summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig11
-rw-r--r--arch/x86/coco/sev/core.c22
-rw-r--r--arch/x86/entry/entry.S8
-rw-r--r--arch/x86/events/intel/core.c2
-rw-r--r--arch/x86/include/asm/amd/fch.h13
-rw-r--r--arch/x86/include/asm/cpufeatures.h6
-rw-r--r--arch/x86/include/asm/debugreg.h19
-rw-r--r--arch/x86/include/asm/irqflags.h4
-rw-r--r--arch/x86/include/asm/kvm_host.h10
-rw-r--r--arch/x86/include/asm/module.h8
-rw-r--r--arch/x86/include/asm/mwait.h27
-rw-r--r--arch/x86/include/asm/nospec-branch.h37
-rw-r--r--arch/x86/include/asm/pgtable.h2
-rw-r--r--arch/x86/include/asm/sev.h17
-rw-r--r--arch/x86/include/asm/shared/tdx.h2
-rw-r--r--arch/x86/include/asm/sighandling.h22
-rw-r--r--arch/x86/include/asm/tdx.h2
-rw-r--r--arch/x86/include/uapi/asm/debugreg.h21
-rw-r--r--arch/x86/include/uapi/asm/kvm.h8
-rw-r--r--arch/x86/kernel/alternative.c81
-rw-r--r--arch/x86/kernel/cpu/amd.c48
-rw-r--r--arch/x86/kernel/cpu/bugs.c136
-rw-r--r--arch/x86/kernel/cpu/common.c38
-rw-r--r--arch/x86/kernel/cpu/mce/amd.c28
-rw-r--r--arch/x86/kernel/cpu/mce/core.c24
-rw-r--r--arch/x86/kernel/cpu/mce/intel.c1
-rw-r--r--arch/x86/kernel/cpu/microcode/amd_shas.c112
-rw-r--r--arch/x86/kernel/cpu/resctrl/core.c6
-rw-r--r--arch/x86/kernel/cpu/scattered.c2
-rw-r--r--arch/x86/kernel/kgdb.c2
-rw-r--r--arch/x86/kernel/process.c16
-rw-r--r--arch/x86/kernel/process_32.c2
-rw-r--r--arch/x86/kernel/process_64.c2
-rw-r--r--arch/x86/kernel/signal_32.c4
-rw-r--r--arch/x86/kernel/signal_64.c4
-rw-r--r--arch/x86/kernel/smp.c24
-rw-r--r--arch/x86/kernel/smpboot.c54
-rw-r--r--arch/x86/kernel/traps.c34
-rw-r--r--arch/x86/kvm/cpuid.c10
-rw-r--r--arch/x86/kvm/hyperv.c5
-rw-r--r--arch/x86/kvm/mmu/mmu.c9
-rw-r--r--arch/x86/kvm/reverse_cpuid.h7
-rw-r--r--arch/x86/kvm/svm/sev.c56
-rw-r--r--arch/x86/kvm/svm/vmenter.S6
-rw-r--r--arch/x86/kvm/vmx/tdx.c113
-rw-r--r--arch/x86/kvm/vmx/vmx.c2
-rw-r--r--arch/x86/kvm/x86.c8
-rw-r--r--arch/x86/kvm/xen.c15
-rw-r--r--arch/x86/mm/init_32.c3
-rw-r--r--arch/x86/mm/init_64.c3
-rw-r--r--arch/x86/mm/pat/set_memory.c3
-rw-r--r--arch/x86/mm/pti.c5
-rw-r--r--arch/x86/power/hibernate.c19
-rw-r--r--arch/x86/um/ptrace.c2
-rw-r--r--arch/x86/virt/vmx/tdx/tdx.c5
55 files changed, 878 insertions, 252 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 340e5468980e..5b3362af7d65 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -89,7 +89,7 @@ config X86
select ARCH_HAS_DMA_OPS if GART_IOMMU || XEN
select ARCH_HAS_EARLY_DEBUG if KGDB
select ARCH_HAS_ELF_RANDOMIZE
- select ARCH_HAS_EXECMEM_ROX if X86_64
+ select ARCH_HAS_EXECMEM_ROX if X86_64 && STRICT_MODULE_RWX
select ARCH_HAS_FAST_MULTIPLIER
select ARCH_HAS_FORTIFY_SOURCE
select ARCH_HAS_GCOV_PROFILE_ALL
@@ -2695,6 +2695,15 @@ config MITIGATION_ITS
disabled, mitigation cannot be enabled via cmdline.
See <file:Documentation/admin-guide/hw-vuln/indirect-target-selection.rst>
+config MITIGATION_TSA
+ bool "Mitigate Transient Scheduler Attacks"
+ depends on CPU_SUP_AMD
+ default y
+ help
+ Enable mitigation for Transient Scheduler Attacks. TSA is a hardware
+ security vulnerability on AMD CPUs which can lead to forwarding of
+ invalid info to subsequent instructions and thus can affect their
+ timing and thereby cause a leakage.
endif
config ARCH_HAS_ADD_PAGES
diff --git a/arch/x86/coco/sev/core.c b/arch/x86/coco/sev/core.c
index b6db4e0b936b..7543a8b52c67 100644
--- a/arch/x86/coco/sev/core.c
+++ b/arch/x86/coco/sev/core.c
@@ -88,7 +88,7 @@ static const char * const sev_status_feat_names[] = {
*/
static u64 snp_tsc_scale __ro_after_init;
static u64 snp_tsc_offset __ro_after_init;
-static u64 snp_tsc_freq_khz __ro_after_init;
+static unsigned long snp_tsc_freq_khz __ro_after_init;
DEFINE_PER_CPU(struct sev_es_runtime_data*, runtime_data);
DEFINE_PER_CPU(struct sev_es_save_area *, sev_vmsa);
@@ -2167,15 +2167,31 @@ static unsigned long securetsc_get_tsc_khz(void)
void __init snp_secure_tsc_init(void)
{
- unsigned long long tsc_freq_mhz;
+ struct snp_secrets_page *secrets;
+ unsigned long tsc_freq_mhz;
+ void *mem;
if (!cc_platform_has(CC_ATTR_GUEST_SNP_SECURE_TSC))
return;
+ mem = early_memremap_encrypted(sev_secrets_pa, PAGE_SIZE);
+ if (!mem) {
+ pr_err("Unable to get TSC_FACTOR: failed to map the SNP secrets page.\n");
+ sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_SECURE_TSC);
+ }
+
+ secrets = (__force struct snp_secrets_page *)mem;
+
setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
rdmsrq(MSR_AMD64_GUEST_TSC_FREQ, tsc_freq_mhz);
- snp_tsc_freq_khz = (unsigned long)(tsc_freq_mhz * 1000);
+
+ /* Extract the GUEST TSC MHZ from BIT[17:0], rest is reserved space */
+ tsc_freq_mhz &= GENMASK_ULL(17, 0);
+
+ snp_tsc_freq_khz = SNP_SCALE_TSC_FREQ(tsc_freq_mhz * 1000, secrets->tsc_factor);
x86_platform.calibrate_cpu = securetsc_get_tsc_khz;
x86_platform.calibrate_tsc = securetsc_get_tsc_khz;
+
+ early_memunmap(mem, PAGE_SIZE);
}
diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S
index 175958b02f2b..8e9a0cc20a4a 100644
--- a/arch/x86/entry/entry.S
+++ b/arch/x86/entry/entry.S
@@ -36,20 +36,20 @@ EXPORT_SYMBOL_GPL(write_ibpb);
/*
* Define the VERW operand that is disguised as entry code so that
- * it can be referenced with KPTI enabled. This ensure VERW can be
+ * it can be referenced with KPTI enabled. This ensures VERW can be
* used late in exit-to-user path after page tables are switched.
*/
.pushsection .entry.text, "ax"
.align L1_CACHE_BYTES, 0xcc
-SYM_CODE_START_NOALIGN(mds_verw_sel)
+SYM_CODE_START_NOALIGN(x86_verw_sel)
UNWIND_HINT_UNDEFINED
ANNOTATE_NOENDBR
.word __KERNEL_DS
.align L1_CACHE_BYTES, 0xcc
-SYM_CODE_END(mds_verw_sel);
+SYM_CODE_END(x86_verw_sel);
/* For KVM */
-EXPORT_SYMBOL_GPL(mds_verw_sel);
+EXPORT_SYMBOL_GPL(x86_verw_sel);
.popsection
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 741b229f0718..c2fb729c270e 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2826,7 +2826,7 @@ static void intel_pmu_read_event(struct perf_event *event)
* If the PEBS counters snapshotting is enabled,
* the topdown event is available in PEBS records.
*/
- if (is_topdown_event(event) && !is_pebs_counter_event_group(event))
+ if (is_topdown_count(event) && !is_pebs_counter_event_group(event))
static_call(intel_pmu_update_topdown_event)(event, NULL);
else
intel_pmu_drain_pebs_buffer();
diff --git a/arch/x86/include/asm/amd/fch.h b/arch/x86/include/asm/amd/fch.h
deleted file mode 100644
index 2cf5153edbc2..000000000000
--- a/arch/x86/include/asm/amd/fch.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_AMD_FCH_H_
-#define _ASM_X86_AMD_FCH_H_
-
-#define FCH_PM_BASE 0xFED80300
-
-/* Register offsets from PM base: */
-#define FCH_PM_DECODEEN 0x00
-#define FCH_PM_DECODEEN_SMBUS0SEL GENMASK(20, 19)
-#define FCH_PM_SCRATCH 0x80
-#define FCH_PM_S5_RESET_STATUS 0xC0
-
-#endif /* _ASM_X86_AMD_FCH_H_ */
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index ee176236c2be..286d509f9363 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -456,6 +456,7 @@
#define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* No Nested Data Breakpoints */
#define X86_FEATURE_WRMSR_XX_BASE_NS (20*32+ 1) /* WRMSR to {FS,GS,KERNEL_GS}_BASE is non-serializing */
#define X86_FEATURE_LFENCE_RDTSC (20*32+ 2) /* LFENCE always serializing / synchronizes RDTSC */
+#define X86_FEATURE_VERW_CLEAR (20*32+ 5) /* The memory form of VERW mitigates TSA */
#define X86_FEATURE_NULL_SEL_CLR_BASE (20*32+ 6) /* Null Selector Clears Base */
#define X86_FEATURE_AUTOIBRS (20*32+ 8) /* Automatic IBRS */
#define X86_FEATURE_NO_SMM_CTL_MSR (20*32+ 9) /* SMM_CTL MSR is not present */
@@ -487,6 +488,9 @@
#define X86_FEATURE_PREFER_YMM (21*32+ 8) /* Avoid ZMM registers due to downclocking */
#define X86_FEATURE_APX (21*32+ 9) /* Advanced Performance Extensions */
#define X86_FEATURE_INDIRECT_THUNK_ITS (21*32+10) /* Use thunk for indirect branches in lower half of cacheline */
+#define X86_FEATURE_TSA_SQ_NO (21*32+11) /* AMD CPU not vulnerable to TSA-SQ */
+#define X86_FEATURE_TSA_L1_NO (21*32+12) /* AMD CPU not vulnerable to TSA-L1 */
+#define X86_FEATURE_CLEAR_CPU_BUF_VM (21*32+13) /* Clear CPU buffers using VERW before VMRUN */
/*
* BUG word(s)
@@ -542,5 +546,5 @@
#define X86_BUG_OLD_MICROCODE X86_BUG( 1*32+ 6) /* "old_microcode" CPU has old microcode, it is surely vulnerable to something */
#define X86_BUG_ITS X86_BUG( 1*32+ 7) /* "its" CPU is affected by Indirect Target Selection */
#define X86_BUG_ITS_NATIVE_ONLY X86_BUG( 1*32+ 8) /* "its_native_only" CPU is affected by ITS, VMX is not affected */
-
+#define X86_BUG_TSA X86_BUG( 1*32+ 9) /* "tsa" CPU is affected by Transient Scheduler Attacks */
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h
index 363110e6b2e3..a2c1f2d24b64 100644
--- a/arch/x86/include/asm/debugreg.h
+++ b/arch/x86/include/asm/debugreg.h
@@ -9,6 +9,14 @@
#include <asm/cpufeature.h>
#include <asm/msr.h>
+/*
+ * Define bits that are always set to 1 in DR7, only bit 10 is
+ * architecturally reserved to '1'.
+ *
+ * This is also the init/reset value for DR7.
+ */
+#define DR7_FIXED_1 0x00000400
+
DECLARE_PER_CPU(unsigned long, cpu_dr7);
#ifndef CONFIG_PARAVIRT_XXL
@@ -100,8 +108,8 @@ static __always_inline void native_set_debugreg(int regno, unsigned long value)
static inline void hw_breakpoint_disable(void)
{
- /* Zero the control register for HW Breakpoint */
- set_debugreg(0UL, 7);
+ /* Reset the control register for HW Breakpoint */
+ set_debugreg(DR7_FIXED_1, 7);
/* Zero-out the individual HW breakpoint address registers */
set_debugreg(0UL, 0);
@@ -125,9 +133,12 @@ static __always_inline unsigned long local_db_save(void)
return 0;
get_debugreg(dr7, 7);
- dr7 &= ~0x400; /* architecturally set bit */
+
+ /* Architecturally set bit */
+ dr7 &= ~DR7_FIXED_1;
if (dr7)
- set_debugreg(0, 7);
+ set_debugreg(DR7_FIXED_1, 7);
+
/*
* Ensure the compiler doesn't lower the above statements into
* the critical section; disabling breakpoints late would not
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index 9a9b21b78905..b30e5474c18e 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -44,13 +44,13 @@ static __always_inline void native_irq_enable(void)
static __always_inline void native_safe_halt(void)
{
- mds_idle_clear_cpu_buffers();
+ x86_idle_clear_cpu_buffers();
asm volatile("sti; hlt": : :"memory");
}
static __always_inline void native_halt(void)
{
- mds_idle_clear_cpu_buffers();
+ x86_idle_clear_cpu_buffers();
asm volatile("hlt": : :"memory");
}
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index b4a391929cdb..f7af967aa16f 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -31,6 +31,7 @@
#include <asm/apic.h>
#include <asm/pvclock-abi.h>
+#include <asm/debugreg.h>
#include <asm/desc.h>
#include <asm/mtrr.h>
#include <asm/msr-index.h>
@@ -249,7 +250,6 @@ enum x86_intercept_stage;
#define DR7_BP_EN_MASK 0x000000ff
#define DR7_GE (1 << 9)
#define DR7_GD (1 << 13)
-#define DR7_FIXED_1 0x00000400
#define DR7_VOLATILE 0xffff2bff
#define KVM_GUESTDBG_VALID_MASK \
@@ -700,8 +700,13 @@ struct kvm_vcpu_hv {
struct kvm_vcpu_hv_tlb_flush_fifo tlb_flush_fifo[HV_NR_TLB_FLUSH_FIFOS];
- /* Preallocated buffer for handling hypercalls passing sparse vCPU set */
+ /*
+ * Preallocated buffers for handling hypercalls that pass sparse vCPU
+ * sets (for high vCPU counts, they're too large to comfortably fit on
+ * the stack).
+ */
u64 sparse_banks[HV_MAX_SPARSE_VCPU_BANKS];
+ DECLARE_BITMAP(vcpu_mask, KVM_MAX_VCPUS);
struct hv_vp_assist_page vp_assist_page;
@@ -764,6 +769,7 @@ enum kvm_only_cpuid_leafs {
CPUID_8000_0022_EAX,
CPUID_7_2_EDX,
CPUID_24_0_EBX,
+ CPUID_8000_0021_ECX,
NR_KVM_CPU_CAPS,
NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS,
diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h
index e988bac0a4a1..3c2de4ce3b10 100644
--- a/arch/x86/include/asm/module.h
+++ b/arch/x86/include/asm/module.h
@@ -5,12 +5,20 @@
#include <asm-generic/module.h>
#include <asm/orc_types.h>
+struct its_array {
+#ifdef CONFIG_MITIGATION_ITS
+ void **pages;
+ int num;
+#endif
+};
+
struct mod_arch_specific {
#ifdef CONFIG_UNWINDER_ORC
unsigned int num_orcs;
int *orc_unwind_ip;
struct orc_entry *orc_unwind;
#endif
+ struct its_array its_pages;
};
#endif /* _ASM_X86_MODULE_H */
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index dd2b129b0418..6ca6516c7492 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -43,8 +43,6 @@ static __always_inline void __monitorx(const void *eax, u32 ecx, u32 edx)
static __always_inline void __mwait(u32 eax, u32 ecx)
{
- mds_idle_clear_cpu_buffers();
-
/*
* Use the instruction mnemonic with implicit operands, as the LLVM
* assembler fails to assemble the mnemonic with explicit operands:
@@ -80,7 +78,7 @@ static __always_inline void __mwait(u32 eax, u32 ecx)
*/
static __always_inline void __mwaitx(u32 eax, u32 ebx, u32 ecx)
{
- /* No MDS buffer clear as this is AMD/HYGON only */
+ /* No need for TSA buffer clearing on AMD */
/* "mwaitx %eax, %ebx, %ecx" */
asm volatile(".byte 0x0f, 0x01, 0xfb"
@@ -98,7 +96,6 @@ static __always_inline void __mwaitx(u32 eax, u32 ebx, u32 ecx)
*/
static __always_inline void __sti_mwait(u32 eax, u32 ecx)
{
- mds_idle_clear_cpu_buffers();
asm volatile("sti; mwait" :: "a" (eax), "c" (ecx));
}
@@ -115,21 +112,29 @@ static __always_inline void __sti_mwait(u32 eax, u32 ecx)
*/
static __always_inline void mwait_idle_with_hints(u32 eax, u32 ecx)
{
+ if (need_resched())
+ return;
+
+ x86_idle_clear_cpu_buffers();
+
if (static_cpu_has_bug(X86_BUG_MONITOR) || !current_set_polling_and_test()) {
const void *addr = &current_thread_info()->flags;
alternative_input("", "clflush (%[addr])", X86_BUG_CLFLUSH_MONITOR, [addr] "a" (addr));
__monitor(addr, 0, 0);
- if (!need_resched()) {
- if (ecx & 1) {
- __mwait(eax, ecx);
- } else {
- __sti_mwait(eax, ecx);
- raw_local_irq_disable();
- }
+ if (need_resched())
+ goto out;
+
+ if (ecx & 1) {
+ __mwait(eax, ecx);
+ } else {
+ __sti_mwait(eax, ecx);
+ raw_local_irq_disable();
}
}
+
+out:
current_clr_polling();
}
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 20d754b98f3f..10f261678749 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -302,25 +302,31 @@
.endm
/*
- * Macro to execute VERW instruction that mitigate transient data sampling
- * attacks such as MDS. On affected systems a microcode update overloaded VERW
- * instruction to also clear the CPU buffers. VERW clobbers CFLAGS.ZF.
- *
+ * Macro to execute VERW insns that mitigate transient data sampling
+ * attacks such as MDS or TSA. On affected systems a microcode update
+ * overloaded VERW insns to also clear the CPU buffers. VERW clobbers
+ * CFLAGS.ZF.
* Note: Only the memory operand variant of VERW clears the CPU buffers.
*/
-.macro CLEAR_CPU_BUFFERS
+.macro __CLEAR_CPU_BUFFERS feature
#ifdef CONFIG_X86_64
- ALTERNATIVE "", "verw mds_verw_sel(%rip)", X86_FEATURE_CLEAR_CPU_BUF
+ ALTERNATIVE "", "verw x86_verw_sel(%rip)", \feature
#else
/*
* In 32bit mode, the memory operand must be a %cs reference. The data
* segments may not be usable (vm86 mode), and the stack segment may not
* be flat (ESPFIX32).
*/
- ALTERNATIVE "", "verw %cs:mds_verw_sel", X86_FEATURE_CLEAR_CPU_BUF
+ ALTERNATIVE "", "verw %cs:x86_verw_sel", \feature
#endif
.endm
+#define CLEAR_CPU_BUFFERS \
+ __CLEAR_CPU_BUFFERS X86_FEATURE_CLEAR_CPU_BUF
+
+#define VM_CLEAR_CPU_BUFFERS \
+ __CLEAR_CPU_BUFFERS X86_FEATURE_CLEAR_CPU_BUF_VM
+
#ifdef CONFIG_X86_64
.macro CLEAR_BRANCH_HISTORY
ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP
@@ -567,24 +573,24 @@ DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
DECLARE_STATIC_KEY_FALSE(switch_vcpu_ibpb);
-DECLARE_STATIC_KEY_FALSE(mds_idle_clear);
+DECLARE_STATIC_KEY_FALSE(cpu_buf_idle_clear);
DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush);
DECLARE_STATIC_KEY_FALSE(cpu_buf_vm_clear);
-extern u16 mds_verw_sel;
+extern u16 x86_verw_sel;
#include <asm/segment.h>
/**
- * mds_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability
+ * x86_clear_cpu_buffers - Buffer clearing support for different x86 CPU vulns
*
* This uses the otherwise unused and obsolete VERW instruction in
* combination with microcode which triggers a CPU buffer flush when the
* instruction is executed.
*/
-static __always_inline void mds_clear_cpu_buffers(void)
+static __always_inline void x86_clear_cpu_buffers(void)
{
static const u16 ds = __KERNEL_DS;
@@ -601,14 +607,15 @@ static __always_inline void mds_clear_cpu_buffers(void)
}
/**
- * mds_idle_clear_cpu_buffers - Mitigation for MDS vulnerability
+ * x86_idle_clear_cpu_buffers - Buffer clearing support in idle for the MDS
+ * and TSA vulnerabilities.
*
* Clear CPU buffers if the corresponding static key is enabled
*/
-static __always_inline void mds_idle_clear_cpu_buffers(void)
+static __always_inline void x86_idle_clear_cpu_buffers(void)
{
- if (static_branch_likely(&mds_idle_clear))
- mds_clear_cpu_buffers();
+ if (static_branch_likely(&cpu_buf_idle_clear))
+ x86_clear_cpu_buffers();
}
#endif /* __ASSEMBLER__ */
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 774430c3abff..97954c936c54 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -1561,7 +1561,7 @@ static inline pte_t pte_swp_mkexclusive(pte_t pte)
return pte_set_flags(pte, _PAGE_SWP_EXCLUSIVE);
}
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
{
return pte_flags(pte) & _PAGE_SWP_EXCLUSIVE;
}
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index 58e028d42e41..a631f7d7c0c0 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -223,6 +223,18 @@ struct snp_tsc_info_resp {
u8 rsvd2[100];
} __packed;
+/*
+ * Obtain the mean TSC frequency by decreasing the nominal TSC frequency with
+ * TSC_FACTOR as documented in the SNP Firmware ABI specification:
+ *
+ * GUEST_TSC_FREQ * (1 - (TSC_FACTOR * 0.00001))
+ *
+ * which is equivalent to:
+ *
+ * GUEST_TSC_FREQ -= (GUEST_TSC_FREQ * TSC_FACTOR) / 100000;
+ */
+#define SNP_SCALE_TSC_FREQ(freq, factor) ((freq) - (freq) * (factor) / 100000)
+
struct snp_guest_req {
void *req_buf;
size_t req_sz;
@@ -282,8 +294,11 @@ struct snp_secrets_page {
u8 svsm_guest_vmpl;
u8 rsvd3[3];
+ /* The percentage decrease from nominal to mean TSC frequency. */
+ u32 tsc_factor;
+
/* Remainder of page */
- u8 rsvd4[3744];
+ u8 rsvd4[3740];
} __packed;
struct snp_msg_desc {
diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h
index 2f3820342598..8bc074c8d7c6 100644
--- a/arch/x86/include/asm/shared/tdx.h
+++ b/arch/x86/include/asm/shared/tdx.h
@@ -72,6 +72,7 @@
#define TDVMCALL_MAP_GPA 0x10001
#define TDVMCALL_GET_QUOTE 0x10002
#define TDVMCALL_REPORT_FATAL_ERROR 0x10003
+#define TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT 0x10004ULL
/*
* TDG.VP.VMCALL Status Codes (returned in R10)
@@ -80,6 +81,7 @@
#define TDVMCALL_STATUS_RETRY 0x0000000000000001ULL
#define TDVMCALL_STATUS_INVALID_OPERAND 0x8000000000000000ULL
#define TDVMCALL_STATUS_ALIGN_ERROR 0x8000000000000002ULL
+#define TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED 0x8000000000000003ULL
/*
* Bitmasks of exposed registers (with VMM).
diff --git a/arch/x86/include/asm/sighandling.h b/arch/x86/include/asm/sighandling.h
index e770c4fc47f4..8727c7e21dd1 100644
--- a/arch/x86/include/asm/sighandling.h
+++ b/arch/x86/include/asm/sighandling.h
@@ -24,4 +24,26 @@ int ia32_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs);
int x64_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs);
int x32_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs);
+/*
+ * To prevent immediate repeat of single step trap on return from SIGTRAP
+ * handler if the trap flag (TF) is set without an external debugger attached,
+ * clear the software event flag in the augmented SS, ensuring no single-step
+ * trap is pending upon ERETU completion.
+ *
+ * Note, this function should be called in sigreturn() before the original
+ * state is restored to make sure the TF is read from the entry frame.
+ */
+static __always_inline void prevent_single_step_upon_eretu(struct pt_regs *regs)
+{
+ /*
+ * If the trap flag (TF) is set, i.e., the sigreturn() SYSCALL instruction
+ * is being single-stepped, do not clear the software event flag in the
+ * augmented SS, thus a debugger won't skip over the following instruction.
+ */
+#ifdef CONFIG_X86_FRED
+ if (!(regs->flags & X86_EFLAGS_TF))
+ regs->fred_ss.swevent = 0;
+#endif
+}
+
#endif /* _ASM_X86_SIGHANDLING_H */
diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h
index 8b19294600c4..7ddef3a69866 100644
--- a/arch/x86/include/asm/tdx.h
+++ b/arch/x86/include/asm/tdx.h
@@ -106,7 +106,7 @@ void tdx_init(void);
typedef u64 (*sc_func_t)(u64 fn, struct tdx_module_args *args);
-static inline u64 sc_retry(sc_func_t func, u64 fn,
+static __always_inline u64 sc_retry(sc_func_t func, u64 fn,
struct tdx_module_args *args)
{
int retry = RDRAND_RETRY_LOOPS;
diff --git a/arch/x86/include/uapi/asm/debugreg.h b/arch/x86/include/uapi/asm/debugreg.h
index 0007ba077c0c..41da492dfb01 100644
--- a/arch/x86/include/uapi/asm/debugreg.h
+++ b/arch/x86/include/uapi/asm/debugreg.h
@@ -15,7 +15,26 @@
which debugging register was responsible for the trap. The other bits
are either reserved or not of interest to us. */
-/* Define reserved bits in DR6 which are always set to 1 */
+/*
+ * Define bits in DR6 which are set to 1 by default.
+ *
+ * This is also the DR6 architectural value following Power-up, Reset or INIT.
+ *
+ * Note, with the introduction of Bus Lock Detection (BLD) and Restricted
+ * Transactional Memory (RTM), the DR6 register has been modified:
+ *
+ * 1) BLD flag (bit 11) is no longer reserved to 1 if the CPU supports
+ * Bus Lock Detection. The assertion of a bus lock could clear it.
+ *
+ * 2) RTM flag (bit 16) is no longer reserved to 1 if the CPU supports
+ * restricted transactional memory. #DB occurred inside an RTM region
+ * could clear it.
+ *
+ * Apparently, DR6.BLD and DR6.RTM are active low bits.
+ *
+ * As a result, DR6_RESERVED is an incorrect name now, but it is kept for
+ * compatibility.
+ */
#define DR6_RESERVED (0xFFFF0FF0)
#define DR_TRAP0 (0x1) /* db0 */
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 6f3499507c5e..0f15d683817d 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -965,7 +965,13 @@ struct kvm_tdx_cmd {
struct kvm_tdx_capabilities {
__u64 supported_attrs;
__u64 supported_xfam;
- __u64 reserved[254];
+
+ __u64 kernel_tdvmcallinfo_1_r11;
+ __u64 user_tdvmcallinfo_1_r11;
+ __u64 kernel_tdvmcallinfo_1_r12;
+ __u64 user_tdvmcallinfo_1_r12;
+
+ __u64 reserved[250];
/* Configurable CPUID bits for userspace */
struct kvm_cpuid2 cpuid;
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index ecfe7b497cad..ea1d984166cd 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -116,6 +116,24 @@ static struct module *its_mod;
#endif
static void *its_page;
static unsigned int its_offset;
+struct its_array its_pages;
+
+static void *__its_alloc(struct its_array *pages)
+{
+ void *page __free(execmem) = execmem_alloc(EXECMEM_MODULE_TEXT, PAGE_SIZE);
+ if (!page)
+ return NULL;
+
+ void *tmp = krealloc(pages->pages, (pages->num+1) * sizeof(void *),
+ GFP_KERNEL);
+ if (!tmp)
+ return NULL;
+
+ pages->pages = tmp;
+ pages->pages[pages->num++] = page;
+
+ return no_free_ptr(page);
+}
/* Initialize a thunk with the "jmp *reg; int3" instructions. */
static void *its_init_thunk(void *thunk, int reg)
@@ -151,6 +169,21 @@ static void *its_init_thunk(void *thunk, int reg)
return thunk + offset;
}
+static void its_pages_protect(struct its_array *pages)
+{
+ for (int i = 0; i < pages->num; i++) {
+ void *page = pages->pages[i];
+ execmem_restore_rox(page, PAGE_SIZE);
+ }
+}
+
+static void its_fini_core(void)
+{
+ if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX))
+ its_pages_protect(&its_pages);
+ kfree(its_pages.pages);
+}
+
#ifdef CONFIG_MODULES
void its_init_mod(struct module *mod)
{
@@ -173,10 +206,8 @@ void its_fini_mod(struct module *mod)
its_page = NULL;
mutex_unlock(&text_mutex);
- for (int i = 0; i < mod->its_num_pages; i++) {
- void *page = mod->its_page_array[i];
- execmem_restore_rox(page, PAGE_SIZE);
- }
+ if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
+ its_pages_protect(&mod->arch.its_pages);
}
void its_free_mod(struct module *mod)
@@ -184,37 +215,33 @@ void its_free_mod(struct module *mod)
if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS))
return;
- for (int i = 0; i < mod->its_num_pages; i++) {
- void *page = mod->its_page_array[i];
+ for (int i = 0; i < mod->arch.its_pages.num; i++) {
+ void *page = mod->arch.its_pages.pages[i];
execmem_free(page);
}
- kfree(mod->its_page_array);
+ kfree(mod->arch.its_pages.pages);
}
#endif /* CONFIG_MODULES */
static void *its_alloc(void)
{
- void *page __free(execmem) = execmem_alloc(EXECMEM_MODULE_TEXT, PAGE_SIZE);
-
- if (!page)
- return NULL;
+ struct its_array *pages = &its_pages;
+ void *page;
#ifdef CONFIG_MODULES
- if (its_mod) {
- void *tmp = krealloc(its_mod->its_page_array,
- (its_mod->its_num_pages+1) * sizeof(void *),
- GFP_KERNEL);
- if (!tmp)
- return NULL;
+ if (its_mod)
+ pages = &its_mod->arch.its_pages;
+#endif
- its_mod->its_page_array = tmp;
- its_mod->its_page_array[its_mod->its_num_pages++] = page;
+ page = __its_alloc(pages);
+ if (!page)
+ return NULL;
- execmem_make_temp_rw(page, PAGE_SIZE);
- }
-#endif /* CONFIG_MODULES */
+ execmem_make_temp_rw(page, PAGE_SIZE);
+ if (pages == &its_pages)
+ set_memory_x((unsigned long)page, 1);
- return no_free_ptr(page);
+ return page;
}
static void *its_allocate_thunk(int reg)
@@ -268,7 +295,9 @@ u8 *its_static_thunk(int reg)
return thunk;
}
-#endif
+#else
+static inline void its_fini_core(void) {}
+#endif /* CONFIG_MITIGATION_ITS */
/*
* Nomenclature for variable names to simplify and clarify this code and ease
@@ -2338,6 +2367,8 @@ void __init alternative_instructions(void)
apply_retpolines(__retpoline_sites, __retpoline_sites_end);
apply_returns(__return_sites, __return_sites_end);
+ its_fini_core();
+
/*
* Adjust all CALL instructions to point to func()-10, including
* those in .altinstr_replacement.
@@ -3107,6 +3138,6 @@ void __ref smp_text_poke_batch_add(void *addr, const void *opcode, size_t len, c
*/
void __ref smp_text_poke_single(void *addr, const void *opcode, size_t len, const void *emulate)
{
- __smp_text_poke_batch_add(addr, opcode, len, emulate);
+ smp_text_poke_batch_add(addr, opcode, len, emulate);
smp_text_poke_batch_finish();
}
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 93da466dfe2c..b750ac008b78 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -9,7 +9,7 @@
#include <linux/sched/clock.h>
#include <linux/random.h>
#include <linux/topology.h>
-#include <asm/amd/fch.h>
+#include <linux/platform_data/x86/amd-fch.h>
#include <asm/processor.h>
#include <asm/apic.h>
#include <asm/cacheinfo.h>
@@ -31,7 +31,7 @@
#include "cpu.h"
-u16 invlpgb_count_max __ro_after_init;
+u16 invlpgb_count_max __ro_after_init = 1;
static inline int rdmsrq_amd_safe(unsigned msr, u64 *p)
{
@@ -377,6 +377,47 @@ static void bsp_determine_snp(struct cpuinfo_x86 *c)
#endif
}
+#define ZEN_MODEL_STEP_UCODE(fam, model, step, ucode) \
+ X86_MATCH_VFM_STEPS(VFM_MAKE(X86_VENDOR_AMD, fam, model), \
+ step, step, ucode)
+
+static const struct x86_cpu_id amd_tsa_microcode[] = {
+ ZEN_MODEL_STEP_UCODE(0x19, 0x01, 0x1, 0x0a0011d7),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x01, 0x2, 0x0a00123b),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x08, 0x2, 0x0a00820d),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x11, 0x1, 0x0a10114c),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x11, 0x2, 0x0a10124c),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x18, 0x1, 0x0a108109),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x21, 0x0, 0x0a20102e),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x21, 0x2, 0x0a201211),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x44, 0x1, 0x0a404108),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x50, 0x0, 0x0a500012),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x61, 0x2, 0x0a60120a),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x74, 0x1, 0x0a704108),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x75, 0x2, 0x0a705208),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x78, 0x0, 0x0a708008),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x7c, 0x0, 0x0a70c008),
+ ZEN_MODEL_STEP_UCODE(0x19, 0xa0, 0x2, 0x0aa00216),
+ {},
+};
+
+static void tsa_init(struct cpuinfo_x86 *c)
+{
+ if (cpu_has(c, X86_FEATURE_HYPERVISOR))
+ return;
+
+ if (cpu_has(c, X86_FEATURE_ZEN3) ||
+ cpu_has(c, X86_FEATURE_ZEN4)) {
+ if (x86_match_min_microcode_rev(amd_tsa_microcode))
+ setup_force_cpu_cap(X86_FEATURE_VERW_CLEAR);
+ else
+ pr_debug("%s: current revision: 0x%x\n", __func__, c->microcode);
+ } else {
+ setup_force_cpu_cap(X86_FEATURE_TSA_SQ_NO);
+ setup_force_cpu_cap(X86_FEATURE_TSA_L1_NO);
+ }
+}
+
static void bsp_init_amd(struct cpuinfo_x86 *c)
{
if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) {
@@ -489,6 +530,9 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
}
bsp_determine_snp(c);
+
+ tsa_init(c);
+
return;
warn:
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 7f94e6a5497d..f4d3abb12317 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -94,6 +94,8 @@ static void __init bhi_apply_mitigation(void);
static void __init its_select_mitigation(void);
static void __init its_update_mitigation(void);
static void __init its_apply_mitigation(void);
+static void __init tsa_select_mitigation(void);
+static void __init tsa_apply_mitigation(void);
/* The base value of the SPEC_CTRL MSR without task-specific bits set */
u64 x86_spec_ctrl_base;
@@ -169,9 +171,9 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
DEFINE_STATIC_KEY_FALSE(switch_vcpu_ibpb);
EXPORT_SYMBOL_GPL(switch_vcpu_ibpb);
-/* Control MDS CPU buffer clear before idling (halt, mwait) */
-DEFINE_STATIC_KEY_FALSE(mds_idle_clear);
-EXPORT_SYMBOL_GPL(mds_idle_clear);
+/* Control CPU buffer clear before idling (halt, mwait) */
+DEFINE_STATIC_KEY_FALSE(cpu_buf_idle_clear);
+EXPORT_SYMBOL_GPL(cpu_buf_idle_clear);
/*
* Controls whether l1d flush based mitigations are enabled,
@@ -225,6 +227,7 @@ void __init cpu_select_mitigations(void)
gds_select_mitigation();
its_select_mitigation();
bhi_select_mitigation();
+ tsa_select_mitigation();
/*
* After mitigations are selected, some may need to update their
@@ -272,6 +275,7 @@ void __init cpu_select_mitigations(void)
gds_apply_mitigation();
its_apply_mitigation();
bhi_apply_mitigation();
+ tsa_apply_mitigation();
}
/*
@@ -637,7 +641,7 @@ static void __init mmio_apply_mitigation(void)
* is required irrespective of SMT state.
*/
if (!(x86_arch_cap_msr & ARCH_CAP_FBSDP_NO))
- static_branch_enable(&mds_idle_clear);
+ static_branch_enable(&cpu_buf_idle_clear);
if (mmio_nosmt || cpu_mitigations_auto_nosmt())
cpu_smt_disable(false);
@@ -1488,6 +1492,94 @@ static void __init its_apply_mitigation(void)
}
#undef pr_fmt
+#define pr_fmt(fmt) "Transient Scheduler Attacks: " fmt
+
+enum tsa_mitigations {
+ TSA_MITIGATION_NONE,
+ TSA_MITIGATION_AUTO,
+ TSA_MITIGATION_UCODE_NEEDED,
+ TSA_MITIGATION_USER_KERNEL,
+ TSA_MITIGATION_VM,
+ TSA_MITIGATION_FULL,
+};
+
+static const char * const tsa_strings[] = {
+ [TSA_MITIGATION_NONE] = "Vulnerable",
+ [TSA_MITIGATION_UCODE_NEEDED] = "Vulnerable: No microcode",
+ [TSA_MITIGATION_USER_KERNEL] = "Mitigation: Clear CPU buffers: user/kernel boundary",
+ [TSA_MITIGATION_VM] = "Mitigation: Clear CPU buffers: VM",
+ [TSA_MITIGATION_FULL] = "Mitigation: Clear CPU buffers",
+};
+
+static enum tsa_mitigations tsa_mitigation __ro_after_init =
+ IS_ENABLED(CONFIG_MITIGATION_TSA) ? TSA_MITIGATION_AUTO : TSA_MITIGATION_NONE;
+
+static int __init tsa_parse_cmdline(char *str)
+{
+ if (!str)
+ return -EINVAL;
+
+ if (!strcmp(str, "off"))
+ tsa_mitigation = TSA_MITIGATION_NONE;
+ else if (!strcmp(str, "on"))
+ tsa_mitigation = TSA_MITIGATION_FULL;
+ else if (!strcmp(str, "user"))
+ tsa_mitigation = TSA_MITIGATION_USER_KERNEL;
+ else if (!strcmp(str, "vm"))
+ tsa_mitigation = TSA_MITIGATION_VM;
+ else
+ pr_err("Ignoring unknown tsa=%s option.\n", str);
+
+ return 0;
+}
+early_param("tsa", tsa_parse_cmdline);
+
+static void __init tsa_select_mitigation(void)
+{
+ if (cpu_mitigations_off() || !boot_cpu_has_bug(X86_BUG_TSA)) {
+ tsa_mitigation = TSA_MITIGATION_NONE;
+ return;
+ }
+
+ if (tsa_mitigation == TSA_MITIGATION_NONE)
+ return;
+
+ if (!boot_cpu_has(X86_FEATURE_VERW_CLEAR)) {
+ tsa_mitigation = TSA_MITIGATION_UCODE_NEEDED;
+ goto out;
+ }
+
+ if (tsa_mitigation == TSA_MITIGATION_AUTO)
+ tsa_mitigation = TSA_MITIGATION_FULL;
+
+ /*
+ * No need to set verw_clear_cpu_buf_mitigation_selected - it
+ * doesn't fit all cases here and it is not needed because this
+ * is the only VERW-based mitigation on AMD.
+ */
+out:
+ pr_info("%s\n", tsa_strings[tsa_mitigation]);
+}
+
+static void __init tsa_apply_mitigation(void)
+{
+ switch (tsa_mitigation) {
+ case TSA_MITIGATION_USER_KERNEL:
+ setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
+ break;
+ case TSA_MITIGATION_VM:
+ setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF_VM);
+ break;
+ case TSA_MITIGATION_FULL:
+ setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
+ setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF_VM);
+ break;
+ default:
+ break;
+ }
+}
+
+#undef pr_fmt
#define pr_fmt(fmt) "Spectre V2 : " fmt
static enum spectre_v2_user_mitigation spectre_v2_user_stibp __ro_after_init =
@@ -2249,10 +2341,10 @@ static void update_mds_branch_idle(void)
return;
if (sched_smt_active()) {
- static_branch_enable(&mds_idle_clear);
+ static_branch_enable(&cpu_buf_idle_clear);
} else if (mmio_mitigation == MMIO_MITIGATION_OFF ||
(x86_arch_cap_msr & ARCH_CAP_FBSDP_NO)) {
- static_branch_disable(&mds_idle_clear);
+ static_branch_disable(&cpu_buf_idle_clear);
}
}
@@ -2316,6 +2408,25 @@ void cpu_bugs_smt_update(void)
break;
}
+ switch (tsa_mitigation) {
+ case TSA_MITIGATION_USER_KERNEL:
+ case TSA_MITIGATION_VM:
+ case TSA_MITIGATION_AUTO:
+ case TSA_MITIGATION_FULL:
+ /*
+ * TSA-SQ can potentially lead to info leakage between
+ * SMT threads.
+ */
+ if (sched_smt_active())
+ static_branch_enable(&cpu_buf_idle_clear);
+ else
+ static_branch_disable(&cpu_buf_idle_clear);
+ break;
+ case TSA_MITIGATION_NONE:
+ case TSA_MITIGATION_UCODE_NEEDED:
+ break;
+ }
+
mutex_unlock(&spec_ctrl_mutex);
}
@@ -3265,6 +3376,11 @@ static ssize_t gds_show_state(char *buf)
return sysfs_emit(buf, "%s\n", gds_strings[gds_mitigation]);
}
+static ssize_t tsa_show_state(char *buf)
+{
+ return sysfs_emit(buf, "%s\n", tsa_strings[tsa_mitigation]);
+}
+
static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
char *buf, unsigned int bug)
{
@@ -3328,6 +3444,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
case X86_BUG_ITS:
return its_show_state(buf);
+ case X86_BUG_TSA:
+ return tsa_show_state(buf);
+
default:
break;
}
@@ -3414,6 +3533,11 @@ ssize_t cpu_show_indirect_target_selection(struct device *dev, struct device_att
{
return cpu_show_common(dev, attr, buf, X86_BUG_ITS);
}
+
+ssize_t cpu_show_tsa(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ return cpu_show_common(dev, attr, buf, X86_BUG_TSA);
+}
#endif
void __warn_thunk(void)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 8feb8fd2957a..fb50c1dd53ef 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1233,6 +1233,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
#define ITS BIT(8)
/* CPU is affected by Indirect Target Selection, but guest-host isolation is not affected */
#define ITS_NATIVE_ONLY BIT(9)
+/* CPU is affected by Transient Scheduler Attacks */
+#define TSA BIT(10)
static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
VULNBL_INTEL_STEPS(INTEL_IVYBRIDGE, X86_STEP_MAX, SRBDS),
@@ -1280,7 +1282,7 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
VULNBL_AMD(0x16, RETBLEED),
VULNBL_AMD(0x17, RETBLEED | SMT_RSB | SRSO),
VULNBL_HYGON(0x18, RETBLEED | SMT_RSB | SRSO),
- VULNBL_AMD(0x19, SRSO),
+ VULNBL_AMD(0x19, SRSO | TSA),
VULNBL_AMD(0x1a, SRSO),
{}
};
@@ -1530,6 +1532,16 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
setup_force_cpu_bug(X86_BUG_ITS_NATIVE_ONLY);
}
+ if (c->x86_vendor == X86_VENDOR_AMD) {
+ if (!cpu_has(c, X86_FEATURE_TSA_SQ_NO) ||
+ !cpu_has(c, X86_FEATURE_TSA_L1_NO)) {
+ if (cpu_matches(cpu_vuln_blacklist, TSA) ||
+ /* Enable bug on Zen guests to allow for live migration. */
+ (cpu_has(c, X86_FEATURE_HYPERVISOR) && cpu_has(c, X86_FEATURE_ZEN)))
+ setup_force_cpu_bug(X86_BUG_TSA);
+ }
+ }
+
if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))
return;
@@ -2243,20 +2255,16 @@ EXPORT_PER_CPU_SYMBOL(__stack_chk_guard);
#endif
#endif
-/*
- * Clear all 6 debug registers:
- */
-static void clear_all_debug_regs(void)
+static void initialize_debug_regs(void)
{
- int i;
-
- for (i = 0; i < 8; i++) {
- /* Ignore db4, db5 */
- if ((i == 4) || (i == 5))
- continue;
-
- set_debugreg(0, i);
- }
+ /* Control register first -- to make sure everything is disabled. */
+ set_debugreg(DR7_FIXED_1, 7);
+ set_debugreg(DR6_RESERVED, 6);
+ /* dr5 and dr4 don't exist */
+ set_debugreg(0, 3);
+ set_debugreg(0, 2);
+ set_debugreg(0, 1);
+ set_debugreg(0, 0);
}
#ifdef CONFIG_KGDB
@@ -2417,7 +2425,7 @@ void cpu_init(void)
load_mm_ldt(&init_mm);
- clear_all_debug_regs();
+ initialize_debug_regs();
dbg_restore_debug_regs();
doublefault_init_cpu_tss();
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index 9d852c3b2cb5..5c4eb28c3ac9 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -350,7 +350,6 @@ static void smca_configure(unsigned int bank, unsigned int cpu)
struct thresh_restart {
struct threshold_block *b;
- int reset;
int set_lvt_off;
int lvt_off;
u16 old_limit;
@@ -432,13 +431,13 @@ static void threshold_restart_bank(void *_tr)
rdmsr(tr->b->address, lo, hi);
- if (tr->b->threshold_limit < (hi & THRESHOLD_MAX))
- tr->reset = 1; /* limit cannot be lower than err count */
-
- if (tr->reset) { /* reset err count and overflow bit */
- hi =
- (hi & ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI)) |
- (THRESHOLD_MAX - tr->b->threshold_limit);
+ /*
+ * Reset error count and overflow bit.
+ * This is done during init or after handling an interrupt.
+ */
+ if (hi & MASK_OVERFLOW_HI || tr->set_lvt_off) {
+ hi &= ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI);
+ hi |= THRESHOLD_MAX - tr->b->threshold_limit;
} else if (tr->old_limit) { /* change limit w/o reset */
int new_count = (hi & THRESHOLD_MAX) +
(tr->old_limit - tr->b->threshold_limit);
@@ -1113,13 +1112,20 @@ static const char *get_name(unsigned int cpu, unsigned int bank, struct threshol
}
bank_type = smca_get_bank_type(cpu, bank);
- if (bank_type >= N_SMCA_BANK_TYPES)
- return NULL;
if (b && (bank_type == SMCA_UMC || bank_type == SMCA_UMC_V2)) {
if (b->block < ARRAY_SIZE(smca_umc_block_names))
return smca_umc_block_names[b->block];
- return NULL;
+ }
+
+ if (b && b->block) {
+ snprintf(buf_mcatype, MAX_MCATYPE_NAME_LEN, "th_block_%u", b->block);
+ return buf_mcatype;
+ }
+
+ if (bank_type >= N_SMCA_BANK_TYPES) {
+ snprintf(buf_mcatype, MAX_MCATYPE_NAME_LEN, "th_bank_%u", bank);
+ return buf_mcatype;
}
if (per_cpu(smca_bank_counts, cpu)[bank_type] == 1)
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index e9b3c5d4a52e..4da4eab56c81 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1740,6 +1740,11 @@ static void mc_poll_banks_default(void)
void (*mc_poll_banks)(void) = mc_poll_banks_default;
+static bool should_enable_timer(unsigned long iv)
+{
+ return !mca_cfg.ignore_ce && iv;
+}
+
static void mce_timer_fn(struct timer_list *t)
{
struct timer_list *cpu_t = this_cpu_ptr(&mce_timer);
@@ -1763,7 +1768,7 @@ static void mce_timer_fn(struct timer_list *t)
if (mce_get_storm_mode()) {
__start_timer(t, HZ);
- } else {
+ } else if (should_enable_timer(iv)) {
__this_cpu_write(mce_next_interval, iv);
__start_timer(t, iv);
}
@@ -2156,11 +2161,10 @@ static void mce_start_timer(struct timer_list *t)
{
unsigned long iv = check_interval * HZ;
- if (mca_cfg.ignore_ce || !iv)
- return;
-
- this_cpu_write(mce_next_interval, iv);
- __start_timer(t, iv);
+ if (should_enable_timer(iv)) {
+ this_cpu_write(mce_next_interval, iv);
+ __start_timer(t, iv);
+ }
}
static void __mcheck_cpu_setup_timer(void)
@@ -2801,15 +2805,9 @@ static int mce_cpu_dead(unsigned int cpu)
static int mce_cpu_online(unsigned int cpu)
{
struct timer_list *t = this_cpu_ptr(&mce_timer);
- int ret;
mce_device_create(cpu);
-
- ret = mce_threshold_create_device(cpu);
- if (ret) {
- mce_device_remove(cpu);
- return ret;
- }
+ mce_threshold_create_device(cpu);
mce_reenable_cpu();
mce_start_timer(t);
return 0;
diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c
index efcf21e9552e..9b149b9c4109 100644
--- a/arch/x86/kernel/cpu/mce/intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -478,6 +478,7 @@ void mce_intel_feature_init(struct cpuinfo_x86 *c)
void mce_intel_feature_clear(struct cpuinfo_x86 *c)
{
intel_clear_lmce();
+ cmci_clear();
}
bool intel_filter_mce(struct mce *m)
diff --git a/arch/x86/kernel/cpu/microcode/amd_shas.c b/arch/x86/kernel/cpu/microcode/amd_shas.c
index 2a1655b1fdd8..1fd349cfc802 100644
--- a/arch/x86/kernel/cpu/microcode/amd_shas.c
+++ b/arch/x86/kernel/cpu/microcode/amd_shas.c
@@ -231,6 +231,13 @@ static const struct patch_digest phashes[] = {
0x0d,0x5b,0x65,0x34,0x69,0xb2,0x62,0x21,
}
},
+ { 0xa0011d7, {
+ 0x35,0x07,0xcd,0x40,0x94,0xbc,0x81,0x6b,
+ 0xfc,0x61,0x56,0x1a,0xe2,0xdb,0x96,0x12,
+ 0x1c,0x1c,0x31,0xb1,0x02,0x6f,0xe5,0xd2,
+ 0xfe,0x1b,0x04,0x03,0x2c,0x8f,0x4c,0x36,
+ }
+ },
{ 0xa001223, {
0xfb,0x32,0x5f,0xc6,0x83,0x4f,0x8c,0xb8,
0xa4,0x05,0xf9,0x71,0x53,0x01,0x16,0xc4,
@@ -294,6 +301,13 @@ static const struct patch_digest phashes[] = {
0xc0,0xcd,0x33,0xf2,0x8d,0xf9,0xef,0x59,
}
},
+ { 0xa00123b, {
+ 0xef,0xa1,0x1e,0x71,0xf1,0xc3,0x2c,0xe2,
+ 0xc3,0xef,0x69,0x41,0x7a,0x54,0xca,0xc3,
+ 0x8f,0x62,0x84,0xee,0xc2,0x39,0xd9,0x28,
+ 0x95,0xa7,0x12,0x49,0x1e,0x30,0x71,0x72,
+ }
+ },
{ 0xa00820c, {
0xa8,0x0c,0x81,0xc0,0xa6,0x00,0xe7,0xf3,
0x5f,0x65,0xd3,0xb9,0x6f,0xea,0x93,0x63,
@@ -301,6 +315,13 @@ static const struct patch_digest phashes[] = {
0xe1,0x3b,0x8d,0xb2,0xf8,0x22,0x03,0xe2,
}
},
+ { 0xa00820d, {
+ 0xf9,0x2a,0xc0,0xf4,0x9e,0xa4,0x87,0xa4,
+ 0x7d,0x87,0x00,0xfd,0xab,0xda,0x19,0xca,
+ 0x26,0x51,0x32,0xc1,0x57,0x91,0xdf,0xc1,
+ 0x05,0xeb,0x01,0x7c,0x5a,0x95,0x21,0xb7,
+ }
+ },
{ 0xa10113e, {
0x05,0x3c,0x66,0xd7,0xa9,0x5a,0x33,0x10,
0x1b,0xf8,0x9c,0x8f,0xed,0xfc,0xa7,0xa0,
@@ -322,6 +343,13 @@ static const struct patch_digest phashes[] = {
0xf1,0x5e,0xb0,0xde,0xb4,0x98,0xae,0xc4,
}
},
+ { 0xa10114c, {
+ 0x9e,0xb6,0xa2,0xd9,0x87,0x38,0xc5,0x64,
+ 0xd8,0x88,0xfa,0x78,0x98,0xf9,0x6f,0x74,
+ 0x39,0x90,0x1b,0xa5,0xcf,0x5e,0xb4,0x2a,
+ 0x02,0xff,0xd4,0x8c,0x71,0x8b,0xe2,0xc0,
+ }
+ },
{ 0xa10123e, {
0x03,0xb9,0x2c,0x76,0x48,0x93,0xc9,0x18,
0xfb,0x56,0xfd,0xf7,0xe2,0x1d,0xca,0x4d,
@@ -343,6 +371,13 @@ static const struct patch_digest phashes[] = {
0x1b,0x7d,0x64,0x9d,0x4b,0x53,0x13,0x75,
}
},
+ { 0xa10124c, {
+ 0x29,0xea,0xf1,0x2c,0xb2,0xe4,0xef,0x90,
+ 0xa4,0xcd,0x1d,0x86,0x97,0x17,0x61,0x46,
+ 0xfc,0x22,0xcb,0x57,0x75,0x19,0xc8,0xcc,
+ 0x0c,0xf5,0xbc,0xac,0x81,0x9d,0x9a,0xd2,
+ }
+ },
{ 0xa108108, {
0xed,0xc2,0xec,0xa1,0x15,0xc6,0x65,0xe9,
0xd0,0xef,0x39,0xaa,0x7f,0x55,0x06,0xc6,
@@ -350,6 +385,13 @@ static const struct patch_digest phashes[] = {
0x28,0x1e,0x9c,0x59,0x69,0x99,0x4d,0x16,
}
},
+ { 0xa108109, {
+ 0x85,0xb4,0xbd,0x7c,0x49,0xa7,0xbd,0xfa,
+ 0x49,0x36,0x80,0x81,0xc5,0xb7,0x39,0x1b,
+ 0x9a,0xaa,0x50,0xde,0x9b,0xe9,0x32,0x35,
+ 0x42,0x7e,0x51,0x4f,0x52,0x2c,0x28,0x59,
+ }
+ },
{ 0xa20102d, {
0xf9,0x6e,0xf2,0x32,0xd3,0x0f,0x5f,0x11,
0x59,0xa1,0xfe,0xcc,0xcd,0x9b,0x42,0x89,
@@ -357,6 +399,13 @@ static const struct patch_digest phashes[] = {
0x8c,0xe9,0x19,0x3e,0xcc,0x3f,0x7b,0xb4,
}
},
+ { 0xa20102e, {
+ 0xbe,0x1f,0x32,0x04,0x0d,0x3c,0x9c,0xdd,
+ 0xe1,0xa4,0xbf,0x76,0x3a,0xec,0xc2,0xf6,
+ 0x11,0x00,0xa7,0xaf,0x0f,0xe5,0x02,0xc5,
+ 0x54,0x3a,0x1f,0x8c,0x16,0xb5,0xff,0xbe,
+ }
+ },
{ 0xa201210, {
0xe8,0x6d,0x51,0x6a,0x8e,0x72,0xf3,0xfe,
0x6e,0x16,0xbc,0x62,0x59,0x40,0x17,0xe9,
@@ -364,6 +413,13 @@ static const struct patch_digest phashes[] = {
0xf7,0x55,0xf0,0x13,0xbb,0x22,0xf6,0x41,
}
},
+ { 0xa201211, {
+ 0x69,0xa1,0x17,0xec,0xd0,0xf6,0x6c,0x95,
+ 0xe2,0x1e,0xc5,0x59,0x1a,0x52,0x0a,0x27,
+ 0xc4,0xed,0xd5,0x59,0x1f,0xbf,0x00,0xff,
+ 0x08,0x88,0xb5,0xe1,0x12,0xb6,0xcc,0x27,
+ }
+ },
{ 0xa404107, {
0xbb,0x04,0x4e,0x47,0xdd,0x5e,0x26,0x45,
0x1a,0xc9,0x56,0x24,0xa4,0x4c,0x82,0xb0,
@@ -371,6 +427,13 @@ static const struct patch_digest phashes[] = {
0x13,0xbc,0xc5,0x25,0xe4,0xc5,0xc3,0x99,
}
},
+ { 0xa404108, {
+ 0x69,0x67,0x43,0x06,0xf8,0x0c,0x62,0xdc,
+ 0xa4,0x21,0x30,0x4f,0x0f,0x21,0x2c,0xcb,
+ 0xcc,0x37,0xf1,0x1c,0xc3,0xf8,0x2f,0x19,
+ 0xdf,0x53,0x53,0x46,0xb1,0x15,0xea,0x00,
+ }
+ },
{ 0xa500011, {
0x23,0x3d,0x70,0x7d,0x03,0xc3,0xc4,0xf4,
0x2b,0x82,0xc6,0x05,0xda,0x80,0x0a,0xf1,
@@ -378,6 +441,13 @@ static const struct patch_digest phashes[] = {
0x11,0x5e,0x96,0x7e,0x71,0xe9,0xfc,0x74,
}
},
+ { 0xa500012, {
+ 0xeb,0x74,0x0d,0x47,0xa1,0x8e,0x09,0xe4,
+ 0x93,0x4c,0xad,0x03,0x32,0x4c,0x38,0x16,
+ 0x10,0x39,0xdd,0x06,0xaa,0xce,0xd6,0x0f,
+ 0x62,0x83,0x9d,0x8e,0x64,0x55,0xbe,0x63,
+ }
+ },
{ 0xa601209, {
0x66,0x48,0xd4,0x09,0x05,0xcb,0x29,0x32,
0x66,0xb7,0x9a,0x76,0xcd,0x11,0xf3,0x30,
@@ -385,6 +455,13 @@ static const struct patch_digest phashes[] = {
0xe8,0x73,0xe2,0xd6,0xdb,0xd2,0x77,0x1d,
}
},
+ { 0xa60120a, {
+ 0x0c,0x8b,0x3d,0xfd,0x52,0x52,0x85,0x7d,
+ 0x20,0x3a,0xe1,0x7e,0xa4,0x21,0x3b,0x7b,
+ 0x17,0x86,0xae,0xac,0x13,0xb8,0x63,0x9d,
+ 0x06,0x01,0xd0,0xa0,0x51,0x9a,0x91,0x2c,
+ }
+ },
{ 0xa704107, {
0xf3,0xc6,0x58,0x26,0xee,0xac,0x3f,0xd6,
0xce,0xa1,0x72,0x47,0x3b,0xba,0x2b,0x93,
@@ -392,6 +469,13 @@ static const struct patch_digest phashes[] = {
0x64,0x39,0x71,0x8c,0xce,0xe7,0x41,0x39,
}
},
+ { 0xa704108, {
+ 0xd7,0x55,0x15,0x2b,0xfe,0xc4,0xbc,0x93,
+ 0xec,0x91,0xa0,0xae,0x45,0xb7,0xc3,0x98,
+ 0x4e,0xff,0x61,0x77,0x88,0xc2,0x70,0x49,
+ 0xe0,0x3a,0x1d,0x84,0x38,0x52,0xbf,0x5a,
+ }
+ },
{ 0xa705206, {
0x8d,0xc0,0x76,0xbd,0x58,0x9f,0x8f,0xa4,
0x12,0x9d,0x21,0xfb,0x48,0x21,0xbc,0xe7,
@@ -399,6 +483,13 @@ static const struct patch_digest phashes[] = {
0x03,0x35,0xe9,0xbe,0xfb,0x06,0xdf,0xfc,
}
},
+ { 0xa705208, {
+ 0x30,0x1d,0x55,0x24,0xbc,0x6b,0x5a,0x19,
+ 0x0c,0x7d,0x1d,0x74,0xaa,0xd1,0xeb,0xd2,
+ 0x16,0x62,0xf7,0x5b,0xe1,0x1f,0x18,0x11,
+ 0x5c,0xf0,0x94,0x90,0x26,0xec,0x69,0xff,
+ }
+ },
{ 0xa708007, {
0x6b,0x76,0xcc,0x78,0xc5,0x8a,0xa3,0xe3,
0x32,0x2d,0x79,0xe4,0xc3,0x80,0xdb,0xb2,
@@ -406,6 +497,13 @@ static const struct patch_digest phashes[] = {
0xdf,0x92,0x73,0x84,0x87,0x3c,0x73,0x93,
}
},
+ { 0xa708008, {
+ 0x08,0x6e,0xf0,0x22,0x4b,0x8e,0xc4,0x46,
+ 0x58,0x34,0xe6,0x47,0xa2,0x28,0xfd,0xab,
+ 0x22,0x3d,0xdd,0xd8,0x52,0x9e,0x1d,0x16,
+ 0xfa,0x01,0x68,0x14,0x79,0x3e,0xe8,0x6b,
+ }
+ },
{ 0xa70c005, {
0x88,0x5d,0xfb,0x79,0x64,0xd8,0x46,0x3b,
0x4a,0x83,0x8e,0x77,0x7e,0xcf,0xb3,0x0f,
@@ -413,6 +511,13 @@ static const struct patch_digest phashes[] = {
0xee,0x49,0xac,0xe1,0x8b,0x13,0xc5,0x13,
}
},
+ { 0xa70c008, {
+ 0x0f,0xdb,0x37,0xa1,0x10,0xaf,0xd4,0x21,
+ 0x94,0x0d,0xa4,0xa2,0xe9,0x86,0x6c,0x0e,
+ 0x85,0x7c,0x36,0x30,0xa3,0x3a,0x78,0x66,
+ 0x18,0x10,0x60,0x0d,0x78,0x3d,0x44,0xd0,
+ }
+ },
{ 0xaa00116, {
0xe8,0x4c,0x2c,0x88,0xa1,0xac,0x24,0x63,
0x65,0xe5,0xaa,0x2d,0x16,0xa9,0xc3,0xf5,
@@ -441,4 +546,11 @@ static const struct patch_digest phashes[] = {
0x68,0x2f,0x46,0xee,0xfe,0xc6,0x6d,0xef,
}
},
+ { 0xaa00216, {
+ 0x79,0xfb,0x5b,0x9f,0xb6,0xe6,0xa8,0xf5,
+ 0x4e,0x7c,0x4f,0x8e,0x1d,0xad,0xd0,0x08,
+ 0xc2,0x43,0x7c,0x8b,0xe6,0xdb,0xd0,0xd2,
+ 0xe8,0x39,0x26,0xc1,0xe5,0x5a,0x48,0xf1,
+ }
+ },
};
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 7109cbfcad4f..187d527ef73b 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -498,6 +498,7 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
struct rdt_hw_mon_domain *hw_dom;
struct rdt_domain_hdr *hdr;
struct rdt_mon_domain *d;
+ struct cacheinfo *ci;
int err;
lockdep_assert_held(&domain_list_lock);
@@ -525,12 +526,13 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
d = &hw_dom->d_resctrl;
d->hdr.id = id;
d->hdr.type = RESCTRL_MON_DOMAIN;
- d->ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
- if (!d->ci) {
+ ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
+ if (!ci) {
pr_warn_once("Can't find L3 cache for CPU:%d resource %s\n", cpu, r->name);
mon_domain_free(hw_dom);
return;
}
+ d->ci_id = ci->id;
cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
arch_mon_domain_online(r, d);
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index dbf6d71bdf18..b4a1f6732a3a 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -50,6 +50,8 @@ static const struct cpuid_bit cpuid_bits[] = {
{ X86_FEATURE_MBA, CPUID_EBX, 6, 0x80000008, 0 },
{ X86_FEATURE_SMBA, CPUID_EBX, 2, 0x80000020, 0 },
{ X86_FEATURE_BMEC, CPUID_EBX, 3, 0x80000020, 0 },
+ { X86_FEATURE_TSA_SQ_NO, CPUID_ECX, 1, 0x80000021, 0 },
+ { X86_FEATURE_TSA_L1_NO, CPUID_ECX, 2, 0x80000021, 0 },
{ X86_FEATURE_AMD_WORKLOAD_CLASS, CPUID_EAX, 22, 0x80000021, 0 },
{ X86_FEATURE_PERFMON_V2, CPUID_EAX, 0, 0x80000022, 0 },
{ X86_FEATURE_AMD_LBR_V2, CPUID_EAX, 1, 0x80000022, 0 },
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 102641fd2172..8b1a9733d13e 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -385,7 +385,7 @@ static void kgdb_disable_hw_debug(struct pt_regs *regs)
struct perf_event *bp;
/* Disable hardware debugging while we are in kgdb: */
- set_debugreg(0UL, 7);
+ set_debugreg(DR7_FIXED_1, 7);
for (i = 0; i < HBP_NUM; i++) {
if (!breakinfo[i].enabled)
continue;
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 704883c21f3a..a838be04f874 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -907,16 +907,24 @@ static __init bool prefer_mwait_c1_over_halt(void)
*/
static __cpuidle void mwait_idle(void)
{
+ if (need_resched())
+ return;
+
+ x86_idle_clear_cpu_buffers();
+
if (!current_set_polling_and_test()) {
const void *addr = &current_thread_info()->flags;
alternative_input("", "clflush (%[addr])", X86_BUG_CLFLUSH_MONITOR, [addr] "a" (addr));
__monitor(addr, 0, 0);
- if (!need_resched()) {
- __sti_mwait(0, 0);
- raw_local_irq_disable();
- }
+ if (need_resched())
+ goto out;
+
+ __sti_mwait(0, 0);
+ raw_local_irq_disable();
}
+
+out:
__current_clr_polling();
}
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index a10e180cbf23..3ef15c2f152f 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -93,7 +93,7 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode,
/* Only print out debug registers if they are in their non-default state. */
if ((d0 == 0) && (d1 == 0) && (d2 == 0) && (d3 == 0) &&
- (d6 == DR6_RESERVED) && (d7 == 0x400))
+ (d6 == DR6_RESERVED) && (d7 == DR7_FIXED_1))
return;
printk("%sDR0: %08lx DR1: %08lx DR2: %08lx DR3: %08lx\n",
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 8d6cf25127aa..b972bf72fb8b 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -133,7 +133,7 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode,
/* Only print out debug registers if they are in their non-default state. */
if (!((d0 == 0) && (d1 == 0) && (d2 == 0) && (d3 == 0) &&
- (d6 == DR6_RESERVED) && (d7 == 0x400))) {
+ (d6 == DR6_RESERVED) && (d7 == DR7_FIXED_1))) {
printk("%sDR0: %016lx DR1: %016lx DR2: %016lx\n",
log_lvl, d0, d1, d2);
printk("%sDR3: %016lx DR6: %016lx DR7: %016lx\n",
diff --git a/arch/x86/kernel/signal_32.c b/arch/x86/kernel/signal_32.c
index 98123ff10506..42bbc42bd350 100644
--- a/arch/x86/kernel/signal_32.c
+++ b/arch/x86/kernel/signal_32.c
@@ -152,6 +152,8 @@ SYSCALL32_DEFINE0(sigreturn)
struct sigframe_ia32 __user *frame = (struct sigframe_ia32 __user *)(regs->sp-8);
sigset_t set;
+ prevent_single_step_upon_eretu(regs);
+
if (!access_ok(frame, sizeof(*frame)))
goto badframe;
if (__get_user(set.sig[0], &frame->sc.oldmask)
@@ -175,6 +177,8 @@ SYSCALL32_DEFINE0(rt_sigreturn)
struct rt_sigframe_ia32 __user *frame;
sigset_t set;
+ prevent_single_step_upon_eretu(regs);
+
frame = (struct rt_sigframe_ia32 __user *)(regs->sp - 4);
if (!access_ok(frame, sizeof(*frame)))
diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c
index ee9453891901..d483b585c6c6 100644
--- a/arch/x86/kernel/signal_64.c
+++ b/arch/x86/kernel/signal_64.c
@@ -250,6 +250,8 @@ SYSCALL_DEFINE0(rt_sigreturn)
sigset_t set;
unsigned long uc_flags;
+ prevent_single_step_upon_eretu(regs);
+
frame = (struct rt_sigframe __user *)(regs->sp - sizeof(long));
if (!access_ok(frame, sizeof(*frame)))
goto badframe;
@@ -366,6 +368,8 @@ COMPAT_SYSCALL_DEFINE0(x32_rt_sigreturn)
sigset_t set;
unsigned long uc_flags;
+ prevent_single_step_upon_eretu(regs);
+
frame = (struct rt_sigframe_x32 __user *)(regs->sp - 8);
if (!access_ok(frame, sizeof(*frame)))
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 18266cc3d98c..b014e6d229f9 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -299,3 +299,27 @@ struct smp_ops smp_ops = {
.send_call_func_single_ipi = native_send_call_func_single_ipi,
};
EXPORT_SYMBOL_GPL(smp_ops);
+
+int arch_cpu_rescan_dead_smt_siblings(void)
+{
+ enum cpuhp_smt_control old = cpu_smt_control;
+ int ret;
+
+ /*
+ * If SMT has been disabled and SMT siblings are in HLT, bring them back
+ * online and offline them again so that they end up in MWAIT proper.
+ *
+ * Called with hotplug enabled.
+ */
+ if (old != CPU_SMT_DISABLED && old != CPU_SMT_FORCE_DISABLED)
+ return 0;
+
+ ret = cpuhp_smt_enable();
+ if (ret)
+ return ret;
+
+ ret = cpuhp_smt_disable(old);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(arch_cpu_rescan_dead_smt_siblings);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index fc78c2325fd2..58ede3fa6a75 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1244,6 +1244,10 @@ void play_dead_common(void)
local_irq_disable();
}
+/*
+ * We need to flush the caches before going to sleep, lest we have
+ * dirty data in our caches when we come back up.
+ */
void __noreturn mwait_play_dead(unsigned int eax_hint)
{
struct mwait_cpu_dead *md = this_cpu_ptr(&mwait_cpu_dead);
@@ -1290,50 +1294,6 @@ void __noreturn mwait_play_dead(unsigned int eax_hint)
}
/*
- * We need to flush the caches before going to sleep, lest we have
- * dirty data in our caches when we come back up.
- */
-static inline void mwait_play_dead_cpuid_hint(void)
-{
- unsigned int eax, ebx, ecx, edx;
- unsigned int highest_cstate = 0;
- unsigned int highest_subcstate = 0;
- int i;
-
- if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
- boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
- return;
- if (!this_cpu_has(X86_FEATURE_MWAIT))
- return;
- if (!this_cpu_has(X86_FEATURE_CLFLUSH))
- return;
-
- eax = CPUID_LEAF_MWAIT;
- ecx = 0;
- native_cpuid(&eax, &ebx, &ecx, &edx);
-
- /*
- * eax will be 0 if EDX enumeration is not valid.
- * Initialized below to cstate, sub_cstate value when EDX is valid.
- */
- if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED)) {
- eax = 0;
- } else {
- edx >>= MWAIT_SUBSTATE_SIZE;
- for (i = 0; i < 7 && edx; i++, edx >>= MWAIT_SUBSTATE_SIZE) {
- if (edx & MWAIT_SUBSTATE_MASK) {
- highest_cstate = i;
- highest_subcstate = edx & MWAIT_SUBSTATE_MASK;
- }
- }
- eax = (highest_cstate << MWAIT_SUBSTATE_SIZE) |
- (highest_subcstate - 1);
- }
-
- mwait_play_dead(eax);
-}
-
-/*
* Kick all "offline" CPUs out of mwait on kexec(). See comment in
* mwait_play_dead().
*/
@@ -1383,9 +1343,9 @@ void native_play_dead(void)
play_dead_common();
tboot_shutdown(TB_SHUTDOWN_WFS);
- mwait_play_dead_cpuid_hint();
- if (cpuidle_play_dead())
- hlt_play_dead();
+ /* Below returns only on error. */
+ cpuidle_play_dead();
+ hlt_play_dead();
}
#else /* ... !CONFIG_HOTPLUG_CPU */
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index c5c897a86418..36354b470590 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -1022,24 +1022,32 @@ static bool is_sysenter_singlestep(struct pt_regs *regs)
#endif
}
-static __always_inline unsigned long debug_read_clear_dr6(void)
+static __always_inline unsigned long debug_read_reset_dr6(void)
{
unsigned long dr6;
+ get_debugreg(dr6, 6);
+ dr6 ^= DR6_RESERVED; /* Flip to positive polarity */
+
/*
* The Intel SDM says:
*
- * Certain debug exceptions may clear bits 0-3. The remaining
- * contents of the DR6 register are never cleared by the
- * processor. To avoid confusion in identifying debug
- * exceptions, debug handlers should clear the register before
- * returning to the interrupted task.
+ * Certain debug exceptions may clear bits 0-3 of DR6.
+ *
+ * BLD induced #DB clears DR6.BLD and any other debug
+ * exception doesn't modify DR6.BLD.
*
- * Keep it simple: clear DR6 immediately.
+ * RTM induced #DB clears DR6.RTM and any other debug
+ * exception sets DR6.RTM.
+ *
+ * To avoid confusion in identifying debug exceptions,
+ * debug handlers should set DR6.BLD and DR6.RTM, and
+ * clear other DR6 bits before returning.
+ *
+ * Keep it simple: write DR6 with its architectural reset
+ * value 0xFFFF0FF0, defined as DR6_RESERVED, immediately.
*/
- get_debugreg(dr6, 6);
set_debugreg(DR6_RESERVED, 6);
- dr6 ^= DR6_RESERVED; /* Flip to positive polarity */
return dr6;
}
@@ -1239,13 +1247,13 @@ out:
/* IST stack entry */
DEFINE_IDTENTRY_DEBUG(exc_debug)
{
- exc_debug_kernel(regs, debug_read_clear_dr6());
+ exc_debug_kernel(regs, debug_read_reset_dr6());
}
/* User entry, runs on regular task stack */
DEFINE_IDTENTRY_DEBUG_USER(exc_debug)
{
- exc_debug_user(regs, debug_read_clear_dr6());
+ exc_debug_user(regs, debug_read_reset_dr6());
}
#ifdef CONFIG_X86_FRED
@@ -1264,7 +1272,7 @@ DEFINE_FREDENTRY_DEBUG(exc_debug)
{
/*
* FRED #DB stores DR6 on the stack in the format which
- * debug_read_clear_dr6() returns for the IDT entry points.
+ * debug_read_reset_dr6() returns for the IDT entry points.
*/
unsigned long dr6 = fred_event_data(regs);
@@ -1279,7 +1287,7 @@ DEFINE_FREDENTRY_DEBUG(exc_debug)
/* 32 bit does not have separate entry points. */
DEFINE_IDTENTRY_RAW(exc_debug)
{
- unsigned long dr6 = debug_read_clear_dr6();
+ unsigned long dr6 = debug_read_reset_dr6();
if (user_mode(regs))
exc_debug_user(regs, dr6);
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index b2d006756e02..f84bc0569c9c 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -1165,6 +1165,8 @@ void kvm_set_cpu_caps(void)
*/
SYNTHESIZED_F(LFENCE_RDTSC),
/* SmmPgCfgLock */
+ /* 4: Resv */
+ SYNTHESIZED_F(VERW_CLEAR),
F(NULL_SEL_CLR_BASE),
/* UpperAddressIgnore */
F(AUTOIBRS),
@@ -1179,6 +1181,11 @@ void kvm_set_cpu_caps(void)
F(SRSO_USER_KERNEL_NO),
);
+ kvm_cpu_cap_init(CPUID_8000_0021_ECX,
+ SYNTHESIZED_F(TSA_SQ_NO),
+ SYNTHESIZED_F(TSA_L1_NO),
+ );
+
kvm_cpu_cap_init(CPUID_8000_0022_EAX,
F(PERFMON_V2),
);
@@ -1748,8 +1755,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
entry->eax = entry->ebx = entry->ecx = entry->edx = 0;
break;
case 0x80000021:
- entry->ebx = entry->ecx = entry->edx = 0;
+ entry->ebx = entry->edx = 0;
cpuid_entry_override(entry, CPUID_8000_0021_EAX);
+ cpuid_entry_override(entry, CPUID_8000_0021_ECX);
break;
/* AMD Extended Performance Monitoring and Debug */
case 0x80000022: {
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 24f0318c50d7..ee27064dd72f 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1979,6 +1979,9 @@ int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu)
if (entries[i] == KVM_HV_TLB_FLUSHALL_ENTRY)
goto out_flush_all;
+ if (is_noncanonical_invlpg_address(entries[i], vcpu))
+ continue;
+
/*
* Lower 12 bits of 'address' encode the number of additional
* pages to flush.
@@ -2001,11 +2004,11 @@ out_flush_all:
static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
{
struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+ unsigned long *vcpu_mask = hv_vcpu->vcpu_mask;
u64 *sparse_banks = hv_vcpu->sparse_banks;
struct kvm *kvm = vcpu->kvm;
struct hv_tlb_flush_ex flush_ex;
struct hv_tlb_flush flush;
- DECLARE_BITMAP(vcpu_mask, KVM_MAX_VCPUS);
struct kvm_vcpu_hv_tlb_flush_fifo *tlb_flush_fifo;
/*
* Normally, there can be no more than 'KVM_HV_TLB_FLUSH_FIFO_SIZE'
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index cbc84c6abc2e..4e06e2e89a8f 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4896,12 +4896,16 @@ long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu,
{
u64 error_code = PFERR_GUEST_FINAL_MASK;
u8 level = PG_LEVEL_4K;
+ u64 direct_bits;
u64 end;
int r;
if (!vcpu->kvm->arch.pre_fault_allowed)
return -EOPNOTSUPP;
+ if (kvm_is_gfn_alias(vcpu->kvm, gpa_to_gfn(range->gpa)))
+ return -EINVAL;
+
/*
* reload is efficient when called repeatedly, so we can do it on
* every iteration.
@@ -4910,15 +4914,18 @@ long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu,
if (r)
return r;
+ direct_bits = 0;
if (kvm_arch_has_private_mem(vcpu->kvm) &&
kvm_mem_is_private(vcpu->kvm, gpa_to_gfn(range->gpa)))
error_code |= PFERR_PRIVATE_ACCESS;
+ else
+ direct_bits = gfn_to_gpa(kvm_gfn_direct_bits(vcpu->kvm));
/*
* Shadow paging uses GVA for kvm page fault, so restrict to
* two-dimensional paging.
*/
- r = kvm_tdp_map_page(vcpu, range->gpa, error_code, &level);
+ r = kvm_tdp_map_page(vcpu, range->gpa | direct_bits, error_code, &level);
if (r < 0)
return r;
diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h
index fde0ae986003..c53b92379e6e 100644
--- a/arch/x86/kvm/reverse_cpuid.h
+++ b/arch/x86/kvm/reverse_cpuid.h
@@ -52,6 +52,10 @@
/* CPUID level 0x80000022 (EAX) */
#define KVM_X86_FEATURE_PERFMON_V2 KVM_X86_FEATURE(CPUID_8000_0022_EAX, 0)
+/* CPUID level 0x80000021 (ECX) */
+#define KVM_X86_FEATURE_TSA_SQ_NO KVM_X86_FEATURE(CPUID_8000_0021_ECX, 1)
+#define KVM_X86_FEATURE_TSA_L1_NO KVM_X86_FEATURE(CPUID_8000_0021_ECX, 2)
+
struct cpuid_reg {
u32 function;
u32 index;
@@ -82,6 +86,7 @@ static const struct cpuid_reg reverse_cpuid[] = {
[CPUID_8000_0022_EAX] = {0x80000022, 0, CPUID_EAX},
[CPUID_7_2_EDX] = { 7, 2, CPUID_EDX},
[CPUID_24_0_EBX] = { 0x24, 0, CPUID_EBX},
+ [CPUID_8000_0021_ECX] = {0x80000021, 0, CPUID_ECX},
};
/*
@@ -121,6 +126,8 @@ static __always_inline u32 __feature_translate(int x86_feature)
KVM_X86_TRANSLATE_FEATURE(PERFMON_V2);
KVM_X86_TRANSLATE_FEATURE(RRSBA_CTRL);
KVM_X86_TRANSLATE_FEATURE(BHI_CTRL);
+ KVM_X86_TRANSLATE_FEATURE(TSA_SQ_NO);
+ KVM_X86_TRANSLATE_FEATURE(TSA_L1_NO);
default:
return x86_feature;
}
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 5a69b657dae9..b201f77fcd49 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -1971,6 +1971,10 @@ static int sev_check_source_vcpus(struct kvm *dst, struct kvm *src)
struct kvm_vcpu *src_vcpu;
unsigned long i;
+ if (src->created_vcpus != atomic_read(&src->online_vcpus) ||
+ dst->created_vcpus != atomic_read(&dst->online_vcpus))
+ return -EBUSY;
+
if (!sev_es_guest(src))
return 0;
@@ -2871,6 +2875,33 @@ void __init sev_set_cpu_caps(void)
}
}
+static bool is_sev_snp_initialized(void)
+{
+ struct sev_user_data_snp_status *status;
+ struct sev_data_snp_addr buf;
+ bool initialized = false;
+ int ret, error = 0;
+
+ status = snp_alloc_firmware_page(GFP_KERNEL | __GFP_ZERO);
+ if (!status)
+ return false;
+
+ buf.address = __psp_pa(status);
+ ret = sev_do_cmd(SEV_CMD_SNP_PLATFORM_STATUS, &buf, &error);
+ if (ret) {
+ pr_err("SEV: SNP_PLATFORM_STATUS failed ret=%d, fw_error=%d (%#x)\n",
+ ret, error, error);
+ goto out;
+ }
+
+ initialized = !!status->state;
+
+out:
+ snp_free_firmware_page(status);
+
+ return initialized;
+}
+
void __init sev_hardware_setup(void)
{
unsigned int eax, ebx, ecx, edx, sev_asid_count, sev_es_asid_count;
@@ -2975,6 +3006,14 @@ void __init sev_hardware_setup(void)
sev_snp_supported = sev_snp_enabled && cc_platform_has(CC_ATTR_HOST_SEV_SNP);
out:
+ if (sev_enabled) {
+ init_args.probe = true;
+ if (sev_platform_init(&init_args))
+ sev_supported = sev_es_supported = sev_snp_supported = false;
+ else if (sev_snp_supported)
+ sev_snp_supported = is_sev_snp_initialized();
+ }
+
if (boot_cpu_has(X86_FEATURE_SEV))
pr_info("SEV %s (ASIDs %u - %u)\n",
sev_supported ? min_sev_asid <= max_sev_asid ? "enabled" :
@@ -3001,15 +3040,6 @@ out:
sev_supported_vmsa_features = 0;
if (sev_es_debug_swap_enabled)
sev_supported_vmsa_features |= SVM_SEV_FEAT_DEBUG_SWAP;
-
- if (!sev_enabled)
- return;
-
- /*
- * Do both SNP and SEV initialization at KVM module load.
- */
- init_args.probe = true;
- sev_platform_init(&init_args);
}
void sev_hardware_unsetup(void)
@@ -4419,8 +4449,12 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
* the VMSA will be NULL if this vCPU is the destination for intrahost
* migration, and will be copied later.
*/
- if (svm->sev_es.vmsa && !svm->sev_es.snp_has_guest_vmsa)
- svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa);
+ if (!svm->sev_es.snp_has_guest_vmsa) {
+ if (svm->sev_es.vmsa)
+ svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa);
+ else
+ svm->vmcb->control.vmsa_pa = INVALID_PAGE;
+ }
if (cpu_feature_enabled(X86_FEATURE_ALLOWED_SEV_FEATURES))
svm->vmcb->control.allowed_sev_features = sev->vmsa_features |
diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S
index 0c61153b275f..235c4af6b692 100644
--- a/arch/x86/kvm/svm/vmenter.S
+++ b/arch/x86/kvm/svm/vmenter.S
@@ -169,6 +169,9 @@ SYM_FUNC_START(__svm_vcpu_run)
#endif
mov VCPU_RDI(%_ASM_DI), %_ASM_DI
+ /* Clobbers EFLAGS.ZF */
+ VM_CLEAR_CPU_BUFFERS
+
/* Enter guest mode */
3: vmrun %_ASM_AX
4:
@@ -335,6 +338,9 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run)
mov SVM_current_vmcb(%rdi), %rax
mov KVM_VMCB_pa(%rax), %rax
+ /* Clobbers EFLAGS.ZF */
+ VM_CLEAR_CPU_BUFFERS
+
/* Enter guest mode */
1: vmrun %rax
2:
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index b952bc673271..f31ccdeb905b 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -173,6 +173,9 @@ static void td_init_cpuid_entry2(struct kvm_cpuid_entry2 *entry, unsigned char i
tdx_clear_unsupported_cpuid(entry);
}
+#define TDVMCALLINFO_GET_QUOTE BIT(0)
+#define TDVMCALLINFO_SETUP_EVENT_NOTIFY_INTERRUPT BIT(1)
+
static int init_kvm_tdx_caps(const struct tdx_sys_info_td_conf *td_conf,
struct kvm_tdx_capabilities *caps)
{
@@ -188,6 +191,10 @@ static int init_kvm_tdx_caps(const struct tdx_sys_info_td_conf *td_conf,
caps->cpuid.nent = td_conf->num_cpuid_config;
+ caps->user_tdvmcallinfo_1_r11 =
+ TDVMCALLINFO_GET_QUOTE |
+ TDVMCALLINFO_SETUP_EVENT_NOTIFY_INTERRUPT;
+
for (i = 0; i < td_conf->num_cpuid_config; i++)
td_init_cpuid_entry2(&caps->cpuid.entries[i], i);
@@ -1212,11 +1219,13 @@ static int tdx_map_gpa(struct kvm_vcpu *vcpu)
/*
* Converting TDVMCALL_MAP_GPA to KVM_HC_MAP_GPA_RANGE requires
* userspace to enable KVM_CAP_EXIT_HYPERCALL with KVM_HC_MAP_GPA_RANGE
- * bit set. If not, the error code is not defined in GHCI for TDX, use
- * TDVMCALL_STATUS_INVALID_OPERAND for this case.
+ * bit set. This is a base call so it should always be supported, but
+ * KVM has no way to ensure that userspace implements the GHCI correctly.
+ * So if KVM_HC_MAP_GPA_RANGE does not cause a VMEXIT, return an error
+ * to the guest.
*/
if (!user_exit_on_hypercall(vcpu->kvm, KVM_HC_MAP_GPA_RANGE)) {
- ret = TDVMCALL_STATUS_INVALID_OPERAND;
+ ret = TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED;
goto error;
}
@@ -1449,20 +1458,106 @@ error:
return 1;
}
+static int tdx_complete_get_td_vm_call_info(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_tdx *tdx = to_tdx(vcpu);
+
+ tdvmcall_set_return_code(vcpu, vcpu->run->tdx.get_tdvmcall_info.ret);
+
+ /*
+ * For now, there is no TDVMCALL beyond GHCI base API supported by KVM
+ * directly without the support from userspace, just set the value
+ * returned from userspace.
+ */
+ tdx->vp_enter_args.r11 = vcpu->run->tdx.get_tdvmcall_info.r11;
+ tdx->vp_enter_args.r12 = vcpu->run->tdx.get_tdvmcall_info.r12;
+ tdx->vp_enter_args.r13 = vcpu->run->tdx.get_tdvmcall_info.r13;
+ tdx->vp_enter_args.r14 = vcpu->run->tdx.get_tdvmcall_info.r14;
+
+ return 1;
+}
+
static int tdx_get_td_vm_call_info(struct kvm_vcpu *vcpu)
{
struct vcpu_tdx *tdx = to_tdx(vcpu);
- if (tdx->vp_enter_args.r12)
- tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND);
- else {
+ switch (tdx->vp_enter_args.r12) {
+ case 0:
tdx->vp_enter_args.r11 = 0;
+ tdx->vp_enter_args.r12 = 0;
tdx->vp_enter_args.r13 = 0;
tdx->vp_enter_args.r14 = 0;
+ tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_SUCCESS);
+ return 1;
+ case 1:
+ vcpu->run->tdx.get_tdvmcall_info.leaf = tdx->vp_enter_args.r12;
+ vcpu->run->exit_reason = KVM_EXIT_TDX;
+ vcpu->run->tdx.flags = 0;
+ vcpu->run->tdx.nr = TDVMCALL_GET_TD_VM_CALL_INFO;
+ vcpu->run->tdx.get_tdvmcall_info.ret = TDVMCALL_STATUS_SUCCESS;
+ vcpu->run->tdx.get_tdvmcall_info.r11 = 0;
+ vcpu->run->tdx.get_tdvmcall_info.r12 = 0;
+ vcpu->run->tdx.get_tdvmcall_info.r13 = 0;
+ vcpu->run->tdx.get_tdvmcall_info.r14 = 0;
+ vcpu->arch.complete_userspace_io = tdx_complete_get_td_vm_call_info;
+ return 0;
+ default:
+ tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND);
+ return 1;
}
+}
+
+static int tdx_complete_simple(struct kvm_vcpu *vcpu)
+{
+ tdvmcall_set_return_code(vcpu, vcpu->run->tdx.unknown.ret);
return 1;
}
+static int tdx_get_quote(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_tdx *tdx = to_tdx(vcpu);
+ u64 gpa = tdx->vp_enter_args.r12;
+ u64 size = tdx->vp_enter_args.r13;
+
+ /* The gpa of buffer must have shared bit set. */
+ if (vt_is_tdx_private_gpa(vcpu->kvm, gpa)) {
+ tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND);
+ return 1;
+ }
+
+ vcpu->run->exit_reason = KVM_EXIT_TDX;
+ vcpu->run->tdx.flags = 0;
+ vcpu->run->tdx.nr = TDVMCALL_GET_QUOTE;
+ vcpu->run->tdx.get_quote.ret = TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED;
+ vcpu->run->tdx.get_quote.gpa = gpa & ~gfn_to_gpa(kvm_gfn_direct_bits(tdx->vcpu.kvm));
+ vcpu->run->tdx.get_quote.size = size;
+
+ vcpu->arch.complete_userspace_io = tdx_complete_simple;
+
+ return 0;
+}
+
+static int tdx_setup_event_notify_interrupt(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_tdx *tdx = to_tdx(vcpu);
+ u64 vector = tdx->vp_enter_args.r12;
+
+ if (vector < 32 || vector > 255) {
+ tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND);
+ return 1;
+ }
+
+ vcpu->run->exit_reason = KVM_EXIT_TDX;
+ vcpu->run->tdx.flags = 0;
+ vcpu->run->tdx.nr = TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT;
+ vcpu->run->tdx.setup_event_notify.ret = TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED;
+ vcpu->run->tdx.setup_event_notify.vector = vector;
+
+ vcpu->arch.complete_userspace_io = tdx_complete_simple;
+
+ return 0;
+}
+
static int handle_tdvmcall(struct kvm_vcpu *vcpu)
{
switch (tdvmcall_leaf(vcpu)) {
@@ -1472,11 +1567,15 @@ static int handle_tdvmcall(struct kvm_vcpu *vcpu)
return tdx_report_fatal_error(vcpu);
case TDVMCALL_GET_TD_VM_CALL_INFO:
return tdx_get_td_vm_call_info(vcpu);
+ case TDVMCALL_GET_QUOTE:
+ return tdx_get_quote(vcpu);
+ case TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT:
+ return tdx_setup_event_notify_interrupt(vcpu);
default:
break;
}
- tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND);
+ tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED);
return 1;
}
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 4953846cb30d..191a9ed0da22 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -7291,7 +7291,7 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
vmx_l1d_flush(vcpu);
else if (static_branch_unlikely(&cpu_buf_vm_clear) &&
kvm_arch_has_assigned_device(vcpu->kvm))
- mds_clear_cpu_buffers();
+ x86_clear_cpu_buffers();
vmx_disable_fb_clear(vmx);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b58a74c1722d..357b9e3a6cef 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3258,9 +3258,11 @@ int kvm_guest_time_update(struct kvm_vcpu *v)
/* With all the info we got, fill in the values */
- if (kvm_caps.has_tsc_control)
+ if (kvm_caps.has_tsc_control) {
tgt_tsc_khz = kvm_scale_tsc(tgt_tsc_khz,
v->arch.l1_tsc_scaling_ratio);
+ tgt_tsc_khz = tgt_tsc_khz ? : 1;
+ }
if (unlikely(vcpu->hw_tsc_khz != tgt_tsc_khz)) {
kvm_get_time_scale(NSEC_PER_SEC, tgt_tsc_khz * 1000LL,
@@ -11035,7 +11037,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
if (unlikely(vcpu->arch.switch_db_regs &&
!(vcpu->arch.switch_db_regs & KVM_DEBUGREG_AUTO_SWITCH))) {
- set_debugreg(0, 7);
+ set_debugreg(DR7_FIXED_1, 7);
set_debugreg(vcpu->arch.eff_db[0], 0);
set_debugreg(vcpu->arch.eff_db[1], 1);
set_debugreg(vcpu->arch.eff_db[2], 2);
@@ -11044,7 +11046,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT))
kvm_x86_call(set_dr6)(vcpu, vcpu->arch.dr6);
} else if (unlikely(hw_breakpoint_active())) {
- set_debugreg(0, 7);
+ set_debugreg(DR7_FIXED_1, 7);
}
vcpu->arch.host_debugctl = get_debugctlmsr();
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index 9b029bb29a16..5fa2cca43653 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -1971,8 +1971,19 @@ int kvm_xen_setup_evtchn(struct kvm *kvm,
{
struct kvm_vcpu *vcpu;
- if (ue->u.xen_evtchn.port >= max_evtchn_port(kvm))
- return -EINVAL;
+ /*
+ * Don't check for the port being within range of max_evtchn_port().
+ * Userspace can configure what ever targets it likes; events just won't
+ * be delivered if/while the target is invalid, just like userspace can
+ * configure MSIs which target non-existent APICs.
+ *
+ * This allow on Live Migration and Live Update, the IRQ routing table
+ * can be restored *independently* of other things like creating vCPUs,
+ * without imposing an ordering dependency on userspace. In this
+ * particular case, the problematic ordering would be with setting the
+ * Xen 'long mode' flag, which changes max_evtchn_port() to allow 4096
+ * instead of 1024 event channels.
+ */
/* We only support 2 level event channels for now */
if (ue->u.xen_evtchn.priority != KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL)
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 607d6a2e66e2..8a34fff6ab2b 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -30,7 +30,6 @@
#include <linux/initrd.h>
#include <linux/cpumask.h>
#include <linux/gfp.h>
-#include <linux/execmem.h>
#include <asm/asm.h>
#include <asm/bios_ebda.h>
@@ -749,8 +748,6 @@ void mark_rodata_ro(void)
pr_info("Write protecting kernel text and read-only data: %luk\n",
size >> 10);
- execmem_cache_make_ro();
-
kernel_set_to_readonly = 1;
#ifdef CONFIG_CPA_DEBUG
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index ee66fae9ebcc..fdb6cab524f0 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -34,7 +34,6 @@
#include <linux/gfp.h>
#include <linux/kcore.h>
#include <linux/bootmem_info.h>
-#include <linux/execmem.h>
#include <asm/processor.h>
#include <asm/bios_ebda.h>
@@ -1392,8 +1391,6 @@ void mark_rodata_ro(void)
(end - start) >> 10);
set_memory_ro(start, (end - start) >> PAGE_SHIFT);
- execmem_cache_make_ro();
-
kernel_set_to_readonly = 1;
/*
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index 46edc11726b7..8834c76f91c9 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -1257,6 +1257,9 @@ static int collapse_pmd_page(pmd_t *pmd, unsigned long addr,
pgprot_t pgprot;
int i = 0;
+ if (!cpu_feature_enabled(X86_FEATURE_PSE))
+ return 0;
+
addr &= PMD_MASK;
pte = pte_offset_kernel(pmd, addr);
first = *pte;
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 190299834011..c0c40b67524e 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -98,6 +98,11 @@ void __init pti_check_boottime_disable(void)
return;
setup_force_cpu_cap(X86_FEATURE_PTI);
+
+ if (cpu_feature_enabled(X86_FEATURE_INVLPGB)) {
+ pr_debug("PTI enabled, disabling INVLPGB\n");
+ setup_clear_cpu_cap(X86_FEATURE_INVLPGB);
+ }
}
static int __init pti_parse_cmdline(char *arg)
diff --git a/arch/x86/power/hibernate.c b/arch/x86/power/hibernate.c
index a7c23f2a58c9..a2294c1649f6 100644
--- a/arch/x86/power/hibernate.c
+++ b/arch/x86/power/hibernate.c
@@ -192,7 +192,8 @@ out:
int arch_resume_nosmt(void)
{
- int ret = 0;
+ int ret;
+
/*
* We reached this while coming out of hibernation. This means
* that SMT siblings are sleeping in hlt, as mwait is not safe
@@ -206,18 +207,10 @@ int arch_resume_nosmt(void)
* Called with hotplug disabled.
*/
cpu_hotplug_enable();
- if (cpu_smt_control == CPU_SMT_DISABLED ||
- cpu_smt_control == CPU_SMT_FORCE_DISABLED) {
- enum cpuhp_smt_control old = cpu_smt_control;
-
- ret = cpuhp_smt_enable();
- if (ret)
- goto out;
- ret = cpuhp_smt_disable(old);
- if (ret)
- goto out;
- }
-out:
+
+ ret = arch_cpu_rescan_dead_smt_siblings();
+
cpu_hotplug_disable();
+
return ret;
}
diff --git a/arch/x86/um/ptrace.c b/arch/x86/um/ptrace.c
index 3275870330fe..fae8aabad10f 100644
--- a/arch/x86/um/ptrace.c
+++ b/arch/x86/um/ptrace.c
@@ -161,7 +161,7 @@ static int fpregs_legacy_set(struct task_struct *target,
from = kbuf;
}
- return um_fxsr_from_i387(fxsave, &buf);
+ return um_fxsr_from_i387(fxsave, from);
}
#endif
diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
index 2457d13c3f9e..c7a9a087ccaf 100644
--- a/arch/x86/virt/vmx/tdx/tdx.c
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -75,8 +75,9 @@ static inline void seamcall_err_ret(u64 fn, u64 err,
args->r9, args->r10, args->r11);
}
-static inline int sc_retry_prerr(sc_func_t func, sc_err_func_t err_func,
- u64 fn, struct tdx_module_args *args)
+static __always_inline int sc_retry_prerr(sc_func_t func,
+ sc_err_func_t err_func,
+ u64 fn, struct tdx_module_args *args)
{
u64 sret = sc_retry(func, fn, args);