aboutsummaryrefslogtreecommitdiffstats
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/arm/mach-ep93xx/edb93xx.c2
-rw-r--r--arch/arm/mach-ep93xx/simone.c2
-rw-r--r--arch/arm/mach-ep93xx/ts72xx.c4
-rw-r--r--arch/arm/mach-ep93xx/vision_ep9307.c2
-rw-r--r--arch/arm64/boot/dts/renesas/hihope-common.dtsi1
-rw-r--r--arch/arm64/boot/dts/renesas/r8a77995-draak.dts6
-rw-r--r--arch/powerpc/kernel/process.c21
-rw-r--r--arch/powerpc/mm/nohash/tlb.c1
-rw-r--r--arch/riscv/include/asm/image.h12
-rw-r--r--arch/riscv/kernel/head.S4
-rw-r--r--arch/s390/kvm/interrupt.c10
-rw-r--r--arch/s390/kvm/kvm-s390.c4
-rw-r--r--arch/sparc/kernel/sys_sparc_64.c33
-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/kvm_host.h2
-rw-r--r--arch/x86/include/asm/uaccess.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/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/purgatory/Makefile35
24 files changed, 200 insertions, 79 deletions
diff --git a/arch/arm/mach-ep93xx/edb93xx.c b/arch/arm/mach-ep93xx/edb93xx.c
index 1f0da76a39de..7b7280c21ee0 100644
--- a/arch/arm/mach-ep93xx/edb93xx.c
+++ b/arch/arm/mach-ep93xx/edb93xx.c
@@ -103,7 +103,7 @@ static struct spi_board_info edb93xx_spi_board_info[] __initdata = {
};
static struct gpiod_lookup_table edb93xx_spi_cs_gpio_table = {
- .dev_id = "ep93xx-spi.0",
+ .dev_id = "spi0",
.table = {
GPIO_LOOKUP("A", 6, "cs", GPIO_ACTIVE_LOW),
{ },
diff --git a/arch/arm/mach-ep93xx/simone.c b/arch/arm/mach-ep93xx/simone.c
index e2658e22bba1..8a53b74dc4b2 100644
--- a/arch/arm/mach-ep93xx/simone.c
+++ b/arch/arm/mach-ep93xx/simone.c
@@ -73,7 +73,7 @@ static struct spi_board_info simone_spi_devices[] __initdata = {
* v1.3 parts will still work, since the signal on SFRMOUT is automatic.
*/
static struct gpiod_lookup_table simone_spi_cs_gpio_table = {
- .dev_id = "ep93xx-spi.0",
+ .dev_id = "spi0",
.table = {
GPIO_LOOKUP("A", 1, "cs", GPIO_ACTIVE_LOW),
{ },
diff --git a/arch/arm/mach-ep93xx/ts72xx.c b/arch/arm/mach-ep93xx/ts72xx.c
index 582e06e104fd..e0e1b11032f1 100644
--- a/arch/arm/mach-ep93xx/ts72xx.c
+++ b/arch/arm/mach-ep93xx/ts72xx.c
@@ -267,7 +267,7 @@ static struct spi_board_info bk3_spi_board_info[] __initdata = {
* goes through CPLD
*/
static struct gpiod_lookup_table bk3_spi_cs_gpio_table = {
- .dev_id = "ep93xx-spi.0",
+ .dev_id = "spi0",
.table = {
GPIO_LOOKUP("F", 3, "cs", GPIO_ACTIVE_LOW),
{ },
@@ -316,7 +316,7 @@ static struct spi_board_info ts72xx_spi_devices[] __initdata = {
};
static struct gpiod_lookup_table ts72xx_spi_cs_gpio_table = {
- .dev_id = "ep93xx-spi.0",
+ .dev_id = "spi0",
.table = {
/* DIO_17 */
GPIO_LOOKUP("F", 2, "cs", GPIO_ACTIVE_LOW),
diff --git a/arch/arm/mach-ep93xx/vision_ep9307.c b/arch/arm/mach-ep93xx/vision_ep9307.c
index a88a1d807b32..cbcba3136d74 100644
--- a/arch/arm/mach-ep93xx/vision_ep9307.c
+++ b/arch/arm/mach-ep93xx/vision_ep9307.c
@@ -242,7 +242,7 @@ static struct spi_board_info vision_spi_board_info[] __initdata = {
};
static struct gpiod_lookup_table vision_spi_cs_gpio_table = {
- .dev_id = "ep93xx-spi.0",
+ .dev_id = "spi0",
.table = {
GPIO_LOOKUP_IDX("A", 6, "cs", 0, GPIO_ACTIVE_LOW),
GPIO_LOOKUP_IDX("A", 7, "cs", 1, GPIO_ACTIVE_LOW),
diff --git a/arch/arm64/boot/dts/renesas/hihope-common.dtsi b/arch/arm64/boot/dts/renesas/hihope-common.dtsi
index 3311a982fff8..23fd0224ca90 100644
--- a/arch/arm64/boot/dts/renesas/hihope-common.dtsi
+++ b/arch/arm64/boot/dts/renesas/hihope-common.dtsi
@@ -279,6 +279,7 @@
mmc-hs200-1_8v;
non-removable;
fixed-emmc-driver-type = <1>;
+ status = "okay";
};
&usb_extal_clk {
diff --git a/arch/arm64/boot/dts/renesas/r8a77995-draak.dts b/arch/arm64/boot/dts/renesas/r8a77995-draak.dts
index 0711170b26b1..3aa2564dfdc2 100644
--- a/arch/arm64/boot/dts/renesas/r8a77995-draak.dts
+++ b/arch/arm64/boot/dts/renesas/r8a77995-draak.dts
@@ -97,7 +97,7 @@
reg = <0x0 0x48000000 0x0 0x18000000>;
};
- reg_1p8v: regulator0 {
+ reg_1p8v: regulator-1p8v {
compatible = "regulator-fixed";
regulator-name = "fixed-1.8V";
regulator-min-microvolt = <1800000>;
@@ -106,7 +106,7 @@
regulator-always-on;
};
- reg_3p3v: regulator1 {
+ reg_3p3v: regulator-3p3v {
compatible = "regulator-fixed";
regulator-name = "fixed-3.3V";
regulator-min-microvolt = <3300000>;
@@ -115,7 +115,7 @@
regulator-always-on;
};
- reg_12p0v: regulator1 {
+ reg_12p0v: regulator-12p0v {
compatible = "regulator-fixed";
regulator-name = "D12.0V";
regulator-min-microvolt = <12000000>;
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 8fc4de0d22b4..7a84c9f1778e 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -101,21 +101,8 @@ static void check_if_tm_restore_required(struct task_struct *tsk)
}
}
-static bool tm_active_with_fp(struct task_struct *tsk)
-{
- return MSR_TM_ACTIVE(tsk->thread.regs->msr) &&
- (tsk->thread.ckpt_regs.msr & MSR_FP);
-}
-
-static bool tm_active_with_altivec(struct task_struct *tsk)
-{
- return MSR_TM_ACTIVE(tsk->thread.regs->msr) &&
- (tsk->thread.ckpt_regs.msr & MSR_VEC);
-}
#else
static inline void check_if_tm_restore_required(struct task_struct *tsk) { }
-static inline bool tm_active_with_fp(struct task_struct *tsk) { return false; }
-static inline bool tm_active_with_altivec(struct task_struct *tsk) { return false; }
#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
bool strict_msr_control;
@@ -252,7 +239,7 @@ EXPORT_SYMBOL(enable_kernel_fp);
static int restore_fp(struct task_struct *tsk)
{
- if (tsk->thread.load_fp || tm_active_with_fp(tsk)) {
+ if (tsk->thread.load_fp) {
load_fp_state(&current->thread.fp_state);
current->thread.load_fp++;
return 1;
@@ -334,8 +321,7 @@ EXPORT_SYMBOL_GPL(flush_altivec_to_thread);
static int restore_altivec(struct task_struct *tsk)
{
- if (cpu_has_feature(CPU_FTR_ALTIVEC) &&
- (tsk->thread.load_vec || tm_active_with_altivec(tsk))) {
+ if (cpu_has_feature(CPU_FTR_ALTIVEC) && (tsk->thread.load_vec)) {
load_vr_state(&tsk->thread.vr_state);
tsk->thread.used_vr = 1;
tsk->thread.load_vec++;
@@ -497,13 +483,14 @@ void giveup_all(struct task_struct *tsk)
if (!tsk->thread.regs)
return;
+ check_if_tm_restore_required(tsk);
+
usermsr = tsk->thread.regs->msr;
if ((usermsr & msr_all_available) == 0)
return;
msr_check_and_set(msr_all_available);
- check_if_tm_restore_required(tsk);
WARN_ON((usermsr & MSR_VSX) && !((usermsr & MSR_FP) && (usermsr & MSR_VEC)));
diff --git a/arch/powerpc/mm/nohash/tlb.c b/arch/powerpc/mm/nohash/tlb.c
index d4acf6fa0596..bf60983a58c7 100644
--- a/arch/powerpc/mm/nohash/tlb.c
+++ b/arch/powerpc/mm/nohash/tlb.c
@@ -630,7 +630,6 @@ static void early_init_this_mmu(void)
#ifdef CONFIG_PPC_FSL_BOOK3E
if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) {
unsigned int num_cams;
- int __maybe_unused cpu = smp_processor_id();
bool map = true;
/* use a quarter of the TLBCAM for bolted linear map */
diff --git a/arch/riscv/include/asm/image.h b/arch/riscv/include/asm/image.h
index ef28e106f247..344db5244547 100644
--- a/arch/riscv/include/asm/image.h
+++ b/arch/riscv/include/asm/image.h
@@ -3,7 +3,8 @@
#ifndef __ASM_IMAGE_H
#define __ASM_IMAGE_H
-#define RISCV_IMAGE_MAGIC "RISCV"
+#define RISCV_IMAGE_MAGIC "RISCV\0\0\0"
+#define RISCV_IMAGE_MAGIC2 "RSC\x05"
#define RISCV_IMAGE_FLAG_BE_SHIFT 0
#define RISCV_IMAGE_FLAG_BE_MASK 0x1
@@ -23,7 +24,7 @@
#define __HEAD_FLAGS (__HEAD_FLAG(BE))
#define RISCV_HEADER_VERSION_MAJOR 0
-#define RISCV_HEADER_VERSION_MINOR 1
+#define RISCV_HEADER_VERSION_MINOR 2
#define RISCV_HEADER_VERSION (RISCV_HEADER_VERSION_MAJOR << 16 | \
RISCV_HEADER_VERSION_MINOR)
@@ -39,9 +40,8 @@
* @version: version
* @res1: reserved
* @res2: reserved
- * @magic: Magic number
- * @res3: reserved (will be used for additional RISC-V specific
- * header)
+ * @magic: Magic number (RISC-V specific; deprecated)
+ * @magic2: Magic number 2 (to match the ARM64 'magic' field pos)
* @res4: reserved (will be used for PE COFF offset)
*
* The intention is for this header format to be shared between multiple
@@ -58,7 +58,7 @@ struct riscv_image_header {
u32 res1;
u64 res2;
u64 magic;
- u32 res3;
+ u32 magic2;
u32 res4;
};
#endif /* __ASSEMBLY__ */
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index 0f1ba17e476f..52eec0c1bf30 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -39,9 +39,9 @@ ENTRY(_start)
.word RISCV_HEADER_VERSION
.word 0
.dword 0
- .asciz RISCV_IMAGE_MAGIC
- .word 0
+ .ascii RISCV_IMAGE_MAGIC
.balign 4
+ .ascii RISCV_IMAGE_MAGIC2
.word 0
.global _start_kernel
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index b5fd6e85657c..d1ccc168c071 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -1961,6 +1961,16 @@ int s390int_to_s390irq(struct kvm_s390_interrupt *s390int,
case KVM_S390_MCHK:
irq->u.mchk.mcic = s390int->parm64;
break;
+ case KVM_S390_INT_PFAULT_INIT:
+ irq->u.ext.ext_params = s390int->parm;
+ irq->u.ext.ext_params2 = s390int->parm64;
+ break;
+ case KVM_S390_RESTART:
+ case KVM_S390_INT_CLOCK_COMP:
+ case KVM_S390_INT_CPU_TIMER:
+ break;
+ default:
+ return -EINVAL;
}
return 0;
}
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index f329dcb3f44c..39cff07bf2eb 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1018,6 +1018,8 @@ static int kvm_s390_vm_start_migration(struct kvm *kvm)
/* mark all the pages in active slots as dirty */
for (slotnr = 0; slotnr < slots->used_slots; slotnr++) {
ms = slots->memslots + slotnr;
+ if (!ms->dirty_bitmap)
+ return -EINVAL;
/*
* The second half of the bitmap is only used on x86,
* and would be wasted otherwise, so we put it to good
@@ -4323,7 +4325,7 @@ long kvm_arch_vcpu_async_ioctl(struct file *filp,
}
case KVM_S390_INTERRUPT: {
struct kvm_s390_interrupt s390int;
- struct kvm_s390_irq s390irq;
+ struct kvm_s390_irq s390irq = {};
if (copy_from_user(&s390int, argp, sizeof(s390int)))
return -EFAULT;
diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c
index ccc88926bc00..9f41a6f5a032 100644
--- a/arch/sparc/kernel/sys_sparc_64.c
+++ b/arch/sparc/kernel/sys_sparc_64.c
@@ -336,25 +336,28 @@ SYSCALL_DEFINE6(sparc_ipc, unsigned int, call, int, first, unsigned long, second
{
long err;
+ if (!IS_ENABLED(CONFIG_SYSVIPC))
+ return -ENOSYS;
+
/* No need for backward compatibility. We can start fresh... */
if (call <= SEMTIMEDOP) {
switch (call) {
case SEMOP:
- err = sys_semtimedop(first, ptr,
- (unsigned int)second, NULL);
+ err = ksys_semtimedop(first, ptr,
+ (unsigned int)second, NULL);
goto out;
case SEMTIMEDOP:
- err = sys_semtimedop(first, ptr, (unsigned int)second,
+ err = ksys_semtimedop(first, ptr, (unsigned int)second,
(const struct __kernel_timespec __user *)
- (unsigned long) fifth);
+ (unsigned long) fifth);
goto out;
case SEMGET:
- err = sys_semget(first, (int)second, (int)third);
+ err = ksys_semget(first, (int)second, (int)third);
goto out;
case SEMCTL: {
- err = sys_semctl(first, second,
- (int)third | IPC_64,
- (unsigned long) ptr);
+ err = ksys_old_semctl(first, second,
+ (int)third | IPC_64,
+ (unsigned long) ptr);
goto out;
}
default:
@@ -365,18 +368,18 @@ SYSCALL_DEFINE6(sparc_ipc, unsigned int, call, int, first, unsigned long, second
if (call <= MSGCTL) {
switch (call) {
case MSGSND:
- err = sys_msgsnd(first, ptr, (size_t)second,
+ err = ksys_msgsnd(first, ptr, (size_t)second,
(int)third);
goto out;
case MSGRCV:
- err = sys_msgrcv(first, ptr, (size_t)second, fifth,
+ err = ksys_msgrcv(first, ptr, (size_t)second, fifth,
(int)third);
goto out;
case MSGGET:
- err = sys_msgget((key_t)first, (int)second);
+ err = ksys_msgget((key_t)first, (int)second);
goto out;
case MSGCTL:
- err = sys_msgctl(first, (int)second | IPC_64, ptr);
+ err = ksys_old_msgctl(first, (int)second | IPC_64, ptr);
goto out;
default:
err = -ENOSYS;
@@ -396,13 +399,13 @@ SYSCALL_DEFINE6(sparc_ipc, unsigned int, call, int, first, unsigned long, second
goto out;
}
case SHMDT:
- err = sys_shmdt(ptr);
+ err = ksys_shmdt(ptr);
goto out;
case SHMGET:
- err = sys_shmget(first, (size_t)second, (int)third);
+ err = ksys_shmget(first, (size_t)second, (int)third);
goto out;
case SHMCTL:
- err = sys_shmctl(first, (int)second | IPC_64, ptr);
+ err = ksys_old_shmctl(first, (int)second | IPC_64, ptr);
goto out;
default:
err = -ENOSYS;
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/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/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/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/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/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)
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.