summaryrefslogtreecommitdiffstats
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig7
-rw-r--r--arch/x86/include/asm/espfix.h2
-rw-r--r--arch/x86/include/asm/kasan.h8
-rw-r--r--arch/x86/include/asm/kvm_host.h2
-rw-r--r--arch/x86/include/uapi/asm/hyperv.h2
-rw-r--r--arch/x86/kernel/apic/vector.c10
-rw-r--r--arch/x86/kernel/early_printk.c4
-rw-r--r--arch/x86/kernel/espfix_64.c28
-rw-r--r--arch/x86/kernel/head64.c10
-rw-r--r--arch/x86/kernel/head_64.S29
-rw-r--r--arch/x86/kernel/irq.c20
-rw-r--r--arch/x86/kernel/smpboot.c27
-rw-r--r--arch/x86/kernel/tsc.c11
-rw-r--r--arch/x86/kvm/cpuid.c2
-rw-r--r--arch/x86/kvm/iommu.c2
-rw-r--r--arch/x86/kvm/mmu.c10
-rw-r--r--arch/x86/kvm/svm.c108
-rw-r--r--arch/x86/kvm/vmx.c11
-rw-r--r--arch/x86/kvm/x86.c26
-rw-r--r--arch/x86/lib/usercopy.c2
-rw-r--r--arch/x86/mm/kasan_init_64.c47
21 files changed, 259 insertions, 109 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 55bced17dc95..3dbb7e7909ca 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -254,6 +254,11 @@ config ARCH_SUPPORTS_OPTIMIZED_INLINING
config ARCH_SUPPORTS_DEBUG_PAGEALLOC
def_bool y
+config KASAN_SHADOW_OFFSET
+ hex
+ depends on KASAN
+ default 0xdffffc0000000000
+
config HAVE_INTEL_TXT
def_bool y
depends on INTEL_IOMMU && ACPI
@@ -2015,7 +2020,7 @@ config CMDLINE_BOOL
To compile command line arguments into the kernel,
set this option to 'Y', then fill in the
- the boot arguments in CONFIG_CMDLINE.
+ boot arguments in CONFIG_CMDLINE.
Systems with fully functional boot loaders (i.e. non-embedded)
should leave this option set to 'N'.
diff --git a/arch/x86/include/asm/espfix.h b/arch/x86/include/asm/espfix.h
index 99efebb2f69d..ca3ce9ab9385 100644
--- a/arch/x86/include/asm/espfix.h
+++ b/arch/x86/include/asm/espfix.h
@@ -9,7 +9,7 @@ DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack);
DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr);
extern void init_espfix_bsp(void);
-extern void init_espfix_ap(void);
+extern void init_espfix_ap(int cpu);
#endif /* CONFIG_X86_64 */
diff --git a/arch/x86/include/asm/kasan.h b/arch/x86/include/asm/kasan.h
index 8b22422fbad8..74a2a8dc9908 100644
--- a/arch/x86/include/asm/kasan.h
+++ b/arch/x86/include/asm/kasan.h
@@ -14,15 +14,11 @@
#ifndef __ASSEMBLY__
-extern pte_t kasan_zero_pte[];
-extern pte_t kasan_zero_pmd[];
-extern pte_t kasan_zero_pud[];
-
#ifdef CONFIG_KASAN
-void __init kasan_map_early_shadow(pgd_t *pgd);
+void __init kasan_early_init(void);
void __init kasan_init(void);
#else
-static inline void kasan_map_early_shadow(pgd_t *pgd) { }
+static inline void kasan_early_init(void) { }
static inline void kasan_init(void) { }
#endif
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 2a7f5d782c33..49ec9038ec14 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -604,6 +604,8 @@ struct kvm_arch {
bool iommu_noncoherent;
#define __KVM_HAVE_ARCH_NONCOHERENT_DMA
atomic_t noncoherent_dma_count;
+#define __KVM_HAVE_ARCH_ASSIGNED_DEVICE
+ atomic_t assigned_device_count;
struct kvm_pic *vpic;
struct kvm_ioapic *vioapic;
struct kvm_pit *vpit;
diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h
index 8fba544e9cc4..f36d56bd7632 100644
--- a/arch/x86/include/uapi/asm/hyperv.h
+++ b/arch/x86/include/uapi/asm/hyperv.h
@@ -108,6 +108,8 @@
#define HV_X64_HYPERCALL_PARAMS_XMM_AVAILABLE (1 << 4)
/* Support for a virtual guest idle state is available */
#define HV_X64_GUEST_IDLE_STATE_AVAILABLE (1 << 5)
+/* Guest crash data handler available */
+#define HV_X64_GUEST_CRASH_MSR_AVAILABLE (1 << 10)
/*
* Implementation recommendations. Indicates which behaviors the hypervisor
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 28eba2d38b15..f813261d9740 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -409,12 +409,6 @@ static void __setup_vector_irq(int cpu)
int irq, vector;
struct apic_chip_data *data;
- /*
- * vector_lock will make sure that we don't run into irq vector
- * assignments that might be happening on another cpu in parallel,
- * while we setup our initial vector to irq mappings.
- */
- raw_spin_lock(&vector_lock);
/* Mark the inuse vectors */
for_each_active_irq(irq) {
data = apic_chip_data(irq_get_irq_data(irq));
@@ -436,16 +430,16 @@ static void __setup_vector_irq(int cpu)
if (!cpumask_test_cpu(cpu, data->domain))
per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
}
- raw_spin_unlock(&vector_lock);
}
/*
- * Setup the vector to irq mappings.
+ * Setup the vector to irq mappings. Must be called with vector_lock held.
*/
void setup_vector_irq(int cpu)
{
int irq;
+ lockdep_assert_held(&vector_lock);
/*
* On most of the platforms, legacy PIC delivers the interrupts on the
* boot cpu. But there are certain platforms where PIC interrupts are
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index 89427d8d4fc5..eec40f595ab9 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -175,7 +175,9 @@ static __init void early_serial_init(char *s)
}
if (*s) {
- if (kstrtoul(s, 0, &baud) < 0 || baud == 0)
+ baud = simple_strtoull(s, &e, 0);
+
+ if (baud == 0 || s == e)
baud = DEFAULT_BAUD;
}
diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c
index f5d0730e7b08..ce95676abd60 100644
--- a/arch/x86/kernel/espfix_64.c
+++ b/arch/x86/kernel/espfix_64.c
@@ -131,25 +131,24 @@ void __init init_espfix_bsp(void)
init_espfix_random();
/* The rest is the same as for any other processor */
- init_espfix_ap();
+ init_espfix_ap(0);
}
-void init_espfix_ap(void)
+void init_espfix_ap(int cpu)
{
- unsigned int cpu, page;
+ unsigned int page;
unsigned long addr;
pud_t pud, *pud_p;
pmd_t pmd, *pmd_p;
pte_t pte, *pte_p;
- int n;
+ int n, node;
void *stack_page;
pteval_t ptemask;
/* We only have to do this once... */
- if (likely(this_cpu_read(espfix_stack)))
+ if (likely(per_cpu(espfix_stack, cpu)))
return; /* Already initialized */
- cpu = smp_processor_id();
addr = espfix_base_addr(cpu);
page = cpu/ESPFIX_STACKS_PER_PAGE;
@@ -165,12 +164,15 @@ void init_espfix_ap(void)
if (stack_page)
goto unlock_done;
+ node = cpu_to_node(cpu);
ptemask = __supported_pte_mask;
pud_p = &espfix_pud_page[pud_index(addr)];
pud = *pud_p;
if (!pud_present(pud)) {
- pmd_p = (pmd_t *)__get_free_page(PGALLOC_GFP);
+ struct page *page = alloc_pages_node(node, PGALLOC_GFP, 0);
+
+ pmd_p = (pmd_t *)page_address(page);
pud = __pud(__pa(pmd_p) | (PGTABLE_PROT & ptemask));
paravirt_alloc_pmd(&init_mm, __pa(pmd_p) >> PAGE_SHIFT);
for (n = 0; n < ESPFIX_PUD_CLONES; n++)
@@ -180,7 +182,9 @@ void init_espfix_ap(void)
pmd_p = pmd_offset(&pud, addr);
pmd = *pmd_p;
if (!pmd_present(pmd)) {
- pte_p = (pte_t *)__get_free_page(PGALLOC_GFP);
+ struct page *page = alloc_pages_node(node, PGALLOC_GFP, 0);
+
+ pte_p = (pte_t *)page_address(page);
pmd = __pmd(__pa(pte_p) | (PGTABLE_PROT & ptemask));
paravirt_alloc_pte(&init_mm, __pa(pte_p) >> PAGE_SHIFT);
for (n = 0; n < ESPFIX_PMD_CLONES; n++)
@@ -188,7 +192,7 @@ void init_espfix_ap(void)
}
pte_p = pte_offset_kernel(&pmd, addr);
- stack_page = (void *)__get_free_page(GFP_KERNEL);
+ stack_page = page_address(alloc_pages_node(node, GFP_KERNEL, 0));
pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask));
for (n = 0; n < ESPFIX_PTE_CLONES; n++)
set_pte(&pte_p[n*PTE_STRIDE], pte);
@@ -199,7 +203,7 @@ void init_espfix_ap(void)
unlock_done:
mutex_unlock(&espfix_init_mutex);
done:
- this_cpu_write(espfix_stack, addr);
- this_cpu_write(espfix_waddr, (unsigned long)stack_page
- + (addr & ~PAGE_MASK));
+ per_cpu(espfix_stack, cpu) = addr;
+ per_cpu(espfix_waddr, cpu) = (unsigned long)stack_page
+ + (addr & ~PAGE_MASK);
}
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 5a4668136e98..f129a9af6357 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -161,11 +161,12 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
/* Kill off the identity-map trampoline */
reset_early_page_tables();
- kasan_map_early_shadow(early_level4_pgt);
-
- /* clear bss before set_intr_gate with early_idt_handler */
clear_bss();
+ clear_page(init_level4_pgt);
+
+ kasan_early_init();
+
for (i = 0; i < NUM_EXCEPTION_VECTORS; i++)
set_intr_gate(i, early_idt_handler_array[i]);
load_idt((const struct desc_ptr *)&idt_descr);
@@ -177,12 +178,9 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
*/
load_ucode_bsp();
- clear_page(init_level4_pgt);
/* set init_level4_pgt kernel high mapping*/
init_level4_pgt[511] = early_level4_pgt[511];
- kasan_map_early_shadow(init_level4_pgt);
-
x86_64_start_reservations(real_mode_data);
}
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index e5c27f729a38..1d40ca8a73f2 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -516,38 +516,9 @@ ENTRY(phys_base)
/* This must match the first entry in level2_kernel_pgt */
.quad 0x0000000000000000
-#ifdef CONFIG_KASAN
-#define FILL(VAL, COUNT) \
- .rept (COUNT) ; \
- .quad (VAL) ; \
- .endr
-
-NEXT_PAGE(kasan_zero_pte)
- FILL(kasan_zero_page - __START_KERNEL_map + _KERNPG_TABLE, 512)
-NEXT_PAGE(kasan_zero_pmd)
- FILL(kasan_zero_pte - __START_KERNEL_map + _KERNPG_TABLE, 512)
-NEXT_PAGE(kasan_zero_pud)
- FILL(kasan_zero_pmd - __START_KERNEL_map + _KERNPG_TABLE, 512)
-
-#undef FILL
-#endif
-
-
#include "../../x86/xen/xen-head.S"
__PAGE_ALIGNED_BSS
NEXT_PAGE(empty_zero_page)
.skip PAGE_SIZE
-#ifdef CONFIG_KASAN
-/*
- * This page used as early shadow. We don't use empty_zero_page
- * at early stages, stack instrumentation could write some garbage
- * to this page.
- * Latter we reuse it as zero shadow for large ranges of memory
- * that allowed to access, but not instrumented by kasan
- * (vmalloc/vmemmap ...).
- */
-NEXT_PAGE(kasan_zero_page)
- .skip PAGE_SIZE
-#endif
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 88b366487b0e..c7dfe1be784e 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -347,14 +347,22 @@ int check_irq_vectors_for_cpu_disable(void)
if (!desc)
continue;
+ /*
+ * Protect against concurrent action removal,
+ * affinity changes etc.
+ */
+ raw_spin_lock(&desc->lock);
data = irq_desc_get_irq_data(desc);
cpumask_copy(&affinity_new, data->affinity);
cpumask_clear_cpu(this_cpu, &affinity_new);
/* Do not count inactive or per-cpu irqs. */
- if (!irq_has_action(irq) || irqd_is_per_cpu(data))
+ if (!irq_has_action(irq) || irqd_is_per_cpu(data)) {
+ raw_spin_unlock(&desc->lock);
continue;
+ }
+ raw_spin_unlock(&desc->lock);
/*
* A single irq may be mapped to multiple
* cpu's vector_irq[] (for example IOAPIC cluster
@@ -385,6 +393,9 @@ int check_irq_vectors_for_cpu_disable(void)
* vector. If the vector is marked in the used vectors
* bitmap or an irq is assigned to it, we don't count
* it as available.
+ *
+ * As this is an inaccurate snapshot anyway, we can do
+ * this w/o holding vector_lock.
*/
for (vector = FIRST_EXTERNAL_VECTOR;
vector < first_system_vector; vector++) {
@@ -486,6 +497,11 @@ void fixup_irqs(void)
*/
mdelay(1);
+ /*
+ * We can walk the vector array of this cpu without holding
+ * vector_lock because the cpu is already marked !online, so
+ * nothing else will touch it.
+ */
for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
unsigned int irr;
@@ -497,9 +513,9 @@ void fixup_irqs(void)
irq = __this_cpu_read(vector_irq[vector]);
desc = irq_to_desc(irq);
+ raw_spin_lock(&desc->lock);
data = irq_desc_get_irq_data(desc);
chip = irq_data_get_irq_chip(data);
- raw_spin_lock(&desc->lock);
if (chip->irq_retrigger) {
chip->irq_retrigger(data);
__this_cpu_write(vector_irq[vector], VECTOR_RETRIGGERED);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 8add66b22f33..d3010aa79daf 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -171,11 +171,6 @@ static void smp_callin(void)
apic_ap_setup();
/*
- * Need to setup vector mappings before we enable interrupts.
- */
- setup_vector_irq(smp_processor_id());
-
- /*
* Save our processor parameters. Note: this information
* is needed for clock calibration.
*/
@@ -239,18 +234,13 @@ static void notrace start_secondary(void *unused)
check_tsc_sync_target();
/*
- * Enable the espfix hack for this CPU
- */
-#ifdef CONFIG_X86_ESPFIX64
- init_espfix_ap();
-#endif
-
- /*
- * We need to hold vector_lock so there the set of online cpus
- * does not change while we are assigning vectors to cpus. Holding
- * this lock ensures we don't half assign or remove an irq from a cpu.
+ * Lock vector_lock and initialize the vectors on this cpu
+ * before setting the cpu online. We must set it online with
+ * vector_lock held to prevent a concurrent setup/teardown
+ * from seeing a half valid vector space.
*/
lock_vector_lock();
+ setup_vector_irq(smp_processor_id());
set_cpu_online(smp_processor_id(), true);
unlock_vector_lock();
cpu_set_state_online(smp_processor_id());
@@ -854,6 +844,13 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
initial_code = (unsigned long)start_secondary;
stack_start = idle->thread.sp;
+ /*
+ * Enable the espfix hack for this CPU
+ */
+#ifdef CONFIG_X86_ESPFIX64
+ init_espfix_ap(cpu);
+#endif
+
/* So we see what's up */
announce_cpu(cpu, apicid);
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 505449700e0c..7437b41f6a47 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -598,10 +598,19 @@ static unsigned long quick_pit_calibrate(void)
if (!pit_expect_msb(0xff-i, &delta, &d2))
break;
+ delta -= tsc;
+
+ /*
+ * Extrapolate the error and fail fast if the error will
+ * never be below 500 ppm.
+ */
+ if (i == 1 &&
+ d1 + d2 >= (delta * MAX_QUICK_PIT_ITERATIONS) >> 11)
+ return 0;
+
/*
* Iterate until the error is less than 500 ppm
*/
- delta -= tsc;
if (d1+d2 >= delta >> 11)
continue;
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 64dd46793099..2fbea2544f24 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -98,6 +98,8 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu)
best->ebx = xstate_required_size(vcpu->arch.xcr0, true);
vcpu->arch.eager_fpu = use_eager_fpu() || guest_cpuid_has_mpx(vcpu);
+ if (vcpu->arch.eager_fpu)
+ kvm_x86_ops->fpu_activate(vcpu);
/*
* The existing code assumes virtual address is 48-bit in the canonical
diff --git a/arch/x86/kvm/iommu.c b/arch/x86/kvm/iommu.c
index 7dbced309ddb..5c520ebf6343 100644
--- a/arch/x86/kvm/iommu.c
+++ b/arch/x86/kvm/iommu.c
@@ -200,6 +200,7 @@ int kvm_assign_device(struct kvm *kvm, struct pci_dev *pdev)
goto out_unmap;
}
+ kvm_arch_start_assignment(kvm);
pci_set_dev_assigned(pdev);
dev_info(&pdev->dev, "kvm assign device\n");
@@ -224,6 +225,7 @@ int kvm_deassign_device(struct kvm *kvm, struct pci_dev *pdev)
iommu_detach_device(domain, &pdev->dev);
pci_clear_dev_assigned(pdev);
+ kvm_arch_end_assignment(kvm);
dev_info(&pdev->dev, "kvm deassign device\n");
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index f807496b62c2..44171462bd2a 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2479,6 +2479,14 @@ static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn,
return 0;
}
+static bool kvm_is_mmio_pfn(pfn_t pfn)
+{
+ if (pfn_valid(pfn))
+ return !is_zero_pfn(pfn) && PageReserved(pfn_to_page(pfn));
+
+ return true;
+}
+
static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
unsigned pte_access, int level,
gfn_t gfn, pfn_t pfn, bool speculative,
@@ -2506,7 +2514,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
spte |= PT_PAGE_SIZE_MASK;
if (tdp_enabled)
spte |= kvm_x86_ops->get_mt_mask(vcpu, gfn,
- kvm_is_reserved_pfn(pfn));
+ kvm_is_mmio_pfn(pfn));
if (host_writable)
spte |= SPTE_HOST_WRITEABLE;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 602b974a60a6..bbc678a66b18 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -865,6 +865,64 @@ static void svm_disable_lbrv(struct vcpu_svm *svm)
set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 0, 0);
}
+#define MTRR_TYPE_UC_MINUS 7
+#define MTRR2PROTVAL_INVALID 0xff
+
+static u8 mtrr2protval[8];
+
+static u8 fallback_mtrr_type(int mtrr)
+{
+ /*
+ * WT and WP aren't always available in the host PAT. Treat
+ * them as UC and UC- respectively. Everything else should be
+ * there.
+ */
+ switch (mtrr)
+ {
+ case MTRR_TYPE_WRTHROUGH:
+ return MTRR_TYPE_UNCACHABLE;
+ case MTRR_TYPE_WRPROT:
+ return MTRR_TYPE_UC_MINUS;
+ default:
+ BUG();
+ }
+}
+
+static void build_mtrr2protval(void)
+{
+ int i;
+ u64 pat;
+
+ for (i = 0; i < 8; i++)
+ mtrr2protval[i] = MTRR2PROTVAL_INVALID;
+
+ /* Ignore the invalid MTRR types. */
+ mtrr2protval[2] = 0;
+ mtrr2protval[3] = 0;
+
+ /*
+ * Use host PAT value to figure out the mapping from guest MTRR
+ * values to nested page table PAT/PCD/PWT values. We do not
+ * want to change the host PAT value every time we enter the
+ * guest.
+ */
+ rdmsrl(MSR_IA32_CR_PAT, pat);
+ for (i = 0; i < 8; i++) {
+ u8 mtrr = pat >> (8 * i);
+
+ if (mtrr2protval[mtrr] == MTRR2PROTVAL_INVALID)
+ mtrr2protval[mtrr] = __cm_idx2pte(i);
+ }
+
+ for (i = 0; i < 8; i++) {
+ if (mtrr2protval[i] == MTRR2PROTVAL_INVALID) {
+ u8 fallback = fallback_mtrr_type(i);
+ mtrr2protval[i] = mtrr2protval[fallback];
+ BUG_ON(mtrr2protval[i] == MTRR2PROTVAL_INVALID);
+ }
+ }
+}
+
static __init int svm_hardware_setup(void)
{
int cpu;
@@ -931,6 +989,7 @@ static __init int svm_hardware_setup(void)
} else
kvm_disable_tdp();
+ build_mtrr2protval();
return 0;
err:
@@ -1085,6 +1144,39 @@ static u64 svm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc)
return target_tsc - tsc;
}
+static void svm_set_guest_pat(struct vcpu_svm *svm, u64 *g_pat)
+{
+ struct kvm_vcpu *vcpu = &svm->vcpu;
+
+ /* Unlike Intel, AMD takes the guest's CR0.CD into account.
+ *
+ * AMD does not have IPAT. To emulate it for the case of guests
+ * with no assigned devices, just set everything to WB. If guests
+ * have assigned devices, however, we cannot force WB for RAM
+ * pages only, so use the guest PAT directly.
+ */
+ if (!kvm_arch_has_assigned_device(vcpu->kvm))
+ *g_pat = 0x0606060606060606;
+ else
+ *g_pat = vcpu->arch.pat;
+}
+
+static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
+{
+ u8 mtrr;
+
+ /*
+ * 1. MMIO: trust guest MTRR, so same as item 3.
+ * 2. No passthrough: always map as WB, and force guest PAT to WB as well
+ * 3. Passthrough: can't guarantee the result, try to trust guest.
+ */
+ if (!is_mmio && !kvm_arch_has_assigned_device(vcpu->kvm))
+ return 0;
+
+ mtrr = kvm_mtrr_get_guest_memory_type(vcpu, gfn);
+ return mtrr2protval[mtrr];
+}
+
static void init_vmcb(struct vcpu_svm *svm, bool init_event)
{
struct vmcb_control_area *control = &svm->vmcb->control;
@@ -1180,6 +1272,7 @@ static void init_vmcb(struct vcpu_svm *svm, bool init_event)
clr_cr_intercept(svm, INTERCEPT_CR3_READ);
clr_cr_intercept(svm, INTERCEPT_CR3_WRITE);
save->g_pat = svm->vcpu.arch.pat;
+ svm_set_guest_pat(svm, &save->g_pat);
save->cr3 = 0;
save->cr4 = 0;
}
@@ -3254,6 +3347,16 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
case MSR_VM_IGNNE:
vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data);
break;
+ case MSR_IA32_CR_PAT:
+ if (npt_enabled) {
+ if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data))
+ return 1;
+ vcpu->arch.pat = data;
+ svm_set_guest_pat(svm, &svm->vmcb->save.g_pat);
+ mark_dirty(svm->vmcb, VMCB_NPT);
+ break;
+ }
+ /* fall through */
default:
return kvm_set_msr_common(vcpu, msr);
}
@@ -4088,11 +4191,6 @@ static bool svm_has_high_real_mode_segbase(void)
return true;
}
-static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
-{
- return 0;
-}
-
static void svm_cpuid_update(struct kvm_vcpu *vcpu)
{
}
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index e856dd566f4c..5b4e9384717a 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -8632,22 +8632,17 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
u64 ipat = 0;
/* For VT-d and EPT combination
- * 1. MMIO: always map as UC
+ * 1. MMIO: guest may want to apply WC, trust it.
* 2. EPT with VT-d:
* a. VT-d without snooping control feature: can't guarantee the
- * result, try to trust guest.
+ * result, try to trust guest. So the same as item 1.
* b. VT-d with snooping control feature: snooping control feature of
* VT-d engine can guarantee the cache correctness. Just set it
* to WB to keep consistent with host. So the same as item 3.
* 3. EPT without VT-d: always map as WB and set IPAT=1 to keep
* consistent with host MTRR
*/
- if (is_mmio) {
- cache = MTRR_TYPE_UNCACHABLE;
- goto exit;
- }
-
- if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) {
+ if (!is_mmio && !kvm_arch_has_noncoherent_dma(vcpu->kvm)) {
ipat = VMX_EPT_IPAT_BIT;
cache = MTRR_TYPE_WRBACK;
goto exit;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index bbaf44e8f0d3..5ef2560075bf 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3157,8 +3157,7 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src)
cpuid_count(XSTATE_CPUID, index,
&size, &offset, &ecx, &edx);
memcpy(dest, src + offset, size);
- } else
- WARN_ON_ONCE(1);
+ }
valid -= feature;
}
@@ -7315,11 +7314,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
vcpu = kvm_x86_ops->vcpu_create(kvm, id);
- /*
- * Activate fpu unconditionally in case the guest needs eager FPU. It will be
- * deactivated soon if it doesn't.
- */
- kvm_x86_ops->fpu_activate(vcpu);
return vcpu;
}
@@ -8218,6 +8212,24 @@ bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu)
kvm_x86_ops->interrupt_allowed(vcpu);
}
+void kvm_arch_start_assignment(struct kvm *kvm)
+{
+ atomic_inc(&kvm->arch.assigned_device_count);
+}
+EXPORT_SYMBOL_GPL(kvm_arch_start_assignment);
+
+void kvm_arch_end_assignment(struct kvm *kvm)
+{
+ atomic_dec(&kvm->arch.assigned_device_count);
+}
+EXPORT_SYMBOL_GPL(kvm_arch_end_assignment);
+
+bool kvm_arch_has_assigned_device(struct kvm *kvm)
+{
+ return atomic_read(&kvm->arch.assigned_device_count);
+}
+EXPORT_SYMBOL_GPL(kvm_arch_has_assigned_device);
+
void kvm_arch_register_noncoherent_dma(struct kvm *kvm)
{
atomic_inc(&kvm->arch.noncoherent_dma_count);
diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c
index ddf9ecb53cc3..e342586db6e4 100644
--- a/arch/x86/lib/usercopy.c
+++ b/arch/x86/lib/usercopy.c
@@ -20,7 +20,7 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
unsigned long ret;
if (__range_not_ok(from, n, TASK_SIZE))
- return 0;
+ return n;
/*
* Even though this function is typically called from NMI/IRQ context
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index 4860906c6b9f..e1840f3db5b5 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -1,3 +1,4 @@
+#define pr_fmt(fmt) "kasan: " fmt
#include <linux/bootmem.h>
#include <linux/kasan.h>
#include <linux/kdebug.h>
@@ -11,7 +12,19 @@
extern pgd_t early_level4_pgt[PTRS_PER_PGD];
extern struct range pfn_mapped[E820_X_MAX];
-extern unsigned char kasan_zero_page[PAGE_SIZE];
+static pud_t kasan_zero_pud[PTRS_PER_PUD] __page_aligned_bss;
+static pmd_t kasan_zero_pmd[PTRS_PER_PMD] __page_aligned_bss;
+static pte_t kasan_zero_pte[PTRS_PER_PTE] __page_aligned_bss;
+
+/*
+ * This page used as early shadow. We don't use empty_zero_page
+ * at early stages, stack instrumentation could write some garbage
+ * to this page.
+ * Latter we reuse it as zero shadow for large ranges of memory
+ * that allowed to access, but not instrumented by kasan
+ * (vmalloc/vmemmap ...).
+ */
+static unsigned char kasan_zero_page[PAGE_SIZE] __page_aligned_bss;
static int __init map_range(struct range *range)
{
@@ -36,7 +49,7 @@ static void __init clear_pgds(unsigned long start,
pgd_clear(pgd_offset_k(start));
}
-void __init kasan_map_early_shadow(pgd_t *pgd)
+static void __init kasan_map_early_shadow(pgd_t *pgd)
{
int i;
unsigned long start = KASAN_SHADOW_START;
@@ -73,7 +86,7 @@ static int __init zero_pmd_populate(pud_t *pud, unsigned long addr,
while (IS_ALIGNED(addr, PMD_SIZE) && addr + PMD_SIZE <= end) {
WARN_ON(!pmd_none(*pmd));
set_pmd(pmd, __pmd(__pa_nodebug(kasan_zero_pte)
- | __PAGE_KERNEL_RO));
+ | _KERNPG_TABLE));
addr += PMD_SIZE;
pmd = pmd_offset(pud, addr);
}
@@ -99,7 +112,7 @@ static int __init zero_pud_populate(pgd_t *pgd, unsigned long addr,
while (IS_ALIGNED(addr, PUD_SIZE) && addr + PUD_SIZE <= end) {
WARN_ON(!pud_none(*pud));
set_pud(pud, __pud(__pa_nodebug(kasan_zero_pmd)
- | __PAGE_KERNEL_RO));
+ | _KERNPG_TABLE));
addr += PUD_SIZE;
pud = pud_offset(pgd, addr);
}
@@ -124,7 +137,7 @@ static int __init zero_pgd_populate(unsigned long addr, unsigned long end)
while (IS_ALIGNED(addr, PGDIR_SIZE) && addr + PGDIR_SIZE <= end) {
WARN_ON(!pgd_none(*pgd));
set_pgd(pgd, __pgd(__pa_nodebug(kasan_zero_pud)
- | __PAGE_KERNEL_RO));
+ | _KERNPG_TABLE));
addr += PGDIR_SIZE;
pgd = pgd_offset_k(addr);
}
@@ -166,6 +179,26 @@ static struct notifier_block kasan_die_notifier = {
};
#endif
+void __init kasan_early_init(void)
+{
+ int i;
+ pteval_t pte_val = __pa_nodebug(kasan_zero_page) | __PAGE_KERNEL;
+ pmdval_t pmd_val = __pa_nodebug(kasan_zero_pte) | _KERNPG_TABLE;
+ pudval_t pud_val = __pa_nodebug(kasan_zero_pmd) | _KERNPG_TABLE;
+
+ for (i = 0; i < PTRS_PER_PTE; i++)
+ kasan_zero_pte[i] = __pte(pte_val);
+
+ for (i = 0; i < PTRS_PER_PMD; i++)
+ kasan_zero_pmd[i] = __pmd(pmd_val);
+
+ for (i = 0; i < PTRS_PER_PUD; i++)
+ kasan_zero_pud[i] = __pud(pud_val);
+
+ kasan_map_early_shadow(early_level4_pgt);
+ kasan_map_early_shadow(init_level4_pgt);
+}
+
void __init kasan_init(void)
{
int i;
@@ -176,6 +209,7 @@ void __init kasan_init(void)
memcpy(early_level4_pgt, init_level4_pgt, sizeof(early_level4_pgt));
load_cr3(early_level4_pgt);
+ __flush_tlb_all();
clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END);
@@ -202,5 +236,8 @@ void __init kasan_init(void)
memset(kasan_zero_page, 0, PAGE_SIZE);
load_cr3(init_level4_pgt);
+ __flush_tlb_all();
init_task.kasan_depth = 0;
+
+ pr_info("Kernel address sanitizer initialized\n");
}
generated by cgit v1.2.3 (git 2.39.1) at 2025-02-02 23:59:12 +0100