summaryrefslogtreecommitdiffstats
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/hyperv/mmu.c8
-rw-r--r--arch/x86/include/asm/bootparam_utils.h1
-rw-r--r--arch/x86/include/asm/efi.h5
-rw-r--r--arch/x86/include/asm/error-injection.h13
-rw-r--r--arch/x86/include/asm/iommu.h1
-rw-r--r--arch/x86/include/asm/kvm_host.h2
-rw-r--r--arch/x86/include/asm/qspinlock.h15
-rw-r--r--arch/x86/include/asm/uaccess.h4
-rw-r--r--arch/x86/include/asm/uv/uv.h4
-rw-r--r--arch/x86/kernel/amd_nb.c3
-rw-r--r--arch/x86/kernel/apic/apic.c8
-rw-r--r--arch/x86/kernel/cpu/mce/severity.c4
-rw-r--r--arch/x86/kernel/pci-dma.c20
-rw-r--r--arch/x86/kvm/mmu.c101
-rw-r--r--arch/x86/kvm/vmx/nested.c4
-rw-r--r--arch/x86/kvm/x86.c7
-rw-r--r--arch/x86/mm/ioremap.c1
-rw-r--r--arch/x86/pci/mmconfig-shared.c5
-rw-r--r--arch/x86/platform/efi/efi.c39
-rw-r--r--arch/x86/platform/uv/bios_uv.c10
-rw-r--r--arch/x86/purgatory/Makefile35
21 files changed, 222 insertions, 68 deletions
diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c
index e65d7fe6489f..5208ba49c89a 100644
--- a/arch/x86/hyperv/mmu.c
+++ b/arch/x86/hyperv/mmu.c
@@ -37,12 +37,14 @@ static inline int fill_gva_list(u64 gva_list[], int offset,
* Lower 12 bits encode the number of additional
* pages to flush (in addition to the 'cur' page).
*/
- if (diff >= HV_TLB_FLUSH_UNIT)
+ if (diff >= HV_TLB_FLUSH_UNIT) {
gva_list[gva_n] |= ~PAGE_MASK;
- else if (diff)
+ cur += HV_TLB_FLUSH_UNIT;
+ } else if (diff) {
gva_list[gva_n] |= (diff - 1) >> PAGE_SHIFT;
+ cur = end;
+ }
- cur += HV_TLB_FLUSH_UNIT;
gva_n++;
} while (cur < end);
diff --git a/arch/x86/include/asm/bootparam_utils.h b/arch/x86/include/asm/bootparam_utils.h
index 9e5f3c722c33..981fe923a59f 100644
--- a/arch/x86/include/asm/bootparam_utils.h
+++ b/arch/x86/include/asm/bootparam_utils.h
@@ -70,6 +70,7 @@ static void sanitize_boot_params(struct boot_params *boot_params)
BOOT_PARAM_PRESERVE(eddbuf_entries),
BOOT_PARAM_PRESERVE(edd_mbr_sig_buf_entries),
BOOT_PARAM_PRESERVE(edd_mbr_sig_buffer),
+ BOOT_PARAM_PRESERVE(secure_boot),
BOOT_PARAM_PRESERVE(hdr),
BOOT_PARAM_PRESERVE(e820_table),
BOOT_PARAM_PRESERVE(eddbuf),
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 606a4b6a9812..43a82e59c59d 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -242,6 +242,7 @@ static inline bool efi_is_64bit(void)
__efi_early()->runtime_services), __VA_ARGS__)
extern bool efi_reboot_required(void);
+extern bool efi_is_table_address(unsigned long phys_addr);
#else
static inline void parse_efi_setup(u64 phys_addr, u32 data_len) {}
@@ -249,6 +250,10 @@ static inline bool efi_reboot_required(void)
{
return false;
}
+static inline bool efi_is_table_address(unsigned long phys_addr)
+{
+ return false;
+}
#endif /* CONFIG_EFI */
#endif /* _ASM_X86_EFI_H */
diff --git a/arch/x86/include/asm/error-injection.h b/arch/x86/include/asm/error-injection.h
deleted file mode 100644
index 47b7a1296245..000000000000
--- a/arch/x86/include/asm/error-injection.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_ERROR_INJECTION_H
-#define _ASM_ERROR_INJECTION_H
-
-#include <linux/compiler.h>
-#include <linux/linkage.h>
-#include <asm/ptrace.h>
-#include <asm-generic/error-injection.h>
-
-asmlinkage void just_return_func(void);
-void override_function_with_return(struct pt_regs *regs);
-
-#endif /* _ASM_ERROR_INJECTION_H */
diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h
index baedab8ac538..b91623d521d9 100644
--- a/arch/x86/include/asm/iommu.h
+++ b/arch/x86/include/asm/iommu.h
@@ -4,7 +4,6 @@
extern int force_iommu, no_iommu;
extern int iommu_detected;
-extern int iommu_pass_through;
/* 10 seconds */
#define DMAR_OPERATION_TIMEOUT ((cycles_t) tsc_khz*10*1000)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 74e88e5edd9c..bdc16b0aa7c6 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -335,6 +335,7 @@ struct kvm_mmu_page {
int root_count; /* Currently serving as active root */
unsigned int unsync_children;
struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */
+ unsigned long mmu_valid_gen;
DECLARE_BITMAP(unsync_child_bitmap, 512);
#ifdef CONFIG_X86_32
@@ -856,6 +857,7 @@ struct kvm_arch {
unsigned long n_requested_mmu_pages;
unsigned long n_max_mmu_pages;
unsigned int indirect_shadow_pages;
+ unsigned long mmu_valid_gen;
struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
/*
* Hash table of struct kvm_mmu_page.
diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h
index bd5ac6cc37db..444d6fd9a6d8 100644
--- a/arch/x86/include/asm/qspinlock.h
+++ b/arch/x86/include/asm/qspinlock.h
@@ -63,10 +63,25 @@ static inline bool vcpu_is_preempted(long cpu)
#endif
#ifdef CONFIG_PARAVIRT
+/*
+ * virt_spin_lock_key - enables (by default) the virt_spin_lock() hijack.
+ *
+ * Native (and PV wanting native due to vCPU pinning) should disable this key.
+ * It is done in this backwards fashion to only have a single direction change,
+ * which removes ordering between native_pv_spin_init() and HV setup.
+ */
DECLARE_STATIC_KEY_TRUE(virt_spin_lock_key);
void native_pv_lock_init(void) __init;
+/*
+ * Shortcut for the queued_spin_lock_slowpath() function that allows
+ * virt to hijack it.
+ *
+ * Returns:
+ * true - lock has been negotiated, all done;
+ * false - queued_spin_lock_slowpath() will do its thing.
+ */
#define virt_spin_lock virt_spin_lock
static inline bool virt_spin_lock(struct qspinlock *lock)
{
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 9c4435307ff8..35c225ede0e4 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -444,8 +444,10 @@ __pu_label: \
({ \
int __gu_err; \
__inttype(*(ptr)) __gu_val; \
+ __typeof__(ptr) __gu_ptr = (ptr); \
+ __typeof__(size) __gu_size = (size); \
__uaccess_begin_nospec(); \
- __get_user_size(__gu_val, (ptr), (size), __gu_err, -EFAULT); \
+ __get_user_size(__gu_val, __gu_ptr, __gu_size, __gu_err, -EFAULT); \
__uaccess_end(); \
(x) = (__force __typeof__(*(ptr)))__gu_val; \
__builtin_expect(__gu_err, 0); \
diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h
index e60c45fd3679..6bc6d89d8e2a 100644
--- a/arch/x86/include/asm/uv/uv.h
+++ b/arch/x86/include/asm/uv/uv.h
@@ -12,10 +12,12 @@ struct mm_struct;
#ifdef CONFIG_X86_UV
#include <linux/efi.h>
+extern unsigned long uv_systab_phys;
+
extern enum uv_system_type get_uv_system_type(void);
static inline bool is_early_uv_system(void)
{
- return !((efi.uv_systab == EFI_INVALID_TABLE_ADDR) || !efi.uv_systab);
+ return uv_systab_phys && uv_systab_phys != EFI_INVALID_TABLE_ADDR;
}
extern int is_uv_system(void);
extern int is_uv_hubless(void);
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index d63e63b7d1d9..251c795b4eb3 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -21,6 +21,7 @@
#define PCI_DEVICE_ID_AMD_17H_DF_F4 0x1464
#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4 0x15ec
#define PCI_DEVICE_ID_AMD_17H_M30H_DF_F4 0x1494
+#define PCI_DEVICE_ID_AMD_17H_M70H_DF_F4 0x1444
/* Protect the PCI config register pairs used for SMN and DF indirect access. */
static DEFINE_MUTEX(smn_mutex);
@@ -50,6 +51,7 @@ const struct pci_device_id amd_nb_misc_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F3) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F3) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F3) },
{}
};
EXPORT_SYMBOL_GPL(amd_nb_misc_ids);
@@ -63,6 +65,7 @@ static const struct pci_device_id amd_nb_link_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F4) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) },
{}
};
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index dba2828b779a..08fb79f37793 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -834,6 +834,10 @@ bool __init apic_needs_pit(void)
if (!boot_cpu_has(X86_FEATURE_APIC))
return true;
+ /* Virt guests may lack ARAT, but still have DEADLINE */
+ if (!boot_cpu_has(X86_FEATURE_ARAT))
+ return true;
+
/* Deadline timer is based on TSC so no further PIT action required */
if (boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER))
return false;
@@ -1179,10 +1183,6 @@ void clear_local_APIC(void)
apic_write(APIC_LVT0, v | APIC_LVT_MASKED);
v = apic_read(APIC_LVT1);
apic_write(APIC_LVT1, v | APIC_LVT_MASKED);
- if (!x2apic_enabled()) {
- v = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
- apic_write(APIC_LDR, v);
- }
if (maxlvt >= 4) {
v = apic_read(APIC_LVTPC);
apic_write(APIC_LVTPC, v | APIC_LVT_MASKED);
diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c
index 210f1f5db5f7..87bcdc6dc2f0 100644
--- a/arch/x86/kernel/cpu/mce/severity.c
+++ b/arch/x86/kernel/cpu/mce/severity.c
@@ -107,11 +107,11 @@ static struct severity {
*/
MCESEV(
AO, "Action optional: memory scrubbing error",
- SER, MASK(MCI_STATUS_OVER|MCI_UC_AR|MCACOD_SCRUBMSK, MCI_STATUS_UC|MCACOD_SCRUB)
+ SER, MASK(MCI_UC_AR|MCACOD_SCRUBMSK, MCI_STATUS_UC|MCACOD_SCRUB)
),
MCESEV(
AO, "Action optional: last level cache writeback error",
- SER, MASK(MCI_STATUS_OVER|MCI_UC_AR|MCACOD, MCI_STATUS_UC|MCACOD_L3WB)
+ SER, MASK(MCI_UC_AR|MCACOD, MCI_STATUS_UC|MCACOD_L3WB)
),
/* ignore OVER for UCNA */
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index f62b498b18fb..fa4352dce491 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/dma-direct.h>
#include <linux/dma-debug.h>
+#include <linux/iommu.h>
#include <linux/dmar.h>
#include <linux/export.h>
#include <linux/memblock.h>
@@ -34,21 +35,6 @@ int no_iommu __read_mostly;
/* Set this to 1 if there is a HW IOMMU in the system */
int iommu_detected __read_mostly = 0;
-/*
- * This variable becomes 1 if iommu=pt is passed on the kernel command line.
- * If this variable is 1, IOMMU implementations do no DMA translation for
- * devices and allow every device to access to whole physical memory. This is
- * useful if a user wants to use an IOMMU only for KVM device assignment to
- * guests and not for driver dma translation.
- * It is also possible to disable by default in kernel config, and enable with
- * iommu=nopt at boot time.
- */
-#ifdef CONFIG_IOMMU_DEFAULT_PASSTHROUGH
-int iommu_pass_through __read_mostly = 1;
-#else
-int iommu_pass_through __read_mostly;
-#endif
-
extern struct iommu_table_entry __iommu_table[], __iommu_table_end[];
void __init pci_iommu_alloc(void)
@@ -120,9 +106,9 @@ static __init int iommu_setup(char *p)
swiotlb = 1;
#endif
if (!strncmp(p, "pt", 2))
- iommu_pass_through = 1;
+ iommu_set_default_passthrough(true);
if (!strncmp(p, "nopt", 4))
- iommu_pass_through = 0;
+ iommu_set_default_translated(true);
gart_parse_options(p);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 218b277bfda3..a63964e7cec7 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2095,6 +2095,12 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, int direct
if (!direct)
sp->gfns = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache);
set_page_private(virt_to_page(sp->spt), (unsigned long)sp);
+
+ /*
+ * active_mmu_pages must be a FIFO list, as kvm_zap_obsolete_pages()
+ * depends on valid pages being added to the head of the list. See
+ * comments in kvm_zap_obsolete_pages().
+ */
list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages);
kvm_mod_used_mmu_pages(vcpu->kvm, +1);
return sp;
@@ -2244,7 +2250,7 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm,
#define for_each_valid_sp(_kvm, _sp, _gfn) \
hlist_for_each_entry(_sp, \
&(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)], hash_link) \
- if ((_sp)->role.invalid) { \
+ if (is_obsolete_sp((_kvm), (_sp)) || (_sp)->role.invalid) { \
} else
#define for_each_gfn_indirect_valid_sp(_kvm, _sp, _gfn) \
@@ -2301,6 +2307,11 @@ static void kvm_mmu_audit(struct kvm_vcpu *vcpu, int point) { }
static void mmu_audit_disable(void) { }
#endif
+static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+ return unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen);
+}
+
static bool kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
struct list_head *invalid_list)
{
@@ -2525,6 +2536,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
if (level > PT_PAGE_TABLE_LEVEL && need_sync)
flush |= kvm_sync_pages(vcpu, gfn, &invalid_list);
}
+ sp->mmu_valid_gen = vcpu->kvm->arch.mmu_valid_gen;
clear_page(sp->spt);
trace_kvm_mmu_get_page(sp, true);
@@ -4233,6 +4245,13 @@ static bool fast_cr3_switch(struct kvm_vcpu *vcpu, gpa_t new_cr3,
return false;
if (cached_root_available(vcpu, new_cr3, new_role)) {
+ /*
+ * It is possible that the cached previous root page is
+ * obsolete because of a change in the MMU generation
+ * number. However, changing the generation number is
+ * accompanied by KVM_REQ_MMU_RELOAD, which will free
+ * the root set here and allocate a new one.
+ */
kvm_make_request(KVM_REQ_LOAD_CR3, vcpu);
if (!skip_tlb_flush) {
kvm_make_request(KVM_REQ_MMU_SYNC, vcpu);
@@ -5649,11 +5668,89 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu)
return alloc_mmu_pages(vcpu);
}
+
+static void kvm_zap_obsolete_pages(struct kvm *kvm)
+{
+ struct kvm_mmu_page *sp, *node;
+ LIST_HEAD(invalid_list);
+ int ign;
+
+restart:
+ list_for_each_entry_safe_reverse(sp, node,
+ &kvm->arch.active_mmu_pages, link) {
+ /*
+ * No obsolete valid page exists before a newly created page
+ * since active_mmu_pages is a FIFO list.
+ */
+ if (!is_obsolete_sp(kvm, sp))
+ break;
+
+ /*
+ * Do not repeatedly zap a root page to avoid unnecessary
+ * KVM_REQ_MMU_RELOAD, otherwise we may not be able to
+ * progress:
+ * vcpu 0 vcpu 1
+ * call vcpu_enter_guest():
+ * 1): handle KVM_REQ_MMU_RELOAD
+ * and require mmu-lock to
+ * load mmu
+ * repeat:
+ * 1): zap root page and
+ * send KVM_REQ_MMU_RELOAD
+ *
+ * 2): if (cond_resched_lock(mmu-lock))
+ *
+ * 2): hold mmu-lock and load mmu
+ *
+ * 3): see KVM_REQ_MMU_RELOAD bit
+ * on vcpu->requests is set
+ * then return 1 to call
+ * vcpu_enter_guest() again.
+ * goto repeat;
+ *
+ * Since we are reversely walking the list and the invalid
+ * list will be moved to the head, skip the invalid page
+ * can help us to avoid the infinity list walking.
+ */
+ if (sp->role.invalid)
+ continue;
+
+ if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
+ kvm_mmu_commit_zap_page(kvm, &invalid_list);
+ cond_resched_lock(&kvm->mmu_lock);
+ goto restart;
+ }
+
+ if (__kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list, &ign))
+ goto restart;
+ }
+
+ kvm_mmu_commit_zap_page(kvm, &invalid_list);
+}
+
+/*
+ * Fast invalidate all shadow pages and use lock-break technique
+ * to zap obsolete pages.
+ *
+ * It's required when memslot is being deleted or VM is being
+ * destroyed, in these cases, we should ensure that KVM MMU does
+ * not use any resource of the being-deleted slot or all slots
+ * after calling the function.
+ */
+static void kvm_mmu_zap_all_fast(struct kvm *kvm)
+{
+ spin_lock(&kvm->mmu_lock);
+ kvm->arch.mmu_valid_gen++;
+
+ kvm_zap_obsolete_pages(kvm);
+ spin_unlock(&kvm->mmu_lock);
+}
+
static void kvm_mmu_invalidate_zap_pages_in_memslot(struct kvm *kvm,
struct kvm_memory_slot *slot,
struct kvm_page_track_notifier_node *node)
{
- kvm_mmu_zap_all(kvm);
+ kvm_mmu_zap_all_fast(kvm);
}
void kvm_mmu_init_vm(struct kvm *kvm)
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index ced9fba32598..a3cba321b5c5 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -4540,6 +4540,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu)
int len;
gva_t gva = 0;
struct vmcs12 *vmcs12;
+ struct x86_exception e;
short offset;
if (!nested_vmx_check_permission(vcpu))
@@ -4588,7 +4589,8 @@ static int handle_vmread(struct kvm_vcpu *vcpu)
vmx_instruction_info, true, len, &gva))
return 1;
/* _system ok, nested_vmx_check_permission has verified cpl=0 */
- kvm_write_guest_virt_system(vcpu, gva, &field_value, len, NULL);
+ if (kvm_write_guest_virt_system(vcpu, gva, &field_value, len, &e))
+ kvm_inject_page_fault(vcpu, &e);
}
return nested_vmx_succeed(vcpu);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 290c3c3efb87..91602d310a3f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5312,6 +5312,13 @@ int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu, gva_t addr, void *val,
/* kvm_write_guest_virt_system can pull in tons of pages. */
vcpu->arch.l1tf_flush_l1d = true;
+ /*
+ * FIXME: this should call handle_emulation_failure if X86EMUL_IO_NEEDED
+ * is returned, but our callers are not ready for that and they blindly
+ * call kvm_inject_page_fault. Ensure that they at least do not leak
+ * uninitialized kernel stack memory into cr2 and error code.
+ */
+ memset(exception, 0, sizeof(*exception));
return kvm_write_guest_virt_helper(addr, val, bytes, vcpu,
PFERR_WRITE_MASK, exception);
}
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 63e99f15d7cf..a39dcdb5ae34 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -19,6 +19,7 @@
#include <asm/set_memory.h>
#include <asm/e820/api.h>
+#include <asm/efi.h>
#include <asm/fixmap.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index 7389db538c30..6fa42e9c4e6f 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -29,6 +29,7 @@
static bool pci_mmcfg_running_state;
static bool pci_mmcfg_arch_init_failed;
static DEFINE_MUTEX(pci_mmcfg_lock);
+#define pci_mmcfg_lock_held() lock_is_held(&(pci_mmcfg_lock).dep_map)
LIST_HEAD(pci_mmcfg_list);
@@ -54,7 +55,7 @@ static void list_add_sorted(struct pci_mmcfg_region *new)
struct pci_mmcfg_region *cfg;
/* keep list sorted by segment and starting bus number */
- list_for_each_entry_rcu(cfg, &pci_mmcfg_list, list) {
+ list_for_each_entry_rcu(cfg, &pci_mmcfg_list, list, pci_mmcfg_lock_held()) {
if (cfg->segment > new->segment ||
(cfg->segment == new->segment &&
cfg->start_bus >= new->start_bus)) {
@@ -118,7 +119,7 @@ struct pci_mmcfg_region *pci_mmconfig_lookup(int segment, int bus)
{
struct pci_mmcfg_region *cfg;
- list_for_each_entry_rcu(cfg, &pci_mmcfg_list, list)
+ list_for_each_entry_rcu(cfg, &pci_mmcfg_list, list, pci_mmcfg_lock_held())
if (cfg->segment == segment &&
cfg->start_bus <= bus && bus <= cfg->end_bus)
return cfg;
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index a7189a3b4d70..c202e1b07e29 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -59,11 +59,34 @@ static efi_system_table_t efi_systab __initdata;
static efi_config_table_type_t arch_tables[] __initdata = {
#ifdef CONFIG_X86_UV
- {UV_SYSTEM_TABLE_GUID, "UVsystab", &efi.uv_systab},
+ {UV_SYSTEM_TABLE_GUID, "UVsystab", &uv_systab_phys},
#endif
{NULL_GUID, NULL, NULL},
};
+static const unsigned long * const efi_tables[] = {
+ &efi.mps,
+ &efi.acpi,
+ &efi.acpi20,
+ &efi.smbios,
+ &efi.smbios3,
+ &efi.boot_info,
+ &efi.hcdp,
+ &efi.uga,
+#ifdef CONFIG_X86_UV
+ &uv_systab_phys,
+#endif
+ &efi.fw_vendor,
+ &efi.runtime,
+ &efi.config_table,
+ &efi.esrt,
+ &efi.properties_table,
+ &efi.mem_attr_table,
+#ifdef CONFIG_EFI_RCI2_TABLE
+ &rci2_table_phys,
+#endif
+};
+
u64 efi_setup; /* efi setup_data physical address */
static int add_efi_memmap __initdata;
@@ -1049,3 +1072,17 @@ static int __init arch_parse_efi_cmdline(char *str)
return 0;
}
early_param("efi", arch_parse_efi_cmdline);
+
+bool efi_is_table_address(unsigned long phys_addr)
+{
+ unsigned int i;
+
+ if (phys_addr == EFI_INVALID_TABLE_ADDR)
+ return false;
+
+ for (i = 0; i < ARRAY_SIZE(efi_tables); i++)
+ if (*(efi_tables[i]) == phys_addr)
+ return true;
+
+ return false;
+}
diff --git a/arch/x86/platform/uv/bios_uv.c b/arch/x86/platform/uv/bios_uv.c
index 7c69652ffeea..c2ee31953372 100644
--- a/arch/x86/platform/uv/bios_uv.c
+++ b/arch/x86/platform/uv/bios_uv.c
@@ -14,6 +14,8 @@
#include <asm/uv/bios.h>
#include <asm/uv/uv_hub.h>
+unsigned long uv_systab_phys __ro_after_init = EFI_INVALID_TABLE_ADDR;
+
struct uv_systab *uv_systab;
static s64 __uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3,
@@ -185,13 +187,13 @@ EXPORT_SYMBOL_GPL(uv_bios_set_legacy_vga_target);
void uv_bios_init(void)
{
uv_systab = NULL;
- if ((efi.uv_systab == EFI_INVALID_TABLE_ADDR) ||
- !efi.uv_systab || efi_runtime_disabled()) {
+ if ((uv_systab_phys == EFI_INVALID_TABLE_ADDR) ||
+ !uv_systab_phys || efi_runtime_disabled()) {
pr_crit("UV: UVsystab: missing\n");
return;
}
- uv_systab = ioremap(efi.uv_systab, sizeof(struct uv_systab));
+ uv_systab = ioremap(uv_systab_phys, sizeof(struct uv_systab));
if (!uv_systab || strncmp(uv_systab->signature, UV_SYSTAB_SIG, 4)) {
pr_err("UV: UVsystab: bad signature!\n");
iounmap(uv_systab);
@@ -203,7 +205,7 @@ void uv_bios_init(void)
int size = uv_systab->size;
iounmap(uv_systab);
- uv_systab = ioremap(efi.uv_systab, size);
+ uv_systab = ioremap(uv_systab_phys, size);
if (!uv_systab) {
pr_err("UV: UVsystab: ioremap(%d) failed!\n", size);
return;
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index 8901a1f89cf5..10fb42da0007 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -18,37 +18,40 @@ targets += purgatory.ro
KASAN_SANITIZE := n
KCOV_INSTRUMENT := n
+# These are adjustments to the compiler flags used for objects that
+# make up the standalone purgatory.ro
+
+PURGATORY_CFLAGS_REMOVE := -mcmodel=kernel
+PURGATORY_CFLAGS := -mcmodel=large -ffreestanding -fno-zero-initialized-in-bss
+
# Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That
# in turn leaves some undefined symbols like __fentry__ in purgatory and not
# sure how to relocate those.
ifdef CONFIG_FUNCTION_TRACER
-CFLAGS_REMOVE_sha256.o += $(CC_FLAGS_FTRACE)
-CFLAGS_REMOVE_purgatory.o += $(CC_FLAGS_FTRACE)
-CFLAGS_REMOVE_string.o += $(CC_FLAGS_FTRACE)
-CFLAGS_REMOVE_kexec-purgatory.o += $(CC_FLAGS_FTRACE)
+PURGATORY_CFLAGS_REMOVE += $(CC_FLAGS_FTRACE)
endif
ifdef CONFIG_STACKPROTECTOR
-CFLAGS_REMOVE_sha256.o += -fstack-protector
-CFLAGS_REMOVE_purgatory.o += -fstack-protector
-CFLAGS_REMOVE_string.o += -fstack-protector
-CFLAGS_REMOVE_kexec-purgatory.o += -fstack-protector
+PURGATORY_CFLAGS_REMOVE += -fstack-protector
endif
ifdef CONFIG_STACKPROTECTOR_STRONG
-CFLAGS_REMOVE_sha256.o += -fstack-protector-strong
-CFLAGS_REMOVE_purgatory.o += -fstack-protector-strong
-CFLAGS_REMOVE_string.o += -fstack-protector-strong
-CFLAGS_REMOVE_kexec-purgatory.o += -fstack-protector-strong
+PURGATORY_CFLAGS_REMOVE += -fstack-protector-strong
endif
ifdef CONFIG_RETPOLINE
-CFLAGS_REMOVE_sha256.o += $(RETPOLINE_CFLAGS)
-CFLAGS_REMOVE_purgatory.o += $(RETPOLINE_CFLAGS)
-CFLAGS_REMOVE_string.o += $(RETPOLINE_CFLAGS)
-CFLAGS_REMOVE_kexec-purgatory.o += $(RETPOLINE_CFLAGS)
+PURGATORY_CFLAGS_REMOVE += $(RETPOLINE_CFLAGS)
endif
+CFLAGS_REMOVE_purgatory.o += $(PURGATORY_CFLAGS_REMOVE)
+CFLAGS_purgatory.o += $(PURGATORY_CFLAGS)
+
+CFLAGS_REMOVE_sha256.o += $(PURGATORY_CFLAGS_REMOVE)
+CFLAGS_sha256.o += $(PURGATORY_CFLAGS)
+
+CFLAGS_REMOVE_string.o += $(PURGATORY_CFLAGS_REMOVE)
+CFLAGS_string.o += $(PURGATORY_CFLAGS)
+
$(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE
$(call if_changed,ld)
generated by cgit v1.2.3 (git 2.39.1) at 2025-01-31 08:33:52 +0100