aboutsummaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig4
-rw-r--r--arch/x86/Makefile1
-rw-r--r--arch/x86/include/asm/hugetlb.h1
-rw-r--r--arch/x86/include/asm/kvm_host.h4
-rw-r--r--arch/x86/include/asm/preempt.h12
-rw-r--r--arch/x86/include/asm/ptrace.h16
-rw-r--r--arch/x86/kernel/entry_32.S15
-rw-r--r--arch/x86/kernel/ldt.c4
-rw-r--r--arch/x86/kvm/lapic.c62
-rw-r--r--arch/x86/kvm/x86.c3
-rw-r--r--arch/x86/mm/hugetlbpage.c10
-rw-r--r--arch/x86/net/bpf_jit_comp.c2
-rw-r--r--arch/x86/syscalls/syscall_64.tbl6
-rw-r--r--arch/x86/vdso/vdso32-setup.c8
-rw-r--r--arch/x86/xen/spinlock.c5
15 files changed, 108 insertions, 45 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 0af5250d914f..1981dd9b8a11 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1909,6 +1909,10 @@ config ARCH_ENABLE_SPLIT_PMD_PTLOCK
def_bool y
depends on X86_64 || X86_PAE
+config ARCH_ENABLE_HUGEPAGE_MIGRATION
+ def_bool y
+ depends on X86_64 && HUGETLB_PAGE && MIGRATION
+
menu "Power management and ACPI options"
config ARCH_HIBERNATION_HEADER
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index f8842c444560..0dd99ea1caf1 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -79,6 +79,7 @@ else
UTS_MACHINE := x86_64
CHECKFLAGS += -D__x86_64__ -m64
+ biarch := -m64
KBUILD_AFLAGS += -m64
KBUILD_CFLAGS += -m64
diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
index a8091216963b..68c05398bba9 100644
--- a/arch/x86/include/asm/hugetlb.h
+++ b/arch/x86/include/asm/hugetlb.h
@@ -52,6 +52,7 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep)
{
+ ptep_clear_flush(vma, addr, ptep);
}
static inline int huge_pte_none(pte_t pte)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index fdf83afbb7d9..3092300a07cd 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -99,7 +99,7 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level)
#define KVM_REFILL_PAGES 25
#define KVM_MAX_CPUID_ENTRIES 80
#define KVM_NR_FIXED_MTRR_REGION 88
-#define KVM_NR_VAR_MTRR 8
+#define KVM_NR_VAR_MTRR 10
#define ASYNC_PF_PER_VCPU 64
@@ -462,7 +462,7 @@ struct kvm_vcpu_arch {
bool nmi_injected; /* Trying to inject an NMI this entry */
struct mtrr_state_type mtrr_state;
- u32 pat;
+ u64 pat;
int switch_db_regs;
unsigned long db[KVM_NR_DB_REGS];
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index c8b051933b1b..b39e194f6c8d 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -5,6 +5,18 @@
#include <asm/percpu.h>
#include <linux/thread_info.h>
+#ifdef CONFIG_X86_32
+/*
+ * i386's current_thread_info() depends on ESP and for interrupt/exception
+ * stacks this doesn't yield the actual task thread_info.
+ *
+ * We hard rely on the fact that all the TIF_NEED_RESCHED bits are
+ * the same, therefore use the slightly more expensive version below.
+ */
+#undef tif_need_resched
+#define tif_need_resched() test_tsk_thread_flag(current, TIF_NEED_RESCHED)
+#endif
+
DECLARE_PER_CPU(int, __preempt_count);
/*
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 14fd6fd75a19..6205f0c434db 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -231,6 +231,22 @@ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
#define ARCH_HAS_USER_SINGLE_STEP_INFO
+/*
+ * When hitting ptrace_stop(), we cannot return using SYSRET because
+ * that does not restore the full CPU state, only a minimal set. The
+ * ptracer can change arbitrary register values, which is usually okay
+ * because the usual ptrace stops run off the signal delivery path which
+ * forces IRET; however, ptrace_event() stops happen in arbitrary places
+ * in the kernel and don't force IRET path.
+ *
+ * So force IRET path after a ptrace stop.
+ */
+#define arch_ptrace_stop_needed(code, info) \
+({ \
+ set_thread_flag(TIF_NOTIFY_RESUME); \
+ false; \
+})
+
struct user_desc;
extern int do_get_thread_area(struct task_struct *p, int idx,
struct user_desc __user *info);
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index a2a4f4697889..6491353cc9aa 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -431,9 +431,10 @@ sysenter_past_esp:
jnz sysenter_audit
sysenter_do_call:
cmpl $(NR_syscalls), %eax
- jae syscall_badsys
+ jae sysenter_badsys
call *sys_call_table(,%eax,4)
movl %eax,PT_EAX(%esp)
+sysenter_after_call:
LOCKDEP_SYS_EXIT
DISABLE_INTERRUPTS(CLBR_ANY)
TRACE_IRQS_OFF
@@ -551,11 +552,6 @@ ENTRY(iret_exc)
CFI_RESTORE_STATE
ldt_ss:
- larl PT_OLDSS(%esp), %eax
- jnz restore_nocheck
- testl $0x00400000, %eax # returning to 32bit stack?
- jnz restore_nocheck # allright, normal return
-
#ifdef CONFIG_PARAVIRT
/*
* The kernel can't run on a non-flat stack if paravirt mode
@@ -688,7 +684,12 @@ END(syscall_fault)
syscall_badsys:
movl $-ENOSYS,PT_EAX(%esp)
- jmp resume_userspace
+ jmp syscall_exit
+END(syscall_badsys)
+
+sysenter_badsys:
+ movl $-ENOSYS,PT_EAX(%esp)
+ jmp sysenter_after_call
END(syscall_badsys)
CFI_ENDPROC
/*
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index af1d14a9ebda..dcbbaa165bde 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -20,6 +20,8 @@
#include <asm/mmu_context.h>
#include <asm/syscalls.h>
+int sysctl_ldt16 = 0;
+
#ifdef CONFIG_SMP
static void flush_ldt(void *current_mm)
{
@@ -234,7 +236,7 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
* IRET leaking the high bits of the kernel stack address.
*/
#ifdef CONFIG_X86_64
- if (!ldt_info.seg_32bit) {
+ if (!ldt_info.seg_32bit && !sysctl_ldt16) {
error = -EINVAL;
goto out_unlock;
}
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 9736529ade08..006911858174 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -360,6 +360,8 @@ static inline void apic_clear_irr(int vec, struct kvm_lapic *apic)
static inline void apic_set_isr(int vec, struct kvm_lapic *apic)
{
+ /* Note that we never get here with APIC virtualization enabled. */
+
if (!__apic_test_and_set_vector(vec, apic->regs + APIC_ISR))
++apic->isr_count;
BUG_ON(apic->isr_count > MAX_APIC_VECTOR);
@@ -371,12 +373,48 @@ static inline void apic_set_isr(int vec, struct kvm_lapic *apic)
apic->highest_isr_cache = vec;
}
+static inline int apic_find_highest_isr(struct kvm_lapic *apic)
+{
+ int result;
+
+ /*
+ * Note that isr_count is always 1, and highest_isr_cache
+ * is always -1, with APIC virtualization enabled.
+ */
+ if (!apic->isr_count)
+ return -1;
+ if (likely(apic->highest_isr_cache != -1))
+ return apic->highest_isr_cache;
+
+ result = find_highest_vector(apic->regs + APIC_ISR);
+ ASSERT(result == -1 || result >= 16);
+
+ return result;
+}
+
static inline void apic_clear_isr(int vec, struct kvm_lapic *apic)
{
- if (__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR))
+ struct kvm_vcpu *vcpu;
+ if (!__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR))
+ return;
+
+ vcpu = apic->vcpu;
+
+ /*
+ * We do get here for APIC virtualization enabled if the guest
+ * uses the Hyper-V APIC enlightenment. In this case we may need
+ * to trigger a new interrupt delivery by writing the SVI field;
+ * on the other hand isr_count and highest_isr_cache are unused
+ * and must be left alone.
+ */
+ if (unlikely(kvm_apic_vid_enabled(vcpu->kvm)))
+ kvm_x86_ops->hwapic_isr_update(vcpu->kvm,
+ apic_find_highest_isr(apic));
+ else {
--apic->isr_count;
- BUG_ON(apic->isr_count < 0);
- apic->highest_isr_cache = -1;
+ BUG_ON(apic->isr_count < 0);
+ apic->highest_isr_cache = -1;
+ }
}
int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu)
@@ -456,22 +494,6 @@ static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu)
__clear_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention);
}
-static inline int apic_find_highest_isr(struct kvm_lapic *apic)
-{
- int result;
-
- /* Note that isr_count is always 1 with vid enabled */
- if (!apic->isr_count)
- return -1;
- if (likely(apic->highest_isr_cache != -1))
- return apic->highest_isr_cache;
-
- result = find_highest_vector(apic->regs + APIC_ISR);
- ASSERT(result == -1 || result >= 16);
-
- return result;
-}
-
void kvm_apic_update_tmr(struct kvm_vcpu *vcpu, u32 *tmr)
{
struct kvm_lapic *apic = vcpu->arch.apic;
@@ -1605,6 +1627,8 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu)
int vector = kvm_apic_has_interrupt(vcpu);
struct kvm_lapic *apic = vcpu->arch.apic;
+ /* Note that we never get here with APIC virtualization enabled. */
+
if (vector == -1)
return -1;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2b8578432d5b..8fbd1a772272 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1109,7 +1109,6 @@ static inline u64 get_kernel_ns(void)
{
struct timespec ts;
- WARN_ON(preemptible());
ktime_get_ts(&ts);
monotonic_to_bootbased(&ts);
return timespec_to_ns(&ts);
@@ -1867,7 +1866,7 @@ static int set_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data)
if (!(data & HV_X64_MSR_TSC_REFERENCE_ENABLE))
break;
gfn = data >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT;
- if (kvm_write_guest(kvm, data,
+ if (kvm_write_guest(kvm, gfn << HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT,
&tsc_ref, sizeof(tsc_ref)))
return 1;
mark_page_dirty(kvm, gfn);
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 8c9f647ff9e1..8b977ebf9388 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -58,11 +58,6 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address,
{
return NULL;
}
-
-int pmd_huge_support(void)
-{
- return 0;
-}
#else
struct page *
@@ -80,11 +75,6 @@ int pud_huge(pud_t pud)
{
return !!(pud_val(pud) & _PAGE_PSE);
}
-
-int pmd_huge_support(void)
-{
- return 1;
-}
#endif
#ifdef CONFIG_HUGETLB_PAGE
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 4ed75dd81d05..af2d4317b218 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -171,7 +171,7 @@ static struct bpf_binary_header *bpf_alloc_binary(unsigned int proglen,
memset(header, 0xcc, sz); /* fill whole space with int3 instructions */
header->pages = sz / PAGE_SIZE;
- hole = sz - (proglen + sizeof(*header));
+ hole = min(sz - (proglen + sizeof(*header)), PAGE_SIZE - sizeof(*header));
/* insert a random number of int3 instructions before BPF code */
*image_ptr = &header->image[prandom_u32() % hole];
diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl
index a12bddc7ccea..7f517ca19d32 100644
--- a/arch/x86/syscalls/syscall_64.tbl
+++ b/arch/x86/syscalls/syscall_64.tbl
@@ -212,10 +212,10 @@
203 common sched_setaffinity sys_sched_setaffinity
204 common sched_getaffinity sys_sched_getaffinity
205 64 set_thread_area
-206 common io_setup sys_io_setup
+206 64 io_setup sys_io_setup
207 common io_destroy sys_io_destroy
208 common io_getevents sys_io_getevents
-209 common io_submit sys_io_submit
+209 64 io_submit sys_io_submit
210 common io_cancel sys_io_cancel
211 64 get_thread_area
212 common lookup_dcookie sys_lookup_dcookie
@@ -358,3 +358,5 @@
540 x32 process_vm_writev compat_sys_process_vm_writev
541 x32 setsockopt compat_sys_setsockopt
542 x32 getsockopt compat_sys_getsockopt
+543 x32 io_setup compat_sys_io_setup
+544 x32 io_submit compat_sys_io_submit
diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c
index d6bfb876cfb0..f1d633a43f8e 100644
--- a/arch/x86/vdso/vdso32-setup.c
+++ b/arch/x86/vdso/vdso32-setup.c
@@ -41,6 +41,7 @@ enum {
#ifdef CONFIG_X86_64
#define vdso_enabled sysctl_vsyscall32
#define arch_setup_additional_pages syscall32_setup_pages
+extern int sysctl_ldt16;
#endif
/*
@@ -380,6 +381,13 @@ static struct ctl_table abi_table2[] = {
.mode = 0644,
.proc_handler = proc_dointvec
},
+ {
+ .procname = "ldt16",
+ .data = &sysctl_ldt16,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
{}
};
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 581521c843a5..c570feab9fa2 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -274,7 +274,7 @@ void __init xen_init_spinlocks(void)
printk(KERN_DEBUG "xen: PV spinlocks disabled\n");
return;
}
-
+ printk(KERN_DEBUG "xen: PV spinlocks enabled\n");
pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(xen_lock_spinning);
pv_lock_ops.unlock_kick = xen_unlock_kick;
}
@@ -290,6 +290,9 @@ static __init int xen_init_spinlocks_jump(void)
if (!xen_pvspin)
return 0;
+ if (!xen_domain())
+ return 0;
+
static_key_slow_inc(&paravirt_ticketlocks_enabled);
return 0;
}
generated by cgit v1.2.3 (git 2.25.1) at 2024-05-27 22:22:17 +0000