aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/include
diff options
context:
space:
mode:
authorThomas Gleixner <tglx@linutronix.de>2020-06-11 15:17:57 +0200
committerThomas Gleixner <tglx@linutronix.de>2020-06-11 15:17:57 +0200
commitf77d26a9fc525286bcef3d4f98b52e17482cf49c (patch)
tree6b179c9aa84787773cb601a14a64255e2912154b /arch/x86/include
parentb6bea24d41519e8c31e4798f1c1a3f67e540c5d0 (diff)
parentf0178fc01fe46bab6a95415f5647d1a74efcad1b (diff)
downloadlinux-f77d26a9fc525286bcef3d4f98b52e17482cf49c.tar.gz
Merge branch 'x86/entry' into ras/core
to fixup conflicts in arch/x86/kernel/cpu/mce/core.c so MCE specific follow up patches can be applied without creating a horrible merge conflict afterwards.
Diffstat (limited to 'arch/x86/include')
-rw-r--r--arch/x86/include/asm/GEN-for-each-reg.h25
-rw-r--r--arch/x86/include/asm/acrn.h11
-rw-r--r--arch/x86/include/asm/agp.h2
-rw-r--r--arch/x86/include/asm/apb_timer.h5
-rw-r--r--arch/x86/include/asm/apic.h33
-rw-r--r--arch/x86/include/asm/archrandom.h26
-rw-r--r--arch/x86/include/asm/asm-prototypes.h37
-rw-r--r--arch/x86/include/asm/atomic.h31
-rw-r--r--arch/x86/include/asm/atomic64_32.h9
-rw-r--r--arch/x86/include/asm/atomic64_64.h15
-rw-r--r--arch/x86/include/asm/audit.h7
-rw-r--r--arch/x86/include/asm/bitops.h12
-rw-r--r--arch/x86/include/asm/bug.h3
-rw-r--r--arch/x86/include/asm/cacheflush.h2
-rw-r--r--arch/x86/include/asm/checksum.h2
-rw-r--r--arch/x86/include/asm/checksum_32.h21
-rw-r--r--arch/x86/include/asm/checksum_64.h12
-rw-r--r--arch/x86/include/asm/compat.h8
-rw-r--r--arch/x86/include/asm/cpu_device_id.h31
-rw-r--r--arch/x86/include/asm/cpu_entry_area.h12
-rw-r--r--arch/x86/include/asm/cpufeatures.h2
-rw-r--r--arch/x86/include/asm/debugreg.h48
-rw-r--r--arch/x86/include/asm/delay.h4
-rw-r--r--arch/x86/include/asm/desc.h52
-rw-r--r--arch/x86/include/asm/device.h2
-rw-r--r--arch/x86/include/asm/dma.h2
-rw-r--r--arch/x86/include/asm/doublefault.h2
-rw-r--r--arch/x86/include/asm/efi.h54
-rw-r--r--arch/x86/include/asm/elf.h22
-rw-r--r--arch/x86/include/asm/entry_arch.h56
-rw-r--r--arch/x86/include/asm/fixmap.h1
-rw-r--r--arch/x86/include/asm/floppy.h19
-rw-r--r--arch/x86/include/asm/fpu/internal.h10
-rw-r--r--arch/x86/include/asm/fpu/xstate.h52
-rw-r--r--arch/x86/include/asm/ftrace.h11
-rw-r--r--arch/x86/include/asm/highmem.h9
-rw-r--r--arch/x86/include/asm/hugetlb.h10
-rw-r--r--arch/x86/include/asm/hw_irq.h22
-rw-r--r--arch/x86/include/asm/hyperv-tlfs.h474
-rw-r--r--arch/x86/include/asm/idtentry.h652
-rw-r--r--arch/x86/include/asm/intel-mid.h9
-rw-r--r--arch/x86/include/asm/intel_pmc_ipc.h59
-rw-r--r--arch/x86/include/asm/intel_scu_ipc.h114
-rw-r--r--arch/x86/include/asm/intel_scu_ipc_legacy.h91
-rw-r--r--arch/x86/include/asm/intel_telemetry.h6
-rw-r--r--arch/x86/include/asm/invpcid.h7
-rw-r--r--arch/x86/include/asm/io_bitmap.h4
-rw-r--r--arch/x86/include/asm/iomap.h1
-rw-r--r--arch/x86/include/asm/irq.h15
-rw-r--r--arch/x86/include/asm/irq_regs.h32
-rw-r--r--arch/x86/include/asm/irq_stack.h53
-rw-r--r--arch/x86/include/asm/irq_work.h1
-rw-r--r--arch/x86/include/asm/irqflags.h54
-rw-r--r--arch/x86/include/asm/kaslr.h2
-rw-r--r--arch/x86/include/asm/kvm_host.h147
-rw-r--r--arch/x86/include/asm/kvm_para.h27
-rw-r--r--arch/x86/include/asm/mce.h2
-rw-r--r--arch/x86/include/asm/memtype.h3
-rw-r--r--arch/x86/include/asm/microcode_amd.h2
-rw-r--r--arch/x86/include/asm/mmu.h2
-rw-r--r--arch/x86/include/asm/mmu_context.h88
-rw-r--r--arch/x86/include/asm/mmzone_32.h39
-rw-r--r--arch/x86/include/asm/module.h60
-rw-r--r--arch/x86/include/asm/mshyperv.h15
-rw-r--r--arch/x86/include/asm/msr-index.h7
-rw-r--r--arch/x86/include/asm/mwait.h24
-rw-r--r--arch/x86/include/asm/nospec-branch.h101
-rw-r--r--arch/x86/include/asm/orc_types.h3
-rw-r--r--arch/x86/include/asm/paravirt.h12
-rw-r--r--arch/x86/include/asm/pgtable-2level_types.h2
-rw-r--r--arch/x86/include/asm/pgtable-3level.h8
-rw-r--r--arch/x86/include/asm/pgtable-3level_types.h2
-rw-r--r--arch/x86/include/asm/pgtable.h92
-rw-r--r--arch/x86/include/asm/pgtable_32.h23
-rw-r--r--arch/x86/include/asm/pgtable_64.h10
-rw-r--r--arch/x86/include/asm/pgtable_64_types.h2
-rw-r--r--arch/x86/include/asm/pgtable_types.h52
-rw-r--r--arch/x86/include/asm/processor.h7
-rw-r--r--arch/x86/include/asm/ptrace.h2
-rw-r--r--arch/x86/include/asm/resctrl.h (renamed from arch/x86/include/asm/resctrl_sched.h)9
-rw-r--r--arch/x86/include/asm/setup.h12
-rw-r--r--arch/x86/include/asm/smap.h11
-rw-r--r--arch/x86/include/asm/special_insns.h22
-rw-r--r--arch/x86/include/asm/spinlock_types.h22
-rw-r--r--arch/x86/include/asm/stackprotector.h7
-rw-r--r--arch/x86/include/asm/stacktrace.h2
-rw-r--r--arch/x86/include/asm/svm.h9
-rw-r--r--arch/x86/include/asm/switch_to.h23
-rw-r--r--arch/x86/include/asm/text-patching.h11
-rw-r--r--arch/x86/include/asm/tlbflush.h441
-rw-r--r--arch/x86/include/asm/trace/common.h4
-rw-r--r--arch/x86/include/asm/trace/irq_vectors.h17
-rw-r--r--arch/x86/include/asm/trapnr.h31
-rw-r--r--arch/x86/include/asm/traps.h125
-rw-r--r--arch/x86/include/asm/uaccess.h28
-rw-r--r--arch/x86/include/asm/unwind.h2
-rw-r--r--arch/x86/include/asm/unwind_hints.h31
-rw-r--r--arch/x86/include/asm/uv/bios.h7
-rw-r--r--arch/x86/include/asm/uv/uv.h3
-rw-r--r--arch/x86/include/asm/uv/uv_bau.h8
-rw-r--r--arch/x86/include/asm/uv/uv_hub.h54
-rw-r--r--arch/x86/include/asm/uv/uv_mmrs.h7
-rw-r--r--arch/x86/include/asm/vermagic.h68
-rw-r--r--arch/x86/include/asm/vmx.h10
-rw-r--r--arch/x86/include/asm/x86_init.h2
-rw-r--r--arch/x86/include/asm/xen/hypercall.h2
-rw-r--r--arch/x86/include/asm/xen/page.h1
-rw-r--r--arch/x86/include/uapi/asm/kvm.h20
-rw-r--r--arch/x86/include/uapi/asm/kvm_para.h17
-rw-r--r--arch/x86/include/uapi/asm/unistd.h11
-rw-r--r--arch/x86/include/uapi/asm/vmx.h3
111 files changed, 1787 insertions, 2221 deletions
diff --git a/arch/x86/include/asm/GEN-for-each-reg.h b/arch/x86/include/asm/GEN-for-each-reg.h
new file mode 100644
index 000000000000..1b07fb102c4e
--- /dev/null
+++ b/arch/x86/include/asm/GEN-for-each-reg.h
@@ -0,0 +1,25 @@
+#ifdef CONFIG_64BIT
+GEN(rax)
+GEN(rbx)
+GEN(rcx)
+GEN(rdx)
+GEN(rsi)
+GEN(rdi)
+GEN(rbp)
+GEN(r8)
+GEN(r9)
+GEN(r10)
+GEN(r11)
+GEN(r12)
+GEN(r13)
+GEN(r14)
+GEN(r15)
+#else
+GEN(eax)
+GEN(ebx)
+GEN(ecx)
+GEN(edx)
+GEN(esi)
+GEN(edi)
+GEN(ebp)
+#endif
diff --git a/arch/x86/include/asm/acrn.h b/arch/x86/include/asm/acrn.h
deleted file mode 100644
index 4adb13f08af7..000000000000
--- a/arch/x86/include/asm/acrn.h
+++ /dev/null
@@ -1,11 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_ACRN_H
-#define _ASM_X86_ACRN_H
-
-extern void acrn_hv_callback_vector(void);
-#ifdef CONFIG_TRACING
-#define trace_acrn_hv_callback_vector acrn_hv_callback_vector
-#endif
-
-extern void acrn_hv_vector_handler(struct pt_regs *regs);
-#endif /* _ASM_X86_ACRN_H */
diff --git a/arch/x86/include/asm/agp.h b/arch/x86/include/asm/agp.h
index 8e25bf4f323a..62da760d6d5a 100644
--- a/arch/x86/include/asm/agp.h
+++ b/arch/x86/include/asm/agp.h
@@ -2,7 +2,7 @@
#ifndef _ASM_X86_AGP_H
#define _ASM_X86_AGP_H
-#include <asm/pgtable.h>
+#include <linux/pgtable.h>
#include <asm/cacheflush.h>
/*
diff --git a/arch/x86/include/asm/apb_timer.h b/arch/x86/include/asm/apb_timer.h
index 99bb207fc04c..87ce8e963215 100644
--- a/arch/x86/include/asm/apb_timer.h
+++ b/arch/x86/include/asm/apb_timer.h
@@ -25,11 +25,7 @@
#define APBT_MIN_FREQ 1000000
#define APBT_MMAP_SIZE 1024
-#define APBT_DEV_USED 1
-
extern void apbt_time_init(void);
-extern unsigned long apbt_quick_calibrate(void);
-extern int arch_setup_apbt_irqs(int irq, int trigger, int mask, int cpu);
extern void apbt_setup_secondary_clock(void);
extern struct sfi_timer_table_entry *sfi_get_mtmr(int hint);
@@ -38,7 +34,6 @@ extern int sfi_mtimer_num;
#else /* CONFIG_APB_TIMER */
-static inline unsigned long apbt_quick_calibrate(void) {return 0; }
static inline void apbt_time_init(void) { }
#endif
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 19e94af9cc5d..2cc44e957c31 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -519,39 +519,6 @@ static inline bool apic_id_is_primary_thread(unsigned int id) { return false; }
static inline void apic_smt_update(void) { }
#endif
-extern void irq_enter(void);
-extern void irq_exit(void);
-
-static inline void entering_irq(void)
-{
- irq_enter();
- kvm_set_cpu_l1tf_flush_l1d();
-}
-
-static inline void entering_ack_irq(void)
-{
- entering_irq();
- ack_APIC_irq();
-}
-
-static inline void ipi_entering_ack_irq(void)
-{
- irq_enter();
- ack_APIC_irq();
- kvm_set_cpu_l1tf_flush_l1d();
-}
-
-static inline void exiting_irq(void)
-{
- irq_exit();
-}
-
-static inline void exiting_ack_irq(void)
-{
- ack_APIC_irq();
- irq_exit();
-}
-
extern void ioapic_zap_locks(void);
#endif /* _ASM_X86_APIC_H */
diff --git a/arch/x86/include/asm/archrandom.h b/arch/x86/include/asm/archrandom.h
index 7a4bb1bd4bdb..ebc248e49549 100644
--- a/arch/x86/include/asm/archrandom.h
+++ b/arch/x86/include/asm/archrandom.h
@@ -15,16 +15,6 @@
#define RDRAND_RETRY_LOOPS 10
-#define RDRAND_INT ".byte 0x0f,0xc7,0xf0"
-#define RDSEED_INT ".byte 0x0f,0xc7,0xf8"
-#ifdef CONFIG_X86_64
-# define RDRAND_LONG ".byte 0x48,0x0f,0xc7,0xf0"
-# define RDSEED_LONG ".byte 0x48,0x0f,0xc7,0xf8"
-#else
-# define RDRAND_LONG RDRAND_INT
-# define RDSEED_LONG RDSEED_INT
-#endif
-
/* Unconditional execution of RDRAND and RDSEED */
static inline bool __must_check rdrand_long(unsigned long *v)
@@ -32,9 +22,9 @@ static inline bool __must_check rdrand_long(unsigned long *v)
bool ok;
unsigned int retry = RDRAND_RETRY_LOOPS;
do {
- asm volatile(RDRAND_LONG
+ asm volatile("rdrand %[out]"
CC_SET(c)
- : CC_OUT(c) (ok), "=a" (*v));
+ : CC_OUT(c) (ok), [out] "=r" (*v));
if (ok)
return true;
} while (--retry);
@@ -46,9 +36,9 @@ static inline bool __must_check rdrand_int(unsigned int *v)
bool ok;
unsigned int retry = RDRAND_RETRY_LOOPS;
do {
- asm volatile(RDRAND_INT
+ asm volatile("rdrand %[out]"
CC_SET(c)
- : CC_OUT(c) (ok), "=a" (*v));
+ : CC_OUT(c) (ok), [out] "=r" (*v));
if (ok)
return true;
} while (--retry);
@@ -58,18 +48,18 @@ static inline bool __must_check rdrand_int(unsigned int *v)
static inline bool __must_check rdseed_long(unsigned long *v)
{
bool ok;
- asm volatile(RDSEED_LONG
+ asm volatile("rdseed %[out]"
CC_SET(c)
- : CC_OUT(c) (ok), "=a" (*v));
+ : CC_OUT(c) (ok), [out] "=r" (*v));
return ok;
}
static inline bool __must_check rdseed_int(unsigned int *v)
{
bool ok;
- asm volatile(RDSEED_INT
+ asm volatile("rdseed %[out]"
CC_SET(c)
- : CC_OUT(c) (ok), "=a" (*v));
+ : CC_OUT(c) (ok), [out] "=r" (*v));
return ok;
}
diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h
index ce92c4acc913..5a42f9206138 100644
--- a/arch/x86/include/asm/asm-prototypes.h
+++ b/arch/x86/include/asm/asm-prototypes.h
@@ -1,13 +1,13 @@
/* SPDX-License-Identifier: GPL-2.0 */
#include <asm/ftrace.h>
#include <linux/uaccess.h>
+#include <linux/pgtable.h>
#include <asm/string.h>
#include <asm/page.h>
#include <asm/checksum.h>
#include <asm-generic/asm-prototypes.h>
-#include <asm/pgtable.h>
#include <asm/special_insns.h>
#include <asm/preempt.h>
#include <asm/asm.h>
@@ -17,24 +17,19 @@ extern void cmpxchg8b_emu(void);
#endif
#ifdef CONFIG_RETPOLINE
-#ifdef CONFIG_X86_32
-#define INDIRECT_THUNK(reg) extern asmlinkage void __x86_indirect_thunk_e ## reg(void);
-#else
-#define INDIRECT_THUNK(reg) extern asmlinkage void __x86_indirect_thunk_r ## reg(void);
-INDIRECT_THUNK(8)
-INDIRECT_THUNK(9)
-INDIRECT_THUNK(10)
-INDIRECT_THUNK(11)
-INDIRECT_THUNK(12)
-INDIRECT_THUNK(13)
-INDIRECT_THUNK(14)
-INDIRECT_THUNK(15)
-#endif
-INDIRECT_THUNK(ax)
-INDIRECT_THUNK(bx)
-INDIRECT_THUNK(cx)
-INDIRECT_THUNK(dx)
-INDIRECT_THUNK(si)
-INDIRECT_THUNK(di)
-INDIRECT_THUNK(bp)
+
+#define DECL_INDIRECT_THUNK(reg) \
+ extern asmlinkage void __x86_indirect_thunk_ ## reg (void);
+
+#define DECL_RETPOLINE(reg) \
+ extern asmlinkage void __x86_retpoline_ ## reg (void);
+
+#undef GEN
+#define GEN(reg) DECL_INDIRECT_THUNK(reg)
+#include <asm/GEN-for-each-reg.h>
+
+#undef GEN
+#define GEN(reg) DECL_RETPOLINE(reg)
+#include <asm/GEN-for-each-reg.h>
+
#endif /* CONFIG_RETPOLINE */
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 115127c7ad28..bf35e476a776 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -28,7 +28,7 @@ static __always_inline int arch_atomic_read(const atomic_t *v)
* Note for KASAN: we deliberately don't use READ_ONCE_NOCHECK() here,
* it's non-inlined function that increases binary size and stack usage.
*/
- return READ_ONCE((v)->counter);
+ return __READ_ONCE((v)->counter);
}
/**
@@ -40,7 +40,7 @@ static __always_inline int arch_atomic_read(const atomic_t *v)
*/
static __always_inline void arch_atomic_set(atomic_t *v, int i)
{
- WRITE_ONCE(v->counter, i);
+ __WRITE_ONCE(v->counter, i);
}
/**
@@ -166,6 +166,7 @@ static __always_inline int arch_atomic_add_return(int i, atomic_t *v)
{
return i + xadd(&v->counter, i);
}
+#define arch_atomic_add_return arch_atomic_add_return
/**
* arch_atomic_sub_return - subtract integer and return
@@ -178,34 +179,39 @@ static __always_inline int arch_atomic_sub_return(int i, atomic_t *v)
{
return arch_atomic_add_return(-i, v);
}
+#define arch_atomic_sub_return arch_atomic_sub_return
static __always_inline int arch_atomic_fetch_add(int i, atomic_t *v)
{
return xadd(&v->counter, i);
}
+#define arch_atomic_fetch_add arch_atomic_fetch_add
static __always_inline int arch_atomic_fetch_sub(int i, atomic_t *v)
{
return xadd(&v->counter, -i);
}
+#define arch_atomic_fetch_sub arch_atomic_fetch_sub
static __always_inline int arch_atomic_cmpxchg(atomic_t *v, int old, int new)
{
return arch_cmpxchg(&v->counter, old, new);
}
+#define arch_atomic_cmpxchg arch_atomic_cmpxchg
-#define arch_atomic_try_cmpxchg arch_atomic_try_cmpxchg
static __always_inline bool arch_atomic_try_cmpxchg(atomic_t *v, int *old, int new)
{
return try_cmpxchg(&v->counter, old, new);
}
+#define arch_atomic_try_cmpxchg arch_atomic_try_cmpxchg
-static inline int arch_atomic_xchg(atomic_t *v, int new)
+static __always_inline int arch_atomic_xchg(atomic_t *v, int new)
{
return arch_xchg(&v->counter, new);
}
+#define arch_atomic_xchg arch_atomic_xchg
-static inline void arch_atomic_and(int i, atomic_t *v)
+static __always_inline void arch_atomic_and(int i, atomic_t *v)
{
asm volatile(LOCK_PREFIX "andl %1,%0"
: "+m" (v->counter)
@@ -213,7 +219,7 @@ static inline void arch_atomic_and(int i, atomic_t *v)
: "memory");
}
-static inline int arch_atomic_fetch_and(int i, atomic_t *v)
+static __always_inline int arch_atomic_fetch_and(int i, atomic_t *v)
{
int val = arch_atomic_read(v);
@@ -221,8 +227,9 @@ static inline int arch_atomic_fetch_and(int i, atomic_t *v)
return val;
}
+#define arch_atomic_fetch_and arch_atomic_fetch_and
-static inline void arch_atomic_or(int i, atomic_t *v)
+static __always_inline void arch_atomic_or(int i, atomic_t *v)
{
asm volatile(LOCK_PREFIX "orl %1,%0"
: "+m" (v->counter)
@@ -230,7 +237,7 @@ static inline void arch_atomic_or(int i, atomic_t *v)
: "memory");
}
-static inline int arch_atomic_fetch_or(int i, atomic_t *v)
+static __always_inline int arch_atomic_fetch_or(int i, atomic_t *v)
{
int val = arch_atomic_read(v);
@@ -238,8 +245,9 @@ static inline int arch_atomic_fetch_or(int i, atomic_t *v)
return val;
}
+#define arch_atomic_fetch_or arch_atomic_fetch_or
-static inline void arch_atomic_xor(int i, atomic_t *v)
+static __always_inline void arch_atomic_xor(int i, atomic_t *v)
{
asm volatile(LOCK_PREFIX "xorl %1,%0"
: "+m" (v->counter)
@@ -247,7 +255,7 @@ static inline void arch_atomic_xor(int i, atomic_t *v)
: "memory");
}
-static inline int arch_atomic_fetch_xor(int i, atomic_t *v)
+static __always_inline int arch_atomic_fetch_xor(int i, atomic_t *v)
{
int val = arch_atomic_read(v);
@@ -255,6 +263,7 @@ static inline int arch_atomic_fetch_xor(int i, atomic_t *v)
return val;
}
+#define arch_atomic_fetch_xor arch_atomic_fetch_xor
#ifdef CONFIG_X86_32
# include <asm/atomic64_32.h>
@@ -262,6 +271,6 @@ static inline int arch_atomic_fetch_xor(int i, atomic_t *v)
# include <asm/atomic64_64.h>
#endif
-#include <asm-generic/atomic-instrumented.h>
+#define ARCH_ATOMIC
#endif /* _ASM_X86_ATOMIC_H */
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index 52cfaecb13f9..5efd01b548d1 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -75,6 +75,7 @@ static inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 o, s64 n)
{
return arch_cmpxchg64(&v->counter, o, n);
}
+#define arch_atomic64_cmpxchg arch_atomic64_cmpxchg
/**
* arch_atomic64_xchg - xchg atomic64 variable
@@ -94,6 +95,7 @@ static inline s64 arch_atomic64_xchg(atomic64_t *v, s64 n)
: "memory");
return o;
}
+#define arch_atomic64_xchg arch_atomic64_xchg
/**
* arch_atomic64_set - set atomic64 variable
@@ -138,6 +140,7 @@ static inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v)
ASM_NO_INPUT_CLOBBER("memory"));
return i;
}
+#define arch_atomic64_add_return arch_atomic64_add_return
/*
* Other variants with different arithmetic operators:
@@ -149,6 +152,7 @@ static inline s64 arch_atomic64_sub_return(s64 i, atomic64_t *v)
ASM_NO_INPUT_CLOBBER("memory"));
return i;
}
+#define arch_atomic64_sub_return arch_atomic64_sub_return
static inline s64 arch_atomic64_inc_return(atomic64_t *v)
{
@@ -242,6 +246,7 @@ static inline int arch_atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
"S" (v) : "memory");
return (int)a;
}
+#define arch_atomic64_add_unless arch_atomic64_add_unless
static inline int arch_atomic64_inc_not_zero(atomic64_t *v)
{
@@ -281,6 +286,7 @@ static inline s64 arch_atomic64_fetch_and(s64 i, atomic64_t *v)
return old;
}
+#define arch_atomic64_fetch_and arch_atomic64_fetch_and
static inline void arch_atomic64_or(s64 i, atomic64_t *v)
{
@@ -299,6 +305,7 @@ static inline s64 arch_atomic64_fetch_or(s64 i, atomic64_t *v)
return old;
}
+#define arch_atomic64_fetch_or arch_atomic64_fetch_or
static inline void arch_atomic64_xor(s64 i, atomic64_t *v)
{
@@ -317,6 +324,7 @@ static inline s64 arch_atomic64_fetch_xor(s64 i, atomic64_t *v)
return old;
}
+#define arch_atomic64_fetch_xor arch_atomic64_fetch_xor
static inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v)
{
@@ -327,6 +335,7 @@ static inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v)
return old;
}
+#define arch_atomic64_fetch_add arch_atomic64_fetch_add
#define arch_atomic64_fetch_sub(i, v) arch_atomic64_fetch_add(-(i), (v))
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 95c6ceac66b9..809bd010a751 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -19,7 +19,7 @@
*/
static inline s64 arch_atomic64_read(const atomic64_t *v)
{
- return READ_ONCE((v)->counter);
+ return __READ_ONCE((v)->counter);
}
/**
@@ -31,7 +31,7 @@ static inline s64 arch_atomic64_read(const atomic64_t *v)
*/
static inline void arch_atomic64_set(atomic64_t *v, s64 i)
{
- WRITE_ONCE(v->counter, i);
+ __WRITE_ONCE(v->counter, i);
}
/**
@@ -159,37 +159,43 @@ static __always_inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v)
{
return i + xadd(&v->counter, i);
}
+#define arch_atomic64_add_return arch_atomic64_add_return
static inline s64 arch_atomic64_sub_return(s64 i, atomic64_t *v)
{
return arch_atomic64_add_return(-i, v);
}
+#define arch_atomic64_sub_return arch_atomic64_sub_return
static inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v)
{
return xadd(&v->counter, i);
}
+#define arch_atomic64_fetch_add arch_atomic64_fetch_add
static inline s64 arch_atomic64_fetch_sub(s64 i, atomic64_t *v)
{
return xadd(&v->counter, -i);
}
+#define arch_atomic64_fetch_sub arch_atomic64_fetch_sub
static inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new)
{
return arch_cmpxchg(&v->counter, old, new);
}
+#define arch_atomic64_cmpxchg arch_atomic64_cmpxchg
-#define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg
static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new)
{
return try_cmpxchg(&v->counter, old, new);
}
+#define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg
static inline s64 arch_atomic64_xchg(atomic64_t *v, s64 new)
{
return arch_xchg(&v->counter, new);
}
+#define arch_atomic64_xchg arch_atomic64_xchg
static inline void arch_atomic64_and(s64 i, atomic64_t *v)
{
@@ -207,6 +213,7 @@ static inline s64 arch_atomic64_fetch_and(s64 i, atomic64_t *v)
} while (!arch_atomic64_try_cmpxchg(v, &val, val & i));
return val;
}
+#define arch_atomic64_fetch_and arch_atomic64_fetch_and
static inline void arch_atomic64_or(s64 i, atomic64_t *v)
{
@@ -224,6 +231,7 @@ static inline s64 arch_atomic64_fetch_or(s64 i, atomic64_t *v)
} while (!arch_atomic64_try_cmpxchg(v, &val, val | i));
return val;
}
+#define arch_atomic64_fetch_or arch_atomic64_fetch_or
static inline void arch_atomic64_xor(s64 i, atomic64_t *v)
{
@@ -241,5 +249,6 @@ static inline s64 arch_atomic64_fetch_xor(s64 i, atomic64_t *v)
} while (!arch_atomic64_try_cmpxchg(v, &val, val ^ i));
return val;
}
+#define arch_atomic64_fetch_xor arch_atomic64_fetch_xor
#endif /* _ASM_X86_ATOMIC64_64_H */
diff --git a/arch/x86/include/asm/audit.h b/arch/x86/include/asm/audit.h
new file mode 100644
index 000000000000..36aec57ea7a3
--- /dev/null
+++ b/arch/x86/include/asm/audit.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_AUDIT_H
+#define _ASM_X86_AUDIT_H
+
+int ia32_classify_syscall(unsigned int syscall);
+
+#endif /* _ASM_X86_AUDIT_H */
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 53f246e9df5a..0367efdc5b7a 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -52,9 +52,9 @@ static __always_inline void
arch_set_bit(long nr, volatile unsigned long *addr)
{
if (__builtin_constant_p(nr)) {
- asm volatile(LOCK_PREFIX "orb %1,%0"
+ asm volatile(LOCK_PREFIX "orb %b1,%0"
: CONST_MASK_ADDR(nr, addr)
- : "iq" (CONST_MASK(nr) & 0xff)
+ : "iq" (CONST_MASK(nr))
: "memory");
} else {
asm volatile(LOCK_PREFIX __ASM_SIZE(bts) " %1,%0"
@@ -72,9 +72,9 @@ static __always_inline void
arch_clear_bit(long nr, volatile unsigned long *addr)
{
if (__builtin_constant_p(nr)) {
- asm volatile(LOCK_PREFIX "andb %1,%0"
+ asm volatile(LOCK_PREFIX "andb %b1,%0"
: CONST_MASK_ADDR(nr, addr)
- : "iq" (CONST_MASK(nr) ^ 0xff));
+ : "iq" (~CONST_MASK(nr)));
} else {
asm volatile(LOCK_PREFIX __ASM_SIZE(btr) " %1,%0"
: : RLONG_ADDR(addr), "Ir" (nr) : "memory");
@@ -123,9 +123,9 @@ static __always_inline void
arch_change_bit(long nr, volatile unsigned long *addr)
{
if (__builtin_constant_p(nr)) {
- asm volatile(LOCK_PREFIX "xorb %1,%0"
+ asm volatile(LOCK_PREFIX "xorb %b1,%0"
: CONST_MASK_ADDR(nr, addr)
- : "iq" ((u8)CONST_MASK(nr)));
+ : "iq" (CONST_MASK(nr)));
} else {
asm volatile(LOCK_PREFIX __ASM_SIZE(btc) " %1,%0"
: : RLONG_ADDR(addr), "Ir" (nr) : "memory");
diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index facba9bc30ca..fb34ff641e0a 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -70,14 +70,17 @@ do { \
#define HAVE_ARCH_BUG
#define BUG() \
do { \
+ instrumentation_begin(); \
_BUG_FLAGS(ASM_UD2, 0); \
unreachable(); \
} while (0)
#define __WARN_FLAGS(flags) \
do { \
+ instrumentation_begin(); \
_BUG_FLAGS(ASM_UD2, BUGFLAG_WARNING|(flags)); \
annotate_reachable(); \
+ instrumentation_end(); \
} while (0)
#include <asm-generic/bug.h>
diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
index 63feaf2a5f93..b192d917a6d0 100644
--- a/arch/x86/include/asm/cacheflush.h
+++ b/arch/x86/include/asm/cacheflush.h
@@ -2,6 +2,8 @@
#ifndef _ASM_X86_CACHEFLUSH_H
#define _ASM_X86_CACHEFLUSH_H
+#include <linux/mm.h>
+
/* Caches aren't brain-dead on the intel. */
#include <asm-generic/cacheflush.h>
#include <asm/special_insns.h>
diff --git a/arch/x86/include/asm/checksum.h b/arch/x86/include/asm/checksum.h
index d79d1e622dcf..0ada98d5d09f 100644
--- a/arch/x86/include/asm/checksum.h
+++ b/arch/x86/include/asm/checksum.h
@@ -1,4 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0 */
+#define _HAVE_ARCH_COPY_AND_CSUM_FROM_USER 1
+#define HAVE_CSUM_COPY_USER
#ifdef CONFIG_X86_32
# include <asm/checksum_32.h>
#else
diff --git a/arch/x86/include/asm/checksum_32.h b/arch/x86/include/asm/checksum_32.h
index f57b94e02c57..11624c8a9d8d 100644
--- a/arch/x86/include/asm/checksum_32.h
+++ b/arch/x86/include/asm/checksum_32.h
@@ -44,18 +44,21 @@ static inline __wsum csum_partial_copy_nocheck(const void *src, void *dst,
return csum_partial_copy_generic(src, dst, len, sum, NULL, NULL);
}
-static inline __wsum csum_partial_copy_from_user(const void __user *src,
- void *dst,
- int len, __wsum sum,
- int *err_ptr)
+static inline __wsum csum_and_copy_from_user(const void __user *src,
+ void *dst, int len,
+ __wsum sum, int *err_ptr)
{
__wsum ret;
might_sleep();
- stac();
+ if (!user_access_begin(src, len)) {
+ if (len)
+ *err_ptr = -EFAULT;
+ return sum;
+ }
ret = csum_partial_copy_generic((__force void *)src, dst,
len, sum, err_ptr, NULL);
- clac();
+ user_access_end();
return ret;
}
@@ -173,7 +176,6 @@ static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
/*
* Copy and checksum to user
*/
-#define HAVE_CSUM_COPY_USER
static inline __wsum csum_and_copy_to_user(const void *src,
void __user *dst,
int len, __wsum sum,
@@ -182,11 +184,10 @@ static inline __wsum csum_and_copy_to_user(const void *src,
__wsum ret;
might_sleep();
- if (access_ok(dst, len)) {
- stac();
+ if (user_access_begin(dst, len)) {
ret = csum_partial_copy_generic(src, (__force void *)dst,
len, sum, NULL, err_ptr);
- clac();
+ user_access_end();
return ret;
}
diff --git a/arch/x86/include/asm/checksum_64.h b/arch/x86/include/asm/checksum_64.h
index 3ec6d3267cf9..0a289b87e872 100644
--- a/arch/x86/include/asm/checksum_64.h
+++ b/arch/x86/include/asm/checksum_64.h
@@ -129,27 +129,19 @@ static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
*/
extern __wsum csum_partial(const void *buff, int len, __wsum sum);
-#define _HAVE_ARCH_COPY_AND_CSUM_FROM_USER 1
-#define HAVE_CSUM_COPY_USER 1
-
-
/* Do not call this directly. Use the wrappers below */
extern __visible __wsum csum_partial_copy_generic(const void *src, const void *dst,
int len, __wsum sum,
int *src_err_ptr, int *dst_err_ptr);
-extern __wsum csum_partial_copy_from_user(const void __user *src, void *dst,
+extern __wsum csum_and_copy_from_user(const void __user *src, void *dst,
int len, __wsum isum, int *errp);
-extern __wsum csum_partial_copy_to_user(const void *src, void __user *dst,
+extern __wsum csum_and_copy_to_user(const void *src, void __user *dst,
int len, __wsum isum, int *errp);
extern __wsum csum_partial_copy_nocheck(const void *src, void *dst,
int len, __wsum sum);
-/* Old names. To be removed. */
-#define csum_and_copy_to_user csum_partial_copy_to_user
-#define csum_and_copy_from_user csum_partial_copy_from_user
-
/**
* ip_compute_csum - Compute an 16bit IP checksum.
* @buff: buffer address.
diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h
index 52e9f3480f69..d4edf281fff4 100644
--- a/arch/x86/include/asm/compat.h
+++ b/arch/x86/include/asm/compat.h
@@ -214,7 +214,11 @@ static inline bool in_compat_syscall(void)
#endif
struct compat_siginfo;
-int __copy_siginfo_to_user32(struct compat_siginfo __user *to,
- const kernel_siginfo_t *from, bool x32_ABI);
+
+#ifdef CONFIG_X86_X32_ABI
+int copy_siginfo_to_user32(struct compat_siginfo __user *to,
+ const kernel_siginfo_t *from);
+#define copy_siginfo_to_user32 copy_siginfo_to_user32
+#endif /* CONFIG_X86_X32_ABI */
#endif /* _ASM_X86_COMPAT_H */
diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h
index cf3d621c6892..eb8fcede9e3b 100644
--- a/arch/x86/include/asm/cpu_device_id.h
+++ b/arch/x86/include/asm/cpu_device_id.h
@@ -20,12 +20,14 @@
#define X86_CENTAUR_FAM6_C7_D 0xd
#define X86_CENTAUR_FAM6_NANO 0xf
+#define X86_STEPPINGS(mins, maxs) GENMASK(maxs, mins)
/**
- * X86_MATCH_VENDOR_FAM_MODEL_FEATURE - Base macro for CPU matching
+ * X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE - Base macro for CPU matching
* @_vendor: The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY
* The name is expanded to X86_VENDOR_@_vendor
* @_family: The family number or X86_FAMILY_ANY
* @_model: The model number, model constant or X86_MODEL_ANY
+ * @_steppings: Bitmask for steppings, stepping constant or X86_STEPPING_ANY
* @_feature: A X86_FEATURE bit or X86_FEATURE_ANY
* @_data: Driver specific data or NULL. The internal storage
* format is unsigned long. The supplied value, pointer
@@ -37,16 +39,35 @@
* into another macro at the usage site for good reasons, then please
* start this local macro with X86_MATCH to allow easy grepping.
*/
-#define X86_MATCH_VENDOR_FAM_MODEL_FEATURE(_vendor, _family, _model, \
- _feature, _data) { \
+#define X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(_vendor, _family, _model, \
+ _steppings, _feature, _data) { \
.vendor = X86_VENDOR_##_vendor, \
.family = _family, \
.model = _model, \
+ .steppings = _steppings, \
.feature = _feature, \
.driver_data = (unsigned long) _data \
}
/**
+ * X86_MATCH_VENDOR_FAM_MODEL_FEATURE - Macro for CPU matching
+ * @_vendor: The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY
+ * The name is expanded to X86_VENDOR_@_vendor
+ * @_family: The family number or X86_FAMILY_ANY
+ * @_model: The model number, model constant or X86_MODEL_ANY
+ * @_feature: A X86_FEATURE bit or X86_FEATURE_ANY
+ * @_data: Driver specific data or NULL. The internal storage
+ * format is unsigned long. The supplied value, pointer
+ * etc. is casted to unsigned long internally.
+ *
+ * The steppings arguments of X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE() is
+ * set to wildcards.
+ */
+#define X86_MATCH_VENDOR_FAM_MODEL_FEATURE(vendor, family, model, feature, data) \
+ X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(vendor, family, model, \
+ X86_STEPPING_ANY, feature, data)
+
+/**
* X86_MATCH_VENDOR_FAM_FEATURE - Macro for matching vendor, family and CPU feature
* @vendor: The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY
* The name is expanded to X86_VENDOR_@vendor
@@ -139,6 +160,10 @@
#define X86_MATCH_INTEL_FAM6_MODEL(model, data) \
X86_MATCH_VENDOR_FAM_MODEL(INTEL, 6, INTEL_FAM6_##model, data)
+#define X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(model, steppings, data) \
+ X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(INTEL, 6, INTEL_FAM6_##model, \
+ steppings, X86_FEATURE_ANY, data)
+
/*
* Match specific microcode revisions.
*
diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h
index 02c0078d3787..8902fdb7de13 100644
--- a/arch/x86/include/asm/cpu_entry_area.h
+++ b/arch/x86/include/asm/cpu_entry_area.h
@@ -11,15 +11,11 @@
#ifdef CONFIG_X86_64
/* Macro to enforce the same ordering and stack sizes */
-#define ESTACKS_MEMBERS(guardsize, db2_holesize)\
+#define ESTACKS_MEMBERS(guardsize) \
char DF_stack_guard[guardsize]; \
char DF_stack[EXCEPTION_STKSZ]; \
char NMI_stack_guard[guardsize]; \
char NMI_stack[EXCEPTION_STKSZ]; \
- char DB2_stack_guard[guardsize]; \
- char DB2_stack[db2_holesize]; \
- char DB1_stack_guard[guardsize]; \
- char DB1_stack[EXCEPTION_STKSZ]; \
char DB_stack_guard[guardsize]; \
char DB_stack[EXCEPTION_STKSZ]; \
char MCE_stack_guard[guardsize]; \
@@ -28,12 +24,12 @@
/* The exception stacks' physical storage. No guard pages required */
struct exception_stacks {
- ESTACKS_MEMBERS(0, 0)
+ ESTACKS_MEMBERS(0)
};
/* The effective cpu entry area mapping with guard pages. */
struct cea_exception_stacks {
- ESTACKS_MEMBERS(PAGE_SIZE, EXCEPTION_STKSZ)
+ ESTACKS_MEMBERS(PAGE_SIZE)
};
/*
@@ -42,8 +38,6 @@ struct cea_exception_stacks {
enum exception_stack_ordering {
ESTACK_DF,
ESTACK_NMI,
- ESTACK_DB2,
- ESTACK_DB1,
ESTACK_DB,
ESTACK_MCE,
N_EXCEPTION_STACKS
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index db189945e9b0..02dabc9e77b0 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -362,6 +362,7 @@
#define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
#define X86_FEATURE_FSRM (18*32+ 4) /* Fast Short Rep Mov */
#define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* AVX-512 Intersect for D/Q */
+#define X86_FEATURE_SRBDS_CTRL (18*32+ 9) /* "" SRBDS mitigation MSR available */
#define X86_FEATURE_MD_CLEAR (18*32+10) /* VERW clears CPU buffers */
#define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */
#define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */
@@ -407,5 +408,6 @@
#define X86_BUG_SWAPGS X86_BUG(21) /* CPU is affected by speculation through SWAPGS */
#define X86_BUG_TAA X86_BUG(22) /* CPU is affected by TSX Async Abort(TAA) */
#define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */
+#define X86_BUG_SRBDS X86_BUG(24) /* CPU may leak RNG bits if not mitigated */
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h
index 1a8609a15856..e89558a3fe4a 100644
--- a/arch/x86/include/asm/debugreg.h
+++ b/arch/x86/include/asm/debugreg.h
@@ -18,7 +18,7 @@ DECLARE_PER_CPU(unsigned long, cpu_dr7);
native_set_debugreg(register, value)
#endif
-static inline unsigned long native_get_debugreg(int regno)
+static __always_inline unsigned long native_get_debugreg(int regno)
{
unsigned long val = 0; /* Damn you, gcc! */
@@ -47,7 +47,7 @@ static inline unsigned long native_get_debugreg(int regno)
return val;
}
-static inline void native_set_debugreg(int regno, unsigned long value)
+static __always_inline void native_set_debugreg(int regno, unsigned long value)
{
switch (regno) {
case 0:
@@ -85,7 +85,7 @@ static inline void hw_breakpoint_disable(void)
set_debugreg(0UL, 3);
}
-static inline int hw_breakpoint_active(void)
+static __always_inline bool hw_breakpoint_active(void)
{
return __this_cpu_read(cpu_dr7) & DR_GLOBAL_ENABLE_MASK;
}
@@ -94,24 +94,38 @@ extern void aout_dump_debugregs(struct user *dump);
extern void hw_breakpoint_restore(void);
-#ifdef CONFIG_X86_64
-DECLARE_PER_CPU(int, debug_stack_usage);
-static inline void debug_stack_usage_inc(void)
+static __always_inline unsigned long local_db_save(void)
{
- __this_cpu_inc(debug_stack_usage);
+ unsigned long dr7;
+
+ if (static_cpu_has(X86_FEATURE_HYPERVISOR) && !hw_breakpoint_active())
+ return 0;
+
+ get_debugreg(dr7, 7);
+ dr7 &= ~0x400; /* architecturally set bit */
+ if (dr7)
+ set_debugreg(0, 7);
+ /*
+ * Ensure the compiler doesn't lower the above statements into
+ * the critical section; disabling breakpoints late would not
+ * be good.
+ */
+ barrier();
+
+ return dr7;
}
-static inline void debug_stack_usage_dec(void)
+
+static __always_inline void local_db_restore(unsigned long dr7)
{
- __this_cpu_dec(debug_stack_usage);
+ /*
+ * Ensure the compiler doesn't raise this statement into
+ * the critical section; enabling breakpoints early would
+ * not be good.
+ */
+ barrier();
+ if (dr7)
+ set_debugreg(dr7, 7);
}
-void debug_stack_set_zero(void);
-void debug_stack_reset(void);
-#else /* !X86_64 */
-static inline void debug_stack_set_zero(void) { }
-static inline void debug_stack_reset(void) { }
-static inline void debug_stack_usage_inc(void) { }
-static inline void debug_stack_usage_dec(void) { }
-#endif /* X86_64 */
#ifdef CONFIG_CPU_SUP_AMD
extern void set_dr_addr_mask(unsigned long mask, int dr);
diff --git a/arch/x86/include/asm/delay.h b/arch/x86/include/asm/delay.h
index de9e7841f953..630891d25819 100644
--- a/arch/x86/include/asm/delay.h
+++ b/arch/x86/include/asm/delay.h
@@ -3,8 +3,10 @@
#define _ASM_X86_DELAY_H
#include <asm-generic/delay.h>
+#include <linux/init.h>
-void use_tsc_delay(void);
+void __init use_tsc_delay(void);
+void __init use_tpause_delay(void);
void use_mwaitx_delay(void);
#endif /* _ASM_X86_DELAY_H */
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index 68a99d2a5f33..1ced11d31932 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -40,11 +40,6 @@ static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *in
desc->l = 0;
}
-extern struct desc_ptr idt_descr;
-extern gate_desc idt_table[];
-extern const struct desc_ptr debug_idt_descr;
-extern gate_desc debug_idt_table[];
-
struct gdt_page {
struct desc_struct gdt[GDT_ENTRIES];
} __attribute__((aligned(PAGE_SIZE)));
@@ -214,7 +209,7 @@ static inline void native_load_gdt(const struct desc_ptr *dtr)
asm volatile("lgdt %0"::"m" (*dtr));
}
-static inline void native_load_idt(const struct desc_ptr *dtr)
+static __always_inline void native_load_idt(const struct desc_ptr *dtr)
{
asm volatile("lidt %0"::"m" (*dtr));
}
@@ -386,64 +381,23 @@ static inline void set_desc_limit(struct desc_struct *desc, unsigned long limit)
desc->limit1 = (limit >> 16) & 0xf;
}
-void update_intr_gate(unsigned int n, const void *addr);
void alloc_intr_gate(unsigned int n, const void *addr);
extern unsigned long system_vectors[];
-#ifdef CONFIG_X86_64
-DECLARE_PER_CPU(u32, debug_idt_ctr);
-static inline bool is_debug_idt_enabled(void)
-{
- if (this_cpu_read(debug_idt_ctr))
- return true;
-
- return false;
-}
-
-static inline void load_debug_idt(void)
-{
- load_idt((const struct desc_ptr *)&debug_idt_descr);
-}
-#else
-static inline bool is_debug_idt_enabled(void)
-{
- return false;
-}
-
-static inline void load_debug_idt(void)
-{
-}
-#endif
-
-/*
- * The load_current_idt() must be called with interrupts disabled
- * to avoid races. That way the IDT will always be set back to the expected
- * descriptor. It's also called when a CPU is being initialized, and
- * that doesn't need to disable interrupts, as nothing should be
- * bothering the CPU then.
- */
-static inline void load_current_idt(void)
-{
- if (is_debug_idt_enabled())
- load_debug_idt();
- else
- load_idt((const struct desc_ptr *)&idt_descr);
-}
-
+extern void load_current_idt(void);
extern void idt_setup_early_handler(void);
extern void idt_setup_early_traps(void);
extern void idt_setup_traps(void);
extern void idt_setup_apic_and_irq_gates(void);
+extern bool idt_is_f00f_address(unsigned long address);
#ifdef CONFIG_X86_64
extern void idt_setup_early_pf(void);
extern void idt_setup_ist_traps(void);
-extern void idt_setup_debugidt_traps(void);
#else
static inline void idt_setup_early_pf(void) { }
static inline void idt_setup_ist_traps(void) { }
-static inline void idt_setup_debugidt_traps(void) { }
#endif
extern void idt_invalidate(void *addr);
diff --git a/arch/x86/include/asm/device.h b/arch/x86/include/asm/device.h
index 7e31f7f1bb06..49bd6cf3eec9 100644
--- a/arch/x86/include/asm/device.h
+++ b/arch/x86/include/asm/device.h
@@ -3,7 +3,7 @@
#define _ASM_X86_DEVICE_H
struct dev_archdata {
-#if defined(CONFIG_INTEL_IOMMU) || defined(CONFIG_AMD_IOMMU)
+#ifdef CONFIG_IOMMU_API
void *iommu; /* hook for IOMMU specific extension */
#endif
};
diff --git a/arch/x86/include/asm/dma.h b/arch/x86/include/asm/dma.h
index 00f7cf45e699..8e95aa4b0d17 100644
--- a/arch/x86/include/asm/dma.h
+++ b/arch/x86/include/asm/dma.h
@@ -74,7 +74,7 @@
#define MAX_DMA_PFN ((16UL * 1024 * 1024) >> PAGE_SHIFT)
/* 4GB broken PCI/AGP hardware bus master zone */
-#define MAX_DMA32_PFN ((4UL * 1024 * 1024 * 1024) >> PAGE_SHIFT)
+#define MAX_DMA32_PFN (1UL << (32 - PAGE_SHIFT))
#ifdef CONFIG_X86_32
/* The maximum address that we can perform a DMA transfer to on this platform */
diff --git a/arch/x86/include/asm/doublefault.h b/arch/x86/include/asm/doublefault.h
index af9a14ac8962..54a6e4a2e132 100644
--- a/arch/x86/include/asm/doublefault.h
+++ b/arch/x86/include/asm/doublefault.h
@@ -2,7 +2,7 @@
#ifndef _ASM_X86_DOUBLEFAULT_H
#define _ASM_X86_DOUBLEFAULT_H
-#if defined(CONFIG_X86_32) && defined(CONFIG_DOUBLEFAULT)
+#ifdef CONFIG_X86_32
extern void doublefault_init_cpu_tss(void);
#else
static inline void doublefault_init_cpu_tss(void)
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index cdcf48d52a12..e7d2ccfdd507 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -3,12 +3,13 @@
#define _ASM_X86_EFI_H
#include <asm/fpu/api.h>
-#include <asm/pgtable.h>
#include <asm/processor-flags.h>
#include <asm/tlb.h>
#include <asm/nospec-branch.h>
#include <asm/mmu_context.h>
#include <linux/build_bug.h>
+#include <linux/kernel.h>
+#include <linux/pgtable.h>
extern unsigned long efi_fw_vendor, efi_config_table;
@@ -178,8 +179,10 @@ extern void efi_free_boot_services(void);
extern pgd_t * __init efi_uv1_memmap_phys_prolog(void);
extern void __init efi_uv1_memmap_phys_epilog(pgd_t *save_pgd);
+/* kexec external ABI */
struct efi_setup_data {
u64 fw_vendor;
+ u64 __unused;
u64 tables;
u64 smbios;
u64 reserved[8];
@@ -223,14 +226,21 @@ efi_status_t efi_set_virtual_address_map(unsigned long memory_map_size,
/* arch specific definitions used by the stub code */
-__attribute_const__ bool efi_is_64bit(void);
+#ifdef CONFIG_EFI_MIXED
+
+#define ARCH_HAS_EFISTUB_WRAPPERS
+
+static inline bool efi_is_64bit(void)
+{
+ extern const bool efi_is64;
+
+ return efi_is64;
+}
static inline bool efi_is_native(void)
{
if (!IS_ENABLED(CONFIG_X86_64))
return true;
- if (!IS_ENABLED(CONFIG_EFI_MIXED))
- return true;
return efi_is_64bit();
}
@@ -284,6 +294,15 @@ static inline u32 efi64_convert_status(efi_status_t status)
#define __efi64_argmap_allocate_pool(type, size, buffer) \
((type), (size), efi64_zero_upper(buffer))
+#define __efi64_argmap_create_event(type, tpl, f, c, event) \
+ ((type), (tpl), (f), (c), efi64_zero_upper(event))
+
+#define __efi64_argmap_set_timer(event, type, time) \
+ ((event), (type), lower_32_bits(time), upper_32_bits(time))
+
+#define __efi64_argmap_wait_for_event(num, event, index) \
+ ((num), (event), efi64_zero_upper(index))
+
#define __efi64_argmap_handle_protocol(handle, protocol, interface) \
((handle), (protocol), efi64_zero_upper(interface))
@@ -305,6 +324,10 @@ static inline u32 efi64_convert_status(efi_status_t status)
#define __efi64_argmap_load_file(protocol, path, policy, bufsize, buf) \
((protocol), (path), (policy), efi64_zero_upper(bufsize), (buf))
+/* Graphics Output Protocol */
+#define __efi64_argmap_query_mode(gop, mode, size, info) \
+ ((gop), (mode), efi64_zero_upper(size), efi64_zero_upper(info))
+
/*
* The macros below handle the plumbing for the argument mapping. To add a
* mapping for a specific EFI method, simply define a macro
@@ -333,15 +356,26 @@ static inline u32 efi64_convert_status(efi_status_t status)
#define efi_bs_call(func, ...) \
(efi_is_native() \
- ? efi_system_table()->boottime->func(__VA_ARGS__) \
- : __efi64_thunk_map(efi_table_attr(efi_system_table(), \
- boottime), func, __VA_ARGS__))
+ ? efi_system_table->boottime->func(__VA_ARGS__) \
+ : __efi64_thunk_map(efi_table_attr(efi_system_table, \
+ boottime), \
+ func, __VA_ARGS__))
#define efi_rt_call(func, ...) \
(efi_is_native() \
- ? efi_system_table()->runtime->func(__VA_ARGS__) \
- : __efi64_thunk_map(efi_table_attr(efi_system_table(), \
- runtime), func, __VA_ARGS__))
+ ? efi_system_table->runtime->func(__VA_ARGS__) \
+ : __efi64_thunk_map(efi_table_attr(efi_system_table, \
+ runtime), \
+ func, __VA_ARGS__))
+
+#else /* CONFIG_EFI_MIXED */
+
+static inline bool efi_is_64bit(void)
+{
+ return IS_ENABLED(CONFIG_X86_64);
+}
+
+#endif /* CONFIG_EFI_MIXED */
extern bool efi_reboot_required(void);
extern bool efi_is_table_address(unsigned long phys_addr);
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 69c0f892e310..452beed7892b 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -281,9 +281,29 @@ extern u32 elf_hwcap2;
/*
* An executable for which elf_read_implies_exec() returns TRUE will
* have the READ_IMPLIES_EXEC personality flag set automatically.
+ *
+ * The decision process for determining the results are:
+ *
+ *              CPU: | lacks NX*  | has NX, ia32     | has NX, x86_64 |
+ * ELF:              |            |                  |                |
+ * ---------------------|------------|------------------|----------------|
+ * missing PT_GNU_STACK | exec-all   | exec-all         | exec-none      |
+ * PT_GNU_STACK == RWX  | exec-stack | exec-stack       | exec-stack     |
+ * PT_GNU_STACK == RW   | exec-none  | exec-none        | exec-none      |
+ *
+ * exec-all : all PROT_READ user mappings are executable, except when
+ * backed by files on a noexec-filesystem.
+ * exec-none : only PROT_EXEC user mappings are executable.
+ * exec-stack: only the stack and PROT_EXEC user mappings are executable.
+ *
+ * *this column has no architectural effect: NX markings are ignored by
+ * hardware, but may have behavioral effects when "wants X" collides with
+ * "cannot be X" constraints in memory permission flags, as in
+ * https://lkml.kernel.org/r/20190418055759.GA3155@mellanox.com
+ *
*/
#define elf_read_implies_exec(ex, executable_stack) \
- (executable_stack != EXSTACK_DISABLE_X)
+ (mmap_is_ia32() && executable_stack == EXSTACK_DEFAULT)
struct task_struct;
diff --git a/arch/x86/include/asm/entry_arch.h b/arch/x86/include/asm/entry_arch.h
deleted file mode 100644
index 416422762845..000000000000
--- a/arch/x86/include/asm/entry_arch.h
+++ /dev/null
@@ -1,56 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * This file is designed to contain the BUILD_INTERRUPT specifications for
- * all of the extra named interrupt vectors used by the architecture.
- * Usually this is the Inter Process Interrupts (IPIs)
- */
-
-/*
- * The following vectors are part of the Linux architecture, there
- * is no hardware IRQ pin equivalent for them, they are triggered
- * through the ICC by us (IPIs)
- */
-#ifdef CONFIG_SMP
-BUILD_INTERRUPT(reschedule_interrupt,RESCHEDULE_VECTOR)
-BUILD_INTERRUPT(call_function_interrupt,CALL_FUNCTION_VECTOR)
-BUILD_INTERRUPT(call_function_single_interrupt,CALL_FUNCTION_SINGLE_VECTOR)
-BUILD_INTERRUPT(irq_move_cleanup_interrupt, IRQ_MOVE_CLEANUP_VECTOR)
-BUILD_INTERRUPT(reboot_interrupt, REBOOT_VECTOR)
-#endif
-
-#ifdef CONFIG_HAVE_KVM
-BUILD_INTERRUPT(kvm_posted_intr_ipi, POSTED_INTR_VECTOR)
-BUILD_INTERRUPT(kvm_posted_intr_wakeup_ipi, POSTED_INTR_WAKEUP_VECTOR)
-BUILD_INTERRUPT(kvm_posted_intr_nested_ipi, POSTED_INTR_NESTED_VECTOR)
-#endif
-
-/*
- * every pentium local APIC has two 'local interrupts', with a
- * soft-definable vector attached to both interrupts, one of
- * which is a timer interrupt, the other one is error counter
- * overflow. Linux uses the local APIC timer interrupt to get
- * a much simpler SMP time architecture:
- */
-#ifdef CONFIG_X86_LOCAL_APIC
-
-BUILD_INTERRUPT(apic_timer_interrupt,LOCAL_TIMER_VECTOR)
-BUILD_INTERRUPT(error_interrupt,ERROR_APIC_VECTOR)
-BUILD_INTERRUPT(spurious_interrupt,SPURIOUS_APIC_VECTOR)
-BUILD_INTERRUPT(x86_platform_ipi, X86_PLATFORM_IPI_VECTOR)
-
-#ifdef CONFIG_IRQ_WORK
-BUILD_INTERRUPT(irq_work_interrupt, IRQ_WORK_VECTOR)
-#endif
-
-#ifdef CONFIG_X86_THERMAL_VECTOR
-BUILD_INTERRUPT(thermal_interrupt,THERMAL_APIC_VECTOR)
-#endif
-
-#ifdef CONFIG_X86_MCE_THRESHOLD
-BUILD_INTERRUPT(threshold_interrupt,THRESHOLD_APIC_VECTOR)
-#endif
-
-#ifdef CONFIG_X86_MCE_AMD
-BUILD_INTERRUPT(deferred_error_interrupt, DEFERRED_ERROR_VECTOR)
-#endif
-#endif
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 28183ee3cc42..b9527a54db99 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -152,7 +152,6 @@ extern void reserve_top_address(unsigned long reserve);
extern int fixmaps_set;
extern pte_t *kmap_pte;
-#define kmap_prot PAGE_KERNEL
extern pte_t *pkmap_page_table;
void __native_set_fixmap(enum fixed_addresses idx, pte_t pte);
diff --git a/arch/x86/include/asm/floppy.h b/arch/x86/include/asm/floppy.h
index 7ec59edde154..d43717b423cb 100644
--- a/arch/x86/include/asm/floppy.h
+++ b/arch/x86/include/asm/floppy.h
@@ -31,8 +31,8 @@
#define CSW fd_routine[can_use_virtual_dma & 1]
-#define fd_inb(port) inb_p(port)
-#define fd_outb(value, port) outb_p(value, port)
+#define fd_inb(base, reg) inb_p((base) + (reg))
+#define fd_outb(value, base, reg) outb_p(value, (base) + (reg))
#define fd_request_dma() CSW._request_dma(FLOPPY_DMA, "floppy")
#define fd_free_dma() CSW._free_dma(FLOPPY_DMA)
@@ -77,25 +77,26 @@ static irqreturn_t floppy_hardint(int irq, void *dev_id)
st = 1;
for (lcount = virtual_dma_count, lptr = virtual_dma_addr;
lcount; lcount--, lptr++) {
- st = inb(virtual_dma_port + 4) & 0xa0;
- if (st != 0xa0)
+ st = inb(virtual_dma_port + FD_STATUS);
+ st &= STATUS_DMA | STATUS_READY;
+ if (st != (STATUS_DMA | STATUS_READY))
break;
if (virtual_dma_mode)
- outb_p(*lptr, virtual_dma_port + 5);
+ outb_p(*lptr, virtual_dma_port + FD_DATA);
else
- *lptr = inb_p(virtual_dma_port + 5);
+ *lptr = inb_p(virtual_dma_port + FD_DATA);
}
virtual_dma_count = lcount;
virtual_dma_addr = lptr;
- st = inb(virtual_dma_port + 4);
+ st = inb(virtual_dma_port + FD_STATUS);
}
#ifdef TRACE_FLPY_INT
calls++;
#endif
- if (st == 0x20)
+ if (st == STATUS_DMA)
return IRQ_HANDLED;
- if (!(st & 0x20)) {
+ if (!(st & STATUS_DMA)) {
virtual_dma_residue += virtual_dma_count;
virtual_dma_count = 0;
#ifdef TRACE_FLPY_INT
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 44c48e34d799..42159f45bf9c 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -31,7 +31,8 @@ extern void fpu__save(struct fpu *fpu);
extern int fpu__restore_sig(void __user *buf, int ia32_frame);
extern void fpu__drop(struct fpu *fpu);
extern int fpu__copy(struct task_struct *dst, struct task_struct *src);
-extern void fpu__clear(struct fpu *fpu);
+extern void fpu__clear_user_states(struct fpu *fpu);
+extern void fpu__clear_all(struct fpu *fpu);
extern int fpu__exception_code(struct fpu *fpu, int trap_nr);
extern int dump_fpu(struct pt_regs *ptregs, struct user_i387_struct *fpstate);
@@ -92,7 +93,7 @@ static inline void fpstate_init_xstate(struct xregs_state *xsave)
* XRSTORS requires these bits set in xcomp_bv, or it will
* trigger #GP:
*/
- xsave->header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | xfeatures_mask;
+ xsave->header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | xfeatures_mask_all;
}
static inline void fpstate_init_fxstate(struct fxregs_state *fx)
@@ -399,7 +400,10 @@ static inline int copy_kernel_to_xregs_err(struct xregs_state *xstate, u64 mask)
u32 hmask = mask >> 32;
int err;
- XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
+ if (static_cpu_has(X86_FEATURE_XSAVES))
+ XSTATE_OP(XRSTORS, xstate, lmask, hmask, err);
+ else
+ XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
return err;
}
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index c6136d79f8c0..422d8369012a 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -21,19 +21,29 @@
#define XSAVE_YMM_SIZE 256
#define XSAVE_YMM_OFFSET (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET)
-/* Supervisor features */
-#define XFEATURE_MASK_SUPERVISOR (XFEATURE_MASK_PT)
-
-/* All currently supported features */
-#define XCNTXT_MASK (XFEATURE_MASK_FP | \
- XFEATURE_MASK_SSE | \
- XFEATURE_MASK_YMM | \
- XFEATURE_MASK_OPMASK | \
- XFEATURE_MASK_ZMM_Hi256 | \
- XFEATURE_MASK_Hi16_ZMM | \
- XFEATURE_MASK_PKRU | \
- XFEATURE_MASK_BNDREGS | \
- XFEATURE_MASK_BNDCSR)
+/* All currently supported user features */
+#define XFEATURE_MASK_USER_SUPPORTED (XFEATURE_MASK_FP | \
+ XFEATURE_MASK_SSE | \
+ XFEATURE_MASK_YMM | \
+ XFEATURE_MASK_OPMASK | \
+ XFEATURE_MASK_ZMM_Hi256 | \
+ XFEATURE_MASK_Hi16_ZMM | \
+ XFEATURE_MASK_PKRU | \
+ XFEATURE_MASK_BNDREGS | \
+ XFEATURE_MASK_BNDCSR)
+
+/* All currently supported supervisor features */
+#define XFEATURE_MASK_SUPERVISOR_SUPPORTED (0)
+
+/*
+ * Unsupported supervisor features. When a supervisor feature in this mask is
+ * supported in the future, move it to the supported supervisor feature mask.
+ */
+#define XFEATURE_MASK_SUPERVISOR_UNSUPPORTED (XFEATURE_MASK_PT)
+
+/* All supervisor states including supported and unsupported states. */
+#define XFEATURE_MASK_SUPERVISOR_ALL (XFEATURE_MASK_SUPERVISOR_SUPPORTED | \
+ XFEATURE_MASK_SUPERVISOR_UNSUPPORTED)
#ifdef CONFIG_X86_64
#define REX_PREFIX "0x48, "
@@ -41,7 +51,18 @@
#define REX_PREFIX
#endif
-extern u64 xfeatures_mask;
+extern u64 xfeatures_mask_all;
+
+static inline u64 xfeatures_mask_supervisor(void)
+{
+ return xfeatures_mask_all & XFEATURE_MASK_SUPERVISOR_SUPPORTED;
+}
+
+static inline u64 xfeatures_mask_user(void)
+{
+ return xfeatures_mask_all & XFEATURE_MASK_USER_SUPPORTED;
+}
+
extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
extern void __init update_regset_xstate_info(unsigned int size,
@@ -54,8 +75,9 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int of
int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int offset, unsigned int size);
int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf);
int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf);
+void copy_supervisor_to_kernel(struct xregs_state *xsave);
/* Validate an xstate header supplied by userspace (ptrace or sigreturn) */
-extern int validate_xstate_header(const struct xstate_header *hdr);
+int validate_user_xstate_header(const struct xstate_header *hdr);
#endif
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index 85be2f506272..84b9449be080 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -56,16 +56,23 @@ struct dyn_arch_ftrace {
#ifndef __ASSEMBLY__
+#if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_DYNAMIC_FTRACE)
+extern void set_ftrace_ops_ro(void);
+#else
+static inline void set_ftrace_ops_ro(void) { }
+#endif
+
#define ARCH_HAS_SYSCALL_MATCH_SYM_NAME
static inline bool arch_syscall_match_sym_name(const char *sym, const char *name)
{
/*
* Compare the symbol name with the system call name. Skip the
- * "__x64_sys", "__ia32_sys" or simple "sys" prefix.
+ * "__x64_sys", "__ia32_sys", "__do_sys" or simple "sys" prefix.
*/
return !strcmp(sym + 3, name + 3) ||
(!strncmp(sym, "__x64_", 6) && !strcmp(sym + 9, name + 3)) ||
- (!strncmp(sym, "__ia32_", 7) && !strcmp(sym + 10, name + 3));
+ (!strncmp(sym, "__ia32_", 7) && !strcmp(sym + 10, name + 3)) ||
+ (!strncmp(sym, "__do_sys", 8) && !strcmp(sym + 8, name + 3));
}
#ifndef COMPILE_OFFSETS
diff --git a/arch/x86/include/asm/highmem.h b/arch/x86/include/asm/highmem.h
index a8059930056d..0f420b24e0fc 100644
--- a/arch/x86/include/asm/highmem.h
+++ b/arch/x86/include/asm/highmem.h
@@ -58,15 +58,6 @@ extern unsigned long highstart_pfn, highend_pfn;
#define PKMAP_NR(virt) ((virt-PKMAP_BASE) >> PAGE_SHIFT)
#define PKMAP_ADDR(nr) (PKMAP_BASE + ((nr) << PAGE_SHIFT))
-extern void *kmap_high(struct page *page);
-extern void kunmap_high(struct page *page);
-
-void *kmap(struct page *page);
-void kunmap(struct page *page);
-
-void *kmap_atomic_prot(struct page *page, pgprot_t prot);
-void *kmap_atomic(struct page *page);
-void __kunmap_atomic(void *kvaddr);
void *kmap_atomic_pfn(unsigned long pfn);
void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot);
diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
index f65cfb48cfdd..1721b1aadeb1 100644
--- a/arch/x86/include/asm/hugetlb.h
+++ b/arch/x86/include/asm/hugetlb.h
@@ -7,14 +7,4 @@
#define hugepages_supported() boot_cpu_has(X86_FEATURE_PSE)
-static inline int is_hugepage_only_range(struct mm_struct *mm,
- unsigned long addr,
- unsigned long len) {
- return 0;
-}
-
-static inline void arch_clear_hugepage_flags(struct page *page)
-{
-}
-
#endif /* _ASM_X86_HUGETLB_H */
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index 4154bc5f6a4e..74c12437401e 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -28,28 +28,6 @@
#include <asm/irq.h>
#include <asm/sections.h>
-/* Interrupt handlers registered during init_IRQ */
-extern asmlinkage void apic_timer_interrupt(void);
-extern asmlinkage void x86_platform_ipi(void);
-extern asmlinkage void kvm_posted_intr_ipi(void);
-extern asmlinkage void kvm_posted_intr_wakeup_ipi(void);
-extern asmlinkage void kvm_posted_intr_nested_ipi(void);
-extern asmlinkage void error_interrupt(void);
-extern asmlinkage void irq_work_interrupt(void);
-extern asmlinkage void uv_bau_message_intr1(void);
-
-extern asmlinkage void spurious_interrupt(void);
-extern asmlinkage void thermal_interrupt(void);
-extern asmlinkage void reschedule_interrupt(void);
-
-extern asmlinkage void irq_move_cleanup_interrupt(void);
-extern asmlinkage void reboot_interrupt(void);
-extern asmlinkage void threshold_interrupt(void);
-extern asmlinkage void deferred_error_interrupt(void);
-
-extern asmlinkage void call_function_interrupt(void);
-extern asmlinkage void call_function_single_interrupt(void);
-
#ifdef CONFIG_X86_LOCAL_APIC
struct irq_data;
struct pci_dev;
diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
index 29336574d0bc..7a4d2062385c 100644
--- a/arch/x86/include/asm/hyperv-tlfs.h
+++ b/arch/x86/include/asm/hyperv-tlfs.h
@@ -11,17 +11,6 @@
#include <linux/types.h>
#include <asm/page.h>
-
-/*
- * While not explicitly listed in the TLFS, Hyper-V always runs with a page size
- * of 4096. These definitions are used when communicating with Hyper-V using
- * guest physical pages and guest physical page addresses, since the guest page
- * size may not be 4096 on all architectures.
- */
-#define HV_HYP_PAGE_SHIFT 12
-#define HV_HYP_PAGE_SIZE BIT(HV_HYP_PAGE_SHIFT)
-#define HV_HYP_PAGE_MASK (~(HV_HYP_PAGE_SIZE - 1))
-
/*
* The below CPUID leaves are present if VersionAndFeatures.HypervisorPresent
* is set by CPUID(HvCpuIdFunctionVersionAndFeatures).
@@ -39,78 +28,41 @@
#define HYPERV_CPUID_MAX 0x4000ffff
/*
- * Feature identification. EAX indicates which features are available
- * to the partition based upon the current partition privileges.
- * These are HYPERV_CPUID_FEATURES.EAX bits.
+ * Aliases for Group A features that have X64 in the name.
+ * On x86/x64 these are HYPERV_CPUID_FEATURES.EAX bits.
*/
-/* VP Runtime (HV_X64_MSR_VP_RUNTIME) available */
-#define HV_X64_MSR_VP_RUNTIME_AVAILABLE BIT(0)
-/* Partition Reference Counter (HV_X64_MSR_TIME_REF_COUNT) available*/
-#define HV_MSR_TIME_REF_COUNT_AVAILABLE BIT(1)
-/*
- * Basic SynIC MSRs (HV_X64_MSR_SCONTROL through HV_X64_MSR_EOM
- * and HV_X64_MSR_SINT0 through HV_X64_MSR_SINT15) available
- */
-#define HV_X64_MSR_SYNIC_AVAILABLE BIT(2)
-/*
- * Synthetic Timer MSRs (HV_X64_MSR_STIMER0_CONFIG through
- * HV_X64_MSR_STIMER3_COUNT) available
- */
-#define HV_MSR_SYNTIMER_AVAILABLE BIT(3)
-/*
- * APIC access MSRs (HV_X64_MSR_EOI, HV_X64_MSR_ICR and HV_X64_MSR_TPR)
- * are available
- */
-#define HV_X64_MSR_APIC_ACCESS_AVAILABLE BIT(4)
-/* Hypercall MSRs (HV_X64_MSR_GUEST_OS_ID and HV_X64_MSR_HYPERCALL) available*/
-#define HV_X64_MSR_HYPERCALL_AVAILABLE BIT(5)
-/* Access virtual processor index MSR (HV_X64_MSR_VP_INDEX) available*/
-#define HV_X64_MSR_VP_INDEX_AVAILABLE BIT(6)
-/* Virtual system reset MSR (HV_X64_MSR_RESET) is available*/
-#define HV_X64_MSR_RESET_AVAILABLE BIT(7)
-/*
- * Access statistics pages MSRs (HV_X64_MSR_STATS_PARTITION_RETAIL_PAGE,
- * HV_X64_MSR_STATS_PARTITION_INTERNAL_PAGE, HV_X64_MSR_STATS_VP_RETAIL_PAGE,
- * HV_X64_MSR_STATS_VP_INTERNAL_PAGE) available
- */
-#define HV_X64_MSR_STAT_PAGES_AVAILABLE BIT(8)
-/* Partition reference TSC MSR is available */
-#define HV_MSR_REFERENCE_TSC_AVAILABLE BIT(9)
-/* Partition Guest IDLE MSR is available */
-#define HV_X64_MSR_GUEST_IDLE_AVAILABLE BIT(10)
-/*
- * There is a single feature flag that signifies if the partition has access
- * to MSRs with local APIC and TSC frequencies.
- */
-#define HV_X64_ACCESS_FREQUENCY_MSRS BIT(11)
-/* AccessReenlightenmentControls privilege */
-#define HV_X64_ACCESS_REENLIGHTENMENT BIT(13)
-/* AccessTscInvariantControls privilege */
-#define HV_X64_ACCESS_TSC_INVARIANT BIT(15)
+#define HV_X64_MSR_VP_RUNTIME_AVAILABLE \
+ HV_MSR_VP_RUNTIME_AVAILABLE
+#define HV_X64_MSR_SYNIC_AVAILABLE \
+ HV_MSR_SYNIC_AVAILABLE
+#define HV_X64_MSR_APIC_ACCESS_AVAILABLE \
+ HV_MSR_APIC_ACCESS_AVAILABLE
+#define HV_X64_MSR_HYPERCALL_AVAILABLE \
+ HV_MSR_HYPERCALL_AVAILABLE
+#define HV_X64_MSR_VP_INDEX_AVAILABLE \
+ HV_MSR_VP_INDEX_AVAILABLE
+#define HV_X64_MSR_RESET_AVAILABLE \
+ HV_MSR_RESET_AVAILABLE
+#define HV_X64_MSR_GUEST_IDLE_AVAILABLE \
+ HV_MSR_GUEST_IDLE_AVAILABLE
+#define HV_X64_ACCESS_FREQUENCY_MSRS \
+ HV_ACCESS_FREQUENCY_MSRS
+#define HV_X64_ACCESS_REENLIGHTENMENT \
+ HV_ACCESS_REENLIGHTENMENT
+#define HV_X64_ACCESS_TSC_INVARIANT \
+ HV_ACCESS_TSC_INVARIANT
/*
- * Feature identification: indicates which flags were specified at partition
- * creation. The format is the same as the partition creation flag structure
- * defined in section Partition Creation Flags.
- * These are HYPERV_CPUID_FEATURES.EBX bits.
+ * Aliases for Group B features that have X64 in the name.
+ * On x86/x64 these are HYPERV_CPUID_FEATURES.EBX bits.
*/
-#define HV_X64_CREATE_PARTITIONS BIT(0)
-#define HV_X64_ACCESS_PARTITION_ID BIT(1)
-#define HV_X64_ACCESS_MEMORY_POOL BIT(2)
-#define HV_X64_ADJUST_MESSAGE_BUFFERS BIT(3)
-#define HV_X64_POST_MESSAGES BIT(4)
-#define HV_X64_SIGNAL_EVENTS BIT(5)
-#define HV_X64_CREATE_PORT BIT(6)
-#define HV_X64_CONNECT_PORT BIT(7)
-#define HV_X64_ACCESS_STATS BIT(8)
-#define HV_X64_DEBUGGING BIT(11)
-#define HV_X64_CPU_POWER_MANAGEMENT BIT(12)
+#define HV_X64_POST_MESSAGES HV_POST_MESSAGES
+#define HV_X64_SIGNAL_EVENTS HV_SIGNAL_EVENTS
/*
- * Feature identification. EDX indicates which miscellaneous features
- * are available to the partition.
- * These are HYPERV_CPUID_FEATURES.EDX bits.
+ * Group D Features. The bit assignments are custom to each architecture.
+ * On x86/x64 these are HYPERV_CPUID_FEATURES.EDX bits.
*/
/* The MWAIT instruction is available (per section MONITOR / MWAIT) */
#define HV_X64_MWAIT_AVAILABLE BIT(0)
@@ -131,6 +83,8 @@
#define HV_FEATURE_FREQUENCY_MSRS_AVAILABLE BIT(8)
/* Crash MSR available */
#define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE BIT(10)
+/* Support for debug MSRs available */
+#define HV_FEATURE_DEBUG_MSRS_AVAILABLE BIT(11)
/* stimer Direct Mode is available */
#define HV_STIMER_DIRECT_MODE_AVAILABLE BIT(19)
@@ -187,7 +141,7 @@
* processor, except for virtual processors that are reported as sibling SMT
* threads.
*/
-#define HV_X64_NO_NONARCH_CORESHARING BIT(18)
+#define HV_X64_NO_NONARCH_CORESHARING BIT(18)
/* Nested features. These are HYPERV_CPUID_NESTED_FEATURES.EAX bits. */
#define HV_X64_NESTED_DIRECT_FLUSH BIT(17)
@@ -295,43 +249,6 @@ union hv_x64_msr_hypercall_contents {
} __packed;
};
-/*
- * TSC page layout.
- */
-struct ms_hyperv_tsc_page {
- volatile u32 tsc_sequence;
- u32 reserved1;
- volatile u64 tsc_scale;
- volatile s64 tsc_offset;
- u64 reserved2[509];
-} __packed;
-
-/*
- * The guest OS needs to register the guest ID with the hypervisor.
- * The guest ID is a 64 bit entity and the structure of this ID is
- * specified in the Hyper-V specification:
- *
- * msdn.microsoft.com/en-us/library/windows/hardware/ff542653%28v=vs.85%29.aspx
- *
- * While the current guideline does not specify how Linux guest ID(s)
- * need to be generated, our plan is to publish the guidelines for
- * Linux and other guest operating systems that currently are hosted
- * on Hyper-V. The implementation here conforms to this yet
- * unpublished guidelines.
- *
- *
- * Bit(s)
- * 63 - Indicates if the OS is Open Source or not; 1 is Open Source
- * 62:56 - Os Type; Linux is 0x100
- * 55:48 - Distro specific identification
- * 47:16 - Linux kernel version number
- * 15:0 - Distro specific identification
- *
- *
- */
-
-#define HV_LINUX_VENDOR_ID 0x8100
-
struct hv_reenlightenment_control {
__u64 vector:8;
__u64 reserved1:8;
@@ -355,31 +272,12 @@ struct hv_tsc_emulation_status {
#define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_MASK \
(~((1ull << HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT) - 1))
-/*
- * Crash notification (HV_X64_MSR_CRASH_CTL) flags.
- */
-#define HV_CRASH_CTL_CRASH_NOTIFY_MSG BIT_ULL(62)
-#define HV_CRASH_CTL_CRASH_NOTIFY BIT_ULL(63)
#define HV_X64_MSR_CRASH_PARAMS \
(1 + (HV_X64_MSR_CRASH_P4 - HV_X64_MSR_CRASH_P0))
#define HV_IPI_LOW_VECTOR 0x10
#define HV_IPI_HIGH_VECTOR 0xff
-/* Declare the various hypercall operations. */
-#define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE 0x0002
-#define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST 0x0003
-#define HVCALL_NOTIFY_LONG_SPIN_WAIT 0x0008
-#define HVCALL_SEND_IPI 0x000b
-#define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX 0x0013
-#define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX 0x0014
-#define HVCALL_SEND_IPI_EX 0x0015
-#define HVCALL_POST_MESSAGE 0x005c
-#define HVCALL_SIGNAL_EVENT 0x005d
-#define HVCALL_RETARGET_INTERRUPT 0x007e
-#define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE 0x00af
-#define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_LIST 0x00b0
-
#define HV_X64_MSR_VP_ASSIST_PAGE_ENABLE 0x00000001
#define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT 12
#define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_MASK \
@@ -391,75 +289,6 @@ struct hv_tsc_emulation_status {
#define HV_X64_MSR_TSC_REFERENCE_ENABLE 0x00000001
#define HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT 12
-#define HV_PROCESSOR_POWER_STATE_C0 0
-#define HV_PROCESSOR_POWER_STATE_C1 1
-#define HV_PROCESSOR_POWER_STATE_C2 2
-#define HV_PROCESSOR_POWER_STATE_C3 3
-
-#define HV_FLUSH_ALL_PROCESSORS BIT(0)
-#define HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES BIT(1)
-#define HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY BIT(2)
-#define HV_FLUSH_USE_EXTENDED_RANGE_FORMAT BIT(3)
-
-enum HV_GENERIC_SET_FORMAT {
- HV_GENERIC_SET_SPARSE_4K,
- HV_GENERIC_SET_ALL,
-};
-
-#define HV_PARTITION_ID_SELF ((u64)-1)
-
-#define HV_HYPERCALL_RESULT_MASK GENMASK_ULL(15, 0)
-#define HV_HYPERCALL_FAST_BIT BIT(16)
-#define HV_HYPERCALL_VARHEAD_OFFSET 17
-#define HV_HYPERCALL_REP_COMP_OFFSET 32
-#define HV_HYPERCALL_REP_COMP_MASK GENMASK_ULL(43, 32)
-#define HV_HYPERCALL_REP_START_OFFSET 48
-#define HV_HYPERCALL_REP_START_MASK GENMASK_ULL(59, 48)
-
-/* hypercall status code */
-#define HV_STATUS_SUCCESS 0
-#define HV_STATUS_INVALID_HYPERCALL_CODE 2
-#define HV_STATUS_INVALID_HYPERCALL_INPUT 3
-#define HV_STATUS_INVALID_ALIGNMENT 4
-#define HV_STATUS_INVALID_PARAMETER 5
-#define HV_STATUS_INSUFFICIENT_MEMORY 11
-#define HV_STATUS_INVALID_PORT_ID 17
-#define HV_STATUS_INVALID_CONNECTION_ID 18
-#define HV_STATUS_INSUFFICIENT_BUFFERS 19
-
-/*
- * The Hyper-V TimeRefCount register and the TSC
- * page provide a guest VM clock with 100ns tick rate
- */
-#define HV_CLOCK_HZ (NSEC_PER_SEC/100)
-
-typedef struct _HV_REFERENCE_TSC_PAGE {
- __u32 tsc_sequence;
- __u32 res1;
- __u64 tsc_scale;
- __s64 tsc_offset;
-} __packed HV_REFERENCE_TSC_PAGE, *PHV_REFERENCE_TSC_PAGE;
-
-/* Define the number of synthetic interrupt sources. */
-#define HV_SYNIC_SINT_COUNT (16)
-/* Define the expected SynIC version. */
-#define HV_SYNIC_VERSION_1 (0x1)
-/* Valid SynIC vectors are 16-255. */
-#define HV_SYNIC_FIRST_VALID_VECTOR (16)
-
-#define HV_SYNIC_CONTROL_ENABLE (1ULL << 0)
-#define HV_SYNIC_SIMP_ENABLE (1ULL << 0)
-#define HV_SYNIC_SIEFP_ENABLE (1ULL << 0)
-#define HV_SYNIC_SINT_MASKED (1ULL << 16)
-#define HV_SYNIC_SINT_AUTO_EOI (1ULL << 17)
-#define HV_SYNIC_SINT_VECTOR_MASK (0xFF)
-
-#define HV_SYNIC_STIMER_COUNT (4)
-
-/* Define synthetic interrupt controller message constants. */
-#define HV_MESSAGE_SIZE (256)
-#define HV_MESSAGE_PAYLOAD_BYTE_COUNT (240)
-#define HV_MESSAGE_PAYLOAD_QWORD_COUNT (30)
/* Define hypervisor message types. */
enum hv_message_type {
@@ -470,76 +299,25 @@ enum hv_message_type {
HVMSG_GPA_INTERCEPT = 0x80000001,
/* Timer notification messages. */
- HVMSG_TIMER_EXPIRED = 0x80000010,
+ HVMSG_TIMER_EXPIRED = 0x80000010,
/* Error messages. */
HVMSG_INVALID_VP_REGISTER_VALUE = 0x80000020,
HVMSG_UNRECOVERABLE_EXCEPTION = 0x80000021,
- HVMSG_UNSUPPORTED_FEATURE = 0x80000022,
+ HVMSG_UNSUPPORTED_FEATURE = 0x80000022,
/* Trace buffer complete messages. */
HVMSG_EVENTLOG_BUFFERCOMPLETE = 0x80000040,
/* Platform-specific processor intercept messages. */
- HVMSG_X64_IOPORT_INTERCEPT = 0x80010000,
+ HVMSG_X64_IOPORT_INTERCEPT = 0x80010000,
HVMSG_X64_MSR_INTERCEPT = 0x80010001,
- HVMSG_X64_CPUID_INTERCEPT = 0x80010002,
+ HVMSG_X64_CPUID_INTERCEPT = 0x80010002,
HVMSG_X64_EXCEPTION_INTERCEPT = 0x80010003,
- HVMSG_X64_APIC_EOI = 0x80010004,
- HVMSG_X64_LEGACY_FP_ERROR = 0x80010005
-};
-
-/* Define synthetic interrupt controller message flags. */
-union hv_message_flags {
- __u8 asu8;
- struct {
- __u8 msg_pending:1;
- __u8 reserved:7;
- } __packed;
-};
-
-/* Define port identifier type. */
-union hv_port_id {
- __u32 asu32;
- struct {
- __u32 id:24;
- __u32 reserved:8;
- } __packed u;
+ HVMSG_X64_APIC_EOI = 0x80010004,
+ HVMSG_X64_LEGACY_FP_ERROR = 0x80010005
};
-/* Define synthetic interrupt controller message header. */
-struct hv_message_header {
- __u32 message_type;
- __u8 payload_size;
- union hv_message_flags message_flags;
- __u8 reserved[2];
- union {
- __u64 sender;
- union hv_port_id port;
- };
-} __packed;
-
-/* Define synthetic interrupt controller message format. */
-struct hv_message {
- struct hv_message_header header;
- union {
- __u64 payload[HV_MESSAGE_PAYLOAD_QWORD_COUNT];
- } u;
-} __packed;
-
-/* Define the synthetic interrupt message page layout. */
-struct hv_message_page {
- struct hv_message sint_message[HV_SYNIC_SINT_COUNT];
-} __packed;
-
-/* Define timer message payload structure. */
-struct hv_timer_message_payload {
- __u32 timer_index;
- __u32 reserved;
- __u64 expiration_time; /* When the timer expired */
- __u64 delivery_time; /* When the message was delivered */
-} __packed;
-
struct hv_nested_enlightenments_control {
struct {
__u32 directhypercall:1;
@@ -767,187 +545,11 @@ struct hv_enlightened_vmcs {
#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL 0xFFFF
-/* Define synthetic interrupt controller flag constants. */
-#define HV_EVENT_FLAGS_COUNT (256 * 8)
-#define HV_EVENT_FLAGS_LONG_COUNT (256 / sizeof(unsigned long))
-
-/*
- * Synthetic timer configuration.
- */
-union hv_stimer_config {
- u64 as_uint64;
- struct {
- u64 enable:1;
- u64 periodic:1;
- u64 lazy:1;
- u64 auto_enable:1;
- u64 apic_vector:8;
- u64 direct_mode:1;
- u64 reserved_z0:3;
- u64 sintx:4;
- u64 reserved_z1:44;
- } __packed;
-};
-
-
-/* Define the synthetic interrupt controller event flags format. */
-union hv_synic_event_flags {
- unsigned long flags[HV_EVENT_FLAGS_LONG_COUNT];
-};
-
-/* Define SynIC control register. */
-union hv_synic_scontrol {
- u64 as_uint64;
- struct {
- u64 enable:1;
- u64 reserved:63;
- } __packed;
-};
-
-/* Define synthetic interrupt source. */
-union hv_synic_sint {
- u64 as_uint64;
- struct {
- u64 vector:8;
- u64 reserved1:8;
- u64 masked:1;
- u64 auto_eoi:1;
- u64 polling:1;
- u64 reserved2:45;
- } __packed;
-};
-
-/* Define the format of the SIMP register */
-union hv_synic_simp {
- u64 as_uint64;
- struct {
- u64 simp_enabled:1;
- u64 preserved:11;
- u64 base_simp_gpa:52;
- } __packed;
-};
-
-/* Define the format of the SIEFP register */
-union hv_synic_siefp {
- u64 as_uint64;
- struct {
- u64 siefp_enabled:1;
- u64 preserved:11;
- u64 base_siefp_gpa:52;
- } __packed;
-};
-
-struct hv_vpset {
- u64 format;
- u64 valid_bank_mask;
- u64 bank_contents[];
-} __packed;
-
-/* HvCallSendSyntheticClusterIpi hypercall */
-struct hv_send_ipi {
- u32 vector;
- u32 reserved;
- u64 cpu_mask;
-} __packed;
-
-/* HvCallSendSyntheticClusterIpiEx hypercall */
-struct hv_send_ipi_ex {
- u32 vector;
- u32 reserved;
- struct hv_vpset vp_set;
-} __packed;
-
-/* HvFlushGuestPhysicalAddressSpace hypercalls */
-struct hv_guest_mapping_flush {
- u64 address_space;
- u64 flags;
-} __packed;
-
-/*
- * HV_MAX_FLUSH_PAGES = "additional_pages" + 1. It's limited
- * by the bitwidth of "additional_pages" in union hv_gpa_page_range.
- */
-#define HV_MAX_FLUSH_PAGES (2048)
-
-/* HvFlushGuestPhysicalAddressList hypercall */
-union hv_gpa_page_range {
- u64 address_space;
- struct {
- u64 additional_pages:11;
- u64 largepage:1;
- u64 basepfn:52;
- } page;
-};
-
-/*
- * All input flush parameters should be in single page. The max flush
- * count is equal with how many entries of union hv_gpa_page_range can
- * be populated into the input parameter page.
- */
-#define HV_MAX_FLUSH_REP_COUNT ((HV_HYP_PAGE_SIZE - 2 * sizeof(u64)) / \
- sizeof(union hv_gpa_page_range))
-
-struct hv_guest_mapping_flush_list {
- u64 address_space;
- u64 flags;
- union hv_gpa_page_range gpa_list[HV_MAX_FLUSH_REP_COUNT];
-};
-
-/* HvFlushVirtualAddressSpace, HvFlushVirtualAddressList hypercalls */
-struct hv_tlb_flush {
- u64 address_space;
- u64 flags;
- u64 processor_mask;
- u64 gva_list[];
-} __packed;
-
-/* HvFlushVirtualAddressSpaceEx, HvFlushVirtualAddressListEx hypercalls */
-struct hv_tlb_flush_ex {
- u64 address_space;
- u64 flags;
- struct hv_vpset hv_vp_set;
- u64 gva_list[];
-} __packed;
-
struct hv_partition_assist_pg {
u32 tlb_lock_count;
};
-union hv_msi_entry {
- u64 as_uint64;
- struct {
- u32 address;
- u32 data;
- } __packed;
-};
-
-struct hv_interrupt_entry {
- u32 source; /* 1 for MSI(-X) */
- u32 reserved1;
- union hv_msi_entry msi_entry;
-} __packed;
-/*
- * flags for hv_device_interrupt_target.flags
- */
-#define HV_DEVICE_INTERRUPT_TARGET_MULTICAST 1
-#define HV_DEVICE_INTERRUPT_TARGET_PROCESSOR_SET 2
-
-struct hv_device_interrupt_target {
- u32 vector;
- u32 flags;
- union {
- u64 vp_mask;
- struct hv_vpset vp_set;
- };
-} __packed;
+#include <asm-generic/hyperv-tlfs.h>
-/* HvRetargetDeviceInterrupt hypercall */
-struct hv_retarget_device_interrupt {
- u64 partition_id; /* use "self" */
- u64 device_id;
- struct hv_interrupt_entry int_entry;
- u64 reserved2;
- struct hv_device_interrupt_target int_target;
-} __packed __aligned(8);
#endif
diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
new file mode 100644
index 000000000000..d203c541a65a
--- /dev/null
+++ b/arch/x86/include/asm/idtentry.h
@@ -0,0 +1,652 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_IDTENTRY_H
+#define _ASM_X86_IDTENTRY_H
+
+/* Interrupts/Exceptions */
+#include <asm/trapnr.h>
+
+#ifndef __ASSEMBLY__
+#include <linux/hardirq.h>
+
+#include <asm/irq_stack.h>
+
+void idtentry_enter_user(struct pt_regs *regs);
+void idtentry_exit_user(struct pt_regs *regs);
+
+bool idtentry_enter_cond_rcu(struct pt_regs *regs);
+void idtentry_exit_cond_rcu(struct pt_regs *regs, bool rcu_exit);
+
+/**
+ * DECLARE_IDTENTRY - Declare functions for simple IDT entry points
+ * No error code pushed by hardware
+ * @vector: Vector number (ignored for C)
+ * @func: Function name of the entry point
+ *
+ * Declares three functions:
+ * - The ASM entry point: asm_##func
+ * - The XEN PV trap entry point: xen_##func (maybe unused)
+ * - The C handler called from the ASM entry point
+ *
+ * Note: This is the C variant of DECLARE_IDTENTRY(). As the name says it
+ * declares the entry points for usage in C code. There is an ASM variant
+ * as well which is used to emit the entry stubs in entry_32/64.S.
+ */
+#define DECLARE_IDTENTRY(vector, func) \
+ asmlinkage void asm_##func(void); \
+ asmlinkage void xen_asm_##func(void); \
+ __visible void func(struct pt_regs *regs)
+
+/**
+ * DEFINE_IDTENTRY - Emit code for simple IDT entry points
+ * @func: Function name of the entry point
+ *
+ * @func is called from ASM entry code with interrupts disabled.
+ *
+ * The macro is written so it acts as function definition. Append the
+ * body with a pair of curly brackets.
+ *
+ * idtentry_enter() contains common code which has to be invoked before
+ * arbitrary code in the body. idtentry_exit() contains common code
+ * which has to run before returning to the low level assembly code.
+ */
+#define DEFINE_IDTENTRY(func) \
+static __always_inline void __##func(struct pt_regs *regs); \
+ \
+__visible noinstr void func(struct pt_regs *regs) \
+{ \
+ bool rcu_exit = idtentry_enter_cond_rcu(regs); \
+ \
+ instrumentation_begin(); \
+ __##func (regs); \
+ instrumentation_end(); \
+ idtentry_exit_cond_rcu(regs, rcu_exit); \
+} \
+ \
+static __always_inline void __##func(struct pt_regs *regs)
+
+/* Special case for 32bit IRET 'trap' */
+#define DECLARE_IDTENTRY_SW DECLARE_IDTENTRY
+#define DEFINE_IDTENTRY_SW DEFINE_IDTENTRY
+
+/**
+ * DECLARE_IDTENTRY_ERRORCODE - Declare functions for simple IDT entry points
+ * Error code pushed by hardware
+ * @vector: Vector number (ignored for C)
+ * @func: Function name of the entry point
+ *
+ * Declares three functions:
+ * - The ASM entry point: asm_##func
+ * - The XEN PV trap entry point: xen_##func (maybe unused)
+ * - The C handler called from the ASM entry point
+ *
+ * Same as DECLARE_IDTENTRY, but has an extra error_code argument for the
+ * C-handler.
+ */
+#define DECLARE_IDTENTRY_ERRORCODE(vector, func) \
+ asmlinkage void asm_##func(void); \
+ asmlinkage void xen_asm_##func(void); \
+ __visible void func(struct pt_regs *regs, unsigned long error_code)
+
+/**
+ * DEFINE_IDTENTRY_ERRORCODE - Emit code for simple IDT entry points
+ * Error code pushed by hardware
+ * @func: Function name of the entry point
+ *
+ * Same as DEFINE_IDTENTRY, but has an extra error_code argument
+ */
+#define DEFINE_IDTENTRY_ERRORCODE(func) \
+static __always_inline void __##func(struct pt_regs *regs, \
+ unsigned long error_code); \
+ \
+__visible noinstr void func(struct pt_regs *regs, \
+ unsigned long error_code) \
+{ \
+ bool rcu_exit = idtentry_enter_cond_rcu(regs); \
+ \
+ instrumentation_begin(); \
+ __##func (regs, error_code); \
+ instrumentation_end(); \
+ idtentry_exit_cond_rcu(regs, rcu_exit); \
+} \
+ \
+static __always_inline void __##func(struct pt_regs *regs, \
+ unsigned long error_code)
+
+/**
+ * DECLARE_IDTENTRY_RAW - Declare functions for raw IDT entry points
+ * No error code pushed by hardware
+ * @vector: Vector number (ignored for C)
+ * @func: Function name of the entry point
+ *
+ * Maps to DECLARE_IDTENTRY().
+ */
+#define DECLARE_IDTENTRY_RAW(vector, func) \
+ DECLARE_IDTENTRY(vector, func)
+
+/**
+ * DEFINE_IDTENTRY_RAW - Emit code for raw IDT entry points
+ * @func: Function name of the entry point
+ *
+ * @func is called from ASM entry code with interrupts disabled.
+ *
+ * The macro is written so it acts as function definition. Append the
+ * body with a pair of curly brackets.
+ *
+ * Contrary to DEFINE_IDTENTRY() this does not invoke the
+ * idtentry_enter/exit() helpers before and after the body invocation. This
+ * needs to be done in the body itself if applicable. Use if extra work
+ * is required before the enter/exit() helpers are invoked.
+ */
+#define DEFINE_IDTENTRY_RAW(func) \
+__visible noinstr void func(struct pt_regs *regs)
+
+/**
+ * DECLARE_IDTENTRY_RAW_ERRORCODE - Declare functions for raw IDT entry points
+ * Error code pushed by hardware
+ * @vector: Vector number (ignored for C)
+ * @func: Function name of the entry point
+ *
+ * Maps to DECLARE_IDTENTRY_ERRORCODE()
+ */
+#define DECLARE_IDTENTRY_RAW_ERRORCODE(vector, func) \
+ DECLARE_IDTENTRY_ERRORCODE(vector, func)
+
+/**
+ * DEFINE_IDTENTRY_RAW_ERRORCODE - Emit code for raw IDT entry points
+ * @func: Function name of the entry point
+ *
+ * @func is called from ASM entry code with interrupts disabled.
+ *
+ * The macro is written so it acts as function definition. Append the
+ * body with a pair of curly brackets.
+ *
+ * Contrary to DEFINE_IDTENTRY_ERRORCODE() this does not invoke the
+ * idtentry_enter/exit() helpers before and after the body invocation. This
+ * needs to be done in the body itself if applicable. Use if extra work
+ * is required before the enter/exit() helpers are invoked.
+ */
+#define DEFINE_IDTENTRY_RAW_ERRORCODE(func) \
+__visible noinstr void func(struct pt_regs *regs, unsigned long error_code)
+
+/**
+ * DECLARE_IDTENTRY_IRQ - Declare functions for device interrupt IDT entry
+ * points (common/spurious)
+ * @vector: Vector number (ignored for C)
+ * @func: Function name of the entry point
+ *
+ * Maps to DECLARE_IDTENTRY_ERRORCODE()
+ */
+#define DECLARE_IDTENTRY_IRQ(vector, func) \
+ DECLARE_IDTENTRY_ERRORCODE(vector, func)
+
+/**
+ * DEFINE_IDTENTRY_IRQ - Emit code for device interrupt IDT entry points
+ * @func: Function name of the entry point
+ *
+ * The vector number is pushed by the low level entry stub and handed
+ * to the function as error_code argument which needs to be truncated
+ * to an u8 because the push is sign extending.
+ *
+ * On 64-bit idtentry_enter/exit() are invoked in the ASM entry code before
+ * and after switching to the interrupt stack. On 32-bit this happens in C.
+ *
+ * irq_enter/exit_rcu() are invoked before the function body and the
+ * KVM L1D flush request is set.
+ */
+#define DEFINE_IDTENTRY_IRQ(func) \
+static __always_inline void __##func(struct pt_regs *regs, u8 vector); \
+ \
+__visible noinstr void func(struct pt_regs *regs, \
+ unsigned long error_code) \
+{ \
+ bool rcu_exit = idtentry_enter_cond_rcu(regs); \
+ \
+ instrumentation_begin(); \
+ irq_enter_rcu(); \
+ kvm_set_cpu_l1tf_flush_l1d(); \
+ __##func (regs, (u8)error_code); \
+ irq_exit_rcu(); \
+ instrumentation_end(); \
+ idtentry_exit_cond_rcu(regs, rcu_exit); \
+} \
+ \
+static __always_inline void __##func(struct pt_regs *regs, u8 vector)
+
+/**
+ * DECLARE_IDTENTRY_SYSVEC - Declare functions for system vector entry points
+ * @vector: Vector number (ignored for C)
+ * @func: Function name of the entry point
+ *
+ * Declares three functions:
+ * - The ASM entry point: asm_##func
+ * - The XEN PV trap entry point: xen_##func (maybe unused)
+ * - The C handler called from the ASM entry point
+ *
+ * Maps to DECLARE_IDTENTRY().
+ */
+#define DECLARE_IDTENTRY_SYSVEC(vector, func) \
+ DECLARE_IDTENTRY(vector, func)
+
+/**
+ * DEFINE_IDTENTRY_SYSVEC - Emit code for system vector IDT entry points
+ * @func: Function name of the entry point
+ *
+ * idtentry_enter/exit() and irq_enter/exit_rcu() are invoked before the
+ * function body. KVM L1D flush request is set.
+ *
+ * Runs the function on the interrupt stack if the entry hit kernel mode
+ */
+#define DEFINE_IDTENTRY_SYSVEC(func) \
+static void __##func(struct pt_regs *regs); \
+ \
+__visible noinstr void func(struct pt_regs *regs) \
+{ \
+ bool rcu_exit = idtentry_enter_cond_rcu(regs); \
+ \
+ instrumentation_begin(); \
+ irq_enter_rcu(); \
+ kvm_set_cpu_l1tf_flush_l1d(); \
+ run_on_irqstack_cond(__##func, regs, regs); \
+ irq_exit_rcu(); \
+ instrumentation_end(); \
+ idtentry_exit_cond_rcu(regs, rcu_exit); \
+} \
+ \
+static noinline void __##func(struct pt_regs *regs)
+
+/**
+ * DEFINE_IDTENTRY_SYSVEC_SIMPLE - Emit code for simple system vector IDT
+ * entry points
+ * @func: Function name of the entry point
+ *
+ * Runs the function on the interrupted stack. No switch to IRQ stack and
+ * only the minimal __irq_enter/exit() handling.
+ *
+ * Only use for 'empty' vectors like reschedule IPI and KVM posted
+ * interrupt vectors.
+ */
+#define DEFINE_IDTENTRY_SYSVEC_SIMPLE(func) \
+static __always_inline void __##func(struct pt_regs *regs); \
+ \
+__visible noinstr void func(struct pt_regs *regs) \
+{ \
+ bool rcu_exit = idtentry_enter_cond_rcu(regs); \
+ \
+ instrumentation_begin(); \
+ __irq_enter_raw(); \
+ kvm_set_cpu_l1tf_flush_l1d(); \
+ __##func (regs); \
+ __irq_exit_raw(); \
+ instrumentation_end(); \
+ idtentry_exit_cond_rcu(regs, rcu_exit); \
+} \
+ \
+static __always_inline void __##func(struct pt_regs *regs)
+
+/**
+ * DECLARE_IDTENTRY_XENCB - Declare functions for XEN HV callback entry point
+ * @vector: Vector number (ignored for C)
+ * @func: Function name of the entry point
+ *
+ * Declares three functions:
+ * - The ASM entry point: asm_##func
+ * - The XEN PV trap entry point: xen_##func (maybe unused)
+ * - The C handler called from the ASM entry point
+ *
+ * Maps to DECLARE_IDTENTRY(). Distinct entry point to handle the 32/64-bit
+ * difference
+ */
+#define DECLARE_IDTENTRY_XENCB(vector, func) \
+ DECLARE_IDTENTRY(vector, func)
+
+#ifdef CONFIG_X86_64
+/**
+ * DECLARE_IDTENTRY_IST - Declare functions for IST handling IDT entry points
+ * @vector: Vector number (ignored for C)
+ * @func: Function name of the entry point
+ *
+ * Maps to DECLARE_IDTENTRY_RAW, but declares also the NOIST C handler
+ * which is called from the ASM entry point on user mode entry
+ */
+#define DECLARE_IDTENTRY_IST(vector, func) \
+ DECLARE_IDTENTRY_RAW(vector, func); \
+ __visible void noist_##func(struct pt_regs *regs)
+
+/**
+ * DEFINE_IDTENTRY_IST - Emit code for IST entry points
+ * @func: Function name of the entry point
+ *
+ * Maps to DEFINE_IDTENTRY_RAW
+ */
+#define DEFINE_IDTENTRY_IST(func) \
+ DEFINE_IDTENTRY_RAW(func)
+
+/**
+ * DEFINE_IDTENTRY_NOIST - Emit code for NOIST entry points which
+ * belong to a IST entry point (MCE, DB)
+ * @func: Function name of the entry point. Must be the same as
+ * the function name of the corresponding IST variant
+ *
+ * Maps to DEFINE_IDTENTRY_RAW().
+ */
+#define DEFINE_IDTENTRY_NOIST(func) \
+ DEFINE_IDTENTRY_RAW(noist_##func)
+
+/**
+ * DECLARE_IDTENTRY_DF - Declare functions for double fault
+ * @vector: Vector number (ignored for C)
+ * @func: Function name of the entry point
+ *
+ * Maps to DECLARE_IDTENTRY_RAW_ERRORCODE
+ */
+#define DECLARE_IDTENTRY_DF(vector, func) \
+ DECLARE_IDTENTRY_RAW_ERRORCODE(vector, func)
+
+/**
+ * DEFINE_IDTENTRY_DF - Emit code for double fault
+ * @func: Function name of the entry point
+ *
+ * Maps to DEFINE_IDTENTRY_RAW_ERRORCODE
+ */
+#define DEFINE_IDTENTRY_DF(func) \
+ DEFINE_IDTENTRY_RAW_ERRORCODE(func)
+
+#else /* CONFIG_X86_64 */
+
+/* Maps to a regular IDTENTRY on 32bit for now */
+# define DECLARE_IDTENTRY_IST DECLARE_IDTENTRY
+# define DEFINE_IDTENTRY_IST DEFINE_IDTENTRY
+
+/**
+ * DECLARE_IDTENTRY_DF - Declare functions for double fault 32bit variant
+ * @vector: Vector number (ignored for C)
+ * @func: Function name of the entry point
+ *
+ * Declares two functions:
+ * - The ASM entry point: asm_##func
+ * - The C handler called from the C shim
+ */
+#define DECLARE_IDTENTRY_DF(vector, func) \
+ asmlinkage void asm_##func(void); \
+ __visible void func(struct pt_regs *regs, \
+ unsigned long error_code, \
+ unsigned long address)
+
+/**
+ * DEFINE_IDTENTRY_DF - Emit code for double fault on 32bit
+ * @func: Function name of the entry point
+ *
+ * This is called through the doublefault shim which already provides
+ * cr2 in the address argument.
+ */
+#define DEFINE_IDTENTRY_DF(func) \
+__visible noinstr void func(struct pt_regs *regs, \
+ unsigned long error_code, \
+ unsigned long address)
+
+#endif /* !CONFIG_X86_64 */
+
+/* C-Code mapping */
+#define DECLARE_IDTENTRY_MCE DECLARE_IDTENTRY_IST
+#define DEFINE_IDTENTRY_MCE DEFINE_IDTENTRY_IST
+#define DEFINE_IDTENTRY_MCE_USER DEFINE_IDTENTRY_NOIST
+
+#define DECLARE_IDTENTRY_NMI DECLARE_IDTENTRY_IST
+#define DEFINE_IDTENTRY_NMI DEFINE_IDTENTRY_IST
+
+#define DECLARE_IDTENTRY_DEBUG DECLARE_IDTENTRY_IST
+#define DEFINE_IDTENTRY_DEBUG DEFINE_IDTENTRY_IST
+#define DEFINE_IDTENTRY_DEBUG_USER DEFINE_IDTENTRY_NOIST
+
+/**
+ * DECLARE_IDTENTRY_XEN - Declare functions for XEN redirect IDT entry points
+ * @vector: Vector number (ignored for C)
+ * @func: Function name of the entry point
+ *
+ * Used for xennmi and xendebug redirections. No DEFINE as this is all ASM
+ * indirection magic.
+ */
+#define DECLARE_IDTENTRY_XEN(vector, func) \
+ asmlinkage void xen_asm_exc_xen##func(void); \
+ asmlinkage void asm_exc_xen##func(void)
+
+#else /* !__ASSEMBLY__ */
+
+/*
+ * The ASM variants for DECLARE_IDTENTRY*() which emit the ASM entry stubs.
+ */
+#define DECLARE_IDTENTRY(vector, func) \
+ idtentry vector asm_##func func has_error_code=0
+
+#define DECLARE_IDTENTRY_ERRORCODE(vector, func) \
+ idtentry vector asm_##func func has_error_code=1
+
+/* Special case for 32bit IRET 'trap'. Do not emit ASM code */
+#define DECLARE_IDTENTRY_SW(vector, func)
+
+#define DECLARE_IDTENTRY_RAW(vector, func) \
+ DECLARE_IDTENTRY(vector, func)
+
+#define DECLARE_IDTENTRY_RAW_ERRORCODE(vector, func) \
+ DECLARE_IDTENTRY_ERRORCODE(vector, func)
+
+/* Entries for common/spurious (device) interrupts */
+#define DECLARE_IDTENTRY_IRQ(vector, func) \
+ idtentry_irq vector func
+
+/* System vector entries */
+#define DECLARE_IDTENTRY_SYSVEC(vector, func) \
+ idtentry_sysvec vector func
+
+#ifdef CONFIG_X86_64
+# define DECLARE_IDTENTRY_MCE(vector, func) \
+ idtentry_mce_db vector asm_##func func
+
+# define DECLARE_IDTENTRY_DEBUG(vector, func) \
+ idtentry_mce_db vector asm_##func func
+
+# define DECLARE_IDTENTRY_DF(vector, func) \
+ idtentry_df vector asm_##func func
+
+# define DECLARE_IDTENTRY_XENCB(vector, func) \
+ DECLARE_IDTENTRY(vector, func)
+
+#else
+# define DECLARE_IDTENTRY_MCE(vector, func) \
+ DECLARE_IDTENTRY(vector, func)
+
+# define DECLARE_IDTENTRY_DEBUG(vector, func) \
+ DECLARE_IDTENTRY(vector, func)
+
+/* No ASM emitted for DF as this goes through a C shim */
+# define DECLARE_IDTENTRY_DF(vector, func)
+
+/* No ASM emitted for XEN hypervisor callback */
+# define DECLARE_IDTENTRY_XENCB(vector, func)
+
+#endif
+
+/* No ASM code emitted for NMI */
+#define DECLARE_IDTENTRY_NMI(vector, func)
+
+/* XEN NMI and DB wrapper */
+#define DECLARE_IDTENTRY_XEN(vector, func) \
+ idtentry vector asm_exc_xen##func exc_##func has_error_code=0
+
+/*
+ * ASM code to emit the common vector entry stubs where each stub is
+ * packed into 8 bytes.
+ *
+ * Note, that the 'pushq imm8' is emitted via '.byte 0x6a, vector' because
+ * GCC treats the local vector variable as unsigned int and would expand
+ * all vectors above 0x7F to a 5 byte push. The original code did an
+ * adjustment of the vector number to be in the signed byte range to avoid
+ * this. While clever it's mindboggling counterintuitive and requires the
+ * odd conversion back to a real vector number in the C entry points. Using
+ * .byte achieves the same thing and the only fixup needed in the C entry
+ * point is to mask off the bits above bit 7 because the push is sign
+ * extending.
+ */
+ .align 8
+SYM_CODE_START(irq_entries_start)
+ vector=FIRST_EXTERNAL_VECTOR
+ pos = .
+ .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
+ UNWIND_HINT_IRET_REGS
+ .byte 0x6a, vector
+ jmp asm_common_interrupt
+ nop
+ /* Ensure that the above is 8 bytes max */
+ . = pos + 8
+ pos=pos+8
+ vector=vector+1
+ .endr
+SYM_CODE_END(irq_entries_start)
+
+#ifdef CONFIG_X86_LOCAL_APIC
+ .align 8
+SYM_CODE_START(spurious_entries_start)
+ vector=FIRST_SYSTEM_VECTOR
+ pos = .
+ .rept (NR_VECTORS - FIRST_SYSTEM_VECTOR)
+ UNWIND_HINT_IRET_REGS
+ .byte 0x6a, vector
+ jmp asm_spurious_interrupt
+ nop
+ /* Ensure that the above is 8 bytes max */
+ . = pos + 8
+ pos=pos+8
+ vector=vector+1
+ .endr
+SYM_CODE_END(spurious_entries_start)
+#endif
+
+#endif /* __ASSEMBLY__ */
+
+/*
+ * The actual entry points. Note that DECLARE_IDTENTRY*() serves two
+ * purposes:
+ * - provide the function declarations when included from C-Code
+ * - emit the ASM stubs when included from entry_32/64.S
+ *
+ * This avoids duplicate defines and ensures that everything is consistent.
+ */
+
+/*
+ * Dummy trap number so the low level ASM macro vector number checks do not
+ * match which results in emitting plain IDTENTRY stubs without bells and
+ * whistels.
+ */
+#define X86_TRAP_OTHER 0xFFFF
+
+/* Simple exception entry points. No hardware error code */
+DECLARE_IDTENTRY(X86_TRAP_DE, exc_divide_error);
+DECLARE_IDTENTRY(X86_TRAP_OF, exc_overflow);
+DECLARE_IDTENTRY(X86_TRAP_BR, exc_bounds);
+DECLARE_IDTENTRY(X86_TRAP_UD, exc_invalid_op);
+DECLARE_IDTENTRY(X86_TRAP_NM, exc_device_not_available);
+DECLARE_IDTENTRY(X86_TRAP_OLD_MF, exc_coproc_segment_overrun);
+DECLARE_IDTENTRY(X86_TRAP_SPURIOUS, exc_spurious_interrupt_bug);
+DECLARE_IDTENTRY(X86_TRAP_MF, exc_coprocessor_error);
+DECLARE_IDTENTRY(X86_TRAP_XF, exc_simd_coprocessor_error);
+
+/* 32bit software IRET trap. Do not emit ASM code */
+DECLARE_IDTENTRY_SW(X86_TRAP_IRET, iret_error);
+
+/* Simple exception entries with error code pushed by hardware */
+DECLARE_IDTENTRY_ERRORCODE(X86_TRAP_TS, exc_invalid_tss);
+DECLARE_IDTENTRY_ERRORCODE(X86_TRAP_NP, exc_segment_not_present);
+DECLARE_IDTENTRY_ERRORCODE(X86_TRAP_SS, exc_stack_segment);
+DECLARE_IDTENTRY_ERRORCODE(X86_TRAP_GP, exc_general_protection);
+DECLARE_IDTENTRY_ERRORCODE(X86_TRAP_AC, exc_alignment_check);
+
+/* Raw exception entries which need extra work */
+DECLARE_IDTENTRY_RAW(X86_TRAP_BP, exc_int3);
+DECLARE_IDTENTRY_RAW_ERRORCODE(X86_TRAP_PF, exc_page_fault);
+
+#ifdef CONFIG_X86_MCE
+DECLARE_IDTENTRY_MCE(X86_TRAP_MC, exc_machine_check);
+#endif
+
+/* NMI */
+DECLARE_IDTENTRY_NMI(X86_TRAP_NMI, exc_nmi);
+DECLARE_IDTENTRY_XEN(X86_TRAP_NMI, nmi);
+
+/* #DB */
+DECLARE_IDTENTRY_DEBUG(X86_TRAP_DB, exc_debug);
+DECLARE_IDTENTRY_XEN(X86_TRAP_DB, debug);
+
+/* #DF */
+DECLARE_IDTENTRY_DF(X86_TRAP_DF, exc_double_fault);
+
+#ifdef CONFIG_XEN_PV
+DECLARE_IDTENTRY_XENCB(X86_TRAP_OTHER, exc_xen_hypervisor_callback);
+#endif
+
+/* Device interrupts common/spurious */
+DECLARE_IDTENTRY_IRQ(X86_TRAP_OTHER, common_interrupt);
+#ifdef CONFIG_X86_LOCAL_APIC
+DECLARE_IDTENTRY_IRQ(X86_TRAP_OTHER, spurious_interrupt);
+#endif
+
+/* System vector entry points */
+#ifdef CONFIG_X86_LOCAL_APIC
+DECLARE_IDTENTRY_SYSVEC(ERROR_APIC_VECTOR, sysvec_error_interrupt);
+DECLARE_IDTENTRY_SYSVEC(SPURIOUS_APIC_VECTOR, sysvec_spurious_apic_interrupt);
+DECLARE_IDTENTRY_SYSVEC(LOCAL_TIMER_VECTOR, sysvec_apic_timer_interrupt);
+DECLARE_IDTENTRY_SYSVEC(X86_PLATFORM_IPI_VECTOR, sysvec_x86_platform_ipi);
+#endif
+
+#ifdef CONFIG_SMP
+DECLARE_IDTENTRY(RESCHEDULE_VECTOR, sysvec_reschedule_ipi);
+DECLARE_IDTENTRY_SYSVEC(IRQ_MOVE_CLEANUP_VECTOR, sysvec_irq_move_cleanup);
+DECLARE_IDTENTRY_SYSVEC(REBOOT_VECTOR, sysvec_reboot);
+DECLARE_IDTENTRY_SYSVEC(CALL_FUNCTION_SINGLE_VECTOR, sysvec_call_function_single);
+DECLARE_IDTENTRY_SYSVEC(CALL_FUNCTION_VECTOR, sysvec_call_function);
+#endif
+
+#ifdef CONFIG_X86_LOCAL_APIC
+# ifdef CONFIG_X86_UV
+DECLARE_IDTENTRY_SYSVEC(UV_BAU_MESSAGE, sysvec_uv_bau_message);
+# endif
+
+# ifdef CONFIG_X86_MCE_THRESHOLD
+DECLARE_IDTENTRY_SYSVEC(THRESHOLD_APIC_VECTOR, sysvec_threshold);
+# endif
+
+# ifdef CONFIG_X86_MCE_AMD
+DECLARE_IDTENTRY_SYSVEC(DEFERRED_ERROR_VECTOR, sysvec_deferred_error);
+# endif
+
+# ifdef CONFIG_X86_THERMAL_VECTOR
+DECLARE_IDTENTRY_SYSVEC(THERMAL_APIC_VECTOR, sysvec_thermal);
+# endif
+
+# ifdef CONFIG_IRQ_WORK
+DECLARE_IDTENTRY_SYSVEC(IRQ_WORK_VECTOR, sysvec_irq_work);
+# endif
+#endif
+
+#ifdef CONFIG_HAVE_KVM
+DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_VECTOR, sysvec_kvm_posted_intr_ipi);
+DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_WAKEUP_VECTOR, sysvec_kvm_posted_intr_wakeup_ipi);
+DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_NESTED_VECTOR, sysvec_kvm_posted_intr_nested_ipi);
+#endif
+
+#if IS_ENABLED(CONFIG_HYPERV)
+DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_CALLBACK_VECTOR, sysvec_hyperv_callback);
+DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_REENLIGHTENMENT_VECTOR, sysvec_hyperv_reenlightenment);
+DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_STIMER0_VECTOR, sysvec_hyperv_stimer0);
+#endif
+
+#if IS_ENABLED(CONFIG_ACRN_GUEST)
+DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_CALLBACK_VECTOR, sysvec_acrn_hv_callback);
+#endif
+
+#ifdef CONFIG_XEN_PVHVM
+DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_CALLBACK_VECTOR, sysvec_xen_hvm_callback);
+#endif
+
+#undef X86_TRAP_OTHER
+
+#endif
diff --git a/arch/x86/include/asm/intel-mid.h b/arch/x86/include/asm/intel-mid.h
index 8e5af119dc2d..de58391bdee0 100644
--- a/arch/x86/include/asm/intel-mid.h
+++ b/arch/x86/include/asm/intel-mid.h
@@ -88,11 +88,17 @@ static inline bool intel_mid_has_msic(void)
return (intel_mid_identify_cpu() == INTEL_MID_CPU_CHIP_PENWELL);
}
+extern void intel_scu_devices_create(void);
+extern void intel_scu_devices_destroy(void);
+
#else /* !CONFIG_X86_INTEL_MID */
#define intel_mid_identify_cpu() 0
#define intel_mid_has_msic() 0
+static inline void intel_scu_devices_create(void) { }
+static inline void intel_scu_devices_destroy(void) { }
+
#endif /* !CONFIG_X86_INTEL_MID */
enum intel_mid_timer_options {
@@ -115,9 +121,6 @@ extern enum intel_mid_timer_options intel_mid_timer_options;
#define SFI_MTMR_MAX_NUM 8
#define SFI_MRTC_MAX 8
-extern void intel_scu_devices_create(void);
-extern void intel_scu_devices_destroy(void);
-
/* VRTC timer */
#define MRST_VRTC_MAP_SZ 1024
/* #define MRST_VRTC_PGOFFSET 0xc00 */
diff --git a/arch/x86/include/asm/intel_pmc_ipc.h b/arch/x86/include/asm/intel_pmc_ipc.h
deleted file mode 100644
index e6da1ce26256..000000000000
--- a/arch/x86/include/asm/intel_pmc_ipc.h
+++ /dev/null
@@ -1,59 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_INTEL_PMC_IPC_H_
-#define _ASM_X86_INTEL_PMC_IPC_H_
-
-/* Commands */
-#define PMC_IPC_PMIC_ACCESS 0xFF
-#define PMC_IPC_PMIC_ACCESS_READ 0x0
-#define PMC_IPC_PMIC_ACCESS_WRITE 0x1
-#define PMC_IPC_USB_PWR_CTRL 0xF0
-#define PMC_IPC_PMIC_BLACKLIST_SEL 0xEF
-#define PMC_IPC_PHY_CONFIG 0xEE
-#define PMC_IPC_NORTHPEAK_CTRL 0xED
-#define PMC_IPC_PM_DEBUG 0xEC
-#define PMC_IPC_PMC_TELEMTRY 0xEB
-#define PMC_IPC_PMC_FW_MSG_CTRL 0xEA
-
-/* IPC return code */
-#define IPC_ERR_NONE 0
-#define IPC_ERR_CMD_NOT_SUPPORTED 1
-#define IPC_ERR_CMD_NOT_SERVICED 2
-#define IPC_ERR_UNABLE_TO_SERVICE 3
-#define IPC_ERR_CMD_INVALID 4
-#define IPC_ERR_CMD_FAILED 5
-#define IPC_ERR_EMSECURITY 6
-#define IPC_ERR_UNSIGNEDKERNEL 7
-
-/* GCR reg offsets from gcr base*/
-#define PMC_GCR_PMC_CFG_REG 0x08
-#define PMC_GCR_TELEM_DEEP_S0IX_REG 0x78
-#define PMC_GCR_TELEM_SHLW_S0IX_REG 0x80
-
-#if IS_ENABLED(CONFIG_INTEL_PMC_IPC)
-
-int intel_pmc_ipc_command(u32 cmd, u32 sub, u8 *in, u32 inlen,
- u32 *out, u32 outlen);
-int intel_pmc_s0ix_counter_read(u64 *data);
-int intel_pmc_gcr_read64(u32 offset, u64 *data);
-
-#else
-
-static inline int intel_pmc_ipc_command(u32 cmd, u32 sub, u8 *in, u32 inlen,
- u32 *out, u32 outlen)
-{
- return -EINVAL;
-}
-
-static inline int intel_pmc_s0ix_counter_read(u64 *data)
-{
- return -EINVAL;
-}
-
-static inline int intel_pmc_gcr_read64(u32 offset, u64 *data)
-{
- return -EINVAL;
-}
-
-#endif /*CONFIG_INTEL_PMC_IPC*/
-
-#endif
diff --git a/arch/x86/include/asm/intel_scu_ipc.h b/arch/x86/include/asm/intel_scu_ipc.h
index 2a1442ba6e78..11d457af68c5 100644
--- a/arch/x86/include/asm/intel_scu_ipc.h
+++ b/arch/x86/include/asm/intel_scu_ipc.h
@@ -2,61 +2,69 @@
#ifndef _ASM_X86_INTEL_SCU_IPC_H_
#define _ASM_X86_INTEL_SCU_IPC_H_
-#include <linux/notifier.h>
-
-#define IPCMSG_INDIRECT_READ 0x02
-#define IPCMSG_INDIRECT_WRITE 0x05
-
-#define IPCMSG_COLD_OFF 0x80 /* Only for Tangier */
-
-#define IPCMSG_WARM_RESET 0xF0
-#define IPCMSG_COLD_RESET 0xF1
-#define IPCMSG_SOFT_RESET 0xF2
-#define IPCMSG_COLD_BOOT 0xF3
-
-#define IPCMSG_VRTC 0xFA /* Set vRTC device */
- /* Command id associated with message IPCMSG_VRTC */
- #define IPC_CMD_VRTC_SETTIME 1 /* Set time */
- #define IPC_CMD_VRTC_SETALARM 2 /* Set alarm */
-
-/* Read single register */
-int intel_scu_ipc_ioread8(u16 addr, u8 *data);
-
-/* Read a vector */
-int intel_scu_ipc_readv(u16 *addr, u8 *data, int len);
-
-/* Write single register */
-int intel_scu_ipc_iowrite8(u16 addr, u8 data);
-
-/* Write a vector */
-int intel_scu_ipc_writev(u16 *addr, u8 *data, int len);
-
-/* Update single register based on the mask */
-int intel_scu_ipc_update_register(u16 addr, u8 data, u8 mask);
-
-/* Issue commands to the SCU with or without data */
-int intel_scu_ipc_simple_command(int cmd, int sub);
-int intel_scu_ipc_command(int cmd, int sub, u32 *in, int inlen,
- u32 *out, int outlen);
-
-extern struct blocking_notifier_head intel_scu_notifier;
-
-static inline void intel_scu_notifier_add(struct notifier_block *nb)
-{
- blocking_notifier_chain_register(&intel_scu_notifier, nb);
-}
-
-static inline void intel_scu_notifier_remove(struct notifier_block *nb)
-{
- blocking_notifier_chain_unregister(&intel_scu_notifier, nb);
-}
-
-static inline int intel_scu_notifier_post(unsigned long v, void *p)
+#include <linux/ioport.h>
+
+struct device;
+struct intel_scu_ipc_dev;
+
+/**
+ * struct intel_scu_ipc_data - Data used to configure SCU IPC
+ * @mem: Base address of SCU IPC MMIO registers
+ * @irq: The IRQ number used for SCU (optional)
+ */
+struct intel_scu_ipc_data {
+ struct resource mem;
+ int irq;
+};
+
+struct intel_scu_ipc_dev *
+__intel_scu_ipc_register(struct device *parent,
+ const struct intel_scu_ipc_data *scu_data,
+ struct module *owner);
+
+#define intel_scu_ipc_register(parent, scu_data) \
+ __intel_scu_ipc_register(parent, scu_data, THIS_MODULE)
+
+void intel_scu_ipc_unregister(struct intel_scu_ipc_dev *scu);
+
+struct intel_scu_ipc_dev *
+__devm_intel_scu_ipc_register(struct device *parent,
+ const struct intel_scu_ipc_data *scu_data,
+ struct module *owner);
+
+#define devm_intel_scu_ipc_register(parent, scu_data) \
+ __devm_intel_scu_ipc_register(parent, scu_data, THIS_MODULE)
+
+struct intel_scu_ipc_dev *intel_scu_ipc_dev_get(void);
+void intel_scu_ipc_dev_put(struct intel_scu_ipc_dev *scu);
+struct intel_scu_ipc_dev *devm_intel_scu_ipc_dev_get(struct device *dev);
+
+int intel_scu_ipc_dev_ioread8(struct intel_scu_ipc_dev *scu, u16 addr,
+ u8 *data);
+int intel_scu_ipc_dev_iowrite8(struct intel_scu_ipc_dev *scu, u16 addr,
+ u8 data);
+int intel_scu_ipc_dev_readv(struct intel_scu_ipc_dev *scu, u16 *addr,
+ u8 *data, size_t len);
+int intel_scu_ipc_dev_writev(struct intel_scu_ipc_dev *scu, u16 *addr,
+ u8 *data, size_t len);
+
+int intel_scu_ipc_dev_update(struct intel_scu_ipc_dev *scu, u16 addr,
+ u8 data, u8 mask);
+
+int intel_scu_ipc_dev_simple_command(struct intel_scu_ipc_dev *scu, int cmd,
+ int sub);
+int intel_scu_ipc_dev_command_with_size(struct intel_scu_ipc_dev *scu, int cmd,
+ int sub, const void *in, size_t inlen,
+ size_t size, void *out, size_t outlen);
+
+static inline int intel_scu_ipc_dev_command(struct intel_scu_ipc_dev *scu, int cmd,
+ int sub, const void *in, size_t inlen,
+ void *out, size_t outlen)
{
- return blocking_notifier_call_chain(&intel_scu_notifier, v, p);
+ return intel_scu_ipc_dev_command_with_size(scu, cmd, sub, in, inlen,
+ inlen, out, outlen);
}
-#define SCU_AVAILABLE 1
-#define SCU_DOWN 2
+#include <asm/intel_scu_ipc_legacy.h>
#endif
diff --git a/arch/x86/include/asm/intel_scu_ipc_legacy.h b/arch/x86/include/asm/intel_scu_ipc_legacy.h
new file mode 100644
index 000000000000..4cf13fecb673
--- /dev/null
+++ b/arch/x86/include/asm/intel_scu_ipc_legacy.h
@@ -0,0 +1,91 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_INTEL_SCU_IPC_LEGACY_H_
+#define _ASM_X86_INTEL_SCU_IPC_LEGACY_H_
+
+#include <linux/notifier.h>
+
+#define IPCMSG_INDIRECT_READ 0x02
+#define IPCMSG_INDIRECT_WRITE 0x05
+
+#define IPCMSG_COLD_OFF 0x80 /* Only for Tangier */
+
+#define IPCMSG_WARM_RESET 0xF0
+#define IPCMSG_COLD_RESET 0xF1
+#define IPCMSG_SOFT_RESET 0xF2
+#define IPCMSG_COLD_BOOT 0xF3
+
+#define IPCMSG_VRTC 0xFA /* Set vRTC device */
+/* Command id associated with message IPCMSG_VRTC */
+#define IPC_CMD_VRTC_SETTIME 1 /* Set time */
+#define IPC_CMD_VRTC_SETALARM 2 /* Set alarm */
+
+/* Don't call these in new code - they will be removed eventually */
+
+/* Read single register */
+static inline int intel_scu_ipc_ioread8(u16 addr, u8 *data)
+{
+ return intel_scu_ipc_dev_ioread8(NULL, addr, data);
+}
+
+/* Read a vector */
+static inline int intel_scu_ipc_readv(u16 *addr, u8 *data, int len)
+{
+ return intel_scu_ipc_dev_readv(NULL, addr, data, len);
+}
+
+/* Write single register */
+static inline int intel_scu_ipc_iowrite8(u16 addr, u8 data)
+{
+ return intel_scu_ipc_dev_iowrite8(NULL, addr, data);
+}
+
+/* Write a vector */
+static inline int intel_scu_ipc_writev(u16 *addr, u8 *data, int len)
+{
+ return intel_scu_ipc_dev_writev(NULL, addr, data, len);
+}
+
+/* Update single register based on the mask */
+static inline int intel_scu_ipc_update_register(u16 addr, u8 data, u8 mask)
+{
+ return intel_scu_ipc_dev_update(NULL, addr, data, mask);
+}
+
+/* Issue commands to the SCU with or without data */
+static inline int intel_scu_ipc_simple_command(int cmd, int sub)
+{
+ return intel_scu_ipc_dev_simple_command(NULL, cmd, sub);
+}
+
+static inline int intel_scu_ipc_command(int cmd, int sub, u32 *in, int inlen,
+ u32 *out, int outlen)
+{
+ /* New API takes both inlen and outlen as bytes so convert here */
+ size_t inbytes = inlen * sizeof(u32);
+ size_t outbytes = outlen * sizeof(u32);
+
+ return intel_scu_ipc_dev_command_with_size(NULL, cmd, sub, in, inbytes,
+ inlen, out, outbytes);
+}
+
+extern struct blocking_notifier_head intel_scu_notifier;
+
+static inline void intel_scu_notifier_add(struct notifier_block *nb)
+{
+ blocking_notifier_chain_register(&intel_scu_notifier, nb);
+}
+
+static inline void intel_scu_notifier_remove(struct notifier_block *nb)
+{
+ blocking_notifier_chain_unregister(&intel_scu_notifier, nb);
+}
+
+static inline int intel_scu_notifier_post(unsigned long v, void *p)
+{
+ return blocking_notifier_call_chain(&intel_scu_notifier, v, p);
+}
+
+#define SCU_AVAILABLE 1
+#define SCU_DOWN 2
+
+#endif
diff --git a/arch/x86/include/asm/intel_telemetry.h b/arch/x86/include/asm/intel_telemetry.h
index 2f77e31a1283..8046e70dfd7c 100644
--- a/arch/x86/include/asm/intel_telemetry.h
+++ b/arch/x86/include/asm/intel_telemetry.h
@@ -10,6 +10,8 @@
#define TELEM_MAX_EVENTS_SRAM 28
#define TELEM_MAX_OS_ALLOCATED_EVENTS 20
+#include <asm/intel_scu_ipc.h>
+
enum telemetry_unit {
TELEM_PSS = 0,
TELEM_IOSS,
@@ -51,6 +53,8 @@ struct telemetry_plt_config {
struct telemetry_unit_config ioss_config;
struct mutex telem_trace_lock;
struct mutex telem_lock;
+ struct intel_pmc_dev *pmc;
+ struct intel_scu_ipc_dev *scu;
bool telem_in_use;
};
@@ -92,7 +96,7 @@ int telemetry_set_pltdata(const struct telemetry_core_ops *ops,
int telemetry_clear_pltdata(void);
-int telemetry_pltconfig_valid(void);
+struct telemetry_plt_config *telemetry_get_pltdata(void);
int telemetry_get_evtname(enum telemetry_unit telem_unit,
const char **name, int len);
diff --git a/arch/x86/include/asm/invpcid.h b/arch/x86/include/asm/invpcid.h
index 989cfa86de85..734482afbf81 100644
--- a/arch/x86/include/asm/invpcid.h
+++ b/arch/x86/include/asm/invpcid.h
@@ -12,12 +12,9 @@ static inline void __invpcid(unsigned long pcid, unsigned long addr,
* stale TLB entries and, especially if we're flushing global
* mappings, we don't want the compiler to reorder any subsequent
* memory accesses before the TLB flush.
- *
- * The hex opcode is invpcid (%ecx), %eax in 32-bit mode and
- * invpcid (%rcx), %rax in long mode.
*/
- asm volatile (".byte 0x66, 0x0f, 0x38, 0x82, 0x01"
- : : "m" (desc), "a" (type), "c" (&desc) : "memory");
+ asm volatile("invpcid %[desc], %[type]"
+ :: [desc] "m" (desc), [type] "r" (type) : "memory");
}
#define INVPCID_TYPE_INDIV_ADDR 0
diff --git a/arch/x86/include/asm/io_bitmap.h b/arch/x86/include/asm/io_bitmap.h
index 07344d82e88e..ac1a99ffbd8d 100644
--- a/arch/x86/include/asm/io_bitmap.h
+++ b/arch/x86/include/asm/io_bitmap.h
@@ -17,7 +17,7 @@ struct task_struct;
#ifdef CONFIG_X86_IOPL_IOPERM
void io_bitmap_share(struct task_struct *tsk);
-void io_bitmap_exit(void);
+void io_bitmap_exit(struct task_struct *tsk);
void native_tss_update_io_bitmap(void);
@@ -29,7 +29,7 @@ void native_tss_update_io_bitmap(void);
#else
static inline void io_bitmap_share(struct task_struct *tsk) { }
-static inline void io_bitmap_exit(void) { }
+static inline void io_bitmap_exit(struct task_struct *tsk) { }
static inline void tss_update_io_bitmap(void) { }
#endif
diff --git a/arch/x86/include/asm/iomap.h b/arch/x86/include/asm/iomap.h
index 2a7b3211ee7a..bacf68c4d70e 100644
--- a/arch/x86/include/asm/iomap.h
+++ b/arch/x86/include/asm/iomap.h
@@ -10,7 +10,6 @@
#include <linux/mm.h>
#include <linux/uaccess.h>
#include <asm/cacheflush.h>
-#include <asm/pgtable.h>
#include <asm/tlbflush.h>
void __iomem *
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index 72fba0eeeb30..528c8a71fe7f 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -11,6 +11,13 @@
#include <asm/apicdef.h>
#include <asm/irq_vectors.h>
+/*
+ * The irq entry code is in the noinstr section and the start/end of
+ * __irqentry_text is emitted via labels. Make the build fail if
+ * something moves a C function into the __irq_entry section.
+ */
+#define __irq_entry __invalid_section
+
static inline int irq_canonicalize(int irq)
{
return ((irq == 2) ? 9 : irq);
@@ -26,17 +33,14 @@ extern void fixup_irqs(void);
#ifdef CONFIG_HAVE_KVM
extern void kvm_set_posted_intr_wakeup_handler(void (*handler)(void));
-extern __visible void smp_kvm_posted_intr_ipi(struct pt_regs *regs);
-extern __visible void smp_kvm_posted_intr_wakeup_ipi(struct pt_regs *regs);
-extern __visible void smp_kvm_posted_intr_nested_ipi(struct pt_regs *regs);
#endif
extern void (*x86_platform_ipi_callback)(void);
extern void native_init_IRQ(void);
-extern void handle_irq(struct irq_desc *desc, struct pt_regs *regs);
+extern void __handle_irq(struct irq_desc *desc, struct pt_regs *regs);
-extern __visible void do_IRQ(struct pt_regs *regs);
+extern __visible void do_IRQ(struct pt_regs *regs, unsigned long vector);
extern void init_ISA_irqs(void);
@@ -46,7 +50,6 @@ extern void __init init_IRQ(void);
void arch_trigger_cpumask_backtrace(const struct cpumask *mask,
bool exclude_self);
-extern __visible void smp_x86_platform_ipi(struct pt_regs *regs);
#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace
#endif
diff --git a/arch/x86/include/asm/irq_regs.h b/arch/x86/include/asm/irq_regs.h
deleted file mode 100644
index 187ce59aea28..000000000000
--- a/arch/x86/include/asm/irq_regs.h
+++ /dev/null
@@ -1,32 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Per-cpu current frame pointer - the location of the last exception frame on
- * the stack, stored in the per-cpu area.
- *
- * Jeremy Fitzhardinge <jeremy@goop.org>
- */
-#ifndef _ASM_X86_IRQ_REGS_H
-#define _ASM_X86_IRQ_REGS_H
-
-#include <asm/percpu.h>
-
-#define ARCH_HAS_OWN_IRQ_REGS
-
-DECLARE_PER_CPU(struct pt_regs *, irq_regs);
-
-static inline struct pt_regs *get_irq_regs(void)
-{
- return __this_cpu_read(irq_regs);
-}
-
-static inline struct pt_regs *set_irq_regs(struct pt_regs *new_regs)
-{
- struct pt_regs *old_regs;
-
- old_regs = get_irq_regs();
- __this_cpu_write(irq_regs, new_regs);
-
- return old_regs;
-}
-
-#endif /* _ASM_X86_IRQ_REGS_32_H */
diff --git a/arch/x86/include/asm/irq_stack.h b/arch/x86/include/asm/irq_stack.h
new file mode 100644
index 000000000000..4ae66f097101
--- /dev/null
+++ b/arch/x86/include/asm/irq_stack.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_IRQ_STACK_H
+#define _ASM_X86_IRQ_STACK_H
+
+#include <linux/ptrace.h>
+
+#include <asm/processor.h>
+
+#ifdef CONFIG_X86_64
+static __always_inline bool irqstack_active(void)
+{
+ return __this_cpu_read(irq_count) != -1;
+}
+
+void asm_call_on_stack(void *sp, void *func, void *arg);
+
+static __always_inline void __run_on_irqstack(void *func, void *arg)
+{
+ void *tos = __this_cpu_read(hardirq_stack_ptr);
+
+ __this_cpu_add(irq_count, 1);
+ asm_call_on_stack(tos - 8, func, arg);
+ __this_cpu_sub(irq_count, 1);
+}
+
+#else /* CONFIG_X86_64 */
+static inline bool irqstack_active(void) { return false; }
+static inline void __run_on_irqstack(void *func, void *arg) { }
+#endif /* !CONFIG_X86_64 */
+
+static __always_inline bool irq_needs_irq_stack(struct pt_regs *regs)
+{
+ if (IS_ENABLED(CONFIG_X86_32))
+ return false;
+ if (!regs)
+ return !irqstack_active();
+ return !user_mode(regs) && !irqstack_active();
+}
+
+static __always_inline void run_on_irqstack_cond(void *func, void *arg,
+ struct pt_regs *regs)
+{
+ void (*__func)(void *arg) = func;
+
+ lockdep_assert_irqs_disabled();
+
+ if (irq_needs_irq_stack(regs))
+ __run_on_irqstack(__func, arg);
+ else
+ __func(arg);
+}
+
+#endif
diff --git a/arch/x86/include/asm/irq_work.h b/arch/x86/include/asm/irq_work.h
index 80b35e3adf03..800ffce0db29 100644
--- a/arch/x86/include/asm/irq_work.h
+++ b/arch/x86/include/asm/irq_work.h
@@ -10,7 +10,6 @@ static inline bool arch_irq_work_has_interrupt(void)
return boot_cpu_has(X86_FEATURE_APIC);
}
extern void arch_irq_work_raise(void);
-extern __visible void smp_irq_work_interrupt(struct pt_regs *regs);
#else
static inline bool arch_irq_work_has_interrupt(void)
{
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index 8a0e56e1dcc9..02a0cf547d7b 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -17,7 +17,7 @@
/* Declaration required for gcc < 4.9 to prevent -Werror=missing-prototypes */
extern inline unsigned long native_save_fl(void);
-extern inline unsigned long native_save_fl(void)
+extern __always_inline unsigned long native_save_fl(void)
{
unsigned long flags;
@@ -44,12 +44,12 @@ extern inline void native_restore_fl(unsigned long flags)
:"memory", "cc");
}
-static inline void native_irq_disable(void)
+static __always_inline void native_irq_disable(void)
{
asm volatile("cli": : :"memory");
}
-static inline void native_irq_enable(void)
+static __always_inline void native_irq_enable(void)
{
asm volatile("sti": : :"memory");
}
@@ -74,22 +74,22 @@ static inline __cpuidle void native_halt(void)
#ifndef __ASSEMBLY__
#include <linux/types.h>
-static inline notrace unsigned long arch_local_save_flags(void)
+static __always_inline unsigned long arch_local_save_flags(void)
{
return native_save_fl();
}
-static inline notrace void arch_local_irq_restore(unsigned long flags)
+static __always_inline void arch_local_irq_restore(unsigned long flags)
{
native_restore_fl(flags);
}
-static inline notrace void arch_local_irq_disable(void)
+static __always_inline void arch_local_irq_disable(void)
{
native_irq_disable();
}
-static inline notrace void arch_local_irq_enable(void)
+static __always_inline void arch_local_irq_enable(void)
{
native_irq_enable();
}
@@ -115,7 +115,7 @@ static inline __cpuidle void halt(void)
/*
* For spinlocks, etc:
*/
-static inline notrace unsigned long arch_local_irq_save(void)
+static __always_inline unsigned long arch_local_irq_save(void)
{
unsigned long flags = arch_local_save_flags();
arch_local_irq_disable();
@@ -159,12 +159,12 @@ static inline notrace unsigned long arch_local_irq_save(void)
#endif /* CONFIG_PARAVIRT_XXL */
#ifndef __ASSEMBLY__
-static inline int arch_irqs_disabled_flags(unsigned long flags)
+static __always_inline int arch_irqs_disabled_flags(unsigned long flags)
{
return !(flags & X86_EFLAGS_IF);
}
-static inline int arch_irqs_disabled(void)
+static __always_inline int arch_irqs_disabled(void)
{
unsigned long flags = arch_local_save_flags();
@@ -172,38 +172,4 @@ static inline int arch_irqs_disabled(void)
}
#endif /* !__ASSEMBLY__ */
-#ifdef __ASSEMBLY__
-#ifdef CONFIG_TRACE_IRQFLAGS
-# define TRACE_IRQS_ON call trace_hardirqs_on_thunk;
-# define TRACE_IRQS_OFF call trace_hardirqs_off_thunk;
-#else
-# define TRACE_IRQS_ON
-# define TRACE_IRQS_OFF
-#endif
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# ifdef CONFIG_X86_64
-# define LOCKDEP_SYS_EXIT call lockdep_sys_exit_thunk
-# define LOCKDEP_SYS_EXIT_IRQ \
- TRACE_IRQS_ON; \
- sti; \
- call lockdep_sys_exit_thunk; \
- cli; \
- TRACE_IRQS_OFF;
-# else
-# define LOCKDEP_SYS_EXIT \
- pushl %eax; \
- pushl %ecx; \
- pushl %edx; \
- call lockdep_sys_exit; \
- popl %edx; \
- popl %ecx; \
- popl %eax;
-# define LOCKDEP_SYS_EXIT_IRQ
-# endif
-#else
-# define LOCKDEP_SYS_EXIT
-# define LOCKDEP_SYS_EXIT_IRQ
-#endif
-#endif /* __ASSEMBLY__ */
-
#endif
diff --git a/arch/x86/include/asm/kaslr.h b/arch/x86/include/asm/kaslr.h
index db7ba2feb947..0648190467ba 100644
--- a/arch/x86/include/asm/kaslr.h
+++ b/arch/x86/include/asm/kaslr.h
@@ -6,8 +6,10 @@ unsigned long kaslr_get_random_long(const char *purpose);
#ifdef CONFIG_RANDOMIZE_MEMORY
void kernel_randomize_memory(void);
+void init_trampoline_kaslr(void);
#else
static inline void kernel_randomize_memory(void) { }
+static inline void init_trampoline_kaslr(void) {}
#endif /* CONFIG_RANDOMIZE_MEMORY */
#endif
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 42a2d0d3984a..1da5858501ca 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -83,6 +83,10 @@
#define KVM_REQ_GET_VMCS12_PAGES KVM_ARCH_REQ(24)
#define KVM_REQ_APICV_UPDATE \
KVM_ARCH_REQ_FLAGS(25, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
+#define KVM_REQ_TLB_FLUSH_CURRENT KVM_ARCH_REQ(26)
+#define KVM_REQ_HV_TLB_FLUSH \
+ KVM_ARCH_REQ_FLAGS(27, KVM_REQUEST_NO_WAKEUP)
+#define KVM_REQ_APF_READY KVM_ARCH_REQ(28)
#define CR0_RESERVED_BITS \
(~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \
@@ -107,15 +111,8 @@
#define UNMAPPED_GVA (~(gpa_t)0)
/* KVM Hugepage definitions for x86 */
-enum {
- PT_PAGE_TABLE_LEVEL = 1,
- PT_DIRECTORY_LEVEL = 2,
- PT_PDPE_LEVEL = 3,
- /* set max level to the biggest one */
- PT_MAX_HUGEPAGE_LEVEL = PT_PDPE_LEVEL,
-};
-#define KVM_NR_PAGE_SIZES (PT_MAX_HUGEPAGE_LEVEL - \
- PT_PAGE_TABLE_LEVEL + 1)
+#define KVM_MAX_HUGEPAGE_LEVEL PG_LEVEL_1G
+#define KVM_NR_PAGE_SIZES (KVM_MAX_HUGEPAGE_LEVEL - PG_LEVEL_4K + 1)
#define KVM_HPAGE_GFN_SHIFT(x) (((x) - 1) * 9)
#define KVM_HPAGE_SHIFT(x) (PAGE_SHIFT + KVM_HPAGE_GFN_SHIFT(x))
#define KVM_HPAGE_SIZE(x) (1UL << KVM_HPAGE_SHIFT(x))
@@ -124,7 +121,7 @@ enum {
static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level)
{
- /* KVM_HPAGE_GFN_SHIFT(PT_PAGE_TABLE_LEVEL) must be 0. */
+ /* KVM_HPAGE_GFN_SHIFT(PG_LEVEL_4K) must be 0. */
return (gfn >> KVM_HPAGE_GFN_SHIFT(level)) -
(base_gfn >> KVM_HPAGE_GFN_SHIFT(level));
}
@@ -164,9 +161,13 @@ enum kvm_reg {
NR_VCPU_REGS,
VCPU_EXREG_PDPTR = NR_VCPU_REGS,
+ VCPU_EXREG_CR0,
VCPU_EXREG_CR3,
+ VCPU_EXREG_CR4,
VCPU_EXREG_RFLAGS,
VCPU_EXREG_SEGMENTS,
+ VCPU_EXREG_EXIT_INFO_1,
+ VCPU_EXREG_EXIT_INFO_2,
};
enum {
@@ -182,8 +183,10 @@ enum {
enum exit_fastpath_completion {
EXIT_FASTPATH_NONE,
- EXIT_FASTPATH_SKIP_EMUL_INS,
+ EXIT_FASTPATH_REENTER_GUEST,
+ EXIT_FASTPATH_EXIT_HANDLED,
};
+typedef enum exit_fastpath_completion fastpath_t;
struct x86_emulate_ctxt;
struct x86_exception;
@@ -372,12 +375,12 @@ struct rsvd_bits_validate {
};
struct kvm_mmu_root_info {
- gpa_t cr3;
+ gpa_t pgd;
hpa_t hpa;
};
#define KVM_MMU_ROOT_INFO_INVALID \
- ((struct kvm_mmu_root_info) { .cr3 = INVALID_PAGE, .hpa = INVALID_PAGE })
+ ((struct kvm_mmu_root_info) { .pgd = INVALID_PAGE, .hpa = INVALID_PAGE })
#define KVM_MMU_NUM_PREV_ROOTS 3
@@ -403,7 +406,7 @@ struct kvm_mmu {
void (*update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
u64 *spte, const void *pte);
hpa_t root_hpa;
- gpa_t root_cr3;
+ gpa_t root_pgd;
union kvm_mmu_role mmu_role;
u8 root_level;
u8 shadow_root_level;
@@ -578,6 +581,7 @@ struct kvm_vcpu_arch {
unsigned long cr4;
unsigned long cr4_guest_owned_bits;
unsigned long cr8;
+ u32 host_pkru;
u32 pkru;
u32 hflags;
u64 efer;
@@ -597,6 +601,7 @@ struct kvm_vcpu_arch {
u64 ia32_xss;
u64 microcode_version;
u64 arch_capabilities;
+ u64 perf_capabilities;
/*
* Paging state of the vcpu
@@ -649,7 +654,6 @@ struct kvm_vcpu_arch {
u64 xcr0;
u64 guest_supported_xcr0;
- u32 guest_xstate_size;
struct kvm_pio_request pio;
void *pio_data;
@@ -679,6 +683,7 @@ struct kvm_vcpu_arch {
struct kvm_cpuid_entry2 cpuid_entries[KVM_MAX_CPUID_ENTRIES];
int maxphyaddr;
+ int tdp_level;
/* emulate context */
@@ -702,6 +707,7 @@ struct kvm_vcpu_arch {
struct gfn_to_pfn_cache cache;
} st;
+ u64 l1_tsc_offset;
u64 tsc_offset;
u64 last_guest_tsc;
u64 last_host_tsc;
@@ -761,14 +767,17 @@ struct kvm_vcpu_arch {
struct {
bool halted;
- gfn_t gfns[roundup_pow_of_two(ASYNC_PF_PER_VCPU)];
+ gfn_t gfns[ASYNC_PF_PER_VCPU];
struct gfn_to_hva_cache data;
- u64 msr_val;
+ u64 msr_en_val; /* MSR_KVM_ASYNC_PF_EN */
+ u64 msr_int_val; /* MSR_KVM_ASYNC_PF_INT */
+ u16 vec;
u32 id;
bool send_user_only;
- u32 host_apf_reason;
+ u32 host_apf_flags;
unsigned long nested_apf_token;
bool delivery_as_pf_vmexit;
+ bool pageready_pending;
} apf;
/* OSVW MSRs (AMD only) */
@@ -854,6 +863,18 @@ struct kvm_apic_map {
struct kvm_lapic *phys_map[];
};
+/* Hyper-V synthetic debugger (SynDbg)*/
+struct kvm_hv_syndbg {
+ struct {
+ u64 control;
+ u64 status;
+ u64 send_page;
+ u64 recv_page;
+ u64 pending_page;
+ } control;
+ u64 options;
+};
+
/* Hyper-V emulation context */
struct kvm_hv {
struct mutex hv_lock;
@@ -865,7 +886,7 @@ struct kvm_hv {
u64 hv_crash_param[HV_X64_MSR_CRASH_PARAMS];
u64 hv_crash_ctl;
- HV_REFERENCE_TSC_PAGE tsc_ref;
+ struct ms_hyperv_tsc_page tsc_ref;
struct idr conn_to_evt;
@@ -877,6 +898,7 @@ struct kvm_hv {
atomic_t num_mismatched_vp_indexes;
struct hv_partition_assist_pg *hv_pa_pg;
+ struct kvm_hv_syndbg hv_syndbg;
};
enum kvm_irqchip_mode {
@@ -1027,6 +1049,8 @@ struct kvm_vcpu_stat {
u64 irq_injections;
u64 nmi_injections;
u64 req_event;
+ u64 halt_poll_success_ns;
+ u64 halt_poll_fail_ns;
};
struct x86_instruction_info;
@@ -1058,7 +1082,7 @@ struct kvm_x86_ops {
void (*hardware_disable)(void);
void (*hardware_unsetup)(void);
bool (*cpu_has_accelerated_tpr)(void);
- bool (*has_emulated_msr)(int index);
+ bool (*has_emulated_msr)(u32 index);
void (*cpuid_update)(struct kvm_vcpu *vcpu);
unsigned int vm_size;
@@ -1084,8 +1108,6 @@ struct kvm_x86_ops {
void (*set_segment)(struct kvm_vcpu *vcpu,
struct kvm_segment *var, int seg);
void (*get_cs_db_l_bits)(struct kvm_vcpu *vcpu, int *db, int *l);
- void (*decache_cr0_guest_bits)(struct kvm_vcpu *vcpu);
- void (*decache_cr4_guest_bits)(struct kvm_vcpu *vcpu);
void (*set_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0);
int (*set_cr4)(struct kvm_vcpu *vcpu, unsigned long cr4);
void (*set_efer)(struct kvm_vcpu *vcpu, u64 efer);
@@ -1093,15 +1115,14 @@ struct kvm_x86_ops {
void (*set_idt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
void (*get_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
void (*set_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
- u64 (*get_dr6)(struct kvm_vcpu *vcpu);
- void (*set_dr6)(struct kvm_vcpu *vcpu, unsigned long value);
void (*sync_dirty_debug_regs)(struct kvm_vcpu *vcpu);
void (*set_dr7)(struct kvm_vcpu *vcpu, unsigned long value);
void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg);
unsigned long (*get_rflags)(struct kvm_vcpu *vcpu);
void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags);
- void (*tlb_flush)(struct kvm_vcpu *vcpu, bool invalidate_gpa);
+ void (*tlb_flush_all)(struct kvm_vcpu *vcpu);
+ void (*tlb_flush_current)(struct kvm_vcpu *vcpu);
int (*tlb_remote_flush)(struct kvm *kvm);
int (*tlb_remote_flush_with_range)(struct kvm *kvm,
struct kvm_tlb_range *range);
@@ -1114,7 +1135,13 @@ struct kvm_x86_ops {
*/
void (*tlb_flush_gva)(struct kvm_vcpu *vcpu, gva_t addr);
- void (*run)(struct kvm_vcpu *vcpu);
+ /*
+ * Flush any TLB entries created by the guest. Like tlb_flush_gva(),
+ * does not need to flush GPA->HPA mappings.
+ */
+ void (*tlb_flush_guest)(struct kvm_vcpu *vcpu);
+
+ enum exit_fastpath_completion (*run)(struct kvm_vcpu *vcpu);
int (*handle_exit)(struct kvm_vcpu *vcpu,
enum exit_fastpath_completion exit_fastpath);
int (*skip_emulated_instruction)(struct kvm_vcpu *vcpu);
@@ -1127,8 +1154,8 @@ struct kvm_x86_ops {
void (*set_nmi)(struct kvm_vcpu *vcpu);
void (*queue_exception)(struct kvm_vcpu *vcpu);
void (*cancel_injection)(struct kvm_vcpu *vcpu);
- int (*interrupt_allowed)(struct kvm_vcpu *vcpu);
- int (*nmi_allowed)(struct kvm_vcpu *vcpu);
+ int (*interrupt_allowed)(struct kvm_vcpu *vcpu, bool for_injection);
+ int (*nmi_allowed)(struct kvm_vcpu *vcpu, bool for_injection);
bool (*get_nmi_mask)(struct kvm_vcpu *vcpu);
void (*set_nmi_mask)(struct kvm_vcpu *vcpu, bool masked);
void (*enable_nmi_window)(struct kvm_vcpu *vcpu);
@@ -1142,7 +1169,7 @@ struct kvm_x86_ops {
bool (*guest_apic_has_interrupt)(struct kvm_vcpu *vcpu);
void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu);
- void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa);
+ void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu);
int (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector);
int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu);
int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
@@ -1154,7 +1181,6 @@ struct kvm_x86_ops {
bool (*has_wbinvd_exit)(void);
- u64 (*read_l1_tsc_offset)(struct kvm_vcpu *vcpu);
/* Returns actual tsc_offset set in active VMCS */
u64 (*write_l1_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset);
@@ -1164,10 +1190,8 @@ struct kvm_x86_ops {
struct x86_instruction_info *info,
enum x86_intercept_stage stage,
struct x86_exception *exception);
- void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu,
- enum exit_fastpath_completion *exit_fastpath);
+ void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu);
- int (*check_nested_events)(struct kvm_vcpu *vcpu);
void (*request_immediate_exit)(struct kvm_vcpu *vcpu);
void (*sched_in)(struct kvm_vcpu *kvm, int cpu);
@@ -1200,6 +1224,7 @@ struct kvm_x86_ops {
/* pmu operations of sub-arch */
const struct kvm_pmu_ops *pmu_ops;
+ const struct kvm_x86_nested_ops *nested_ops;
/*
* Architecture specific hooks for vCPU blocking due to
@@ -1227,18 +1252,10 @@ struct kvm_x86_ops {
void (*setup_mce)(struct kvm_vcpu *vcpu);
- int (*get_nested_state)(struct kvm_vcpu *vcpu,
- struct kvm_nested_state __user *user_kvm_nested_state,
- unsigned user_data_size);
- int (*set_nested_state)(struct kvm_vcpu *vcpu,
- struct kvm_nested_state __user *user_kvm_nested_state,
- struct kvm_nested_state *kvm_state);
- bool (*get_vmcs12_pages)(struct kvm_vcpu *vcpu);
-
- int (*smi_allowed)(struct kvm_vcpu *vcpu);
+ int (*smi_allowed)(struct kvm_vcpu *vcpu, bool for_injection);
int (*pre_enter_smm)(struct kvm_vcpu *vcpu, char *smstate);
int (*pre_leave_smm)(struct kvm_vcpu *vcpu, const char *smstate);
- int (*enable_smi_window)(struct kvm_vcpu *vcpu);
+ void (*enable_smi_window)(struct kvm_vcpu *vcpu);
int (*mem_enc_op)(struct kvm *kvm, void __user *argp);
int (*mem_enc_reg_region)(struct kvm *kvm, struct kvm_enc_region *argp);
@@ -1246,14 +1263,28 @@ struct kvm_x86_ops {
int (*get_msr_feature)(struct kvm_msr_entry *entry);
- int (*nested_enable_evmcs)(struct kvm_vcpu *vcpu,
- uint16_t *vmcs_version);
- uint16_t (*nested_get_evmcs_version)(struct kvm_vcpu *vcpu);
-
bool (*need_emulation_on_page_fault)(struct kvm_vcpu *vcpu);
bool (*apic_init_signal_blocked)(struct kvm_vcpu *vcpu);
int (*enable_direct_tlbflush)(struct kvm_vcpu *vcpu);
+
+ void (*migrate_timers)(struct kvm_vcpu *vcpu);
+};
+
+struct kvm_x86_nested_ops {
+ int (*check_events)(struct kvm_vcpu *vcpu);
+ bool (*hv_timer_pending)(struct kvm_vcpu *vcpu);
+ int (*get_state)(struct kvm_vcpu *vcpu,
+ struct kvm_nested_state __user *user_kvm_nested_state,
+ unsigned user_data_size);
+ int (*set_state)(struct kvm_vcpu *vcpu,
+ struct kvm_nested_state __user *user_kvm_nested_state,
+ struct kvm_nested_state *kvm_state);
+ bool (*get_vmcs12_pages)(struct kvm_vcpu *vcpu);
+
+ int (*enable_evmcs)(struct kvm_vcpu *vcpu,
+ uint16_t *vmcs_version);
+ uint16_t (*get_evmcs_version)(struct kvm_vcpu *vcpu);
};
struct kvm_x86_init_ops {
@@ -1280,8 +1311,7 @@ extern struct kmem_cache *x86_fpu_cache;
#define __KVM_HAVE_ARCH_VM_ALLOC
static inline struct kvm *kvm_arch_alloc_vm(void)
{
- return __vmalloc(kvm_x86_ops.vm_size,
- GFP_KERNEL_ACCOUNT | __GFP_ZERO, PAGE_KERNEL);
+ return __vmalloc(kvm_x86_ops.vm_size, GFP_KERNEL_ACCOUNT | __GFP_ZERO);
}
void kvm_arch_free_vm(struct kvm *kvm);
@@ -1449,9 +1479,12 @@ bool kvm_rdpmc(struct kvm_vcpu *vcpu);
void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr);
void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
+void kvm_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr, unsigned long payload);
void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr);
void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault);
+bool kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu,
+ struct x86_exception *fault);
int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
gfn_t gfn, void *data, int offset, int len,
u32 access);
@@ -1479,6 +1512,8 @@ void kvm_pic_clear_all(struct kvm_pic *pic, int irq_source_id);
void kvm_inject_nmi(struct kvm_vcpu *vcpu);
+void kvm_update_dr7(struct kvm_vcpu *vcpu);
+
int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn);
int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva);
void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
@@ -1509,8 +1544,11 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code,
void *insn, int insn_len);
void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva);
+void kvm_mmu_invalidate_gva(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
+ gva_t gva, hpa_t root_hpa);
void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid);
-void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu, gpa_t new_cr3, bool skip_tlb_flush);
+void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd, bool skip_tlb_flush,
+ bool skip_mmu_sync);
void kvm_configure_mmu(bool enable_tdp, int tdp_page_level);
@@ -1574,8 +1612,6 @@ enum {
};
#define HF_GIF_MASK (1 << 0)
-#define HF_HIF_MASK (1 << 1)
-#define HF_VINTR_MASK (1 << 2)
#define HF_NMI_MASK (1 << 3)
#define HF_IRET_MASK (1 << 4)
#define HF_GUEST_MASK (1 << 5) /* VCPU is in guest-mode */
@@ -1641,7 +1677,8 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
struct kvm_async_pf *work);
void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu,
struct kvm_async_pf *work);
-bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu);
+void kvm_arch_async_page_present_queued(struct kvm_vcpu *vcpu);
+bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu);
extern bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn);
int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu);
@@ -1663,8 +1700,8 @@ void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e,
static inline bool kvm_irq_is_postable(struct kvm_lapic_irq *irq)
{
/* We can only post Fixed and LowPrio IRQs */
- return (irq->delivery_mode == dest_Fixed ||
- irq->delivery_mode == dest_LowestPrio);
+ return (irq->delivery_mode == APIC_DM_FIXED ||
+ irq->delivery_mode == APIC_DM_LOWEST);
}
static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 9b4df6eaa11a..49d3a9edb06f 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -88,11 +88,21 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1,
bool kvm_para_available(void);
unsigned int kvm_arch_para_features(void);
unsigned int kvm_arch_para_hints(void);
-void kvm_async_pf_task_wait(u32 token, int interrupt_kernel);
+void kvm_async_pf_task_wait_schedule(u32 token);
void kvm_async_pf_task_wake(u32 token);
-u32 kvm_read_and_reset_pf_reason(void);
-extern void kvm_disable_steal_time(void);
-void do_async_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address);
+u32 kvm_read_and_reset_apf_flags(void);
+void kvm_disable_steal_time(void);
+bool __kvm_handle_async_pf(struct pt_regs *regs, u32 token);
+
+DECLARE_STATIC_KEY_FALSE(kvm_async_pf_enabled);
+
+static __always_inline bool kvm_handle_async_pf(struct pt_regs *regs, u32 token)
+{
+ if (static_branch_unlikely(&kvm_async_pf_enabled))
+ return __kvm_handle_async_pf(regs, token);
+ else
+ return false;
+}
#ifdef CONFIG_PARAVIRT_SPINLOCKS
void __init kvm_spinlock_init(void);
@@ -103,7 +113,7 @@ static inline void kvm_spinlock_init(void)
#endif /* CONFIG_PARAVIRT_SPINLOCKS */
#else /* CONFIG_KVM_GUEST */
-#define kvm_async_pf_task_wait(T, I) do {} while(0)
+#define kvm_async_pf_task_wait_schedule(T) do {} while(0)
#define kvm_async_pf_task_wake(T) do {} while(0)
static inline bool kvm_para_available(void)
@@ -121,7 +131,7 @@ static inline unsigned int kvm_arch_para_hints(void)
return 0;
}
-static inline u32 kvm_read_and_reset_pf_reason(void)
+static inline u32 kvm_read_and_reset_apf_flags(void)
{
return 0;
}
@@ -130,6 +140,11 @@ static inline void kvm_disable_steal_time(void)
{
return;
}
+
+static __always_inline bool kvm_handle_async_pf(struct pt_regs *regs, u32 token)
+{
+ return false;
+}
#endif
#endif /* _ASM_X86_KVM_PARA_H */
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index c598aaab071b..cf503824529c 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -251,7 +251,7 @@ extern void mce_disable_bank(int bank);
/*
* Exception handler
*/
-void do_machine_check(struct pt_regs *, long);
+void do_machine_check(struct pt_regs *pt_regs);
/*
* Threshold handler
diff --git a/arch/x86/include/asm/memtype.h b/arch/x86/include/asm/memtype.h
index 9c2447b3555d..9ca760e430b9 100644
--- a/arch/x86/include/asm/memtype.h
+++ b/arch/x86/include/asm/memtype.h
@@ -24,4 +24,7 @@ extern void memtype_free_io(resource_size_t start, resource_size_t end);
extern bool pat_pfn_immune_to_uc_mtrr(unsigned long pfn);
+bool x86_has_pat_wp(void);
+enum page_cache_mode pgprot2cachemode(pgprot_t pgprot);
+
#endif /* _ASM_X86_MEMTYPE_H */
diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h
index 6685e1218959..7063b5a43220 100644
--- a/arch/x86/include/asm/microcode_amd.h
+++ b/arch/x86/include/asm/microcode_amd.h
@@ -41,7 +41,7 @@ struct microcode_amd {
unsigned int mpb[0];
};
-#define PATCH_MAX_SIZE PAGE_SIZE
+#define PATCH_MAX_SIZE (3 * PAGE_SIZE)
#ifdef CONFIG_MICROCODE_AMD
extern void __init load_ucode_amd_bsp(unsigned int family);
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index bdeae9291e5c..0a301ad0b02f 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -45,7 +45,7 @@ typedef struct {
#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
/*
* One bit per protection key says whether userspace can
- * use it or not. protected by mmap_sem.
+ * use it or not. protected by mmap_lock.
*/
u16 pkey_allocation_map;
s16 execute_only_pkey;
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 4e55370e48e8..47562147e70b 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -24,21 +24,9 @@ static inline void paravirt_activate_mm(struct mm_struct *prev,
#endif /* !CONFIG_PARAVIRT_XXL */
#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) ||
- (!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);
-}
-#else
-static inline void load_mm_cr4_irqsoff(struct mm_struct *mm) {}
+void cr4_update_pce(void *ignored);
#endif
#ifdef CONFIG_MODIFY_LDT_SYSCALL
@@ -225,78 +213,6 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
return __pkru_allows_pkey(vma_pkey(vma), write);
}
-/*
- * This can be used from process context to figure out what the value of
- * CR3 is without needing to do a (slow) __read_cr3().
- *
- * It's intended to be used for code like KVM that sneakily changes CR3
- * and needs to restore it. It needs to be used very carefully.
- */
-static inline unsigned long __get_current_cr3_fast(void)
-{
- unsigned long cr3 = build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm)->pgd,
- this_cpu_read(cpu_tlbstate.loaded_mm_asid));
-
- /* For now, be very restrictive about when this can be called. */
- VM_WARN_ON(in_nmi() || preemptible());
-
- VM_BUG_ON(cr3 != __read_cr3());
- return cr3;
-}
-
-typedef struct {
- struct mm_struct *mm;
-} temp_mm_state_t;
-
-/*
- * Using a temporary mm allows to set temporary mappings that are not accessible
- * by other CPUs. Such mappings are needed to perform sensitive memory writes
- * that override the kernel memory protections (e.g., W^X), without exposing the
- * temporary page-table mappings that are required for these write operations to
- * other CPUs. Using a temporary mm also allows to avoid TLB shootdowns when the
- * mapping is torn down.
- *
- * Context: The temporary mm needs to be used exclusively by a single core. To
- * harden security IRQs must be disabled while the temporary mm is
- * loaded, thereby preventing interrupt handler bugs from overriding
- * the kernel memory protection.
- */
-static inline temp_mm_state_t use_temporary_mm(struct mm_struct *mm)
-{
- temp_mm_state_t temp_state;
-
- lockdep_assert_irqs_disabled();
- temp_state.mm = this_cpu_read(cpu_tlbstate.loaded_mm);
- switch_mm_irqs_off(NULL, mm, current);
-
- /*
- * If breakpoints are enabled, disable them while the temporary mm is
- * used. Userspace might set up watchpoints on addresses that are used
- * in the temporary mm, which would lead to wrong signals being sent or
- * crashes.
- *
- * Note that breakpoints are not disabled selectively, which also causes
- * kernel breakpoints (e.g., perf's) to be disabled. This might be
- * undesirable, but still seems reasonable as the code that runs in the
- * temporary mm should be short.
- */
- if (hw_breakpoint_active())
- hw_breakpoint_disable();
-
- return temp_state;
-}
-
-static inline void unuse_temporary_mm(temp_mm_state_t prev_state)
-{
- lockdep_assert_irqs_disabled();
- switch_mm_irqs_off(NULL, prev_state.mm, current);
-
- /*
- * Restore the breakpoints if they were disabled before the temporary mm
- * was loaded.
- */
- if (hw_breakpoint_active())
- hw_breakpoint_restore();
-}
+unsigned long __get_current_cr3_fast(void);
#endif /* _ASM_X86_MMU_CONTEXT_H */
diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h
index 73d8dd14dda2..2d4515e8b7df 100644
--- a/arch/x86/include/asm/mmzone_32.h
+++ b/arch/x86/include/asm/mmzone_32.h
@@ -14,43 +14,4 @@ extern struct pglist_data *node_data[];
#define NODE_DATA(nid) (node_data[nid])
#endif /* CONFIG_NUMA */
-#ifdef CONFIG_DISCONTIGMEM
-
-/*
- * generic node memory support, the following assumptions apply:
- *
- * 1) memory comes in 64Mb contiguous chunks which are either present or not
- * 2) we will not have more than 64Gb in total
- *
- * for now assume that 64Gb is max amount of RAM for whole system
- * 64Gb / 4096bytes/page = 16777216 pages
- */
-#define MAX_NR_PAGES 16777216
-#define MAX_SECTIONS 1024
-#define PAGES_PER_SECTION (MAX_NR_PAGES/MAX_SECTIONS)
-
-extern s8 physnode_map[];
-
-static inline int pfn_to_nid(unsigned long pfn)
-{
-#ifdef CONFIG_NUMA
- return((int) physnode_map[(pfn) / PAGES_PER_SECTION]);
-#else
- return 0;
-#endif
-}
-
-static inline int pfn_valid(int pfn)
-{
- int nid = pfn_to_nid(pfn);
-
- if (nid >= 0)
- return (pfn < node_end_pfn(nid));
- return 0;
-}
-
-#define early_pfn_valid(pfn) pfn_valid((pfn))
-
-#endif /* CONFIG_DISCONTIGMEM */
-
#endif /* _ASM_X86_MMZONE_32_H */
diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h
index c215d2762488..e988bac0a4a1 100644
--- a/arch/x86/include/asm/module.h
+++ b/arch/x86/include/asm/module.h
@@ -13,64 +13,4 @@ struct mod_arch_specific {
#endif
};
-#ifdef CONFIG_X86_64
-/* X86_64 does not define MODULE_PROC_FAMILY */
-#elif defined CONFIG_M486SX
-#define MODULE_PROC_FAMILY "486SX "
-#elif defined CONFIG_M486
-#define MODULE_PROC_FAMILY "486 "
-#elif defined CONFIG_M586
-#define MODULE_PROC_FAMILY "586 "
-#elif defined CONFIG_M586TSC
-#define MODULE_PROC_FAMILY "586TSC "
-#elif defined CONFIG_M586MMX
-#define MODULE_PROC_FAMILY "586MMX "
-#elif defined CONFIG_MCORE2
-#define MODULE_PROC_FAMILY "CORE2 "
-#elif defined CONFIG_MATOM
-#define MODULE_PROC_FAMILY "ATOM "
-#elif defined CONFIG_M686
-#define MODULE_PROC_FAMILY "686 "
-#elif defined CONFIG_MPENTIUMII
-#define MODULE_PROC_FAMILY "PENTIUMII "
-#elif defined CONFIG_MPENTIUMIII
-#define MODULE_PROC_FAMILY "PENTIUMIII "
-#elif defined CONFIG_MPENTIUMM
-#define MODULE_PROC_FAMILY "PENTIUMM "
-#elif defined CONFIG_MPENTIUM4
-#define MODULE_PROC_FAMILY "PENTIUM4 "
-#elif defined CONFIG_MK6
-#define MODULE_PROC_FAMILY "K6 "
-#elif defined CONFIG_MK7
-#define MODULE_PROC_FAMILY "K7 "
-#elif defined CONFIG_MK8
-#define MODULE_PROC_FAMILY "K8 "
-#elif defined CONFIG_MELAN
-#define MODULE_PROC_FAMILY "ELAN "
-#elif defined CONFIG_MCRUSOE
-#define MODULE_PROC_FAMILY "CRUSOE "
-#elif defined CONFIG_MEFFICEON
-#define MODULE_PROC_FAMILY "EFFICEON "
-#elif defined CONFIG_MWINCHIPC6
-#define MODULE_PROC_FAMILY "WINCHIPC6 "
-#elif defined CONFIG_MWINCHIP3D
-#define MODULE_PROC_FAMILY "WINCHIP3D "
-#elif defined CONFIG_MCYRIXIII
-#define MODULE_PROC_FAMILY "CYRIXIII "
-#elif defined CONFIG_MVIAC3_2
-#define MODULE_PROC_FAMILY "VIAC3-2 "
-#elif defined CONFIG_MVIAC7
-#define MODULE_PROC_FAMILY "VIAC7 "
-#elif defined CONFIG_MGEODEGX1
-#define MODULE_PROC_FAMILY "GEODEGX1 "
-#elif defined CONFIG_MGEODE_LX
-#define MODULE_PROC_FAMILY "GEODE "
-#else
-#error unknown processor family
-#endif
-
-#ifdef CONFIG_X86_32
-# define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY
-#endif
-
#endif /* _ASM_X86_MODULE_H */
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 1c42ecbe75cb..60b944dd2df1 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -35,6 +35,8 @@ typedef int (*hyperv_fill_flush_list_func)(
rdmsrl(HV_X64_MSR_SINT0 + int_num, val)
#define hv_set_synint_state(int_num, val) \
wrmsrl(HV_X64_MSR_SINT0 + int_num, val)
+#define hv_recommend_using_aeoi() \
+ (!(ms_hyperv.hints & HV_DEPRECATING_AEOI_RECOMMENDED))
#define hv_get_crash_ctl(val) \
rdmsrl(HV_X64_MSR_CRASH_CTL, val)
@@ -52,20 +54,8 @@ typedef int (*hyperv_fill_flush_list_func)(
vclocks_set_used(VDSO_CLOCKMODE_HVCLOCK);
#define hv_get_raw_timer() rdtsc_ordered()
-void hyperv_callback_vector(void);
-void hyperv_reenlightenment_vector(void);
-#ifdef CONFIG_TRACING
-#define trace_hyperv_callback_vector hyperv_callback_vector
-#endif
void hyperv_vector_handler(struct pt_regs *regs);
-/*
- * Routines for stimer0 Direct Mode handling.
- * On x86/x64, there are no percpu actions to take.
- */
-void hv_stimer0_vector_handler(struct pt_regs *regs);
-void hv_stimer0_callback_vector(void);
-
static inline void hv_enable_stimer0_percpu_irq(int irq) {}
static inline void hv_disable_stimer0_percpu_irq(int irq) {}
@@ -224,7 +214,6 @@ 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));
void clear_hv_tscchange_cb(void);
void hyperv_stop_tsc_emulation(void);
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 12c9684d59ba..e8370e64a155 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -128,6 +128,10 @@
#define TSX_CTRL_RTM_DISABLE BIT(0) /* Disable RTM feature */
#define TSX_CTRL_CPUID_CLEAR BIT(1) /* Disable TSX enumeration */
+/* SRBDS support */
+#define MSR_IA32_MCU_OPT_CTRL 0x00000123
+#define RNGDS_MITG_DIS BIT(0)
+
#define MSR_IA32_SYSENTER_CS 0x00000174
#define MSR_IA32_SYSENTER_ESP 0x00000175
#define MSR_IA32_SYSENTER_EIP 0x00000176
@@ -301,6 +305,9 @@
#define MSR_PP1_ENERGY_STATUS 0x00000641
#define MSR_PP1_POLICY 0x00000642
+#define MSR_AMD_PKG_ENERGY_STATUS 0xc001029b
+#define MSR_AMD_RAPL_POWER_UNIT 0xc0010299
+
/* Config TDP MSRs */
#define MSR_CONFIG_TDP_NOMINAL 0x00000648
#define MSR_CONFIG_TDP_LEVEL_1 0x00000649
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index b809f117f3f4..73d997aa2966 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -20,8 +20,10 @@
#define MWAIT_ECX_INTERRUPT_BREAK 0x1
#define MWAITX_ECX_TIMER_ENABLE BIT(1)
-#define MWAITX_MAX_LOOPS ((u32)-1)
+#define MWAITX_MAX_WAIT_CYCLES UINT_MAX
#define MWAITX_DISABLE_CSTATES 0xf0
+#define TPAUSE_C01_STATE 1
+#define TPAUSE_C02_STATE 0
u32 get_umwait_control_msr(void);
@@ -122,4 +124,24 @@ static inline void mwait_idle_with_hints(unsigned long eax, unsigned long ecx)
current_clr_polling();
}
+/*
+ * Caller can specify whether to enter C0.1 (low latency, less
+ * power saving) or C0.2 state (saves more power, but longer wakeup
+ * latency). This may be overridden by the IA32_UMWAIT_CONTROL MSR
+ * which can force requests for C0.2 to be downgraded to C0.1.
+ */
+static inline void __tpause(u32 ecx, u32 edx, u32 eax)
+{
+ /* "tpause %ecx, %edx, %eax;" */
+ #ifdef CONFIG_AS_TPAUSE
+ asm volatile("tpause %%ecx\n"
+ :
+ : "c"(ecx), "d"(edx), "a"(eax));
+ #else
+ asm volatile(".byte 0x66, 0x0f, 0xae, 0xf1\t\n"
+ :
+ : "c"(ecx), "d"(edx), "a"(eax));
+ #endif
+}
+
#endif /* _ASM_X86_MWAIT_H */
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 07e95dcb40ad..e7752b4038ff 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -4,20 +4,13 @@
#define _ASM_X86_NOSPEC_BRANCH_H_
#include <linux/static_key.h>
+#include <linux/frame.h>
#include <asm/alternative.h>
#include <asm/alternative-asm.h>
#include <asm/cpufeatures.h>
#include <asm/msr-index.h>
-
-/*
- * This should be used immediately before a retpoline alternative. It tells
- * objtool where the retpolines are so that it can make sense of the control
- * flow by just reading the original instruction(s) and ignoring the
- * alternatives.
- */
-#define ANNOTATE_NOSPEC_ALTERNATIVE \
- ANNOTATE_IGNORE_ALTERNATIVE
+#include <asm/unwind_hints.h>
/*
* Fill the CPU return stack buffer.
@@ -46,21 +39,25 @@
#define __FILL_RETURN_BUFFER(reg, nr, sp) \
mov $(nr/2), reg; \
771: \
+ ANNOTATE_INTRA_FUNCTION_CALL; \
call 772f; \
773: /* speculation trap */ \
+ UNWIND_HINT_EMPTY; \
pause; \
lfence; \
jmp 773b; \
772: \
+ ANNOTATE_INTRA_FUNCTION_CALL; \
call 774f; \
775: /* speculation trap */ \
+ UNWIND_HINT_EMPTY; \
pause; \
lfence; \
jmp 775b; \
774: \
+ add $(BITS_PER_LONG/8) * 2, sp; \
dec reg; \
- jnz 771b; \
- add $(BITS_PER_LONG/8) * nr, sp;
+ jnz 771b;
#ifdef __ASSEMBLY__
@@ -77,57 +74,27 @@
.endm
/*
- * These are the bare retpoline primitives for indirect jmp and call.
- * Do not use these directly; they only exist to make the ALTERNATIVE
- * invocation below less ugly.
- */
-.macro RETPOLINE_JMP reg:req
- call .Ldo_rop_\@
-.Lspec_trap_\@:
- pause
- lfence
- jmp .Lspec_trap_\@
-.Ldo_rop_\@:
- mov \reg, (%_ASM_SP)
- ret
-.endm
-
-/*
- * This is a wrapper around RETPOLINE_JMP so the called function in reg
- * returns to the instruction after the macro.
- */
-.macro RETPOLINE_CALL reg:req
- jmp .Ldo_call_\@
-.Ldo_retpoline_jmp_\@:
- RETPOLINE_JMP \reg
-.Ldo_call_\@:
- call .Ldo_retpoline_jmp_\@
-.endm
-
-/*
* JMP_NOSPEC and CALL_NOSPEC macros can be used instead of a simple
* indirect jmp/call which may be susceptible to the Spectre variant 2
* attack.
*/
.macro JMP_NOSPEC reg:req
#ifdef CONFIG_RETPOLINE
- ANNOTATE_NOSPEC_ALTERNATIVE
- ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *\reg), \
- __stringify(RETPOLINE_JMP \reg), X86_FEATURE_RETPOLINE, \
- __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *\reg), X86_FEATURE_RETPOLINE_AMD
+ ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \
+ __stringify(jmp __x86_retpoline_\reg), X86_FEATURE_RETPOLINE, \
+ __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), X86_FEATURE_RETPOLINE_AMD
#else
- jmp *\reg
+ jmp *%\reg
#endif
.endm
.macro CALL_NOSPEC reg:req
#ifdef CONFIG_RETPOLINE
- ANNOTATE_NOSPEC_ALTERNATIVE
- ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; call *\reg), \
- __stringify(RETPOLINE_CALL \reg), X86_FEATURE_RETPOLINE,\
- __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; call *\reg), X86_FEATURE_RETPOLINE_AMD
+ ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; call *%\reg), \
+ __stringify(call __x86_retpoline_\reg), X86_FEATURE_RETPOLINE, \
+ __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; call *%\reg), X86_FEATURE_RETPOLINE_AMD
#else
- call *\reg
+ call *%\reg
#endif
.endm
@@ -137,10 +104,8 @@
*/
.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req
#ifdef CONFIG_RETPOLINE
- ANNOTATE_NOSPEC_ALTERNATIVE
- ALTERNATIVE "jmp .Lskip_rsb_\@", \
- __stringify(__FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP)) \
- \ftr
+ ALTERNATIVE "jmp .Lskip_rsb_\@", "", \ftr
+ __FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP)
.Lskip_rsb_\@:
#endif
.endm
@@ -161,16 +126,16 @@
* which is ensured when CONFIG_RETPOLINE is defined.
*/
# define CALL_NOSPEC \
- ANNOTATE_NOSPEC_ALTERNATIVE \
ALTERNATIVE_2( \
ANNOTATE_RETPOLINE_SAFE \
"call *%[thunk_target]\n", \
- "call __x86_indirect_thunk_%V[thunk_target]\n", \
+ "call __x86_retpoline_%V[thunk_target]\n", \
X86_FEATURE_RETPOLINE, \
"lfence;\n" \
ANNOTATE_RETPOLINE_SAFE \
"call *%[thunk_target]\n", \
X86_FEATURE_RETPOLINE_AMD)
+
# define THUNK_TARGET(addr) [thunk_target] "r" (addr)
#else /* CONFIG_X86_32 */
@@ -180,7 +145,6 @@
* here, anyway.
*/
# define CALL_NOSPEC \
- ANNOTATE_NOSPEC_ALTERNATIVE \
ALTERNATIVE_2( \
ANNOTATE_RETPOLINE_SAFE \
"call *%[thunk_target]\n", \
@@ -237,27 +201,6 @@ enum ssb_mitigation {
extern char __indirect_thunk_start[];
extern char __indirect_thunk_end[];
-/*
- * On VMEXIT we must ensure that no RSB predictions learned in the guest
- * can be followed in the host, by overwriting the RSB completely. Both
- * retpoline and IBRS mitigations for Spectre v2 need this; only on future
- * CPUs with IBRS_ALL *might* it be avoided.
- */
-static inline void vmexit_fill_RSB(void)
-{
-#ifdef CONFIG_RETPOLINE
- unsigned long loops;
-
- asm volatile (ANNOTATE_NOSPEC_ALTERNATIVE
- ALTERNATIVE("jmp 910f",
- __stringify(__FILL_RETURN_BUFFER(%0, RSB_CLEAR_LOOPS, %1)),
- X86_FEATURE_RETPOLINE)
- "910:"
- : "=r" (loops), ASM_CALL_CONSTRAINT
- : : "memory" );
-#endif
-}
-
static __always_inline
void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature)
{
@@ -319,7 +262,7 @@ DECLARE_STATIC_KEY_FALSE(mds_idle_clear);
* combination with microcode which triggers a CPU buffer flush when the
* instruction is executed.
*/
-static inline void mds_clear_cpu_buffers(void)
+static __always_inline void mds_clear_cpu_buffers(void)
{
static const u16 ds = __KERNEL_DS;
@@ -340,7 +283,7 @@ static inline void mds_clear_cpu_buffers(void)
*
* Clear CPU buffers if the corresponding static key is enabled
*/
-static inline void mds_user_clear_cpu_buffers(void)
+static __always_inline void mds_user_clear_cpu_buffers(void)
{
if (static_branch_likely(&mds_user_clear))
mds_clear_cpu_buffers();
diff --git a/arch/x86/include/asm/orc_types.h b/arch/x86/include/asm/orc_types.h
index 6e060907c163..d25534940bde 100644
--- a/arch/x86/include/asm/orc_types.h
+++ b/arch/x86/include/asm/orc_types.h
@@ -58,8 +58,7 @@
#define ORC_TYPE_CALL 0
#define ORC_TYPE_REGS 1
#define ORC_TYPE_REGS_IRET 2
-#define UNWIND_HINT_TYPE_SAVE 3
-#define UNWIND_HINT_TYPE_RESTORE 4
+#define UNWIND_HINT_TYPE_RET_OFFSET 3
#ifndef __ASSEMBLY__
/*
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 694d8daf4983..5ca5d297df75 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -47,7 +47,13 @@ static inline void slow_down_io(void)
#endif
}
-static inline void __flush_tlb(void)
+void native_flush_tlb_local(void);
+void native_flush_tlb_global(void);
+void native_flush_tlb_one_user(unsigned long addr);
+void native_flush_tlb_others(const struct cpumask *cpumask,
+ const struct flush_tlb_info *info);
+
+static inline void __flush_tlb_local(void)
{
PVOP_VCALL0(mmu.flush_tlb_user);
}
@@ -62,8 +68,8 @@ static inline void __flush_tlb_one_user(unsigned long addr)
PVOP_VCALL1(mmu.flush_tlb_one_user, addr);
}
-static inline void flush_tlb_others(const struct cpumask *cpumask,
- const struct flush_tlb_info *info)
+static inline void __flush_tlb_others(const struct cpumask *cpumask,
+ const struct flush_tlb_info *info)
{
PVOP_VCALL2(mmu.flush_tlb_others, cpumask, info);
}
diff --git a/arch/x86/include/asm/pgtable-2level_types.h b/arch/x86/include/asm/pgtable-2level_types.h
index 6deb6cd236e3..7f6ccff0ba72 100644
--- a/arch/x86/include/asm/pgtable-2level_types.h
+++ b/arch/x86/include/asm/pgtable-2level_types.h
@@ -20,6 +20,8 @@ typedef union {
#define SHARED_KERNEL_PMD 0
+#define ARCH_PAGE_TABLE_SYNC_MASK PGTBL_PMD_MODIFIED
+
/*
* traditional i386 two-level paging structure:
*/
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index 5afb5e0fe903..e896ebef8c24 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -39,23 +39,23 @@ static inline void native_set_pte(pte_t *ptep, pte_t pte)
* pte_offset_map_lock() on 32-bit PAE kernels was reading the pmd_t with
* a "*pmdp" dereference done by GCC. Problem is, in certain places
* where pte_offset_map_lock() is called, concurrent page faults are
- * allowed, if the mmap_sem is hold for reading. An example is mincore
+ * allowed, if the mmap_lock is hold for reading. An example is mincore
* vs page faults vs MADV_DONTNEED. On the page fault side
* pmd_populate() rightfully does a set_64bit(), but if we're reading the
* pmd_t with a "*pmdp" on the mincore side, a SMP race can happen
* because GCC will not read the 64-bit value of the pmd atomically.
*
* To fix this all places running pte_offset_map_lock() while holding the
- * mmap_sem in read mode, shall read the pmdp pointer using this
+ * mmap_lock in read mode, shall read the pmdp pointer using this
* function to know if the pmd is null or not, and in turn to know if
* they can run pte_offset_map_lock() or pmd_trans_huge() or other pmd
* operations.
*
- * Without THP if the mmap_sem is held for reading, the pmd can only
+ * Without THP if the mmap_lock is held for reading, the pmd can only
* transition from null to not null while pmd_read_atomic() runs. So
* we can always return atomic pmd values with this function.
*
- * With THP if the mmap_sem is held for reading, the pmd can become
+ * With THP if the mmap_lock is held for reading, the pmd can become
* trans_huge or none or point to a pte (and in turn become "stable")
* at any time under pmd_read_atomic(). We could read it truly
* atomically here with an atomic64_read() for the THP enabled case (and
diff --git a/arch/x86/include/asm/pgtable-3level_types.h b/arch/x86/include/asm/pgtable-3level_types.h
index 33845d36897c..80fbb4a9ed87 100644
--- a/arch/x86/include/asm/pgtable-3level_types.h
+++ b/arch/x86/include/asm/pgtable-3level_types.h
@@ -27,6 +27,8 @@ typedef union {
#define SHARED_KERNEL_PMD (!static_cpu_has(X86_FEATURE_PTI))
#endif
+#define ARCH_PAGE_TABLE_SYNC_MASK (SHARED_KERNEL_PMD ? 0 : PGTBL_PMD_MODIFIED)
+
/*
* PGDIR_SHIFT determines what a top-level page table entry can map
*/
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 4d02e64af1b3..76aa21e8128d 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -257,6 +257,7 @@ static inline int pmd_large(pmd_t pte)
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+/* NOTE: when predicate huge page, consider also pmd_devmap, or use pmd_large */
static inline int pmd_trans_huge(pmd_t pmd)
{
return (pmd_val(pmd) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE;
@@ -624,7 +625,7 @@ static inline pud_t pfn_pud(unsigned long page_nr, pgprot_t pgprot)
return __pud(pfn | check_pgprot(pgprot));
}
-static inline pmd_t pmd_mknotpresent(pmd_t pmd)
+static inline pmd_t pmd_mkinvalid(pmd_t pmd)
{
return pfn_pmd(pmd_pfn(pmd),
__pgprot(pmd_flags(pmd) & ~(_PAGE_PRESENT|_PAGE_PROTNONE)));
@@ -801,7 +802,7 @@ static inline int pmd_present(pmd_t pmd)
#ifdef CONFIG_NUMA_BALANCING
/*
* These work without NUMA balancing but the kernel does not care. See the
- * comment in include/asm-generic/pgtable.h
+ * comment in include/linux/pgtable.h
*/
static inline int pte_protnone(pte_t pte)
{
@@ -836,17 +837,6 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
#define pmd_page(pmd) pfn_to_page(pmd_pfn(pmd))
/*
- * the pmd page can be thought of an array like this: pmd_t[PTRS_PER_PMD]
- *
- * this macro returns the index of the entry in the pmd page which would
- * control the given virtual address
- */
-static inline unsigned long pmd_index(unsigned long address)
-{
- return (address >> PMD_SHIFT) & (PTRS_PER_PMD - 1);
-}
-
-/*
* Conversion functions: convert a page and protection to a page entry,
* and a page entry and page directory to the page they refer to.
*
@@ -855,25 +845,6 @@ static inline unsigned long pmd_index(unsigned long address)
*/
#define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot))
-/*
- * the pte page can be thought of an array like this: pte_t[PTRS_PER_PTE]
- *
- * this function returns the index of the entry in the pte page which would
- * control the given virtual address
- *
- * Also define macro so we can test if pte_index is defined for arch.
- */
-#define pte_index pte_index
-static inline unsigned long pte_index(unsigned long address)
-{
- return (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1);
-}
-
-static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long address)
-{
- return (pte_t *)pmd_page_vaddr(*pmd) + pte_index(address);
-}
-
static inline int pmd_bad(pmd_t pmd)
{
return (pmd_flags(pmd) & ~_PAGE_USER) != _KERNPG_TABLE;
@@ -906,12 +877,6 @@ static inline unsigned long pud_page_vaddr(pud_t pud)
*/
#define pud_page(pud) pfn_to_page(pud_pfn(pud))
-/* Find an entry in the second-level page table.. */
-static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
-{
- return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(address);
-}
-
#define pud_leaf pud_large
static inline int pud_large(pud_t pud)
{
@@ -931,11 +896,6 @@ static inline int pud_large(pud_t pud)
}
#endif /* CONFIG_PGTABLE_LEVELS > 2 */
-static inline unsigned long pud_index(unsigned long address)
-{
- return (address >> PUD_SHIFT) & (PTRS_PER_PUD - 1);
-}
-
#if CONFIG_PGTABLE_LEVELS > 3
static inline int p4d_none(p4d_t p4d)
{
@@ -958,12 +918,6 @@ static inline unsigned long p4d_page_vaddr(p4d_t p4d)
*/
#define p4d_page(p4d) pfn_to_page(p4d_pfn(p4d))
-/* Find an entry in the third-level page table.. */
-static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
-{
- return (pud_t *)p4d_page_vaddr(*p4d) + pud_index(address);
-}
-
static inline int p4d_bad(p4d_t p4d)
{
unsigned long ignore_flags = _KERNPG_TABLE | _PAGE_USER;
@@ -1036,30 +990,6 @@ static inline int pgd_none(pgd_t pgd)
#endif /* __ASSEMBLY__ */
-/*
- * the pgd page can be thought of an array like this: pgd_t[PTRS_PER_PGD]
- *
- * this macro returns the index of the entry in the pgd page which would
- * control the given virtual address
- */
-#define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1))
-
-/*
- * pgd_offset() returns a (pgd_t *)
- * pgd_index() is used get the offset into the pgd page's array of pgd_t's;
- */
-#define pgd_offset_pgd(pgd, address) (pgd + pgd_index((address)))
-/*
- * a shortcut to get a pgd_t in a given mm
- */
-#define pgd_offset(mm, address) pgd_offset_pgd((mm)->pgd, (address))
-/*
- * a shortcut which implies the use of the kernel's pgd, instead
- * of a process's
- */
-#define pgd_offset_k(address) pgd_offset(&init_mm, (address))
-
-
#define KERNEL_PGD_BOUNDARY pgd_index(PAGE_OFFSET)
#define KERNEL_PGD_PTRS (PTRS_PER_PGD - KERNEL_PGD_BOUNDARY)
@@ -1070,27 +1000,14 @@ void init_mem_mapping(void);
void early_alloc_pgt_buf(void);
extern void memblock_find_dma_reserve(void);
+
#ifdef CONFIG_X86_64
-/* Realmode trampoline initialization. */
extern pgd_t trampoline_pgd_entry;
-static inline void __meminit init_trampoline_default(void)
-{
- /* Default trampoline pgd value */
- trampoline_pgd_entry = init_top_pgt[pgd_index(__PAGE_OFFSET)];
-}
void __init poking_init(void);
unsigned long init_memory_mapping(unsigned long start,
unsigned long end, pgprot_t prot);
-
-# ifdef CONFIG_RANDOMIZE_MEMORY
-void __meminit init_trampoline(void);
-# else
-# define init_trampoline init_trampoline_default
-# endif
-#else
-static inline void init_trampoline(void) { }
#endif
/* local pte updates need not use xchg for locking */
@@ -1545,7 +1462,6 @@ static inline bool arch_faults_on_old_pte(void)
return false;
}
-#include <asm-generic/pgtable.h>
#endif /* __ASSEMBLY__ */
#endif /* _ASM_X86_PGTABLE_H */
diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h
index 0dca7f7aeff2..d7acae4120d5 100644
--- a/arch/x86/include/asm/pgtable_32.h
+++ b/arch/x86/include/asm/pgtable_32.h
@@ -32,42 +32,23 @@ extern pmd_t initial_pg_pmd[];
void paging_init(void);
void sync_initial_page_table(void);
-/*
- * Define this if things work differently on an i386 and an i486:
- * it will (on an i486) warn about kernel memory accesses that are
- * done without a 'access_ok( ..)'
- */
-#undef TEST_ACCESS_OK
-
#ifdef CONFIG_X86_PAE
# include <asm/pgtable-3level.h>
#else
# include <asm/pgtable-2level.h>
#endif
-#if defined(CONFIG_HIGHPTE)
-#define pte_offset_map(dir, address) \
- ((pte_t *)kmap_atomic(pmd_page(*(dir))) + \
- pte_index((address)))
-#define pte_unmap(pte) kunmap_atomic((pte))
-#else
-#define pte_offset_map(dir, address) \
- ((pte_t *)page_address(pmd_page(*(dir))) + pte_index((address)))
-#define pte_unmap(pte) do { } while (0)
-#endif
-
/* Clear a kernel PTE and flush it from the TLB */
#define kpte_clear_flush(ptep, vaddr) \
do { \
pte_clear(&init_mm, (vaddr), (ptep)); \
- __flush_tlb_one_kernel((vaddr)); \
+ flush_tlb_one_kernel((vaddr)); \
} while (0)
#endif /* !__ASSEMBLY__ */
/*
- * kern_addr_valid() is (1) for FLATMEM and (0) for
- * SPARSEMEM and DISCONTIGMEM
+ * kern_addr_valid() is (1) for FLATMEM and (0) for SPARSEMEM
*/
#ifdef CONFIG_FLATMEM
#define kern_addr_valid(addr) (1)
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index df1373415f11..1b68d24dc6a0 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -53,6 +53,12 @@ static inline void sync_initial_page_table(void) { }
struct mm_struct;
+#define mm_p4d_folded mm_p4d_folded
+static inline bool mm_p4d_folded(struct mm_struct *mm)
+{
+ return !pgtable_l5_enabled();
+}
+
void set_pte_vaddr_p4d(p4d_t *p4d_page, unsigned long vaddr, pte_t new_pte);
void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte);
@@ -180,10 +186,6 @@ extern void sync_global_pgds(unsigned long start, unsigned long end);
/* PTE - Level 1 access. */
-/* x86-64 always has all page tables mapped. */
-#define pte_offset_map(dir, address) pte_offset_kernel((dir), (address))
-#define pte_unmap(pte) ((void)(pte))/* NOP */
-
/*
* Encode and de-code a swap entry
*
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 52e5f5f2240d..8f63efb2a2cc 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -159,4 +159,6 @@ extern unsigned int ptrs_per_p4d;
#define PGD_KERNEL_START ((PAGE_SIZE / 2) / sizeof(pgd_t))
+#define ARCH_PAGE_TABLE_SYNC_MASK (pgtable_l5_enabled() ? PGTBL_PGD_MODIFIED : PGTBL_P4D_MODIFIED)
+
#endif /* _ASM_X86_PGTABLE_64_DEFS_H */
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index b6606fe6cfdf..2da1f95b88d7 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -194,7 +194,6 @@ enum page_cache_mode {
#define _PAGE_TABLE_NOENC (__PP|__RW|_USR|___A| 0|___D| 0| 0)
#define _PAGE_TABLE (__PP|__RW|_USR|___A| 0|___D| 0| 0| _ENC)
#define __PAGE_KERNEL_RO (__PP| 0| 0|___A|__NX|___D| 0|___G)
-#define __PAGE_KERNEL_RX (__PP| 0| 0|___A| 0|___D| 0|___G)
#define __PAGE_KERNEL_NOCACHE (__PP|__RW| 0|___A|__NX|___D| 0|___G| __NC)
#define __PAGE_KERNEL_VVAR (__PP| 0|_USR|___A|__NX|___D| 0|___G)
#define __PAGE_KERNEL_LARGE (__PP|__RW| 0|___A|__NX|___D|_PSE|___G)
@@ -220,7 +219,6 @@ enum page_cache_mode {
#define PAGE_KERNEL_RO __pgprot_mask(__PAGE_KERNEL_RO | _ENC)
#define PAGE_KERNEL_EXEC __pgprot_mask(__PAGE_KERNEL_EXEC | _ENC)
#define PAGE_KERNEL_EXEC_NOENC __pgprot_mask(__PAGE_KERNEL_EXEC | 0)
-#define PAGE_KERNEL_RX __pgprot_mask(__PAGE_KERNEL_RX | _ENC)
#define PAGE_KERNEL_NOCACHE __pgprot_mask(__PAGE_KERNEL_NOCACHE | _ENC)
#define PAGE_KERNEL_LARGE __pgprot_mask(__PAGE_KERNEL_LARGE | _ENC)
#define PAGE_KERNEL_LARGE_EXEC __pgprot_mask(__PAGE_KERNEL_LARGE_EXEC | _ENC)
@@ -284,6 +282,12 @@ typedef struct pgprot { pgprotval_t pgprot; } pgprot_t;
typedef struct { pgdval_t pgd; } pgd_t;
+static inline pgprot_t pgprot_nx(pgprot_t prot)
+{
+ return __pgprot(pgprot_val(prot) | _PAGE_NX);
+}
+#define pgprot_nx pgprot_nx
+
#ifdef CONFIG_X86_PAE
/*
@@ -467,9 +471,6 @@ static inline pteval_t pte_flags(pte_t pte)
return native_pte_val(pte) & PTE_FLAGS_MASK;
}
-extern uint16_t __cachemode2pte_tbl[_PAGE_CACHE_MODE_NUM];
-extern uint8_t __pte2cachemode_tbl[8];
-
#define __pte2cm_idx(cb) \
((((cb) >> (_PAGE_BIT_PAT - 2)) & 4) | \
(((cb) >> (_PAGE_BIT_PCD - 1)) & 2) | \
@@ -479,43 +480,26 @@ extern uint8_t __pte2cachemode_tbl[8];
(((i) & 2) << (_PAGE_BIT_PCD - 1)) | \
(((i) & 1) << _PAGE_BIT_PWT))
-static inline unsigned long cachemode2protval(enum page_cache_mode pcm)
-{
- if (likely(pcm == 0))
- return 0;
- return __cachemode2pte_tbl[pcm];
-}
-static inline pgprot_t cachemode2pgprot(enum page_cache_mode pcm)
+unsigned long cachemode2protval(enum page_cache_mode pcm);
+
+static inline pgprotval_t protval_4k_2_large(pgprotval_t val)
{
- return __pgprot(cachemode2protval(pcm));
+ return (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) |
+ ((val & _PAGE_PAT) << (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT));
}
-static inline enum page_cache_mode pgprot2cachemode(pgprot_t pgprot)
+static inline pgprot_t pgprot_4k_2_large(pgprot_t pgprot)
{
- unsigned long masked;
-
- masked = pgprot_val(pgprot) & _PAGE_CACHE_MASK;
- if (likely(masked == 0))
- return 0;
- return __pte2cachemode_tbl[__pte2cm_idx(masked)];
+ return __pgprot(protval_4k_2_large(pgprot_val(pgprot)));
}
-static inline pgprot_t pgprot_4k_2_large(pgprot_t pgprot)
+static inline pgprotval_t protval_large_2_4k(pgprotval_t val)
{
- pgprotval_t val = pgprot_val(pgprot);
- pgprot_t new;
-
- pgprot_val(new) = (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) |
- ((val & _PAGE_PAT) << (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT));
- return new;
+ return (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) |
+ ((val & _PAGE_PAT_LARGE) >>
+ (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT));
}
static inline pgprot_t pgprot_large_2_4k(pgprot_t pgprot)
{
- pgprotval_t val = pgprot_val(pgprot);
- pgprot_t new;
-
- pgprot_val(new) = (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) |
- ((val & _PAGE_PAT_LARGE) >>
- (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT));
- return new;
+ return __pgprot(protval_large_2_4k(pgprot_val(pgprot)));
}
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 3bcf27caf6c9..42cd333616c4 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -113,9 +113,10 @@ struct cpuinfo_x86 {
/* in KB - valid for CPUS which support this call: */
unsigned int x86_cache_size;
int x86_cache_alignment; /* In bytes */
- /* Cache QoS architectural values: */
+ /* Cache QoS architectural values, valid only on the BSP: */
int x86_cache_max_rmid; /* max index */
int x86_cache_occ_scale; /* scale to bytes */
+ int x86_cache_mbm_width_offset;
int x86_power;
unsigned long loops_per_jiffy;
/* cpuid returned max cores value: */
@@ -727,7 +728,6 @@ static inline void sync_core(void)
unsigned int tmp;
asm volatile (
- UNWIND_HINT_SAVE
"mov %%ss, %0\n\t"
"pushq %q0\n\t"
"pushq %%rsp\n\t"
@@ -737,7 +737,6 @@ static inline void sync_core(void)
"pushq %q0\n\t"
"pushq $1f\n\t"
"iretq\n\t"
- UNWIND_HINT_RESTORE
"1:"
: "=&r" (tmp), ASM_CALL_CONSTRAINT : : "cc", "memory");
#endif
@@ -824,7 +823,7 @@ static inline void prefetch(const void *x)
* Useful for spinlocks to avoid one state transition in the
* cache coherency protocol:
*/
-static inline void prefetchw(const void *x)
+static __always_inline void prefetchw(const void *x)
{
alternative_input(BASE_PREFETCH, "prefetchw %P1",
X86_FEATURE_3DNOWPREFETCH,
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 6d6475fdd327..ebedeab48704 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -123,7 +123,7 @@ static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
* On x86_64, vm86 mode is mercifully nonexistent, and we don't need
* the extra check.
*/
-static inline int user_mode(struct pt_regs *regs)
+static __always_inline int user_mode(struct pt_regs *regs)
{
#ifdef CONFIG_X86_32
return ((regs->cs & SEGMENT_RPL_MASK) | (regs->flags & X86_VM_MASK)) >= USER_RPL;
diff --git a/arch/x86/include/asm/resctrl_sched.h b/arch/x86/include/asm/resctrl.h
index f6b7fe2833cc..07603064df8f 100644
--- a/arch/x86/include/asm/resctrl_sched.h
+++ b/arch/x86/include/asm/resctrl.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_RESCTRL_SCHED_H
-#define _ASM_X86_RESCTRL_SCHED_H
+#ifndef _ASM_X86_RESCTRL_H
+#define _ASM_X86_RESCTRL_H
#ifdef CONFIG_X86_CPU_RESCTRL
@@ -84,10 +84,13 @@ static inline void resctrl_sched_in(void)
__resctrl_sched_in();
}
+void resctrl_cpu_detect(struct cpuinfo_x86 *c);
+
#else
static inline void resctrl_sched_in(void) {}
+static inline void resctrl_cpu_detect(struct cpuinfo_x86 *c) {}
#endif /* CONFIG_X86_CPU_RESCTRL */
-#endif /* _ASM_X86_RESCTRL_SCHED_H */
+#endif /* _ASM_X86_RESCTRL_H */
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index ed8ec011a9fd..84b645cc8bc9 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -75,7 +75,17 @@ extern char _text[];
static inline bool kaslr_enabled(void)
{
- return !!(boot_params.hdr.loadflags & KASLR_FLAG);
+ return IS_ENABLED(CONFIG_RANDOMIZE_MEMORY) &&
+ !!(boot_params.hdr.loadflags & KASLR_FLAG);
+}
+
+/*
+ * Apply no randomization if KASLR was disabled at boot or if KASAN
+ * is enabled. KASAN shadow mappings rely on regions being PGD aligned.
+ */
+static inline bool kaslr_memory_enabled(void)
+{
+ return kaslr_enabled() && !IS_ENABLED(CONFIG_KASAN);
}
static inline unsigned long kaslr_offset(void)
diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h
index 27c47d183f4b..8b58d6975d5d 100644
--- a/arch/x86/include/asm/smap.h
+++ b/arch/x86/include/asm/smap.h
@@ -57,8 +57,10 @@ static __always_inline unsigned long smap_save(void)
{
unsigned long flags;
- asm volatile (ALTERNATIVE("", "pushf; pop %0; " __ASM_CLAC,
- X86_FEATURE_SMAP)
+ asm volatile ("# smap_save\n\t"
+ ALTERNATIVE("jmp 1f", "", X86_FEATURE_SMAP)
+ "pushf; pop %0; " __ASM_CLAC "\n\t"
+ "1:"
: "=rm" (flags) : : "memory", "cc");
return flags;
@@ -66,7 +68,10 @@ static __always_inline unsigned long smap_save(void)
static __always_inline void smap_restore(unsigned long flags)
{
- asm volatile (ALTERNATIVE("", "push %0; popf", X86_FEATURE_SMAP)
+ asm volatile ("# smap_restore\n\t"
+ ALTERNATIVE("jmp 1f", "", X86_FEATURE_SMAP)
+ "push %0; popf\n\t"
+ "1:"
: : "g" (flags) : "memory", "cc");
}
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 6d37b8fcfc77..eb8e781c4353 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -7,6 +7,7 @@
#include <asm/nops.h>
#include <asm/processor-flags.h>
+#include <linux/irqflags.h>
#include <linux/jump_label.h>
/*
@@ -27,14 +28,14 @@ static inline unsigned long native_read_cr0(void)
return val;
}
-static inline unsigned long native_read_cr2(void)
+static __always_inline unsigned long native_read_cr2(void)
{
unsigned long val;
asm volatile("mov %%cr2,%0\n\t" : "=r" (val), "=m" (__force_order));
return val;
}
-static inline void native_write_cr2(unsigned long val)
+static __always_inline void native_write_cr2(unsigned long val)
{
asm volatile("mov %0,%%cr2": : "r" (val), "m" (__force_order));
}
@@ -129,7 +130,16 @@ static inline void native_wbinvd(void)
asm volatile("wbinvd": : :"memory");
}
-extern asmlinkage void native_load_gs_index(unsigned);
+extern asmlinkage void asm_load_gs_index(unsigned int selector);
+
+static inline void native_load_gs_index(unsigned int selector)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ asm_load_gs_index(selector);
+ local_irq_restore(flags);
+}
static inline unsigned long __read_cr4(void)
{
@@ -150,12 +160,12 @@ static inline void write_cr0(unsigned long x)
native_write_cr0(x);
}
-static inline unsigned long read_cr2(void)
+static __always_inline unsigned long read_cr2(void)
{
return native_read_cr2();
}
-static inline void write_cr2(unsigned long x)
+static __always_inline void write_cr2(unsigned long x)
{
native_write_cr2(x);
}
@@ -186,7 +196,7 @@ static inline void wbinvd(void)
#ifdef CONFIG_X86_64
-static inline void load_gs_index(unsigned selector)
+static inline void load_gs_index(unsigned int selector)
{
native_load_gs_index(selector);
}
diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h
index bf3e34b25afc..323db6c5852a 100644
--- a/arch/x86/include/asm/spinlock_types.h
+++ b/arch/x86/include/asm/spinlock_types.h
@@ -3,29 +3,7 @@
#define _ASM_X86_SPINLOCK_TYPES_H
#include <linux/types.h>
-
-#ifdef CONFIG_PARAVIRT_SPINLOCKS
-#define __TICKET_LOCK_INC 2
-#define TICKET_SLOWPATH_FLAG ((__ticket_t)1)
-#else
-#define __TICKET_LOCK_INC 1
-#define TICKET_SLOWPATH_FLAG ((__ticket_t)0)
-#endif
-
-#if (CONFIG_NR_CPUS < (256 / __TICKET_LOCK_INC))
-typedef u8 __ticket_t;
-typedef u16 __ticketpair_t;
-#else
-typedef u16 __ticket_t;
-typedef u32 __ticketpair_t;
-#endif
-
-#define TICKET_LOCK_INC ((__ticket_t)__TICKET_LOCK_INC)
-
-#define TICKET_SHIFT (sizeof(__ticket_t) * 8)
-
#include <asm-generic/qspinlock_types.h>
-
#include <asm-generic/qrwlock_types.h>
#endif /* _ASM_X86_SPINLOCK_TYPES_H */
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
index 91e29b6a86a5..9804a7957f4e 100644
--- a/arch/x86/include/asm/stackprotector.h
+++ b/arch/x86/include/asm/stackprotector.h
@@ -55,8 +55,13 @@
/*
* Initialize the stackprotector canary value.
*
- * NOTE: this must only be called from functions that never return,
+ * NOTE: this must only be called from functions that never return
* and it must always be inlined.
+ *
+ * In addition, it should be called from a compilation unit for which
+ * stack protector is disabled. Alternatively, the caller should not end
+ * with a function call which gets tail-call optimized as that would
+ * lead to checking a modified canary value.
*/
static __always_inline void boot_init_stack_canary(void)
{
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index 14db05086bbf..5ae5a68e469d 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -87,7 +87,7 @@ get_stack_pointer(struct task_struct *task, struct pt_regs *regs)
}
void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
- unsigned long *stack, char *log_lvl);
+ unsigned long *stack, const char *log_lvl);
/* The form of the top of the frame on the stack */
struct stack_frame {
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 6ece8561ba66..8a1f5382a4ea 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -96,7 +96,6 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
u8 reserved_6[8]; /* Offset 0xe8 */
u64 avic_logical_id; /* Offset 0xf0 */
u64 avic_physical_id; /* Offset 0xf8 */
- u8 reserved_7[768];
};
@@ -203,8 +202,16 @@ struct __attribute__ ((__packed__)) vmcb_save_area {
u64 last_excp_to;
};
+
+static inline void __unused_size_checks(void)
+{
+ BUILD_BUG_ON(sizeof(struct vmcb_save_area) != 0x298);
+ BUILD_BUG_ON(sizeof(struct vmcb_control_area) != 256);
+}
+
struct __attribute__ ((__packed__)) vmcb {
struct vmcb_control_area control;
+ u8 reserved_control[1024 - sizeof(struct vmcb_control_area)];
struct vmcb_save_area save;
};
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index 0e059b73437b..9f69cc497f4b 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -12,27 +12,6 @@ struct task_struct *__switch_to_asm(struct task_struct *prev,
__visible struct task_struct *__switch_to(struct task_struct *prev,
struct task_struct *next);
-/* This runs runs on the previous thread's stack. */
-static inline void prepare_switch_to(struct task_struct *next)
-{
-#ifdef CONFIG_VMAP_STACK
- /*
- * If we switch to a stack that has a top-level paging entry
- * that is not present in the current mm, the resulting #PF will
- * will be promoted to a double-fault and we'll panic. Probe
- * the new stack now so that vmalloc_fault can fix up the page
- * tables if needed. This can only happen if we use a stack
- * in vmap space.
- *
- * We assume that the stack is aligned so that it never spans
- * more than one top-level paging entry.
- *
- * To minimize cache pollution, just follow the stack pointer.
- */
- READ_ONCE(*(unsigned char *)next->thread.sp);
-#endif
-}
-
asmlinkage void ret_from_fork(void);
/*
@@ -67,8 +46,6 @@ struct fork_frame {
#define switch_to(prev, next, last) \
do { \
- prepare_switch_to(next); \
- \
((last) = __switch_to_asm((prev), (next))); \
} while (0)
diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h
index 67315fa3956a..6593b42cb379 100644
--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -64,7 +64,7 @@ extern void text_poke_finish(void);
#define DISP32_SIZE 4
-static inline int text_opcode_size(u8 opcode)
+static __always_inline int text_opcode_size(u8 opcode)
{
int size = 0;
@@ -118,12 +118,14 @@ extern __ro_after_init struct mm_struct *poking_mm;
extern __ro_after_init unsigned long poking_addr;
#ifndef CONFIG_UML_X86
-static inline void int3_emulate_jmp(struct pt_regs *regs, unsigned long ip)
+static __always_inline
+void int3_emulate_jmp(struct pt_regs *regs, unsigned long ip)
{
regs->ip = ip;
}
-static inline void int3_emulate_push(struct pt_regs *regs, unsigned long val)
+static __always_inline
+void int3_emulate_push(struct pt_regs *regs, unsigned long val)
{
/*
* The int3 handler in entry_64.S adds a gap between the
@@ -138,7 +140,8 @@ static inline void int3_emulate_push(struct pt_regs *regs, unsigned long val)
*(unsigned long *)regs->sp = val;
}
-static inline void int3_emulate_call(struct pt_regs *regs, unsigned long func)
+static __always_inline
+void int3_emulate_call(struct pt_regs *regs, unsigned long func)
{
int3_emulate_push(regs, regs->ip - INT3_INSN_SIZE + CALL_INSN_SIZE);
int3_emulate_jmp(regs, func);
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 6f66d841262d..8c87a2e0b660 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -13,140 +13,51 @@
#include <asm/pti.h>
#include <asm/processor-flags.h>
-/*
- * The x86 feature is called PCID (Process Context IDentifier). It is similar
- * to what is traditionally called ASID on the RISC processors.
- *
- * We don't use the traditional ASID implementation, where each process/mm gets
- * its own ASID and flush/restart when we run out of ASID space.
- *
- * Instead we have a small per-cpu array of ASIDs and cache the last few mm's
- * that came by on this CPU, allowing cheaper switch_mm between processes on
- * this CPU.
- *
- * We end up with different spaces for different things. To avoid confusion we
- * use different names for each of them:
- *
- * ASID - [0, TLB_NR_DYN_ASIDS-1]
- * the canonical identifier for an mm
- *
- * kPCID - [1, TLB_NR_DYN_ASIDS]
- * the value we write into the PCID part of CR3; corresponds to the
- * ASID+1, because PCID 0 is special.
- *
- * uPCID - [2048 + 1, 2048 + TLB_NR_DYN_ASIDS]
- * for KPTI each mm has two address spaces and thus needs two
- * PCID values, but we can still do with a single ASID denomination
- * for each mm. Corresponds to kPCID + 2048.
- *
- */
-
-/* There are 12 bits of space for ASIDS in CR3 */
-#define CR3_HW_ASID_BITS 12
-
-/*
- * When enabled, PAGE_TABLE_ISOLATION consumes a single bit for
- * user/kernel switches
- */
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
-# define PTI_CONSUMED_PCID_BITS 1
-#else
-# define PTI_CONSUMED_PCID_BITS 0
-#endif
+void __flush_tlb_all(void);
-#define CR3_AVAIL_PCID_BITS (X86_CR3_PCID_BITS - PTI_CONSUMED_PCID_BITS)
+#define TLB_FLUSH_ALL -1UL
-/*
- * ASIDs are zero-based: 0->MAX_AVAIL_ASID are valid. -1 below to account
- * for them being zero-based. Another -1 is because PCID 0 is reserved for
- * use by non-PCID-aware users.
- */
-#define MAX_ASID_AVAILABLE ((1 << CR3_AVAIL_PCID_BITS) - 2)
+void cr4_update_irqsoff(unsigned long set, unsigned long clear);
+unsigned long cr4_read_shadow(void);
-/*
- * 6 because 6 should be plenty and struct tlb_state will fit in two cache
- * lines.
- */
-#define TLB_NR_DYN_ASIDS 6
-
-/*
- * Given @asid, compute kPCID
- */
-static inline u16 kern_pcid(u16 asid)
+/* Set in this cpu's CR4. */
+static inline void cr4_set_bits_irqsoff(unsigned long mask)
{
- VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE);
-
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
- /*
- * Make sure that the dynamic ASID space does not confict with the
- * bit we are using to switch between user and kernel ASIDs.
- */
- BUILD_BUG_ON(TLB_NR_DYN_ASIDS >= (1 << X86_CR3_PTI_PCID_USER_BIT));
-
- /*
- * The ASID being passed in here should have respected the
- * MAX_ASID_AVAILABLE and thus never have the switch bit set.
- */
- VM_WARN_ON_ONCE(asid & (1 << X86_CR3_PTI_PCID_USER_BIT));
-#endif
- /*
- * The dynamically-assigned ASIDs that get passed in are small
- * (<TLB_NR_DYN_ASIDS). They never have the high switch bit set,
- * so do not bother to clear it.
- *
- * If PCID is on, ASID-aware code paths put the ASID+1 into the
- * PCID bits. This serves two purposes. It prevents a nasty
- * situation in which PCID-unaware code saves CR3, loads some other
- * value (with PCID == 0), and then restores CR3, thus corrupting
- * the TLB for ASID 0 if the saved ASID was nonzero. It also means
- * that any bugs involving loading a PCID-enabled CR3 with
- * CR4.PCIDE off will trigger deterministically.
- */
- return asid + 1;
+ cr4_update_irqsoff(mask, 0);
}
-/*
- * Given @asid, compute uPCID
- */
-static inline u16 user_pcid(u16 asid)
+/* Clear in this cpu's CR4. */
+static inline void cr4_clear_bits_irqsoff(unsigned long mask)
{
- u16 ret = kern_pcid(asid);
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
- ret |= 1 << X86_CR3_PTI_PCID_USER_BIT;
-#endif
- return ret;
+ cr4_update_irqsoff(0, mask);
}
-struct pgd_t;
-static inline unsigned long build_cr3(pgd_t *pgd, u16 asid)
+/* Set in this cpu's CR4. */
+static inline void cr4_set_bits(unsigned long mask)
{
- if (static_cpu_has(X86_FEATURE_PCID)) {
- return __sme_pa(pgd) | kern_pcid(asid);
- } else {
- VM_WARN_ON_ONCE(asid != 0);
- return __sme_pa(pgd);
- }
+ unsigned long flags;
+
+ local_irq_save(flags);
+ cr4_set_bits_irqsoff(mask);
+ local_irq_restore(flags);
}
-static inline unsigned long build_cr3_noflush(pgd_t *pgd, u16 asid)
+/* Clear in this cpu's CR4. */
+static inline void cr4_clear_bits(unsigned long mask)
{
- VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE);
- /*
- * Use boot_cpu_has() instead of this_cpu_has() as this function
- * might be called during early boot. This should work even after
- * boot because all CPU's the have same capabilities:
- */
- VM_WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_PCID));
- return __sme_pa(pgd) | kern_pcid(asid) | CR3_NOFLUSH;
+ unsigned long flags;
+
+ local_irq_save(flags);
+ cr4_clear_bits_irqsoff(mask);
+ local_irq_restore(flags);
}
-#ifdef CONFIG_PARAVIRT
-#include <asm/paravirt.h>
-#else
-#define __flush_tlb() __native_flush_tlb()
-#define __flush_tlb_global() __native_flush_tlb_global()
-#define __flush_tlb_one_user(addr) __native_flush_tlb_one_user(addr)
-#endif
+#ifndef MODULE
+/*
+ * 6 because 6 should be plenty and struct tlb_state will fit in two cache
+ * lines.
+ */
+#define TLB_NR_DYN_ASIDS 6
struct tlb_context {
u64 ctx_id;
@@ -242,38 +153,7 @@ struct tlb_state {
};
DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate);
-/*
- * Blindly accessing user memory from NMI context can be dangerous
- * if we're in the middle of switching the current user task or
- * switching the loaded mm. It can also be dangerous if we
- * interrupted some kernel code that was temporarily using a
- * different mm.
- */
-static inline bool nmi_uaccess_okay(void)
-{
- struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm);
- struct mm_struct *current_mm = current->mm;
-
- VM_WARN_ON_ONCE(!loaded_mm);
-
- /*
- * The condition we want to check is
- * current_mm->pgd == __va(read_cr3_pa()). This may be slow, though,
- * if we're running in a VM with shadow paging, and nmi_uaccess_okay()
- * is supposed to be reasonably fast.
- *
- * Instead, we check the almost equivalent but somewhat conservative
- * condition below, and we rely on the fact that switch_mm_irqs_off()
- * sets loaded_mm to LOADED_MM_SWITCHING before writing to CR3.
- */
- if (loaded_mm != current_mm)
- return false;
-
- VM_WARN_ON_ONCE(current_mm->pgd != __va(read_cr3_pa()));
-
- return true;
-}
-
+bool nmi_uaccess_okay(void);
#define nmi_uaccess_okay nmi_uaccess_okay
/* Initialize cr4 shadow for this CPU. */
@@ -282,250 +162,12 @@ static inline void cr4_init_shadow(void)
this_cpu_write(cpu_tlbstate.cr4, __read_cr4());
}
-static inline void __cr4_set(unsigned long cr4)
-{
- lockdep_assert_irqs_disabled();
- this_cpu_write(cpu_tlbstate.cr4, cr4);
- __write_cr4(cr4);
-}
-
-/* Set in this cpu's CR4. */
-static inline void cr4_set_bits_irqsoff(unsigned long mask)
-{
- unsigned long cr4;
-
- cr4 = this_cpu_read(cpu_tlbstate.cr4);
- if ((cr4 | mask) != cr4)
- __cr4_set(cr4 | mask);
-}
-
-/* Clear in this cpu's CR4. */
-static inline void cr4_clear_bits_irqsoff(unsigned long mask)
-{
- unsigned long cr4;
-
- cr4 = this_cpu_read(cpu_tlbstate.cr4);
- if ((cr4 & ~mask) != cr4)
- __cr4_set(cr4 & ~mask);
-}
-
-/* Set in this cpu's CR4. */
-static inline void cr4_set_bits(unsigned long mask)
-{
- unsigned long flags;
-
- local_irq_save(flags);
- cr4_set_bits_irqsoff(mask);
- local_irq_restore(flags);
-}
-
-/* Clear in this cpu's CR4. */
-static inline void cr4_clear_bits(unsigned long mask)
-{
- unsigned long flags;
-
- local_irq_save(flags);
- cr4_clear_bits_irqsoff(mask);
- local_irq_restore(flags);
-}
-
-static inline void cr4_toggle_bits_irqsoff(unsigned long mask)
-{
- unsigned long cr4;
-
- cr4 = this_cpu_read(cpu_tlbstate.cr4);
- __cr4_set(cr4 ^ mask);
-}
-
-/* Read the CR4 shadow. */
-static inline unsigned long cr4_read_shadow(void)
-{
- return this_cpu_read(cpu_tlbstate.cr4);
-}
-
-/*
- * Mark all other ASIDs as invalid, preserves the current.
- */
-static inline void invalidate_other_asid(void)
-{
- this_cpu_write(cpu_tlbstate.invalidate_other, true);
-}
-
-/*
- * Save some of cr4 feature set we're using (e.g. Pentium 4MB
- * enable and PPro Global page enable), so that any CPU's that boot
- * up after us can get the correct flags. This should only be used
- * during boot on the boot cpu.
- */
extern unsigned long mmu_cr4_features;
extern u32 *trampoline_cr4_features;
-static inline void cr4_set_bits_and_update_boot(unsigned long mask)
-{
- mmu_cr4_features |= mask;
- if (trampoline_cr4_features)
- *trampoline_cr4_features = mmu_cr4_features;
- cr4_set_bits(mask);
-}
-
extern void initialize_tlbstate_and_flush(void);
/*
- * Given an ASID, flush the corresponding user ASID. We can delay this
- * until the next time we switch to it.
- *
- * See SWITCH_TO_USER_CR3.
- */
-static inline void invalidate_user_asid(u16 asid)
-{
- /* There is no user ASID if address space separation is off */
- if (!IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
- return;
-
- /*
- * We only have a single ASID if PCID is off and the CR3
- * write will have flushed it.
- */
- if (!cpu_feature_enabled(X86_FEATURE_PCID))
- return;
-
- if (!static_cpu_has(X86_FEATURE_PTI))
- return;
-
- __set_bit(kern_pcid(asid),
- (unsigned long *)this_cpu_ptr(&cpu_tlbstate.user_pcid_flush_mask));
-}
-
-/*
- * flush the entire current user mapping
- */
-static inline void __native_flush_tlb(void)
-{
- /*
- * Preemption or interrupts must be disabled to protect the access
- * to the per CPU variable and to prevent being preempted between
- * read_cr3() and write_cr3().
- */
- WARN_ON_ONCE(preemptible());
-
- invalidate_user_asid(this_cpu_read(cpu_tlbstate.loaded_mm_asid));
-
- /* If current->mm == NULL then the read_cr3() "borrows" an mm */
- native_write_cr3(__native_read_cr3());
-}
-
-/*
- * flush everything
- */
-static inline void __native_flush_tlb_global(void)
-{
- unsigned long cr4, flags;
-
- if (static_cpu_has(X86_FEATURE_INVPCID)) {
- /*
- * Using INVPCID is considerably faster than a pair of writes
- * to CR4 sandwiched inside an IRQ flag save/restore.
- *
- * Note, this works with CR4.PCIDE=0 or 1.
- */
- invpcid_flush_all();
- return;
- }
-
- /*
- * Read-modify-write to CR4 - protect it from preemption and
- * from interrupts. (Use the raw variant because this code can
- * be called from deep inside debugging code.)
- */
- raw_local_irq_save(flags);
-
- cr4 = this_cpu_read(cpu_tlbstate.cr4);
- /* toggle PGE */
- native_write_cr4(cr4 ^ X86_CR4_PGE);
- /* write old PGE again and flush TLBs */
- native_write_cr4(cr4);
-
- raw_local_irq_restore(flags);
-}
-
-/*
- * flush one page in the user mapping
- */
-static inline void __native_flush_tlb_one_user(unsigned long addr)
-{
- u32 loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
-
- asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
-
- if (!static_cpu_has(X86_FEATURE_PTI))
- return;
-
- /*
- * Some platforms #GP if we call invpcid(type=1/2) before CR4.PCIDE=1.
- * Just use invalidate_user_asid() in case we are called early.
- */
- if (!this_cpu_has(X86_FEATURE_INVPCID_SINGLE))
- invalidate_user_asid(loaded_mm_asid);
- else
- invpcid_flush_one(user_pcid(loaded_mm_asid), addr);
-}
-
-/*
- * flush everything
- */
-static inline void __flush_tlb_all(void)
-{
- /*
- * This is to catch users with enabled preemption and the PGE feature
- * and don't trigger the warning in __native_flush_tlb().
- */
- VM_WARN_ON_ONCE(preemptible());
-
- if (boot_cpu_has(X86_FEATURE_PGE)) {
- __flush_tlb_global();
- } else {
- /*
- * !PGE -> !PCID (setup_pcid()), thus every flush is total.
- */
- __flush_tlb();
- }
-}
-
-/*
- * flush one page in the kernel mapping
- */
-static inline void __flush_tlb_one_kernel(unsigned long addr)
-{
- count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);
-
- /*
- * If PTI is off, then __flush_tlb_one_user() is just INVLPG or its
- * paravirt equivalent. Even with PCID, this is sufficient: we only
- * use PCID if we also use global PTEs for the kernel mapping, and
- * INVLPG flushes global translations across all address spaces.
- *
- * If PTI is on, then the kernel is mapped with non-global PTEs, and
- * __flush_tlb_one_user() will flush the given address for the current
- * kernel address space and for its usermode counterpart, but it does
- * not flush it for other address spaces.
- */
- __flush_tlb_one_user(addr);
-
- if (!static_cpu_has(X86_FEATURE_PTI))
- return;
-
- /*
- * See above. We need to propagate the flush to all other address
- * spaces. In principle, we only need to propagate it to kernelmode
- * address spaces, but the extra bookkeeping we would need is not
- * worth it.
- */
- invalidate_other_asid();
-}
-
-#define TLB_FLUSH_ALL -1UL
-
-/*
* TLB flushing:
*
* - flush_tlb_all() flushes all processes TLBs
@@ -563,7 +205,15 @@ struct flush_tlb_info {
bool freed_tables;
};
-#define local_flush_tlb() __flush_tlb()
+void flush_tlb_local(void);
+void flush_tlb_one_user(unsigned long addr);
+void flush_tlb_one_kernel(unsigned long addr);
+void flush_tlb_others(const struct cpumask *cpumask,
+ const struct flush_tlb_info *info);
+
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#endif
#define flush_tlb_mm(mm) \
flush_tlb_mm_range(mm, 0UL, TLB_FLUSH_ALL, 0UL, true)
@@ -585,9 +235,6 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a)
flush_tlb_mm_range(vma->vm_mm, a, a + PAGE_SIZE, PAGE_SHIFT, false);
}
-void native_flush_tlb_others(const struct cpumask *cpumask,
- const struct flush_tlb_info *info);
-
static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
{
/*
@@ -608,12 +255,6 @@ static inline void arch_tlbbatch_add_mm(struct arch_tlbflush_unmap_batch *batch,
extern void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch);
-#ifndef CONFIG_PARAVIRT
-#define flush_tlb_others(mask, info) \
- native_flush_tlb_others(mask, info)
-
-#define paravirt_tlb_remove_table(tlb, page) \
- tlb_remove_page(tlb, (void *)(page))
-#endif
+#endif /* !MODULE */
#endif /* _ASM_X86_TLBFLUSH_H */
diff --git a/arch/x86/include/asm/trace/common.h b/arch/x86/include/asm/trace/common.h
index 57c8da027d99..f0f9bcdb74d9 100644
--- a/arch/x86/include/asm/trace/common.h
+++ b/arch/x86/include/asm/trace/common.h
@@ -5,12 +5,8 @@
DECLARE_STATIC_KEY_FALSE(trace_pagefault_key);
#define trace_pagefault_enabled() \
static_branch_unlikely(&trace_pagefault_key)
-DECLARE_STATIC_KEY_FALSE(trace_resched_ipi_key);
-#define trace_resched_ipi_enabled() \
- static_branch_unlikely(&trace_resched_ipi_key)
#else
static inline bool trace_pagefault_enabled(void) { return false; }
-static inline bool trace_resched_ipi_enabled(void) { return false; }
#endif
#endif
diff --git a/arch/x86/include/asm/trace/irq_vectors.h b/arch/x86/include/asm/trace/irq_vectors.h
index 33b9d0f0aafe..88e7f0f3bf62 100644
--- a/arch/x86/include/asm/trace/irq_vectors.h
+++ b/arch/x86/include/asm/trace/irq_vectors.h
@@ -10,9 +10,6 @@
#ifdef CONFIG_X86_LOCAL_APIC
-extern int trace_resched_ipi_reg(void);
-extern void trace_resched_ipi_unreg(void);
-
DECLARE_EVENT_CLASS(x86_irq_vector,
TP_PROTO(int vector),
@@ -37,18 +34,6 @@ DEFINE_EVENT_FN(x86_irq_vector, name##_exit, \
TP_PROTO(int vector), \
TP_ARGS(vector), NULL, NULL);
-#define DEFINE_RESCHED_IPI_EVENT(name) \
-DEFINE_EVENT_FN(x86_irq_vector, name##_entry, \
- TP_PROTO(int vector), \
- TP_ARGS(vector), \
- trace_resched_ipi_reg, \
- trace_resched_ipi_unreg); \
-DEFINE_EVENT_FN(x86_irq_vector, name##_exit, \
- TP_PROTO(int vector), \
- TP_ARGS(vector), \
- trace_resched_ipi_reg, \
- trace_resched_ipi_unreg);
-
/*
* local_timer - called when entering/exiting a local timer interrupt
* vector handler
@@ -99,7 +84,7 @@ TRACE_EVENT_PERF_PERM(irq_work_exit, is_sampling_event(p_event) ? -EPERM : 0);
/*
* reschedule - called when entering/exiting a reschedule vector handler
*/
-DEFINE_RESCHED_IPI_EVENT(reschedule);
+DEFINE_IRQ_VECTOR_EVENT(reschedule);
/*
* call_function - called when entering/exiting a call function interrupt
diff --git a/arch/x86/include/asm/trapnr.h b/arch/x86/include/asm/trapnr.h
new file mode 100644
index 000000000000..082f45631fa9
--- /dev/null
+++ b/arch/x86/include/asm/trapnr.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_TRAPNR_H
+#define _ASM_X86_TRAPNR_H
+
+/* Interrupts/Exceptions */
+
+#define X86_TRAP_DE 0 /* Divide-by-zero */
+#define X86_TRAP_DB 1 /* Debug */
+#define X86_TRAP_NMI 2 /* Non-maskable Interrupt */
+#define X86_TRAP_BP 3 /* Breakpoint */
+#define X86_TRAP_OF 4 /* Overflow */
+#define X86_TRAP_BR 5 /* Bound Range Exceeded */
+#define X86_TRAP_UD 6 /* Invalid Opcode */
+#define X86_TRAP_NM 7 /* Device Not Available */
+#define X86_TRAP_DF 8 /* Double Fault */
+#define X86_TRAP_OLD_MF 9 /* Coprocessor Segment Overrun */
+#define X86_TRAP_TS 10 /* Invalid TSS */
+#define X86_TRAP_NP 11 /* Segment Not Present */
+#define X86_TRAP_SS 12 /* Stack Segment Fault */
+#define X86_TRAP_GP 13 /* General Protection Fault */
+#define X86_TRAP_PF 14 /* Page Fault */
+#define X86_TRAP_SPURIOUS 15 /* Spurious Interrupt */
+#define X86_TRAP_MF 16 /* x87 Floating-Point Exception */
+#define X86_TRAP_AC 17 /* Alignment Check */
+#define X86_TRAP_MC 18 /* Machine Check */
+#define X86_TRAP_XF 19 /* SIMD Floating-Point Exception */
+#define X86_TRAP_VE 20 /* Virtualization Exception */
+#define X86_TRAP_CP 21 /* Control Protection Exception */
+#define X86_TRAP_IRET 32 /* IRET Exception */
+
+#endif
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index c26a7e1d8a2c..714b1a30e7b0 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -6,87 +6,9 @@
#include <linux/kprobes.h>
#include <asm/debugreg.h>
+#include <asm/idtentry.h>
#include <asm/siginfo.h> /* TRAP_TRACE, ... */
-#define dotraplinkage __visible
-
-asmlinkage void divide_error(void);
-asmlinkage void debug(void);
-asmlinkage void nmi(void);
-asmlinkage void int3(void);
-asmlinkage void overflow(void);
-asmlinkage void bounds(void);
-asmlinkage void invalid_op(void);
-asmlinkage void device_not_available(void);
-#ifdef CONFIG_X86_64
-asmlinkage void double_fault(void);
-#endif
-asmlinkage void coprocessor_segment_overrun(void);
-asmlinkage void invalid_TSS(void);
-asmlinkage void segment_not_present(void);
-asmlinkage void stack_segment(void);
-asmlinkage void general_protection(void);
-asmlinkage void page_fault(void);
-asmlinkage void async_page_fault(void);
-asmlinkage void spurious_interrupt_bug(void);
-asmlinkage void coprocessor_error(void);
-asmlinkage void alignment_check(void);
-#ifdef CONFIG_X86_MCE
-asmlinkage void machine_check(void);
-#endif /* CONFIG_X86_MCE */
-asmlinkage void simd_coprocessor_error(void);
-
-#if defined(CONFIG_X86_64) && defined(CONFIG_XEN_PV)
-asmlinkage void xen_divide_error(void);
-asmlinkage void xen_xennmi(void);
-asmlinkage void xen_xendebug(void);
-asmlinkage void xen_int3(void);
-asmlinkage void xen_overflow(void);
-asmlinkage void xen_bounds(void);
-asmlinkage void xen_invalid_op(void);
-asmlinkage void xen_device_not_available(void);
-asmlinkage void xen_double_fault(void);
-asmlinkage void xen_coprocessor_segment_overrun(void);
-asmlinkage void xen_invalid_TSS(void);
-asmlinkage void xen_segment_not_present(void);
-asmlinkage void xen_stack_segment(void);
-asmlinkage void xen_general_protection(void);
-asmlinkage void xen_page_fault(void);
-asmlinkage void xen_spurious_interrupt_bug(void);
-asmlinkage void xen_coprocessor_error(void);
-asmlinkage void xen_alignment_check(void);
-#ifdef CONFIG_X86_MCE
-asmlinkage void xen_machine_check(void);
-#endif /* CONFIG_X86_MCE */
-asmlinkage void xen_simd_coprocessor_error(void);
-#endif
-
-dotraplinkage void do_divide_error(struct pt_regs *regs, long error_code);
-dotraplinkage void do_debug(struct pt_regs *regs, long error_code);
-dotraplinkage void do_nmi(struct pt_regs *regs, long error_code);
-dotraplinkage void do_int3(struct pt_regs *regs, long error_code);
-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);
-dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code);
-dotraplinkage void do_general_protection(struct pt_regs *regs, long error_code);
-dotraplinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address);
-dotraplinkage void do_spurious_interrupt_bug(struct pt_regs *regs, long error_code);
-dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code);
-dotraplinkage void do_alignment_check(struct pt_regs *regs, long error_code);
-dotraplinkage void do_simd_coprocessor_error(struct pt_regs *regs, long error_code);
-#ifdef CONFIG_X86_32
-dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code);
-#endif
-dotraplinkage void do_mce(struct pt_regs *regs, long error_code);
-
#ifdef CONFIG_X86_64
asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs);
asmlinkage __visible notrace
@@ -94,6 +16,11 @@ struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s);
void __init trap_init(void);
#endif
+#ifdef CONFIG_X86_F00F_BUG
+/* For handling the FOOF bug */
+void handle_invalid_op(struct pt_regs *regs);
+#endif
+
static inline int get_si_code(unsigned long condition)
{
if (condition & DR_STEP)
@@ -107,21 +34,6 @@ static inline int get_si_code(unsigned long condition)
extern int panic_on_unrecovered_nmi;
void math_emulate(struct math_emu_info *);
-#ifndef CONFIG_X86_32
-asmlinkage void smp_thermal_interrupt(struct pt_regs *regs);
-asmlinkage void smp_threshold_interrupt(struct pt_regs *regs);
-asmlinkage void smp_deferred_error_interrupt(struct pt_regs *regs);
-#endif
-
-void smp_apic_timer_interrupt(struct pt_regs *regs);
-void smp_spurious_interrupt(struct pt_regs *regs);
-void smp_error_interrupt(struct pt_regs *regs);
-asmlinkage void smp_irq_move_cleanup_interrupt(void);
-
-extern void ist_enter(struct pt_regs *regs);
-extern void ist_exit(struct pt_regs *regs);
-extern void ist_begin_non_atomic(struct pt_regs *regs);
-extern void ist_end_non_atomic(void);
#ifdef CONFIG_VMAP_STACK
void __noreturn handle_stack_overflow(const char *message,
@@ -129,31 +41,6 @@ void __noreturn handle_stack_overflow(const char *message,
unsigned long fault_address);
#endif
-/* Interrupts/Exceptions */
-enum {
- X86_TRAP_DE = 0, /* 0, Divide-by-zero */
- X86_TRAP_DB, /* 1, Debug */
- X86_TRAP_NMI, /* 2, Non-maskable Interrupt */
- X86_TRAP_BP, /* 3, Breakpoint */
- X86_TRAP_OF, /* 4, Overflow */
- X86_TRAP_BR, /* 5, Bound Range Exceeded */
- X86_TRAP_UD, /* 6, Invalid Opcode */
- X86_TRAP_NM, /* 7, Device Not Available */
- X86_TRAP_DF, /* 8, Double Fault */
- X86_TRAP_OLD_MF, /* 9, Coprocessor Segment Overrun */
- X86_TRAP_TS, /* 10, Invalid TSS */
- X86_TRAP_NP, /* 11, Segment Not Present */
- X86_TRAP_SS, /* 12, Stack Segment Fault */
- X86_TRAP_GP, /* 13, General Protection Fault */
- X86_TRAP_PF, /* 14, Page Fault */
- X86_TRAP_SPURIOUS, /* 15, Spurious Interrupt */
- X86_TRAP_MF, /* 16, x87 Floating-Point Exception */
- X86_TRAP_AC, /* 17, Alignment Check */
- X86_TRAP_MC, /* 18, Machine Check */
- X86_TRAP_XF, /* 19, SIMD Floating-Point Exception */
- X86_TRAP_IRET = 32, /* 32, IRET Exception */
-};
-
/*
* Page fault error code bits:
*
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index d8f283b9a569..18dfa07d3ef0 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -504,12 +504,12 @@ do { \
* We want the unsafe accessors to always be inlined and use
* the error labels - thus the macro games.
*/
-#define unsafe_copy_loop(dst, src, len, type, label) \
- while (len >= sizeof(type)) { \
- unsafe_put_user(*(type *)src,(type __user *)dst,label); \
- dst += sizeof(type); \
- src += sizeof(type); \
- len -= sizeof(type); \
+#define unsafe_copy_loop(dst, src, len, type, label) \
+ while (len >= sizeof(type)) { \
+ unsafe_put_user(*(type *)(src),(type __user *)(dst),label); \
+ dst += sizeof(type); \
+ src += sizeof(type); \
+ len -= sizeof(type); \
}
#define unsafe_copy_to_user(_dst,_src,_len,label) \
@@ -523,5 +523,21 @@ do { \
unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u8, label); \
} while (0)
+#define HAVE_GET_KERNEL_NOFAULT
+
+#define __get_kernel_nofault(dst, src, type, err_label) \
+do { \
+ int __kr_err; \
+ \
+ __get_user_size(*((type *)(dst)), (__force type __user *)(src), \
+ sizeof(type), __kr_err); \
+ if (unlikely(__kr_err)) \
+ goto err_label; \
+} while (0)
+
+#define __put_kernel_nofault(dst, src, type, err_label) \
+ __put_user_size(*((type *)(src)), (__force type __user *)(dst), \
+ sizeof(type), err_label)
+
#endif /* _ASM_X86_UACCESS_H */
diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h
index 499578f7e6d7..70fc159ebe69 100644
--- a/arch/x86/include/asm/unwind.h
+++ b/arch/x86/include/asm/unwind.h
@@ -19,7 +19,7 @@ struct unwind_state {
#if defined(CONFIG_UNWINDER_ORC)
bool signal, full_regs;
unsigned long sp, bp, ip;
- struct pt_regs *regs;
+ struct pt_regs *regs, *prev_regs;
#elif defined(CONFIG_UNWINDER_FRAME_POINTER)
bool got_irq;
unsigned long *bp, *orig_sp, ip;
diff --git a/arch/x86/include/asm/unwind_hints.h b/arch/x86/include/asm/unwind_hints.h
index f5e2eb12cb71..7d903fdb3f43 100644
--- a/arch/x86/include/asm/unwind_hints.h
+++ b/arch/x86/include/asm/unwind_hints.h
@@ -86,32 +86,15 @@
UNWIND_HINT sp_offset=\sp_offset
.endm
-.macro UNWIND_HINT_SAVE
- UNWIND_HINT type=UNWIND_HINT_TYPE_SAVE
-.endm
-
-.macro UNWIND_HINT_RESTORE
- UNWIND_HINT type=UNWIND_HINT_TYPE_RESTORE
+/*
+ * RET_OFFSET: Used on instructions that terminate a function; mostly RETURN
+ * and sibling calls. On these, sp_offset denotes the expected offset from
+ * initial_func_cfi.
+ */
+.macro UNWIND_HINT_RET_OFFSET sp_offset=8
+ UNWIND_HINT type=UNWIND_HINT_TYPE_RET_OFFSET sp_offset=\sp_offset
.endm
-#else /* !__ASSEMBLY__ */
-
-#define UNWIND_HINT(sp_reg, sp_offset, type, end) \
- "987: \n\t" \
- ".pushsection .discard.unwind_hints\n\t" \
- /* struct unwind_hint */ \
- ".long 987b - .\n\t" \
- ".short " __stringify(sp_offset) "\n\t" \
- ".byte " __stringify(sp_reg) "\n\t" \
- ".byte " __stringify(type) "\n\t" \
- ".byte " __stringify(end) "\n\t" \
- ".balign 4 \n\t" \
- ".popsection\n\t"
-
-#define UNWIND_HINT_SAVE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_SAVE, 0)
-
-#define UNWIND_HINT_RESTORE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_RESTORE, 0)
-
#endif /* __ASSEMBLY__ */
#endif /* _ASM_X86_UNWIND_HINTS_H */
diff --git a/arch/x86/include/asm/uv/bios.h b/arch/x86/include/asm/uv/bios.h
index 389174eaec79..2fcc3ac12e76 100644
--- a/arch/x86/include/asm/uv/bios.h
+++ b/arch/x86/include/asm/uv/bios.h
@@ -123,12 +123,6 @@ enum uv_memprotect {
UV_MEMPROT_ALLOW_RW
};
-/*
- * bios calls have 6 parameters
- */
-extern s64 uv_bios_call(enum uv_bios_cmd, u64, u64, u64, u64, u64);
-extern s64 uv_bios_call_irqsave(enum uv_bios_cmd, u64, u64, u64, u64, u64);
-
extern s64 uv_bios_get_sn_info(int, int *, long *, long *, long *, long *);
extern s64 uv_bios_freq_base(u64, u64 *);
extern int uv_bios_mq_watchlist_alloc(unsigned long, unsigned int,
@@ -146,7 +140,6 @@ extern long sn_partition_id;
extern long sn_coherency_id;
extern long sn_region_size;
extern long system_serial_number;
-#define uv_partition_coherence_id() (sn_coherency_id)
extern struct kobject *sgi_uv_kobj; /* /sys/firmware/sgi_uv */
diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h
index 45ea95ce79b4..3db85626048f 100644
--- a/arch/x86/include/asm/uv/uv.h
+++ b/arch/x86/include/asm/uv/uv.h
@@ -8,6 +8,7 @@ enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC};
struct cpumask;
struct mm_struct;
+struct flush_tlb_info;
#ifdef CONFIG_X86_UV
#include <linux/efi.h>
@@ -31,7 +32,6 @@ static inline bool is_early_uv_system(void)
}
extern int is_uv_system(void);
extern int is_uv_hubbed(int uvtype);
-extern int is_uv_hubless(int uvtype);
extern void uv_cpu_init(void);
extern void uv_nmi_init(void);
extern void uv_system_init(void);
@@ -44,7 +44,6 @@ static inline enum uv_system_type get_uv_system_type(void) { return UV_NONE; }
static inline bool is_early_uv_system(void) { return 0; }
static inline int is_uv_system(void) { return 0; }
static inline int is_uv_hubbed(int uv) { return 0; }
-static inline int is_uv_hubless(int uv) { return 0; }
static inline void uv_cpu_init(void) { }
static inline void uv_system_init(void) { }
static inline const struct cpumask *
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 13687bf0e0a9..f1188bd47658 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -12,6 +12,8 @@
#define _ASM_X86_UV_UV_BAU_H
#include <linux/bitmap.h>
+#include <asm/idtentry.h>
+
#define BITSPERBYTE 8
/*
@@ -799,12 +801,6 @@ static inline void bau_cpubits_clear(struct bau_local_cpumask *dstp, int nbits)
bitmap_zero(&dstp->bits, nbits);
}
-extern void uv_bau_message_intr1(void);
-#ifdef CONFIG_TRACING
-#define trace_uv_bau_message_intr1 uv_bau_message_intr1
-#endif
-extern void uv_bau_timeout_intr1(void);
-
struct atomic_short {
short counter;
};
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 950cd1395d5d..60ca0afdeaf9 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -219,20 +219,6 @@ static inline struct uv_hub_info_s *uv_cpu_hub_info(int cpu)
return (struct uv_hub_info_s *)uv_cpu_info_per(cpu)->p_uv_hub_info;
}
-#define UV_HUB_INFO_VERSION 0x7150
-extern int uv_hub_info_version(void);
-static inline int uv_hub_info_check(int version)
-{
- if (uv_hub_info_version() == version)
- return 0;
-
- pr_crit("UV: uv_hub_info version(%x) mismatch, expecting(%x)\n",
- uv_hub_info_version(), version);
-
- BUG(); /* Catastrophic - cannot continue on unknown UV system */
-}
-#define _uv_hub_info_check() uv_hub_info_check(UV_HUB_INFO_VERSION)
-
/*
* HUB revision ranges for each UV HUB architecture.
* This is a software convention - NOT the hardware revision numbers in
@@ -244,51 +230,32 @@ static inline int uv_hub_info_check(int version)
#define UV4_HUB_REVISION_BASE 7
#define UV4A_HUB_REVISION_BASE 8 /* UV4 (fixed) rev 2 */
-/* WARNING: UVx_HUB_IS_SUPPORTED defines are deprecated and will be removed */
static inline int is_uv1_hub(void)
{
-#ifdef UV1_HUB_IS_SUPPORTED
return is_uv_hubbed(uv(1));
-#else
- return 0;
-#endif
}
static inline int is_uv2_hub(void)
{
-#ifdef UV2_HUB_IS_SUPPORTED
return is_uv_hubbed(uv(2));
-#else
- return 0;
-#endif
}
static inline int is_uv3_hub(void)
{
-#ifdef UV3_HUB_IS_SUPPORTED
return is_uv_hubbed(uv(3));
-#else
- return 0;
-#endif
}
/* First test "is UV4A", then "is UV4" */
static inline int is_uv4a_hub(void)
{
-#ifdef UV4A_HUB_IS_SUPPORTED
if (is_uv_hubbed(uv(4)))
return (uv_hub_info->hub_revision == UV4A_HUB_REVISION_BASE);
-#endif
return 0;
}
static inline int is_uv4_hub(void)
{
-#ifdef UV4_HUB_IS_SUPPORTED
return is_uv_hubbed(uv(4));
-#else
- return 0;
-#endif
}
static inline int is_uvx_hub(void)
@@ -692,7 +659,6 @@ static inline int uv_cpu_blade_processor_id(int cpu)
{
return uv_cpu_info_per(cpu)->blade_cpu_id;
}
-#define _uv_cpu_blade_processor_id 1 /* indicate function available */
/* Blade number to Node number (UV1..UV4 is 1:1) */
static inline int uv_blade_to_node(int blade)
@@ -856,26 +822,6 @@ static inline void uv_set_cpu_scir_bits(int cpu, unsigned char value)
}
extern unsigned int uv_apicid_hibits;
-static unsigned long uv_hub_ipi_value(int apicid, int vector, int mode)
-{
- apicid |= uv_apicid_hibits;
- return (1UL << UVH_IPI_INT_SEND_SHFT) |
- ((apicid) << UVH_IPI_INT_APIC_ID_SHFT) |
- (mode << UVH_IPI_INT_DELIVERY_MODE_SHFT) |
- (vector << UVH_IPI_INT_VECTOR_SHFT);
-}
-
-static inline void uv_hub_send_ipi(int pnode, int apicid, int vector)
-{
- unsigned long val;
- unsigned long dmode = dest_Fixed;
-
- if (vector == NMI_VECTOR)
- dmode = dest_NMI;
-
- val = uv_hub_ipi_value(apicid, vector, dmode);
- uv_write_global_mmr64(pnode, UVH_IPI_INT, val);
-}
/*
* Get the minimum revision number of the hub chips within the partition.
diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h
index 62c79e26a59a..9ee5ed6e8b34 100644
--- a/arch/x86/include/asm/uv/uv_mmrs.h
+++ b/arch/x86/include/asm/uv/uv_mmrs.h
@@ -99,13 +99,6 @@
#define UV3_HUB_PART_NUMBER_X 0x4321
#define UV4_HUB_PART_NUMBER 0x99a1
-/* Compat: Indicate which UV Hubs are supported. */
-#define UV1_HUB_IS_SUPPORTED 1
-#define UV2_HUB_IS_SUPPORTED 1
-#define UV3_HUB_IS_SUPPORTED 1
-#define UV4_HUB_IS_SUPPORTED 1
-#define UV4A_HUB_IS_SUPPORTED 1
-
/* Error function to catch undefined references */
extern unsigned long uv_undefined(char *str);
diff --git a/arch/x86/include/asm/vermagic.h b/arch/x86/include/asm/vermagic.h
new file mode 100644
index 000000000000..75884d2cdec3
--- /dev/null
+++ b/arch/x86/include/asm/vermagic.h
@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_VERMAGIC_H
+#define _ASM_VERMAGIC_H
+
+#ifdef CONFIG_X86_64
+/* X86_64 does not define MODULE_PROC_FAMILY */
+#elif defined CONFIG_M486SX
+#define MODULE_PROC_FAMILY "486SX "
+#elif defined CONFIG_M486
+#define MODULE_PROC_FAMILY "486 "
+#elif defined CONFIG_M586
+#define MODULE_PROC_FAMILY "586 "
+#elif defined CONFIG_M586TSC
+#define MODULE_PROC_FAMILY "586TSC "
+#elif defined CONFIG_M586MMX
+#define MODULE_PROC_FAMILY "586MMX "
+#elif defined CONFIG_MCORE2
+#define MODULE_PROC_FAMILY "CORE2 "
+#elif defined CONFIG_MATOM
+#define MODULE_PROC_FAMILY "ATOM "
+#elif defined CONFIG_M686
+#define MODULE_PROC_FAMILY "686 "
+#elif defined CONFIG_MPENTIUMII
+#define MODULE_PROC_FAMILY "PENTIUMII "
+#elif defined CONFIG_MPENTIUMIII
+#define MODULE_PROC_FAMILY "PENTIUMIII "
+#elif defined CONFIG_MPENTIUMM
+#define MODULE_PROC_FAMILY "PENTIUMM "
+#elif defined CONFIG_MPENTIUM4
+#define MODULE_PROC_FAMILY "PENTIUM4 "
+#elif defined CONFIG_MK6
+#define MODULE_PROC_FAMILY "K6 "
+#elif defined CONFIG_MK7
+#define MODULE_PROC_FAMILY "K7 "
+#elif defined CONFIG_MK8
+#define MODULE_PROC_FAMILY "K8 "
+#elif defined CONFIG_MELAN
+#define MODULE_PROC_FAMILY "ELAN "
+#elif defined CONFIG_MCRUSOE
+#define MODULE_PROC_FAMILY "CRUSOE "
+#elif defined CONFIG_MEFFICEON
+#define MODULE_PROC_FAMILY "EFFICEON "
+#elif defined CONFIG_MWINCHIPC6
+#define MODULE_PROC_FAMILY "WINCHIPC6 "
+#elif defined CONFIG_MWINCHIP3D
+#define MODULE_PROC_FAMILY "WINCHIP3D "
+#elif defined CONFIG_MCYRIXIII
+#define MODULE_PROC_FAMILY "CYRIXIII "
+#elif defined CONFIG_MVIAC3_2
+#define MODULE_PROC_FAMILY "VIAC3-2 "
+#elif defined CONFIG_MVIAC7
+#define MODULE_PROC_FAMILY "VIAC7 "
+#elif defined CONFIG_MGEODEGX1
+#define MODULE_PROC_FAMILY "GEODEGX1 "
+#elif defined CONFIG_MGEODE_LX
+#define MODULE_PROC_FAMILY "GEODE "
+#else
+#error unknown processor family
+#endif
+
+#ifdef CONFIG_X86_32
+# define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY
+#else
+# define MODULE_ARCH_VERMAGIC ""
+#endif
+
+#endif /* _ASM_VERMAGIC_H */
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 5e090d1f03f8..cd7de4b401fe 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -527,10 +527,12 @@ struct vmx_msr_entry {
/*
* Exit Qualifications for entry failure during or after loading guest state
*/
-#define ENTRY_FAIL_DEFAULT 0
-#define ENTRY_FAIL_PDPTE 2
-#define ENTRY_FAIL_NMI 3
-#define ENTRY_FAIL_VMCS_LINK_PTR 4
+enum vm_entry_failure_code {
+ ENTRY_FAIL_DEFAULT = 0,
+ ENTRY_FAIL_PDPTE = 2,
+ ENTRY_FAIL_NMI = 3,
+ ENTRY_FAIL_VMCS_LINK_PTR = 4,
+};
/*
* Exit Qualifications for EPT Violations
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 96d9cd208610..6807153c0410 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -50,14 +50,12 @@ struct x86_init_resources {
* @pre_vector_init: init code to run before interrupt vectors
* are set up.
* @intr_init: interrupt init code
- * @trap_init: platform specific trap setup
* @intr_mode_select: interrupt delivery mode selection
* @intr_mode_init: interrupt delivery mode setup
*/
struct x86_init_irqs {
void (*pre_vector_init)(void);
void (*intr_init)(void);
- void (*trap_init)(void);
void (*intr_mode_select)(void);
void (*intr_mode_init)(void);
};
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index d50c7b747d8b..ba4c1b15908b 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -38,11 +38,11 @@
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/types.h>
+#include <linux/pgtable.h>
#include <trace/events/xen.h>
#include <asm/page.h>
-#include <asm/pgtable.h>
#include <asm/smap.h>
#include <asm/nospec-branch.h>
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 790ce08e41f2..5941e18edd5a 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -11,7 +11,6 @@
#include <asm/extable.h>
#include <asm/page.h>
-#include <asm/pgtable.h>
#include <xen/interface/xen.h>
#include <xen/interface/grant_table.h>
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 3f3f780c8c65..17c5a038f42d 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -385,32 +385,48 @@ struct kvm_sync_regs {
#define KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT (1 << 4)
#define KVM_STATE_NESTED_FORMAT_VMX 0
-#define KVM_STATE_NESTED_FORMAT_SVM 1 /* unused */
+#define KVM_STATE_NESTED_FORMAT_SVM 1
#define KVM_STATE_NESTED_GUEST_MODE 0x00000001
#define KVM_STATE_NESTED_RUN_PENDING 0x00000002
#define KVM_STATE_NESTED_EVMCS 0x00000004
#define KVM_STATE_NESTED_MTF_PENDING 0x00000008
+#define KVM_STATE_NESTED_GIF_SET 0x00000100
#define KVM_STATE_NESTED_SMM_GUEST_MODE 0x00000001
#define KVM_STATE_NESTED_SMM_VMXON 0x00000002
#define KVM_STATE_NESTED_VMX_VMCS_SIZE 0x1000
+#define KVM_STATE_NESTED_SVM_VMCB_SIZE 0x1000
+
+#define KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE 0x00000001
+
struct kvm_vmx_nested_state_data {
__u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE];
__u8 shadow_vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE];
};
struct kvm_vmx_nested_state_hdr {
+ __u32 flags;
__u64 vmxon_pa;
__u64 vmcs12_pa;
+ __u64 preemption_timer_deadline;
struct {
__u16 flags;
} smm;
};
+struct kvm_svm_nested_state_data {
+ /* Save area only used if KVM_STATE_NESTED_RUN_PENDING. */
+ __u8 vmcb12[KVM_STATE_NESTED_SVM_VMCB_SIZE];
+};
+
+struct kvm_svm_nested_state_hdr {
+ __u64 vmcb_pa;
+};
+
/* for KVM_CAP_NESTED_STATE */
struct kvm_nested_state {
__u16 flags;
@@ -419,6 +435,7 @@ struct kvm_nested_state {
union {
struct kvm_vmx_nested_state_hdr vmx;
+ struct kvm_svm_nested_state_hdr svm;
/* Pad the header to 128 bytes. */
__u8 pad[120];
@@ -431,6 +448,7 @@ struct kvm_nested_state {
*/
union {
struct kvm_vmx_nested_state_data vmx[0];
+ struct kvm_svm_nested_state_data svm[0];
} data;
};
diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index 2a8e0b6b9805..812e9b4c1114 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -31,6 +31,7 @@
#define KVM_FEATURE_PV_SEND_IPI 11
#define KVM_FEATURE_POLL_CONTROL 12
#define KVM_FEATURE_PV_SCHED_YIELD 13
+#define KVM_FEATURE_ASYNC_PF_INT 14
#define KVM_HINTS_REALTIME 0
@@ -50,6 +51,8 @@
#define MSR_KVM_STEAL_TIME 0x4b564d03
#define MSR_KVM_PV_EOI_EN 0x4b564d04
#define MSR_KVM_POLL_CONTROL 0x4b564d05
+#define MSR_KVM_ASYNC_PF_INT 0x4b564d06
+#define MSR_KVM_ASYNC_PF_ACK 0x4b564d07
struct kvm_steal_time {
__u64 steal;
@@ -81,6 +84,11 @@ struct kvm_clock_pairing {
#define KVM_ASYNC_PF_ENABLED (1 << 0)
#define KVM_ASYNC_PF_SEND_ALWAYS (1 << 1)
#define KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT (1 << 2)
+#define KVM_ASYNC_PF_DELIVERY_AS_INT (1 << 3)
+
+/* MSR_KVM_ASYNC_PF_INT */
+#define KVM_ASYNC_PF_VEC_MASK GENMASK(7, 0)
+
/* Operations for KVM_HC_MMU_OP */
#define KVM_MMU_OP_WRITE_PTE 1
@@ -112,8 +120,13 @@ struct kvm_mmu_op_release_pt {
#define KVM_PV_REASON_PAGE_READY 2
struct kvm_vcpu_pv_apf_data {
- __u32 reason;
- __u8 pad[60];
+ /* Used for 'page not present' events delivered via #PF */
+ __u32 flags;
+
+ /* Used for 'page ready' events delivered via interrupt notification */
+ __u32 token;
+
+ __u8 pad[56];
__u32 enabled;
};
diff --git a/arch/x86/include/uapi/asm/unistd.h b/arch/x86/include/uapi/asm/unistd.h
index 196fdd02b8b1..be5e2e747f50 100644
--- a/arch/x86/include/uapi/asm/unistd.h
+++ b/arch/x86/include/uapi/asm/unistd.h
@@ -2,8 +2,15 @@
#ifndef _UAPI_ASM_X86_UNISTD_H
#define _UAPI_ASM_X86_UNISTD_H
-/* x32 syscall flag bit */
-#define __X32_SYSCALL_BIT 0x40000000UL
+/*
+ * x32 syscall flag bit. Some user programs expect syscall NR macros
+ * and __X32_SYSCALL_BIT to have type int, even though syscall numbers
+ * are, for practical purposes, unsigned long.
+ *
+ * Fortunately, expressions like (nr & ~__X32_SYSCALL_BIT) do the right
+ * thing regardless.
+ */
+#define __X32_SYSCALL_BIT 0x40000000
#ifndef __KERNEL__
# ifdef __i386__
diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h
index e95b72ec19bc..b8ff9e8ac0d5 100644
--- a/arch/x86/include/uapi/asm/vmx.h
+++ b/arch/x86/include/uapi/asm/vmx.h
@@ -150,6 +150,9 @@
{ EXIT_REASON_UMWAIT, "UMWAIT" }, \
{ EXIT_REASON_TPAUSE, "TPAUSE" }
+#define VMX_EXIT_REASON_FLAGS \
+ { VMX_EXIT_REASONS_FAILED_VMENTRY, "FAILED_VMENTRY" }
+
#define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1
#define VMX_ABORT_LOAD_HOST_PDPTE_FAIL 2
#define VMX_ABORT_LOAD_HOST_MSR_FAIL 4