forge/pve-kernel-thunderx
1
0
Fork 0
Code Issues 3 Pull requests Projects Releases Packages 16 Wiki Activity Actions

Synchronize kernel patches with upstream

Browse source 
This change updates the kernel patches with the patches used by Proxmox.
This commit is contained in:
Fabian Mastenbroek 2022-08-17 14:34:44 +02:00
parent 458f87fda1
commit 3c771c6126
No known key found for this signature in database
GPG key ID: 405FC6F81F0A7B85
19 changed files with 2242 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

147
debian/patches/pve/0009-blk-cgroup-always-terminate-io.stat-lines.patch vendored Normal file
View file

@ -0,0 +1,147 @@
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Wolfgang Bumiller <w.bumiller@proxmox.com>
Date: Tue, 11 Jan 2022 09:31:59 +0100
Subject: [PATCH] blk-cgroup: always terminate io.stat lines
With the removal of seq_get_buf in blkcg_print_one_stat, we
cannot make adding the newline conditional on there being
relevant stats because the name was already written out
unconditionally.
Otherwise we may end up with multiple device names in one
line which is confusing and doesn't follow the nested-keyed
file format.
Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
Fixes: 252c651a4c85 ("blk-cgroup: stop using seq_get_buf")
Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
---
block/blk-cgroup.c | 9 ++-------
block/blk-iocost.c | 5 ++---
block/blk-iolatency.c | 8 +++-----
include/linux/blk-cgroup.h | 2 +-
4 files changed, 8 insertions(+), 16 deletions(-)
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 07a2524e6efd..fd09c20a5543 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -887,7 +887,6 @@ static void blkcg_print_one_stat(struct blkcg_gq *blkg, struct seq_file *s)
{
struct blkg_iostat_set *bis = &blkg->iostat;
u64 rbytes, wbytes, rios, wios, dbytes, dios;
- bool has_stats = false;
const char *dname;
unsigned seq;
int i;
@@ -913,14 +912,12 @@ static void blkcg_print_one_stat(struct blkcg_gq *blkg, struct seq_file *s)
} while (u64_stats_fetch_retry(&bis->sync, seq));
if (rbytes || wbytes || rios || wios) {
- has_stats = true;
seq_printf(s, "rbytes=%llu wbytes=%llu rios=%llu wios=%llu dbytes=%llu dios=%llu",
rbytes, wbytes, rios, wios,
dbytes, dios);
}
if (blkcg_debug_stats && atomic_read(&blkg->use_delay)) {
- has_stats = true;
seq_printf(s, " use_delay=%d delay_nsec=%llu",
atomic_read(&blkg->use_delay),
atomic64_read(&blkg->delay_nsec));
@@ -932,12 +929,10 @@ static void blkcg_print_one_stat(struct blkcg_gq *blkg, struct seq_file *s)
if (!blkg->pd[i] || !pol->pd_stat_fn)
continue;
- if (pol->pd_stat_fn(blkg->pd[i], s))
- has_stats = true;
+ pol->pd_stat_fn(blkg->pd[i], s);
}
- if (has_stats)
- seq_printf(s, "\n");
+ seq_puts(s, "\n");
}
static int blkcg_print_stat(struct seq_file *sf, void *v)
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index 10851493940c..21db328c0bcc 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -3005,13 +3005,13 @@ static void ioc_pd_free(struct blkg_policy_data *pd)
kfree(iocg);
}
-static bool ioc_pd_stat(struct blkg_policy_data *pd, struct seq_file *s)
+static void ioc_pd_stat(struct blkg_policy_data *pd, struct seq_file *s)
{
struct ioc_gq *iocg = pd_to_iocg(pd);
struct ioc *ioc = iocg->ioc;
if (!ioc->enabled)
- return false;
+ return;
if (iocg->level == 0) {
unsigned vp10k = DIV64_U64_ROUND_CLOSEST(
@@ -3027,7 +3027,6 @@ static bool ioc_pd_stat(struct blkg_policy_data *pd, struct seq_file *s)
iocg->last_stat.wait_us,
iocg->last_stat.indebt_us,
iocg->last_stat.indelay_us);
- return true;
}
static u64 ioc_weight_prfill(struct seq_file *sf, struct blkg_policy_data *pd,
diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c
index c0545f9da549..d33460f3d43d 100644
--- a/block/blk-iolatency.c
+++ b/block/blk-iolatency.c
@@ -890,7 +890,7 @@ static int iolatency_print_limit(struct seq_file *sf, void *v)
return 0;
}
-static bool iolatency_ssd_stat(struct iolatency_grp *iolat, struct seq_file *s)
+static void iolatency_ssd_stat(struct iolatency_grp *iolat, struct seq_file *s)
{
struct latency_stat stat;
int cpu;
@@ -913,17 +913,16 @@ static bool iolatency_ssd_stat(struct iolatency_grp *iolat, struct seq_file *s)
(unsigned long long)stat.ps.missed,
(unsigned long long)stat.ps.total,
iolat->rq_depth.max_depth);
- return true;
}
-static bool iolatency_pd_stat(struct blkg_policy_data *pd, struct seq_file *s)
+static void iolatency_pd_stat(struct blkg_policy_data *pd, struct seq_file *s)
{
struct iolatency_grp *iolat = pd_to_lat(pd);
unsigned long long avg_lat;
unsigned long long cur_win;
if (!blkcg_debug_stats)
- return false;
+ return;
if (iolat->ssd)
return iolatency_ssd_stat(iolat, s);
@@ -936,7 +935,6 @@ static bool iolatency_pd_stat(struct blkg_policy_data *pd, struct seq_file *s)
else
seq_printf(s, " depth=%u avg_lat=%llu win=%llu",
iolat->rq_depth.max_depth, avg_lat, cur_win);
- return true;
}
static struct blkg_policy_data *iolatency_pd_alloc(gfp_t gfp,
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index bc5c04d711bb..618359e3beca 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -153,7 +153,7 @@ typedef void (blkcg_pol_online_pd_fn)(struct blkg_policy_data *pd);
typedef void (blkcg_pol_offline_pd_fn)(struct blkg_policy_data *pd);
typedef void (blkcg_pol_free_pd_fn)(struct blkg_policy_data *pd);
typedef void (blkcg_pol_reset_pd_stats_fn)(struct blkg_policy_data *pd);
-typedef bool (blkcg_pol_stat_pd_fn)(struct blkg_policy_data *pd,
+typedef void (blkcg_pol_stat_pd_fn)(struct blkg_policy_data *pd,
struct seq_file *s);
struct blkcg_policy {

34
debian/patches/pve/0010-drivers-firmware-Don-t-mark-as-busy-the-simple-frame.patch vendored Normal file
View file

@ -0,0 +1,34 @@
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Javier Martinez Canillas <javierm@redhat.com>
Date: Tue, 25 Jan 2022 10:12:19 +0100
Subject: [PATCH] drivers/firmware: Don't mark as busy the simple-framebuffer
IO resource
The sysfb_create_simplefb() function requests a IO memory resource for the
simple-framebuffer platform device, but it also marks it as busy which can
lead to drivers requesting the same memory resource to fail.
Let's drop the IORESOURCE_BUSY flag and let drivers to request it as busy
instead.
Signed-off-by: Javier Martinez Canillas <javierm@redhat.com>
Reviewed-by: Zack Rusin <zackr@vmware.com>
Reviewed-by: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
---
drivers/firmware/sysfb_simplefb.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/firmware/sysfb_simplefb.c b/drivers/firmware/sysfb_simplefb.c
index 757cc8b9f3de..bda8712bfd8c 100644
--- a/drivers/firmware/sysfb_simplefb.c
+++ b/drivers/firmware/sysfb_simplefb.c
@@ -99,7 +99,7 @@ __init int sysfb_create_simplefb(const struct screen_info *si,
/* setup IORESOURCE_MEM as framebuffer memory */
memset(&res, 0, sizeof(res));
- res.flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+ res.flags = IORESOURCE_MEM;
res.name = simplefb_resname;
res.start = base;
res.end = res.start + length - 1;

63
debian/patches/pve/0011-drm-simpledrm-Request-memory-region-in-driver.patch vendored Normal file
View file

@ -0,0 +1,63 @@
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Tue, 25 Jan 2022 10:12:20 +0100
Subject: [PATCH] drm/simpledrm: Request memory region in driver
Requesting the framebuffer memory in simpledrm marks the memory
range as busy. This used to be done by the firmware sysfb code,
but the driver is the correct place.
v2:
* use I/O memory if request_mem_region() fails (Jocelyn)
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: Javier Martinez Canillas <javierm@redhat.com>
Reviewed-by: Jocelyn Falempe <jfalempe@redhat.com>
Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
---
drivers/gpu/drm/tiny/simpledrm.c | 22 +++++++++++++++++-----
1 file changed, 17 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/tiny/simpledrm.c b/drivers/gpu/drm/tiny/simpledrm.c
index 3e3f9ba1e885..806fdc3237b3 100644
--- a/drivers/gpu/drm/tiny/simpledrm.c
+++ b/drivers/gpu/drm/tiny/simpledrm.c
@@ -525,21 +525,33 @@ static int simpledrm_device_init_mm(struct simpledrm_device *sdev)
{
struct drm_device *dev = &sdev->dev;
struct platform_device *pdev = sdev->pdev;
- struct resource *mem;
+ struct resource *res, *mem;
void __iomem *screen_base;
int ret;
- mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (!mem)
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!res)
return -EINVAL;
- ret = devm_aperture_acquire_from_firmware(dev, mem->start, resource_size(mem));
+ ret = devm_aperture_acquire_from_firmware(dev, res->start, resource_size(res));
if (ret) {
drm_err(dev, "could not acquire memory range %pr: error %d\n",
- mem, ret);
+ res, ret);
return ret;
}
+ mem = devm_request_mem_region(&pdev->dev, res->start, resource_size(res),
+ sdev->dev.driver->name);
+ if (!mem) {
+ /*
+ * We cannot make this fatal. Sometimes this comes from magic
+ * spaces our resource handlers simply don't know about. Use
+ * the I/O-memory resource as-is and try to map that instead.
+ */
+ drm_warn(dev, "could not acquire memory region %pr\n", res);
+ mem = res;
+ }
+
screen_base = devm_ioremap_wc(&pdev->dev, mem->start,
resource_size(mem));
if (!screen_base)

144
debian/patches/pve/0012-fbdev-simplefb-Request-memory-region-in-driver.patch vendored Normal file
View file

@ -0,0 +1,144 @@
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Tue, 25 Jan 2022 10:12:21 +0100
Subject: [PATCH] fbdev/simplefb: Request memory region in driver
Requesting the framebuffer memory in simpledrm marks the memory
range as busy. This used to be done by the firmware sysfb code,
but the driver is the correct place.
v2:
* store memory region in struct for later cleanup (Javier)
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: Javier Martinez Canillas <javierm@redhat.com>
Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
---
drivers/video/fbdev/simplefb.c | 65 +++++++++++++++++++++++-----------
1 file changed, 45 insertions(+), 20 deletions(-)
diff --git a/drivers/video/fbdev/simplefb.c b/drivers/video/fbdev/simplefb.c
index b63074fd892e..6885ac0203de 100644
--- a/drivers/video/fbdev/simplefb.c
+++ b/drivers/video/fbdev/simplefb.c
@@ -66,16 +66,36 @@ static int simplefb_setcolreg(u_int regno, u_int red, u_int green, u_int blue,
return 0;
}
-struct simplefb_par;
+struct simplefb_par {
+ u32 palette[PSEUDO_PALETTE_SIZE];
+ struct resource *mem;
+#if defined CONFIG_OF && defined CONFIG_COMMON_CLK
+ bool clks_enabled;
+ unsigned int clk_count;
+ struct clk **clks;
+#endif
+#if defined CONFIG_OF && defined CONFIG_REGULATOR
+ bool regulators_enabled;
+ u32 regulator_count;
+ struct regulator **regulators;
+#endif
+};
+
static void simplefb_clocks_destroy(struct simplefb_par *par);
static void simplefb_regulators_destroy(struct simplefb_par *par);
static void simplefb_destroy(struct fb_info *info)
{
+ struct simplefb_par *par = info->par;
+ struct resource *mem = par->mem;
+
simplefb_regulators_destroy(info->par);
simplefb_clocks_destroy(info->par);
if (info->screen_base)
iounmap(info->screen_base);
+
+ if (mem)
+ release_mem_region(mem->start, resource_size(mem));
}
static const struct fb_ops simplefb_ops = {
@@ -169,20 +189,6 @@ static int simplefb_parse_pd(struct platform_device *pdev,
return 0;
}
-struct simplefb_par {
- u32 palette[PSEUDO_PALETTE_SIZE];
-#if defined CONFIG_OF && defined CONFIG_COMMON_CLK
- bool clks_enabled;
- unsigned int clk_count;
- struct clk **clks;
-#endif
-#if defined CONFIG_OF && defined CONFIG_REGULATOR
- bool regulators_enabled;
- u32 regulator_count;
- struct regulator **regulators;
-#endif
-};
-
#if defined CONFIG_OF && defined CONFIG_COMMON_CLK
/*
* Clock handling code.
@@ -405,7 +411,7 @@ static int simplefb_probe(struct platform_device *pdev)
struct simplefb_params params;
struct fb_info *info;
struct simplefb_par *par;
- struct resource *mem;
+ struct resource *res, *mem;
/*
* Generic drivers must not be registered if a framebuffer exists.
@@ -430,15 +436,28 @@ static int simplefb_probe(struct platform_device *pdev)
if (ret)
return ret;
- mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (!mem) {
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!res) {
dev_err(&pdev->dev, "No memory resource\n");
return -EINVAL;
}
+ mem = request_mem_region(res->start, resource_size(res), "simplefb");
+ if (!mem) {
+ /*
+ * We cannot make this fatal. Sometimes this comes from magic
+ * spaces our resource handlers simply don't know about. Use
+ * the I/O-memory resource as-is and try to map that instead.
+ */
+ dev_warn(&pdev->dev, "simplefb: cannot reserve video memory at %pR\n", res);
+ mem = res;
+ }
+
info = framebuffer_alloc(sizeof(struct simplefb_par), &pdev->dev);
- if (!info)
- return -ENOMEM;
+ if (!info) {
+ ret = -ENOMEM;
+ goto error_release_mem_region;
+ }
platform_set_drvdata(pdev, info);
par = info->par;
@@ -495,6 +514,9 @@ static int simplefb_probe(struct platform_device *pdev)
info->var.xres, info->var.yres,
info->var.bits_per_pixel, info->fix.line_length);
+ if (mem != res)
+ par->mem = mem; /* release in clean-up handler */
+
ret = register_framebuffer(info);
if (ret < 0) {
dev_err(&pdev->dev, "Unable to register simplefb: %d\n", ret);
@@ -513,6 +535,9 @@ static int simplefb_probe(struct platform_device *pdev)
iounmap(info->screen_base);
error_fb_release:
framebuffer_release(info);
+error_release_mem_region:
+ if (mem != res)
+ release_mem_region(mem->start, resource_size(mem));
return ret;
}

81
debian/patches/pve/0013-NFSv4.1-provide-mount-option-to-toggle-trunking-disc.patch vendored Normal file
View file

@ -0,0 +1,81 @@
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Olga Kornievskaia <kolga@netapp.com>
Date: Wed, 16 Mar 2022 18:24:26 -0400
Subject: [PATCH] NFSv4.1 provide mount option to toggle trunking discovery
Introduce a new mount option -- trunkdiscovery,notrunkdiscovery -- to
toggle whether or not the client will engage in actively discovery
of trunking locations.
v2 make notrunkdiscovery default
Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
Fixes: 1976b2b31462 ("NFSv4.1 query for fs_location attr on a new file system")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
(cherry picked from commit a43bf604446414103b7535f38e739b65601c4fb2)
Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
---
fs/nfs/client.c | 3 ++-
fs/nfs/fs_context.c | 8 ++++++++
include/linux/nfs_fs_sb.h | 1 +
3 files changed, 11 insertions(+), 1 deletion(-)
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 090b16890e3d..f303e96ce165 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -861,7 +861,8 @@ int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *mntfh, struct nfs
}
if (clp->rpc_ops->discover_trunking != NULL &&
- (server->caps & NFS_CAP_FS_LOCATIONS)) {
+ (server->caps & NFS_CAP_FS_LOCATIONS &&
+ (server->flags & NFS_MOUNT_TRUNK_DISCOVERY))) {
error = clp->rpc_ops->discover_trunking(server, mntfh);
if (error < 0)
return error;
diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c
index 0d444a90f513..da5217abc2e5 100644
--- a/fs/nfs/fs_context.c
+++ b/fs/nfs/fs_context.c
@@ -79,6 +79,7 @@ enum nfs_param {
Opt_source,
Opt_tcp,
Opt_timeo,
+ Opt_trunkdiscovery,
Opt_udp,
Opt_v,
Opt_vers,
@@ -179,6 +180,7 @@ static const struct fs_parameter_spec nfs_fs_parameters[] = {
fsparam_string("source", Opt_source),
fsparam_flag ("tcp", Opt_tcp),
fsparam_u32 ("timeo", Opt_timeo),
+ fsparam_flag_no("trunkdiscovery", Opt_trunkdiscovery),
fsparam_flag ("udp", Opt_udp),
fsparam_flag ("v2", Opt_v),
fsparam_flag ("v3", Opt_v),
@@ -528,6 +530,12 @@ static int nfs_fs_context_parse_param(struct fs_context *fc,
else
ctx->flags &= ~NFS_MOUNT_NOCTO;
break;
+ case Opt_trunkdiscovery:
+ if (result.negated)
+ ctx->flags &= ~NFS_MOUNT_TRUNK_DISCOVERY;
+ else
+ ctx->flags |= NFS_MOUNT_TRUNK_DISCOVERY;
+ break;
case Opt_ac:
if (result.negated)
ctx->flags |= NFS_MOUNT_NOAC;
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 9a6e70ccde56..10c347416dd2 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -156,6 +156,7 @@ struct nfs_server {
#define NFS_MOUNT_SOFTREVAL 0x800000
#define NFS_MOUNT_WRITE_EAGER 0x01000000
#define NFS_MOUNT_WRITE_WAIT 0x02000000
+#define NFS_MOUNT_TRUNK_DISCOVERY 0x04000000
unsigned int fattr_valid; /* Valid attributes */
unsigned int caps; /* server capabilities */

69
debian/patches/pve/0014-EDAC-amd64-Add-PCI-device-IDs-for-family-19h-model-5.patch vendored Normal file
View file

@ -0,0 +1,69 @@
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Marc Bevand <m@zorinaq.com>
Date: Tue, 21 Dec 2021 15:31:12 -0800
Subject: [PATCH] EDAC/amd64: Add PCI device IDs for family 19h model 50h
Add the new family 19h model 50h PCI IDs (device 18h functions 0 and 6)
to support Ryzen 5000 APUs ("Cezanne").
Signed-off-by: Marc Bevand <m@zorinaq.com>
Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
---
drivers/edac/amd64_edac.c | 15 +++++++++++++++
drivers/edac/amd64_edac.h | 3 +++
2 files changed, 18 insertions(+)
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index c6c58f01067f..f8ef2edf8abf 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -2660,6 +2660,16 @@ static struct amd64_family_type family_types[] = {
.dbam_to_cs = f17_addr_mask_to_cs_size,
}
},
+ [F19_M50H_CPUS] = {
+ .ctl_name = "F19h_M50h",
+ .f0_id = PCI_DEVICE_ID_AMD_19H_M50H_DF_F0,
+ .f6_id = PCI_DEVICE_ID_AMD_19H_M50H_DF_F6,
+ .max_mcs = 2,
+ .ops = {
+ .early_channel_count = f17_early_channel_count,
+ .dbam_to_cs = f17_addr_mask_to_cs_size,
+ }
+ },
};
/*
@@ -3706,6 +3716,11 @@ static struct amd64_family_type *per_family_init(struct amd64_pvt *pvt)
pvt->ops = &family_types[F17_M70H_CPUS].ops;
fam_type->ctl_name = "F19h_M20h";
break;
+ } else if (pvt->model >= 0x50 && pvt->model <= 0x5f) {
+ fam_type = &family_types[F19_M50H_CPUS];
+ pvt->ops = &family_types[F19_M50H_CPUS].ops;
+ fam_type->ctl_name = "F19h_M50h";
+ break;
} else if (pvt->model >= 0xa0 && pvt->model <= 0xaf) {
fam_type = &family_types[F19_M10H_CPUS];
pvt->ops = &family_types[F19_M10H_CPUS].ops;
diff --git a/drivers/edac/amd64_edac.h b/drivers/edac/amd64_edac.h
index 650cab401e21..352bda9803f6 100644
--- a/drivers/edac/amd64_edac.h
+++ b/drivers/edac/amd64_edac.h
@@ -128,6 +128,8 @@
#define PCI_DEVICE_ID_AMD_19H_DF_F6 0x1656
#define PCI_DEVICE_ID_AMD_19H_M10H_DF_F0 0x14ad
#define PCI_DEVICE_ID_AMD_19H_M10H_DF_F6 0x14b3
+#define PCI_DEVICE_ID_AMD_19H_M50H_DF_F0 0x166a
+#define PCI_DEVICE_ID_AMD_19H_M50H_DF_F6 0x1670
/*
* Function 1 - Address Map
@@ -301,6 +303,7 @@ enum amd_families {
F17_M70H_CPUS,
F19_CPUS,
F19_M10H_CPUS,
+ F19_M50H_CPUS,
NUM_FAMILIES,
};

53
debian/patches/pve/0015-bug-introduce-ASSERT_STRUCT_OFFSET.patch vendored Normal file
View file

@ -0,0 +1,53 @@
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Maxim Levitsky <mlevitsk@redhat.com>
Date: Wed, 3 Aug 2022 18:49:59 +0300
Subject: [PATCH] bug: introduce ASSERT_STRUCT_OFFSET
ASSERT_STRUCT_OFFSET allows to assert during the build of
the kernel that a field in a struct have an expected offset.
KVM used to have such macro, but there is almost nothing KVM specific
in it so move it to build_bug.h, so that it can be used in other
places in KVM.
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
---
arch/x86/kvm/vmx/vmcs12.h | 5 ++---
include/linux/build_bug.h | 9 +++++++++
2 files changed, 11 insertions(+), 3 deletions(-)
diff --git a/arch/x86/kvm/vmx/vmcs12.h b/arch/x86/kvm/vmx/vmcs12.h
index 2a45f026ee11..ba8617964982 100644
--- a/arch/x86/kvm/vmx/vmcs12.h
+++ b/arch/x86/kvm/vmx/vmcs12.h
@@ -208,9 +208,8 @@ struct __packed vmcs12 {
/*
* For save/restore compatibility, the vmcs12 field offsets must not change.
*/
-#define CHECK_OFFSET(field, loc) \
- BUILD_BUG_ON_MSG(offsetof(struct vmcs12, field) != (loc), \
- "Offset of " #field " in struct vmcs12 has changed.")
+#define CHECK_OFFSET(field, loc) \
+ ASSERT_STRUCT_OFFSET(struct vmcs12, field, loc)
static inline void vmx_check_vmcs12_offsets(void)
{
diff --git a/include/linux/build_bug.h b/include/linux/build_bug.h
index e3a0be2c90ad..3aa3640f8c18 100644
--- a/include/linux/build_bug.h
+++ b/include/linux/build_bug.h
@@ -77,4 +77,13 @@
#define static_assert(expr, ...) __static_assert(expr, ##__VA_ARGS__, #expr)
#define __static_assert(expr, msg, ...) _Static_assert(expr, msg)
+
+/*
+ * Compile time check that field has an expected offset
+ */
+#define ASSERT_STRUCT_OFFSET(type, field, expected_offset) \
+ BUILD_BUG_ON_MSG(offsetof(type, field) != (expected_offset), \
+ "Offset of " #field " in " #type " has changed.")
+
+
#endif /* _LINUX_BUILD_BUG_H */

31
debian/patches/pve/0016-KVM-x86-emulator-em_sysexit-should-update-ctxt-mode.patch vendored Normal file
View file

@ -0,0 +1,31 @@
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Maxim Levitsky <mlevitsk@redhat.com>
Date: Wed, 3 Aug 2022 18:50:00 +0300
Subject: [PATCH] KVM: x86: emulator: em_sysexit should update ctxt->mode
This is one of the instructions that can change the
processor mode.
Note that this is likely a benign bug, because the only problematic
mode change is from 32 bit to 64 bit which can lead to truncation of RIP,
and it is not possible to do with sysexit,
since sysexit running in 32 bit mode will be limited to 32 bit version.
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
---
arch/x86/kvm/emulate.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 318a78379ca6..35b12692739c 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2862,6 +2862,7 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt)
ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS);
ctxt->_eip = rdx;
+ ctxt->mode = usermode;
*reg_write(ctxt, VCPU_REGS_RSP) = rcx;
return X86EMUL_CONTINUE;

158
debian/patches/pve/0017-KVM-x86-emulator-introduce-emulator_recalc_and_set_m.patch vendored Normal file
View file

@ -0,0 +1,158 @@
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Maxim Levitsky <mlevitsk@redhat.com>
Date: Wed, 3 Aug 2022 18:50:01 +0300
Subject: [PATCH] KVM: x86: emulator: introduce emulator_recalc_and_set_mode
Some instructions update the cpu execution mode, which needs
to update the emulation mode.
Extract this code, and make assign_eip_far use it.
assign_eip_far now reads CS, instead of getting it via a parameter,
which is ok, because callers always assign CS to the
same value before calling it.
No functional change is intended.
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
---
arch/x86/kvm/emulate.c | 85 ++++++++++++++++++++++++++++--------------
1 file changed, 57 insertions(+), 28 deletions(-)
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 35b12692739c..6a597d68d456 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -795,8 +795,7 @@ static int linearize(struct x86_emulate_ctxt *ctxt,
ctxt->mode, linear);
}
-static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst,
- enum x86emul_mode mode)
+static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst)
{
ulong linear;
int rc;
@@ -806,41 +805,71 @@ static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst,
if (ctxt->op_bytes != sizeof(unsigned long))
addr.ea = dst & ((1UL << (ctxt->op_bytes << 3)) - 1);
- rc = __linearize(ctxt, addr, &max_size, 1, false, true, mode, &linear);
+ rc = __linearize(ctxt, addr, &max_size, 1, false, true, ctxt->mode, &linear);
if (rc == X86EMUL_CONTINUE)
ctxt->_eip = addr.ea;
return rc;
}
+static inline int emulator_recalc_and_set_mode(struct x86_emulate_ctxt *ctxt)
+{
+ u64 efer;
+ struct desc_struct cs;
+ u16 selector;
+ u32 base3;
+
+ ctxt->ops->get_msr(ctxt, MSR_EFER, &efer);
+
+ if (!ctxt->ops->get_cr(ctxt, 0) & X86_CR0_PE) {
+ /* Real mode. cpu must not have long mode active */
+ if (efer & EFER_LMA)
+ return X86EMUL_UNHANDLEABLE;
+ ctxt->mode = X86EMUL_MODE_REAL;
+ return X86EMUL_CONTINUE;
+ }
+
+ if (ctxt->eflags & X86_EFLAGS_VM) {
+ /* Protected/VM86 mode. cpu must not have long mode active */
+ if (efer & EFER_LMA)
+ return X86EMUL_UNHANDLEABLE;
+ ctxt->mode = X86EMUL_MODE_VM86;
+ return X86EMUL_CONTINUE;
+ }
+
+ if (!ctxt->ops->get_segment(ctxt, &selector, &cs, &base3, VCPU_SREG_CS))
+ return X86EMUL_UNHANDLEABLE;
+
+ if (efer & EFER_LMA) {
+ if (cs.l) {
+ /* Proper long mode */
+ ctxt->mode = X86EMUL_MODE_PROT64;
+ } else if (cs.d) {
+ /* 32 bit compatibility mode*/
+ ctxt->mode = X86EMUL_MODE_PROT32;
+ } else {
+ ctxt->mode = X86EMUL_MODE_PROT16;
+ }
+ } else {
+ /* Legacy 32 bit / 16 bit mode */
+ ctxt->mode = cs.d ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16;
+ }
+
+ return X86EMUL_CONTINUE;
+}
+
static inline int assign_eip_near(struct x86_emulate_ctxt *ctxt, ulong dst)
{
- return assign_eip(ctxt, dst, ctxt->mode);
+ return assign_eip(ctxt, dst);
}
-static int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst,
- const struct desc_struct *cs_desc)
+static int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst)
{
- enum x86emul_mode mode = ctxt->mode;
- int rc;
+ int rc = emulator_recalc_and_set_mode(ctxt);
-#ifdef CONFIG_X86_64
- if (ctxt->mode >= X86EMUL_MODE_PROT16) {
- if (cs_desc->l) {
- u64 efer = 0;
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
- ctxt->ops->get_msr(ctxt, MSR_EFER, &efer);
- if (efer & EFER_LMA)
- mode = X86EMUL_MODE_PROT64;
- } else
- mode = X86EMUL_MODE_PROT32; /* temporary value */
- }
-#endif
- if (mode == X86EMUL_MODE_PROT16 || mode == X86EMUL_MODE_PROT32)
- mode = cs_desc->d ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16;
- rc = assign_eip(ctxt, dst, mode);
- if (rc == X86EMUL_CONTINUE)
- ctxt->mode = mode;
- return rc;
+ return assign_eip(ctxt, dst);
}
static inline int jmp_rel(struct x86_emulate_ctxt *ctxt, int rel)
@@ -2154,7 +2183,7 @@ static int em_jmp_far(struct x86_emulate_ctxt *ctxt)
if (rc != X86EMUL_CONTINUE)
return rc;
- rc = assign_eip_far(ctxt, ctxt->src.val, &new_desc);
+ rc = assign_eip_far(ctxt, ctxt->src.val);
/* Error handling is not implemented. */
if (rc != X86EMUL_CONTINUE)
return X86EMUL_UNHANDLEABLE;
@@ -2235,7 +2264,7 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt)
&new_desc);
if (rc != X86EMUL_CONTINUE)
return rc;
- rc = assign_eip_far(ctxt, eip, &new_desc);
+ rc = assign_eip_far(ctxt, eip);
/* Error handling is not implemented. */
if (rc != X86EMUL_CONTINUE)
return X86EMUL_UNHANDLEABLE;
@@ -3459,7 +3488,7 @@ static int em_call_far(struct x86_emulate_ctxt *ctxt)
if (rc != X86EMUL_CONTINUE)
return rc;
- rc = assign_eip_far(ctxt, ctxt->src.val, &new_desc);
+ rc = assign_eip_far(ctxt, ctxt->src.val);
if (rc != X86EMUL_CONTINUE)
goto fail;

34
debian/patches/pve/0018-KVM-x86-emulator-update-the-emulation-mode-after-rsm.patch vendored Normal file
View file

@ -0,0 +1,34 @@
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Maxim Levitsky <mlevitsk@redhat.com>
Date: Wed, 3 Aug 2022 18:50:02 +0300
Subject: [PATCH] KVM: x86: emulator: update the emulation mode after rsm
This ensures that RIP will be correctly written back,
because the RSM instruction can switch the CPU mode from
32 bit (or less) to 64 bit.
This fixes a guest crash in case the #SMI is received
while the guest runs a code from an address > 32 bit.
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
---
arch/x86/kvm/emulate.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 6a597d68d456..49697d589f87 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2639,6 +2639,11 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt)
if (ret != X86EMUL_CONTINUE)
goto emulate_shutdown;
+
+ ret = emulator_recalc_and_set_mode(ctxt);
+ if (ret != X86EMUL_CONTINUE)
+ goto emulate_shutdown;
+
/*
* Note, the ctxt->ops callbacks are responsible for handling side
* effects when writing MSRs and CRs, e.g. MMU context resets, CPUID

49
debian/patches/pve/0019-KVM-x86-emulator-update-the-emulation-mode-after-CR0.patch vendored Normal file
View file

@ -0,0 +1,49 @@
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Maxim Levitsky <mlevitsk@redhat.com>
Date: Wed, 3 Aug 2022 18:50:03 +0300
Subject: [PATCH] KVM: x86: emulator: update the emulation mode after CR0 write
CR0.PE toggles real/protected mode, thus its update
should update the emulation mode.
This is likely a benign bug because there is no writeback
of state, other than the RIP increment, and when toggling
CR0.PE, the CPU has to execute code from a very low memory address.
Also CR0.PG toggle when EFER.LMA is set, toggles the long mode.
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
---
arch/x86/kvm/emulate.c | 14 +++++++++++++-
1 file changed, 13 insertions(+), 1 deletion(-)
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 49697d589f87..89f035fc52e7 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -3635,11 +3635,23 @@ static int em_movbe(struct x86_emulate_ctxt *ctxt)
static int em_cr_write(struct x86_emulate_ctxt *ctxt)
{
- if (ctxt->ops->set_cr(ctxt, ctxt->modrm_reg, ctxt->src.val))
+ int cr_num = ctxt->modrm_reg;
+ int r;
+
+ if (ctxt->ops->set_cr(ctxt, cr_num, ctxt->src.val))
return emulate_gp(ctxt, 0);
/* Disable writeback. */
ctxt->dst.type = OP_NONE;
+
+ if (cr_num == 0) {
+ /* CR0 write might have updated CR0.PE and/or CR0.PG
+ * which can affect the cpu execution mode */
+ r = emulator_recalc_and_set_mode(ctxt);
+ if (r != X86EMUL_CONTINUE)
+ return r;
+ }
+
return X86EMUL_CONTINUE;
}

280
debian/patches/pve/0020-KVM-x86-emulator-smm-add-structs-for-KVM-s-smram-lay.patch vendored Normal file
View file

@ -0,0 +1,280 @@
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Maxim Levitsky <mlevitsk@redhat.com>
Date: Wed, 3 Aug 2022 18:50:05 +0300
Subject: [PATCH] KVM: x86: emulator/smm: add structs for KVM's smram layout
Those structs will be used to read/write the smram state image.
Also document the differences between KVM's SMRAM layout and SMRAM
layout that is used by real Intel/AMD cpus.
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
---
arch/x86/kvm/emulate.c | 6 +
arch/x86/kvm/kvm_emulate.h | 218 +++++++++++++++++++++++++++++++++++++
arch/x86/kvm/x86.c | 1 +
3 files changed, 225 insertions(+)
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 89f035fc52e7..bfaf5d24bf1e 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -5825,3 +5825,9 @@ bool emulator_can_use_gpa(struct x86_emulate_ctxt *ctxt)
return true;
}
+
+void __init kvm_emulator_init(void)
+{
+ __check_smram32_offsets();
+ __check_smram64_offsets();
+}
diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h
index fb09cd22cb7f..0b2bbcce321a 100644
--- a/arch/x86/kvm/kvm_emulate.h
+++ b/arch/x86/kvm/kvm_emulate.h
@@ -13,6 +13,7 @@
#define _ASM_X86_KVM_X86_EMULATE_H
#include <asm/desc_defs.h>
+#include <linux/build_bug.h>
#include "fpu.h"
struct x86_emulate_ctxt;
@@ -482,6 +483,223 @@ enum x86_intercept {
nr_x86_intercepts
};
+
+/* 32 bit KVM's emulated SMM layout. Loosely based on Intel's layout */
+
+struct kvm_smm_seg_state_32 {
+ u32 flags;
+ u32 limit;
+ u32 base;
+} __packed;
+
+struct kvm_smram_state_32 {
+ u32 reserved1[62];
+ u32 smbase;
+ u32 smm_revision;
+ u32 reserved2[5];
+ u32 cr4; /* CR4 is not present in Intel/AMD SMRAM image */
+ u32 reserved3[5];
+
+ /*
+ * Segment state is not present/documented in the Intel/AMD SMRAM image
+ * Instead this area on Intel/AMD contains IO/HLT restart flags.
+ */
+ struct kvm_smm_seg_state_32 ds;
+ struct kvm_smm_seg_state_32 fs;
+ struct kvm_smm_seg_state_32 gs;
+ struct kvm_smm_seg_state_32 idtr; /* IDTR has only base and limit */
+ struct kvm_smm_seg_state_32 tr;
+ u32 reserved;
+ struct kvm_smm_seg_state_32 gdtr; /* GDTR has only base and limit */
+ struct kvm_smm_seg_state_32 ldtr;
+ struct kvm_smm_seg_state_32 es;
+ struct kvm_smm_seg_state_32 cs;
+ struct kvm_smm_seg_state_32 ss;
+
+ u32 es_sel;
+ u32 cs_sel;
+ u32 ss_sel;
+ u32 ds_sel;
+ u32 fs_sel;
+ u32 gs_sel;
+ u32 ldtr_sel;
+ u32 tr_sel;
+
+ u32 dr7;
+ u32 dr6;
+ u32 gprs[8]; /* GPRS in the "natural" X86 order (EAX/ECX/EDX.../EDI) */
+ u32 eip;
+ u32 eflags;
+ u32 cr3;
+ u32 cr0;
+} __packed;
+
+
+static inline void __check_smram32_offsets(void)
+{
+#define __CHECK_SMRAM32_OFFSET(field, offset) \
+ ASSERT_STRUCT_OFFSET(struct kvm_smram_state_32, field, offset - 0xFE00)
+
+ __CHECK_SMRAM32_OFFSET(reserved1, 0xFE00);
+ __CHECK_SMRAM32_OFFSET(smbase, 0xFEF8);
+ __CHECK_SMRAM32_OFFSET(smm_revision, 0xFEFC);
+ __CHECK_SMRAM32_OFFSET(reserved2, 0xFF00);
+ __CHECK_SMRAM32_OFFSET(cr4, 0xFF14);
+ __CHECK_SMRAM32_OFFSET(reserved3, 0xFF18);
+ __CHECK_SMRAM32_OFFSET(ds, 0xFF2C);
+ __CHECK_SMRAM32_OFFSET(fs, 0xFF38);
+ __CHECK_SMRAM32_OFFSET(gs, 0xFF44);
+ __CHECK_SMRAM32_OFFSET(idtr, 0xFF50);
+ __CHECK_SMRAM32_OFFSET(tr, 0xFF5C);
+ __CHECK_SMRAM32_OFFSET(gdtr, 0xFF6C);
+ __CHECK_SMRAM32_OFFSET(ldtr, 0xFF78);
+ __CHECK_SMRAM32_OFFSET(es, 0xFF84);
+ __CHECK_SMRAM32_OFFSET(cs, 0xFF90);
+ __CHECK_SMRAM32_OFFSET(ss, 0xFF9C);
+ __CHECK_SMRAM32_OFFSET(es_sel, 0xFFA8);
+ __CHECK_SMRAM32_OFFSET(cs_sel, 0xFFAC);
+ __CHECK_SMRAM32_OFFSET(ss_sel, 0xFFB0);
+ __CHECK_SMRAM32_OFFSET(ds_sel, 0xFFB4);
+ __CHECK_SMRAM32_OFFSET(fs_sel, 0xFFB8);
+ __CHECK_SMRAM32_OFFSET(gs_sel, 0xFFBC);
+ __CHECK_SMRAM32_OFFSET(ldtr_sel, 0xFFC0);
+ __CHECK_SMRAM32_OFFSET(tr_sel, 0xFFC4);
+ __CHECK_SMRAM32_OFFSET(dr7, 0xFFC8);
+ __CHECK_SMRAM32_OFFSET(dr6, 0xFFCC);
+ __CHECK_SMRAM32_OFFSET(gprs, 0xFFD0);
+ __CHECK_SMRAM32_OFFSET(eip, 0xFFF0);
+ __CHECK_SMRAM32_OFFSET(eflags, 0xFFF4);
+ __CHECK_SMRAM32_OFFSET(cr3, 0xFFF8);
+ __CHECK_SMRAM32_OFFSET(cr0, 0xFFFC);
+#undef __CHECK_SMRAM32_OFFSET
+}
+
+
+/* 64 bit KVM's emulated SMM layout. Based on AMD64 layout */
+
+struct kvm_smm_seg_state_64 {
+ u16 selector;
+ u16 attributes;
+ u32 limit;
+ u64 base;
+};
+
+struct kvm_smram_state_64 {
+
+ struct kvm_smm_seg_state_64 es;
+ struct kvm_smm_seg_state_64 cs;
+ struct kvm_smm_seg_state_64 ss;
+ struct kvm_smm_seg_state_64 ds;
+ struct kvm_smm_seg_state_64 fs;
+ struct kvm_smm_seg_state_64 gs;
+ struct kvm_smm_seg_state_64 gdtr; /* GDTR has only base and limit*/
+ struct kvm_smm_seg_state_64 ldtr;
+ struct kvm_smm_seg_state_64 idtr; /* IDTR has only base and limit*/
+ struct kvm_smm_seg_state_64 tr;
+
+ /* I/O restart and auto halt restart are not implemented by KVM */
+ u64 io_restart_rip;
+ u64 io_restart_rcx;
+ u64 io_restart_rsi;
+ u64 io_restart_rdi;
+ u32 io_restart_dword;
+ u32 reserved1;
+ u8 io_inst_restart;
+ u8 auto_hlt_restart;
+ u8 reserved2[6];
+
+ u64 efer;
+
+ /*
+ * Two fields below are implemented on AMD only, to store
+ * SVM guest vmcb address if the #SMI was received while in the guest mode.
+ */
+ u64 svm_guest_flag;
+ u64 svm_guest_vmcb_gpa;
+ u64 svm_guest_virtual_int; /* unknown purpose, not implemented */
+
+ u32 reserved3[3];
+ u32 smm_revison;
+ u32 smbase;
+ u32 reserved4[5];
+
+ /* ssp and svm_* fields below are not implemented by KVM */
+ u64 ssp;
+ u64 svm_guest_pat;
+ u64 svm_host_efer;
+ u64 svm_host_cr4;
+ u64 svm_host_cr3;
+ u64 svm_host_cr0;
+
+ u64 cr4;
+ u64 cr3;
+ u64 cr0;
+ u64 dr7;
+ u64 dr6;
+ u64 rflags;
+ u64 rip;
+ u64 gprs[16]; /* GPRS in a reversed "natural" X86 order (R15/R14/../RCX/RAX.) */
+};
+
+
+static inline void __check_smram64_offsets(void)
+{
+#define __CHECK_SMRAM64_OFFSET(field, offset) \
+ ASSERT_STRUCT_OFFSET(struct kvm_smram_state_64, field, offset - 0xFE00)
+
+ __CHECK_SMRAM64_OFFSET(es, 0xFE00);
+ __CHECK_SMRAM64_OFFSET(cs, 0xFE10);
+ __CHECK_SMRAM64_OFFSET(ss, 0xFE20);
+ __CHECK_SMRAM64_OFFSET(ds, 0xFE30);
+ __CHECK_SMRAM64_OFFSET(fs, 0xFE40);
+ __CHECK_SMRAM64_OFFSET(gs, 0xFE50);
+ __CHECK_SMRAM64_OFFSET(gdtr, 0xFE60);
+ __CHECK_SMRAM64_OFFSET(ldtr, 0xFE70);
+ __CHECK_SMRAM64_OFFSET(idtr, 0xFE80);
+ __CHECK_SMRAM64_OFFSET(tr, 0xFE90);
+ __CHECK_SMRAM64_OFFSET(io_restart_rip, 0xFEA0);
+ __CHECK_SMRAM64_OFFSET(io_restart_rcx, 0xFEA8);
+ __CHECK_SMRAM64_OFFSET(io_restart_rsi, 0xFEB0);
+ __CHECK_SMRAM64_OFFSET(io_restart_rdi, 0xFEB8);
+ __CHECK_SMRAM64_OFFSET(io_restart_dword, 0xFEC0);
+ __CHECK_SMRAM64_OFFSET(reserved1, 0xFEC4);
+ __CHECK_SMRAM64_OFFSET(io_inst_restart, 0xFEC8);
+ __CHECK_SMRAM64_OFFSET(auto_hlt_restart, 0xFEC9);
+ __CHECK_SMRAM64_OFFSET(reserved2, 0xFECA);
+ __CHECK_SMRAM64_OFFSET(efer, 0xFED0);
+ __CHECK_SMRAM64_OFFSET(svm_guest_flag, 0xFED8);
+ __CHECK_SMRAM64_OFFSET(svm_guest_vmcb_gpa, 0xFEE0);
+ __CHECK_SMRAM64_OFFSET(svm_guest_virtual_int, 0xFEE8);
+ __CHECK_SMRAM64_OFFSET(reserved3, 0xFEF0);
+ __CHECK_SMRAM64_OFFSET(smm_revison, 0xFEFC);
+ __CHECK_SMRAM64_OFFSET(smbase, 0xFF00);
+ __CHECK_SMRAM64_OFFSET(reserved4, 0xFF04);
+ __CHECK_SMRAM64_OFFSET(ssp, 0xFF18);
+ __CHECK_SMRAM64_OFFSET(svm_guest_pat, 0xFF20);
+ __CHECK_SMRAM64_OFFSET(svm_host_efer, 0xFF28);
+ __CHECK_SMRAM64_OFFSET(svm_host_cr4, 0xFF30);
+ __CHECK_SMRAM64_OFFSET(svm_host_cr3, 0xFF38);
+ __CHECK_SMRAM64_OFFSET(svm_host_cr0, 0xFF40);
+ __CHECK_SMRAM64_OFFSET(cr4, 0xFF48);
+ __CHECK_SMRAM64_OFFSET(cr3, 0xFF50);
+ __CHECK_SMRAM64_OFFSET(cr0, 0xFF58);
+ __CHECK_SMRAM64_OFFSET(dr7, 0xFF60);
+ __CHECK_SMRAM64_OFFSET(dr6, 0xFF68);
+ __CHECK_SMRAM64_OFFSET(rflags, 0xFF70);
+ __CHECK_SMRAM64_OFFSET(rip, 0xFF78);
+ __CHECK_SMRAM64_OFFSET(gprs, 0xFF80);
+#undef __CHECK_SMRAM64_OFFSET
+}
+
+union kvm_smram {
+ struct kvm_smram_state_64 smram64;
+ struct kvm_smram_state_32 smram32;
+ u8 bytes[512];
+};
+
+void __init kvm_emulator_init(void);
+
+
/* Host execution mode. */
#if defined(CONFIG_X86_32)
#define X86EMUL_MODE_HOST X86EMUL_MODE_PROT32
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 922fc258c37f..07575e5eb254 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -12442,6 +12442,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_exit);
static int __init kvm_x86_init(void)
{
kvm_mmu_x86_module_init();
+ kvm_emulator_init();
return 0;
}
module_init(kvm_x86_init);

214
debian/patches/pve/0021-KVM-x86-emulator-smm-use-smram-structs-in-the-common.patch vendored Normal file
View file

@ -0,0 +1,214 @@
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Maxim Levitsky <mlevitsk@redhat.com>
Date: Wed, 3 Aug 2022 18:50:06 +0300
Subject: [PATCH] KVM: x86: emulator/smm: use smram structs in the common code
Switch from using a raw array to 'union kvm_smram'.
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
---
arch/x86/include/asm/kvm_host.h | 5 +++--
arch/x86/kvm/emulate.c | 12 +++++++-----
arch/x86/kvm/kvm_emulate.h | 3 ++-
arch/x86/kvm/svm/svm.c | 8 ++++++--
arch/x86/kvm/vmx/vmx.c | 4 ++--
arch/x86/kvm/x86.c | 16 ++++++++--------
6 files changed, 28 insertions(+), 20 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 867febee8fc3..fb48dd8773e1 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -200,6 +200,7 @@ typedef enum exit_fastpath_completion fastpath_t;
struct x86_emulate_ctxt;
struct x86_exception;
+union kvm_smram;
enum x86_intercept;
enum x86_intercept_stage;
@@ -1463,8 +1464,8 @@ struct kvm_x86_ops {
void (*setup_mce)(struct kvm_vcpu *vcpu);
int (*smi_allowed)(struct kvm_vcpu *vcpu, bool for_injection);
- int (*enter_smm)(struct kvm_vcpu *vcpu, char *smstate);
- int (*leave_smm)(struct kvm_vcpu *vcpu, const char *smstate);
+ int (*enter_smm)(struct kvm_vcpu *vcpu, union kvm_smram *smram);
+ int (*leave_smm)(struct kvm_vcpu *vcpu, const union kvm_smram *smram);
void (*enable_smi_window)(struct kvm_vcpu *vcpu);
int (*mem_enc_op)(struct kvm *kvm, void __user *argp);
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index bfaf5d24bf1e..730c3e2662d6 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2567,16 +2567,18 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt,
static int em_rsm(struct x86_emulate_ctxt *ctxt)
{
unsigned long cr0, cr4, efer;
- char buf[512];
+ const union kvm_smram smram;
u64 smbase;
int ret;
+ BUILD_BUG_ON(sizeof(smram) != 512);
+
if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_MASK) == 0)
return emulate_ud(ctxt);
smbase = ctxt->ops->get_smbase(ctxt);
- ret = ctxt->ops->read_phys(ctxt, smbase + 0xfe00, buf, sizeof(buf));
+ ret = ctxt->ops->read_phys(ctxt, smbase + 0xfe00, (void *)&smram, sizeof(smram));
if (ret != X86EMUL_CONTINUE)
return X86EMUL_UNHANDLEABLE;
@@ -2626,15 +2628,15 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt)
* state (e.g. enter guest mode) before loading state from the SMM
* state-save area.
*/
- if (ctxt->ops->leave_smm(ctxt, buf))
+ if (ctxt->ops->leave_smm(ctxt, &smram))
goto emulate_shutdown;
#ifdef CONFIG_X86_64
if (emulator_has_longmode(ctxt))
- ret = rsm_load_state_64(ctxt, buf);
+ ret = rsm_load_state_64(ctxt, (const char *)&smram);
else
#endif
- ret = rsm_load_state_32(ctxt, buf);
+ ret = rsm_load_state_32(ctxt, (const char *)&smram);
if (ret != X86EMUL_CONTINUE)
goto emulate_shutdown;
diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h
index 0b2bbcce321a..3b37b3e17379 100644
--- a/arch/x86/kvm/kvm_emulate.h
+++ b/arch/x86/kvm/kvm_emulate.h
@@ -19,6 +19,7 @@
struct x86_emulate_ctxt;
enum x86_intercept;
enum x86_intercept_stage;
+union kvm_smram;
struct x86_exception {
u8 vector;
@@ -233,7 +234,7 @@ struct x86_emulate_ops {
unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt);
void (*exiting_smm)(struct x86_emulate_ctxt *ctxt);
- int (*leave_smm)(struct x86_emulate_ctxt *ctxt, const char *smstate);
+ int (*leave_smm)(struct x86_emulate_ctxt *ctxt, const union kvm_smram *smram);
void (*triple_fault)(struct x86_emulate_ctxt *ctxt);
int (*set_xcr)(struct x86_emulate_ctxt *ctxt, u32 index, u64 xcr);
};
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 21f747eacc9a..d903120811b9 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4302,12 +4302,14 @@ static int svm_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection)
return !svm_smi_blocked(vcpu);
}
-static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
+static int svm_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct kvm_host_map map_save;
int ret;
+ char *smstate = (char *)smram;
+
if (!is_guest_mode(vcpu))
return 0;
@@ -4349,7 +4351,7 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
return 0;
}
-static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
+static int svm_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct kvm_host_map map, map_save;
@@ -4357,6 +4359,8 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
struct vmcb *vmcb12;
int ret;
+ const char *smstate = (const char *)smram;
+
if (!guest_cpuid_has(vcpu, X86_FEATURE_LM))
return 0;
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 417176817d80..a45a43bcc844 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -7594,7 +7594,7 @@ static int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection)
return !is_smm(vcpu);
}
-static int vmx_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
+static int vmx_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -7608,7 +7608,7 @@ static int vmx_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
return 0;
}
-static int vmx_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
+static int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
int ret;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 07575e5eb254..2ebbb441880c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -7312,9 +7312,9 @@ static void emulator_exiting_smm(struct x86_emulate_ctxt *ctxt)
}
static int emulator_leave_smm(struct x86_emulate_ctxt *ctxt,
- const char *smstate)
+ const union kvm_smram *smram)
{
- return static_call(kvm_x86_leave_smm)(emul_to_vcpu(ctxt), smstate);
+ return static_call(kvm_x86_leave_smm)(emul_to_vcpu(ctxt), smram);
}
static void emulator_triple_fault(struct x86_emulate_ctxt *ctxt)
@@ -9164,25 +9164,25 @@ static void enter_smm(struct kvm_vcpu *vcpu)
struct kvm_segment cs, ds;
struct desc_ptr dt;
unsigned long cr0;
- char buf[512];
+ union kvm_smram smram;
- memset(buf, 0, 512);
+ memset(smram.bytes, 0, sizeof(smram.bytes));
#ifdef CONFIG_X86_64
if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
- enter_smm_save_state_64(vcpu, buf);
+ enter_smm_save_state_64(vcpu, (char *)&smram);
else
#endif
- enter_smm_save_state_32(vcpu, buf);
+ enter_smm_save_state_32(vcpu, (char *)&smram);
/*
* Give enter_smm() a chance to make ISA-specific changes to the vCPU
* state (e.g. leave guest mode) after we've saved the state into the
* SMM state-save area.
*/
- static_call(kvm_x86_enter_smm)(vcpu, buf);
+ static_call(kvm_x86_enter_smm)(vcpu, &smram);
kvm_smm_changed(vcpu, true);
- kvm_vcpu_write_guest(vcpu, vcpu->arch.smbase + 0xfe00, buf, sizeof(buf));
+ kvm_vcpu_write_guest(vcpu, vcpu->arch.smbase + 0xfe00, &smram, sizeof(smram));
if (static_call(kvm_x86_get_nmi_mask)(vcpu))
vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;

268
debian/patches/pve/0022-KVM-x86-emulator-smm-use-smram-struct-for-32-bit-smr.patch vendored Normal file
View file

@ -0,0 +1,268 @@
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Maxim Levitsky <mlevitsk@redhat.com>
Date: Wed, 3 Aug 2022 18:50:07 +0300
Subject: [PATCH] KVM: x86: emulator/smm: use smram struct for 32 bit smram
load/restore
Use kvm_smram_state_32 struct to save/restore 32 bit SMM state
(used when X86_FEATURE_LM is not present in the guest CPUID).
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
---
arch/x86/kvm/emulate.c | 81 +++++++++++++++---------------------------
arch/x86/kvm/x86.c | 75 +++++++++++++++++---------------------
2 files changed, 60 insertions(+), 96 deletions(-)
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 730c3e2662d6..ad5d2ab9ab84 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2344,25 +2344,17 @@ static void rsm_set_desc_flags(struct desc_struct *desc, u32 flags)
desc->type = (flags >> 8) & 15;
}
-static int rsm_load_seg_32(struct x86_emulate_ctxt *ctxt, const char *smstate,
+static void rsm_load_seg_32(struct x86_emulate_ctxt *ctxt,
+ const struct kvm_smm_seg_state_32 *state,
+ u16 selector,
int n)
{
struct desc_struct desc;
- int offset;
- u16 selector;
-
- selector = GET_SMSTATE(u32, smstate, 0x7fa8 + n * 4);
-
- if (n < 3)
- offset = 0x7f84 + n * 12;
- else
- offset = 0x7f2c + (n - 3) * 12;
- set_desc_base(&desc, GET_SMSTATE(u32, smstate, offset + 8));
- set_desc_limit(&desc, GET_SMSTATE(u32, smstate, offset + 4));
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, offset));
+ set_desc_base(&desc, state->base);
+ set_desc_limit(&desc, state->limit);
+ rsm_set_desc_flags(&desc, state->flags);
ctxt->ops->set_segment(ctxt, selector, &desc, 0, n);
- return X86EMUL_CONTINUE;
}
#ifdef CONFIG_X86_64
@@ -2433,63 +2425,46 @@ static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt,
}
static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt,
- const char *smstate)
+ const struct kvm_smram_state_32 *smstate)
{
- struct desc_struct desc;
struct desc_ptr dt;
- u16 selector;
- u32 val, cr0, cr3, cr4;
int i;
- cr0 = GET_SMSTATE(u32, smstate, 0x7ffc);
- cr3 = GET_SMSTATE(u32, smstate, 0x7ff8);
- ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7ff4) | X86_EFLAGS_FIXED;
- ctxt->_eip = GET_SMSTATE(u32, smstate, 0x7ff0);
+ ctxt->eflags = smstate->eflags | X86_EFLAGS_FIXED;
+ ctxt->_eip = smstate->eip;
for (i = 0; i < 8; i++)
- *reg_write(ctxt, i) = GET_SMSTATE(u32, smstate, 0x7fd0 + i * 4);
-
- val = GET_SMSTATE(u32, smstate, 0x7fcc);
+ *reg_write(ctxt, i) = smstate->gprs[i];
- if (ctxt->ops->set_dr(ctxt, 6, val))
+ if (ctxt->ops->set_dr(ctxt, 6, smstate->dr6))
return X86EMUL_UNHANDLEABLE;
-
- val = GET_SMSTATE(u32, smstate, 0x7fc8);
-
- if (ctxt->ops->set_dr(ctxt, 7, val))
+ if (ctxt->ops->set_dr(ctxt, 7, smstate->dr7))
return X86EMUL_UNHANDLEABLE;
- selector = GET_SMSTATE(u32, smstate, 0x7fc4);
- set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7f64));
- set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7f60));
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7f5c));
- ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_TR);
+ rsm_load_seg_32(ctxt, &smstate->tr, smstate->tr_sel, VCPU_SREG_TR);
+ rsm_load_seg_32(ctxt, &smstate->ldtr, smstate->ldtr_sel, VCPU_SREG_LDTR);
- selector = GET_SMSTATE(u32, smstate, 0x7fc0);
- set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7f80));
- set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7f7c));
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7f78));
- ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_LDTR);
- dt.address = GET_SMSTATE(u32, smstate, 0x7f74);
- dt.size = GET_SMSTATE(u32, smstate, 0x7f70);
+ dt.address = smstate->gdtr.base;
+ dt.size = smstate->gdtr.limit;
ctxt->ops->set_gdt(ctxt, &dt);
- dt.address = GET_SMSTATE(u32, smstate, 0x7f58);
- dt.size = GET_SMSTATE(u32, smstate, 0x7f54);
+ dt.address = smstate->idtr.base;
+ dt.size = smstate->idtr.limit;
ctxt->ops->set_idt(ctxt, &dt);
- for (i = 0; i < 6; i++) {
- int r = rsm_load_seg_32(ctxt, smstate, i);
- if (r != X86EMUL_CONTINUE)
- return r;
- }
+ rsm_load_seg_32(ctxt, &smstate->es, smstate->es_sel, VCPU_SREG_ES);
+ rsm_load_seg_32(ctxt, &smstate->cs, smstate->cs_sel, VCPU_SREG_CS);
+ rsm_load_seg_32(ctxt, &smstate->ss, smstate->ss_sel, VCPU_SREG_SS);
- cr4 = GET_SMSTATE(u32, smstate, 0x7f14);
+ rsm_load_seg_32(ctxt, &smstate->ds, smstate->ds_sel, VCPU_SREG_DS);
+ rsm_load_seg_32(ctxt, &smstate->fs, smstate->fs_sel, VCPU_SREG_FS);
+ rsm_load_seg_32(ctxt, &smstate->gs, smstate->gs_sel, VCPU_SREG_GS);
- ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7ef8));
+ ctxt->ops->set_smbase(ctxt, smstate->smbase);
- return rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
+ return rsm_enter_protected_mode(ctxt, smstate->cr0,
+ smstate->cr3, smstate->cr4);
}
#ifdef CONFIG_X86_64
@@ -2636,7 +2611,7 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt)
ret = rsm_load_state_64(ctxt, (const char *)&smram);
else
#endif
- ret = rsm_load_state_32(ctxt, (const char *)&smram);
+ ret = rsm_load_state_32(ctxt, &smram.smram32);
if (ret != X86EMUL_CONTINUE)
goto emulate_shutdown;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2ebbb441880c..8a6b9bffc770 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -9018,22 +9018,18 @@ static u32 enter_smm_get_segment_flags(struct kvm_segment *seg)
return flags;
}
-static void enter_smm_save_seg_32(struct kvm_vcpu *vcpu, char *buf, int n)
+static void enter_smm_save_seg_32(struct kvm_vcpu *vcpu,
+ struct kvm_smm_seg_state_32 *state,
+ u32 *selector,
+ int n)
{
struct kvm_segment seg;
- int offset;
kvm_get_segment(vcpu, &seg, n);
- put_smstate(u32, buf, 0x7fa8 + n * 4, seg.selector);
-
- if (n < 3)
- offset = 0x7f84 + n * 12;
- else
- offset = 0x7f2c + (n - 3) * 12;
-
- put_smstate(u32, buf, offset + 8, seg.base);
- put_smstate(u32, buf, offset + 4, seg.limit);
- put_smstate(u32, buf, offset, enter_smm_get_segment_flags(&seg));
+ *selector = seg.selector;
+ state->base = seg.base;
+ state->limit = seg.limit;
+ state->flags = enter_smm_get_segment_flags(&seg);
}
#ifdef CONFIG_X86_64
@@ -9054,54 +9050,47 @@ static void enter_smm_save_seg_64(struct kvm_vcpu *vcpu, char *buf, int n)
}
#endif
-static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, char *buf)
+static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, struct kvm_smram_state_32 *smram)
{
struct desc_ptr dt;
- struct kvm_segment seg;
unsigned long val;
int i;
- put_smstate(u32, buf, 0x7ffc, kvm_read_cr0(vcpu));
- put_smstate(u32, buf, 0x7ff8, kvm_read_cr3(vcpu));
- put_smstate(u32, buf, 0x7ff4, kvm_get_rflags(vcpu));
- put_smstate(u32, buf, 0x7ff0, kvm_rip_read(vcpu));
+ smram->cr0 = kvm_read_cr0(vcpu);
+ smram->cr3 = kvm_read_cr3(vcpu);
+ smram->eflags = kvm_get_rflags(vcpu);
+ smram->eip = kvm_rip_read(vcpu);
for (i = 0; i < 8; i++)
- put_smstate(u32, buf, 0x7fd0 + i * 4, kvm_register_read_raw(vcpu, i));
+ smram->gprs[i] = kvm_register_read_raw(vcpu, i);
kvm_get_dr(vcpu, 6, &val);
- put_smstate(u32, buf, 0x7fcc, (u32)val);
+ smram->dr6 = (u32)val;
kvm_get_dr(vcpu, 7, &val);
- put_smstate(u32, buf, 0x7fc8, (u32)val);
+ smram->dr7 = (u32)val;
- kvm_get_segment(vcpu, &seg, VCPU_SREG_TR);
- put_smstate(u32, buf, 0x7fc4, seg.selector);
- put_smstate(u32, buf, 0x7f64, seg.base);
- put_smstate(u32, buf, 0x7f60, seg.limit);
- put_smstate(u32, buf, 0x7f5c, enter_smm_get_segment_flags(&seg));
-
- kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR);
- put_smstate(u32, buf, 0x7fc0, seg.selector);
- put_smstate(u32, buf, 0x7f80, seg.base);
- put_smstate(u32, buf, 0x7f7c, seg.limit);
- put_smstate(u32, buf, 0x7f78, enter_smm_get_segment_flags(&seg));
+ enter_smm_save_seg_32(vcpu, &smram->tr, &smram->tr_sel, VCPU_SREG_TR);
+ enter_smm_save_seg_32(vcpu, &smram->ldtr, &smram->ldtr_sel, VCPU_SREG_LDTR);
static_call(kvm_x86_get_gdt)(vcpu, &dt);
- put_smstate(u32, buf, 0x7f74, dt.address);
- put_smstate(u32, buf, 0x7f70, dt.size);
+ smram->gdtr.base = dt.address;
+ smram->gdtr.limit = dt.size;
static_call(kvm_x86_get_idt)(vcpu, &dt);
- put_smstate(u32, buf, 0x7f58, dt.address);
- put_smstate(u32, buf, 0x7f54, dt.size);
+ smram->idtr.base = dt.address;
+ smram->idtr.limit = dt.size;
- for (i = 0; i < 6; i++)
- enter_smm_save_seg_32(vcpu, buf, i);
+ enter_smm_save_seg_32(vcpu, &smram->es, &smram->es_sel, VCPU_SREG_ES);
+ enter_smm_save_seg_32(vcpu, &smram->cs, &smram->cs_sel, VCPU_SREG_CS);
+ enter_smm_save_seg_32(vcpu, &smram->ss, &smram->ss_sel, VCPU_SREG_SS);
- put_smstate(u32, buf, 0x7f14, kvm_read_cr4(vcpu));
+ enter_smm_save_seg_32(vcpu, &smram->ds, &smram->ds_sel, VCPU_SREG_DS);
+ enter_smm_save_seg_32(vcpu, &smram->fs, &smram->fs_sel, VCPU_SREG_FS);
+ enter_smm_save_seg_32(vcpu, &smram->gs, &smram->gs_sel, VCPU_SREG_GS);
- /* revision id */
- put_smstate(u32, buf, 0x7efc, 0x00020000);
- put_smstate(u32, buf, 0x7ef8, vcpu->arch.smbase);
+ smram->cr4 = kvm_read_cr4(vcpu);
+ smram->smm_revision = 0x00020000;
+ smram->smbase = vcpu->arch.smbase;
}
#ifdef CONFIG_X86_64
@@ -9172,7 +9161,7 @@ static void enter_smm(struct kvm_vcpu *vcpu)
enter_smm_save_state_64(vcpu, (char *)&smram);
else
#endif
- enter_smm_save_state_32(vcpu, (char *)&smram);
+ enter_smm_save_state_32(vcpu, &smram.smram32);
/*
* Give enter_smm() a chance to make ISA-specific changes to the vCPU

279
debian/patches/pve/0023-KVM-x86-emulator-smm-use-smram-struct-for-64-bit-smr.patch vendored Normal file
View file

@ -0,0 +1,279 @@
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Maxim Levitsky <mlevitsk@redhat.com>
Date: Wed, 3 Aug 2022 18:50:08 +0300
Subject: [PATCH] KVM: x86: emulator/smm: use smram struct for 64 bit smram
load/restore
Use kvm_smram_state_64 struct to save/restore the 64 bit SMM state
(used when X86_FEATURE_LM is present in the guest CPUID,
regardless of 32-bitness of the guest).
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
---
arch/x86/kvm/emulate.c | 88 ++++++++++++++----------------------------
arch/x86/kvm/x86.c | 75 ++++++++++++++++-------------------
2 files changed, 62 insertions(+), 101 deletions(-)
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index ad5d2ab9ab84..4eb35a0a33a5 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2358,24 +2358,16 @@ static void rsm_load_seg_32(struct x86_emulate_ctxt *ctxt,
}
#ifdef CONFIG_X86_64
-static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, const char *smstate,
- int n)
+static void rsm_load_seg_64(struct x86_emulate_ctxt *ctxt,
+ const struct kvm_smm_seg_state_64 *state,
+ int n)
{
struct desc_struct desc;
- int offset;
- u16 selector;
- u32 base3;
-
- offset = 0x7e00 + n * 16;
-
- selector = GET_SMSTATE(u16, smstate, offset);
- rsm_set_desc_flags(&desc, GET_SMSTATE(u16, smstate, offset + 2) << 8);
- set_desc_limit(&desc, GET_SMSTATE(u32, smstate, offset + 4));
- set_desc_base(&desc, GET_SMSTATE(u32, smstate, offset + 8));
- base3 = GET_SMSTATE(u32, smstate, offset + 12);
- ctxt->ops->set_segment(ctxt, selector, &desc, base3, n);
- return X86EMUL_CONTINUE;
+ rsm_set_desc_flags(&desc, state->attributes << 8);
+ set_desc_limit(&desc, state->limit);
+ set_desc_base(&desc, (u32)state->base);
+ ctxt->ops->set_segment(ctxt, state->selector, &desc, state->base >> 32, n);
}
#endif
@@ -2469,71 +2461,49 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt,
#ifdef CONFIG_X86_64
static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt,
- const char *smstate)
+ const struct kvm_smram_state_64 *smstate)
{
- struct desc_struct desc;
struct desc_ptr dt;
- u64 val, cr0, cr3, cr4;
- u32 base3;
- u16 selector;
int i, r;
for (i = 0; i < 16; i++)
- *reg_write(ctxt, i) = GET_SMSTATE(u64, smstate, 0x7ff8 - i * 8);
+ *reg_write(ctxt, i) = smstate->gprs[15 - i];
- ctxt->_eip = GET_SMSTATE(u64, smstate, 0x7f78);
- ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7f70) | X86_EFLAGS_FIXED;
+ ctxt->_eip = smstate->rip;
+ ctxt->eflags = smstate->rflags | X86_EFLAGS_FIXED;
- val = GET_SMSTATE(u64, smstate, 0x7f68);
-
- if (ctxt->ops->set_dr(ctxt, 6, val))
+ if (ctxt->ops->set_dr(ctxt, 6, smstate->dr6))
return X86EMUL_UNHANDLEABLE;
-
- val = GET_SMSTATE(u64, smstate, 0x7f60);
-
- if (ctxt->ops->set_dr(ctxt, 7, val))
+ if (ctxt->ops->set_dr(ctxt, 7, smstate->dr7))
return X86EMUL_UNHANDLEABLE;
- cr0 = GET_SMSTATE(u64, smstate, 0x7f58);
- cr3 = GET_SMSTATE(u64, smstate, 0x7f50);
- cr4 = GET_SMSTATE(u64, smstate, 0x7f48);
- ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7f00));
- val = GET_SMSTATE(u64, smstate, 0x7ed0);
+ ctxt->ops->set_smbase(ctxt, smstate->smbase);
- if (ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA))
+ if (ctxt->ops->set_msr(ctxt, MSR_EFER, smstate->efer & ~EFER_LMA))
return X86EMUL_UNHANDLEABLE;
- selector = GET_SMSTATE(u32, smstate, 0x7e90);
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7e92) << 8);
- set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7e94));
- set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7e98));
- base3 = GET_SMSTATE(u32, smstate, 0x7e9c);
- ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_TR);
+ rsm_load_seg_64(ctxt, &smstate->tr, VCPU_SREG_TR);
- dt.size = GET_SMSTATE(u32, smstate, 0x7e84);
- dt.address = GET_SMSTATE(u64, smstate, 0x7e88);
+ dt.size = smstate->idtr.limit;
+ dt.address = smstate->idtr.base;
ctxt->ops->set_idt(ctxt, &dt);
- selector = GET_SMSTATE(u32, smstate, 0x7e70);
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7e72) << 8);
- set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7e74));
- set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7e78));
- base3 = GET_SMSTATE(u32, smstate, 0x7e7c);
- ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_LDTR);
+ rsm_load_seg_64(ctxt, &smstate->ldtr, VCPU_SREG_LDTR);
- dt.size = GET_SMSTATE(u32, smstate, 0x7e64);
- dt.address = GET_SMSTATE(u64, smstate, 0x7e68);
+ dt.size = smstate->gdtr.limit;
+ dt.address = smstate->gdtr.base;
ctxt->ops->set_gdt(ctxt, &dt);
- r = rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
+ r = rsm_enter_protected_mode(ctxt, smstate->cr0, smstate->cr3, smstate->cr4);
if (r != X86EMUL_CONTINUE)
return r;
- for (i = 0; i < 6; i++) {
- r = rsm_load_seg_64(ctxt, smstate, i);
- if (r != X86EMUL_CONTINUE)
- return r;
- }
+ rsm_load_seg_64(ctxt, &smstate->es, VCPU_SREG_ES);
+ rsm_load_seg_64(ctxt, &smstate->cs, VCPU_SREG_CS);
+ rsm_load_seg_64(ctxt, &smstate->ss, VCPU_SREG_SS);
+ rsm_load_seg_64(ctxt, &smstate->ds, VCPU_SREG_DS);
+ rsm_load_seg_64(ctxt, &smstate->fs, VCPU_SREG_FS);
+ rsm_load_seg_64(ctxt, &smstate->gs, VCPU_SREG_GS);
return X86EMUL_CONTINUE;
}
@@ -2608,7 +2578,7 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt)
#ifdef CONFIG_X86_64
if (emulator_has_longmode(ctxt))
- ret = rsm_load_state_64(ctxt, (const char *)&smram);
+ ret = rsm_load_state_64(ctxt, &smram.smram64);
else
#endif
ret = rsm_load_state_32(ctxt, &smram.smram32);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 8a6b9bffc770..d00b82ee6ca4 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -9033,20 +9033,17 @@ static void enter_smm_save_seg_32(struct kvm_vcpu *vcpu,
}
#ifdef CONFIG_X86_64
-static void enter_smm_save_seg_64(struct kvm_vcpu *vcpu, char *buf, int n)
+static void enter_smm_save_seg_64(struct kvm_vcpu *vcpu,
+ struct kvm_smm_seg_state_64 *state,
+ int n)
{
struct kvm_segment seg;
- int offset;
- u16 flags;
kvm_get_segment(vcpu, &seg, n);
- offset = 0x7e00 + n * 16;
-
- flags = enter_smm_get_segment_flags(&seg) >> 8;
- put_smstate(u16, buf, offset, seg.selector);
- put_smstate(u16, buf, offset + 2, flags);
- put_smstate(u32, buf, offset + 4, seg.limit);
- put_smstate(u64, buf, offset + 8, seg.base);
+ state->selector = seg.selector;
+ state->attributes = enter_smm_get_segment_flags(&seg) >> 8;
+ state->limit = seg.limit;
+ state->base = seg.base;
}
#endif
@@ -9094,57 +9091,51 @@ static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, struct kvm_smram_stat
}
#ifdef CONFIG_X86_64
-static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf)
+static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, struct kvm_smram_state_64 *smram)
{
struct desc_ptr dt;
- struct kvm_segment seg;
unsigned long val;
int i;
for (i = 0; i < 16; i++)
- put_smstate(u64, buf, 0x7ff8 - i * 8, kvm_register_read_raw(vcpu, i));
+ smram->gprs[15 - i] = kvm_register_read_raw(vcpu, i);
+
+ smram->rip = kvm_rip_read(vcpu);
+ smram->rflags = kvm_get_rflags(vcpu);
- put_smstate(u64, buf, 0x7f78, kvm_rip_read(vcpu));
- put_smstate(u32, buf, 0x7f70, kvm_get_rflags(vcpu));
kvm_get_dr(vcpu, 6, &val);
- put_smstate(u64, buf, 0x7f68, val);
+ smram->dr6 = val;
kvm_get_dr(vcpu, 7, &val);
- put_smstate(u64, buf, 0x7f60, val);
-
- put_smstate(u64, buf, 0x7f58, kvm_read_cr0(vcpu));
- put_smstate(u64, buf, 0x7f50, kvm_read_cr3(vcpu));
- put_smstate(u64, buf, 0x7f48, kvm_read_cr4(vcpu));
+ smram->dr7 = val;
- put_smstate(u32, buf, 0x7f00, vcpu->arch.smbase);
+ smram->cr0 = kvm_read_cr0(vcpu);
+ smram->cr3 = kvm_read_cr3(vcpu);
+ smram->cr4 = kvm_read_cr4(vcpu);
- /* revision id */
- put_smstate(u32, buf, 0x7efc, 0x00020064);
+ smram->smbase = vcpu->arch.smbase;
+ smram->smm_revison = 0x00020064;
- put_smstate(u64, buf, 0x7ed0, vcpu->arch.efer);
+ smram->efer = vcpu->arch.efer;
- kvm_get_segment(vcpu, &seg, VCPU_SREG_TR);
- put_smstate(u16, buf, 0x7e90, seg.selector);
- put_smstate(u16, buf, 0x7e92, enter_smm_get_segment_flags(&seg) >> 8);
- put_smstate(u32, buf, 0x7e94, seg.limit);
- put_smstate(u64, buf, 0x7e98, seg.base);
+ enter_smm_save_seg_64(vcpu, &smram->tr, VCPU_SREG_TR);
static_call(kvm_x86_get_idt)(vcpu, &dt);
- put_smstate(u32, buf, 0x7e84, dt.size);
- put_smstate(u64, buf, 0x7e88, dt.address);
+ smram->idtr.limit = dt.size;
+ smram->idtr.base = dt.address;
- kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR);
- put_smstate(u16, buf, 0x7e70, seg.selector);
- put_smstate(u16, buf, 0x7e72, enter_smm_get_segment_flags(&seg) >> 8);
- put_smstate(u32, buf, 0x7e74, seg.limit);
- put_smstate(u64, buf, 0x7e78, seg.base);
+ enter_smm_save_seg_64(vcpu, &smram->ldtr, VCPU_SREG_LDTR);
static_call(kvm_x86_get_gdt)(vcpu, &dt);
- put_smstate(u32, buf, 0x7e64, dt.size);
- put_smstate(u64, buf, 0x7e68, dt.address);
+ smram->gdtr.limit = dt.size;
+ smram->gdtr.base = dt.address;
- for (i = 0; i < 6; i++)
- enter_smm_save_seg_64(vcpu, buf, i);
+ enter_smm_save_seg_64(vcpu, &smram->es, VCPU_SREG_ES);
+ enter_smm_save_seg_64(vcpu, &smram->cs, VCPU_SREG_CS);
+ enter_smm_save_seg_64(vcpu, &smram->ss, VCPU_SREG_SS);
+ enter_smm_save_seg_64(vcpu, &smram->ds, VCPU_SREG_DS);
+ enter_smm_save_seg_64(vcpu, &smram->fs, VCPU_SREG_FS);
+ enter_smm_save_seg_64(vcpu, &smram->gs, VCPU_SREG_GS);
}
#endif
@@ -9158,7 +9149,7 @@ static void enter_smm(struct kvm_vcpu *vcpu)
memset(smram.bytes, 0, sizeof(smram.bytes));
#ifdef CONFIG_X86_64
if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
- enter_smm_save_state_64(vcpu, (char *)&smram);
+ enter_smm_save_state_64(vcpu, &smram.smram64);
else
#endif
enter_smm_save_state_32(vcpu, &smram.smram32);

98
debian/patches/pve/0024-KVM-x86-SVM-use-smram-structs.patch vendored Normal file
View file

@ -0,0 +1,98 @@
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Maxim Levitsky <mlevitsk@redhat.com>
Date: Wed, 3 Aug 2022 18:50:09 +0300
Subject: [PATCH] KVM: x86: SVM: use smram structs
This removes the last user of put_smstate/GET_SMSTATE so
remove these functions as well.
Also add a sanity check that we don't attempt to enter the SMM
on non long mode capable guest CPU with a running nested guest.
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
---
arch/x86/include/asm/kvm_host.h | 6 ------
arch/x86/kvm/svm/svm.c | 21 ++++++---------------
2 files changed, 6 insertions(+), 21 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index d752fabde94ad2..d570ec522ebb55 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -2077,12 +2077,6 @@ static inline int kvm_cpu_get_apicid(int mps_cpu)
#endif
}
-#define put_smstate(type, buf, offset, val) \
- *(type *)((buf) + (offset) - 0x7e00) = val
-
-#define GET_SMSTATE(type, buf, offset) \
- (*(type *)((buf) + (offset) - 0x7e00))
-
int kvm_cpu_dirty_log_size(void);
int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages);
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 688315d1dfabd1..7ca5e06878e19a 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4439,15 +4439,11 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram)
struct kvm_host_map map_save;
int ret;
- char *smstate = (char *)smram;
-
if (!is_guest_mode(vcpu))
return 0;
- /* FED8h - SVM Guest */
- put_smstate(u64, smstate, 0x7ed8, 1);
- /* FEE0h - SVM Guest VMCB Physical Address */
- put_smstate(u64, smstate, 0x7ee0, svm->nested.vmcb12_gpa);
+ smram->smram64.svm_guest_flag = 1;
+ smram->smram64.svm_guest_vmcb_gpa = svm->nested.vmcb12_gpa;
svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX];
svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP];
@@ -4486,28 +4482,23 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct kvm_host_map map, map_save;
- u64 saved_efer, vmcb12_gpa;
struct vmcb *vmcb12;
int ret;
- const char *smstate = (const char *)smram;
-
if (!guest_cpuid_has(vcpu, X86_FEATURE_LM))
return 0;
/* Non-zero if SMI arrived while vCPU was in guest mode. */
- if (!GET_SMSTATE(u64, smstate, 0x7ed8))
+ if (!smram->smram64.svm_guest_flag)
return 0;
if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM))
return 1;
- saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0);
- if (!(saved_efer & EFER_SVME))
+ if (!(smram->smram64.efer & EFER_SVME))
return 1;
- vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0);
- if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcb12_gpa), &map) == -EINVAL)
+ if (kvm_vcpu_map(vcpu, gpa_to_gfn(smram->smram64.svm_guest_vmcb_gpa), &map) == -EINVAL)
return 1;
ret = 1;
@@ -4533,7 +4524,7 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram)
vmcb12 = map.hva;
nested_copy_vmcb_control_to_cache(svm, &vmcb12->control);
nested_copy_vmcb_save_to_cache(svm, &vmcb12->save);
- ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, false);
+ ret = enter_svm_guest_mode(vcpu, smram->smram64.svm_guest_vmcb_gpa, vmcb12, false);
if (ret)
goto unmap_save;

40
debian/patches/pve/0025-KVM-x86-SVM-don-t-save-SVM-state-to-SMRAM-when-VM-is.patch vendored Normal file
View file

@ -0,0 +1,40 @@
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Maxim Levitsky <mlevitsk@redhat.com>
Date: Wed, 3 Aug 2022 18:50:10 +0300
Subject: [PATCH] KVM: x86: SVM: don't save SVM state to SMRAM when VM is not
long mode capable
When the guest CPUID doesn't have support for long mode, 32 bit SMRAM
layout is used and it has no support for preserving EFER and/or SVM
state.
Note that this isn't relevant to running 32 bit guests on VM which is
long mode capable - such VM can still run 32 bit guests in compatibility
mode.
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
---
arch/x86/kvm/svm/svm.c | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 742497b1d4c3..938b9b24f0ee 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4311,6 +4311,15 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram)
if (!is_guest_mode(vcpu))
return 0;
+ /*
+ * 32 bit SMRAM format doesn't preserve EFER and SVM state.
+ * SVM should not be enabled by the userspace without marking
+ * the CPU as at least long mode capable.
+ */
+
+ if (!guest_cpuid_has(vcpu, X86_FEATURE_LM))
+ return 1;
+
smram->smram64.svm_guest_flag = 1;
smram->smram64.svm_guest_vmcb_gpa = svm->nested.vmcb12_gpa;

180
debian/patches/pve/0026-KVM-x86-emulator-smm-preserve-interrupt-shadow-in-SM.patch vendored Normal file
View file

@ -0,0 +1,180 @@
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Maxim Levitsky <mlevitsk@redhat.com>
Date: Wed, 3 Aug 2022 18:50:11 +0300
Subject: [PATCH] KVM: x86: emulator/smm: preserve interrupt shadow in SMRAM
When #SMI is asserted, the CPU can be in interrupt shadow
due to sti or mov ss.
It is not mandatory in Intel/AMD prm to have the #SMI
blocked during the shadow, and on top of
that, since neither SVM nor VMX has true support for SMI
window, waiting for one instruction would mean single stepping
the guest.
Instead, allow #SMI in this case, but both reset the interrupt
window and stash its value in SMRAM to restore it on exit
from SMM.
This fixes rare failures seen mostly on windows guests on VMX,
when #SMI falls on the sti instruction which mainfest in
VM entry failure due to EFLAGS.IF not being set, but STI interrupt
window still being set in the VMCS.
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
---
arch/x86/kvm/emulate.c | 17 ++++++++++++++---
arch/x86/kvm/kvm_emulate.h | 10 ++++++----
arch/x86/kvm/x86.c | 12 ++++++++++++
3 files changed, 32 insertions(+), 7 deletions(-)
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 4eb35a0a33a5..3e6ea2951e2b 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2420,7 +2420,7 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt,
const struct kvm_smram_state_32 *smstate)
{
struct desc_ptr dt;
- int i;
+ int i, r;
ctxt->eflags = smstate->eflags | X86_EFLAGS_FIXED;
ctxt->_eip = smstate->eip;
@@ -2455,8 +2455,16 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt,
ctxt->ops->set_smbase(ctxt, smstate->smbase);
- return rsm_enter_protected_mode(ctxt, smstate->cr0,
- smstate->cr3, smstate->cr4);
+ r = rsm_enter_protected_mode(ctxt, smstate->cr0,
+ smstate->cr3, smstate->cr4);
+
+ if (r != X86EMUL_CONTINUE)
+ return r;
+
+ ctxt->ops->set_int_shadow(ctxt, 0);
+ ctxt->interruptibility = (u8)smstate->int_shadow;
+
+ return X86EMUL_CONTINUE;
}
#ifdef CONFIG_X86_64
@@ -2505,6 +2513,9 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt,
rsm_load_seg_64(ctxt, &smstate->fs, VCPU_SREG_FS);
rsm_load_seg_64(ctxt, &smstate->gs, VCPU_SREG_GS);
+ ctxt->ops->set_int_shadow(ctxt, 0);
+ ctxt->interruptibility = (u8)smstate->int_shadow;
+
return X86EMUL_CONTINUE;
}
#endif
diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h
index 3b37b3e17379..a64c190abf28 100644
--- a/arch/x86/kvm/kvm_emulate.h
+++ b/arch/x86/kvm/kvm_emulate.h
@@ -231,6 +231,7 @@ struct x86_emulate_ops {
bool (*guest_has_rdpid)(struct x86_emulate_ctxt *ctxt);
void (*set_nmi_mask)(struct x86_emulate_ctxt *ctxt, bool masked);
+ void (*set_int_shadow)(struct x86_emulate_ctxt *ctxt, u8 shadow);
unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt);
void (*exiting_smm)(struct x86_emulate_ctxt *ctxt);
@@ -497,7 +498,8 @@ struct kvm_smram_state_32 {
u32 reserved1[62];
u32 smbase;
u32 smm_revision;
- u32 reserved2[5];
+ u32 reserved2[4];
+ u32 int_shadow; /* KVM extension */
u32 cr4; /* CR4 is not present in Intel/AMD SMRAM image */
u32 reserved3[5];
@@ -545,6 +547,7 @@ static inline void __check_smram32_offsets(void)
__CHECK_SMRAM32_OFFSET(smbase, 0xFEF8);
__CHECK_SMRAM32_OFFSET(smm_revision, 0xFEFC);
__CHECK_SMRAM32_OFFSET(reserved2, 0xFF00);
+ __CHECK_SMRAM32_OFFSET(int_shadow, 0xFF10);
__CHECK_SMRAM32_OFFSET(cr4, 0xFF14);
__CHECK_SMRAM32_OFFSET(reserved3, 0xFF18);
__CHECK_SMRAM32_OFFSET(ds, 0xFF2C);
@@ -604,7 +607,7 @@ struct kvm_smram_state_64 {
u64 io_restart_rsi;
u64 io_restart_rdi;
u32 io_restart_dword;
- u32 reserved1;
+ u32 int_shadow;
u8 io_inst_restart;
u8 auto_hlt_restart;
u8 reserved2[6];
@@ -642,7 +645,6 @@ struct kvm_smram_state_64 {
u64 gprs[16]; /* GPRS in a reversed "natural" X86 order (R15/R14/../RCX/RAX.) */
};
-
static inline void __check_smram64_offsets(void)
{
#define __CHECK_SMRAM64_OFFSET(field, offset) \
@@ -663,7 +665,7 @@ static inline void __check_smram64_offsets(void)
__CHECK_SMRAM64_OFFSET(io_restart_rsi, 0xFEB0);
__CHECK_SMRAM64_OFFSET(io_restart_rdi, 0xFEB8);
__CHECK_SMRAM64_OFFSET(io_restart_dword, 0xFEC0);
- __CHECK_SMRAM64_OFFSET(reserved1, 0xFEC4);
+ __CHECK_SMRAM64_OFFSET(int_shadow, 0xFEC4);
__CHECK_SMRAM64_OFFSET(io_inst_restart, 0xFEC8);
__CHECK_SMRAM64_OFFSET(auto_hlt_restart, 0xFEC9);
__CHECK_SMRAM64_OFFSET(reserved2, 0xFECA);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index d00b82ee6ca4..4cefdd83a448 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -7299,6 +7299,11 @@ static void emulator_set_nmi_mask(struct x86_emulate_ctxt *ctxt, bool masked)
static_call(kvm_x86_set_nmi_mask)(emul_to_vcpu(ctxt), masked);
}
+static void emulator_set_int_shadow(struct x86_emulate_ctxt *ctxt, u8 shadow)
+{
+ static_call(kvm_x86_set_interrupt_shadow)(emul_to_vcpu(ctxt), shadow);
+}
+
static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt)
{
return emul_to_vcpu(ctxt)->arch.hflags;
@@ -7368,6 +7373,7 @@ static const struct x86_emulate_ops emulate_ops = {
.guest_has_fxsr = emulator_guest_has_fxsr,
.guest_has_rdpid = emulator_guest_has_rdpid,
.set_nmi_mask = emulator_set_nmi_mask,
+ .set_int_shadow = emulator_set_int_shadow,
.get_hflags = emulator_get_hflags,
.exiting_smm = emulator_exiting_smm,
.leave_smm = emulator_leave_smm,
@@ -9088,6 +9094,8 @@ static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, struct kvm_smram_stat
smram->cr4 = kvm_read_cr4(vcpu);
smram->smm_revision = 0x00020000;
smram->smbase = vcpu->arch.smbase;
+
+ smram->int_shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu);
}
#ifdef CONFIG_X86_64
@@ -9136,6 +9144,8 @@ static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, struct kvm_smram_stat
enter_smm_save_seg_64(vcpu, &smram->ds, VCPU_SREG_DS);
enter_smm_save_seg_64(vcpu, &smram->fs, VCPU_SREG_FS);
enter_smm_save_seg_64(vcpu, &smram->gs, VCPU_SREG_GS);
+
+ smram->int_shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu);
}
#endif
@@ -9172,6 +9182,8 @@ static void enter_smm(struct kvm_vcpu *vcpu)
kvm_set_rflags(vcpu, X86_EFLAGS_FIXED);
kvm_rip_write(vcpu, 0x8000);
+ static_call(kvm_x86_set_interrupt_shadow)(vcpu, 0);
+
cr0 = vcpu->arch.cr0 & ~(X86_CR0_PE | X86_CR0_EM | X86_CR0_TS | X86_CR0_PG);
static_call(kvm_x86_set_cr0)(vcpu, cr0);
vcpu->arch.cr0 = cr0;

22
debian/patches/series.linux vendored
View file

@ -8,6 +8,24 @@ pve/0002-bridge-keep-MAC-of-first-assigned-port.patch
pve/0003-pci-Enable-overrides-for-missing-ACS-capabilities-4..patch
pve/0004-kvm-disable-default-dynamic-halt-polling-growth.patch
pve/0005-net-core-downgrade-unregister_netdevice-refcount-lea.patch
# pve/0006-Revert-PCI-Coalesce-host-bridge-contiguous-apertures.patch
# pve/0007-PCI-Reinstate-PCI-Coalesce-host-bridge-contiguous-ap.patch
# pve/0006-Revert-PCI-Coalesce-host-bridge-contiguous-apertures.patch # Already in mainline (v5.16)
# pve/0007-PCI-Reinstate-PCI-Coalesce-host-bridge-contiguous-ap.patch # Already in mainline (v5.16)
pve/0008-do-not-generate-split-BTF-type-info-per-default.patch
# pve/0009-blk-cgroup-always-terminate-io.stat-lines.patch # Already in mainline (v5.17)
# pve/0010-drivers-firmware-Don-t-mark-as-busy-the-simple-frame.patch # Already in mainline (v5.18)
# pve/0011-drm-simpledrm-Request-memory-region-in-driver.patch # Already in mainline (v5.18)
# pve/0012-fbdev-simplefb-Request-memory-region-in-driver.patch # Already in mainline (v5.18)
# pve/0013-NFSv4.1-provide-mount-option-to-toggle-trunking-disc.patch # Already in mainline (v5.18)
# pve/0014-EDAC-amd64-Add-PCI-device-IDs-for-family-19h-model-5.patch # Already in mainline (v5.17)
pve/0015-bug-introduce-ASSERT_STRUCT_OFFSET.patch
pve/0016-KVM-x86-emulator-em_sysexit-should-update-ctxt-mode.patch
pve/0017-KVM-x86-emulator-introduce-emulator_recalc_and_set_m.patch
pve/0018-KVM-x86-emulator-update-the-emulation-mode-after-rsm.patch
pve/0019-KVM-x86-emulator-update-the-emulation-mode-after-CR0.patch
pve/0020-KVM-x86-emulator-smm-add-structs-for-KVM-s-smram-lay.patch
pve/0021-KVM-x86-emulator-smm-use-smram-structs-in-the-common.patch
pve/0022-KVM-x86-emulator-smm-use-smram-struct-for-32-bit-smr.patch
pve/0023-KVM-x86-emulator-smm-use-smram-struct-for-64-bit-smr.patch
pve/0024-KVM-x86-SVM-use-smram-structs.patch
pve/0025-KVM-x86-SVM-don-t-save-SVM-state-to-SMRAM-when-VM-is.patch
pve/0026-KVM-x86-emulator-smm-preserve-interrupt-shadow-in-SM.patch