From fb3bd914b3ec28f5fb697ac55c4846ac2d542855 Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Wed, 28 Jun 2023 11:02:39 +0200 Subject: x86/srso: Add a Speculative RAS Overflow mitigation Add a mitigation for the speculative return address stack overflow vulnerability found on AMD processors. The mitigation works by ensuring all RET instructions speculate to a controlled location, similar to how speculation is controlled in the retpoline sequence. To accomplish this, the __x86_return_thunk forces the CPU to mispredict every function return using a 'safe return' sequence. To ensure the safety of this mitigation, the kernel must ensure that the safe return sequence is itself free from attacker interference. In Zen3 and Zen4, this is accomplished by creating a BTB alias between the untraining function srso_untrain_ret_alias() and the safe return function srso_safe_ret_alias() which results in evicting a potentially poisoned BTB entry and using that safe one for all function returns. In older Zen1 and Zen2, this is accomplished using a reinterpretation technique similar to Retbleed one: srso_untrain_ret() and srso_safe_ret(). Signed-off-by: Borislav Petkov (AMD) --- arch/x86/include/asm/processor.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/x86/include/asm/processor.h') diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index d46300e94f85..7c67db7c9f53 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -682,9 +682,11 @@ extern u16 get_llc_id(unsigned int cpu); #ifdef CONFIG_CPU_SUP_AMD extern u32 amd_get_nodes_per_socket(void); extern u32 amd_get_highest_perf(void); +extern bool cpu_has_ibpb_brtype_microcode(void); #else static inline u32 amd_get_nodes_per_socket(void) { return 0; } static inline u32 amd_get_highest_perf(void) { return 0; } +static inline bool cpu_has_ibpb_brtype_microcode(void) { return false; } #endif extern unsigned long arch_align_stack(unsigned long sp); -- cgit From 77245f1c3c6495521f6a3af082696ee2f8ce3921 Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Sat, 5 Aug 2023 00:06:43 +0200 Subject: x86/CPU/AMD: Do not leak quotient data after a division by 0 Under certain circumstances, an integer division by 0 which faults, can leave stale quotient data from a previous division operation on Zen1 microarchitectures. Do a dummy division 0/1 before returning from the #DE exception handler in order to avoid any leaks of potentially sensitive data. Signed-off-by: Borislav Petkov (AMD) Cc: Signed-off-by: Linus Torvalds --- arch/x86/include/asm/processor.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/x86/include/asm/processor.h') diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 7c67db7c9f53..973db0406528 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -683,10 +683,12 @@ extern u16 get_llc_id(unsigned int cpu); extern u32 amd_get_nodes_per_socket(void); extern u32 amd_get_highest_perf(void); extern bool cpu_has_ibpb_brtype_microcode(void); +extern void amd_clear_divider(void); #else static inline u32 amd_get_nodes_per_socket(void) { return 0; } static inline u32 amd_get_highest_perf(void) { return 0; } static inline bool cpu_has_ibpb_brtype_microcode(void) { return false; } +static inline void amd_clear_divider(void) { } #endif extern unsigned long arch_align_stack(unsigned long sp); -- cgit From eb3515dc99c7c85f4170b50838136b2a193f8012 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 9 Aug 2023 15:05:00 +0200 Subject: x86: Move gds_ucode_mitigated() declaration to header The declaration got placed in the .c file of the caller, but that causes a warning for the definition: arch/x86/kernel/cpu/bugs.c:682:6: error: no previous prototype for 'gds_ucode_mitigated' [-Werror=missing-prototypes] Move it to a header where both sides can observe it instead. Fixes: 81ac7e5d74174 ("KVM: Add GDS_NO support to KVM") Signed-off-by: Arnd Bergmann Signed-off-by: Dave Hansen Tested-by: Daniel Sneddon Cc: stable@kernel.org Link: https://lore.kernel.org/all/20230809130530.1913368-2-arnd%40kernel.org --- arch/x86/include/asm/processor.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/x86/include/asm/processor.h') diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 973db0406528..4ae2773b873d 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -731,4 +731,6 @@ bool arch_is_platform_page(u64 paddr); #define arch_is_platform_page arch_is_platform_page #endif +extern bool gds_ucode_mitigated(void); + #endif /* _ASM_X86_PROCESSOR_H */ -- cgit From c8afaa1b0f8bc93d013ab2ea6b9649958af3f1d3 Mon Sep 17 00:00:00 2001 From: Mateusz Guzik Date: Sat, 12 Aug 2023 18:15:54 +0200 Subject: locking: remove spin_lock_prefetch The only remaining consumer is new_inode, where it showed up in 2001 as commit c37fa164f793 ("v2.4.9.9 -> v2.4.9.10") in a historical repo [1] with a changelog which does not mention it. Since then the line got only touched up to keep compiling. While it may have been of benefit back in the day, it is guaranteed to at best not get in the way in the multicore setting -- as the code performs *a lot* of work between the prefetch and actual lock acquire, any contention means the cacheline is already invalid by the time the routine calls spin_lock(). It adds spurious traffic, for short. On top of it prefetch is notoriously tricky to use for single-threaded purposes, making it questionable from the get go. As such, remove it. I admit upfront I did not see value in benchmarking this change, but I can do it if that is deemed appropriate. Removal from new_inode and of the entire thing are in the same patch as requested by Linus, so whatever weird looks can be directed at that guy. Link: https://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git/commit/fs/inode.c?id=c37fa164f793735b32aa3f53154ff1a7659e6442 [1] Signed-off-by: Mateusz Guzik Signed-off-by: Linus Torvalds --- arch/x86/include/asm/processor.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'arch/x86/include/asm/processor.h') diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 4ae2773b873d..fd750247ca89 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -586,7 +586,6 @@ extern char ignore_fpu_irq; #define HAVE_ARCH_PICK_MMAP_LAYOUT 1 #define ARCH_HAS_PREFETCHW -#define ARCH_HAS_SPINLOCK_PREFETCH #ifdef CONFIG_X86_32 # define BASE_PREFETCH "" @@ -620,11 +619,6 @@ static __always_inline void prefetchw(const void *x) "m" (*(const char *)x)); } -static inline void spin_lock_prefetch(const void *x) -{ - prefetchw(x); -} - #define TOP_OF_INIT_STACK ((unsigned long)&init_stack + sizeof(init_stack) - \ TOP_OF_KERNEL_STACK_PADDING) -- cgit