user_bad(void) __attribute__((noreturn)); - unsigned long __must_check raw_copy_in_user(void __user *to, const void __user *from, unsigned long n); From 10e5afb3d260f2d2521889d87ebdefb7fc3d4087 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Thu, 8 Oct 2020 16:43:17 +0200 Subject: [PATCH 399/645] s390/uaccess: fix indentation Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/uaccess.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h index bf47d93ff1c6..c868e7ee49b3 100644 --- a/arch/s390/include/asm/uaccess.h +++ b/arch/s390/include/asm/uaccess.h @@ -188,7 +188,7 @@ static inline int __get_user_fn(void *x, const void __user *ptr, unsigned long s default: \ __put_user_bad(); \ break; \ - } \ + } \ __builtin_expect(__pu_err, 0); \ }) From 90761cee5f4c9a97e9952e1a8e2165c8ab346ea4 Mon Sep 17 00:00:00 2001 From: Mikhail Gusarov Date: Sat, 10 Oct 2020 12:08:58 +0200 Subject: [PATCH 400/645] mips: octeon: Add Ubiquiti E200 and E220 boards These boards are used in - Ubiquiti EdgeRouter (E200), - Ubiquiti EdgeRouter Pro (E200) and - Ubiquiti Security Gateway Pro 4 (E220). Signed-off-by: Mikhail Gusarov Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/octeon/cvmx-bootinfo.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/mips/include/asm/octeon/cvmx-bootinfo.h b/arch/mips/include/asm/octeon/cvmx-bootinfo.h index 62787765575e..c114a7ba0bad 100644 --- a/arch/mips/include/asm/octeon/cvmx-bootinfo.h +++ b/arch/mips/include/asm/octeon/cvmx-bootinfo.h @@ -295,6 +295,8 @@ enum cvmx_board_types_enum { */ CVMX_BOARD_TYPE_CUST_PRIVATE_MIN = 20001, CVMX_BOARD_TYPE_UBNT_E100 = 20002, + CVMX_BOARD_TYPE_UBNT_E200 = 20003, + CVMX_BOARD_TYPE_UBNT_E220 = 20005, CVMX_BOARD_TYPE_CUST_DSR1000N = 20006, CVMX_BOARD_TYPE_KONTRON_S1901 = 21901, CVMX_BOARD_TYPE_CUST_PRIVATE_MAX = 30000, @@ -396,6 +398,8 @@ static inline const char *cvmx_board_type_to_string(enum /* Customer private range */ ENUM_BRD_TYPE_CASE(CVMX_BOARD_TYPE_CUST_PRIVATE_MIN) ENUM_BRD_TYPE_CASE(CVMX_BOARD_TYPE_UBNT_E100) + ENUM_BRD_TYPE_CASE(CVMX_BOARD_TYPE_UBNT_E200) + ENUM_BRD_TYPE_CASE(CVMX_BOARD_TYPE_UBNT_E220) ENUM_BRD_TYPE_CASE(CVMX_BOARD_TYPE_CUST_DSR1000N) ENUM_BRD_TYPE_CASE(CVMX_BOARD_TYPE_KONTRON_S1901) ENUM_BRD_TYPE_CASE(CVMX_BOARD_TYPE_CUST_PRIVATE_MAX) From 1062fc45d1e93faefb93961f3be0a687f3f0e2e1 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Sun, 11 Oct 2020 07:47:51 +0800 Subject: [PATCH 401/645] MIPS: Loongson64: Select SMP in Kconfig to avoid build error In the current code, CONFIG_SMP can be set as N by user on the Loongson platform, then there exists the following build error under !CONFIG_SMP: CC arch/mips/kernel/asm-offsets.s In file included from ./include/linux/gfp.h:9:0, from ./include/linux/xarray.h:14, from ./include/linux/radix-tree.h:18, from ./include/linux/fs.h:15, from ./include/linux/compat.h:17, from arch/mips/kernel/asm-offsets.c:12: ./include/linux/topology.h: In function 'numa_node_id': ./include/linux/topology.h:119:2: error: implicit declaration of function 'cpu_logical_map' [-Werror=implicit-function-declaration] return cpu_to_node(raw_smp_processor_id()); ^ cc1: some warnings being treated as errors scripts/Makefile.build:117: recipe for target 'arch/mips/kernel/asm-offsets.s' failed make[1]: *** [arch/mips/kernel/asm-offsets.s] Error 1 Select SMP in Kconfig to avoid the above build error and then remove CONFIG_SMP=y in loongson3_defconfig. Signed-off-by: Tiezhu Yang Signed-off-by: Thomas Bogendoerfer --- arch/mips/Kconfig | 1 + arch/mips/configs/loongson3_defconfig | 1 - 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index b557fa578e62..75f26d1f11ab 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -488,6 +488,7 @@ config MACH_LOONGSON64 select SYS_SUPPORTS_ZBOOT select ZONE_DMA32 select NUMA + select SMP select COMMON_CLK select USE_OF select BUILTIN_DTB diff --git a/arch/mips/configs/loongson3_defconfig b/arch/mips/configs/loongson3_defconfig index a5005c8cee8a..38a817ead8e7 100644 --- a/arch/mips/configs/loongson3_defconfig +++ b/arch/mips/configs/loongson3_defconfig @@ -30,7 +30,6 @@ CONFIG_EMBEDDED=y CONFIG_PERF_EVENTS=y CONFIG_MACH_LOONGSON64=y CONFIG_CPU_HAS_MSA=y -CONFIG_SMP=y CONFIG_NR_CPUS=16 CONFIG_HZ_256=y CONFIG_KEXEC=y From 73826d604bbf31328108c6c2a93a7a8a13a74371 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Sun, 11 Oct 2020 07:47:52 +0800 Subject: [PATCH 402/645] MIPS: Loongson64: Clean up numa.c (1) Replace nid_to_addroffset() with nid_to_addrbase() and then remove the related useless code. (2) Since end_pfn = start_pfn + node_psize, use "node_psize" instead of "end_pfn - start_pfn" to avoid the redundant calculation. (3) After commit 6fbde6b492df ("MIPS: Loongson64: Move files to the top-level directory"), CONFIG_ZONE_DMA32 is always set for Loongson64 due to MACH_LOONGSON64 selects ZONE_DMA32, so no need to use ifdef any more, just remove it. Signed-off-by: Tiezhu Yang Reviewed-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer --- .../mips/include/asm/mach-loongson64/mmzone.h | 6 +--- arch/mips/loongson64/numa.c | 29 ++----------------- 2 files changed, 4 insertions(+), 31 deletions(-) diff --git a/arch/mips/include/asm/mach-loongson64/mmzone.h b/arch/mips/include/asm/mach-loongson64/mmzone.h index 3a25dbd3b3e9..c3f0f7a75e31 100644 --- a/arch/mips/include/asm/mach-loongson64/mmzone.h +++ b/arch/mips/include/asm/mach-loongson64/mmzone.h @@ -11,13 +11,9 @@ #include #define NODE_ADDRSPACE_SHIFT 44 -#define NODE0_ADDRSPACE_OFFSET 0x000000000000UL -#define NODE1_ADDRSPACE_OFFSET 0x100000000000UL -#define NODE2_ADDRSPACE_OFFSET 0x200000000000UL -#define NODE3_ADDRSPACE_OFFSET 0x300000000000UL #define pa_to_nid(addr) (((addr) & 0xf00000000000) >> NODE_ADDRSPACE_SHIFT) -#define nid_to_addrbase(nid) ((nid) << NODE_ADDRSPACE_SHIFT) +#define nid_to_addrbase(nid) ((unsigned long)(nid) << NODE_ADDRSPACE_SHIFT) extern struct pglist_data *__node_data[]; diff --git a/arch/mips/loongson64/numa.c b/arch/mips/loongson64/numa.c index ea8bb1bc667e..cf9459f79f9b 100644 --- a/arch/mips/loongson64/numa.c +++ b/arch/mips/loongson64/numa.c @@ -98,27 +98,6 @@ static void __init init_topology_matrix(void) } } -static unsigned long nid_to_addroffset(unsigned int nid) -{ - unsigned long result; - switch (nid) { - case 0: - default: - result = NODE0_ADDRSPACE_OFFSET; - break; - case 1: - result = NODE1_ADDRSPACE_OFFSET; - break; - case 2: - result = NODE2_ADDRSPACE_OFFSET; - break; - case 3: - result = NODE3_ADDRSPACE_OFFSET; - break; - } - return result; -} - static void __init szmem(unsigned int node) { u32 i, mem_type; @@ -146,7 +125,7 @@ static void __init szmem(unsigned int node) pr_info(" start_pfn:0x%llx, end_pfn:0x%llx, num_physpages:0x%lx\n", start_pfn, end_pfn, num_physpages); memblock_add_node(PFN_PHYS(start_pfn), - PFN_PHYS(end_pfn - start_pfn), node); + PFN_PHYS(node_psize), node); break; case SYSTEM_RAM_HIGH: start_pfn = ((node_id << 44) + mem_start) >> PAGE_SHIFT; @@ -158,7 +137,7 @@ static void __init szmem(unsigned int node) pr_info(" start_pfn:0x%llx, end_pfn:0x%llx, num_physpages:0x%lx\n", start_pfn, end_pfn, num_physpages); memblock_add_node(PFN_PHYS(start_pfn), - PFN_PHYS(end_pfn - start_pfn), node); + PFN_PHYS(node_psize), node); break; case SYSTEM_RAM_RESERVED: pr_info("Node%d: mem_type:%d, mem_start:0x%llx, mem_size:0x%llx MB\n", @@ -175,7 +154,7 @@ static void __init node_mem_init(unsigned int node) unsigned long node_addrspace_offset; unsigned long start_pfn, end_pfn; - node_addrspace_offset = nid_to_addroffset(node); + node_addrspace_offset = nid_to_addrbase(node); pr_info("Node%d's addrspace_offset is 0x%lx\n", node, node_addrspace_offset); @@ -242,9 +221,7 @@ void __init paging_init(void) unsigned long zones_size[MAX_NR_ZONES] = {0, }; pagetable_init(); -#ifdef CONFIG_ZONE_DMA32 zones_size[ZONE_DMA32] = MAX_DMA32_PFN; -#endif zones_size[ZONE_NORMAL] = max_low_pfn; free_area_init(zones_size); } From e7ae8d174eec0b3b9de92b76abc15f3f53b98f1c Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Fri, 9 Oct 2020 14:14:46 +0200 Subject: [PATCH 403/645] MIPS: replace add_memory_region with memblock add_memory_region was the old interface for registering memory and was already changed to used memblock internaly. Replace it by directly calling memblock functions. Signed-off-by: Thomas Bogendoerfer --- arch/mips/alchemy/common/prom.c | 3 +- arch/mips/ar7/memory.c | 2 +- arch/mips/ath25/ar2315.c | 3 +- arch/mips/ath25/ar5312.c | 3 +- arch/mips/bcm47xx/prom.c | 3 +- arch/mips/bcm47xx/setup.c | 2 +- arch/mips/bcm63xx/setup.c | 2 +- arch/mips/cavium-octeon/setup.c | 24 ++++----- arch/mips/cobalt/setup.c | 3 +- arch/mips/dec/prom/memory.c | 8 ++- arch/mips/fw/arc/memory.c | 28 ++++++++--- arch/mips/fw/sni/sniprom.c | 4 +- arch/mips/include/asm/bootinfo.h | 7 --- arch/mips/include/asm/netlogic/psb-bootinfo.h | 1 + arch/mips/kernel/prom.c | 25 ---------- arch/mips/kernel/setup.c | 50 +++---------------- arch/mips/loongson2ef/common/mem.c | 12 +---- arch/mips/loongson32/common/prom.c | 4 +- arch/mips/netlogic/xlp/setup.c | 2 +- arch/mips/netlogic/xlr/setup.c | 5 +- arch/mips/ralink/of.c | 3 +- arch/mips/rb532/prom.c | 2 +- arch/mips/sgi-ip32/ip32-memory.c | 3 +- arch/mips/sibyte/common/cfe.c | 16 +++--- arch/mips/txx9/jmr3927/prom.c | 4 +- arch/mips/txx9/rbtx4927/prom.c | 5 +- arch/mips/txx9/rbtx4938/prom.c | 3 +- arch/mips/txx9/rbtx4939/prom.c | 4 +- 28 files changed, 82 insertions(+), 149 deletions(-) diff --git a/arch/mips/alchemy/common/prom.c b/arch/mips/alchemy/common/prom.c index cfa203064d3c..d910c0a64de9 100644 --- a/arch/mips/alchemy/common/prom.c +++ b/arch/mips/alchemy/common/prom.c @@ -35,6 +35,7 @@ #include #include +#include #include #include @@ -93,7 +94,7 @@ void __init prom_init(void) if (!memsize_str || kstrtoul(memsize_str, 0, &memsize)) memsize = SZ_64M; /* minimum memsize is 64MB RAM */ - add_memory_region(0, memsize, BOOT_MEM_RAM); + memblock_add(0, memsize); } static inline unsigned char str2hexnum(unsigned char c) diff --git a/arch/mips/ar7/memory.c b/arch/mips/ar7/memory.c index ad6efb36ebfe..787716c5e946 100644 --- a/arch/mips/ar7/memory.c +++ b/arch/mips/ar7/memory.c @@ -47,7 +47,7 @@ void __init prom_meminit(void) unsigned long pages; pages = memsize() >> PAGE_SHIFT; - add_memory_region(PHYS_OFFSET, pages << PAGE_SHIFT, BOOT_MEM_RAM); + memblock_add(PHYS_OFFSET, pages << PAGE_SHIFT); } void __init prom_free_prom_memory(void) diff --git a/arch/mips/ath25/ar2315.c b/arch/mips/ath25/ar2315.c index e7b53e3960c8..9dbed7b5ea76 100644 --- a/arch/mips/ath25/ar2315.c +++ b/arch/mips/ath25/ar2315.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include @@ -266,7 +267,7 @@ void __init ar2315_plat_mem_setup(void) memsize <<= 1 + ATH25_REG_MS(memcfg, AR2315_MEM_CFG_COL_WIDTH); memsize <<= 1 + ATH25_REG_MS(memcfg, AR2315_MEM_CFG_ROW_WIDTH); memsize <<= 3; - add_memory_region(0, memsize, BOOT_MEM_RAM); + memblock_add(0, memsize); iounmap(sdram_base); ar2315_rst_base = ioremap(AR2315_RST_BASE, AR2315_RST_SIZE); diff --git a/arch/mips/ath25/ar5312.c b/arch/mips/ath25/ar5312.c index 42bf2afb4765..23c879f4b734 100644 --- a/arch/mips/ath25/ar5312.c +++ b/arch/mips/ath25/ar5312.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include @@ -363,7 +364,7 @@ void __init ar5312_plat_mem_setup(void) memsize = (bank0_ac ? (1 << (bank0_ac + 1)) : 0) + (bank1_ac ? (1 << (bank1_ac + 1)) : 0); memsize <<= 20; - add_memory_region(0, memsize, BOOT_MEM_RAM); + memblock_add(0, memsize); iounmap(sdram_base); ar5312_rst_base = ioremap(AR5312_RST_BASE, AR5312_RST_SIZE); diff --git a/arch/mips/bcm47xx/prom.c b/arch/mips/bcm47xx/prom.c index 135a5407f015..3e2a8166377f 100644 --- a/arch/mips/bcm47xx/prom.c +++ b/arch/mips/bcm47xx/prom.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -97,7 +98,7 @@ static __init void prom_init_mem(void) */ if (c->cputype == CPU_74K && (mem == (128 << 20))) mem -= 0x1000; - add_memory_region(0, mem, BOOT_MEM_RAM); + memblock_add(0, mem); } /* diff --git a/arch/mips/bcm47xx/setup.c b/arch/mips/bcm47xx/setup.c index 82627c264964..751997eb1552 100644 --- a/arch/mips/bcm47xx/setup.c +++ b/arch/mips/bcm47xx/setup.c @@ -141,7 +141,7 @@ static void __init bcm47xx_register_bcma(void) /* * Memory setup is done in the early part of MIPS's arch_mem_init. It's supposed - * to detect memory and record it with add_memory_region. + * to detect memory and record it with memblock_add. * Any extra initializaion performed here must not use kmalloc or bootmem. */ void __init plat_mem_setup(void) diff --git a/arch/mips/bcm63xx/setup.c b/arch/mips/bcm63xx/setup.c index e28ee9a7cc7e..d811e3e03f81 100644 --- a/arch/mips/bcm63xx/setup.c +++ b/arch/mips/bcm63xx/setup.c @@ -146,7 +146,7 @@ void __init plat_time_init(void) void __init plat_mem_setup(void) { - add_memory_region(0, bcm63xx_get_memory_size(), BOOT_MEM_RAM); + memblock_add(0, bcm63xx_get_memory_size()); _machine_halt = bcm63xx_machine_halt; _machine_restart = __bcm63xx_machine_reboot; diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c index 8a357cb068c2..561389d3fadb 100644 --- a/arch/mips/cavium-octeon/setup.c +++ b/arch/mips/cavium-octeon/setup.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -930,7 +931,7 @@ static __init void memory_exclude_page(u64 addr, u64 *mem, u64 *size) { if (addr > *mem && addr < *mem + *size) { u64 inc = addr - *mem; - add_memory_region(*mem, inc, BOOT_MEM_RAM); + memblock_add(*mem, inc); *mem += inc; *size -= inc; } @@ -992,19 +993,18 @@ void __init plat_mem_setup(void) /* Crashkernel ignores bootmem list. It relies on mem=X@Y option */ #ifdef CONFIG_CRASH_DUMP - add_memory_region(reserve_low_mem, max_memory, BOOT_MEM_RAM); + memblock_add(reserve_low_mem, max_memory); total += max_memory; #else #ifdef CONFIG_KEXEC if (crashk_size > 0) { - add_memory_region(crashk_base, crashk_size, BOOT_MEM_RAM); + memblock_add(crashk_base, crashk_size); crashk_end = crashk_base + crashk_size; } #endif /* - * When allocating memory, we want incrementing addresses from - * bootmem_alloc so the code in add_memory_region can merge - * regions next to each other. + * When allocating memory, we want incrementing addresses, + * which is handled by memblock */ cvmx_bootmem_lock(); while (total < max_memory) { @@ -1039,13 +1039,9 @@ void __init plat_mem_setup(void) */ if (memory < crashk_base && end > crashk_end) { /* region is fully in */ - add_memory_region(memory, - crashk_base - memory, - BOOT_MEM_RAM); + memblock_add(memory, crashk_base - memory); total += crashk_base - memory; - add_memory_region(crashk_end, - end - crashk_end, - BOOT_MEM_RAM); + memblock_add(crashk_end, end - crashk_end); total += end - crashk_end; continue; } @@ -1073,7 +1069,7 @@ void __init plat_mem_setup(void) */ mem_alloc_size -= end - crashk_base; #endif - add_memory_region(memory, mem_alloc_size, BOOT_MEM_RAM); + memblock_add(memory, mem_alloc_size); total += mem_alloc_size; /* Recovering mem_alloc_size */ mem_alloc_size = 4 << 20; @@ -1088,7 +1084,7 @@ void __init plat_mem_setup(void) /* Adjust for physical offset. */ kernel_start &= ~0xffffffff80000000ULL; - add_memory_region(kernel_start, kernel_size, BOOT_MEM_RAM); + memblock_add(kernel_start, kernel_size); #endif /* CONFIG_CRASH_DUMP */ #ifdef CONFIG_CAVIUM_RESERVE32 diff --git a/arch/mips/cobalt/setup.c b/arch/mips/cobalt/setup.c index c136a18c7221..46581e686882 100644 --- a/arch/mips/cobalt/setup.c +++ b/arch/mips/cobalt/setup.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include @@ -112,7 +113,7 @@ void __init prom_init(void) strlcat(arcs_cmdline, " ", COMMAND_LINE_SIZE); } - add_memory_region(0x0, memsz, BOOT_MEM_RAM); + memblock_add(0, memsz); setup_8250_early_printk_port(CKSEG1ADDR(0x1c800000), 0, 0); } diff --git a/arch/mips/dec/prom/memory.c b/arch/mips/dec/prom/memory.c index 5073d2ed78bb..288772c3eb0c 100644 --- a/arch/mips/dec/prom/memory.c +++ b/arch/mips/dec/prom/memory.c @@ -12,7 +12,6 @@ #include #include -#include #include #include #include @@ -50,8 +49,7 @@ static inline void pmax_setup_memory_region(void) } memcpy((void *)(CKSEG0 + 0x80), &old_handler, 0x80); - add_memory_region(0, (unsigned long)memory_page - CKSEG1 - CHUNK_SIZE, - BOOT_MEM_RAM); + memblock_add(0, (unsigned long)memory_page - CKSEG1 - CHUNK_SIZE); } /* @@ -76,13 +74,13 @@ static inline void rex_setup_memory_region(void) else if (!mem_size) mem_start += (8 * bm->pagesize); else { - add_memory_region(mem_start, mem_size, BOOT_MEM_RAM); + memblock_add(mem_start, mem_size); mem_start += mem_size + (8 * bm->pagesize); mem_size = 0; } } if (mem_size) - add_memory_region(mem_start, mem_size, BOOT_MEM_RAM); + memblock_add(mem_start, mem_size); } void __init prom_meminit(u32 magic) diff --git a/arch/mips/fw/arc/memory.c b/arch/mips/fw/arc/memory.c index da0712ad85f5..37625ae5e35d 100644 --- a/arch/mips/fw/arc/memory.c +++ b/arch/mips/fw/arc/memory.c @@ -68,20 +68,24 @@ static char *arc_mtypes[8] = { : arc_mtypes[a.arc] #endif +enum { + mem_free, mem_prom_used, mem_reserved +}; + static inline int memtype_classify_arcs(union linux_memtypes type) { switch (type.arcs) { case arcs_fcontig: case arcs_free: - return BOOT_MEM_RAM; + return mem_free; case arcs_atmp: - return BOOT_MEM_ROM_DATA; + return mem_prom_used; case arcs_eblock: case arcs_rvpage: case arcs_bmem: case arcs_prog: case arcs_aperm: - return BOOT_MEM_RESERVED; + return mem_reserved; default: BUG(); } @@ -93,15 +97,15 @@ static inline int memtype_classify_arc(union linux_memtypes type) switch (type.arc) { case arc_free: case arc_fcontig: - return BOOT_MEM_RAM; + return mem_free; case arc_atmp: - return BOOT_MEM_ROM_DATA; + return mem_prom_used; case arc_eblock: case arc_rvpage: case arc_bmem: case arc_prog: case arc_aperm: - return BOOT_MEM_RESERVED; + return mem_reserved; default: BUG(); } @@ -143,9 +147,17 @@ void __weak __init prom_meminit(void) size = p->pages << ARC_PAGE_SHIFT; type = prom_memtype_classify(p->type); - add_memory_region(base, size, type); + /* ignore mirrored RAM on IP28/IP30 */ + if (base < PHYS_OFFSET) + continue; - if (type == BOOT_MEM_ROM_DATA) { + memblock_add(base, size); + + if (type == mem_reserved) + memblock_reserve(base, size); + + if (type == mem_prom_used) { + memblock_reserve(base, size); if (nr_prom_mem >= 5) { pr_err("Too many ROM DATA regions"); continue; diff --git a/arch/mips/fw/sni/sniprom.c b/arch/mips/fw/sni/sniprom.c index 80112f2298b6..8f6730376a42 100644 --- a/arch/mips/fw/sni/sniprom.c +++ b/arch/mips/fw/sni/sniprom.c @@ -11,6 +11,7 @@ #include #include +#include #include #include @@ -131,8 +132,7 @@ static void __init sni_mem_init(void) } pr_debug("Bank%d: %08x @ %08x\n", i, memconf[i].size, memconf[i].base); - add_memory_region(memconf[i].base, memconf[i].size, - BOOT_MEM_RAM); + memblock_add(memconf[i].base, memconf[i].size); } } diff --git a/arch/mips/include/asm/bootinfo.h b/arch/mips/include/asm/bootinfo.h index 6dd173a22aeb..aa03b1237155 100644 --- a/arch/mips/include/asm/bootinfo.h +++ b/arch/mips/include/asm/bootinfo.h @@ -90,13 +90,6 @@ const char *get_system_type(void); extern unsigned long mips_machtype; -#define BOOT_MEM_RAM 1 -#define BOOT_MEM_ROM_DATA 2 -#define BOOT_MEM_RESERVED 3 -#define BOOT_MEM_INIT_RAM 4 -#define BOOT_MEM_NOMAP 5 - -extern void add_memory_region(phys_addr_t start, phys_addr_t size, long type); extern void detect_memory_region(phys_addr_t start, phys_addr_t sz_min, phys_addr_t sz_max); extern void prom_init(void); diff --git a/arch/mips/include/asm/netlogic/psb-bootinfo.h b/arch/mips/include/asm/netlogic/psb-bootinfo.h index 272544b55ceb..c716e9397113 100644 --- a/arch/mips/include/asm/netlogic/psb-bootinfo.h +++ b/arch/mips/include/asm/netlogic/psb-bootinfo.h @@ -87,6 +87,7 @@ struct nlm_boot_mem_map { uint32_t type; /* type of memory segment */ } map[NLM_BOOT_MEM_MAP_MAX]; }; +#define NLM_BOOT_MEM_RAM 1 /* Pointer to saved boot loader info */ extern struct psb_info nlm_prom_info; diff --git a/arch/mips/kernel/prom.c b/arch/mips/kernel/prom.c index 9e50dc8df2f6..6abebd57b218 100644 --- a/arch/mips/kernel/prom.c +++ b/arch/mips/kernel/prom.c @@ -36,31 +36,6 @@ char *mips_get_machine_name(void) } #ifdef CONFIG_USE_OF -void __init early_init_dt_add_memory_arch(u64 base, u64 size) -{ - if (base >= PHYS_ADDR_MAX) { - pr_warn("Trying to add an invalid memory region, skipped\n"); - return; - } - - /* Truncate the passed memory region instead of type casting */ - if (base + size - 1 >= PHYS_ADDR_MAX || base + size < base) { - pr_warn("Truncate memory region %llx @ %llx to size %llx\n", - size, base, PHYS_ADDR_MAX - base); - size = PHYS_ADDR_MAX - base; - } - - add_memory_region(base, size, BOOT_MEM_RAM); -} - -int __init early_init_dt_reserve_memory_arch(phys_addr_t base, - phys_addr_t size, bool nomap) -{ - add_memory_region(base, size, - nomap ? BOOT_MEM_NOMAP : BOOT_MEM_RESERVED); - - return 0; -} void __init __dt_setup_arch(void *bph) { diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 4c04a86f075b..fb05b66e111f 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -91,45 +91,6 @@ unsigned long ARCH_PFN_OFFSET; EXPORT_SYMBOL(ARCH_PFN_OFFSET); #endif -void __init add_memory_region(phys_addr_t start, phys_addr_t size, long type) -{ - /* - * Note: This function only exists for historical reason, - * new code should use memblock_add or memblock_add_node instead. - */ - - /* - * If the region reaches the top of the physical address space, adjust - * the size slightly so that (start + size) doesn't overflow - */ - if (start + size - 1 == PHYS_ADDR_MAX) - --size; - - /* Sanity check */ - if (start + size < start) { - pr_warn("Trying to add an invalid memory region, skipped\n"); - return; - } - - if (start < PHYS_OFFSET) - return; - - memblock_add(start, size); - /* Reserve any memory except the ordinary RAM ranges. */ - switch (type) { - case BOOT_MEM_RAM: - break; - - case BOOT_MEM_NOMAP: /* Discard the range from the system. */ - memblock_remove(start, size); - break; - - default: /* Reserve the rest of the memory types at boot time */ - memblock_reserve(start, size); - break; - } -} - void __init detect_memory_region(phys_addr_t start, phys_addr_t sz_min, phys_addr_t sz_max) { void *dm = &detect_magic; @@ -146,7 +107,7 @@ void __init detect_memory_region(phys_addr_t start, phys_addr_t sz_min, phys_add ((unsigned long long) sz_min) / SZ_1M, ((unsigned long long) sz_max) / SZ_1M); - add_memory_region(start, size, BOOT_MEM_RAM); + memblock_add(start, size); } /* @@ -400,7 +361,7 @@ static int __init early_parse_mem(char *p) if (*p == '@') start = memparse(p + 1, &p); - add_memory_region(start, size, BOOT_MEM_RAM); + memblock_add(start, size); return 0; } @@ -426,13 +387,14 @@ static int __init early_parse_memmap(char *p) if (*p == '@') { start_at = memparse(p+1, &p); - add_memory_region(start_at, mem_size, BOOT_MEM_RAM); + memblock_add(start_at, mem_size); } else if (*p == '#') { pr_err("\"memmap=nn#ss\" (force ACPI data) invalid on MIPS\n"); return -EINVAL; } else if (*p == '$') { start_at = memparse(p+1, &p); - add_memory_region(start_at, mem_size, BOOT_MEM_RESERVED); + memblock_add(start_at, mem_size); + memblock_reserve(start_at, mem_size); } else { pr_err("\"memmap\" invalid format!\n"); return -EINVAL; @@ -644,7 +606,7 @@ static void __init bootcmdline_init(void) * arch_mem_init - initialize memory management subsystem * * o plat_mem_setup() detects the memory configuration and will record detected - * memory areas using add_memory_region. + * memory areas using memblock_add. * * At this stage the memory configuration of the system is known to the * kernel but generic memory management system is still entirely uninitialized. diff --git a/arch/mips/loongson2ef/common/mem.c b/arch/mips/loongson2ef/common/mem.c index ae21f1c62baa..057d58bb470e 100644 --- a/arch/mips/loongson2ef/common/mem.c +++ b/arch/mips/loongson2ef/common/mem.c @@ -17,10 +17,7 @@ u32 memsize, highmemsize; void __init prom_init_memory(void) { - add_memory_region(0x0, (memsize << 20), BOOT_MEM_RAM); - - add_memory_region(memsize << 20, LOONGSON_PCI_MEM_START - (memsize << - 20), BOOT_MEM_RESERVED); + memblock_add(0x0, (memsize << 20)); #ifdef CONFIG_CPU_SUPPORTS_ADDRWINCFG { @@ -41,12 +38,7 @@ void __init prom_init_memory(void) #ifdef CONFIG_64BIT if (highmemsize > 0) - add_memory_region(LOONGSON_HIGHMEM_START, - highmemsize << 20, BOOT_MEM_RAM); - - add_memory_region(LOONGSON_PCI_MEM_END + 1, LOONGSON_HIGHMEM_START - - LOONGSON_PCI_MEM_END - 1, BOOT_MEM_RESERVED); - + memblock_add(LOONGSON_HIGHMEM_START, highmemsize << 20); #endif /* !CONFIG_64BIT */ } diff --git a/arch/mips/loongson32/common/prom.c b/arch/mips/loongson32/common/prom.c index fd76114fa3b0..c133b5adf34e 100644 --- a/arch/mips/loongson32/common/prom.c +++ b/arch/mips/loongson32/common/prom.c @@ -7,8 +7,8 @@ #include #include +#include #include -#include #include #include @@ -42,5 +42,5 @@ void __init prom_free_prom_memory(void) void __init plat_mem_setup(void) { - add_memory_region(0x0, (memsize << 20), BOOT_MEM_RAM); + memblock_add(0x0, (memsize << 20)); } diff --git a/arch/mips/netlogic/xlp/setup.c b/arch/mips/netlogic/xlp/setup.c index 1a0fc5b62ba4..230adaf93e11 100644 --- a/arch/mips/netlogic/xlp/setup.c +++ b/arch/mips/netlogic/xlp/setup.c @@ -89,7 +89,7 @@ static void __init xlp_init_mem_from_bars(void) if (map[i] > 0x10000000 && map[i] < 0x20000000) map[i] = 0x20000000; - add_memory_region(map[i], map[i+1] - map[i], BOOT_MEM_RAM); + memblock_add(map[i], map[i+1] - map[i]); } } diff --git a/arch/mips/netlogic/xlr/setup.c b/arch/mips/netlogic/xlr/setup.c index 72ceddc9a03f..627e88101316 100644 --- a/arch/mips/netlogic/xlr/setup.c +++ b/arch/mips/netlogic/xlr/setup.c @@ -34,6 +34,7 @@ #include #include +#include #include #include @@ -149,7 +150,7 @@ static void prom_add_memory(void) bootm = (void *)(long)nlm_prom_info.psb_mem_map; for (i = 0; i < bootm->nr_map; i++) { - if (bootm->map[i].type != BOOT_MEM_RAM) + if (bootm->map[i].type != NLM_BOOT_MEM_RAM) continue; start = bootm->map[i].addr; size = bootm->map[i].size; @@ -158,7 +159,7 @@ static void prom_add_memory(void) if (i == 0 && start == 0 && size == 0x0c000000) size = 0x0ff00000; - add_memory_region(start, size - pref_backup, BOOT_MEM_RAM); + memblock_add(start, size - pref_backup); } } diff --git a/arch/mips/ralink/of.c b/arch/mips/ralink/of.c index 90c6d4a11c5d..cbae9d23ab7f 100644 --- a/arch/mips/ralink/of.c +++ b/arch/mips/ralink/of.c @@ -84,8 +84,7 @@ void __init plat_mem_setup(void) if (memory_dtb) of_scan_flat_dt(early_init_dt_scan_memory, NULL); else if (soc_info.mem_size) - add_memory_region(soc_info.mem_base, soc_info.mem_size * SZ_1M, - BOOT_MEM_RAM); + memblock_add(soc_info.mem_base, soc_info.mem_size * SZ_1M); else detect_memory_region(soc_info.mem_base, soc_info.mem_size_min * SZ_1M, diff --git a/arch/mips/rb532/prom.c b/arch/mips/rb532/prom.c index 303cc3dc1749..a9d1f2019dc3 100644 --- a/arch/mips/rb532/prom.c +++ b/arch/mips/rb532/prom.c @@ -126,5 +126,5 @@ void __init prom_init(void) /* give all RAM to boot allocator, * except for the first 0x400 and the last 0x200 bytes */ - add_memory_region(ddrbase + 0x400, memsize - 0x600, BOOT_MEM_RAM); + memblock_add(ddrbase + 0x400, memsize - 0x600); } diff --git a/arch/mips/sgi-ip32/ip32-memory.c b/arch/mips/sgi-ip32/ip32-memory.c index 62b956cc2d1d..0f53fed39da6 100644 --- a/arch/mips/sgi-ip32/ip32-memory.c +++ b/arch/mips/sgi-ip32/ip32-memory.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include @@ -36,7 +37,7 @@ void __init prom_meminit(void) printk("CRIME MC: bank %u base 0x%016Lx size %LuMiB\n", bank, base, size >> 20); - add_memory_region(base, size, BOOT_MEM_RAM); + memblock_add(base, size); } } diff --git a/arch/mips/sibyte/common/cfe.c b/arch/mips/sibyte/common/cfe.c index cbf5939ed53a..89f7fca45152 100644 --- a/arch/mips/sibyte/common/cfe.c +++ b/arch/mips/sibyte/common/cfe.c @@ -114,16 +114,14 @@ static __init void prom_meminit(void) if (initrd_start) { if ((initrd_pstart > addr) && (initrd_pstart < (addr + size))) { - add_memory_region(addr, - initrd_pstart - addr, - BOOT_MEM_RAM); + memblock_add(addr, + initrd_pstart - addr); rd_flag = 1; } if ((initrd_pend > addr) && (initrd_pend < (addr + size))) { - add_memory_region(initrd_pend, - (addr + size) - initrd_pend, - BOOT_MEM_RAM); + memblock_add(initrd_pend, + (addr + size) - initrd_pend); rd_flag = 1; } } @@ -142,7 +140,7 @@ static __init void prom_meminit(void) */ if (size > 512) size -= 512; - add_memory_region(addr, size, BOOT_MEM_RAM); + memblock_add(addr, size); } board_mem_region_addrs[board_mem_region_count] = addr; board_mem_region_sizes[board_mem_region_count] = size; @@ -158,8 +156,8 @@ static __init void prom_meminit(void) } #ifdef CONFIG_BLK_DEV_INITRD if (initrd_start) { - add_memory_region(initrd_pstart, initrd_pend - initrd_pstart, - BOOT_MEM_RESERVED); + memblock_add(initrd_pstart, initrd_pend - initrd_pstart); + memblock_reserve(initrd_pstart, initrd_pend - initrd_pstart); } #endif } diff --git a/arch/mips/txx9/jmr3927/prom.c b/arch/mips/txx9/jmr3927/prom.c index 68a96473c134..53c68de54d30 100644 --- a/arch/mips/txx9/jmr3927/prom.c +++ b/arch/mips/txx9/jmr3927/prom.c @@ -37,7 +37,7 @@ */ #include #include -#include +#include #include #include @@ -47,6 +47,6 @@ void __init jmr3927_prom_init(void) if ((tx3927_ccfgptr->ccfg & TX3927_CCFG_TLBOFF) == 0) pr_err("TX3927 TLB off\n"); - add_memory_region(0, JMR3927_SDRAM_SIZE, BOOT_MEM_RAM); + memblock_add(0, JMR3927_SDRAM_SIZE); txx9_sio_putchar_init(TX3927_SIO_REG(1)); } diff --git a/arch/mips/txx9/rbtx4927/prom.c b/arch/mips/txx9/rbtx4927/prom.c index fe6d0b54763f..9b4acff826eb 100644 --- a/arch/mips/txx9/rbtx4927/prom.c +++ b/arch/mips/txx9/rbtx4927/prom.c @@ -29,13 +29,14 @@ * with this program; if not, write to the Free Software Foundation, Inc., * 675 Mass Ave, Cambridge, MA 02139, USA. */ + #include -#include +#include #include #include void __init rbtx4927_prom_init(void) { - add_memory_region(0, tx4927_get_mem_size(), BOOT_MEM_RAM); + memblock_add(0, tx4927_get_mem_size()); txx9_sio_putchar_init(TX4927_SIO_REG(0) & 0xfffffffffULL); } diff --git a/arch/mips/txx9/rbtx4938/prom.c b/arch/mips/txx9/rbtx4938/prom.c index 2b36a2ee744c..0de84716a428 100644 --- a/arch/mips/txx9/rbtx4938/prom.c +++ b/arch/mips/txx9/rbtx4938/prom.c @@ -12,12 +12,11 @@ #include #include -#include #include #include void __init rbtx4938_prom_init(void) { - add_memory_region(0, tx4938_get_mem_size(), BOOT_MEM_RAM); + memblock_add(0, tx4938_get_mem_size()); txx9_sio_putchar_init(TX4938_SIO_REG(0) & 0xfffffffffULL); } diff --git a/arch/mips/txx9/rbtx4939/prom.c b/arch/mips/txx9/rbtx4939/prom.c index 1dc47ce81c92..ba25ba1bd2ec 100644 --- a/arch/mips/txx9/rbtx4939/prom.c +++ b/arch/mips/txx9/rbtx4939/prom.c @@ -7,7 +7,7 @@ */ #include -#include +#include #include #include @@ -23,7 +23,7 @@ void __init rbtx4939_prom_init(void) win = ____raw_readq(&tx4939_ddrcptr->win[i]); start = (unsigned long)(win >> 48); size = (((unsigned long)(win >> 32) & 0xffff) + 1) - start; - add_memory_region(start << 20, size << 20, BOOT_MEM_RAM); + memblock_add(start << 20, size << 20); } txx9_sio_putchar_init(TX4939_SIO_REG(0) & 0xfffffffffULL); } From a616c0617aa36ea0bd51af90adfb87e8d3e9cb72 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Thu, 8 Oct 2020 23:33:25 +0200 Subject: [PATCH 404/645] MIPS: cpu-probe: move fpu probing/handling into its own file cpu-probe.c has grown when supporting more and more CPUs and there are use cases where probing for all the CPUs isn't useful like running on a R3k system. But still the fpu handling is nearly the same. For sharing put the fpu code into it's own file. Signed-off-by: Thomas Bogendoerfer --- arch/mips/kernel/Makefile | 1 + arch/mips/kernel/cpu-probe.c | 326 +---------------------------------- arch/mips/kernel/fpu-probe.c | 321 ++++++++++++++++++++++++++++++++++ arch/mips/kernel/fpu-probe.h | 40 +++++ 4 files changed, 364 insertions(+), 324 deletions(-) create mode 100644 arch/mips/kernel/fpu-probe.c create mode 100644 arch/mips/kernel/fpu-probe.h diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile index 13a26d254829..026801c21724 100644 --- a/arch/mips/kernel/Makefile +++ b/arch/mips/kernel/Makefile @@ -42,6 +42,7 @@ sw-$(CONFIG_CPU_TX39XX) := r2300_switch.o sw-$(CONFIG_CPU_CAVIUM_OCTEON) := octeon_switch.o obj-y += $(sw-y) +obj-$(CONFIG_MIPS_FP_SUPPORT) += fpu-probe.o obj-$(CONFIG_CPU_R2300_FPU) += r2300_fpu.o obj-$(CONFIG_CPU_R4K_FPU) += r4k_fpu.o diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index 6be23f205e74..b8e073772bdb 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -28,336 +28,14 @@ #include #include +#include "fpu-probe.h" + #include /* Hardware capabilities */ unsigned int elf_hwcap __read_mostly; EXPORT_SYMBOL_GPL(elf_hwcap); -#ifdef CONFIG_MIPS_FP_SUPPORT - -/* - * Get the FPU Implementation/Revision. - */ -static inline unsigned long cpu_get_fpu_id(void) -{ - unsigned long tmp, fpu_id; - - tmp = read_c0_status(); - __enable_fpu(FPU_AS_IS); - fpu_id = read_32bit_cp1_register(CP1_REVISION); - write_c0_status(tmp); - return fpu_id; -} - -/* - * Check if the CPU has an external FPU. - */ -static inline int __cpu_has_fpu(void) -{ - return (cpu_get_fpu_id() & FPIR_IMP_MASK) != FPIR_IMP_NONE; -} - -/* - * Determine the FCSR mask for FPU hardware. - */ -static inline void cpu_set_fpu_fcsr_mask(struct cpuinfo_mips *c) -{ - unsigned long sr, mask, fcsr, fcsr0, fcsr1; - - fcsr = c->fpu_csr31; - mask = FPU_CSR_ALL_X | FPU_CSR_ALL_E | FPU_CSR_ALL_S | FPU_CSR_RM; - - sr = read_c0_status(); - __enable_fpu(FPU_AS_IS); - - fcsr0 = fcsr & mask; - write_32bit_cp1_register(CP1_STATUS, fcsr0); - fcsr0 = read_32bit_cp1_register(CP1_STATUS); - - fcsr1 = fcsr | ~mask; - write_32bit_cp1_register(CP1_STATUS, fcsr1); - fcsr1 = read_32bit_cp1_register(CP1_STATUS); - - write_32bit_cp1_register(CP1_STATUS, fcsr); - - write_c0_status(sr); - - c->fpu_msk31 = ~(fcsr0 ^ fcsr1) & ~mask; -} - -/* - * Determine the IEEE 754 NaN encodings and ABS.fmt/NEG.fmt execution modes - * supported by FPU hardware. - */ -static void cpu_set_fpu_2008(struct cpuinfo_mips *c) -{ - if (c->isa_level & (MIPS_CPU_ISA_M32R1 | MIPS_CPU_ISA_M64R1 | - MIPS_CPU_ISA_M32R2 | MIPS_CPU_ISA_M64R2 | - MIPS_CPU_ISA_M32R5 | MIPS_CPU_ISA_M64R5 | - MIPS_CPU_ISA_M32R6 | MIPS_CPU_ISA_M64R6)) { - unsigned long sr, fir, fcsr, fcsr0, fcsr1; - - sr = read_c0_status(); - __enable_fpu(FPU_AS_IS); - - fir = read_32bit_cp1_register(CP1_REVISION); - if (fir & MIPS_FPIR_HAS2008) { - fcsr = read_32bit_cp1_register(CP1_STATUS); - - /* - * MAC2008 toolchain never landed in real world, so we're only - * testing wether it can be disabled and don't try to enabled - * it. - */ - fcsr0 = fcsr & ~(FPU_CSR_ABS2008 | FPU_CSR_NAN2008 | FPU_CSR_MAC2008); - write_32bit_cp1_register(CP1_STATUS, fcsr0); - fcsr0 = read_32bit_cp1_register(CP1_STATUS); - - fcsr1 = fcsr | FPU_CSR_ABS2008 | FPU_CSR_NAN2008; - write_32bit_cp1_register(CP1_STATUS, fcsr1); - fcsr1 = read_32bit_cp1_register(CP1_STATUS); - - write_32bit_cp1_register(CP1_STATUS, fcsr); - - if (c->isa_level & (MIPS_CPU_ISA_M32R2 | MIPS_CPU_ISA_M64R2)) { - /* - * The bit for MAC2008 might be reused by R6 in future, - * so we only test for R2-R5. - */ - if (fcsr0 & FPU_CSR_MAC2008) - c->options |= MIPS_CPU_MAC_2008_ONLY; - } - - if (!(fcsr0 & FPU_CSR_NAN2008)) - c->options |= MIPS_CPU_NAN_LEGACY; - if (fcsr1 & FPU_CSR_NAN2008) - c->options |= MIPS_CPU_NAN_2008; - - if ((fcsr0 ^ fcsr1) & FPU_CSR_ABS2008) - c->fpu_msk31 &= ~FPU_CSR_ABS2008; - else - c->fpu_csr31 |= fcsr & FPU_CSR_ABS2008; - - if ((fcsr0 ^ fcsr1) & FPU_CSR_NAN2008) - c->fpu_msk31 &= ~FPU_CSR_NAN2008; - else - c->fpu_csr31 |= fcsr & FPU_CSR_NAN2008; - } else { - c->options |= MIPS_CPU_NAN_LEGACY; - } - - write_c0_status(sr); - } else { - c->options |= MIPS_CPU_NAN_LEGACY; - } -} - -/* - * IEEE 754 conformance mode to use. Affects the NaN encoding and the - * ABS.fmt/NEG.fmt execution mode. - */ -static enum { STRICT, LEGACY, STD2008, RELAXED } ieee754 = STRICT; - -/* - * Set the IEEE 754 NaN encodings and the ABS.fmt/NEG.fmt execution modes - * to support by the FPU emulator according to the IEEE 754 conformance - * mode selected. Note that "relaxed" straps the emulator so that it - * allows 2008-NaN binaries even for legacy processors. - */ -static void cpu_set_nofpu_2008(struct cpuinfo_mips *c) -{ - c->options &= ~(MIPS_CPU_NAN_2008 | MIPS_CPU_NAN_LEGACY); - c->fpu_csr31 &= ~(FPU_CSR_ABS2008 | FPU_CSR_NAN2008); - c->fpu_msk31 &= ~(FPU_CSR_ABS2008 | FPU_CSR_NAN2008); - - switch (ieee754) { - case STRICT: - if (c->isa_level & (MIPS_CPU_ISA_M32R1 | MIPS_CPU_ISA_M64R1 | - MIPS_CPU_ISA_M32R2 | MIPS_CPU_ISA_M64R2 | - MIPS_CPU_ISA_M32R5 | MIPS_CPU_ISA_M64R5 | - MIPS_CPU_ISA_M32R6 | MIPS_CPU_ISA_M64R6)) { - c->options |= MIPS_CPU_NAN_2008 | MIPS_CPU_NAN_LEGACY; - } else { - c->options |= MIPS_CPU_NAN_LEGACY; - c->fpu_msk31 |= FPU_CSR_ABS2008 | FPU_CSR_NAN2008; - } - break; - case LEGACY: - c->options |= MIPS_CPU_NAN_LEGACY; - c->fpu_msk31 |= FPU_CSR_ABS2008 | FPU_CSR_NAN2008; - break; - case STD2008: - c->options |= MIPS_CPU_NAN_2008; - c->fpu_csr31 |= FPU_CSR_ABS2008 | FPU_CSR_NAN2008; - c->fpu_msk31 |= FPU_CSR_ABS2008 | FPU_CSR_NAN2008; - break; - case RELAXED: - c->options |= MIPS_CPU_NAN_2008 | MIPS_CPU_NAN_LEGACY; - break; - } -} - -/* - * Override the IEEE 754 NaN encoding and ABS.fmt/NEG.fmt execution mode - * according to the "ieee754=" parameter. - */ -static void cpu_set_nan_2008(struct cpuinfo_mips *c) -{ - switch (ieee754) { - case STRICT: - mips_use_nan_legacy = !!cpu_has_nan_legacy; - mips_use_nan_2008 = !!cpu_has_nan_2008; - break; - case LEGACY: - mips_use_nan_legacy = !!cpu_has_nan_legacy; - mips_use_nan_2008 = !cpu_has_nan_legacy; - break; - case STD2008: - mips_use_nan_legacy = !cpu_has_nan_2008; - mips_use_nan_2008 = !!cpu_has_nan_2008; - break; - case RELAXED: - mips_use_nan_legacy = true; - mips_use_nan_2008 = true; - break; - } -} - -/* - * IEEE 754 NaN encoding and ABS.fmt/NEG.fmt execution mode override - * settings: - * - * strict: accept binaries that request a NaN encoding supported by the FPU - * legacy: only accept legacy-NaN binaries - * 2008: only accept 2008-NaN binaries - * relaxed: accept any binaries regardless of whether supported by the FPU - */ -static int __init ieee754_setup(char *s) -{ - if (!s) - return -1; - else if (!strcmp(s, "strict")) - ieee754 = STRICT; - else if (!strcmp(s, "legacy")) - ieee754 = LEGACY; - else if (!strcmp(s, "2008")) - ieee754 = STD2008; - else if (!strcmp(s, "relaxed")) - ieee754 = RELAXED; - else - return -1; - - if (!(boot_cpu_data.options & MIPS_CPU_FPU)) - cpu_set_nofpu_2008(&boot_cpu_data); - cpu_set_nan_2008(&boot_cpu_data); - - return 0; -} - -early_param("ieee754", ieee754_setup); - -/* - * Set the FIR feature flags for the FPU emulator. - */ -static void cpu_set_nofpu_id(struct cpuinfo_mips *c) -{ - u32 value; - - value = 0; - if (c->isa_level & (MIPS_CPU_ISA_M32R1 | MIPS_CPU_ISA_M64R1 | - MIPS_CPU_ISA_M32R2 | MIPS_CPU_ISA_M64R2 | - MIPS_CPU_ISA_M32R5 | MIPS_CPU_ISA_M64R5 | - MIPS_CPU_ISA_M32R6 | MIPS_CPU_ISA_M64R6)) - value |= MIPS_FPIR_D | MIPS_FPIR_S; - if (c->isa_level & (MIPS_CPU_ISA_M32R2 | MIPS_CPU_ISA_M64R2 | - MIPS_CPU_ISA_M32R5 | MIPS_CPU_ISA_M64R5 | - MIPS_CPU_ISA_M32R6 | MIPS_CPU_ISA_M64R6)) - value |= MIPS_FPIR_F64 | MIPS_FPIR_L | MIPS_FPIR_W; - if (c->options & MIPS_CPU_NAN_2008) - value |= MIPS_FPIR_HAS2008; - c->fpu_id = value; -} - -/* Determined FPU emulator mask to use for the boot CPU with "nofpu". */ -static unsigned int mips_nofpu_msk31; - -/* - * Set options for FPU hardware. - */ -static void cpu_set_fpu_opts(struct cpuinfo_mips *c) -{ - c->fpu_id = cpu_get_fpu_id(); - mips_nofpu_msk31 = c->fpu_msk31; - - if (c->isa_level & (MIPS_CPU_ISA_M32R1 | MIPS_CPU_ISA_M64R1 | - MIPS_CPU_ISA_M32R2 | MIPS_CPU_ISA_M64R2 | - MIPS_CPU_ISA_M32R5 | MIPS_CPU_ISA_M64R5 | - MIPS_CPU_ISA_M32R6 | MIPS_CPU_ISA_M64R6)) { - if (c->fpu_id & MIPS_FPIR_3D) - c->ases |= MIPS_ASE_MIPS3D; - if (c->fpu_id & MIPS_FPIR_UFRP) - c->options |= MIPS_CPU_UFR; - if (c->fpu_id & MIPS_FPIR_FREP) - c->options |= MIPS_CPU_FRE; - } - - cpu_set_fpu_fcsr_mask(c); - cpu_set_fpu_2008(c); - cpu_set_nan_2008(c); -} - -/* - * Set options for the FPU emulator. - */ -static void cpu_set_nofpu_opts(struct cpuinfo_mips *c) -{ - c->options &= ~MIPS_CPU_FPU; - c->fpu_msk31 = mips_nofpu_msk31; - - cpu_set_nofpu_2008(c); - cpu_set_nan_2008(c); - cpu_set_nofpu_id(c); -} - -static int mips_fpu_disabled; - -static int __init fpu_disable(char *s) -{ - cpu_set_nofpu_opts(&boot_cpu_data); - mips_fpu_disabled = 1; - - return 1; -} - -__setup("nofpu", fpu_disable); - -#else /* !CONFIG_MIPS_FP_SUPPORT */ - -#define mips_fpu_disabled 1 - -static inline unsigned long cpu_get_fpu_id(void) -{ - return FPIR_IMP_NONE; -} - -static inline int __cpu_has_fpu(void) -{ - return 0; -} - -static void cpu_set_fpu_opts(struct cpuinfo_mips *c) -{ - /* no-op */ -} - -static void cpu_set_nofpu_opts(struct cpuinfo_mips *c) -{ - /* no-op */ -} - -#endif /* CONFIG_MIPS_FP_SUPPORT */ - static inline unsigned long cpu_get_msa_id(void) { unsigned long status, msa_id; diff --git a/arch/mips/kernel/fpu-probe.c b/arch/mips/kernel/fpu-probe.c new file mode 100644 index 000000000000..e689d6a83234 --- /dev/null +++ b/arch/mips/kernel/fpu-probe.c @@ -0,0 +1,321 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Processor capabilities determination functions. + * + * Copyright (C) xxxx the Anonymous + * Copyright (C) 1994 - 2006 Ralf Baechle + * Copyright (C) 2003, 2004 Maciej W. Rozycki + * Copyright (C) 2001, 2004, 2011, 2012 MIPS Technologies, Inc. + */ + +#include +#include + +#include +#include +#include +#include +#include +#include +#include + +#include "fpu-probe.h" + +/* + * Get the FPU Implementation/Revision. + */ +static inline unsigned long cpu_get_fpu_id(void) +{ + unsigned long tmp, fpu_id; + + tmp = read_c0_status(); + __enable_fpu(FPU_AS_IS); + fpu_id = read_32bit_cp1_register(CP1_REVISION); + write_c0_status(tmp); + return fpu_id; +} + +/* + * Check if the CPU has an external FPU. + */ +int __cpu_has_fpu(void) +{ + return (cpu_get_fpu_id() & FPIR_IMP_MASK) != FPIR_IMP_NONE; +} + +/* + * Determine the FCSR mask for FPU hardware. + */ +static inline void cpu_set_fpu_fcsr_mask(struct cpuinfo_mips *c) +{ + unsigned long sr, mask, fcsr, fcsr0, fcsr1; + + fcsr = c->fpu_csr31; + mask = FPU_CSR_ALL_X | FPU_CSR_ALL_E | FPU_CSR_ALL_S | FPU_CSR_RM; + + sr = read_c0_status(); + __enable_fpu(FPU_AS_IS); + + fcsr0 = fcsr & mask; + write_32bit_cp1_register(CP1_STATUS, fcsr0); + fcsr0 = read_32bit_cp1_register(CP1_STATUS); + + fcsr1 = fcsr | ~mask; + write_32bit_cp1_register(CP1_STATUS, fcsr1); + fcsr1 = read_32bit_cp1_register(CP1_STATUS); + + write_32bit_cp1_register(CP1_STATUS, fcsr); + + write_c0_status(sr); + + c->fpu_msk31 = ~(fcsr0 ^ fcsr1) & ~mask; +} + +/* + * Determine the IEEE 754 NaN encodings and ABS.fmt/NEG.fmt execution modes + * supported by FPU hardware. + */ +static void cpu_set_fpu_2008(struct cpuinfo_mips *c) +{ + if (c->isa_level & (MIPS_CPU_ISA_M32R1 | MIPS_CPU_ISA_M64R1 | + MIPS_CPU_ISA_M32R2 | MIPS_CPU_ISA_M64R2 | + MIPS_CPU_ISA_M32R5 | MIPS_CPU_ISA_M64R5 | + MIPS_CPU_ISA_M32R6 | MIPS_CPU_ISA_M64R6)) { + unsigned long sr, fir, fcsr, fcsr0, fcsr1; + + sr = read_c0_status(); + __enable_fpu(FPU_AS_IS); + + fir = read_32bit_cp1_register(CP1_REVISION); + if (fir & MIPS_FPIR_HAS2008) { + fcsr = read_32bit_cp1_register(CP1_STATUS); + + /* + * MAC2008 toolchain never landed in real world, so + * we're only testing whether it can be disabled and + * don't try to enabled it. + */ + fcsr0 = fcsr & ~(FPU_CSR_ABS2008 | FPU_CSR_NAN2008 | + FPU_CSR_MAC2008); + write_32bit_cp1_register(CP1_STATUS, fcsr0); + fcsr0 = read_32bit_cp1_register(CP1_STATUS); + + fcsr1 = fcsr | FPU_CSR_ABS2008 | FPU_CSR_NAN2008; + write_32bit_cp1_register(CP1_STATUS, fcsr1); + fcsr1 = read_32bit_cp1_register(CP1_STATUS); + + write_32bit_cp1_register(CP1_STATUS, fcsr); + + if (c->isa_level & (MIPS_CPU_ISA_M32R2 | + MIPS_CPU_ISA_M64R2)) { + /* + * The bit for MAC2008 might be reused by R6 + * in future, so we only test for R2-R5. + */ + if (fcsr0 & FPU_CSR_MAC2008) + c->options |= MIPS_CPU_MAC_2008_ONLY; + } + + if (!(fcsr0 & FPU_CSR_NAN2008)) + c->options |= MIPS_CPU_NAN_LEGACY; + if (fcsr1 & FPU_CSR_NAN2008) + c->options |= MIPS_CPU_NAN_2008; + + if ((fcsr0 ^ fcsr1) & FPU_CSR_ABS2008) + c->fpu_msk31 &= ~FPU_CSR_ABS2008; + else + c->fpu_csr31 |= fcsr & FPU_CSR_ABS2008; + + if ((fcsr0 ^ fcsr1) & FPU_CSR_NAN2008) + c->fpu_msk31 &= ~FPU_CSR_NAN2008; + else + c->fpu_csr31 |= fcsr & FPU_CSR_NAN2008; + } else { + c->options |= MIPS_CPU_NAN_LEGACY; + } + + write_c0_status(sr); + } else { + c->options |= MIPS_CPU_NAN_LEGACY; + } +} + +/* + * IEEE 754 conformance mode to use. Affects the NaN encoding and the + * ABS.fmt/NEG.fmt execution mode. + */ +static enum { STRICT, LEGACY, STD2008, RELAXED } ieee754 = STRICT; + +/* + * Set the IEEE 754 NaN encodings and the ABS.fmt/NEG.fmt execution modes + * to support by the FPU emulator according to the IEEE 754 conformance + * mode selected. Note that "relaxed" straps the emulator so that it + * allows 2008-NaN binaries even for legacy processors. + */ +static void cpu_set_nofpu_2008(struct cpuinfo_mips *c) +{ + c->options &= ~(MIPS_CPU_NAN_2008 | MIPS_CPU_NAN_LEGACY); + c->fpu_csr31 &= ~(FPU_CSR_ABS2008 | FPU_CSR_NAN2008); + c->fpu_msk31 &= ~(FPU_CSR_ABS2008 | FPU_CSR_NAN2008); + + switch (ieee754) { + case STRICT: + if (c->isa_level & (MIPS_CPU_ISA_M32R1 | MIPS_CPU_ISA_M64R1 | + MIPS_CPU_ISA_M32R2 | MIPS_CPU_ISA_M64R2 | + MIPS_CPU_ISA_M32R5 | MIPS_CPU_ISA_M64R5 | + MIPS_CPU_ISA_M32R6 | MIPS_CPU_ISA_M64R6)) { + c->options |= MIPS_CPU_NAN_2008 | MIPS_CPU_NAN_LEGACY; + } else { + c->options |= MIPS_CPU_NAN_LEGACY; + c->fpu_msk31 |= FPU_CSR_ABS2008 | FPU_CSR_NAN2008; + } + break; + case LEGACY: + c->options |= MIPS_CPU_NAN_LEGACY; + c->fpu_msk31 |= FPU_CSR_ABS2008 | FPU_CSR_NAN2008; + break; + case STD2008: + c->options |= MIPS_CPU_NAN_2008; + c->fpu_csr31 |= FPU_CSR_ABS2008 | FPU_CSR_NAN2008; + c->fpu_msk31 |= FPU_CSR_ABS2008 | FPU_CSR_NAN2008; + break; + case RELAXED: + c->options |= MIPS_CPU_NAN_2008 | MIPS_CPU_NAN_LEGACY; + break; + } +} + +/* + * Override the IEEE 754 NaN encoding and ABS.fmt/NEG.fmt execution mode + * according to the "ieee754=" parameter. + */ +static void cpu_set_nan_2008(struct cpuinfo_mips *c) +{ + switch (ieee754) { + case STRICT: + mips_use_nan_legacy = !!cpu_has_nan_legacy; + mips_use_nan_2008 = !!cpu_has_nan_2008; + break; + case LEGACY: + mips_use_nan_legacy = !!cpu_has_nan_legacy; + mips_use_nan_2008 = !cpu_has_nan_legacy; + break; + case STD2008: + mips_use_nan_legacy = !cpu_has_nan_2008; + mips_use_nan_2008 = !!cpu_has_nan_2008; + break; + case RELAXED: + mips_use_nan_legacy = true; + mips_use_nan_2008 = true; + break; + } +} + +/* + * IEEE 754 NaN encoding and ABS.fmt/NEG.fmt execution mode override + * settings: + * + * strict: accept binaries that request a NaN encoding supported by the FPU + * legacy: only accept legacy-NaN binaries + * 2008: only accept 2008-NaN binaries + * relaxed: accept any binaries regardless of whether supported by the FPU + */ +static int __init ieee754_setup(char *s) +{ + if (!s) + return -1; + else if (!strcmp(s, "strict")) + ieee754 = STRICT; + else if (!strcmp(s, "legacy")) + ieee754 = LEGACY; + else if (!strcmp(s, "2008")) + ieee754 = STD2008; + else if (!strcmp(s, "relaxed")) + ieee754 = RELAXED; + else + return -1; + + if (!(boot_cpu_data.options & MIPS_CPU_FPU)) + cpu_set_nofpu_2008(&boot_cpu_data); + cpu_set_nan_2008(&boot_cpu_data); + + return 0; +} + +early_param("ieee754", ieee754_setup); + +/* + * Set the FIR feature flags for the FPU emulator. + */ +static void cpu_set_nofpu_id(struct cpuinfo_mips *c) +{ + u32 value; + + value = 0; + if (c->isa_level & (MIPS_CPU_ISA_M32R1 | MIPS_CPU_ISA_M64R1 | + MIPS_CPU_ISA_M32R2 | MIPS_CPU_ISA_M64R2 | + MIPS_CPU_ISA_M32R5 | MIPS_CPU_ISA_M64R5 | + MIPS_CPU_ISA_M32R6 | MIPS_CPU_ISA_M64R6)) + value |= MIPS_FPIR_D | MIPS_FPIR_S; + if (c->isa_level & (MIPS_CPU_ISA_M32R2 | MIPS_CPU_ISA_M64R2 | + MIPS_CPU_ISA_M32R5 | MIPS_CPU_ISA_M64R5 | + MIPS_CPU_ISA_M32R6 | MIPS_CPU_ISA_M64R6)) + value |= MIPS_FPIR_F64 | MIPS_FPIR_L | MIPS_FPIR_W; + if (c->options & MIPS_CPU_NAN_2008) + value |= MIPS_FPIR_HAS2008; + c->fpu_id = value; +} + +/* Determined FPU emulator mask to use for the boot CPU with "nofpu". */ +static unsigned int mips_nofpu_msk31; + +/* + * Set options for FPU hardware. + */ +void cpu_set_fpu_opts(struct cpuinfo_mips *c) +{ + c->fpu_id = cpu_get_fpu_id(); + mips_nofpu_msk31 = c->fpu_msk31; + + if (c->isa_level & (MIPS_CPU_ISA_M32R1 | MIPS_CPU_ISA_M64R1 | + MIPS_CPU_ISA_M32R2 | MIPS_CPU_ISA_M64R2 | + MIPS_CPU_ISA_M32R5 | MIPS_CPU_ISA_M64R5 | + MIPS_CPU_ISA_M32R6 | MIPS_CPU_ISA_M64R6)) { + if (c->fpu_id & MIPS_FPIR_3D) + c->ases |= MIPS_ASE_MIPS3D; + if (c->fpu_id & MIPS_FPIR_UFRP) + c->options |= MIPS_CPU_UFR; + if (c->fpu_id & MIPS_FPIR_FREP) + c->options |= MIPS_CPU_FRE; + } + + cpu_set_fpu_fcsr_mask(c); + cpu_set_fpu_2008(c); + cpu_set_nan_2008(c); +} + +/* + * Set options for the FPU emulator. + */ +void cpu_set_nofpu_opts(struct cpuinfo_mips *c) +{ + c->options &= ~MIPS_CPU_FPU; + c->fpu_msk31 = mips_nofpu_msk31; + + cpu_set_nofpu_2008(c); + cpu_set_nan_2008(c); + cpu_set_nofpu_id(c); +} + +int mips_fpu_disabled; + +static int __init fpu_disable(char *s) +{ + cpu_set_nofpu_opts(&boot_cpu_data); + mips_fpu_disabled = 1; + + return 1; +} + +__setup("nofpu", fpu_disable); + diff --git a/arch/mips/kernel/fpu-probe.h b/arch/mips/kernel/fpu-probe.h new file mode 100644 index 000000000000..951ce50890d0 --- /dev/null +++ b/arch/mips/kernel/fpu-probe.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#include + +#include +#include + +#ifdef CONFIG_MIPS_FP_SUPPORT + +extern int mips_fpu_disabled; + +int __cpu_has_fpu(void); +void cpu_set_fpu_opts(struct cpuinfo_mips *c); +void cpu_set_nofpu_opts(struct cpuinfo_mips *c); + +#else /* !CONFIG_MIPS_FP_SUPPORT */ + +#define mips_fpu_disabled 1 + +static inline unsigned long cpu_get_fpu_id(void) +{ + return FPIR_IMP_NONE; +} + +static inline int __cpu_has_fpu(void) +{ + return 0; +} + +static inline void cpu_set_fpu_opts(struct cpuinfo_mips *c) +{ + /* no-op */ +} + +static inline void cpu_set_nofpu_opts(struct cpuinfo_mips *c) +{ + /* no-op */ +} + +#endif /* CONFIG_MIPS_FP_SUPPORT */ From 90c68c6dbcb439b4d8ed9736463d80b98c95771f Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Thu, 8 Oct 2020 23:33:26 +0200 Subject: [PATCH 405/645] MIPS: cpu-probe: introduce exclusive R3k CPU probe Running a kernel on a R3k of machine definitly will never see one of the newer CPU cores. And since R3k system usually are low on memory we could save quite some kbytes: text data bss dec hex filename 15070 88 32 15190 3b56 arch/mips/kernel/cpu-probe.o 844 4 16 864 360 arch/mips/kernel/cpu-r3k-probe.o Signed-off-by: Thomas Bogendoerfer --- arch/mips/kernel/Makefile | 8 +- arch/mips/kernel/cpu-r3k-probe.c | 171 +++++++++++++++++++++++++++++++ 2 files changed, 178 insertions(+), 1 deletion(-) create mode 100644 arch/mips/kernel/cpu-r3k-probe.c diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile index 026801c21724..2a05b923f579 100644 --- a/arch/mips/kernel/Makefile +++ b/arch/mips/kernel/Makefile @@ -5,11 +5,17 @@ extra-y := head.o vmlinux.lds -obj-y += cmpxchg.o cpu-probe.o branch.o elf.o entry.o genex.o idle.o irq.o \ +obj-y += branch.o cmpxchg.o elf.o entry.o genex.o idle.o irq.o \ process.o prom.o ptrace.o reset.o setup.o signal.o \ syscall.o time.o topology.o traps.o unaligned.o watch.o \ vdso.o cacheinfo.o +ifdef CONFIG_CPU_R3K_TLB +obj-y += cpu-r3k-probe.o +else +obj-y += cpu-probe.o +endif + ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_ftrace.o = -pg CFLAGS_REMOVE_early_printk.o = -pg diff --git a/arch/mips/kernel/cpu-r3k-probe.c b/arch/mips/kernel/cpu-r3k-probe.c new file mode 100644 index 000000000000..abdbbe8c5a43 --- /dev/null +++ b/arch/mips/kernel/cpu-r3k-probe.c @@ -0,0 +1,171 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Processor capabilities determination functions. + * + * Copyright (C) xxxx the Anonymous + * Copyright (C) 1994 - 2006 Ralf Baechle + * Copyright (C) 2003, 2004 Maciej W. Rozycki + * Copyright (C) 2001, 2004, 2011, 2012 MIPS Technologies, Inc. + */ +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include + +#include "fpu-probe.h" + +/* Hardware capabilities */ +unsigned int elf_hwcap __read_mostly; +EXPORT_SYMBOL_GPL(elf_hwcap); + +void __init check_bugs32(void) +{ + +} + +/* + * Probe whether cpu has config register by trying to play with + * alternate cache bit and see whether it matters. + * It's used by cpu_probe to distinguish between R3000A and R3081. + */ +static inline int cpu_has_confreg(void) +{ +#ifdef CONFIG_CPU_R3000 + extern unsigned long r3k_cache_size(unsigned long); + unsigned long size1, size2; + unsigned long cfg = read_c0_conf(); + + size1 = r3k_cache_size(ST0_ISC); + write_c0_conf(cfg ^ R30XX_CONF_AC); + size2 = r3k_cache_size(ST0_ISC); + write_c0_conf(cfg); + return size1 != size2; +#else + return 0; +#endif +} + +static inline void set_elf_platform(int cpu, const char *plat) +{ + if (cpu == 0) + __elf_platform = plat; +} + +const char *__cpu_name[NR_CPUS]; +const char *__elf_platform; +const char *__elf_base_platform; + +void cpu_probe(void) +{ + struct cpuinfo_mips *c = ¤t_cpu_data; + unsigned int cpu = smp_processor_id(); + + /* + * Set a default elf platform, cpu probe may later + * overwrite it with a more precise value + */ + set_elf_platform(cpu, "mips"); + + c->processor_id = PRID_IMP_UNKNOWN; + c->fpu_id = FPIR_IMP_NONE; + c->cputype = CPU_UNKNOWN; + c->writecombine = _CACHE_UNCACHED; + + c->fpu_csr31 = FPU_CSR_RN; + c->fpu_msk31 = FPU_CSR_RSVD | FPU_CSR_ABS2008 | FPU_CSR_NAN2008 | + FPU_CSR_CONDX | FPU_CSR_FS; + + c->srsets = 1; + + c->processor_id = read_c0_prid(); + switch (c->processor_id & (PRID_COMP_MASK | PRID_IMP_MASK)) { + case PRID_COMP_LEGACY | PRID_IMP_R2000: + c->cputype = CPU_R2000; + __cpu_name[cpu] = "R2000"; + c->options = MIPS_CPU_TLB | MIPS_CPU_3K_CACHE | + MIPS_CPU_NOFPUEX; + if (__cpu_has_fpu()) + c->options |= MIPS_CPU_FPU; + c->tlbsize = 64; + break; + case PRID_COMP_LEGACY | PRID_IMP_R3000: + if ((c->processor_id & PRID_REV_MASK) == PRID_REV_R3000A) { + if (cpu_has_confreg()) { + c->cputype = CPU_R3081E; + __cpu_name[cpu] = "R3081"; + } else { + c->cputype = CPU_R3000A; + __cpu_name[cpu] = "R3000A"; + } + } else { + c->cputype = CPU_R3000; + __cpu_name[cpu] = "R3000"; + } + c->options = MIPS_CPU_TLB | MIPS_CPU_3K_CACHE | + MIPS_CPU_NOFPUEX; + if (__cpu_has_fpu()) + c->options |= MIPS_CPU_FPU; + c->tlbsize = 64; + break; + case PRID_COMP_LEGACY | PRID_IMP_TX39: + c->options = MIPS_CPU_TLB | MIPS_CPU_TX39_CACHE; + + if ((c->processor_id & 0xf0) == (PRID_REV_TX3927 & 0xf0)) { + c->cputype = CPU_TX3927; + __cpu_name[cpu] = "TX3927"; + c->tlbsize = 64; + } else { + switch (c->processor_id & PRID_REV_MASK) { + case PRID_REV_TX3912: + c->cputype = CPU_TX3912; + __cpu_name[cpu] = "TX3912"; + c->tlbsize = 32; + break; + case PRID_REV_TX3922: + c->cputype = CPU_TX3922; + __cpu_name[cpu] = "TX3922"; + c->tlbsize = 64; + break; + } + } + break; + } + + BUG_ON(!__cpu_name[cpu]); + BUG_ON(c->cputype == CPU_UNKNOWN); + + /* + * Platform code can force the cpu type to optimize code + * generation. In that case be sure the cpu type is correctly + * manually setup otherwise it could trigger some nasty bugs. + */ + BUG_ON(current_cpu_type() != c->cputype); + + if (mips_fpu_disabled) + c->options &= ~MIPS_CPU_FPU; + + if (c->options & MIPS_CPU_FPU) + cpu_set_fpu_opts(c); + else + cpu_set_nofpu_opts(c); +} + +void cpu_report(void) +{ + struct cpuinfo_mips *c = ¤t_cpu_data; + + pr_info("CPU%d revision is: %08x (%s)\n", + smp_processor_id(), c->processor_id, cpu_name_string()); + if (c->options & MIPS_CPU_FPU) + pr_info("FPU revision is: %08x\n", c->fpu_id); +} From 20cc5b649d9978494fb29259763c2505f6acc3c0 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Fri, 9 Oct 2020 14:26:48 +0200 Subject: [PATCH 406/645] MIPS: cpu-probe: remove MIPS_CPU_BP_GHIST option bit MIPS_CPU_BP_GHIST is only set two times and more or less immediately used in cpu-probe.c itself. Remove this option to make room in options word. Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/cpu-features.h | 3 --- arch/mips/include/asm/cpu.h | 1 - .../include/asm/mach-au1x00/cpu-feature-overrides.h | 1 - arch/mips/kernel/cpu-probe.c | 10 ++++------ 4 files changed, 4 insertions(+), 11 deletions(-) diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h index 78cf7e300f12..f2e216eef7da 100644 --- a/arch/mips/include/asm/cpu-features.h +++ b/arch/mips/include/asm/cpu-features.h @@ -171,9 +171,6 @@ #ifndef cpu_has_llsc #define cpu_has_llsc __isa_ge_or_opt(1, MIPS_CPU_LLSC) #endif -#ifndef cpu_has_bp_ghist -#define cpu_has_bp_ghist __opt(MIPS_CPU_BP_GHIST) -#endif #ifndef kernel_uses_llsc #define kernel_uses_llsc cpu_has_llsc #endif diff --git a/arch/mips/include/asm/cpu.h b/arch/mips/include/asm/cpu.h index 388a82f28a87..c9222cc2244f 100644 --- a/arch/mips/include/asm/cpu.h +++ b/arch/mips/include/asm/cpu.h @@ -398,7 +398,6 @@ enum cpu_type_enum { #define MIPS_CPU_RW_LLB BIT_ULL(32) /* LLADDR/LLB writes are allowed */ #define MIPS_CPU_LPA BIT_ULL(33) /* CPU supports Large Physical Addressing */ #define MIPS_CPU_CDMM BIT_ULL(34) /* CPU has Common Device Memory Map */ -#define MIPS_CPU_BP_GHIST BIT_ULL(35) /* R12K+ Branch Prediction Global History */ #define MIPS_CPU_SP BIT_ULL(36) /* Small (1KB) page support */ #define MIPS_CPU_FTLB BIT_ULL(37) /* CPU has Fixed-page-size TLB */ #define MIPS_CPU_NAN_LEGACY BIT_ULL(38) /* Legacy NaN implemented */ diff --git a/arch/mips/include/asm/mach-au1x00/cpu-feature-overrides.h b/arch/mips/include/asm/mach-au1x00/cpu-feature-overrides.h index ecfbb5aeada3..e6e527224a15 100644 --- a/arch/mips/include/asm/mach-au1x00/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-au1x00/cpu-feature-overrides.h @@ -39,7 +39,6 @@ #define cpu_has_guestctl2 0 #define cpu_has_guestid 0 #define cpu_has_drg 0 -#define cpu_has_bp_ghist 0 #define cpu_has_mips16 0 #define cpu_has_mips16e2 0 #define cpu_has_mdmx 0 diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index b8e073772bdb..e6853697a056 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -1278,8 +1278,9 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu) c->options = MIPS_CPU_TLB | MIPS_CPU_4K_CACHE | MIPS_CPU_4KEX | MIPS_CPU_FPU | MIPS_CPU_32FPR | MIPS_CPU_COUNTER | MIPS_CPU_WATCH | - MIPS_CPU_LLSC | MIPS_CPU_BP_GHIST; + MIPS_CPU_LLSC; c->tlbsize = 64; + write_c0_r10k_diag(read_c0_r10k_diag() | R10K_DIAG_E_GHIST); break; case PRID_IMP_R14000: if (((c->processor_id >> 4) & 0x0f) > 2) { @@ -1293,8 +1294,9 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu) c->options = MIPS_CPU_TLB | MIPS_CPU_4K_CACHE | MIPS_CPU_4KEX | MIPS_CPU_FPU | MIPS_CPU_32FPR | MIPS_CPU_COUNTER | MIPS_CPU_WATCH | - MIPS_CPU_LLSC | MIPS_CPU_BP_GHIST; + MIPS_CPU_LLSC; c->tlbsize = 64; + write_c0_r10k_diag(read_c0_r10k_diag() | R10K_DIAG_E_GHIST); break; case PRID_IMP_LOONGSON_64C: /* Loongson-2/3 */ switch (c->processor_id & PRID_REV_MASK) { @@ -2054,10 +2056,6 @@ void cpu_probe(void) else cpu_set_nofpu_opts(c); - if (cpu_has_bp_ghist) - write_c0_r10k_diag(read_c0_r10k_diag() | - R10K_DIAG_E_GHIST); - if (cpu_has_mips_r2_r6) { c->srsets = ((read_c0_srsctl() >> 26) & 0x0f) + 1; /* R2 has Performance Counter Interrupt indicator */ From 69b686ddd579bdaec2bfe448672e50626920d0bb Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Mon, 12 Oct 2020 21:27:39 +0200 Subject: [PATCH 407/645] MIPS: ingenic: Remove CPU_SUPPORTS_HUGEPAGES While it is true that Ingenic SoCs support huge pages, we cannot use them yet as PTEs don't have any single bit that is free. Right now, having that symbol only causes build errors, so remove it until the situation with PTEs is resolved. Fixes: f0f4a753079c ("MIPS: generic: Add support for Ingenic SoCs") Signed-off-by: Paul Cercueil Reviewed-by: Guenter Roeck Tested-by: Guenter Roeck Signed-off-by: Thomas Bogendoerfer --- arch/mips/Kconfig | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 75f26d1f11ab..99091b059c0b 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -101,7 +101,6 @@ config MACH_INGENIC select SYS_SUPPORTS_32BIT_KERNEL select SYS_SUPPORTS_LITTLE_ENDIAN select SYS_SUPPORTS_ZBOOT - select CPU_SUPPORTS_HUGEPAGES select DMA_NONCOHERENT select IRQ_MIPS_CPU select PINCTRL From 1f0400d0e2c410b04f246aefb2e9b5155eb4b0bf Mon Sep 17 00:00:00 2001 From: Chuanhong Guo Date: Tue, 13 Oct 2020 10:05:47 +0800 Subject: [PATCH 408/645] mips: ralink: enable zboot support Some of these ralink devices come with an ancient u-boot which can't extract LZMA properly when image gets too big. Enable zboot support to get a self-extracting kernel instead of relying on broken u-boot support. Signed-off-by: Chuanhong Guo Signed-off-by: Thomas Bogendoerfer --- arch/mips/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 99091b059c0b..6e75f02ca6fb 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -616,6 +616,7 @@ config RALINK select SYS_SUPPORTS_32BIT_KERNEL select SYS_SUPPORTS_LITTLE_ENDIAN select SYS_SUPPORTS_MIPS16 + select SYS_SUPPORTS_ZBOOT select SYS_HAS_EARLY_PRINTK select CLKDEV_LOOKUP select ARCH_HAS_RESET_CONTROLLER From 3528f8ec95a5b1ee1b98d3e85371843c6428e4be Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 15 Jul 2020 18:28:58 -0700 Subject: [PATCH 409/645] bcm963xx_tag.h: fix duplicated word Change doubled word "is" to "it is". Signed-off-by: Randy Dunlap Cc: Florian Fainelli Cc: bcm-kernel-feedback-list@broadcom.com Cc: linux-mips@vger.kernel.org Acked-by: Florian Fainelli Signed-off-by: Thomas Bogendoerfer --- include/linux/bcm963xx_tag.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/bcm963xx_tag.h b/include/linux/bcm963xx_tag.h index b87945cb6946..7edb809a2586 100644 --- a/include/linux/bcm963xx_tag.h +++ b/include/linux/bcm963xx_tag.h @@ -84,7 +84,7 @@ struct bcm_tag { char flash_layout_ver[FLASHLAYOUTVER_LEN]; /* 196-199: kernel+rootfs CRC32 */ __u32 fskernel_crc; - /* 200-215: Unused except on Alice Gate where is is information */ + /* 200-215: Unused except on Alice Gate where it is information */ char information2[TAGINFO2_LEN]; /* 216-219: CRC32 of image less imagetag (kernel for Alice Gate) */ __u32 image_crc; From 996f9e0f93f16211945c8d5f18f296a88cb32f91 Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Wed, 14 Oct 2020 13:47:11 +1100 Subject: [PATCH 410/645] selftests/powerpc: Fix eeh-basic.sh exit codes The kselftests test running infrastructure expects tests to finish with an exit code of 4 if the test decided it should be skipped. Currently eeh-basic.sh exits with the number of devices that failed to recover, so if four devices didn't recover we'll report a skip instead of a fail. Fix this by checking if the return code is non-zero and report success and failure by returning 0 or 1 respectively. For the cases where should actually skip return 4. Fixes: 85d86c8aa52e ("selftests/powerpc: Add basic EEH selftest") Signed-off-by: Oliver O'Halloran Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20201014024711.1138386-1-oohall@gmail.com --- tools/testing/selftests/powerpc/eeh/eeh-basic.sh | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/powerpc/eeh/eeh-basic.sh b/tools/testing/selftests/powerpc/eeh/eeh-basic.sh index 8a8d0f456946..0d783e1065c8 100755 --- a/tools/testing/selftests/powerpc/eeh/eeh-basic.sh +++ b/tools/testing/selftests/powerpc/eeh/eeh-basic.sh @@ -1,17 +1,19 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0-only +KSELFTESTS_SKIP=4 + . ./eeh-functions.sh if ! eeh_supported ; then echo "EEH not supported on this system, skipping" - exit 0; + exit $KSELFTESTS_SKIP; fi if [ ! -e "/sys/kernel/debug/powerpc/eeh_dev_check" ] && \ [ ! -e "/sys/kernel/debug/powerpc/eeh_dev_break" ] ; then echo "debugfs EEH testing files are missing. Is debugfs mounted?" - exit 1; + exit $KSELFTESTS_SKIP; fi pre_lspci=`mktemp` @@ -84,4 +86,5 @@ echo "$failed devices failed to recover ($dev_count tested)" lspci | diff -u $pre_lspci - rm -f $pre_lspci -exit $failed +test "$failed" == 0 +exit $? From 3e4614e7fddec8a8bafd387ca93bd368e64cae9a Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Tue, 6 Oct 2020 16:00:03 +0200 Subject: [PATCH 411/645] MIPS: dec: fix section mismatch Drop inline for memory setup functions and mark them __init to fix section mismatch of pmax_setup_memory_region. Signed-off-by: Thomas Bogendoerfer Acked-by: Maciej W. Rozycki --- arch/mips/dec/prom/memory.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/mips/dec/prom/memory.c b/arch/mips/dec/prom/memory.c index 288772c3eb0c..44490c30d63b 100644 --- a/arch/mips/dec/prom/memory.c +++ b/arch/mips/dec/prom/memory.c @@ -27,7 +27,7 @@ volatile unsigned long mem_err; /* So we know an error occurred */ #define CHUNK_SIZE 0x400000 -static inline void pmax_setup_memory_region(void) +static __init void pmax_setup_memory_region(void) { volatile unsigned char *memory_page, dummy; char old_handler[0x80]; @@ -56,7 +56,7 @@ static inline void pmax_setup_memory_region(void) * Use the REX prom calls to get hold of the memory bitmap, and thence * determine memory size. */ -static inline void rex_setup_memory_region(void) +static __init void rex_setup_memory_region(void) { int i, bitmap_size; unsigned long mem_start = 0, mem_size = 0; From cf3af0a4d3b62ab48e0b90180ea161d0f5d4953f Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Wed, 14 Oct 2020 22:34:56 +0100 Subject: [PATCH 412/645] MIPS: DEC: Restore bootmem reservation for firmware working memory area Fix a crash on DEC platforms starting with: VFS: Mounted root (nfs filesystem) on device 0:11. Freeing unused PROM memory: 124k freed BUG: Bad page state in process swapper pfn:00001 page:(ptrval) refcount:0 mapcount:-128 mapping:00000000 index:0x1 pfn:0x1 flags: 0x0() raw: 00000000 00000100 00000122 00000000 00000001 00000000 ffffff7f 00000000 page dumped because: nonzero mapcount Modules linked in: CPU: 0 PID: 1 Comm: swapper Not tainted 5.9.0-00858-g865c50e1d279 #1 Stack : 8065dc48 0000000b 8065d2b8 9bc27dcc 80645bfc 9bc259a4 806a1b97 80703124 80710000 8064a900 00000001 80099574 806b116c 1000ec00 9bc27d88 806a6f30 00000000 00000000 80645bfc 00000000 31232039 80706ba4 2e392e35 8039f348 2d383538 00000070 0000000a 35363867 00000000 806c2830 80710000 806b0000 80710000 8064a900 00000001 81000000 00000000 00000000 8035af2c 80700000 ... Call Trace: [<8004bc5c>] show_stack+0x34/0x104 [<8015675c>] bad_page+0xfc/0x128 [<80157714>] free_pcppages_bulk+0x1f4/0x5dc [<801591cc>] free_unref_page+0xc0/0x130 [<8015cb04>] free_reserved_area+0x144/0x1d8 [<805abd78>] kernel_init+0x20/0x100 [<80046070>] ret_from_kernel_thread+0x14/0x1c Disabling lock debugging due to kernel taint caused by an attempt to free bootmem space that as from commit b93ddc4f9156 ("mips: Reserve memory for the kernel image resources") has not been anymore reserved due to the removal of generic MIPS arch code that used to reserve all the memory from the beginning of RAM up to the kernel load address. This memory does need to be reserved on DEC platforms however as it is used by REX firmware as working area, as per the TURBOchannel firmware specification[1]: Table 2-2 REX Memory Regions ------------------------------------------------------------------------- Starting Ending Region Address Address Use ------------------------------------------------------------------------- 0 0xa0000000 0xa000ffff Restart block, exception vectors, REX stack and bss 1 0xa0010000 0xa0017fff Keyboard or tty drivers 2 0xa0018000 0xa001f3ff 1) CRT driver 3 0xa0020000 0xa002ffff boot, cnfg, init and t objects 4 0xa0020000 0xa002ffff 64KB scratch space ------------------------------------------------------------------------- 1) Note that the last 3 Kbytes of region 2 are reserved for backward compatibility with previous system software. ------------------------------------------------------------------------- (this table uses KSEG2 unmapped virtual addresses, which in the MIPS architecture are offset from physical addresses by a fixed value of 0xa0000000 and therefore the regions referred do correspond to the beginning of the physical address space) and we call into the firmware on several occasions throughout the bootstrap process. It is believed that pre-REX firmware used with non-TURBOchannel DEC platforms has the same requirements, as hinted by note #1 cited. Recreate the discarded reservation then, in DEC platform code, removing the crash. References: [1] "TURBOchannel Firmware Specification", On-line version, EK-TCAAD-FS-004, Digital Equipment Corporation, January 1993, Chapter 2 "System Module Firmware", p. 2-5 Signed-off-by: Maciej W. Rozycki Fixes: b93ddc4f9156 ("mips: Reserve memory for the kernel image resources") Cc: stable@vger.kernel.org # v5.2+ Signed-off-by: Thomas Bogendoerfer --- arch/mips/dec/setup.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/arch/mips/dec/setup.c b/arch/mips/dec/setup.c index d4e868b828e5..eaad0ed4b523 100644 --- a/arch/mips/dec/setup.c +++ b/arch/mips/dec/setup.c @@ -6,7 +6,7 @@ * for more details. * * Copyright (C) 1998 Harald Koerfgen - * Copyright (C) 2000, 2001, 2002, 2003, 2005 Maciej W. Rozycki + * Copyright (C) 2000, 2001, 2002, 2003, 2005, 2020 Maciej W. Rozycki */ #include #include @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -22,6 +23,7 @@ #include #include +#include #include #include #include @@ -29,7 +31,9 @@ #include #include #include +#include #include +#include #include #include #include @@ -146,6 +150,9 @@ void __init plat_mem_setup(void) ioport_resource.start = ~0UL; ioport_resource.end = 0UL; + + /* Stay away from the firmware working memory area for now. */ + memblock_reserve(PHYS_OFFSET, __pa_symbol(&_text) - PHYS_OFFSET); } /* From ffd0b25ca049a477cb757e5bcf2d5e1664d12e5d Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Wed, 14 Oct 2020 14:28:11 -0400 Subject: [PATCH 413/645] Revert "powerpc/pci: unmap legacy INTx interrupts when a PHB is removed" This reverts commit 3a3181e16fbde752007759f8759d25e0ff1fc425 which causes memory corruptions on POWER9 powernv. eg: pci_bus 0035:08: busn_res: [bus 08-0c] is released ============================================================================= BUG kmalloc-16 (Tainted: G W O ): Object already free ----------------------------------------------------------------------------- Disabling lock debugging due to kernel taint INFO: Allocated in pcibios_scan_phb+0x104/0x3e0 age=1960714 cpu=4 pid=1 __slab_alloc+0xa4/0xf0 __kmalloc+0x294/0x330 pcibios_scan_phb+0x104/0x3e0 pcibios_init+0x84/0x124 do_one_initcall+0xac/0x528 kernel_init_freeable+0x35c/0x3fc kernel_init+0x24/0x148 ret_from_kernel_thread+0x5c/0x80 INFO: Freed in pcibios_remove_bus+0x70/0x90 age=0 cpu=16 pid=1717146 kfree+0x49c/0x510 pcibios_remove_bus+0x70/0x90 pci_remove_bus+0xe4/0x110 pci_remove_bus_device+0x74/0x170 pci_remove_bus_device+0x4c/0x170 pci_stop_and_remove_bus_device_locked+0x34/0x50 remove_store+0xc0/0xe0 dev_attr_store+0x30/0x50 sysfs_kf_write+0x68/0xb0 kernfs_fop_write+0x114/0x260 vfs_write+0xe4/0x260 ksys_write+0x74/0x130 system_call_exception+0xf8/0x1d0 system_call_common+0xe8/0x218 INFO: Slab 0x0000000099caaf22 objects=178 used=174 fp=0x00000000006a64b0 flags=0x7fff8000000201 INFO: Object 0x00000000f360132d @offset=30192 fp=0x0000000000000000 Signed-off-by: Qian Cai Acked-by: Oliver O'Halloran Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20201014182811.12027-1-cai@lca.pw --- arch/powerpc/include/asm/pci-bridge.h | 6 -- arch/powerpc/kernel/pci-common.c | 114 -------------------------- 2 files changed, 120 deletions(-) diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index d21e070352dc..d2a2a14e56f9 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -48,9 +48,6 @@ struct pci_controller_ops { /* * Structure of a PCI controller (host bridge) - * - * @irq_count: number of interrupt mappings - * @irq_map: interrupt mappings */ struct pci_controller { struct pci_bus *bus; @@ -130,9 +127,6 @@ struct pci_controller { void *private_data; struct npu *npu; - - unsigned int irq_count; - unsigned int *irq_map; }; /* These are used for config access before all the PCI probing diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index deb831f0ae13..be108616a721 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -353,115 +353,6 @@ struct pci_controller *pci_find_controller_for_domain(int domain_nr) return NULL; } -/* - * Assumption is made on the interrupt parent. All interrupt-map - * entries are considered to have the same parent. - */ -static int pcibios_irq_map_count(struct pci_controller *phb) -{ - const __be32 *imap; - int imaplen; - struct device_node *parent; - u32 intsize, addrsize, parintsize, paraddrsize; - - if (of_property_read_u32(phb->dn, "#interrupt-cells", &intsize)) - return 0; - if (of_property_read_u32(phb->dn, "#address-cells", &addrsize)) - return 0; - - imap = of_get_property(phb->dn, "interrupt-map", &imaplen); - if (!imap) { - pr_debug("%pOF : no interrupt-map\n", phb->dn); - return 0; - } - imaplen /= sizeof(u32); - pr_debug("%pOF : imaplen=%d\n", phb->dn, imaplen); - - if (imaplen < (addrsize + intsize + 1)) - return 0; - - imap += intsize + addrsize; - parent = of_find_node_by_phandle(be32_to_cpup(imap)); - if (!parent) { - pr_debug("%pOF : no imap parent found !\n", phb->dn); - return 0; - } - - if (of_property_read_u32(parent, "#interrupt-cells", &parintsize)) { - pr_debug("%pOF : parent lacks #interrupt-cells!\n", phb->dn); - return 0; - } - - if (of_property_read_u32(parent, "#address-cells", ¶ddrsize)) - paraddrsize = 0; - - return imaplen / (addrsize + intsize + 1 + paraddrsize + parintsize); -} - -static void pcibios_irq_map_init(struct pci_controller *phb) -{ - phb->irq_count = pcibios_irq_map_count(phb); - if (phb->irq_count < PCI_NUM_INTX) - phb->irq_count = PCI_NUM_INTX; - - pr_debug("%pOF : interrupt map #%d\n", phb->dn, phb->irq_count); - - phb->irq_map = kcalloc(phb->irq_count, sizeof(unsigned int), - GFP_KERNEL); -} - -static void pci_irq_map_register(struct pci_dev *pdev, unsigned int virq) -{ - struct pci_controller *phb = pci_bus_to_host(pdev->bus); - int i; - - if (!phb->irq_map) - return; - - for (i = 0; i < phb->irq_count; i++) { - /* - * Look for an empty or an equivalent slot, as INTx - * interrupts can be shared between adapters. - */ - if (phb->irq_map[i] == virq || !phb->irq_map[i]) { - phb->irq_map[i] = virq; - break; - } - } - - if (i == phb->irq_count) - pr_err("PCI:%s all platform interrupts mapped\n", - pci_name(pdev)); -} - -/* - * Clearing the mapped interrupts will also clear the underlying - * mappings of the ESB pages of the interrupts when under XIVE. It is - * a requirement of PowerVM to clear all memory mappings before - * removing a PHB. - */ -static void pci_irq_map_dispose(struct pci_bus *bus) -{ - struct pci_controller *phb = pci_bus_to_host(bus); - int i; - - if (!phb->irq_map) - return; - - pr_debug("PCI: Clearing interrupt mappings for PHB %04x:%02x...\n", - pci_domain_nr(bus), bus->number); - for (i = 0; i < phb->irq_count; i++) - irq_dispose_mapping(phb->irq_map[i]); - - kfree(phb->irq_map); -} - -void pcibios_remove_bus(struct pci_bus *bus) -{ - pci_irq_map_dispose(bus); -} -EXPORT_SYMBOL_GPL(pcibios_remove_bus); - /* * Reads the interrupt pin to determine if interrupt is use by card. * If the interrupt is used, then gets the interrupt line from the @@ -510,8 +401,6 @@ static int pci_read_irq_line(struct pci_dev *pci_dev) pci_dev->irq = virq; - /* Record all interrut mappings for later removal of a PHB */ - pci_irq_map_register(pci_dev, virq); return 0; } @@ -1665,9 +1554,6 @@ void pcibios_scan_phb(struct pci_controller *hose) pr_debug("PCI: Scanning PHB %pOF\n", node); - /* Allocate interrupt mappings array */ - pcibios_irq_map_init(hose); - /* Get some IO space for the new PHB */ pcibios_setup_phb_io_space(hose); From d38c8cfb057183f619dc8534030bb64b63f78043 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 1 Oct 2020 08:23:52 +0200 Subject: [PATCH 414/645] scripts: kernel-doc: add support for typedef enum The PHY kernel-doc markup has gained support for documenting a typedef enum. However, right now the parser was not prepared for it. So, add support for parsing it. Fixes: 4069a572d423 ("net: phy: Document core PHY structures") Signed-off-by: Mauro Carvalho Chehab --- scripts/kernel-doc | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/scripts/kernel-doc b/scripts/kernel-doc index 724528f4b7d6..adc05406c68e 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -1265,14 +1265,22 @@ sub show_warnings($$) { sub dump_enum($$) { my $x = shift; my $file = shift; + my $members; + $x =~ s@/\*.*?\*/@@gos; # strip comments. # strip #define macros inside enums $x =~ s@#\s*((define|ifdef)\s+|endif)[^;]*;@@gos; - if ($x =~ /enum\s+(\w*)\s*\{(.*)\}/) { + if ($x =~ /typedef\s+enum\s*\{(.*)\}\s*(\w*)\s*;/) { + $declaration_name = $2; + $members = $1; + } elsif ($x =~ /enum\s+(\w*)\s*\{(.*)\}/) { $declaration_name = $1; - my $members = $2; + $members = $2; + } + + if ($declaration_name) { my %_members; $members =~ s/\s+$//; @@ -1307,8 +1315,7 @@ sub dump_enum($$) { 'sections' => \%sections, 'purpose' => $declaration_purpose }); - } - else { + } else { print STDERR "${file}:$.: error: Cannot parse enum!\n"; ++$errors; } From efa44475b8f5c692be4c5822a659e1a96f16dacb Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 24 Sep 2020 15:30:37 +0200 Subject: [PATCH 415/645] scripts: kernel-doc: make it more compatible with Sphinx 3.x With Sphinx 3.x, the ".. c:type:" tag was changed to accept either: .. c:type:: typedef-like declaration .. c:type:: name Using it for other types (including functions) don't work anymore. So, there are newer tags for macro, enum, struct, union, and others, which doesn't exist on older versions. Add a check for the Sphinx version and change the produced tags accordingly. Signed-off-by: Mauro Carvalho Chehab --- scripts/kernel-doc | 71 ++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 65 insertions(+), 6 deletions(-) diff --git a/scripts/kernel-doc b/scripts/kernel-doc index adc05406c68e..096317ef2e97 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -271,6 +271,8 @@ if ($#ARGV == -1) { } my $kernelversion; +my $sphinx_major; + my $dohighlight = ""; my $verbose = 0; @@ -465,6 +467,43 @@ while ($ARGV[0] =~ m/^--?(.*)/) { # continue execution near EOF; +# The C domain dialect changed on Sphinx 3. So, we need to check the +# version in order to produce the right tags. +sub findprog($) +{ + foreach(split(/:/, $ENV{PATH})) { + return "$_/$_[0]" if(-x "$_/$_[0]"); + } +} + +sub get_sphinx_version() +{ + my $ver; + my $major = 1; + + my $cmd = "sphinx-build"; + if (!findprog($cmd)) { + my $cmd = "sphinx-build3"; + return $major if (!findprog($cmd)); + } + + open IN, "$cmd --version 2>&1 |"; + while () { + if (m/^\s*sphinx-build\s+([\d]+)\.([\d\.]+)(\+\/[\da-f]+)?$/) { + $major=$1; + last; + } + # Sphinx 1.2.x uses a different format + if (m/^\s*Sphinx.*\s+([\d]+)\.([\d\.]+)$/) { + $major=$1; + last; + } + } + close IN; + + return $major; +} + # get kernel version from env sub get_kernel_version() { my $version = 'unknown kernel version'; @@ -848,7 +887,11 @@ sub output_function_rst(%) { my $start = ""; if ($args{'typedef'}) { - print ".. c:type:: ". $args{'function'} . "\n\n"; + if ($sphinx_major < 3) { + print ".. c:type:: ". $args{'function'} . "\n\n"; + } else { + print ".. c:function:: ". $args{'function'} . "\n\n"; + } print_lineno($declaration_start_line); print " **Typedef**: "; $lineprefix = ""; @@ -938,9 +981,14 @@ sub output_enum_rst(%) { my ($parameter); my $oldprefix = $lineprefix; my $count; - my $name = "enum " . $args{'enum'}; - print "\n\n.. c:type:: " . $name . "\n\n"; + if ($sphinx_major < 3) { + my $name = "enum " . $args{'enum'}; + print "\n\n.. c:type:: " . $name . "\n\n"; + } else { + my $name = $args{'enum'}; + print "\n\n.. c:enum:: " . $name . "\n\n"; + } print_lineno($declaration_start_line); $lineprefix = " "; output_highlight_rst($args{'purpose'}); @@ -966,8 +1014,13 @@ sub output_typedef_rst(%) { my %args = %{$_[0]}; my ($parameter); my $oldprefix = $lineprefix; - my $name = "typedef " . $args{'typedef'}; + my $name; + if ($sphinx_major < 3) { + $name = "typedef " . $args{'typedef'}; + } else { + $name = $args{'typedef'}; + } print "\n\n.. c:type:: " . $name . "\n\n"; print_lineno($declaration_start_line); $lineprefix = " "; @@ -982,9 +1035,14 @@ sub output_struct_rst(%) { my %args = %{$_[0]}; my ($parameter); my $oldprefix = $lineprefix; - my $name = $args{'type'} . " " . $args{'struct'}; - print "\n\n.. c:type:: " . $name . "\n\n"; + if ($sphinx_major < 3) { + my $name = $args{'type'} . " " . $args{'struct'}; + print "\n\n.. c:type:: " . $name . "\n\n"; + } else { + my $name = $args{'struct'}; + print "\n\n.. c:struct:: " . $name . "\n\n"; + } print_lineno($declaration_start_line); $lineprefix = " "; output_highlight_rst($args{'purpose'}); @@ -2242,6 +2300,7 @@ sub process_file($) { } +$sphinx_major = get_sphinx_version(); $kernelversion = get_kernel_version(); # generate a sequence of code that will splice in highlighting information From e3ad05fe6e6ff645aa91e9a555231ff53470daba Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 25 Sep 2020 10:05:40 +0200 Subject: [PATCH 416/645] scripts: kernel-doc: use a less pedantic markup for funcs on Sphinx 3.x Unfortunately, Sphinx 3.x parser for c functions is too pedantic: https://github.com/sphinx-doc/sphinx/issues/8241 While it could be relaxed with some configurations, there are several corner cases that it would make it hard to maintain, and will require teaching conf.py about several macros. So, let's instead use the :c:macro notation. This will produce an output that it is not as nice as currently, but it should still be acceptable, and will provide cross-references, removing thousands of warnings when building with newer versions of Sphinx. Signed-off-by: Mauro Carvalho Chehab --- scripts/kernel-doc | 34 ++++++++++++++++++++++++---------- 1 file changed, 24 insertions(+), 10 deletions(-) diff --git a/scripts/kernel-doc b/scripts/kernel-doc index 096317ef2e97..d9783c98f33b 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -886,19 +886,29 @@ sub output_function_rst(%) { my $oldprefix = $lineprefix; my $start = ""; - if ($args{'typedef'}) { - if ($sphinx_major < 3) { + if ($sphinx_major < 3) { + if ($args{'typedef'}) { print ".. c:type:: ". $args{'function'} . "\n\n"; + print_lineno($declaration_start_line); + print " **Typedef**: "; + $lineprefix = ""; + output_highlight_rst($args{'purpose'}); + $start = "\n\n**Syntax**\n\n ``"; } else { - print ".. c:function:: ". $args{'function'} . "\n\n"; + print ".. c:function:: "; } - print_lineno($declaration_start_line); - print " **Typedef**: "; - $lineprefix = ""; - output_highlight_rst($args{'purpose'}); - $start = "\n\n**Syntax**\n\n ``"; } else { - print ".. c:function:: "; + print ".. c:macro:: ". $args{'function'} . "\n\n"; + + if ($args{'typedef'}) { + print_lineno($declaration_start_line); + print " **Typedef**: "; + $lineprefix = ""; + output_highlight_rst($args{'purpose'}); + $start = "\n\n**Syntax**\n\n ``"; + } else { + print "``"; + } } if ($args{'functiontype'} ne "") { $start .= $args{'functiontype'} . " " . $args{'function'} . " ("; @@ -925,7 +935,11 @@ sub output_function_rst(%) { if ($args{'typedef'}) { print ");``\n\n"; } else { - print ")\n\n"; + if ($sphinx_major < 3) { + print ")\n\n"; + } else { + print ")``\n"; + } print_lineno($declaration_start_line); $lineprefix = " "; output_highlight_rst($args{'purpose'}); From dbe8ba00e5adc7573b8a91855f28a383c9728991 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 Sep 2020 12:52:34 +0200 Subject: [PATCH 417/645] scripts: kernel-doc: fix troubles with line counts There's currently a bug with the way kernel-doc script counts line numbers that can be seen with: $ ./scripts/kernel-doc -rst -enable-lineno include/linux/math64.h >all && ./scripts/kernel-doc -rst -internal -enable-lineno include/linux/math64.h >int && diff -U0 int all --- int 2020-09-28 12:58:08.927486808 +0200 +++ all 2020-09-28 12:58:08.905486845 +0200 @@ -1 +1 @@ -#define LINENO 27 +#define LINENO 26 @@ -3 +3 @@ -#define LINENO 16 +#define LINENO 15 @@ -9 +9 @@ -#define LINENO 17 +#define LINENO 16 ... This is happening with perl version 5.30.3, but I'm not so sure if this is a perl bug, or if this is due to something else. In any case, fixing it is easy. Basically, when "-internal" parameter is used, the process_export_file() function opens the handle "IN". This makes the line number to be incremented, as the handler for the main open is also "IN". Fix the problem by using a different handler for the main open(). While here, add a missing close for it. Signed-off-by: Mauro Carvalho Chehab --- scripts/kernel-doc | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/scripts/kernel-doc b/scripts/kernel-doc index d9783c98f33b..bdd2ebb4ac41 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -2268,7 +2268,7 @@ sub process_file($) { $file = map_filename($orig_file); - if (!open(IN,"<$file")) { + if (!open(IN_FILE,"<$file")) { print STDERR "Error: Cannot open file $file\n"; ++$errors; return; @@ -2277,9 +2277,9 @@ sub process_file($) { $. = 1; $section_counter = 0; - while () { + while () { while (s/\\\s*$//) { - $_ .= ; + $_ .= ; } # Replace tabs by spaces while ($_ =~ s/\t+/' ' x (length($&) * 8 - length($`) % 8)/e) {}; @@ -2311,6 +2311,7 @@ sub process_file($) { print STDERR "${file}:1: warning: no structured comments found\n"; } } + close IN_FILE; } From eab795ddd84ffdb1c67250062d01a81be20bb208 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 29 Sep 2020 14:23:39 +0200 Subject: [PATCH 418/645] scripts: kernel-doc: reimplement -nofunction argument Right now, the build system doesn't use -nofunction, as it is pretty much useless, because it doesn't consider the other output modes (extern, internal), working only with all. Also, it is limited to exclude functions. Re-implement it in order to allow excluding any symbols from the document output, no matter what mode is used. The parameter was also renamed to "-nosymbol", as it express better its meaning. Signed-off-by: Mauro Carvalho Chehab --- scripts/kernel-doc | 44 +++++++++++++++++++++----------------------- 1 file changed, 21 insertions(+), 23 deletions(-) diff --git a/scripts/kernel-doc b/scripts/kernel-doc index bdd2ebb4ac41..6a7996c96bbb 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -66,9 +66,8 @@ Output selection (mutually exclusive): -function NAME Only output documentation for the given function(s) or DOC: section title(s). All other functions and DOC: sections are ignored. May be specified multiple times. - -nofunction NAME Do NOT output documentation for the given function(s); - only output documentation for the other functions and - DOC: sections. May be specified multiple times. + -nosymbol NAME Exclude the specified symbols from the output + documentation. May be specified multiple times. Output selection modifiers: -no-doc-sections Do not output DOC: sections. @@ -288,9 +287,8 @@ my $modulename = "Kernel API"; use constant { OUTPUT_ALL => 0, # output all symbols and doc sections OUTPUT_INCLUDE => 1, # output only specified symbols - OUTPUT_EXCLUDE => 2, # output everything except specified symbols - OUTPUT_EXPORTED => 3, # output exported symbols - OUTPUT_INTERNAL => 4, # output non-exported symbols + OUTPUT_EXPORTED => 2, # output exported symbols + OUTPUT_INTERNAL => 3, # output non-exported symbols }; my $output_selection = OUTPUT_ALL; my $show_not_found = 0; # No longer used @@ -315,6 +313,7 @@ my $man_date = ('January', 'February', 'March', 'April', 'May', 'June', # CAVEAT EMPTOR! Some of the others I localised may not want to be, which # could cause "use of undefined value" or other bugs. my ($function, %function_table, %parametertypes, $declaration_purpose); +my %nosymbol_table = (); my $declaration_start_line; my ($type, $declaration_name, $return_type); my ($newsection, $newcontents, $prototype, $brcount, %source_map); @@ -434,10 +433,9 @@ while ($ARGV[0] =~ m/^--?(.*)/) { $output_selection = OUTPUT_INCLUDE; $function = shift @ARGV; $function_table{$function} = 1; - } elsif ($cmd eq "nofunction") { # output all except specific functions - $output_selection = OUTPUT_EXCLUDE; - $function = shift @ARGV; - $function_table{$function} = 1; + } elsif ($cmd eq "nosymbol") { # Exclude specific symbols + my $symbol = shift @ARGV; + $nosymbol_table{$symbol} = 1; } elsif ($cmd eq "export") { # only exported symbols $output_selection = OUTPUT_EXPORTED; %function_table = (); @@ -570,11 +568,11 @@ sub dump_doc_section { return; } + return if (defined($nosymbol_table{$name})); + if (($output_selection == OUTPUT_ALL) || - ($output_selection == OUTPUT_INCLUDE && - defined($function_table{$name})) || - ($output_selection == OUTPUT_EXCLUDE && - !defined($function_table{$name}))) + (($output_selection == OUTPUT_INCLUDE) && + defined($function_table{$name}))) { dump_section($file, $name, $contents); output_blockhead({'sectionlist' => \@sectionlist, @@ -800,6 +798,8 @@ sub output_blockhead_rst(%) { my ($parameter, $section); foreach $section (@{$args{'sectionlist'}}) { + next if (defined($nosymbol_table{$section})); + if ($output_selection != OUTPUT_INCLUDE) { print "**$section**\n\n"; } @@ -1115,12 +1115,14 @@ sub output_declaration { my $name = shift; my $functype = shift; my $func = "output_${functype}_$output_mode"; + + return if (defined($nosymbol_table{$name})); + if (($output_selection == OUTPUT_ALL) || (($output_selection == OUTPUT_INCLUDE || $output_selection == OUTPUT_EXPORTED) && defined($function_table{$name})) || - (($output_selection == OUTPUT_EXCLUDE || - $output_selection == OUTPUT_INTERNAL) && + ($output_selection == OUTPUT_INTERNAL && !($functype eq "function" && defined($function_table{$name})))) { &$func(@_); @@ -1301,6 +1303,8 @@ sub show_warnings($$) { my $functype = shift; my $name = shift; + return 0 if (defined($nosymbol_table{$name})); + return 1 if ($output_selection == OUTPUT_ALL); if ($output_selection == OUTPUT_EXPORTED) { @@ -1324,13 +1328,6 @@ sub show_warnings($$) { return 0; } } - if ($output_selection == OUTPUT_EXCLUDE) { - if (!defined($function_table{$name})) { - return 1; - } else { - return 0; - } - } die("Please add the new output type at show_warnings()"); } @@ -1952,6 +1949,7 @@ sub process_export_file($) { while () { if (/$export_symbol/) { + next if (defined($nosymbol_table{$2})); $function_table{$2} = 1; } } From 47bcacfd2b00e3795eac3faf47eb854eb9675a4f Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 30 Sep 2020 09:47:01 +0200 Subject: [PATCH 419/645] scripts: kernel-doc: fix typedef identification Some typedef expressions are output as normal functions. As we need to be clearer about the type with Sphinx 3.x, detect such cases. While here, fix a wrongly-indented block. Signed-off-by: Mauro Carvalho Chehab --- scripts/kernel-doc | 62 ++++++++++++++++++++++++++++++---------------- 1 file changed, 40 insertions(+), 22 deletions(-) diff --git a/scripts/kernel-doc b/scripts/kernel-doc index 6a7996c96bbb..33ad3ce66f73 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -1748,30 +1748,48 @@ sub dump_function($$) { return; } - my $prms = join " ", @parameterlist; - check_sections($file, $declaration_name, "function", $sectcheck, $prms); + my $prms = join " ", @parameterlist; + check_sections($file, $declaration_name, "function", $sectcheck, $prms); - # This check emits a lot of warnings at the moment, because many - # functions don't have a 'Return' doc section. So until the number - # of warnings goes sufficiently down, the check is only performed in - # verbose mode. - # TODO: always perform the check. - if ($verbose && !$noret) { - check_return_section($file, $declaration_name, $return_type); - } + # This check emits a lot of warnings at the moment, because many + # functions don't have a 'Return' doc section. So until the number + # of warnings goes sufficiently down, the check is only performed in + # verbose mode. + # TODO: always perform the check. + if ($verbose && !$noret) { + check_return_section($file, $declaration_name, $return_type); + } - output_declaration($declaration_name, - 'function', - {'function' => $declaration_name, - 'module' => $modulename, - 'functiontype' => $return_type, - 'parameterlist' => \@parameterlist, - 'parameterdescs' => \%parameterdescs, - 'parametertypes' => \%parametertypes, - 'sectionlist' => \@sectionlist, - 'sections' => \%sections, - 'purpose' => $declaration_purpose - }); + # The function parser can be called with a typedef parameter. + # Handle it. + if ($return_type =~ /typedef/) { + output_declaration($declaration_name, + 'function', + {'function' => $declaration_name, + 'typedef' => 1, + 'module' => $modulename, + 'functiontype' => $return_type, + 'parameterlist' => \@parameterlist, + 'parameterdescs' => \%parameterdescs, + 'parametertypes' => \%parametertypes, + 'sectionlist' => \@sectionlist, + 'sections' => \%sections, + 'purpose' => $declaration_purpose + }); + } else { + output_declaration($declaration_name, + 'function', + {'function' => $declaration_name, + 'module' => $modulename, + 'functiontype' => $return_type, + 'parameterlist' => \@parameterlist, + 'parameterdescs' => \%parameterdescs, + 'parametertypes' => \%parametertypes, + 'sectionlist' => \@sectionlist, + 'sections' => \%sections, + 'purpose' => $declaration_purpose + }); + } } sub reset_state { From ed8348e23abce79780f3b679c74a48bcdc47c947 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 30 Sep 2020 12:24:43 +0200 Subject: [PATCH 420/645] scripts: kernel-doc: don't mangle with parameter list While kernel-doc needs to parse parameters in order to identify its name, it shouldn't be touching the type, as parsing it is very difficult, and errors happen. One current error is when parsing this parameter: const u32 (*tab)[256] Found at ./lib/crc32.c, on this function: u32 __pure crc32_be_generic (u32 crc, unsigned char const *p, size_t len, const u32 (*tab)[256], u32 polynomial); The current logic mangles it, producing this output: const u32 ( *tab That's something that it is not recognizeable. So, instead, let's push the argument as-is, and use it when printing the function prototype and when describing each argument. Signed-off-by: Mauro Carvalho Chehab --- scripts/kernel-doc | 26 ++++++++++++++------------ 1 file changed, 14 insertions(+), 12 deletions(-) diff --git a/scripts/kernel-doc b/scripts/kernel-doc index 33ad3ce66f73..09e3e78b9723 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -655,10 +655,10 @@ sub output_function_man(%) { $type = $args{'parametertypes'}{$parameter}; if ($type =~ m/([^\(]*\(\*)\s*\)\s*\(([^\)]*)\)/) { # pointer-to-function - print ".BI \"" . $parenth . $1 . "\" " . $parameter . " \") (" . $2 . ")" . $post . "\"\n"; + print ".BI \"" . $parenth . $1 . "\" " . " \") (" . $2 . ")" . $post . "\"\n"; } else { $type =~ s/([^\*])$/$1 /; - print ".BI \"" . $parenth . $type . "\" " . $parameter . " \"" . $post . "\"\n"; + print ".BI \"" . $parenth . $type . "\" " . " \"" . $post . "\"\n"; } $count++; $parenth = ""; @@ -929,7 +929,7 @@ sub output_function_rst(%) { # pointer-to-function print $1 . $parameter . ") (" . $2 . ")"; } else { - print $type . " " . $parameter; + print $type; } } if ($args{'typedef'}) { @@ -954,7 +954,7 @@ sub output_function_rst(%) { $type = $args{'parametertypes'}{$parameter}; if ($type ne "") { - print "``$type $parameter``\n"; + print "``$type``\n"; } else { print "``$parameter``\n"; } @@ -1479,7 +1479,7 @@ sub create_parameterlist($$$$) { # Treat preprocessor directive as a typeless variable just to fill # corresponding data structures "correctly". Catch it later in # output_* subs. - push_parameter($arg, "", $file); + push_parameter($arg, "", "", $file); } elsif ($arg =~ m/\(.+\)\s*\(/) { # pointer-to-function $arg =~ tr/#/,/; @@ -1488,7 +1488,7 @@ sub create_parameterlist($$$$) { $type = $arg; $type =~ s/([^\(]+\(\*?)\s*$param/$1/; save_struct_actual($param); - push_parameter($param, $type, $file, $declaration_name); + push_parameter($param, $type, $arg, $file, $declaration_name); } elsif ($arg) { $arg =~ s/\s*:\s*/:/g; $arg =~ s/\s*\[/\[/g; @@ -1513,26 +1513,28 @@ sub create_parameterlist($$$$) { foreach $param (@args) { if ($param =~ m/^(\*+)\s*(.*)/) { save_struct_actual($2); - push_parameter($2, "$type $1", $file, $declaration_name); + + push_parameter($2, "$type $1", $arg, $file, $declaration_name); } elsif ($param =~ m/(.*?):(\d+)/) { if ($type ne "") { # skip unnamed bit-fields save_struct_actual($1); - push_parameter($1, "$type:$2", $file, $declaration_name) + push_parameter($1, "$type:$2", $arg, $file, $declaration_name) } } else { save_struct_actual($param); - push_parameter($param, $type, $file, $declaration_name); + push_parameter($param, $type, $arg, $file, $declaration_name); } } } } } -sub push_parameter($$$$) { +sub push_parameter($$$$$) { my $param = shift; my $type = shift; + my $org_arg = shift; my $file = shift; my $declaration_name = shift; @@ -1596,8 +1598,8 @@ sub push_parameter($$$$) { # "[blah" in a parameter string; ###$param =~ s/\s*//g; push @parameterlist, $param; - $type =~ s/\s\s+/ /g; - $parametertypes{$param} = $type; + $org_arg =~ s/\s\s+/ /g; + $parametertypes{$param} = $org_arg; } sub check_sections($$$$$) { From 93351d4196802b3ee01074d96df47b73716984ba Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Sun, 4 Oct 2020 09:44:28 +0200 Subject: [PATCH 421/645] scripts: kernel-doc: allow passing desired Sphinx C domain dialect When kernel-doc is called via kerneldoc.py, there's no need to auto-detect the Sphinx version, as the Sphinx module already knows it. So, add an optional parameter to allow changing the Sphinx dialect. As kernel-doc can also be manually called, keep the auto-detection logic if the parameter was not specified. On such case, emit a warning if sphinx-build can't be found at PATH. I ended using a suggestion from Joe for using a more readable regex, instead of using a complex one with a hidden group like: m/^(\d+)\.(\d+)(?:\.?(\d+)?)/ in order to get the optional argument. Thanks-to: Joe Perches Suggested-by: Jonathan Corbet Signed-off-by: Mauro Carvalho Chehab --- Documentation/sphinx/kerneldoc.py | 5 +++ scripts/kernel-doc | 51 ++++++++++++++++++++++++++----- 2 files changed, 48 insertions(+), 8 deletions(-) diff --git a/Documentation/sphinx/kerneldoc.py b/Documentation/sphinx/kerneldoc.py index 4bcbd6ae01cd..1a1b12242a45 100644 --- a/Documentation/sphinx/kerneldoc.py +++ b/Documentation/sphinx/kerneldoc.py @@ -70,6 +70,11 @@ class KernelDocDirective(Directive): env = self.state.document.settings.env cmd = [env.config.kerneldoc_bin, '-rst', '-enable-lineno'] + # Pass the version string to kernel-doc, as it needs to use a different + # dialect, depending what the C domain supports for each specific + # Sphinx versions + cmd += ['-sphinx-version', sphinx.__version__] + filename = env.config.kerneldoc_srctree + '/' + self.arguments[0] export_file_patterns = [] diff --git a/scripts/kernel-doc b/scripts/kernel-doc index 09e3e78b9723..ed32883c3221 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -56,6 +56,13 @@ Output format selection (mutually exclusive): -rst Output reStructuredText format. -none Do not output documentation, only warnings. +Output format selection modifier (affects only ReST output): + + -sphinx-version Use the ReST C domain dialect compatible with an + specific Sphinx Version. + If not specified, kernel-doc will auto-detect using + the sphinx-build version found on PATH. + Output selection (mutually exclusive): -export Only output documentation for symbols that have been exported using EXPORT_SYMBOL() or EXPORT_SYMBOL_GPL() @@ -270,7 +277,7 @@ if ($#ARGV == -1) { } my $kernelversion; -my $sphinx_major; +my ($sphinx_major, $sphinx_minor, $sphinx_patch); my $dohighlight = ""; @@ -457,6 +464,23 @@ while ($ARGV[0] =~ m/^--?(.*)/) { $enable_lineno = 1; } elsif ($cmd eq 'show-not-found') { $show_not_found = 1; # A no-op but don't fail + } elsif ($cmd eq "sphinx-version") { + my $ver_string = shift @ARGV; + if ($ver_string =~ m/^(\d+)(\.\d+)?(\.\d+)?/) { + $sphinx_major = $1; + if (defined($2)) { + $sphinx_minor = substr($2,1); + } else { + $sphinx_minor = 0; + } + if (defined($3)) { + $sphinx_patch = substr($3,1) + } else { + $sphinx_patch = 0; + } + } else { + die "Sphinx version should either major.minor or major.minor.patch format\n"; + } } else { # Unknown argument usage(); @@ -477,29 +501,37 @@ sub findprog($) sub get_sphinx_version() { my $ver; - my $major = 1; my $cmd = "sphinx-build"; if (!findprog($cmd)) { my $cmd = "sphinx-build3"; - return $major if (!findprog($cmd)); + if (!findprog($cmd)) { + $sphinx_major = 1; + $sphinx_minor = 2; + $sphinx_patch = 0; + printf STDERR "Warning: Sphinx version not found. Using default (Sphinx version %d.%d.%d)\n", + $sphinx_major, $sphinx_minor, $sphinx_patch; + return; + } } open IN, "$cmd --version 2>&1 |"; while () { if (m/^\s*sphinx-build\s+([\d]+)\.([\d\.]+)(\+\/[\da-f]+)?$/) { - $major=$1; + $sphinx_major = $1; + $sphinx_minor = $2; + $sphinx_patch = $3; last; } # Sphinx 1.2.x uses a different format if (m/^\s*Sphinx.*\s+([\d]+)\.([\d\.]+)$/) { - $major=$1; + $sphinx_major = $1; + $sphinx_minor = $2; + $sphinx_patch = $3; last; } } close IN; - - return $major; } # get kernel version from env @@ -2333,7 +2365,10 @@ sub process_file($) { } -$sphinx_major = get_sphinx_version(); +if ($output_mode eq "rst") { + get_sphinx_version() if (!$sphinx_major); +} + $kernelversion = get_kernel_version(); # generate a sequence of code that will splice in highlighting information From 5ef09c96d48b41a55121df1b57404f68d7e4e5f1 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 9 Oct 2020 10:15:25 +0200 Subject: [PATCH 422/645] scripts: kernel-doc: fix line number handling Address several issues related to pointing to the wrong line number: 1) ensure that line numbers will always be initialized When section is the default (Description), the line number is not initializing, producing this: $ ./scripts/kernel-doc --enable-lineno ./drivers/media/v4l2-core/v4l2-mem2mem.c|less **Description** #define LINENO 0 In case of streamoff or release called on any context, 1] If the context is currently running, then abort job will be called 2] If the context is queued, then the context will be removed from the job_queue Which is not right. Ensure that the line number will always be there. After applied, the result now points to the right location: **Description** #define LINENO 410 In case of streamoff or release called on any context, 1] If the context is currently running, then abort job will be called 2] If the context is queued, then the context will be removed from the job_queue 2) The line numbers for function prototypes are always + 1, because it is taken at the line after handling the prototype. Change the logic to point to the next line after the /** */ block; 3) The "DOC:" line number should point to the same line as this markup is found, and not to the next one. Probably part of the issues were due to a but that was causing the line number offset to be incremented by one, if --export were used. Signed-off-by: Mauro Carvalho Chehab --- scripts/kernel-doc | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/scripts/kernel-doc b/scripts/kernel-doc index ed32883c3221..9496abba9538 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -1705,7 +1705,7 @@ sub dump_function($$) { my $file = shift; my $noret = 0; - print_lineno($.); + print_lineno($new_start_line); $prototype =~ s/^static +//; $prototype =~ s/^extern +//; @@ -2033,7 +2033,7 @@ sub process_name($$) { if (/$doc_block/o) { $state = STATE_DOCBLOCK; $contents = ""; - $new_start_line = $. + 1; + $new_start_line = $.; if ( $1 eq "" ) { $section = $section_intro; @@ -2116,6 +2116,7 @@ sub process_body($$) { if ($state == STATE_BODY_WITH_BLANK_LINE && /^\s*\*\s?\S/) { dump_section($file, $section, $contents); $section = $section_default; + $new_start_line = $.; $contents = ""; } @@ -2171,6 +2172,7 @@ sub process_body($$) { $prototype = ""; $state = STATE_PROTO; $brcount = 0; + $new_start_line = $. + 1; } elsif (/$doc_content/) { if ($1 eq "") { if ($section eq $section_context) { From 6e9e415854c15dbf920481eb1d245988e405bbc0 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 30 Sep 2020 09:47:01 +0200 Subject: [PATCH 423/645] scripts: kernel-doc: try to use c:function if possible There are a few namespace clashes by using c:macro everywhere: basically, when using it, we can't have something like: .. c:struct:: pwm_capture .. c:macro:: pwm_capture So, we need to use, instead: .. c:function:: int pwm_capture (struct pwm_device * pwm, struct pwm_capture * result, unsigned long timeout) for the function declaration. The kernel-doc change was proposed by Jakob Lykke Andersen here: https://github.com/jakobandersen/linux_docs/commit/6fd2076ec001cca7466857493cd678df4dfe4a65 Although I did a different implementation. Signed-off-by: Mauro Carvalho Chehab --- scripts/kernel-doc | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-) diff --git a/scripts/kernel-doc b/scripts/kernel-doc index 9496abba9538..c8f6b11d5da1 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -917,6 +917,7 @@ sub output_function_rst(%) { my ($parameter, $section); my $oldprefix = $lineprefix; my $start = ""; + my $is_macro = 0; if ($sphinx_major < 3) { if ($args{'typedef'}) { @@ -926,11 +927,17 @@ sub output_function_rst(%) { $lineprefix = ""; output_highlight_rst($args{'purpose'}); $start = "\n\n**Syntax**\n\n ``"; + $is_macro = 1; } else { print ".. c:function:: "; } } else { - print ".. c:macro:: ". $args{'function'} . "\n\n"; + if ($args{'typedef'} || $args{'functiontype'} eq "") { + $is_macro = 1; + print ".. c:macro:: ". $args{'function'} . "\n\n"; + } else { + print ".. c:function:: "; + } if ($args{'typedef'}) { print_lineno($declaration_start_line); @@ -939,7 +946,7 @@ sub output_function_rst(%) { output_highlight_rst($args{'purpose'}); $start = "\n\n**Syntax**\n\n ``"; } else { - print "``"; + print "``" if ($is_macro); } } if ($args{'functiontype'} ne "") { @@ -964,14 +971,12 @@ sub output_function_rst(%) { print $type; } } - if ($args{'typedef'}) { - print ");``\n\n"; + if ($is_macro) { + print ")``\n\n"; } else { - if ($sphinx_major < 3) { - print ")\n\n"; - } else { - print ")``\n"; - } + print ")\n\n"; + } + if (!$args{'typedef'}) { print_lineno($declaration_start_line); $lineprefix = " "; output_highlight_rst($args{'purpose'}); From 71e552aebf260239463d348ecb75b972bee0804b Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 24 Sep 2020 11:32:38 +0200 Subject: [PATCH 424/645] docs: cdomain.py: add support for a new Sphinx 3.1+ tag Since Sphinx 3.0, the C domain code was rewritten, but only after version 3.1 it got support for setting namespaces on C domains, with is something that it is required, in order to document system calls, like ioctl() and others. As part of changing the documentation subsystem to properly build with Sphinx 3.1+, add support for such new tag: .. c:namespace::" Such tag optionally replaces the optional "name" tag for functions, setting a single namespace domain for all C references found at the file. With that, it should be possible to convert existing documentation to be compatible with both Sphinx 1.x/2.x and 3.1+. Signed-off-by: Mauro Carvalho Chehab --- Documentation/sphinx/cdomain.py | 55 ++++++++++++++++++++++++++++++++- 1 file changed, 54 insertions(+), 1 deletion(-) diff --git a/Documentation/sphinx/cdomain.py b/Documentation/sphinx/cdomain.py index cbac8e608dc4..35805c44a4fc 100644 --- a/Documentation/sphinx/cdomain.py +++ b/Documentation/sphinx/cdomain.py @@ -40,14 +40,56 @@ from sphinx import addnodes from sphinx.domains.c import c_funcptr_sig_re, c_sig_re from sphinx.domains.c import CObject as Base_CObject from sphinx.domains.c import CDomain as Base_CDomain +from itertools import chain +import re -__version__ = '1.0' +__version__ = '1.1' # Get Sphinx version major, minor, patch = sphinx.version_info[:3] +# Namespace to be prepended to the full name +namespace = None + +# +# Handle trivial newer c domain tags that are part of Sphinx 3.1 c domain tags +# - Store the namespace if ".. c:namespace::" tag is found + +RE_namespace = re.compile(r'^\s*..\s*c:namespace::\s*(\S+)\s*$') + +def markup_namespace(match): + global namespace + + namespace = match.group(1) + + return "" + +def c_markups(app, docname, source): + result = "" + markup_func = { + RE_namespace: markup_namespace, + } + + lines = iter(source[0].splitlines(True)) + for n in lines: + match_iterators = [regex.finditer(n) for regex in markup_func] + matches = sorted(chain(*match_iterators), key=lambda m: m.start()) + for m in matches: + n = n[:m.start()] + markup_func[m.re](m) + n[m.end():] + + result = result + n + + source[0] = result + +# +# Now implements support for the cdomain namespacing logic +# + def setup(app): + # Handle easy Sphinx 3.1+ simple new tags: :c:expr and .. c:namespace:: + app.connect('source-read', c_markups) + if (major == 1 and minor < 8): app.override_domain(CDomain) else: @@ -75,6 +117,8 @@ class CObject(Base_CObject): function-like macro, the name of the macro is returned. Otherwise ``False`` is returned. """ + global namespace + if not self.objtype == 'function': return False @@ -107,11 +151,16 @@ class CObject(Base_CObject): param += nodes.emphasis(argname, argname) paramlist += param + if namespace: + fullname = namespace + "." + fullname + return fullname def handle_signature(self, sig, signode): """Transform a C signature into RST nodes.""" + global namespace + fullname = self.handle_func_like_macro(sig, signode) if not fullname: fullname = super(CObject, self).handle_signature(sig, signode) @@ -122,6 +171,10 @@ class CObject(Base_CObject): else: # FIXME: handle :name: value of other declaration types? pass + else: + if namespace: + fullname = namespace + "." + fullname + return fullname def add_target_and_index(self, name, sig, signode): From 95f49490515e50f7ac23c453241503cd9fb4b434 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 25 Sep 2020 13:38:27 +0200 Subject: [PATCH 425/645] docs: cdomain.py: extend it to handle new Sphinx 3.x tags While most of the C domain parsing is done via kernel-doc, some RST files use C domain tags directly. While several of them can be removed for Sphinx < 3.0, due to automarkup.py, and several others that could be converted into kernel-doc markups, changes like that are time-consuming, and may not fit all cases. As we already have the cdomain.py for handing backward compatibility with Sphinx versions below 3.0, let's make it more complete, in order to cover any usage of the newer tags outside kernel-doc. This way, it should be feasible to use the new tags inside the Kernel tree, without losing backward compatibility. This should allow fixing the remaining warnings with the Kernel tags. Signed-off-by: Mauro Carvalho Chehab --- Documentation/sphinx/cdomain.py | 40 ++++++++++++++++++++++++++++++++- 1 file changed, 39 insertions(+), 1 deletion(-) diff --git a/Documentation/sphinx/cdomain.py b/Documentation/sphinx/cdomain.py index 35805c44a4fc..014a5229e57a 100644 --- a/Documentation/sphinx/cdomain.py +++ b/Documentation/sphinx/cdomain.py @@ -54,7 +54,7 @@ namespace = None # # Handle trivial newer c domain tags that are part of Sphinx 3.1 c domain tags # - Store the namespace if ".. c:namespace::" tag is found - +# RE_namespace = re.compile(r'^\s*..\s*c:namespace::\s*(\S+)\s*$') def markup_namespace(match): @@ -64,10 +64,48 @@ def markup_namespace(match): return "" +# +# Handle c:macro for function-style declaration +# +RE_macro = re.compile(r'^\s*..\s*c:macro::\s*(\S+)\s+(\S.*)\s*$') +def markup_macro(match): + return ".. c:function:: " + match.group(1) + ' ' + match.group(2) + +# +# Handle newer c domain tags that are evaluated as .. c:type: for +# backward-compatibility with Sphinx < 3.0 +# +RE_ctype = re.compile(r'^\s*..\s*c:(struct|union|enum|enumerator|alias)::\s*(.*)$') + +def markup_ctype(match): + return ".. c:type:: " + match.group(2) + +# +# Handle newer c domain tags that are evaluated as :c:type: for +# backward-compatibility with Sphinx < 3.0 +# +RE_ctype_refs = re.compile(r':c:(var|struct|union|enum|enumerator)::`([^\`]+)`') +def markup_ctype_refs(match): + return ":c:type:`" + match.group(2) + '`' + +# +# Simply convert :c:expr: and :c:texpr: into a literal block. +# +RE_expr = re.compile(r':c:(expr|texpr):`([^\`]+)`') +def markup_c_expr(match): + return '\ ``' + match.group(2) + '``\ ' + +# +# Parse Sphinx 3.x C markups, replacing them by backward-compatible ones +# def c_markups(app, docname, source): result = "" markup_func = { RE_namespace: markup_namespace, + RE_expr: markup_c_expr, + RE_macro: markup_macro, + RE_ctype: markup_ctype, + RE_ctype_refs: markup_ctype_refs, } lines = iter(source[0].splitlines(True)) From 91fc6d8afe06698326bdd4d3bcb362c17c52e288 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 Sep 2020 11:22:12 +0200 Subject: [PATCH 426/645] docs: kerneldoc.py: append the name of the parsed doc file Finding where an error like this was generated: ../lib/math/div64.c:73: WARNING: Duplicate C declaration, also defined in 'kernel-api'. Can take some time, as there's no glue about what kernel-doc tag generated it. It is a way better to display it as: .../Documentation/core-api/kernel-api:171: ../lib/math/div64.c:73: WARNING: Duplicate C declaration, also defined in 'kernel-api'. Declaration is 'div_s64_rem'. Signed-off-by: Mauro Carvalho Chehab --- Documentation/sphinx/kerneldoc.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/Documentation/sphinx/kerneldoc.py b/Documentation/sphinx/kerneldoc.py index 1a1b12242a45..a3a5427130da 100644 --- a/Documentation/sphinx/kerneldoc.py +++ b/Documentation/sphinx/kerneldoc.py @@ -141,7 +141,8 @@ class KernelDocDirective(Directive): lineoffset = int(match.group(1)) - 1 # we must eat our comments since the upset the markup else: - result.append(line, filename, lineoffset) + doc = env.srcdir + "/" + env.docname + ":" + str(self.lineno) + result.append(line, doc + ": " + filename, lineoffset) lineoffset += 1 node = nodes.section() From 2791f47d26d1e49a747a0a1aa2d694e6aab447ab Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 29 Sep 2020 11:32:18 +0200 Subject: [PATCH 427/645] docs: kerneldoc.py: add support for kerneldoc -nosymbol Currently, there's no way to exclude identifiers from a kernel-doc markup. Add support for it. Signed-off-by: Mauro Carvalho Chehab --- Documentation/doc-guide/kernel-doc.rst | 8 ++++++++ Documentation/sphinx/kerneldoc.py | 7 +++++++ 2 files changed, 15 insertions(+) diff --git a/Documentation/doc-guide/kernel-doc.rst b/Documentation/doc-guide/kernel-doc.rst index 4fd86c21397b..52a87ab4c99f 100644 --- a/Documentation/doc-guide/kernel-doc.rst +++ b/Documentation/doc-guide/kernel-doc.rst @@ -490,6 +490,14 @@ identifiers: *[ function/type ...]* .. kernel-doc:: lib/idr.c :identifiers: +no-identifiers: *[ function/type ...]* + Exclude documentation for each *function* and *type* in *source*. + + Example:: + + .. kernel-doc:: lib/bitmap.c + :no-identifiers: bitmap_parselist + functions: *[ function/type ...]* This is an alias of the 'identifiers' directive and deprecated. diff --git a/Documentation/sphinx/kerneldoc.py b/Documentation/sphinx/kerneldoc.py index a3a5427130da..e9857ab904f1 100644 --- a/Documentation/sphinx/kerneldoc.py +++ b/Documentation/sphinx/kerneldoc.py @@ -62,6 +62,7 @@ class KernelDocDirective(Directive): 'export': directives.unchanged, 'internal': directives.unchanged, 'identifiers': directives.unchanged, + 'no-identifiers': directives.unchanged, 'functions': directives.unchanged, } has_content = False @@ -104,6 +105,12 @@ class KernelDocDirective(Directive): else: cmd += ['-no-doc-sections'] + if 'no-identifiers' in self.options: + no_identifiers = self.options.get('no-identifiers').split() + if no_identifiers: + for i in no_identifiers: + cmd += ['-nosymbol', i] + for pattern in export_file_patterns: for f in glob.glob(env.config.kerneldoc_srctree + '/' + pattern): env.note_dependency(os.path.abspath(f)) From 06dc65b0fa6130aae73927399269bdea1b7658d8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?N=C3=ADcolas=20F=2E=20R=2E=20A=2E=20Prado?= Date: Tue, 13 Oct 2020 23:13:11 +0000 Subject: [PATCH 428/645] docs: automarkup.py: Use new C roles in Sphinx 3 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit While Sphinx 2 used a single c:type role for struct, union, enum and typedef, Sphinx 3 uses a specific role for each one. To keep backward compatibility, detect the Sphinx version and use the correct roles for that version. Signed-off-by: Nícolas F. R. A. Prado Signed-off-by: Mauro Carvalho Chehab --- Documentation/sphinx/automarkup.py | 55 ++++++++++++++++++++++++++---- 1 file changed, 49 insertions(+), 6 deletions(-) diff --git a/Documentation/sphinx/automarkup.py b/Documentation/sphinx/automarkup.py index a1b0f554cd82..db13fb15cedc 100644 --- a/Documentation/sphinx/automarkup.py +++ b/Documentation/sphinx/automarkup.py @@ -23,7 +23,21 @@ from itertools import chain # bit tries to restrict matches to things that won't create trouble. # RE_function = re.compile(r'(([\w_][\w\d_]+)\(\))') -RE_type = re.compile(r'(struct|union|enum|typedef)\s+([\w_][\w\d_]+)') + +# +# Sphinx 2 uses the same :c:type role for struct, union, enum and typedef +# +RE_generic_type = re.compile(r'(struct|union|enum|typedef)\s+([\w_][\w\d_]+)') + +# +# Sphinx 3 uses a different C role for each one of struct, union, enum and +# typedef +# +RE_struct = re.compile(r'\b(struct)\s+([a-zA-Z_]\w+)', flags=re.ASCII) +RE_union = re.compile(r'\b(union)\s+([a-zA-Z_]\w+)', flags=re.ASCII) +RE_enum = re.compile(r'\b(enum)\s+([a-zA-Z_]\w+)', flags=re.ASCII) +RE_typedef = re.compile(r'\b(typedef)\s+([a-zA-Z_]\w+)', flags=re.ASCII) + # # Detects a reference to a documentation page of the form Documentation/... with # an optional extension @@ -48,9 +62,22 @@ def markup_refs(docname, app, node): # # Associate each regex with the function that will markup its matches # - markup_func = {RE_type: markup_c_ref, - RE_function: markup_c_ref, - RE_doc: markup_doc_ref} + markup_func_sphinx2 = {RE_doc: markup_doc_ref, + RE_function: markup_c_ref, + RE_generic_type: markup_c_ref} + + markup_func_sphinx3 = {RE_doc: markup_doc_ref, + RE_function: markup_c_ref, + RE_struct: markup_c_ref, + RE_union: markup_c_ref, + RE_enum: markup_c_ref, + RE_typedef: markup_c_ref} + + if sphinx.version_info[0] >= 3: + markup_func = markup_func_sphinx3 + else: + markup_func = markup_func_sphinx2 + match_iterators = [regex.finditer(t) for regex in markup_func] # # Sort all references by the starting position in text @@ -79,8 +106,24 @@ def markup_refs(docname, app, node): # type_name) with an appropriate cross reference. # def markup_c_ref(docname, app, match): - class_str = {RE_function: 'c-func', RE_type: 'c-type'} - reftype_str = {RE_function: 'function', RE_type: 'type'} + class_str = {RE_function: 'c-func', + # Sphinx 2 only + RE_generic_type: 'c-type', + # Sphinx 3+ only + RE_struct: 'c-struct', + RE_union: 'c-union', + RE_enum: 'c-enum', + RE_typedef: 'c-type', + } + reftype_str = {RE_function: 'function', + # Sphinx 2 only + RE_generic_type: 'type', + # Sphinx 3+ only + RE_struct: 'struct', + RE_union: 'union', + RE_enum: 'enum', + RE_typedef: 'type', + } cdom = app.env.domains['c'] # From f66e47f98c1e827a85654a8cfa1ba539bb381a1b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?N=C3=ADcolas=20F=2E=20R=2E=20A=2E=20Prado?= Date: Tue, 13 Oct 2020 23:13:17 +0000 Subject: [PATCH 429/645] docs: automarkup.py: Fix regexes to solve sphinx 3 warnings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit With the transition to Sphinx 3, new warnings were generated by automarkup, exposing bugs in the regexes. The warnings were caused by the expressions matching words in the translated versions of the documentation, since any unicode character was matched. Fix the regular expression by making the C regexes use ASCII and ensuring the expressions only match the beginning of words, in order to avoid warnings like this: WARNING: Unparseable C cross-reference: '调用debugfs_rename' That's probably due to the lack of using spaces between words on Chinese. Signed-off-by: Nícolas F. R. A. Prado Signed-off-by: Mauro Carvalho Chehab --- Documentation/sphinx/automarkup.py | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/Documentation/sphinx/automarkup.py b/Documentation/sphinx/automarkup.py index db13fb15cedc..43dd9025fc77 100644 --- a/Documentation/sphinx/automarkup.py +++ b/Documentation/sphinx/automarkup.py @@ -22,12 +22,13 @@ from itertools import chain # :c:func: block (i.e. ":c:func:`mmap()`s" flakes out), so the last # bit tries to restrict matches to things that won't create trouble. # -RE_function = re.compile(r'(([\w_][\w\d_]+)\(\))') +RE_function = re.compile(r'\b(([a-zA-Z_]\w+)\(\))', flags=re.ASCII) # # Sphinx 2 uses the same :c:type role for struct, union, enum and typedef # -RE_generic_type = re.compile(r'(struct|union|enum|typedef)\s+([\w_][\w\d_]+)') +RE_generic_type = re.compile(r'\b(struct|union|enum|typedef)\s+([a-zA-Z_]\w+)', + flags=re.ASCII) # # Sphinx 3 uses a different C role for each one of struct, union, enum and @@ -42,7 +43,7 @@ RE_typedef = re.compile(r'\b(typedef)\s+([a-zA-Z_]\w+)', flags=re.ASCII) # Detects a reference to a documentation page of the form Documentation/... with # an optional extension # -RE_doc = re.compile(r'Documentation(/[\w\-_/]+)(\.\w+)*') +RE_doc = re.compile(r'\bDocumentation(/[\w\-_/]+)(\.\w+)*') # # Many places in the docs refer to common system calls. It is From 3050edfd7971da7fddc77ac7c4607697ec10a554 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?N=C3=ADcolas=20F=2E=20R=2E=20A=2E=20Prado?= Date: Tue, 13 Oct 2020 23:13:23 +0000 Subject: [PATCH 430/645] docs: automarkup.py: Skip C reserved words when cross-referencing MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit With the transition to Sphinx 3, new warnings were caused by automarkup, exposing bugs in the name matching. When automarkup parsed a text like "struct struct" in the documentation, it tried to cross-reference to a "struct" symbol, which is recognized as a C reserved word by Sphinx 3, generating a warning. Add some C reserved words (only the ones that were causing warnings) to a list and skip them while trying to cross-reference. Signed-off-by: Nícolas F. R. A. Prado Signed-off-by: Mauro Carvalho Chehab --- Documentation/sphinx/automarkup.py | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/Documentation/sphinx/automarkup.py b/Documentation/sphinx/automarkup.py index 43dd9025fc77..1cc3a2cf2a88 100644 --- a/Documentation/sphinx/automarkup.py +++ b/Documentation/sphinx/automarkup.py @@ -45,6 +45,12 @@ RE_typedef = re.compile(r'\b(typedef)\s+([a-zA-Z_]\w+)', flags=re.ASCII) # RE_doc = re.compile(r'\bDocumentation(/[\w\-_/]+)(\.\w+)*') +# +# Reserved C words that we should skip when cross-referencing +# +Skipnames = [ 'for', 'if', 'register', 'sizeof', 'struct', 'unsigned' ] + + # # Many places in the docs refer to common system calls. It is # pointless to try to cross-reference them and, as has been known @@ -133,7 +139,8 @@ def markup_c_ref(docname, app, match): target = match.group(2) target_text = nodes.Text(match.group(0)) xref = None - if not (match.re == RE_function and target in Skipfuncs): + if not ((match.re == RE_function and target in Skipfuncs) + or (target in Skipnames)): lit_text = nodes.literal(classes=['xref', 'c', class_str[match.re]]) lit_text += target_text pxref = addnodes.pending_xref('', refdomain = 'c', From c51d9b046f907b7c96760700c6bdda6fbe38de60 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?N=C3=ADcolas=20F=2E=20R=2E=20A=2E=20Prado?= Date: Tue, 13 Oct 2020 23:13:34 +0000 Subject: [PATCH 431/645] docs: automarkup.py: Add cross-reference for parametrized C macros MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Sphinx 3 added support for declaring C macros with parameters using the :c:macro role. To support automarkup for both functions and parametrized macros using the same regex (words ending in ()), try to cross-reference to both, and only fall back to regular text if neither exist. Signed-off-by: Nícolas F. R. A. Prado Signed-off-by: Mauro Carvalho Chehab --- Documentation/sphinx/automarkup.py | 49 +++++++++++++++++++++++++----- 1 file changed, 42 insertions(+), 7 deletions(-) diff --git a/Documentation/sphinx/automarkup.py b/Documentation/sphinx/automarkup.py index 1cc3a2cf2a88..409dbc4100de 100644 --- a/Documentation/sphinx/automarkup.py +++ b/Documentation/sphinx/automarkup.py @@ -74,7 +74,7 @@ def markup_refs(docname, app, node): RE_generic_type: markup_c_ref} markup_func_sphinx3 = {RE_doc: markup_doc_ref, - RE_function: markup_c_ref, + RE_function: markup_func_ref_sphinx3, RE_struct: markup_c_ref, RE_union: markup_c_ref, RE_enum: markup_c_ref, @@ -109,12 +109,47 @@ def markup_refs(docname, app, node): return repl # -# Try to replace a C reference (function() or struct/union/enum/typedef -# type_name) with an appropriate cross reference. +# In sphinx3 we can cross-reference to C macro and function, each one with its +# own C role, but both match the same regex, so we try both. # +def markup_func_ref_sphinx3(docname, app, match): + class_str = ['c-func', 'c-macro'] + reftype_str = ['function', 'macro'] + + cdom = app.env.domains['c'] + # + # Go through the dance of getting an xref out of the C domain + # + target = match.group(2) + target_text = nodes.Text(match.group(0)) + xref = None + if not (target in Skipfuncs or target in Skipnames): + for class_s, reftype_s in zip(class_str, reftype_str): + lit_text = nodes.literal(classes=['xref', 'c', class_s]) + lit_text += target_text + pxref = addnodes.pending_xref('', refdomain = 'c', + reftype = reftype_s, + reftarget = target, modname = None, + classname = None) + # + # XXX The Latex builder will throw NoUri exceptions here, + # work around that by ignoring them. + # + try: + xref = cdom.resolve_xref(app.env, docname, app.builder, + reftype_s, target, pxref, + lit_text) + except NoUri: + xref = None + + if xref: + return xref + + return target_text + def markup_c_ref(docname, app, match): - class_str = {RE_function: 'c-func', - # Sphinx 2 only + class_str = {# Sphinx 2 only + RE_function: 'c-func', RE_generic_type: 'c-type', # Sphinx 3+ only RE_struct: 'c-struct', @@ -122,8 +157,8 @@ def markup_c_ref(docname, app, match): RE_enum: 'c-enum', RE_typedef: 'c-type', } - reftype_str = {RE_function: 'function', - # Sphinx 2 only + reftype_str = {# Sphinx 2 only + RE_function: 'function', RE_generic_type: 'type', # Sphinx 3+ only RE_struct: 'struct', From 01fae02d8d67116f5b9bc36a8571356aa76f02f0 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 24 Sep 2020 08:15:55 +0200 Subject: [PATCH 432/645] media: docs: make CEC documents compatible with Sphinx 3.1+ Sphinx 3.x broke support for the cdomain.py extension, as the c domain code was rewritten. Due to that, the c tags need to be re-written, in order to use the new c domain notation. Signed-off-by: Mauro Carvalho Chehab --- .../media/cec/cec-func-close.rst | 10 +++------- .../media/cec/cec-func-ioctl.rst | 11 ++++------ .../userspace-api/media/cec/cec-func-open.rst | 10 +++------- .../userspace-api/media/cec/cec-func-poll.rst | 14 +++++-------- .../media/cec/cec-ioc-adap-g-caps.rst | 10 +++++----- .../media/cec/cec-ioc-adap-g-conn-info.rst | 11 +++++----- .../media/cec/cec-ioc-adap-g-log-addrs.rst | 20 ++++++++----------- .../media/cec/cec-ioc-adap-g-phys-addr.rst | 15 +++++++------- .../media/cec/cec-ioc-dqevent.rst | 15 +++++--------- .../media/cec/cec-ioc-g-mode.rst | 16 +++++++-------- .../media/cec/cec-ioc-receive.rst | 18 ++++++++--------- 11 files changed, 63 insertions(+), 87 deletions(-) diff --git a/Documentation/userspace-api/media/cec/cec-func-close.rst b/Documentation/userspace-api/media/cec/cec-func-close.rst index 33c563f414a8..409e70a5f80f 100644 --- a/Documentation/userspace-api/media/cec/cec-func-close.rst +++ b/Documentation/userspace-api/media/cec/cec-func-close.rst @@ -1,4 +1,5 @@ .. SPDX-License-Identifier: GFDL-1.1-no-invariants-or-later +.. c:namespace:: CEC .. _cec-func-close: @@ -11,7 +12,6 @@ Name cec-close - Close a cec device - Synopsis ======== @@ -19,16 +19,13 @@ Synopsis #include - .. c:function:: int close( int fd ) - :name: cec-close Arguments ========= ``fd`` - File descriptor returned by :c:func:`open() `. - + File descriptor returned by :c:func:`open()`. Description =========== @@ -36,11 +33,10 @@ Description Closes the cec device. Resources associated with the file descriptor are freed. The device configuration remain unchanged. - Return Value ============ -:c:func:`close() ` returns 0 on success. On error, -1 is returned, and +:c:func:`close()` returns 0 on success. On error, -1 is returned, and ``errno`` is set appropriately. Possible error codes are: ``EBADF`` diff --git a/Documentation/userspace-api/media/cec/cec-func-ioctl.rst b/Documentation/userspace-api/media/cec/cec-func-ioctl.rst index 3b88230fad80..7c93f86de6cc 100644 --- a/Documentation/userspace-api/media/cec/cec-func-ioctl.rst +++ b/Documentation/userspace-api/media/cec/cec-func-ioctl.rst @@ -1,4 +1,5 @@ .. SPDX-License-Identifier: GFDL-1.1-no-invariants-or-later +.. c:namespace:: CEC .. _cec-func-ioctl: @@ -18,15 +19,13 @@ Synopsis #include - -.. c:function:: int ioctl( int fd, int request, void *argp ) - :name: cec-ioctl +``int ioctl(int fd, int request, void *argp)`` Arguments ========= ``fd`` - File descriptor returned by :c:func:`open() `. + File descriptor returned by :c:func:`open()`. ``request`` CEC ioctl request code as defined in the cec.h header file, for @@ -35,11 +34,10 @@ Arguments ``argp`` Pointer to a request-specific structure. - Description =========== -The :c:func:`ioctl() ` function manipulates cec device parameters. The +The :c:func:`ioctl()` function manipulates cec device parameters. The argument ``fd`` must be an open file descriptor. The ioctl ``request`` code specifies the cec function to be called. It @@ -51,7 +49,6 @@ their parameters are located in the cec.h header file. All cec ioctl requests, their respective function and parameters are specified in :ref:`cec-user-func`. - Return Value ============ diff --git a/Documentation/userspace-api/media/cec/cec-func-open.rst b/Documentation/userspace-api/media/cec/cec-func-open.rst index 887bfd2a755e..d86563a34b9e 100644 --- a/Documentation/userspace-api/media/cec/cec-func-open.rst +++ b/Documentation/userspace-api/media/cec/cec-func-open.rst @@ -1,4 +1,5 @@ .. SPDX-License-Identifier: GFDL-1.1-no-invariants-or-later +.. c:namespace:: CEC .. _cec-func-open: @@ -18,10 +19,7 @@ Synopsis #include - .. c:function:: int open( const char *device_name, int flags ) - :name: cec-open - Arguments ========= @@ -42,11 +40,10 @@ Arguments Other flags have no effect. - Description =========== -To open a cec device applications call :c:func:`open() ` with the +To open a cec device applications call :c:func:`open()` with the desired device name. The function has no side effects; the device configuration remain unchanged. @@ -54,11 +51,10 @@ When the device is opened in read-only mode, attempts to modify its configuration will result in an error, and ``errno`` will be set to EBADF. - Return Value ============ -:c:func:`open() ` returns the new file descriptor on success. On error, +:c:func:`open()` returns the new file descriptor on success. On error, -1 is returned, and ``errno`` is set appropriately. Possible error codes include: diff --git a/Documentation/userspace-api/media/cec/cec-func-poll.rst b/Documentation/userspace-api/media/cec/cec-func-poll.rst index 2d87136e9a3f..980bbfc0bcce 100644 --- a/Documentation/userspace-api/media/cec/cec-func-poll.rst +++ b/Documentation/userspace-api/media/cec/cec-func-poll.rst @@ -1,4 +1,5 @@ .. SPDX-License-Identifier: GFDL-1.1-no-invariants-or-later +.. c:namespace:: CEC .. _cec-func-poll: @@ -11,7 +12,6 @@ Name cec-poll - Wait for some event on a file descriptor - Synopsis ======== @@ -19,9 +19,7 @@ Synopsis #include - .. c:function:: int poll( struct pollfd *ufds, unsigned int nfds, int timeout ) - :name: cec-poll Arguments ========= @@ -35,14 +33,13 @@ Arguments ``timeout`` Timeout to wait for events - Description =========== -With the :c:func:`poll() ` function applications can wait for CEC +With the :c:func:`poll()` function applications can wait for CEC events. -On success :c:func:`poll() ` returns the number of file descriptors +On success :c:func:`poll()` returns the number of file descriptors that have been selected (that is, file descriptors for which the ``revents`` field of the respective struct :c:type:`pollfd` is non-zero). CEC devices set the ``POLLIN`` and ``POLLRDNORM`` flags in @@ -53,13 +50,12 @@ then the ``POLLPRI`` flag is set. When the function times out it returns a value of zero, on failure it returns -1 and the ``errno`` variable is set appropriately. -For more details see the :c:func:`poll() ` manual page. - +For more details see the :c:func:`poll()` manual page. Return Value ============ -On success, :c:func:`poll() ` returns the number structures which have +On success, :c:func:`poll()` returns the number structures which have non-zero ``revents`` fields, or zero if the call timed out. On error -1 is returned, and the ``errno`` variable is set appropriately: diff --git a/Documentation/userspace-api/media/cec/cec-ioc-adap-g-caps.rst b/Documentation/userspace-api/media/cec/cec-ioc-adap-g-caps.rst index 7f25365ce0fb..c7309a2fcbce 100644 --- a/Documentation/userspace-api/media/cec/cec-ioc-adap-g-caps.rst +++ b/Documentation/userspace-api/media/cec/cec-ioc-adap-g-caps.rst @@ -1,4 +1,5 @@ .. SPDX-License-Identifier: GFDL-1.1-no-invariants-or-later +.. c:namespace:: CEC .. _CEC_ADAP_G_CAPS: @@ -14,18 +15,18 @@ CEC_ADAP_G_CAPS - Query device capabilities Synopsis ======== -.. c:function:: int ioctl( int fd, CEC_ADAP_G_CAPS, struct cec_caps *argp ) - :name: CEC_ADAP_G_CAPS +.. c:macro:: CEC_ADAP_G_CAPS + +``int ioctl(int fd, CEC_ADAP_G_CAPS, struct cec_caps *argp)`` Arguments ========= ``fd`` - File descriptor returned by :c:func:`open() `. + File descriptor returned by :c:func:`open()`. ``argp`` - Description =========== @@ -62,7 +63,6 @@ returns the information to the application. The ioctl never fails. - CEC Framework API version, formatted with the ``KERNEL_VERSION()`` macro. - .. tabularcolumns:: |p{4.4cm}|p{2.5cm}|p{10.6cm}| .. _cec-capabilities: diff --git a/Documentation/userspace-api/media/cec/cec-ioc-adap-g-conn-info.rst b/Documentation/userspace-api/media/cec/cec-ioc-adap-g-conn-info.rst index 6818ddf1495c..13116b0b5c17 100644 --- a/Documentation/userspace-api/media/cec/cec-ioc-adap-g-conn-info.rst +++ b/Documentation/userspace-api/media/cec/cec-ioc-adap-g-conn-info.rst @@ -2,6 +2,8 @@ .. .. Copyright 2019 Google LLC .. +.. c:namespace:: CEC + .. _CEC_ADAP_G_CONNECTOR_INFO: ******************************* @@ -16,18 +18,18 @@ CEC_ADAP_G_CONNECTOR_INFO - Query HDMI connector information Synopsis ======== -.. c:function:: int ioctl( int fd, CEC_ADAP_G_CONNECTOR_INFO, struct cec_connector_info *argp ) - :name: CEC_ADAP_G_CONNECTOR_INFO +.. c:macro:: CEC_ADAP_G_CONNECTOR_INFO + +``int ioctl(int fd, CEC_ADAP_G_CONNECTOR_INFO, struct cec_connector_info *argp)`` Arguments ========= ``fd`` - File descriptor returned by :c:func:`open() `. + File descriptor returned by :c:func:`open()`. ``argp`` - Description =========== @@ -57,7 +59,6 @@ is only available if the ``CEC_CAP_CONNECTOR_INFO`` capability is set. * - } - - .. tabularcolumns:: |p{4.4cm}|p{2.5cm}|p{10.6cm}| .. _connector-type: diff --git a/Documentation/userspace-api/media/cec/cec-ioc-adap-g-log-addrs.rst b/Documentation/userspace-api/media/cec/cec-ioc-adap-g-log-addrs.rst index 1ca893270ae9..c760c07b6b3f 100644 --- a/Documentation/userspace-api/media/cec/cec-ioc-adap-g-log-addrs.rst +++ b/Documentation/userspace-api/media/cec/cec-ioc-adap-g-log-addrs.rst @@ -1,4 +1,5 @@ .. SPDX-License-Identifier: GFDL-1.1-no-invariants-or-later +.. c:namespace:: CEC .. _CEC_ADAP_LOG_ADDRS: .. _CEC_ADAP_G_LOG_ADDRS: @@ -13,21 +14,22 @@ Name CEC_ADAP_G_LOG_ADDRS, CEC_ADAP_S_LOG_ADDRS - Get or set the logical addresses - Synopsis ======== -.. c:function:: int ioctl( int fd, CEC_ADAP_G_LOG_ADDRS, struct cec_log_addrs *argp ) - :name: CEC_ADAP_G_LOG_ADDRS +.. c:macro:: CEC_ADAP_G_LOG_ADDRS -.. c:function:: int ioctl( int fd, CEC_ADAP_S_LOG_ADDRS, struct cec_log_addrs *argp ) - :name: CEC_ADAP_S_LOG_ADDRS +``int ioctl(int fd, CEC_ADAP_G_LOG_ADDRS, struct cec_log_addrs *argp)`` + +.. c:macro:: CEC_ADAP_S_LOG_ADDRS + +``int ioctl(int fd, CEC_ADAP_S_LOG_ADDRS, struct cec_log_addrs *argp)`` Arguments ========= ``fd`` - File descriptor returned by :c:func:`open() `. + File descriptor returned by :c:func:`open()`. ``argp`` Pointer to struct :c:type:`cec_log_addrs`. @@ -148,7 +150,6 @@ logical address types are already defined will return with error ``EBUSY``. give the CEC framework more information about the device type, even though the framework won't use it directly in the CEC message. - .. tabularcolumns:: |p{7.8cm}|p{1.0cm}|p{8.7cm}| .. _cec-log-addrs-flags: @@ -185,7 +186,6 @@ logical address types are already defined will return with error ``EBUSY``. All other messages are ignored. - .. tabularcolumns:: |p{7.8cm}|p{1.0cm}|p{8.7cm}| .. _cec-versions: @@ -211,7 +211,6 @@ logical address types are already defined will return with error ``EBUSY``. - 6 - CEC version according to the HDMI 2.0 standard. - .. tabularcolumns:: |p{6.6cm}|p{2.2cm}|p{8.7cm}| .. _cec-prim-dev-types: @@ -257,7 +256,6 @@ logical address types are already defined will return with error ``EBUSY``. - 7 - Use for a video processor device. - .. tabularcolumns:: |p{6.6cm}|p{2.2cm}|p{8.7cm}| .. _cec-log-addr-types: @@ -306,7 +304,6 @@ logical address types are already defined will return with error ``EBUSY``. Control). - .. tabularcolumns:: |p{6.6cm}|p{2.2cm}|p{8.7cm}| .. _cec-all-dev-types-flags: @@ -348,7 +345,6 @@ logical address types are already defined will return with error ``EBUSY``. - This supports the CEC Switch or Video Processing type. - Return Value ============ diff --git a/Documentation/userspace-api/media/cec/cec-ioc-adap-g-phys-addr.rst b/Documentation/userspace-api/media/cec/cec-ioc-adap-g-phys-addr.rst index a10443be1b26..fb22f6894f26 100644 --- a/Documentation/userspace-api/media/cec/cec-ioc-adap-g-phys-addr.rst +++ b/Documentation/userspace-api/media/cec/cec-ioc-adap-g-phys-addr.rst @@ -1,4 +1,5 @@ .. SPDX-License-Identifier: GFDL-1.1-no-invariants-or-later +.. c:namespace:: CEC .. _CEC_ADAP_PHYS_ADDR: .. _CEC_ADAP_G_PHYS_ADDR: @@ -13,21 +14,22 @@ Name CEC_ADAP_G_PHYS_ADDR, CEC_ADAP_S_PHYS_ADDR - Get or set the physical address - Synopsis ======== -.. c:function:: int ioctl( int fd, CEC_ADAP_G_PHYS_ADDR, __u16 *argp ) - :name: CEC_ADAP_G_PHYS_ADDR +.. c:macro:: CEC_ADAP_G_PHYS_ADDR -.. c:function:: int ioctl( int fd, CEC_ADAP_S_PHYS_ADDR, __u16 *argp ) - :name: CEC_ADAP_S_PHYS_ADDR +``int ioctl(int fd, CEC_ADAP_G_PHYS_ADDR, __u16 *argp)`` + +.. c:macro:: CEC_ADAP_S_PHYS_ADDR + +``int ioctl(int fd, CEC_ADAP_S_PHYS_ADDR, __u16 *argp)`` Arguments ========= ``fd`` - File descriptor returned by :c:func:`open() `. + File descriptor returned by :c:func:`open()`. ``argp`` Pointer to the CEC address. @@ -71,7 +73,6 @@ For example, the EDID for each HDMI input of the TV will have a different physical address of the form a.0.0.0 that the sources will read out and use as their physical address. - Return Value ============ diff --git a/Documentation/userspace-api/media/cec/cec-ioc-dqevent.rst b/Documentation/userspace-api/media/cec/cec-ioc-dqevent.rst index 3bc81fc5a73f..736fda5ad73d 100644 --- a/Documentation/userspace-api/media/cec/cec-ioc-dqevent.rst +++ b/Documentation/userspace-api/media/cec/cec-ioc-dqevent.rst @@ -1,4 +1,5 @@ .. SPDX-License-Identifier: GFDL-1.1-no-invariants-or-later +.. c:namespace:: CEC .. _CEC_DQEVENT: @@ -11,22 +12,21 @@ Name CEC_DQEVENT - Dequeue a CEC event - Synopsis ======== -.. c:function:: int ioctl( int fd, CEC_DQEVENT, struct cec_event *argp ) - :name: CEC_DQEVENT +.. c:macro:: CEC_DQEVENT + +``int ioctl(int fd, CEC_DQEVENT, struct cec_event *argp)`` Arguments ========= ``fd`` - File descriptor returned by :c:func:`open() `. + File descriptor returned by :c:func:`open()`. ``argp`` - Description =========== @@ -72,7 +72,6 @@ it is guaranteed that the state did change in between the two events. the HDMI driver is still configuring the device or because the HDMI device was unbound. - .. c:type:: cec_event_lost_msgs .. tabularcolumns:: |p{1.0cm}|p{2.0cm}|p{14.5cm}| @@ -94,7 +93,6 @@ it is guaranteed that the state did change in between the two events. replied to within a second according to the CEC specification, this is more than enough. - .. tabularcolumns:: |p{1.0cm}|p{4.4cm}|p{2.5cm}|p{9.6cm}| .. c:type:: cec_event @@ -130,7 +128,6 @@ it is guaranteed that the state did change in between the two events. * - } - - .. tabularcolumns:: |p{5.6cm}|p{0.9cm}|p{11.0cm}| .. _cec-events: @@ -204,7 +201,6 @@ it is guaranteed that the state did change in between the two events. if the 5V is high, then an initial event will be generated for that filehandle. - .. tabularcolumns:: |p{6.0cm}|p{0.6cm}|p{10.9cm}| .. _cec-event-flags: @@ -230,7 +226,6 @@ it is guaranteed that the state did change in between the two events. This is an indication that the application cannot keep up. - Return Value ============ diff --git a/Documentation/userspace-api/media/cec/cec-ioc-g-mode.rst b/Documentation/userspace-api/media/cec/cec-ioc-g-mode.rst index 2093e373c93c..d3387b1fa7c5 100644 --- a/Documentation/userspace-api/media/cec/cec-ioc-g-mode.rst +++ b/Documentation/userspace-api/media/cec/cec-ioc-g-mode.rst @@ -1,4 +1,5 @@ .. SPDX-License-Identifier: GFDL-1.1-no-invariants-or-later +.. c:namespace:: CEC .. _CEC_MODE: .. _CEC_G_MODE: @@ -13,17 +14,19 @@ CEC_G_MODE, CEC_S_MODE - Get or set exclusive use of the CEC adapter Synopsis ======== -.. c:function:: int ioctl( int fd, CEC_G_MODE, __u32 *argp ) - :name: CEC_G_MODE +.. c:macro:: CEC_G_MODE -.. c:function:: int ioctl( int fd, CEC_S_MODE, __u32 *argp ) - :name: CEC_S_MODE +``int ioctl(int fd, CEC_G_MODE, __u32 *argp)`` + +.. c:macro:: CEC_S_MODE + +``int ioctl(int fd, CEC_S_MODE, __u32 *argp)`` Arguments ========= ``fd`` - File descriptor returned by :c:func:`open() `. + File descriptor returned by :c:func:`open()`. ``argp`` Pointer to CEC mode. @@ -101,7 +104,6 @@ Available initiator modes are: then an attempt to become one will return the ``EBUSY`` error code error. - Available follower modes are: .. tabularcolumns:: |p{6.6cm}|p{0.9cm}|p{10.0cm}| @@ -193,7 +195,6 @@ Available follower modes are: the process has the ``CAP_NET_ADMIN`` capability. If that is not set, then the ``EPERM`` error code is returned. - Core message processing details: .. tabularcolumns:: |p{6.6cm}|p{10.9cm}| @@ -272,7 +273,6 @@ Core message processing details: and then just pass the message on to the follower(s). - Return Value ============ diff --git a/Documentation/userspace-api/media/cec/cec-ioc-receive.rst b/Documentation/userspace-api/media/cec/cec-ioc-receive.rst index 9d629d46973c..b2fc051e99f4 100644 --- a/Documentation/userspace-api/media/cec/cec-ioc-receive.rst +++ b/Documentation/userspace-api/media/cec/cec-ioc-receive.rst @@ -1,4 +1,5 @@ .. SPDX-License-Identifier: GFDL-1.1-no-invariants-or-later +.. c:namespace:: CEC .. _CEC_TRANSMIT: .. _CEC_RECEIVE: @@ -12,21 +13,22 @@ Name CEC_RECEIVE, CEC_TRANSMIT - Receive or transmit a CEC message - Synopsis ======== -.. c:function:: int ioctl( int fd, CEC_RECEIVE, struct cec_msg \*argp ) - :name: CEC_RECEIVE +.. c:macro:: CEC_RECEIVE -.. c:function:: int ioctl( int fd, CEC_TRANSMIT, struct cec_msg \*argp ) - :name: CEC_TRANSMIT +``int ioctl(int fd, CEC_RECEIVE, struct cec_msg *argp)`` + +.. c:macro:: CEC_TRANSMIT + +``int ioctl(int fd, CEC_TRANSMIT, struct cec_msg *argp)`` Arguments ========= ``fd`` - File descriptor returned by :c:func:`open() `. + File descriptor returned by :c:func:`open()`. ``argp`` Pointer to struct cec_msg. @@ -194,7 +196,6 @@ View On' messages from initiator 0xf ('Unregistered') to destination 0 ('TV'). supports this, otherwise it is always 0. This counter is only valid if the :ref:`CEC_TX_STATUS_ERROR ` status bit is set. - .. tabularcolumns:: |p{6.2cm}|p{1.0cm}|p{10.3cm}| .. _cec-msg-flags: @@ -228,7 +229,6 @@ View On' messages from initiator 0xf ('Unregistered') to destination 0 ('TV'). capability. If that is not set, then the ``EPERM`` error code is returned. - .. tabularcolumns:: |p{5.6cm}|p{0.9cm}|p{11.0cm}| .. _cec-tx-status: @@ -298,7 +298,6 @@ View On' messages from initiator 0xf ('Unregistered') to destination 0 ('TV'). - The transmit timed out. This should not normally happen and this indicates a driver problem. - .. tabularcolumns:: |p{5.6cm}|p{0.9cm}|p{11.0cm}| .. _cec-rx-status: @@ -335,7 +334,6 @@ View On' messages from initiator 0xf ('Unregistered') to destination 0 ('TV'). reply was interrupted. - Return Value ============ From 407e84cd1e9a802df1955e281d8956439abc499b Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 24 Sep 2020 14:04:26 +0200 Subject: [PATCH 433/645] media: docs: make V4L documents more compatible with Sphinx 3.1+ Sphinx 3.x broke support for the cdomain.py extension, as the c domain code was rewritten. Due to that, the c tags need to be re-written, in order to use the new c domain notation. Signed-off-by: Mauro Carvalho Chehab --- .../userspace-api/media/v4l/buffer.rst | 14 +--- .../userspace-api/media/v4l/dev-capture.rst | 7 +- .../userspace-api/media/v4l/dev-output.rst | 7 +- .../userspace-api/media/v4l/dev-raw-vbi.rst | 19 ++--- .../userspace-api/media/v4l/dev-rds.rst | 12 +--- .../media/v4l/dev-sliced-vbi.rst | 31 ++------ .../userspace-api/media/v4l/diff-v4l.rst | 39 ++--------- .../userspace-api/media/v4l/dmabuf.rst | 8 +-- .../userspace-api/media/v4l/format.rst | 7 +- .../userspace-api/media/v4l/func-close.rst | 8 +-- .../userspace-api/media/v4l/func-ioctl.rst | 10 +-- .../userspace-api/media/v4l/func-mmap.rst | 18 ++--- .../userspace-api/media/v4l/func-munmap.rst | 14 ++-- .../userspace-api/media/v4l/func-open.rst | 14 ++-- .../userspace-api/media/v4l/func-poll.rst | 40 +++++------ .../userspace-api/media/v4l/func-read.rst | 39 +++++------ .../userspace-api/media/v4l/func-select.rst | 42 +++++------ .../userspace-api/media/v4l/func-write.rst | 13 ++-- .../userspace-api/media/v4l/hist-v4l2.rst | 70 ++----------------- Documentation/userspace-api/media/v4l/io.rst | 6 +- .../media/v4l/libv4l-introduction.rst | 30 ++++---- .../userspace-api/media/v4l/mmap.rst | 26 +++---- .../userspace-api/media/v4l/open.rst | 15 ++-- Documentation/userspace-api/media/v4l/rw.rst | 18 ++--- .../userspace-api/media/v4l/streaming-par.rst | 5 +- .../userspace-api/media/v4l/userp.rst | 11 +-- .../media/v4l/vidioc-create-bufs.rst | 11 ++- .../media/v4l/vidioc-cropcap.rst | 11 ++- .../media/v4l/vidioc-dbg-g-chip-info.rst | 13 ++-- .../media/v4l/vidioc-dbg-g-register.rst | 18 ++--- .../media/v4l/vidioc-decoder-cmd.rst | 19 +++-- .../media/v4l/vidioc-dqevent.rst | 19 ++--- .../media/v4l/vidioc-dv-timings-cap.rst | 17 ++--- .../media/v4l/vidioc-encoder-cmd.rst | 25 +++---- .../media/v4l/vidioc-enum-dv-timings.rst | 16 ++--- .../media/v4l/vidioc-enum-fmt.rst | 12 ++-- .../media/v4l/vidioc-enum-frameintervals.rst | 15 ++-- .../media/v4l/vidioc-enum-framesizes.rst | 16 ++--- .../media/v4l/vidioc-enum-freq-bands.rst | 12 ++-- .../media/v4l/vidioc-enumaudio.rst | 10 ++- .../media/v4l/vidioc-enumaudioout.rst | 10 ++- .../media/v4l/vidioc-enuminput.rst | 14 ++-- .../media/v4l/vidioc-enumoutput.rst | 13 ++-- .../media/v4l/vidioc-enumstd.rst | 23 ++---- .../userspace-api/media/v4l/vidioc-expbuf.rst | 14 ++-- .../media/v4l/vidioc-g-audio.rst | 18 ++--- .../media/v4l/vidioc-g-audioout.rst | 16 ++--- .../userspace-api/media/v4l/vidioc-g-crop.rst | 16 ++--- .../userspace-api/media/v4l/vidioc-g-ctrl.rst | 16 ++--- .../media/v4l/vidioc-g-dv-timings.rst | 26 +++---- .../userspace-api/media/v4l/vidioc-g-edid.rst | 25 ++++--- .../media/v4l/vidioc-g-enc-index.rst | 13 ++-- .../media/v4l/vidioc-g-ext-ctrls.rst | 21 +++--- .../userspace-api/media/v4l/vidioc-g-fbuf.rst | 18 ++--- .../userspace-api/media/v4l/vidioc-g-fmt.rst | 22 +++--- .../media/v4l/vidioc-g-frequency.rst | 16 ++--- .../media/v4l/vidioc-g-input.rst | 15 ++-- .../media/v4l/vidioc-g-jpegcomp.rst | 17 ++--- .../media/v4l/vidioc-g-modulator.rst | 17 ++--- .../media/v4l/vidioc-g-output.rst | 15 ++-- .../userspace-api/media/v4l/vidioc-g-parm.rst | 30 ++++---- .../media/v4l/vidioc-g-priority.rst | 16 ++--- .../media/v4l/vidioc-g-selection.rst | 15 ++-- .../media/v4l/vidioc-g-sliced-vbi-cap.rst | 12 ++-- .../userspace-api/media/v4l/vidioc-g-std.rst | 24 ++++--- .../media/v4l/vidioc-g-tuner.rst | 19 ++--- .../media/v4l/vidioc-log-status.rst | 10 ++- .../media/v4l/vidioc-overlay.rst | 10 ++- .../media/v4l/vidioc-prepare-buf.rst | 10 ++- .../userspace-api/media/v4l/vidioc-qbuf.rst | 17 +++-- .../media/v4l/vidioc-query-dv-timings.rst | 15 ++-- .../media/v4l/vidioc-querybuf.rst | 10 ++- .../media/v4l/vidioc-querycap.rst | 16 ++--- .../media/v4l/vidioc-queryctrl.rst | 22 +++--- .../media/v4l/vidioc-querystd.rst | 15 ++-- .../media/v4l/vidioc-reqbufs.rst | 10 ++- .../media/v4l/vidioc-s-hw-freq-seek.rst | 11 ++- .../media/v4l/vidioc-streamon.rst | 14 ++-- .../v4l/vidioc-subdev-enum-frame-interval.rst | 10 ++- .../v4l/vidioc-subdev-enum-frame-size.rst | 11 ++- .../v4l/vidioc-subdev-enum-mbus-code.rst | 10 ++- .../media/v4l/vidioc-subdev-g-crop.rst | 16 ++--- .../media/v4l/vidioc-subdev-g-fmt.rst | 17 ++--- .../v4l/vidioc-subdev-g-frame-interval.rst | 16 ++--- .../media/v4l/vidioc-subdev-g-selection.rst | 17 ++--- .../media/v4l/vidioc-subdev-querycap.rst | 9 ++- .../media/v4l/vidioc-subscribe-event.rst | 17 ++--- 87 files changed, 559 insertions(+), 922 deletions(-) diff --git a/Documentation/userspace-api/media/v4l/buffer.rst b/Documentation/userspace-api/media/v4l/buffer.rst index 4f95496adc5b..8be62dcffbb2 100644 --- a/Documentation/userspace-api/media/v4l/buffer.rst +++ b/Documentation/userspace-api/media/v4l/buffer.rst @@ -1,4 +1,5 @@ .. SPDX-License-Identifier: GFDL-1.1-no-invariants-or-later +.. c:namespace:: V4L .. _buffer: @@ -33,7 +34,6 @@ mem-to-mem devices is an exception to the rule: the timestamp source flags are copied from the OUTPUT video buffer to the CAPTURE video buffer. - Interactions between formats, controls and buffers ================================================== @@ -152,7 +152,6 @@ based on the queried sizes (for instance by allocating a set of buffers large enough for all the desired formats and controls, or by allocating separate set of appropriately sized buffers for each use case). - .. c:type:: v4l2_buffer struct v4l2_buffer @@ -257,7 +256,7 @@ struct v4l2_buffer ``V4L2_MEMORY_MMAP`` this is the offset of the buffer from the start of the device memory. The value is returned by the driver and apart of serving as parameter to the - :ref:`mmap() ` function not useful for applications. + :c:func:`mmap()` function not useful for applications. See :ref:`mmap` for details * - unsigned long - ``userptr`` @@ -310,7 +309,6 @@ struct v4l2_buffer given, then ``EINVAL`` will be returned. - .. c:type:: v4l2_plane struct v4l2_plane @@ -350,7 +348,7 @@ struct v4l2_plane - ``mem_offset`` - When the memory type in the containing struct :c:type:`v4l2_buffer` is ``V4L2_MEMORY_MMAP``, this - is the value that should be passed to :ref:`mmap() `, + is the value that should be passed to :c:func:`mmap()`, similar to the ``offset`` field in struct :c:type:`v4l2_buffer`. * - unsigned long @@ -384,7 +382,6 @@ struct v4l2_plane applications. - .. c:type:: v4l2_buf_type enum v4l2_buf_type @@ -448,7 +445,6 @@ enum v4l2_buf_type - Buffer for metadata output, see :ref:`metadata`. - .. _buffer-flags: Buffer Flags @@ -720,7 +716,6 @@ enum v4l2_memory - The buffer is used for :ref:`DMA shared buffer ` I/O. - Timecodes ========= @@ -729,7 +724,6 @@ The :c:type:`v4l2_buffer_timecode` structure is designed to hold a (struct :c:type:`timeval` timestamps are stored in the struct :c:type:`v4l2_buffer` ``timestamp`` field.) - .. c:type:: v4l2_timecode struct v4l2_timecode @@ -766,7 +760,6 @@ struct v4l2_timecode - The "user group" bits from the timecode. - .. _timecode-type: Timecode Types @@ -796,7 +789,6 @@ Timecode Types - - .. _timecode-flags: Timecode Flags diff --git a/Documentation/userspace-api/media/v4l/dev-capture.rst b/Documentation/userspace-api/media/v4l/dev-capture.rst index 5ea1ffe71fa6..fe58fd450e2f 100644 --- a/Documentation/userspace-api/media/v4l/dev-capture.rst +++ b/Documentation/userspace-api/media/v4l/dev-capture.rst @@ -1,4 +1,5 @@ .. SPDX-License-Identifier: GFDL-1.1-no-invariants-or-later +.. c:namespace:: V4L .. _capture: @@ -19,7 +20,6 @@ device. .. note:: The same device file names are used for video output devices. - Querying Capabilities ===================== @@ -34,7 +34,6 @@ functions they may also support the :ref:`video overlay ` streaming I/O methods must be supported. Tuners and audio inputs are optional. - Supplemental Functions ====================== @@ -45,7 +44,6 @@ Video capture devices shall support :ref:`audio input