summaryrefslogtreecommitdiffstats
path: root/arch/x86/include/asm
diff options
context:
space:
mode:
Diffstat (limited to '')
-rw-r--r--arch/x86/include/asm/acpi.h2
-rw-r--r--arch/x86/include/asm/alternative.h14
-rw-r--r--arch/x86/include/asm/apic.h8
-rw-r--r--arch/x86/include/asm/asm.h3
-rw-r--r--arch/x86/include/asm/atomic.h12
-rw-r--r--arch/x86/include/asm/atomic64_32.h79
-rw-r--r--arch/x86/include/asm/atomic64_64.h12
-rw-r--r--arch/x86/include/asm/barrier.h24
-rw-r--r--arch/x86/include/asm/bitops.h10
-rw-r--r--arch/x86/include/asm/boot.h5
-rw-r--r--arch/x86/include/asm/cmpxchg_32.h203
-rw-r--r--arch/x86/include/asm/cmpxchg_64.h6
-rw-r--r--arch/x86/include/asm/cpu_device_id.h8
-rw-r--r--arch/x86/include/asm/cpufeature.h16
-rw-r--r--arch/x86/include/asm/extable_fixup_types.h2
-rw-r--r--arch/x86/include/asm/fb.h19
-rw-r--r--arch/x86/include/asm/fpu.h13
-rw-r--r--arch/x86/include/asm/fpu/api.h3
-rw-r--r--arch/x86/include/asm/fpu/types.h6
-rw-r--r--arch/x86/include/asm/hardirq.h6
-rw-r--r--arch/x86/include/asm/ia32.h11
-rw-r--r--arch/x86/include/asm/ia32_unistd.h12
-rw-r--r--arch/x86/include/asm/idtentry.h6
-rw-r--r--arch/x86/include/asm/inat.h17
-rw-r--r--arch/x86/include/asm/insn.h32
-rw-r--r--arch/x86/include/asm/intel-family.h84
-rw-r--r--arch/x86/include/asm/io.h18
-rw-r--r--arch/x86/include/asm/irq_remapping.h7
-rw-r--r--arch/x86/include/asm/irq_vectors.h8
-rw-r--r--arch/x86/include/asm/kexec.h13
-rw-r--r--arch/x86/include/asm/kvm-x86-ops.h2
-rw-r--r--arch/x86/include/asm/kvm_host.h67
-rw-r--r--arch/x86/include/asm/mce.h2
-rw-r--r--arch/x86/include/asm/mpspec.h6
-rw-r--r--arch/x86/include/asm/msr-index.h9
-rw-r--r--arch/x86/include/asm/page_types.h8
-rw-r--r--arch/x86/include/asm/percpu.h127
-rw-r--r--arch/x86/include/asm/pgtable.h20
-rw-r--r--arch/x86/include/asm/pgtable_64.h1
-rw-r--r--arch/x86/include/asm/posted_intr.h118
-rw-r--r--arch/x86/include/asm/processor.h32
-rw-r--r--arch/x86/include/asm/prom.h9
-rw-r--r--arch/x86/include/asm/qspinlock.h13
-rw-r--r--arch/x86/include/asm/qspinlock_paravirt.h7
-rw-r--r--arch/x86/include/asm/seccomp.h2
-rw-r--r--arch/x86/include/asm/sev-common.h8
-rw-r--r--arch/x86/include/asm/sev.h2
-rw-r--r--arch/x86/include/asm/shstk.h2
-rw-r--r--arch/x86/include/asm/special_insns.h8
-rw-r--r--arch/x86/include/asm/string_64.h45
-rw-r--r--arch/x86/include/asm/text-patching.h2
-rw-r--r--arch/x86/include/asm/vdso/gettimeofday.h44
-rw-r--r--arch/x86/include/asm/video.h21
-rw-r--r--arch/x86/include/asm/vm86.h2
-rw-r--r--arch/x86/include/asm/vmx.h13
-rw-r--r--arch/x86/include/asm/vmxfeatures.h2
56 files changed, 792 insertions, 439 deletions
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index f896eed451..5af926c050 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -56,6 +56,8 @@ static inline void disable_acpi(void)
extern int acpi_gsi_to_irq(u32 gsi, unsigned int *irq);
+extern int acpi_blacklisted(void);
+
static inline void acpi_noirq_set(void) { acpi_noirq = 1; }
static inline void acpi_disable_pci(void)
{
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 0cb2396de0..ba99ef75f5 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -286,20 +286,6 @@ static inline int alternatives_text_reserved(void *start, void *end)
asm_inline volatile (ALTERNATIVE(oldinstr, newinstr, ft_flags) \
: : "i" (0), ## input)
-/*
- * This is similar to alternative_input. But it has two features and
- * respective instructions.
- *
- * If CPU has feature2, newinstr2 is used.
- * Otherwise, if CPU has feature1, newinstr1 is used.
- * Otherwise, oldinstr is used.
- */
-#define alternative_input_2(oldinstr, newinstr1, ft_flags1, newinstr2, \
- ft_flags2, input...) \
- asm_inline volatile(ALTERNATIVE_2(oldinstr, newinstr1, ft_flags1, \
- newinstr2, ft_flags2) \
- : : "i" (0), ## input)
-
/* Like alternative_input, but with a single output argument */
#define alternative_io(oldinstr, newinstr, ft_flags, output, input...) \
asm_inline volatile (ALTERNATIVE(oldinstr, newinstr, ft_flags) \
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index e6ab0cf15e..9327eb00e9 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -14,6 +14,7 @@
#include <asm/msr.h>
#include <asm/hardirq.h>
#include <asm/io.h>
+#include <asm/posted_intr.h>
#define ARCH_APICTIMER_STOPS_ON_C3 1
@@ -92,7 +93,7 @@ static inline void native_apic_mem_write(u32 reg, u32 v)
{
volatile u32 *addr = (volatile u32 *)(APIC_BASE + reg);
- alternative_io("movl %0, %P1", "xchgl %0, %P1", X86_BUG_11AP,
+ alternative_io("movl %0, %1", "xchgl %0, %1", X86_BUG_11AP,
ASM_OUTPUT2("=r" (v), "=m" (*addr)),
ASM_OUTPUT2("0" (v), "m" (*addr)));
}
@@ -500,6 +501,11 @@ static inline bool lapic_vector_set_in_irr(unsigned int vector)
return !!(irr & (1U << (vector % 32)));
}
+static inline bool is_vector_pending(unsigned int vector)
+{
+ return lapic_vector_set_in_irr(vector) || pi_pending_this_cpu(vector);
+}
+
/*
* Warm reset vector position:
*/
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index ca8eed1d49..2bec0c89a9 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -229,9 +229,6 @@ register unsigned long current_stack_pointer asm(_ASM_SP);
#define _ASM_EXTABLE_UA(from, to) \
_ASM_EXTABLE_TYPE(from, to, EX_TYPE_UACCESS)
-#define _ASM_EXTABLE_CPY(from, to) \
- _ASM_EXTABLE_TYPE(from, to, EX_TYPE_COPY)
-
#define _ASM_EXTABLE_FAULT(from, to) \
_ASM_EXTABLE_TYPE(from, to, EX_TYPE_FAULT)
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 55a55ec043..55b4d24356 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -86,11 +86,7 @@ static __always_inline int arch_atomic_add_return(int i, atomic_t *v)
}
#define arch_atomic_add_return arch_atomic_add_return
-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
+#define arch_atomic_sub_return(i, v) arch_atomic_add_return(-(i), v)
static __always_inline int arch_atomic_fetch_add(int i, atomic_t *v)
{
@@ -98,11 +94,7 @@ static __always_inline int arch_atomic_fetch_add(int i, atomic_t *v)
}
#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
+#define arch_atomic_fetch_sub(i, v) arch_atomic_fetch_add(-(i), v)
static __always_inline int arch_atomic_cmpxchg(atomic_t *v, int old, int new)
{
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index d510405e4e..8db2ec4d6c 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -14,6 +14,32 @@ typedef struct {
#define ATOMIC64_INIT(val) { (val) }
+/*
+ * Read an atomic64_t non-atomically.
+ *
+ * This is intended to be used in cases where a subsequent atomic operation
+ * will handle the torn value, and can be used to prime the first iteration
+ * of unconditional try_cmpxchg() loops, e.g.:
+ *
+ * s64 val = arch_atomic64_read_nonatomic(v);
+ * do { } while (!arch_atomic64_try_cmpxchg(v, &val, val OP i);
+ *
+ * This is NOT safe to use where the value is not always checked by a
+ * subsequent atomic operation, such as in conditional try_cmpxchg() loops
+ * that can break before the atomic operation, e.g.:
+ *
+ * s64 val = arch_atomic64_read_nonatomic(v);
+ * do {
+ * if (condition(val))
+ * break;
+ * } while (!arch_atomic64_try_cmpxchg(v, &val, val OP i);
+ */
+static __always_inline s64 arch_atomic64_read_nonatomic(const atomic64_t *v)
+{
+ /* See comment in arch_atomic_read(). */
+ return __READ_ONCE(v->counter);
+}
+
#define __ATOMIC64_DECL(sym) void atomic64_##sym(atomic64_t *, ...)
#ifndef ATOMIC64_EXPORT
#define ATOMIC64_DECL_ONE __ATOMIC64_DECL
@@ -61,12 +87,18 @@ ATOMIC64_DECL(add_unless);
#undef __ATOMIC64_DECL
#undef ATOMIC64_EXPORT
-static __always_inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 o, s64 n)
+static __always_inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new)
{
- return arch_cmpxchg64(&v->counter, o, n);
+ return arch_cmpxchg64(&v->counter, old, new);
}
#define arch_atomic64_cmpxchg arch_atomic64_cmpxchg
+static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new)
+{
+ return arch_try_cmpxchg64(&v->counter, old, new);
+}
+#define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg
+
static __always_inline s64 arch_atomic64_xchg(atomic64_t *v, s64 n)
{
s64 o;
@@ -195,69 +227,62 @@ static __always_inline s64 arch_atomic64_dec_if_positive(atomic64_t *v)
static __always_inline void arch_atomic64_and(s64 i, atomic64_t *v)
{
- s64 old, c = 0;
+ s64 val = arch_atomic64_read_nonatomic(v);
- while ((old = arch_atomic64_cmpxchg(v, c, c & i)) != c)
- c = old;
+ do { } while (!arch_atomic64_try_cmpxchg(v, &val, val & i));
}
static __always_inline s64 arch_atomic64_fetch_and(s64 i, atomic64_t *v)
{
- s64 old, c = 0;
+ s64 val = arch_atomic64_read_nonatomic(v);
- while ((old = arch_atomic64_cmpxchg(v, c, c & i)) != c)
- c = old;
+ do { } while (!arch_atomic64_try_cmpxchg(v, &val, val & i));
- return old;
+ return val;
}
#define arch_atomic64_fetch_and arch_atomic64_fetch_and
static __always_inline void arch_atomic64_or(s64 i, atomic64_t *v)
{
- s64 old, c = 0;
+ s64 val = arch_atomic64_read_nonatomic(v);
- while ((old = arch_atomic64_cmpxchg(v, c, c | i)) != c)
- c = old;
+ do { } while (!arch_atomic64_try_cmpxchg(v, &val, val | i));
}
static __always_inline s64 arch_atomic64_fetch_or(s64 i, atomic64_t *v)
{
- s64 old, c = 0;
+ s64 val = arch_atomic64_read_nonatomic(v);
- while ((old = arch_atomic64_cmpxchg(v, c, c | i)) != c)
- c = old;
+ do { } while (!arch_atomic64_try_cmpxchg(v, &val, val | i));
- return old;
+ return val;
}
#define arch_atomic64_fetch_or arch_atomic64_fetch_or
static __always_inline void arch_atomic64_xor(s64 i, atomic64_t *v)
{
- s64 old, c = 0;
+ s64 val = arch_atomic64_read_nonatomic(v);
- while ((old = arch_atomic64_cmpxchg(v, c, c ^ i)) != c)
- c = old;
+ do { } while (!arch_atomic64_try_cmpxchg(v, &val, val ^ i));
}
static __always_inline s64 arch_atomic64_fetch_xor(s64 i, atomic64_t *v)
{
- s64 old, c = 0;
+ s64 val = arch_atomic64_read_nonatomic(v);
- while ((old = arch_atomic64_cmpxchg(v, c, c ^ i)) != c)
- c = old;
+ do { } while (!arch_atomic64_try_cmpxchg(v, &val, val ^ i));
- return old;
+ return val;
}
#define arch_atomic64_fetch_xor arch_atomic64_fetch_xor
static __always_inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v)
{
- s64 old, c = 0;
+ s64 val = arch_atomic64_read_nonatomic(v);
- while ((old = arch_atomic64_cmpxchg(v, c, c + i)) != c)
- c = old;
+ do { } while (!arch_atomic64_try_cmpxchg(v, &val, val + i));
- return old;
+ return val;
}
#define arch_atomic64_fetch_add arch_atomic64_fetch_add
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 3165c0feed..ae12acae5b 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -80,11 +80,7 @@ static __always_inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v)
}
#define arch_atomic64_add_return arch_atomic64_add_return
-static __always_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
+#define arch_atomic64_sub_return(i, v) arch_atomic64_add_return(-(i), v)
static __always_inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v)
{
@@ -92,11 +88,7 @@ static __always_inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v)
}
#define arch_atomic64_fetch_add arch_atomic64_fetch_add
-static __always_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
+#define arch_atomic64_fetch_sub(i, v) arch_atomic64_fetch_add(-(i), v)
static __always_inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new)
{
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 63bdc6b852..7b44b3c4cc 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -33,20 +33,16 @@
* Returns:
* 0 - (index < size)
*/
-static __always_inline unsigned long array_index_mask_nospec(unsigned long index,
- unsigned long size)
-{
- unsigned long mask;
-
- asm volatile ("cmp %1,%2; sbb %0,%0;"
- :"=r" (mask)
- :"g"(size),"r" (index)
- :"cc");
- return mask;
-}
-
-/* Override the default implementation from linux/nospec.h. */
-#define array_index_mask_nospec array_index_mask_nospec
+#define array_index_mask_nospec(idx,sz) ({ \
+ typeof((idx)+(sz)) __idx = (idx); \
+ typeof(__idx) __sz = (sz); \
+ unsigned long __mask; \
+ asm volatile ("cmp %1,%2; sbb %0,%0" \
+ :"=r" (__mask) \
+ :ASM_INPUT_G (__sz), \
+ "r" (__idx) \
+ :"cc"); \
+ __mask; })
/* Prevent speculative execution past this barrier. */
#define barrier_nospec() alternative("", "lfence", X86_FEATURE_LFENCE_RDTSC)
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 990eb686ca..b96d45944c 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -250,7 +250,7 @@ static __always_inline unsigned long variable__ffs(unsigned long word)
{
asm("rep; bsf %1,%0"
: "=r" (word)
- : "rm" (word));
+ : ASM_INPUT_RM (word));
return word;
}
@@ -297,7 +297,7 @@ static __always_inline unsigned long __fls(unsigned long word)
asm("bsr %1,%0"
: "=r" (word)
- : "rm" (word));
+ : ASM_INPUT_RM (word));
return word;
}
@@ -320,7 +320,7 @@ static __always_inline int variable_ffs(int x)
*/
asm("bsfl %1,%0"
: "=r" (r)
- : "rm" (x), "0" (-1));
+ : ASM_INPUT_RM (x), "0" (-1));
#elif defined(CONFIG_X86_CMOV)
asm("bsfl %1,%0\n\t"
"cmovzl %2,%0"
@@ -377,7 +377,7 @@ static __always_inline int fls(unsigned int x)
*/
asm("bsrl %1,%0"
: "=r" (r)
- : "rm" (x), "0" (-1));
+ : ASM_INPUT_RM (x), "0" (-1));
#elif defined(CONFIG_X86_CMOV)
asm("bsrl %1,%0\n\t"
"cmovzl %2,%0"
@@ -416,7 +416,7 @@ static __always_inline int fls64(__u64 x)
*/
asm("bsrq %1,%q0"
: "+r" (bitpos)
- : "rm" (x));
+ : ASM_INPUT_RM (x));
return bitpos + 1;
}
#else
diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h
index a3e0be0470..3e5b111e61 100644
--- a/arch/x86/include/asm/boot.h
+++ b/arch/x86/include/asm/boot.h
@@ -6,11 +6,6 @@
#include <asm/pgtable_types.h>
#include <uapi/asm/boot.h>
-/* Physical address where kernel should be loaded. */
-#define LOAD_PHYSICAL_ADDR ((CONFIG_PHYSICAL_START \
- + (CONFIG_PHYSICAL_ALIGN - 1)) \
- & ~(CONFIG_PHYSICAL_ALIGN - 1))
-
/* Minimum kernel alignment, as a power of two */
#ifdef CONFIG_X86_64
# define MIN_KERNEL_ALIGN_LG2 PMD_SHIFT
diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h
index b5731c51f0..62cef2113c 100644
--- a/arch/x86/include/asm/cmpxchg_32.h
+++ b/arch/x86/include/asm/cmpxchg_32.h
@@ -3,103 +3,148 @@
#define _ASM_X86_CMPXCHG_32_H
/*
- * Note: if you use set64_bit(), __cmpxchg64(), or their variants,
+ * Note: if you use __cmpxchg64(), or their variants,
* you need to test for the feature in boot_cpu_data.
*/
-#ifdef CONFIG_X86_CMPXCHG64
-#define arch_cmpxchg64(ptr, o, n) \
- ((__typeof__(*(ptr)))__cmpxchg64((ptr), (unsigned long long)(o), \
- (unsigned long long)(n)))
-#define arch_cmpxchg64_local(ptr, o, n) \
- ((__typeof__(*(ptr)))__cmpxchg64_local((ptr), (unsigned long long)(o), \
- (unsigned long long)(n)))
-#define arch_try_cmpxchg64(ptr, po, n) \
- __try_cmpxchg64((ptr), (unsigned long long *)(po), \
- (unsigned long long)(n))
-#endif
+union __u64_halves {
+ u64 full;
+ struct {
+ u32 low, high;
+ };
+};
+
+#define __arch_cmpxchg64(_ptr, _old, _new, _lock) \
+({ \
+ union __u64_halves o = { .full = (_old), }, \
+ n = { .full = (_new), }; \
+ \
+ asm volatile(_lock "cmpxchg8b %[ptr]" \
+ : [ptr] "+m" (*(_ptr)), \
+ "+a" (o.low), "+d" (o.high) \
+ : "b" (n.low), "c" (n.high) \
+ : "memory"); \
+ \
+ o.full; \
+})
+
+
+static __always_inline u64 __cmpxchg64(volatile u64 *ptr, u64 old, u64 new)
+{
+ return __arch_cmpxchg64(ptr, old, new, LOCK_PREFIX);
+}
-static inline u64 __cmpxchg64(volatile u64 *ptr, u64 old, u64 new)
+static __always_inline u64 __cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new)
{
- u64 prev;
- asm volatile(LOCK_PREFIX "cmpxchg8b %1"
- : "=A" (prev),
- "+m" (*ptr)
- : "b" ((u32)new),
- "c" ((u32)(new >> 32)),
- "0" (old)
- : "memory");
- return prev;
+ return __arch_cmpxchg64(ptr, old, new,);
}
-static inline u64 __cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new)
+#define __arch_try_cmpxchg64(_ptr, _oldp, _new, _lock) \
+({ \
+ union __u64_halves o = { .full = *(_oldp), }, \
+ n = { .full = (_new), }; \
+ bool ret; \
+ \
+ asm volatile(_lock "cmpxchg8b %[ptr]" \
+ CC_SET(e) \
+ : CC_OUT(e) (ret), \
+ [ptr] "+m" (*(_ptr)), \
+ "+a" (o.low), "+d" (o.high) \
+ : "b" (n.low), "c" (n.high) \
+ : "memory"); \
+ \
+ if (unlikely(!ret)) \
+ *(_oldp) = o.full; \
+ \
+ likely(ret); \
+})
+
+static __always_inline bool __try_cmpxchg64(volatile u64 *ptr, u64 *oldp, u64 new)
{
- u64 prev;
- asm volatile("cmpxchg8b %1"
- : "=A" (prev),
- "+m" (*ptr)
- : "b" ((u32)new),
- "c" ((u32)(new >> 32)),
- "0" (old)
- : "memory");
- return prev;
+ return __arch_try_cmpxchg64(ptr, oldp, new, LOCK_PREFIX);
}
-static inline bool __try_cmpxchg64(volatile u64 *ptr, u64 *pold, u64 new)
+static __always_inline bool __try_cmpxchg64_local(volatile u64 *ptr, u64 *oldp, u64 new)
{
- bool success;
- u64 old = *pold;
- asm volatile(LOCK_PREFIX "cmpxchg8b %[ptr]"
- CC_SET(z)
- : CC_OUT(z) (success),
- [ptr] "+m" (*ptr),
- "+A" (old)
- : "b" ((u32)new),
- "c" ((u32)(new >> 32))
- : "memory");
-
- if (unlikely(!success))
- *pold = old;
- return success;
+ return __arch_try_cmpxchg64(ptr, oldp, new,);
}
-#ifndef CONFIG_X86_CMPXCHG64
+#ifdef CONFIG_X86_CMPXCHG64
+
+#define arch_cmpxchg64 __cmpxchg64
+
+#define arch_cmpxchg64_local __cmpxchg64_local
+
+#define arch_try_cmpxchg64 __try_cmpxchg64
+
+#define arch_try_cmpxchg64_local __try_cmpxchg64_local
+
+#else
+
/*
* Building a kernel capable running on 80386 and 80486. It may be necessary
* to simulate the cmpxchg8b on the 80386 and 80486 CPU.
*/
-#define arch_cmpxchg64(ptr, o, n) \
-({ \
- __typeof__(*(ptr)) __ret; \
- __typeof__(*(ptr)) __old = (o); \
- __typeof__(*(ptr)) __new = (n); \
- alternative_io(LOCK_PREFIX_HERE \
- "call cmpxchg8b_emu", \
- "lock; cmpxchg8b (%%esi)" , \
- X86_FEATURE_CX8, \
- "=A" (__ret), \
- "S" ((ptr)), "0" (__old), \
- "b" ((unsigned int)__new), \
- "c" ((unsigned int)(__new>>32)) \
- : "memory"); \
- __ret; })
-
-
-#define arch_cmpxchg64_local(ptr, o, n) \
-({ \
- __typeof__(*(ptr)) __ret; \
- __typeof__(*(ptr)) __old = (o); \
- __typeof__(*(ptr)) __new = (n); \
- alternative_io("call cmpxchg8b_emu", \
- "cmpxchg8b (%%esi)" , \
- X86_FEATURE_CX8, \
- "=A" (__ret), \
- "S" ((ptr)), "0" (__old), \
- "b" ((unsigned int)__new), \
- "c" ((unsigned int)(__new>>32)) \
- : "memory"); \
- __ret; })
+#define __arch_cmpxchg64_emu(_ptr, _old, _new, _lock_loc, _lock) \
+({ \
+ union __u64_halves o = { .full = (_old), }, \
+ n = { .full = (_new), }; \
+ \
+ asm volatile(ALTERNATIVE(_lock_loc \
+ "call cmpxchg8b_emu", \
+ _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8) \
+ : "+a" (o.low), "+d" (o.high) \
+ : "b" (n.low), "c" (n.high), [ptr] "S" (_ptr) \
+ : "memory"); \
+ \
+ o.full; \
+})
+
+static __always_inline u64 arch_cmpxchg64(volatile u64 *ptr, u64 old, u64 new)
+{
+ return __arch_cmpxchg64_emu(ptr, old, new, LOCK_PREFIX_HERE, "lock; ");
+}
+#define arch_cmpxchg64 arch_cmpxchg64
+
+static __always_inline u64 arch_cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new)
+{
+ return __arch_cmpxchg64_emu(ptr, old, new, ,);
+}
+#define arch_cmpxchg64_local arch_cmpxchg64_local
+
+#define __arch_try_cmpxchg64_emu(_ptr, _oldp, _new, _lock_loc, _lock) \
+({ \
+ union __u64_halves o = { .full = *(_oldp), }, \
+ n = { .full = (_new), }; \
+ bool ret; \
+ \
+ asm volatile(ALTERNATIVE(_lock_loc \
+ "call cmpxchg8b_emu", \
+ _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8) \
+ CC_SET(e) \
+ : CC_OUT(e) (ret), \
+ "+a" (o.low), "+d" (o.high) \
+ : "b" (n.low), "c" (n.high), [ptr] "S" (_ptr) \
+ : "memory"); \
+ \
+ if (unlikely(!ret)) \
+ *(_oldp) = o.full; \
+ \
+ likely(ret); \
+})
+
+static __always_inline bool arch_try_cmpxchg64(volatile u64 *ptr, u64 *oldp, u64 new)
+{
+ return __arch_try_cmpxchg64_emu(ptr, oldp, new, LOCK_PREFIX_HERE, "lock; ");
+}
+#define arch_try_cmpxchg64 arch_try_cmpxchg64
+
+static __always_inline bool arch_try_cmpxchg64_local(volatile u64 *ptr, u64 *oldp, u64 new)
+{
+ return __arch_try_cmpxchg64_emu(ptr, oldp, new, ,);
+}
+#define arch_try_cmpxchg64_local arch_try_cmpxchg64_local
#endif
diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h
index c1d6cd58f8..5e241306db 100644
--- a/arch/x86/include/asm/cmpxchg_64.h
+++ b/arch/x86/include/asm/cmpxchg_64.h
@@ -20,6 +20,12 @@
arch_try_cmpxchg((ptr), (po), (n)); \
})
+#define arch_try_cmpxchg64_local(ptr, po, n) \
+({ \
+ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \
+ arch_try_cmpxchg_local((ptr), (po), (n)); \
+})
+
union __u128_halves {
u128 full;
struct {
diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h
index e8e3dbe7f1..b6325ee308 100644
--- a/arch/x86/include/asm/cpu_device_id.h
+++ b/arch/x86/include/asm/cpu_device_id.h
@@ -288,6 +288,14 @@ struct x86_cpu_desc {
.x86_microcode_rev = (revision), \
}
+#define AMD_CPU_DESC(fam, model, stepping, revision) { \
+ .x86_family = (fam), \
+ .x86_vendor = X86_VENDOR_AMD, \
+ .x86_model = (model), \
+ .x86_stepping = (stepping), \
+ .x86_microcode_rev = (revision), \
+}
+
extern const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match);
extern bool x86_cpu_has_min_microcode_rev(const struct x86_cpu_desc *table);
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 3508f3fc92..0b9611da6c 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -129,8 +129,7 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
#define this_cpu_has(bit) \
(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \
- x86_this_cpu_test_bit(bit, \
- (unsigned long __percpu *)&cpu_info.x86_capability))
+ x86_this_cpu_test_bit(bit, cpu_info.x86_capability))
/*
* This macro is for detection of features which need kernel
@@ -150,8 +149,12 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
extern void setup_clear_cpu_cap(unsigned int bit);
extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
-#define setup_force_cpu_cap(bit) do { \
- set_cpu_cap(&boot_cpu_data, bit); \
+#define setup_force_cpu_cap(bit) do { \
+ \
+ if (!boot_cpu_has(bit)) \
+ WARN_ON(alternatives_patched); \
+ \
+ set_cpu_cap(&boot_cpu_data, bit); \
set_bit(bit, (unsigned long *)cpu_caps_set); \
} while (0)
@@ -172,11 +175,10 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
*/
static __always_inline bool _static_cpu_has(u16 bit)
{
- asm goto(
- ALTERNATIVE_TERNARY("jmp 6f", %c[feature], "", "jmp %l[t_no]")
+ asm goto(ALTERNATIVE_TERNARY("jmp 6f", %c[feature], "", "jmp %l[t_no]")
".pushsection .altinstr_aux,\"ax\"\n"
"6:\n"
- " testb %[bitnum]," _ASM_RIP(%P[cap_byte]) "\n"
+ " testb %[bitnum], %a[cap_byte]\n"
" jnz %l[t_yes]\n"
" jmp %l[t_no]\n"
".popsection\n"
diff --git a/arch/x86/include/asm/extable_fixup_types.h b/arch/x86/include/asm/extable_fixup_types.h
index 7acf0383be..906b0d5541 100644
--- a/arch/x86/include/asm/extable_fixup_types.h
+++ b/arch/x86/include/asm/extable_fixup_types.h
@@ -36,7 +36,7 @@
#define EX_TYPE_DEFAULT 1
#define EX_TYPE_FAULT 2
#define EX_TYPE_UACCESS 3
-#define EX_TYPE_COPY 4
+/* unused, was: #define EX_TYPE_COPY 4 */
#define EX_TYPE_CLEAR_FS 5
#define EX_TYPE_FPU_RESTORE 6
#define EX_TYPE_BPF 7
diff --git a/arch/x86/include/asm/fb.h b/arch/x86/include/asm/fb.h
deleted file mode 100644
index c3b9582de7..0000000000
--- a/arch/x86/include/asm/fb.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_FB_H
-#define _ASM_X86_FB_H
-
-#include <asm/page.h>
-
-struct fb_info;
-
-pgprot_t pgprot_framebuffer(pgprot_t prot,
- unsigned long vm_start, unsigned long vm_end,
- unsigned long offset);
-#define pgprot_framebuffer pgprot_framebuffer
-
-int fb_is_primary_device(struct fb_info *info);
-#define fb_is_primary_device fb_is_primary_device
-
-#include <asm-generic/fb.h>
-
-#endif /* _ASM_X86_FB_H */
diff --git a/arch/x86/include/asm/fpu.h b/arch/x86/include/asm/fpu.h
new file mode 100644
index 0000000000..b2743fe193
--- /dev/null
+++ b/arch/x86/include/asm/fpu.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2023 SiFive
+ */
+
+#ifndef _ASM_X86_FPU_H
+#define _ASM_X86_FPU_H
+
+#include <asm/fpu/api.h>
+
+#define kernel_fpu_available() true
+
+#endif /* ! _ASM_X86_FPU_H */
diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index a2be3aefff..f86ad33355 100644
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -143,6 +143,9 @@ extern void fpstate_clear_xstate_component(struct fpstate *fps, unsigned int xfe
extern u64 xstate_get_guest_group_perm(void);
+extern void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr);
+
+
/* KVM specific functions */
extern bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu);
extern void fpu_free_guest_fpstate(struct fpu_guest *gfpu);
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index ace9aa3b78..eb17f31b06 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -2,8 +2,8 @@
/*
* FPU data structures:
*/
-#ifndef _ASM_X86_FPU_H
-#define _ASM_X86_FPU_H
+#ifndef _ASM_X86_FPU_TYPES_H
+#define _ASM_X86_FPU_TYPES_H
#include <asm/page_types.h>
@@ -596,4 +596,4 @@ struct fpu_state_config {
/* FPU state configuration information */
extern struct fpu_state_config fpu_kernel_cfg, fpu_user_cfg;
-#endif /* _ASM_X86_FPU_H */
+#endif /* _ASM_X86_FPU_TYPES_H */
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index fbc7722b87..c67fa6ad09 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -44,10 +44,16 @@ typedef struct {
unsigned int irq_hv_reenlightenment_count;
unsigned int hyperv_stimer0_count;
#endif
+#ifdef CONFIG_X86_POSTED_MSI
+ unsigned int posted_msi_notification_count;
+#endif
} ____cacheline_aligned irq_cpustat_t;
DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
+#ifdef CONFIG_X86_POSTED_MSI
+DECLARE_PER_CPU_ALIGNED(struct pi_desc, posted_msi_pi_desc);
+#endif
#define __ARCH_IRQ_STAT
#define inc_irq_stat(member) this_cpu_inc(irq_stat.member)
diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h
index 4212c00c97..9d69f3f8db 100644
--- a/arch/x86/include/asm/ia32.h
+++ b/arch/x86/include/asm/ia32.h
@@ -56,17 +56,6 @@ struct stat64 {
unsigned long long st_ino;
} __attribute__((packed));
-#define IA32_STACK_TOP IA32_PAGE_OFFSET
-
-#ifdef __KERNEL__
-struct linux_binprm;
-extern int ia32_setup_arg_pages(struct linux_binprm *bprm,
- unsigned long stack_top, int exec_stack);
-struct mm_struct;
-extern void ia32_pick_mmap_layout(struct mm_struct *mm);
-
-#endif
-
extern bool __ia32_enabled;
static __always_inline bool ia32_enabled(void)
diff --git a/arch/x86/include/asm/ia32_unistd.h b/arch/x86/include/asm/ia32_unistd.h
deleted file mode 100644
index aa065c94cc..0000000000
--- a/arch/x86/include/asm/ia32_unistd.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_IA32_UNISTD_H
-#define _ASM_X86_IA32_UNISTD_H
-
-/*
- * This file contains the system call numbers of the ia32 compat ABI,
- * this is for the kernel only.
- */
-#define __SYSCALL_ia32_NR(x) (x)
-#include <asm/unistd_32_ia32.h>
-
-#endif /* _ASM_X86_IA32_UNISTD_H */
diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index 749c7411d2..d4f24499b2 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -751,6 +751,12 @@ DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_NESTED_VECTOR, sysvec_kvm_posted_intr_nested
# define fred_sysvec_kvm_posted_intr_nested_ipi NULL
#endif
+# ifdef CONFIG_X86_POSTED_MSI
+DECLARE_IDTENTRY_SYSVEC(POSTED_MSI_NOTIFICATION_VECTOR, sysvec_posted_msi_notification);
+#else
+# define fred_sysvec_posted_msi_notification NULL
+# endif
+
#if IS_ENABLED(CONFIG_HYPERV)
DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_CALLBACK_VECTOR, sysvec_hyperv_callback);
DECLARE_IDTENTRY_SYSVEC(HYPERV_REENLIGHTENMENT_VECTOR, sysvec_hyperv_reenlightenment);
diff --git a/arch/x86/include/asm/inat.h b/arch/x86/include/asm/inat.h
index b56c574158..53e4015242 100644
--- a/arch/x86/include/asm/inat.h
+++ b/arch/x86/include/asm/inat.h
@@ -35,6 +35,8 @@
#define INAT_PFX_VEX2 13 /* 2-bytes VEX prefix */
#define INAT_PFX_VEX3 14 /* 3-bytes VEX prefix */
#define INAT_PFX_EVEX 15 /* EVEX prefix */
+/* x86-64 REX2 prefix */
+#define INAT_PFX_REX2 16 /* 0xD5 */
#define INAT_LSTPFX_MAX 3
#define INAT_LGCPFX_MAX 11
@@ -50,7 +52,7 @@
/* Legacy prefix */
#define INAT_PFX_OFFS 0
-#define INAT_PFX_BITS 4
+#define INAT_PFX_BITS 5
#define INAT_PFX_MAX ((1 << INAT_PFX_BITS) - 1)
#define INAT_PFX_MASK (INAT_PFX_MAX << INAT_PFX_OFFS)
/* Escape opcodes */
@@ -77,6 +79,9 @@
#define INAT_VEXOK (1 << (INAT_FLAG_OFFS + 5))
#define INAT_VEXONLY (1 << (INAT_FLAG_OFFS + 6))
#define INAT_EVEXONLY (1 << (INAT_FLAG_OFFS + 7))
+#define INAT_NO_REX2 (1 << (INAT_FLAG_OFFS + 8))
+#define INAT_REX2_VARIANT (1 << (INAT_FLAG_OFFS + 9))
+#define INAT_EVEX_SCALABLE (1 << (INAT_FLAG_OFFS + 10))
/* Attribute making macros for attribute tables */
#define INAT_MAKE_PREFIX(pfx) (pfx << INAT_PFX_OFFS)
#define INAT_MAKE_ESCAPE(esc) (esc << INAT_ESC_OFFS)
@@ -128,6 +133,11 @@ static inline int inat_is_rex_prefix(insn_attr_t attr)
return (attr & INAT_PFX_MASK) == INAT_PFX_REX;
}
+static inline int inat_is_rex2_prefix(insn_attr_t attr)
+{
+ return (attr & INAT_PFX_MASK) == INAT_PFX_REX2;
+}
+
static inline int inat_last_prefix_id(insn_attr_t attr)
{
if ((attr & INAT_PFX_MASK) > INAT_LSTPFX_MAX)
@@ -227,4 +237,9 @@ static inline int inat_must_evex(insn_attr_t attr)
{
return attr & INAT_EVEXONLY;
}
+
+static inline int inat_evex_scalable(insn_attr_t attr)
+{
+ return attr & INAT_EVEX_SCALABLE;
+}
#endif
diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
index 1b29f58f73..7152ea809e 100644
--- a/arch/x86/include/asm/insn.h
+++ b/arch/x86/include/asm/insn.h
@@ -112,10 +112,15 @@ struct insn {
#define X86_SIB_INDEX(sib) (((sib) & 0x38) >> 3)
#define X86_SIB_BASE(sib) ((sib) & 0x07)
-#define X86_REX_W(rex) ((rex) & 8)
-#define X86_REX_R(rex) ((rex) & 4)
-#define X86_REX_X(rex) ((rex) & 2)
-#define X86_REX_B(rex) ((rex) & 1)
+#define X86_REX2_M(rex) ((rex) & 0x80) /* REX2 M0 */
+#define X86_REX2_R(rex) ((rex) & 0x40) /* REX2 R4 */
+#define X86_REX2_X(rex) ((rex) & 0x20) /* REX2 X4 */
+#define X86_REX2_B(rex) ((rex) & 0x10) /* REX2 B4 */
+
+#define X86_REX_W(rex) ((rex) & 8) /* REX or REX2 W */
+#define X86_REX_R(rex) ((rex) & 4) /* REX or REX2 R3 */
+#define X86_REX_X(rex) ((rex) & 2) /* REX or REX2 X3 */
+#define X86_REX_B(rex) ((rex) & 1) /* REX or REX2 B3 */
/* VEX bit flags */
#define X86_VEX_W(vex) ((vex) & 0x80) /* VEX3 Byte2 */
@@ -161,6 +166,18 @@ static inline void insn_get_attribute(struct insn *insn)
/* Instruction uses RIP-relative addressing */
extern int insn_rip_relative(struct insn *insn);
+static inline int insn_is_rex2(struct insn *insn)
+{
+ if (!insn->prefixes.got)
+ insn_get_prefixes(insn);
+ return insn->rex_prefix.nbytes == 2;
+}
+
+static inline insn_byte_t insn_rex2_m_bit(struct insn *insn)
+{
+ return X86_REX2_M(insn->rex_prefix.bytes[1]);
+}
+
static inline int insn_is_avx(struct insn *insn)
{
if (!insn->prefixes.got)
@@ -198,6 +215,13 @@ static inline insn_byte_t insn_vex_p_bits(struct insn *insn)
return X86_VEX_P(insn->vex_prefix.bytes[2]);
}
+static inline insn_byte_t insn_vex_w_bit(struct insn *insn)
+{
+ if (insn->vex_prefix.nbytes < 3)
+ return 0;
+ return X86_VEX_W(insn->vex_prefix.bytes[2]);
+}
+
/* Get the last prefix id from last prefix or VEX prefix */
static inline int insn_last_prefix_id(struct insn *insn)
{
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index d0941f4c27..f81a851c46 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -40,137 +40,221 @@
* their own names :-(
*/
+#define IFM(_fam, _model) VFM_MAKE(X86_VENDOR_INTEL, _fam, _model)
+
/* Wildcard match for FAM6 so X86_MATCH_INTEL_FAM6_MODEL(ANY) works */
#define INTEL_FAM6_ANY X86_MODEL_ANY
+/* Wildcard match for FAM6 so X86_MATCH_VFM(ANY) works */
+#define INTEL_ANY IFM(X86_FAMILY_ANY, X86_MODEL_ANY)
#define INTEL_FAM6_CORE_YONAH 0x0E
+#define INTEL_CORE_YONAH IFM(6, 0x0E)
#define INTEL_FAM6_CORE2_MEROM 0x0F
+#define INTEL_CORE2_MEROM IFM(6, 0x0F)
#define INTEL_FAM6_CORE2_MEROM_L 0x16
+#define INTEL_CORE2_MEROM_L IFM(6, 0x16)
#define INTEL_FAM6_CORE2_PENRYN 0x17
+#define INTEL_CORE2_PENRYN IFM(6, 0x17)
#define INTEL_FAM6_CORE2_DUNNINGTON 0x1D
+#define INTEL_CORE2_DUNNINGTON IFM(6, 0x1D)
#define INTEL_FAM6_NEHALEM 0x1E
+#define INTEL_NEHALEM IFM(6, 0x1E)
#define INTEL_FAM6_NEHALEM_G 0x1F /* Auburndale / Havendale */
+#define INTEL_NEHALEM_G IFM(6, 0x1F) /* Auburndale / Havendale */
#define INTEL_FAM6_NEHALEM_EP 0x1A
+#define INTEL_NEHALEM_EP IFM(6, 0x1A)
#define INTEL_FAM6_NEHALEM_EX 0x2E
+#define INTEL_NEHALEM_EX IFM(6, 0x2E)
#define INTEL_FAM6_WESTMERE 0x25
+#define INTEL_WESTMERE IFM(6, 0x25)
#define INTEL_FAM6_WESTMERE_EP 0x2C
+#define INTEL_WESTMERE_EP IFM(6, 0x2C)
#define INTEL_FAM6_WESTMERE_EX 0x2F
+#define INTEL_WESTMERE_EX IFM(6, 0x2F)
#define INTEL_FAM6_SANDYBRIDGE 0x2A
+#define INTEL_SANDYBRIDGE IFM(6, 0x2A)
#define INTEL_FAM6_SANDYBRIDGE_X 0x2D
+#define INTEL_SANDYBRIDGE_X IFM(6, 0x2D)
#define INTEL_FAM6_IVYBRIDGE 0x3A
+#define INTEL_IVYBRIDGE IFM(6, 0x3A)
#define INTEL_FAM6_IVYBRIDGE_X 0x3E
+#define INTEL_IVYBRIDGE_X IFM(6, 0x3E)
#define INTEL_FAM6_HASWELL 0x3C
+#define INTEL_HASWELL IFM(6, 0x3C)
#define INTEL_FAM6_HASWELL_X 0x3F
+#define INTEL_HASWELL_X IFM(6, 0x3F)
#define INTEL_FAM6_HASWELL_L 0x45
+#define INTEL_HASWELL_L IFM(6, 0x45)
#define INTEL_FAM6_HASWELL_G 0x46
+#define INTEL_HASWELL_G IFM(6, 0x46)
#define INTEL_FAM6_BROADWELL 0x3D
+#define INTEL_BROADWELL IFM(6, 0x3D)
#define INTEL_FAM6_BROADWELL_G 0x47
+#define INTEL_BROADWELL_G IFM(6, 0x47)
#define INTEL_FAM6_BROADWELL_X 0x4F
+#define INTEL_BROADWELL_X IFM(6, 0x4F)
#define INTEL_FAM6_BROADWELL_D 0x56
+#define INTEL_BROADWELL_D IFM(6, 0x56)
#define INTEL_FAM6_SKYLAKE_L 0x4E /* Sky Lake */
+#define INTEL_SKYLAKE_L IFM(6, 0x4E) /* Sky Lake */
#define INTEL_FAM6_SKYLAKE 0x5E /* Sky Lake */
+#define INTEL_SKYLAKE IFM(6, 0x5E) /* Sky Lake */
#define INTEL_FAM6_SKYLAKE_X 0x55 /* Sky Lake */
+#define INTEL_SKYLAKE_X IFM(6, 0x55) /* Sky Lake */
/* CASCADELAKE_X 0x55 Sky Lake -- s: 7 */
/* COOPERLAKE_X 0x55 Sky Lake -- s: 11 */
#define INTEL_FAM6_KABYLAKE_L 0x8E /* Sky Lake */
+#define INTEL_KABYLAKE_L IFM(6, 0x8E) /* Sky Lake */
/* AMBERLAKE_L 0x8E Sky Lake -- s: 9 */
/* COFFEELAKE_L 0x8E Sky Lake -- s: 10 */
/* WHISKEYLAKE_L 0x8E Sky Lake -- s: 11,12 */
#define INTEL_FAM6_KABYLAKE 0x9E /* Sky Lake */
+#define INTEL_KABYLAKE IFM(6, 0x9E) /* Sky Lake */
/* COFFEELAKE 0x9E Sky Lake -- s: 10-13 */
#define INTEL_FAM6_COMETLAKE 0xA5 /* Sky Lake */
+#define INTEL_COMETLAKE IFM(6, 0xA5) /* Sky Lake */
#define INTEL_FAM6_COMETLAKE_L 0xA6 /* Sky Lake */
+#define INTEL_COMETLAKE_L IFM(6, 0xA6) /* Sky Lake */
#define INTEL_FAM6_CANNONLAKE_L 0x66 /* Palm Cove */
+#define INTEL_CANNONLAKE_L IFM(6, 0x66) /* Palm Cove */
#define INTEL_FAM6_ICELAKE_X 0x6A /* Sunny Cove */
+#define INTEL_ICELAKE_X IFM(6, 0x6A) /* Sunny Cove */
#define INTEL_FAM6_ICELAKE_D 0x6C /* Sunny Cove */
+#define INTEL_ICELAKE_D IFM(6, 0x6C) /* Sunny Cove */
#define INTEL_FAM6_ICELAKE 0x7D /* Sunny Cove */
+#define INTEL_ICELAKE IFM(6, 0x7D) /* Sunny Cove */
#define INTEL_FAM6_ICELAKE_L 0x7E /* Sunny Cove */
+#define INTEL_ICELAKE_L IFM(6, 0x7E) /* Sunny Cove */
#define INTEL_FAM6_ICELAKE_NNPI 0x9D /* Sunny Cove */
+#define INTEL_ICELAKE_NNPI IFM(6, 0x9D) /* Sunny Cove */
#define INTEL_FAM6_ROCKETLAKE 0xA7 /* Cypress Cove */
+#define INTEL_ROCKETLAKE IFM(6, 0xA7) /* Cypress Cove */
#define INTEL_FAM6_TIGERLAKE_L 0x8C /* Willow Cove */
+#define INTEL_TIGERLAKE_L IFM(6, 0x8C) /* Willow Cove */
#define INTEL_FAM6_TIGERLAKE 0x8D /* Willow Cove */
+#define INTEL_TIGERLAKE IFM(6, 0x8D) /* Willow Cove */
#define INTEL_FAM6_SAPPHIRERAPIDS_X 0x8F /* Golden Cove */
+#define INTEL_SAPPHIRERAPIDS_X IFM(6, 0x8F) /* Golden Cove */
#define INTEL_FAM6_EMERALDRAPIDS_X 0xCF
+#define INTEL_EMERALDRAPIDS_X IFM(6, 0xCF)
#define INTEL_FAM6_GRANITERAPIDS_X 0xAD
+#define INTEL_GRANITERAPIDS_X IFM(6, 0xAD)
#define INTEL_FAM6_GRANITERAPIDS_D 0xAE
+#define INTEL_GRANITERAPIDS_D IFM(6, 0xAE)
/* "Hybrid" Processors (P-Core/E-Core) */
#define INTEL_FAM6_LAKEFIELD 0x8A /* Sunny Cove / Tremont */
+#define INTEL_LAKEFIELD IFM(6, 0x8A) /* Sunny Cove / Tremont */
#define INTEL_FAM6_ALDERLAKE 0x97 /* Golden Cove / Gracemont */
+#define INTEL_ALDERLAKE IFM(6, 0x97) /* Golden Cove / Gracemont */
#define INTEL_FAM6_ALDERLAKE_L 0x9A /* Golden Cove / Gracemont */
+#define INTEL_ALDERLAKE_L IFM(6, 0x9A) /* Golden Cove / Gracemont */
#define INTEL_FAM6_RAPTORLAKE 0xB7 /* Raptor Cove / Enhanced Gracemont */
+#define INTEL_RAPTORLAKE IFM(6, 0xB7) /* Raptor Cove / Enhanced Gracemont */
#define INTEL_FAM6_RAPTORLAKE_P 0xBA
+#define INTEL_RAPTORLAKE_P IFM(6, 0xBA)
#define INTEL_FAM6_RAPTORLAKE_S 0xBF
+#define INTEL_RAPTORLAKE_S IFM(6, 0xBF)
#define INTEL_FAM6_METEORLAKE 0xAC
+#define INTEL_METEORLAKE IFM(6, 0xAC)
#define INTEL_FAM6_METEORLAKE_L 0xAA
+#define INTEL_METEORLAKE_L IFM(6, 0xAA)
#define INTEL_FAM6_ARROWLAKE_H 0xC5
+#define INTEL_ARROWLAKE_H IFM(6, 0xC5)
#define INTEL_FAM6_ARROWLAKE 0xC6
+#define INTEL_ARROWLAKE IFM(6, 0xC6)
#define INTEL_FAM6_ARROWLAKE_U 0xB5
+#define INTEL_ARROWLAKE_U IFM(6, 0xB5)
#define INTEL_FAM6_LUNARLAKE_M 0xBD
+#define INTEL_LUNARLAKE_M IFM(6, 0xBD)
/* "Small Core" Processors (Atom/E-Core) */
#define INTEL_FAM6_ATOM_BONNELL 0x1C /* Diamondville, Pineview */
+#define INTEL_ATOM_BONNELL IFM(6, 0x1C) /* Diamondville, Pineview */
#define INTEL_FAM6_ATOM_BONNELL_MID 0x26 /* Silverthorne, Lincroft */
+#define INTEL_ATOM_BONNELL_MID IFM(6, 0x26) /* Silverthorne, Lincroft */
#define INTEL_FAM6_ATOM_SALTWELL 0x36 /* Cedarview */
+#define INTEL_ATOM_SALTWELL IFM(6, 0x36) /* Cedarview */
#define INTEL_FAM6_ATOM_SALTWELL_MID 0x27 /* Penwell */
+#define INTEL_ATOM_SALTWELL_MID IFM(6, 0x27) /* Penwell */
#define INTEL_FAM6_ATOM_SALTWELL_TABLET 0x35 /* Cloverview */
+#define INTEL_ATOM_SALTWELL_TABLET IFM(6, 0x35) /* Cloverview */
#define INTEL_FAM6_ATOM_SILVERMONT 0x37 /* Bay Trail, Valleyview */
+#define INTEL_ATOM_SILVERMONT IFM(6, 0x37) /* Bay Trail, Valleyview */
#define INTEL_FAM6_ATOM_SILVERMONT_D 0x4D /* Avaton, Rangely */
+#define INTEL_ATOM_SILVERMONT_D IFM(6, 0x4D) /* Avaton, Rangely */
#define INTEL_FAM6_ATOM_SILVERMONT_MID 0x4A /* Merriefield */
+#define INTEL_ATOM_SILVERMONT_MID IFM(6, 0x4A) /* Merriefield */
#define INTEL_FAM6_ATOM_AIRMONT 0x4C /* Cherry Trail, Braswell */
+#define INTEL_ATOM_AIRMONT IFM(6, 0x4C) /* Cherry Trail, Braswell */
#define INTEL_FAM6_ATOM_AIRMONT_MID 0x5A /* Moorefield */
+#define INTEL_ATOM_AIRMONT_MID IFM(6, 0x5A) /* Moorefield */
#define INTEL_FAM6_ATOM_AIRMONT_NP 0x75 /* Lightning Mountain */
+#define INTEL_ATOM_AIRMONT_NP IFM(6, 0x75) /* Lightning Mountain */
#define INTEL_FAM6_ATOM_GOLDMONT 0x5C /* Apollo Lake */
+#define INTEL_ATOM_GOLDMONT IFM(6, 0x5C) /* Apollo Lake */
#define INTEL_FAM6_ATOM_GOLDMONT_D 0x5F /* Denverton */
+#define INTEL_ATOM_GOLDMONT_D IFM(6, 0x5F) /* Denverton */
/* Note: the micro-architecture is "Goldmont Plus" */
#define INTEL_FAM6_ATOM_GOLDMONT_PLUS 0x7A /* Gemini Lake */
+#define INTEL_ATOM_GOLDMONT_PLUS IFM(6, 0x7A) /* Gemini Lake */
#define INTEL_FAM6_ATOM_TREMONT_D 0x86 /* Jacobsville */
+#define INTEL_ATOM_TREMONT_D IFM(6, 0x86) /* Jacobsville */
#define INTEL_FAM6_ATOM_TREMONT 0x96 /* Elkhart Lake */
+#define INTEL_ATOM_TREMONT IFM(6, 0x96) /* Elkhart Lake */
#define INTEL_FAM6_ATOM_TREMONT_L 0x9C /* Jasper Lake */
+#define INTEL_ATOM_TREMONT_L IFM(6, 0x9C) /* Jasper Lake */
#define INTEL_FAM6_ATOM_GRACEMONT 0xBE /* Alderlake N */
+#define INTEL_ATOM_GRACEMONT IFM(6, 0xBE) /* Alderlake N */
#define INTEL_FAM6_ATOM_CRESTMONT_X 0xAF /* Sierra Forest */
+#define INTEL_ATOM_CRESTMONT_X IFM(6, 0xAF) /* Sierra Forest */
#define INTEL_FAM6_ATOM_CRESTMONT 0xB6 /* Grand Ridge */
+#define INTEL_ATOM_CRESTMONT IFM(6, 0xB6) /* Grand Ridge */
#define INTEL_FAM6_ATOM_DARKMONT_X 0xDD /* Clearwater Forest */
+#define INTEL_ATOM_DARKMONT_X IFM(6, 0xDD) /* Clearwater Forest */
/* Xeon Phi */
#define INTEL_FAM6_XEON_PHI_KNL 0x57 /* Knights Landing */
+#define INTEL_XEON_PHI_KNL IFM(6, 0x57) /* Knights Landing */
#define INTEL_FAM6_XEON_PHI_KNM 0x85 /* Knights Mill */
+#define INTEL_XEON_PHI_KNM IFM(6, 0x85) /* Knights Mill */
/* Family 5 */
#define INTEL_FAM5_QUARK_X1000 0x09 /* Quark X1000 SoC */
+#define INTEL_QUARK_X1000 IFM(5, 0x09) /* Quark X1000 SoC */
#endif /* _ASM_X86_INTEL_FAMILY_H */
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 294cd2a408..1d60427379 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -42,6 +42,7 @@
#include <asm/early_ioremap.h>
#include <asm/pgtable_types.h>
#include <asm/shared/io.h>
+#include <asm/special_insns.h>
#define build_mmio_read(name, size, type, reg, barrier) \
static inline type name(const volatile void __iomem *addr) \
@@ -209,6 +210,23 @@ void memset_io(volatile void __iomem *, int, size_t);
#define memcpy_toio memcpy_toio
#define memset_io memset_io
+#ifdef CONFIG_X86_64
+/*
+ * Commit 0f07496144c2 ("[PATCH] Add faster __iowrite32_copy routine for
+ * x86_64") says that circa 2006 rep movsl is noticeably faster than a copy
+ * loop.
+ */
+static inline void __iowrite32_copy(void __iomem *to, const void *from,
+ size_t count)
+{
+ asm volatile("rep ; movsl"
+ : "=&c"(count), "=&D"(to), "=&S"(from)
+ : "0"(count), "1"(to), "2"(from)
+ : "memory");
+}
+#define __iowrite32_copy __iowrite32_copy
+#endif
+
/*
* ISA space is 'always mapped' on a typical x86 system, no need to
* explicitly ioremap() it. The fact that the ISA IO space is mapped
diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h
index 7a2ed154a5..5036f13ab6 100644
--- a/arch/x86/include/asm/irq_remapping.h
+++ b/arch/x86/include/asm/irq_remapping.h
@@ -50,6 +50,13 @@ static inline struct irq_domain *arch_get_ir_parent_domain(void)
return x86_vector_domain;
}
+extern bool enable_posted_msi;
+
+static inline bool posted_msi_supported(void)
+{
+ return enable_posted_msi && irq_remapping_cap(IRQ_POSTING_CAP);
+}
+
#else /* CONFIG_IRQ_REMAP */
static inline bool irq_remapping_cap(enum irq_remap_cap cap) { return 0; }
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index d18bfb238f..13aea8fc3d 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -97,10 +97,16 @@
#define LOCAL_TIMER_VECTOR 0xec
+/*
+ * Posted interrupt notification vector for all device MSIs delivered to
+ * the host kernel.
+ */
+#define POSTED_MSI_NOTIFICATION_VECTOR 0xeb
+
#define NR_VECTORS 256
#ifdef CONFIG_X86_LOCAL_APIC
-#define FIRST_SYSTEM_VECTOR LOCAL_TIMER_VECTOR
+#define FIRST_SYSTEM_VECTOR POSTED_MSI_NOTIFICATION_VECTOR
#else
#define FIRST_SYSTEM_VECTOR NR_VECTORS
#endif
diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index 91ca9a9ee3..ae5482a2f0 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -207,18 +207,11 @@ int arch_kimage_file_post_load_cleanup(struct kimage *image);
extern void kdump_nmi_shootdown_cpus(void);
#ifdef CONFIG_CRASH_HOTPLUG
-void arch_crash_handle_hotplug_event(struct kimage *image);
+void arch_crash_handle_hotplug_event(struct kimage *image, void *arg);
#define arch_crash_handle_hotplug_event arch_crash_handle_hotplug_event
-#ifdef CONFIG_HOTPLUG_CPU
-int arch_crash_hotplug_cpu_support(void);
-#define crash_hotplug_cpu_support arch_crash_hotplug_cpu_support
-#endif
-
-#ifdef CONFIG_MEMORY_HOTPLUG
-int arch_crash_hotplug_memory_support(void);
-#define crash_hotplug_memory_support arch_crash_hotplug_memory_support
-#endif
+int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags);
+#define arch_crash_hotplug_support arch_crash_hotplug_support
unsigned int arch_crash_get_elfcorehdr_size(void);
#define crash_get_elfcorehdr_size arch_crash_get_elfcorehdr_size
diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 110d7f29ca..8d5a2b4f5f 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -85,7 +85,6 @@ KVM_X86_OP_OPTIONAL(update_cr8_intercept)
KVM_X86_OP(refresh_apicv_exec_ctrl)
KVM_X86_OP_OPTIONAL(hwapic_irr_update)
KVM_X86_OP_OPTIONAL(hwapic_isr_update)
-KVM_X86_OP_OPTIONAL_RET0(guest_apic_has_interrupt)
KVM_X86_OP_OPTIONAL(load_eoi_exitmap)
KVM_X86_OP_OPTIONAL(set_virtual_apic_mode)
KVM_X86_OP_OPTIONAL(set_apic_access_page_addr)
@@ -121,6 +120,7 @@ KVM_X86_OP(enter_smm)
KVM_X86_OP(leave_smm)
KVM_X86_OP(enable_smi_window)
#endif
+KVM_X86_OP_OPTIONAL(dev_get_attr)
KVM_X86_OP_OPTIONAL(mem_enc_ioctl)
KVM_X86_OP_OPTIONAL(mem_enc_register_region)
KVM_X86_OP_OPTIONAL(mem_enc_unregister_region)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 6efd1497b0..d0274b3be2 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -254,28 +254,31 @@ enum x86_intercept_stage;
KVM_GUESTDBG_INJECT_DB | \
KVM_GUESTDBG_BLOCKIRQ)
+#define PFERR_PRESENT_MASK BIT(0)
+#define PFERR_WRITE_MASK BIT(1)
+#define PFERR_USER_MASK BIT(2)
+#define PFERR_RSVD_MASK BIT(3)
+#define PFERR_FETCH_MASK BIT(4)
+#define PFERR_PK_MASK BIT(5)
+#define PFERR_SGX_MASK BIT(15)
+#define PFERR_GUEST_RMP_MASK BIT_ULL(31)
+#define PFERR_GUEST_FINAL_MASK BIT_ULL(32)
+#define PFERR_GUEST_PAGE_MASK BIT_ULL(33)
+#define PFERR_GUEST_ENC_MASK BIT_ULL(34)
+#define PFERR_GUEST_SIZEM_MASK BIT_ULL(35)
+#define PFERR_GUEST_VMPL_MASK BIT_ULL(36)
-#define PFERR_PRESENT_BIT 0
-#define PFERR_WRITE_BIT 1
-#define PFERR_USER_BIT 2
-#define PFERR_RSVD_BIT 3
-#define PFERR_FETCH_BIT 4
-#define PFERR_PK_BIT 5
-#define PFERR_SGX_BIT 15
-#define PFERR_GUEST_FINAL_BIT 32
-#define PFERR_GUEST_PAGE_BIT 33
-#define PFERR_IMPLICIT_ACCESS_BIT 48
-
-#define PFERR_PRESENT_MASK BIT(PFERR_PRESENT_BIT)
-#define PFERR_WRITE_MASK BIT(PFERR_WRITE_BIT)
-#define PFERR_USER_MASK BIT(PFERR_USER_BIT)
-#define PFERR_RSVD_MASK BIT(PFERR_RSVD_BIT)
-#define PFERR_FETCH_MASK BIT(PFERR_FETCH_BIT)
-#define PFERR_PK_MASK BIT(PFERR_PK_BIT)
-#define PFERR_SGX_MASK BIT(PFERR_SGX_BIT)
-#define PFERR_GUEST_FINAL_MASK BIT_ULL(PFERR_GUEST_FINAL_BIT)
-#define PFERR_GUEST_PAGE_MASK BIT_ULL(PFERR_GUEST_PAGE_BIT)
-#define PFERR_IMPLICIT_ACCESS BIT_ULL(PFERR_IMPLICIT_ACCESS_BIT)
+/*
+ * IMPLICIT_ACCESS is a KVM-defined flag used to correctly perform SMAP checks
+ * when emulating instructions that triggers implicit access.
+ */
+#define PFERR_IMPLICIT_ACCESS BIT_ULL(48)
+/*
+ * PRIVATE_ACCESS is a KVM-defined flag us to indicate that a fault occurred
+ * when the guest was accessing private memory.
+ */
+#define PFERR_PRIVATE_ACCESS BIT_ULL(49)
+#define PFERR_SYNTHETIC_MASK (PFERR_IMPLICIT_ACCESS | PFERR_PRIVATE_ACCESS)
#define PFERR_NESTED_GUEST_PAGE (PFERR_GUEST_PAGE_MASK | \
PFERR_WRITE_MASK | \
@@ -994,9 +997,6 @@ struct kvm_vcpu_arch {
u64 msr_kvm_poll_control;
- /* set at EPT violation at this point */
- unsigned long exit_qualification;
-
/* pv related host specific info */
struct {
bool pv_unhalted;
@@ -1280,12 +1280,14 @@ enum kvm_apicv_inhibit {
};
struct kvm_arch {
- unsigned long vm_type;
unsigned long n_used_mmu_pages;
unsigned long n_requested_mmu_pages;
unsigned long n_max_mmu_pages;
unsigned int indirect_shadow_pages;
u8 mmu_valid_gen;
+ u8 vm_type;
+ bool has_private_mem;
+ bool has_protected_state;
struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
struct list_head active_mmu_pages;
struct list_head zapped_obsolete_pages;
@@ -1312,6 +1314,8 @@ struct kvm_arch {
*/
spinlock_t mmu_unsync_pages_lock;
+ u64 shadow_mmio_value;
+
struct iommu_domain *iommu_domain;
bool iommu_noncoherent;
#define __KVM_HAVE_ARCH_NONCOHERENT_DMA
@@ -1710,7 +1714,6 @@ struct kvm_x86_ops {
void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu);
void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr);
void (*hwapic_isr_update)(int isr);
- 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);
@@ -1779,6 +1782,7 @@ struct kvm_x86_ops {
void (*enable_smi_window)(struct kvm_vcpu *vcpu);
#endif
+ int (*dev_get_attr)(u32 group, u64 attr, u64 *val);
int (*mem_enc_ioctl)(struct kvm *kvm, void __user *argp);
int (*mem_enc_register_region)(struct kvm *kvm, struct kvm_enc_region *argp);
int (*mem_enc_unregister_region)(struct kvm *kvm, struct kvm_enc_region *argp);
@@ -1814,7 +1818,7 @@ struct kvm_x86_nested_ops {
bool (*is_exception_vmexit)(struct kvm_vcpu *vcpu, u8 vector,
u32 error_code);
int (*check_events)(struct kvm_vcpu *vcpu);
- bool (*has_events)(struct kvm_vcpu *vcpu);
+ bool (*has_events)(struct kvm_vcpu *vcpu, bool for_injection);
void (*triple_fault)(struct kvm_vcpu *vcpu);
int (*get_state)(struct kvm_vcpu *vcpu,
struct kvm_nested_state __user *user_kvm_nested_state,
@@ -1844,6 +1848,7 @@ struct kvm_arch_async_pf {
gfn_t gfn;
unsigned long cr3;
bool direct_map;
+ u64 error_code;
};
extern u32 __read_mostly kvm_nr_uret_msrs;
@@ -2140,10 +2145,15 @@ static inline void kvm_clear_apicv_inhibit(struct kvm *kvm,
kvm_set_or_clear_apicv_inhibit(kvm, reason, false);
}
+unsigned long __kvm_emulate_hypercall(struct kvm_vcpu *vcpu, unsigned long nr,
+ unsigned long a0, unsigned long a1,
+ unsigned long a2, unsigned long a3,
+ int op_64_bit, int cpl);
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_print_sptes(struct kvm_vcpu *vcpu, gpa_t gpa, const char *msg);
void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva);
void kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
u64 addr, unsigned long roots);
@@ -2153,8 +2163,9 @@ void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd);
void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level,
int tdp_max_root_level, int tdp_huge_page_level);
+
#ifdef CONFIG_KVM_PRIVATE_MEM
-#define kvm_arch_has_private_mem(kvm) ((kvm)->arch.vm_type != KVM_X86_DEFAULT_VM)
+#define kvm_arch_has_private_mem(kvm) ((kvm)->arch.has_private_mem)
#else
#define kvm_arch_has_private_mem(kvm) false
#endif
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index de31183058..dfd2e9699b 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -13,6 +13,7 @@
#define MCG_CTL_P BIT_ULL(8) /* MCG_CTL register available */
#define MCG_EXT_P BIT_ULL(9) /* Extended registers available */
#define MCG_CMCI_P BIT_ULL(10) /* CMCI supported */
+#define MCG_SEAM_NR BIT_ULL(12) /* MCG_STATUS_SEAM_NR supported */
#define MCG_EXT_CNT_MASK 0xff0000 /* Number of Extended registers */
#define MCG_EXT_CNT_SHIFT 16
#define MCG_EXT_CNT(c) (((c) & MCG_EXT_CNT_MASK) >> MCG_EXT_CNT_SHIFT)
@@ -25,6 +26,7 @@
#define MCG_STATUS_EIPV BIT_ULL(1) /* ip points to correct instruction */
#define MCG_STATUS_MCIP BIT_ULL(2) /* machine check in progress */
#define MCG_STATUS_LMCES BIT_ULL(3) /* LMCE signaled */
+#define MCG_STATUS_SEAM_NR BIT_ULL(12) /* Machine check inside SEAM non-root mode */
/* MCG_EXT_CTL register defines */
#define MCG_EXT_CTL_LMCE_EN BIT_ULL(0) /* Enable LMCE */
diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h
index c72c7ff78f..d593e52e66 100644
--- a/arch/x86/include/asm/mpspec.h
+++ b/arch/x86/include/asm/mpspec.h
@@ -16,10 +16,10 @@ extern int pic_mode;
* Summit or generic (i.e. installer) kernels need lots of bus entries.
* Maximum 256 PCI busses, plus 1 ISA bus in each of 4 cabinets.
*/
-#if CONFIG_BASE_SMALL == 0
-# define MAX_MP_BUSSES 260
-#else
+#ifdef CONFIG_BASE_SMALL
# define MAX_MP_BUSSES 32
+#else
+# define MAX_MP_BUSSES 260
#endif
#define MAX_IRQ_SOURCES 256
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index e72c2b8729..e022e6eb76 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -170,6 +170,10 @@
* CPU is not affected by Branch
* History Injection.
*/
+#define ARCH_CAP_XAPIC_DISABLE BIT(21) /*
+ * IA32_XAPIC_DISABLE_STATUS MSR
+ * supported
+ */
#define ARCH_CAP_PBRSB_NO BIT(24) /*
* Not susceptible to Post-Barrier
* Return Stack Buffer Predictions.
@@ -192,11 +196,6 @@
* File.
*/
-#define ARCH_CAP_XAPIC_DISABLE BIT(21) /*
- * IA32_XAPIC_DISABLE_STATUS MSR
- * supported
- */
-
#define MSR_IA32_FLUSH_CMD 0x0000010b
#define L1D_FLUSH BIT(0) /*
* Writeback and invalidate the
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index 9da9c8a2f1..52f1b4ff0c 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -31,10 +31,12 @@
#define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_TSK_EXEC
-#define __PHYSICAL_START ALIGN(CONFIG_PHYSICAL_START, \
- CONFIG_PHYSICAL_ALIGN)
+/* Physical address where kernel should be loaded. */
+#define LOAD_PHYSICAL_ADDR ((CONFIG_PHYSICAL_START \
+ + (CONFIG_PHYSICAL_ALIGN - 1)) \
+ & ~(CONFIG_PHYSICAL_ALIGN - 1))
-#define __START_KERNEL (__START_KERNEL_map + __PHYSICAL_START)
+#define __START_KERNEL (__START_KERNEL_map + LOAD_PHYSICAL_ADDR)
#ifdef CONFIG_X86_64
#include <asm/page_64_types.h>
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index ce5111cec3..3bedee1801 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -59,12 +59,6 @@
#define __force_percpu_prefix "%%"__stringify(__percpu_seg)":"
#define __my_cpu_offset this_cpu_read(this_cpu_off)
-#ifdef CONFIG_X86_64
-#define __raw_my_cpu_offset raw_cpu_read_8(this_cpu_off);
-#else
-#define __raw_my_cpu_offset raw_cpu_read_4(this_cpu_off);
-#endif
-
/*
* Compared to the generic __my_cpu_offset version, the following
* saves one instruction and avoids clobbering a temp register.
@@ -76,7 +70,7 @@
#ifndef BUILD_VDSO32_64
#define arch_raw_cpu_ptr(_ptr) \
({ \
- unsigned long tcp_ptr__ = __raw_my_cpu_offset; \
+ unsigned long tcp_ptr__ = raw_cpu_read_long(this_cpu_off); \
tcp_ptr__ += (__force unsigned long)(_ptr); \
(typeof(*(_ptr)) __kernel __force *)tcp_ptr__; \
})
@@ -96,7 +90,7 @@
#endif /* CONFIG_SMP */
#define __my_cpu_type(var) typeof(var) __percpu_seg_override
-#define __my_cpu_ptr(ptr) (__my_cpu_type(*ptr)*)(__force uintptr_t)(ptr)
+#define __my_cpu_ptr(ptr) (__my_cpu_type(*(ptr))*)(__force uintptr_t)(ptr)
#define __my_cpu_var(var) (*__my_cpu_ptr(&(var)))
#define __percpu_arg(x) __percpu_prefix "%" #x
#define __force_percpu_arg(x) __force_percpu_prefix "%" #x
@@ -224,25 +218,26 @@ do { \
})
/*
- * xchg is implemented using cmpxchg without a lock prefix. xchg is
- * expensive due to the implied lock prefix. The processor cannot prefetch
- * cachelines if xchg is used.
+ * raw_cpu_xchg() can use a load-store since
+ * it is not required to be IRQ-safe.
*/
-#define percpu_xchg_op(size, qual, _var, _nval) \
+#define raw_percpu_xchg_op(_var, _nval) \
({ \
- __pcpu_type_##size pxo_old__; \
- __pcpu_type_##size pxo_new__ = __pcpu_cast_##size(_nval); \
- asm qual (__pcpu_op2_##size("mov", __percpu_arg([var]), \
- "%[oval]") \
- "\n1:\t" \
- __pcpu_op2_##size("cmpxchg", "%[nval]", \
- __percpu_arg([var])) \
- "\n\tjnz 1b" \
- : [oval] "=&a" (pxo_old__), \
- [var] "+m" (__my_cpu_var(_var)) \
- : [nval] __pcpu_reg_##size(, pxo_new__) \
- : "memory"); \
- (typeof(_var))(unsigned long) pxo_old__; \
+ typeof(_var) pxo_old__ = raw_cpu_read(_var); \
+ raw_cpu_write(_var, _nval); \
+ pxo_old__; \
+})
+
+/*
+ * this_cpu_xchg() is implemented using cmpxchg without a lock prefix.
+ * xchg is expensive due to the implied lock prefix. The processor
+ * cannot prefetch cachelines if xchg is used.
+ */
+#define this_percpu_xchg_op(_var, _nval) \
+({ \
+ typeof(_var) pxo_old__ = this_cpu_read(_var); \
+ do { } while (!this_cpu_try_cmpxchg(_var, &pxo_old__, _nval)); \
+ pxo_old__; \
})
/*
@@ -422,10 +417,6 @@ do { \
* actually per-thread variables implemented as per-CPU variables and
* thus stable for the duration of the respective task.
*/
-#define this_cpu_read_stable_1(pcp) percpu_stable_op(1, "mov", pcp)
-#define this_cpu_read_stable_2(pcp) percpu_stable_op(2, "mov", pcp)
-#define this_cpu_read_stable_4(pcp) percpu_stable_op(4, "mov", pcp)
-#define this_cpu_read_stable_8(pcp) percpu_stable_op(8, "mov", pcp)
#define this_cpu_read_stable(pcp) __pcpu_size_call_return(this_cpu_read_stable_, pcp)
#ifdef CONFIG_USE_X86_SEG_SUPPORT
@@ -494,6 +485,10 @@ do { \
#define this_cpu_read_const(pcp) ({ BUILD_BUG(); (typeof(pcp))0; })
#endif /* CONFIG_USE_X86_SEG_SUPPORT */
+#define this_cpu_read_stable_1(pcp) percpu_stable_op(1, "mov", pcp)
+#define this_cpu_read_stable_2(pcp) percpu_stable_op(2, "mov", pcp)
+#define this_cpu_read_stable_4(pcp) percpu_stable_op(4, "mov", pcp)
+
#define raw_cpu_add_1(pcp, val) percpu_add_op(1, , (pcp), val)
#define raw_cpu_add_2(pcp, val) percpu_add_op(2, , (pcp), val)
#define raw_cpu_add_4(pcp, val) percpu_add_op(4, , (pcp), val)
@@ -503,18 +498,6 @@ do { \
#define raw_cpu_or_1(pcp, val) percpu_to_op(1, , "or", (pcp), val)
#define raw_cpu_or_2(pcp, val) percpu_to_op(2, , "or", (pcp), val)
#define raw_cpu_or_4(pcp, val) percpu_to_op(4, , "or", (pcp), val)
-
-/*
- * raw_cpu_xchg() can use a load-store since it is not required to be
- * IRQ-safe.
- */
-#define raw_percpu_xchg_op(var, nval) \
-({ \
- typeof(var) pxo_ret__ = raw_cpu_read(var); \
- raw_cpu_write(var, (nval)); \
- pxo_ret__; \
-})
-
#define raw_cpu_xchg_1(pcp, val) raw_percpu_xchg_op(pcp, val)
#define raw_cpu_xchg_2(pcp, val) raw_percpu_xchg_op(pcp, val)
#define raw_cpu_xchg_4(pcp, val) raw_percpu_xchg_op(pcp, val)
@@ -528,9 +511,9 @@ do { \
#define this_cpu_or_1(pcp, val) percpu_to_op(1, volatile, "or", (pcp), val)
#define this_cpu_or_2(pcp, val) percpu_to_op(2, volatile, "or", (pcp), val)
#define this_cpu_or_4(pcp, val) percpu_to_op(4, volatile, "or", (pcp), val)
-#define this_cpu_xchg_1(pcp, nval) percpu_xchg_op(1, volatile, pcp, nval)
-#define this_cpu_xchg_2(pcp, nval) percpu_xchg_op(2, volatile, pcp, nval)
-#define this_cpu_xchg_4(pcp, nval) percpu_xchg_op(4, volatile, pcp, nval)
+#define this_cpu_xchg_1(pcp, nval) this_percpu_xchg_op(pcp, nval)
+#define this_cpu_xchg_2(pcp, nval) this_percpu_xchg_op(pcp, nval)
+#define this_cpu_xchg_4(pcp, nval) this_percpu_xchg_op(pcp, nval)
#define raw_cpu_add_return_1(pcp, val) percpu_add_return_op(1, , pcp, val)
#define raw_cpu_add_return_2(pcp, val) percpu_add_return_op(2, , pcp, val)
@@ -557,6 +540,8 @@ do { \
* 32 bit must fall back to generic operations.
*/
#ifdef CONFIG_X86_64
+#define this_cpu_read_stable_8(pcp) percpu_stable_op(8, "mov", pcp)
+
#define raw_cpu_add_8(pcp, val) percpu_add_op(8, , (pcp), val)
#define raw_cpu_and_8(pcp, val) percpu_to_op(8, , "and", (pcp), val)
#define raw_cpu_or_8(pcp, val) percpu_to_op(8, , "or", (pcp), val)
@@ -569,41 +554,41 @@ do { \
#define this_cpu_and_8(pcp, val) percpu_to_op(8, volatile, "and", (pcp), val)
#define this_cpu_or_8(pcp, val) percpu_to_op(8, volatile, "or", (pcp), val)
#define this_cpu_add_return_8(pcp, val) percpu_add_return_op(8, volatile, pcp, val)
-#define this_cpu_xchg_8(pcp, nval) percpu_xchg_op(8, volatile, pcp, nval)
+#define this_cpu_xchg_8(pcp, nval) this_percpu_xchg_op(pcp, nval)
#define this_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(8, volatile, pcp, oval, nval)
#define this_cpu_try_cmpxchg_8(pcp, ovalp, nval) percpu_try_cmpxchg_op(8, volatile, pcp, ovalp, nval)
-#endif
-
-static __always_inline bool x86_this_cpu_constant_test_bit(unsigned int nr,
- const unsigned long __percpu *addr)
-{
- unsigned long __percpu *a =
- (unsigned long __percpu *)addr + nr / BITS_PER_LONG;
-#ifdef CONFIG_X86_64
- return ((1UL << (nr % BITS_PER_LONG)) & raw_cpu_read_8(*a)) != 0;
+#define raw_cpu_read_long(pcp) raw_cpu_read_8(pcp)
#else
- return ((1UL << (nr % BITS_PER_LONG)) & raw_cpu_read_4(*a)) != 0;
-#endif
-}
+/* There is no generic 64 bit read stable operation for 32 bit targets. */
+#define this_cpu_read_stable_8(pcp) ({ BUILD_BUG(); (typeof(pcp))0; })
-static inline bool x86_this_cpu_variable_test_bit(int nr,
- const unsigned long __percpu *addr)
-{
- bool oldbit;
+#define raw_cpu_read_long(pcp) raw_cpu_read_4(pcp)
+#endif
- asm volatile("btl "__percpu_arg(2)",%1"
- CC_SET(c)
- : CC_OUT(c) (oldbit)
- : "m" (*__my_cpu_ptr((unsigned long __percpu *)(addr))), "Ir" (nr));
+#define x86_this_cpu_constant_test_bit(_nr, _var) \
+({ \
+ unsigned long __percpu *addr__ = \
+ (unsigned long __percpu *)&(_var) + ((_nr) / BITS_PER_LONG); \
+ !!((1UL << ((_nr) % BITS_PER_LONG)) & raw_cpu_read(*addr__)); \
+})
- return oldbit;
-}
+#define x86_this_cpu_variable_test_bit(_nr, _var) \
+({ \
+ bool oldbit; \
+ \
+ asm volatile("btl %[nr], " __percpu_arg([var]) \
+ CC_SET(c) \
+ : CC_OUT(c) (oldbit) \
+ : [var] "m" (__my_cpu_var(_var)), \
+ [nr] "rI" (_nr)); \
+ oldbit; \
+})
-#define x86_this_cpu_test_bit(nr, addr) \
- (__builtin_constant_p((nr)) \
- ? x86_this_cpu_constant_test_bit((nr), (addr)) \
- : x86_this_cpu_variable_test_bit((nr), (addr)))
+#define x86_this_cpu_test_bit(_nr, _var) \
+ (__builtin_constant_p(_nr) \
+ ? x86_this_cpu_constant_test_bit(_nr, _var) \
+ : x86_this_cpu_variable_test_bit(_nr, _var))
#include <asm-generic/percpu.h>
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 315535ffb2..65b8e5bb90 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -234,6 +234,7 @@ static inline unsigned long pmd_pfn(pmd_t pmd)
return (pfn & pmd_pfn_mask(pmd)) >> PAGE_SHIFT;
}
+#define pud_pfn pud_pfn
static inline unsigned long pud_pfn(pud_t pud)
{
phys_addr_t pfn = pud_val(pud);
@@ -387,23 +388,7 @@ static inline pte_t pte_wrprotect(pte_t pte)
#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP
static inline int pte_uffd_wp(pte_t pte)
{
- bool wp = pte_flags(pte) & _PAGE_UFFD_WP;
-
-#ifdef CONFIG_DEBUG_VM
- /*
- * Having write bit for wr-protect-marked present ptes is fatal,
- * because it means the uffd-wp bit will be ignored and write will
- * just go through.
- *
- * Use any chance of pgtable walking to verify this (e.g., when
- * page swapped out or being migrated for all purposes). It means
- * something is already wrong. Tell the admin even before the
- * process crashes. We also nail it with wrong pgtable setup.
- */
- WARN_ON_ONCE(wp && pte_write(pte));
-#endif
-
- return wp;
+ return pte_flags(pte) & _PAGE_UFFD_WP;
}
static inline pte_t pte_mkuffd_wp(pte_t pte)
@@ -1200,7 +1185,6 @@ static inline int pgd_none(pgd_t pgd)
extern int direct_gbpages;
void init_mem_mapping(void);
void early_alloc_pgt_buf(void);
-extern void memblock_find_dma_reserve(void);
void __init poking_init(void);
unsigned long init_memory_mapping(unsigned long start,
unsigned long end, pgprot_t prot);
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 7e9db77231..3c4407271d 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -245,6 +245,7 @@ extern void cleanup_highmap(void);
#define HAVE_ARCH_UNMAPPED_AREA
#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
+#define HAVE_ARCH_UNMAPPED_AREA_VMFLAGS
#define PAGE_AGP PAGE_KERNEL_NOCACHE
#define HAVE_PAGE_AGP 1
diff --git a/arch/x86/include/asm/posted_intr.h b/arch/x86/include/asm/posted_intr.h
new file mode 100644
index 0000000000..de788b400f
--- /dev/null
+++ b/arch/x86/include/asm/posted_intr.h
@@ -0,0 +1,118 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _X86_POSTED_INTR_H
+#define _X86_POSTED_INTR_H
+#include <asm/irq_vectors.h>
+
+#define POSTED_INTR_ON 0
+#define POSTED_INTR_SN 1
+
+#define PID_TABLE_ENTRY_VALID 1
+
+/* Posted-Interrupt Descriptor */
+struct pi_desc {
+ union {
+ u32 pir[8]; /* Posted interrupt requested */
+ u64 pir64[4];
+ };
+ union {
+ struct {
+ u16 notifications; /* Suppress and outstanding bits */
+ u8 nv;
+ u8 rsvd_2;
+ u32 ndst;
+ };
+ u64 control;
+ };
+ u32 rsvd[6];
+} __aligned(64);
+
+static inline bool pi_test_and_set_on(struct pi_desc *pi_desc)
+{
+ return test_and_set_bit(POSTED_INTR_ON, (unsigned long *)&pi_desc->control);
+}
+
+static inline bool pi_test_and_clear_on(struct pi_desc *pi_desc)
+{
+ return test_and_clear_bit(POSTED_INTR_ON, (unsigned long *)&pi_desc->control);
+}
+
+static inline bool pi_test_and_clear_sn(struct pi_desc *pi_desc)
+{
+ return test_and_clear_bit(POSTED_INTR_SN, (unsigned long *)&pi_desc->control);
+}
+
+static inline bool pi_test_and_set_pir(int vector, struct pi_desc *pi_desc)
+{
+ return test_and_set_bit(vector, (unsigned long *)pi_desc->pir);
+}
+
+static inline bool pi_is_pir_empty(struct pi_desc *pi_desc)
+{
+ return bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS);
+}
+
+static inline void pi_set_sn(struct pi_desc *pi_desc)
+{
+ set_bit(POSTED_INTR_SN, (unsigned long *)&pi_desc->control);
+}
+
+static inline void pi_set_on(struct pi_desc *pi_desc)
+{
+ set_bit(POSTED_INTR_ON, (unsigned long *)&pi_desc->control);
+}
+
+static inline void pi_clear_on(struct pi_desc *pi_desc)
+{
+ clear_bit(POSTED_INTR_ON, (unsigned long *)&pi_desc->control);
+}
+
+static inline void pi_clear_sn(struct pi_desc *pi_desc)
+{
+ clear_bit(POSTED_INTR_SN, (unsigned long *)&pi_desc->control);
+}
+
+static inline bool pi_test_on(struct pi_desc *pi_desc)
+{
+ return test_bit(POSTED_INTR_ON, (unsigned long *)&pi_desc->control);
+}
+
+static inline bool pi_test_sn(struct pi_desc *pi_desc)
+{
+ return test_bit(POSTED_INTR_SN, (unsigned long *)&pi_desc->control);
+}
+
+/* Non-atomic helpers */
+static inline void __pi_set_sn(struct pi_desc *pi_desc)
+{
+ pi_desc->notifications |= BIT(POSTED_INTR_SN);
+}
+
+static inline void __pi_clear_sn(struct pi_desc *pi_desc)
+{
+ pi_desc->notifications &= ~BIT(POSTED_INTR_SN);
+}
+
+#ifdef CONFIG_X86_POSTED_MSI
+/*
+ * Not all external vectors are subject to interrupt remapping, e.g. IOMMU's
+ * own interrupts. Here we do not distinguish them since those vector bits in
+ * PIR will always be zero.
+ */
+static inline bool pi_pending_this_cpu(unsigned int vector)
+{
+ struct pi_desc *pid = this_cpu_ptr(&posted_msi_pi_desc);
+
+ if (WARN_ON_ONCE(vector > NR_VECTORS || vector < FIRST_EXTERNAL_VECTOR))
+ return false;
+
+ return test_bit(vector, (unsigned long *)pid->pir);
+}
+
+extern void intel_posted_msi_init(void);
+#else
+static inline bool pi_pending_this_cpu(unsigned int vector) { return false; }
+
+static inline void intel_posted_msi_init(void) {};
+#endif /* X86_POSTED_MSI */
+
+#endif /* _X86_POSTED_INTR_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 78e51b0d64..cb4f6c513c 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -108,9 +108,23 @@ struct cpuinfo_topology {
};
struct cpuinfo_x86 {
- __u8 x86; /* CPU family */
- __u8 x86_vendor; /* CPU vendor */
- __u8 x86_model;
+ union {
+ /*
+ * The particular ordering (low-to-high) of (vendor,
+ * family, model) is done in case range of models, like
+ * it is usually done on AMD, need to be compared.
+ */
+ struct {
+ __u8 x86_model;
+ /* CPU family */
+ __u8 x86;
+ /* CPU vendor */
+ __u8 x86_vendor;
+ __u8 x86_reserved;
+ };
+ /* combined vendor, family, model */
+ __u32 x86_vfm;
+ };
__u8 x86_stepping;
#ifdef CONFIG_X86_64
/* Number of 4K pages in DTLB/ITLB combined(in pages): */
@@ -586,7 +600,7 @@ extern char ignore_fpu_irq;
# define BASE_PREFETCH ""
# define ARCH_HAS_PREFETCH
#else
-# define BASE_PREFETCH "prefetcht0 %P1"
+# define BASE_PREFETCH "prefetcht0 %1"
#endif
/*
@@ -597,7 +611,7 @@ extern char ignore_fpu_irq;
*/
static inline void prefetch(const void *x)
{
- alternative_input(BASE_PREFETCH, "prefetchnta %P1",
+ alternative_input(BASE_PREFETCH, "prefetchnta %1",
X86_FEATURE_XMM,
"m" (*(const char *)x));
}
@@ -609,7 +623,7 @@ static inline void prefetch(const void *x)
*/
static __always_inline void prefetchw(const void *x)
{
- alternative_input(BASE_PREFETCH, "prefetchw %P1",
+ alternative_input(BASE_PREFETCH, "prefetchw %1",
X86_FEATURE_3DNOWPREFETCH,
"m" (*(const char *)x));
}
@@ -635,12 +649,10 @@ static __always_inline void prefetchw(const void *x)
#define KSTK_ESP(task) (task_pt_regs(task)->sp)
#else
-extern unsigned long __end_init_task[];
+extern unsigned long __top_init_kernel_stack[];
#define INIT_THREAD { \
- .sp = (unsigned long)&__end_init_task - \
- TOP_OF_KERNEL_STACK_PADDING - \
- sizeof(struct pt_regs), \
+ .sp = (unsigned long)&__top_init_kernel_stack, \
}
extern unsigned long KSTK_ESP(struct task_struct *task);
diff --git a/arch/x86/include/asm/prom.h b/arch/x86/include/asm/prom.h
index 043758a2e6..365798cb44 100644
--- a/arch/x86/include/asm/prom.h
+++ b/arch/x86/include/asm/prom.h
@@ -23,19 +23,14 @@ extern int of_ioapic;
extern u64 initial_dtb;
extern void add_dtb(u64 data);
void x86_of_pci_init(void);
-void x86_dtb_parse_smp_config(void);
+void x86_flattree_get_config(void);
#else
static inline void add_dtb(u64 data) { }
static inline void x86_of_pci_init(void) { }
-static inline void x86_dtb_parse_smp_config(void) { }
+static inline void x86_flattree_get_config(void) { }
#define of_ioapic 0
#endif
-#ifdef CONFIG_OF_EARLY_FLATTREE
-void x86_flattree_get_config(void);
-#else
-static inline void x86_flattree_get_config(void) { }
-#endif
extern char cmd_line[COMMAND_LINE_SIZE];
#endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h
index cde8357bb2..a053c12939 100644
--- a/arch/x86/include/asm/qspinlock.h
+++ b/arch/x86/include/asm/qspinlock.h
@@ -85,6 +85,8 @@ DECLARE_STATIC_KEY_TRUE(virt_spin_lock_key);
#define virt_spin_lock virt_spin_lock
static inline bool virt_spin_lock(struct qspinlock *lock)
{
+ int val;
+
if (!static_branch_likely(&virt_spin_lock_key))
return false;
@@ -94,10 +96,13 @@ static inline bool virt_spin_lock(struct qspinlock *lock)
* horrible lock 'holder' preemption issues.
*/
- do {
- while (atomic_read(&lock->val) != 0)
- cpu_relax();
- } while (atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL) != 0);
+ __retry:
+ val = atomic_read(&lock->val);
+
+ if (val || !atomic_try_cmpxchg(&lock->val, &val, _Q_LOCKED_VAL)) {
+ cpu_relax();
+ goto __retry;
+ }
return true;
}
diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h
index ef9697f201..0a985784be 100644
--- a/arch/x86/include/asm/qspinlock_paravirt.h
+++ b/arch/x86/include/asm/qspinlock_paravirt.h
@@ -25,9 +25,9 @@ __PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath, ".spinlock.text");
*
* void __lockfunc __pv_queued_spin_unlock(struct qspinlock *lock)
* {
- * u8 lockval = cmpxchg(&lock->locked, _Q_LOCKED_VAL, 0);
+ * u8 lockval = _Q_LOCKED_VAL;
*
- * if (likely(lockval == _Q_LOCKED_VAL))
+ * if (try_cmpxchg(&lock->locked, &lockval, 0))
* return;
* pv_queued_spin_unlock_slowpath(lock, lockval);
* }
@@ -40,10 +40,9 @@ __PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath, ".spinlock.text");
#define PV_UNLOCK_ASM \
FRAME_BEGIN \
"push %rdx\n\t" \
- "mov $0x1,%eax\n\t" \
+ "mov $" __stringify(_Q_LOCKED_VAL) ",%eax\n\t" \
"xor %edx,%edx\n\t" \
LOCK_PREFIX "cmpxchg %dl,(%rdi)\n\t" \
- "cmp $0x1,%al\n\t" \
"jne .slowpath\n\t" \
"pop %rdx\n\t" \
FRAME_END \
diff --git a/arch/x86/include/asm/seccomp.h b/arch/x86/include/asm/seccomp.h
index fef16e3981..42bcd42d70 100644
--- a/arch/x86/include/asm/seccomp.h
+++ b/arch/x86/include/asm/seccomp.h
@@ -9,7 +9,7 @@
#endif
#ifdef CONFIG_COMPAT
-#include <asm/ia32_unistd.h>
+#include <asm/unistd_32_ia32.h>
#define __NR_seccomp_read_32 __NR_ia32_read
#define __NR_seccomp_write_32 __NR_ia32_write
#define __NR_seccomp_exit_32 __NR_ia32_exit
diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h
index b463fcbd4b..5a8246dd53 100644
--- a/arch/x86/include/asm/sev-common.h
+++ b/arch/x86/include/asm/sev-common.h
@@ -54,8 +54,10 @@
(((unsigned long)fn) << 32))
/* AP Reset Hold */
-#define GHCB_MSR_AP_RESET_HOLD_REQ 0x006
-#define GHCB_MSR_AP_RESET_HOLD_RESP 0x007
+#define GHCB_MSR_AP_RESET_HOLD_REQ 0x006
+#define GHCB_MSR_AP_RESET_HOLD_RESP 0x007
+#define GHCB_MSR_AP_RESET_HOLD_RESULT_POS 12
+#define GHCB_MSR_AP_RESET_HOLD_RESULT_MASK GENMASK_ULL(51, 0)
/* GHCB GPA Register */
#define GHCB_MSR_REG_GPA_REQ 0x012
@@ -99,6 +101,8 @@ enum psc_op {
/* GHCB Hypervisor Feature Request/Response */
#define GHCB_MSR_HV_FT_REQ 0x080
#define GHCB_MSR_HV_FT_RESP 0x081
+#define GHCB_MSR_HV_FT_POS 12
+#define GHCB_MSR_HV_FT_MASK GENMASK_ULL(51, 0)
#define GHCB_MSR_HV_FT_RESP_VAL(v) \
/* GHCBData[63:12] */ \
(((u64)(v) & GENMASK_ULL(63, 12)) >> 12)
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index 93ed60080c..ca20cc4e58 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -140,7 +140,7 @@ struct secrets_os_area {
#define VMPCK_KEY_LEN 32
/* See the SNP spec version 0.9 for secrets page format */
-struct snp_secrets_page_layout {
+struct snp_secrets_page {
u32 version;
u32 imien : 1,
rsvd1 : 31;
diff --git a/arch/x86/include/asm/shstk.h b/arch/x86/include/asm/shstk.h
index 42fee8959d..896909f306 100644
--- a/arch/x86/include/asm/shstk.h
+++ b/arch/x86/include/asm/shstk.h
@@ -21,6 +21,7 @@ unsigned long shstk_alloc_thread_stack(struct task_struct *p, unsigned long clon
void shstk_free(struct task_struct *p);
int setup_signal_shadow_stack(struct ksignal *ksig);
int restore_signal_shadow_stack(void);
+int shstk_update_last_frame(unsigned long val);
#else
static inline long shstk_prctl(struct task_struct *task, int option,
unsigned long arg2) { return -EINVAL; }
@@ -31,6 +32,7 @@ static inline unsigned long shstk_alloc_thread_stack(struct task_struct *p,
static inline void shstk_free(struct task_struct *p) {}
static inline int setup_signal_shadow_stack(struct ksignal *ksig) { return 0; }
static inline int restore_signal_shadow_stack(void) { return 0; }
+static inline int shstk_update_last_frame(unsigned long val) { return 0; }
#endif /* CONFIG_X86_USER_SHADOW_STACK */
#endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 2e9fc5c400..aec6e2d3aa 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -182,8 +182,8 @@ static __always_inline void clflush(volatile void *__p)
static inline void clflushopt(volatile void *__p)
{
- alternative_io(".byte 0x3e; clflush %P0",
- ".byte 0x66; clflush %P0",
+ alternative_io(".byte 0x3e; clflush %0",
+ ".byte 0x66; clflush %0",
X86_FEATURE_CLFLUSHOPT,
"+m" (*(volatile char __force *)__p));
}
@@ -205,9 +205,9 @@ static inline void clwb(volatile void *__p)
#ifdef CONFIG_X86_USER_SHADOW_STACK
static inline int write_user_shstk_64(u64 __user *addr, u64 val)
{
- asm goto("1: wrussq %[val], (%[addr])\n"
+ asm goto("1: wrussq %[val], %[addr]\n"
_ASM_EXTABLE(1b, %l[fail])
- :: [addr] "r" (addr), [val] "r" (val)
+ :: [addr] "m" (*addr), [val] "r" (val)
:: fail);
return 0;
fail:
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index 857d364b98..9d0b324eab 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/arch/x86/include/asm/string_64.h
@@ -30,37 +30,40 @@ void *__memset(void *s, int c, size_t n);
#define __HAVE_ARCH_MEMSET16
static inline void *memset16(uint16_t *s, uint16_t v, size_t n)
{
- long d0, d1;
- asm volatile("rep\n\t"
- "stosw"
- : "=&c" (d0), "=&D" (d1)
- : "a" (v), "1" (s), "0" (n)
- : "memory");
- return s;
+ const __auto_type s0 = s;
+ asm volatile (
+ "rep stosw"
+ : "+D" (s), "+c" (n)
+ : "a" (v)
+ : "memory"
+ );
+ return s0;
}
#define __HAVE_ARCH_MEMSET32
static inline void *memset32(uint32_t *s, uint32_t v, size_t n)
{
- long d0, d1;
- asm volatile("rep\n\t"
- "stosl"
- : "=&c" (d0), "=&D" (d1)
- : "a" (v), "1" (s), "0" (n)
- : "memory");
- return s;
+ const __auto_type s0 = s;
+ asm volatile (
+ "rep stosl"
+ : "+D" (s), "+c" (n)
+ : "a" (v)
+ : "memory"
+ );
+ return s0;
}
#define __HAVE_ARCH_MEMSET64
static inline void *memset64(uint64_t *s, uint64_t v, size_t n)
{
- long d0, d1;
- asm volatile("rep\n\t"
- "stosq"
- : "=&c" (d0), "=&D" (d1)
- : "a" (v), "1" (s), "0" (n)
- : "memory");
- return s;
+ const __auto_type s0 = s;
+ asm volatile (
+ "rep stosq"
+ : "+D" (s), "+c" (n)
+ : "a" (v)
+ : "memory"
+ );
+ return s0;
}
#endif
diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h
index 345aafbc19..6259f1937f 100644
--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -15,7 +15,7 @@
extern void text_poke_early(void *addr, const void *opcode, size_t len);
-extern void apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len);
+extern void apply_relocation(u8 *buf, const u8 * const instr, size_t instrlen, u8 *repl, size_t repl_len);
/*
* Clear and restore the kernel write-protection flag on the local CPU.
diff --git a/arch/x86/include/asm/vdso/gettimeofday.h b/arch/x86/include/asm/vdso/gettimeofday.h
index 8e048ca980..0ef36190ab 100644
--- a/arch/x86/include/asm/vdso/gettimeofday.h
+++ b/arch/x86/include/asm/vdso/gettimeofday.h
@@ -300,7 +300,7 @@ static inline bool arch_vdso_cycles_ok(u64 cycles)
#define vdso_cycles_ok arch_vdso_cycles_ok
/*
- * x86 specific delta calculation.
+ * x86 specific calculation of nanoseconds for the current cycle count
*
* The regular implementation assumes that clocksource reads are globally
* monotonic. The TSC can be slightly off across sockets which can cause
@@ -308,8 +308,8 @@ static inline bool arch_vdso_cycles_ok(u64 cycles)
* jump.
*
* Therefore it needs to be verified that @cycles are greater than
- * @last. If not then use @last, which is the base time of the current
- * conversion period.
+ * @vd->cycles_last. If not then use @vd->cycles_last, which is the base
+ * time of the current conversion period.
*
* This variant also uses a custom mask because while the clocksource mask of
* all the VDSO capable clocksources on x86 is U64_MAX, the above code uses
@@ -317,25 +317,37 @@ static inline bool arch_vdso_cycles_ok(u64 cycles)
* declares everything with the MSB/Sign-bit set as invalid. Therefore the
* effective mask is S64_MAX.
*/
-static __always_inline
-u64 vdso_calc_delta(u64 cycles, u64 last, u64 mask, u32 mult)
+static __always_inline u64 vdso_calc_ns(const struct vdso_data *vd, u64 cycles, u64 base)
{
- /*
- * Due to the MSB/Sign-bit being used as invalid marker (see
- * arch_vdso_cycles_valid() above), the effective mask is S64_MAX.
- */
- u64 delta = (cycles - last) & S64_MAX;
+ u64 delta = cycles - vd->cycle_last;
/*
- * Due to the above mentioned TSC wobbles, filter out negative motion.
- * Per the above masking, the effective sign bit is now bit 62.
+ * Negative motion and deltas which can cause multiplication
+ * overflow require special treatment. This check covers both as
+ * negative motion is guaranteed to be greater than @vd::max_cycles
+ * due to unsigned comparison.
+ *
+ * Due to the MSB/Sign-bit being used as invalid marker (see
+ * arch_vdso_cycles_valid() above), the effective mask is S64_MAX,
+ * but that case is also unlikely and will also take the unlikely path
+ * here.
*/
- if (unlikely(delta & (1ULL << 62)))
- return 0;
+ if (unlikely(delta > vd->max_cycles)) {
+ /*
+ * Due to the above mentioned TSC wobbles, filter out
+ * negative motion. Per the above masking, the effective
+ * sign bit is now bit 62.
+ */
+ if (delta & (1ULL << 62))
+ return base >> vd->shift;
+
+ /* Handle multiplication overflow gracefully */
+ return mul_u64_u32_add_u64_shr(delta & S64_MAX, vd->mult, base, vd->shift);
+ }
- return delta * mult;
+ return ((delta * vd->mult) + base) >> vd->shift;
}
-#define vdso_calc_delta vdso_calc_delta
+#define vdso_calc_ns vdso_calc_ns
#endif /* !__ASSEMBLY__ */
diff --git a/arch/x86/include/asm/video.h b/arch/x86/include/asm/video.h
new file mode 100644
index 0000000000..0950c9535f
--- /dev/null
+++ b/arch/x86/include/asm/video.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_VIDEO_H
+#define _ASM_X86_VIDEO_H
+
+#include <linux/types.h>
+
+#include <asm/page.h>
+
+struct device;
+
+pgprot_t pgprot_framebuffer(pgprot_t prot,
+ unsigned long vm_start, unsigned long vm_end,
+ unsigned long offset);
+#define pgprot_framebuffer pgprot_framebuffer
+
+bool video_is_primary_device(struct device *dev);
+#define video_is_primary_device video_is_primary_device
+
+#include <asm-generic/video.h>
+
+#endif /* _ASM_X86_VIDEO_H */
diff --git a/arch/x86/include/asm/vm86.h b/arch/x86/include/asm/vm86.h
index 9e8ac5073e..62ee199099 100644
--- a/arch/x86/include/asm/vm86.h
+++ b/arch/x86/include/asm/vm86.h
@@ -84,7 +84,7 @@ static inline int handle_vm86_trap(struct kernel_vm86_regs *a, long b, int c)
static inline void save_v86_state(struct kernel_vm86_regs *a, int b) { }
-#define free_vm86(t) do { } while(0)
+#define free_vm86(task) do { (void)(task); } while(0)
#endif /* CONFIG_VM86 */
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 4dba173630..d77a31039f 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -71,6 +71,7 @@
#define SECONDARY_EXEC_ENCLS_EXITING VMCS_CONTROL_BIT(ENCLS_EXITING)
#define SECONDARY_EXEC_RDSEED_EXITING VMCS_CONTROL_BIT(RDSEED_EXITING)
#define SECONDARY_EXEC_ENABLE_PML VMCS_CONTROL_BIT(PAGE_MOD_LOGGING)
+#define SECONDARY_EXEC_EPT_VIOLATION_VE VMCS_CONTROL_BIT(EPT_VIOLATION_VE)
#define SECONDARY_EXEC_PT_CONCEAL_VMX VMCS_CONTROL_BIT(PT_CONCEAL_VMX)
#define SECONDARY_EXEC_ENABLE_XSAVES VMCS_CONTROL_BIT(XSAVES)
#define SECONDARY_EXEC_MODE_BASED_EPT_EXEC VMCS_CONTROL_BIT(MODE_BASED_EPT_EXEC)
@@ -226,6 +227,8 @@ enum vmcs_field {
VMREAD_BITMAP_HIGH = 0x00002027,
VMWRITE_BITMAP = 0x00002028,
VMWRITE_BITMAP_HIGH = 0x00002029,
+ VE_INFORMATION_ADDRESS = 0x0000202A,
+ VE_INFORMATION_ADDRESS_HIGH = 0x0000202B,
XSS_EXIT_BITMAP = 0x0000202C,
XSS_EXIT_BITMAP_HIGH = 0x0000202D,
ENCLS_EXITING_BITMAP = 0x0000202E,
@@ -514,6 +517,7 @@ enum vmcs_field {
#define VMX_EPT_IPAT_BIT (1ull << 6)
#define VMX_EPT_ACCESS_BIT (1ull << 8)
#define VMX_EPT_DIRTY_BIT (1ull << 9)
+#define VMX_EPT_SUPPRESS_VE_BIT (1ull << 63)
#define VMX_EPT_RWX_MASK (VMX_EPT_READABLE_MASK | \
VMX_EPT_WRITABLE_MASK | \
VMX_EPT_EXECUTABLE_MASK)
@@ -630,4 +634,13 @@ enum vmx_l1d_flush_state {
extern enum vmx_l1d_flush_state l1tf_vmx_mitigation;
+struct vmx_ve_information {
+ u32 exit_reason;
+ u32 delivery;
+ u64 exit_qualification;
+ u64 guest_linear_address;
+ u64 guest_physical_address;
+ u16 eptp_index;
+};
+
#endif
diff --git a/arch/x86/include/asm/vmxfeatures.h b/arch/x86/include/asm/vmxfeatures.h
index 266daf5b5b..695f366648 100644
--- a/arch/x86/include/asm/vmxfeatures.h
+++ b/arch/x86/include/asm/vmxfeatures.h
@@ -77,7 +77,7 @@
#define VMX_FEATURE_ENCLS_EXITING ( 2*32+ 15) /* "" VM-Exit on ENCLS (leaf dependent) */
#define VMX_FEATURE_RDSEED_EXITING ( 2*32+ 16) /* "" VM-Exit on RDSEED */
#define VMX_FEATURE_PAGE_MOD_LOGGING ( 2*32+ 17) /* "pml" Log dirty pages into buffer */
-#define VMX_FEATURE_EPT_VIOLATION_VE ( 2*32+ 18) /* "" Conditionally reflect EPT violations as #VE exceptions */
+#define VMX_FEATURE_EPT_VIOLATION_VE ( 2*32+ 18) /* Conditionally reflect EPT violations as #VE exceptions */
#define VMX_FEATURE_PT_CONCEAL_VMX ( 2*32+ 19) /* "" Suppress VMX indicators in Processor Trace */
#define VMX_FEATURE_XSAVES ( 2*32+ 20) /* "" Enable XSAVES and XRSTORS in guest */
#define VMX_FEATURE_MODE_BASED_EPT_EXEC ( 2*32+ 22) /* "ept_mode_based_exec" Enable separate EPT EXEC bits for supervisor vs. user */