summaryrefslogtreecommitdiffstats
path: root/arch/x86/include/asm/nospec-branch.h
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-12-14 15:03:00 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2022-12-14 15:03:00 -0800
commit94a855111ed9106971ca2617c5d075269e6aefde (patch)
tree330c762a403cf70c2cdbf12e7394e5e7c2a69a79 /arch/x86/include/asm/nospec-branch.h
parent93761c93e9da28d8a020777cee2a84133082b477 (diff)
parentf1a033cc6b9eb6d80322008422df3c87aa5d47a0 (diff)
downloadlinux-94a855111ed9106971ca2617c5d075269e6aefde.tar.bz2
Merge tag 'x86_core_for_v6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 core updates from Borislav Petkov: - Add the call depth tracking mitigation for Retbleed which has been long in the making. It is a lighterweight software-only fix for Skylake-based cores where enabling IBRS is a big hammer and causes a significant performance impact. What it basically does is, it aligns all kernel functions to 16 bytes boundary and adds a 16-byte padding before the function, objtool collects all functions' locations and when the mitigation gets applied, it patches a call accounting thunk which is used to track the call depth of the stack at any time. When that call depth reaches a magical, microarchitecture-specific value for the Return Stack Buffer, the code stuffs that RSB and avoids its underflow which could otherwise lead to the Intel variant of Retbleed. This software-only solution brings a lot of the lost performance back, as benchmarks suggest: https://lore.kernel.org/all/20220915111039.092790446@infradead.org/ That page above also contains a lot more detailed explanation of the whole mechanism - Implement a new control flow integrity scheme called FineIBT which is based on the software kCFI implementation and uses hardware IBT support where present to annotate and track indirect branches using a hash to validate them - Other misc fixes and cleanups * tag 'x86_core_for_v6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (80 commits) x86/paravirt: Use common macro for creating simple asm paravirt functions x86/paravirt: Remove clobber bitmask from .parainstructions x86/debug: Include percpu.h in debugreg.h to get DECLARE_PER_CPU() et al x86/cpufeatures: Move X86_FEATURE_CALL_DEPTH from bit 18 to bit 19 of word 11, to leave space for WIP X86_FEATURE_SGX_EDECCSSA bit x86/Kconfig: Enable kernel IBT by default x86,pm: Force out-of-line memcpy() objtool: Fix weak hole vs prefix symbol objtool: Optimize elf_dirty_reloc_sym() x86/cfi: Add boot time hash randomization x86/cfi: Boot time selection of CFI scheme x86/ibt: Implement FineIBT objtool: Add --cfi to generate the .cfi_sites section x86: Add prefix symbols for function padding objtool: Add option to generate prefix symbols objtool: Avoid O(bloody terrible) behaviour -- an ode to libelf objtool: Slice up elf_create_section_symbol() kallsyms: Revert "Take callthunks into account" x86: Unconfuse CONFIG_ and X86_FEATURE_ namespaces x86/retpoline: Fix crash printing warning x86/paravirt: Fix a !PARAVIRT build warning ...
Diffstat (limited to 'arch/x86/include/asm/nospec-branch.h')
-rw-r--r--arch/x86/include/asm/nospec-branch.h176
1 files changed, 170 insertions, 6 deletions
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index dfdb103ae4f6..771b0a2b7a34 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -12,8 +12,104 @@
#include <asm/msr-index.h>
#include <asm/unwind_hints.h>
#include <asm/percpu.h>
+#include <asm/current.h>
-#define RETPOLINE_THUNK_SIZE 32
+/*
+ * Call depth tracking for Intel SKL CPUs to address the RSB underflow
+ * issue in software.
+ *
+ * The tracking does not use a counter. It uses uses arithmetic shift
+ * right on call entry and logical shift left on return.
+ *
+ * The depth tracking variable is initialized to 0x8000.... when the call
+ * depth is zero. The arithmetic shift right sign extends the MSB and
+ * saturates after the 12th call. The shift count is 5 for both directions
+ * so the tracking covers 12 nested calls.
+ *
+ * Call
+ * 0: 0x8000000000000000 0x0000000000000000
+ * 1: 0xfc00000000000000 0xf000000000000000
+ * ...
+ * 11: 0xfffffffffffffff8 0xfffffffffffffc00
+ * 12: 0xffffffffffffffff 0xffffffffffffffe0
+ *
+ * After a return buffer fill the depth is credited 12 calls before the
+ * next stuffing has to take place.
+ *
+ * There is a inaccuracy for situations like this:
+ *
+ * 10 calls
+ * 5 returns
+ * 3 calls
+ * 4 returns
+ * 3 calls
+ * ....
+ *
+ * The shift count might cause this to be off by one in either direction,
+ * but there is still a cushion vs. the RSB depth. The algorithm does not
+ * claim to be perfect and it can be speculated around by the CPU, but it
+ * is considered that it obfuscates the problem enough to make exploitation
+ * extremly difficult.
+ */
+#define RET_DEPTH_SHIFT 5
+#define RSB_RET_STUFF_LOOPS 16
+#define RET_DEPTH_INIT 0x8000000000000000ULL
+#define RET_DEPTH_INIT_FROM_CALL 0xfc00000000000000ULL
+#define RET_DEPTH_CREDIT 0xffffffffffffffffULL
+
+#ifdef CONFIG_CALL_THUNKS_DEBUG
+# define CALL_THUNKS_DEBUG_INC_CALLS \
+ incq %gs:__x86_call_count;
+# define CALL_THUNKS_DEBUG_INC_RETS \
+ incq %gs:__x86_ret_count;
+# define CALL_THUNKS_DEBUG_INC_STUFFS \
+ incq %gs:__x86_stuffs_count;
+# define CALL_THUNKS_DEBUG_INC_CTXSW \
+ incq %gs:__x86_ctxsw_count;
+#else
+# define CALL_THUNKS_DEBUG_INC_CALLS
+# define CALL_THUNKS_DEBUG_INC_RETS
+# define CALL_THUNKS_DEBUG_INC_STUFFS
+# define CALL_THUNKS_DEBUG_INC_CTXSW
+#endif
+
+#if defined(CONFIG_CALL_DEPTH_TRACKING) && !defined(COMPILE_OFFSETS)
+
+#include <asm/asm-offsets.h>
+
+#define CREDIT_CALL_DEPTH \
+ movq $-1, PER_CPU_VAR(pcpu_hot + X86_call_depth);
+
+#define ASM_CREDIT_CALL_DEPTH \
+ movq $-1, PER_CPU_VAR(pcpu_hot + X86_call_depth);
+
+#define RESET_CALL_DEPTH \
+ mov $0x80, %rax; \
+ shl $56, %rax; \
+ movq %rax, PER_CPU_VAR(pcpu_hot + X86_call_depth);
+
+#define RESET_CALL_DEPTH_FROM_CALL \
+ mov $0xfc, %rax; \
+ shl $56, %rax; \
+ movq %rax, PER_CPU_VAR(pcpu_hot + X86_call_depth); \
+ CALL_THUNKS_DEBUG_INC_CALLS
+
+#define INCREMENT_CALL_DEPTH \
+ sarq $5, %gs:pcpu_hot + X86_call_depth; \
+ CALL_THUNKS_DEBUG_INC_CALLS
+
+#define ASM_INCREMENT_CALL_DEPTH \
+ sarq $5, PER_CPU_VAR(pcpu_hot + X86_call_depth); \
+ CALL_THUNKS_DEBUG_INC_CALLS
+
+#else
+#define CREDIT_CALL_DEPTH
+#define ASM_CREDIT_CALL_DEPTH
+#define RESET_CALL_DEPTH
+#define INCREMENT_CALL_DEPTH
+#define ASM_INCREMENT_CALL_DEPTH
+#define RESET_CALL_DEPTH_FROM_CALL
+#endif
/*
* Fill the CPU return stack buffer.
@@ -32,6 +128,7 @@
* from C via asm(".include <asm/nospec-branch.h>") but let's not go there.
*/
+#define RETPOLINE_THUNK_SIZE 32
#define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */
/*
@@ -60,7 +157,9 @@
dec reg; \
jnz 771b; \
/* barrier for jnz misprediction */ \
- lfence;
+ lfence; \
+ ASM_CREDIT_CALL_DEPTH \
+ CALL_THUNKS_DEBUG_INC_CTXSW
#else
/*
* i386 doesn't unconditionally have LFENCE, as such it can't
@@ -185,11 +284,32 @@
* where we have a stack but before any RET instruction.
*/
.macro UNTRAIN_RET
-#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY)
+#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \
+ defined(CONFIG_CALL_DEPTH_TRACKING)
ANNOTATE_UNRET_END
- ALTERNATIVE_2 "", \
- CALL_ZEN_UNTRAIN_RET, X86_FEATURE_UNRET, \
- "call entry_ibpb", X86_FEATURE_ENTRY_IBPB
+ ALTERNATIVE_3 "", \
+ CALL_ZEN_UNTRAIN_RET, X86_FEATURE_UNRET, \
+ "call entry_ibpb", X86_FEATURE_ENTRY_IBPB, \
+ __stringify(RESET_CALL_DEPTH), X86_FEATURE_CALL_DEPTH
+#endif
+.endm
+
+.macro UNTRAIN_RET_FROM_CALL
+#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \
+ defined(CONFIG_CALL_DEPTH_TRACKING)
+ ANNOTATE_UNRET_END
+ ALTERNATIVE_3 "", \
+ CALL_ZEN_UNTRAIN_RET, X86_FEATURE_UNRET, \
+ "call entry_ibpb", X86_FEATURE_ENTRY_IBPB, \
+ __stringify(RESET_CALL_DEPTH_FROM_CALL), X86_FEATURE_CALL_DEPTH
+#endif
+.endm
+
+
+.macro CALL_DEPTH_ACCOUNT
+#ifdef CONFIG_CALL_DEPTH_TRACKING
+ ALTERNATIVE "", \
+ __stringify(ASM_INCREMENT_CALL_DEPTH), X86_FEATURE_CALL_DEPTH
#endif
.endm
@@ -203,11 +323,45 @@
typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE];
extern retpoline_thunk_t __x86_indirect_thunk_array[];
+extern retpoline_thunk_t __x86_indirect_call_thunk_array[];
+extern retpoline_thunk_t __x86_indirect_jump_thunk_array[];
extern void __x86_return_thunk(void);
extern void zen_untrain_ret(void);
extern void entry_ibpb(void);
+#ifdef CONFIG_CALL_THUNKS
+extern void (*x86_return_thunk)(void);
+#else
+#define x86_return_thunk (&__x86_return_thunk)
+#endif
+
+#ifdef CONFIG_CALL_DEPTH_TRACKING
+extern void __x86_return_skl(void);
+
+static inline void x86_set_skl_return_thunk(void)
+{
+ x86_return_thunk = &__x86_return_skl;
+}
+
+#define CALL_DEPTH_ACCOUNT \
+ ALTERNATIVE("", \
+ __stringify(INCREMENT_CALL_DEPTH), \
+ X86_FEATURE_CALL_DEPTH)
+
+#ifdef CONFIG_CALL_THUNKS_DEBUG
+DECLARE_PER_CPU(u64, __x86_call_count);
+DECLARE_PER_CPU(u64, __x86_ret_count);
+DECLARE_PER_CPU(u64, __x86_stuffs_count);
+DECLARE_PER_CPU(u64, __x86_ctxsw_count);
+#endif
+#else
+static inline void x86_set_skl_return_thunk(void) {}
+
+#define CALL_DEPTH_ACCOUNT ""
+
+#endif
+
#ifdef CONFIG_RETPOLINE
#define GEN(reg) \
@@ -215,6 +369,16 @@ extern void entry_ibpb(void);
#include <asm/GEN-for-each-reg.h>
#undef GEN
+#define GEN(reg) \
+ extern retpoline_thunk_t __x86_indirect_call_thunk_ ## reg;
+#include <asm/GEN-for-each-reg.h>
+#undef GEN
+
+#define GEN(reg) \
+ extern retpoline_thunk_t __x86_indirect_jump_thunk_ ## reg;
+#include <asm/GEN-for-each-reg.h>
+#undef GEN
+
#ifdef CONFIG_X86_64
/*