diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 101632379b8b..26ce8c9a473c 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -61,7 +61,9 @@ head-y := arch/arm64/kernel/head.o # The byte offset of the kernel image in RAM from the start of RAM. ifeq ($(CONFIG_ARM64_RANDOMIZE_TEXT_OFFSET), y) -TEXT_OFFSET := $(shell awk 'BEGIN {srand(); printf "0x%03x000\n", int(512 * rand())}') +TEXT_OFFSET := $(shell awk "BEGIN {srand(); printf \"0x%06x\n\", \ + int(2 * 1024 * 1024 / (2 ^ $(CONFIG_ARM64_PAGE_SHIFT)) * \ + rand()) * (2 ^ $(CONFIG_ARM64_PAGE_SHIFT))}") else TEXT_OFFSET := 0x00080000 endif diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h index 43a66881fd57..73f5d548bba1 100644 --- a/arch/arm64/include/asm/spinlock.h +++ b/arch/arm64/include/asm/spinlock.h @@ -31,6 +31,12 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) unsigned int tmp; arch_spinlock_t lockval; + /* + * Ensure prior spin_lock operations to other locks have completed + * on this CPU before we test whether "lock" is locked. + */ + smp_mb(); + asm volatile( " sevl\n" "1: wfe\n" @@ -152,6 +158,7 @@ static inline int arch_spin_value_unlocked(arch_spinlock_t lock) static inline int arch_spin_is_locked(arch_spinlock_t *lock) { + smp_mb(); /* See arch_spin_unlock_wait */ return !arch_spin_value_unlocked(READ_ONCE(*lock)); } diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index f8df75d740f4..6dd18140ebb8 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -34,6 +34,7 @@ #include #include #include +#include #include /* @@ -216,12 +217,22 @@ static int create_safe_exec_page(void *src_start, size_t length, set_pte(pte, __pte(virt_to_phys((void *)dst) | pgprot_val(PAGE_KERNEL_EXEC))); - /* Load our new page tables */ - asm volatile("msr ttbr0_el1, %0;" - "isb;" - "tlbi vmalle1is;" - "dsb ish;" - "isb" : : "r"(virt_to_phys(pgd))); + /* + * Load our new page tables. A strict BBM approach requires that we + * ensure that TLBs are free of any entries that may overlap with the + * global mappings we are about to install. + * + * For a real hibernate/resume cycle TTBR0 currently points to a zero + * page, but TLBs may contain stale ASID-tagged entries (e.g. for EFI + * runtime services), while for a userspace-driven test_resume cycle it + * points to userspace page tables (and we must point it at a zero page + * ourselves). Elsewhere we only (un)install the idmap with preemption + * disabled, so T0SZ should be as required regardless. + */ + cpu_set_reserved_ttbr0(); + local_flush_tlb_all(); + write_sysreg(virt_to_phys(pgd), ttbr0_el1); + isb(); *phys_dst_addr = virt_to_phys((void *)dst); @@ -387,6 +398,38 @@ int swsusp_arch_resume(void) void __noreturn (*hibernate_exit)(phys_addr_t, phys_addr_t, void *, void *, phys_addr_t, phys_addr_t); + /* + * Restoring the memory image will overwrite the ttbr1 page tables. + * Create a second copy of just the linear map, and use this when + * restoring. + */ + tmp_pg_dir = (pgd_t *)get_safe_page(GFP_ATOMIC); + if (!tmp_pg_dir) { + pr_err("Failed to allocate memory for temporary page tables."); + rc = -ENOMEM; + goto out; + } + rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, 0); + if (rc) + goto out; + + /* + * Since we only copied the linear map, we need to find restore_pblist's + * linear map address. + */ + lm_restore_pblist = LMADDR(restore_pblist); + + /* + * We need a zero page that is zero before & after resume in order to + * to break before make on the ttbr1 page tables. + */ + zero_page = (void *)get_safe_page(GFP_ATOMIC); + if (!zero_page) { + pr_err("Failed to allocate zero page."); + rc = -ENOMEM; + goto out; + } + /* * Locate the exit code in the bottom-but-one page, so that *NULL * still has disastrous affects. @@ -412,27 +455,6 @@ int swsusp_arch_resume(void) */ __flush_dcache_area(hibernate_exit, exit_size); - /* - * Restoring the memory image will overwrite the ttbr1 page tables. - * Create a second copy of just the linear map, and use this when - * restoring. - */ - tmp_pg_dir = (pgd_t *)get_safe_page(GFP_ATOMIC); - if (!tmp_pg_dir) { - pr_err("Failed to allocate memory for temporary page tables."); - rc = -ENOMEM; - goto out; - } - rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, 0); - if (rc) - goto out; - - /* - * Since we only copied the linear map, we need to find restore_pblist's - * linear map address. - */ - lm_restore_pblist = LMADDR(restore_pblist); - /* * KASLR will cause the el2 vectors to be in a different location in * the resumed kernel. Load hibernate's temporary copy into el2. @@ -447,12 +469,6 @@ int swsusp_arch_resume(void) __hyp_set_vectors(el2_vectors); } - /* - * We need a zero page that is zero before & after resume in order to - * to break before make on the ttbr1 page tables. - */ - zero_page = (void *)get_safe_page(GFP_ATOMIC); - hibernate_exit(virt_to_phys(tmp_pg_dir), resume_hdr.ttbr1_el1, resume_hdr.reenter_kernel, lm_restore_pblist, resume_hdr.__hyp_stub_vectors, virt_to_phys(zero_page)); diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index cfd46c227c8c..a99eff9afc1f 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -43,6 +43,9 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) unsigned long fp = frame->fp; unsigned long irq_stack_ptr; + if (!tsk) + tsk = current; + /* * Switching between stacks is valid when tracing current and in * non-preemptible context. @@ -67,7 +70,7 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) frame->pc = *(unsigned long *)(fp + 8); #ifdef CONFIG_FUNCTION_GRAPH_TRACER - if (tsk && tsk->ret_stack && + if (tsk->ret_stack && (frame->pc == (unsigned long)return_to_handler)) { /* * This is a case where function graph tracer has diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index f5c82c76cf7c..a1cfcaa562a2 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -149,6 +149,11 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) unsigned long irq_stack_ptr; int skip; + pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk); + + if (!tsk) + tsk = current; + /* * Switching between stacks is valid when tracing current and in * non-preemptible context. @@ -158,11 +163,6 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) else irq_stack_ptr = 0; - pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk); - - if (!tsk) - tsk = current; - if (tsk == current) { frame.fp = (unsigned long)__builtin_frame_address(0); frame.sp = current_stack_pointer; diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index da30529bb1f6..019f13637fae 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -51,20 +51,8 @@ static int find_num_contig(struct mm_struct *mm, unsigned long addr, *pgsize = PAGE_SIZE; if (!pte_cont(pte)) return 1; - if (!pgd_present(*pgd)) { - VM_BUG_ON(!pgd_present(*pgd)); - return 1; - } pud = pud_offset(pgd, addr); - if (!pud_present(*pud)) { - VM_BUG_ON(!pud_present(*pud)); - return 1; - } pmd = pmd_offset(pud, addr); - if (!pmd_present(*pmd)) { - VM_BUG_ON(!pmd_present(*pmd)); - return 1; - } if ((pte_t *)pmd == ptep) { *pgsize = PMD_SIZE; return CONT_PMDS; @@ -212,7 +200,7 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm, ncontig = find_num_contig(mm, addr, cpte, *cpte, &pgsize); /* save the 1st pte to return */ pte = ptep_get_and_clear(mm, addr, cpte); - for (i = 1; i < ncontig; ++i) { + for (i = 1, addr += pgsize; i < ncontig; ++i, addr += pgsize) { /* * If HW_AFDBM is enabled, then the HW could * turn on the dirty bit for any of the page @@ -250,8 +238,8 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma, pfn = pte_pfn(*cpte); ncontig = find_num_contig(vma->vm_mm, addr, cpte, *cpte, &pgsize); - for (i = 0; i < ncontig; ++i, ++cpte) { - changed = ptep_set_access_flags(vma, addr, cpte, + for (i = 0; i < ncontig; ++i, ++cpte, addr += pgsize) { + changed |= ptep_set_access_flags(vma, addr, cpte, pfn_pte(pfn, hugeprot), dirty); @@ -273,7 +261,7 @@ void huge_ptep_set_wrprotect(struct mm_struct *mm, cpte = huge_pte_offset(mm, addr); ncontig = find_num_contig(mm, addr, cpte, *cpte, &pgsize); - for (i = 0; i < ncontig; ++i, ++cpte) + for (i = 0; i < ncontig; ++i, ++cpte, addr += pgsize) ptep_set_wrprotect(mm, addr, cpte); } else { ptep_set_wrprotect(mm, addr, ptep); @@ -291,7 +279,7 @@ void huge_ptep_clear_flush(struct vm_area_struct *vma, cpte = huge_pte_offset(vma->vm_mm, addr); ncontig = find_num_contig(vma->vm_mm, addr, cpte, *cpte, &pgsize); - for (i = 0; i < ncontig; ++i, ++cpte) + for (i = 0; i < ncontig; ++i, ++cpte, addr += pgsize) ptep_clear_flush(vma, addr, cpte); } else { ptep_clear_flush(vma, addr, ptep); diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 8292784d44c9..d88a2a80ada8 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -100,7 +100,16 @@ ENTRY(cpu_do_resume) msr tcr_el1, x8 msr vbar_el1, x9 + + /* + * __cpu_setup() cleared MDSCR_EL1.MDE and friends, before unmasking + * debug exceptions. By restoring MDSCR_EL1 here, we may take a debug + * exception. Mask them until local_dbg_restore() in cpu_suspend() + * resets them. + */ + disable_dbg msr mdscr_el1, x10 + msr sctlr_el1, x12 /* * Restore oslsr_el1 by writing oslar_el1 diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 60530fd93d6d..06176328f83d 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -62,6 +62,9 @@ config PCI_QUIRKS config ARCH_SUPPORTS_UPROBES def_bool y +config DEBUG_RODATA + def_bool y + config S390 def_bool y select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index feff9caf89b5..91376d9e4286 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -109,6 +109,13 @@ void __init paging_init(void) free_area_init_nodes(max_zone_pfns); } +void mark_rodata_ro(void) +{ + /* Text and rodata are already protected. Nothing to do here. */ + pr_info("Write protecting the kernel read-only data: %luk\n", + ((unsigned long)&_eshared - (unsigned long)&_stext) >> 10); +} + void __init mem_init(void) { if (MACHINE_HAS_TLB_LC) @@ -127,9 +134,6 @@ void __init mem_init(void) setup_zero_pages(); /* Setup zeroed pages. */ mem_init_print_info(NULL); - printk("Write protected kernel read-only data: %#lx - %#lx\n", - (unsigned long)&_stext, - PFN_ALIGN((unsigned long)&_eshared) - 1); } void free_initmem(void) diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c index 433b60092972..d8f4cc22856c 100644 --- a/drivers/base/power/opp/core.c +++ b/drivers/base/power/opp/core.c @@ -259,9 +259,6 @@ unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev) reg = opp_table->regulator; if (IS_ERR(reg)) { /* Regulator may not be required for device */ - if (reg) - dev_err(dev, "%s: Invalid regulator (%ld)\n", __func__, - PTR_ERR(reg)); rcu_read_unlock(); return 0; } diff --git a/drivers/hwtracing/coresight/coresight-tmc.c b/drivers/hwtracing/coresight/coresight-tmc.c index 9e02ac963cd0..3978cbb6b038 100644 --- a/drivers/hwtracing/coresight/coresight-tmc.c +++ b/drivers/hwtracing/coresight/coresight-tmc.c @@ -388,9 +388,6 @@ static int tmc_probe(struct amba_device *adev, const struct amba_id *id) err_misc_register: coresight_unregister(drvdata->csdev); err_devm_kzalloc: - if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) - dma_free_coherent(dev, drvdata->size, - drvdata->vaddr, drvdata->paddr); return ret; } diff --git a/kernel/events/core.c b/kernel/events/core.c index fe9420e421b0..19f34aa0eb68 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -5823,7 +5823,7 @@ static int __perf_pmu_output_stop(void *info) { struct perf_event *event = info; struct pmu *pmu = event->pmu; - struct perf_cpu_context *cpuctx = get_cpu_ptr(pmu->pmu_cpu_context); + struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); struct remote_output ro = { .rb = event->rb, };