[GIT PULL] x86/xsave changes for v3.17-rc1
From: H. Peter Anvin
Date: Mon Aug 11 2014 - 19:04:06 EST
Hi Linus,
This is a patchset to support the XSAVES instruction required to
support context switch of supervisor-only features in upcoming
silicon. This patchset missed the 3.16 merge window, which is why it
is based on 3.15-rc7.
-hpa
The following changes since commit c7208164e66f63e3ec1759b98087849286410741:
Linux 3.15-rc7 (2014-05-25 16:06:00 -0700)
are available in the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86-xsave-for-linus
for you to fetch changes up to d0f2dd186133a0241a2ccefb188a0e49e8187859:
x86, xsave: Add forgotten inline annotation (2014-06-18 15:19:59 -0700)
----------------------------------------------------------------
Borislav Petkov (1):
x86, xsave: Add forgotten inline annotation
Fenghua Yu (17):
x86/cpufeature.h: Reformat x86 feature macros
x86/xsaves: Detect xsaves/xrstors feature
x86/xsaves: Add a kernel parameter noxsaves to disable xsaves/xrstors
x86/alternative: Add alternative_input_2 to support alternative with two features and input
x86/xsaves: Change compacted format xsave area header
x86/xsaves: Define macros for xsave instructions
x86/xsaves: Define a macro for handling xsave/xrstor instruction fault
x86/xsaves: Use xsaves/xrstors to save and restore xsave area
x86/xsaves: Use xsaves/xrstors for context switch
x86/xsaves: Use xsave/xrstor for saving and restoring user space context
x86/xsaves: Clear reserved bits in xsave header
x86/xsaves: Add xsaves and xrstors support for booting time
x86/xsaves: Save xstate to task's xsave area in __save_fpu during booting time
x86/xsaves: Call booting time xsaves and xrstors in setup_init_fpu_buf
x86/xsaves: Enable xsaves/xrstors
Define kernel API to get address of each state in xsave area
x86/xsaves: Clean up code in xstate offsets computation in xsave area
H. Peter Anvin (1):
x86/xsave: Make it clear that the XSAVE macros use (%edi)/(%rdi)
Documentation/kernel-parameters.txt | 15 ++
arch/x86/include/asm/alternative.h | 14 ++
arch/x86/include/asm/cpufeature.h | 370 +++++++++++++++++-----------------
arch/x86/include/asm/fpu-internal.h | 9 +-
arch/x86/include/asm/processor.h | 4 +-
arch/x86/include/asm/xsave.h | 223 +++++++++++++++-----
arch/x86/include/uapi/asm/msr-index.h | 2 +
arch/x86/kernel/cpu/common.c | 17 ++
arch/x86/kernel/cpu/scattered.c | 1 -
arch/x86/kernel/i387.c | 2 +-
arch/x86/kernel/process.c | 1 +
arch/x86/kernel/xsave.c | 118 ++++++++++-
12 files changed, 523 insertions(+), 253 deletions(-)
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 30a8ad0d..0ebd952 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2124,6 +2124,21 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
and restore using xsave. The kernel will fallback to
enabling legacy floating-point and sse state.
+ noxsaveopt [X86] Disables xsaveopt used in saving x86 extended
+ register states. The kernel will fall back to use
+ xsave to save the states. By using this parameter,
+ performance of saving the states is degraded because
+ xsave doesn't support modified optimization while
+ xsaveopt supports it on xsaveopt enabled systems.
+
+ noxsaves [X86] Disables xsaves and xrstors used in saving and
+ restoring x86 extended register state in compacted
+ form of xsave area. The kernel will fall back to use
+ xsaveopt and xrstor to save and restore the states
+ in standard form of xsave area. By using this
+ parameter, xsave area per process might occupy more
+ memory on xsaves enabled systems.
+
eagerfpu= [X86]
on enable eager fpu restore
off disable eager fpu restore
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 0a3f9c9..473bdbe 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -161,6 +161,20 @@ static inline int alternatives_text_reserved(void *start, void *end)
asm volatile (ALTERNATIVE(oldinstr, newinstr, feature) \
: : "i" (0), ## input)
+/*
+ * This is similar to alternative_input. But it has two features and
+ * respective instructions.
+ *
+ * If CPU has feature2, newinstr2 is used.
+ * Otherwise, if CPU has feature1, newinstr1 is used.
+ * Otherwise, oldinstr is used.
+ */
+#define alternative_input_2(oldinstr, newinstr1, feature1, newinstr2, \
+ feature2, input...) \
+ asm volatile(ALTERNATIVE_2(oldinstr, newinstr1, feature1, \
+ newinstr2, feature2) \
+ : : "i" (0), ## input)
+
/* Like alternative_input, but with a single output argument */
#define alternative_io(oldinstr, newinstr, feature, output, input...) \
asm volatile (ALTERNATIVE(oldinstr, newinstr, feature) \
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index e265ff9..b82f951 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -8,7 +8,7 @@
#include <asm/required-features.h>
#endif
-#define NCAPINTS 10 /* N 32-bit words worth of info */
+#define NCAPINTS 11 /* N 32-bit words worth of info */
#define NBUGINTS 1 /* N 32-bit bug flags */
/*
@@ -18,213 +18,218 @@
*/
/* Intel-defined CPU features, CPUID level 0x00000001 (edx), word 0 */
-#define X86_FEATURE_FPU (0*32+ 0) /* Onboard FPU */
-#define X86_FEATURE_VME (0*32+ 1) /* Virtual Mode Extensions */
-#define X86_FEATURE_DE (0*32+ 2) /* Debugging Extensions */
-#define X86_FEATURE_PSE (0*32+ 3) /* Page Size Extensions */
-#define X86_FEATURE_TSC (0*32+ 4) /* Time Stamp Counter */
-#define X86_FEATURE_MSR (0*32+ 5) /* Model-Specific Registers */
-#define X86_FEATURE_PAE (0*32+ 6) /* Physical Address Extensions */
-#define X86_FEATURE_MCE (0*32+ 7) /* Machine Check Exception */
-#define X86_FEATURE_CX8 (0*32+ 8) /* CMPXCHG8 instruction */
-#define X86_FEATURE_APIC (0*32+ 9) /* Onboard APIC */
-#define X86_FEATURE_SEP (0*32+11) /* SYSENTER/SYSEXIT */
-#define X86_FEATURE_MTRR (0*32+12) /* Memory Type Range Registers */
-#define X86_FEATURE_PGE (0*32+13) /* Page Global Enable */
-#define X86_FEATURE_MCA (0*32+14) /* Machine Check Architecture */
-#define X86_FEATURE_CMOV (0*32+15) /* CMOV instructions */
+#define X86_FEATURE_FPU ( 0*32+ 0) /* Onboard FPU */
+#define X86_FEATURE_VME ( 0*32+ 1) /* Virtual Mode Extensions */
+#define X86_FEATURE_DE ( 0*32+ 2) /* Debugging Extensions */
+#define X86_FEATURE_PSE ( 0*32+ 3) /* Page Size Extensions */
+#define X86_FEATURE_TSC ( 0*32+ 4) /* Time Stamp Counter */
+#define X86_FEATURE_MSR ( 0*32+ 5) /* Model-Specific Registers */
+#define X86_FEATURE_PAE ( 0*32+ 6) /* Physical Address Extensions */
+#define X86_FEATURE_MCE ( 0*32+ 7) /* Machine Check Exception */
+#define X86_FEATURE_CX8 ( 0*32+ 8) /* CMPXCHG8 instruction */
+#define X86_FEATURE_APIC ( 0*32+ 9) /* Onboard APIC */
+#define X86_FEATURE_SEP ( 0*32+11) /* SYSENTER/SYSEXIT */
+#define X86_FEATURE_MTRR ( 0*32+12) /* Memory Type Range Registers */
+#define X86_FEATURE_PGE ( 0*32+13) /* Page Global Enable */
+#define X86_FEATURE_MCA ( 0*32+14) /* Machine Check Architecture */
+#define X86_FEATURE_CMOV ( 0*32+15) /* CMOV instructions */
/* (plus FCMOVcc, FCOMI with FPU) */
-#define X86_FEATURE_PAT (0*32+16) /* Page Attribute Table */
-#define X86_FEATURE_PSE36 (0*32+17) /* 36-bit PSEs */
-#define X86_FEATURE_PN (0*32+18) /* Processor serial number */
-#define X86_FEATURE_CLFLUSH (0*32+19) /* CLFLUSH instruction */
-#define X86_FEATURE_DS (0*32+21) /* "dts" Debug Store */
-#define X86_FEATURE_ACPI (0*32+22) /* ACPI via MSR */
-#define X86_FEATURE_MMX (0*32+23) /* Multimedia Extensions */
-#define X86_FEATURE_FXSR (0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */
-#define X86_FEATURE_XMM (0*32+25) /* "sse" */
-#define X86_FEATURE_XMM2 (0*32+26) /* "sse2" */
-#define X86_FEATURE_SELFSNOOP (0*32+27) /* "ss" CPU self snoop */
-#define X86_FEATURE_HT (0*32+28) /* Hyper-Threading */
-#define X86_FEATURE_ACC (0*32+29) /* "tm" Automatic clock control */
-#define X86_FEATURE_IA64 (0*32+30) /* IA-64 processor */
-#define X86_FEATURE_PBE (0*32+31) /* Pending Break Enable */
+#define X86_FEATURE_PAT ( 0*32+16) /* Page Attribute Table */
+#define X86_FEATURE_PSE36 ( 0*32+17) /* 36-bit PSEs */
+#define X86_FEATURE_PN ( 0*32+18) /* Processor serial number */
+#define X86_FEATURE_CLFLUSH ( 0*32+19) /* CLFLUSH instruction */
+#define X86_FEATURE_DS ( 0*32+21) /* "dts" Debug Store */
+#define X86_FEATURE_ACPI ( 0*32+22) /* ACPI via MSR */
+#define X86_FEATURE_MMX ( 0*32+23) /* Multimedia Extensions */
+#define X86_FEATURE_FXSR ( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */
+#define X86_FEATURE_XMM ( 0*32+25) /* "sse" */
+#define X86_FEATURE_XMM2 ( 0*32+26) /* "sse2" */
+#define X86_FEATURE_SELFSNOOP ( 0*32+27) /* "ss" CPU self snoop */
+#define X86_FEATURE_HT ( 0*32+28) /* Hyper-Threading */
+#define X86_FEATURE_ACC ( 0*32+29) /* "tm" Automatic clock control */
+#define X86_FEATURE_IA64 ( 0*32+30) /* IA-64 processor */
+#define X86_FEATURE_PBE ( 0*32+31) /* Pending Break Enable */
/* AMD-defined CPU features, CPUID level 0x80000001, word 1 */
/* Don't duplicate feature flags which are redundant with Intel! */
-#define X86_FEATURE_SYSCALL (1*32+11) /* SYSCALL/SYSRET */
-#define X86_FEATURE_MP (1*32+19) /* MP Capable. */
-#define X86_FEATURE_NX (1*32+20) /* Execute Disable */
-#define X86_FEATURE_MMXEXT (1*32+22) /* AMD MMX extensions */
-#define X86_FEATURE_FXSR_OPT (1*32+25) /* FXSAVE/FXRSTOR optimizations */
-#define X86_FEATURE_GBPAGES (1*32+26) /* "pdpe1gb" GB pages */
-#define X86_FEATURE_RDTSCP (1*32+27) /* RDTSCP */
-#define X86_FEATURE_LM (1*32+29) /* Long Mode (x86-64) */
-#define X86_FEATURE_3DNOWEXT (1*32+30) /* AMD 3DNow! extensions */
-#define X86_FEATURE_3DNOW (1*32+31) /* 3DNow! */
+#define X86_FEATURE_SYSCALL ( 1*32+11) /* SYSCALL/SYSRET */
+#define X86_FEATURE_MP ( 1*32+19) /* MP Capable. */
+#define X86_FEATURE_NX ( 1*32+20) /* Execute Disable */
+#define X86_FEATURE_MMXEXT ( 1*32+22) /* AMD MMX extensions */
+#define X86_FEATURE_FXSR_OPT ( 1*32+25) /* FXSAVE/FXRSTOR optimizations */
+#define X86_FEATURE_GBPAGES ( 1*32+26) /* "pdpe1gb" GB pages */
+#define X86_FEATURE_RDTSCP ( 1*32+27) /* RDTSCP */
+#define X86_FEATURE_LM ( 1*32+29) /* Long Mode (x86-64) */
+#define X86_FEATURE_3DNOWEXT ( 1*32+30) /* AMD 3DNow! extensions */
+#define X86_FEATURE_3DNOW ( 1*32+31) /* 3DNow! */
/* Transmeta-defined CPU features, CPUID level 0x80860001, word 2 */
-#define X86_FEATURE_RECOVERY (2*32+ 0) /* CPU in recovery mode */
-#define X86_FEATURE_LONGRUN (2*32+ 1) /* Longrun power control */
-#define X86_FEATURE_LRTI (2*32+ 3) /* LongRun table interface */
+#define X86_FEATURE_RECOVERY ( 2*32+ 0) /* CPU in recovery mode */
+#define X86_FEATURE_LONGRUN ( 2*32+ 1) /* Longrun power control */
+#define X86_FEATURE_LRTI ( 2*32+ 3) /* LongRun table interface */
/* Other features, Linux-defined mapping, word 3 */
/* This range is used for feature bits which conflict or are synthesized */
-#define X86_FEATURE_CXMMX (3*32+ 0) /* Cyrix MMX extensions */
-#define X86_FEATURE_K6_MTRR (3*32+ 1) /* AMD K6 nonstandard MTRRs */
-#define X86_FEATURE_CYRIX_ARR (3*32+ 2) /* Cyrix ARRs (= MTRRs) */
-#define X86_FEATURE_CENTAUR_MCR (3*32+ 3) /* Centaur MCRs (= MTRRs) */
+#define X86_FEATURE_CXMMX ( 3*32+ 0) /* Cyrix MMX extensions */
+#define X86_FEATURE_K6_MTRR ( 3*32+ 1) /* AMD K6 nonstandard MTRRs */
+#define X86_FEATURE_CYRIX_ARR ( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */
+#define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* Centaur MCRs (= MTRRs) */
/* cpu types for specific tunings: */
-#define X86_FEATURE_K8 (3*32+ 4) /* "" Opteron, Athlon64 */
-#define X86_FEATURE_K7 (3*32+ 5) /* "" Athlon */
-#define X86_FEATURE_P3 (3*32+ 6) /* "" P3 */
-#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 */
-#define X86_FEATURE_FXSAVE_LEAK (3*32+10) /* "" FXSAVE leaks FOP/FIP/FOP */
-#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 */
-#define X86_FEATURE_SYSCALL32 (3*32+14) /* "" syscall in ia32 userspace */
-#define X86_FEATURE_SYSENTER32 (3*32+15) /* "" sysenter in ia32 userspace */
-#define X86_FEATURE_REP_GOOD (3*32+16) /* rep microcode works well */
-#define X86_FEATURE_MFENCE_RDTSC (3*32+17) /* "" Mfence synchronizes RDTSC */
-#define X86_FEATURE_LFENCE_RDTSC (3*32+18) /* "" Lfence synchronizes RDTSC */
-#define X86_FEATURE_11AP (3*32+19) /* "" Bad local APIC aka 11AP */
-#define X86_FEATURE_NOPL (3*32+20) /* The NOPL (0F 1F) instructions */
-#define X86_FEATURE_ALWAYS (3*32+21) /* "" Always-present feature */
-#define X86_FEATURE_XTOPOLOGY (3*32+22) /* cpu topology enum extensions */
-#define X86_FEATURE_TSC_RELIABLE (3*32+23) /* TSC is known to be reliable */
-#define X86_FEATURE_NONSTOP_TSC (3*32+24) /* TSC does not stop in C states */
-#define X86_FEATURE_CLFLUSH_MONITOR (3*32+25) /* "" clflush reqd with monitor */
-#define X86_FEATURE_EXTD_APICID (3*32+26) /* has extended APICID (8 bits) */
-#define X86_FEATURE_AMD_DCM (3*32+27) /* multi-node processor */
-#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_K8 ( 3*32+ 4) /* "" Opteron, Athlon64 */
+#define X86_FEATURE_K7 ( 3*32+ 5) /* "" Athlon */
+#define X86_FEATURE_P3 ( 3*32+ 6) /* "" P3 */
+#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 */
+#define X86_FEATURE_FXSAVE_LEAK ( 3*32+10) /* "" FXSAVE leaks FOP/FIP/FOP */
+#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 */
+#define X86_FEATURE_SYSCALL32 ( 3*32+14) /* "" syscall in ia32 userspace */
+#define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in ia32 userspace */
+#define X86_FEATURE_REP_GOOD ( 3*32+16) /* rep microcode works well */
+#define X86_FEATURE_MFENCE_RDTSC ( 3*32+17) /* "" Mfence synchronizes RDTSC */
+#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" Lfence synchronizes RDTSC */
+#define X86_FEATURE_11AP ( 3*32+19) /* "" Bad local APIC aka 11AP */
+#define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */
+#define X86_FEATURE_ALWAYS ( 3*32+21) /* "" Always-present feature */
+#define X86_FEATURE_XTOPOLOGY ( 3*32+22) /* cpu topology enum extensions */
+#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */
+#define X86_FEATURE_NONSTOP_TSC ( 3*32+24) /* TSC does not stop in C states */
+#define X86_FEATURE_CLFLUSH_MONITOR ( 3*32+25) /* "" clflush reqd with monitor */
+#define X86_FEATURE_EXTD_APICID ( 3*32+26) /* has extended APICID (8 bits) */
+#define X86_FEATURE_AMD_DCM ( 3*32+27) /* multi-node processor */
+#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 */
/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
-#define X86_FEATURE_XMM3 (4*32+ 0) /* "pni" SSE-3 */
-#define X86_FEATURE_PCLMULQDQ (4*32+ 1) /* PCLMULQDQ instruction */
-#define X86_FEATURE_DTES64 (4*32+ 2) /* 64-bit Debug Store */
-#define X86_FEATURE_MWAIT (4*32+ 3) /* "monitor" Monitor/Mwait support */
-#define X86_FEATURE_DSCPL (4*32+ 4) /* "ds_cpl" CPL Qual. Debug Store */
-#define X86_FEATURE_VMX (4*32+ 5) /* Hardware virtualization */
-#define X86_FEATURE_SMX (4*32+ 6) /* Safer mode */
-#define X86_FEATURE_EST (4*32+ 7) /* Enhanced SpeedStep */
-#define X86_FEATURE_TM2 (4*32+ 8) /* Thermal Monitor 2 */
-#define X86_FEATURE_SSSE3 (4*32+ 9) /* Supplemental SSE-3 */
-#define X86_FEATURE_CID (4*32+10) /* Context ID */
-#define X86_FEATURE_FMA (4*32+12) /* Fused multiply-add */
-#define X86_FEATURE_CX16 (4*32+13) /* CMPXCHG16B */
-#define X86_FEATURE_XTPR (4*32+14) /* Send Task Priority Messages */
-#define X86_FEATURE_PDCM (4*32+15) /* Performance Capabilities */
-#define X86_FEATURE_PCID (4*32+17) /* Process Context Identifiers */
-#define X86_FEATURE_DCA (4*32+18) /* Direct Cache Access */
-#define X86_FEATURE_XMM4_1 (4*32+19) /* "sse4_1" SSE-4.1 */
-#define X86_FEATURE_XMM4_2 (4*32+20) /* "sse4_2" SSE-4.2 */
-#define X86_FEATURE_X2APIC (4*32+21) /* x2APIC */
-#define X86_FEATURE_MOVBE (4*32+22) /* MOVBE instruction */
-#define X86_FEATURE_POPCNT (4*32+23) /* POPCNT instruction */
-#define X86_FEATURE_TSC_DEADLINE_TIMER (4*32+24) /* Tsc deadline timer */
-#define X86_FEATURE_AES (4*32+25) /* AES instructions */
-#define X86_FEATURE_XSAVE (4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */
-#define X86_FEATURE_OSXSAVE (4*32+27) /* "" XSAVE enabled in the OS */
-#define X86_FEATURE_AVX (4*32+28) /* Advanced Vector Extensions */
-#define X86_FEATURE_F16C (4*32+29) /* 16-bit fp conversions */
-#define X86_FEATURE_RDRAND (4*32+30) /* The RDRAND instruction */
-#define X86_FEATURE_HYPERVISOR (4*32+31) /* Running on a hypervisor */
+#define X86_FEATURE_XMM3 ( 4*32+ 0) /* "pni" SSE-3 */
+#define X86_FEATURE_PCLMULQDQ ( 4*32+ 1) /* PCLMULQDQ instruction */
+#define X86_FEATURE_DTES64 ( 4*32+ 2) /* 64-bit Debug Store */
+#define X86_FEATURE_MWAIT ( 4*32+ 3) /* "monitor" Monitor/Mwait support */
+#define X86_FEATURE_DSCPL ( 4*32+ 4) /* "ds_cpl" CPL Qual. Debug Store */
+#define X86_FEATURE_VMX ( 4*32+ 5) /* Hardware virtualization */
+#define X86_FEATURE_SMX ( 4*32+ 6) /* Safer mode */
+#define X86_FEATURE_EST ( 4*32+ 7) /* Enhanced SpeedStep */
+#define X86_FEATURE_TM2 ( 4*32+ 8) /* Thermal Monitor 2 */
+#define X86_FEATURE_SSSE3 ( 4*32+ 9) /* Supplemental SSE-3 */
+#define X86_FEATURE_CID ( 4*32+10) /* Context ID */
+#define X86_FEATURE_FMA ( 4*32+12) /* Fused multiply-add */
+#define X86_FEATURE_CX16 ( 4*32+13) /* CMPXCHG16B */
+#define X86_FEATURE_XTPR ( 4*32+14) /* Send Task Priority Messages */
+#define X86_FEATURE_PDCM ( 4*32+15) /* Performance Capabilities */
+#define X86_FEATURE_PCID ( 4*32+17) /* Process Context Identifiers */
+#define X86_FEATURE_DCA ( 4*32+18) /* Direct Cache Access */
+#define X86_FEATURE_XMM4_1 ( 4*32+19) /* "sse4_1" SSE-4.1 */
+#define X86_FEATURE_XMM4_2 ( 4*32+20) /* "sse4_2" SSE-4.2 */
+#define X86_FEATURE_X2APIC ( 4*32+21) /* x2APIC */
+#define X86_FEATURE_MOVBE ( 4*32+22) /* MOVBE instruction */
+#define X86_FEATURE_POPCNT ( 4*32+23) /* POPCNT instruction */
+#define X86_FEATURE_TSC_DEADLINE_TIMER ( 4*32+24) /* Tsc deadline timer */
+#define X86_FEATURE_AES ( 4*32+25) /* AES instructions */
+#define X86_FEATURE_XSAVE ( 4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */
+#define X86_FEATURE_OSXSAVE ( 4*32+27) /* "" XSAVE enabled in the OS */
+#define X86_FEATURE_AVX ( 4*32+28) /* Advanced Vector Extensions */
+#define X86_FEATURE_F16C ( 4*32+29) /* 16-bit fp conversions */
+#define X86_FEATURE_RDRAND ( 4*32+30) /* The RDRAND instruction */
+#define X86_FEATURE_HYPERVISOR ( 4*32+31) /* Running on a hypervisor */
/* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */
-#define X86_FEATURE_XSTORE (5*32+ 2) /* "rng" RNG present (xstore) */
-#define X86_FEATURE_XSTORE_EN (5*32+ 3) /* "rng_en" RNG enabled */
-#define X86_FEATURE_XCRYPT (5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */
-#define X86_FEATURE_XCRYPT_EN (5*32+ 7) /* "ace_en" on-CPU crypto enabled */
-#define X86_FEATURE_ACE2 (5*32+ 8) /* Advanced Cryptography Engine v2 */
-#define X86_FEATURE_ACE2_EN (5*32+ 9) /* ACE v2 enabled */
-#define X86_FEATURE_PHE (5*32+10) /* PadLock Hash Engine */
-#define X86_FEATURE_PHE_EN (5*32+11) /* PHE enabled */
-#define X86_FEATURE_PMM (5*32+12) /* PadLock Montgomery Multiplier */
-#define X86_FEATURE_PMM_EN (5*32+13) /* PMM enabled */
+#define X86_FEATURE_XSTORE ( 5*32+ 2) /* "rng" RNG present (xstore) */
+#define X86_FEATURE_XSTORE_EN ( 5*32+ 3) /* "rng_en" RNG enabled */
+#define X86_FEATURE_XCRYPT ( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */
+#define X86_FEATURE_XCRYPT_EN ( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */
+#define X86_FEATURE_ACE2 ( 5*32+ 8) /* Advanced Cryptography Engine v2 */
+#define X86_FEATURE_ACE2_EN ( 5*32+ 9) /* ACE v2 enabled */
+#define X86_FEATURE_PHE ( 5*32+10) /* PadLock Hash Engine */
+#define X86_FEATURE_PHE_EN ( 5*32+11) /* PHE enabled */
+#define X86_FEATURE_PMM ( 5*32+12) /* PadLock Montgomery Multiplier */
+#define X86_FEATURE_PMM_EN ( 5*32+13) /* PMM enabled */
/* More extended AMD flags: CPUID level 0x80000001, ecx, word 6 */
-#define X86_FEATURE_LAHF_LM (6*32+ 0) /* LAHF/SAHF in long mode */
-#define X86_FEATURE_CMP_LEGACY (6*32+ 1) /* If yes HyperThreading not valid */
-#define X86_FEATURE_SVM (6*32+ 2) /* Secure virtual machine */
-#define X86_FEATURE_EXTAPIC (6*32+ 3) /* Extended APIC space */
-#define X86_FEATURE_CR8_LEGACY (6*32+ 4) /* CR8 in 32-bit mode */
-#define X86_FEATURE_ABM (6*32+ 5) /* Advanced bit manipulation */
-#define X86_FEATURE_SSE4A (6*32+ 6) /* SSE-4A */
-#define X86_FEATURE_MISALIGNSSE (6*32+ 7) /* Misaligned SSE mode */
-#define X86_FEATURE_3DNOWPREFETCH (6*32+ 8) /* 3DNow prefetch instructions */
-#define X86_FEATURE_OSVW (6*32+ 9) /* OS Visible Workaround */
-#define X86_FEATURE_IBS (6*32+10) /* Instruction Based Sampling */
-#define X86_FEATURE_XOP (6*32+11) /* extended AVX instructions */
-#define X86_FEATURE_SKINIT (6*32+12) /* SKINIT/STGI instructions */
-#define X86_FEATURE_WDT (6*32+13) /* Watchdog timer */
-#define X86_FEATURE_LWP (6*32+15) /* Light Weight Profiling */
-#define X86_FEATURE_FMA4 (6*32+16) /* 4 operands MAC instructions */
-#define X86_FEATURE_TCE (6*32+17) /* translation cache extension */
-#define X86_FEATURE_NODEID_MSR (6*32+19) /* NodeId MSR */
-#define X86_FEATURE_TBM (6*32+21) /* trailing bit manipulations */
-#define X86_FEATURE_TOPOEXT (6*32+22) /* topology extensions CPUID leafs */
-#define X86_FEATURE_PERFCTR_CORE (6*32+23) /* core performance counter extensions */
-#define X86_FEATURE_PERFCTR_NB (6*32+24) /* NB performance counter extensions */
-#define X86_FEATURE_PERFCTR_L2 (6*32+28) /* L2 performance counter extensions */
+#define X86_FEATURE_LAHF_LM ( 6*32+ 0) /* LAHF/SAHF in long mode */
+#define X86_FEATURE_CMP_LEGACY ( 6*32+ 1) /* If yes HyperThreading not valid */
+#define X86_FEATURE_SVM ( 6*32+ 2) /* Secure virtual machine */
+#define X86_FEATURE_EXTAPIC ( 6*32+ 3) /* Extended APIC space */
+#define X86_FEATURE_CR8_LEGACY ( 6*32+ 4) /* CR8 in 32-bit mode */
+#define X86_FEATURE_ABM ( 6*32+ 5) /* Advanced bit manipulation */
+#define X86_FEATURE_SSE4A ( 6*32+ 6) /* SSE-4A */
+#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* Misaligned SSE mode */
+#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* 3DNow prefetch instructions */
+#define X86_FEATURE_OSVW ( 6*32+ 9) /* OS Visible Workaround */
+#define X86_FEATURE_IBS ( 6*32+10) /* Instruction Based Sampling */
+#define X86_FEATURE_XOP ( 6*32+11) /* extended AVX instructions */
+#define X86_FEATURE_SKINIT ( 6*32+12) /* SKINIT/STGI instructions */
+#define X86_FEATURE_WDT ( 6*32+13) /* Watchdog timer */
+#define X86_FEATURE_LWP ( 6*32+15) /* Light Weight Profiling */
+#define X86_FEATURE_FMA4 ( 6*32+16) /* 4 operands MAC instructions */
+#define X86_FEATURE_TCE ( 6*32+17) /* translation cache extension */
+#define X86_FEATURE_NODEID_MSR ( 6*32+19) /* NodeId MSR */
+#define X86_FEATURE_TBM ( 6*32+21) /* trailing bit manipulations */
+#define X86_FEATURE_TOPOEXT ( 6*32+22) /* topology extensions CPUID leafs */
+#define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* core performance counter extensions */
+#define X86_FEATURE_PERFCTR_NB ( 6*32+24) /* NB performance counter extensions */
+#define X86_FEATURE_PERFCTR_L2 ( 6*32+28) /* L2 performance counter extensions */
/*
* Auxiliary flags: Linux defined - For features scattered in various
* CPUID levels like 0x6, 0xA etc, word 7
*/
-#define X86_FEATURE_IDA (7*32+ 0) /* Intel Dynamic Acceleration */
-#define X86_FEATURE_ARAT (7*32+ 1) /* Always Running APIC Timer */
-#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_XSAVEOPT (7*32+ 4) /* Optimized Xsave */
-#define X86_FEATURE_PLN (7*32+ 5) /* Intel Power Limit Notification */
-#define X86_FEATURE_PTS (7*32+ 6) /* Intel Package Thermal Status */
-#define X86_FEATURE_DTHERM (7*32+ 7) /* Digital Thermal Sensor */
-#define X86_FEATURE_HW_PSTATE (7*32+ 8) /* AMD HW-PState */
-#define X86_FEATURE_PROC_FEEDBACK (7*32+ 9) /* AMD ProcFeedbackInterface */
+#define X86_FEATURE_IDA ( 7*32+ 0) /* Intel Dynamic Acceleration */
+#define X86_FEATURE_ARAT ( 7*32+ 1) /* Always Running APIC Timer */
+#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_PLN ( 7*32+ 5) /* Intel Power Limit Notification */
+#define X86_FEATURE_PTS ( 7*32+ 6) /* Intel Package Thermal Status */
+#define X86_FEATURE_DTHERM ( 7*32+ 7) /* Digital Thermal Sensor */
+#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */
+#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
/* 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 */
-#define X86_FEATURE_FLEXPRIORITY (8*32+ 2) /* Intel FlexPriority */
-#define X86_FEATURE_EPT (8*32+ 3) /* Intel Extended Page Table */
-#define X86_FEATURE_VPID (8*32+ 4) /* Intel Virtual Processor ID */
-#define X86_FEATURE_NPT (8*32+ 5) /* AMD Nested Page Table support */
-#define X86_FEATURE_LBRV (8*32+ 6) /* AMD LBR Virtualization support */
-#define X86_FEATURE_SVML (8*32+ 7) /* "svm_lock" AMD SVM locking MSR */
-#define X86_FEATURE_NRIPS (8*32+ 8) /* "nrip_save" AMD SVM next_rip save */
-#define X86_FEATURE_TSCRATEMSR (8*32+ 9) /* "tsc_scale" AMD TSC scaling support */
-#define X86_FEATURE_VMCBCLEAN (8*32+10) /* "vmcb_clean" AMD VMCB clean bits support */
-#define X86_FEATURE_FLUSHBYASID (8*32+11) /* AMD flush-by-ASID support */
-#define X86_FEATURE_DECODEASSISTS (8*32+12) /* AMD Decode Assists support */
-#define X86_FEATURE_PAUSEFILTER (8*32+13) /* AMD filtered pause intercept */
-#define X86_FEATURE_PFTHRESHOLD (8*32+14) /* AMD pause filter threshold */
+#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */
+#define X86_FEATURE_VNMI ( 8*32+ 1) /* Intel Virtual NMI */
+#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */
+#define X86_FEATURE_EPT ( 8*32+ 3) /* Intel Extended Page Table */
+#define X86_FEATURE_VPID ( 8*32+ 4) /* Intel Virtual Processor ID */
+#define X86_FEATURE_NPT ( 8*32+ 5) /* AMD Nested Page Table support */
+#define X86_FEATURE_LBRV ( 8*32+ 6) /* AMD LBR Virtualization support */
+#define X86_FEATURE_SVML ( 8*32+ 7) /* "svm_lock" AMD SVM locking MSR */
+#define X86_FEATURE_NRIPS ( 8*32+ 8) /* "nrip_save" AMD SVM next_rip save */
+#define X86_FEATURE_TSCRATEMSR ( 8*32+ 9) /* "tsc_scale" AMD TSC scaling support */
+#define X86_FEATURE_VMCBCLEAN ( 8*32+10) /* "vmcb_clean" AMD VMCB clean bits support */
+#define X86_FEATURE_FLUSHBYASID ( 8*32+11) /* AMD flush-by-ASID support */
+#define X86_FEATURE_DECODEASSISTS ( 8*32+12) /* AMD Decode Assists support */
+#define X86_FEATURE_PAUSEFILTER ( 8*32+13) /* AMD filtered pause intercept */
+#define X86_FEATURE_PFTHRESHOLD ( 8*32+14) /* AMD pause filter threshold */
/* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
-#define X86_FEATURE_FSGSBASE (9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/
-#define X86_FEATURE_TSC_ADJUST (9*32+ 1) /* TSC adjustment MSR 0x3b */
-#define X86_FEATURE_BMI1 (9*32+ 3) /* 1st group bit manipulation extensions */
-#define X86_FEATURE_HLE (9*32+ 4) /* Hardware Lock Elision */
-#define X86_FEATURE_AVX2 (9*32+ 5) /* AVX2 instructions */
-#define X86_FEATURE_SMEP (9*32+ 7) /* Supervisor Mode Execution Protection */
-#define X86_FEATURE_BMI2 (9*32+ 8) /* 2nd group bit manipulation extensions */
-#define X86_FEATURE_ERMS (9*32+ 9) /* Enhanced REP MOVSB/STOSB */
-#define X86_FEATURE_INVPCID (9*32+10) /* Invalidate Processor Context ID */
-#define X86_FEATURE_RTM (9*32+11) /* Restricted Transactional Memory */
-#define X86_FEATURE_MPX (9*32+14) /* Memory Protection Extension */
-#define X86_FEATURE_AVX512F (9*32+16) /* AVX-512 Foundation */
-#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 */
-#define X86_FEATURE_CLFLUSHOPT (9*32+23) /* CLFLUSHOPT instruction */
-#define X86_FEATURE_AVX512PF (9*32+26) /* AVX-512 Prefetch */
-#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_FSGSBASE ( 9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/
+#define X86_FEATURE_TSC_ADJUST ( 9*32+ 1) /* TSC adjustment MSR 0x3b */
+#define X86_FEATURE_BMI1 ( 9*32+ 3) /* 1st group bit manipulation extensions */
+#define X86_FEATURE_HLE ( 9*32+ 4) /* Hardware Lock Elision */
+#define X86_FEATURE_AVX2 ( 9*32+ 5) /* AVX2 instructions */
+#define X86_FEATURE_SMEP ( 9*32+ 7) /* Supervisor Mode Execution Protection */
+#define X86_FEATURE_BMI2 ( 9*32+ 8) /* 2nd group bit manipulation extensions */
+#define X86_FEATURE_ERMS ( 9*32+ 9) /* Enhanced REP MOVSB/STOSB */
+#define X86_FEATURE_INVPCID ( 9*32+10) /* Invalidate Processor Context ID */
+#define X86_FEATURE_RTM ( 9*32+11) /* Restricted Transactional Memory */
+#define X86_FEATURE_MPX ( 9*32+14) /* Memory Protection Extension */
+#define X86_FEATURE_AVX512F ( 9*32+16) /* AVX-512 Foundation */
+#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 */
+#define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */
+#define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */
+#define X86_FEATURE_AVX512ER ( 9*32+27) /* AVX-512 Exponential and Reciprocal */
+#define X86_FEATURE_AVX512CD ( 9*32+28) /* AVX-512 Conflict Detection */
+
+/* Extended state features, CPUID level 0x0000000d:1 (eax), word 10 */
+#define X86_FEATURE_XSAVEOPT (10*32+ 0) /* XSAVEOPT */
+#define X86_FEATURE_XSAVEC (10*32+ 1) /* XSAVEC */
+#define X86_FEATURE_XGETBV1 (10*32+ 2) /* XGETBV with ECX = 1 */
+#define X86_FEATURE_XSAVES (10*32+ 3) /* XSAVES/XRSTORS */
/*
* BUG word(s)
@@ -328,6 +333,7 @@ extern const char * const x86_power_flags[32];
#define cpu_has_x2apic boot_cpu_has(X86_FEATURE_X2APIC)
#define cpu_has_xsave boot_cpu_has(X86_FEATURE_XSAVE)
#define cpu_has_xsaveopt boot_cpu_has(X86_FEATURE_XSAVEOPT)
+#define cpu_has_xsaves boot_cpu_has(X86_FEATURE_XSAVES)
#define cpu_has_osxsave boot_cpu_has(X86_FEATURE_OSXSAVE)
#define cpu_has_hypervisor boot_cpu_has(X86_FEATURE_HYPERVISOR)
#define cpu_has_pclmulqdq boot_cpu_has(X86_FEATURE_PCLMULQDQ)
diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
index cea1c76..6099c0e 100644
--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -508,9 +508,12 @@ static inline void user_fpu_begin(void)
static inline void __save_fpu(struct task_struct *tsk)
{
- if (use_xsave())
- xsave_state(&tsk->thread.fpu.state->xsave, -1);
- else
+ if (use_xsave()) {
+ if (unlikely(system_state == SYSTEM_BOOTING))
+ xsave_state_booting(&tsk->thread.fpu.state->xsave, -1);
+ else
+ xsave_state(&tsk->thread.fpu.state->xsave, -1);
+ } else
fpu_fxsave(&tsk->thread.fpu);
}
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index a4ea023..2c8d3b8 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -386,8 +386,8 @@ struct bndcsr_struct {
struct xsave_hdr_struct {
u64 xstate_bv;
- u64 reserved1[2];
- u64 reserved2[5];
+ u64 xcomp_bv;
+ u64 reserved[6];
} __attribute__((packed));
struct xsave_struct {
diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h
index d949ef2..7e7a79a 100644
--- a/arch/x86/include/asm/xsave.h
+++ b/arch/x86/include/asm/xsave.h
@@ -52,24 +52,170 @@ extern void xsave_init(void);
extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask);
extern int init_fpu(struct task_struct *child);
-static inline int fpu_xrstor_checking(struct xsave_struct *fx)
+/* These macros all use (%edi)/(%rdi) as the single memory argument. */
+#define XSAVE ".byte " REX_PREFIX "0x0f,0xae,0x27"
+#define XSAVEOPT ".byte " REX_PREFIX "0x0f,0xae,0x37"
+#define XSAVES ".byte " REX_PREFIX "0x0f,0xc7,0x2f"
+#define XRSTOR ".byte " REX_PREFIX "0x0f,0xae,0x2f"
+#define XRSTORS ".byte " REX_PREFIX "0x0f,0xc7,0x1f"
+
+#define xstate_fault ".section .fixup,\"ax\"\n" \
+ "3: movl $-1,%[err]\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ _ASM_EXTABLE(1b, 3b) \
+ : [err] "=r" (err)
+
+/*
+ * This function is called only during boot time when x86 caps are not set
+ * up and alternative can not be used yet.
+ */
+static inline int xsave_state_booting(struct xsave_struct *fx, u64 mask)
{
- int err;
+ u32 lmask = mask;
+ u32 hmask = mask >> 32;
+ int err = 0;
+
+ WARN_ON(system_state != SYSTEM_BOOTING);
+
+ if (boot_cpu_has(X86_FEATURE_XSAVES))
+ asm volatile("1:"XSAVES"\n\t"
+ "2:\n\t"
+ : : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+ : "memory");
+ else
+ asm volatile("1:"XSAVE"\n\t"
+ "2:\n\t"
+ : : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+ : "memory");
+
+ asm volatile(xstate_fault
+ : "0" (0)
+ : "memory");
+
+ return err;
+}
+
+/*
+ * This function is called only during boot time when x86 caps are not set
+ * up and alternative can not be used yet.
+ */
+static inline int xrstor_state_booting(struct xsave_struct *fx, u64 mask)
+{
+ u32 lmask = mask;
+ u32 hmask = mask >> 32;
+ int err = 0;
+
+ WARN_ON(system_state != SYSTEM_BOOTING);
- asm volatile("1: .byte " REX_PREFIX "0x0f,0xae,0x2f\n\t"
- "2:\n"
- ".section .fixup,\"ax\"\n"
- "3: movl $-1,%[err]\n"
- " jmp 2b\n"
- ".previous\n"
- _ASM_EXTABLE(1b, 3b)
- : [err] "=r" (err)
- : "D" (fx), "m" (*fx), "a" (-1), "d" (-1), "0" (0)
+ if (boot_cpu_has(X86_FEATURE_XSAVES))
+ asm volatile("1:"XRSTORS"\n\t"
+ "2:\n\t"
+ : : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+ : "memory");
+ else
+ asm volatile("1:"XRSTOR"\n\t"
+ "2:\n\t"
+ : : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+ : "memory");
+
+ asm volatile(xstate_fault
+ : "0" (0)
+ : "memory");
+
+ return err;
+}
+
+/*
+ * Save processor xstate to xsave area.
+ */
+static inline int xsave_state(struct xsave_struct *fx, u64 mask)
+{
+ u32 lmask = mask;
+ u32 hmask = mask >> 32;
+ int err = 0;
+
+ /*
+ * If xsaves is enabled, xsaves replaces xsaveopt because
+ * it supports compact format and supervisor states in addition to
+ * modified optimization in xsaveopt.
+ *
+ * Otherwise, if xsaveopt is enabled, xsaveopt replaces xsave
+ * because xsaveopt supports modified optimization which is not
+ * supported by xsave.
+ *
+ * If none of xsaves and xsaveopt is enabled, use xsave.
+ */
+ alternative_input_2(
+ "1:"XSAVE,
+ "1:"XSAVEOPT,
+ X86_FEATURE_XSAVEOPT,
+ "1:"XSAVES,
+ X86_FEATURE_XSAVES,
+ [fx] "D" (fx), "a" (lmask), "d" (hmask) :
+ "memory");
+ asm volatile("2:\n\t"
+ xstate_fault
+ : "0" (0)
: "memory");
return err;
}
+/*
+ * Restore processor xstate from xsave area.
+ */
+static inline int xrstor_state(struct xsave_struct *fx, u64 mask)
+{
+ int err = 0;
+ u32 lmask = mask;
+ u32 hmask = mask >> 32;
+
+ /*
+ * Use xrstors to restore context if it is enabled. xrstors supports
+ * compacted format of xsave area which is not supported by xrstor.
+ */
+ alternative_input(
+ "1: " XRSTOR,
+ "1: " XRSTORS,
+ X86_FEATURE_XSAVES,
+ "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+ : "memory");
+
+ asm volatile("2:\n"
+ xstate_fault
+ : "0" (0)
+ : "memory");
+
+ return err;
+}
+
+/*
+ * Save xstate context for old process during context switch.
+ */
+static inline void fpu_xsave(struct fpu *fpu)
+{
+ xsave_state(&fpu->state->xsave, -1);
+}
+
+/*
+ * Restore xstate context for new process during context switch.
+ */
+static inline int fpu_xrstor_checking(struct xsave_struct *fx)
+{
+ return xrstor_state(fx, -1);
+}
+
+/*
+ * Save xstate to user space xsave area.
+ *
+ * We don't use modified optimization because xrstor/xrstors might track
+ * a different application.
+ *
+ * We don't use compacted format xsave area for
+ * backward compatibility for old applications which don't understand
+ * compacted format of xsave area.
+ */
static inline int xsave_user(struct xsave_struct __user *buf)
{
int err;
@@ -83,69 +229,34 @@ static inline int xsave_user(struct xsave_struct __user *buf)
return -EFAULT;
__asm__ __volatile__(ASM_STAC "\n"
- "1: .byte " REX_PREFIX "0x0f,0xae,0x27\n"
+ "1:"XSAVE"\n"
"2: " ASM_CLAC "\n"
- ".section .fixup,\"ax\"\n"
- "3: movl $-1,%[err]\n"
- " jmp 2b\n"
- ".previous\n"
- _ASM_EXTABLE(1b,3b)
- : [err] "=r" (err)
+ xstate_fault
: "D" (buf), "a" (-1), "d" (-1), "0" (0)
: "memory");
return err;
}
+/*
+ * Restore xstate from user space xsave area.
+ */
static inline int xrestore_user(struct xsave_struct __user *buf, u64 mask)
{
- int err;
+ int err = 0;
struct xsave_struct *xstate = ((__force struct xsave_struct *)buf);
u32 lmask = mask;
u32 hmask = mask >> 32;
__asm__ __volatile__(ASM_STAC "\n"
- "1: .byte " REX_PREFIX "0x0f,0xae,0x2f\n"
+ "1:"XRSTOR"\n"
"2: " ASM_CLAC "\n"
- ".section .fixup,\"ax\"\n"
- "3: movl $-1,%[err]\n"
- " jmp 2b\n"
- ".previous\n"
- _ASM_EXTABLE(1b,3b)
- : [err] "=r" (err)
+ xstate_fault
: "D" (xstate), "a" (lmask), "d" (hmask), "0" (0)
: "memory"); /* memory required? */
return err;
}
-static inline void xrstor_state(struct xsave_struct *fx, u64 mask)
-{
- u32 lmask = mask;
- u32 hmask = mask >> 32;
-
- asm volatile(".byte " REX_PREFIX "0x0f,0xae,0x2f\n\t"
- : : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
- : "memory");
-}
-
-static inline void xsave_state(struct xsave_struct *fx, u64 mask)
-{
- u32 lmask = mask;
- u32 hmask = mask >> 32;
+void *get_xsave_addr(struct xsave_struct *xsave, int xstate);
+void setup_xstate_comp(void);
- asm volatile(".byte " REX_PREFIX "0x0f,0xae,0x27\n\t"
- : : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
- : "memory");
-}
-
-static inline void fpu_xsave(struct fpu *fpu)
-{
- /* This, however, we can work around by forcing the compiler to select
- an addressing mode that doesn't require extended registers. */
- alternative_input(
- ".byte " REX_PREFIX "0x0f,0xae,0x27",
- ".byte " REX_PREFIX "0x0f,0xae,0x37",
- X86_FEATURE_XSAVEOPT,
- [fx] "D" (&fpu->state->xsave), "a" (-1), "d" (-1) :
- "memory");
-}
#endif
diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h
index fcf2b3a..5cd1569 100644
--- a/arch/x86/include/uapi/asm/msr-index.h
+++ b/arch/x86/include/uapi/asm/msr-index.h
@@ -297,6 +297,8 @@
#define MSR_IA32_TSC_ADJUST 0x0000003b
#define MSR_IA32_BNDCFGS 0x00000d90
+#define MSR_IA32_XSS 0x00000da0
+
#define FEATURE_CONTROL_LOCKED (1<<0)
#define FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX (1<<1)
#define FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX (1<<2)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index a135239..cdc9585 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -146,6 +146,7 @@ static int __init x86_xsave_setup(char *s)
{
setup_clear_cpu_cap(X86_FEATURE_XSAVE);
setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
+ setup_clear_cpu_cap(X86_FEATURE_XSAVES);
setup_clear_cpu_cap(X86_FEATURE_AVX);
setup_clear_cpu_cap(X86_FEATURE_AVX2);
return 1;
@@ -159,6 +160,13 @@ static int __init x86_xsaveopt_setup(char *s)
}
__setup("noxsaveopt", x86_xsaveopt_setup);
+static int __init x86_xsaves_setup(char *s)
+{
+ setup_clear_cpu_cap(X86_FEATURE_XSAVES);
+ return 1;
+}
+__setup("noxsaves", x86_xsaves_setup);
+
#ifdef CONFIG_X86_32
static int cachesize_override = -1;
static int disable_x86_serial_nr = 1;
@@ -632,6 +640,15 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
c->x86_capability[9] = ebx;
}
+ /* Extended state features: level 0x0000000d */
+ if (c->cpuid_level >= 0x0000000d) {
+ u32 eax, ebx, ecx, edx;
+
+ cpuid_count(0x0000000d, 1, &eax, &ebx, &ecx, &edx);
+
+ c->x86_capability[10] = eax;
+ }
+
/* AMD-defined flags: level 0x80000001 */
xlvl = cpuid_eax(0x80000000);
c->extended_cpuid_level = xlvl;
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index b6f794a..4a8013d 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -38,7 +38,6 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c)
{ X86_FEATURE_PTS, CR_EAX, 6, 0x00000006, 0 },
{ X86_FEATURE_APERFMPERF, CR_ECX, 0, 0x00000006, 0 },
{ X86_FEATURE_EPB, CR_ECX, 3, 0x00000006, 0 },
- { X86_FEATURE_XSAVEOPT, CR_EAX, 0, 0x0000000d, 1 },
{ X86_FEATURE_HW_PSTATE, CR_EDX, 7, 0x80000007, 0 },
{ X86_FEATURE_CPB, CR_EDX, 9, 0x80000007, 0 },
{ X86_FEATURE_PROC_FEEDBACK, CR_EDX,11, 0x80000007, 0 },
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index d5dd808..a9a4229 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -375,7 +375,7 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
/*
* These bits must be zero.
*/
- xsave_hdr->reserved1[0] = xsave_hdr->reserved1[1] = 0;
+ memset(xsave_hdr->reserved, 0, 48);
return ret;
}
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 4505e2a..f804dc9 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -93,6 +93,7 @@ void arch_task_cache_init(void)
kmem_cache_create("task_xstate", xstate_size,
__alignof__(union thread_xstate),
SLAB_PANIC | SLAB_NOTRACK, NULL);
+ setup_xstate_comp();
}
/*
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index a4b451c..940b142 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -8,6 +8,7 @@
#include <linux/bootmem.h>
#include <linux/compat.h>
+#include <linux/cpu.h>
#include <asm/i387.h>
#include <asm/fpu-internal.h>
#include <asm/sigframe.h>
@@ -24,7 +25,9 @@ u64 pcntxt_mask;
struct xsave_struct *init_xstate_buf;
static struct _fpx_sw_bytes fx_sw_reserved, fx_sw_reserved_ia32;
-static unsigned int *xstate_offsets, *xstate_sizes, xstate_features;
+static unsigned int *xstate_offsets, *xstate_sizes;
+static unsigned int xstate_comp_offsets[sizeof(pcntxt_mask)*8];
+static unsigned int xstate_features;
/*
* If a processor implementation discern that a processor state component is
@@ -283,7 +286,7 @@ sanitize_restored_xstate(struct task_struct *tsk,
if (use_xsave()) {
/* These bits must be zero. */
- xsave_hdr->reserved1[0] = xsave_hdr->reserved1[1] = 0;
+ memset(xsave_hdr->reserved, 0, 48);
/*
* Init the state that is not present in the memory
@@ -479,6 +482,52 @@ static void __init setup_xstate_features(void)
}
/*
+ * This function sets up offsets and sizes of all extended states in
+ * xsave area. This supports both standard format and compacted format
+ * of the xsave aread.
+ *
+ * Input: void
+ * Output: void
+ */
+void setup_xstate_comp(void)
+{
+ unsigned int xstate_comp_sizes[sizeof(pcntxt_mask)*8];
+ int i;
+
+ /*
+ * The FP xstates and SSE xstates are legacy states. They are always
+ * in the fixed offsets in the xsave area in either compacted form
+ * or standard form.
+ */
+ xstate_comp_offsets[0] = 0;
+ xstate_comp_offsets[1] = offsetof(struct i387_fxsave_struct, xmm_space);
+
+ if (!cpu_has_xsaves) {
+ for (i = 2; i < xstate_features; i++) {
+ if (test_bit(i, (unsigned long *)&pcntxt_mask)) {
+ xstate_comp_offsets[i] = xstate_offsets[i];
+ xstate_comp_sizes[i] = xstate_sizes[i];
+ }
+ }
+ return;
+ }
+
+ xstate_comp_offsets[2] = FXSAVE_SIZE + XSAVE_HDR_SIZE;
+
+ for (i = 2; i < xstate_features; i++) {
+ if (test_bit(i, (unsigned long *)&pcntxt_mask))
+ xstate_comp_sizes[i] = xstate_sizes[i];
+ else
+ xstate_comp_sizes[i] = 0;
+
+ if (i > 2)
+ xstate_comp_offsets[i] = xstate_comp_offsets[i-1]
+ + xstate_comp_sizes[i-1];
+
+ }
+}
+
+/*
* setup the xstate image representing the init state
*/
static void __init setup_init_fpu_buf(void)
@@ -496,15 +545,21 @@ static void __init setup_init_fpu_buf(void)
setup_xstate_features();
+ if (cpu_has_xsaves) {
+ init_xstate_buf->xsave_hdr.xcomp_bv =
+ (u64)1 << 63 | pcntxt_mask;
+ init_xstate_buf->xsave_hdr.xstate_bv = pcntxt_mask;
+ }
+
/*
* Init all the features state with header_bv being 0x0
*/
- xrstor_state(init_xstate_buf, -1);
+ xrstor_state_booting(init_xstate_buf, -1);
/*
* Dump the init state again. This is to identify the init state
* of any feature which is not represented by all zero's.
*/
- xsave_state(init_xstate_buf, -1);
+ xsave_state_booting(init_xstate_buf, -1);
}
static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO;
@@ -520,6 +575,30 @@ static int __init eager_fpu_setup(char *s)
}
__setup("eagerfpu=", eager_fpu_setup);
+
+/*
+ * Calculate total size of enabled xstates in XCR0/pcntxt_mask.
+ */
+static void __init init_xstate_size(void)
+{
+ unsigned int eax, ebx, ecx, edx;
+ int i;
+
+ if (!cpu_has_xsaves) {
+ cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
+ xstate_size = ebx;
+ return;
+ }
+
+ xstate_size = FXSAVE_SIZE + XSAVE_HDR_SIZE;
+ for (i = 2; i < 64; i++) {
+ if (test_bit(i, (unsigned long *)&pcntxt_mask)) {
+ cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx);
+ xstate_size += eax;
+ }
+ }
+}
+
/*
* Enable and initialize the xsave feature.
*/
@@ -551,8 +630,7 @@ static void __init xstate_enable_boot_cpu(void)
/*
* Recompute the context size for enabled features
*/
- cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
- xstate_size = ebx;
+ init_xstate_size();
update_regset_xstate_info(xstate_size, pcntxt_mask);
prepare_fx_sw_frame();
@@ -572,8 +650,9 @@ static void __init xstate_enable_boot_cpu(void)
}
}
- pr_info("enabled xstate_bv 0x%llx, cntxt size 0x%x\n",
- pcntxt_mask, xstate_size);
+ pr_info("enabled xstate_bv 0x%llx, cntxt size 0x%x using %s\n",
+ pcntxt_mask, xstate_size,
+ cpu_has_xsaves ? "compacted form" : "standard form");
}
/*
@@ -635,3 +714,26 @@ void eager_fpu_init(void)
else
fxrstor_checking(&init_xstate_buf->i387);
}
+
+/*
+ * Given the xsave area and a state inside, this function returns the
+ * address of the state.
+ *
+ * This is the API that is called to get xstate address in either
+ * standard format or compacted format of xsave area.
+ *
+ * Inputs:
+ * xsave: base address of the xsave area;
+ * xstate: state which is defined in xsave.h (e.g. XSTATE_FP, XSTATE_SSE,
+ * etc.)
+ * Output:
+ * address of the state in the xsave area.
+ */
+void *get_xsave_addr(struct xsave_struct *xsave, int xstate)
+{
+ int feature = fls64(xstate) - 1;
+ if (!test_bit(feature, (unsigned long *)&pcntxt_mask))
+ return NULL;
+
+ return (void *)xsave + xstate_comp_offsets[feature];
+}
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/