aboutsummaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/boot/compressed/eboot.c4
-rw-r--r--arch/x86/entry/entry_64_compat.S14
-rw-r--r--arch/x86/include/asm/desc.h15
-rw-r--r--arch/x86/include/asm/mmu.h3
-rw-r--r--arch/x86/include/asm/mmu_context.h54
-rw-r--r--arch/x86/include/uapi/asm/kvm.h4
-rw-r--r--arch/x86/kernel/apic/io_apic.c2
-rw-r--r--arch/x86/kernel/cpu/common.c4
-rw-r--r--arch/x86/kernel/cpu/perf_event.c12
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_cqm.c8
-rw-r--r--arch/x86/kernel/fpu/init.c6
-rw-r--r--arch/x86/kernel/ldt.c262
-rw-r--r--arch/x86/kernel/process_64.c4
-rw-r--r--arch/x86/kernel/step.c6
-rw-r--r--arch/x86/kvm/lapic.c2
-rw-r--r--arch/x86/kvm/mtrr.c40
-rw-r--r--arch/x86/kvm/svm.c2
-rw-r--r--arch/x86/kvm/vmx.c5
-rw-r--r--arch/x86/kvm/x86.h5
-rw-r--r--arch/x86/mm/ioremap.c23
-rw-r--r--arch/x86/mm/mmap.c7
-rw-r--r--arch/x86/mm/mpx.c24
-rw-r--r--arch/x86/mm/tlb.c2
-rw-r--r--arch/x86/net/bpf_jit_comp.c8
-rw-r--r--arch/x86/platform/efi/efi.c5
-rw-r--r--arch/x86/power/cpu.c3
-rw-r--r--arch/x86/xen/enlighten.c40
27 files changed, 347 insertions, 217 deletions
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index 2c82bd150d43..7d69afd8b6fa 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -1193,6 +1193,10 @@ static efi_status_t setup_e820(struct boot_params *params,
unsigned int e820_type = 0;
unsigned long m = efi->efi_memmap;
+#ifdef CONFIG_X86_64
+ m |= (u64)efi->efi_memmap_hi << 32;
+#endif
+
d = (efi_memory_desc_t *)(m + (i * efi->efi_memdesc_size));
switch (d->type) {
case EFI_RESERVED_TYPE:
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index bb187a6a877c..5a1844765a7a 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -205,7 +205,6 @@ sysexit_from_sys_call:
movl RDX(%rsp), %edx /* arg3 */
movl RSI(%rsp), %ecx /* arg4 */
movl RDI(%rsp), %r8d /* arg5 */
- movl %ebp, %r9d /* arg6 */
.endm
.macro auditsys_exit exit
@@ -236,6 +235,7 @@ sysexit_from_sys_call:
sysenter_auditsys:
auditsys_entry_common
+ movl %ebp, %r9d /* reload 6th syscall arg */
jmp sysenter_dispatch
sysexit_audit:
@@ -336,7 +336,7 @@ ENTRY(entry_SYSCALL_compat)
* 32-bit zero extended:
*/
ASM_STAC
-1: movl (%r8), %ebp
+1: movl (%r8), %r9d
_ASM_EXTABLE(1b, ia32_badarg)
ASM_CLAC
orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
@@ -346,7 +346,7 @@ ENTRY(entry_SYSCALL_compat)
cstar_do_call:
/* 32-bit syscall -> 64-bit C ABI argument conversion */
movl %edi, %r8d /* arg5 */
- movl %ebp, %r9d /* arg6 */
+ /* r9 already loaded */ /* arg6 */
xchg %ecx, %esi /* rsi:arg2, rcx:arg4 */
movl %ebx, %edi /* arg1 */
movl %edx, %edx /* arg3 (zero extension) */
@@ -358,7 +358,6 @@ cstar_dispatch:
call *ia32_sys_call_table(, %rax, 8)
movq %rax, RAX(%rsp)
1:
- movl RCX(%rsp), %ebp
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
@@ -392,7 +391,9 @@ sysretl_from_sys_call:
#ifdef CONFIG_AUDITSYSCALL
cstar_auditsys:
+ movl %r9d, R9(%rsp) /* register to be clobbered by call */
auditsys_entry_common
+ movl R9(%rsp), %r9d /* reload 6th syscall arg */
jmp cstar_dispatch
sysretl_audit:
@@ -404,14 +405,16 @@ cstar_tracesys:
testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
jz cstar_auditsys
#endif
+ xchgl %r9d, %ebp
SAVE_EXTRA_REGS
xorl %eax, %eax /* Do not leak kernel information */
movq %rax, R11(%rsp)
movq %rax, R10(%rsp)
- movq %rax, R9(%rsp)
+ movq %r9, R9(%rsp)
movq %rax, R8(%rsp)
movq %rsp, %rdi /* &pt_regs -> arg1 */
call syscall_trace_enter
+ movl R9(%rsp), %r9d
/* Reload arg registers from stack. (see sysenter_tracesys) */
movl RCX(%rsp), %ecx
@@ -421,6 +424,7 @@ cstar_tracesys:
movl %eax, %eax /* zero extension */
RESTORE_EXTRA_REGS
+ xchgl %ebp, %r9d
jmp cstar_do_call
END(entry_SYSCALL_compat)
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index a0bf89fd2647..4e10d73cf018 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -280,21 +280,6 @@ static inline void clear_LDT(void)
set_ldt(NULL, 0);
}
-/*
- * load one particular LDT into the current CPU
- */
-static inline void load_LDT_nolock(mm_context_t *pc)
-{
- set_ldt(pc->ldt, pc->size);
-}
-
-static inline void load_LDT(mm_context_t *pc)
-{
- preempt_disable();
- load_LDT_nolock(pc);
- preempt_enable();
-}
-
static inline unsigned long get_desc_base(const struct desc_struct *desc)
{
return (unsigned)(desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24));
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 09b9620a73b4..364d27481a52 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -9,8 +9,7 @@
* we put the segment information here.
*/
typedef struct {
- void *ldt;
- int size;
+ struct ldt_struct *ldt;
#ifdef CONFIG_X86_64
/* True if mm supports a task running in 32 bit compatibility mode. */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 804a3a6030ca..984abfe47edc 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -34,6 +34,50 @@ static inline void load_mm_cr4(struct mm_struct *mm) {}
#endif
/*
+ * ldt_structs can be allocated, used, and freed, but they are never
+ * modified while live.
+ */
+struct ldt_struct {
+ /*
+ * Xen requires page-aligned LDTs with special permissions. This is
+ * needed to prevent us from installing evil descriptors such as
+ * call gates. On native, we could merge the ldt_struct and LDT
+ * allocations, but it's not worth trying to optimize.
+ */
+ struct desc_struct *entries;
+ int size;
+};
+
+static inline void load_mm_ldt(struct mm_struct *mm)
+{
+ struct ldt_struct *ldt;
+
+ /* lockless_dereference synchronizes with smp_store_release */
+ ldt = lockless_dereference(mm->context.ldt);
+
+ /*
+ * Any change to mm->context.ldt is followed by an IPI to all
+ * CPUs with the mm active. The LDT will not be freed until
+ * after the IPI is handled by all such CPUs. This means that,
+ * if the ldt_struct changes before we return, the values we see
+ * will be safe, and the new values will be loaded before we run
+ * any user code.
+ *
+ * NB: don't try to convert this to use RCU without extreme care.
+ * We would still need IRQs off, because we don't want to change
+ * the local LDT after an IPI loaded a newer value than the one
+ * that we can see.
+ */
+
+ if (unlikely(ldt))
+ set_ldt(ldt->entries, ldt->size);
+ else
+ clear_LDT();
+
+ DEBUG_LOCKS_WARN_ON(preemptible());
+}
+
+/*
* Used for LDT copy/destruction.
*/
int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
@@ -78,12 +122,12 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
* was called and then modify_ldt changed
* prev->context.ldt but suppressed an IPI to this CPU.
* In this case, prev->context.ldt != NULL, because we
- * never free an LDT while the mm still exists. That
- * means that next->context.ldt != prev->context.ldt,
- * because mms never share an LDT.
+ * never set context.ldt to NULL while the mm still
+ * exists. That means that next->context.ldt !=
+ * prev->context.ldt, because mms never share an LDT.
*/
if (unlikely(prev->context.ldt != next->context.ldt))
- load_LDT_nolock(&next->context);
+ load_mm_ldt(next);
}
#ifdef CONFIG_SMP
else {
@@ -106,7 +150,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
load_cr3(next->pgd);
trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
load_mm_cr4(next);
- load_LDT_nolock(&next->context);
+ load_mm_ldt(next);
}
}
#endif
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index a4ae82eb82aa..cd54147cb365 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -354,7 +354,7 @@ struct kvm_xcrs {
struct kvm_sync_regs {
};
-#define KVM_QUIRK_LINT0_REENABLED (1 << 0)
-#define KVM_QUIRK_CD_NW_CLEARED (1 << 1)
+#define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0)
+#define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1)
#endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 845dc0df2002..206052e55517 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -943,7 +943,7 @@ static bool mp_check_pin_attr(int irq, struct irq_alloc_info *info)
*/
if (irq < nr_legacy_irqs() && data->count == 1) {
if (info->ioapic_trigger != data->trigger)
- mp_register_handler(irq, data->trigger);
+ mp_register_handler(irq, info->ioapic_trigger);
data->entry.trigger = data->trigger = info->ioapic_trigger;
data->entry.polarity = data->polarity = info->ioapic_polarity;
}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 922c5e0cea4c..cb9e5df42dd2 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1410,7 +1410,7 @@ void cpu_init(void)
load_sp0(t, &current->thread);
set_tss_desc(cpu, t);
load_TR_desc();
- load_LDT(&init_mm.context);
+ load_mm_ldt(&init_mm);
clear_all_debug_regs();
dbg_restore_debug_regs();
@@ -1459,7 +1459,7 @@ void cpu_init(void)
load_sp0(t, thread);
set_tss_desc(cpu, t);
load_TR_desc();
- load_LDT(&init_mm.context);
+ load_mm_ldt(&init_mm);
t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap);
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 3658de47900f..9469dfa55607 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -2179,21 +2179,25 @@ static unsigned long get_segment_base(unsigned int segment)
int idx = segment >> 3;
if ((segment & SEGMENT_TI_MASK) == SEGMENT_LDT) {
+ struct ldt_struct *ldt;
+
if (idx > LDT_ENTRIES)
return 0;
- if (idx > current->active_mm->context.size)
+ /* IRQs are off, so this synchronizes with smp_store_release */
+ ldt = lockless_dereference(current->active_mm->context.ldt);
+ if (!ldt || idx > ldt->size)
return 0;
- desc = current->active_mm->context.ldt;
+ desc = &ldt->entries[idx];
} else {
if (idx > GDT_ENTRIES)
return 0;
- desc = raw_cpu_ptr(gdt_page.gdt);
+ desc = raw_cpu_ptr(gdt_page.gdt) + idx;
}
- return get_desc_base(desc + idx);
+ return get_desc_base(desc);
}
#ifdef CONFIG_COMPAT
diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
index 188076161c1b..63eb68b73589 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
@@ -952,6 +952,14 @@ static u64 intel_cqm_event_count(struct perf_event *event)
return 0;
/*
+ * Getting up-to-date values requires an SMP IPI which is not
+ * possible if we're being called in interrupt context. Return
+ * the cached values instead.
+ */
+ if (unlikely(in_interrupt()))
+ goto out;
+
+ /*
* Notice that we don't perform the reading of an RMID
* atomically, because we can't hold a spin lock across the
* IPIs.
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 0b39173dd971..1e173f6285c7 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -351,9 +351,15 @@ static int __init x86_noxsave_setup(char *s)
setup_clear_cpu_cap(X86_FEATURE_XSAVE);
setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
+ setup_clear_cpu_cap(X86_FEATURE_XSAVEC);
setup_clear_cpu_cap(X86_FEATURE_XSAVES);
setup_clear_cpu_cap(X86_FEATURE_AVX);
setup_clear_cpu_cap(X86_FEATURE_AVX2);
+ setup_clear_cpu_cap(X86_FEATURE_AVX512F);
+ setup_clear_cpu_cap(X86_FEATURE_AVX512PF);
+ setup_clear_cpu_cap(X86_FEATURE_AVX512ER);
+ setup_clear_cpu_cap(X86_FEATURE_AVX512CD);
+ setup_clear_cpu_cap(X86_FEATURE_MPX);
return 1;
}
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index c37886d759cc..2bcc0525f1c1 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -12,6 +12,7 @@
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/smp.h>
+#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/uaccess.h>
@@ -20,82 +21,82 @@
#include <asm/mmu_context.h>
#include <asm/syscalls.h>
-#ifdef CONFIG_SMP
+/* context.lock is held for us, so we don't need any locking. */
static void flush_ldt(void *current_mm)
{
- if (current->active_mm == current_mm)
- load_LDT(&current->active_mm->context);
+ mm_context_t *pc;
+
+ if (current->active_mm != current_mm)
+ return;
+
+ pc = &current->active_mm->context;
+ set_ldt(pc->ldt->entries, pc->ldt->size);
}
-#endif
-static int alloc_ldt(mm_context_t *pc, int mincount, int reload)
+/* The caller must call finalize_ldt_struct on the result. LDT starts zeroed. */
+static struct ldt_struct *alloc_ldt_struct(int size)
{
- void *oldldt, *newldt;
- int oldsize;
-
- if (mincount <= pc->size)
- return 0;
- oldsize = pc->size;
- mincount = (mincount + (PAGE_SIZE / LDT_ENTRY_SIZE - 1)) &
- (~(PAGE_SIZE / LDT_ENTRY_SIZE - 1));
- if (mincount * LDT_ENTRY_SIZE > PAGE_SIZE)
- newldt = vmalloc(mincount * LDT_ENTRY_SIZE);
+ struct ldt_struct *new_ldt;
+ int alloc_size;
+
+ if (size > LDT_ENTRIES)
+ return NULL;
+
+ new_ldt = kmalloc(sizeof(struct ldt_struct), GFP_KERNEL);
+ if (!new_ldt)
+ return NULL;
+
+ BUILD_BUG_ON(LDT_ENTRY_SIZE != sizeof(struct desc_struct));
+ alloc_size = size * LDT_ENTRY_SIZE;
+
+ /*
+ * Xen is very picky: it requires a page-aligned LDT that has no
+ * trailing nonzero bytes in any page that contains LDT descriptors.
+ * Keep it simple: zero the whole allocation and never allocate less
+ * than PAGE_SIZE.
+ */
+ if (alloc_size > PAGE_SIZE)
+ new_ldt->entries = vzalloc(alloc_size);
else
- newldt = (void *)__get_free_page(GFP_KERNEL);
-
- if (!newldt)
- return -ENOMEM;
+ new_ldt->entries = kzalloc(PAGE_SIZE, GFP_KERNEL);
- if (oldsize)
- memcpy(newldt, pc->ldt, oldsize * LDT_ENTRY_SIZE);
- oldldt = pc->ldt;
- memset(newldt + oldsize * LDT_ENTRY_SIZE, 0,
- (mincount - oldsize) * LDT_ENTRY_SIZE);
+ if (!new_ldt->entries) {
+ kfree(new_ldt);
+ return NULL;
+ }
- paravirt_alloc_ldt(newldt, mincount);
+ new_ldt->size = size;
+ return new_ldt;
+}
-#ifdef CONFIG_X86_64
- /* CHECKME: Do we really need this ? */
- wmb();
-#endif
- pc->ldt = newldt;
- wmb();
- pc->size = mincount;
- wmb();
-
- if (reload) {
-#ifdef CONFIG_SMP
- preempt_disable();
- load_LDT(pc);
- if (!cpumask_equal(mm_cpumask(current->mm),
- cpumask_of(smp_processor_id())))
- smp_call_function(flush_ldt, current->mm, 1);
- preempt_enable();
-#else
- load_LDT(pc);
-#endif
- }
- if (oldsize) {
- paravirt_free_ldt(oldldt, oldsize);
- if (oldsize * LDT_ENTRY_SIZE > PAGE_SIZE)
- vfree(oldldt);
- else
- put_page(virt_to_page(oldldt));
- }
- return 0;
+/* After calling this, the LDT is immutable. */
+static void finalize_ldt_struct(struct ldt_struct *ldt)
+{
+ paravirt_alloc_ldt(ldt->entries, ldt->size);
}
-static inline int copy_ldt(mm_context_t *new, mm_context_t *old)
+/* context.lock is held */
+static void install_ldt(struct mm_struct *current_mm,
+ struct ldt_struct *ldt)
{
- int err = alloc_ldt(new, old->size, 0);
- int i;
+ /* Synchronizes with lockless_dereference in load_mm_ldt. */
+ smp_store_release(&current_mm->context.ldt, ldt);
+
+ /* Activate the LDT for all CPUs using current_mm. */
+ on_each_cpu_mask(mm_cpumask(current_mm), flush_ldt, current_mm, true);
+}
- if (err < 0)
- return err;
+static void free_ldt_struct(struct ldt_struct *ldt)
+{
+ if (likely(!ldt))
+ return;
- for (i = 0; i < old->size; i++)
- write_ldt_entry(new->ldt, i, old->ldt + i * LDT_ENTRY_SIZE);
- return 0;
+ paravirt_free_ldt(ldt->entries, ldt->size);
+ if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE)
+ vfree(ldt->entries);
+ else
+ kfree(ldt->entries);
+ kfree(ldt);
}
/*
@@ -104,17 +105,37 @@ static inline int copy_ldt(mm_context_t *new, mm_context_t *old)
*/
int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
{
+ struct ldt_struct *new_ldt;
struct mm_struct *old_mm;
int retval = 0;
mutex_init(&mm->context.lock);
- mm->context.size = 0;
old_mm = current->mm;
- if (old_mm && old_mm->context.size > 0) {
- mutex_lock(&old_mm->context.lock);
- retval = copy_ldt(&mm->context, &old_mm->context);
- mutex_unlock(&old_mm->context.lock);
+ if (!old_mm) {
+ mm->context.ldt = NULL;
+ return 0;
}
+
+ mutex_lock(&old_mm->context.lock);
+ if (!old_mm->context.ldt) {
+ mm->context.ldt = NULL;
+ goto out_unlock;
+ }
+
+ new_ldt = alloc_ldt_struct(old_mm->context.ldt->size);
+ if (!new_ldt) {
+ retval = -ENOMEM;
+ goto out_unlock;
+ }
+
+ memcpy(new_ldt->entries, old_mm->context.ldt->entries,
+ new_ldt->size * LDT_ENTRY_SIZE);
+ finalize_ldt_struct(new_ldt);
+
+ mm->context.ldt = new_ldt;
+
+out_unlock:
+ mutex_unlock(&old_mm->context.lock);
return retval;
}
@@ -125,53 +146,47 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
*/
void destroy_context(struct mm_struct *mm)
{
- if (mm->context.size) {
-#ifdef CONFIG_X86_32
- /* CHECKME: Can this ever happen ? */
- if (mm == current->active_mm)
- clear_LDT();
-#endif
- paravirt_free_ldt(mm->context.ldt, mm->context.size);
- if (mm->context.size * LDT_ENTRY_SIZE > PAGE_SIZE)
- vfree(mm->context.ldt);
- else
- put_page(virt_to_page(mm->context.ldt));
- mm->context.size = 0;
- }
+ free_ldt_struct(mm->context.ldt);
+ mm->context.ldt = NULL;
}
static int read_ldt(void __user *ptr, unsigned long bytecount)
{
- int err;
+ int retval;
unsigned long size;
struct mm_struct *mm = current->mm;
- if (!mm->context.size)
- return 0;
+ mutex_lock(&mm->context.lock);
+
+ if (!mm->context.ldt) {
+ retval = 0;
+ goto out_unlock;
+ }
+
if (bytecount > LDT_ENTRY_SIZE * LDT_ENTRIES)
bytecount = LDT_ENTRY_SIZE * LDT_ENTRIES;
- mutex_lock(&mm->context.lock);
- size = mm->context.size * LDT_ENTRY_SIZE;
+ size = mm->context.ldt->size * LDT_ENTRY_SIZE;
if (size > bytecount)
size = bytecount;
- err = 0;
- if (copy_to_user(ptr, mm->context.ldt, size))
- err = -EFAULT;
- mutex_unlock(&mm->context.lock);
- if (err < 0)
- goto error_return;
+ if (copy_to_user(ptr, mm->context.ldt->entries, size)) {
+ retval = -EFAULT;
+ goto out_unlock;
+ }
+
if (size != bytecount) {
- /* zero-fill the rest */
- if (clear_user(ptr + size, bytecount - size) != 0) {
- err = -EFAULT;
- goto error_return;
+ /* Zero-fill the rest and pretend we read bytecount bytes. */
+ if (clear_user(ptr + size, bytecount - size)) {
+ retval = -EFAULT;
+ goto out_unlock;
}
}
- return bytecount;
-error_return:
- return err;
+ retval = bytecount;
+
+out_unlock:
+ mutex_unlock(&mm->context.lock);
+ return retval;
}
static int read_default_ldt(void __user *ptr, unsigned long bytecount)
@@ -195,6 +210,8 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
struct desc_struct ldt;
int error;
struct user_desc ldt_info;
+ int oldsize, newsize;
+ struct ldt_struct *new_ldt, *old_ldt;
error = -EINVAL;
if (bytecount != sizeof(ldt_info))
@@ -213,34 +230,39 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
goto out;
}
- mutex_lock(&mm->context.lock);
- if (ldt_info.entry_number >= mm->context.size) {
- error = alloc_ldt(&current->mm->context,
- ldt_info.entry_number + 1, 1);
- if (error < 0)
- goto out_unlock;
- }
-
- /* Allow LDTs to be cleared by the user. */
- if (ldt_info.base_addr == 0 && ldt_info.limit == 0) {
- if (oldmode || LDT_empty(&ldt_info)) {
- memset(&ldt, 0, sizeof(ldt));
- goto install;
+ if ((oldmode && !ldt_info.base_addr && !ldt_info.limit) ||
+ LDT_empty(&ldt_info)) {
+ /* The user wants to clear the entry. */
+ memset(&ldt, 0, sizeof(ldt));
+ } else {
+ if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) {
+ error = -EINVAL;
+ goto out;
}
+
+ fill_ldt(&ldt, &ldt_info);
+ if (oldmode)
+ ldt.avl = 0;
}
- if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) {
- error = -EINVAL;
+ mutex_lock(&mm->context.lock);
+
+ old_ldt = mm->context.ldt;
+ oldsize = old_ldt ? old_ldt->size : 0;
+ newsize = max((int)(ldt_info.entry_number + 1), oldsize);
+
+ error = -ENOMEM;
+ new_ldt = alloc_ldt_struct(newsize);
+ if (!new_ldt)
goto out_unlock;
- }
- fill_ldt(&ldt, &ldt_info);
- if (oldmode)
- ldt.avl = 0;
+ if (old_ldt)
+ memcpy(new_ldt->entries, old_ldt->entries, oldsize * LDT_ENTRY_SIZE);
+ new_ldt->entries[ldt_info.entry_number] = ldt;
+ finalize_ldt_struct(new_ldt);
- /* Install the new entry ... */
-install:
- write_ldt_entry(mm->context.ldt, ldt_info.entry_number, &ldt);
+ install_ldt(mm, new_ldt);
+ free_ldt_struct(old_ldt);
error = 0;
out_unlock:
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 71d7849a07f7..f6b916387590 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -121,11 +121,11 @@ void __show_regs(struct pt_regs *regs, int all)
void release_thread(struct task_struct *dead_task)
{
if (dead_task->mm) {
- if (dead_task->mm->context.size) {
+ if (dead_task->mm->context.ldt) {
pr_warn("WARNING: dead process %s still has LDT? <%p/%d>\n",
dead_task->comm,
dead_task->mm->context.ldt,
- dead_task->mm->context.size);
+ dead_task->mm->context.ldt->size);
BUG();
}
}
diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c
index 9b4d51d0c0d0..6273324186ac 100644
--- a/arch/x86/kernel/step.c
+++ b/arch/x86/kernel/step.c
@@ -5,6 +5,7 @@
#include <linux/mm.h>
#include <linux/ptrace.h>
#include <asm/desc.h>
+#include <asm/mmu_context.h>
unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs)
{
@@ -30,10 +31,11 @@ unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *re
seg &= ~7UL;
mutex_lock(&child->mm->context.lock);
- if (unlikely((seg >> 3) >= child->mm->context.size))
+ if (unlikely(!child->mm->context.ldt ||
+ (seg >> 3) >= child->mm->context.ldt->size))
addr = -1L; /* bogus selector, access would fault */
else {
- desc = child->mm->context.ldt + seg;
+ desc = &child->mm->context.ldt->entries[seg];
base = get_desc_base(desc);
/* 16-bit code segment? */
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 954e98a8c2e3..2a5ca97c263b 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1595,7 +1595,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
for (i = 0; i < APIC_LVT_NUM; i++)
apic_set_reg(apic, APIC_LVTT + 0x10 * i, APIC_LVT_MASKED);
apic_update_lvtt(apic);
- if (!(vcpu->kvm->arch.disabled_quirks & KVM_QUIRK_LINT0_REENABLED))
+ if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_LINT0_REENABLED))
apic_set_reg(apic, APIC_LVT0,
SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT));
apic_manage_nmi_watchdog(apic, kvm_apic_get_reg(apic, APIC_LVT0));
diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c
index de1d2d8062e2..dc0a84a6f309 100644
--- a/arch/x86/kvm/mtrr.c
+++ b/arch/x86/kvm/mtrr.c
@@ -120,6 +120,16 @@ static u8 mtrr_default_type(struct kvm_mtrr *mtrr_state)
return mtrr_state->deftype & IA32_MTRR_DEF_TYPE_TYPE_MASK;
}
+static u8 mtrr_disabled_type(void)
+{
+ /*
+ * Intel SDM 11.11.2.2: all MTRRs are disabled when
+ * IA32_MTRR_DEF_TYPE.E bit is cleared, and the UC
+ * memory type is applied to all of physical memory.
+ */
+ return MTRR_TYPE_UNCACHABLE;
+}
+
/*
* Three terms are used in the following code:
* - segment, it indicates the address segments covered by fixed MTRRs.
@@ -434,6 +444,8 @@ struct mtrr_iter {
/* output fields. */
int mem_type;
+ /* mtrr is completely disabled? */
+ bool mtrr_disabled;
/* [start, end) is not fully covered in MTRRs? */
bool partial_map;
@@ -549,7 +561,7 @@ static void mtrr_lookup_var_next(struct mtrr_iter *iter)
static void mtrr_lookup_start(struct mtrr_iter *iter)
{
if (!mtrr_is_enabled(iter->mtrr_state)) {
- iter->partial_map = true;
+ iter->mtrr_disabled = true;
return;
}
@@ -563,6 +575,7 @@ static void mtrr_lookup_init(struct mtrr_iter *iter,
iter->mtrr_state = mtrr_state;
iter->start = start;
iter->end = end;
+ iter->mtrr_disabled = false;
iter->partial_map = false;
iter->fixed = false;
iter->range = NULL;
@@ -656,15 +669,19 @@ u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn)
return MTRR_TYPE_WRBACK;
}
- /* It is not covered by MTRRs. */
- if (iter.partial_map) {
- /*
- * We just check one page, partially covered by MTRRs is
- * impossible.
- */
- WARN_ON(type != -1);
- type = mtrr_default_type(mtrr_state);
- }
+ if (iter.mtrr_disabled)
+ return mtrr_disabled_type();
+
+ /*
+ * We just check one page, partially covered by MTRRs is
+ * impossible.
+ */
+ WARN_ON(iter.partial_map);
+
+ /* not contained in any MTRRs. */
+ if (type == -1)
+ return mtrr_default_type(mtrr_state);
+
return type;
}
EXPORT_SYMBOL_GPL(kvm_mtrr_get_guest_memory_type);
@@ -689,6 +706,9 @@ bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn,
return false;
}
+ if (iter.mtrr_disabled)
+ return true;
+
if (!iter.partial_map)
return true;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index bbc678a66b18..8e0c0844c6b9 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1672,7 +1672,7 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
* does not do it - this results in some delay at
* reboot
*/
- if (!(vcpu->kvm->arch.disabled_quirks & KVM_QUIRK_CD_NW_CLEARED))
+ if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED))
cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
svm->vmcb->save.cr0 = cr0;
mark_dirty(svm->vmcb, VMCB_CR);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 5b4e9384717a..83b7b5cd75d5 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -8650,7 +8650,10 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
if (kvm_read_cr0(vcpu) & X86_CR0_CD) {
ipat = VMX_EPT_IPAT_BIT;
- cache = MTRR_TYPE_UNCACHABLE;
+ if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED))
+ cache = MTRR_TYPE_WRBACK;
+ else
+ cache = MTRR_TYPE_UNCACHABLE;
goto exit;
}
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index edc8cdcd786b..0ca2f3e4803c 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -147,6 +147,11 @@ static inline void kvm_register_writel(struct kvm_vcpu *vcpu,
return kvm_register_write(vcpu, reg, val);
}
+static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk)
+{
+ return !(kvm->arch.disabled_quirks & quirk);
+}
+
void kvm_before_handle_nmi(struct kvm_vcpu *vcpu);
void kvm_after_handle_nmi(struct kvm_vcpu *vcpu);
void kvm_set_pending_timer(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index cc5ccc415cc0..b9c78f3bcd67 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -63,8 +63,6 @@ static int __ioremap_check_ram(unsigned long start_pfn, unsigned long nr_pages,
!PageReserved(pfn_to_page(start_pfn + i)))
return 1;
- WARN_ONCE(1, "ioremap on RAM pfn 0x%lx\n", start_pfn);
-
return 0;
}
@@ -94,7 +92,6 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
pgprot_t prot;
int retval;
void __iomem *ret_addr;
- int ram_region;
/* Don't allow wraparound or zero size */
last_addr = phys_addr + size - 1;
@@ -117,23 +114,15 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
/*
* Don't allow anybody to remap normal RAM that we're using..
*/
- /* First check if whole region can be identified as RAM or not */
- ram_region = region_is_ram(phys_addr, size);
- if (ram_region > 0) {
- WARN_ONCE(1, "ioremap on RAM at 0x%lx - 0x%lx\n",
- (unsigned long int)phys_addr,
- (unsigned long int)last_addr);
+ pfn = phys_addr >> PAGE_SHIFT;
+ last_pfn = last_addr >> PAGE_SHIFT;
+ if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL,
+ __ioremap_check_ram) == 1) {
+ WARN_ONCE(1, "ioremap on RAM at %pa - %pa\n",
+ &phys_addr, &last_addr);
return NULL;
}
- /* If could not be identified(-1), check page by page */
- if (ram_region < 0) {
- pfn = phys_addr >> PAGE_SHIFT;
- last_pfn = last_addr >> PAGE_SHIFT;
- if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL,
- __ioremap_check_ram) == 1)
- return NULL;
- }
/*
* Mappings have to be page-aligned
*/
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 9d518d693b4b..844b06d67df4 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -126,3 +126,10 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
mm->get_unmapped_area = arch_get_unmapped_area_topdown;
}
}
+
+const char *arch_vma_name(struct vm_area_struct *vma)
+{
+ if (vma->vm_flags & VM_MPX)
+ return "[mpx]";
+ return NULL;
+}
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index 7a657f58bbea..db1b0bc5017c 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -20,20 +20,6 @@
#define CREATE_TRACE_POINTS
#include <asm/trace/mpx.h>
-static const char *mpx_mapping_name(struct vm_area_struct *vma)
-{
- return "[mpx]";
-}
-
-static struct vm_operations_struct mpx_vma_ops = {
- .name = mpx_mapping_name,
-};
-
-static int is_mpx_vma(struct vm_area_struct *vma)
-{
- return (vma->vm_ops == &mpx_vma_ops);
-}
-
static inline unsigned long mpx_bd_size_bytes(struct mm_struct *mm)
{
if (is_64bit_mm(mm))
@@ -53,9 +39,6 @@ static inline unsigned long mpx_bt_size_bytes(struct mm_struct *mm)
/*
* This is really a simplified "vm_mmap". it only handles MPX
* bounds tables (the bounds directory is user-allocated).
- *
- * Later on, we use the vma->vm_ops to uniquely identify these
- * VMAs.
*/
static unsigned long mpx_mmap(unsigned long len)
{
@@ -101,7 +84,6 @@ static unsigned long mpx_mmap(unsigned long len)
ret = -ENOMEM;
goto out;
}
- vma->vm_ops = &mpx_vma_ops;
if (vm_flags & VM_LOCKED) {
up_write(&mm->mmap_sem);
@@ -812,7 +794,7 @@ static noinline int zap_bt_entries_mapping(struct mm_struct *mm,
* so stop immediately and return an error. This
* probably results in a SIGSEGV.
*/
- if (!is_mpx_vma(vma))
+ if (!(vma->vm_flags & VM_MPX))
return -EINVAL;
len = min(vma->vm_end, end) - addr;
@@ -945,9 +927,9 @@ static int try_unmap_single_bt(struct mm_struct *mm,
* lots of tables even though we have no actual table
* entries in use.
*/
- while (next && is_mpx_vma(next))
+ while (next && (next->vm_flags & VM_MPX))
next = next->vm_next;
- while (prev && is_mpx_vma(prev))
+ while (prev && (prev->vm_flags & VM_MPX))
prev = prev->vm_prev;
/*
* We know 'start' and 'end' lie within an area controlled
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 3250f2371aea..90b924acd982 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -117,7 +117,7 @@ static void flush_tlb_func(void *info)
} else {
unsigned long addr;
unsigned long nr_pages =
- f->flush_end - f->flush_start / PAGE_SIZE;
+ (f->flush_end - f->flush_start) / PAGE_SIZE;
addr = f->flush_start;
while (addr < f->flush_end) {
__flush_tlb_single(addr);
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 579a8fd74be0..be2e7a2b10d7 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -269,7 +269,7 @@ static void emit_bpf_tail_call(u8 **pprog)
EMIT4(0x48, 0x8B, 0x46, /* mov rax, qword ptr [rsi + 16] */
offsetof(struct bpf_array, map.max_entries));
EMIT3(0x48, 0x39, 0xD0); /* cmp rax, rdx */
-#define OFFSET1 44 /* number of bytes to jump */
+#define OFFSET1 47 /* number of bytes to jump */
EMIT2(X86_JBE, OFFSET1); /* jbe out */
label1 = cnt;
@@ -278,15 +278,15 @@ static void emit_bpf_tail_call(u8 **pprog)
*/
EMIT2_off32(0x8B, 0x85, -STACKSIZE + 36); /* mov eax, dword ptr [rbp - 516] */
EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */
-#define OFFSET2 33
+#define OFFSET2 36
EMIT2(X86_JA, OFFSET2); /* ja out */
label2 = cnt;
EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */
EMIT2_off32(0x89, 0x85, -STACKSIZE + 36); /* mov dword ptr [rbp - 516], eax */
/* prog = array->prog[index]; */
- EMIT4(0x48, 0x8D, 0x44, 0xD6); /* lea rax, [rsi + rdx * 8 + 0x50] */
- EMIT1(offsetof(struct bpf_array, prog));
+ EMIT4_off32(0x48, 0x8D, 0x84, 0xD6, /* lea rax, [rsi + rdx * 8 + offsetof(...)] */
+ offsetof(struct bpf_array, prog));
EMIT3(0x48, 0x8B, 0x00); /* mov rax, qword ptr [rax] */
/* if (prog == NULL)
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index cfba30f27392..e4308fe6afe8 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -972,6 +972,11 @@ u64 efi_mem_attributes(unsigned long phys_addr)
static int __init arch_parse_efi_cmdline(char *str)
{
+ if (!str) {
+ pr_warn("need at least one option\n");
+ return -EINVAL;
+ }
+
if (parse_option_str(str, "old_map"))
set_bit(EFI_OLD_MEMMAP, &efi.flags);
if (parse_option_str(str, "debug"))
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 0d7dd1f5ac36..9ab52791fed5 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -22,6 +22,7 @@
#include <asm/fpu/internal.h>
#include <asm/debugreg.h>
#include <asm/cpu.h>
+#include <asm/mmu_context.h>
#ifdef CONFIG_X86_32
__visible unsigned long saved_context_ebx;
@@ -153,7 +154,7 @@ static void fix_processor_context(void)
syscall_init(); /* This sets MSR_*STAR and related */
#endif
load_TR_desc(); /* This does ltr */
- load_LDT(&current->active_mm->context); /* This does lldt */
+ load_mm_ldt(current->active_mm); /* This does lldt */
fpu__resume_cpu();
}
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 0b95c9b8283f..11d6fb4e8483 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -483,6 +483,7 @@ static void set_aliased_prot(void *v, pgprot_t prot)
pte_t pte;
unsigned long pfn;
struct page *page;
+ unsigned char dummy;
ptep = lookup_address((unsigned long)v, &level);
BUG_ON(ptep == NULL);
@@ -492,6 +493,32 @@ static void set_aliased_prot(void *v, pgprot_t prot)
pte = pfn_pte(pfn, prot);
+ /*
+ * Careful: update_va_mapping() will fail if the virtual address
+ * we're poking isn't populated in the page tables. We don't
+ * need to worry about the direct map (that's always in the page
+ * tables), but we need to be careful about vmap space. In
+ * particular, the top level page table can lazily propagate
+ * entries between processes, so if we've switched mms since we
+ * vmapped the target in the first place, we might not have the
+ * top-level page table entry populated.
+ *
+ * We disable preemption because we want the same mm active when
+ * we probe the target and when we issue the hypercall. We'll
+ * have the same nominal mm, but if we're a kernel thread, lazy
+ * mm dropping could change our pgd.
+ *
+ * Out of an abundance of caution, this uses __get_user() to fault
+ * in the target address just in case there's some obscure case
+ * in which the target address isn't readable.
+ */
+
+ preempt_disable();
+
+ pagefault_disable(); /* Avoid warnings due to being atomic. */
+ __get_user(dummy, (unsigned char __user __force *)v);
+ pagefault_enable();
+
if (HYPERVISOR_update_va_mapping((unsigned long)v, pte, 0))
BUG();
@@ -503,6 +530,8 @@ static void set_aliased_prot(void *v, pgprot_t prot)
BUG();
} else
kmap_flush_unused();
+
+ preempt_enable();
}
static void xen_alloc_ldt(struct desc_struct *ldt, unsigned entries)
@@ -510,6 +539,17 @@ static void xen_alloc_ldt(struct desc_struct *ldt, unsigned entries)
const unsigned entries_per_page = PAGE_SIZE / LDT_ENTRY_SIZE;
int i;
+ /*
+ * We need to mark the all aliases of the LDT pages RO. We
+ * don't need to call vm_flush_aliases(), though, since that's
+ * only responsible for flushing aliases out the TLBs, not the
+ * page tables, and Xen will flush the TLB for us if needed.
+ *
+ * To avoid confusing future readers: none of this is necessary
+ * to load the LDT. The hypervisor only checks this when the
+ * LDT is faulted in due to subsequent descriptor access.
+ */
+
for(i = 0; i < entries; i += entries_per_page)
set_aliased_prot(ldt + i, PAGE_KERNEL_RO);
}