From 3c52b5c64326d9dcfee4e10611c53ec1b1b20675 Mon Sep 17 00:00:00 2001 From: Uros Bizjak Date: Wed, 6 Sep 2017 17:18:08 +0200 Subject: x86/asm: Remove unnecessary \n\t in front of CC_SET() from asm templates There is no need for \n\t in front of CC_SET(), as the macro already includes these two. Signed-off-by: Uros Bizjak Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20170906151808.5634-1-ubizjak@gmail.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/archrandom.h | 8 ++++---- arch/x86/include/asm/bitops.h | 10 +++++----- arch/x86/include/asm/percpu.h | 2 +- arch/x86/include/asm/rmwcc.h | 2 +- 4 files changed, 11 insertions(+), 11 deletions(-) diff --git a/arch/x86/include/asm/archrandom.h b/arch/x86/include/asm/archrandom.h index 5b0579abb398..3ac991d81e74 100644 --- a/arch/x86/include/asm/archrandom.h +++ b/arch/x86/include/asm/archrandom.h @@ -45,7 +45,7 @@ static inline bool rdrand_long(unsigned long *v) bool ok; unsigned int retry = RDRAND_RETRY_LOOPS; do { - asm volatile(RDRAND_LONG "\n\t" + asm volatile(RDRAND_LONG CC_SET(c) : CC_OUT(c) (ok), "=a" (*v)); if (ok) @@ -59,7 +59,7 @@ static inline bool rdrand_int(unsigned int *v) bool ok; unsigned int retry = RDRAND_RETRY_LOOPS; do { - asm volatile(RDRAND_INT "\n\t" + asm volatile(RDRAND_INT CC_SET(c) : CC_OUT(c) (ok), "=a" (*v)); if (ok) @@ -71,7 +71,7 @@ static inline bool rdrand_int(unsigned int *v) static inline bool rdseed_long(unsigned long *v) { bool ok; - asm volatile(RDSEED_LONG "\n\t" + asm volatile(RDSEED_LONG CC_SET(c) : CC_OUT(c) (ok), "=a" (*v)); return ok; @@ -80,7 +80,7 @@ static inline bool rdseed_long(unsigned long *v) static inline bool rdseed_int(unsigned int *v) { bool ok; - asm volatile(RDSEED_INT "\n\t" + asm volatile(RDSEED_INT CC_SET(c) : CC_OUT(c) (ok), "=a" (*v)); return ok; diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 854022772c5b..8cee8db6dffb 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -142,7 +142,7 @@ static __always_inline void __clear_bit(long nr, volatile unsigned long *addr) static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr) { bool negative; - asm volatile(LOCK_PREFIX "andb %2,%1\n\t" + asm volatile(LOCK_PREFIX "andb %2,%1" CC_SET(s) : CC_OUT(s) (negative), ADDR : "ir" ((char) ~(1 << nr)) : "memory"); @@ -245,7 +245,7 @@ static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long * { bool oldbit; - asm("bts %2,%1\n\t" + asm("bts %2,%1" CC_SET(c) : CC_OUT(c) (oldbit), ADDR : "Ir" (nr)); @@ -285,7 +285,7 @@ static __always_inline bool __test_and_clear_bit(long nr, volatile unsigned long { bool oldbit; - asm volatile("btr %2,%1\n\t" + asm volatile("btr %2,%1" CC_SET(c) : CC_OUT(c) (oldbit), ADDR : "Ir" (nr)); @@ -297,7 +297,7 @@ static __always_inline bool __test_and_change_bit(long nr, volatile unsigned lon { bool oldbit; - asm volatile("btc %2,%1\n\t" + asm volatile("btc %2,%1" CC_SET(c) : CC_OUT(c) (oldbit), ADDR : "Ir" (nr) : "memory"); @@ -328,7 +328,7 @@ static __always_inline bool variable_test_bit(long nr, volatile const unsigned l { bool oldbit; - asm volatile("bt %2,%1\n\t" + asm volatile("bt %2,%1" CC_SET(c) : CC_OUT(c) (oldbit) : "m" (*(unsigned long *)addr), "Ir" (nr)); diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index 9fa03604b2b3..b21a475fd7ed 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -525,7 +525,7 @@ static inline bool x86_this_cpu_variable_test_bit(int nr, { bool oldbit; - asm volatile("bt "__percpu_arg(2)",%1\n\t" + asm volatile("bt "__percpu_arg(2)",%1" CC_SET(c) : CC_OUT(c) (oldbit) : "m" (*(unsigned long __percpu *)addr), "Ir" (nr)); diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h index 045f99211a99..0c411c8bbdbd 100644 --- a/arch/x86/include/asm/rmwcc.h +++ b/arch/x86/include/asm/rmwcc.h @@ -28,7 +28,7 @@ cc_label: \ #define __GEN_RMWcc(fullop, var, cc, clobbers, ...) \ do { \ bool c; \ - asm volatile (fullop ";" CC_SET(cc) \ + asm volatile (fullop CC_SET(cc) \ : [counter] "+m" (var), CC_OUT(cc) (c) \ : __VA_ARGS__ : clobbers); \ return c; \ -- cgit v1.2.3 From 00d96180dc38ef872ac471c2d3e14b067cbd895d Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 18 Sep 2017 21:43:30 -0500 Subject: objtool: Don't report end of section error after an empty unwind hint If asm code specifies an UNWIND_HINT_EMPTY hint, don't warn if the section ends unexpectedly. This can happen with the xen-head.S code because the hypercall_page is "text" but it's all zeros. Signed-off-by: Josh Poimboeuf Cc: Andy Lutomirski Cc: Boris Ostrovsky Cc: Jiri Slaby Cc: Juergen Gross Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/ddafe199dd8797e40e3c2777373347eba1d65572.1505764066.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- tools/objtool/check.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index a0c518ecf085..83f370fa00c2 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -1752,11 +1752,14 @@ static int validate_branch(struct objtool_file *file, struct instruction *first, if (insn->dead_end) return 0; - insn = next_insn; - if (!insn) { + if (!next_insn) { + if (state.cfa.base == CFI_UNDEFINED) + return 0; WARN("%s: unexpected end of section", sec->name); return 1; } + + insn = next_insn; } return 0; -- cgit v1.2.3 From 17270717e80de33a884ad328fea5f407d87f6d6a Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 18 Sep 2017 21:43:31 -0500 Subject: x86/head: Remove confusing comment This comment is actively wrong and confusing. It refers to the registers' stack offsets after the pt_regs has been constructed on the stack, but this code is *before* that. At this point the stack just has the standard iret frame, for which no comment should be needed. Signed-off-by: Josh Poimboeuf Cc: Andy Lutomirski Cc: Boris Ostrovsky Cc: Jiri Slaby Cc: Juergen Gross Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/a3c267b770fc56c9b86df9c11c552848248aace2.1505764066.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/head_64.S | 4 ---- 1 file changed, 4 deletions(-) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 513cbb012ecc..3b04e4c99389 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -270,10 +270,6 @@ bad_address: __INIT ENTRY(early_idt_handler_array) - # 104(%rsp) %rflags - # 96(%rsp) %cs - # 88(%rsp) %rip - # 80(%rsp) error code i = 0 .rept NUM_EXCEPTION_VECTORS .ifeq (EXCEPTION_ERRCODE_MASK >> i) & 1 -- cgit v1.2.3 From a8b88e84d124bc92c4808e72b8b8c0e0bb538630 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 18 Sep 2017 21:43:32 -0500 Subject: x86/head: Remove unused 'bad_address' code It's no longer possible for this code to be executed, so remove it. Signed-off-by: Josh Poimboeuf Cc: Andy Lutomirski Cc: Boris Ostrovsky Cc: Jiri Slaby Cc: Juergen Gross Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/32a46fe92d2083700599b36872b26e7dfd7b7965.1505764066.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/head_64.S | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 3b04e4c99389..afb0a1e22d41 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -265,9 +265,6 @@ ENDPROC(start_cpu0) .quad init_thread_union + THREAD_SIZE - SIZEOF_PTREGS __FINITDATA -bad_address: - jmp bad_address - __INIT ENTRY(early_idt_handler_array) i = 0 -- cgit v1.2.3 From 015a2ea5478680fc5216d56b7ff306f2a74efaf9 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 18 Sep 2017 21:43:33 -0500 Subject: x86/head: Fix head ELF function annotations These functions aren't callable C-type functions, so don't annotate them as such. Signed-off-by: Josh Poimboeuf Cc: Andy Lutomirski Cc: Boris Ostrovsky Cc: Jiri Slaby Cc: Juergen Gross Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/36eb182738c28514f8bf95e403d89b6413a88883.1505764066.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/head_64.S | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index afb0a1e22d41..edacd579d504 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -234,7 +234,7 @@ ENTRY(secondary_startup_64) pushq %rax # target address in negative space lretq .Lafter_lret: -ENDPROC(secondary_startup_64) +END(secondary_startup_64) #include "verify_cpu.S" @@ -277,7 +277,7 @@ ENTRY(early_idt_handler_array) i = i + 1 .fill early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc .endr -ENDPROC(early_idt_handler_array) +END(early_idt_handler_array) early_idt_handler_common: /* @@ -320,7 +320,7 @@ early_idt_handler_common: 20: decl early_recursion_flag(%rip) jmp restore_regs_and_iret -ENDPROC(early_idt_handler_common) +END(early_idt_handler_common) __INITDATA -- cgit v1.2.3 From e93db75a0054b23a874a12c63376753544f3fe9e Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 18 Sep 2017 21:43:34 -0500 Subject: x86/boot: Annotate verify_cpu() as a callable function verify_cpu() is a callable function. Annotate it as such. Signed-off-by: Josh Poimboeuf Cc: Andy Lutomirski Cc: Boris Ostrovsky Cc: Jiri Slaby Cc: Juergen Gross Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/293024b8a080832075312f38c07ccc970fc70292.1505764066.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/verify_cpu.S | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/verify_cpu.S b/arch/x86/kernel/verify_cpu.S index 014ea59aa153..3d3c2f71f617 100644 --- a/arch/x86/kernel/verify_cpu.S +++ b/arch/x86/kernel/verify_cpu.S @@ -33,7 +33,7 @@ #include #include -verify_cpu: +ENTRY(verify_cpu) pushf # Save caller passed flags push $0 # Kill any dangerous flags popf @@ -139,3 +139,4 @@ verify_cpu: popf # Restore caller passed flags xorl %eax, %eax ret +ENDPROC(verify_cpu) -- cgit v1.2.3 From 2582d3df95c76d3b686453baf90b64d57e87d1e8 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 18 Sep 2017 21:43:35 -0500 Subject: x86/xen: Fix xen head ELF annotations Mark the ends of the startup_xen and hypercall_page code sections. Signed-off-by: Josh Poimboeuf Cc: Andy Lutomirski Cc: Boris Ostrovsky Cc: Jiri Slaby Cc: Juergen Gross Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/3a80a394d30af43d9cefa1a29628c45ed8420c97.1505764066.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/xen/xen-head.S | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index a7525e95d53f..9753225289e8 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -33,7 +33,7 @@ ENTRY(startup_xen) mov $init_thread_union+THREAD_SIZE, %_ASM_SP jmp xen_start_kernel - +END(startup_xen) __FINIT #endif @@ -47,7 +47,7 @@ ENTRY(hypercall_page) .type xen_hypercall_##n, @function; .size xen_hypercall_##n, 32 #include #undef HYPERCALL - +END(hypercall_page) .popsection ELFNOTE(Xen, XEN_ELFNOTE_GUEST_OS, .asciz "linux") -- cgit v1.2.3 From abbe1cac6214d81d2f4e149aba64a8760703144e Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 18 Sep 2017 21:43:36 -0500 Subject: x86/xen: Add unwind hint annotations Add unwind hint annotations to the xen head code so the ORC unwinder can read head_64.o. hypercall_page needs empty annotations at 32-byte intervals to match the 'xen_hypercall_*' ELF functions at those locations. Signed-off-by: Josh Poimboeuf Cc: Andy Lutomirski Cc: Boris Ostrovsky Cc: Jiri Slaby Cc: Juergen Gross Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/70ed2eb516fe9266be766d953f93c2571bca88cc.1505764066.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/xen/xen-head.S | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index 9753225289e8..124941d09b2b 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -9,6 +9,7 @@ #include #include #include +#include #include #include @@ -19,6 +20,7 @@ #ifdef CONFIG_XEN_PV __INIT ENTRY(startup_xen) + UNWIND_HINT_EMPTY cld /* Clear .bss */ @@ -40,7 +42,10 @@ END(startup_xen) .pushsection .text .balign PAGE_SIZE ENTRY(hypercall_page) - .skip PAGE_SIZE + .rept (PAGE_SIZE / 32) + UNWIND_HINT_EMPTY + .skip 32 + .endr #define HYPERCALL(n) \ .equ xen_hypercall_##n, hypercall_page + __HYPERVISOR_##n * 32; \ -- cgit v1.2.3 From 2704fbb672d0d9a19414907fda7949283dcef6a1 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 18 Sep 2017 21:43:37 -0500 Subject: x86/head: Add unwind hint annotations Jiri Slaby reported an ORC issue when unwinding from an idle task. The stack was: ffffffff811083c2 do_idle+0x142/0x1e0 ffffffff8110861d cpu_startup_entry+0x5d/0x60 ffffffff82715f58 start_kernel+0x3ff/0x407 ffffffff827153e8 x86_64_start_kernel+0x14e/0x15d ffffffff810001bf secondary_startup_64+0x9f/0xa0 The ORC unwinder errored out at secondary_startup_64 because the head code isn't annotated yet so there wasn't a corresponding ORC entry. Fix that and any other head-related unwinding issues by adding unwind hints to the head code. Reported-by: Jiri Slaby Tested-by: Jiri Slaby Signed-off-by: Josh Poimboeuf Cc: Andy Lutomirski Cc: Boris Ostrovsky Cc: Juergen Gross Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/78ef000a2f68f545d6eef44ee912edceaad82ccf.1505764066.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/Makefile | 1 - arch/x86/kernel/head_64.S | 14 ++++++++++++-- 2 files changed, 12 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index fd0a7895b63f..d8e2b700d1db 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -26,7 +26,6 @@ KASAN_SANITIZE_dumpstack.o := n KASAN_SANITIZE_dumpstack_$(BITS).o := n KASAN_SANITIZE_stacktrace.o := n -OBJECT_FILES_NON_STANDARD_head_$(BITS).o := y OBJECT_FILES_NON_STANDARD_relocate_kernel_$(BITS).o := y OBJECT_FILES_NON_STANDARD_ftrace_$(BITS).o := y OBJECT_FILES_NON_STANDARD_test_nx.o := y diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index edacd579d504..42e32c2e51bb 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -49,6 +49,7 @@ L3_START_KERNEL = pud_index(__START_KERNEL_map) .code64 .globl startup_64 startup_64: + UNWIND_HINT_EMPTY /* * At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 0, * and someone has loaded an identity mapped page table @@ -88,6 +89,7 @@ startup_64: addq $(early_top_pgt - __START_KERNEL_map), %rax jmp 1f ENTRY(secondary_startup_64) + UNWIND_HINT_EMPTY /* * At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 0, * and someone has loaded a mapped page table. @@ -132,6 +134,7 @@ ENTRY(secondary_startup_64) movq $1f, %rax jmp *%rax 1: + UNWIND_HINT_EMPTY /* Check if nx is implemented */ movl $0x80000001, %eax @@ -246,6 +249,7 @@ END(secondary_startup_64) */ ENTRY(start_cpu0) movq initial_stack(%rip), %rsp + UNWIND_HINT_EMPTY jmp .Ljump_to_C_code ENDPROC(start_cpu0) #endif @@ -270,13 +274,18 @@ ENTRY(early_idt_handler_array) i = 0 .rept NUM_EXCEPTION_VECTORS .ifeq (EXCEPTION_ERRCODE_MASK >> i) & 1 - pushq $0 # Dummy error code, to make stack frame uniform + UNWIND_HINT_IRET_REGS + pushq $0 # Dummy error code, to make stack frame uniform + .else + UNWIND_HINT_IRET_REGS offset=8 .endif pushq $i # 72(%rsp) Vector number jmp early_idt_handler_common + UNWIND_HINT_IRET_REGS i = i + 1 .fill early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc .endr + UNWIND_HINT_IRET_REGS offset=16 END(early_idt_handler_array) early_idt_handler_common: @@ -305,6 +314,7 @@ early_idt_handler_common: pushq %r13 /* pt_regs->r13 */ pushq %r14 /* pt_regs->r14 */ pushq %r15 /* pt_regs->r15 */ + UNWIND_HINT_REGS cmpq $14,%rsi /* Page fault? */ jnz 10f @@ -427,7 +437,7 @@ ENTRY(phys_base) EXPORT_SYMBOL(phys_base) #include "../../x86/xen/xen-head.S" - + __PAGE_ALIGNED_BSS NEXT_PAGE(empty_zero_page) .skip PAGE_SIZE -- cgit v1.2.3 From 1e4078f0bba46ad61b69548abe6a6faf63b89380 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 12 Oct 2017 09:24:30 +0200 Subject: x86/unwinder: Make CONFIG_UNWINDER_ORC=y the default in the 64-bit defconfig Increase testing coverage by turning on the primary x86 unwinder for the 64-bit defconfig. Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/configs/x86_64_defconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index 4a4b16e56d35..eb65c248708d 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -299,6 +299,7 @@ CONFIG_DEBUG_STACKOVERFLOW=y # CONFIG_DEBUG_RODATA_TEST is not set CONFIG_DEBUG_BOOT_PARAMS=y CONFIG_OPTIMIZE_INLINING=y +CONFIG_ORC_UNWINDER=y CONFIG_SECURITY=y CONFIG_SECURITY_NETWORK=y CONFIG_SECURITY_SELINUX=y -- cgit v1.2.3 From 127a1bea40f7f2a36bc7207ea4d51bb6b4e936fa Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 12 Oct 2017 18:06:19 -0400 Subject: x86/fpu/debug: Remove unused 'x86_fpu_state' and 'x86_fpu_deactivate_state' tracepoints Commit: d1898b733619 ("x86/fpu: Add tracepoints to dump FPU state at key points") ... added the 'x86_fpu_state' and 'x86_fpu_deactivate_state' trace points, but never used them. Today they are still not used. As they take up and waste memory, remove them. Signed-off-by: Steven Rostedt (VMware) Cc: Dave Hansen Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20171012180619.670b68b6@gandalf.local.home Signed-off-by: Ingo Molnar --- arch/x86/include/asm/trace/fpu.h | 10 ---------- 1 file changed, 10 deletions(-) diff --git a/arch/x86/include/asm/trace/fpu.h b/arch/x86/include/asm/trace/fpu.h index 39f7a27bef13..6b086c39e6dc 100644 --- a/arch/x86/include/asm/trace/fpu.h +++ b/arch/x86/include/asm/trace/fpu.h @@ -33,11 +33,6 @@ DECLARE_EVENT_CLASS(x86_fpu, ) ); -DEFINE_EVENT(x86_fpu, x86_fpu_state, - TP_PROTO(struct fpu *fpu), - TP_ARGS(fpu) -); - DEFINE_EVENT(x86_fpu, x86_fpu_before_save, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) @@ -73,11 +68,6 @@ DEFINE_EVENT(x86_fpu, x86_fpu_activate_state, TP_ARGS(fpu) ); -DEFINE_EVENT(x86_fpu, x86_fpu_deactivate_state, - TP_PROTO(struct fpu *fpu), - TP_ARGS(fpu) -); - DEFINE_EVENT(x86_fpu, x86_fpu_init_state, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) -- cgit v1.2.3 From 11af847446ed0d131cf24d16a7ef3d5ea7a49554 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Fri, 13 Oct 2017 15:02:00 -0500 Subject: x86/unwind: Rename unwinder config options to 'CONFIG_UNWINDER_*' Rename the unwinder config options from: CONFIG_ORC_UNWINDER CONFIG_FRAME_POINTER_UNWINDER CONFIG_GUESS_UNWINDER to: CONFIG_UNWINDER_ORC CONFIG_UNWINDER_FRAME_POINTER CONFIG_UNWINDER_GUESS ... in order to give them a more logical config namespace. Suggested-by: Ingo Molnar Signed-off-by: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/73972fc7e2762e91912c6b9584582703d6f1b8cc.1507924831.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- Documentation/x86/orc-unwinder.txt | 2 +- Makefile | 4 ++-- arch/x86/Kconfig | 2 +- arch/x86/Kconfig.debug | 10 +++++----- arch/x86/configs/tiny.config | 4 ++-- arch/x86/configs/x86_64_defconfig | 2 +- arch/x86/include/asm/module.h | 2 +- arch/x86/include/asm/unwind.h | 8 ++++---- arch/x86/kernel/Makefile | 6 +++--- include/asm-generic/vmlinux.lds.h | 2 +- lib/Kconfig.debug | 2 +- scripts/Makefile.build | 2 +- 12 files changed, 23 insertions(+), 23 deletions(-) diff --git a/Documentation/x86/orc-unwinder.txt b/Documentation/x86/orc-unwinder.txt index af0c9a4c65a6..cd4b29be29af 100644 --- a/Documentation/x86/orc-unwinder.txt +++ b/Documentation/x86/orc-unwinder.txt @@ -4,7 +4,7 @@ ORC unwinder Overview -------- -The kernel CONFIG_ORC_UNWINDER option enables the ORC unwinder, which is +The kernel CONFIG_UNWINDER_ORC option enables the ORC unwinder, which is similar in concept to a DWARF unwinder. The difference is that the format of the ORC data is much simpler than DWARF, which in turn allows the ORC unwinder to be much simpler and faster. diff --git a/Makefile b/Makefile index bc5c79e8e3cf..c0f723f81c06 100644 --- a/Makefile +++ b/Makefile @@ -933,8 +933,8 @@ ifdef CONFIG_STACK_VALIDATION ifeq ($(has_libelf),1) objtool_target := tools/objtool FORCE else - ifdef CONFIG_ORC_UNWINDER - $(error "Cannot generate ORC metadata for CONFIG_ORC_UNWINDER=y, please install libelf-dev, libelf-devel or elfutils-libelf-devel") + ifdef CONFIG_UNWINDER_ORC + $(error "Cannot generate ORC metadata for CONFIG_UNWINDER_ORC=y, please install libelf-dev, libelf-devel or elfutils-libelf-devel") else $(warning "Cannot use CONFIG_STACK_VALIDATION=y, please install libelf-dev, libelf-devel or elfutils-libelf-devel") endif diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 971feac13506..6b94ca0aa585 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -170,7 +170,7 @@ config X86 select HAVE_PERF_USER_STACK_DUMP select HAVE_RCU_TABLE_FREE select HAVE_REGS_AND_STACK_ACCESS_API - select HAVE_RELIABLE_STACKTRACE if X86_64 && FRAME_POINTER_UNWINDER && STACK_VALIDATION + select HAVE_RELIABLE_STACKTRACE if X86_64 && UNWINDER_FRAME_POINTER && STACK_VALIDATION select HAVE_STACK_VALIDATION if X86_64 select HAVE_SYSCALL_TRACEPOINTS select HAVE_UNSTABLE_SCHED_CLOCK diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 71a48a30fc84..f274dbb87c26 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -358,13 +358,13 @@ config PUNIT_ATOM_DEBUG choice prompt "Choose kernel unwinder" - default FRAME_POINTER_UNWINDER + default UNWINDER_FRAME_POINTER ---help--- This determines which method will be used for unwinding kernel stack traces for panics, oopses, bugs, warnings, perf, /proc//stack, livepatch, lockdep, and more. -config FRAME_POINTER_UNWINDER +config UNWINDER_FRAME_POINTER bool "Frame pointer unwinder" select FRAME_POINTER ---help--- @@ -379,7 +379,7 @@ config FRAME_POINTER_UNWINDER consistency model, as this is currently the only way to get a reliable stack trace (CONFIG_HAVE_RELIABLE_STACKTRACE). -config ORC_UNWINDER +config UNWINDER_ORC bool "ORC unwinder" depends on X86_64 select STACK_VALIDATION @@ -395,7 +395,7 @@ config ORC_UNWINDER Enabling this option will increase the kernel's runtime memory usage by roughly 2-4MB, depending on your kernel config. -config GUESS_UNWINDER +config UNWINDER_GUESS bool "Guess unwinder" depends on EXPERT ---help--- @@ -410,7 +410,7 @@ config GUESS_UNWINDER endchoice config FRAME_POINTER - depends on !ORC_UNWINDER && !GUESS_UNWINDER + depends on !UNWINDER_ORC && !UNWINDER_GUESS bool endmenu diff --git a/arch/x86/configs/tiny.config b/arch/x86/configs/tiny.config index 550cd5012b73..66c9e2aab16c 100644 --- a/arch/x86/configs/tiny.config +++ b/arch/x86/configs/tiny.config @@ -1,5 +1,5 @@ CONFIG_NOHIGHMEM=y # CONFIG_HIGHMEM4G is not set # CONFIG_HIGHMEM64G is not set -CONFIG_GUESS_UNWINDER=y -# CONFIG_FRAME_POINTER_UNWINDER is not set +CONFIG_UNWINDER_GUESS=y +# CONFIG_UNWINDER_FRAME_POINTER is not set diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index eb65c248708d..e32fc1f274d8 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -299,7 +299,7 @@ CONFIG_DEBUG_STACKOVERFLOW=y # CONFIG_DEBUG_RODATA_TEST is not set CONFIG_DEBUG_BOOT_PARAMS=y CONFIG_OPTIMIZE_INLINING=y -CONFIG_ORC_UNWINDER=y +CONFIG_UNWINDER_ORC=y CONFIG_SECURITY=y CONFIG_SECURITY_NETWORK=y CONFIG_SECURITY_SELINUX=y diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h index 9eb7c718aaf8..9f05a1002aa9 100644 --- a/arch/x86/include/asm/module.h +++ b/arch/x86/include/asm/module.h @@ -5,7 +5,7 @@ #include struct mod_arch_specific { -#ifdef CONFIG_ORC_UNWINDER +#ifdef CONFIG_UNWINDER_ORC unsigned int num_orcs; int *orc_unwind_ip; struct orc_entry *orc_unwind; diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h index e9f793e2df7a..35d67dc7b69f 100644 --- a/arch/x86/include/asm/unwind.h +++ b/arch/x86/include/asm/unwind.h @@ -12,11 +12,11 @@ struct unwind_state { struct task_struct *task; int graph_idx; bool error; -#if defined(CONFIG_ORC_UNWINDER) +#if defined(CONFIG_UNWINDER_ORC) bool signal, full_regs; unsigned long sp, bp, ip; struct pt_regs *regs; -#elif defined(CONFIG_FRAME_POINTER_UNWINDER) +#elif defined(CONFIG_UNWINDER_FRAME_POINTER) bool got_irq; unsigned long *bp, *orig_sp, ip; struct pt_regs *regs; @@ -50,7 +50,7 @@ void unwind_start(struct unwind_state *state, struct task_struct *task, __unwind_start(state, task, regs, first_frame); } -#if defined(CONFIG_ORC_UNWINDER) || defined(CONFIG_FRAME_POINTER_UNWINDER) +#if defined(CONFIG_UNWINDER_ORC) || defined(CONFIG_UNWINDER_FRAME_POINTER) static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state) { if (unwind_done(state)) @@ -65,7 +65,7 @@ static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state) } #endif -#ifdef CONFIG_ORC_UNWINDER +#ifdef CONFIG_UNWINDER_ORC void unwind_init(void); void unwind_module_init(struct module *mod, void *orc_ip, size_t orc_ip_size, void *orc, size_t orc_size); diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index fd0a7895b63f..6209ab6deb50 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -127,9 +127,9 @@ obj-$(CONFIG_PERF_EVENTS) += perf_regs.o obj-$(CONFIG_TRACING) += tracepoint.o obj-$(CONFIG_SCHED_MC_PRIO) += itmt.o -obj-$(CONFIG_ORC_UNWINDER) += unwind_orc.o -obj-$(CONFIG_FRAME_POINTER_UNWINDER) += unwind_frame.o -obj-$(CONFIG_GUESS_UNWINDER) += unwind_guess.o +obj-$(CONFIG_UNWINDER_ORC) += unwind_orc.o +obj-$(CONFIG_UNWINDER_FRAME_POINTER) += unwind_frame.o +obj-$(CONFIG_UNWINDER_GUESS) += unwind_guess.o ### # 64 bit specific files diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 8acfc1e099e1..63e56f6c1877 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -687,7 +687,7 @@ #define BUG_TABLE #endif -#ifdef CONFIG_ORC_UNWINDER +#ifdef CONFIG_UNWINDER_ORC #define ORC_UNWIND_TABLE \ . = ALIGN(4); \ .orc_unwind_ip : AT(ADDR(.orc_unwind_ip) - LOAD_OFFSET) { \ diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 2689b7c50c52..7566eff22236 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -376,7 +376,7 @@ config STACK_VALIDATION that runtime stack traces are more reliable. This is also a prerequisite for generation of ORC unwind data, which - is needed for CONFIG_ORC_UNWINDER. + is needed for CONFIG_UNWINDER_ORC. For more information, see tools/objtool/Documentation/stack-validation.txt. diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 061d0c3a420a..f965f477832e 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -258,7 +258,7 @@ ifneq ($(SKIP_STACK_VALIDATION),1) __objtool_obj := $(objtree)/tools/objtool/objtool -objtool_args = $(if $(CONFIG_ORC_UNWINDER),orc generate,check) +objtool_args = $(if $(CONFIG_UNWINDER_ORC),orc generate,check) ifndef CONFIG_FRAME_POINTER objtool_args += --no-fp -- cgit v1.2.3 From fc72ae40e30327aa24eb88a24b9c7058f938bd36 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Fri, 13 Oct 2017 15:02:01 -0500 Subject: x86/unwind: Make CONFIG_UNWINDER_ORC=y the default in kconfig for 64-bit The ORC unwinder has been stable in testing so far. Give it much wider testing by making it the default in kconfig for x86_64. It's not yet supported for 32-bit, so leave frame pointers as the default there. Suggested-by: Ingo Molnar Signed-off-by: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/9b1237bbe7244ed9cdf8db2dcb1253e37e1c341e.1507924831.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/Kconfig.debug | 33 +++++++++++++++++---------------- 1 file changed, 17 insertions(+), 16 deletions(-) diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index f274dbb87c26..a4ff214fb760 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -358,27 +358,13 @@ config PUNIT_ATOM_DEBUG choice prompt "Choose kernel unwinder" - default UNWINDER_FRAME_POINTER + default UNWINDER_ORC if X86_64 + default UNWINDER_FRAME_POINTER if X86_32 ---help--- This determines which method will be used for unwinding kernel stack traces for panics, oopses, bugs, warnings, perf, /proc//stack, livepatch, lockdep, and more. -config UNWINDER_FRAME_POINTER - bool "Frame pointer unwinder" - select FRAME_POINTER - ---help--- - This option enables the frame pointer unwinder for unwinding kernel - stack traces. - - The unwinder itself is fast and it uses less RAM than the ORC - unwinder, but the kernel text size will grow by ~3% and the kernel's - overall performance will degrade by roughly 5-10%. - - This option is recommended if you want to use the livepatch - consistency model, as this is currently the only way to get a - reliable stack trace (CONFIG_HAVE_RELIABLE_STACKTRACE). - config UNWINDER_ORC bool "ORC unwinder" depends on X86_64 @@ -395,6 +381,21 @@ config UNWINDER_ORC Enabling this option will increase the kernel's runtime memory usage by roughly 2-4MB, depending on your kernel config. +config UNWINDER_FRAME_POINTER + bool "Frame pointer unwinder" + select FRAME_POINTER + ---help--- + This option enables the frame pointer unwinder for unwinding kernel + stack traces. + + The unwinder itself is fast and it uses less RAM than the ORC + unwinder, but the kernel text size will grow by ~3% and the kernel's + overall performance will degrade by roughly 5-10%. + + This option is recommended if you want to use the livepatch + consistency model, as this is currently the only way to get a + reliable stack trace (CONFIG_HAVE_RELIABLE_STACKTRACE). + config UNWINDER_GUESS bool "Guess unwinder" depends on EXPERT -- cgit v1.2.3 From cbe96375025e14fc76f9ed42ee5225120d7210f8 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Fri, 13 Oct 2017 14:56:41 -0700 Subject: bitops: Add clear/set_bit32() to linux/bitops.h Add two simple wrappers around set_bit/clear_bit() that accept the common case of an u32 array. This avoids writing casts in all callers. Signed-off-by: Andi Kleen Reviewed-by: Thomas Gleixner Cc: Linus Torvalds Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20171013215645.23166-2-andi@firstfloor.org Signed-off-by: Ingo Molnar --- include/linux/bitops.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 8fbe259b197c..36794f058ba6 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -227,6 +227,32 @@ static inline unsigned long __ffs64(u64 word) return __ffs((unsigned long)word); } +/* + * clear_bit32 - Clear a bit in memory for u32 array + * @nr: Bit to clear + * @addr: u32 * address of bitmap + * + * Same as clear_bit, but avoids needing casts for u32 arrays. + */ + +static __always_inline void clear_bit32(long nr, volatile u32 *addr) +{ + clear_bit(nr, (volatile unsigned long *)addr); +} + +/* + * set_bit32 - Set a bit in memory for u32 array + * @nr: Bit to clear + * @addr: u32 * address of bitmap + * + * Same as set_bit, but avoids needing casts for u32 arrays. + */ + +static __always_inline void set_bit32(long nr, volatile u32 *addr) +{ + set_bit(nr, (volatile unsigned long *)addr); +} + #ifdef __KERNEL__ #ifndef set_mask_bits -- cgit v1.2.3 From 0b00de857a648dafe7020878c7a27cf776f5edf4 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Fri, 13 Oct 2017 14:56:42 -0700 Subject: x86/cpuid: Add generic table for CPUID dependencies Some CPUID features depend on other features. Currently it's possible to to clear dependent features, but not clear the base features, which can cause various interesting problems. This patch implements a generic table to describe dependencies between CPUID features, to be used by all code that clears CPUID. Some subsystems (like XSAVE) had an own implementation of this, but it's better to do it all in a single place for everyone. Then clear_cpu_cap and setup_clear_cpu_cap always look up this table and clear all dependencies too. This is intended to be a practical table: only for features that make sense to clear. If someone for example clears FPU, or other features that are essentially part of the required base feature set, not much is going to work. Handling that is right now out of scope. We're only handling features which can be usefully cleared. Signed-off-by: Andi Kleen Reviewed-by: Thomas Gleixner Cc: Jonathan McDowell Cc: Linus Torvalds Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20171013215645.23166-3-andi@firstfloor.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/cpufeature.h | 9 ++- arch/x86/include/asm/cpufeatures.h | 5 ++ arch/x86/kernel/cpu/Makefile | 1 + arch/x86/kernel/cpu/cpuid-deps.c | 113 +++++++++++++++++++++++++++++++++++++ 4 files changed, 123 insertions(+), 5 deletions(-) create mode 100644 arch/x86/kernel/cpu/cpuid-deps.c diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index d59c15c3defd..225fd8374fae 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -125,11 +125,10 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; #define boot_cpu_has(bit) cpu_has(&boot_cpu_data, bit) #define set_cpu_cap(c, bit) set_bit(bit, (unsigned long *)((c)->x86_capability)) -#define clear_cpu_cap(c, bit) clear_bit(bit, (unsigned long *)((c)->x86_capability)) -#define setup_clear_cpu_cap(bit) do { \ - clear_cpu_cap(&boot_cpu_data, bit); \ - set_bit(bit, (unsigned long *)cpu_caps_cleared); \ -} while (0) + +extern void setup_clear_cpu_cap(unsigned int bit); +extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); + #define setup_force_cpu_cap(bit) do { \ set_cpu_cap(&boot_cpu_data, bit); \ set_bit(bit, (unsigned long *)cpu_caps_set); \ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 2519c6c801c9..401a70992060 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -21,6 +21,11 @@ * this feature bit is not displayed in /proc/cpuinfo at all. */ +/* + * When adding new features here that depend on other features, + * please update the table in kernel/cpu/cpuid-deps.c + */ + /* 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 */ diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index e17942c131c8..de260fae1017 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -22,6 +22,7 @@ obj-y += rdrand.o obj-y += match.o obj-y += bugs.o obj-$(CONFIG_CPU_FREQ) += aperfmperf.o +obj-y += cpuid-deps.o obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c new file mode 100644 index 000000000000..e48eb7313120 --- /dev/null +++ b/arch/x86/kernel/cpu/cpuid-deps.c @@ -0,0 +1,113 @@ +/* Declare dependencies between CPUIDs */ +#include +#include +#include +#include + +struct cpuid_dep { + unsigned int feature; + unsigned int depends; +}; + +/* + * Table of CPUID features that depend on others. + * + * This only includes dependencies that can be usefully disabled, not + * features part of the base set (like FPU). + * + * Note this all is not __init / __initdata because it can be + * called from cpu hotplug. It shouldn't do anything in this case, + * but it's difficult to tell that to the init reference checker. + */ +const static struct cpuid_dep cpuid_deps[] = { + { X86_FEATURE_XSAVEOPT, X86_FEATURE_XSAVE }, + { X86_FEATURE_XSAVEC, X86_FEATURE_XSAVE }, + { X86_FEATURE_XSAVES, X86_FEATURE_XSAVE }, + { X86_FEATURE_AVX, X86_FEATURE_XSAVE }, + { X86_FEATURE_PKU, X86_FEATURE_XSAVE }, + { X86_FEATURE_MPX, X86_FEATURE_XSAVE }, + { X86_FEATURE_XGETBV1, X86_FEATURE_XSAVE }, + { X86_FEATURE_FXSR_OPT, X86_FEATURE_FXSR }, + { X86_FEATURE_XMM, X86_FEATURE_FXSR }, + { X86_FEATURE_XMM2, X86_FEATURE_XMM }, + { X86_FEATURE_XMM3, X86_FEATURE_XMM2 }, + { X86_FEATURE_XMM4_1, X86_FEATURE_XMM2 }, + { X86_FEATURE_XMM4_2, X86_FEATURE_XMM2 }, + { X86_FEATURE_XMM3, X86_FEATURE_XMM2 }, + { X86_FEATURE_PCLMULQDQ, X86_FEATURE_XMM2 }, + { X86_FEATURE_SSSE3, X86_FEATURE_XMM2, }, + { X86_FEATURE_F16C, X86_FEATURE_XMM2, }, + { X86_FEATURE_AES, X86_FEATURE_XMM2 }, + { X86_FEATURE_SHA_NI, X86_FEATURE_XMM2 }, + { X86_FEATURE_FMA, X86_FEATURE_AVX }, + { X86_FEATURE_AVX2, X86_FEATURE_AVX, }, + { X86_FEATURE_AVX512F, X86_FEATURE_AVX, }, + { X86_FEATURE_AVX512IFMA, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512PF, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512ER, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512CD, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512DQ, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512BW, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512VL, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512VBMI, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512_4VNNIW, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512_4FMAPS, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512_VPOPCNTDQ, X86_FEATURE_AVX512F }, + {} +}; + +static inline void __clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit) +{ + clear_bit32(bit, c->x86_capability); +} + +static inline void __setup_clear_cpu_cap(unsigned int bit) +{ + clear_cpu_cap(&boot_cpu_data, bit); + set_bit32(bit, cpu_caps_cleared); +} + +static inline void clear_feature(struct cpuinfo_x86 *c, unsigned int feature) +{ + if (!c) + __setup_clear_cpu_cap(feature); + else + __clear_cpu_cap(c, feature); +} + +static void do_clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int feature) +{ + bool changed; + DECLARE_BITMAP(disable, NCAPINTS * sizeof(u32) * 8); + const struct cpuid_dep *d; + + clear_feature(c, feature); + + /* Collect all features to disable, handling dependencies */ + memset(disable, 0, sizeof(disable)); + __set_bit(feature, disable); + + /* Loop until we get a stable state. */ + do { + changed = false; + for (d = cpuid_deps; d->feature; d++) { + if (!test_bit(d->depends, disable)) + continue; + if (__test_and_set_bit(d->feature, disable)) + continue; + + changed = true; + clear_feature(c, d->feature); + } + } while (changed); +} + +void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int feature) +{ + do_clear_cpu_cap(c, feature); +} + +void setup_clear_cpu_cap(unsigned int feature) +{ + do_clear_cpu_cap(NULL, feature); +} -- cgit v1.2.3 From 0c2a3913d6f50503f7c59d83a6219e39508cc898 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Fri, 13 Oct 2017 14:56:43 -0700 Subject: x86/fpu: Parse clearcpuid= as early XSAVE argument With a followon patch we want to make clearcpuid affect the XSAVE configuration. But xsave is currently initialized before arguments are parsed. Move the clearcpuid= parsing into the special early xsave argument parsing code. Since clearcpuid= contains a = we need to keep the old __setup around as a dummy, otherwise it would end up as a environment variable in init's environment. Signed-off-by: Andi Kleen Reviewed-by: Thomas Gleixner Cc: Linus Torvalds Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20171013215645.23166-4-andi@firstfloor.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/common.c | 16 +++++++--------- arch/x86/kernel/fpu/init.c | 11 +++++++++++ 2 files changed, 18 insertions(+), 9 deletions(-) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index c9176bae7fd8..03bb004bb15e 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1301,18 +1301,16 @@ void print_cpu_info(struct cpuinfo_x86 *c) pr_cont(")\n"); } -static __init int setup_disablecpuid(char *arg) +/* + * clearcpuid= was already parsed in fpu__init_parse_early_param. + * But we need to keep a dummy __setup around otherwise it would + * show up as an environment variable for init. + */ +static __init int setup_clearcpuid(char *arg) { - int bit; - - if (get_option(&arg, &bit) && bit >= 0 && bit < NCAPINTS * 32) - setup_clear_cpu_cap(bit); - else - return 0; - return 1; } -__setup("clearcpuid=", setup_disablecpuid); +__setup("clearcpuid=", setup_clearcpuid); #ifdef CONFIG_X86_64 DEFINE_PER_CPU_FIRST(union irq_stack_union, diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 7affb7e3d9a5..6abd83572b01 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -249,6 +249,10 @@ static void __init fpu__init_system_ctx_switch(void) */ static void __init fpu__init_parse_early_param(void) { + char arg[32]; + char *argptr = arg; + int bit; + if (cmdline_find_option_bool(boot_command_line, "no387")) setup_clear_cpu_cap(X86_FEATURE_FPU); @@ -266,6 +270,13 @@ static void __init fpu__init_parse_early_param(void) if (cmdline_find_option_bool(boot_command_line, "noxsaves")) setup_clear_cpu_cap(X86_FEATURE_XSAVES); + + if (cmdline_find_option(boot_command_line, "clearcpuid", arg, + sizeof(arg)) && + get_option(&argptr, &bit) && + bit >= 0 && + bit < NCAPINTS * 32) + setup_clear_cpu_cap(bit); } /* -- cgit v1.2.3 From ccb18db2ab9d923df07e7495123fe5fb02329713 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Fri, 13 Oct 2017 14:56:44 -0700 Subject: x86/fpu: Make XSAVE check the base CPUID features before enabling Before enabling XSAVE, not only check the XSAVE specific CPUID bits, but also the base CPUID features of the respective XSAVE feature. This allows to disable individual XSAVE states using the existing clearcpuid= option, which can be useful for performance testing and debugging, and also in general avoids inconsistencies. Signed-off-by: Andi Kleen Reviewed-by: Thomas Gleixner Cc: Linus Torvalds Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20171013215645.23166-5-andi@firstfloor.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/fpu/xstate.c | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index f1d5476c9022..fb581292975b 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -15,6 +15,7 @@ #include #include +#include /* * Although we spell it out in here, the Processor Trace @@ -36,6 +37,19 @@ static const char *xfeature_names[] = "unknown xstate feature" , }; +static short xsave_cpuid_features[] __initdata = { + X86_FEATURE_FPU, + X86_FEATURE_XMM, + X86_FEATURE_AVX, + X86_FEATURE_MPX, + X86_FEATURE_MPX, + X86_FEATURE_AVX512F, + X86_FEATURE_AVX512F, + X86_FEATURE_AVX512F, + X86_FEATURE_INTEL_PT, + X86_FEATURE_PKU, +}; + /* * Mask of xstate features supported by the CPU and the kernel: */ @@ -726,6 +740,7 @@ void __init fpu__init_system_xstate(void) unsigned int eax, ebx, ecx, edx; static int on_boot_cpu __initdata = 1; int err; + int i; WARN_ON_FPU(!on_boot_cpu); on_boot_cpu = 0; @@ -759,6 +774,14 @@ void __init fpu__init_system_xstate(void) goto out_disable; } + /* + * Clear XSAVE features that are disabled in the normal CPUID. + */ + for (i = 0; i < ARRAY_SIZE(xsave_cpuid_features); i++) { + if (!boot_cpu_has(xsave_cpuid_features[i])) + xfeatures_mask &= ~BIT(i); + } + xfeatures_mask &= fpu__get_supported_xfeatures_mask(); /* Enable xstate instructions to be able to continue with initialization: */ -- cgit v1.2.3 From 73e3a7d2a7c3be29a5a22b85026f6cfa5664267f Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Fri, 13 Oct 2017 14:56:45 -0700 Subject: x86/fpu: Remove the explicit clearing of XSAVE dependent features Clearing a CPU feature with setup_clear_cpu_cap() clears all features which depend on it. Expressing feature dependencies in one place is easier to maintain than keeping functions like fpu__xstate_clear_all_cpu_caps() up to date. The features which depend on XSAVE have their dependency expressed in the dependency table, so its sufficient to clear X86_FEATURE_XSAVE. Remove the explicit clearing of XSAVE dependent features. Signed-off-by: Andi Kleen Reviewed-by: Thomas Gleixner Cc: Linus Torvalds Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20171013215645.23166-6-andi@firstfloor.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/fpu/xstate.c | 20 -------------------- 1 file changed, 20 deletions(-) diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index fb581292975b..87a57b7642d3 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -73,26 +73,6 @@ unsigned int fpu_user_xstate_size; void fpu__xstate_clear_all_cpu_caps(void) { setup_clear_cpu_cap(X86_FEATURE_XSAVE); - setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); - setup_clear_cpu_cap(X86_FEATURE_XSAVEC); - setup_clear_cpu_cap(X86_FEATURE_XSAVES); - setup_clear_cpu_cap(X86_FEATURE_AVX); - setup_clear_cpu_cap(X86_FEATURE_AVX2); - setup_clear_cpu_cap(X86_FEATURE_AVX512F); - setup_clear_cpu_cap(X86_FEATURE_AVX512IFMA); - setup_clear_cpu_cap(X86_FEATURE_AVX512PF); - setup_clear_cpu_cap(X86_FEATURE_AVX512ER); - setup_clear_cpu_cap(X86_FEATURE_AVX512CD); - setup_clear_cpu_cap(X86_FEATURE_AVX512DQ); - setup_clear_cpu_cap(X86_FEATURE_AVX512BW); - setup_clear_cpu_cap(X86_FEATURE_AVX512VL); - setup_clear_cpu_cap(X86_FEATURE_MPX); - setup_clear_cpu_cap(X86_FEATURE_XGETBV1); - setup_clear_cpu_cap(X86_FEATURE_AVX512VBMI); - setup_clear_cpu_cap(X86_FEATURE_PKU); - setup_clear_cpu_cap(X86_FEATURE_AVX512_4VNNIW); - setup_clear_cpu_cap(X86_FEATURE_AVX512_4FMAPS); - setup_clear_cpu_cap(X86_FEATURE_AVX512_VPOPCNTDQ); } /* -- cgit v1.2.3 From 6a93bb7e4a7d6670677d5b0eb980936eb9cc5d2e Mon Sep 17 00:00:00 2001 From: Kamalesh Babulal Date: Sat, 14 Oct 2017 20:17:54 +0530 Subject: objtool: Print top level commands on incorrect usage Print top-level objtool commands, along with the error on incorrect command line usage. Objtool command line parser exit's with code 129, for incorrect usage. Convert the cmd_usage() exit code also, to maintain consistency across objtool. After the patch: $ ./objtool -j Unknown option: -j usage: objtool COMMAND [ARGS] Commands: check Perform stack metadata validation on an object file orc Generate in-place ORC unwind tables for an object file $ echo $? 129 Signed-off-by: Kamalesh Babulal Acked-by: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1507992474-16142-1-git-send-email-kamalesh@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- tools/objtool/objtool.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/tools/objtool/objtool.c b/tools/objtool/objtool.c index 31e0f9143840..07f329919828 100644 --- a/tools/objtool/objtool.c +++ b/tools/objtool/objtool.c @@ -70,7 +70,7 @@ static void cmd_usage(void) printf("\n"); - exit(1); + exit(129); } static void handle_options(int *argc, const char ***argv) @@ -86,9 +86,7 @@ static void handle_options(int *argc, const char ***argv) break; } else { fprintf(stderr, "Unknown option: %s\n", cmd); - fprintf(stderr, "\n Usage: %s\n", - objtool_usage_string); - exit(1); + cmd_usage(); } (*argv)++; -- cgit v1.2.3 From 57b8b1a1856adaa849d02d547411a553a531022b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 18 Oct 2017 19:39:35 +0200 Subject: x86/cpuid: Prevent out of bound access in do_clear_cpu_cap() do_clear_cpu_cap() allocates a bitmap to keep track of disabled feature dependencies. That bitmap is sized NCAPINTS * BITS_PER_INIT. The possible 'features' which can be handed in are larger than this, because after the capabilities the bug 'feature' bits occupy another 32bit. Not really obvious... So clearing any of the misfeature bits, as 32bit does for the F00F bug, accesses that bitmap out of bounds thereby corrupting the stack. Size the bitmap proper and add a sanity check to catch accidental out of bound access. Fixes: 0b00de857a64 ("x86/cpuid: Add generic table for CPUID dependencies") Reported-by: kernel test robot Signed-off-by: Thomas Gleixner Cc: Andi Kleen Cc: Borislav Petkov Link: https://lkml.kernel.org/r/20171018022023.GA12058@yexl-desktop --- arch/x86/kernel/cpu/cpuid-deps.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c index e48eb7313120..c1d49842a411 100644 --- a/arch/x86/kernel/cpu/cpuid-deps.c +++ b/arch/x86/kernel/cpu/cpuid-deps.c @@ -75,11 +75,17 @@ static inline void clear_feature(struct cpuinfo_x86 *c, unsigned int feature) __clear_cpu_cap(c, feature); } +/* Take the capabilities and the BUG bits into account */ +#define MAX_FEATURE_BITS ((NCAPINTS + NBUGINTS) * sizeof(u32) * 8) + static void do_clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int feature) { - bool changed; - DECLARE_BITMAP(disable, NCAPINTS * sizeof(u32) * 8); + DECLARE_BITMAP(disable, MAX_FEATURE_BITS); const struct cpuid_dep *d; + bool changed; + + if (WARN_ON(feature >= MAX_FEATURE_BITS)) + return; clear_feature(c, feature); -- cgit v1.2.3 From da20ab35180780e4a6eadc804544f1fa967f3567 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Wed, 18 Oct 2017 10:21:07 -0700 Subject: x86/entry: Use SYSCALL_DEFINE() macros for sys_modify_ldt() We do not have tracepoints for sys_modify_ldt() because we define it directly instead of using the normal SYSCALL_DEFINEx() macros. However, there is a reason sys_modify_ldt() does not use the macros: it has an 'int' return type instead of 'unsigned long'. This is a bug, but it's a bug cemented in the ABI. What does this mean? If we return -EINVAL from a function that returns 'int', we have 0x00000000ffffffea in %rax. But, if we return -EINVAL from a function returning 'unsigned long', we end up with 0xffffffffffffffea in %rax, which is wrong. To work around this and maintain the 'int' behavior while using the SYSCALL_DEFINEx() macros, so we add a cast to 'unsigned int' in both implementations of sys_modify_ldt(). Signed-off-by: Dave Hansen Reviewed-by: Andy Lutomirski Reviewed-by: Brian Gerst Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20171018172107.1A79C532@viggo.jf.intel.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/syscalls.h | 2 +- arch/x86/kernel/ldt.c | 16 +++++++++++++--- arch/x86/um/ldt.c | 7 +++++-- 3 files changed, 19 insertions(+), 6 deletions(-) diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h index 91dfcafe27a6..bad25bb80679 100644 --- a/arch/x86/include/asm/syscalls.h +++ b/arch/x86/include/asm/syscalls.h @@ -21,7 +21,7 @@ asmlinkage long sys_ioperm(unsigned long, unsigned long, int); asmlinkage long sys_iopl(unsigned int); /* kernel/ldt.c */ -asmlinkage int sys_modify_ldt(int, void __user *, unsigned long); +asmlinkage long sys_modify_ldt(int, void __user *, unsigned long); /* kernel/signal.c */ asmlinkage long sys_rt_sigreturn(void); diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index f0e64db18ac8..0402d44deb4d 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -294,8 +295,8 @@ out: return error; } -asmlinkage int sys_modify_ldt(int func, void __user *ptr, - unsigned long bytecount) +SYSCALL_DEFINE3(modify_ldt, int , func , void __user * , ptr , + unsigned long , bytecount) { int ret = -ENOSYS; @@ -313,5 +314,14 @@ asmlinkage int sys_modify_ldt(int func, void __user *ptr, ret = write_ldt(ptr, bytecount, 0); break; } - return ret; + /* + * The SYSCALL_DEFINE() macros give us an 'unsigned long' + * return type, but tht ABI for sys_modify_ldt() expects + * 'int'. This cast gives us an int-sized value in %rax + * for the return code. The 'unsigned' is necessary so + * the compiler does not try to sign-extend the negative + * return codes into the high half of the register when + * taking the value from int->long. + */ + return (unsigned int)ret; } diff --git a/arch/x86/um/ldt.c b/arch/x86/um/ldt.c index 836a1eb5df43..3ee234b6234d 100644 --- a/arch/x86/um/ldt.c +++ b/arch/x86/um/ldt.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include @@ -369,7 +370,9 @@ void free_ldt(struct mm_context *mm) mm->arch.ldt.entry_count = 0; } -int sys_modify_ldt(int func, void __user *ptr, unsigned long bytecount) +SYSCALL_DEFINE3(modify_ldt, int , func , void __user * , ptr , + unsigned long , bytecount) { - return do_modify_ldt_skas(func, ptr, bytecount); + /* See non-um modify_ldt() for why we do this cast */ + return (unsigned int)do_modify_ldt_skas(func, ptr, bytecount); } -- cgit v1.2.3 From 82c62fa0c49aa305104013cee4468772799bb391 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Fri, 20 Oct 2017 11:21:35 -0500 Subject: x86/asm: Don't use the confusing '.ifeq' directive I find the '.ifeq ' directive to be confusing. Reading it quickly seems to suggest its opposite meaning, or that it's missing an argument. Improve readability by replacing all of its x86 uses with '.if == 0'. Signed-off-by: Josh Poimboeuf Cc: Andrei Vagin Cc: Andy Lutomirski Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/757da028e802c7e98d23fbab8d234b1063e161cf.1508516398.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/entry/entry_64.S | 2 +- arch/x86/kernel/head_32.S | 2 +- arch/x86/kernel/head_64.S | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index f6cdb7a1455e..846e84a1d1f7 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -817,7 +817,7 @@ ENTRY(\sym) ASM_CLAC - .ifeq \has_error_code + .if \has_error_code == 0 pushq $-1 /* ORIG_RAX: no syscall to restart */ .endif diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 9ed3074d0d27..6e50f87765e5 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -401,7 +401,7 @@ ENTRY(early_idt_handler_array) # 24(%rsp) error code i = 0 .rept NUM_EXCEPTION_VECTORS - .ifeq (EXCEPTION_ERRCODE_MASK >> i) & 1 + .if ((EXCEPTION_ERRCODE_MASK >> i) & 1) == 0 pushl $0 # Dummy error code, to make stack frame uniform .endif pushl $i # 20(%esp) Vector number diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 42e32c2e51bb..311db1a73c11 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -273,7 +273,7 @@ ENDPROC(start_cpu0) ENTRY(early_idt_handler_array) i = 0 .rept NUM_EXCEPTION_VECTORS - .ifeq (EXCEPTION_ERRCODE_MASK >> i) & 1 + .if ((EXCEPTION_ERRCODE_MASK >> i) & 1) == 0 UNWIND_HINT_IRET_REGS pushq $0 # Dummy error code, to make stack frame uniform .else -- cgit v1.2.3 From c128dbfa0f879f8ce7b79054037889b0b2240728 Mon Sep 17 00:00:00 2001 From: Gayatri Kammela Date: Mon, 30 Oct 2017 18:20:29 -0700 Subject: x86/cpufeatures: Enable new SSE/AVX/AVX512 CPU features Add a few new SSE/AVX/AVX512 instruction groups/features for enumeration in /proc/cpuinfo: AVX512_VBMI2, GFNI, VAES, VPCLMULQDQ, AVX512_VNNI, AVX512_BITALG. CPUID.(EAX=7,ECX=0):ECX[bit 6] AVX512_VBMI2 CPUID.(EAX=7,ECX=0):ECX[bit 8] GFNI CPUID.(EAX=7,ECX=0):ECX[bit 9] VAES CPUID.(EAX=7,ECX=0):ECX[bit 10] VPCLMULQDQ CPUID.(EAX=7,ECX=0):ECX[bit 11] AVX512_VNNI CPUID.(EAX=7,ECX=0):ECX[bit 12] AVX512_BITALG Detailed information of CPUID bits for these features can be found in the Intel Architecture Instruction Set Extensions and Future Features Programming Interface document (refer to Table 1-1. and Table 1-2.). A copy of this document is available at https://bugzilla.kernel.org/show_bug.cgi?id=197239 Signed-off-by: Gayatri Kammela Acked-by: Thomas Gleixner Cc: Andi Kleen Cc: Fenghua Yu Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Ravi Shankar Cc: Ricardo Neri Cc: Yang Zhong Cc: bp@alien8.de Link: http://lkml.kernel.org/r/1509412829-23380-1-git-send-email-gayatri.kammela@intel.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/cpufeatures.h | 6 ++++++ arch/x86/kernel/cpu/cpuid-deps.c | 6 ++++++ 2 files changed, 12 insertions(+) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 401a70992060..b0556f882aa8 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -299,6 +299,12 @@ #define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/ #define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */ #define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */ +#define X86_FEATURE_AVX512_VBMI2 (16*32+ 6) /* Additional AVX512 Vector Bit Manipulation Instructions */ +#define X86_FEATURE_GFNI (16*32+ 8) /* Galois Field New Instructions */ +#define X86_FEATURE_VAES (16*32+ 9) /* Vector AES */ +#define X86_FEATURE_VPCLMULQDQ (16*32+ 10) /* Carry-Less Multiplication Double Quadword */ +#define X86_FEATURE_AVX512_VNNI (16*32+ 11) /* Vector Neural Network Instructions */ +#define X86_FEATURE_AVX512_BITALG (16*32+12) /* Support for VPOPCNT[B,W] and VPSHUF-BITQMB */ #define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */ #define X86_FEATURE_LA57 (16*32+16) /* 5-level page tables */ #define X86_FEATURE_RDPID (16*32+22) /* RDPID instruction */ diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c index c1d49842a411..c21f22d836ad 100644 --- a/arch/x86/kernel/cpu/cpuid-deps.c +++ b/arch/x86/kernel/cpu/cpuid-deps.c @@ -50,6 +50,12 @@ const static struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_AVX512BW, X86_FEATURE_AVX512F }, { X86_FEATURE_AVX512VL, X86_FEATURE_AVX512F }, { X86_FEATURE_AVX512VBMI, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512_VBMI2, X86_FEATURE_AVX512VL }, + { X86_FEATURE_GFNI, X86_FEATURE_AVX512VL }, + { X86_FEATURE_VAES, X86_FEATURE_AVX512VL }, + { X86_FEATURE_VPCLMULQDQ, X86_FEATURE_AVX512VL }, + { X86_FEATURE_AVX512_VNNI, X86_FEATURE_AVX512VL }, + { X86_FEATURE_AVX512_BITALG, X86_FEATURE_AVX512VL }, { X86_FEATURE_AVX512_4VNNIW, X86_FEATURE_AVX512F }, { X86_FEATURE_AVX512_4FMAPS, X86_FEATURE_AVX512F }, { X86_FEATURE_AVX512_VPOPCNTDQ, X86_FEATURE_AVX512F }, -- cgit v1.2.3 From 1067f030994c69ca1fba8c607437c8895dcf8509 Mon Sep 17 00:00:00 2001 From: Ricardo Neri Date: Fri, 27 Oct 2017 13:25:28 -0700 Subject: x86/mm: Relocate page fault e