summaryrefslogtreecommitdiff
path: root/arch/x86/include
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/include')
-rw-r--r--arch/x86/include/asm/acpi.h2
-rw-r--r--arch/x86/include/asm/apic.h7
-rw-r--r--arch/x86/include/asm/atomic.h33
-rw-r--r--arch/x86/include/asm/atomic64_64.h46
-rw-r--r--arch/x86/include/asm/bug.h80
-rw-r--r--arch/x86/include/asm/cmpxchg.h70
-rw-r--r--arch/x86/include/asm/cpufeatures.h3
-rw-r--r--arch/x86/include/asm/e820.h73
-rw-r--r--arch/x86/include/asm/e820/api.h50
-rw-r--r--arch/x86/include/asm/e820/types.h104
-rw-r--r--arch/x86/include/asm/elf.h2
-rw-r--r--arch/x86/include/asm/gart.h4
-rw-r--r--arch/x86/include/asm/intel-family.h6
-rw-r--r--arch/x86/include/asm/intel_rdt.h157
-rw-r--r--arch/x86/include/asm/kprobes.h7
-rw-r--r--arch/x86/include/asm/kvm_page_track.h1
-rw-r--r--arch/x86/include/asm/mce.h12
-rw-r--r--arch/x86/include/asm/mpspec.h4
-rw-r--r--arch/x86/include/asm/msr-index.h11
-rw-r--r--arch/x86/include/asm/page_64.h16
-rw-r--r--arch/x86/include/asm/pci_x86.h2
-rw-r--r--arch/x86/include/asm/pgtable-3level.h3
-rw-r--r--arch/x86/include/asm/pgtable.h5
-rw-r--r--arch/x86/include/asm/pmem.h42
-rw-r--r--arch/x86/include/asm/processor.h13
-rw-r--r--arch/x86/include/asm/proto.h4
-rw-r--r--arch/x86/include/asm/purgatory.h20
-rw-r--r--arch/x86/include/asm/reboot.h1
-rw-r--r--arch/x86/include/asm/smp.h35
-rw-r--r--arch/x86/include/asm/thread_info.h6
-rw-r--r--arch/x86/include/asm/timer.h2
-rw-r--r--arch/x86/include/asm/tlbflush.h12
-rw-r--r--arch/x86/include/asm/uaccess.h70
-rw-r--r--arch/x86/include/asm/uaccess_32.h127
-rw-r--r--arch/x86/include/asm/uaccess_64.h128
-rw-r--r--arch/x86/include/asm/unwind.h2
-rw-r--r--arch/x86/include/asm/uv/uv_bau.h82
-rw-r--r--arch/x86/include/asm/uv/uv_hub.h8
-rw-r--r--arch/x86/include/asm/xen/page.h1
-rw-r--r--arch/x86/include/uapi/asm/bootparam.h18
-rw-r--r--arch/x86/include/uapi/asm/prctl.h11
41 files changed, 704 insertions, 576 deletions
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 395b69551fce..2efc768e4362 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -52,6 +52,8 @@ extern u8 acpi_sci_flags;
extern int acpi_sci_override_gsi;
void acpi_pic_sci_set_trigger(unsigned int, u16);
+struct device;
+
extern int (*__acpi_register_gsi)(struct device *dev, u32 gsi,
int trigger, int polarity);
extern void (*__acpi_unregister_gsi)(u32 gsi);
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 730ef65e8393..bdffcd9eab2b 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -252,12 +252,6 @@ static inline int x2apic_enabled(void) { return 0; }
#define x2apic_supported() (0)
#endif /* !CONFIG_X86_X2APIC */
-#ifdef CONFIG_X86_64
-#define SET_APIC_ID(x) (apic->set_apic_id(x))
-#else
-
-#endif
-
/*
* Copyright 2004 James Cleverdon, IBM.
* Subject to the GNU Public License, v.2
@@ -299,6 +293,7 @@ struct apic {
int (*phys_pkg_id)(int cpuid_apic, int index_msb);
unsigned int (*get_apic_id)(unsigned long x);
+ /* Can't be NULL on 64-bit */
unsigned long (*set_apic_id)(unsigned int id);
int (*cpu_mask_to_apicid_and)(const struct cpumask *cpumask,
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 14635c5ea025..caa5798c92f4 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -186,6 +186,12 @@ static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new)
return cmpxchg(&v->counter, old, new);
}
+#define atomic_try_cmpxchg atomic_try_cmpxchg
+static __always_inline bool atomic_try_cmpxchg(atomic_t *v, int *old, int new)
+{
+ return try_cmpxchg(&v->counter, old, new);
+}
+
static inline int atomic_xchg(atomic_t *v, int new)
{
return xchg(&v->counter, new);
@@ -201,16 +207,12 @@ static inline void atomic_##op(int i, atomic_t *v) \
}
#define ATOMIC_FETCH_OP(op, c_op) \
-static inline int atomic_fetch_##op(int i, atomic_t *v) \
+static inline int atomic_fetch_##op(int i, atomic_t *v) \
{ \
- int old, val = atomic_read(v); \
- for (;;) { \
- old = atomic_cmpxchg(v, val, val c_op i); \
- if (old == val) \
- break; \
- val = old; \
- } \
- return old; \
+ int val = atomic_read(v); \
+ do { \
+ } while (!atomic_try_cmpxchg(v, &val, val c_op i)); \
+ return val; \
}
#define ATOMIC_OPS(op, c_op) \
@@ -236,16 +238,11 @@ ATOMIC_OPS(xor, ^)
*/
static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
{
- int c, old;
- c = atomic_read(v);
- for (;;) {
- if (unlikely(c == (u)))
- break;
- old = atomic_cmpxchg((v), c, c + (a));
- if (likely(old == c))
+ int c = atomic_read(v);
+ do {
+ if (unlikely(c == u))
break;
- c = old;
- }
+ } while (!atomic_try_cmpxchg(v, &c, c + a));
return c;
}
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 89ed2f6ae2f7..6189a433c9a9 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -176,6 +176,12 @@ static inline long atomic64_cmpxchg(atomic64_t *v, long old, long new)
return cmpxchg(&v->counter, old, new);
}
+#define atomic64_try_cmpxchg atomic64_try_cmpxchg
+static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, long *old, long new)
+{
+ return try_cmpxchg(&v->counter, old, new);
+}
+
static inline long atomic64_xchg(atomic64_t *v, long new)
{
return xchg(&v->counter, new);
@@ -192,17 +198,12 @@ static inline long atomic64_xchg(atomic64_t *v, long new)
*/
static inline bool atomic64_add_unless(atomic64_t *v, long a, long u)
{
- long c, old;
- c = atomic64_read(v);
- for (;;) {
- if (unlikely(c == (u)))
- break;
- old = atomic64_cmpxchg((v), c, c + (a));
- if (likely(old == c))
- break;
- c = old;
- }
- return c != (u);
+ long c = atomic64_read(v);
+ do {
+ if (unlikely(c == u))
+ return false;
+ } while (!atomic64_try_cmpxchg(v, &c, c + a));
+ return true;
}
#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
@@ -216,17 +217,12 @@ static inline bool atomic64_add_unless(atomic64_t *v, long a, long u)
*/
static inline long atomic64_dec_if_positive(atomic64_t *v)
{
- long c, old, dec;
- c = atomic64_read(v);
- for (;;) {
+ long dec, c = atomic64_read(v);
+ do {
dec = c - 1;
if (unlikely(dec < 0))
break;
- old = atomic64_cmpxchg((v), c, dec);
- if (likely(old == c))
- break;
- c = old;
- }
+ } while (!atomic64_try_cmpxchg(v, &c, dec));
return dec;
}
@@ -242,14 +238,10 @@ static inline void atomic64_##op(long i, atomic64_t *v) \
#define ATOMIC64_FETCH_OP(op, c_op) \
static inline long atomic64_fetch_##op(long i, atomic64_t *v) \
{ \
- long old, val = atomic64_read(v); \
- for (;;) { \
- old = atomic64_cmpxchg(v, val, val c_op i); \
- if (old == val) \
- break; \
- val = old; \
- } \
- return old; \
+ long val = atomic64_read(v); \
+ do { \
+ } while (!atomic64_try_cmpxchg(v, &val, val c_op i)); \
+ return val; \
}
#define ATOMIC64_OPS(op, c_op) \
diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index ba38ebbaced3..39e702d90cdb 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -1,36 +1,82 @@
#ifndef _ASM_X86_BUG_H
#define _ASM_X86_BUG_H
-#define HAVE_ARCH_BUG
+#include <linux/stringify.h>
-#ifdef CONFIG_DEBUG_BUGVERBOSE
+/*
+ * Since some emulators terminate on UD2, we cannot use it for WARN.
+ * Since various instruction decoders disagree on the length of UD1,
+ * we cannot use it either. So use UD0 for WARN.
+ *
+ * (binutils knows about "ud1" but {en,de}codes it as 2 bytes, whereas
+ * our kernel decoder thinks it takes a ModRM byte, which seems consistent
+ * with various things like the Intel SDM instruction encoding rules)
+ */
+
+#define ASM_UD0 ".byte 0x0f, 0xff"
+#define ASM_UD1 ".byte 0x0f, 0xb9" /* + ModRM */
+#define ASM_UD2 ".byte 0x0f, 0x0b"
+
+#define INSN_UD0 0xff0f
+#define INSN_UD2 0x0b0f
+
+#define LEN_UD0 2
+
+#ifdef CONFIG_GENERIC_BUG
#ifdef CONFIG_X86_32
-# define __BUG_C0 "2:\t.long 1b, %c0\n"
+# define __BUG_REL(val) ".long " __stringify(val)
#else
-# define __BUG_C0 "2:\t.long 1b - 2b, %c0 - 2b\n"
+# define __BUG_REL(val) ".long " __stringify(val) " - 2b"
#endif
-#define BUG() \
-do { \
- asm volatile("1:\tud2\n" \
- ".pushsection __bug_table,\"a\"\n" \
- __BUG_C0 \
- "\t.word %c1, 0\n" \
- "\t.org 2b+%c2\n" \
- ".popsection" \
- : : "i" (__FILE__), "i" (__LINE__), \
- "i" (sizeof(struct bug_entry))); \
- unreachable(); \
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+
+#define _BUG_FLAGS(ins, flags) \
+do { \
+ asm volatile("1:\t" ins "\n" \
+ ".pushsection __bug_table,\"a\"\n" \
+ "2:\t" __BUG_REL(1b) "\t# bug_entry::bug_addr\n" \
+ "\t" __BUG_REL(%c0) "\t# bug_entry::file\n" \
+ "\t.word %c1" "\t# bug_entry::line\n" \
+ "\t.word %c2" "\t# bug_entry::flags\n" \
+ "\t.org 2b+%c3\n" \
+ ".popsection" \
+ : : "i" (__FILE__), "i" (__LINE__), \
+ "i" (flags), \
+ "i" (sizeof(struct bug_entry))); \
} while (0)
+#else /* !CONFIG_DEBUG_BUGVERBOSE */
+
+#define _BUG_FLAGS(ins, flags) \
+do { \
+ asm volatile("1:\t" ins "\n" \
+ ".pushsection __bug_table,\"a\"\n" \
+ "2:\t" __BUG_REL(1b) "\t# bug_entry::bug_addr\n" \
+ "\t.word %c0" "\t# bug_entry::flags\n" \
+ "\t.org 2b+%c1\n" \
+ ".popsection" \
+ : : "i" (flags), \
+ "i" (sizeof(struct bug_entry))); \
+} while (0)
+
+#endif /* CONFIG_DEBUG_BUGVERBOSE */
+
#else
+
+#define _BUG_FLAGS(ins, flags) asm volatile(ins)
+
+#endif /* CONFIG_GENERIC_BUG */
+
+#define HAVE_ARCH_BUG
#define BUG() \
do { \
- asm volatile("ud2"); \
+ _BUG_FLAGS(ASM_UD2, 0); \
unreachable(); \
} while (0)
-#endif
+
+#define __WARN_FLAGS(flags) _BUG_FLAGS(ASM_UD0, BUGFLAG_WARNING|(flags))
#include <asm-generic/bug.h>
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index 97848cdfcb1a..d90296d061e8 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -153,6 +153,76 @@ extern void __add_wrong_size(void)
#define cmpxchg_local(ptr, old, new) \
__cmpxchg_local(ptr, old, new, sizeof(*(ptr)))
+
+#define __raw_try_cmpxchg(_ptr, _pold, _new, size, lock) \
+({ \
+ bool success; \
+ __typeof__(_ptr) _old = (_pold); \
+ __typeof__(*(_ptr)) __old = *_old; \
+ __typeof__(*(_ptr)) __new = (_new); \
+ switch (size) { \
+ case __X86_CASE_B: \
+ { \
+ volatile u8 *__ptr = (volatile u8 *)(_ptr); \
+ asm volatile(lock "cmpxchgb %[new], %[ptr]" \
+ CC_SET(z) \
+ : CC_OUT(z) (success), \
+ [ptr] "+m" (*__ptr), \
+ [old] "+a" (__old) \
+ : [new] "q" (__new) \
+ : "memory"); \
+ break; \
+ } \
+ case __X86_CASE_W: \
+ { \
+ volatile u16 *__ptr = (volatile u16 *)(_ptr); \
+ asm volatile(lock "cmpxchgw %[new], %[ptr]" \
+ CC_SET(z) \
+ : CC_OUT(z) (success), \
+ [ptr] "+m" (*__ptr), \
+ [old] "+a" (__old) \
+ : [new] "r" (__new) \
+ : "memory"); \
+ break; \
+ } \
+ case __X86_CASE_L: \
+ { \
+ volatile u32 *__ptr = (volatile u32 *)(_ptr); \
+ asm volatile(lock "cmpxchgl %[new], %[ptr]" \
+ CC_SET(z) \
+ : CC_OUT(z) (success), \
+ [ptr] "+m" (*__ptr), \
+ [old] "+a" (__old) \
+ : [new] "r" (__new) \
+ : "memory"); \
+ break; \
+ } \
+ case __X86_CASE_Q: \
+ { \
+ volatile u64 *__ptr = (volatile u64 *)(_ptr); \
+ asm volatile(lock "cmpxchgq %[new], %[ptr]" \
+ CC_SET(z) \
+ : CC_OUT(z) (success), \
+ [ptr] "+m" (*__ptr), \
+ [old] "+a" (__old) \
+ : [new] "r" (__new) \
+ : "memory"); \
+ break; \
+ } \
+ default: \
+ __cmpxchg_wrong_size(); \
+ } \
+ if (unlikely(!success)) \
+ *_old = __old; \
+ likely(success); \
+})
+
+#define __try_cmpxchg(ptr, pold, new, size) \
+ __raw_try_cmpxchg((ptr), (pold), (new), (size), LOCK_PREFIX)
+
+#define try_cmpxchg(ptr, pold, new) \
+ __try_cmpxchg((ptr), (pold), (new), sizeof(*(ptr)))
+
/*
* xadd() adds "inc" to "*ptr" and atomically returns the previous
* value of "*ptr".
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index b04bb6dfed7f..2701e5f8145b 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -187,6 +187,7 @@
* Reuse free bits when adding new feature flags!
*/
#define X86_FEATURE_RING3MWAIT ( 7*32+ 0) /* Ring 3 MONITOR/MWAIT */
+#define X86_FEATURE_CPUID_FAULT ( 7*32+ 1) /* Intel CPUID faulting */
#define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */
#define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
#define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */
@@ -201,6 +202,8 @@
#define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */
#define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */
+
/* Virtualization flags: Linux defined, word 8 */
#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */
#define X86_FEATURE_VNMI ( 8*32+ 1) /* Intel Virtual NMI */
diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
deleted file mode 100644
index 67313f3a9874..000000000000
--- a/arch/x86/include/asm/e820.h
+++ /dev/null
@@ -1,73 +0,0 @@
-#ifndef _ASM_X86_E820_H
-#define _ASM_X86_E820_H
-
-/*
- * E820_X_MAX is the maximum size of the extended E820 table. The extended
- * table may contain up to 3 extra E820 entries per possible NUMA node, so we
- * make room for 3 * MAX_NUMNODES possible entries, beyond the standard 128.
- * Also note that E820_X_MAX *must* be defined before we include uapi/asm/e820.h.
- */
-#include <linux/numa.h>
-#define E820_X_MAX (E820MAX + 3 * MAX_NUMNODES)
-
-#include <uapi/asm/e820.h>
-
-#ifndef __ASSEMBLY__
-/* see comment in arch/x86/kernel/e820.c */
-extern struct e820map *e820;
-extern struct e820map *e820_saved;
-
-extern unsigned long pci_mem_start;
-extern int e820_any_mapped(u64 start, u64 end, unsigned type);
-extern int e820_all_mapped(u64 start, u64 end, unsigned type);
-extern void e820_add_region(u64 start, u64 size, int type);
-extern void e820_print_map(char *who);
-extern int
-sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, u32 *pnr_map);
-extern u64 e820_update_range(u64 start, u64 size, unsigned old_type,
- unsigned new_type);
-extern u64 e820_remove_range(u64 start, u64 size, unsigned old_type,
- int checktype);
-extern void update_e820(void);
-extern void e820_setup_gap(void);
-struct setup_data;
-extern void parse_e820_ext(u64 phys_addr, u32 data_len);
-
-#if defined(CONFIG_X86_64) || \
- (defined(CONFIG_X86_32) && defined(CONFIG_HIBERNATION))
-extern void e820_mark_nosave_regions(unsigned long limit_pfn);
-#else
-static inline void e820_mark_nosave_regions(unsigned long limit_pfn)
-{
-}
-#endif
-
-extern unsigned long e820_end_of_ram_pfn(void);
-extern unsigned long e820_end_of_low_ram_pfn(void);
-extern u64 early_reserve_e820(u64 sizet, u64 align);
-
-void memblock_x86_fill(void);
-void memblock_find_dma_reserve(void);
-
-extern void finish_e820_parsing(void);
-extern void e820_reserve_resources(void);
-extern void e820_reserve_resources_late(void);
-extern void setup_memory_map(void);
-extern char *default_machine_specific_memory_setup(void);
-
-extern void e820_reallocate_tables(void);
-
-/*
- * Returns true iff the specified range [s,e) is completely contained inside
- * the ISA region.
- */
-static inline bool is_ISA_range(u64 s, u64 e)
-{
- return s >= ISA_START_ADDRESS && e <= ISA_END_ADDRESS;
-}
-
-#endif /* __ASSEMBLY__ */
-#include <linux/ioport.h>
-
-#define HIGH_MEMORY (1024*1024)
-#endif /* _ASM_X86_E820_H */
diff --git a/arch/x86/include/asm/e820/api.h b/arch/x86/include/asm/e820/api.h
new file mode 100644
index 000000000000..8e0f8b85b209
--- /dev/null
+++ b/arch/x86/include/asm/e820/api.h
@@ -0,0 +1,50 @@
+#ifndef _ASM_E820_API_H
+#define _ASM_E820_API_H
+
+#include <asm/e820/types.h>
+
+extern struct e820_table *e820_table;
+extern struct e820_table *e820_table_firmware;
+
+extern unsigned long pci_mem_start;
+
+extern bool e820__mapped_any(u64 start, u64 end, enum e820_type type);
+extern bool e820__mapped_all(u64 start, u64 end, enum e820_type type);
+
+extern void e820__range_add (u64 start, u64 size, enum e820_type type);
+extern u64 e820__range_update(u64 start, u64 size, enum e820_type old_type, enum e820_type new_type);
+extern u64 e820__range_remove(u64 start, u64 size, enum e820_type old_type, bool check_type);
+
+extern void e820__print_table(char *who);
+extern int e820__update_table(struct e820_table *table);
+extern void e820__update_table_print(void);
+
+extern unsigned long e820__end_of_ram_pfn(void);
+extern unsigned long e820__end_of_low_ram_pfn(void);
+
+extern u64 e820__memblock_alloc_reserved(u64 size, u64 align);
+extern void e820__memblock_setup(void);
+
+extern void e820__reserve_setup_data(void);
+extern void e820__finish_early_params(void);
+extern void e820__reserve_resources(void);
+extern void e820__reserve_resources_late(void);
+
+extern void e820__memory_setup(void);
+extern void e820__memory_setup_extended(u64 phys_addr, u32 data_len);
+extern char *e820__memory_setup_default(void);
+extern void e820__setup_pci_gap(void);
+
+extern void e820__reallocate_tables(void);
+extern void e820__register_nosave_regions(unsigned long limit_pfn);
+
+/*
+ * Returns true iff the specified range [start,end) is completely contained inside
+ * the ISA region.
+ */
+static inline bool is_ISA_range(u64 start, u64 end)
+{
+ return start >= ISA_START_ADDRESS && end <= ISA_END_ADDRESS;
+}
+
+#endif /* _ASM_E820_API_H */
diff --git a/arch/x86/include/asm/e820/types.h b/arch/x86/include/asm/e820/types.h
new file mode 100644
index 000000000000..4adeed03a9a1
--- /dev/null
+++ b/arch/x86/include/asm/e820/types.h
@@ -0,0 +1,104 @@
+#ifndef _ASM_E820_TYPES_H
+#define _ASM_E820_TYPES_H
+
+#include <uapi/asm/bootparam.h>
+
+/*
+ * These are the E820 types known to the kernel:
+ */
+enum e820_type {
+ E820_TYPE_RAM = 1,
+ E820_TYPE_RESERVED = 2,
+ E820_TYPE_ACPI = 3,
+ E820_TYPE_NVS = 4,
+ E820_TYPE_UNUSABLE = 5,
+ E820_TYPE_PMEM = 7,
+
+ /*
+ * This is a non-standardized way to represent ADR or
+ * NVDIMM regions that persist over a reboot.
+ *
+ * The kernel will ignore their special capabilities
+ * unless the CONFIG_X86_PMEM_LEGACY=y option is set.
+ *
+ * ( Note that older platforms also used 6 for the same
+ * type of memory, but newer versions switched to 12 as
+ * 6 was assigned differently. Some time they will learn... )
+ */
+ E820_TYPE_PRAM = 12,
+
+ /*
+ * Reserved RAM used by the kernel itself if
+ * CONFIG_INTEL_TXT=y is enabled, memory of this type
+ * will be included in the S3 integrity calculation
+ * and so should not include any memory that the BIOS
+ * might alter over the S3 transition:
+ */
+ E820_TYPE_RESERVED_KERN = 128,
+};
+
+/*
+ * A single E820 map entry, describing a memory range of [addr...addr+size-1],
+ * of 'type' memory type:
+ *
+ * (We pack it because there can be thousands of them on large systems.)
+ */
+struct e820_entry {
+ u64 addr;
+ u64 size;
+ enum e820_type type;
+} __attribute__((packed));
+
+/*
+ * The legacy E820 BIOS limits us to 128 (E820_MAX_ENTRIES_ZEROPAGE) nodes
+ * due to the constrained space in the zeropage.
+ *
+ * On large systems we can easily have thousands of nodes with RAM,
+ * which cannot be fit into so few entries - so we have a mechanism
+ * to extend the e820 table size at build-time, via the E820_MAX_ENTRIES
+ * define below.
+ *
+ * ( Those extra entries are enumerated via the EFI memory map, not
+ * via the legacy zeropage mechanism. )
+ *
+ * Size our internal memory map tables to have room for these additional
+ * entries, based on a heuristic calculation: up to three entries per
+ * NUMA node, plus E820_MAX_ENTRIES_ZEROPAGE for some extra space.
+ *
+ * This allows for bootstrap/firmware quirks such as possible duplicate
+ * E820 entries that might need room in the same arrays, prior to the
+ * call to e820__update_table() to remove duplicates. The allowance
+ * of three memory map entries per node is "enough" entries for
+ * the initial hardware platform motivating this mechanism to make
+ * use of additional EFI map entries. Future platforms may want
+ * to allow more than three entries per node or otherwise refine
+ * this size.
+ */
+
+#include <linux/numa.h>
+
+#define E820_MAX_ENTRIES (E820_MAX_ENTRIES_ZEROPAGE + 3*MAX_NUMNODES)
+
+/*
+ * The whole array of E820 entries:
+ */
+struct e820_table {
+ __u32 nr_entries;
+ struct e820_entry entries[E820_MAX_ENTRIES];
+};
+
+/*
+ * Various well-known legacy memory ranges in physical memory:
+ */
+#define ISA_START_ADDRESS 0x000a0000
+#define ISA_END_ADDRESS 0x00100000
+
+#define BIOS_BEGIN 0x000a0000
+#define BIOS_END 0x00100000
+
+#define HIGH_MEMORY 0x00100000
+
+#define BIOS_ROM_BASE 0xffe00000
+#define BIOS_ROM_END 0xffffffff
+
+#endif /* _ASM_E820_TYPES_H */
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 9d49c18b5ea9..3762536619f8 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -287,7 +287,7 @@ struct task_struct;
#define ARCH_DLINFO_IA32 \
do { \
- if (vdso32_enabled) { \
+ if (VDSO_CURRENT_BASE) { \
NEW_AUX_ENT(AT_SYSINFO, VDSO_ENTRY); \
NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_CURRENT_BASE); \
} \
diff --git a/arch/x86/include/asm/gart.h b/arch/x86/include/asm/gart.h
index 156cd5d18d2a..1d268098ac2e 100644
--- a/arch/x86/include/asm/gart.h
+++ b/arch/x86/include/asm/gart.h
@@ -1,7 +1,7 @@
#ifndef _ASM_X86_GART_H
#define _ASM_X86_GART_H
-#include <asm/e820.h>
+#include <asm/e820/api.h>
extern void set_up_gart_resume(u32, u32);
@@ -97,7 +97,7 @@ static inline int aperture_valid(u64 aper_base, u32 aper_size, u32 min_size)
printk(KERN_INFO "Aperture beyond 4GB. Ignoring.\n");
return 0;
}
- if (e820_any_mapped(aper_base, aper_base + aper_size, E820_RAM)) {
+ if (e820__mapped_any(aper_base, aper_base + aper_size, E820_TYPE_RAM)) {
printk(KERN_INFO "Aperture pointing to e820 RAM. Ignoring.\n");
return 0;
}
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 9814db42b790..75b748a1deb8 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -12,6 +12,7 @@
*/
#define INTEL_FAM6_CORE_YONAH 0x0E
+
#define INTEL_FAM6_CORE2_MEROM 0x0F
#define INTEL_FAM6_CORE2_MEROM_L 0x16
#define INTEL_FAM6_CORE2_PENRYN 0x17
@@ -21,6 +22,7 @@
#define INTEL_FAM6_NEHALEM_G 0x1F /* Auburndale / Havendale */
#define INTEL_FAM6_NEHALEM_EP 0x1A
#define INTEL_FAM6_NEHALEM_EX 0x2E
+
#define INTEL_FAM6_WESTMERE 0x25
#define INTEL_FAM6_WESTMERE_EP 0x2C
#define INTEL_FAM6_WESTMERE_EX 0x2F
@@ -36,9 +38,9 @@
#define INTEL_FAM6_HASWELL_GT3E 0x46
#define INTEL_FAM6_BROADWELL_CORE 0x3D
-#define INTEL_FAM6_BROADWELL_XEON_D 0x56
#define INTEL_FAM6_BROADWELL_GT3E 0x47
#define INTEL_FAM6_BROADWELL_X 0x4F
+#define INTEL_FAM6_BROADWELL_XEON_D 0x56
#define INTEL_FAM6_SKYLAKE_MOBILE 0x4E
#define INTEL_FAM6_SKYLAKE_DESKTOP 0x5E
@@ -59,8 +61,8 @@
#define INTEL_FAM6_ATOM_MERRIFIELD 0x4A /* Tangier */
#define INTEL_FAM6_ATOM_MOOREFIELD 0x5A /* Anniedale */
#define INTEL_FAM6_ATOM_GOLDMONT 0x5C
-#define INTEL_FAM6_ATOM_GEMINI_LAKE 0x7A
#define INTEL_FAM6_ATOM_DENVERTON 0x5F /* Goldmont Microserver */
+#define INTEL_FAM6_ATOM_GEMINI_LAKE 0x7A
/* Xeon Phi */
diff --git a/arch/x86/include/asm/intel_rdt.h b/arch/x86/include/asm/intel_rdt.h
index 0d64397cee58..597dc4995678 100644
--- a/arch/x86/include/asm/intel_rdt.h
+++ b/arch/x86/include/asm/intel_rdt.h
@@ -12,6 +12,7 @@
#define IA32_L3_QOS_CFG 0xc81
#define IA32_L3_CBM_BASE 0xc90
#define IA32_L2_CBM_BASE 0xd10
+#define IA32_MBA_THRTL_BASE 0xd50
#define L3_QOS_CDP_ENABLE 0x01ULL
@@ -37,23 +38,30 @@ struct rdtgroup {
/* rdtgroup.flags */
#define RDT_DELETED 1
+/* rftype.flags */
+#define RFTYPE_FLAGS_CPUS_LIST 1
+
/* List of all resource groups */
extern struct list_head rdt_all_groups;
+extern int max_name_width, max_data_width;
+
int __init rdtgroup_init(void);
/**
* struct rftype - describe each file in the resctrl file system
- * @name: file name
- * @mode: access mode
- * @kf_ops: operations
- * @seq_show: show content of the file
- * @write: write to the file
+ * @name: File name
+ * @mode: Access mode
+ * @kf_ops: File operations
+ * @flags: File specific RFTYPE_FLAGS_* flags
+ * @seq_show: Show content of the file
+ * @write: Write to the file
*/
struct rftype {
char *name;
umode_t mode;
struct kernfs_ops *kf_ops;
+ unsigned long flags;
int (*seq_show)(struct kernfs_open_file *of,
struct seq_file *sf, void *v);
@@ -67,54 +75,21 @@ struct rftype {
};
/**
- * struct rdt_resource - attributes of an RDT resource
- * @enabled: Is this feature enabled on this machine
- * @capable: Is this feature available on this machine
- * @name: Name to use in "schemata" file
- * @num_closid: Number of CLOSIDs available
- * @max_cbm: Largest Cache Bit Mask allowed
- * @min_cbm_bits: Minimum number of consecutive bits to be set
- * in a cache bit mask
- * @domains: All domains for this resource
- * @num_domains: Number of domains active
- * @msr_base: Base MSR address for CBMs
- * @tmp_cbms: Scratch space when updating schemata
- * @num_tmp_cbms: Number of CBMs in tmp_cbms
- * @cache_level: Which cache level defines scope of this domain
- * @cbm_idx_multi: Multiplier of CBM index
- * @cbm_idx_offset: Offset of CBM index. CBM index is computed by:
- * closid * cbm_idx_multi + cbm_idx_offset
- */
-struct rdt_resource {
- bool enabled;
- bool capable;
- char *name;
- int num_closid;
- int cbm_len;
- int min_cbm_bits;
- u32 max_cbm;
- struct list_head domains;
- int num_domains;
- int msr_base;
- u32 *tmp_cbms;
- int num_tmp_cbms;
- int cache_level;
- int cbm_idx_multi;
- int cbm_idx_offset;
-};
-
-/**
* struct rdt_domain - group of cpus sharing an RDT resource
* @list: all instances of this resource
* @id: unique id for this instance
* @cpu_mask: which cpus share this resource
- * @cbm: array of cache bit masks (indexed by CLOSID)
+ * @ctrl_val: array of cache or mem ctrl values (indexed by CLOSID)
+ * @new_ctrl: new ctrl value to be loaded
+ * @have_new_ctrl: did user provide new_ctrl for this domain
*/
struct rdt_domain {
struct list_head list;
int id;
struct cpumask cpu_mask;
- u32 *cbm;
+ u32 *ctrl_val;
+ u32 new_ctrl;
+ bool have_new_ctrl;
};
/**
@@ -129,6 +104,83 @@ struct msr_param {
int high;
};
+/**
+ * struct rdt_cache - Cache allocation related data
+ * @cbm_len: Length of the cache bit mask
+ * @min_cbm_bits: Minimum number of consecutive bits to be set
+ * @cbm_idx_mult: Multiplier of CBM index
+ * @cbm_idx_offset: Offset of CBM index. CBM index is computed by:
+ * closid * cbm_idx_multi + cbm_idx_offset
+ * in a cache bit mask
+ */
+struct rdt_cache {
+ unsigned int cbm_len;
+ unsigned int min_cbm_bits;
+ unsigned int cbm_idx_mult;
+ unsigned int cbm_idx_offset;
+};
+
+/**
+ * struct rdt_membw - Memory bandwidth allocation related data
+ * @max_delay: Max throttle delay. Delay is the hardware
+ * representation for memory bandwidth.
+ * @min_bw: Minimum memory bandwidth percentage user can request
+ * @bw_gran: Granularity at which the memory bandwidth is allocated
+ * @delay_linear: True if memory B/W delay is in linear scale
+ * @mb_map: Mapping of memory B/W percentage to memory B/W delay
+ */
+struct rdt_membw {
+ u32 max_delay;
+ u32 min_bw;
+ u32 bw_gran;
+ u32 delay_linear;
+ u32 *mb_map;
+};
+
+/**
+ * struct rdt_resource - attributes of an RDT resource
+ * @enabled: Is this feature enabled on this machine
+ * @capable: Is this feature available on this machine
+ * @name: Name to use in "schemata" file
+ * @num_closid: Number of CLOSIDs available
+ * @cache_level: Which cache level defines scope of this resource
+ * @default_ctrl: Specifies default cache cbm or memory B/W percent.
+ * @msr_base: Base MSR address for CBMs
+ * @msr_update: Function pointer to update QOS MSRs
+ * @data_width: Character width of data when displaying
+ * @domains: All domains for this resource
+ * @cache: Cache allocation related data
+ * @info_files: resctrl info files for the resource
+ * @nr_info_files: Number of info files
+ * @format_str: Per resource format string to show domain value
+ * @parse_ctrlval: Per resource function pointer to parse control values
+ */
+struct rdt_resource {
+ bool enabled;
+ bool capable;
+ char *name;
+ int num_closid;
+ int cache_level;
+ u32 default_ctrl;
+ unsigned int msr_base;
+ void (*msr_update) (struct rdt_domain *d, struct msr_param *m,
+ struct rdt_resource *r);
+ int data_width;
+ struct list_head domains;
+ struct rdt_cache cache;
+ struct rdt_membw membw;
+ struct rftype *info_files;
+ int nr_info_files;
+ const char *format_str;
+ int (*parse_ctrlval) (char *buf, struct rdt_resource *r,
+ struct rdt_domain *d);
+};
+
+void rdt_get_cache_infofile(struct rdt_resource *r);
+void rdt_get_mba_infofile(struct rdt_resource *r);
+int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d);
+int parse_bw(char *buf, struct rdt_resource *r, struct rdt_domain *d);
+
extern struct mutex rdtgroup_mutex;
extern struct rdt_resource rdt_resources_all[];
@@ -142,6 +194,7 @@ enum {
RDT_RESOURCE_L3DATA,
RDT_RESOURCE_L3CODE,
RDT_RESOURCE_L2,
+ RDT_RESOURCE_MBA,
/* Must be the last */
RDT_NUM_RESOURCES,
@@ -149,7 +202,7 @@ enum {
#define for_each_capable_rdt_resource(r) \
for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\
- r++) \
+ r++) \
if (r->capable)
#define for_each_enabled_rdt_resource(r) \
@@ -165,8 +218,16 @@ union cpuid_0x10_1_eax {
unsigned int full;
};
-/* CPUID.(EAX=10H, ECX=ResID=1).EDX */
-union cpuid_0x10_1_edx {
+/* CPUID.(EAX=10H, ECX=ResID=3).EAX */
+union cpuid_0x10_3_eax {
+ struct {
+ unsigned int max_delay:12;
+ } split;
+ unsigned int full;
+};
+
+/* CPUID.(EAX=10H, ECX=ResID).EDX */
+union cpuid_0x10_x_edx {
struct {
unsigned int cos_max:16;
} split;
@@ -175,7 +236,7 @@ union cpuid_0x10_1_edx {
DECLARE_PER_CPU_READ_MOSTLY(int, cpu_closid);
-void rdt_cbm_update(void *arg);
+void rdt_ctrl_update(void *arg);
struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn);
void rdtgroup_kn_unlock(struct kernfs_node *kn);
ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index 200581691c6e..34b984c60790 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -72,14 +72,13 @@ struct arch_specific_insn {
/* copy of the original instruction */
kprobe_opcode_t *insn;
/*
- * boostable = -1: This instruction type is not boostable.
- * boostable = 0: This instruction type is boostable.
- * boostable = 1: This instruction has been boosted: we have
+ * boostable = false: This instruction type is not boostable.
+ * boostable = true: This instruction has been boosted: we have
* added a relative jump after the instruction copy in insn,
* so no single-step and fixup are needed (unless there's
* a post_handler or break_handler).
*/
- int boostable;
+ bool boostable;
bool if_modifier;
};
diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h
index d74747b031ec..c4eda791f877 100644
--- a/arch/x86/include/asm/kvm_page_track.h
+++ b/arch/x86/include/asm/kvm_page_track.h
@@ -46,6 +46,7 @@ struct kvm_page_track_notifier_node {
};
void kvm_page_track_init(struct kvm *kvm);
+void kvm_page_track_cleanup(struct kvm *kvm);
void kvm_page_track_free_memslot(struct kvm_memory_slot *free,
struct kvm_memory_slot *dont);
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index e63873683d4a..4fd5195deed0 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -128,7 +128,7 @@
* debugging tools. Each entry is only valid when its finished flag
* is set.
*/
-struct mce_log {
+struct mce_log_buffer {
char signature[12]; /* "MACHINECHECK" */
unsigned len; /* = MCE_LOG_LEN */
unsigned next;
@@ -191,10 +191,12 @@ extern struct mca_config mca_cfg;
extern struct mca_msr_regs msr_ops;
enum mce_notifier_prios {
- MCE_PRIO_SRAO = INT_MAX,
- MCE_PRIO_EXTLOG = INT_MAX - 1,
- MCE_PRIO_NFIT = INT_MAX - 2,
- MCE_PRIO_EDAC = INT_MAX - 3,
+ MCE_PRIO_FIRST = INT_MAX,
+ MCE_PRIO_SRAO = INT_MAX - 1,
+ MCE_PRIO_EXTLOG = INT_MAX - 2,
+ MCE_PRIO_NFIT = INT_MAX - 3,
+ MCE_PRIO_EDAC = INT_MAX - 4,
+ MCE_PRIO_MCELOG = 1,
MCE_PRIO_LOWEST = 0,
};
diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h
index 32007041ef8c..831eb7895535 100644
--- a/arch/x86/include/asm/mpspec.h
+++ b/arch/x86/include/asm/mpspec.h
@@ -64,7 +64,7 @@ static inline void find_smp_config(void)
}
#ifdef CONFIG_X86_MPPARSE
-extern void early_reserve_e820_mpc_new(void);
+extern void e820__memblock_alloc_reserved_mpc_new(void);
extern int enable_update_mptable;
extern int default_mpc_apic_id(struct mpc_cpu *m);
extern void default_smp_read_mpc_oem(struct mpc_table *mpc);
@@ -76,7 +76,7 @@ extern void default_mpc_oem_bus_info(struct mpc_bus *m, char *str);
extern void default_find_smp_config(void);
extern void default_get_smp_config(unsigned int early);
#else
-static inline void early_reserve_e820_mpc_new(void) { }
+static inline void e820__memblock_alloc_reserved_mpc_new(void) { }
#define enable_update_mptable 0
#define default_mpc_apic_id NULL
#define default_smp_read_mpc_oem NULL
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index d8b5f8ab8ef9..673f9ac50f6d 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -45,6 +45,8 @@
#define MSR_IA32_PERFCTR1 0x000000c2
#define MSR_FSB_FREQ 0x000000cd
#define MSR_PLATFORM_INFO 0x000000ce
+#define MSR_PLATFORM_INFO_CPUID_FAULT_BIT 31
+#define MSR_PLATFORM_INFO_CPUID_FAULT BIT_ULL(MSR_PLATFORM_INFO_CPUID_FAULT_BIT)
#define MSR_PKG_CST_CONFIG_CONTROL 0x000000e2
#define NHM_C3_AUTO_DEMOTE (1UL << 25)
@@ -127,6 +129,7 @@
/* DEBUGCTLMSR bits (others vary by model): */
#define DEBUGCTLMSR_LBR (1UL << 0) /* last branch recording */
+#define DEBUGCTLMSR_BTF_SHIFT 1
#define DEBUGCTLMSR_BTF (1UL << 1) /* single-step on branches */
#define DEBUGCTLMSR_TR (1UL << 6)
#define DEBUGCTLMSR_BTS (1UL << 7)
@@ -552,10 +555,12 @@
#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT 39
#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT)
-/* MISC_FEATURE_ENABLES non-architectural features */
-#define MSR_MISC_FEATURE_ENABLES 0x00000140
+/* MISC_FEATURES_ENABLES non-architectural features */
+#define MSR_MISC_FEATURES_ENABLES 0x00000140
-#define MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT 1
+#define MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT 0
+#define MSR_MISC_FEATURES_ENABLES_CPUID_FAULT BIT_ULL(MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT)
+#define MSR_MISC_FEATURES_ENABLES_RING3MWAIT_BIT 1
#define MSR_IA32_TSC_DEADLINE 0x000006E0
diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h
index b3bebf9e5746..b4a0d43248cf 100644
--- a/arch/x86/include/asm/page_64.h
+++ b/arch/x86/include/asm/page_64.h
@@ -4,6 +4,7 @@
#include <asm/page_64_types.h>
#ifndef __ASSEMBLY__
+#include <asm/alternative.h>
/* duplicated to the one in bootmem.h */
extern unsigned long max_pfn;
@@ -34,7 +35,20 @@ extern unsigned long __phys_addr_symbol(unsigned long);
#define pfn_valid(pfn) ((pfn) < max_pfn)
#endif
-void clear_page(void *page);
+void clear_page_orig(void *page);
+void clear_page_rep(void *page);
+void clear_page_erms(void *page);
+
+static inline void clear_page(void *page)
+{
+ alternative_call_2(clear_page_orig,
+ clear_page_rep, X86_FEATURE_REP_GOOD,
+ clear_page_erms, X86_FEATURE_ERMS,
+ "=D" (page),
+ "0" (page)
+ : "memory", "rax", "rcx");
+}
+
void copy_page(void *to, void *from);
#endif /* !__ASSEMBLY__ */
diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h
index d08eacd298c2..9f1b21f372fe 100644
--- a/arch/x86/include/asm/pci_x86.h
+++ b/arch/x86/include/asm/pci_x86.h
@@ -4,6 +4,8 @@
* (c) 1999 Martin Mares <mj@ucw.cz>
*/
+#include <linux/ioport.h>
+
#undef DEBUG
#ifdef DEBUG
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index 72277b1028a5..50d35e3185f5 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -121,12 +121,9 @@ static inline void native_pmd_clear(pmd_t *pmd)
*(tmp + 1) = 0;
}
-#if !defined(CONFIG_SMP) || (defined(CONFIG_HIGHMEM64G) && \
- defined(CONFIG_PARAVIRT))
static inline void native_pud_clear(pud_t *pudp)
{
}
-#endif
static inline void pud_clear(pud_t *pudp)
{
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 1cfb36b8c024..2197e5322df9 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -2,8 +2,6 @@
#define _ASM_X86_PGTABLE_H
#include <asm/page.h>
-#include <asm/e820.h>
-
#include <asm/pgtable_types.h>
/*
@@ -62,7 +60,7 @@ extern struct mm_struct *pgd_page_get_mm(struct page *page);
# define set_pud(pudp, pud) native_set_pud(pudp, pud)
#endif
-#ifndef __PAGETABLE_PMD_FOLDED
+#ifndef __PAGETABLE_PUD_FOLDED
#define pud_clear(pud) native_pud_clear(pud)
#endif
@@ -845,6 +843,7 @@ 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);
#ifdef CONFIG_X86_64
/* Realmode trampoline initialization. */
diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h
index 2c1ebeb4d737..529bb4a6487a 100644
--- a/arch/x86/include/asm/pmem.h
+++ b/arch/x86/include/asm/pmem.h
@@ -55,7 +55,8 @@ static inline int arch_memcpy_from_pmem(void *dst, const void *src, size_t n)
* @size: number of bytes to write back
*
* Write back a cache range using the CLWB (cache line write back)
- * instruction.
+ * instruction. Note that @size is internally rounded up to be cache
+ * line size aligned.
*/
static inline void arch_wb_cache_pmem(void *addr, size_t size)
{
@@ -69,15 +70,6 @@ static inline void arch_wb_cache_pmem(void *addr, size_t size)
clwb(p);
}
-/*
- * copy_from_iter_nocache() on x86 only uses non-temporal stores for iovec
- * iterators, so for other types (bvec & kvec) we must do a cache write-back.
- */
-static inline bool __iter_needs_pmem_wb(struct iov_iter *i)
-{
- return iter_is_iovec(i) == false;
-}
-
/**
* arch_copy_from_iter_pmem - copy data from an iterator to PMEM
* @addr: PMEM destination address
@@ -94,7 +86,35 @@ static inline size_t arch_copy_from_iter_pmem(void *addr, size_t bytes,
/* TODO: skip the write-back by always using non-temporal stores */
len = copy_from_iter_nocache(addr, bytes, i);
- if (__iter_needs_pmem_wb(i))
+ /*
+ * In the iovec case on x86_64 copy_from_iter_nocache() uses
+ * non-temporal stores for the bulk of the transfer, but we need
+ * to manually flush if the transfer is unaligned. A cached
+ * memory copy is used when destination or size is not naturally
+ * aligned. That is:
+ * - Require 8-byte alignment when size is 8 bytes or larger.
+ * - Require 4-byte alignment when size is 4 bytes.
+ *
+ * In the non-iovec case the entire destination needs to be
+ * flushed.
+ */
+ if (iter_is_iovec(i)) {
+ unsigned long flushed, dest = (unsigned long) addr;
+
+ if (bytes < 8) {
+ if (!IS_ALIGNED(dest, 4) || (bytes != 4))
+ arch_wb_cache_pmem(addr, 1);
+ } else {
+ if (!IS_ALIGNED(dest, 8)) {
+ dest = ALIGN(dest, boot_cpu_data.x86_clflush_size);
+ arch_wb_cache_pmem(addr, 1);
+ }
+
+ flushed = dest - (unsigned long) addr;
+ if (bytes > flushed && !IS_ALIGNED(bytes - flushed, 8))
+ arch_wb_cache_pmem(addr + bytes - 1, 1);
+ }
+ } else
arch_wb_cache_pmem(addr, bytes);
return len;
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index f385eca5407a..78defd0aa220 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -80,7 +80,7 @@ extern u16 __read_mostly tlb_lld_1g[NR_INFO];
/*
* CPU type and hardware bug flags. Kept separately for each CPU.
- * Members of this structure are referenced in head.S, so think twice
+ * Members of this structure are referenced in head_32.S, so think twice
* before touching them. [mj]
*/
@@ -89,14 +89,7 @@ struct cpuinfo_x86 {
__u8 x86_vendor; /* CPU vendor */
__u8 x86_model;
__u8 x86_mask;
-#ifdef CONFIG_X86_32
- char wp_works_ok; /* It doesn't on 386's */
-
- /* Problems on some 486Dx4's and old 386's: */
- char rfu;
- char pad0;
- char pad1;
-#else
+#ifdef CONFIG_X86_64
/* Number of 4K pages in DTLB/ITLB combined(in pages): */
int x86_tlbsize;
#endif
@@ -884,6 +877,8 @@ extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
extern int get_tsc_mode(unsigned long adr);
extern int set_tsc_mode(unsigned int val);
+DECLARE_PER_CPU(u64, msr_misc_features_shadow);
+
/* Register/unregister a process' MPX related resource */
#define MPX_ENABLE_MANAGEMENT() mpx_enable_management()
#define MPX_DISABLE_MANAGEMENT() mpx_disable_management()
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index 9b9b30b19441..8d3964fc5f91 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -9,6 +9,7 @@ void syscall_init(void);
#ifdef CONFIG_X86_64
void entry_SYSCALL_64(void);
+long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2);
#endif
#ifdef CONFIG_X86_32
@@ -30,6 +31,7 @@ void x86_report_nx(void);
extern int reboot_force;
-long do_arch_prctl(struct task_struct *task, int code, unsigned long addr);
+long do_arch_prctl_common(struct task_struct *task, int option,
+ unsigned long cpuid_enabled);
#endif /* _ASM_X86_PROTO_H */
diff --git a/arch/x86/include/asm/purgatory.h b/arch/x86/include/asm/purgatory.h
new file mode 100644
index 000000000000..d7da2729903d
--- /dev/null
+++ b/arch/x86/include/asm/purgatory.h
@@ -0,0 +1,20 @@
+#ifndef _ASM_X86_PURGATORY_H
+#define _ASM_X86_PURGATORY_H
+
+#ifndef __ASSEMBLY__
+#include <linux/purgatory.h>
+
+extern void purgatory(void);
+/*
+ * These forward declarations serve two purposes:
+ *
+ * 1) Make sparse happy when checking arch/purgatory
+ * 2) Document that these are required to be global so the symbol
+ * lookup in kexec works
+ */
+extern unsigned long purgatory_backup_dest;
+extern unsigned long purgatory_backup_src;
+extern unsigned long purgatory_backup_sz;
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_PURGATORY_H */
diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h
index 2cb1cc253d51..fc62ba8dce93 100644
--- a/arch/x86/include/asm/reboot.h
+++ b/arch/x86/include/asm/reboot.h
@@ -15,6 +15,7 @@ struct machine_ops {
};
extern struct machine_ops machine_ops;
+extern int crashing_cpu;
void native_machine_crash_shutdown(struct pt_regs *regs);
void native_machine_shutdown(void);
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 026ea82ecc60..47103eca3775 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -149,6 +149,19 @@ void smp_store_cpu_info(int id);
#define cpu_physical_id(cpu) per_cpu(x86_cpu_to_apicid, cpu)
#define cpu_acpi_id(cpu) per_cpu(x86_cpu_to_acpiid, cpu)
+/*
+ * This function is needed by all SMP systems. It must _always_ be valid
+ * from the initial startup. We map APIC_BASE very early in page_setup(),
+ * so this is correct in the x86 case.
+ */
+#define raw_smp_processor_id() (this_cpu_read(cpu_number))
+
+#ifdef CONFIG_X86_32
+extern int safe_smp_processor_id(void);
+#else
+# define safe_smp_processor_id() smp_processor_id()
+#endif
+
#else /* !CONFIG_SMP */
#define wbinvd_on_cpu(cpu) wbinvd()
static inline int wbinvd_on_all_cpus(void)
@@ -161,22 +174,6 @@ static inline int wbinvd_on_all_cpus(void)
extern unsigned disabled_cpus;
-#ifdef CONFIG_X86_32_SMP
-/*
- * This function is needed by all SMP systems. It must _always_ be valid
- * from the initial startup. We map APIC_BASE very early in page_setup(),
- * so this is correct in the x86 case.
- */
-#define raw_smp_processor_id() (this_cpu_read(cpu_number))
-extern int safe_smp_processor_id(void);
-
-#elif defined(CONFIG_X86_64_SMP)
-#define raw_smp_processor_id() (this_cpu_read(cpu_number))
-
-#define safe_smp_processor_id() smp_processor_id()
-
-#endif
-
#ifdef CONFIG_X86_LOCAL_APIC
#ifndef CONFIG_X86_64
@@ -191,11 +188,7 @@ static inline int logical_smp_processor_id(void)
extern int hard_smp_processor_id(void);
#else /* CONFIG_X86_LOCAL_APIC */
-
-# ifndef CONFIG_SMP
-# define hard_smp_processor_id() 0
-# endif
-
+#define hard_smp_processor_id() 0
#endif /* CONFIG_X86_LOCAL_APIC */
#ifdef CONFIG_DEBUG_NMI_SELFTEST
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index ad6f5eb07a95..9fc44b95f7cb 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -87,6 +87,7 @@ struct thread_info {
#define TIF_SECCOMP 8 /* secure computing */
#define TIF_USER_RETURN_NOTIFY 11 /* notify kernel of userspace return */
#define TIF_UPROBE 12 /* breakpointed or singlestepping */
+#define TIF_NOCPUID 15 /* CPUID is not accessible in userland */
#define TIF_NOTSC 16 /* TSC is not accessible in userland */
#define TIF_IA32 17 /* IA32 compatibility process */
#define TIF_NOHZ 19 /* in adaptive nohz mode */
@@ -110,6 +111,7 @@ struct thread_info {
#define _TIF_SECCOMP (1 << TIF_SECCOMP)
#define _TIF_USER_RETURN_NOTIFY (1 << TIF_USER_RETURN_NOTIFY)
#define _TIF_UPROBE (1 << TIF_UPROBE)
+#define _TIF_NOCPUID (1 << TIF_NOCPUID)
#define _TIF_NOTSC (1 << TIF_NOTSC)
#define _TIF_IA32 (1 << TIF_IA32)
#define _TIF_NOHZ (1 << TIF_NOHZ)
@@ -138,7 +140,7 @@ struct thread_info {
/* flags to check in __switch_to() */
#define _TIF_WORK_CTXSW \
- (_TIF_IO_BITMAP|_TIF_NOTSC|_TIF_BLOCKSTEP)
+ (_TIF_IO_BITMAP|_TIF_NOCPUID|_TIF_NOTSC|_TIF_BLOCKSTEP)
#define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY)
#define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW)
@@ -239,6 +241,8 @@ static inline int arch_within_stack_frames(const void * const stack,
extern void arch_task_cache_init(void);
extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
extern void arch_release_task_struct(struct task_struct *tsk);
+extern void arch_setup_new_exec(void);
+#define arch_setup_new_exec arch_setup_new_exec
#endif /* !__ASSEMBLY__ */
#endif /* _ASM_X86_THREAD_INFO_H */
diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h
index a04eabd43d06..27e9f9d769b8 100644
--- a/arch/x86/include/asm/timer.h
+++ b/arch/x86/include/asm/timer.h
@@ -12,6 +12,8 @@ extern int recalibrate_cpu_khz(void);
extern int no_timer_check;
+extern bool using_native_sched_clock(void);
+
/*
* We use the full linear equation: f(x) = a + b*x, in order to allow
* a continuous function in the face of dynamic freq changes.
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 6fa85944af83..75d002bdb3f3 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -110,6 +110,16 @@ static inline void cr4_clear_bits(unsigned long mask)
}
}
+static inline void cr4_toggle_bits(unsigned long mask)
+{
+ unsigned long cr4;
+
+ cr4 = this_cpu_read(cpu_tlbstate.cr4);
+ cr4 ^= mask;
+ this_cpu_write(cpu_tlbstate.cr4, cr4);
+ __write_cr4(cr4);
+}
+
/* Read the CR4 shadow. */
static inline unsigned long cr4_read_shadow(void)
{
@@ -188,7 +198,7 @@ static inline void __native_flush_tlb_single(unsigned long addr)
static inline void __flush_tlb_all(void)
{
- if (static_cpu_has(X86_FEATURE_PGE))
+ if (boot_cpu_has(X86_FEATURE_PGE))
__flush_tlb_global();
else
__flush_tlb();
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index ea148313570f..68766b276d9e 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -3,19 +3,14 @@
/*
* User space memory access functions
*/
-#include <linux/errno.h>
#include <linux/compiler.h>
#include <linux/kasan-checks.h>
-#include <linux/thread_info.h>
#include <linux/string.h>
#include <asm/asm.h>
#include <asm/page.h>
#include <asm/smap.h>
#include <asm/extable.h>
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
-
/*
* The fs value determines whether argument validity checking should be
* performed or not. If get_fs() == USER_DS, checking is performed, with
@@ -384,6 +379,18 @@ do { \
: "=r" (err), ltype(x) \
: "m" (__m(addr)), "i" (errret), "0" (err))
+#define __get_user_asm_nozero(x, addr, err, itype, rtype, ltype, errret) \
+ asm volatile("\n" \
+ "1: mov"itype" %2,%"rtype"1\n" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: mov %3,%0\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ _ASM_EXTABLE(1b, 3b) \
+ : "=r" (err), ltype(x) \
+ : "m" (__m(addr)), "i" (errret), "0" (err))
+
/*
* This doesn't do __uaccess_begin/end - the exception handling
* around it must do that.
@@ -675,59 +682,6 @@ extern struct movsl_mask {
# include <asm/uaccess_64.h>
#endif
-unsigned long __must_check _copy_from_user(void *to, const void __user *from,
- unsigned n);
-unsigned long __must_check _copy_to_user(void __user *to, const void *from,
- unsigned n);
-
-extern void __compiletime_error("usercopy buffer size is too small")
-__bad_copy_user(void);
-
-static inline void copy_user_overflow(int size, unsigned long count)
-{
- WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count);
-}
-
-static __always_inline unsigned long __must_check
-copy_from_user(void *to, const void __user *from, unsigned long n)
-{
- int sz = __compiletime_object_size(to);
-
- might_fault();
-
- kasan_check_write(to, n);
-
- if (likely(sz < 0 || sz >= n)) {
- check_object_size(to, n, false);
- n = _copy_from_user(to, from, n);
- } else if (!__builtin_constant_p(n))
- copy_user_overflow(sz, n);
- else
- __bad_copy_user();
-
- return n;
-}
-
-static __always_inline unsigned long __must_check
-copy_to_user(void __user *to, const void *from, unsigned long n)
-{
- int sz = __compiletime_object_size(from);
-
- kasan_check_read(from, n);
-
- might_fault();
-
- if (likely(sz < 0 || sz >= n)) {
- check_object_size(from, n, true);
- n = _copy_to_user(to, from, n);
- } else if (!__builtin_constant_p(n))
- copy_user_overflow(sz, n);
- else
- __bad_copy_user();
-
- return n;
-}
-
/*
* We rely on the nested NMI work to allow atomic faults from the NMI path; the
* nested NMI paths are careful to preserve CR2.
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index 7d3bdd1ed697..aeda9bb8af50 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -4,149 +4,52 @@
/*
* User space memory access functions
*/
-#include <linux/errno.h>
-#include <linux/thread_info.h>
#include <linux/string.h>
#include <asm/asm.h>
#include <asm/page.h>
-unsigned long __must_check __copy_to_user_ll
- (void __user *to, const void *from, unsigned long n);
-unsigned long __must_check __copy_from_user_ll
- (void *to, const void __user *from, unsigned long n);
-unsigned long __must_check __copy_from_user_ll_nozero
- (void *to, const void __user *from, unsigned long n);
-unsigned long __must_check __copy_from_user_ll_nocache
- (void *to, const void __user *from, unsigned long n);
+unsigned long __must_check __copy_user_ll
+ (void *to, const void *from, unsigned long n);
unsigned long __must_check __copy_from_user_ll_nocache_nozero
(void *to, const void __user *from, unsigned long n);
-/**
- * __copy_to_user_inatomic: - Copy a block of data into user space, with less checking.
- * @to: Destination address, in user space.
- * @from: Source address, in kernel space.
- * @n: Number of bytes to copy.
- *
- * Context: User context only.
- *
- * Copy data from kernel space to user space. Caller must check
- * the specified block with access_ok() before calling this function.
- * The caller should also make sure he pins the user space address
- * so that we don't result in page fault and sleep.
- */
-static __always_inline unsigned long __must_check
-__copy_to_user_inatomic(void __user *to, const void *from, unsigned long n)
-{
- check_object_size(from, n, true);
- return __copy_to_user_ll(to, from, n);
-}
-
-/**
- * __copy_to_user: - Copy a block of data into user space, with less checking.
- * @to: Destination address, in user space.
- * @from: Source address, in kernel space.
- * @n: Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- * enabled.
- *
- * Copy data from kernel space to user space. Caller must check
- * the specified block with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- */
static __always_inline unsigned long __must_check
-__copy_to_user(void __user *to, const void *from, unsigned long n)
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
{
- might_fault();
- return __copy_to_user_inatomic(to, from, n);
+ return __copy_user_ll((__force void *)to, from, n);
}
static __always_inline unsigned long
-__copy_from_user_inatomic(void *to, const void __user *from, unsigned long n)
-{
- return __copy_from_user_ll_nozero(to, from, n);
-}
-
-/**
- * __copy_from_user: - Copy a block of data from user space, with less checking.
- * @to: Destination address, in kernel space.
- * @from: Source address, in user space.
- * @n: Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- * enabled.
- *
- * Copy data from user space to kernel space. Caller must check
- * the specified block with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- *
- * If some data could not be copied, this function will pad the copied
- * data to the requested size using zero bytes.
- *
- * An alternate version - __copy_from_user_inatomic() - may be called from
- * atomic context and will fail rather than sleep. In this case the
- * uncopied bytes will *NOT* be padded with zeros. See fs/filemap.h
- * for explanation of why this is needed.
- */
-static __always_inline unsigned long
-__copy_from_user(void *to, const void __user *from, unsigned long n)
-{
- might_fault();
- check_object_size(to, n, false);
- if (__builtin_constant_p(n)) {
- unsigned long ret;
-
- switch (n) {
- case 1:
- __uaccess_begin();
- __get_user_size(*(u8 *)to, from, 1, ret, 1);
- __uaccess_end();
- return ret;
- case 2:
- __uaccess_begin();
- __get_user_size(*(u16 *)to, from, 2, ret, 2);
- __uaccess_end();
- return ret;
- case 4:
- __uaccess_begin();
- __get_user_size(*(u32 *)to, from, 4, ret, 4);
- __uaccess_end();
- return ret;
- }
- }
- return __copy_from_user_ll(to, from, n);
-}
-
-static __always_inline unsigned long __copy_from_user_nocache(void *to,
- const void __user *from, unsigned long n)
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
{
- might_fault();
if (__builtin_constant_p(n)) {
unsigned long ret;
switch (n) {
case 1:
+ ret = 0;
__uaccess_begin();
- __get_user_size(*(u8 *)to, from, 1, ret, 1);
+ __get_user_asm_nozero(*(u8 *)to, from, ret,
+ "b", "b", "=q", 1);
__uaccess_end();
return ret;
case 2:
+ ret = 0;
__uaccess_begin();
- __get_user_size(*(u16 *)to, from, 2, ret, 2);
+ __get_user_asm_nozero(*(u16 *)to, from, ret,
+ "w", "w", "=r", 2);
__uaccess_end();
return ret;
case 4:
+ ret = 0;
__uaccess_begin();
- __get_user_size(*(u32 *)to, from, 4, ret, 4);
+ __get_user_asm_nozero(*(u32 *)to, from, ret,
+ "l", "k", "=r", 4);
__uaccess_end();
return ret;
}
}
- return __copy_from_user_ll_nocache(to, from, n);
+ return __copy_user_ll(to, (__force const void *)from, n);
}
static __always_inline unsigned long
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index 673059a109fe..c5504b9a472e 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -5,7 +5,6 @@
* User space memory access functions
*/
#include <linux/compiler.h>
-#include <linux/errno.h>
#include <linux/lockdep.h>
#include <linux/kasan-checks.h>
#include <asm/alternative.h>
@@ -46,58 +45,54 @@ copy_user_generic(void *to, const void *from, unsigned len)
return ret;
}
-__must_check unsigned long
-copy_in_user(void __user *to, const void __user *from, unsigned len);
-
-static __always_inline __must_check
-int __copy_from_user_nocheck(void *dst, const void __user *src, unsigned size)
+static __always_inline __must_check unsigned long
+raw_copy_from_user(void *dst, const void __user *src, unsigned long size)
{
int ret = 0;
- check_object_size(dst, size, false);
if (!__builtin_constant_p(size))
return copy_user_generic(dst, (__force void *)src, size);
switch (size) {
case 1:
__uaccess_begin();
- __get_user_asm(*(u8 *)dst, (u8 __user *)src,
+ __get_user_asm_nozero(*(u8 *)dst, (u8 __user *)src,
ret, "b", "b", "=q", 1);
__uaccess_end();
return ret;
case 2:
__uaccess_begin();
- __get_user_asm(*(u16 *)dst, (u16 __user *)src,
+ __get_user_asm_nozero(*(u16 *)dst, (u16 __user *)src,
ret, "w", "w", "=r", 2);
__uaccess_end();
return ret;
case 4:
__uaccess_begin();
- __get_user_asm(*(u32 *)dst, (u32 __user *)src,
+ __get_user_asm_nozero(*(u32 *)dst, (u32 __user *)src,
ret, "l", "k", "=r", 4);
__uaccess_end();
return ret;
case 8:
__uaccess_begin();
- __get_user_asm(*(u64 *)dst, (u64 __user *)src,
+ __get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src,
ret, "q", "", "=r", 8);
__uaccess_end();
return ret;
case 10:
__uaccess_begin();
- __get_user_asm(*(u64 *)dst, (u64 __user *)src,
+ __get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src,
ret, "q", "", "=r", 10);
if (likely(!ret))
- __get_user_asm(*(u16 *)(8 + (char *)dst),
+ __get_user_asm_nozero(*(u16 *)(8 + (char *)dst),
(u16 __user *)(8 + (char __user *)src),
ret, "w", "w", "=r", 2);
__uaccess_end();
return ret;
case 16:
__uaccess_begin();
- __get_user_asm(*(u64 *)dst, (u64 __user *)src,
+ __get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src,
ret, "q", "", "=r", 16);
if (likely(!ret))
- __get_user_asm(*(u64 *)(8 + (char *)dst),
+ __get_user_asm_nozero(*(u64 *)(8 + (char *)dst),
(u64 __user *)(8 + (char __user *)src),
ret, "q", "", "=r", 8);
__uaccess_end();
@@ -107,20 +102,11 @@ int __copy_from_user_nocheck(void *dst, const void __user *src, unsigned size)
}
}
-static __always_inline __must_check
-int __copy_from_user(void *dst, const void __user *src, unsigned size)
-{
- might_fault();
- kasan_check_write(dst, size);
- return __copy_from_user_nocheck(dst, src, size);
-}
-
-static __always_inline __must_check
-int __copy_to_user_nocheck(void __user *dst, const void *src, unsigned size)
+static __always_inline __must_check unsigned long
+raw_copy_to_user(void __user *dst, const void *src, unsigned long size)
{
int ret = 0;
- check_object_size(src, size, true);
if (!__builtin_constant_p(size))
return copy_user_generic((__force void *)dst, src, size);
switch (size) {
@@ -176,100 +162,16 @@ int __copy_to_user_nocheck(void __user *dst, const void *src, unsigned size)
}
static __always_inline __must_check
-int __copy_to_user(void __user *dst, const void *src, unsigned size)
-{
- might_fault();
- kasan_check_read(src, size);
- return __copy_to_user_nocheck(dst, src, size);
-}
-
-static __always_inline __must_check
-int __copy_in_user(void __user *dst, const void __user *src, unsigned size)
-{
- int ret = 0;
-
- might_fault();
- if (!__builtin_constant_p(size))
- return copy_user_generic((__force void *)dst,
- (__force void *)src, size);
- switch (size) {
- case 1: {
- u8 tmp;
- __uaccess_begin();
- __get_user_asm(tmp, (u8 __user *)src,
- ret, "b", "b", "=q", 1);
- if (likely(!ret))
- __put_user_asm(tmp, (u8 __user *)dst,
- ret, "b", "b", "iq", 1);
- __uaccess_end();
- return ret;
- }
- case 2: {
- u16 tmp;
- __uaccess_begin();
- __get_user_asm(tmp, (u16 __user *)src,
- ret, "w", "w", "=r", 2);
- if (likely(!ret))
- __put_user_asm(tmp, (u16 __user *)dst,
- ret, "w", "w", "ir", 2);
- __uaccess_end();
- return ret;
- }
-
- case 4: {
- u32 tmp;
- __uaccess_begin();
- __get_user_asm(tmp, (u32 __user *)src,
- ret, "l", "k", "=r", 4);
- if (likely(!ret))
- __put_user_asm(tmp, (u32 __user *)dst,
- ret, "l", "k", "ir", 4);
- __uaccess_end();
- return ret;
- }
- case 8: {
- u64 tmp;
- __uaccess_begin();
- __get_user_asm(tmp, (u64 __user *)src,
- ret, "q", "", "=r", 8);
- if (likely(!ret))
- __put_user_asm(tmp, (u64 __user *)dst,
- ret, "q", "", "er", 8);
- __uaccess_end();
- return ret;
- }
- default:
- return copy_user_generic((__force void *)dst,
- (__force void *)src, size);
- }
-}
-
-static __must_check __always_inline int
-__copy_from_user_inatomic(void *dst, const void __user *src, unsigned size)
-{
- kasan_check_write(dst, size);
- return __copy_from_user_nocheck(dst, src, size);
-}
-
-static __must_check __always_inline int
-__copy_to_user_inatomic(void __user *dst, const void *src, unsigned size)
+unsigned long raw_copy_in_user(void __user *dst, const void __user *src, unsigned long size)
{
- kasan_check_read(src, size);
- return __copy_to_user_nocheck(dst, src, size);
+ return copy_user_generic((__force void *)dst,
+ (__force void *)src, size);
}
extern long __copy_user_nocache(void *dst, const void __user *src,
unsigned size, int zerorest);
static inline int
-__copy_from_user_nocache(void *dst, const void __user *src, unsigned size)
-{
- might_fault();
- kasan_check_write(dst, size);
- return __copy_user_nocache(dst, src, size, 1);
-}
-
-static inline int
__copy_from_user_inatomic_nocache(void *dst, const void __user *src,
unsigned size)
{
diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h
index 6fa75b17aec3..9b10dcd51716 100644
--- a/arch/x86/include/asm/unwind.h
+++ b/arch/x86/include/asm/unwind.h
@@ -12,8 +12,10 @@ struct unwind_state {
struct task_struct *task;
int graph_idx;
#ifdef CONFIG_FRAME_POINTER
+ bool got_irq;
unsigned long *bp, *orig_sp;
struct pt_regs *regs;
+ unsigned long ip;
#else
unsigned long *sp;
#endif
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 57ab86d94d64..7cac79802ad2 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -185,6 +185,15 @@
#define MSG_REGULAR 1
#define MSG_RETRY 2
+#define BAU_DESC_QUALIFIER 0x534749
+
+enum uv_bau_version {
+ UV_BAU_V1 = 1,
+ UV_BAU_V2,
+ UV_BAU_V3,
+ UV_BAU_V4,
+};
+
/*
* Distribution: 32 bytes (256 bits) (bytes 0-0x1f of descriptor)
* If the 'multilevel' flag in the header portion of the descriptor
@@ -222,20 +231,32 @@ struct bau_local_cpumask {
* the s/w ack bit vector ]
*/
-/*
- * The payload is software-defined for INTD transactions
+/**
+ * struct uv1_2_3_bau_msg_payload - defines payload for INTD transactions
+ * @address: Signifies a page or all TLB's of the cpu
+ * @sending_cpu: CPU from which the message originates
+ * @acknowledge_count: CPUs on the destination Hub that received the interrupt
*/
-struct bau_msg_payload {
- unsigned long address; /* signifies a page or all
- TLB's of the cpu */
- /* 64 bits */
- unsigned short sending_cpu; /* filled in by sender */
- /* 16 bits */
- unsigned short acknowledge_count; /* filled in by destination */
- /* 16 bits */
- unsigned int reserved1:32; /* not usable */
+struct uv1_2_3_bau_msg_payload {
+ u64 address;
+ u16 sending_cpu;
+ u16 acknowledge_count;
};
+/**
+ * struct uv4_bau_msg_payload - defines payload for INTD transactions
+ * @address: Signifies a page or all TLB's of the cpu
+ * @sending_cpu: CPU from which the message originates
+ * @acknowledge_count: CPUs on the destination Hub that received the interrupt
+ * @qualifier: Set by source to verify origin of INTD broadcast
+ */
+struct uv4_bau_msg_payload {
+ u64 address;
+ u16 sending_cpu;
+ u16 acknowledge_count;
+ u32 reserved:8;
+ u32 qualifier:24;
+};
/*
* UV1 Message header: 16 bytes (128 bits) (bytes 0x30-0x3f of descriptor)
@@ -385,17 +406,6 @@ struct uv2_3_bau_msg_header {
/* bits 127:120 */
};
-/* Abstracted BAU functions */
-struct bau_operations {
- unsigned long (*read_l_sw_ack)(void);
- unsigned long (*read_g_sw_ack)(int pnode);
- unsigned long (*bau_gpa_to_offset)(unsigned long vaddr);
- void (*write_l_sw_ack)(unsigned long mmr);
- void (*write_g_sw_ack)(int pnode, unsigned long mmr);
- void (*write_payload_first)(int pnode, unsigned long mmr);
- void (*write_payload_last)(int pnode, unsigned long mmr);
-};
-
/*
* The activation descriptor:
* The format of the message to send, plus all accompanying control
@@ -411,7 +421,10 @@ struct bau_desc {
struct uv2_3_bau_msg_header uv2_3_hdr;
} header;
- struct bau_msg_payload payload;
+ union bau_payload_header {
+ struct uv1_2_3_bau_msg_payload uv1_2_3;
+ struct uv4_bau_msg_payload uv4;
+ } payload;
};
/* UV1:
* -payload-- ---------header------
@@ -588,8 +601,12 @@ struct uvhub_desc {
struct socket_desc socket[2];
};
-/*
- * one per-cpu; to locate the software tables
+/**
+ * struct bau_control
+ * @status_mmr: location of status mmr, determined by uvhub_cpu
+ * @status_index: index of ERR|BUSY bits in status mmr, determined by uvhub_cpu
+ *
+ * Per-cpu control struct containing CPU topology information and BAU tuneables.
*/
struct bau_control {
struct bau_desc *descriptor_base;
@@ -607,6 +624,8 @@ struct bau_control {
int timeout_tries;
int ipi_attempts;
int conseccompletes;
+ u64 status_mmr;
+ int status_index;
bool nobau;
short baudisabled;
short cpu;
@@ -644,6 +663,19 @@ struct bau_control {
struct hub_and_pnode *thp;
};
+/* Abstracted BAU functions */
+struct bau_operations {
+ unsigned long (*read_l_sw_ack)(void);
+ unsigned long (*read_g_sw_ack)(int pnode);
+ unsigned long (*bau_gpa_to_offset)(unsigned long vaddr);
+ void (*write_l_sw_ack)(unsigned long mmr);
+ void (*write_g_sw_ack)(int pnode, unsigned long mmr);
+ void (*write_payload_first)(int pnode, unsigned long mmr);
+ void (*write_payload_last)(int pnode, unsigned long mmr);
+ int (*wait_completion)(struct bau_desc*,
+ struct bau_control*, long try);
+};
+
static inline void write_mmr_data_broadcast(int pnode, unsigned long mmr_image)
{
write_gmmr(pnode, UVH_BAU_DATA_BROADCAST, mmr_image);
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 72e8300b1e8a..9cffb44a3cf5 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -485,15 +485,17 @@ static inline unsigned long uv_soc_phys_ram_to_gpa(unsigned long paddr)
if (paddr < uv_hub_info->lowmem_remap_top)
paddr |= uv_hub_info->lowmem_remap_base;
- paddr |= uv_hub_info->gnode_upper;
- if (m_val)
+
+ if (m_val) {
+ paddr |= uv_hub_info->gnode_upper;
paddr = ((paddr << uv_hub_info->m_shift)
>> uv_hub_info->m_shift) |
((paddr >> uv_hub_info->m_val)
<< uv_hub_info->n_lshift);
- else
+ } else {
paddr |= uv_soc_phys_ram_to_nasid(paddr)
<< uv_hub_info->gpa_shift;
+ }
return paddr;
}
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 33cbd3db97b9..64c5e745ebad 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -6,6 +6,7 @@
#include <linux/spinlock.h>
#include <linux/pfn.h>
#include <linux/mm.h>
+#include <linux/device.h>
#include <linux/uaccess.h>
#include <asm/page.h>
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index 07244ea16765..ddef37b16af2 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -34,7 +34,6 @@
#include <linux/screen_info.h>
#include <linux/apm_bios.h>
#include <linux/edd.h>
-#include <asm/e820.h>
#include <asm/ist.h>
#include <video/edid.h>
@@ -111,6 +110,21 @@ struct efi_info {
__u32 efi_memmap_hi;
};
+/*
+ * This is the maximum number of entries in struct boot_params::e820_table
+ * (the zeropage), which is part of the x86 boot protocol ABI:
+ */
+#define E820_MAX_ENTRIES_ZEROPAGE 128
+
+/*
+ * The E820 memory region entry of the boot protocol ABI:
+ */
+struct boot_e820_entry {
+ __u64 addr;
+ __u64 size;
+ __u32 type;
+} __attribute__((packed));
+
/* The so-called "zeropage" */
struct boot_params {
struct screen_info screen_info; /* 0x000 */
@@ -153,7 +167,7 @@ struct boot_params {
struct setup_header hdr; /* setup header */ /* 0x1f1 */
__u8 _pad7[0x290-0x1f1-sizeof(struct setup_header)];
__u32 edd_mbr_sig_buffer[EDD_MBR_SIG_MAX]; /* 0x290 */
- struct e820entry e820_map[E820MAX]; /* 0x2d0 */
+ struct boot_e820_entry e820_table[E820_MAX_ENTRIES_ZEROPAGE]; /* 0x2d0 */
__u8 _pad8[48]; /* 0xcd0 */
struct edd_info eddbuf[EDDMAXNR]; /* 0xd00 */
__u8 _pad9[276]; /* 0xeec */
diff --git a/arch/x86/include/uapi/asm/prctl.h b/arch/x86/include/uapi/asm/prctl.h
index 835aa51c7f6e..c45765517092 100644
--- a/arch/x86/include/uapi/asm/prctl.h
+++ b/arch/x86/include/uapi/asm/prctl.h
@@ -1,10 +1,13 @@
#ifndef _ASM_X86_PRCTL_H
#define _ASM_X86_PRCTL_H
-#define ARCH_SET_GS 0x1001
-#define ARCH_SET_FS 0x1002
-#define ARCH_GET_FS 0x1003
-#define ARCH_GET_GS 0x1004
+#define ARCH_SET_GS 0x1001
+#define ARCH_SET_FS 0x1002
+#define ARCH_GET_FS 0x1003
+#define ARCH_GET_GS 0x1004
+
+#define ARCH_GET_CPUID 0x1011
+#define ARCH_SET_CPUID 0x1012
#define ARCH_MAP_VDSO_X32 0x2001
#define ARCH_MAP_VDSO_32 0x2002