summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig1
-rw-r--r--arch/x86/Kconfig.debug2
-rw-r--r--arch/x86/crypto/blake2s-glue.c6
-rw-r--r--arch/x86/crypto/chacha_glue.c5
-rw-r--r--arch/x86/crypto/curve25519-x86_64.c7
-rw-r--r--arch/x86/crypto/poly1305_glue.c5
-rw-r--r--arch/x86/entry/entry_32.S43
-rw-r--r--arch/x86/entry/vdso/vclock_gettime.c6
-rw-r--r--arch/x86/entry/vsyscall/vsyscall_64.c6
-rw-r--r--arch/x86/events/core.c18
-rw-r--r--arch/x86/hyperv/hv_init.c15
-rw-r--r--arch/x86/include/asm/bitops.h4
-rw-r--r--arch/x86/include/asm/cpu_entry_area.h12
-rw-r--r--arch/x86/include/asm/doublefault.h13
-rw-r--r--arch/x86/include/asm/fpu/internal.h2
-rw-r--r--arch/x86/include/asm/iommu.h18
-rw-r--r--arch/x86/include/asm/mmu_context.h4
-rw-r--r--arch/x86/include/asm/mshyperv.h1
-rw-r--r--arch/x86/include/asm/pgtable_32_types.h7
-rw-r--r--arch/x86/include/asm/processor.h2
-rw-r--r--arch/x86/include/asm/traps.h3
-rw-r--r--arch/x86/include/uapi/asm/msgbuf.h9
-rw-r--r--arch/x86/include/uapi/asm/sembuf.h6
-rw-r--r--arch/x86/include/uapi/asm/shmbuf.h6
-rw-r--r--arch/x86/kernel/Makefile4
-rw-r--r--arch/x86/kernel/cpu/common.c12
-rw-r--r--arch/x86/kernel/cpu/mce/therm_throt.c17
-rw-r--r--arch/x86/kernel/doublefault.c86
-rw-r--r--arch/x86/kernel/doublefault_32.c136
-rw-r--r--arch/x86/kernel/dumpstack_32.c30
-rw-r--r--arch/x86/kernel/process.c52
-rw-r--r--arch/x86/kernel/ptrace.c36
-rw-r--r--arch/x86/kernel/traps.c31
-rw-r--r--arch/x86/kvm/cpuid.c10
-rw-r--r--arch/x86/kvm/svm.c7
-rw-r--r--arch/x86/kvm/vmx/vmx.c12
-rw-r--r--arch/x86/kvm/vmx/vmx.h8
-rw-r--r--arch/x86/lib/x86-opcode-map.txt44
-rw-r--r--arch/x86/mm/cpu_entry_area.c14
-rw-r--r--arch/x86/mm/fault.c2
-rw-r--r--arch/x86/mm/kasan_init_64.c61
-rw-r--r--arch/x86/mm/pat_interval.c12
-rw-r--r--arch/x86/pci/Makefile4
-rw-r--r--arch/x86/pci/common.c2
-rw-r--r--arch/x86/pci/fixup.c11
-rw-r--r--arch/x86/pci/intel_mid_pci.c2
-rw-r--r--arch/x86/pci/numachip.c5
-rw-r--r--arch/x86/platform/olpc/olpc-xo1-pm.c8
-rw-r--r--arch/x86/platform/olpc/olpc-xo1-sci.c6
-rw-r--r--arch/x86/um/vdso/um_vdso.c12
50 files changed, 567 insertions, 258 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 0cb1756223be..5e8949953660 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -134,6 +134,7 @@ config X86
select HAVE_ARCH_JUMP_LABEL
select HAVE_ARCH_JUMP_LABEL_RELATIVE
select HAVE_ARCH_KASAN if X86_64
+ select HAVE_ARCH_KASAN_VMALLOC if X86_64
select HAVE_ARCH_KGDB
select HAVE_ARCH_MMAP_RND_BITS if MMU
select HAVE_ARCH_MMAP_RND_COMPAT_BITS if MMU && COMPAT
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 409c00f74e60..c4eab8ed33a3 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -117,7 +117,7 @@ config DEBUG_WX
config DOUBLEFAULT
default y
- bool "Enable doublefault exception handler" if EXPERT
+ bool "Enable doublefault exception handler" if EXPERT && X86_32
---help---
This option allows trapping of rare doublefault exceptions that
would otherwise cause a system to silently reboot. Disabling this
diff --git a/arch/x86/crypto/blake2s-glue.c b/arch/x86/crypto/blake2s-glue.c
index 4a37ba7cdbe5..1d9ff8a45e1f 100644
--- a/arch/x86/crypto/blake2s-glue.c
+++ b/arch/x86/crypto/blake2s-glue.c
@@ -210,12 +210,14 @@ static int __init blake2s_mod_init(void)
XFEATURE_MASK_AVX512, NULL))
static_branch_enable(&blake2s_use_avx512);
- return crypto_register_shashes(blake2s_algs, ARRAY_SIZE(blake2s_algs));
+ return IS_REACHABLE(CONFIG_CRYPTO_HASH) ?
+ crypto_register_shashes(blake2s_algs,
+ ARRAY_SIZE(blake2s_algs)) : 0;
}
static void __exit blake2s_mod_exit(void)
{
- if (boot_cpu_has(X86_FEATURE_SSSE3))
+ if (IS_REACHABLE(CONFIG_CRYPTO_HASH) && boot_cpu_has(X86_FEATURE_SSSE3))
crypto_unregister_shashes(blake2s_algs, ARRAY_SIZE(blake2s_algs));
}
diff --git a/arch/x86/crypto/chacha_glue.c b/arch/x86/crypto/chacha_glue.c
index a94e30b6f941..68a74953efaf 100644
--- a/arch/x86/crypto/chacha_glue.c
+++ b/arch/x86/crypto/chacha_glue.c
@@ -299,12 +299,13 @@ static int __init chacha_simd_mod_init(void)
boot_cpu_has(X86_FEATURE_AVX512BW)) /* kmovq */
static_branch_enable(&chacha_use_avx512vl);
}
- return crypto_register_skciphers(algs, ARRAY_SIZE(algs));
+ return IS_REACHABLE(CONFIG_CRYPTO_SKCIPHER) ?
+ crypto_register_skciphers(algs, ARRAY_SIZE(algs)) : 0;
}
static void __exit chacha_simd_mod_fini(void)
{
- if (boot_cpu_has(X86_FEATURE_SSSE3))
+ if (IS_REACHABLE(CONFIG_CRYPTO_SKCIPHER) && boot_cpu_has(X86_FEATURE_SSSE3))
crypto_unregister_skciphers(algs, ARRAY_SIZE(algs));
}
diff --git a/arch/x86/crypto/curve25519-x86_64.c b/arch/x86/crypto/curve25519-x86_64.c
index a52a3fb15727..eec7d2d24239 100644
--- a/arch/x86/crypto/curve25519-x86_64.c
+++ b/arch/x86/crypto/curve25519-x86_64.c
@@ -2457,13 +2457,14 @@ static int __init curve25519_mod_init(void)
static_branch_enable(&curve25519_use_adx);
else
return 0;
- return crypto_register_kpp(&curve25519_alg);
+ return IS_REACHABLE(CONFIG_CRYPTO_KPP) ?
+ crypto_register_kpp(&curve25519_alg) : 0;
}
static void __exit curve25519_mod_exit(void)
{
- if (boot_cpu_has(X86_FEATURE_BMI2) ||
- boot_cpu_has(X86_FEATURE_ADX))
+ if (IS_REACHABLE(CONFIG_CRYPTO_KPP) &&
+ (boot_cpu_has(X86_FEATURE_BMI2) || boot_cpu_has(X86_FEATURE_ADX)))
crypto_unregister_kpp(&curve25519_alg);
}
diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c
index 370cd88068ec..0cc4537e6617 100644
--- a/arch/x86/crypto/poly1305_glue.c
+++ b/arch/x86/crypto/poly1305_glue.c
@@ -224,12 +224,13 @@ static int __init poly1305_simd_mod_init(void)
cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL))
static_branch_enable(&poly1305_use_avx2);
- return crypto_register_shash(&alg);
+ return IS_REACHABLE(CONFIG_CRYPTO_HASH) ? crypto_register_shash(&alg) : 0;
}
static void __exit poly1305_simd_mod_exit(void)
{
- crypto_unregister_shash(&alg);
+ if (IS_REACHABLE(CONFIG_CRYPTO_HASH))
+ crypto_unregister_shash(&alg);
}
module_init(poly1305_simd_mod_init);
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 5832b11f01bb..7e0560442538 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -1090,7 +1090,6 @@ SYM_FUNC_START(entry_INT80_32)
restore_all:
TRACE_IRQS_IRET
SWITCH_TO_ENTRY_STACK
-.Lrestore_all_notrace:
CHECK_AND_APPLY_ESPFIX
.Lrestore_nocheck:
/* Switch back to user CR3 */
@@ -1537,6 +1536,48 @@ SYM_CODE_START(debug)
jmp common_exception
SYM_CODE_END(debug)
+#ifdef CONFIG_DOUBLEFAULT
+SYM_CODE_START(double_fault)
+1:
+ /*
+ * This is a task gate handler, not an interrupt gate handler.
+ * The error code is on the stack, but the stack is otherwise
+ * empty. Interrupts are off. Our state is sane with the following
+ * exceptions:
+ *
+ * - CR0.TS is set. "TS" literally means "task switched".
+ * - EFLAGS.NT is set because we're a "nested task".
+ * - The doublefault TSS has back_link set and has been marked busy.
+ * - TR points to the doublefault TSS and the normal TSS is busy.
+ * - CR3 is the normal kernel PGD. This would be delightful, except
+ * that the CPU didn't bother to save the old CR3 anywhere. This
+ * would make it very awkward to return back to the context we came
+ * from.
+ *
+ * The rest of EFLAGS is sanitized for us, so we don't need to
+ * worry about AC or DF.
+ *
+ * Don't even bother popping the error code. It's always zero,
+ * and ignoring it makes us a bit more robust against buggy
+ * hypervisor task gate implementations.
+ *
+ * We will manually undo the task switch instead of doing a
+ * task-switching IRET.
+ */
+
+ clts /* clear CR0.TS */
+ pushl $X86_EFLAGS_FIXED
+ popfl /* clear EFLAGS.NT */
+
+ call doublefault_shim
+
+ /* We don't support returning, so we have no IRET here. */
+1:
+ hlt
+ jmp 1b
+SYM_CODE_END(double_fault)
+#endif
+
/*
* NMI is doubly nasty. It can happen on the first instruction of
* entry_SYSENTER_32 (just like #DB), but it can also interrupt the beginning
diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index d9ff616bb0f6..7d70935b6758 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -15,7 +15,7 @@
#include "../../../../lib/vdso/gettimeofday.c"
extern int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz);
-extern time_t __vdso_time(time_t *t);
+extern __kernel_old_time_t __vdso_time(__kernel_old_time_t *t);
int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
{
@@ -25,12 +25,12 @@ int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
int gettimeofday(struct __kernel_old_timeval *, struct timezone *)
__attribute__((weak, alias("__vdso_gettimeofday")));
-time_t __vdso_time(time_t *t)
+__kernel_old_time_t __vdso_time(__kernel_old_time_t *t)
{
return __cvdso_time(t);
}
-time_t time(time_t *t) __attribute__((weak, alias("__vdso_time")));
+__kernel_old_time_t time(__kernel_old_time_t *t) __attribute__((weak, alias("__vdso_time")));
#if defined(CONFIG_X86_64) && !defined(BUILD_VDSO32_64)
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index e7c596dea947..44c33103a955 100644
--- a/arch/x86/entry/vsyscall/vsyscall_64.c
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
@@ -184,7 +184,7 @@ bool emulate_vsyscall(unsigned long error_code,
*/
switch (vsyscall_nr) {
case 0:
- if (!write_ok_or_segv(regs->di, sizeof(struct timeval)) ||
+ if (!write_ok_or_segv(regs->di, sizeof(struct __kernel_old_timeval)) ||
!write_ok_or_segv(regs->si, sizeof(struct timezone))) {
ret = -EFAULT;
goto check_fault;
@@ -194,7 +194,7 @@ bool emulate_vsyscall(unsigned long error_code,
break;
case 1:
- if (!write_ok_or_segv(regs->di, sizeof(time_t))) {
+ if (!write_ok_or_segv(regs->di, sizeof(__kernel_old_time_t))) {
ret = -EFAULT;
goto check_fault;
}
@@ -222,7 +222,7 @@ bool emulate_vsyscall(unsigned long error_code,
*/
regs->orig_ax = syscall_nr;
regs->ax = -ENOSYS;
- tmp = secure_computing(NULL);
+ tmp = secure_computing();
if ((!tmp && regs->orig_ax != syscall_nr) || regs->ip != address) {
warn_bad_vsyscall(KERN_DEBUG, regs,
"seccomp tried to change syscall nr or ip");
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 6e3f0c18908e..9a89d98c55bd 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -49,6 +49,7 @@ DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = {
.enabled = 1,
};
+DEFINE_STATIC_KEY_FALSE(rdpmc_never_available_key);
DEFINE_STATIC_KEY_FALSE(rdpmc_always_available_key);
u64 __read_mostly hw_cache_event_ids
@@ -2181,21 +2182,26 @@ static ssize_t set_attr_rdpmc(struct device *cdev,
if (x86_pmu.attr_rdpmc_broken)
return -ENOTSUPP;
- if ((val == 2) != (x86_pmu.attr_rdpmc == 2)) {
+ if (val != x86_pmu.attr_rdpmc) {
/*
- * Changing into or out of always available, aka
- * perf-event-bypassing mode. This path is extremely slow,
+ * Changing into or out of never available or always available,
+ * aka perf-event-bypassing mode. This path is extremely slow,
* but only root can trigger it, so it's okay.
*/
+ if (val == 0)
+ static_branch_inc(&rdpmc_never_available_key);
+ else if (x86_pmu.attr_rdpmc == 0)
+ static_branch_dec(&rdpmc_never_available_key);
+
if (val == 2)
static_branch_inc(&rdpmc_always_available_key);
- else
+ else if (x86_pmu.attr_rdpmc == 2)
static_branch_dec(&rdpmc_always_available_key);
+
on_each_cpu(refresh_pce, NULL, 1);
+ x86_pmu.attr_rdpmc = val;
}
- x86_pmu.attr_rdpmc = val;
-
return count;
}
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 50ff030d9224..caaf4dce99bf 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -7,6 +7,7 @@
* Author : K. Y. Srinivasan <kys@microsoft.com>
*/
+#include <linux/acpi.h>
#include <linux/efi.h>
#include <linux/types.h>
#include <asm/apic.h>
@@ -45,6 +46,14 @@ void *hv_alloc_hyperv_page(void)
}
EXPORT_SYMBOL_GPL(hv_alloc_hyperv_page);
+void *hv_alloc_hyperv_zeroed_page(void)
+{
+ BUILD_BUG_ON(PAGE_SIZE != HV_HYP_PAGE_SIZE);
+
+ return (void *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
+}
+EXPORT_SYMBOL_GPL(hv_alloc_hyperv_zeroed_page);
+
void hv_free_hyperv_page(unsigned long addr)
{
free_page(addr);
@@ -437,3 +446,9 @@ bool hv_is_hyperv_initialized(void)
return hypercall_msr.enable;
}
EXPORT_SYMBOL_GPL(hv_is_hyperv_initialized);
+
+bool hv_is_hibernation_supported(void)
+{
+ return acpi_sleep_state_supported(ACPI_STATE_S4);
+}
+EXPORT_SYMBOL_GPL(hv_is_hibernation_supported);
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 7d1f6a49bfae..062cdecb2f24 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -388,7 +388,9 @@ static __always_inline int fls64(__u64 x)
#include <asm-generic/bitops/const_hweight.h>
-#include <asm-generic/bitops-instrumented.h>
+#include <asm-generic/bitops/instrumented-atomic.h>
+#include <asm-generic/bitops/instrumented-non-atomic.h>
+#include <asm-generic/bitops/instrumented-lock.h>
#include <asm-generic/bitops/le.h>
diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h
index ea866c7bf31d..804734058c77 100644
--- a/arch/x86/include/asm/cpu_entry_area.h
+++ b/arch/x86/include/asm/cpu_entry_area.h
@@ -65,6 +65,13 @@ enum exception_stack_ordering {
#endif
+#ifdef CONFIG_X86_32
+struct doublefault_stack {
+ unsigned long stack[(PAGE_SIZE - sizeof(struct x86_hw_tss)) / sizeof(unsigned long)];
+ struct x86_hw_tss tss;
+} __aligned(PAGE_SIZE);
+#endif
+
/*
* cpu_entry_area is a percpu region that contains things needed by the CPU
* and early entry/exit code. Real types aren't used for all fields here
@@ -86,6 +93,11 @@ struct cpu_entry_area {
#endif
struct entry_stack_page entry_stack_page;
+#ifdef CONFIG_X86_32
+ char guard_doublefault_stack[PAGE_SIZE];
+ struct doublefault_stack doublefault_stack;
+#endif
+
/*
* On x86_64, the TSS is mapped RO. On x86_32, it's mapped RW because
* we need task switches to work, and task switches write to the TSS.
diff --git a/arch/x86/include/asm/doublefault.h b/arch/x86/include/asm/doublefault.h
new file mode 100644
index 000000000000..af9a14ac8962
--- /dev/null
+++ b/arch/x86/include/asm/doublefault.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_DOUBLEFAULT_H
+#define _ASM_X86_DOUBLEFAULT_H
+
+#if defined(CONFIG_X86_32) && defined(CONFIG_DOUBLEFAULT)
+extern void doublefault_init_cpu_tss(void);
+#else
+static inline void doublefault_init_cpu_tss(void)
+{
+}
+#endif
+
+#endif /* _ASM_X86_DOUBLEFAULT_H */
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 4c95c365058a..44c48e34d799 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -509,7 +509,7 @@ static inline void __fpu_invalidate_fpregs_state(struct fpu *fpu)
static inline int fpregs_state_valid(struct fpu *fpu, unsigned int cpu)
{
- return fpu == this_cpu_read_stable(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu;
+ return fpu == this_cpu_read(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu;
}
/*
diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h
index b91623d521d9..bf1ed2ddc74b 100644
--- a/arch/x86/include/asm/iommu.h
+++ b/arch/x86/include/asm/iommu.h
@@ -2,10 +2,28 @@
#ifndef _ASM_X86_IOMMU_H
#define _ASM_X86_IOMMU_H
+#include <linux/acpi.h>
+
+#include <asm/e820/api.h>
+
extern int force_iommu, no_iommu;
extern int iommu_detected;
/* 10 seconds */
#define DMAR_OPERATION_TIMEOUT ((cycles_t) tsc_khz*10*1000)
+static inline int __init
+arch_rmrr_sanity_check(struct acpi_dmar_reserved_memory *rmrr)
+{
+ u64 start = rmrr->base_address;
+ u64 end = rmrr->end_address + 1;
+
+ if (e820__mapped_all(start, end, E820_TYPE_RESERVED))
+ return 0;
+
+ pr_err(FW_BUG "No firmware reserved region can cover this RMRR [%#018Lx-%#018Lx], contact BIOS vendor for fixes\n",
+ start, end - 1);
+ return -EINVAL;
+}
+
#endif /* _ASM_X86_IOMMU_H */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 16ae821483c8..5f33924e200f 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -26,12 +26,14 @@ static inline void paravirt_activate_mm(struct mm_struct *prev,
#ifdef CONFIG_PERF_EVENTS
+DECLARE_STATIC_KEY_FALSE(rdpmc_never_available_key);
DECLARE_STATIC_KEY_FALSE(rdpmc_always_available_key);
static inline void load_mm_cr4_irqsoff(struct mm_struct *mm)
{
if (static_branch_unlikely(&rdpmc_always_available_key) ||
- atomic_read(&mm->context.perf_rdpmc_allowed))
+ (!static_branch_unlikely(&rdpmc_never_available_key) &&
+ atomic_read(&mm->context.perf_rdpmc_allowed)))
cr4_set_bits_irqsoff(X86_CR4_PCE);
else
cr4_clear_bits_irqsoff(X86_CR4_PCE);
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index f4138aeb4280..6b79515abb82 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -219,6 +219,7 @@ static inline struct hv_vp_assist_page *hv_get_vp_assist_page(unsigned int cpu)
void __init hyperv_init(void);
void hyperv_setup_mmu_ops(void);
void *hv_alloc_hyperv_page(void);
+void *hv_alloc_hyperv_zeroed_page(void);
void hv_free_hyperv_page(unsigned long addr);
void hyperv_reenlightenment_intr(struct pt_regs *regs);
void set_hv_tscchange_cb(void (*cb)(void));
diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h
index 19f5807260c3..0416d42e5bdd 100644
--- a/arch/x86/include/asm/pgtable_32_types.h
+++ b/arch/x86/include/asm/pgtable_32_types.h
@@ -41,10 +41,11 @@ extern bool __vmalloc_start_set; /* set once high_memory is set */
#endif
/*
- * Define this here and validate with BUILD_BUG_ON() in pgtable_32.c
- * to avoid include recursion hell
+ * This is an upper bound on sizeof(struct cpu_entry_area) / PAGE_SIZE.
+ * Define this here and validate with BUILD_BUG_ON() in cpu_entry_area.c
+ * to avoid include recursion hell.
*/
-#define CPU_ENTRY_AREA_PAGES (NR_CPUS * 41)
+#define CPU_ENTRY_AREA_PAGES (NR_CPUS * 43)
/* The +1 is for the readonly IDT page: */
#define CPU_ENTRY_AREA_BASE \
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index e51afbb0cbfb..0340aad3f2fc 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -166,7 +166,6 @@ enum cpuid_regs_idx {
extern struct cpuinfo_x86 boot_cpu_data;
extern struct cpuinfo_x86 new_cpu_data;
-extern struct x86_hw_tss doublefault_tss;
extern __u32 cpu_caps_cleared[NCAPINTS + NBUGINTS];
extern __u32 cpu_caps_set[NCAPINTS + NBUGINTS];
@@ -997,7 +996,6 @@ bool xen_set_default_idle(void);
#endif
void stop_this_cpu(void *dummy);
-void df_debug(struct pt_regs *regs, long error_code);
void microcode_check(void);
enum l1tf_mitigations {
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index b25e633033c3..ffa0dc8a535e 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -69,6 +69,9 @@ dotraplinkage void do_overflow(struct pt_regs *regs, long error_code);
dotraplinkage void do_bounds(struct pt_regs *regs, long error_code);
dotraplinkage void do_invalid_op(struct pt_regs *regs, long error_code);
dotraplinkage void do_device_not_available(struct pt_regs *regs, long error_code);
+#if defined(CONFIG_X86_64) || defined(CONFIG_DOUBLEFAULT)
+dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code, unsigned long cr2);
+#endif
dotraplinkage void do_coprocessor_segment_overrun(struct pt_regs *regs, long error_code);
dotraplinkage void do_invalid_TSS(struct pt_regs *regs, long error_code);
dotraplinkage void do_segment_not_present(struct pt_regs *regs, long error_code);
diff --git a/arch/x86/include/uapi/asm/msgbuf.h b/arch/x86/include/uapi/asm/msgbuf.h
index 90ab9a795b49..b3d0664fadc9 100644
--- a/arch/x86/include/uapi/asm/msgbuf.h
+++ b/arch/x86/include/uapi/asm/msgbuf.h
@@ -5,6 +5,9 @@
#if !defined(__x86_64__) || !defined(__ILP32__)
#include <asm-generic/msgbuf.h>
#else
+
+#include <asm/ipcbuf.h>
+
/*
* The msqid64_ds structure for x86 architecture with x32 ABI.
*
@@ -15,9 +18,9 @@
struct msqid64_ds {
struct ipc64_perm msg_perm;
- __kernel_time_t msg_stime; /* last msgsnd time */
- __kernel_time_t msg_rtime; /* last msgrcv time */
- __kernel_time_t msg_ctime; /* last change time */
+ __kernel_long_t msg_stime; /* last msgsnd time */
+ __kernel_long_t msg_rtime; /* last msgrcv time */
+ __kernel_long_t msg_ctime; /* last change time */
__kernel_ulong_t msg_cbytes; /* current number of bytes on queue */
__kernel_ulong_t msg_qnum; /* number of messages in queue */
__kernel_ulong_t msg_qbytes; /* max number of bytes on queue */
diff --git a/arch/x86/include/uapi/asm/sembuf.h b/arch/x86/include/uapi/asm/sembuf.h
index 89de6cd9f0a7..71205b02a191 100644
--- a/arch/x86/include/uapi/asm/sembuf.h
+++ b/arch/x86/include/uapi/asm/sembuf.h
@@ -2,6 +2,8 @@
#ifndef _ASM_X86_SEMBUF_H
#define _ASM_X86_SEMBUF_H
+#include <asm/ipcbuf.h>
+
/*
* The semid64_ds structure for x86 architecture.
* Note extra padding because this structure is passed back and forth
@@ -21,9 +23,9 @@ struct semid64_ds {
unsigned long sem_ctime; /* last change time */
unsigned long sem_ctime_high;
#else
- __kernel_time_t sem_otime; /* last semop time */
+ __kernel_long_t sem_otime; /* last semop time */
__kernel_ulong_t __unused1;
- __kernel_time_t sem_ctime; /* last change time */
+ __kernel_long_t sem_ctime; /* last change time */
__kernel_ulong_t __unused2;
#endif
__kernel_ulong_t sem_nsems; /* no. of semaphores in array */
diff --git a/arch/x86/include/uapi/asm/shmbuf.h b/arch/x86/include/uapi/asm/shmbuf.h
index 644421f3823b..f0305dc660c9 100644
--- a/arch/x86/include/uapi/asm/shmbuf.h
+++ b/arch/x86/include/uapi/asm/shmbuf.h
@@ -16,9 +16,9 @@
struct shmid64_ds {
struct ipc64_perm shm_perm; /* operation perms */
size_t shm_segsz; /* size of segment (bytes) */
- __kernel_time_t shm_atime; /* last attach time */
- __kernel_time_t shm_dtime; /* last detach time */
- __kernel_time_t shm_ctime; /* last change time */
+ __kernel_long_t shm_atime; /* last attach time */
+ __kernel_long_t shm_dtime; /* last detach time */
+ __kernel_long_t shm_ctime; /* last change time */
__kernel_pid_t shm_cpid; /* pid of creator */
__kernel_pid_t shm_lpid; /* pid of last operator */
__kernel_ulong_t shm_nattch; /* no. of current attaches */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 32acb970f416..6175e370ee4a 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -100,7 +100,9 @@ obj-$(CONFIG_KEXEC_FILE) += kexec-bzimage64.o
obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o
obj-y += kprobes/
obj-$(CONFIG_MODULES) += module.o
-obj-$(CONFIG_DOUBLEFAULT) += doublefault.o
+ifeq ($(CONFIG_X86_32),y)
+obj-$(CONFIG_DOUBLEFAULT) += doublefault_32.o
+endif
obj-$(CONFIG_KGDB) += kgdb.o
obj-$(CONFIG_VM86) += vm86_32.o
obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index baa2fed8deb6..2e4d90294fe6 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -24,6 +24,7 @@
#include <asm/stackprotector.h>
#include <asm/perf_event.h>
#include <asm/mmu_context.h>
+#include <asm/doublefault.h>
#include <asm/archrandom.h>
#include <asm/hypervisor.h>
#include <asm/processor.h>
@@ -1814,8 +1815,6 @@ static inline void tss_setup_ist(struct tss_struct *tss)
tss->x86_tss.ist[IST_INDEX_MCE] = __this_cpu_ist_top_va(MCE);
}
-static inline void gdt_setup_doublefault_tss(int cpu) { }
-
#else /* CONFIG_X86_64 */
static inline void setup_getcpu(int cpu) { }
@@ -1827,13 +1826,6 @@ static inline void ucode_cpu_init(int cpu)
static inline void tss_setup_ist(struct tss_struct *tss) { }
-static inline void gdt_setup_doublefault_tss(int cpu)
-{
-#ifdef CONFIG_DOUBLEFAULT
- /* Set up the doublefault TSS pointer in the GDT */
- __set_tss_desc(cpu, GDT_ENTRY_DOUBLEFAULT_TSS, &doublefault_tss);
-#endif
-}
#endif /* !CONFIG_X86_64 */
static inline void tss_setup_io_bitmap(struct tss_struct *tss)
@@ -1923,7 +1915,7 @@ void cpu_init(void)
clear_all_debug_regs();
dbg_restore_debug_regs();
- gdt_setup_doublefault_tss(cpu);
+ doublefault_init_cpu_tss();
fpu__init_cpu();
diff --git a/arch/x86/kernel/cpu/mce/therm_throt.c b/arch/x86/kernel/cpu/mce/therm_throt.c
index d01e0da0163a..b38010b541d6 100644
--- a/arch/x86/kernel/cpu/mce/therm_throt.c
+++ b/arch/x86/kernel/cpu/mce/therm_throt.c
@@ -195,17 +195,24 @@ static const struct attribute_group thermal_attr_group = {
#define THERM_THROT_POLL_INTERVAL HZ
#define THERM_STATUS_PROCHOT_LOG BIT(1)
+#define THERM_STATUS_CLEAR_CORE_MASK (BIT(1) | BIT(3) | BIT(5) | BIT(7) | BIT(9) | BIT(11) | BIT(13) | BIT(15))
+#define THERM_STATUS_CLEAR_PKG_MASK (BIT(1) | BIT(3) | BIT(5) | BIT(7) | BIT(9) | BIT(11))
+
static void clear_therm_status_log(int level)
{
int msr;
- u64 msr_val;
+ u64 mask, msr_val;
- if (level == CORE_LEVEL)
- msr = MSR_IA32_THERM_STATUS;
- else
- msr = MSR_IA32_PACKAGE_THERM_STATUS;
+ if (level == CORE_LEVEL) {
+ msr = MSR_IA32_THERM_STATUS;
+ mask = THERM_STATUS_CLEAR_CORE_MASK;
+ } else {
+ msr = MSR_IA32_PACKAGE_THERM_STATUS;
+ mask = THERM_STATUS_CLEAR_PKG_MASK;
+ }
rdmsrl(msr, msr_val);
+ msr_val &= mask;
wrmsrl(msr, msr_val & ~THERM_STATUS_PROCHOT_LOG);
}
diff --git a/arch/x86/kernel/doublefault.c b/arch/x86/kernel/doublefault.c
deleted file mode 100644
index 0d6c657593f8..000000000000
--- a/arch/x86/kernel/doublefault.c
+++ /dev/null
@@ -1,86 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/mm.h>
-#include <linux/sched.h>
-#include <linux/sched/debug.h>
-#include <linux/init_task.h>
-#include <linux/fs.h>
-
-#include <linux/uaccess.h>
-#include <asm/pgtable.h>
-#include <asm/processor.h>
-#include <asm/desc.h>
-
-#ifdef CONFIG_X86_32
-
-#define DOUBLEFAULT_STACKSIZE (1024)
-static unsigned long doublefault_stack[DOUBLEFAULT_STACKSIZE];
-#define STACK_START (unsigned long)(doublefault_stack+DOUBLEFAULT_STACKSIZE)
-
-#define ptr_ok(x) ((x) > PAGE_OFFSET && (x) < PAGE_OFFSET + MAXMEM)
-
-static void doublefault_fn(void)
-{
- struct desc_ptr gdt_desc = {0, 0};
- unsigned long gdt, tss;
-
- native_store_gdt(&gdt_desc);
- gdt = gdt_desc.address;
-
- printk(KERN_EMERG "PANIC: double fault, gdt at %08lx [%d bytes]\n", gdt, gdt_desc.size);
-
- if (ptr_ok(gdt)) {
- gdt += GDT_ENTRY_TSS << 3;
- tss = get_desc_base((struct desc_struct *)gdt);
- printk(KERN_EMERG "double fault, tss at %08lx\n", tss);
-
- if (ptr_ok(tss)) {
- struct x86_hw_tss *t = (struct x86_hw_tss *)tss;
-
- printk(KERN_EMERG "eip = %08lx, esp = %08lx\n",
- t->ip, t->sp);
-
- printk(KERN_EMERG "eax = %08lx, ebx = %08lx, ecx = %08lx, edx = %08lx\n",
- t->ax, t->bx, t->cx, t->dx);
- printk(KERN_EMERG "esi = %08lx, edi = %08lx\n",
- t->si, t->di);
- }
- }
-
- for (;;)
- cpu_relax();
-}
-
-struct x86_hw_tss doublefault_tss __cacheline_aligned = {
- .sp0 = STACK_START,
- .ss0 = __KERNEL_DS,
- .ldt = 0,
- .io_bitmap_base = IO_BITMAP_OFFSET_INVALID,
-
- .ip = (unsigned long) doublefault_fn,
- /* 0x2 bit is always set */
- .flags = X86_EFLAGS_SF | 0x2,
- .sp = STACK_START,
- .es = __USER_DS,
- .cs = __KERNEL_CS,
- .ss = __KERNEL_DS,
- .ds = __USER_DS,
- .fs = __KERNEL_PERCPU,
-#ifndef CONFIG_X86_32_LAZY_GS
- .gs = __KERNEL_STACK_CANARY,
-#endif
-
- .__cr3 = __pa_nodebug(swapper_pg_dir),
-};
-
-/* dummy for do_double_fault() call */
-void df_debug(struct pt_regs *regs, long error_code) {}
-
-#else /* !CONFIG_X86_32 */
-
-void df_debug(struct pt_regs *regs, long error_code)
-{
- pr_emerg("PANIC: double fault, error_code: 0x%lx\n", error_code);
- show_regs(regs);
- panic("Machine halted.");
-}
-#endif
diff --git a/arch/x86/kernel/doublefault_32.c b/arch/x86/kernel/doublefault_32.c
new file mode 100644
index 000000000000..3793646f0fb5
--- /dev/null
+++ b/arch/x86/kernel/doublefault_32.c
@@ -0,0 +1,136 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/sched/debug.h>
+#include <linux/init_task.h>
+#include <linux/fs.h>
+
+#include <linux/uaccess.h>
+#include <asm/pgtable.h>
+#include <asm/processor.h>
+#include <asm/desc.h>
+#include <asm/traps.h>
+
+extern void double_fault(void);
+#define ptr_ok(x) ((x) > PAGE_OFFSET && (x) < PAGE_OFFSET + MAXMEM)
+
+#define TSS(x) this_cpu_read(cpu_tss_rw.x86_tss.x)
+
+static void set_df_gdt_entry(unsigned int cpu);
+
+/*
+ * Called by double_fault with CR0.TS and EFLAGS.NT cleared. The CPU thinks
+ * we're running the doublefault task. Cannot return.
+ */
+asmlinkage notrace void __noreturn doublefault_shim(void)
+{
+ unsigned long cr2;
+ struct pt_regs regs;
+
+ BUILD_BUG_ON(sizeof(struct doublefault_stack) != PAGE_SIZE);
+
+ cr2 = native_read_cr2();
+
+ /* Reset back to the normal kernel task. */
+ force_reload_TR();
+ set_df_gdt_entry(smp_processor_id());
+
+ trace_hardirqs_off();
+
+ /*
+ * Fill in pt_regs. A downside of doing this in C is that the unwinder
+ * won't see it (no ENCODE_FRAME_POINTER), so a nested stack dump
+ * won't successfully unwind to the source of the double fault.
+ * The main dump from do_double_fault() is fine, though, since it
+ * uses these regs directly.
+ *
+ * If anyone ever cares, this could be moved to asm.
+ */
+ regs.ss = TSS(ss);
+ regs.__ssh = 0;
+ regs.sp = TSS(sp);
+ regs.flags = TSS(flags);
+ regs.cs = TSS(cs);
+ /* We won't go through the entry asm, so we can leave __csh as 0. */
+ regs.__csh = 0;
+ regs.ip = TSS(ip);
+ regs.orig_ax = 0;
+ regs.gs = TSS(gs);
+ regs.__gsh = 0;
+ regs.fs = TSS(fs);
+ regs.__fsh = 0;
+ regs.es = TSS(es);
+ regs.__esh = 0;
+ regs.ds = TSS(ds);
+ regs.__dsh = 0;
+ regs.ax = TSS(ax);
+ regs.bp = TSS(bp);
+ regs.di = TSS(di);
+ regs.si = TSS(si);
+ regs.dx = TSS(dx);
+ regs.cx = TSS(cx);
+ regs.bx = TSS(bx);
+
+ do_double_fault(&regs, 0, cr2);
+
+ /*
+ * x86_32 does not save the original CR3 anywhere on a task switch.
+ * This means that, even if we wanted to return, we would need to find
+ * some way to reconstruct CR3. We could make a credible guess based
+ * on cpu_tlbstate, but that would be racy and would not account for
+ * PTI.
+ *
+ * Instead, don't bother. We can return through
+ * rewind_stack_do_exit() instead.
+ */
+ panic("cannot return from double fault\n");
+}
+NOKPROBE_SYMBOL(doublefault_shim);
+
+DEFINE_PER_CPU_PAGE_ALIGNED(struct doublefault_stack, doublefault_stack) = {
+ .tss = {
+ /*
+ * No sp0 or ss0 -- we never run CPL != 0 with this TSS
+ * active. sp is filled in later.
+ */
+ .ldt = 0,
+ .io_bitmap_base = IO_BITMAP_OFFSET_INVALID,
+
+ .ip = (unsigned long) double_fault,
+ .flags = X86_EFLAGS_FIXED,
+ .es = __USER_DS,
+ .cs = __KERNEL_CS,
+ .ss = __KERNEL_DS,
+ .ds = __USER_DS,
+ .fs = __KERNEL_PERCPU,
+#ifndef CONFIG_X86_32_LAZY_GS
+ .gs = __KERNEL_STACK_CANARY,
+#endif
+
+ .__cr3 = __pa_nodebug(swapper_pg_dir),
+ },
+};
+
+static void set_df_gdt_entry(unsigned int cpu)
+{
+ /* Set up doublefault TSS pointer in the GDT */
+ __set_tss_desc(cpu, GDT_ENTRY_DOUBLEFAULT_TSS,
+ &get_cpu_entry_area(cpu)->doublefault_stack.tss);
+
+}
+
+void doublefault_init_cpu_tss(void)
+{
+ unsigned int cpu = smp_processor_id();
+ struct cpu_entry_area *cea = get_cpu_entry_area(cpu);
+
+ /*
+ * The linker isn't smart enough to initialize percpu variables that
+ * point to other places in percpu space.
+ */
+ this_cpu_write(doublefault_stack.tss.sp,
+ (unsigned long)&cea->doublefault_stack.stack +
+ sizeof(doublefault_stack.stack));
+
+ set_df_gdt_entry(cpu);
+}
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index 64a59d726639..8e3a8fedfa4d 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -29,6 +29,9 @@ const char *stack_type_name(enum stack_type type)
if (type == STACK_TYPE_ENTRY)
return "ENTRY_TRAMPOLINE";
+ if (type == STACK_TYPE_EXCEPTION)
+ return "#DF";
+
return NULL;
}
@@ -82,6 +85,30 @@ static bool in_softirq_stack(unsigned long *stack, struct stack_info *info)
return true;
}
+static bool in_doublefault_stack(unsigned long *stack, struct stack_info *info)
+{
+#ifdef CONFIG_DOUBLEFAULT
+ struct cpu_entry_area *cea = get_cpu_entry_area(raw_smp_processor_id());
+ struct doublefault_stack *ss = &cea->doublefault_stack;
+
+ void *begin = ss->stack;
+ void *end = begin + sizeof(ss->stack);
+
+ if ((void *)stack < begin || (void *)stack >= end)
+ return false;
+
+ info->type = STACK_TYPE_EXCEPTION;
+ info->begin = begin;
+ info->end = end;
+ info->next_sp = (unsigned long *)this_cpu_read(cpu_tss_rw.x86_tss.sp);
+
+ return true;
+#else
+ return false;
+#endif
+}
+
+
int get_stack_info(unsigned long *stack, struct task_struct *task,
struct stack_info *info, unsigned long *visit_mask)
{
@@ -105,6 +132,9 @@ int get_stack_info(unsigned long *stack, struct task_struct *task,
if (in_softirq_stack(stack, info))
goto recursion_check;
+ if (in_doublefault_stack(stack, info))
+ goto recursion_check;
+
goto unknown;
recursion_check:
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index bd2a11ca5dd6..61e93a318983 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -377,37 +377,37 @@ static void tss_copy_io_bitmap(struct tss_struct *tss, struct io_bitmap *iobm)
void tss_update_io_bitmap(void)
{
struct tss_struct *tss = this_cpu_ptr(&cpu_tss_rw);
+ struct thread_struct *t = &current->thread;
u16 *base = &tss->x86_tss.io_bitmap_base;
- if (test_thread_flag(TIF_IO_BITMAP)) {
- struct thread_struct *t = &current->thread;
-
- if (IS_ENABLED(CONFIG_X86_IOPL_IOPERM) && t->iopl_emul == 3) {
- *base = IO_BITMAP_OFFSET_VALID_ALL;
- } else {
- struct io_bitmap *iobm = t->io_bitmap;
- /*
- * Only copy bitmap data when the sequence number
- * differs. The update time is accounted to the
- * incoming task.
- */
- if (tss->io_bitmap.prev_sequence != iobm->sequence)
- tss_copy_io_bitmap(tss, iobm);
-
- /* Enable the bitmap */
- *base = IO_BITMAP_OFFSET_VALID_MAP;
- }
+ if (!test_thread_flag(TIF_IO_BITMAP)) {
+ tss_invalidate_io_bitmap(tss);
+ return;
+ }
+
+ if (IS_ENABLED(CONFIG_X86_IOPL_IOPERM) && t->iopl_emul == 3) {
+ *base = IO_BITMAP_OFFSET_VALID_ALL;
+ } else {
+ struct io_bitmap *iobm = t->io_bitmap;
+
/*
- * Make sure that the TSS limit is covering the io bitmap.
- * It might have been cut down by a VMEXIT to 0x67 which
- * would cause a subsequent I/O access from user space to
- * trigger a #GP because tbe bitmap is outside the TSS
- * limit.
+ * Only copy bitmap data when the sequence number differs. The
+ * update time is accounted to the incoming task.
*/
- refresh_tss_limit();
- } else {
- tss_invalidate_io_bitmap(tss);
+ if (tss->io_bitmap.prev_sequence != iobm->sequence)
+ tss_copy_io_bitmap(tss, iobm);
+
+ /* Enable the bitmap */
+ *base = IO_BITMAP_OFFSET_VALID_MAP;
}
+
+ /*
+ * Make sure that the TSS limit is covering the IO bitmap. It might have
+ * been cut down by a VMEXIT to 0x67 which would cause a subsequent I/O
+ * access from user space to trigger a #GP because tbe bitmap is outside
+ * the TSS limit.
+ */
+ refresh_tss_limit();
}
#else /* CONFIG_X86_IOPL_IOPERM */
static inline void switch_to_bitmap(unsigned long tifp) { }
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 066e5b01a7e0..f0e1ddbc2fd7 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -182,6 +182,9 @@ static u16 get_segment_reg(struct task_struct *task, unsigned long offset)
static int set_segment_reg(struct task_struct *task,
unsigned long offset, u16 value)
{
+ if (WARN_ON_ONCE(task == current))
+ return -EIO;
+
/*
* The value argument was already truncated to 16 bits.
*/
@@ -209,10 +212,7 @@ static int set_segment_reg(struct task_struct *task,
break;
case offsetof(struct user_regs_struct, gs):
- if (task == current)
- set_user_gs(task_pt_regs(task), value);
- else
- task_user_gs(task) = value;
+ task_user_gs(task) = value;
}
return 0;
@@ -272,32 +272,41 @@ static u16 get_segment_reg(struct task_struct *task, unsigned long offset)
static int set_segment_reg(struct task_struct *task,
unsigned long offset, u16 value)
{
+ if (WARN_ON_ONCE(task == current))
+ return -EIO;
+
/*
* The value argument was already truncated to 16 bits.
*/
if (invalid_selector(value))
return -EIO;
+ /*
+ * This function has some ABI oddities.
+ *
+ * A 32-bit ptracer probably expects that writing FS or GS will change
+ * FSBASE or GSBASE respectively. In the absence of FSGSBASE support,
+ * this code indeed has that effect. When FSGSBASE is added, this
+ * will require a special case.
+ *
+ * For existing 64-bit ptracers, writing FS or GS *also* currently
+ * changes the base if the selector is nonzero the next time the task
+ * is run. This behavior may not be needed, and trying to preserve it
+ * when FSGSBASE is added would be complicated at best.
+ */
+
switch (offset) {
case offsetof(struct user_regs_struct,fs):
task->thread.fsindex = value;
- if (task == current)
- loadsegment(fs, task->thread.fsindex);
break;
case offsetof(struct user_regs_struct,gs):
task->thread.gsindex = value;
- if (task == current)
- load_gs_index(task->thread.gsindex);
break;
case offsetof(struct user_regs_struct,ds):
task->thread.ds = value;
- if (task == current)
- loadsegment(ds, task->thread.ds);
break;
case offsetof(struct user_regs_struct,es):
task->thread.es = value;
- if (task == current)
- loadsegment(es, task->thread.es);
break;
/*
@@ -375,6 +384,9 @@ static int putreg(struct task_struct *child,
* When changing the FS base, use do_arch_prctl_64()
* to set the index to zero and to set the base
* as requested.
+ *
+ * NB: This behavior is nonsensical and likely needs to
+ * change when FSGSBASE support is added.
*/
if (child->thread.fsbase != value)
return do_arch_prctl_64(child, ARCH_SET_FS, value);
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index c90312146da0..05da6b5b167b 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -306,8 +306,23 @@ __visible void __noreturn handle_stack_overflow(const char *message,
}
#endif
-#ifdef CONFIG_X86_64
-/* Runs on IST stack */
+#if defined(CONFIG_X86_64) || defined(CONFIG_DOUBLEFAULT)
+/*
+ * Runs on an IST stack for x86_64 and on a special task stack for x86_32.
+ *
+ * On x86_64, this is more or less a normal kernel entry. Notwithstanding the
+ * SDM's warnings about double faults being unrecoverable, returning works as
+ * expected. Presumably what the SDM actually means is that the CPU may get
+ * the register state wrong on entry, so returning could be a bad idea.
+ *
+ * Various CPU engineers have promised that double faults due to an IRET fault
+ * while the stack is read-only are, in fact, recoverable.
+ *
+ * On x86_32, this is entered through a task gate, and regs are synthesized
+ * from the TSS. Returning is, in principle, okay, but changes to regs will
+ * be lost. If, for some reason, we need to return to a context with modified
+ * regs, the shim code could be adjusted to synchronize the registers.
+ */
dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code, unsigned long cr2)
{
static const char str[] = "double fault";
@@ -411,15 +426,9 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code, unsign
handle_stack_overflow("kernel stack overflow (double-fault)", regs, cr2);
#endif
-#ifdef CONFIG_DOUBLEFAULT
- df_debug(regs, error_code);
-#endif
- /*
- * This is always a kernel trap and never fixable (and thus must
- * never return).
- */
- for (;;)
- die(str, regs, error_code);
+ pr_emerg("PANIC: double fault, error_code: 0x%lx\n", error_code);
+ die("double fault", regs, error_code);
+ panic("Machine halted.");
}
#endif
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index c0aa07487eb8..cfafa320a8cf 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -504,7 +504,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function,
r = -E2BIG;
- if (*nent >= maxnent)
+ if (WARN_ON(*nent >= maxnent))
goto out;
do_host_cpuid(entry, function, 0);
@@ -778,6 +778,11 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function,
case 0x8000001a:
case 0x8000001e:
break;
+ /* Support memory encryption cpuid if host supports it */
+ case 0x8000001F:
+ if (!boot_cpu_has(X86_FEATURE_SEV))
+ entry->eax = entry->ebx = entry->ecx = entry->edx = 0;
+ break;
/*Add support for Centaur's CPUID instruction*/
case 0xC0000000:
/*Just support up to 0xC0000004 now*/
@@ -810,6 +815,9 @@ out:
static int do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 func,
int *nent, int maxnent, unsigned int type)
{
+ if (*nent >= maxnent)
+ return -E2BIG;
+
if (type == KVM_GET_EMULATED_CPUID)
return __do_cpuid_func_emulated(entry, func, nent, maxnent);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 362e874297e4..122d4ce3b1ab 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -5958,13 +5958,6 @@ static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
if (npt_enabled)
entry->edx |= F(NPT);
- break;
- case 0x8000001F:
- /* Support memory encryption cpuid if host supports it */
- if (boot_cpu_has(X86_FEATURE_SEV))
- cpuid(0x8000001f, &entry->eax, &entry->ebx,
- &entry->ecx, &entry->edx);
-
}
}
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 1b9ab4166397..e3394c839dea 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6666,7 +6666,6 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
free_vpid(vmx->vpid);
nested_vmx_free_vcpu(vcpu);
free_loaded_vmcs(vmx->loaded_vmcs);
- kfree(vmx->guest_msrs);
kvm_vcpu_uninit(vcpu);
kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu);
kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu);
@@ -6723,12 +6722,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
goto uninit_vcpu;
}
- vmx->guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL_ACCOUNT);
- BUILD_BUG_ON(ARRAY_SIZE(vmx_msr_index) * sizeof(vmx->guest_msrs[0])
- > PAGE_SIZE);
-
- if (!vmx->guest_msrs)
- goto free_pml;
+ BUILD_BUG_ON(ARRAY_SIZE(vmx_msr_index) != NR_SHARED_MSRS);
for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i) {
u32 index = vmx_msr_index[i];
@@ -6760,7 +6754,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
err = alloc_loaded_vmcs(&vmx->vmcs01);
if (err < 0)
- goto free_msrs;
+ goto free_pml;
msr_bitmap = vmx->vmcs01.msr_bitmap;
vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_TSC, MSR_TYPE_R);
@@ -6822,8 +6816,6 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
free_vmcs:
free_loaded_vmcs(vmx->loaded_vmcs);
-free_msrs:
- kfree(vmx->guest_msrs);
free_pml:
vmx_destroy_pml_buffer(vmx);
uninit_vcpu:
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 7c1b978b2df4..a4f7f737c5d4 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -22,6 +22,12 @@ extern u32 get_umwait_control_msr(void);
#define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4))
+#ifdef CONFIG_X86_64
+#define NR_SHARED_MSRS 7
+#else
+#define NR_SHARED_MSRS 4
+#endif
+
#define NR_LOADSTORE_MSRS 8
struct vmx_msrs {
@@ -206,7 +212,7 @@ struct vcpu_vmx {
u32 idt_vectoring_info;
ulong rflags;
- struct shared_msr_entry *guest_msrs;
+ struct shared_msr_entry guest_msrs[NR_SHARED_MSRS];
int nmsrs;
int save_nmsrs;
bool guest_msrs_ready;
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index 0a0e9112f284..8908c58bd6cd 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -695,16 +695,28 @@ AVXcode: 2
4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev)
4e: vrsqrt14ps/d Vpd,Wpd (66),(ev)
4f: vrsqrt14ss/d Vsd,Hsd,Wsd (66),(ev)
-# Skip 0x50-0x57
+50: vpdpbusd Vx,Hx,Wx (66),(ev)
+51: vpdpbusds Vx,Hx,Wx (66),(ev)
+52: vdpbf16ps Vx,Hx,Wx (F3),(ev) | vpdpwssd Vx,Hx,Wx (66),(ev) | vp4dpwssd Vdqq,Hdqq,Wdq (F2),(ev)
+53: vpdpwssds Vx,Hx,Wx (66),(ev) | vp4dpwssds Vdqq,Hdqq,Wdq (F2),(ev)
+54: vpopcntb/w Vx,Wx (66),(ev)
+55: vpopcntd/q Vx,Wx (66),(ev)
58: vpbroadcastd Vx,Wx (66),(v)
59: vpbroadcastq Vx,Wx (66),(v) | vbroadcasti32x2 Vx,Wx (66),(evo)
5a: vbroadcasti128 Vqq,Mdq (66),(v) | vbroadcasti32x4/64x2 Vx,Wx (66),(evo)
5b: vbroadcasti32x8/64x4 Vqq,Mdq (66),(ev)
-# Skip 0x5c-0x63
+# Skip 0x5c-0x61
+62: vpexpandb/w Vx,Wx (66),(ev)
+63: vpcompressb/w Wx,Vx (66),(ev)
64: vpblendmd/q Vx,Hx,Wx (66),(ev)
65: vblendmps/d Vx,Hx,Wx (66),(ev)
66: vpblendmb/w Vx,Hx,Wx (66),(ev)
-# Skip 0x67-0x74
+68: vp2intersectd/q Kx,Hx,Wx (F2),(ev)
+# Skip 0x69-0x6f
+70: vpshldvw Vx,Hx,Wx (66),(ev)
+71: vpshldvd/q Vx,Hx,Wx (66),(ev)
+72: vcvtne2ps2bf16 Vx,Hx,Wx (F2),(ev) | vcvtneps2bf16 Vx,Wx (F3),(ev) | vpshrdvw Vx,Hx,Wx (66),(ev)
+73: vpshrdvd/q Vx,Hx,Wx (66),(ev)
75: vpermi2b/w Vx,Hx,Wx (66),(ev)
76: vpermi2d/q Vx,Hx,Wx (66),(ev)
77: vpermi2ps/d Vx,Hx,Wx (66),(ev)
@@ -727,6 +739,7 @@ AVXcode: 2
8c: vpmaskmovd/q Vx,Hx,Mx (66),(v)
8d: vpermb/w Vx,Hx,Wx (66),(ev)
8e: vpmaskmovd/q Mx,Vx,Hx (66),(v)
+8f: vpshufbitqmb Kx,Hx,Wx (66),(ev)
# 0x0f 0x38 0x90-0xbf (FMA)
90: vgatherdd/q Vx,Hx,Wx (66),(v) | vpgatherdd/q Vx,Wx (66),(evo)
91: vgatherqd/q Vx,Hx,Wx (66),(v) | vpgatherqd/q Vx,Wx (66),(evo)
@@ -738,8 +751,8 @@ AVXcode: 2
97: vfmsubadd132ps/d Vx,Hx,Wx (66),(v)
98: vfmadd132ps/d Vx,Hx,Wx (66),(v)
99: vfmadd132ss/d Vx,Hx,Wx (66),(v),(v1)
-9a: vfmsub132ps/d Vx,Hx,Wx (66),(v)
-9b: vfmsub132ss/d Vx,Hx,Wx (66),(v),(v1)
+9a: vfmsub132ps/d Vx,Hx,Wx (66),(v) | v4fmaddps Vdqq,Hdqq,Wdq (F2),(ev)
+9b: vfmsub132ss/d Vx,Hx,Wx (66),(v),(v1) | v4fmaddss Vdq,Hdq,Wdq (F2),(ev)
9c: vfnmadd132ps/d Vx,Hx,Wx (66),(v)
9d: vfnmadd132ss/d Vx,Hx,Wx (66),(v),(v1)
9e: vfnmsub132ps/d Vx,Hx,Wx (66),(v)
@@ -752,8 +765,8 @@ a6: vfmaddsub213ps/d Vx,Hx,Wx (66),(v)
a7: vfmsubadd213ps/d Vx,Hx,Wx (66),(v)
a8: vfmadd213ps/d Vx,Hx,Wx (66),(v)
a9: vfmadd213ss/d Vx,Hx,Wx (66),(v),(v1)
-aa: vfmsub213ps/d Vx,Hx,Wx (66),(v)
-ab: vfmsub213ss/d Vx,Hx,Wx (66),(v),(v1)
+aa: vfmsub213ps/d Vx,Hx,Wx (66),(v) | v4fnmaddps Vdqq,Hdqq,Wdq (F2),(ev)
+ab: vfmsub213ss/d Vx,Hx,Wx (66),(v),(v1) | v4fnmaddss Vdq,Hdq,Wdq (F2),(ev)
ac: vfnmadd213ps/d Vx,Hx,Wx (66),(v)
ad: vfnmadd213ss/d Vx,Hx,Wx (66),(v),(v1)
ae: vfnmsub213ps/d Vx,Hx,Wx (66),(v)
@@ -780,11 +793,12 @@ ca: sha1msg2 Vdq,Wdq | vrcp28ps/d Vx,Wx (66),(ev)
cb: sha256rnds2 Vdq,Wdq | vrcp28ss/d Vx,Hx,Wx (66),(ev)
cc: sha256msg1 Vdq,Wdq | vrsqrt28ps/d Vx,Wx (66),(ev)
cd: sha256msg2 Vdq,Wdq | vrsqrt28ss/d Vx,Hx,Wx (66),(ev)
+cf: vgf2p8mulb Vx,Wx (66)
db: VAESIMC Vdq,Wdq (66),(v1)
-dc: VAESENC Vdq,Hdq,Wdq (66),(v1)
-dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1)
-de: VAESDEC Vdq,Hdq,Wdq (66),(v1)
-df: VAESDECLAST Vdq,Hdq,Wdq (66),(v1)
+dc: vaesenc Vx,Hx,Wx (66)
+dd: vaesenclast Vx,Hx,Wx (66)
+de: vaesdec Vx,Hx,Wx (66)
+df: vaesdeclast Vx,Hx,Wx (66)
f0: MOVBE Gy,My | MOVBE Gw,Mw (66) | CRC32 Gd,Eb (F2) | CRC32 Gd,Eb (66&F2)
f1: MOVBE My,Gy | MOVBE Mw,Gw (66) | CRC32 Gd,Ey (F2) | CRC32 Gd,Ew (66&F2)
f2: ANDN Gy,By,Ey (v)
@@ -848,7 +862,7 @@ AVXcode: 3
41: vdppd Vdq,Hdq,Wdq,Ib (66),(v1)
42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1) | vdbpsadbw Vx,Hx,Wx,Ib (66),(evo)
43: vshufi32x4/64x2 Vx,Hx,Wx,Ib (66),(ev)
-44: vpclmulqdq Vdq,Hdq,Wdq,Ib (66),(v1)
+44: vpclmulqdq Vx,Hx,Wx,Ib (66)
46: vperm2i128 Vqq,Hqq,Wqq,Ib (66),(v)
4a: vblendvps Vx,Hx,Wx,Lx (66),(v)
4b: vblendvpd Vx,Hx,Wx,Lx (66),(v)
@@ -865,7 +879,13 @@ AVXcode: 3
63: vpcmpistri Vdq,Wdq,Ib (66),(v1)
66: vfpclassps/d Vk,Wx,Ib (66),(ev)
67: vfpclassss/d Vk,Wx,Ib (66),(ev)
+70: vpshldw Vx,Hx,Wx,Ib (66),(ev)
+71: vpshldd/q Vx,Hx,Wx,Ib (66),(ev)
+72: vpshrdw Vx,Hx,Wx,Ib (66),(ev)
+73: vpshrdd/q Vx,Hx,Wx,Ib (66),(ev)
cc: sha1rnds4 Vdq,Wdq,Ib
+ce: vgf2p8affineqb Vx,Wx,Ib (66)
+cf: vgf2p8affineinvqb Vx,Wx,Ib (66)
df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1)
f0: RORX Gy,Ey,Ib (F2),(v)
EndTable
diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c
index 82ead8e27888..56f9189bbadb 100644
--- a/arch/x86/mm/cpu_entry_area.c
+++ b/arch/x86/mm/cpu_entry_area.c
@@ -17,6 +17,10 @@ static DEFINE_PER_CPU_PAGE_ALIGNED(struct exception_stacks, exception_stacks);
DEFINE_PER_CPU(struct cea_exception_stacks*, cea_exception_stacks);
#endif
+#if defined(CONFIG_X86_32) && defined(CONFIG_DOUBLEFAULT)
+DECLARE_PER_CPU_PAGE_ALIGNED(struct doublefault_stack, doublefault_stack);
+#endif
+
struct cpu_entry_area *get_cpu_entry_area(int cpu)
{
unsigned long va = CPU_ENTRY_AREA_PER_CPU + cpu * CPU_ENTRY_AREA_SIZE;
@@ -108,7 +112,15 @@ static void __init percpu_setup_exception_stacks(unsigned int cpu)
cea_map_stack(MCE);
}
#else
-static inline void percpu_setup_exception_stacks(unsigned int cpu) {}
+static inline void percpu_setup_exception_stacks(unsigned int cpu)
+{
+#ifdef CONFIG_DOUBLEFAULT
+ struct cpu_entry_area *cea = get_cpu_entry_area(cpu);
+
+ cea_map_percpu_pages(&cea->doublefault_stack,
+ &per_cpu(doublefault_stack, cpu), 1, PAGE_KERNEL);
+#endif
+}
#endif
/* Setup the fixmap mappings only once per-processor */
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 9ceacd1156db..304d31d8cbbc 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -197,7 +197,7 @@ void vmalloc_sync_all(void)
return;
for (address = VMALLOC_START & PMD_MASK;
- address >= TASK_SIZE_MAX && address < FIXADDR_TOP;
+ address >= TASK_SIZE_MAX && address < VMALLOC_END;
address += PMD_SIZE) {
struct page *page;
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index 296da58f3013..cf5bc37c90ac 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -245,6 +245,49 @@ static void __init kasan_map_early_shadow(pgd_t *pgd)
} while (pgd++, addr = next, addr != end);
}
+static void __init kasan_shallow_populate_p4ds(pgd_t *pgd,
+ unsigned long addr,
+ unsigned long end)
+{
+ p4d_t *p4d;
+ unsigned long next;
+ void *p;
+
+ p4d = p4d_offset(pgd, addr);
+ do {
+ next = p4d_addr_end(addr, end);
+
+ if (p4d_none(*p4d)) {
+ p = early_alloc(PAGE_SIZE, NUMA_NO_NODE, true);
+ p4d_populate(&init_mm, p4d, p);
+ }
+ } while (p4d++, addr = next, addr != end);
+}
+
+static void __init kasan_shallow_populate_pgds(void *start, void *end)
+{
+ unsigned long addr, next;
+ pgd_t *pgd;
+ void *p;
+
+ addr = (unsigned long)start;
+ pgd = pgd_offset_k(addr);
+ do {
+ next = pgd_addr_end(addr, (unsigned long)end);
+
+ if (pgd_none(*pgd)) {
+ p = early_alloc(PAGE_SIZE, NUMA_NO_NODE, true);
+ pgd_populate(&init_mm, pgd, p);
+ }
+
+ /*
+ * we need to populate p4ds to be synced when running in
+ * four level mode - see sync_global_pgds_l4()
+ */
+ kasan_shallow_populate_p4ds(pgd, addr, next);
+ } while (pgd++, addr = next, addr != (unsigned long)end);
+}
+
#ifdef CONFIG_KASAN_INLINE
static int kasan_die_handler(struct notifier_block *self,
unsigned long val,
@@ -354,6 +397,24 @@ void __init kasan_init(void)
kasan_populate_early_shadow(
kasan_mem_to_shadow((void *)PAGE_OFFSET + MAXMEM),
+ kasan_mem_to_shadow((void *)VMALLOC_START));
+
+ /*
+ * If we're in full vmalloc mode, don't back vmalloc space with early
+ * shadow pages. Instead, prepopulate pgds/p4ds so they are synced to
+ * the global table and we can populate the lower levels on demand.
+ */
+ if (IS_ENABLED(CONFIG_KASAN_VMALLOC))
+ kasan_shallow_populate_pgds(
+ kasan_mem_to_shadow((void *)VMALLOC_START),
+ kasan_mem_to_shadow((void *)VMALLOC_END));
+ else
+ kasan_populate_early_shadow(
+ kasan_mem_to_shadow((void *)VMALLOC_START),
+ kasan_mem_to_shadow((void *)VMALLOC_END));
+
+ kasan_populate_early_shadow(
+ kasan_mem_to_shadow((void *)VMALLOC_END + 1),
shadow_cpu_entry_begin);
kasan_populate_shadow((unsigned long)shadow_cpu_entry_begin,
diff --git a/arch/x86/mm/pat_interval.c b/arch/x86/mm/pat_interval.c
index 47a1bf30748f..6855362eaf21 100644
--- a/arch/x86/mm/pat_interval.c
+++ b/arch/x86/mm/pat_interval.c
@@ -56,7 +56,7 @@ static struct memtype *memtype_match(u64 start, u64 end, int match_type)
{
struct memtype *match;
- match = memtype_interval_iter_first(&memtype_rbroot, start, end);
+ match = memtype_interval_iter_first(&memtype_rbroot, start, end-1);
while (match != NULL && match->start < end) {
if ((match_type == MEMTYPE_EXACT_MATCH) &&
(match->start == start) && (match->end == end))
@@ -66,7 +66,7 @@ static struct memtype *memtype_match(u64 start, u64 end, int match_type)
(match->start < start) && (match->end == end))
return match;
- match = memtype_interval_iter_next(match, start, end);
+ match = memtype_interval_iter_next(match, start, end-1);
}
return NULL; /* Returns NULL if there is no match */
@@ -79,7 +79,7 @@ static int memtype_check_conflict(u64 start, u64 end,
struct memtype *match;
enum page_cache_mode found_type = reqtype;
- match = memtype_interval_iter_first(&memtype_rbroot, start, end);
+ match = memtype_interval_iter_first(&memtype_rbroot, start, end-1);
if (match == NULL)
goto success;
@@ -89,12 +89,12 @@ static int memtype_check_conflict(u64 start, u64 end,
dprintk("Overlap at 0x%Lx-0x%Lx\n", match->start, match->end);
found_type = match->type;
- match = memtype_interval_iter_next(match, start, end);
+ match = memtype_interval_iter_next(match, start, end-1);
while (match) {
if (match->type != found_type)
goto failure;
- match = memtype_interval_iter_next(match, start, end);
+ match = memtype_interval_iter_next(match, start, end-1);
}
success:
if (newtype)
@@ -160,7 +160,7 @@ struct memtype *memtype_erase(u64 start, u64 end)
struct memtype *memtype_lookup(u64 addr)
{
return memtype_interval_iter_first(&memtype_rbroot, addr,
- addr + PAGE_SIZE);
+ addr + PAGE_SIZE-1);
}
#if defined(CONFIG_DEBUG_FS)
diff --git a/arch/x86/pci/Makefile b/arch/x86/pci/Makefile
index c806b57d3f22..48bcada5cabe 100644
--- a/arch/x86/pci/Makefile
+++ b/arch/x86/pci/Makefile
@@ -24,6 +24,4 @@ obj-y += bus_numa.o
obj-$(CONFIG_AMD_NB) += amd_bus.o
obj-$(CONFIG_PCI_CNB20LE_QUIRK) += broadcom_bus.o
-ifeq ($(CONFIG_PCI_DEBUG),y)
-EXTRA_CFLAGS += -DDEBUG
-endif
+ccflags-$(CONFIG_PCI_DEBUG) += -DDEBUG
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 9acab6ac28f5..1e59df041456 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -135,7 +135,7 @@ static void pcibios_fixup_device_resources(struct pci_dev *dev)
* resource so the kernel doesn't attempt to assign
* it later on in pci_assign_unassigned_resources
*/
- for (bar = 0; bar <= PCI_STD_RESOURCE_END; bar++) {
+ for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) {
bar_r = &dev->resource[bar];
if (bar_r->start == 0 && bar_r->end != 0) {
bar_r->flags = 0;
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index 527e69b12002..e723559c386a 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -589,6 +589,17 @@ static void pci_fixup_amd_ehci_pme(struct pci_dev *dev)
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x7808, pci_fixup_amd_ehci_pme);
/*
+ * Device [1022:7914]
+ * When in D0, PME# doesn't get asserted when plugging USB 2.0 device.
+ */
+static void pci_fixup_amd_fch_xhci_pme(struct pci_dev *dev)
+{
+ dev_info(&dev->dev, "PME# does not work under D0, disabling it\n");
+ dev->pme_support &= ~(PCI_PM_CAP_PME_D0 >> PCI_PM_CAP_PME_SHIFT);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x7914, pci_fixup_amd_fch_xhci_pme);
+
+/*
* Apple MacBook Pro: Avoid [mem 0x7fa00000-0x7fbfffff]
*
* Using the [mem 0x7fa00000-0x7fbfffff] region, e.g., by assigning it to
diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c
index 43867bc85368..00c62115f39c 100644
--- a/arch/x86/pci/intel_mid_pci.c
+++ b/arch/x86/pci/intel_mid_pci.c
@@ -382,7 +382,7 @@ static void pci_fixed_bar_fixup(struct pci_dev *dev)
PCI_DEVFN(2, 2) == dev->devfn)
return;
- for (i = 0; i < PCI_ROM_RESOURCE; i++) {
+ for (i = 0; i < PCI_STD_NUM_BARS; i++) {
pci_read_config_dword(dev, offset + 8 + (i * 4), &size);
dev->resource[i].end = dev->resource[i].start + size - 1;
dev->resource[i].flags |= IORESOURCE_PCI_FIXED;
diff --git a/arch/x86/pci/numachip.c b/arch/x86/pci/numachip.c
index 2e565e65c893..01a085d9135a 100644
--- a/arch/x86/pci/numachip.c
+++ b/arch/x86/pci/numachip.c
@@ -1,8 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- *
* Numascale NumaConnect-specific PCI code
*
* Copyright (C) 2012 Numascale AS. All rights reserved.
diff --git a/arch/x86/platform/olpc/olpc-xo1-pm.c b/arch/x86/platform/olpc/olpc-xo1-pm.c
index e1a32062a375..f067ac780ba7 100644
--- a/arch/x86/platform/olpc/olpc-xo1-pm.c
+++ b/arch/x86/platform/olpc/olpc-xo1-pm.c
@@ -12,7 +12,6 @@
#include <linux/platform_device.h>
#include <linux/export.h>
#include <linux/pm.h>
-#include <linux/mfd/core.h>
#include <linux/suspend.h>
#include <linux/olpc-ec.h>
@@ -120,16 +119,11 @@ static const struct platform_suspend_ops xo1_suspend_ops = {
static int xo1_pm_probe(struct platform_device *pdev)
{
struct resource *res;
- int err;
/* don't run on non-XOs */
if (!machine_is_olpc())
return -ENODEV;
- err = mfd_cell_enable(pdev);
- if (err)
- return err;
-
res = platform_get_resource(pdev, IORESOURCE_IO, 0);
if (!res) {
dev_err(&pdev->dev, "can't fetch device resource info\n");
@@ -152,8 +146,6 @@ static int xo1_pm_probe(struct platform_device *pdev)
static int xo1_pm_remove(struct platform_device *pdev)
{
- mfd_cell_disable(pdev);
-
if (strcmp(pdev->name, "cs5535-pms") == 0)
pms_base = 0;
else if (strcmp(pdev->name, "olpc-xo1-pm-acpi") == 0)
diff --git a/arch/x86/platform/olpc/olpc-xo1-sci.c b/arch/x86/platform/olpc/olpc-xo1-sci.c
index 99a28ce2244c..933dd4fe3a97 100644
--- a/arch/x86/platform/olpc/olpc-xo1-sci.c
+++ b/arch/x86/platform/olpc/olpc-xo1-sci.c
@@ -15,7 +15,6 @@
#include <linux/platform_device.h>
#include <linux/pm.h>
#include <linux/pm_wakeup.h>
-#include <linux/mfd/core.h>
#include <linux/power_supply.h>
#include <linux/suspend.h>
#include <linux/workqueue.h>
@@ -537,10 +536,6 @@ static int xo1_sci_probe(struct platform_device *pdev)
if (!machine_is_olpc())
return -ENODEV;
- r = mfd_cell_enable(pdev);
- if (r)
- return r;
-
res = platform_get_resource(pdev, IORESOURCE_IO, 0);
if (!res) {
dev_err(&pdev->dev, "can't fetch device resource info\n");
@@ -605,7 +600,6 @@ err_ebook:
static int xo1_sci_remove(struct platform_device *pdev)
{
- mfd_cell_disable(pdev);
free_irq(sci_irq, pdev);
cancel_work_sync(&sci_work);
free_ec_sci();
diff --git a/arch/x86/um/vdso/um_vdso.c b/arch/x86/um/vdso/um_vdso.c
index 891868756a51..2112b8d14668 100644
--- a/arch/x86/um/vdso/um_vdso.c
+++ b/arch/x86/um/vdso/um_vdso.c
@@ -13,7 +13,7 @@
#include <linux/getcpu.h>
#include <asm/unistd.h>
-int __vdso_clock_gettime(clockid_t clock, struct timespec *ts)
+int __vdso_clock_gettime(clockid_t clock, struct __kernel_old_timespec *ts)
{
long ret;
@@ -22,10 +22,10 @@ int __vdso_clock_gettime(clockid_t clock, struct timespec *ts)
return ret;
}
-int clock_gettime(clockid_t, struct timespec *)
+int clock_gettime(clockid_t, struct __kernel_old_timespec *)
__attribute__((weak, alias("__vdso_clock_gettime")));
-int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
+int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
{
long ret;
@@ -34,10 +34,10 @@ int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
return ret;
}
-int gettimeofday(struct timeval *, struct timezone *)
+int gettimeofday(struct __kernel_old_timeval *, struct timezone *)
__attribute__((weak, alias("__vdso_gettimeofday")));
-time_t __vdso_time(time_t *t)
+__kernel_old_time_t __vdso_time(__kernel_old_time_t *t)
{
long secs;
@@ -47,7 +47,7 @@ time_t __vdso_time(time_t *t)
return secs;
}
-time_t time(time_t *t) __attribute__((weak, alias("__vdso_time")));
+__kernel_old_time_t time(__kernel_old_time_t *t) __attribute__((weak, alias("__vdso_time")));
long
__vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused)