From 71c208dd54ab971036d83ff6d9837bae4976e623 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 26 Feb 2018 15:08:18 +0100 Subject: x86/xen: Zero MSR_IA32_SPEC_CTRL before suspend Older Xen versions (4.5 and before) might have problems migrating pv guests with MSR_IA32_SPEC_CTRL having a non-zero value. So before suspending zero that MSR and restore it after being resumed. Signed-off-by: Juergen Gross Signed-off-by: Thomas Gleixner Reviewed-by: Jan Beulich Cc: stable@vger.kernel.org Cc: xen-devel@lists.xenproject.org Cc: boris.ostrovsky@oracle.com Link: https://lkml.kernel.org/r/20180226140818.4849-1-jgross@suse.com --- arch/x86/xen/suspend.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index d9f96cc5d743..1d83152c761b 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -1,12 +1,15 @@ // SPDX-License-Identifier: GPL-2.0 #include #include +#include #include #include #include #include +#include +#include #include #include #include @@ -15,6 +18,8 @@ #include "mmu.h" #include "pmu.h" +static DEFINE_PER_CPU(u64, spec_ctrl); + void xen_arch_pre_suspend(void) { xen_save_time_memory_area(); @@ -35,6 +40,9 @@ void xen_arch_post_suspend(int cancelled) static void xen_vcpu_notify_restore(void *data) { + if (xen_pv_domain() && boot_cpu_has(X86_FEATURE_SPEC_CTRL)) + wrmsrl(MSR_IA32_SPEC_CTRL, this_cpu_read(spec_ctrl)); + /* Boot processor notified via generic timekeeping_resume() */ if (smp_processor_id() == 0) return; @@ -44,7 +52,15 @@ static void xen_vcpu_notify_restore(void *data) static void xen_vcpu_notify_suspend(void *data) { + u64 tmp; + tick_suspend_local(); + + if (xen_pv_domain() && boot_cpu_has(X86_FEATURE_SPEC_CTRL)) { + rdmsrl(MSR_IA32_SPEC_CTRL, tmp); + this_cpu_write(spec_ctrl, tmp); + wrmsrl(MSR_IA32_SPEC_CTRL, 0); + } } void xen_arch_resume(void) -- cgit v1.2.3 From 1402fd8ed7e5bda1b3e7613b70780b0db392d1e6 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 28 Feb 2018 07:19:21 -0600 Subject: objtool: Fix another switch table detection issue Continue the switch table detection whack-a-mole. Add a check to distinguish KASAN data reads from switch data reads. The switch jump tables in .rodata have relocations associated with them. This fixes the following warning: crypto/asymmetric_keys/x509_cert_parser.o: warning: objtool: x509_note_pkey_algo()+0xa4: sibling call from callable instruction with modified stack frame Reported-by: Arnd Bergmann Signed-off-by: Josh Poimboeuf Signed-off-by: Thomas Gleixner Tested-by: Arnd Bergmann Cc: Peter Zijlstra Link: https://lkml.kernel.org/r/d7c8853022ad47d158cb81e953a40469fc08a95e.1519784382.git.jpoimboe@redhat.com --- tools/objtool/check.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 472e64e95891..46c1d239cc1b 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -925,7 +925,11 @@ static struct rela *find_switch_table(struct objtool_file *file, if (find_symbol_containing(file->rodata, text_rela->addend)) continue; - return find_rela_by_dest(file->rodata, text_rela->addend); + rodata_rela = find_rela_by_dest(file->rodata, text_rela->addend); + if (!rodata_rela) + continue; + + return rodata_rela; } return NULL; -- cgit v1.2.3 From 945fd17ab6bab8a4d05da6c3170519fbcfe62ddb Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 28 Feb 2018 21:14:26 +0100 Subject: x86/cpu_entry_area: Sync cpu_entry_area to initial_page_table The separation of the cpu_entry_area from the fixmap missed the fact that on 32bit non-PAE kernels the cpu_entry_area mapping might not be covered in initial_page_table by the previous synchronizations. This results in suspend/resume failures because 32bit utilizes initial page table for resume. The absence of the cpu_entry_area mapping results in a triple fault, aka. insta reboot. With PAE enabled this works by chance because the PGD entry which covers the fixmap and other parts incindentally provides the cpu_entry_area mapping as well. Synchronize the initial page table after setting up the cpu entry area. Instead of adding yet another copy of the same code, move it to a function and invoke it from the various places. It needs to be investigated if the existing calls in setup_arch() and setup_per_cpu_areas() can be replaced by the later invocation from setup_cpu_entry_areas(), but that's beyond the scope of this fix. Fixes: 92a0f81d8957 ("x86/cpu_entry_area: Move it out of the fixmap") Reported-by: Woody Suwalski Signed-off-by: Thomas Gleixner Tested-by: Woody Suwalski Cc: William Grant Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1802282137290.1392@nanos.tec.linutronix.de --- arch/x86/include/asm/pgtable_32.h | 1 + arch/x86/include/asm/pgtable_64.h | 1 + arch/x86/kernel/setup.c | 17 +++++------------ arch/x86/kernel/setup_percpu.c | 17 ++++------------- arch/x86/mm/cpu_entry_area.c | 6 ++++++ arch/x86/mm/init_32.c | 15 +++++++++++++++ 6 files changed, 32 insertions(+), 25 deletions(-) diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h index e55466760ff8..b3ec519e3982 100644 --- a/arch/x86/include/asm/pgtable_32.h +++ b/arch/x86/include/asm/pgtable_32.h @@ -32,6 +32,7 @@ extern pmd_t initial_pg_pmd[]; static inline void pgtable_cache_init(void) { } static inline void check_pgt_cache(void) { } void paging_init(void); +void sync_initial_page_table(void); /* * Define this if things work differently on an i386 and an i486: diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 81462e9a34f6..1149d2112b2e 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -28,6 +28,7 @@ extern pgd_t init_top_pgt[]; #define swapper_pg_dir init_top_pgt extern void paging_init(void); +static inline void sync_initial_page_table(void) { } #define pte_ERROR(e) \ pr_err("%s:%d: bad pte %p(%016lx)\n", \ diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 1ae67e982af7..4c616be28506 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1204,20 +1204,13 @@ void __init setup_arch(char **cmdline_p) kasan_init(); -#ifdef CONFIG_X86_32 - /* sync back kernel address range */ - clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY, - swapper_pg_dir + KERNEL_PGD_BOUNDARY, - KERNEL_PGD_PTRS); - /* - * sync back low identity map too. It is used for example - * in the 32-bit EFI stub. + * Sync back kernel address range. + * + * FIXME: Can the later sync in setup_cpu_entry_areas() replace + * this call? */ - clone_pgd_range(initial_page_table, - swapper_pg_dir + KERNEL_PGD_BOUNDARY, - min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY)); -#endif + sync_initial_page_table(); tboot_probe(); diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 497aa766fab3..ea554f812ee1 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -287,24 +287,15 @@ void __init setup_per_cpu_areas(void) /* Setup cpu initialized, callin, callout masks */ setup_cpu_local_masks(); -#ifdef CONFIG_X86_32 /* * Sync back kernel address range again. We already did this in * setup_arch(), but percpu data also needs to be available in * the smpboot asm. We can't reliably pick up percpu mappings * using vmalloc_fault(), because exception dispatch needs * percpu data. + * + * FIXME: Can the later sync in setup_cpu_entry_areas() replace + * this call? */ - clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY, - swapper_pg_dir + KERNEL_PGD_BOUNDARY, - KERNEL_PGD_PTRS); - - /* - * sync back low identity map too. It is used for example - * in the 32-bit EFI stub. - */ - clone_pgd_range(initial_page_table, - swapper_pg_dir + KERNEL_PGD_BOUNDARY, - min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY)); -#endif + sync_initial_page_table(); } diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c index b9283cc27622..476d810639a8 100644 --- a/arch/x86/mm/cpu_entry_area.c +++ b/arch/x86/mm/cpu_entry_area.c @@ -163,4 +163,10 @@ void __init setup_cpu_entry_areas(void) for_each_possible_cpu(cpu) setup_cpu_entry_area(cpu); + + /* + * This is the last essential update to swapper_pgdir which needs + * to be synchronized to initial_page_table on 32bit. + */ + sync_initial_page_table(); } diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 79cb066f40c0..396e1f0151ac 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -453,6 +453,21 @@ static inline void permanent_kmaps_init(pgd_t *pgd_base) } #endif /* CONFIG_HIGHMEM */ +void __init sync_initial_page_table(void) +{ + clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY, + swapper_pg_dir + KERNEL_PGD_BOUNDARY, + KERNEL_PGD_PTRS); + + /* + * sync back low identity map too. It is used for example + * in the 32-bit EFI stub. + */ + clone_pgd_range(initial_page_table, + swapper_pg_dir + KERNEL_PGD_BOUNDARY, + min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY)); +} + void __init native_pagetable_init(void) { unsigned long pfn, va; -- cgit v1.2.3