summaryrefslogtreecommitdiff
path: root/arch/x86/include
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/include')
-rw-r--r--arch/x86/include/asm/amd_nb.h26
-rw-r--r--arch/x86/include/asm/asm.h40
-rw-r--r--arch/x86/include/asm/barrier.h15
-rw-r--r--arch/x86/include/asm/cacheflush.h6
-rw-r--r--arch/x86/include/asm/checksum_32.h9
-rw-r--r--arch/x86/include/asm/checksum_64.h10
-rw-r--r--arch/x86/include/asm/cpufeatures.h14
-rw-r--r--arch/x86/include/asm/desc_defs.h23
-rw-r--r--arch/x86/include/asm/efi.h30
-rw-r--r--arch/x86/include/asm/elf.h2
-rw-r--r--arch/x86/include/asm/fpu/xstate.h9
-rw-r--r--arch/x86/include/asm/gpio.h4
-rw-r--r--arch/x86/include/asm/imr.h2
-rw-r--r--arch/x86/include/asm/ipi.h58
-rw-r--r--arch/x86/include/asm/kvm_host.h31
-rw-r--r--arch/x86/include/asm/kvm_page_track.h61
-rw-r--r--arch/x86/include/asm/kvm_para.h7
-rw-r--r--arch/x86/include/asm/livepatch.h4
-rw-r--r--arch/x86/include/asm/mce.h70
-rw-r--r--arch/x86/include/asm/microcode.h26
-rw-r--r--arch/x86/include/asm/microcode_intel.h1
-rw-r--r--arch/x86/include/asm/msr-index.h15
-rw-r--r--arch/x86/include/asm/paravirt.h9
-rw-r--r--arch/x86/include/asm/paravirt_types.h18
-rw-r--r--arch/x86/include/asm/pci.h18
-rw-r--r--arch/x86/include/asm/pci_x86.h2
-rw-r--r--arch/x86/include/asm/perf_event.h1
-rw-r--r--arch/x86/include/asm/pmem.h5
-rw-r--r--arch/x86/include/asm/preempt.h13
-rw-r--r--arch/x86/include/asm/processor.h7
-rw-r--r--arch/x86/include/asm/proto.h15
-rw-r--r--arch/x86/include/asm/qspinlock_paravirt.h4
-rw-r--r--arch/x86/include/asm/sections.h2
-rw-r--r--arch/x86/include/asm/sighandling.h1
-rw-r--r--arch/x86/include/asm/stacktrace.h2
-rw-r--r--arch/x86/include/asm/string_64.h13
-rw-r--r--arch/x86/include/asm/thread_info.h7
-rw-r--r--arch/x86/include/asm/topology.h11
-rw-r--r--arch/x86/include/asm/tsc.h2
-rw-r--r--arch/x86/include/asm/uaccess.h21
-rw-r--r--arch/x86/include/asm/uaccess_32.h26
-rw-r--r--arch/x86/include/asm/xen/hypercall.h5
-rw-r--r--arch/x86/include/asm/xen/pci.h4
-rw-r--r--arch/x86/include/uapi/asm/hyperv.h4
-rw-r--r--arch/x86/include/uapi/asm/sigcontext.h32
-rw-r--r--arch/x86/include/uapi/asm/ucontext.h53
46 files changed, 545 insertions, 193 deletions
diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h
index 3c56ef1ae068..5e828da2e18f 100644
--- a/arch/x86/include/asm/amd_nb.h
+++ b/arch/x86/include/asm/amd_nb.h
@@ -27,15 +27,23 @@ struct amd_l3_cache {
};
struct threshold_block {
- unsigned int block;
- unsigned int bank;
- unsigned int cpu;
- u32 address;
- u16 interrupt_enable;
- bool interrupt_capable;
- u16 threshold_limit;
- struct kobject kobj;
- struct list_head miscj;
+ unsigned int block; /* Number within bank */
+ unsigned int bank; /* MCA bank the block belongs to */
+ unsigned int cpu; /* CPU which controls MCA bank */
+ u32 address; /* MSR address for the block */
+ u16 interrupt_enable; /* Enable/Disable APIC interrupt */
+ bool interrupt_capable; /* Bank can generate an interrupt. */
+
+ u16 threshold_limit; /*
+ * Value upon which threshold
+ * interrupt is generated.
+ */
+
+ struct kobject kobj; /* sysfs object */
+ struct list_head miscj; /*
+ * List of threshold blocks
+ * within a bank.
+ */
};
struct threshold_bank {
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 189679aba703..f5063b6659eb 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -44,19 +44,22 @@
/* Exception table entry */
#ifdef __ASSEMBLY__
-# define _ASM_EXTABLE(from,to) \
+# define _ASM_EXTABLE_HANDLE(from, to, handler) \
.pushsection "__ex_table","a" ; \
- .balign 8 ; \
+ .balign 4 ; \
.long (from) - . ; \
.long (to) - . ; \
+ .long (handler) - . ; \
.popsection
-# define _ASM_EXTABLE_EX(from,to) \
- .pushsection "__ex_table","a" ; \
- .balign 8 ; \
- .long (from) - . ; \
- .long (to) - . + 0x7ffffff0 ; \
- .popsection
+# define _ASM_EXTABLE(from, to) \
+ _ASM_EXTABLE_HANDLE(from, to, ex_handler_default)
+
+# define _ASM_EXTABLE_FAULT(from, to) \
+ _ASM_EXTABLE_HANDLE(from, to, ex_handler_fault)
+
+# define _ASM_EXTABLE_EX(from, to) \
+ _ASM_EXTABLE_HANDLE(from, to, ex_handler_ext)
# define _ASM_NOKPROBE(entry) \
.pushsection "_kprobe_blacklist","aw" ; \
@@ -89,19 +92,24 @@
.endm
#else
-# define _ASM_EXTABLE(from,to) \
+# define _EXPAND_EXTABLE_HANDLE(x) #x
+# define _ASM_EXTABLE_HANDLE(from, to, handler) \
" .pushsection \"__ex_table\",\"a\"\n" \
- " .balign 8\n" \
+ " .balign 4\n" \
" .long (" #from ") - .\n" \
" .long (" #to ") - .\n" \
+ " .long (" _EXPAND_EXTABLE_HANDLE(handler) ") - .\n" \
" .popsection\n"
-# define _ASM_EXTABLE_EX(from,to) \
- " .pushsection \"__ex_table\",\"a\"\n" \
- " .balign 8\n" \
- " .long (" #from ") - .\n" \
- " .long (" #to ") - . + 0x7ffffff0\n" \
- " .popsection\n"
+# define _ASM_EXTABLE(from, to) \
+ _ASM_EXTABLE_HANDLE(from, to, ex_handler_default)
+
+# define _ASM_EXTABLE_FAULT(from, to) \
+ _ASM_EXTABLE_HANDLE(from, to, ex_handler_fault)
+
+# define _ASM_EXTABLE_EX(from, to) \
+ _ASM_EXTABLE_HANDLE(from, to, ex_handler_ext)
+
/* For C file, we already have NOKPROBE_SYMBOL macro */
#endif
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index a584e1c50918..bfb28caf97b1 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -6,18 +6,17 @@
/*
* Force strict CPU ordering.
- * And yes, this is required on UP too when we're talking
+ * And yes, this might be required on UP too when we're talking
* to devices.
*/
#ifdef CONFIG_X86_32
-/*
- * Some non-Intel clones support out of order store. wmb() ceases to be a
- * nop for these.
- */
-#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2)
-#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)
-#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM)
+#define mb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "mfence", \
+ X86_FEATURE_XMM2) ::: "memory", "cc")
+#define rmb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "lfence", \
+ X86_FEATURE_XMM2) ::: "memory", "cc")
+#define wmb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "sfence", \
+ X86_FEATURE_XMM2) ::: "memory", "cc")
#else
#define mb() asm volatile("mfence":::"memory")
#define rmb() asm volatile("lfence":::"memory")
diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
index e63aa38e85fb..61518cf79437 100644
--- a/arch/x86/include/asm/cacheflush.h
+++ b/arch/x86/include/asm/cacheflush.h
@@ -91,16 +91,10 @@ void clflush_cache_range(void *addr, unsigned int size);
#define mmio_flush_range(addr, size) clflush_cache_range(addr, size)
-#ifdef CONFIG_DEBUG_RODATA
-void mark_rodata_ro(void);
extern const int rodata_test_data;
extern int kernel_set_to_readonly;
void set_kernel_text_rw(void);
void set_kernel_text_ro(void);
-#else
-static inline void set_kernel_text_rw(void) { }
-static inline void set_kernel_text_ro(void) { }
-#endif
#ifdef CONFIG_DEBUG_RODATA_TEST
int rodata_test(void);
diff --git a/arch/x86/include/asm/checksum_32.h b/arch/x86/include/asm/checksum_32.h
index f50de6951738..532f85e6651f 100644
--- a/arch/x86/include/asm/checksum_32.h
+++ b/arch/x86/include/asm/checksum_32.h
@@ -112,8 +112,7 @@ static inline __sum16 csum_fold(__wsum sum)
}
static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
- unsigned short len,
- unsigned short proto,
+ __u32 len, __u8 proto,
__wsum sum)
{
asm("addl %1, %0 ;\n"
@@ -131,8 +130,7 @@ static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
* returns a 16-bit checksum, already complemented
*/
static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
- unsigned short len,
- unsigned short proto,
+ __u32 len, __u8 proto,
__wsum sum)
{
return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
@@ -151,8 +149,7 @@ static inline __sum16 ip_compute_csum(const void *buff, int len)
#define _HAVE_ARCH_IPV6_CSUM
static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
const struct in6_addr *daddr,
- __u32 len, unsigned short proto,
- __wsum sum)
+ __u32 len, __u8 proto, __wsum sum)
{
asm("addl 0(%1), %0 ;\n"
"adcl 4(%1), %0 ;\n"
diff --git a/arch/x86/include/asm/checksum_64.h b/arch/x86/include/asm/checksum_64.h
index cd00e1774491..c020ee75dce7 100644
--- a/arch/x86/include/asm/checksum_64.h
+++ b/arch/x86/include/asm/checksum_64.h
@@ -84,8 +84,8 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
* 32bit unfolded.
*/
static inline __wsum
-csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len,
- unsigned short proto, __wsum sum)
+csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len,
+ __u8 proto, __wsum sum)
{
asm(" addl %1, %0\n"
" adcl %2, %0\n"
@@ -110,8 +110,8 @@ csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len,
* complemented and ready to be filled in.
*/
static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
- unsigned short len,
- unsigned short proto, __wsum sum)
+ __u32 len, __u8 proto,
+ __wsum sum)
{
return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
}
@@ -177,7 +177,7 @@ struct in6_addr;
#define _HAVE_ARCH_IPV6_CSUM 1
extern __sum16
csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr,
- __u32 len, unsigned short proto, __wsum sum);
+ __u32 len, __u8 proto, __wsum sum);
static inline unsigned add32_with_carry(unsigned a, unsigned b)
{
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 89949a299cd5..3d1a84383162 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -85,7 +85,7 @@
#define X86_FEATURE_P4 ( 3*32+ 7) /* "" P4 */
#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */
#define X86_FEATURE_UP ( 3*32+ 9) /* smp kernel running on up */
-/* free, was #define X86_FEATURE_FXSAVE_LEAK ( 3*32+10) * "" FXSAVE leaks FOP/FIP/FOP */
+#define X86_FEATURE_ART ( 3*32+10) /* Platform has always running timer (ART) */
#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* Intel Architectural PerfMon */
#define X86_FEATURE_PEBS ( 3*32+12) /* Precise-Event Based Sampling */
#define X86_FEATURE_BTS ( 3*32+13) /* Branch Trace Store */
@@ -106,6 +106,7 @@
#define X86_FEATURE_APERFMPERF ( 3*32+28) /* APERFMPERF */
#define X86_FEATURE_EAGER_FPU ( 3*32+29) /* "eagerfpu" Non lazy FPU restore */
#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */
+#define X86_FEATURE_MCE_RECOVERY ( 3*32+31) /* cpu has recoverable machine checks */
/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
#define X86_FEATURE_XMM3 ( 4*32+ 0) /* "pni" SSE-3 */
@@ -219,6 +220,7 @@
#define X86_FEATURE_CQM ( 9*32+12) /* Cache QoS Monitoring */
#define X86_FEATURE_MPX ( 9*32+14) /* Memory Protection Extension */
#define X86_FEATURE_AVX512F ( 9*32+16) /* AVX-512 Foundation */
+#define X86_FEATURE_AVX512DQ ( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */
#define X86_FEATURE_RDSEED ( 9*32+18) /* The RDSEED instruction */
#define X86_FEATURE_ADX ( 9*32+19) /* The ADCX and ADOX instructions */
#define X86_FEATURE_SMAP ( 9*32+20) /* Supervisor Mode Access Prevention */
@@ -229,6 +231,8 @@
#define X86_FEATURE_AVX512ER ( 9*32+27) /* AVX-512 Exponential and Reciprocal */
#define X86_FEATURE_AVX512CD ( 9*32+28) /* AVX-512 Conflict Detection */
#define X86_FEATURE_SHA_NI ( 9*32+29) /* SHA1/SHA256 Instruction Extensions */
+#define X86_FEATURE_AVX512BW ( 9*32+30) /* AVX-512 BW (Byte/Word granular) Instructions */
+#define X86_FEATURE_AVX512VL ( 9*32+31) /* AVX-512 VL (128/256 Vector Length) Extensions */
/* Extended state features, CPUID level 0x0000000d:1 (eax), word 10 */
#define X86_FEATURE_XSAVEOPT (10*32+ 0) /* XSAVEOPT */
@@ -289,4 +293,12 @@
#define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */
#define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* SYSRET doesn't fix up SS attrs */
+#ifdef CONFIG_X86_32
+/*
+ * 64-bit kernels don't use X86_BUG_ESPFIX. Make the define conditional
+ * to avoid confusion.
+ */
+#define X86_BUG_ESPFIX X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */
+#endif
+
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/desc_defs.h b/arch/x86/include/asm/desc_defs.h
index 278441f39856..eb5deb42484d 100644
--- a/arch/x86/include/asm/desc_defs.h
+++ b/arch/x86/include/asm/desc_defs.h
@@ -98,4 +98,27 @@ struct desc_ptr {
#endif /* !__ASSEMBLY__ */
+/* Access rights as returned by LAR */
+#define AR_TYPE_RODATA (0 * (1 << 9))
+#define AR_TYPE_RWDATA (1 * (1 << 9))
+#define AR_TYPE_RODATA_EXPDOWN (2 * (1 << 9))
+#define AR_TYPE_RWDATA_EXPDOWN (3 * (1 << 9))
+#define AR_TYPE_XOCODE (4 * (1 << 9))
+#define AR_TYPE_XRCODE (5 * (1 << 9))
+#define AR_TYPE_XOCODE_CONF (6 * (1 << 9))
+#define AR_TYPE_XRCODE_CONF (7 * (1 << 9))
+#define AR_TYPE_MASK (7 * (1 << 9))
+
+#define AR_DPL0 (0 * (1 << 13))
+#define AR_DPL3 (3 * (1 << 13))
+#define AR_DPL_MASK (3 * (1 << 13))
+
+#define AR_A (1 << 8) /* "Accessed" */
+#define AR_S (1 << 12) /* If clear, "System" segment */
+#define AR_P (1 << 15) /* "Present" */
+#define AR_AVL (1 << 20) /* "AVaiLable" (no HW effect) */
+#define AR_L (1 << 21) /* "Long mode" for code segments */
+#define AR_DB (1 << 22) /* D/B, effect depends on type */
+#define AR_G (1 << 23) /* "Granularity" (limit in pages) */
+
#endif /* _ASM_X86_DESC_DEFS_H */
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 0010c78c4998..53748c45e488 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -3,6 +3,7 @@
#include <asm/fpu/api.h>
#include <asm/pgtable.h>
+#include <asm/tlb.h>
/*
* We map the EFI regions needed for runtime services non-contiguously,
@@ -25,6 +26,8 @@
#define EFI32_LOADER_SIGNATURE "EL32"
#define EFI64_LOADER_SIGNATURE "EL64"
+#define MAX_CMDLINE_ADDRESS UINT_MAX
+
#ifdef CONFIG_X86_32
@@ -64,6 +67,17 @@ extern u64 asmlinkage efi_call(void *fp, ...);
#define efi_call_phys(f, args...) efi_call((f), args)
+/*
+ * Scratch space used for switching the pagetable in the EFI stub
+ */
+struct efi_scratch {
+ u64 r15;
+ u64 prev_cr3;
+ pgd_t *efi_pgt;
+ bool use_pgd;
+ u64 phys_stack;
+} __packed;
+
#define efi_call_virt(f, ...) \
({ \
efi_status_t __s; \
@@ -71,7 +85,20 @@ extern u64 asmlinkage efi_call(void *fp, ...);
efi_sync_low_kernel_mappings(); \
preempt_disable(); \
__kernel_fpu_begin(); \
+ \
+ if (efi_scratch.use_pgd) { \
+ efi_scratch.prev_cr3 = read_cr3(); \
+ write_cr3((unsigned long)efi_scratch.efi_pgt); \
+ __flush_tlb_all(); \
+ } \
+ \
__s = efi_call((void *)efi.systab->runtime->f, __VA_ARGS__); \
+ \
+ if (efi_scratch.use_pgd) { \
+ write_cr3(efi_scratch.prev_cr3); \
+ __flush_tlb_all(); \
+ } \
+ \
__kernel_fpu_end(); \
preempt_enable(); \
__s; \
@@ -111,11 +138,12 @@ extern void __init efi_memory_uc(u64 addr, unsigned long size);
extern void __init efi_map_region(efi_memory_desc_t *md);
extern void __init efi_map_region_fixed(efi_memory_desc_t *md);
extern void efi_sync_low_kernel_mappings(void);
+extern int __init efi_alloc_page_tables(void);
extern int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages);
extern void __init efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages);
extern void __init old_map_region(efi_memory_desc_t *md);
extern void __init runtime_code_page_mkexec(void);
-extern void __init efi_runtime_mkexec(void);
+extern void __init efi_runtime_update_mappings(void);
extern void __init efi_dump_pagetable(void);
extern void __init efi_apply_memmap_quirks(void);
extern int __init efi_reuse_config(u64 tables, int nr_tables);
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 1514753fd435..15340e36ddcb 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -256,7 +256,7 @@ extern int force_personality32;
instruction set this CPU supports. This could be done in user space,
but it's not easy, and we've already done it here. */
-#define ELF_HWCAP (boot_cpu_data.x86_capability[0])
+#define ELF_HWCAP (boot_cpu_data.x86_capability[CPUID_1_EDX])
/* This yields a string that ld.so will use to load implementation
specific libraries for optimization. This is more specific in
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index 9994d4229002..38951b0fcc5a 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -20,17 +20,16 @@
/* Supported features which support lazy state saving */
#define XFEATURE_MASK_LAZY (XFEATURE_MASK_FP | \
- XFEATURE_MASK_SSE)
-
-/* Supported features which require eager state saving */
-#define XFEATURE_MASK_EAGER (XFEATURE_MASK_BNDREGS | \
- XFEATURE_MASK_BNDCSR | \
+ XFEATURE_MASK_SSE | \
XFEATURE_MASK_YMM | \
XFEATURE_MASK_OPMASK | \
XFEATURE_MASK_ZMM_Hi256 | \
XFEATURE_MASK_Hi16_ZMM | \
XFEATURE_MASK_PKRU)
+/* Supported features which require eager state saving */
+#define XFEATURE_MASK_EAGER (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR)
+
/* All currently supported features */
#define XCNTXT_MASK (XFEATURE_MASK_LAZY | XFEATURE_MASK_EAGER)
diff --git a/arch/x86/include/asm/gpio.h b/arch/x86/include/asm/gpio.h
deleted file mode 100644
index b3799d88ffcf..000000000000
--- a/arch/x86/include/asm/gpio.h
+++ /dev/null
@@ -1,4 +0,0 @@
-#ifndef __LINUX_GPIO_H
-#warning Include linux/gpio.h instead of asm/gpio.h
-#include <linux/gpio.h>
-#endif
diff --git a/arch/x86/include/asm/imr.h b/arch/x86/include/asm/imr.h
index cd2ce4068441..ebea2c9d2cdc 100644
--- a/arch/x86/include/asm/imr.h
+++ b/arch/x86/include/asm/imr.h
@@ -53,7 +53,7 @@
#define IMR_MASK (IMR_ALIGN - 1)
int imr_add_range(phys_addr_t base, size_t size,
- unsigned int rmask, unsigned int wmask, bool lock);
+ unsigned int rmask, unsigned int wmask);
int imr_remove_range(phys_addr_t base, size_t size);
diff --git a/arch/x86/include/asm/ipi.h b/arch/x86/include/asm/ipi.h
index cfc9a0d2d07c..a4fe16e42b7b 100644
--- a/arch/x86/include/asm/ipi.h
+++ b/arch/x86/include/asm/ipi.h
@@ -57,67 +57,13 @@ static inline void __xapic_wait_icr_idle(void)
cpu_relax();
}
-static inline void
-__default_send_IPI_shortcut(unsigned int shortcut, int vector, unsigned int dest)
-{
- /*
- * Subtle. In the case of the 'never do double writes' workaround
- * we have to lock out interrupts to be safe. As we don't care
- * of the value read we use an atomic rmw access to avoid costly
- * cli/sti. Otherwise we use an even cheaper single atomic write
- * to the APIC.
- */
- unsigned int cfg;
-
- /*
- * Wait for idle.
- */
- __xapic_wait_icr_idle();
-
- /*
- * No need to touch the target chip field
- */
- cfg = __prepare_ICR(shortcut, vector, dest);
-
- /*
- * Send the IPI. The write to APIC_ICR fires this off.
- */
- native_apic_mem_write(APIC_ICR, cfg);
-}
+void __default_send_IPI_shortcut(unsigned int shortcut, int vector, unsigned int dest);
/*
* This is used to send an IPI with no shorthand notation (the destination is
* specified in bits 56 to 63 of the ICR).
*/
-static inline void
- __default_send_IPI_dest_field(unsigned int mask, int vector, unsigned int dest)
-{
- unsigned long cfg;
-
- /*
- * Wait for idle.
- */
- if (unlikely(vector == NMI_VECTOR))
- safe_apic_wait_icr_idle();
- else
- __xapic_wait_icr_idle();
-
- /*
- * prepare target chip field
- */
- cfg = __prepare_ICR2(mask);
- native_apic_mem_write(APIC_ICR2, cfg);
-
- /*
- * program the ICR
- */
- cfg = __prepare_ICR(0, vector, dest);
-
- /*
- * Send the IPI. The write to APIC_ICR fires this off.
- */
- native_apic_mem_write(APIC_ICR, cfg);
-}
+void __default_send_IPI_dest_field(unsigned int mask, int vector, unsigned int dest);
extern void default_send_IPI_single(int cpu, int vector);
extern void default_send_IPI_single_phys(int cpu, int vector);
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 44adbb819041..01c8b501cb6d 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -32,6 +32,7 @@
#include <asm/mtrr.h>
#include <asm/msr-index.h>
#include <asm/asm.h>
+#include <asm/kvm_page_track.h>
#define KVM_MAX_VCPUS 255
#define KVM_SOFT_MAX_VCPUS 160
@@ -214,6 +215,14 @@ struct kvm_mmu_memory_cache {
void *objects[KVM_NR_MEM_OBJS];
};
+/*
+ * the pages used as guest page table on soft mmu are tracked by
+ * kvm_memory_slot.arch.gfn_track which is 16 bits, so the role bits used
+ * by indirect shadow page can not be more than 15 bits.
+ *
+ * Currently, we used 14 bits that are @level, @cr4_pae, @quadrant, @access,
+ * @nxe, @cr0_wp, @smep_andnot_wp and @smap_andnot_wp.
+ */
union kvm_mmu_page_role {
unsigned word;
struct {
@@ -276,7 +285,7 @@ struct kvm_mmu_page {
#endif
/* Number of writes since the last time traversal visited this page. */
- int write_flooding_count;
+ atomic_t write_flooding_count;
};
struct kvm_pio_request {
@@ -338,12 +347,8 @@ struct kvm_mmu {
struct rsvd_bits_validate guest_rsvd_check;
- /*
- * Bitmap: bit set = last pte in walk
- * index[0:1]: level (zero-based)
- * index[2]: pte.ps
- */
- u8 last_pte_bitmap;
+ /* Can have large pages at levels 2..last_nonleaf_level-1. */
+ u8 last_nonleaf_level;
bool nx;
@@ -498,7 +503,6 @@ struct kvm_vcpu_arch {
struct kvm_mmu_memory_cache mmu_page_header_cache;
struct fpu guest_fpu;
- bool eager_fpu;
u64 xcr0;
u64 guest_supported_xcr0;
u32 guest_xstate_size;
@@ -644,12 +648,13 @@ struct kvm_vcpu_arch {
};
struct kvm_lpage_info {
- int write_count;
+ int disallow_lpage;
};
struct kvm_arch_memory_slot {
struct kvm_rmap_head *rmap[KVM_NR_PAGE_SIZES];
struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1];
+ unsigned short *gfn_track[KVM_PAGE_TRACK_MAX];
};
/*
@@ -694,6 +699,8 @@ struct kvm_arch {
*/
struct list_head active_mmu_pages;
struct list_head zapped_obsolete_pages;
+ struct kvm_page_track_notifier_node mmu_sp_tracker;
+ struct kvm_page_track_notifier_head track_notifier_head;
struct list_head assigned_dev_head;
struct iommu_domain *iommu_domain;
@@ -754,6 +761,8 @@ struct kvm_arch {
bool irqchip_split;
u8 nr_reserved_ioapic_pins;
+
+ bool disabled_lapic_found;
};
struct kvm_vm_stat {
@@ -988,6 +997,8 @@ void kvm_mmu_module_exit(void);
void kvm_mmu_destroy(struct kvm_vcpu *vcpu);
int kvm_mmu_create(struct kvm_vcpu *vcpu);
void kvm_mmu_setup(struct kvm_vcpu *vcpu);
+void kvm_mmu_init_vm(struct kvm *kvm);
+void kvm_mmu_uninit_vm(struct kvm *kvm);
void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
u64 dirty_mask, u64 nx_mask, u64 x_mask);
@@ -1127,8 +1138,6 @@ void kvm_pic_clear_all(struct kvm_pic *pic, int irq_source_id);
void kvm_inject_nmi(struct kvm_vcpu *vcpu);
-void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
- const u8 *new, int bytes);
int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn);
int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva);
void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h
new file mode 100644
index 000000000000..c2b8d24a235c
--- /dev/null
+++ b/arch/x86/include/asm/kvm_page_track.h
@@ -0,0 +1,61 @@
+#ifndef _ASM_X86_KVM_PAGE_TRACK_H
+#define _ASM_X86_KVM_PAGE_TRACK_H
+
+enum kvm_page_track_mode {
+ KVM_PAGE_TRACK_WRITE,
+ KVM_PAGE_TRACK_MAX,
+};
+
+/*
+ * The notifier represented by @kvm_page_track_notifier_node is linked into
+ * the head which will be notified when guest is triggering the track event.
+ *
+ * Write access on the head is protected by kvm->mmu_lock, read access
+ * is protected by track_srcu.
+ */
+struct kvm_page_track_notifier_head {
+ struct srcu_struct track_srcu;
+ struct hlist_head track_notifier_list;
+};
+
+struct kvm_page_track_notifier_node {
+ struct hlist_node node;
+
+ /*
+ * It is called when guest is writing the write-tracked page
+ * and write emulation is finished at that time.
+ *
+ * @vcpu: the vcpu where the write access happened.
+ * @gpa: the physical address written by guest.
+ * @new: the data was written to the address.
+ * @bytes: the written length.
+ */
+ void (*track_write)(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
+ int bytes);
+};
+
+void kvm_page_track_init(struct kvm *kvm);
+
+void kvm_page_track_free_memslot(struct kvm_memory_slot *free,
+ struct kvm_memory_slot *dont);
+int kvm_page_track_create_memslot(struct kvm_memory_slot *slot,
+ unsigned long npages);
+
+void kvm_slot_page_track_add_page(struct kvm *kvm,
+ struct kvm_memory_slot *slot, gfn_t gfn,
+ enum kvm_page_track_mode mode);
+void kvm_slot_page_track_remove_page(struct kvm *kvm,
+ struct kvm_memory_slot *slot, gfn_t gfn,
+ enum kvm_page_track_mode mode);
+bool kvm_page_track_is_active(struct kvm_vcpu *vcpu, gfn_t gfn,
+ enum kvm_page_track_mode mode);
+
+void
+kvm_page_track_register_notifier(struct kvm *kvm,
+ struct kvm_page_track_notifier_node *n);
+void
+kvm_page_track_unregister_notifier(struct kvm *kvm,
+ struct kvm_page_track_notifier_node *n);
+void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
+ int bytes);
+#endif
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index c1adf33fdd0d..bc62e7cbf1b1 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -17,15 +17,8 @@ static inline bool kvm_check_and_clear_guest_paused(void)
}
#endif /* CONFIG_KVM_GUEST */
-#ifdef CONFIG_DEBUG_RODATA
#define KVM_HYPERCALL \
ALTERNATIVE(".byte 0x0f,0x01,0xc1", ".byte 0x0f,0x01,0xd9", X86_FEATURE_VMMCALL)
-#else
-/* On AMD processors, vmcall will generate a trap that we will
- * then rewrite to the appropriate instruction.
- */
-#define KVM_HYPERCALL ".byte 0x0f,0x01,0xc1"
-#endif
/* For KVM hypercalls, a three-byte sequence of either the vmcall or the vmmcall
* instruction. The hypervisor may replace it with something else but only the
diff --git a/arch/x86/include/asm/livepatch.h b/arch/x86/include/asm/livepatch.h
index 19c099afa861..7e68f9558552 100644
--- a/arch/x86/include/asm/livepatch.h
+++ b/arch/x86/include/asm/livepatch.h
@@ -25,7 +25,6 @@
#include <linux/module.h>
#include <linux/ftrace.h>
-#ifdef CONFIG_LIVEPATCH
static inline int klp_check_compiler_support(void)
{
#ifndef CC_USING_FENTRY
@@ -40,8 +39,5 @@ static inline void klp_arch_set_pc(struct pt_regs *regs, unsigned long ip)
{
regs->ip = ip;
}
-#else
-#error Live patching support is disabled; check CONFIG_LIVEPATCH
-#endif
#endif /* _ASM_X86_LIVEPATCH_H */
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 2ea4527e462f..92b6f651fa4f 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -40,8 +40,20 @@
#define MCI_STATUS_AR (1ULL<<55) /* Action required */
/* AMD-specific bits */
-#define MCI_STATUS_DEFERRED (1ULL<<44) /* declare an uncorrected error */
+#define MCI_STATUS_DEFERRED (1ULL<<44) /* uncorrected error, deferred exception */
#define MCI_STATUS_POISON (1ULL<<43) /* access poisonous data */
+#define MCI_STATUS_TCC (1ULL<<55) /* Task context corrupt */
+
+/*
+ * McaX field if set indicates a given bank supports MCA extensions:
+ * - Deferred error interrupt type is specifiable by bank.
+ * - MCx_MISC0[BlkPtr] field indicates presence of extended MISC registers,
+ * But should not be used to determine MSR numbers.
+ * - TCC bit is present in MCx_STATUS.
+ */
+#define MCI_CONFIG_MCAX 0x1
+#define MCI_IPID_MCATYPE 0xFFFF0000
+#define MCI_IPID_HWID 0xFFF
/*
* Note that the full MCACOD field of IA32_MCi_STATUS MSR is
@@ -91,6 +103,16 @@
#define MCE_LOG_LEN 32
#define MCE_LOG_SIGNATURE "MACHINECHECK"
+/* AMD Scalable MCA */
+#define MSR_AMD64_SMCA_MC0_MISC0 0xc0002003
+#define MSR_AMD64_SMCA_MC0_CONFIG 0xc0002004
+#define MSR_AMD64_SMCA_MC0_IPID 0xc0002005
+#define MSR_AMD64_SMCA_MC0_MISC1 0xc000200a
+#define MSR_AMD64_SMCA_MCx_MISC(x) (MSR_AMD64_SMCA_MC0_MISC0 + 0x10*(x))
+#define MSR_AMD64_SMCA_MCx_CONFIG(x) (MSR_AMD64_SMCA_MC0_CONFIG + 0x10*(x))
+#define MSR_AMD64_SMCA_MCx_IPID(x) (MSR_AMD64_SMCA_MC0_IPID + 0x10*(x))
+#define MSR_AMD64_SMCA_MCx_MISCy(x, y) ((MSR_AMD64_SMCA_MC0_MISC1 + y) + (0x10*(x)))
+
/*
* This structure contains all data related to the MCE log. Also
* carries a signature to make it easier to find from external
@@ -113,6 +135,7 @@ struct mca_config {
bool ignore_ce;
bool disabled;
bool ser;
+ bool recovery;
bool bios_cmci_threshold;
u8 banks;
s8 bootlog;
@@ -287,4 +310,49 @@ struct cper_sec_mem_err;
extern void apei_mce_report_mem_error(int corrected,
struct cper_sec_mem_err *mem_err);
+/*
+ * Enumerate new IP types and HWID values in AMD processors which support
+ * Scalable MCA.
+ */
+#ifdef CONFIG_X86_MCE_AMD
+enum amd_ip_types {
+ SMCA_F17H_CORE = 0, /* Core errors */
+ SMCA_DF, /* Data Fabric */
+ SMCA_UMC, /* Unified Memory Controller */
+ SMCA_PB, /* Parameter Block */
+ SMCA_PSP, /* Platform Security Processor */
+ SMCA_SMU, /* System Management Unit */
+ N_AMD_IP_TYPES
+};
+
+struct amd_hwid {
+ const char *name;
+ unsigned int hwid;
+};
+
+extern struct amd_hwid amd_hwids[N_AMD_IP_TYPES];
+
+enum amd_core_mca_blocks {
+ SMCA_LS = 0, /* Load Store */
+ SMCA_IF, /* Instruction Fetch */
+ SMCA_L2_CACHE, /* L2 cache */
+ SMCA_DE, /* Decoder unit */
+ RES, /* Reserved */
+ SMCA_EX, /* Execution unit */
+ SMCA_FP, /* Floating Point */
+ SMCA_L3_CACHE, /* L3 cache */
+ N_CORE_MCA_BLOCKS
+};
+
+extern const char * const amd_core_mcablock_names[N_CORE_MCA_BLOCKS];
+
+enum amd_df_mca_blocks {
+ SMCA_CS = 0, /* Coherent Slave */
+ SMCA_PIE, /* Power management, Interrupts, etc */
+ N_DF_BLOCKS
+};
+
+extern const char * const amd_df_mcablock_names[N_DF_BLOCKS];
+#endif
+
#endif /* _ASM_X86_MCE_H */
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 1e1b07a5a738..9d3a96c4da78 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -3,6 +3,7 @@
#include <asm/cpu.h>
#include <linux/earlycpio.h>
+#include <linux/initrd.h>
#define native_rdmsr(msr, val1, val2) \
do { \
@@ -143,4 +144,29 @@ static inline void reload_early_microcode(void) { }
static inline bool
get_builtin_firmware(struct cpio_data *cd, const char *name) { return false; }
#endif
+
+static inline unsigned long get_initrd_start(void)
+{
+#ifdef CONFIG_BLK_DEV_INITRD
+ return initrd_start;
+#else
+ return 0;
+#endif
+}
+
+static inline unsigned long get_initrd_start_addr(void)
+{
+#ifdef CONFIG_BLK_DEV_INITRD
+#ifdef CONFIG_X86_32
+ unsigned long *initrd_start_p = (unsigned long *)__pa_nodebug(&initrd_start);
+
+ return (unsigned long)__pa_nodebug(*initrd_start_p);
+#else
+ return get_initrd_start();
+#endif
+#else /* CONFIG_BLK_DEV_INITRD */
+ return 0;
+#endif
+}
+
#endif /* _ASM_X86_MICROCODE_H */
diff --git a/arch/x86/include/asm/microcode_intel.h b/arch/x86/include/asm/microcode_intel.h
index 8559b0102ea1..603417f8dd6c 100644
--- a/arch/x86/include/asm/microcode_intel.h
+++ b/arch/x86/include/asm/microcode_intel.h
@@ -40,7 +40,6 @@ struct extended_sigtable {
#define DEFAULT_UCODE_TOTALSIZE (DEFAULT_UCODE_DATASIZE + MC_HEADER_SIZE)
#define EXT_HEADER_SIZE (sizeof(struct extended_sigtable))
#define EXT_SIGNATURE_SIZE (sizeof(struct extended_signature))
-#define DWSIZE (sizeof(u32))
#define get_totalsize(mc) \
(((struct microcode_intel *)mc)->hdr.datasize ? \
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index b05402ef3b84..2da46ac16e37 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -1,7 +1,12 @@
#ifndef _ASM_X86_MSR_INDEX_H
#define _ASM_X86_MSR_INDEX_H
-/* CPU model specific register (MSR) numbers */
+/*
+ * CPU model specific register (MSR) numbers.
+ *
+ * Do not add new entries to this file unless the definitions are shared
+ * between multiple compilation units.
+ */
/* x86-64 specific MSRs */
#define MSR_EFER 0xc0000080 /* extended feature register */
@@ -230,10 +235,10 @@
#define HWP_PACKAGE_LEVEL_REQUEST_BIT (1<<11)
/* IA32_HWP_CAPABILITIES */
-#define HWP_HIGHEST_PERF(x) (x & 0xff)
-#define HWP_GUARANTEED_PERF(x) ((x & (0xff << 8)) >>8)
-#define HWP_MOSTEFFICIENT_PERF(x) ((x & (0xff << 16)) >>16)
-#define HWP_LOWEST_PERF(x) ((x & (0xff << 24)) >>24)
+#define HWP_HIGHEST_PERF(x) (((x) >> 0) & 0xff)
+#define HWP_GUARANTEED_PERF(x) (((x) >> 8) & 0xff)
+#define HWP_MOSTEFFICIENT_PERF(x) (((x) >> 16) & 0xff)
+#define HWP_LOWEST_PERF(x) (((x) >> 24) & 0xff)
/* IA32_HWP_REQUEST */
#define HWP_MIN_PERF(x) (x & 0xff)
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index f6192502149e..601f1b8f9961 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -13,6 +13,7 @@
#include <linux/bug.h>
#include <linux/types.h>
#include <linux/cpumask.h>
+#include <asm/frame.h>
static inline int paravirt_enabled(void)
{
@@ -756,15 +757,19 @@ static __always_inline void __ticket_unlock_kick(struct arch_spinlock *lock,
* call. The return value in rax/eax will not be saved, even for void
* functions.
*/
+#define PV_THUNK_NAME(func) "__raw_callee_save_" #func
#define PV_CALLEE_SAVE_REGS_THUNK(func) \
extern typeof(func) __raw_callee_save_##func; \
\
asm(".pushsection .text;" \
- ".globl __raw_callee_save_" #func " ; " \
- "__raw_callee_save_" #func ": " \
+ ".globl " PV_THUNK_NAME(func) ";" \
+ ".type " PV_THUNK_NAME(func) ", @function;" \
+ PV_THUNK_NAME(func) ":" \
+ FRAME_BEGIN \
PV_SAVE_ALL_CALLER_REGS \
"call " #func ";" \
PV_RESTORE_ALL_CALLER_REGS \
+ FRAME_END \
"ret;" \
".popsection")
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 77db5616a473..e8c2326478c8 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -466,8 +466,9 @@ int paravirt_disable_iospace(void);
* makes sure the incoming and outgoing types are always correct.
*/
#ifdef CONFIG_X86_32
-#define PVOP_VCALL_ARGS \
- unsigned long __eax = __eax, __edx = __edx, __ecx = __ecx
+#define PVOP_VCALL_ARGS \
+ unsigned long __eax = __eax, __edx = __edx, __ecx = __ecx; \
+ register void *__sp asm("esp")
#define PVOP_CALL_ARGS PVOP_VCALL_ARGS
#define PVOP_CALL_ARG1(x) "a" ((unsigned long)(x))
@@ -485,9 +486,10 @@ int paravirt_disable_iospace(void);
#define VEXTRA_CLOBBERS
#else /* CONFIG_X86_64 */
/* [re]ax isn't an arg, but the return val */
-#define PVOP_VCALL_ARGS \
- unsigned long __edi = __edi, __esi = __esi, \
- __edx = __edx, __ecx = __ecx, __eax = __eax
+#define PVOP_VCALL_ARGS \
+ unsigned long __edi = __edi, __esi = __esi, \
+ __edx = __edx, __ecx = __ecx, __eax = __eax; \
+ register void *__sp asm("rsp")
#define PVOP_CALL_ARGS PVOP_VCALL_ARGS
#define PVOP_CALL_ARG1(x) "D" ((unsigned long)(x))
@@ -526,7 +528,7 @@ int paravirt_disable_iospace(void);
asm volatile(pre \
paravirt_alt(PARAVIRT_CALL) \
post \
- : call_clbr \
+ : call_clbr, "+r" (__sp) \
: paravirt_type(op), \
paravirt_clobber(clbr), \
##__VA_ARGS__ \
@@ -536,7 +538,7 @@ int paravirt_disable_iospace(void);
asm volatile(pre \
paravirt_alt(PARAVIRT_CALL) \
post \
- : call_clbr \
+ : call_clbr, "+r" (__sp) \
: paravirt_type(op), \
paravirt_clobber(clbr), \
##__VA_ARGS__ \
@@ -563,7 +565,7 @@ int paravirt_disable_iospace(void);
asm volatile(pre \
paravirt_alt(PARAVIRT_CALL) \
post \
- : call_clbr \
+ : call_clbr, "+r" (__sp) \
: paravirt_type(op), \
paravirt_clobber(clbr), \
##__VA_ARGS__ \
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 462594320d39..9ab7507ca1c2 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -20,6 +20,9 @@ struct pci_sysdata {
#ifdef CONFIG_X86_64
void *iommu; /* IOMMU private data */
#endif
+#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN
+ void *fwnode; /* IRQ domain for MSI assignment */
+#endif
};
extern int pci_routeirq;
@@ -32,6 +35,7 @@ extern int noioapicreroute;
static inline int pci_domain_nr(struct pci_bus *bus)
{
struct pci_sysdata *sd = bus->sysdata;
+
return sd->domain;
}
@@ -41,6 +45,17 @@ static inline int pci_proc_domain(struct pci_bus *bus)
}
#endif
+#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN
+static inline void *_pci_root_bus_fwnode(struct pci_bus *bus)
+{
+ struct pci_sysdata *sd = bus->sysdata;
+
+ return sd->fwnode;
+}
+
+#define pci_root_bus_fwnode _pci_root_bus_fwnode
+#endif
+
/* Can be used to override the logic in pci_scan_bus for skipping
already-configured bus numbers - to be used for buggy BIOSes
or architectures with incomplete PCI setup by the loader */
@@ -105,9 +120,6 @@ void native_restore_msi_irqs(struct pci_dev *dev);
#include <asm/pci_64.h>
#endif
-/* implement the pci_ DMA API in terms of the generic device dma_ one */
-#include <asm-generic/pci-dma-compat.h>
-
/* generic pci stuff */
#include <asm-generic/pci.h>
diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h
index 46873fbd44e1..d08eacd298c2 100644
--- a/arch/x86/include/asm/pci_x86.h
+++ b/arch/x86/include/asm/pci_x86.h
@@ -93,6 +93,8 @@ extern raw_spinlock_t pci_config_lock;
extern int (*pcibios_enable_irq)(struct pci_dev *dev);
extern void (*pcibios_disable_irq)(struct pci_dev *dev);
+extern bool mp_should_keep_irq(struct device *dev);
+
struct pci_raw_ops {
int (*read)(unsigned int domain, unsigned int bus, unsigned int devfn,
int reg, int len, u32 *val);
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 7bcb861a04e5..5a2ed3ed2f26 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -165,6 +165,7 @@ struct x86_pmu_capability {
#define GLOBAL_STATUS_ASIF BIT_ULL(60)
#define GLOBAL_STATUS_COUNTERS_FROZEN BIT_ULL(59)
#define GLOBAL_STATUS_LBRS_FROZEN BIT_ULL(58)
+#define GLOBAL_STATUS_TRACE_TOPAPMI BIT_ULL(55)
/*
* IBS cpuid feature detection
diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h
index c57fd1ea9689..bf8b35d2035a 100644
--- a/arch/x86/include/asm/pmem.h
+++ b/arch/x86/include/asm/pmem.h
@@ -137,6 +137,11 @@ static inline void arch_clear_pmem(void __pmem *addr, size_t size)
arch_wb_cache_pmem(addr, size);
}
+static inline void arch_invalidate_pmem(void __pmem *addr, size_t size)
+{
+ clflush_cache_range((void __force *) addr, size);
+}
+
static inline bool __arch_has_wmb_pmem(void)
{
/*
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index 01bcde84d3e4..d397deb58146 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -94,10 +94,19 @@ static __always_inline bool should_resched(int preempt_offset)
#ifdef CONFIG_PREEMPT
extern asmlinkage void ___preempt_schedule(void);
-# define __preempt_schedule() asm ("call ___preempt_schedule")
+# define __preempt_schedule() \
+({ \
+ register void *__sp asm(_ASM_SP); \
+ asm volatile ("call ___preempt_schedule" : "+r"(__sp)); \
+})
+
extern asmlinkage void preempt_schedule(void);
extern asmlinkage void ___preempt_schedule_notrace(void);
-# define __preempt_schedule_notrace() asm ("call ___preempt_schedule_notrace")
+# define __preempt_schedule_notrace() \
+({ \
+ register void *__sp asm(_ASM_SP); \
+ asm volatile ("call ___preempt_schedule_notrace" : "+r"(__sp)); \
+})
extern asmlinkage void preempt_schedule_notrace(void);
#endif
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index ecb410310e70..983738ac014c 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -128,6 +128,8 @@ struct cpuinfo_x86 {
u16 booted_cores;
/* Physical processor id: */
u16 phys_proc_id;
+ /* Logical processor id: */
+ u16 logical_proc_id;
/* Core id: */
u16 cpu_core_id;
/* Compute unit id */
@@ -297,10 +299,13 @@ struct tss_struct {
*/
unsigned long io_bitmap[IO_BITMAP_LONGS + 1];
+#ifdef CONFIG_X86_32
/*
- * Space for the temporary SYSENTER stack:
+ * Space for the temporary SYSENTER stack.
*/
+ unsigned long SYSENTER_stack_canary;
unsigned long SYSENTER_stack[64];
+#endif
} ____cacheline_aligned;
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index a4a77286cb1d..9b9b30b19441 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -7,12 +7,23 @@
void syscall_init(void);
+#ifdef CONFIG_X86_64
void entry_SYSCALL_64(void);
-void entry_SYSCALL_compat(void);
+#endif
+
+#ifdef CONFIG_X86_32
void entry_INT80_32(void);
-void entry_INT80_compat(void);
void entry_SYSENTER_32(void);
+void __begin_SYSENTER_singlestep_region(void);
+void __end_SYSENTER_singlestep_region(void);
+#endif
+
+#ifdef CONFIG_IA32_EMULATION
void entry_SYSENTER_compat(void);
+void __end_entry_SYSENTER_compat(void);
+void entry_SYSCALL_compat(void);
+void entry_INT80_compat(void);
+#endif
void x86_configure_nx(void);
void x86_report_nx(void);
diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h
index 9f92c180ed2f..9d55f9b6e167 100644
--- a/arch/x86/include/asm/qspinlock_paravirt.h
+++ b/arch/x86/include/asm/qspinlock_paravirt.h
@@ -36,8 +36,10 @@ PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath);
*/
asm (".pushsection .text;"
".globl " PV_UNLOCK ";"
+ ".type " PV_UNLOCK ", @function;"
".align 4,0x90;"
PV_UNLOCK ": "
+ FRAME_BEGIN
"push %rdx;"
"mov $0x1,%eax;"
"xor %edx,%edx;"
@@ -45,6 +47,7 @@ asm (".pushsection .text;"
"cmp $0x1,%al;"
"jne .slowpath;"
"pop %rdx;"
+ FRAME_END
"ret;"
".slowpath: "
"push %rsi;"
@@ -52,6 +55,7 @@ asm (".pushsection .text;"
"call " PV_UNLOCK_SLOWPATH ";"
"pop %rsi;"
"pop %rdx;"
+ FRAME_END
"ret;"
".size " PV_UNLOCK ", .-" PV_UNLOCK ";"
".popsection");
diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h
index 0a5242428659..13b6cdd0af57 100644
--- a/arch/x86/include/asm/sections.h
+++ b/arch/x86/include/asm/sections.h
@@ -7,7 +7,7 @@
extern char __brk_base[], __brk_limit[];
extern struct exception_table_entry __stop___ex_table[];
-#if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA)
+#if defined(CONFIG_X86_64)
extern char __end_rodata_hpage_align[];
#endif
diff --git a/arch/x86/include/asm/sighandling.h b/arch/x86/include/asm/sighandling.h
index 89db46752a8f..452c88b8ad06 100644
--- a/arch/x86/include/asm/sighandling.h
+++ b/arch/x86/include/asm/sighandling.h
@@ -13,7 +13,6 @@
X86_EFLAGS_CF | X86_EFLAGS_RF)
void signal_fault(struct pt_regs *regs, void __user *frame, char *where);
-int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc);
int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
struct pt_regs *regs, unsigned long mask);
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index 70bbe39043a9..7c247e7404be 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -37,7 +37,7 @@ print_context_stack_bp(struct thread_info *tinfo,
/* Generic stack tracer with callbacks */
struct stacktrace_ops {
- void (*address)(void *data, unsigned long address, int reliable);
+ int (*address)(void *data, unsigned long address, int reliable);
/* On negative return stop dumping */
int (*stack)(void *data, char *name);
walk_stack_t walk_stack;
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index ff8b9a17dc4b..ca6ba3607705 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/arch/x86/include/asm/string_64.h
@@ -78,6 +78,19 @@ int strcmp(const char *cs, const char *ct);
#define memset(s, c, n) __memset(s, c, n)
#endif
+/**
+ * memcpy_mcsafe - copy memory with indication if a machine check happened
+ *
+ * @dst: destination address
+ * @src: source address
+ * @cnt: number of bytes to copy
+ *
+ * Low level memory copy function that catches machine checks
+ *
+ * Return true for success, false for fail
+ */
+bool memcpy_mcsafe(void *dst, const void *src, size_t cnt);
+
#endif /* __KERNEL__ */
#endif /* _ASM_X86_STRING_64_H */
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index c0778fcab06d..82866697fcf1 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -134,10 +134,13 @@ struct thread_info {
#define _TIF_ADDR32 (1 << TIF_ADDR32)
#define _TIF_X32 (1 << TIF_X32)
-/* work to do in syscall_trace_enter() */
+/*
+ * work to do in syscall_trace_enter(). Also includes TIF_NOHZ for
+ * enter_from_user_mode()
+ */
#define _TIF_WORK_SYSCALL_ENTRY \
(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | _TIF_SYSCALL_AUDIT | \
- _TIF_SECCOMP | _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT | \
+ _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT | \
_TIF_NOHZ)
/* work to do on any return to user space */
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 0fb46482dfde..7f991bd5031b 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -119,12 +119,23 @@ static inline void setup_node_to_cpumask_map(void) { }
extern const struct cpumask *cpu_coregroup_mask(int cpu);
+#define topology_logical_package_id(cpu) (cpu_data(cpu).logical_proc_id)
#define topology_physical_package_id(cpu) (cpu_data(cpu).phys_proc_id)
#define topology_core_id(cpu) (cpu_data(cpu).cpu_core_id)
#ifdef ENABLE_TOPO_DEFINES
#define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu))
#define topology_sibling_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu))
+
+extern unsigned int __max_logical_packages;
+#define topology_max_packages() (__max_logical_packages)
+int topology_update_package_map(unsigned int apicid, unsigned int cpu);
+extern int topology_phys_to_logical_pkg(unsigned int pkg);
+#else
+#define topology_max_packages() (1)
+static inline int
+topology_update_package_map(unsigned int apicid, unsigned int cpu) { return 0; }
+static inline int topology_phys_to_logical_pkg(unsigned int pkg) { return 0; }
#endif
static inline void arch_fix_phys_package_id(int num, u32 slot)
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 6d7c5479bcea..174c4212780a 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -29,6 +29,8 @@ static inline cycles_t get_cycles(void)
return rdtsc();
}
+extern struct system_counterval_t convert_art_to_tsc(cycle_t art);
+
extern void tsc_init(void);
extern void mark_tsc_unstable(char *reason);
extern int unsynchronized_tsc(void);
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index a4a30e4b2d34..88bff6dd23ad 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -90,12 +90,11 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un
likely(!__range_not_ok(addr, size, user_addr_max()))
/*
- * The exception table consists of pairs of addresses relative to the
- * exception table enty itself: the first is the address of an
- * instruction that is allowed to fault, and the second is the address
- * at which the program should continue. No registers are modified,
- * so it is entirely up to the continuation code to figure out what to
- * do.
+ * The exception table consists of triples of addresses relative to the
+ * exception table entry itself. The first address is of an instruction
+ * that is allowed to fault, the second is the target at which the program
+ * should continue. The third is a handler function to deal with the fault
+ * caused by the instruction in the first field.
*
* All the routines below use bits of fixup code that are out of line
* with the main instruction path. This means when everything is well,
@@ -104,13 +103,14 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un
*/
struct exception_table_entry {
- int insn, fixup;
+ int insn, fixup, handler;
};
/* This is not the generic standard exception_table_entry format */
#define ARCH_HAS_SORT_EXTABLE
#define ARCH_HAS_SEARCH_EXTABLE
-extern int fixup_exception(struct pt_regs *regs);
+extern int fixup_exception(struct pt_regs *regs, int trapnr);
+extern bool ex_has_fault_handler(unsigned long ip);
extern int early_fixup_exception(unsigned long *ip);
/*
@@ -179,10 +179,11 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL))
({ \
int __ret_gu; \
register __inttype(*(ptr)) __val_gu asm("%"_ASM_DX); \
+ register void *__sp asm(_ASM_SP); \
__chk_user_ptr(ptr); \
might_fault(); \
- asm volatile("call __get_user_%P3" \
- : "=a" (__ret_gu), "=r" (__val_gu) \
+ asm volatile("call __get_user_%P4" \
+ : "=a" (__ret_gu), "=r" (__val_gu), "+r" (__sp) \
: "0" (ptr), "i" (sizeof(*(ptr)))); \
(x) = (__force __typeof__(*(ptr))) __val_gu; \
__builtin_expect(__ret_gu, 0); \
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index f5dcb5204dcd..3fe0eac59462 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -48,20 +48,28 @@ __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n)
switch (n) {
case 1:
+ __uaccess_begin();
__put_user_size(*(u8 *)from, (u8 __user *)to,
1, ret, 1);
+ __uaccess_end();
return ret;
case 2:
+ __uaccess_begin();
__put_user_size(*(u16 *)from, (u16 __user *)to,
2, ret, 2);
+ __uaccess_end();
return ret;
case 4:
+ __uaccess_begin();
__put_user_size(*(u32 *)from, (u32 __user *)to,
4, ret, 4);
+ __uaccess_end();
return ret;
case 8:
+ __uaccess_begin();
__put_user_size(*(u64 *)from, (u64 __user *)to,
8, ret, 8);
+ __uaccess_end();
return ret;
}
}
@@ -103,13 +111,19 @@ __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n)
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;
}
}
@@ -148,13 +162,19 @@ __copy_from_user(void *to, const void __user *from, unsigned long n)
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;
}
}
@@ -170,13 +190,19 @@ static __always_inline unsigned long __copy_from_user_nocache(void *to,
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;
}
}
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 3bcdcc84259d..a12a047184ee 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -110,9 +110,10 @@ extern struct { char _entry[32]; } hypercall_page[];
register unsigned long __arg2 asm(__HYPERCALL_ARG2REG) = __arg2; \
register unsigned long __arg3 asm(__HYPERCALL_ARG3REG) = __arg3; \
register unsigned long __arg4 asm(__HYPERCALL_ARG4REG) = __arg4; \
- register unsigned long __arg5 asm(__HYPERCALL_ARG5REG) = __arg5;
+ register unsigned long __arg5 asm(__HYPERCALL_ARG5REG) = __arg5; \
+ register void *__sp asm(_ASM_SP);
-#define __HYPERCALL_0PARAM "=r" (__res)
+#define __HYPERCALL_0PARAM "=r" (__res), "+r" (__sp)
#define __HYPERCALL_1PARAM __HYPERCALL_0PARAM, "+r" (__arg1)
#define __HYPERCALL_2PARAM __HYPERCALL_1PARAM, "+r" (__arg2)
#define __HYPERCALL_3PARAM __HYPERCALL_2PARAM, "+r" (__arg3)
diff --git a/arch/x86/include/asm/xen/pci.h b/arch/x86/include/asm/xen/pci.h
index 968d57dd54c9..f320ee32d5a1 100644
--- a/arch/x86/include/asm/xen/pci.h
+++ b/arch/x86/include/asm/xen/pci.h
@@ -57,7 +57,7 @@ static inline int xen_pci_frontend_enable_msi(struct pci_dev *dev,
{
if (xen_pci_frontend && xen_pci_frontend->enable_msi)
return xen_pci_frontend->enable_msi(dev, vectors);
- return -ENODEV;
+ return -ENOSYS;
}
static inline void xen_pci_frontend_disable_msi(struct pci_dev *dev)
{
@@ -69,7 +69,7 @@ static inline int xen_pci_frontend_enable_msix(struct pci_dev *dev,
{
if (xen_pci_frontend && xen_pci_frontend->enable_msix)
return xen_pci_frontend->enable_msix(dev, vectors, nvec);
- return -ENODEV;
+ return -ENOSYS;
}
static inline void xen_pci_frontend_disable_msix(struct pci_dev *dev)
{
diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h
index 7956412d09bd..9b1a91834ac8 100644
--- a/arch/x86/include/uapi/asm/hyperv.h
+++ b/arch/x86/include/uapi/asm/hyperv.h
@@ -226,7 +226,9 @@
(~((1ull << HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT) - 1))
/* Declare the various hypercall operations. */
-#define HV_X64_HV_NOTIFY_LONG_SPIN_WAIT 0x0008
+#define HVCALL_NOTIFY_LONG_SPIN_WAIT 0x0008
+#define HVCALL_POST_MESSAGE 0x005c
+#define HVCALL_SIGNAL_EVENT 0x005d
#define HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE 0x00000001
#define HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT 12
diff --git a/arch/x86/include/uapi/asm/sigcontext.h b/arch/x86/include/uapi/asm/sigcontext.h
index d485232f1e9f..62d4111c1c54 100644
--- a/arch/x86/include/uapi/asm/sigcontext.h
+++ b/arch/x86/include/uapi/asm/sigcontext.h
@@ -256,7 +256,7 @@ struct sigcontext_64 {
__u16 cs;
__u16 gs;
__u16 fs;
- __u16 __pad0;
+ __u16 ss;
__u64 err;
__u64 trapno;
__u64 oldmask;
@@ -341,9 +341,37 @@ struct sigcontext {
__u64 rip;
__u64 eflags; /* RFLAGS */
__u16 cs;
+
+ /*
+ * Prior to 2.5.64 ("[PATCH] x86-64 updates for 2.5.64-bk3"),
+ * Linux saved and restored fs and gs in these slots. This
+ * was counterproductive, as fsbase and gsbase were never
+ * saved, so arch_prctl was presumably unreliable.
+ *
+ * These slots should never be reused without extreme caution:
+ *
+ * - Some DOSEMU versions stash fs and gs in these slots manually,
+ * thus overwriting anything the kernel expects to be preserved
+ * in these slots.
+ *
+ * - If these slots are ever needed for any other purpose,
+ * there is some risk that very old 64-bit binaries could get
+ * confused. I doubt that many such binaries still work,
+ * though, since the same patch in 2.5.64 also removed the
+ * 64-bit set_thread_area syscall, so it appears that there
+ * is no TLS API beyond modify_ldt that works in both pre-
+ * and post-2.5.64 kernels.
+ *
+ * If the kernel ever adds explicit fs, gs, fsbase, and gsbase
+ * save/restore, it will most likely need to be opt-in and use
+ * different context slots.
+ */
__u16 gs;
__u16 fs;
- __u16 __pad0;
+ union {
+ __u16 ss; /* If UC_SIGCONTEXT_SS */
+ __u16 __pad0; /* Alias name for old (!UC_SIGCONTEXT_SS) user-space */
+ };
__u64 err;
__u64 trapno;
__u64 oldmask;
diff --git a/arch/x86/include/uapi/asm/ucontext.h b/arch/x86/include/uapi/asm/ucontext.h
index b7c29c8017f2..e3d1ec90616e 100644
--- a/arch/x86/include/uapi/asm/ucontext.h
+++ b/arch/x86/include/uapi/asm/ucontext.h
@@ -1,11 +1,54 @@
#ifndef _ASM_X86_UCONTEXT_H
#define _ASM_X86_UCONTEXT_H
-#define UC_FP_XSTATE 0x1 /* indicates the presence of extended state
- * information in the memory layout pointed
- * by the fpstate pointer in the ucontext's
- * sigcontext struct (uc_mcontext).
- */
+/*
+ * Indicates the presence of extended state information in the memory
+ * layout pointed by the fpstate pointer in the ucontext's sigcontext
+ * struct (uc_mcontext).
+ */
+#define UC_FP_XSTATE 0x1
+
+#ifdef __x86_64__
+/*
+ * UC_SIGCONTEXT_SS will be set when delivering 64-bit or x32 signals on
+ * kernels that save SS in the sigcontext. All kernels that set
+ * UC_SIGCONTEXT_SS will correctly restore at least the low 32 bits of esp
+ * regardless of SS (i.e. they implement espfix).
+ *
+ * Kernels that set UC_SIGCONTEXT_SS will also set UC_STRICT_RESTORE_SS
+ * when delivering a signal that came from 64-bit code.
+ *
+ * Sigreturn restores SS as follows:
+ *
+ * if (saved SS is valid || UC_STRICT_RESTORE_SS is set ||
+ * saved CS is not 64-bit)
+ * new SS = saved SS (will fail IRET and signal if invalid)
+ * else
+ * new SS = a flat 32-bit data segment
+ *
+ * This behavior serves three purposes:
+ *
+ * - Legacy programs that construct a 64-bit sigcontext from scratch
+ * with zero or garbage in the SS slot (e.g. old CRIU) and call
+ * sigreturn will still work.
+ *
+ * - Old DOSEMU versions sometimes catch a signal from a segmented
+ * context, delete the old SS segment (with modify_ldt), and change
+ * the saved CS to a 64-bit segment. These DOSEMU versions expect
+ * sigreturn to send them back to 64-bit mode without killing them,
+ * despite the fact that the SS selector when the signal was raised is
+ * no longer valid. UC_STRICT_RESTORE_SS will be clear, so the kernel
+ * will fix up SS for these DOSEMU versions.
+ *
+ * - Old and new programs that catch a signal and return without
+ * modifying the saved context will end up in exactly the state they
+ * started in, even if they were running in a segmented context when
+ * the signal was raised.. Old kernels would lose track of the
+ * previous SS value.
+ */
+#define UC_SIGCONTEXT_SS 0x2
+#define UC_STRICT_RESTORE_SS 0x4
+#endif
#include <asm-generic/ucontext.h>