summaryrefslogtreecommitdiffstats
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/include/asm/efi.h2
-rw-r--r--arch/x86/include/asm/kvm-x86-ops.h1
-rw-r--r--arch/x86/include/asm/kvm_host.h1
-rw-r--r--arch/x86/include/asm/pkru.h4
-rw-r--r--arch/x86/kernel/setup.c72
-rw-r--r--arch/x86/kvm/mmu/tdp_iter.c6
-rw-r--r--arch/x86/kvm/mmu/tdp_iter.h6
-rw-r--r--arch/x86/kvm/mmu/tdp_mmu.c29
-rw-r--r--arch/x86/kvm/svm/svm.c21
-rw-r--r--arch/x86/kvm/vmx/vmx.c45
-rw-r--r--arch/x86/kvm/x86.c11
-rw-r--r--arch/x86/tools/relocs.c2
12 files changed, 109 insertions, 91 deletions
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 4d0b126835b8..63158fd55856 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -197,8 +197,6 @@ static inline bool efi_runtime_supported(void)
extern void parse_efi_setup(u64 phys_addr, u32 data_len);
-extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt);
-
extern void efi_thunk_runtime_setup(void);
efi_status_t efi_set_virtual_address_map(unsigned long memory_map_size,
unsigned long descriptor_size,
diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index cefe1d81e2e8..9e50da3ed01a 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -47,6 +47,7 @@ KVM_X86_OP(set_dr7)
KVM_X86_OP(cache_reg)
KVM_X86_OP(get_rflags)
KVM_X86_OP(set_rflags)
+KVM_X86_OP(get_if_flag)
KVM_X86_OP(tlb_flush_all)
KVM_X86_OP(tlb_flush_current)
KVM_X86_OP_NULL(tlb_remote_flush)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 2164b9f4c7b0..555f4de47ef2 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1349,6 +1349,7 @@ struct kvm_x86_ops {
void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg);
unsigned long (*get_rflags)(struct kvm_vcpu *vcpu);
void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags);
+ bool (*get_if_flag)(struct kvm_vcpu *vcpu);
void (*tlb_flush_all)(struct kvm_vcpu *vcpu);
void (*tlb_flush_current)(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/include/asm/pkru.h b/arch/x86/include/asm/pkru.h
index 4cd49afa0ca4..74f0a2d34ffd 100644
--- a/arch/x86/include/asm/pkru.h
+++ b/arch/x86/include/asm/pkru.h
@@ -4,8 +4,8 @@
#include <asm/cpufeature.h>
-#define PKRU_AD_BIT 0x1
-#define PKRU_WD_BIT 0x2
+#define PKRU_AD_BIT 0x1u
+#define PKRU_WD_BIT 0x2u
#define PKRU_BITS_PER_PKEY 2
#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 6a190c7f4d71..e04f5e6eb33f 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -713,9 +713,6 @@ static void __init early_reserve_memory(void)
early_reserve_initrd();
- if (efi_enabled(EFI_BOOT))
- efi_memblock_x86_reserve_range();
-
memblock_x86_reserve_range_setup_data();
reserve_ibft_region();
@@ -742,28 +739,6 @@ dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p)
return 0;
}
-static char * __init prepare_command_line(void)
-{
-#ifdef CONFIG_CMDLINE_BOOL
-#ifdef CONFIG_CMDLINE_OVERRIDE
- strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
-#else
- if (builtin_cmdline[0]) {
- /* append boot loader cmdline to builtin */
- strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE);
- strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE);
- strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
- }
-#endif
-#endif
-
- strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
-
- parse_early_param();
-
- return command_line;
-}
-
/*
* Determine if we were loaded by an EFI loader. If so, then we have also been
* passed the efi memmap, systab, etc., so we should use these data structures
@@ -853,23 +828,6 @@ void __init setup_arch(char **cmdline_p)
x86_init.oem.arch_setup();
/*
- * x86_configure_nx() is called before parse_early_param() (called by
- * prepare_command_line()) to detect whether hardware doesn't support
- * NX (so that the early EHCI debug console setup can safely call
- * set_fixmap()). It may then be called again from within noexec_setup()
- * during parsing early parameters to honor the respective command line
- * option.
- */
- x86_configure_nx();
-
- /*
- * This parses early params and it needs to run before
- * early_reserve_memory() because latter relies on such settings
- * supplied as early params.
- */
- *cmdline_p = prepare_command_line();
-
- /*
* Do some memory reservations *before* memory is added to memblock, so
* memblock allocations won't overwrite it.
*
@@ -902,6 +860,36 @@ void __init setup_arch(char **cmdline_p)
bss_resource.start = __pa_symbol(__bss_start);
bss_resource.end = __pa_symbol(__bss_stop)-1;
+#ifdef CONFIG_CMDLINE_BOOL
+#ifdef CONFIG_CMDLINE_OVERRIDE
+ strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
+#else
+ if (builtin_cmdline[0]) {
+ /* append boot loader cmdline to builtin */
+ strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE);
+ strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE);
+ strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
+ }
+#endif
+#endif
+
+ strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
+ *cmdline_p = command_line;
+
+ /*
+ * x86_configure_nx() is called before parse_early_param() to detect
+ * whether hardware doesn't support NX (so that the early EHCI debug
+ * console setup can safely call set_fixmap()). It may then be called
+ * again from within noexec_setup() during parsing early parameters
+ * to honor the respective command line option.
+ */
+ x86_configure_nx();
+
+ parse_early_param();
+
+ if (efi_enabled(EFI_BOOT))
+ efi_memblock_x86_reserve_range();
+
#ifdef CONFIG_MEMORY_HOTPLUG
/*
* Memory used by the kernel cannot be hot-removed because Linux
diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c
index b3ed302c1a35..caa96c270b95 100644
--- a/arch/x86/kvm/mmu/tdp_iter.c
+++ b/arch/x86/kvm/mmu/tdp_iter.c
@@ -26,6 +26,7 @@ static gfn_t round_gfn_for_level(gfn_t gfn, int level)
*/
void tdp_iter_restart(struct tdp_iter *iter)
{
+ iter->yielded = false;
iter->yielded_gfn = iter->next_last_level_gfn;
iter->level = iter->root_level;
@@ -160,6 +161,11 @@ static bool try_step_up(struct tdp_iter *iter)
*/
void tdp_iter_next(struct tdp_iter *iter)
{
+ if (iter->yielded) {
+ tdp_iter_restart(iter);
+ return;
+ }
+
if (try_step_down(iter))
return;
diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h
index b1748b988d3a..e19cabbcb65c 100644
--- a/arch/x86/kvm/mmu/tdp_iter.h
+++ b/arch/x86/kvm/mmu/tdp_iter.h
@@ -45,6 +45,12 @@ struct tdp_iter {
* iterator walks off the end of the paging structure.
*/
bool valid;
+ /*
+ * True if KVM dropped mmu_lock and yielded in the middle of a walk, in
+ * which case tdp_iter_next() needs to restart the walk at the root
+ * level instead of advancing to the next entry.
+ */
+ bool yielded;
};
/*
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 1db8496259ad..1beb4ca90560 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -502,6 +502,8 @@ static inline bool tdp_mmu_set_spte_atomic(struct kvm *kvm,
struct tdp_iter *iter,
u64 new_spte)
{
+ WARN_ON_ONCE(iter->yielded);
+
lockdep_assert_held_read(&kvm->mmu_lock);
/*
@@ -575,6 +577,8 @@ static inline void __tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter,
u64 new_spte, bool record_acc_track,
bool record_dirty_log)
{
+ WARN_ON_ONCE(iter->yielded);
+
lockdep_assert_held_write(&kvm->mmu_lock);
/*
@@ -640,18 +644,19 @@ static inline void tdp_mmu_set_spte_no_dirty_log(struct kvm *kvm,
* If this function should yield and flush is set, it will perform a remote
* TLB flush before yielding.
*
- * If this function yields, it will also reset the tdp_iter's walk over the
- * paging structure and the calling function should skip to the next
- * iteration to allow the iterator to continue its traversal from the
- * paging structure root.
+ * If this function yields, iter->yielded is set and the caller must skip to
+ * the next iteration, where tdp_iter_next() will reset the tdp_iter's walk
+ * over the paging structures to allow the iterator to continue its traversal
+ * from the paging structure root.
*
- * Return true if this function yielded and the iterator's traversal was reset.
- * Return false if a yield was not needed.
+ * Returns true if this function yielded.
*/
-static inline bool tdp_mmu_iter_cond_resched(struct kvm *kvm,
- struct tdp_iter *iter, bool flush,
- bool shared)
+static inline bool __must_check tdp_mmu_iter_cond_resched(struct kvm *kvm,
+ struct tdp_iter *iter,
+ bool flush, bool shared)
{
+ WARN_ON(iter->yielded);
+
/* Ensure forward progress has been made before yielding. */
if (iter->next_last_level_gfn == iter->yielded_gfn)
return false;
@@ -671,12 +676,10 @@ static inline bool tdp_mmu_iter_cond_resched(struct kvm *kvm,
WARN_ON(iter->gfn > iter->next_last_level_gfn);
- tdp_iter_restart(iter);
-
- return true;
+ iter->yielded = true;
}
- return false;
+ return iter->yielded;
}
/*
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index d0f68d11ec70..5151efa424ac 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1585,6 +1585,15 @@ static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
to_svm(vcpu)->vmcb->save.rflags = rflags;
}
+static bool svm_get_if_flag(struct kvm_vcpu *vcpu)
+{
+ struct vmcb *vmcb = to_svm(vcpu)->vmcb;
+
+ return sev_es_guest(vcpu->kvm)
+ ? vmcb->control.int_state & SVM_GUEST_INTERRUPT_MASK
+ : kvm_get_rflags(vcpu) & X86_EFLAGS_IF;
+}
+
static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
{
switch (reg) {
@@ -3568,14 +3577,7 @@ bool svm_interrupt_blocked(struct kvm_vcpu *vcpu)
if (!gif_set(svm))
return true;
- if (sev_es_guest(vcpu->kvm)) {
- /*
- * SEV-ES guests to not expose RFLAGS. Use the VMCB interrupt mask
- * bit to determine the state of the IF flag.
- */
- if (!(vmcb->control.int_state & SVM_GUEST_INTERRUPT_MASK))
- return true;
- } else if (is_guest_mode(vcpu)) {
+ if (is_guest_mode(vcpu)) {
/* As long as interrupts are being delivered... */
if ((svm->nested.ctl.int_ctl & V_INTR_MASKING_MASK)
? !(svm->vmcb01.ptr->save.rflags & X86_EFLAGS_IF)
@@ -3586,7 +3588,7 @@ bool svm_interrupt_blocked(struct kvm_vcpu *vcpu)
if (nested_exit_on_intr(svm))
return false;
} else {
- if (!(kvm_get_rflags(vcpu) & X86_EFLAGS_IF))
+ if (!svm_get_if_flag(vcpu))
return true;
}
@@ -4621,6 +4623,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
.cache_reg = svm_cache_reg,
.get_rflags = svm_get_rflags,
.set_rflags = svm_set_rflags,
+ .get_if_flag = svm_get_if_flag,
.tlb_flush_all = svm_flush_tlb,
.tlb_flush_current = svm_flush_tlb,
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 5aadad3e7367..0dbf94eb954f 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1363,6 +1363,11 @@ void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
vmx->emulation_required = vmx_emulation_required(vcpu);
}
+static bool vmx_get_if_flag(struct kvm_vcpu *vcpu)
+{
+ return vmx_get_rflags(vcpu) & X86_EFLAGS_IF;
+}
+
u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu)
{
u32 interruptibility = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO);
@@ -3959,8 +3964,7 @@ static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
if (pi_test_and_set_on(&vmx->pi_desc))
return 0;
- if (vcpu != kvm_get_running_vcpu() &&
- !kvm_vcpu_trigger_posted_interrupt(vcpu, false))
+ if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false))
kvm_vcpu_kick(vcpu);
return 0;
@@ -5877,18 +5881,14 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
vmx_flush_pml_buffer(vcpu);
/*
- * We should never reach this point with a pending nested VM-Enter, and
- * more specifically emulation of L2 due to invalid guest state (see
- * below) should never happen as that means we incorrectly allowed a
- * nested VM-Enter with an invalid vmcs12.
+ * KVM should never reach this point with a pending nested VM-Enter.
+ * More specifically, short-circuiting VM-Entry to emulate L2 due to
+ * invalid guest state should never happen as that means KVM knowingly
+ * allowed a nested VM-Enter with an invalid vmcs12. More below.
*/
if (KVM_BUG_ON(vmx->nested.nested_run_pending, vcpu->kvm))
return -EIO;
- /* If guest state is invalid, start emulating */
- if (vmx->emulation_required)
- return handle_invalid_guest_state(vcpu);
-
if (is_guest_mode(vcpu)) {
/*
* PML is never enabled when running L2, bail immediately if a
@@ -5910,10 +5910,30 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
*/
nested_mark_vmcs12_pages_dirty(vcpu);
+ /*
+ * Synthesize a triple fault if L2 state is invalid. In normal
+ * operation, nested VM-Enter rejects any attempt to enter L2
+ * with invalid state. However, those checks are skipped if
+ * state is being stuffed via RSM or KVM_SET_NESTED_STATE. If
+ * L2 state is invalid, it means either L1 modified SMRAM state
+ * or userspace provided bad state. Synthesize TRIPLE_FAULT as
+ * doing so is architecturally allowed in the RSM case, and is
+ * the least awful solution for the userspace case without
+ * risking false positives.
+ */
+ if (vmx->emulation_required) {
+ nested_vmx_vmexit(vcpu, EXIT_REASON_TRIPLE_FAULT, 0, 0);
+ return 1;
+ }
+
if (nested_vmx_reflect_vmexit(vcpu))
return 1;
}
+ /* If guest state is invalid, start emulating. L2 is handled above. */
+ if (vmx->emulation_required)
+ return handle_invalid_guest_state(vcpu);
+
if (exit_reason.failed_vmentry) {
dump_vmcs(vcpu);
vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY;
@@ -6608,9 +6628,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
* consistency check VM-Exit due to invalid guest state and bail.
*/
if (unlikely(vmx->emulation_required)) {
-
- /* We don't emulate invalid state of a nested guest */
- vmx->fail = is_guest_mode(vcpu);
+ vmx->fail = 0;
vmx->exit_reason.full = EXIT_REASON_INVALID_STATE;
vmx->exit_reason.failed_vmentry = 1;
@@ -7579,6 +7597,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
.cache_reg = vmx_cache_reg,
.get_rflags = vmx_get_rflags,
.set_rflags = vmx_set_rflags,
+ .get_if_flag = vmx_get_if_flag,
.tlb_flush_all = vmx_flush_tlb_all,
.tlb_flush_current = vmx_flush_tlb_current,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9a2972fdae82..e50e97ac4408 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1331,7 +1331,7 @@ static const u32 msrs_to_save_all[] = {
MSR_IA32_UMWAIT_CONTROL,
MSR_ARCH_PERFMON_FIXED_CTR0, MSR_ARCH_PERFMON_FIXED_CTR1,
- MSR_ARCH_PERFMON_FIXED_CTR0 + 2, MSR_ARCH_PERFMON_FIXED_CTR0 + 3,
+ MSR_ARCH_PERFMON_FIXED_CTR0 + 2,
MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS,
MSR_CORE_PERF_GLOBAL_CTRL, MSR_CORE_PERF_GLOBAL_OVF_CTRL,
MSR_ARCH_PERFMON_PERFCTR0, MSR_ARCH_PERFMON_PERFCTR1,
@@ -9001,14 +9001,7 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu)
{
struct kvm_run *kvm_run = vcpu->run;
- /*
- * if_flag is obsolete and useless, so do not bother
- * setting it for SEV-ES guests. Userspace can just
- * use kvm_run->ready_for_interrupt_injection.
- */
- kvm_run->if_flag = !vcpu->arch.guest_state_protected
- && (kvm_get_rflags(vcpu) & X86_EFLAGS_IF) != 0;
-
+ kvm_run->if_flag = static_call(kvm_x86_get_if_flag)(vcpu);
kvm_run->cr8 = kvm_get_cr8(vcpu);
kvm_run->apic_base = kvm_get_apic_base(vcpu);
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index c736cf2ac76b..e2c5b296120d 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -68,7 +68,7 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = {
"(__parainstructions|__alt_instructions)(_end)?|"
"(__iommu_table|__apicdrivers|__smp_locks)(_end)?|"
"__(start|end)_pci_.*|"
-#if CONFIG_FW_LOADER_BUILTIN
+#if CONFIG_FW_LOADER
"__(start|end)_builtin_fw|"
#endif
"__(start|stop)___ksymtab(_gpl)?|"
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-06 19:51:29 +0000