summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/boot/compressed/eboot.c6
-rw-r--r--arch/x86/boot/compressed/head_64.S79
-rw-r--r--arch/x86/boot/compressed/pgtable_64.c14
-rw-r--r--arch/x86/include/asm/cpufeature.h15
-rw-r--r--arch/x86/include/asm/cpufeatures.h20
-rw-r--r--arch/x86/include/asm/insn.h18
-rw-r--r--arch/x86/include/asm/kvm_host.h2
-rw-r--r--arch/x86/include/asm/mmu_context.h2
-rw-r--r--arch/x86/include/asm/msr-index.h9
-rw-r--r--arch/x86/include/asm/nospec-branch.h43
-rw-r--r--arch/x86/include/asm/pkeys.h18
-rw-r--r--arch/x86/include/asm/spec-ctrl.h80
-rw-r--r--arch/x86/include/asm/thread_info.h4
-rw-r--r--arch/x86/include/uapi/asm/kvm_para.h2
-rw-r--r--arch/x86/kernel/amd_nb.c6
-rw-r--r--arch/x86/kernel/apic/x2apic_cluster.c1
-rw-r--r--arch/x86/kernel/cpu/amd.c22
-rw-r--r--arch/x86/kernel/cpu/bugs.c397
-rw-r--r--arch/x86/kernel/cpu/common.c67
-rw-r--r--arch/x86/kernel/cpu/cpu.h2
-rw-r--r--arch/x86/kernel/cpu/intel.c3
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_amd.c29
-rw-r--r--arch/x86/kernel/head64.c10
-rw-r--r--arch/x86/kernel/kprobes/core.c4
-rw-r--r--arch/x86/kernel/kvm.c8
-rw-r--r--arch/x86/kernel/machine_kexec_32.c6
-rw-r--r--arch/x86/kernel/machine_kexec_64.c5
-rw-r--r--arch/x86/kernel/process.c146
-rw-r--r--arch/x86/kernel/process_64.c1
-rw-r--r--arch/x86/kernel/smpboot.c5
-rw-r--r--arch/x86/kernel/uprobes.c4
-rw-r--r--arch/x86/kvm/cpuid.c26
-rw-r--r--arch/x86/kvm/hyperv.c23
-rw-r--r--arch/x86/kvm/lapic.c16
-rw-r--r--arch/x86/kvm/svm.c66
-rw-r--r--arch/x86/kvm/vmx.c59
-rw-r--r--arch/x86/kvm/x86.c32
-rw-r--r--arch/x86/mm/pkeys.c21
-rw-r--r--arch/x86/xen/mmu.c4
-rw-r--r--arch/x86/xen/mmu_pv.c4
40 files changed, 1077 insertions, 202 deletions
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index 47d3efff6805..09f36c0d9d4f 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -163,7 +163,8 @@ __setup_efi_pci32(efi_pci_io_protocol_32 *pci, struct pci_setup_rom **__rom)
if (status != EFI_SUCCESS)
goto free_struct;
- memcpy(rom->romdata, pci->romimage, pci->romsize);
+ memcpy(rom->romdata, (void *)(unsigned long)pci->romimage,
+ pci->romsize);
return status;
free_struct:
@@ -269,7 +270,8 @@ __setup_efi_pci64(efi_pci_io_protocol_64 *pci, struct pci_setup_rom **__rom)
if (status != EFI_SUCCESS)
goto free_struct;
- memcpy(rom->romdata, pci->romimage, pci->romsize);
+ memcpy(rom->romdata, (void *)(unsigned long)pci->romimage,
+ pci->romsize);
return status;
free_struct:
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index fca012baba19..8169e8b7a4dc 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -306,6 +306,25 @@ ENTRY(startup_64)
leaq boot_stack_end(%rbx), %rsp
/*
+ * paging_prepare() and cleanup_trampoline() below can have GOT
+ * references. Adjust the table with address we are running at.
+ *
+ * Zero RAX for adjust_got: the GOT was not adjusted before;
+ * there's no adjustment to undo.
+ */
+ xorq %rax, %rax
+
+ /*
+ * Calculate the address the binary is loaded at and use it as
+ * a GOT adjustment.
+ */
+ call 1f
+1: popq %rdi
+ subq $1b, %rdi
+
+ call adjust_got
+
+ /*
* At this point we are in long mode with 4-level paging enabled,
* but we might want to enable 5-level paging or vice versa.
*
@@ -370,10 +389,14 @@ trampoline_return:
/*
* cleanup_trampoline() would restore trampoline memory.
*
+ * RDI is address of the page table to use instead of page table
+ * in trampoline memory (if required).
+ *
* RSI holds real mode data and needs to be preserved across
* this function call.
*/
pushq %rsi
+ leaq top_pgtable(%rbx), %rdi
call cleanup_trampoline
popq %rsi
@@ -381,6 +404,21 @@ trampoline_return:
pushq $0
popfq
+ /*
+ * Previously we've adjusted the GOT with address the binary was
+ * loaded at. Now we need to re-adjust for relocation address.
+ *
+ * Calculate the address the binary is loaded at, so that we can
+ * undo the previous GOT adjustment.
+ */
+ call 1f
+1: popq %rax
+ subq $1b, %rax
+
+ /* The new adjustment is the relocation address */
+ movq %rbx, %rdi
+ call adjust_got
+
/*
* Copy the compressed kernel to the end of our buffer
* where decompression in place becomes safe.
@@ -482,19 +520,6 @@ relocated:
rep stosq
/*
- * Adjust our own GOT
- */
- leaq _got(%rip), %rdx
- leaq _egot(%rip), %rcx
-1:
- cmpq %rcx, %rdx
- jae 2f
- addq %rbx, (%rdx)
- addq $8, %rdx
- jmp 1b
-2:
-
-/*
* Do the extraction, and jump to the new kernel..
*/
pushq %rsi /* Save the real mode argument */
@@ -512,6 +537,27 @@ relocated:
*/
jmp *%rax
+/*
+ * Adjust the global offset table
+ *
+ * RAX is the previous adjustment of the table to undo (use 0 if it's the
+ * first time we touch GOT).
+ * RDI is the new adjustment to apply.
+ */
+adjust_got:
+ /* Walk through the GOT adding the address to the entries */
+ leaq _got(%rip), %rdx
+ leaq _egot(%rip), %rcx
+1:
+ cmpq %rcx, %rdx
+ jae 2f
+ subq %rax, (%rdx) /* Undo previous adjustment */
+ addq %rdi, (%rdx) /* Apply the new adjustment */
+ addq $8, %rdx
+ jmp 1b
+2:
+ ret
+
.code32
/*
* This is the 32-bit trampoline that will be copied over to low memory.
@@ -649,3 +695,10 @@ boot_stack_end:
.balign 4096
pgtable:
.fill BOOT_PGT_SIZE, 1, 0
+
+/*
+ * The page table is going to be used instead of page table in the trampoline
+ * memory.
+ */
+top_pgtable:
+ .fill PAGE_SIZE, 1, 0
diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c
index 32af1cbcd903..a362fa0b849c 100644
--- a/arch/x86/boot/compressed/pgtable_64.c
+++ b/arch/x86/boot/compressed/pgtable_64.c
@@ -23,14 +23,6 @@ struct paging_config {
static char trampoline_save[TRAMPOLINE_32BIT_SIZE];
/*
- * The page table is going to be used instead of page table in the trampoline
- * memory.
- *
- * It must not be in BSS as BSS is cleared after cleanup_trampoline().
- */
-static char top_pgtable[PAGE_SIZE] __aligned(PAGE_SIZE) __section(.data);
-
-/*
* Trampoline address will be printed by extract_kernel() for debugging
* purposes.
*
@@ -134,7 +126,7 @@ out:
return paging_config;
}
-void cleanup_trampoline(void)
+void cleanup_trampoline(void *pgtable)
{
void *trampoline_pgtable;
@@ -145,8 +137,8 @@ void cleanup_trampoline(void)
* if it's there.
*/
if ((void *)__native_read_cr3() == trampoline_pgtable) {
- memcpy(top_pgtable, trampoline_pgtable, PAGE_SIZE);
- native_write_cr3((unsigned long)top_pgtable);
+ memcpy(pgtable, trampoline_pgtable, PAGE_SIZE);
+ native_write_cr3((unsigned long)pgtable);
}
/* Restore trampoline memory */
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index b27da9602a6d..aced6c9290d6 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -140,6 +140,20 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
#define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit)
+#if defined(__clang__) && !defined(CC_HAVE_ASM_GOTO)
+
+/*
+ * Workaround for the sake of BPF compilation which utilizes kernel
+ * headers, but clang does not support ASM GOTO and fails the build.
+ */
+#ifndef __BPF_TRACING__
+#warning "Compiler lacks ASM_GOTO support. Add -D __BPF_TRACING__ to your compiler arguments"
+#endif
+
+#define static_cpu_has(bit) boot_cpu_has(bit)
+
+#else
+
/*
* Static testing of CPU features. Used the same as boot_cpu_has().
* These will statically patch the target code for additional
@@ -195,6 +209,7 @@ t_no:
boot_cpu_has(bit) : \
_static_cpu_has(bit) \
)
+#endif
#define cpu_has_bug(c, bit) cpu_has(c, (bit))
#define set_cpu_bug(c, bit) set_cpu_cap(c, (bit))
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 578793e97431..fb00a2fca990 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -198,7 +198,6 @@
#define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */
#define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */
#define X86_FEATURE_INVPCID_SINGLE ( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */
-
#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */
#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
#define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */
@@ -207,13 +206,19 @@
#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_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */
+#define X86_FEATURE_SSBD ( 7*32+17) /* Speculative Store Bypass Disable */
#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_SEV ( 7*32+20) /* AMD Secure Encrypted Virtualization */
-
#define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */
#define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* "" Use IBRS during runtime firmware calls */
+#define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* "" Disable Speculative Store Bypass. */
+#define X86_FEATURE_LS_CFG_SSBD ( 7*32+24) /* "" AMD SSBD implementation via LS_CFG MSR */
+#define X86_FEATURE_IBRS ( 7*32+25) /* Indirect Branch Restricted Speculation */
+#define X86_FEATURE_IBPB ( 7*32+26) /* Indirect Branch Prediction Barrier */
+#define X86_FEATURE_STIBP ( 7*32+27) /* Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_ZEN ( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */
/* Virtualization flags: Linux defined, word 8 */
#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */
@@ -274,9 +279,10 @@
#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 */
+#define X86_FEATURE_AMD_IBPB (13*32+12) /* "" Indirect Branch Prediction Barrier */
+#define X86_FEATURE_AMD_IBRS (13*32+14) /* "" Indirect Branch Restricted Speculation */
+#define X86_FEATURE_AMD_STIBP (13*32+15) /* "" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */
/* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
#define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */
@@ -334,6 +340,7 @@
#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) */
+#define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* "" Speculative Store Bypass Disable */
/*
* BUG word(s)
@@ -363,5 +370,6 @@
#define X86_BUG_CPU_MELTDOWN X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */
#define X86_BUG_SPECTRE_V1 X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */
#define X86_BUG_SPECTRE_V2 X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */
+#define X86_BUG_SPEC_STORE_BYPASS X86_BUG(17) /* CPU is affected by speculative store bypass attack */
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
index b3e32b010ab1..c2c01f84df75 100644
--- a/arch/x86/include/asm/insn.h
+++ b/arch/x86/include/asm/insn.h
@@ -208,4 +208,22 @@ static inline int insn_offset_immediate(struct insn *insn)
return insn_offset_displacement(insn) + insn->displacement.nbytes;
}
+#define POP_SS_OPCODE 0x1f
+#define MOV_SREG_OPCODE 0x8e
+
+/*
+ * Intel SDM Vol.3A 6.8.3 states;
+ * "Any single-step trap that would be delivered following the MOV to SS
+ * instruction or POP to SS instruction (because EFLAGS.TF is 1) is
+ * suppressed."
+ * This function returns true if @insn is MOV SS or POP SS. On these
+ * instructions, single stepping is suppressed.
+ */
+static inline int insn_masking_exception(struct insn *insn)
+{
+ return insn->opcode.bytes[0] == POP_SS_OPCODE ||
+ (insn->opcode.bytes[0] == MOV_SREG_OPCODE &&
+ X86_MODRM_REG(insn->modrm.bytes[0]) == 2);
+}
+
#endif /* _ASM_X86_INSN_H */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index c25775fad4ed..f4b2588865e9 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -924,7 +924,7 @@ struct kvm_x86_ops {
int (*hardware_setup)(void); /* __init */
void (*hardware_unsetup)(void); /* __exit */
bool (*cpu_has_accelerated_tpr)(void);
- bool (*cpu_has_high_real_mode_segbase)(void);
+ bool (*has_emulated_msr)(int index);
void (*cpuid_update)(struct kvm_vcpu *vcpu);
struct kvm *(*vm_alloc)(void);
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 57e3785d0d26..cf9911b5a53c 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -193,7 +193,7 @@ static inline int init_new_context(struct task_struct *tsk,
#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
if (cpu_feature_enabled(X86_FEATURE_OSPKE)) {
- /* pkey 0 is the default and always allocated */
+ /* pkey 0 is the default and allocated implicitly */
mm->context.pkey_allocation_map = 0x1;
/* -1 means unallocated or invalid */
mm->context.execute_only_pkey = -1;
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 53d5b1b9255e..fda2114197b3 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -42,6 +42,8 @@
#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 SPEC_CTRL_SSBD_SHIFT 2 /* Speculative Store Bypass Disable bit */
+#define SPEC_CTRL_SSBD (1 << SPEC_CTRL_SSBD_SHIFT) /* Speculative Store Bypass Disable */
#define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */
#define PRED_CMD_IBPB (1 << 0) /* Indirect Branch Prediction Barrier */
@@ -68,6 +70,11 @@
#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 ARCH_CAP_SSB_NO (1 << 4) /*
+ * Not susceptible to Speculative Store Bypass
+ * attack, so no Speculative Store Bypass
+ * control required.
+ */
#define MSR_IA32_BBL_CR_CTL 0x00000119
#define MSR_IA32_BBL_CR_CTL3 0x0000011e
@@ -340,6 +347,8 @@
#define MSR_AMD64_SEV_ENABLED_BIT 0
#define MSR_AMD64_SEV_ENABLED BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT)
+#define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f
+
/* Fam 17h MSRs */
#define MSR_F17H_IRPERF 0xc00000e9
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index f928ad9b143f..8b38df98548e 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -217,6 +217,14 @@ enum spectre_v2_mitigation {
SPECTRE_V2_IBRS,
};
+/* The Speculative Store Bypass disable variants */
+enum ssb_mitigation {
+ SPEC_STORE_BYPASS_NONE,
+ SPEC_STORE_BYPASS_DISABLE,
+ SPEC_STORE_BYPASS_PRCTL,
+ SPEC_STORE_BYPASS_SECCOMP,
+};
+
extern char __indirect_thunk_start[];
extern char __indirect_thunk_end[];
@@ -241,22 +249,27 @@ static inline void vmexit_fill_RSB(void)
#endif
}
-#define alternative_msr_write(_msr, _val, _feature) \
- asm volatile(ALTERNATIVE("", \
- "movl %[msr], %%ecx\n\t" \
- "movl %[val], %%eax\n\t" \
- "movl $0, %%edx\n\t" \
- "wrmsr", \
- _feature) \
- : : [msr] "i" (_msr), [val] "i" (_val) \
- : "eax", "ecx", "edx", "memory")
+static __always_inline
+void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature)
+{
+ asm volatile(ALTERNATIVE("", "wrmsr", %c[feature])
+ : : "c" (msr),
+ "a" ((u32)val),
+ "d" ((u32)(val >> 32)),
+ [feature] "i" (feature)
+ : "memory");
+}
static inline void indirect_branch_prediction_barrier(void)
{
- alternative_msr_write(MSR_IA32_PRED_CMD, PRED_CMD_IBPB,
- X86_FEATURE_USE_IBPB);
+ u64 val = PRED_CMD_IBPB;
+
+ alternative_msr_write(MSR_IA32_PRED_CMD, val, X86_FEATURE_USE_IBPB);
}
+/* The Intel SPEC CTRL MSR base value cache */
+extern u64 x86_spec_ctrl_base;
+
/*
* With retpoline, we must use IBRS to restrict branch prediction
* before calling into firmware.
@@ -265,14 +278,18 @@ static inline void indirect_branch_prediction_barrier(void)
*/
#define firmware_restrict_branch_speculation_start() \
do { \
+ u64 val = x86_spec_ctrl_base | SPEC_CTRL_IBRS; \
+ \
preempt_disable(); \
- alternative_msr_write(MSR_IA32_SPEC_CTRL, SPEC_CTRL_IBRS, \
+ alternative_msr_write(MSR_IA32_SPEC_CTRL, val, \
X86_FEATURE_USE_IBRS_FW); \
} while (0)
#define firmware_restrict_branch_speculation_end() \
do { \
- alternative_msr_write(MSR_IA32_SPEC_CTRL, 0, \
+ u64 val = x86_spec_ctrl_base; \
+ \
+ alternative_msr_write(MSR_IA32_SPEC_CTRL, val, \
X86_FEATURE_USE_IBRS_FW); \
preempt_enable(); \
} while (0)
diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h
index a0ba1ffda0df..851c04b7a092 100644
--- a/arch/x86/include/asm/pkeys.h
+++ b/arch/x86/include/asm/pkeys.h
@@ -2,6 +2,8 @@
#ifndef _ASM_X86_PKEYS_H
#define _ASM_X86_PKEYS_H
+#define ARCH_DEFAULT_PKEY 0
+
#define arch_max_pkey() (boot_cpu_has(X86_FEATURE_OSPKE) ? 16 : 1)
extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
@@ -15,7 +17,7 @@ extern int __execute_only_pkey(struct mm_struct *mm);
static inline int execute_only_pkey(struct mm_struct *mm)
{
if (!boot_cpu_has(X86_FEATURE_OSPKE))
- return 0;
+ return ARCH_DEFAULT_PKEY;
return __execute_only_pkey(mm);
}
@@ -49,13 +51,21 @@ bool mm_pkey_is_allocated(struct mm_struct *mm, int pkey)
{
/*
* "Allocated" pkeys are those that have been returned
- * from pkey_alloc(). pkey 0 is special, and never
- * returned from pkey_alloc().
+ * from pkey_alloc() or pkey 0 which is allocated
+ * implicitly when the mm is created.
*/
- if (pkey <= 0)
+ if (pkey < 0)
return false;
if (pkey >= arch_max_pkey())
return false;
+ /*
+ * The exec-only pkey is set in the allocation map, but
+ * is not available to any of the user interfaces like
+ * mprotect_pkey().
+ */
+ if (pkey == mm->context.execute_only_pkey)
+ return false;
+
return mm_pkey_allocation_map(mm) & (1U << pkey);
}
diff --git a/arch/x86/include/asm/spec-ctrl.h b/arch/x86/include/asm/spec-ctrl.h
new file mode 100644
index 000000000000..ae7c2c5cd7f0
--- /dev/null
+++ b/arch/x86/include/asm/spec-ctrl.h
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_SPECCTRL_H_
+#define _ASM_X86_SPECCTRL_H_
+
+#include <linux/thread_info.h>
+#include <asm/nospec-branch.h>
+
+/*
+ * On VMENTER we must preserve whatever view of the SPEC_CTRL MSR
+ * the guest has, while on VMEXIT we restore the host view. This
+ * would be easier if SPEC_CTRL were architecturally maskable or
+ * shadowable for guests but this is not (currently) the case.
+ * Takes the guest view of SPEC_CTRL MSR as a parameter and also
+ * the guest's version of VIRT_SPEC_CTRL, if emulated.
+ */
+extern void x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool guest);
+
+/**
+ * x86_spec_ctrl_set_guest - Set speculation control registers for the guest
+ * @guest_spec_ctrl: The guest content of MSR_SPEC_CTRL
+ * @guest_virt_spec_ctrl: The guest controlled bits of MSR_VIRT_SPEC_CTRL
+ * (may get translated to MSR_AMD64_LS_CFG bits)
+ *
+ * Avoids writing to the MSR if the content/bits are the same
+ */
+static inline
+void x86_spec_ctrl_set_guest(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl)
+{
+ x86_virt_spec_ctrl(guest_spec_ctrl, guest_virt_spec_ctrl, true);
+}
+
+/**
+ * x86_spec_ctrl_restore_host - Restore host speculation control registers
+ * @guest_spec_ctrl: The guest content of MSR_SPEC_CTRL
+ * @guest_virt_spec_ctrl: The guest controlled bits of MSR_VIRT_SPEC_CTRL
+ * (may get translated to MSR_AMD64_LS_CFG bits)
+ *
+ * Avoids writing to the MSR if the content/bits are the same
+ */
+static inline
+void x86_spec_ctrl_restore_host(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl)
+{
+ x86_virt_spec_ctrl(guest_spec_ctrl, guest_virt_spec_ctrl, false);
+}
+
+/* AMD specific Speculative Store Bypass MSR data */
+extern u64 x86_amd_ls_cfg_base;
+extern u64 x86_amd_ls_cfg_ssbd_mask;
+
+static inline u64 ssbd_tif_to_spec_ctrl(u64 tifn)
+{
+ BUILD_BUG_ON(TIF_SSBD < SPEC_CTRL_SSBD_SHIFT);
+ return (tifn & _TIF_SSBD) >> (TIF_SSBD - SPEC_CTRL_SSBD_SHIFT);
+}
+
+static inline unsigned long ssbd_spec_ctrl_to_tif(u64 spec_ctrl)
+{
+ BUILD_BUG_ON(TIF_SSBD < SPEC_CTRL_SSBD_SHIFT);
+ return (spec_ctrl & SPEC_CTRL_SSBD) << (TIF_SSBD - SPEC_CTRL_SSBD_SHIFT);
+}
+
+static inline u64 ssbd_tif_to_amd_ls_cfg(u64 tifn)
+{
+ return (tifn & _TIF_SSBD) ? x86_amd_ls_cfg_ssbd_mask : 0ULL;
+}
+
+#ifdef CONFIG_SMP
+extern void speculative_store_bypass_ht_init(void);
+#else
+static inline void speculative_store_bypass_ht_init(void) { }
+#endif
+
+extern void speculative_store_bypass_update(unsigned long tif);
+
+static inline void speculative_store_bypass_update_current(void)
+{
+ speculative_store_bypass_update(current_thread_info()->flags);
+}
+
+#endif
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index a5d9521bb2cb..2ff2a30a264f 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -79,6 +79,7 @@ struct thread_info {
#define TIF_SIGPENDING 2 /* signal pending */
#define TIF_NEED_RESCHED 3 /* rescheduling necessary */
#define TIF_SINGLESTEP 4 /* reenable singlestep on user return*/
+#define TIF_SSBD 5 /* Reduced data speculation */
#define TIF_SYSCALL_EMU 6 /* syscall emulation active */
#define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */
#define TIF_SECCOMP 8 /* secure computing */
@@ -105,6 +106,7 @@ struct thread_info {
#define _TIF_SIGPENDING (1 << TIF_SIGPENDING)
#define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED)
#define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP)
+#define _TIF_SSBD (1 << TIF_SSBD)
#define _TIF_SYSCALL_EMU (1 << TIF_SYSCALL_EMU)
#define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT)
#define _TIF_SECCOMP (1 << TIF_SECCOMP)
@@ -144,7 +146,7 @@ struct thread_info {
/* flags to check in __switch_to() */
#define _TIF_WORK_CTXSW \
- (_TIF_IO_BITMAP|_TIF_NOCPUID|_TIF_NOTSC|_TIF_BLOCKSTEP)
+ (_TIF_IO_BITMAP|_TIF_NOCPUID|_TIF_NOTSC|_TIF_BLOCKSTEP|_TIF_SSBD)
#define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY)
#define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW)
diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index 4c851ebb3ceb..0ede697c3961 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -29,7 +29,7 @@
#define KVM_FEATURE_PV_TLB_FLUSH 9
#define KVM_FEATURE_ASYNC_PF_VMEXIT 10
-#define KVM_HINTS_DEDICATED 0
+#define KVM_HINTS_REALTIME 0
/* The last 8 bits are used to indicate how to interpret the flags field
* in pvclock structure. If no bits are set, all flags are ignored.
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index c88e0b127810..b481b95bd8f6 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -14,8 +14,11 @@
#include <asm/amd_nb.h>
#define PCI_DEVICE_ID_AMD_17H_ROOT 0x1450
+#define PCI_DEVICE_ID_AMD_17H_M10H_ROOT 0x15d0
#define PCI_DEVICE_ID_AMD_17H_DF_F3 0x1463
#define PCI_DEVICE_ID_AMD_17H_DF_F4 0x1464
+#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F3 0x15eb
+#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4 0x15ec
/* Protect the PCI config register pairs used for SMN and DF indirect access. */
static DEFINE_MUTEX(smn_mutex);
@@ -24,6 +27,7 @@ static u32 *flush_words;
static const struct pci_device_id amd_root_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_ROOT) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_ROOT) },
{}
};
@@ -39,6 +43,7 @@ const struct pci_device_id amd_nb_misc_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F3) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F3) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) },
{}
};
@@ -51,6 +56,7 @@ static const struct pci_device_id amd_nb_link_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F4) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) },
{}
};
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 8b04234e010b..7685444a106b 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -116,6 +116,7 @@ static void init_x2apic_ldr(void)
goto update;
}
cmsk = cluster_hotplug_mask;
+ cmsk->clusterid = cluster;
cluster_hotplug_mask = NULL;
update:
this_cpu_write(cluster_masks, cmsk);
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 12bc0a1139da..1b18be3f35a8 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -10,6 +10,7 @@
#include <asm/processor.h>
#include <asm/apic.h>
#include <asm/cpu.h>
+#include <asm/spec-ctrl.h>
#include <asm/smp.h>
#include <asm/pci-direct.h>
#include <asm/delay.h>
@@ -554,6 +555,26 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
rdmsrl(MSR_FAM10H_NODE_ID, value);
nodes_per_socket = ((value >> 3) & 7) + 1;
}
+
+ if (c->x86 >= 0x15 && c->x86 <= 0x17) {
+ unsigned int bit;
+
+ switch (c->x86) {
+ case 0x15: bit = 54; break;
+ case 0x16: bit = 33; break;
+ case 0x17: bit = 10; break;
+ default: return;
+ }
+ /*
+ * Try to cache the base value so further operations can
+ * avoid RMW. If that faults, do not enable SSBD.
+ */
+ if (!rdmsrl_safe(MSR_AMD64_LS_CFG, &x86_amd_ls_cfg_base)) {
+ setup_force_cpu_cap(X86_FEATURE_LS_CFG_SSBD);
+ setup_force_cpu_cap(X86_FEATURE_SSBD);
+ x86_amd_ls_cfg_ssbd_mask = 1ULL << bit;
+ }
+ }
}
static void early_detect_mem_encrypt(struct cpuinfo_x86 *c)
@@ -791,6 +812,7 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
static void init_amd_zn(struct cpuinfo_x86 *c)
{
+ set_cpu_cap(c, X86_FEATURE_ZEN);
/*
* Fix erratum 1076: CPB feature bit not being set in CPUID. It affects
* all up to and including B1.
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index bfca937bdcc3..7416fc206b4a 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -12,8 +12,10 @@
#include <linux/utsname.h>
#include <linux/cpu.h>
#include <linux/module.h>
+#include <linux/nospec.h>
+#include <linux/prctl.h>
-#include <asm/nospec-branch.h>
+#include <asm/spec-ctrl.h>
#include <asm/cmdline.h>
#include <asm/bugs.h>
#include <asm/processor.h>
@@ -27,6 +29,27 @@
#include <asm/intel-family.h>
static void __init spectre_v2_select_mitigation(void);
+static void __init ssb_select_mitigation(void);
+
+/*
+ * Our boot-time value of the SPEC_CTRL MSR. We read it once so that any
+ * writes to SPEC_CTRL contain whatever reserved bits have been set.
+ */
+u64 __ro_after_init x86_spec_ctrl_base;
+EXPORT_SYMBOL_GPL(x86_spec_ctrl_base);
+
+/*
+ * The vendor and possibly platform specific bits which can be modified in
+ * x86_spec_ctrl_base.
+ */
+static u64 __ro_after_init x86_spec_ctrl_mask = SPEC_CTRL_IBRS;
+
+/*
+ * AMD specific MSR info for Speculative Store Bypass control.
+ * x86_amd_ls_cfg_ssbd_mask is initialized in identify_boot_cpu().
+ */
+u64 __ro_after_init x86_amd_ls_cfg_base;
+u64 __ro_after_init x86_amd_ls_cfg_ssbd_mask;
void __init check_bugs(void)
{
@@ -37,9 +60,27 @@ void __init check_bugs(void)
print_cpu_info(&boot_cpu_data);
}
+ /*
+ * Read the SPEC_CTRL MSR to account for reserved bits which may
+ * have unknown values. AMD64_LS_CFG MSR is cached in the early AMD
+ * init code as it is not enumerated and depends on the family.
+ */
+ if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL))
+ rdmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+
+ /* Allow STIBP in MSR_SPEC_CTRL if supported */
+ if (boot_cpu_has(X86_FEATURE_STIBP))
+ x86_spec_ctrl_mask |= SPEC_CTRL_STIBP;
+
/* Select the proper spectre mitigation before patching alternatives */
spectre_v2_select_mitigation();
+ /*
+ * Select proper mitigation for any exposure to the Speculative Store
+ * Bypass vulnerability.
+ */
+ ssb_select_mitigation();
+
#ifdef CONFIG_X86_32
/*
* Check whether we are able to run this kernel safely on SMP.
@@ -93,7 +134,76 @@ static const char *spectre_v2_strings[] = {
#undef pr_fmt
#define pr_fmt(fmt) "Spectre V2 : " fmt
-static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE;
+static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init =
+ SPECTRE_V2_NONE;
+
+void
+x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest)
+{
+ u64 msrval, guestval, hostval = x86_spec_ctrl_base;
+ struct thread_info *ti = current_thread_info();
+
+ /* Is MSR_SPEC_CTRL implemented ? */
+ if (static_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) {
+ /*
+ * Restrict guest_spec_ctrl to supported values. Clear the
+ * modifiable bits in the host base value and or the
+ * modifiable bits from the guest value.
+ */
+ guestval = hostval & ~x86_spec_ctrl_mask;
+ guestval |= guest_spec_ctrl & x86_spec_ctrl_mask;
+
+ /* SSBD controlled in MSR_SPEC_CTRL */
+ if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD))
+ hostval |= ssbd_tif_to_spec_ctrl(ti->flags);
+
+ if (hostval != guestval) {
+ msrval = setguest ? guestval : hostval;
+ wrmsrl(MSR_IA32_SPEC_CTRL, msrval);
+ }
+ }
+
+ /*
+ * If SSBD is not handled in MSR_SPEC_CTRL on AMD, update
+ * MSR_AMD64_L2_CFG or MSR_VIRT_SPEC_CTRL if supported.
+ */
+ if (!static_cpu_has(X86_FEATURE_LS_CFG_SSBD) &&
+ !static_cpu_has(X86_FEATURE_VIRT_SSBD))
+ return;
+
+ /*
+ * If the host has SSBD mitigation enabled, force it in the host's
+ * virtual MSR value. If its not permanently enabled, evaluate
+ * current's TIF_SSBD thread flag.
+ */
+ if (static_cpu_has(X86_FEATURE_SPEC_STORE_BYPASS_DISABLE))
+ hostval = SPEC_CTRL_SSBD;
+ else
+ hostval = ssbd_tif_to_spec_ctrl(ti->flags);
+
+ /* Sanitize the guest value */
+ guestval = guest_virt_spec_ctrl & SPEC_CTRL_SSBD;
+
+ if (hostval != guestval) {
+ unsigned long tif;
+
+ tif = setguest ? ssbd_spec_ctrl_to_tif(guestval) :
+ ssbd_spec_ctrl_to_tif(hostval);
+
+ speculative_store_bypass_update(tif);
+ }
+}
+EXPORT_SYMBOL_GPL(x86_virt_spec_ctrl);
+
+static void x86_amd_ssb_disable(void)
+{
+ u64 msrval = x86_amd_ls_cfg_base | x86_amd_ls_cfg_ssbd_mask;
+
+ if (boot_cpu_has(X86_FEATURE_VIRT_SSBD))
+ wrmsrl(MSR_AMD64_VIRT_SPEC_CTRL, SPEC_CTRL_SSBD);
+ else if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD))
+ wrmsrl(MSR_AMD64_LS_CFG, msrval);
+}
#ifdef RETPOLINE
static bool spectre_v2_bad_module;
@@ -312,32 +422,289 @@ retpoline_auto:
}
#undef pr_fmt
+#define pr_fmt(fmt) "Speculative Store Bypass: " fmt
+
+static enum ssb_mitigation ssb_mode __ro_after_init = SPEC_STORE_BYPASS_NONE;
+
+/* The kernel command line selection */
+enum ssb_mitigation_cmd {
+ SPEC_STORE_BYPASS_CMD_NONE,
+ SPEC_STORE_BYPASS_CMD_AUTO,
+ SPEC_STORE_BYPASS_CMD_ON,
+ SPEC_STORE_BYPASS_CMD_PRCTL,
+ SPEC_STORE_BYPASS_CMD_SECCOMP,
+};
+
+static const char *ssb_strings[] = {
+ [SPEC_STORE_BYPASS_NONE] = "Vulnerable",
+ [SPEC_STORE_BYPASS_DISABLE] = "Mitigation: Speculative Store Bypass disabled",
+ [SPEC_STORE_BYPASS_PRCTL] = "Mitigation: Speculative Store Bypass disabled via prctl",
+ [SPEC_STORE_BYPASS_SECCOMP] = "Mitigation: Speculative Store Bypass disabled via prctl and seccomp",
+};
+
+static const struct {
+ const char *option;
+ enum ssb_mitigation_cmd cmd;
+} ssb_mitigation_options[] = {
+ { "auto", SPEC_STORE_BYPASS_CMD_AUTO }, /* Platform decides */
+ { "on", SPEC_STORE_BYPASS_CMD_ON }, /* Disable Speculative Store Bypass */
+ { "off", SPEC_STORE_BYPASS_CMD_NONE }, /* Don't touch Speculative Store Bypass */
+ { "prctl", SPEC_STORE_BYPASS_CMD_PRCTL }, /* Disable Speculative Store Bypass via prctl */
+ { "seccomp", SPEC_STORE_BYPASS_CMD_SECCOMP }, /* Disable Speculative Store Bypass via prctl and seccomp */
+};
+
+static enum ssb_mitigation_cmd __init ssb_parse_cmdline(void)
+{
+ enum ssb_mitigation_cmd cmd = SPEC_STORE_BYPASS_CMD_AUTO;
+ char arg[20];
+ int ret, i;
+
+ if (cmdline_find_option_bool(boot_command_line, "nospec_store_bypass_disable")) {
+ return SPEC_STORE_BYPASS_CMD_NONE;
+ } else {
+ ret = cmdline_find_option(boot_command_line, "spec_store_bypass_disable",
+ arg, sizeof(arg));
+ if (ret < 0)
+ return SPEC_STORE_BYPASS_CMD_AUTO;
+
+ for (i = 0; i < ARRAY_SIZE(ssb_mitigation_options); i++) {
+ if (!match_option(arg, ret, ssb_mitigation_options[i].option))
+ continue;
+
+ cmd = ssb_mitigation_options[i].cmd;
+ break;
+ }
+
+ if (i >= ARRAY_SIZE(ssb_mitigation_options)) {
+ pr_err("unknown option (%s). Switching to AUTO select\n", arg);
+ return SPEC_STORE_BYPASS_CMD_AUTO;
+ }
+ }
+
+ return cmd;
+}
+
+static enum ssb_mitigation __init __ssb_select_mitigation(void)
+{
+ enum ssb_mitigation mode = SPEC_STORE_BYPASS_NONE;
+ enum ssb_mitigation_cmd cmd;
+
+ if (!boot_cpu_has(X86_FEATURE_SSBD))
+ return mode;
+
+ cmd = ssb_parse_cmdline();
+ if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS) &&
+ (cmd == SPEC_STORE_BYPASS_CMD_NONE ||
+ cmd == SPEC_STORE_BYPASS_CMD_AUTO))
+ return mode;
+
+ switch (cmd) {
+ case SPEC_STORE_BYPASS_CMD_AUTO:
+ case SPEC_STORE_BYPASS_CMD_SECCOMP:
+ /*
+ * Choose prctl+seccomp as the default mode if seccomp is
+ * enabled.
+ */
+ if (IS_ENABLED(CONFIG_SECCOMP))
+ mode = SPEC_STORE_BYPASS_SECCOMP;
+ else
+ mode = SPEC_STORE_BYPASS_PRCTL;
+ break;
+ case SPEC_STORE_BYPASS_CMD_ON:
+ mode = SPEC_STORE_BYPASS_DISABLE;
+ break;
+ case SPEC_STORE_BYPASS_CMD_PRCTL:
+ mode = SPEC_STORE_BYPASS_PRCTL;
+ break;
+ case SPEC_STORE_BYPASS_CMD_NONE:
+ break;
+ }
+
+ /*
+ * We have three CPU feature flags that are in play here:
+ * - X86_BUG_SPEC_STORE_BYPASS - CPU is susceptible.
+ * - X86_FEATURE_SSBD - CPU is able to turn off speculative store bypass
+ * - X86_FEATURE_SPEC_STORE_BYPASS_DISABLE - engage the mitigation
+ */
+ if (mode == SPEC_STORE_BYPASS_DISABLE) {
+ setup_force_cpu_cap(X86_FEATURE_SPEC_STORE_BYPASS_DISABLE);
+ /*
+ * Intel uses the SPEC CTRL MSR Bit(2) for this, while AMD uses
+ * a completely different MSR and bit dependent on family.
+ */
+ switch (boot_cpu_data.x86_vendor) {
+ case X86_VENDOR_INTEL:
+ x86_spec_ctrl_base |= SPEC_CTRL_SSBD;
+ x86_spec_ctrl_mask |= SPEC_CTRL_SSBD;
+ wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+ break;
+ case X86_VENDOR_AMD:
+ x86_amd_ssb_disable();
+ break;
+ }
+ }
+
+ return mode;
+}
+
+static void ssb_select_mitigation(void)
+{
+ ssb_mode = __ssb_select_mitigation();
+
+ if (boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS))
+ pr_info("%s\n", ssb_strings[ssb_mode]);
+}
+
+#undef pr_fmt
+#define pr_fmt(fmt) "Speculation prctl: " fmt
+
+static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl)
+{
+ bool update;
+
+ if (ssb_mode != SPEC_STORE_BYPASS_PRCTL &&
+ ssb_mode != SPEC_STORE_BYPASS_SECCOMP)
+ return -ENXIO;
+
+ switch (ctrl) {
+ case PR_SPEC_ENABLE:
+ /* If speculation is force disabled, enable is not allowed */
+ if (task_spec_ssb_force_disable(task))
+ return -EPERM;
+ task_clear_spec_ssb_disable(task);
+ update = test_and_clear_tsk_thread_flag(task, TIF_SSBD);
+ break;
+ case PR_SPEC_DISABLE:
+ task_set_spec_ssb_disable(task);
+ update = !test_and_set_tsk_thread_flag(task, TIF_SSBD);
+ break;
+ case PR_SPEC_FORCE_DISABLE:
+ task_set_spec_ssb_disable(task);
+ task_set_spec_ssb_force_disable(task);
+ update = !test_and_set_tsk_thread_flag(task, TIF_SSBD);
+ break;
+ default:
+ return -ERANGE;
+ }
+
+ /*
+ * If being set on non-current task, delay setting the CPU
+ * mitigation until it is next scheduled.
+ */
+ if (task == current && update)
+ speculative_store_bypass_update_current();
+
+ return 0;
+}
+
+int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which,
+ unsigned long ctrl)
+{
+ switch (which) {
+ case PR_SPEC_STORE_BYPASS:
+ return ssb_prctl_set(task, ctrl);
+ default:
+ return -ENODEV;
+ }
+}
+
+#ifdef CONFIG_SECCOMP
+void arch_seccomp_spec_mitigate(struct task_struct *task)
+{
+ if (ssb_mode == SPEC_STORE_BYPASS_SECCOMP)
+ ssb_prctl_set(task, PR_SPEC_FORCE_DISABLE);
+}
+#endif
+
+static int ssb_prctl_get(struct task_struct *task)
+{
+ switch (ssb_mode) {
+ case SPEC_STORE_BYPASS_DISABLE:
+ return PR_SPEC_DISABLE;
+ case SPEC_STORE_BYPASS_SECCOMP:
+ case SPEC_STORE_BYPASS_PRCTL:
+ if (task_spec_ssb_force_disable(task))
+ return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE;
+ if (task_spec_ssb_disable(task))
+ return PR_SPEC_PRCTL | PR_SPEC_DISABLE;
+ return PR_SPEC_PRCTL | PR_SPEC_ENABLE;
+ default:
+ if (boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS))
+ return PR_SPEC_ENABLE;
+ return PR_SPEC_NOT_AFFECTED;
+ }
+}
+
+int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which)
+{
+ switch (which) {
+ case PR_SPEC_STORE_BYPASS:
+ return ssb_prctl_get(task);
+ default:
+ return -ENODEV;
+ }
+}
+
+void x86_spec_ctrl_setup_ap(void)
+{
+ if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL))
+ wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+
+ if (ssb_mode == SPEC_STORE_BYPASS_DISABLE)
+ x86_amd_ssb_disable();
+}
#ifdef CONFIG_SYSFS
-ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf)
+
+static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
+ char *buf, unsigned int bug)
{
- if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
+ if (!boot_cpu_has_bug(bug))
return sprintf(buf, "Not affected\n");
- if (boot_cpu_has(X86_FEATURE_PTI))
- return sprintf(buf, "Mitigation: PTI\n");
+
+ switch (bug) {
+ case X86_BUG_CPU_MELTDOWN:
+ if (boot_cpu_has(X86_FEATURE_PTI))
+ return sprintf(buf, "Mitigation: PTI\n");
+
+ break;
+
+ case X86_BUG_SPECTRE_V1:
+ return sprintf(buf, "Mitigation: __user pointer sanitization\n");
+
+ case X86_BUG_SPECTRE_V2:
+ return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
+ boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "",
+ boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "",
+ spectre_v2_module_string());
+
+ case X86_BUG_SPEC_STORE_BYPASS:
+ return sprintf(buf, "%s\n", ssb_strings[ssb_mode]);
+
+ default:
+ break;
+ }
+
return sprintf(buf, "Vulnerable\n");
}
+ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ return cpu_show_common(dev, attr, buf, X86_BUG_CPU_MELTDOWN);
+}
+
ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf)
{
- if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1))
- return sprintf(buf, "Not affected\n");
- return sprintf(buf, "Mitigation: __user pointer sanitization\n");
+ return cpu_show_common(dev, attr, buf, X86_BUG_SPECTRE_V1);
}
ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf)
{
- if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
- return sprintf(buf, "Not affected\n");
+ return cpu_show_common(dev, attr, buf, X86_BUG_SPECTRE_V2);
+}
- return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
- boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "",
- boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "",
- spectre_v2_module_string());
+ssize_t cpu_show_spec_store_bypass(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ return cpu_show_common(dev, attr, buf, X86_BUG_SPEC_STORE_BYPASS);
}
#endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index ce243f7d2d4e..38276f58d3bf 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -757,17 +757,32 @@ static void init_speculation_control(struct cpuinfo_x86 *c)
* 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.
- *
- * We use the AMD bits in 0x8000_0008 EBX as the generic hardware
- * features, which are visible in /proc/cpuinfo and used by the
- * kernel. So set those accordingly from the Intel bits.
*/
if (cpu_has(c, X86_FEATURE_SPEC_CTRL)) {
set_cpu_cap(c, X86_FEATURE_IBRS);
set_cpu_cap(c, X86_FEATURE_IBPB);
+ set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL);
}
+
if (cpu_has(c, X86_FEATURE_INTEL_STIBP))
set_cpu_cap(c, X86_FEATURE_STIBP);
+
+ if (cpu_has(c, X86_FEATURE_SPEC_CTRL_SSBD) ||
+ cpu_has(c, X86_FEATURE_VIRT_SSBD))
+ set_cpu_cap(c, X86_FEATURE_SSBD);
+
+ if (cpu_has(c, X86_FEATURE_AMD_IBRS)) {
+ set_cpu_cap(c, X86_FEATURE_IBRS);
+ set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL);
+ }
+
+ if (cpu_has(c, X86_FEATURE_AMD_IBPB))
+ set_cpu_cap(c, X86_FEATURE_IBPB);
+
+ if (cpu_has(c, X86_FEATURE_AMD_STIBP)) {
+ set_cpu_cap(c, X86_FEATURE_STIBP);
+ set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL);
+ }
}
void get_cpu_cap(struct cpuinfo_x86 *c)
@@ -927,21 +942,47 @@ static const __initconst struct x86_cpu_id cpu_no_meltdown[] = {
{}
};
-static bool __init cpu_vulnerable_to_meltdown(struct cpuinfo_x86 *c)
+/* Only list CPUs which speculate but are non susceptible to SSB */
+static const __initconst struct x86_cpu_id cpu_no_spec_store_bypass[] = {
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT1 },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT2 },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_MERRIFIELD },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_CORE_YONAH },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNL },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNM },
+ { X86_VENDOR_AMD, 0x12, },
+ { X86_VENDOR_AMD, 0x11, },
+ { X86_VENDOR_AMD, 0x10, },
+ { X86_VENDOR_AMD, 0xf, },
+ {}
+};
+
+static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
{
u64 ia32_cap = 0;
- if (x86_match_cpu(cpu_no_meltdown))
- return false;
+ if (x86_match_cpu(cpu_no_speculation))
+ return;
+
+ setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
+ setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES))
rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap);
+ if (!x86_match_cpu(cpu_no_spec_store_bypass) &&
+ !(ia32_cap & ARCH_CAP_SSB_NO))
+ setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS);
+
+ if (x86_match_cpu(cpu_no_meltdown))
+ return;
+
/* Rogue Data Cache Load? No! */
if (ia32_cap & ARCH_CAP_RDCL_NO)
- return false;
+ return;
- return true;
+ setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
}
/*
@@ -992,12 +1033,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
setup_force_cpu_cap(X86_FEATURE_ALWAYS);
- 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);
- }
+ cpu_set_bug_bits(c);
fpu__init_system(c);
@@ -1359,6 +1395,7 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c)
#endif
mtrr_ap_init();
validate_apic_and_package_id(c);
+ x86_spec_ctrl_setup_ap();
}
static __init int setup_noclflush(char *arg)
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index e806b11a99af..37672d299e35 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -50,4 +50,6 @@ extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c);
unsigned int aperfmperf_get_khz(int cpu);
+extern void x86_spec_ctrl_setup_ap(void);
+
#endif /* ARCH_X86_CPU_H */
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 60d1897041da..577e7f7ae273 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -188,7 +188,10 @@ static void early_init_intel(struct cpuinfo_x86 *c)
setup_clear_cpu_cap(X86_FEATURE_IBPB);
setup_clear_cpu_cap(X86_FEATURE_STIBP);
setup_clear_cpu_cap(X86_FEATURE_SPEC_CTRL);
+ setup_clear_cpu_cap(X86_FEATURE_MSR_SPEC_CTRL);
setup_clear_cpu_cap(X86_FEATURE_INTEL_STIBP);
+ setup_clear_cpu_cap(X86_FEATURE_SSBD);
+ setup_clear_cpu_cap(X86_FEATURE_SPEC_CTRL_SSBD);
}
/*
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index f7666eef4a87..c8e038800591 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -94,6 +94,11 @@ static struct smca_bank_name smca_names[] = {
[SMCA_SMU] = { "smu", "System Management Unit" },
};
+static u32 smca_bank_addrs[MAX_NR_BANKS][NR_BLOCKS] __ro_after_init =
+{
+ [0 ... MAX_NR_BANKS - 1] = { [0 ... NR_BLOCKS - 1] = -1 }
+};
+
const char *smca_get_name(enum smca_bank_types t)
{
if (t >= N_SMCA_BANK_TYPES)
@@ -443,20 +448,26 @@ static u32 smca_get_block_address(unsigned int cpu, unsigned int bank,
if (!block)
return MSR_AMD64_SMCA_MCx_MISC(bank);
+ /* Check our cache first: */
+ if (smca_bank_addrs[bank][block] != -1)
+ return smca_bank_addrs[bank][block];
+
/*
* For SMCA enabled processors, BLKPTR field of the first MISC register
* (MCx_MISC0) indicates presence of additional MISC regs set (MISC1-4).
*/
if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high))
- return addr;
+ goto out;
if (!(low & MCI_CONFIG_MCAX))
- return addr;
+ goto out;
if (!rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high) &&
(low & MASK_BLKPTR_LO))
- return MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1);
+ addr = MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1);
+out:
+ smca_bank_addrs[bank][block] = addr;
return addr;
}
@@ -468,18 +479,6 @@ static u32 get_block_address(unsigned int cpu, u32 current_addr, u32 low, u32 hi
if ((bank >= mca_cfg.banks) || (block >= NR_BLOCKS))
return addr;
- /* Get address from already initialized block. */
- if (per_cpu(threshold_banks, cpu)) {
- struct threshold_bank *bankp = per_cpu(threshold_banks, cpu)[bank];
-
- if (bankp && bankp->blocks) {
- struct threshold_block *blockp = &bankp->blocks[block];
-
- if (blockp)
- return blockp->address;
- }
- }
-
if (mce_flags.smca)
return smca_get_block_address(cpu, bank, block);
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 0c408f8c4ed4..2d29e47c056e 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -104,6 +104,12 @@ static bool __head check_la57_support(unsigned long physaddr)
}
#endif
+/* Code in __startup_64() can be relocated during execution, but the compiler
+ * doesn't have to generate PC-relative relocations when accessing globals from
+ * that function. Clang actually does not generate them, which leads to
+ * boot-time crashes. To work around this problem, every global pointer must
+ * be adjusted using fixup_pointer().
+ */
unsigned long __head __startup_64(unsigned long physaddr,
struct boot_params *bp)
{
@@ -113,6 +119,7 @@ unsigned long __head __startup_64(unsigned long physaddr,
p4dval_t *p4d;
pudval_t *pud;
pmdval_t *pmd, pmd_entry;
+ pteval_t *mask_ptr;
bool la57;
int i;
unsigned int *next_pgt_ptr;
@@ -196,7 +203,8 @@ unsigned long __head __startup_64(unsigned long physaddr,
pmd_entry = __PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL;
/* Filter out unsupported __PAGE_KERNEL_* bits: */
- pmd_entry &= __supported_pte_mask;
+ mask_ptr = fixup_pointer(&__supported_pte_mask, physaddr);
+ pmd_entry &= *mask_ptr;
pmd_entry += sme_get_me_mask();
pmd_entry += physaddr;
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 0715f827607c..6f4d42377fe5 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -370,6 +370,10 @@ int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn)
if (insn->opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
return 0;
+ /* We should not singlestep on the exception masking instructions */
+ if (insn_masking_exception(insn))
+ return 0;
+
#ifdef CONFIG_X86_64
/* Only x86_64 has RIP relative instructions */
if (insn_rip_relative(insn)) {
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 7867417cfaff..5b2300b818af 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -457,7 +457,7 @@ static void __init sev_map_percpu_data(void)
static void __init kvm_smp_prepare_cpus(unsigned int max_cpus)
{
native_smp_prepare_cpus(max_cpus);
- if (kvm_para_has_hint(KVM_HINTS_DEDICATED))
+ if (kvm_para_has_hint(KVM_HINTS_REALTIME))
static_branch_disable(&virt_spin_lock_key);
}
@@ -553,7 +553,7 @@ static void __init kvm_guest_init(void)
}
if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
- !kvm_para_has_hint(KVM_HINTS_DEDICATED) &&
+ !kvm_para_has_hint(KVM_HINTS_REALTIME) &&
kvm_para_has_feature(KVM_FEATURE_STEAL_TIME))
pv_mmu_ops.flush_tlb_others = kvm_flush_tlb_others;
@@ -649,7 +649,7 @@ static __init int kvm_setup_pv_tlb_flush(void)
int cpu;
if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
- !kvm_para_has_hint(KVM_HINTS_DEDICATED) &&
+ !kvm_para_has_hint(KVM_HINTS_REALTIME) &&
kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
for_each_possible_cpu(cpu) {
zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu),
@@ -745,7 +745,7 @@ void __init kvm_spinlock_init(void)
if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
return;
- if (kvm_para_has_hint(KVM_HINTS_DEDICATED))
+ if (kvm_para_has_hint(KVM_HINTS_REALTIME))
return;
__pv_init_lock_hash();
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index 60cdec6628b0..d1ab07ec8c9a 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -57,12 +57,17 @@ static void load_segments(void)
static void machine_kexec_free_page_tables(struct kimage *image)
{
free_page((unsigned long)image->arch.pgd);
+ image->arch.pgd = NULL;
#ifdef CONFIG_X86_PAE
free_page((unsigned long)image->arch.pmd0);
+ image->arch.pmd0 = NULL;
free_page((unsigned long)image->arch.pmd1);
+ image->arch.pmd1 = NULL;
#endif
free_page((unsigned long)image->arch.pte0);
+ image->arch.pte0 = NULL;
free_page((unsigned long)image->arch.pte1);
+ image->arch.pte1 = NULL;
}
static int machine_kexec_alloc_page_tables(struct kimage *image)
@@ -79,7 +84,6 @@ static int machine_kexec_alloc_page_tables(struct kimage *image)
!image->arch.pmd0 || !image->arch.pmd1 ||
#endif
!image->arch.pte0 || !image->arch.pte1) {
- machine_kexec_free_page_tables(image);
return -ENOMEM;
}
return 0;
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index a5e55d832d0a..6010449ca6d2 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -39,9 +39,13 @@ const struct kexec_file_ops * const kexec_file_loaders[] = {
static void free_transition_pgtable(struct kimage *image)
{
free_page((unsigned long)image->arch.p4d);
+ image->arch.p4d = NULL;
free_page((unsigned long)image->arch.pud);
+ image->arch.pud = NULL;
free_page((unsigned long)image->arch.pmd);
+ image->arch.pmd = NULL;
free_page((unsigned long)image->arch.pte);
+ image->arch.pte = NULL;
}
static int init_transition_pgtable(struct kimage *image, pgd_t *pgd)
@@ -91,7 +95,6 @@ static int init_transition_pgtable(struct kimage *image, pgd_t *pgd)
set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL_EXEC_NOENC));
return 0;
err:
- free_transition_pgtable(image);
return result;
}
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 03408b942adb..30ca2d1a9231 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -38,6 +38,7 @@
#include <asm/switch_to.h>
#include <asm/desc.h>
#include <asm/prctl.h>
+#include <asm/spec-ctrl.h>
/*
* per-CPU TSS segments. Threads are completely 'soft' on Linux,
@@ -278,6 +279,148 @@ static inline void switch_to_bitmap(struct tss_struct *tss,
}
}
+#ifdef CONFIG_SMP
+
+struct ssb_state {
+ struct ssb_state *shared_state;
+ raw_spinlock_t lock;
+ unsigned int disable_state;
+ unsigned long local_state;
+};
+
+#define LSTATE_SSB 0
+
+static DEFINE_PER_CPU(struct ssb_state, ssb_state);
+
+void speculative_store_bypass_ht_init(void)
+{
+ struct ssb_state *st = this_cpu_ptr(&ssb_state);
+ unsigned int this_cpu = smp_processor_id();
+ unsigned int cpu;
+
+ st->local_state = 0;
+
+ /*
+ * Shared state setup happens once on the first bringup
+ * of the CPU. It's not destroyed on CPU hotunplug.
+ */
+ if (st->shared_state)
+ return;
+
+ raw_spin_lock_init(&st->lock);
+
+ /*
+ * Go over HT siblings and check whether one of them has set up the
+ * shared state pointer already.
+ */
+ for_each_cpu(cpu, topology_sibling_cpumask(this_cpu)) {
+ if (cpu == this_cpu)
+ continue;
+
+ if (!per_cpu(ssb_state, cpu).shared_state)
+ continue;
+
+ /* Link it to the state of the sibling: */
+ st->shared_state = per_cpu(ssb_state, cpu).shared_state;
+ return;
+ }
+
+ /*
+ * First HT sibling to come up on the core. Link shared state of
+ * the first HT sibling to itself. The siblings on the same core
+ * which come up later will see the shared state pointer and link
+ * themself to the state of this CPU.
+ */
+ st->shared_state = st;
+}
+
+/*
+ * Logic is: First HT sibling enables SSBD for both siblings in the core
+ * and last sibling to disable it, disables it for the whole core. This how
+ * MSR_SPEC_CTRL works in "hardware":
+ *
+ * CORE_SPEC_CTRL = THREAD0_SPEC_CTRL | THREAD1_SPEC_CTRL
+ */
+static __always_inline void amd_set_core_ssb_state(unsigned long tifn)
+{
+ struct ssb_state *st = this_cpu_ptr(&ssb_state);
+ u64 msr = x86_amd_ls_cfg_base;
+
+ if (!static_cpu_has(X86_FEATURE_ZEN)) {
+ msr |= ssbd_tif_to_amd_ls_cfg(tifn);
+ wrmsrl(MSR_AMD64_LS_CFG, msr);
+ return;
+ }
+
+ if (tifn & _TIF_SSBD) {
+ /*
+ * Since this can race with prctl(), block reentry on the
+ * same CPU.
+ */
+ if (__test_and_set_bit(LSTATE_SSB, &st->local_state))
+ return;
+
+ msr |= x86_amd_ls_cfg_ssbd_mask;
+
+ raw_spin_lock(&st->shared_state->lock);
+ /* First sibling enables SSBD: */
+ if (!st->shared_state->disable_state)
+ wrmsrl(MSR_AMD64_LS_CFG, msr);
+ st->shared_state->disable_state++;
+ raw_spin_unlock(&st->shared_state->lock);
+ } else {
+ if (!__test_and_clear_bit(LSTATE_SSB, &st->local_state))
+ return;
+
+ raw_spin_lock(&st->shared_state->lock);
+ st->shared_state->disable_state--;
+ if (!st->shared_state->disable_state)
+ wrmsrl(MSR_AMD64_LS_CFG, msr);
+ raw_spin_unlock(&st->shared_state->lock);
+ }
+}
+#else
+static __always_inline void amd_set_core_ssb_state(unsigned long tifn)
+{
+ u64 msr = x86_amd_ls_cfg_base | ssbd_tif_to_amd_ls_cfg(tifn);
+
+ wrmsrl(MSR_AMD64_LS_CFG, msr);
+}
+#endif
+
+static __always_inline void amd_set_ssb_virt_state(unsigned long tifn)
+{
+ /*
+ * SSBD has the same definition in SPEC_CTRL and VIRT_SPEC_CTRL,
+ * so ssbd_tif_to_spec_ctrl() just works.
+ */
+ wrmsrl(MSR_AMD64_VIRT_SPEC_CTRL, ssbd_tif_to_spec_ctrl(tifn));
+}
+
+static __always_inline void intel_set_ssb_state(unsigned long tifn)
+{
+ u64 msr = x86_spec_ctrl_base | ssbd_tif_to_spec_ctrl(tifn);
+
+ wrmsrl(MSR_IA32_SPEC_CTRL, msr);
+}
+
+static __always_inline void __speculative_store_bypass_update(unsigned long tifn)
+{
+ if (static_cpu_has(X86_FEATURE_VIRT_SSBD))
+ amd_set_ssb_virt_state(tifn);
+ else if (static_cpu_has(X86_FEATURE_LS_CFG_SSBD))
+ amd_set_core_ssb_state(tifn);
+ else
+ intel_set_ssb_state(tifn);
+}
+
+void speculative_store_bypass_update(unsigned long tif)
+{
+ preempt_disable();
+ __speculative_store_bypass_update(tif);
+ preempt_enable();
+}
+
void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
struct tss_struct *tss)
{
@@ -309,6 +452,9 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
if ((tifp ^ tifn) & _TIF_NOCPUID)
set_cpuid_faulting(!!(tifn & _TIF_NOCPUID));
+
+ if ((tifp ^ tifn) & _TIF_SSBD)
+ __speculative_store_bypass_update(tifn);
}
/*
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 4b100fe0f508..12bb445fb98d 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -542,6 +542,7 @@ void set_personality_64bit(void)
clear_thread_flag(TIF_X32);
/* Pretend that this comes from a 64bit execve */
task_pt_regs(current)->orig_ax = __NR_execve;
+ current_thread_info()->status &= ~TS_COMPAT;
/* Ensure the corresponding mm is not marked. */
if (current->mm)
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 0f1cbb042f49..9dd324ae4832 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -79,6 +79,7 @@
#include <asm/qspinlock.h>
#include <asm/intel-family.h>
#include <asm/cpu_device_id.h>
+#include <asm/spec-ctrl.h>
/* Number of siblings per CPU package */
int smp_num_siblings = 1;
@@ -244,6 +245,8 @@ static void notrace start_secondary(void *unused)
*/
check_tsc_sync_target();
+ speculative_store_bypass_ht_init();
+
/*
* Lock vector_lock, set CPU online and bring the vector
* allocator online. Online must be set with vector_lock held
@@ -1292,6 +1295,8 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
set_mtrr_aps_delayed_init();
smp_quirk_init_udelay();
+
+ speculative_store_bypass_ht_init();
}
void arch_enable_nonboot_cpus_begin(void)
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 85c7ef23d99f..c84bb5396958 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -299,6 +299,10 @@ static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool
if (is_prefix_bad(insn))
return -ENOTSUPP;
+ /* We should not singlestep on the exception masking instructions */
+ if (insn_masking_exception(insn))
+ return -ENOTSUPP;
+
if (x86_64)
good_insns = good_insns_64;
else
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 82055b90a8b3..92bf2f2e7cdd 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -379,7 +379,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
/* cpuid 0x80000008.ebx */
const u32 kvm_cpuid_8000_0008_ebx_x86_features =
- F(IBPB) | F(IBRS);
+ F(AMD_IBPB) | F(AMD_IBRS) | F(VIRT_SSBD);
/* cpuid 0xC0000001.edx */
const u32 kvm_cpuid_C000_0001_edx_x86_features =
@@ -408,7 +408,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
/* cpuid 7.0.edx*/
const u32 kvm_cpuid_7_0_edx_x86_features =
F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) |
- F(ARCH_CAPABILITIES);
+ F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES);
/* all calls to cpuid_count() should be made on the same cpu */
get_cpu();
@@ -495,6 +495,11 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
entry->ecx &= ~F(PKU);
entry->edx &= kvm_cpuid_7_0_edx_x86_features;
cpuid_mask(&entry->edx, CPUID_7_EDX);
+ /*
+ * We emulate ARCH_CAPABILITIES in software even
+ * if the host doesn't support it.
+ */
+ entry->edx |= F(ARCH_CAPABILITIES);
} else {
entry->ebx = 0;
entry->ecx = 0;
@@ -647,13 +652,20 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
g_phys_as = phys_as;
entry->eax = g_phys_as | (virt_as << 8);
entry->edx = 0;
- /* IBRS and IBPB aren't necessarily present in hardware cpuid */
- if (boot_cpu_has(X86_FEATURE_IBPB))
- entry->ebx |= F(IBPB);
- if (boot_cpu_has(X86_FEATURE_IBRS))
- entry->ebx |= F(IBRS);
+ /*
+ * IBRS, IBPB and VIRT_SSBD aren't necessarily present in
+ * hardware cpuid
+ */
+ if (boot_cpu_has(X86_FEATURE_AMD_IBPB))
+ entry->ebx |= F(AMD_IBPB);
+ if (boot_cpu_has(X86_FEATURE_AMD_IBRS))
+ entry->ebx |= F(AMD_IBRS);
+ if (boot_cpu_has(X86_FEATURE_VIRT_SSBD))
+ entry->ebx |= F(VIRT_SSBD);
entry->ebx &= kvm_cpuid_8000_0008_ebx_x86_features;
cpuid_mask(&entry->ebx, CPUID_8000_0008_EBX);
+ if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD))
+ entry->ebx |= F(VIRT_SSBD);
break;
}
case 0x80000019:
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 98618e397342..46ff64da44ca 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1260,12 +1260,16 @@ static void kvm_hv_hypercall_set_result(struct kvm_vcpu *vcpu, u64 result)
}
}
-static int kvm_hv_hypercall_complete_userspace(struct kvm_vcpu *vcpu)
+static int kvm_hv_hypercall_complete(struct kvm_vcpu *vcpu, u64 result)
{
- struct kvm_run *run = vcpu->run;
+ kvm_hv_hypercall_set_result(vcpu, result);
+ ++vcpu->stat.hypercalls;
+ return kvm_skip_emulated_instruction(vcpu);
+}
- kvm_hv_hypercall_set_result(vcpu, run->hyperv.u.hcall.result);
- return 1;
+static int kvm_hv_hypercall_complete_userspace(struct kvm_vcpu *vcpu)
+{
+ return kvm_hv_hypercall_complete(vcpu, vcpu->run->hyperv.u.hcall.result);
}
static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, bool fast, u64 param)
@@ -1296,8 +1300,10 @@ static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, bool fast, u64 param)
if (param & ~KVM_HYPERV_CONN_ID_MASK)
return HV_STATUS_INVALID_HYPERCALL_INPUT;
- /* conn_to_evt is protected by vcpu->kvm->srcu */
+ /* the eventfd is protected by vcpu->kvm->srcu, but conn_to_evt isn't */
+ rcu_read_lock();
eventfd = idr_find(&vcpu->kvm->arch.hyperv.conn_to_evt, param);
+ rcu_read_unlock();
if (!eventfd)
return HV_STATUS_INVALID_PORT_ID;
@@ -1348,7 +1354,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
/* Hypercall continuation is not supported yet */
if (rep_cnt || rep_idx) {
ret = HV_STATUS_INVALID_HYPERCALL_CODE;
- goto set_result;
+ goto out;
}
switch (code) {
@@ -1379,9 +1385,8 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
break;
}
-set_result:
- kvm_hv_hypercall_set_result(vcpu, ret);
- return 1;
+out:
+ return kvm_hv_hypercall_complete(vcpu, ret);
}
void kvm_hv_init_vm(struct kvm *kvm)
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index b74c9c1405b9..3773c4625114 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1522,11 +1522,23 @@ static bool set_target_expiration(struct kvm_lapic *apic)
static void advance_periodic_target_expiration(struct kvm_lapic *apic)
{
- apic->lapic_timer.tscdeadline +=
- nsec_to_cycles(apic->vcpu, apic->lapic_timer.period);
+ ktime_t now = ktime_get();
+ u64 tscl = rdtsc();
+ ktime_t delta;
+
+ /*
+ * Synchronize both deadlines to the same time source or
+ * differences in the periods (caused by differences in the
+ * underlying clocks or numerical approximation errors) will
+ * cause the two to drift apart over time as the errors
+ * accumulate.
+ */
apic->lapic_timer.target_expiration =
ktime_add_ns(apic->lapic_timer.target_expiration,
apic->lapic_timer.period);
+ delta = ktime_sub(apic->lapic_timer.target_expiration, now);
+ apic->lapic_timer.tscdeadline = kvm_read_l1_tsc(apic->vcpu, tscl) +
+ nsec_to_cycles(apic->vcpu, delta);
}
static void start_sw_period(struct kvm_lapic *apic)
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 1fc05e428aba..26110c202b19 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -49,7 +49,7 @@
#include <asm/debugreg.h>
#include <asm/kvm_para.h>
#include <asm/irq_remapping.h>
-#include <asm/nospec-branch.h>
+#include <asm/spec-ctrl.h>
#include <asm/virtext.h>
#include "trace.h"
@@ -213,6 +213,12 @@ struct vcpu_svm {
} host;
u64 spec_ctrl;
+ /*
+ * Contains guest-controlled bits of VIRT_SPEC_CTRL, which will be
+ * translated into the appropriate L2_CFG bits on the host to
+ * perform speculative control.
+ */
+ u64 virt_spec_ctrl;
u32 *msrpm;
@@ -2060,6 +2066,7 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
vcpu->arch.microcode_version = 0x01000065;
svm->spec_ctrl = 0;
+ svm->virt_spec_ctrl = 0;
if (!init_event) {
svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE |
@@ -4108,11 +4115,18 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
break;
case MSR_IA32_SPEC_CTRL:
if (!msr_info->host_initiated &&
- !guest_cpuid_has(vcpu, X86_FEATURE_IBRS))
+ !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS))
return 1;
msr_info->data = svm->spec_ctrl;
break;
+ case MSR_AMD64_VIRT_SPEC_CTRL:
+ if (!msr_info->host_initiated &&
+ !guest_cpuid_has(vcpu, X86_FEATURE_VIRT_SSBD))
+ return 1;
+
+ msr_info->data = svm->virt_spec_ctrl;
+ break;
case MSR_F15H_IC_CFG: {
int family, model;
@@ -4203,7 +4217,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
break;
case MSR_IA32_SPEC_CTRL:
if (!msr->host_initiated &&
- !guest_cpuid_has(vcpu, X86_FEATURE_IBRS))
+ !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS))
return 1;
/* The STIBP bit doesn't fault even if it's not advertised */
@@ -4230,7 +4244,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
break;
case MSR_IA32_PRED_CMD:
if (!msr->host_initiated &&
- !guest_cpuid_has(vcpu, X86_FEATURE_IBPB))
+ !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBPB))
return 1;
if (data & ~PRED_CMD_IBPB)
@@ -4244,6 +4258,16 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
break;
set_msr_interception(svm->msrpm, MSR_IA32_PRED_CMD, 0, 1);
break;
+ case MSR_AMD64_VIRT_SPEC_CTRL:
+ if (!msr->host_initiated &&
+ !guest_cpuid_has(vcpu, X86_FEATURE_VIRT_SSBD))
+ return 1;
+
+ if (data & ~SPEC_CTRL_SSBD)
+ return 1;
+
+ svm->virt_spec_ctrl = data;
+ break;
case MSR_STAR:
svm->vmcb->save.star = data;
break;
@@ -5557,8 +5581,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
* is no need to worry about the conditional branch over the wrmsr
* being speculatively taken.
*/
- if (svm->spec_ctrl)
- native_wrmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl);
+ x86_spec_ctrl_set_guest(svm->spec_ctrl, svm->virt_spec_ctrl);
asm volatile (
"push %%" _ASM_BP "; \n\t"
@@ -5652,6 +5675,18 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
#endif
);
+ /* Eliminate branch target predictions from guest mode */
+ vmexit_fill_RSB();
+
+#ifdef CONFIG_X86_64
+ wrmsrl(MSR_GS_BASE, svm->host.gs_base);
+#else
+ loadsegment(fs, svm->host.fs);
+#ifndef CONFIG_X86_32_LAZY_GS
+ loadsegment(gs, svm->host.gs);
+#endif
+#endif
+
/*
* We do not use IBRS in the kernel. If this vCPU has used the
* SPEC_CTRL MSR it may have left it on; save the value and
@@ -5670,20 +5705,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)))
svm->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);
- if (svm->spec_ctrl)
- native_wrmsrl(MSR_IA32_SPEC_CTRL, 0);
-
- /* Eliminate branch target predictions from guest mode */
- vmexit_fill_RSB();
-
-#ifdef CONFIG_X86_64
- wrmsrl(MSR_GS_BASE, svm->host.gs_base);
-#else
- loadsegment(fs, svm->host.fs);
-#ifndef CONFIG_X86_32_LAZY_GS
- loadsegment(gs, svm->host.gs);
-#endif
-#endif
+ x86_spec_ctrl_restore_host(svm->spec_ctrl, svm->virt_spec_ctrl);
reload_tss(vcpu);
@@ -5786,7 +5808,7 @@ static bool svm_cpu_has_accelerated_tpr(void)
return false;
}
-static bool svm_has_high_real_mode_segbase(void)
+static bool svm_has_emulated_msr(int index)
{
return true;
}
@@ -7012,7 +7034,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
.hardware_enable = svm_hardware_enable,
.hardware_disable = svm_hardware_disable,
.cpu_has_accelerated_tpr = svm_cpu_has_accelerated_tpr,
- .cpu_has_high_real_mode_segbase = svm_has_high_real_mode_segbase,
+ .has_emulated_msr = svm_has_emulated_msr,
.vcpu_create = svm_create_vcpu,
.vcpu_free = svm_free_vcpu,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c7668806163f..40aa29204baf 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -51,7 +51,7 @@
#include <asm/apic.h>
#include <asm/irq_remapping.h>
#include <asm/mmu_context.h>
-#include <asm/nospec-branch.h>
+#include <asm/spec-ctrl.h>
#include <asm/mshyperv.h>
#include "trace.h"
@@ -1494,6 +1494,12 @@ static inline bool cpu_has_vmx_vmfunc(void)
SECONDARY_EXEC_ENABLE_VMFUNC;
}
+static bool vmx_umip_emulated(void)
+{
+ return vmcs_config.cpu_based_2nd_exec_ctrl &
+ SECONDARY_EXEC_DESC;
+}
+
static inline bool report_flexpriority(void)
{
return flexpriority_enabled;
@@ -3523,7 +3529,6 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
return kvm_get_msr_common(vcpu, msr_info);
case MSR_IA32_SPEC_CTRL:
if (!msr_info->host_initiated &&
- !guest_cpuid_has(vcpu, X86_FEATURE_IBRS) &&
!guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
return 1;
@@ -3642,12 +3647,11 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
break;
case MSR_IA32_SPEC_CTRL:
if (!msr_info->host_initiated &&
- !guest_cpuid_has(vcpu, X86_FEATURE_IBRS) &&
!guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
return 1;
/* The STIBP bit doesn't fault even if it's not advertised */
- if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP))
+ if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD))
return 1;
vmx->spec_ctrl = data;
@@ -3673,7 +3677,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
break;
case MSR_IA32_PRED_CMD:
if (!msr_info->host_initiated &&
- !guest_cpuid_has(vcpu, X86_FEATURE_IBPB) &&
!guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
return 1;
@@ -4761,14 +4764,16 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
else
hw_cr4 |= KVM_PMODE_VM_CR4_ALWAYS_ON;
- if ((cr4 & X86_CR4_UMIP) && !boot_cpu_has(X86_FEATURE_UMIP)) {
- vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
- SECONDARY_EXEC_DESC);
- hw_cr4 &= ~X86_CR4_UMIP;
- } else if (!is_guest_mode(vcpu) ||
- !nested_cpu_has2(get_vmcs12(vcpu), SECONDARY_EXEC_DESC))
- vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
+ if (!boot_cpu_has(X86_FEATURE_UMIP) && vmx_umip_emulated()) {
+ if (cr4 & X86_CR4_UMIP) {
+ vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
SECONDARY_EXEC_DESC);
+ hw_cr4 &= ~X86_CR4_UMIP;
+ } else if (!is_guest_mode(vcpu) ||
+ !nested_cpu_has2(get_vmcs12(vcpu), SECONDARY_EXEC_DESC))
+ vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
+ SECONDARY_EXEC_DESC);
+ }
if (cr4 & X86_CR4_VMXE) {
/*
@@ -9480,9 +9485,21 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
}
STACK_FRAME_NON_STANDARD(vmx_handle_external_intr);
-static bool vmx_has_high_real_mode_segbase(void)
+static bool vmx_has_emulated_msr(int index)
{
- return enable_unrestricted_guest || emulate_invalid_guest_state;
+ switch (index) {
+ case MSR_IA32_SMBASE:
+ /*
+ * We cannot do SMM unless we can run the guest in big
+ * real mode.
+ */
+ return enable_unrestricted_guest || emulate_invalid_guest_state;
+ case MSR_AMD64_VIRT_SPEC_CTRL:
+ /* This is AMD only. */
+ return false;
+ default:
+ return true;
+ }
}
static bool vmx_mpx_supported(void)
@@ -9497,12 +9514,6 @@ static bool vmx_xsaves_supported(void)
SECONDARY_EXEC_XSAVES;
}
-static bool vmx_umip_emulated(void)
-{
- return vmcs_config.cpu_based_2nd_exec_ctrl &
- SECONDARY_EXEC_DESC;
-}
-
static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx)
{
u32 exit_intr_info;
@@ -9720,8 +9731,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
* is no need to worry about the conditional branch over the wrmsr
* being speculatively taken.
*/
- if (vmx->spec_ctrl)
- native_wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl);
+ x86_spec_ctrl_set_guest(vmx->spec_ctrl, 0);
vmx->__launched = vmx->loaded_vmcs->launched;
@@ -9869,8 +9879,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)))
vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);
- if (vmx->spec_ctrl)
- native_wrmsrl(MSR_IA32_SPEC_CTRL, 0);
+ x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0);
/* Eliminate branch target predictions from guest mode */
vmexit_fill_RSB();
@@ -12630,7 +12639,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
.hardware_enable = hardware_enable,
.hardware_disable = hardware_disable,
.cpu_has_accelerated_tpr = report_flexpriority,
- .cpu_has_high_real_mode_segbase = vmx_has_high_real_mode_segbase,
+ .has_emulated_msr = vmx_has_emulated_msr,
.vm_init = vmx_vm_init,
.vm_alloc = vmx_vm_alloc,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 51ecd381793b..71e7cda6d014 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -114,7 +114,7 @@ module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR);
static bool __read_mostly report_ignored_msrs = true;
module_param(report_ignored_msrs, bool, S_IRUGO | S_IWUSR);
-unsigned int min_timer_period_us = 500;
+unsigned int min_timer_period_us = 200;
module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR);
static bool __read_mostly kvmclock_periodic_sync = true;
@@ -843,7 +843,10 @@ EXPORT_SYMBOL_GPL(kvm_set_cr4);
int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
{
#ifdef CONFIG_X86_64
- cr3 &= ~CR3_PCID_INVD;
+ bool pcid_enabled = kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE);
+
+ if (pcid_enabled)
+ cr3 &= ~CR3_PCID_INVD;
#endif
if (cr3 == kvm_read_cr3(vcpu) && !pdptrs_changed(vcpu)) {
@@ -1058,6 +1061,7 @@ static u32 emulated_msrs[] = {
MSR_SMI_COUNT,
MSR_PLATFORM_INFO,
MSR_MISC_FEATURES_ENABLES,
+ MSR_AMD64_VIRT_SPEC_CTRL,
};
static unsigned num_emulated_msrs;
@@ -2903,7 +2907,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
* fringe case that is not enabled except via specific settings
* of the module parameters.
*/
- r = kvm_x86_ops->cpu_has_high_real_mode_segbase();
+ r = kvm_x86_ops->has_emulated_msr(MSR_IA32_SMBASE);
break;
case KVM_CAP_VAPIC:
r = !kvm_x86_ops->cpu_has_accelerated_tpr();
@@ -4603,14 +4607,8 @@ static void kvm_init_msr_list(void)
num_msrs_to_save = j;
for (i = j = 0; i < ARRAY_SIZE(emulated_msrs); i++) {
- switch (emulated_msrs[i]) {
- case MSR_IA32_SMBASE:
- if (!kvm_x86_ops->cpu_has_high_real_mode_segbase())
- continue;
- break;
- default:
- break;
- }
+ if (!kvm_x86_ops->has_emulated_msr(emulated_msrs[i]))
+ continue;
if (j < i)
emulated_msrs[j] = emulated_msrs[i];
@@ -6671,9 +6669,7 @@ void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu)
int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
{
unsigned long nr, a0, a1, a2, a3, ret;
- int op_64_bit, r;
-
- r = kvm_skip_emulated_instruction(vcpu);
+ int op_64_bit;
if (kvm_hv_hypercall_enabled(vcpu->kvm))
return kvm_hv_hypercall(vcpu);
@@ -6721,8 +6717,9 @@ out:
if (!op_64_bit)
ret = (u32)ret;
kvm_register_write(vcpu, VCPU_REGS_RAX, ret);
+
++vcpu->stat.hypercalls;
- return r;
+ return kvm_skip_emulated_instruction(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_emulate_hypercall);
@@ -7979,6 +7976,7 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
{
struct msr_data apic_base_msr;
int mmu_reset_needed = 0;
+ int cpuid_update_needed = 0;
int pending_vec, max_bits, idx;
struct desc_ptr dt;
int ret = -EINVAL;
@@ -8017,8 +8015,10 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
vcpu->arch.cr0 = sregs->cr0;
mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4;
+ cpuid_update_needed |= ((kvm_read_cr4(vcpu) ^ sregs->cr4) &
+ (X86_CR4_OSXSAVE | X86_CR4_PKE));
kvm_x86_ops->set_cr4(vcpu, sregs->cr4);
- if (sregs->cr4 & (X86_CR4_OSXSAVE | X86_CR4_PKE))
+ if (cpuid_update_needed)
kvm_update_cpuid(vcpu);
idx = srcu_read_lock(&vcpu->kvm->srcu);
diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c
index d7bc0eea20a5..6e98e0a7c923 100644
--- a/arch/x86/mm/pkeys.c
+++ b/arch/x86/mm/pkeys.c
@@ -94,26 +94,27 @@ int __arch_override_mprotect_pkey(struct vm_area_struct *vma, int prot, int pkey
*/
if (pkey != -1)
return pkey;
- /*
- * Look for a protection-key-drive execute-only mapping
- * which is now being given permissions that are not
- * execute-only. Move it back to the default pkey.
- */
- if (vma_is_pkey_exec_only(vma) &&
- (prot & (PROT_READ|PROT_WRITE))) {
- return 0;
- }
+
/*
* The mapping is execute-only. Go try to get the
* execute-only protection key. If we fail to do that,
* fall through as if we do not have execute-only
- * support.
+ * support in this mm.
*/
if (prot == PROT_EXEC) {
pkey = execute_only_pkey(vma->vm_mm);
if (pkey > 0)
return pkey;
+ } else if (vma_is_pkey_exec_only(vma)) {
+ /*
+ * Protections are *not* PROT_EXEC, but the mapping
+ * is using the exec-only pkey. This mapping was
+ * PROT_EXEC and will no longer be. Move back to
+ * the default pkey.
+ */
+ return ARCH_DEFAULT_PKEY;
}
+
/*
* This is a vanilla, non-pkey mprotect (or we failed to
* setup execute-only), inherit the pkey from the VMA we
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index d33e7dbe3129..2d76106788a3 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -42,13 +42,11 @@ xmaddr_t arbitrary_virt_to_machine(void *vaddr)
}
EXPORT_SYMBOL_GPL(arbitrary_virt_to_machine);
-static void xen_flush_tlb_all(void)
+static noinline void xen_flush_tlb_all(void)
{
struct mmuext_op *op;
struct multicall_space mcs;
- trace_xen_mmu_flush_tlb_all(0);
-
preempt_disable();
mcs = xen_mc_entry(sizeof(*op));
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 486c0a34d00b..2c30cabfda90 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -1310,13 +1310,11 @@ unsigned long xen_read_cr2_direct(void)
return this_cpu_read(xen_vcpu_info.arch.cr2);
}
-static void xen_flush_tlb(void)
+static noinline void xen_flush_tlb(void)
{
struct mmuext_op *op;
struct multicall_space mcs;
- trace_xen_mmu_flush_tlb(0);
-
preempt_disable();
mcs = xen_mc_entry(sizeof(*op));