aboutsummaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
authorLinus Torvalds2018-01-29 19:08:02 -0800
committerLinus Torvalds2018-01-29 19:08:02 -0800
commit6304672b7f0a5c010002e63a075160856dc4f88d (patch)
tree3f2d7fbaa9fe998787fa474c63fb1e6aa98090ab /arch
parent942633523cde99c5bfa0329996dd839ca66a87aa (diff)
parent64e16720ea0879f8ab4547e3b9758936d483909b (diff)
Merge branch 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86/pti updates from Thomas Gleixner: "Another set of melted spectrum related changes: - Code simplifications and cleanups for RSB and retpolines. - Make the indirect calls in KVM speculation safe. - Whitelist CPUs which are known not to speculate from Meltdown and prepare for the new CPUID flag which tells the kernel that a CPU is not affected. - A less rigorous variant of the module retpoline check which merily warns when a non-retpoline protected module is loaded and reflects that fact in the sysfs file. - Prepare for Indirect Branch Prediction Barrier support. - Prepare for exposure of the Speculation Control MSRs to guests, so guest OSes which depend on those "features" can use them. Includes a blacklist of the broken microcodes. The actual exposure of the MSRs through KVM is still being worked on" * 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: x86/speculation: Simplify indirect_branch_prediction_barrier() x86/retpoline: Simplify vmexit_fill_RSB() x86/cpufeatures: Clean up Spectre v2 related CPUID flags x86/cpu/bugs: Make retpoline module warning conditional x86/bugs: Drop one "mitigation" from dmesg x86/nospec: Fix header guards names x86/alternative: Print unadorned pointers x86/speculation: Add basic IBPB (Indirect Branch Prediction Barrier) support x86/cpufeature: Blacklist SPEC_CTRL/PRED_CMD on early Spectre v2 microcodes x86/pti: Do not enable PTI on CPUs which are not vulnerable to Meltdown x86/msr: Add definitions for new speculation control MSRs x86/cpufeatures: Add AMD feature bits for Speculation Control x86/cpufeatures: Add Intel feature bits for Speculation Control x86/cpufeatures: Add CPUID_7_EDX CPUID leaf module/retpoline: Warn about missing retpoline in module KVM: VMX: Make indirect call speculation safe KVM: x86: Make indirect calls in emulator speculation safe
Diffstat (limited to 'arch')
-rw-r--r--arch/x86/entry/entry_32.S3
-rw-r--r--arch/x86/entry/entry_64.S3
-rw-r--r--arch/x86/include/asm/asm-prototypes.h3
-rw-r--r--arch/x86/include/asm/cpufeature.h7
-rw-r--r--arch/x86/include/asm/cpufeatures.h22
-rw-r--r--arch/x86/include/asm/disabled-features.h3
-rw-r--r--arch/x86/include/asm/msr-index.h12
-rw-r--r--arch/x86/include/asm/nospec-branch.h84
-rw-r--r--arch/x86/include/asm/processor.h3
-rw-r--r--arch/x86/include/asm/required-features.h3
-rw-r--r--arch/x86/kernel/alternative.c14
-rw-r--r--arch/x86/kernel/cpu/bugs.c40
-rw-r--r--arch/x86/kernel/cpu/common.c49
-rw-r--r--arch/x86/kernel/cpu/intel.c77
-rw-r--r--arch/x86/kernel/cpu/scattered.c2
-rw-r--r--arch/x86/kvm/emulate.c9
-rw-r--r--arch/x86/kvm/vmx.c4
-rw-r--r--arch/x86/lib/Makefile1
-rw-r--r--arch/x86/lib/retpoline.S56
19 files changed, 295 insertions, 100 deletions
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 60c4c342316c..2a35b1e0fb90 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -252,7 +252,8 @@ ENTRY(__switch_to_asm)
* exist, overwrite the RSB with entries which capture
* speculative execution to prevent attack.
*/
- FILL_RETURN_BUFFER %ebx, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
+ /* Clobbers %ebx */
+ FILL_RETURN_BUFFER RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
#endif
/* restore callee-saved registers */
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index ff6f8022612c..a83570495162 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -499,7 +499,8 @@ ENTRY(__switch_to_asm)
* exist, overwrite the RSB with entries which capture
* speculative execution to prevent attack.
*/
- FILL_RETURN_BUFFER %r12, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
+ /* Clobbers %rbx */
+ FILL_RETURN_BUFFER RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
#endif
/* restore callee-saved registers */
diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h
index 1908214b9125..4d111616524b 100644
--- a/arch/x86/include/asm/asm-prototypes.h
+++ b/arch/x86/include/asm/asm-prototypes.h
@@ -38,4 +38,7 @@ INDIRECT_THUNK(dx)
INDIRECT_THUNK(si)
INDIRECT_THUNK(di)
INDIRECT_THUNK(bp)
+asmlinkage void __fill_rsb(void);
+asmlinkage void __clear_rsb(void);
+
#endif /* CONFIG_RETPOLINE */
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index ea9a7dde62e5..70eddb3922ff 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -29,6 +29,7 @@ enum cpuid_leafs
CPUID_8000_000A_EDX,
CPUID_7_ECX,
CPUID_8000_0007_EBX,
+ CPUID_7_EDX,
};
#ifdef CONFIG_X86_FEATURE_NAMES
@@ -79,8 +80,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 15, feature_bit) || \
CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 16, feature_bit) || \
CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 17, feature_bit) || \
+ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) || \
REQUIRED_MASK_CHECK || \
- BUILD_BUG_ON_ZERO(NCAPINTS != 18))
+ BUILD_BUG_ON_ZERO(NCAPINTS != 19))
#define DISABLED_MASK_BIT_SET(feature_bit) \
( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 0, feature_bit) || \
@@ -101,8 +103,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 15, feature_bit) || \
CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 16, feature_bit) || \
CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 17, feature_bit) || \
+ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) || \
DISABLED_MASK_CHECK || \
- BUILD_BUG_ON_ZERO(NCAPINTS != 18))
+ BUILD_BUG_ON_ZERO(NCAPINTS != 19))
#define cpu_has(c, bit) \
(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 67bbfaa1448b..1d9199e1c2ad 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -13,7 +13,7 @@
/*
* Defines x86 CPU feature bits
*/
-#define NCAPINTS 18 /* N 32-bit words worth of info */
+#define NCAPINTS 19 /* N 32-bit words worth of info */
#define NBUGINTS 1 /* N 32-bit bug flags */
/*
@@ -203,15 +203,15 @@
#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
#define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */
#define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */
-#define X86_FEATURE_RETPOLINE ( 7*32+12) /* Generic Retpoline mitigation for Spectre variant 2 */
-#define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* AMD Retpoline mitigation for Spectre variant 2 */
+#define X86_FEATURE_RETPOLINE ( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */
+#define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */
#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */
#define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */
-#define X86_FEATURE_AVX512_4VNNIW ( 7*32+16) /* AVX-512 Neural Network Instructions */
-#define X86_FEATURE_AVX512_4FMAPS ( 7*32+17) /* AVX-512 Multiply Accumulation Single precision */
#define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */
-#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* Fill RSB on context switches */
+#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */
+
+#define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */
/* Virtualization flags: Linux defined, word 8 */
#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */
@@ -272,6 +272,9 @@
#define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */
#define X86_FEATURE_IRPERF (13*32+ 1) /* Instructions Retired Count */
#define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* Always save/restore FP error pointers */
+#define X86_FEATURE_IBPB (13*32+12) /* Indirect Branch Prediction Barrier */
+#define X86_FEATURE_IBRS (13*32+14) /* Indirect Branch Restricted Speculation */
+#define X86_FEATURE_STIBP (13*32+15) /* Single Thread Indirect Branch Predictors */
/* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
#define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */
@@ -320,6 +323,13 @@
#define X86_FEATURE_SUCCOR (17*32+ 1) /* Uncorrectable error containment and recovery */
#define X86_FEATURE_SMCA (17*32+ 3) /* Scalable MCA */
+/* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
+#define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */
+#define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */
+#define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
+
/*
* BUG word(s)
*/
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index b027633e7300..33833d1909af 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -77,6 +77,7 @@
#define DISABLED_MASK15 0
#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP)
#define DISABLED_MASK17 0
-#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
+#define DISABLED_MASK18 0
+#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)
#endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index e7b983a35506..e520a1e6fc11 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -39,6 +39,13 @@
/* Intel MSRs. Some also available on other CPUs */
+#define MSR_IA32_SPEC_CTRL 0x00000048 /* Speculation Control */
+#define SPEC_CTRL_IBRS (1 << 0) /* Indirect Branch Restricted Speculation */
+#define SPEC_CTRL_STIBP (1 << 1) /* Single Thread Indirect Branch Predictors */
+
+#define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */
+#define PRED_CMD_IBPB (1 << 0) /* Indirect Branch Prediction Barrier */
+
#define MSR_PPIN_CTL 0x0000004e
#define MSR_PPIN 0x0000004f
@@ -57,6 +64,11 @@
#define SNB_C3_AUTO_UNDEMOTE (1UL << 28)
#define MSR_MTRRcap 0x000000fe
+
+#define MSR_IA32_ARCH_CAPABILITIES 0x0000010a
+#define ARCH_CAP_RDCL_NO (1 << 0) /* Not susceptible to Meltdown */
+#define ARCH_CAP_IBRS_ALL (1 << 1) /* Enhanced IBRS support */
+
#define MSR_IA32_BBL_CR_CTL 0x00000119
#define MSR_IA32_BBL_CR_CTL3 0x0000011e
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 4ad41087ce0e..d15d471348b8 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -1,56 +1,12 @@
/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __NOSPEC_BRANCH_H__
-#define __NOSPEC_BRANCH_H__
+#ifndef _ASM_X86_NOSPEC_BRANCH_H_
+#define _ASM_X86_NOSPEC_BRANCH_H_
#include <asm/alternative.h>
#include <asm/alternative-asm.h>
#include <asm/cpufeatures.h>
-/*
- * Fill the CPU return stack buffer.
- *
- * Each entry in the RSB, if used for a speculative 'ret', contains an
- * infinite 'pause; lfence; jmp' loop to capture speculative execution.
- *
- * This is required in various cases for retpoline and IBRS-based
- * mitigations for the Spectre variant 2 vulnerability. Sometimes to
- * eliminate potentially bogus entries from the RSB, and sometimes
- * purely to ensure that it doesn't get empty, which on some CPUs would
- * allow predictions from other (unwanted!) sources to be used.
- *
- * We define a CPP macro such that it can be used from both .S files and
- * inline assembly. It's possible to do a .macro and then include that
- * from C via asm(".include <asm/nospec-branch.h>") but let's not go there.
- */
-
-#define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */
-#define RSB_FILL_LOOPS 16 /* To avoid underflow */
-
-/*
- * Google experimented with loop-unrolling and this turned out to be
- * the optimal version — two calls, each with their own speculation
- * trap should their return address end up getting used, in a loop.
- */
-#define __FILL_RETURN_BUFFER(reg, nr, sp) \
- mov $(nr/2), reg; \
-771: \
- call 772f; \
-773: /* speculation trap */ \
- pause; \
- lfence; \
- jmp 773b; \
-772: \
- call 774f; \
-775: /* speculation trap */ \
- pause; \
- lfence; \
- jmp 775b; \
-774: \
- dec reg; \
- jnz 771b; \
- add $(BITS_PER_LONG/8) * nr, sp;
-
#ifdef __ASSEMBLY__
/*
@@ -121,17 +77,10 @@
#endif
.endm
- /*
- * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP
- * monstrosity above, manually.
- */
-.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req
+/* This clobbers the BX register */
+.macro FILL_RETURN_BUFFER nr:req ftr:req
#ifdef CONFIG_RETPOLINE
- ANNOTATE_NOSPEC_ALTERNATIVE
- ALTERNATIVE "jmp .Lskip_rsb_\@", \
- __stringify(__FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP)) \
- \ftr
-.Lskip_rsb_\@:
+ ALTERNATIVE "", "call __clear_rsb", \ftr
#endif
.endm
@@ -206,17 +155,20 @@ extern char __indirect_thunk_end[];
static inline void vmexit_fill_RSB(void)
{
#ifdef CONFIG_RETPOLINE
- unsigned long loops;
-
- asm volatile (ANNOTATE_NOSPEC_ALTERNATIVE
- ALTERNATIVE("jmp 910f",
- __stringify(__FILL_RETURN_BUFFER(%0, RSB_CLEAR_LOOPS, %1)),
- X86_FEATURE_RETPOLINE)
- "910:"
- : "=r" (loops), ASM_CALL_CONSTRAINT
- : : "memory" );
+ alternative_input("",
+ "call __fill_rsb",
+ X86_FEATURE_RETPOLINE,
+ ASM_NO_INPUT_CLOBBER(_ASM_BX, "memory"));
#endif
}
+static inline void indirect_branch_prediction_barrier(void)
+{
+ alternative_input("",
+ "call __ibp_barrier",
+ X86_FEATURE_USE_IBPB,
+ ASM_NO_INPUT_CLOBBER("eax", "ecx", "edx", "memory"));
+}
+
#endif /* __ASSEMBLY__ */
-#endif /* __NOSPEC_BRANCH_H__ */
+#endif /* _ASM_X86_NOSPEC_BRANCH_H_ */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index d3a67fba200a..efbde088a718 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -971,4 +971,7 @@ bool xen_set_default_idle(void);
void stop_this_cpu(void *dummy);
void df_debug(struct pt_regs *regs, long error_code);
+
+void __ibp_barrier(void);
+
#endif /* _ASM_X86_PROCESSOR_H */
diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h
index d91ba04dd007..fb3a6de7440b 100644
--- a/arch/x86/include/asm/required-features.h
+++ b/arch/x86/include/asm/required-features.h
@@ -106,6 +106,7 @@
#define REQUIRED_MASK15 0
#define REQUIRED_MASK16 (NEED_LA57)
#define REQUIRED_MASK17 0
-#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
+#define REQUIRED_MASK18 0
+#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)
#endif /* _ASM_X86_REQUIRED_FEATURES_H */
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 4817d743c263..30571fdaaf6f 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -298,7 +298,7 @@ recompute_jump(struct alt_instr *a, u8 *orig_insn, u8 *repl_insn, u8 *insnbuf)
tgt_rip = next_rip + o_dspl;
n_dspl = tgt_rip - orig_insn;
- DPRINTK("target RIP: %p, new_displ: 0x%x", tgt_rip, n_dspl);
+ DPRINTK("target RIP: %px, new_displ: 0x%x", tgt_rip, n_dspl);
if (tgt_rip - orig_insn >= 0) {
if (n_dspl - 2 <= 127)
@@ -355,7 +355,7 @@ static void __init_or_module noinline optimize_nops(struct alt_instr *a, u8 *ins
add_nops(instr + (a->instrlen - a->padlen), a->padlen);
local_irq_restore(flags);
- DUMP_BYTES(instr, a->instrlen, "%p: [%d:%d) optimized NOPs: ",
+ DUMP_BYTES(instr, a->instrlen, "%px: [%d:%d) optimized NOPs: ",
instr, a->instrlen - a->padlen, a->padlen);
}
@@ -376,7 +376,7 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
u8 *instr, *replacement;
u8 insnbuf[MAX_PATCH_LEN];
- DPRINTK("alt table %p -> %p", start, end);
+ DPRINTK("alt table %px, -> %px", start, end);
/*
* The scan order should be from start to end. A later scanned
* alternative code can overwrite previously scanned alternative code.
@@ -400,14 +400,14 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
continue;
}
- DPRINTK("feat: %d*32+%d, old: (%p, len: %d), repl: (%p, len: %d), pad: %d",
+ DPRINTK("feat: %d*32+%d, old: (%px len: %d), repl: (%px, len: %d), pad: %d",
a->cpuid >> 5,
a->cpuid & 0x1f,
instr, a->instrlen,
replacement, a->replacementlen, a->padlen);
- DUMP_BYTES(instr, a->instrlen, "%p: old_insn: ", instr);
- DUMP_BYTES(replacement, a->replacementlen, "%p: rpl_insn: ", replacement);
+ DUMP_BYTES(instr, a->instrlen, "%px: old_insn: ", instr);
+ DUMP_BYTES(replacement, a->replacementlen, "%px: rpl_insn: ", replacement);
memcpy(insnbuf, replacement, a->replacementlen);
insnbuf_sz = a->replacementlen;
@@ -433,7 +433,7 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
a->instrlen - a->replacementlen);
insnbuf_sz += a->instrlen - a->replacementlen;
}
- DUMP_BYTES(insnbuf, insnbuf_sz, "%p: final_insn: ", instr);
+ DUMP_BYTES(insnbuf, insnbuf_sz, "%px: final_insn: ", instr);
text_poke_early(instr, insnbuf, insnbuf_sz);
}
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 390b3dc3d438..3bfb2b23d79c 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -11,6 +11,7 @@
#include <linux/init.h>
#include <linux/utsname.h>
#include <linux/cpu.h>
+#include <linux/module.h>
#include <asm/nospec-branch.h>
#include <asm/cmdline.h>
@@ -90,10 +91,31 @@ static const char *spectre_v2_strings[] = {
};
#undef pr_fmt
-#define pr_fmt(fmt) "Spectre V2 mitigation: " fmt
+#define pr_fmt(fmt) "Spectre V2 : " fmt
static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE;
+#ifdef RETPOLINE
+static bool spectre_v2_bad_module;
+
+bool retpoline_module_ok(bool has_retpoline)
+{
+ if (spectre_v2_enabled == SPECTRE_V2_NONE || has_retpoline)
+ return true;
+
+ pr_err("System may be vunerable to spectre v2\n");
+ spectre_v2_bad_module = true;
+ return false;
+}
+
+static inline const char *spectre_v2_module_string(void)
+{
+ return spectre_v2_bad_module ? " - vulnerable module loaded" : "";
+}
+#else
+static inline const char *spectre_v2_module_string(void) { return ""; }
+#endif
+
static void __init spec2_print_if_insecure(const char *reason)
{
if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
@@ -249,6 +271,12 @@ retpoline_auto:
setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
pr_info("Filling RSB on context switch\n");
}
+
+ /* Initialize Indirect Branch Prediction Barrier if supported */
+ if (boot_cpu_has(X86_FEATURE_IBPB)) {
+ setup_force_cpu_cap(X86_FEATURE_USE_IBPB);
+ pr_info("Enabling Indirect Branch Prediction Barrier\n");
+ }
}
#undef pr_fmt
@@ -278,6 +306,14 @@ ssize_t cpu_show_spectre_v2(struct device *dev,
if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
return sprintf(buf, "Not affected\n");
- return sprintf(buf, "%s\n", spectre_v2_strings[spectre_v2_enabled]);
+ return sprintf(buf, "%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
+ boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "",
+ spectre_v2_module_string());
}
#endif
+
+void __ibp_barrier(void)
+{
+ __wrmsr(MSR_IA32_PRED_CMD, PRED_CMD_IBPB, 0);
+}
+EXPORT_SYMBOL_GPL(__ibp_barrier);
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index ef29ad001991..c7c996a692fd 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -47,6 +47,8 @@
#include <asm/pat.h>
#include <asm/microcode.h>
#include <asm/microcode_intel.h>
+#include <asm/intel-family.h>
+#include <asm/cpu_device_id.h>
#ifdef CONFIG_X86_LOCAL_APIC
#include <asm/uv/uv.h>
@@ -769,6 +771,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
cpuid_count(0x00000007, 0, &eax, &ebx, &ecx, &edx);
c->x86_capability[CPUID_7_0_EBX] = ebx;
c->x86_capability[CPUID_7_ECX] = ecx;
+ c->x86_capability[CPUID_7_EDX] = edx;
}
/* Extended state features: level 0x0000000d */
@@ -876,6 +879,41 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
#endif
}
+static const __initdata struct x86_cpu_id cpu_no_speculation[] = {
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CEDARVIEW, X86_FEATURE_ANY },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CLOVERVIEW, X86_FEATURE_ANY },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_LINCROFT, X86_FEATURE_ANY },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PENWELL, X86_FEATURE_ANY },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PINEVIEW, X86_FEATURE_ANY },
+ { X86_VENDOR_CENTAUR, 5 },
+ { X86_VENDOR_INTEL, 5 },
+ { X86_VENDOR_NSC, 5 },
+ { X86_VENDOR_ANY, 4 },
+ {}
+};
+
+static const __initdata struct x86_cpu_id cpu_no_meltdown[] = {
+ { X86_VENDOR_AMD },
+ {}
+};
+
+static bool __init cpu_vulnerable_to_meltdown(struct cpuinfo_x86 *c)
+{
+ u64 ia32_cap = 0;
+
+ if (x86_match_cpu(cpu_no_meltdown))
+ return false;
+
+ if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES))
+ rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap);
+
+ /* Rogue Data Cache Load? No! */
+ if (ia32_cap & ARCH_CAP_RDCL_NO)
+ return false;
+
+ return true;
+}
+
/*
* Do minimum CPU detection early.
* Fields really needed: vendor, cpuid_level, family, model, mask,
@@ -923,11 +961,12 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
setup_force_cpu_cap(X86_FEATURE_ALWAYS);
- if (c->x86_vendor != X86_VENDOR_AMD)
- setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
-
- setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
- setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
+ if (!x86_match_cpu(cpu_no_speculation)) {
+ if (cpu_vulnerable_to_meltdown(c))
+ setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
+ setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
+ setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
+ }
fpu__init_system(c);
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index b1af22073e28..6936d14d4c77 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -102,6 +102,59 @@ static void probe_xeon_phi_r3mwait(struct cpuinfo_x86 *c)
ELF_HWCAP2 |= HWCAP2_RING3MWAIT;
}
+/*
+ * Early microcode releases for the Spectre v2 mitigation were broken.
+ * Information taken from;
+ * - https://newsroom.intel.com/wp-content/uploads/sites/11/2018/01/microcode-update-guidance.pdf
+ * - https://kb.vmware.com/s/article/52345
+ * - Microcode revisions observed in the wild
+ * - Release note from 20180108 microcode release
+ */
+struct sku_microcode {
+ u8 model;
+ u8 stepping;
+ u32 microcode;
+};
+static const struct sku_microcode spectre_bad_microcodes[] = {
+ { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0B, 0x84 },
+ { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0A, 0x84 },
+ { INTEL_FAM6_KABYLAKE_DESKTOP, 0x09, 0x84 },
+ { INTEL_FAM6_KABYLAKE_MOBILE, 0x0A, 0x84 },
+ { INTEL_FAM6_KABYLAKE_MOBILE, 0x09, 0x84 },
+ { INTEL_FAM6_SKYLAKE_X, 0x03, 0x0100013e },
+ { INTEL_FAM6_SKYLAKE_X, 0x04, 0x0200003c },
+ { INTEL_FAM6_SKYLAKE_MOBILE, 0x03, 0xc2 },
+ { INTEL_FAM6_SKYLAKE_DESKTOP, 0x03, 0xc2 },
+ { INTEL_FAM6_BROADWELL_CORE, 0x04, 0x28 },
+ { INTEL_FAM6_BROADWELL_GT3E, 0x01, 0x1b },
+ { INTEL_FAM6_BROADWELL_XEON_D, 0x02, 0x14 },
+ { INTEL_FAM6_BROADWELL_XEON_D, 0x03, 0x07000011 },
+ { INTEL_FAM6_BROADWELL_X, 0x01, 0x0b000025 },
+ { INTEL_FAM6_HASWELL_ULT, 0x01, 0x21 },
+ { INTEL_FAM6_HASWELL_GT3E, 0x01, 0x18 },
+ { INTEL_FAM6_HASWELL_CORE, 0x03, 0x23 },
+ { INTEL_FAM6_HASWELL_X, 0x02, 0x3b },
+ { INTEL_FAM6_HASWELL_X, 0x04, 0x10 },
+ { INTEL_FAM6_IVYBRIDGE_X, 0x04, 0x42a },
+ /* Updated in the 20180108 release; blacklist until we know otherwise */
+ { INTEL_FAM6_ATOM_GEMINI_LAKE, 0x01, 0x22 },
+ /* Observed in the wild */
+ { INTEL_FAM6_SANDYBRIDGE_X, 0x06, 0x61b },
+ { INTEL_FAM6_SANDYBRIDGE_X, 0x07, 0x712 },
+};
+
+static bool bad_spectre_microcode(struct cpuinfo_x86 *c)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) {
+ if (c->x86_model == spectre_bad_microcodes[i].model &&
+ c->x86_mask == spectre_bad_microcodes[i].stepping)
+ return (c->microcode <= spectre_bad_microcodes[i].microcode);
+ }
+ return false;
+}
+
static void early_init_intel(struct cpuinfo_x86 *c)
{
u64 misc_enable;
@@ -123,6 +176,30 @@ static void early_init_intel(struct cpuinfo_x86 *c)
c->microcode = intel_get_microcode_revision();
/*
+ * The Intel SPEC_CTRL CPUID bit implies IBRS and IBPB support,
+ * and they also have a different bit for STIBP support. Also,
+ * a hypervisor might have set the individual AMD bits even on
+ * Intel CPUs, for finer-grained selection of what's available.
+ */
+ if (cpu_has(c, X86_FEATURE_SPEC_CTRL)) {
+ set_cpu_cap(c, X86_FEATURE_IBRS);
+ set_cpu_cap(c, X86_FEATURE_IBPB);
+ }
+ if (cpu_has(c, X86_FEATURE_INTEL_STIBP))
+ set_cpu_cap(c, X86_FEATURE_STIBP);
+
+ /* Now if any of them are set, check the blacklist and clear the lot */
+ if ((cpu_has(c, X86_FEATURE_IBRS) || cpu_has(c, X86_FEATURE_IBPB) ||
+ cpu_has(c, X86_FEATURE_STIBP)) && bad_spectre_microcode(c)) {
+ pr_warn("Intel Spectre v2 broken microcode detected; disabling Speculation Control\n");
+ clear_cpu_cap(c, X86_FEATURE_IBRS);
+ clear_cpu_cap(c, X86_FEATURE_IBPB);
+ clear_cpu_cap(c, X86_FEATURE_STIBP);
+ clear_cpu_cap(c, X86_FEATURE_SPEC_CTRL);
+ clear_cpu_cap(c, X86_FEATURE_INTEL_STIBP);
+ }
+
+ /*
* Atom erratum AAE44/AAF40/AAG38/AAH41:
*
* A race condition between speculative fetches and invalidating
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index df4d8f7595a5..4075d2be5357 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -21,8 +21,6 @@ struct cpuid_bit {
static const struct cpuid_bit cpuid_bits[] = {
{ X86_FEATURE_APERFMPERF, CPUID_ECX, 0, 0x00000006, 0 },
{ X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 },
- { X86_FEATURE_AVX512_4VNNIW, CPUID_EDX, 2, 0x00000007, 0 },
- { X86_FEATURE_AVX512_4FMAPS, CPUID_EDX, 3, 0x00000007, 0 },
{ X86_FEATURE_CAT_L3, CPUID_EBX, 1, 0x00000010, 0 },
{ X86_FEATURE_CAT_L2, CPUID_EBX, 2, 0x00000010, 0 },
{ X86_FEATURE_CDP_L3, CPUID_ECX, 2, 0x00000010, 1 },
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index b514b2b2845a..290ecf711aec 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -25,6 +25,7 @@
#include <asm/kvm_emulate.h>
#include <linux/stringify.h>
#include <asm/debugreg.h>
+#include <asm/nospec-branch.h>
#include "x86.h"
#include "tss.h"
@@ -1021,8 +1022,8 @@ static __always_inline u8 test_cc(unsigned int condition, unsigned long flags)
void (*fop)(void) = (void *)em_setcc + 4 * (condition & 0xf);
flags = (flags & EFLAGS_MASK) | X86_EFLAGS_IF;
- asm("push %[flags]; popf; call *%[fastop]"
- : "=a"(rc) : [fastop]"r"(fop), [flags]"r"(flags));
+ asm("push %[flags]; popf; " CALL_NOSPEC
+ : "=a"(rc) : [thunk_target]"r"(fop), [flags]"r"(flags));
return rc;
}
@@ -5335,9 +5336,9 @@ static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *))
if (!(ctxt->d & ByteOp))
fop += __ffs(ctxt->dst.bytes) * FASTOP_SIZE;
- asm("push %[flags]; popf; call *%[fastop]; pushf; pop %[flags]\n"
+ asm("push %[flags]; popf; " CALL_NOSPEC " ; pushf; pop %[flags]\n"
: "+a"(ctxt->dst.val), "+d"(ctxt->src.val), [flags]"+D"(flags),
- [fastop]"+S"(fop), ASM_CALL_CONSTRAINT
+ [thunk_target]"+S"(fop), ASM_CALL_CONSTRAINT
: "c"(ctxt->src2.val));
ctxt->eflags = (ctxt->eflags & ~EFLAGS_MASK) | (flags & EFLAGS_MASK);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c829d89e2e63..a8b96dc4cd83 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -9129,14 +9129,14 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
#endif
"pushf\n\t"
__ASM_SIZE(push) " $%c[cs]\n\t"
- "call *%[entry]\n\t"
+ CALL_NOSPEC
:
#ifdef CONFIG_X86_64
[sp]"=&r"(tmp),
#endif
ASM_CALL_CONSTRAINT
:
- [entry]"r"(entry),
+ THUNK_TARGET(entry),
[ss]"i"(__KERNEL_DS),
[cs]"i"(__KERNEL_CS)
);
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index f23934bbaf4e..69a473919260 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -27,6 +27,7 @@ lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o insn-eval.o
lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o
lib-$(CONFIG_RETPOLINE) += retpoline.o
+OBJECT_FILES_NON_STANDARD_retpoline.o :=y
obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index c909961e678a..480edc3a5e03 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -7,6 +7,7 @@
#include <asm/alternative-asm.h>
#include <asm/export.h>
#include <asm/nospec-branch.h>
+#include <asm/bitsperlong.h>
.macro THUNK reg
.section .text.__x86.indirect_thunk
@@ -46,3 +47,58 @@ GENERATE_THUNK(r13)
GENERATE_THUNK(r14)
GENERATE_THUNK(r15)
#endif
+
+/*
+ * Fill the CPU return stack buffer.
+ *
+ * Each entry in the RSB, if used for a speculative 'ret', contains an
+ * infinite 'pause; lfence; jmp' loop to capture speculative execution.
+ *
+ * This is required in various cases for retpoline and IBRS-based
+ * mitigations for the Spectre variant 2 vulnerability. Sometimes to
+ * eliminate potentially bogus entries from the RSB, and sometimes
+ * purely to ensure that it doesn't get empty, which on some CPUs would
+ * allow predictions from other (unwanted!) sources to be used.
+ *
+ * Google experimented with loop-unrolling and this turned out to be
+ * the optimal version - two calls, each with their own speculation
+ * trap should their return address end up getting used, in a loop.
+ */
+.macro STUFF_RSB nr:req sp:req
+ mov $(\nr / 2), %_ASM_BX
+ .align 16
+771:
+ call 772f
+773: /* speculation trap */
+ pause
+ lfence
+ jmp 773b
+ .align 16
+772:
+ call 774f
+775: /* speculation trap */
+ pause
+ lfence
+ jmp 775b
+ .align 16
+774:
+ dec %_ASM_BX
+ jnz 771b
+ add $((BITS_PER_LONG/8) * \nr), \sp
+.endm
+
+#define RSB_FILL_LOOPS 16 /* To avoid underflow */
+
+ENTRY(__fill_rsb)
+ STUFF_RSB RSB_FILL_LOOPS, %_ASM_SP
+ ret
+END(__fill_rsb)
+EXPORT_SYMBOL_GPL(__fill_rsb)
+
+#define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */
+
+ENTRY(__clear_rsb)
+ STUFF_RSB RSB_CLEAR_LOOPS, %_ASM_SP
+ ret
+END(__clear_rsb)
+EXPORT_SYMBOL_GPL(__clear_rsb)