summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/entry/entry_64.S16
-rw-r--r--arch/x86/include/asm/efi.h10
-rw-r--r--arch/x86/include/asm/kvm_host.h2
-rw-r--r--arch/x86/include/asm/msr-index.h1
-rw-r--r--arch/x86/kernel/apic/vector.c4
-rw-r--r--arch/x86/kernel/irq_32.c19
-rw-r--r--arch/x86/kernel/irq_64.c2
-rw-r--r--arch/x86/kernel/paravirt.c16
-rw-r--r--arch/x86/kernel/pci-dma.c2
-rw-r--r--arch/x86/kvm/mmu.c25
-rw-r--r--arch/x86/kvm/svm.c4
-rw-r--r--arch/x86/kvm/vmx.c2
-rw-r--r--arch/x86/kvm/x86.c3
-rw-r--r--arch/x86/lguest/boot.c2
-rw-r--r--arch/x86/pci/common.c1
15 files changed, 78 insertions, 31 deletions
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index d3033183ed70..055a01de7c8d 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1128,7 +1128,18 @@ END(error_exit)
/* Runs on exception stack */
ENTRY(nmi)
+ /*
+ * Fix up the exception frame if we're on Xen.
+ * PARAVIRT_ADJUST_EXCEPTION_FRAME is guaranteed to push at most
+ * one value to the stack on native, so it may clobber the rdx
+ * scratch slot, but it won't clobber any of the important
+ * slots past it.
+ *
+ * Xen is a different story, because the Xen frame itself overlaps
+ * the "NMI executing" variable.
+ */
PARAVIRT_ADJUST_EXCEPTION_FRAME
+
/*
* We allow breakpoints in NMIs. If a breakpoint occurs, then
* the iretq it performs will take us out of NMI context.
@@ -1179,9 +1190,12 @@ ENTRY(nmi)
* we don't want to enable interrupts, because then we'll end
* up in an awkward situation in which IRQs are on but NMIs
* are off.
+ *
+ * We also must not push anything to the stack before switching
+ * stacks lest we corrupt the "NMI executing" variable.
*/
- SWAPGS
+ SWAPGS_UNSAFE_STACK
cld
movq %rsp, %rdx
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 155162ea0e00..ab5f1d447ef9 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -86,6 +86,16 @@ extern u64 asmlinkage efi_call(void *fp, ...);
extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size,
u32 type, u64 attribute);
+/*
+ * CONFIG_KASAN may redefine memset to __memset. __memset function is present
+ * only in kernel binary. Since the EFI stub linked into a separate binary it
+ * doesn't have __memset(). So we should use standard memset from
+ * arch/x86/boot/compressed/string.c. The same applies to memcpy and memmove.
+ */
+#undef memcpy
+#undef memset
+#undef memmove
+
#endif /* CONFIG_X86_32 */
extern struct efi_scratch efi_scratch;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index c12e845f59e6..2beee0382088 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -40,6 +40,7 @@
#define KVM_PIO_PAGE_OFFSET 1
#define KVM_COALESCED_MMIO_PAGE_OFFSET 2
+#define KVM_HALT_POLL_NS_DEFAULT 500000
#define KVM_IRQCHIP_NUM_PINS KVM_IOAPIC_NUM_PINS
@@ -711,6 +712,7 @@ struct kvm_vcpu_stat {
u32 nmi_window_exits;
u32 halt_exits;
u32 halt_successful_poll;
+ u32 halt_attempted_poll;
u32 halt_wakeup;
u32 request_irq_exits;
u32 irq_exits;
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 54390bc140dd..b8c14bb7fc8f 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -333,6 +333,7 @@
/* C1E active bits in int pending message */
#define K8_INTP_C1E_ACTIVE_MASK 0x18000000
#define MSR_K8_TSEG_ADDR 0xc0010112
+#define MSR_K8_TSEG_MASK 0xc0010113
#define K8_MTRRFIXRANGE_DRAM_ENABLE 0x00040000 /* MtrrFixDramEn bit */
#define K8_MTRRFIXRANGE_DRAM_MODIFY 0x00080000 /* MtrrFixDramModEn bit */
#define K8_MTRR_RDMEM_WRMEM_MASK 0x18181818 /* Mask: RdMem|WrMem */
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 1bbd0fe2c806..836d11b92811 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -489,10 +489,8 @@ static int apic_set_affinity(struct irq_data *irq_data,
err = assign_irq_vector(irq, data, dest);
if (err) {
- struct irq_data *top = irq_get_irq_data(irq);
-
if (assign_irq_vector(irq, data,
- irq_data_get_affinity_mask(top)))
+ irq_data_get_affinity_mask(irq_data)))
pr_err("Failed to recover vector for irq %d\n", irq);
return err;
}
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index c80cf6699678..38da8f29a9c8 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -68,11 +68,10 @@ static inline void *current_stack(void)
return (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1));
}
-static inline int
-execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq)
+static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
{
struct irq_stack *curstk, *irqstk;
- u32 *isp, *prev_esp, arg1, arg2;
+ u32 *isp, *prev_esp, arg1;
curstk = (struct irq_stack *) current_stack();
irqstk = __this_cpu_read(hardirq_stack);
@@ -98,8 +97,8 @@ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq)
asm volatile("xchgl %%ebx,%%esp \n"
"call *%%edi \n"
"movl %%ebx,%%esp \n"
- : "=a" (arg1), "=d" (arg2), "=b" (isp)
- : "0" (irq), "1" (desc), "2" (isp),
+ : "=a" (arg1), "=b" (isp)
+ : "0" (desc), "1" (isp),
"D" (desc->handle_irq)
: "memory", "cc", "ecx");
return 1;
@@ -150,19 +149,15 @@ void do_softirq_own_stack(void)
bool handle_irq(struct irq_desc *desc, struct pt_regs *regs)
{
- unsigned int irq;
- int overflow;
-
- overflow = check_stack_overflow();
+ int overflow = check_stack_overflow();
if (IS_ERR_OR_NULL(desc))
return false;
- irq = irq_desc_get_irq(desc);
- if (user_mode(regs) || !execute_on_irq_stack(overflow, desc, irq)) {
+ if (user_mode(regs) || !execute_on_irq_stack(overflow, desc)) {
if (unlikely(overflow))
print_stack_overflow();
- generic_handle_irq_desc(irq, desc);
+ generic_handle_irq_desc(desc);
}
return true;
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index ff16ccb918f2..c767cf2bc80a 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -75,6 +75,6 @@ bool handle_irq(struct irq_desc *desc, struct pt_regs *regs)
if (unlikely(IS_ERR_OR_NULL(desc)))
return false;
- generic_handle_irq_desc(irq_desc_get_irq(desc), desc);
+ generic_handle_irq_desc(desc);
return true;
}
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index f68e48f5f6c2..c2130aef3f9d 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -41,10 +41,18 @@
#include <asm/timer.h>
#include <asm/special_insns.h>
-/* nop stub */
-void _paravirt_nop(void)
-{
-}
+/*
+ * nop stub, which must not clobber anything *including the stack* to
+ * avoid confusing the entry prologues.
+ */
+extern void _paravirt_nop(void);
+asm (".pushsection .entry.text, \"ax\"\n"
+ ".global _paravirt_nop\n"
+ "_paravirt_nop:\n\t"
+ "ret\n\t"
+ ".size _paravirt_nop, . - _paravirt_nop\n\t"
+ ".type _paravirt_nop, @function\n\t"
+ ".popsection");
/* identity function, which can be inlined */
u32 _paravirt_ident_32(u32 x)
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 84b8ef82a159..1b55de1267cf 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -131,8 +131,8 @@ void dma_generic_free_coherent(struct device *dev, size_t size, void *vaddr,
bool arch_dma_alloc_attrs(struct device **dev, gfp_t *gfp)
{
- *gfp = dma_alloc_coherent_gfp_flags(*dev, *gfp);
*gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
+ *gfp = dma_alloc_coherent_gfp_flags(*dev, *gfp);
if (!*dev)
*dev = &x86_dma_fallback_dev;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 69088a1ba509..ff606f507913 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3322,7 +3322,7 @@ walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
break;
reserved |= is_shadow_zero_bits_set(&vcpu->arch.mmu, spte,
- leaf);
+ iterator.level);
}
walk_shadow_page_lockless_end(vcpu);
@@ -3614,7 +3614,7 @@ static void
__reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
struct rsvd_bits_validate *rsvd_check,
int maxphyaddr, int level, bool nx, bool gbpages,
- bool pse)
+ bool pse, bool amd)
{
u64 exb_bit_rsvd = 0;
u64 gbpages_bit_rsvd = 0;
@@ -3631,7 +3631,7 @@ __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
* Non-leaf PML4Es and PDPEs reserve bit 8 (which would be the G bit for
* leaf entries) on AMD CPUs only.
*/
- if (guest_cpuid_is_amd(vcpu))
+ if (amd)
nonleaf_bit8_rsvd = rsvd_bits(8, 8);
switch (level) {
@@ -3699,7 +3699,7 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
__reset_rsvds_bits_mask(vcpu, &context->guest_rsvd_check,
cpuid_maxphyaddr(vcpu), context->root_level,
context->nx, guest_cpuid_has_gbpages(vcpu),
- is_pse(vcpu));
+ is_pse(vcpu), guest_cpuid_is_amd(vcpu));
}
static void
@@ -3749,13 +3749,24 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
void
reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
{
+ /*
+ * Passing "true" to the last argument is okay; it adds a check
+ * on bit 8 of the SPTEs which KVM doesn't use anyway.
+ */
__reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check,
boot_cpu_data.x86_phys_bits,
context->shadow_root_level, context->nx,
- guest_cpuid_has_gbpages(vcpu), is_pse(vcpu));
+ guest_cpuid_has_gbpages(vcpu), is_pse(vcpu),
+ true);
}
EXPORT_SYMBOL_GPL(reset_shadow_zero_bits_mask);
+static inline bool boot_cpu_is_amd(void)
+{
+ WARN_ON_ONCE(!tdp_enabled);
+ return shadow_x_mask == 0;
+}
+
/*
* the direct page table on host, use as much mmu features as
* possible, however, kvm currently does not do execution-protection.
@@ -3764,11 +3775,11 @@ static void
reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu,
struct kvm_mmu *context)
{
- if (guest_cpuid_is_amd(vcpu))
+ if (boot_cpu_is_amd())
__reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check,
boot_cpu_data.x86_phys_bits,
context->shadow_root_level, false,
- cpu_has_gbpages, true);
+ cpu_has_gbpages, true, true);
else
__reset_rsvds_bits_mask_ept(&context->shadow_zero_check,
boot_cpu_data.x86_phys_bits,
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index fdb8cb63a6c0..94b7d15db3fc 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -202,6 +202,7 @@ module_param(npt, int, S_IRUGO);
static int nested = true;
module_param(nested, int, S_IRUGO);
+static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
static void svm_flush_tlb(struct kvm_vcpu *vcpu);
static void svm_complete_interrupts(struct vcpu_svm *svm);
@@ -1263,7 +1264,8 @@ static void init_vmcb(struct vcpu_svm *svm, bool init_event)
* svm_set_cr0() sets PG and WP and clears NW and CD on save->cr0.
* It also updates the guest-visible cr0 value.
*/
- (void)kvm_set_cr0(&svm->vcpu, X86_CR0_NW | X86_CR0_CD | X86_CR0_ET);
+ svm_set_cr0(&svm->vcpu, X86_CR0_NW | X86_CR0_CD | X86_CR0_ET);
+ kvm_mmu_reset_context(&svm->vcpu);
save->cr4 = X86_CR4_PAE;
/* rdx = ?? */
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index d01986832afc..64076740251e 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6064,6 +6064,8 @@ static __init int hardware_setup(void)
memcpy(vmx_msr_bitmap_longmode_x2apic,
vmx_msr_bitmap_longmode, PAGE_SIZE);
+ set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */
+
if (enable_apicv) {
for (msr = 0x800; msr <= 0x8ff; msr++)
vmx_disable_intercept_msr_read_x2apic(msr);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index a60bdbccff51..991466bf8dee 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -149,6 +149,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
{ "nmi_window", VCPU_STAT(nmi_window_exits) },
{ "halt_exits", VCPU_STAT(halt_exits) },
{ "halt_successful_poll", VCPU_STAT(halt_successful_poll) },
+ { "halt_attempted_poll", VCPU_STAT(halt_attempted_poll) },
{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
{ "hypercalls", VCPU_STAT(hypercalls) },
{ "request_irq", VCPU_STAT(request_irq_exits) },
@@ -2189,6 +2190,8 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
case MSR_IA32_LASTINTFROMIP:
case MSR_IA32_LASTINTTOIP:
case MSR_K8_SYSCFG:
+ case MSR_K8_TSEG_ADDR:
+ case MSR_K8_TSEG_MASK:
case MSR_K7_HWCR:
case MSR_VM_HSAVE_PA:
case MSR_K8_INT_PENDING_MSG:
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 161804de124a..a0d09f6c6533 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -1015,7 +1015,7 @@ static struct clock_event_device lguest_clockevent = {
* This is the Guest timer interrupt handler (hardware interrupt 0). We just
* call the clockevent infrastructure and it does whatever needs doing.
*/
-static void lguest_time_irq(unsigned int irq, struct irq_desc *desc)
+static void lguest_time_irq(struct irq_desc *desc)
{
unsigned long flags;
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 09d3afc0a181..dc78a4a9a466 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -166,6 +166,7 @@ void pcibios_fixup_bus(struct pci_bus *b)
{
struct pci_dev *dev;
+ pci_read_bridge_bases(b);
list_for_each_entry(dev, &b->devices, bus_list)
pcibios_fixup_device_resources(dev);
}
generated by cgit v1.2.3 (git 2.39.0) at 2025-02-20 06:33:32 +0300