diff options
Diffstat (limited to 'arch/x86')
| -rw-r--r-- | arch/x86/Makefile | 6 | ||||
| -rw-r--r-- | arch/x86/include/asm/asm.h | 25 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/perf_event_intel.c | 7 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/perf_event_intel_rapl.c | 1 | ||||
| -rw-r--r-- | arch/x86/kernel/entry_64.S | 8 | ||||
| -rw-r--r-- | arch/x86/kernel/head_32.S | 4 | ||||
| -rw-r--r-- | arch/x86/kernel/head_64.S | 4 | ||||
| -rw-r--r-- | arch/x86/lib/Makefile | 2 | ||||
| -rw-r--r-- | arch/x86/lib/copy_user_64.S | 116 | ||||
| -rw-r--r-- | arch/x86/lib/copy_user_nocache_64.S | 136 | ||||
| -rw-r--r-- | arch/x86/net/bpf_jit_comp.c | 28 | ||||
| -rw-r--r-- | arch/x86/vdso/Makefile | 2 |
12 files changed, 165 insertions, 174 deletions
diff --git a/arch/x86/Makefile b/arch/x86/Makefile index c7c3187..57996ee 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -77,6 +77,12 @@ else KBUILD_AFLAGS += -m64 KBUILD_CFLAGS += -m64 + # Align jump targets to 1 byte, not the default 16 bytes: + KBUILD_CFLAGS += -falign-jumps=1 + + # Pack loops tightly as well: + KBUILD_CFLAGS += -falign-loops=1 + # Don't autogenerate traditional x87 instructions KBUILD_CFLAGS += $(call cc-option,-mno-80387) KBUILD_CFLAGS += $(call cc-option,-mno-fp-ret-in-387) diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 7730c1c..189679a 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -63,6 +63,31 @@ _ASM_ALIGN ; \ _ASM_PTR (entry); \ .popsection + +.macro ALIGN_DESTINATION + /* check for bad alignment of destination */ + movl %edi,%ecx + andl $7,%ecx + jz 102f /* already aligned */ + subl $8,%ecx + negl %ecx + subl %ecx,%edx +100: movb (%rsi),%al +101: movb %al,(%rdi) + incq %rsi + incq %rdi + decl %ecx + jnz 100b +102: + .section .fixup,"ax" +103: addl %ecx,%edx /* ecx is zerorest also */ + jmp copy_user_handle_tail + .previous + + _ASM_EXTABLE(100b,103b) + _ASM_EXTABLE(101b,103b) + .endm + #else # define _ASM_EXTABLE(from,to) \ " .pushsection \"__ex_table\",\"a\"\n" \ diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 960e85d..3998131 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1134,7 +1134,7 @@ static __initconst const u64 slm_hw_cache_extra_regs [ C(LL ) ] = { [ C(OP_READ) ] = { [ C(RESULT_ACCESS) ] = SLM_DMND_READ|SLM_LLC_ACCESS, - [ C(RESULT_MISS) ] = SLM_DMND_READ|SLM_LLC_MISS, + [ C(RESULT_MISS) ] = 0, }, [ C(OP_WRITE) ] = { [ C(RESULT_ACCESS) ] = SLM_DMND_WRITE|SLM_LLC_ACCESS, @@ -1184,8 +1184,7 @@ static __initconst const u64 slm_hw_cache_event_ids [ C(OP_READ) ] = { /* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */ [ C(RESULT_ACCESS) ] = 0x01b7, - /* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */ - [ C(RESULT_MISS) ] = 0x01b7, + [ C(RESULT_MISS) ] = 0, }, [ C(OP_WRITE) ] = { /* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */ @@ -1217,7 +1216,7 @@ static __initconst const u64 slm_hw_cache_event_ids [ C(ITLB) ] = { [ C(OP_READ) ] = { [ C(RESULT_ACCESS) ] = 0x00c0, /* INST_RETIRED.ANY_P */ - [ C(RESULT_MISS) ] = 0x0282, /* ITLB.MISSES */ + [ C(RESULT_MISS) ] = 0x40205, /* PAGE_WALKS.I_SIDE_WALKS */ }, [ C(OP_WRITE) ] = { [ C(RESULT_ACCESS) ] = -1, diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c index 999289b9..358c54a 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c +++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c @@ -722,6 +722,7 @@ static int __init rapl_pmu_init(void) break; case 60: /* Haswell */ case 69: /* Haswell-Celeron */ + case 61: /* Broadwell */ rapl_cntr_mask = RAPL_IDX_HSW; rapl_pmu_events_group.attrs = rapl_events_hsw_attr; break; diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 09c3f9e..47b9581 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -1190,17 +1190,17 @@ ENTRY(xen_failsafe_callback) /*CFI_REL_OFFSET ds,DS*/ CFI_REL_OFFSET r11,8 CFI_REL_OFFSET rcx,0 - movw %ds,%cx + movl %ds,%ecx cmpw %cx,0x10(%rsp) CFI_REMEMBER_STATE jne 1f - movw %es,%cx + movl %es,%ecx cmpw %cx,0x18(%rsp) jne 1f - movw %fs,%cx + movl %fs,%ecx cmpw %cx,0x20(%rsp) jne 1f - movw %gs,%cx + movl %gs,%ecx cmpw %cx,0x28(%rsp) jne 1f /* All segments match their saved values => Category 2 (Bad IRET). */ diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index d031bad..02d2572 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -547,7 +547,7 @@ ENTRY(early_idt_handler) cld cmpl $2,(%esp) # X86_TRAP_NMI - je is_nmi # Ignore NMI + je .Lis_nmi # Ignore NMI cmpl $2,%ss:early_recursion_flag je hlt_loop @@ -600,7 +600,7 @@ ex_entry: pop %ecx pop %eax decl %ss:early_recursion_flag -is_nmi: +.Lis_nmi: addl $8,%esp /* drop vector number and error code */ iret ENDPROC(early_idt_handler) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index ae6588b..43eafc8 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -344,7 +344,7 @@ ENTRY(early_idt_handler) cld cmpl $2,(%rsp) # X86_TRAP_NMI - je is_nmi # Ignore NMI + je .Lis_nmi # Ignore NMI cmpl $2,early_recursion_flag(%rip) jz 1f @@ -409,7 +409,7 @@ ENTRY(early_idt_handler) popq %rcx popq %rax decl early_recursion_flag(%rip) -is_nmi: +.Lis_nmi: addq $16,%rsp # drop vector number and error code INTERRUPT_RETURN ENDPROC(early_idt_handler) diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 1530afb..982989d 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -40,6 +40,6 @@ else lib-y += csum-partial_64.o csum-copy_64.o csum-wrappers_64.o lib-y += clear_page_64.o copy_page_64.o lib-y += memmove_64.o memset_64.o - lib-y += copy_user_64.o copy_user_nocache_64.o + lib-y += copy_user_64.o lib-y += cmpxchg16b_emu.o endif diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index fa997df..e4b3bee 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -16,30 +16,6 @@ #include <asm/asm.h> #include <asm/smap.h> - .macro ALIGN_DESTINATION - /* check for bad alignment of destination */ - movl %edi,%ecx - andl $7,%ecx - jz 102f /* already aligned */ - subl $8,%ecx - negl %ecx - subl %ecx,%edx -100: movb (%rsi),%al -101: movb %al,(%rdi) - incq %rsi - incq %rdi - decl %ecx - jnz 100b -102: - .section .fixup,"ax" -103: addl %ecx,%edx /* ecx is zerorest also */ - jmp copy_user_handle_tail - .previous - - _ASM_EXTABLE(100b,103b) - _ASM_EXTABLE(101b,103b) - .endm - /* Standard copy_to_user with segment limit checking */ ENTRY(_copy_to_user) CFI_STARTPROC @@ -266,3 +242,95 @@ ENTRY(copy_user_enhanced_fast_string) _ASM_EXTABLE(1b,12b) CFI_ENDPROC ENDPROC(copy_user_enhanced_fast_string) + +/* + * copy_user_nocache - Uncached memory copy with exception handling + * This will force destination/source out of cache for more performance. + */ +ENTRY(__copy_user_nocache) + CFI_STARTPROC + ASM_STAC + cmpl $8,%edx + jb 20f /* less then 8 bytes, go to byte copy loop */ + ALIGN_DESTINATION + movl %edx,%ecx + andl $63,%edx + shrl $6,%ecx + jz 17f +1: movq (%rsi),%r8 +2: movq 1*8(%rsi),%r9 +3: movq 2*8(%rsi),%r10 +4: movq 3*8(%rsi),%r11 +5: movnti %r8,(%rdi) +6: movnti %r9,1*8(%rdi) +7: movnti %r10,2*8(%rdi) +8: movnti %r11,3*8(%rdi) +9: movq 4*8(%rsi),%r8 +10: movq 5*8(%rsi),%r9 +11: movq 6*8(%rsi),%r10 +12: movq 7*8(%rsi),%r11 +13: movnti %r8,4*8(%rdi) +14: movnti %r9,5*8(%rdi) +15: movnti %r10,6*8(%rdi) +16: movnti %r11,7*8(%rdi) + leaq 64(%rsi),%rsi + leaq 64(%rdi),%rdi + decl %ecx + jnz 1b +17: movl %edx,%ecx + andl $7,%edx + shrl $3,%ecx + jz 20f +18: movq (%rsi),%r8 +19: movnti %r8,(%rdi) + leaq 8(%rsi),%rsi + leaq 8(%rdi),%rdi + decl %ecx + jnz 18b +20: andl %edx,%edx + jz 23f + movl %edx,%ecx +21: movb (%rsi),%al +22: movb %al,(%rdi) + incq %rsi + incq %rdi + decl %ecx + jnz 21b +23: xorl %eax,%eax + ASM_CLAC + sfence + ret + + .section .fixup,"ax" +30: shll $6,%ecx + addl %ecx,%edx + jmp 60f +40: lea (%rdx,%rcx,8),%rdx + jmp 60f +50: movl %ecx,%edx +60: sfence + jmp copy_user_handle_tail + .previous + + _ASM_EXTABLE(1b,30b) + _ASM_EXTABLE(2b,30b) + _ASM_EXTABLE(3b,30b) + _ASM_EXTABLE(4b,30b) + _ASM_EXTABLE(5b,30b) + _ASM_EXTABLE(6b,30b) + _ASM_EXTABLE(7b,30b) + _ASM_EXTABLE(8b,30b) + _ASM_EXTABLE(9b,30b) + _ASM_EXTABLE(10b,30b) + _ASM_EXTABLE(11b,30b) + _ASM_EXTABLE(12b,30b) + _ASM_EXTABLE(13b,30b) + _ASM_EXTABLE(14b,30b) + _ASM_EXTABLE(15b,30b) + _ASM_EXTABLE(16b,30b) + _ASM_EXTABLE(18b,40b) + _ASM_EXTABLE(19b,40b) + _ASM_EXTABLE(21b,50b) + _ASM_EXTABLE(22b,50b) + CFI_ENDPROC +ENDPROC(__copy_user_nocache) diff --git a/arch/x86/lib/copy_user_nocache_64.S b/arch/x86/lib/copy_user_nocache_64.S deleted file mode 100644 index 6a4f43c..0000000 --- a/arch/x86/lib/copy_user_nocache_64.S +++ /dev/null @@ -1,136 +0,0 @@ -/* - * Copyright 2008 Vitaly Mayatskikh <vmayatsk@redhat.com> - * Copyright 2002 Andi Kleen, SuSE Labs. - * Subject to the GNU Public License v2. - * - * Functions to copy from and to user space. - */ - -#include <linux/linkage.h> -#include <asm/dwarf2.h> - -#define FIX_ALIGNMENT 1 - -#include <asm/current.h> -#include <asm/asm-offsets.h> -#include <asm/thread_info.h> -#include <asm/asm.h> -#include <asm/smap.h> - - .macro ALIGN_DESTINATION -#ifdef FIX_ALIGNMENT - /* check for bad alignment of destination */ - movl %edi,%ecx - andl $7,%ecx - jz 102f /* already aligned */ - subl $8,%ecx - negl %ecx - subl %ecx,%edx -100: movb (%rsi),%al -101: movb %al,(%rdi) - incq %rsi - incq %rdi - decl %ecx - jnz 100b -102: - .section .fixup,"ax" -103: addl %ecx,%edx /* ecx is zerorest also */ - jmp copy_user_handle_tail - .previous - - _ASM_EXTABLE(100b,103b) - _ASM_EXTABLE(101b,103b) -#endif - .endm - -/* - * copy_user_nocache - Uncached memory copy with exception handling - * This will force destination/source out of cache for more performance. - */ -ENTRY(__copy_user_nocache) - CFI_STARTPROC - ASM_STAC - cmpl $8,%edx - jb 20f /* less then 8 bytes, go to byte copy loop */ - ALIGN_DESTINATION - movl %edx,%ecx - andl $63,%edx - shrl $6,%ecx - jz 17f -1: movq (%rsi),%r8 -2: movq 1*8(%rsi),%r9 -3: movq 2*8(%rsi),%r10 -4: movq 3*8(%rsi),%r11 -5: movnti %r8,(%rdi) -6: movnti %r9,1*8(%rdi) -7: movnti %r10,2*8(%rdi) -8: movnti %r11,3*8(%rdi) -9: movq 4*8(%rsi),%r8 -10: movq 5*8(%rsi),%r9 -11: movq 6*8(%rsi),%r10 -12: movq 7*8(%rsi),%r11 -13: movnti %r8,4*8(%rdi) -14: movnti %r9,5*8(%rdi) -15: movnti %r10,6*8(%rdi) -16: movnti %r11,7*8(%rdi) - leaq 64(%rsi),%rsi - leaq 64(%rdi),%rdi - decl %ecx - jnz 1b -17: movl %edx,%ecx - andl $7,%edx - shrl $3,%ecx - jz 20f -18: movq (%rsi),%r8 -19: movnti %r8,(%rdi) - leaq 8(%rsi),%rsi - leaq 8(%rdi),%rdi - decl %ecx - jnz 18b -20: andl %edx,%edx - jz 23f - movl %edx,%ecx -21: movb (%rsi),%al -22: movb %al,(%rdi) - incq %rsi - incq %rdi - decl %ecx - jnz 21b -23: xorl %eax,%eax - ASM_CLAC - sfence - ret - - .section .fixup,"ax" -30: shll $6,%ecx - addl %ecx,%edx - jmp 60f -40: lea (%rdx,%rcx,8),%rdx - jmp 60f -50: movl %ecx,%edx -60: sfence - jmp copy_user_handle_tail - .previous - - _ASM_EXTABLE(1b,30b) - _ASM_EXTABLE(2b,30b) - _ASM_EXTABLE(3b,30b) - _ASM_EXTABLE(4b,30b) - _ASM_EXTABLE(5b,30b) - _ASM_EXTABLE(6b,30b) - _ASM_EXTABLE(7b,30b) - _ASM_EXTABLE(8b,30b) - _ASM_EXTABLE(9b,30b) - _ASM_EXTABLE(10b,30b) - _ASM_EXTABLE(11b,30b) - _ASM_EXTABLE(12b,30b) - _ASM_EXTABLE(13b,30b) - _ASM_EXTABLE(14b,30b) - _ASM_EXTABLE(15b,30b) - _ASM_EXTABLE(16b,30b) - _ASM_EXTABLE(18b,40b) - _ASM_EXTABLE(19b,40b) - _ASM_EXTABLE(21b,50b) - _ASM_EXTABLE(22b,50b) - CFI_ENDPROC -ENDPROC(__copy_user_nocache) diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 9875143..99f7610 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -559,6 +559,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, if (is_ereg(dst_reg)) EMIT1(0x41); EMIT3(0xC1, add_1reg(0xC8, dst_reg), 8); + + /* emit 'movzwl eax, ax' */ + if (is_ereg(dst_reg)) + EMIT3(0x45, 0x0F, 0xB7); + else + EMIT2(0x0F, 0xB7); + EMIT1(add_2reg(0xC0, dst_reg, dst_reg)); break; case 32: /* emit 'bswap eax' to swap lower 4 bytes */ @@ -577,6 +584,27 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, break; case BPF_ALU | BPF_END | BPF_FROM_LE: + switch (imm32) { + case 16: + /* emit 'movzwl eax, ax' to zero extend 16-bit + * into 64 bit + */ + if (is_ereg(dst_reg)) + EMIT3(0x45, 0x0F, 0xB7); + else + EMIT2(0x0F, 0xB7); + EMIT1(add_2reg(0xC0, dst_reg, dst_reg)); + break; + case 32: + /* emit 'mov eax, eax' to clear upper 32-bits */ + if (is_ereg(dst_reg)) + EMIT1(0x45); + EMIT2(0x89, add_2reg(0xC0, dst_reg, dst_reg)); + break; + case 64: + /* nop */ + break; + } break; /* ST: *(u8*)(dst_reg + off) = imm */ diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile index 275a3a8..e970320 100644 --- a/arch/x86/vdso/Makefile +++ b/arch/x86/vdso/Makefile @@ -51,7 +51,7 @@ VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \ $(obj)/vdso64.so.dbg: $(src)/vdso.lds $(vobjs) FORCE $(call if_changed,vdso) -HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi +HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi -I$(srctree)/arch/x86/include/uapi hostprogs-y += vdso2c quiet_cmd_vdso2c = VDSO2C $@ |
