summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Makefile12
-rw-r--r--arch/x86/crypto/aria-aesni-avx-asm_64.S2
-rw-r--r--arch/x86/events/intel/core.c17
-rw-r--r--arch/x86/events/intel/uncore_snbep.c11
-rw-r--r--arch/x86/hyperv/hv_init.c2
-rw-r--r--arch/x86/hyperv/hv_vtl.c2
-rw-r--r--arch/x86/include/asm/Kbuild1
-rw-r--r--arch/x86/include/asm/fpu/sched.h2
-rw-r--r--arch/x86/include/asm/orc_header.h19
-rw-r--r--arch/x86/include/asm/vmx.h2
-rw-r--r--arch/x86/kernel/Makefile1
-rw-r--r--arch/x86/kernel/apic/x2apic_phys.c5
-rw-r--r--arch/x86/kernel/cpu/topology.c5
-rw-r--r--arch/x86/kernel/dumpstack.c7
-rw-r--r--arch/x86/kernel/fpu/context.h2
-rw-r--r--arch/x86/kernel/fpu/core.c2
-rw-r--r--arch/x86/kernel/head_64.S18
-rw-r--r--arch/x86/kernel/unwind_orc.c3
-rw-r--r--arch/x86/kvm/cpuid.c16
-rw-r--r--arch/x86/kvm/lapic.c20
-rw-r--r--arch/x86/kvm/mmu/mmu.c5
-rw-r--r--arch/x86/kvm/svm/svm.c2
-rw-r--r--arch/x86/kvm/vmx/sgx.c11
-rw-r--r--arch/x86/kvm/x86.c9
-rw-r--r--arch/x86/lib/copy_user_64.S10
-rw-r--r--arch/x86/mm/init.c25
-rw-r--r--arch/x86/mm/kaslr.c8
-rw-r--r--arch/x86/net/bpf_jit_comp.c2
-rw-r--r--arch/x86/pci/xen.c8
-rw-r--r--arch/x86/purgatory/Makefile5
30 files changed, 180 insertions, 54 deletions
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index b39975977c03..fdc2e3abd615 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -305,6 +305,18 @@ ifeq ($(RETPOLINE_CFLAGS),)
endif
endif
+ifdef CONFIG_UNWINDER_ORC
+orc_hash_h := arch/$(SRCARCH)/include/generated/asm/orc_hash.h
+orc_hash_sh := $(srctree)/scripts/orc_hash.sh
+targets += $(orc_hash_h)
+quiet_cmd_orc_hash = GEN $@
+ cmd_orc_hash = mkdir -p $(dir $@); \
+ $(CONFIG_SHELL) $(orc_hash_sh) < $< > $@
+$(orc_hash_h): $(srctree)/arch/x86/include/asm/orc_types.h $(orc_hash_sh) FORCE
+ $(call if_changed,orc_hash)
+archprepare: $(orc_hash_h)
+endif
+
archclean:
$(Q)rm -rf $(objtree)/arch/i386
$(Q)rm -rf $(objtree)/arch/x86_64
diff --git a/arch/x86/crypto/aria-aesni-avx-asm_64.S b/arch/x86/crypto/aria-aesni-avx-asm_64.S
index 7c1abc513f34..9556dacd9841 100644
--- a/arch/x86/crypto/aria-aesni-avx-asm_64.S
+++ b/arch/x86/crypto/aria-aesni-avx-asm_64.S
@@ -773,8 +773,6 @@
.octa 0x3F893781E95FE1576CDA64D2BA0CB204
#ifdef CONFIG_AS_GFNI
-.section .rodata.cst8, "aM", @progbits, 8
-.align 8
/* AES affine: */
#define tf_aff_const BV8(1, 1, 0, 0, 0, 1, 1, 0)
.Ltf_aff_bitmatrix:
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 070cc4ef2672..27f3a7b34bd5 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -349,6 +349,16 @@ static struct event_constraint intel_spr_event_constraints[] = {
EVENT_CONSTRAINT_END
};
+static struct extra_reg intel_gnr_extra_regs[] __read_mostly = {
+ INTEL_UEVENT_EXTRA_REG(0x012a, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0),
+ INTEL_UEVENT_EXTRA_REG(0x012b, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1),
+ INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
+ INTEL_UEVENT_EXTRA_REG(0x02c6, MSR_PEBS_FRONTEND, 0x9, FE),
+ INTEL_UEVENT_EXTRA_REG(0x03c6, MSR_PEBS_FRONTEND, 0x7fff1f, FE),
+ INTEL_UEVENT_EXTRA_REG(0x40ad, MSR_PEBS_FRONTEND, 0x7, FE),
+ INTEL_UEVENT_EXTRA_REG(0x04c2, MSR_PEBS_FRONTEND, 0x8, FE),
+ EVENT_EXTRA_END
+};
EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3");
EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3");
@@ -4074,7 +4084,7 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data)
if (x86_pmu.intel_cap.pebs_baseline) {
arr[(*nr)++] = (struct perf_guest_switch_msr){
.msr = MSR_PEBS_DATA_CFG,
- .host = cpuc->pebs_data_cfg,
+ .host = cpuc->active_pebs_data_cfg,
.guest = kvm_pmu->pebs_data_cfg,
};
}
@@ -6496,6 +6506,7 @@ __init int intel_pmu_init(void)
case INTEL_FAM6_SAPPHIRERAPIDS_X:
case INTEL_FAM6_EMERALDRAPIDS_X:
x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX;
+ x86_pmu.extra_regs = intel_spr_extra_regs;
fallthrough;
case INTEL_FAM6_GRANITERAPIDS_X:
case INTEL_FAM6_GRANITERAPIDS_D:
@@ -6506,7 +6517,8 @@ __init int intel_pmu_init(void)
x86_pmu.event_constraints = intel_spr_event_constraints;
x86_pmu.pebs_constraints = intel_spr_pebs_event_constraints;
- x86_pmu.extra_regs = intel_spr_extra_regs;
+ if (!x86_pmu.extra_regs)
+ x86_pmu.extra_regs = intel_gnr_extra_regs;
x86_pmu.limit_period = spr_limit_period;
x86_pmu.pebs_ept = 1;
x86_pmu.pebs_aliases = NULL;
@@ -6650,6 +6662,7 @@ __init int intel_pmu_init(void)
pmu->pebs_constraints = intel_grt_pebs_event_constraints;
pmu->extra_regs = intel_grt_extra_regs;
if (is_mtl(boot_cpu_data.x86_model)) {
+ x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX].extra_regs = intel_gnr_extra_regs;
x86_pmu.pebs_latency_data = mtl_latency_data_small;
extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
mtl_hybrid_extra_attr_rtm : mtl_hybrid_extra_attr;
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index fa9b209a11fa..d49e90dc04a4 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -6150,6 +6150,7 @@ static struct intel_uncore_type spr_uncore_mdf = {
};
#define UNCORE_SPR_NUM_UNCORE_TYPES 12
+#define UNCORE_SPR_CHA 0
#define UNCORE_SPR_IIO 1
#define UNCORE_SPR_IMC 6
#define UNCORE_SPR_UPI 8
@@ -6460,12 +6461,22 @@ static int uncore_type_max_boxes(struct intel_uncore_type **types,
return max + 1;
}
+#define SPR_MSR_UNC_CBO_CONFIG 0x2FFE
+
void spr_uncore_cpu_init(void)
{
+ struct intel_uncore_type *type;
+ u64 num_cbo;
+
uncore_msr_uncores = uncore_get_uncores(UNCORE_ACCESS_MSR,
UNCORE_SPR_MSR_EXTRA_UNCORES,
spr_msr_uncores);
+ type = uncore_find_type_by_id(uncore_msr_uncores, UNCORE_SPR_CHA);
+ if (type) {
+ rdmsrl(SPR_MSR_UNC_CBO_CONFIG, num_cbo);
+ type->num_boxes = num_cbo;
+ }
spr_uncore_iio_free_running.num_boxes = uncore_type_max_boxes(uncore_msr_uncores, UNCORE_SPR_IIO);
}
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index a5f9474f08e1..6c04b52f139b 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -416,7 +416,7 @@ void __init hyperv_init(void)
goto free_vp_assist_page;
}
- cpuhp = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/hyperv_init:online",
+ cpuhp = cpuhp_setup_state(CPUHP_AP_HYPERV_ONLINE, "x86/hyperv_init:online",
hv_cpu_init, hv_cpu_die);
if (cpuhp < 0)
goto free_ghcb_page;
diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c
index 1ba5d3b99b16..85d38b9f3586 100644
--- a/arch/x86/hyperv/hv_vtl.c
+++ b/arch/x86/hyperv/hv_vtl.c
@@ -20,6 +20,8 @@ void __init hv_vtl_init_platform(void)
{
pr_info("Linux runs in Hyper-V Virtual Trust Level\n");
+ x86_platform.realmode_reserve = x86_init_noop;
+ x86_platform.realmode_init = x86_init_noop;
x86_init.irqs.pre_vector_init = x86_init_noop;
x86_init.timers.timer_init = x86_init_noop;
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 1e51650b79d7..4f1ce5fc4e19 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -1,6 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
+generated-y += orc_hash.h
generated-y += syscalls_32.h
generated-y += syscalls_64.h
generated-y += syscalls_x32.h
diff --git a/arch/x86/include/asm/fpu/sched.h b/arch/x86/include/asm/fpu/sched.h
index c2d6cd78ed0c..78fcde7b1f07 100644
--- a/arch/x86/include/asm/fpu/sched.h
+++ b/arch/x86/include/asm/fpu/sched.h
@@ -39,7 +39,7 @@ extern void fpu_flush_thread(void);
static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu)
{
if (cpu_feature_enabled(X86_FEATURE_FPU) &&
- !(current->flags & (PF_KTHREAD | PF_IO_WORKER))) {
+ !(current->flags & (PF_KTHREAD | PF_USER_WORKER))) {
save_fpregs_to_fpstate(old_fpu);
/*
* The save operation preserved register state, so the
diff --git a/arch/x86/include/asm/orc_header.h b/arch/x86/include/asm/orc_header.h
new file mode 100644
index 000000000000..07bacf3e160e
--- /dev/null
+++ b/arch/x86/include/asm/orc_header.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/* Copyright (c) Meta Platforms, Inc. and affiliates. */
+
+#ifndef _ORC_HEADER_H
+#define _ORC_HEADER_H
+
+#include <linux/types.h>
+#include <linux/compiler.h>
+#include <asm/orc_hash.h>
+
+/*
+ * The header is currently a 20-byte hash of the ORC entry definition; see
+ * scripts/orc_hash.sh.
+ */
+#define ORC_HEADER \
+ __used __section(".orc_header") __aligned(4) \
+ static const u8 orc_header[] = { ORC_HASH }
+
+#endif /* _ORC_HEADER_H */
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 498dc600bd5c..0d02c4aafa6f 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -13,7 +13,9 @@
#include <linux/bitops.h>
+#include <linux/bug.h>
#include <linux/types.h>
+
#include <uapi/asm/vmx.h>
#include <asm/vmxfeatures.h>
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index dd61752f4c96..4070a01c11b7 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -17,6 +17,7 @@ CFLAGS_REMOVE_ftrace.o = -pg
CFLAGS_REMOVE_early_printk.o = -pg
CFLAGS_REMOVE_head64.o = -pg
CFLAGS_REMOVE_sev.o = -pg
+CFLAGS_REMOVE_rethook.o = -pg
endif
KASAN_SANITIZE_head$(BITS).o := n
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index 6bde05a86b4e..896bc41cb2ba 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -97,7 +97,10 @@ static void init_x2apic_ldr(void)
static int x2apic_phys_probe(void)
{
- if (x2apic_mode && (x2apic_phys || x2apic_fadt_phys()))
+ if (!x2apic_mode)
+ return 0;
+
+ if (x2apic_phys || x2apic_fadt_phys())
return 1;
return apic == &apic_x2apic_phys;
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index 5e868b62a7c4..0270925fe013 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -79,7 +79,7 @@ int detect_extended_topology_early(struct cpuinfo_x86 *c)
* initial apic id, which also represents 32-bit extended x2apic id.
*/
c->initial_apicid = edx;
- smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx);
+ smp_num_siblings = max_t(int, smp_num_siblings, LEVEL_MAX_SIBLINGS(ebx));
#endif
return 0;
}
@@ -109,7 +109,8 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
*/
cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
c->initial_apicid = edx;
- core_level_siblings = smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx);
+ core_level_siblings = LEVEL_MAX_SIBLINGS(ebx);
+ smp_num_siblings = max_t(int, smp_num_siblings, LEVEL_MAX_SIBLINGS(ebx));
core_plus_mask_width = ht_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
die_level_siblings = LEVEL_MAX_SIBLINGS(ebx);
pkg_mask_width = die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 0bf6779187dd..f18ca44c904b 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -195,7 +195,6 @@ static void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
printk("%sCall Trace:\n", log_lvl);
unwind_start(&state, task, regs, stack);
- stack = stack ? : get_stack_pointer(task, regs);
regs = unwind_get_entry_regs(&state, &partial);
/*
@@ -214,9 +213,13 @@ static void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
* - hardirq stack
* - entry stack
*/
- for ( ; stack; stack = PTR_ALIGN(stack_info.next_sp, sizeof(long))) {
+ for (stack = stack ?: get_stack_pointer(task, regs);
+ stack;
+ stack = stack_info.next_sp) {
const char *stack_name;
+ stack = PTR_ALIGN(stack, sizeof(long));
+
if (get_stack_info(stack, task, &stack_info, &visit_mask)) {
/*
* We weren't on a valid stack. It's possible that
diff --git a/arch/x86/kernel/fpu/context.h b/arch/x86/kernel/fpu/context.h
index 9fcfa5c4dad7..af5cbdd9bd29 100644
--- a/arch/x86/kernel/fpu/context.h
+++ b/arch/x86/kernel/fpu/context.h
@@ -57,7 +57,7 @@ static inline void fpregs_restore_userregs(void)
struct fpu *fpu = &current->thread.fpu;
int cpu = smp_processor_id();
- if (WARN_ON_ONCE(current->flags & (PF_KTHREAD | PF_IO_WORKER)))
+ if (WARN_ON_ONCE(current->flags & (PF_KTHREAD | PF_USER_WORKER)))
return;
if (!fpregs_state_valid(fpu, cpu)) {
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index caf33486dc5e..1015af1ae562 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -426,7 +426,7 @@ void kernel_fpu_begin_mask(unsigned int kfpu_mask)
this_cpu_write(in_kernel_fpu, true);
- if (!(current->flags & (PF_KTHREAD | PF_IO_WORKER)) &&
+ if (!(current->flags & (PF_KTHREAD | PF_USER_WORKER)) &&
!test_thread_flag(TIF_NEED_FPU_LOAD)) {
set_thread_flag(TIF_NEED_FPU_LOAD);
save_fpregs_to_fpstate(&current->thread.fpu);
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index a5df3e994f04..113c13376e51 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -77,6 +77,15 @@ SYM_CODE_START_NOALIGN(startup_64)
call startup_64_setup_env
popq %rsi
+ /* Now switch to __KERNEL_CS so IRET works reliably */
+ pushq $__KERNEL_CS
+ leaq .Lon_kernel_cs(%rip), %rax
+ pushq %rax
+ lretq
+
+.Lon_kernel_cs:
+ UNWIND_HINT_END_OF_STACK
+
#ifdef CONFIG_AMD_MEM_ENCRYPT
/*
* Activate SEV/SME memory encryption if supported/enabled. This needs to
@@ -90,15 +99,6 @@ SYM_CODE_START_NOALIGN(startup_64)
popq %rsi
#endif
- /* Now switch to __KERNEL_CS so IRET works reliably */
- pushq $__KERNEL_CS
- leaq .Lon_kernel_cs(%rip), %rax
- pushq %rax
- lretq
-
-.Lon_kernel_cs:
- UNWIND_HINT_END_OF_STACK
-
/* Sanitize CPU configuration */
call verify_cpu
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index 3ac50b7298d1..4d8e518365f4 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -7,6 +7,9 @@
#include <asm/unwind.h>
#include <asm/orc_types.h>
#include <asm/orc_lookup.h>
+#include <asm/orc_header.h>
+
+ORC_HEADER;
#define orc_warn(fmt, ...) \
printk_deferred_once(KERN_WARNING "WARNING: " fmt, ##__VA_ARGS__)
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 123bf8b97a4b..0c9660a07b23 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -253,7 +253,6 @@ static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_e
int nent)
{
struct kvm_cpuid_entry2 *best;
- u64 guest_supported_xcr0 = cpuid_get_supported_xcr0(entries, nent);
best = cpuid_entry2_find(entries, nent, 1, KVM_CPUID_INDEX_NOT_SIGNIFICANT);
if (best) {
@@ -292,21 +291,6 @@ static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_e
vcpu->arch.ia32_misc_enable_msr &
MSR_IA32_MISC_ENABLE_MWAIT);
}
-
- /*
- * Bits 127:0 of the allowed SECS.ATTRIBUTES (CPUID.0x12.0x1) enumerate
- * the supported XSAVE Feature Request Mask (XFRM), i.e. the enclave's
- * requested XCR0 value. The enclave's XFRM must be a subset of XCRO
- * at the time of EENTER, thus adjust the allowed XFRM by the guest's
- * supported XCR0. Similar to XCR0 handling, FP and SSE are forced to
- * '1' even on CPUs that don't support XSAVE.
- */
- best = cpuid_entry2_find(entries, nent, 0x12, 0x1);
- if (best) {
- best->ecx &= guest_supported_xcr0 & 0xffffffff;
- best->edx &= guest_supported_xcr0 >> 32;
- best->ecx |= XFEATURE_MASK_FPSSE;
- }
}
void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index e542cf285b51..3c300a196bdf 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -229,6 +229,23 @@ static int kvm_recalculate_phys_map(struct kvm_apic_map *new,
u32 physical_id;
/*
+ * For simplicity, KVM always allocates enough space for all possible
+ * xAPIC IDs. Yell, but don't kill the VM, as KVM can continue on
+ * without the optimized map.
+ */
+ if (WARN_ON_ONCE(xapic_id > new->max_apic_id))
+ return -EINVAL;
+
+ /*
+ * Bail if a vCPU was added and/or enabled its APIC between allocating
+ * the map and doing the actual calculations for the map. Note, KVM
+ * hardcodes the x2APIC ID to vcpu_id, i.e. there's no TOCTOU bug if
+ * the compiler decides to reload x2apic_id after this check.
+ */
+ if (x2apic_id > new->max_apic_id)
+ return -E2BIG;
+
+ /*
* Deliberately truncate the vCPU ID when detecting a mismatched APIC
* ID to avoid false positives if the vCPU ID, i.e. x2APIC ID, is a
* 32-bit value. Any unwanted aliasing due to truncation results will
@@ -253,8 +270,7 @@ static int kvm_recalculate_phys_map(struct kvm_apic_map *new,
*/
if (vcpu->kvm->arch.x2apic_format) {
/* See also kvm_apic_match_physical_addr(). */
- if ((apic_x2apic_mode(apic) || x2apic_id > 0xff) &&
- x2apic_id <= new->max_apic_id)
+ if (apic_x2apic_mode(apic) || x2apic_id > 0xff)
new->phys_map[x2apic_id] = apic;
if (!apic_x2apic_mode(apic) && !new->phys_map[xapic_id])
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index c8961f45e3b1..6eaa3d6994ae 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -7091,7 +7091,10 @@ static void kvm_recover_nx_huge_pages(struct kvm *kvm)
*/
slot = NULL;
if (atomic_read(&kvm->nr_memslots_dirty_logging)) {
- slot = gfn_to_memslot(kvm, sp->gfn);
+ struct kvm_memslots *slots;
+
+ slots = kvm_memslots_for_spte_role(kvm, sp->role);
+ slot = __gfn_to_memslot(slots, sp->gfn);
WARN_ON_ONCE(!slot);
}
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index ca32389f3c36..54089f990c8f 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3510,7 +3510,7 @@ static bool svm_is_vnmi_pending(struct kvm_vcpu *vcpu)
if (!is_vnmi_enabled(svm))
return false;
- return !!(svm->vmcb->control.int_ctl & V_NMI_BLOCKING_MASK);
+ return !!(svm->vmcb->control.int_ctl & V_NMI_PENDING_MASK);
}
static bool svm_set_vnmi_pending(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/vmx/sgx.c b/arch/x86/kvm/vmx/sgx.c
index 0574030b071f..2261b684a7d4 100644
--- a/arch/x86/kvm/vmx/sgx.c
+++ b/arch/x86/kvm/vmx/sgx.c
@@ -170,12 +170,19 @@ static int __handle_encls_ecreate(struct kvm_vcpu *vcpu,
return 1;
}
- /* Enforce CPUID restrictions on MISCSELECT, ATTRIBUTES and XFRM. */
+ /*
+ * Enforce CPUID restrictions on MISCSELECT, ATTRIBUTES and XFRM. Note
+ * that the allowed XFRM (XFeature Request Mask) isn't strictly bound
+ * by the supported XCR0. FP+SSE *must* be set in XFRM, even if XSAVE
+ * is unsupported, i.e. even if XCR0 itself is completely unsupported.
+ */
if ((u32)miscselect & ~sgx_12_0->ebx ||
(u32)attributes & ~sgx_12_1->eax ||
(u32)(attributes >> 32) & ~sgx_12_1->ebx ||
(u32)xfrm & ~sgx_12_1->ecx ||
- (u32)(xfrm >> 32) & ~sgx_12_1->edx) {
+ (u32)(xfrm >> 32) & ~sgx_12_1->edx ||
+ xfrm & ~(vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FPSSE) ||
+ (xfrm & XFEATURE_MASK_FPSSE) != XFEATURE_MASK_FPSSE) {
kvm_inject_gp(vcpu, 0);
return 1;
}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index ceb7c5e9cf9e..04b57a336b34 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1446,7 +1446,7 @@ static const u32 msrs_to_save_base[] = {
#endif
MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA,
MSR_IA32_FEAT_CTL, MSR_IA32_BNDCFGS, MSR_TSC_AUX,
- MSR_IA32_SPEC_CTRL,
+ MSR_IA32_SPEC_CTRL, MSR_IA32_TSX_CTRL,
MSR_IA32_RTIT_CTL, MSR_IA32_RTIT_STATUS, MSR_IA32_RTIT_CR3_MATCH,
MSR_IA32_RTIT_OUTPUT_BASE, MSR_IA32_RTIT_OUTPUT_MASK,
MSR_IA32_RTIT_ADDR0_A, MSR_IA32_RTIT_ADDR0_B,
@@ -7155,6 +7155,10 @@ static void kvm_probe_msr_to_save(u32 msr_index)
if (!kvm_cpu_cap_has(X86_FEATURE_XFD))
return;
break;
+ case MSR_IA32_TSX_CTRL:
+ if (!(kvm_get_arch_capabilities() & ARCH_CAP_TSX_CTRL_MSR))
+ return;
+ break;
default:
break;
}
@@ -10754,6 +10758,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
exit_fastpath = EXIT_FASTPATH_EXIT_HANDLED;
break;
}
+
+ /* Note, VM-Exits that go down the "slow" path are accounted below. */
+ ++vcpu->stat.exits;
}
/*
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index 4fc5c2de2de4..01c5de4c279b 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -7,6 +7,8 @@
*/
#include <linux/linkage.h>
+#include <asm/cpufeatures.h>
+#include <asm/alternative.h>
#include <asm/asm.h>
#include <asm/export.h>
@@ -29,7 +31,7 @@
*/
SYM_FUNC_START(rep_movs_alternative)
cmpq $64,%rcx
- jae .Lunrolled
+ jae .Llarge
cmp $8,%ecx
jae .Lword
@@ -65,6 +67,12 @@ SYM_FUNC_START(rep_movs_alternative)
_ASM_EXTABLE_UA( 2b, .Lcopy_user_tail)
_ASM_EXTABLE_UA( 3b, .Lcopy_user_tail)
+.Llarge:
+0: ALTERNATIVE "jmp .Lunrolled", "rep movsb", X86_FEATURE_ERMS
+1: RET
+
+ _ASM_EXTABLE_UA( 0b, 1b)
+
.p2align 4
.Lunrolled:
10: movq (%rsi),%r8
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 3cdac0f0055d..8192452d1d2d 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -9,6 +9,7 @@
#include <linux/sched/task.h>
#include <asm/set_memory.h>
+#include <asm/cpu_device_id.h>
#include <asm/e820/api.h>
#include <asm/init.h>
#include <asm/page.h>
@@ -261,6 +262,24 @@ static void __init probe_page_size_mask(void)
}
}
+#define INTEL_MATCH(_model) { .vendor = X86_VENDOR_INTEL, \
+ .family = 6, \
+ .model = _model, \
+ }
+/*
+ * INVLPG may not properly flush Global entries
+ * on these CPUs when PCIDs are enabled.
+ */
+static const struct x86_cpu_id invlpg_miss_ids[] = {
+ INTEL_MATCH(INTEL_FAM6_ALDERLAKE ),
+ INTEL_MATCH(INTEL_FAM6_ALDERLAKE_L ),
+ INTEL_MATCH(INTEL_FAM6_ALDERLAKE_N ),
+ INTEL_MATCH(INTEL_FAM6_RAPTORLAKE ),
+ INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_P),
+ INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_S),
+ {}
+};
+
static void setup_pcid(void)
{
if (!IS_ENABLED(CONFIG_X86_64))
@@ -269,6 +288,12 @@ static void setup_pcid(void)
if (!boot_cpu_has(X86_FEATURE_PCID))
return;
+ if (x86_match_cpu(invlpg_miss_ids)) {
+ pr_info("Incomplete global flushes, disabling PCID");
+ setup_clear_cpu_cap(X86_FEATURE_PCID);
+ return;
+ }
+
if (boot_cpu_has(X86_FEATURE_PGE)) {
/*
* This can't be cr4_set_bits_and_update_boot() -- the
diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
index 557f0fe25dff..37db264866b6 100644
--- a/arch/x86/mm/kaslr.c
+++ b/arch/x86/mm/kaslr.c
@@ -172,10 +172,10 @@ void __meminit init_trampoline_kaslr(void)
set_p4d(p4d_tramp,
__p4d(_KERNPG_TABLE | __pa(pud_page_tramp)));
- set_pgd(&trampoline_pgd_entry,
- __pgd(_KERNPG_TABLE | __pa(p4d_page_tramp)));
+ trampoline_pgd_entry =
+ __pgd(_KERNPG_TABLE | __pa(p4d_page_tramp));
} else {
- set_pgd(&trampoline_pgd_entry,
- __pgd(_KERNPG_TABLE | __pa(pud_page_tramp)));
+ trampoline_pgd_entry =
+ __pgd(_KERNPG_TABLE | __pa(pud_page_tramp));
}
}
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 1056bbf55b17..438adb695daa 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -2570,7 +2570,7 @@ out_image:
}
if (bpf_jit_enable > 1)
- bpf_jit_dump(prog->len, proglen, pass + 1, image);
+ bpf_jit_dump(prog->len, proglen, pass + 1, rw_image);
if (image) {
if (!prog->is_func || extra_pass) {
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index 8babce71915f..014c508e914d 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -198,7 +198,7 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
i++;
}
kfree(v);
- return 0;
+ return msi_device_populate_sysfs(&dev->dev);
error:
if (ret == -ENOSYS)
@@ -254,7 +254,7 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
dev_dbg(&dev->dev,
"xen: msi --> pirq=%d --> irq=%d\n", pirq, irq);
}
- return 0;
+ return msi_device_populate_sysfs(&dev->dev);
error:
dev_err(&dev->dev, "Failed to create MSI%s! ret=%d!\n",
@@ -346,7 +346,7 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
if (ret < 0)
goto out;
}
- ret = 0;
+ ret = msi_device_populate_sysfs(&dev->dev);
out:
return ret;
}
@@ -394,6 +394,8 @@ static void xen_teardown_msi_irqs(struct pci_dev *dev)
xen_destroy_irq(msidesc->irq + i);
msidesc->irq = 0;
}
+
+ msi_device_destroy_sysfs(&dev->dev);
}
static void xen_pv_teardown_msi_irqs(struct pci_dev *dev)
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index 82fec66d46d2..42abd6af1198 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -14,6 +14,11 @@ $(obj)/sha256.o: $(srctree)/lib/crypto/sha256.c FORCE
CFLAGS_sha256.o := -D__DISABLE_EXPORTS
+# When profile-guided optimization is enabled, llvm emits two different
+# overlapping text sections, which is not supported by kexec. Remove profile
+# optimization flags.
+KBUILD_CFLAGS := $(filter-out -fprofile-sample-use=% -fprofile-use=%,$(KBUILD_CFLAGS))
+
# When linking purgatory.ro with -r unresolved symbols are not checked,
# also link a purgatory.chk binary without -r to check for unresolved symbols.
PURGATORY_LDFLAGS := -e purgatory_start -z nodefaultlib