summaryrefslogtreecommitdiffstats
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig1
-rw-r--r--arch/x86/boot/compressed/Makefile5
-rw-r--r--arch/x86/boot/compressed/eboot.c26
-rw-r--r--arch/x86/crypto/Makefile2
-rw-r--r--arch/x86/crypto/aes-i586-asm_32.S15
-rw-r--r--arch/x86/crypto/aes-x86_64-asm_64.S30
-rw-r--r--arch/x86/crypto/aesni-intel_asm.S23
-rw-r--r--arch/x86/crypto/blowfish-x86_64-asm_64.S39
-rw-r--r--arch/x86/crypto/camellia-aesni-avx-asm_64.S38
-rw-r--r--arch/x86/crypto/camellia-x86_64-asm_64.S50
-rw-r--r--arch/x86/crypto/cast5-avx-x86_64-asm_64.S48
-rw-r--r--arch/x86/crypto/cast6-avx-x86_64-asm_64.S35
-rw-r--r--arch/x86/crypto/crc32-pclmul_asm.S246
-rw-r--r--arch/x86/crypto/crc32-pclmul_glue.c201
-rw-r--r--arch/x86/crypto/crc32c-pcl-intel-asm_64.S8
-rw-r--r--arch/x86/crypto/ghash-clmulni-intel_asm.S4
-rw-r--r--arch/x86/crypto/salsa20-i586-asm_32.S28
-rw-r--r--arch/x86/crypto/salsa20-x86_64-asm_64.S28
-rw-r--r--arch/x86/crypto/salsa20_glue.c5
-rw-r--r--arch/x86/crypto/serpent-avx-x86_64-asm_64.S35
-rw-r--r--arch/x86/crypto/serpent-sse2-i586-asm_32.S20
-rw-r--r--arch/x86/crypto/serpent-sse2-x86_64-asm_64.S20
-rw-r--r--arch/x86/crypto/sha1_ssse3_asm.S10
-rw-r--r--arch/x86/crypto/twofish-avx-x86_64-asm_64.S35
-rw-r--r--arch/x86/crypto/twofish-i586-asm_32.S11
-rw-r--r--arch/x86/crypto/twofish-x86_64-asm_64-3way.S20
-rw-r--r--arch/x86/crypto/twofish-x86_64-asm_64.S11
-rw-r--r--arch/x86/ia32/ia32_aout.c6
-rw-r--r--arch/x86/ia32/sys_ia32.c5
-rw-r--r--arch/x86/include/asm/bootparam_utils.h20
-rw-r--r--arch/x86/include/asm/efi.h9
-rw-r--r--arch/x86/include/asm/ftrace.h24
-rw-r--r--arch/x86/include/asm/kprobes.h1
-rw-r--r--arch/x86/include/asm/kvm_host.h4
-rw-r--r--arch/x86/include/asm/pci.h3
-rw-r--r--arch/x86/include/asm/pci_x86.h1
-rw-r--r--arch/x86/include/asm/sys_ia32.h1
-rw-r--r--arch/x86/include/asm/syscall.h4
-rw-r--r--arch/x86/include/asm/thread_info.h1
-rw-r--r--arch/x86/include/uapi/asm/msr-index.h1
-rw-r--r--arch/x86/kernel/apic/apic.c2
-rw-r--r--arch/x86/kernel/cpu/amd.c3
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c2
-rw-r--r--arch/x86/kernel/cpu/mcheck/p5.c2
-rw-r--r--arch/x86/kernel/cpu/mcheck/winchip.c2
-rw-r--r--arch/x86/kernel/cpu/mtrr/generic.c2
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c27
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_ds.c10
-rw-r--r--arch/x86/kernel/cpuid.c4
-rw-r--r--arch/x86/kernel/dumpstack.c2
-rw-r--r--arch/x86/kernel/head.c53
-rw-r--r--arch/x86/kernel/head_64.S4
-rw-r--r--arch/x86/kernel/kprobes/core.c13
-rw-r--r--arch/x86/kernel/microcode_intel_early.c30
-rw-r--r--arch/x86/kernel/msr.c9
-rw-r--r--arch/x86/kernel/nmi.c1
-rw-r--r--arch/x86/kernel/pvclock.c2
-rw-r--r--arch/x86/kernel/setup.c26
-rw-r--r--arch/x86/kernel/smpboot.c3
-rw-r--r--arch/x86/kvm/lapic.c2
-rw-r--r--arch/x86/kvm/mmu.c26
-rw-r--r--arch/x86/kvm/x86.c69
-rw-r--r--arch/x86/lib/usercopy_64.c4
-rw-r--r--arch/x86/mm/fault.c8
-rw-r--r--arch/x86/mm/init.c5
-rw-r--r--arch/x86/mm/numa.c14
-rw-r--r--arch/x86/mm/pageattr.c50
-rw-r--r--arch/x86/mm/pat.c7
-rw-r--r--arch/x86/mm/srat.c125
-rw-r--r--arch/x86/pci/acpi.c9
-rw-r--r--arch/x86/pci/common.c1
-rw-r--r--arch/x86/pci/i386.c185
-rw-r--r--arch/x86/pci/legacy.c2
-rw-r--r--arch/x86/pci/numaq_32.c2
-rw-r--r--arch/x86/platform/efi/efi.c10
-rw-r--r--arch/x86/power/cpu.c2
-rw-r--r--arch/x86/syscalls/syscall_32.tbl6
77 files changed, 1127 insertions, 671 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 6a938337031..70c0f3da047 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -112,6 +112,7 @@ config X86
select GENERIC_STRNLEN_USER
select HAVE_CONTEXT_TRACKING if X86_64
select HAVE_IRQ_TIME_ACCOUNTING
+ select VIRT_TO_BUS
select MODULES_USE_ELF_REL if X86_32
select MODULES_USE_ELF_RELA if X86_64
select CLONE_BACKWARDS if X86_32
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 8a84501acb1..5ef205c5f37 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -4,7 +4,7 @@
# create a compressed vmlinux image from the original vmlinux
#
-targets := vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma vmlinux.bin.xz vmlinux.bin.lzo head_$(BITS).o misc.o string.o cmdline.o early_serial_console.o piggy.o
+targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma vmlinux.bin.xz vmlinux.bin.lzo
KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2
KBUILD_CFLAGS += -fno-strict-aliasing -fPIC
@@ -29,7 +29,6 @@ VMLINUX_OBJS = $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o \
$(obj)/piggy.o
$(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone
-$(obj)/efi_stub_$(BITS).o: KBUILD_CLFAGS += -fshort-wchar -mno-red-zone
ifeq ($(CONFIG_EFI_STUB), y)
VMLINUX_OBJS += $(obj)/eboot.o $(obj)/efi_stub_$(BITS).o
@@ -43,7 +42,7 @@ OBJCOPYFLAGS_vmlinux.bin := -R .comment -S
$(obj)/vmlinux.bin: vmlinux FORCE
$(call if_changed,objcopy)
-targets += vmlinux.bin.all vmlinux.relocs
+targets += $(patsubst $(obj)/%,%,$(VMLINUX_OBJS)) vmlinux.bin.all vmlinux.relocs
CMD_RELOCS = arch/x86/tools/relocs
quiet_cmd_relocs = RELOCS $@
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index f8fa41190c3..c205035a6b9 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -19,23 +19,28 @@
static efi_system_table_t *sys_table;
+static void efi_char16_printk(efi_char16_t *str)
+{
+ struct efi_simple_text_output_protocol *out;
+
+ out = (struct efi_simple_text_output_protocol *)sys_table->con_out;
+ efi_call_phys2(out->output_string, out, str);
+}
+
static void efi_printk(char *str)
{
char *s8;
for (s8 = str; *s8; s8++) {
- struct efi_simple_text_output_protocol *out;
efi_char16_t ch[2] = { 0 };
ch[0] = *s8;
- out = (struct efi_simple_text_output_protocol *)sys_table->con_out;
-
if (*s8 == '\n') {
efi_char16_t nl[2] = { '\r', 0 };
- efi_call_phys2(out->output_string, out, nl);
+ efi_char16_printk(nl);
}
- efi_call_phys2(out->output_string, out, ch);
+ efi_char16_printk(ch);
}
}
@@ -709,7 +714,12 @@ static efi_status_t handle_ramdisks(efi_loaded_image_t *image,
if ((u8 *)p >= (u8 *)filename_16 + sizeof(filename_16))
break;
- *p++ = *str++;
+ if (*str == '/') {
+ *p++ = '\\';
+ *str++;
+ } else {
+ *p++ = *str++;
+ }
}
*p = '\0';
@@ -737,7 +747,9 @@ static efi_status_t handle_ramdisks(efi_loaded_image_t *image,
status = efi_call_phys5(fh->open, fh, &h, filename_16,
EFI_FILE_MODE_READ, (u64)0);
if (status != EFI_SUCCESS) {
- efi_printk("Failed to open initrd file\n");
+ efi_printk("Failed to open initrd file: ");
+ efi_char16_printk(filename_16);
+ efi_printk("\n");
goto close_handles;
}
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index e0ca7c9ac38..63947a8f9f0 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -27,6 +27,7 @@ obj-$(CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL) += ghash-clmulni-intel.o
obj-$(CONFIG_CRYPTO_CRC32C_INTEL) += crc32c-intel.o
obj-$(CONFIG_CRYPTO_SHA1_SSSE3) += sha1-ssse3.o
+obj-$(CONFIG_CRYPTO_CRC32_PCLMUL) += crc32-pclmul.o
aes-i586-y := aes-i586-asm_32.o aes_glue.o
twofish-i586-y := twofish-i586-asm_32.o twofish_glue.o
@@ -52,3 +53,4 @@ ghash-clmulni-intel-y := ghash-clmulni-intel_asm.o ghash-clmulni-intel_glue.o
sha1-ssse3-y := sha1_ssse3_asm.o sha1_ssse3_glue.o
crc32c-intel-y := crc32c-intel_glue.o
crc32c-intel-$(CONFIG_CRYPTO_CRC32C_X86_64) += crc32c-pcl-intel-asm_64.o
+crc32-pclmul-y := crc32-pclmul_asm.o crc32-pclmul_glue.o
diff --git a/arch/x86/crypto/aes-i586-asm_32.S b/arch/x86/crypto/aes-i586-asm_32.S
index b949ec2f9af..2849dbc59e1 100644
--- a/arch/x86/crypto/aes-i586-asm_32.S
+++ b/arch/x86/crypto/aes-i586-asm_32.S
@@ -36,6 +36,7 @@
.file "aes-i586-asm.S"
.text
+#include <linux/linkage.h>
#include <asm/asm-offsets.h>
#define tlen 1024 // length of each of 4 'xor' arrays (256 32-bit words)
@@ -219,14 +220,10 @@
// AES (Rijndael) Encryption Subroutine
/* void aes_enc_blk(struct crypto_aes_ctx *ctx, u8 *out_blk, const u8 *in_blk) */
-.global aes_enc_blk
-
.extern crypto_ft_tab
.extern crypto_fl_tab
-.align 4
-
-aes_enc_blk:
+ENTRY(aes_enc_blk)
push %ebp
mov ctx(%esp),%ebp
@@ -290,18 +287,15 @@ aes_enc_blk:
mov %r0,(%ebp)
pop %ebp
ret
+ENDPROC(aes_enc_blk)
// AES (Rijndael) Decryption Subroutine
/* void aes_dec_blk(struct crypto_aes_ctx *ctx, u8 *out_blk, const u8 *in_blk) */
-.global aes_dec_blk
-
.extern crypto_it_tab
.extern crypto_il_tab
-.align 4
-
-aes_dec_blk:
+ENTRY(aes_dec_blk)
push %ebp
mov ctx(%esp),%ebp
@@ -365,3 +359,4 @@ aes_dec_blk:
mov %r0,(%ebp)
pop %ebp
ret
+ENDPROC(aes_dec_blk)
diff --git a/arch/x86/crypto/aes-x86_64-asm_64.S b/arch/x86/crypto/aes-x86_64-asm_64.S
index 5b577d5a059..91056554716 100644
--- a/arch/x86/crypto/aes-x86_64-asm_64.S
+++ b/arch/x86/crypto/aes-x86_64-asm_64.S
@@ -15,6 +15,7 @@
.text
+#include <linux/linkage.h>
#include <asm/asm-offsets.h>
#define R1 %rax
@@ -49,10 +50,8 @@
#define R11 %r11
#define prologue(FUNC,KEY,B128,B192,r1,r2,r3,r4,r5,r6,r7,r8,r9,r10,r11) \
- .global FUNC; \
- .type FUNC,@function; \
- .align 8; \
-FUNC: movq r1,r2; \
+ ENTRY(FUNC); \
+ movq r1,r2; \
movq r3,r4; \
leaq KEY+48(r8),r9; \
movq r10,r11; \
@@ -71,14 +70,15 @@ FUNC: movq r1,r2; \
je B192; \
leaq 32(r9),r9;
-#define epilogue(r1,r2,r3,r4,r5,r6,r7,r8,r9) \
+#define epilogue(FUNC,r1,r2,r3,r4,r5,r6,r7,r8,r9) \
movq r1,r2; \
movq r3,r4; \
movl r5 ## E,(r9); \
movl r6 ## E,4(r9); \
movl r7 ## E,8(r9); \
movl r8 ## E,12(r9); \
- ret;
+ ret; \
+ ENDPROC(FUNC);
#define round(TAB,OFFSET,r1,r2,r3,r4,r5,r6,r7,r8,ra,rb,rc,rd) \
movzbl r2 ## H,r5 ## E; \
@@ -133,7 +133,7 @@ FUNC: movq r1,r2; \
#define entry(FUNC,KEY,B128,B192) \
prologue(FUNC,KEY,B128,B192,R2,R8,R7,R9,R1,R3,R4,R6,R10,R5,R11)
-#define return epilogue(R8,R2,R9,R7,R5,R6,R3,R4,R11)
+#define return(FUNC) epilogue(FUNC,R8,R2,R9,R7,R5,R6,R3,R4,R11)
#define encrypt_round(TAB,OFFSET) \
round(TAB,OFFSET,R1,R2,R3,R4,R5,R6,R7,R10,R5,R6,R3,R4) \
@@ -151,12 +151,12 @@ FUNC: movq r1,r2; \
/* void aes_enc_blk(stuct crypto_tfm *tfm, u8 *out, const u8 *in) */
- entry(aes_enc_blk,0,enc128,enc192)
+ entry(aes_enc_blk,0,.Le128,.Le192)
encrypt_round(crypto_ft_tab,-96)
encrypt_round(crypto_ft_tab,-80)
-enc192: encrypt_round(crypto_ft_tab,-64)
+.Le192: encrypt_round(crypto_ft_tab,-64)
encrypt_round(crypto_ft_tab,-48)
-enc128: encrypt_round(crypto_ft_tab,-32)
+.Le128: encrypt_round(crypto_ft_tab,-32)
encrypt_round(crypto_ft_tab,-16)
encrypt_round(crypto_ft_tab, 0)
encrypt_round(crypto_ft_tab, 16)
@@ -166,16 +166,16 @@ enc128: encrypt_round(crypto_ft_tab,-32)
encrypt_round(crypto_ft_tab, 80)
encrypt_round(crypto_ft_tab, 96)
encrypt_final(crypto_fl_tab,112)
- return
+ return(aes_enc_blk)
/* void aes_dec_blk(struct crypto_tfm *tfm, u8 *out, const u8 *in) */
- entry(aes_dec_blk,240,dec128,dec192)
+ entry(aes_dec_blk,240,.Ld128,.Ld192)
decrypt_round(crypto_it_tab,-96)
decrypt_round(crypto_it_tab,-80)
-dec192: decrypt_round(crypto_it_tab,-64)
+.Ld192: decrypt_round(crypto_it_tab,-64)
decrypt_round(crypto_it_tab,-48)
-dec128: decrypt_round(crypto_it_tab,-32)
+.Ld128: decrypt_round(crypto_it_tab,-32)
decrypt_round(crypto_it_tab,-16)
decrypt_round(crypto_it_tab, 0)
decrypt_round(crypto_it_tab, 16)
@@ -185,4 +185,4 @@ dec128: decrypt_round(crypto_it_tab,-32)
decrypt_round(crypto_it_tab, 80)
decrypt_round(crypto_it_tab, 96)
decrypt_final(crypto_il_tab,112)
- return
+ return(aes_dec_blk)
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index 3470624d783..04b797767b9 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -1262,7 +1262,6 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst
* poly = x^128 + x^127 + x^126 + x^121 + 1
*
*****************************************************************************/
-
ENTRY(aesni_gcm_dec)
push %r12
push %r13
@@ -1437,6 +1436,7 @@ _return_T_done_decrypt:
pop %r13
pop %r12
ret
+ENDPROC(aesni_gcm_dec)
/*****************************************************************************
@@ -1700,10 +1700,12 @@ _return_T_done_encrypt:
pop %r13
pop %r12
ret
+ENDPROC(aesni_gcm_enc)
#endif
+.align 4
_key_expansion_128:
_key_expansion_256a:
pshufd $0b11111111, %xmm1, %xmm1
@@ -1715,6 +1717,8 @@ _key_expansion_256a:
movaps %xmm0, (TKEYP)
add $0x10, TKEYP
ret
+ENDPROC(_key_expansion_128)
+ENDPROC(_key_expansion_256a)
.align 4
_key_expansion_192a:
@@ -1739,6 +1743,7 @@ _key_expansion_192a:
movaps %xmm1, 0x10(TKEYP)
add $0x20, TKEYP
ret
+ENDPROC(_key_expansion_192a)
.align 4
_key_expansion_192b:
@@ -1758,6 +1763,7 @@ _key_expansion_192b:
movaps %xmm0, (TKEYP)
add $0x10, TKEYP
ret
+ENDPROC(_key_expansion_192b)
.align 4
_key_expansion_256b:
@@ -1770,6 +1776,7 @@ _key_expansion_256b:
movaps %xmm2, (TKEYP)
add $0x10, TKEYP
ret
+ENDPROC(_key_expansion_256b)
/*
* int aesni_set_key(struct crypto_aes_ctx *ctx, const u8 *in_key,
@@ -1882,6 +1889,7 @@ ENTRY(aesni_set_key)
popl KEYP
#endif
ret
+ENDPROC(aesni_set_key)
/*
* void aesni_enc(struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src)
@@ -1903,6 +1911,7 @@ ENTRY(aesni_enc)
popl KEYP
#endif
ret
+ENDPROC(aesni_enc)
/*
* _aesni_enc1: internal ABI
@@ -1960,6 +1969,7 @@ _aesni_enc1:
movaps 0x70(TKEYP), KEY
AESENCLAST KEY STATE
ret
+ENDPROC(_aesni_enc1)
/*
* _aesni_enc4: internal ABI
@@ -2068,6 +2078,7 @@ _aesni_enc4:
AESENCLAST KEY STATE3
AESENCLAST KEY STATE4
ret
+ENDPROC(_aesni_enc4)
/*
* void aesni_dec (struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src)
@@ -2090,6 +2101,7 @@ ENTRY(aesni_dec)
popl KEYP
#endif
ret
+ENDPROC(aesni_dec)
/*
* _aesni_dec1: internal ABI
@@ -2147,6 +2159,7 @@ _aesni_dec1:
movaps 0x70(TKEYP), KEY
AESDECLAST KEY STATE
ret
+ENDPROC(_aesni_dec1)
/*
* _aesni_dec4: internal ABI
@@ -2255,6 +2268,7 @@ _aesni_dec4:
AESDECLAST KEY STATE3
AESDECLAST KEY STATE4
ret
+ENDPROC(_aesni_dec4)
/*
* void aesni_ecb_enc(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src,
@@ -2312,6 +2326,7 @@ ENTRY(aesni_ecb_enc)
popl LEN
#endif
ret
+ENDPROC(aesni_ecb_enc)
/*
* void aesni_ecb_dec(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src,
@@ -2370,6 +2385,7 @@ ENTRY(aesni_ecb_dec)
popl LEN
#endif
ret
+ENDPROC(aesni_ecb_dec)
/*
* void aesni_cbc_enc(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src,
@@ -2411,6 +2427,7 @@ ENTRY(aesni_cbc_enc)
popl IVP
#endif
ret
+ENDPROC(aesni_cbc_enc)
/*
* void aesni_cbc_dec(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src,
@@ -2501,6 +2518,7 @@ ENTRY(aesni_cbc_dec)
popl IVP
#endif
ret
+ENDPROC(aesni_cbc_dec)
#ifdef __x86_64__
.align 16
@@ -2527,6 +2545,7 @@ _aesni_inc_init:
MOVQ_R64_XMM TCTR_LOW INC
MOVQ_R64_XMM CTR TCTR_LOW
ret
+ENDPROC(_aesni_inc_init)
/*
* _aesni_inc: internal ABI
@@ -2555,6 +2574,7 @@ _aesni_inc:
movaps CTR, IV
PSHUFB_XMM BSWAP_MASK IV
ret
+ENDPROC(_aesni_inc)
/*
* void aesni_ctr_enc(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src,
@@ -2615,4 +2635,5 @@ ENTRY(aesni_ctr_enc)
movups IV, (IVP)
.Lctr_enc_just_ret:
ret
+ENDPROC(aesni_ctr_enc)
#endif
diff --git a/arch/x86/crypto/blowfish-x86_64-asm_64.S b/arch/x86/crypto/blowfish-x86_64-asm_64.S
index 391d245dc08..246c67006ed 100644
--- a/arch/x86/crypto/blowfish-x86_64-asm_64.S
+++ b/arch/x86/crypto/blowfish-x86_64-asm_64.S
@@ -20,6 +20,8 @@
*
*/
+#include <linux/linkage.h>
+
.file "blowfish-x86_64-asm.S"
.text
@@ -116,11 +118,7 @@
bswapq RX0; \
xorq RX0, (RIO);
-.align 8
-.global __blowfish_enc_blk
-.type __blowfish_enc_blk,@function;
-
-__blowfish_enc_blk:
+ENTRY(__blowfish_enc_blk)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
@@ -148,19 +146,16 @@ __blowfish_enc_blk:
movq %r10, RIO;
test %cl, %cl;
- jnz __enc_xor;
+ jnz .L__enc_xor;
write_block();
ret;
-__enc_xor:
+.L__enc_xor:
xor_block();
ret;
+ENDPROC(__blowfish_enc_blk)
-.align 8
-.global blowfish_dec_blk
-.type blowfish_dec_blk,@function;
-
-blowfish_dec_blk:
+ENTRY(blowfish_dec_blk)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
@@ -189,6 +184,7 @@ blowfish_dec_blk:
movq %r11, %rbp;
ret;
+ENDPROC(blowfish_dec_blk)
/**********************************************************************
4-way blowfish, four blocks parallel
@@ -300,11 +296,7 @@ blowfish_dec_blk:
bswapq RX3; \
xorq RX3, 24(RIO);
-.align 8
-.global __blowfish_enc_blk_4way
-.type __blowfish_enc_blk_4way,@function;
-
-__blowfish_enc_blk_4way:
+ENTRY(__blowfish_enc_blk_4way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
@@ -336,7 +328,7 @@ __blowfish_enc_blk_4way:
movq %r11, RIO;
test %bpl, %bpl;
- jnz __enc_xor4;
+ jnz .L__enc_xor4;
write_block4();
@@ -344,18 +336,15 @@ __blowfish_enc_blk_4way:
popq %rbp;
ret;
-__enc_xor4:
+.L__enc_xor4:
xor_block4();
popq %rbx;
popq %rbp;
ret;
+ENDPROC(__blowfish_enc_blk_4way)
-.align 8
-.global blowfish_dec_blk_4way
-.type blowfish_dec_blk_4way,@function;
-
-blowfish_dec_blk_4way:
+ENTRY(blowfish_dec_blk_4way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
@@ -387,4 +376,4 @@ blowfish_dec_blk_4way:
popq %rbp;
ret;
-
+ENDPROC(blowfish_dec_blk_4way)
diff --git a/arch/x86/crypto/camellia-aesni-avx-asm_64.S b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
index 2306d2e4816..cfc163469c7 100644
--- a/arch/x86/crypto/camellia-aesni-avx-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
@@ -15,6 +15,8 @@
* http://koti.mbnet.fi/axh/crypto/camellia-BSD-1.2.0-aesni1.tar.xz
*/
+#include <linux/linkage.h>
+
#define CAMELLIA_TABLE_BYTE_LEN 272
/* struct camellia_ctx: */
@@ -190,6 +192,7 @@ roundsm16_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd:
%xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, %xmm15,
%rcx, (%r9));
ret;
+ENDPROC(roundsm16_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd)
.align 8
roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab:
@@ -197,6 +200,7 @@ roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab:
%xmm12, %xmm13, %xmm14, %xmm15, %xmm8, %xmm9, %xmm10, %xmm11,
%rax, (%r9));
ret;
+ENDPROC(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
/*
* IN/OUT:
@@ -709,8 +713,6 @@ roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab:
.text
.align 8
-.type __camellia_enc_blk16,@function;
-
__camellia_enc_blk16:
/* input:
* %rdi: ctx, CTX
@@ -793,10 +795,9 @@ __camellia_enc_blk16:
%xmm15, %rax, %rcx, 24);
jmp .Lenc_done;
+ENDPROC(__camellia_enc_blk16)
.align 8
-.type __camellia_dec_blk16,@function;
-
__camellia_dec_blk16:
/* input:
* %rdi: ctx, CTX
@@ -877,12 +878,9 @@ __camellia_dec_blk16:
((key_table + (24) * 8) + 4)(CTX));
jmp .Ldec_max24;
+ENDPROC(__camellia_dec_blk16)
-.align 8
-.global camellia_ecb_enc_16way
-.type camellia_ecb_enc_16way,@function;
-
-camellia_ecb_enc_16way:
+ENTRY(camellia_ecb_enc_16way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst (16 blocks)
@@ -903,12 +901,9 @@ camellia_ecb_enc_16way:
%xmm8, %rsi);
ret;
+ENDPROC(camellia_ecb_enc_16way)
-.align 8
-.global camellia_ecb_dec_16way
-.type camellia_ecb_dec_16way,@function;
-
-camellia_ecb_dec_16way:
+ENTRY(camellia_ecb_dec_16way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst (16 blocks)
@@ -934,12 +929,9 @@ camellia_ecb_dec_16way:
%xmm8, %rsi);
ret;
+ENDPROC(camellia_ecb_dec_16way)
-.align 8
-.global camellia_cbc_dec_16way
-.type camellia_cbc_dec_16way,@function;
-
-camellia_cbc_dec_16way:
+ENTRY(camellia_cbc_dec_16way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst (16 blocks)
@@ -986,6 +978,7 @@ camellia_cbc_dec_16way:
%xmm8, %rsi);
ret;
+ENDPROC(camellia_cbc_dec_16way)
#define inc_le128(x, minus_one, tmp) \
vpcmpeqq minus_one, x, tmp; \
@@ -993,11 +986,7 @@ camellia_cbc_dec_16way:
vpslldq $8, tmp, tmp; \
vpsubq tmp, x, x;
-.align 8
-.global camellia_ctr_16way
-.type camellia_ctr_16way,@function;
-
-camellia_ctr_16way:
+ENTRY(camellia_ctr_16way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst (16 blocks)
@@ -1100,3 +1089,4 @@ camellia_ctr_16way:
%xmm8, %rsi);
ret;
+ENDPROC(camellia_ctr_16way)
diff --git a/arch/x86/crypto/camellia-x86_64-asm_64.S b/arch/x86/crypto/camellia-x86_64-asm_64.S
index 0b3374335fd..310319c601e 100644
--- a/arch/x86/crypto/camellia-x86_64-asm_64.S
+++ b/arch/x86/crypto/camellia-x86_64-asm_64.S
@@ -20,6 +20,8 @@
*
*/
+#include <linux/linkage.h>
+
.file "camellia-x86_64-asm_64.S"
.text
@@ -188,10 +190,7 @@
bswapq RAB0; \
movq RAB0, 4*2(RIO);
-.global __camellia_enc_blk;
-.type __camellia_enc_blk,@function;
-
-__camellia_enc_blk:
+ENTRY(__camellia_enc_blk)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
@@ -214,33 +213,31 @@ __camellia_enc_blk:
movl $24, RT1d; /* max */
cmpb $16, key_length(CTX);
- je __enc_done;
+ je .L__enc_done;
enc_fls(24);
enc_rounds(24);
movl $32, RT1d; /* max */
-__enc_done:
+.L__enc_done:
testb RXORbl, RXORbl;
movq RDST, RIO;
- jnz __enc_xor;
+ jnz .L__enc_xor;
enc_outunpack(mov, RT1);
movq RRBP, %rbp;
ret;
-__enc_xor:
+.L__enc_xor:
enc_outunpack(xor, RT1);
movq RRBP, %rbp;
ret;
+ENDPROC(__camellia_enc_blk)
-.global camellia_dec_blk;
-.type camellia_dec_blk,@function;
-
-camellia_dec_blk:
+ENTRY(camellia_dec_blk)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
@@ -258,12 +255,12 @@ camellia_dec_blk:
dec_inpack(RT2);
cmpb $24, RT2bl;
- je __dec_rounds16;
+ je .L__dec_rounds16;
dec_rounds(24);
dec_fls(24);
-__dec_rounds16:
+.L__dec_rounds16:
dec_rounds(16);
dec_fls(16);
dec_rounds(8);
@@ -276,6 +273,7 @@ __dec_rounds16:
movq RRBP, %rbp;
ret;
+ENDPROC(camellia_dec_blk)
/**********************************************************************
2-way camellia
@@ -426,10 +424,7 @@ __dec_rounds16:
bswapq RAB1; \
movq RAB1, 12*2(RIO);
-.global __camellia_enc_blk_2way;
-.type __camellia_enc_blk_2way,@function;
-
-__camellia_enc_blk_2way:
+ENTRY(__camellia_enc_blk_2way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
@@ -453,16 +448,16 @@ __camellia_enc_blk_2way:
movl $24, RT2d; /* max */
cmpb $16, key_length(CTX);
- je __enc2_done;
+ je .L__enc2_done;
enc_fls2(24);
enc_rounds2(24);
movl $32, RT2d; /* max */
-__enc2_done:
+.L__enc2_done:
test RXORbl, RXORbl;
movq RDST, RIO;
- jnz __enc2_xor;
+ jnz .L__enc2_xor;
enc_outunpack2(mov, RT2);
@@ -470,17 +465,15 @@ __enc2_done:
popq %rbx;
ret;
-__enc2_xor:
+.L__enc2_xor:
enc_outunpack2(xor, RT2);
movq RRBP, %rbp;
popq %rbx;
ret;
+ENDPROC(__camellia_enc_blk_2way)
-.global camellia_dec_blk_2way;
-.type camellia_dec_blk_2way,@function;
-
-camellia_dec_blk_2way:
+ENTRY(camellia_dec_blk_2way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
@@ -499,12 +492,12 @@ camellia_dec_blk_2way:
dec_inpack2(RT2);
cmpb $24, RT2bl;
- je __dec2_rounds16;
+ je .L__dec2_rounds16;
dec_rounds2(24);
dec_fls2(24);
-__dec2_rounds16:
+.L__dec2_rounds16:
dec_rounds2(16);
dec_fls2(16);
dec_rounds2(8);
@@ -518,3 +511,4 @@ __dec2_rounds16:
movq RRBP, %rbp;
movq RXOR, %rbx;
ret;
+ENDPROC(camellia_dec_blk_2way)
diff --git a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
index 15b00ac7cbd..c35fd5d6ecd 100644
--- a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
@@ -23,6 +23,8 @@
*
*/
+#include <linux/linkage.h>
+
.file "cast5-avx-x86_64-asm_64.S"
.extern cast_s1
@@ -211,8 +213,6 @@
.text
.align 16
-.type __cast5_enc_blk16,@function;
-
__cast5_enc_blk16:
/* input:
* %rdi: ctx, CTX
@@ -263,14 +263,14 @@ __cast5_enc_blk16:
movzbl rr(CTX), %eax;
testl %eax, %eax;
- jnz __skip_enc;
+ jnz .L__skip_enc;
round(RL, RR, 12, 1);
round(RR, RL, 13, 2);
round(RL, RR, 14, 3);
round(RR, RL, 15, 1);
-__skip_enc:
+.L__skip_enc:
popq %rbx;
popq %rbp;
@@ -282,10 +282,9 @@ __skip_enc:
outunpack_blocks(RR4, RL4, RTMP, RX, RKM);
ret;
+ENDPROC(__cast5_enc_blk16)
.align 16
-.type __cast5_dec_blk16,@function;
-
__cast5_dec_blk16:
/* input:
* %rdi: ctx, CTX
@@ -323,14 +322,14 @@ __cast5_dec_blk16:
movzbl rr(CTX), %eax;
testl %eax, %eax;
- jnz __skip_dec;
+ jnz .L__skip_dec;
round(RL, RR, 15, 1);
round(RR, RL, 14, 3);
round(RL, RR, 13, 2);
round(RR, RL, 12, 1);
-__dec_tail:
+.L__dec_tail:
round(RL, RR, 11, 3);
round(RR, RL, 10, 2);
round(RL, RR, 9, 1);
@@ -355,15 +354,12 @@ __dec_tail:
ret;
-__skip_dec:
+.L__skip_dec:
vpsrldq $4, RKR, RKR;
- jmp __dec_tail;
+ jmp .L__dec_tail;
+ENDPROC(__cast5_dec_blk16)
-.align 16
-.global cast5_ecb_enc_16way
-.type cast5_ecb_enc_16way,@function;
-
-cast5_ecb_enc_16way:
+ENTRY(cast5_ecb_enc_16way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
@@ -393,12 +389,9 @@ cast5_ecb_enc_16way:
vmovdqu RL4, (7*4*4)(%r11);
ret;
+ENDPROC(cast5_ecb_enc_16way)
-.align 16
-.global cast5_ecb_dec_16way
-.type cast5_ecb_dec_16way,@function;
-
-cast5_ecb_dec_16way:
+ENTRY(cast5_ecb_dec_16way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
@@ -428,12 +421,9 @@ cast5_ecb_dec_16way:
vmovdqu RL4, (7*4*4)(%r11);
ret;
+ENDPROC(cast5_ecb_dec_16way)
-.align 16
-.global cast5_cbc_dec_16way
-.type cast5_cbc_dec_16way,@function;
-
-cast5_cbc_dec_16way:
+ENTRY(cast5_cbc_dec_16way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
@@ -480,12 +470,9 @@ cast5_cbc_dec_16way:
popq %r12;
ret;
+ENDPROC(cast5_cbc_dec_16way)
-.align 16
-.global cast5_ctr_16way
-.type cast5_ctr_16way,@function;
-
-cast5_ctr_16way:
+ENTRY(cast5_ctr_16way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
@@ -556,3 +543,4 @@ cast5_ctr_16way:
popq %r12;
ret;
+ENDPROC(cast5_ctr_16way)
diff --git a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
index 2569d0da841..f93b6105a0c 100644
--- a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
@@ -23,6 +23,7 @@
*
*/
+#include <linux/linkage.h>
#include "glue_helper-asm-avx.S"
.file "cast6-avx-x86_64-asm_64.S"
@@ -250,8 +251,6 @@
.text
.align 8
-.type __cast6_enc_blk8,@function;
-
__cast6_enc_blk8:
/* input:
* %rdi: ctx, CTX
@@ -295,10 +294,9 @@ __cast6_enc_blk8:
outunpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
ret;
+ENDPROC(__cast6_enc_blk8)
.align 8
-.type __cast6_dec_blk8,@function;
-
__cast6_dec_blk8:
/* input:
* %rdi: ctx, CTX
@@ -341,12 +339,9 @@ __cast6_dec_blk8:
outunpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
ret;
+ENDPROC(__cast6_dec_blk8)
-.align 8
-.global cast6_ecb_enc_8way
-.type cast6_ecb_enc_8way,@function;
-
-cast6_ecb_enc_8way:
+ENTRY(cast6_ecb_enc_8way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
@@ -362,12 +357,9 @@ cast6_ecb_enc_8way:
store_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
ret;
+ENDPROC(cast6_ecb_enc_8way)
-.align 8
-.global cast6_ecb_dec_8way
-.type cast6_ecb_dec_8way,@function;
-
-cast6_ecb_dec_8way:
+ENTRY(cast6_ecb_dec_8way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
@@ -383,12 +375,9 @@ cast6_ecb_dec_8way:
store_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
ret;
+ENDPROC(cast6_ecb_dec_8way)
-.align 8
-.global cast6_cbc_dec_8way
-.type cast6_cbc_dec_8way,@function;
-
-cast6_cbc_dec_8way:
+ENTRY(cast6_cbc_dec_8way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
@@ -409,12 +398,9 @@ cast6_cbc_dec_8way:
popq %r12;
ret;
+ENDPROC(cast6_cbc_dec_8way)
-.align 8
-.global cast6_ctr_8way
-.type cast6_ctr_8way,@function;
-
-cast6_ctr_8way:
+ENTRY(cast6_ctr_8way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
@@ -437,3 +423,4 @@ cast6_ctr_8way:
popq %r12;
ret;
+ENDPROC(cast6_ctr_8way)
diff --git a/arch/x86/crypto/crc32-pclmul_asm.S b/arch/x86/crypto/crc32-pclmul_asm.S
new file mode 100644
index 00000000000..c8335014a04
--- /dev/null
+++ b/arch/x86/crypto/crc32-pclmul_asm.S
@@ -0,0 +1,246 @@
+/* GPL HEADER START
+ *
+ * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 only,
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License version 2 for more details (a copy is included
+ * in the LICENSE file that accompanied this code).
+ *
+ * You should have received a copy of the GNU General Public License
+ * version 2 along with this program; If not, see http://www.gnu.org/licenses
+ *
+ * Please visit http://www.xyratex.com/contact if you need additional
+ * information or have any questions.
+ *
+ * GPL HEADER END
+ */
+
+/*
+ * Copyright 2012 Xyratex Technology Limited
+ *
+ * Using hardware provided PCLMULQDQ instruction to accelerate the CRC32
+ * calculation.
+ * CRC32 polynomial:0x04c11db7(BE)/0xEDB88320(LE)
+ * PCLMULQDQ is a new instruction in Intel SSE4.2, the reference can be found
+ * at:
+ * http://www.intel.com/products/processor/manuals/
+ * Intel(R) 64 and IA-32 Architectures Software Developer's Manual
+ * Volume 2B: Instruction Set Reference, N-Z
+ *
+ * Authors: Gregory Prestas <Gregory_Prestas@us.xyratex.com>
+ * Alexander Boyko <Alexander_Boyko@xyratex.com>
+ */
+
+#include <linux/linkage.h>
+#include <asm/inst.h>
+
+
+.align 16
+/*
+ * [x4*128+32 mod P(x) << 32)]' << 1 = 0x154442bd4
+ * #define CONSTANT_R1 0x154442bd4LL
+ *
+ * [(x4*128-32 mod P(x) << 32)]' << 1 = 0x1c6e41596
+ * #define CONSTANT_R2 0x1c6e41596LL
+ */
+.Lconstant_R2R1:
+ .octa 0x00000001c6e415960000000154442bd4
+/*
+ * [(x128+32 mod P(x) << 32)]' << 1 = 0x1751997d0
+ * #define CONSTANT_R3 0x1751997d0LL
+ *
+ * [(x128-32 mod P(x) << 32)]' << 1 = 0x0ccaa009e
+ * #define CONSTANT_R4 0x0ccaa009eLL
+ */
+.Lconstant_R4R3:
+ .octa 0x00000000ccaa009e00000001751997d0
+/*
+ * [(x64 mod P(x) << 32)]' << 1 = 0x163cd6124
+ * #define CONSTANT_R5 0x163cd6124LL
+ */
+.Lconstant_R5:
+ .octa 0x00000000000000000000000163cd6124
+.Lconstant_mask32:
+ .octa 0x000000000000000000000000FFFFFFFF
+/*
+ * #define CRCPOLY_TRUE_LE_FULL 0x1DB710641LL
+ *
+ * Barrett Reduction constant (u64`) = u` = (x**64 / P(x))` = 0x1F7011641LL
+ * #define CONSTANT_RU 0x1F7011641LL
+ */
+.Lconstant_RUpoly:
+ .octa 0x00000001F701164100000001DB710641
+
+#define CONSTANT %xmm0
+
+#ifdef __x86_64__
+#define BUF %rdi
+#define LEN %rsi
+#define CRC %edx
+#else
+#define BUF %eax
+#define LEN %edx
+#define CRC %ecx
+#endif
+
+
+
+.text
+/**
+ * Calculate crc32
+ * BUF - buffer (16 bytes aligned)
+ * LEN - sizeof buffer (16 bytes aligned), LEN should be grater than 63
+ * CRC - initial crc32
+ * return %eax crc32
+ * uint crc32_pclmul_le_16(unsigned char const *buffer,
+ * size_t len, uint crc32)
+ */
+.globl crc32_pclmul_le_16
+.align 4, 0x90
+crc32_pclmul_le_16:/* buffer and buffer size are 16 bytes aligned */
+ movdqa (BUF), %xmm1
+ movdqa 0x10(BUF), %xmm2
+ movdqa 0x20(BUF), %xmm3
+ movdqa 0x30(BUF), %xmm4
+ movd CRC, CONSTANT
+ pxor CONSTANT, %xmm1
+ sub $0x40, LEN
+ add $0x40, BUF
+#ifndef __x86_64__
+ /* This is for position independent code(-fPIC) support for 32bit */
+ call delta
+delta:
+ pop %ecx
+#endif
+ cmp $0x40, LEN
+ jb less_64
+
+#ifdef __x86_64__
+ movdqa .Lconstant_R2R1(%rip), CONSTANT
+#else
+ movdqa .Lconstant_R2R1 - delta(%ecx), CONSTANT
+#endif
+
+loop_64:/* 64 bytes Full cache line folding */
+ prefetchnta 0x40(BUF)
+ movdqa %xmm1, %xmm5
+ movdqa %xmm2, %xmm6
+ movdqa %xmm3, %xmm7
+#ifdef __x86_64__
+ movdqa %xmm4, %xmm8
+#endif
+ PCLMULQDQ 00, CONSTANT, %xmm1
+ PCLMULQDQ 00, CONSTANT, %xmm2
+ PCLMULQDQ 00, CONSTANT, %xmm3
+#ifdef __x86_64__
+ PCLMULQDQ 00, CONSTANT, %xmm4
+#endif
+ PCLMULQDQ 0x11, CONSTANT, %xmm5
+ PCLMULQDQ 0x11, CONSTANT, %xmm6
+ PCLMULQDQ 0x11, CONSTANT, %xmm7
+#ifdef __x86_64__
+ PCLMULQDQ 0x11, CONSTANT, %xmm8
+#endif
+ pxor %xmm5, %xmm1
+ pxor %xmm6, %xmm2
+ pxor %xmm7, %xmm3
+#ifdef __x86_64__
+ pxor %xmm8, %xmm4
+#else
+ /* xmm8 unsupported for x32 */
+ movdqa %xmm4, %xmm5
+ PCLMULQDQ 00, CONSTANT, %xmm4
+ PCLMULQDQ 0x11, CONSTANT, %xmm5
+ pxor %xmm5, %xmm4
+#endif
+
+ pxor (BUF), %xmm1
+ pxor 0x10(BUF), %xmm2
+ pxor 0x20(BUF), %xmm3
+ pxor 0x30(BUF), %xmm4
+
+ sub $0x40, LEN
+ add $0x40, BUF
+ cmp $0x40, LEN
+ jge loop_64
+less_64:/* Folding cache line into 128bit */
+#ifdef __x86_64__
+ movdqa .Lconstant_R4R3(%rip), CONSTANT
+#else
+ movdqa .Lconstant_R4R3 - delta(%ecx), CONSTANT
+#endif
+ prefetchnta (BUF)
+
+ movdqa %xmm1, %xmm5
+ PCLMULQDQ 0x00, CONSTANT, %xmm1
+ PCLMULQDQ 0x11, CONSTANT, %xmm5
+ pxor %xmm5, %xmm1
+ pxor %xmm2, %xmm1
+
+ movdqa %xmm1, %xmm5
+ PCLMULQDQ 0x00, CONSTANT, %xmm1
+ PCLMULQDQ 0x11, CONSTANT, %xmm5
+ pxor %xmm5, %xmm1
+ pxor %xmm3, %xmm1
+
+ movdqa %xmm1, %xmm5
+ PCLMULQDQ 0x00, CONSTANT, %xmm1
+ PCLMULQDQ 0x11, CONSTANT, %xmm5
+ pxor %xmm5, %xmm1
+ pxor %xmm4, %xmm1
+
+ cmp $0x10, LEN
+ jb fold_64
+loop_16:/* Folding rest buffer into 128bit */
+ movdqa %xmm1, %xmm5
+ PCLMULQDQ 0x00, CONSTANT, %xmm1
+ PCLMULQDQ 0x11, CONSTANT, %xmm5
+ pxor %xmm5, %xmm1
+ pxor (BUF), %xmm1
+ sub $0x10, LEN
+ add $0x10, BUF
+ cmp $0x10, LEN
+ jge loop_16
+
+fold_64:
+ /* perform the last 64 bit fold, also adds 32 zeroes
+ * to the input stream */
+ PCLMULQDQ 0x01, %xmm1, CONSTANT /* R4 * xmm1.low */
+ psrldq $0x08, %xmm1
+ pxor CONSTANT, %xmm1
+
+ /* final 32-bit fold */
+ movdqa %xmm1, %xmm2
+#ifdef __x86_64__
+ movdqa .Lconstant_R5(%rip), CONSTANT
+ movdqa .Lconstant_mask32(%rip), %xmm3
+#else
+ movdqa .Lconstant_R5 - delta(%ecx), CONSTANT
+ movdqa .Lconstant_mask32 - delta(%ecx), %xmm3
+#endif
+ psrldq $0x04, %xmm2
+ pand %xmm3, %xmm1
+ PCLMULQDQ 0x00, CONSTANT, %xmm1
+ pxor %xmm2, %xmm1
+
+ /* Finish up with the bit-reversed barrett reduction 64 ==> 32 bits */
+#ifdef __x86_64__
+ movdqa .Lconstant_RUpoly(%rip), CONSTANT
+#else
+ movdqa .Lconstant_RUpoly - delta(%ecx), CONSTANT
+#endif
+ movdqa %xmm1, %xmm2
+ pand %xmm3, %xmm1
+ PCLMULQDQ 0x10, CONSTANT, %xmm1
+ pand %xmm3, %xmm1
+ PCLMULQDQ 0x00, CONSTANT, %xmm1
+ pxor %xmm2, %xmm1
+ pextrd $0x01, %xmm1, %eax
+
+ ret
diff --git a/arch/x86/crypto/crc32-pclmul_glue.c b/arch/x86/crypto/crc32-pclmul_glue.c
new file mode 100644
index 00000000000..9d014a74ef9
--- /dev/null
+++ b/arch/x86/crypto/crc32-pclmul_glue.c
@@ -0,0 +1,201 @@
+/* GPL HEADER START
+ *
+ * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 only,
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License version 2 for more details (a copy is included
+ * in the LICENSE file that accompanied this code).
+ *
+ * You should have received a copy of the GNU General Public License
+ * version 2 along with this program; If not, see http://www.gnu.org/licenses
+ *
+ * Please visit http://www.xyratex.com/contact if you need additional
+ * information or have any questions.
+ *
+ * GPL HEADER END
+ */
+
+/*
+ * Copyright 2012 Xyratex Technology Limited
+ *
+ * Wrappers for kernel crypto shash api to pclmulqdq crc32 imlementation.
+ */
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/crc32.h>
+#include <crypto/internal/hash.h>
+
+#include <asm/cpufeature.h>
+#include <asm/cpu_device_id.h>
+#include <asm/i387.h>
+
+#define CHKSUM_BLOCK_SIZE 1
+#define CHKSUM_DIGEST_SIZE 4
+
+#define PCLMUL_MIN_LEN 64L /* minimum size of buffer
+ * for crc32_pclmul_le_16 */
+#define SCALE_F 16L /* size of xmm register */
+#define SCALE_F_MASK (SCALE_F - 1)
+
+u32 crc32_pclmul_le_16(unsigned char const *buffer, size_t len, u32 crc32);
+
+static u32 __attribute__((pure))
+ crc32_pclmul_le(u32 crc, unsigned char const *p, size_t len)
+{
+ unsigned int iquotient;
+ unsigned int iremainder;
+ unsigned int prealign;
+
+ if (len < PCLMUL_MIN_LEN + SCALE_F_MASK || !irq_fpu_usable())
+ return crc32_le(crc, p, len);
+
+ if ((long)p & SCALE_F_MASK) {
+ /* align p to 16 byte */
+ prealign = SCALE_F - ((long)p & SCALE_F_MASK);
+
+ crc = crc32_le(crc, p, prealign);
+ len -= prealign;
+ p = (unsigned char *)(((unsigned long)p + SCALE_F_MASK) &
+ ~SCALE_F_MASK);
+ }
+ iquotient = len & (~SCALE_F_MASK);
+ iremainder = len & SCALE_F_MASK;
+
+ kernel_fpu_begin();
+ crc = crc32_pclmul_le_16(p, iquotient, crc);
+ kernel_fpu_end();
+
+ if (iremainder)
+ crc = crc32_le(crc, p + iquotient, iremainder);
+
+ return crc;
+}
+
+static int crc32_pclmul_cra_init(struct crypto_tfm *tfm)
+{
+ u32 *key = crypto_tfm_ctx(tfm);
+
+ *key = 0;
+
+ return 0;
+}
+
+static int crc32_pclmul_setkey(struct crypto_shash *hash, const u8 *key,
+ unsigned int keylen)
+{
+ u32 *mctx = crypto_shash_ctx(hash);
+
+ if (keylen != sizeof(u32)) {
+ crypto_shash_set_flags(hash, CRYPTO_TFM_RES_BAD_KEY_LEN);
+ return -EINVAL;
+ }
+ *mctx = le32_to_cpup((__le32 *)key);
+ return 0;
+}
+
+static int crc32_pclmul_init(struct shash_desc *desc)
+{
+ u32 *mctx = crypto_shash_ctx(desc->tfm);
+ u32 *crcp = shash_desc_ctx(desc);
+
+ *crcp = *mctx;
+
+ return 0;
+}
+
+static int crc32_pclmul_update(struct shash_desc *desc, const u8 *data,
+ unsigned int len)
+{
+ u32 *crcp = shash_desc_ctx(desc);
+
+ *crcp = crc32_pclmul_le(*crcp, data, len);
+ return 0;
+}
+
+/* No final XOR 0xFFFFFFFF, like crc32_le */
+static int __crc32_pclmul_finup(u32 *crcp, const u8 *data, unsigned int len,
+ u8 *out)
+{
+ *(__le32 *)out = cpu_to_le32(crc32_pclmul_le(*crcp, data, len));
+ return 0;
+}
+
+static int crc32_pclmul_finup(struct shash_desc *desc, const u8 *data,
+ unsigned int len, u8 *out)
+{
+ return __crc32_pclmul_finup(shash_desc_ctx(desc), data, len, out);
+}
+
+static int crc32_pclmul_final(struct shash_desc *desc, u8 *out)
+{
+ u32 *crcp = shash_desc_ctx(desc);
+
+ *(__le32 *)out = cpu_to_le32p(crcp);
+ return 0;
+}
+
+static int crc32_pclmul_digest(struct shash_desc *desc, const u8 *data,
+ unsigned int len, u8 *out)
+{
+ return __crc32_pclmul_finup(crypto_shash_ctx(desc->tfm), data, len,
+ out);
+}
+
+static struct shash_alg alg = {
+ .setkey = crc32_pclmul_setkey,
+ .init = crc32_pclmul_init,
+ .update = crc32_pclmul_update,
+ .final = crc32_pclmul_final,
+ .finup = crc32_pclmul_finup,
+ .digest = crc32_pclmul_digest,
+ .descsize = sizeof(u32),
+ .digestsize = CHKSUM_DIGEST_SIZE,
+ .base = {
+ .cra_name = "crc32",
+ .cra_driver_name = "crc32-pclmul",
+ .cra_priority = 200,
+ .cra_blocksize = CHKSUM_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(u32),
+ .cra_module = THIS_MODULE,
+ .cra_init = crc32_pclmul_cra_init,
+ }
+};
+
+static const struct x86_cpu_id crc32pclmul_cpu_id[] = {
+ X86_FEATURE_MATCH(X86_FEATURE_PCLMULQDQ),
+ {}
+};
+MODULE_DEVICE_TABLE(x86cpu, crc32pclmul_cpu_id);
+
+
+static int __init crc32_pclmul_mod_init(void)
+{
+
+ if (!x86_match_cpu(crc32pclmul_cpu_id)) {
+ pr_info("PCLMULQDQ-NI instructions are not detected.\n");
+ return -ENODEV;
+ }
+ return crypto_register_shash(&alg);
+}
+
+static void __exit crc32_pclmul_mod_fini(void)
+{
+ crypto_unregister_shash(&alg);
+}
+
+module_init(crc32_pclmul_mod_init);
+module_exit(crc32_pclmul_mod_fini);
+
+MODULE_AUTHOR("Alexander Boyko <alexander_boyko@xyratex.com>");
+MODULE_LICENSE("GPL");
+
+MODULE_ALIAS("crc32");
+MODULE_ALIAS("crc32-pclmul");
diff --git a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
index 93c6d39237a..cf1a7ec4cc3 100644
--- a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
+++ b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
@@ -42,6 +42,8 @@
* SOFTWARE.
*/
+#include <linux/linkage.h>
+
## ISCSI CRC 32 Implementation with crc32 and pclmulqdq Instruction
.macro LABEL prefix n
@@ -68,8 +70,7 @@
# unsigned int crc_pcl(u8 *buffer, int len, unsigned int crc_init);
-.global crc_pcl
-crc_pcl:
+ENTRY(crc_pcl)
#define bufp %rdi
#define bufp_dw %edi
#define bufp_w %di
@@ -323,6 +324,9 @@ JMPTBL_ENTRY %i
.noaltmacro
i=i+1
.endr
+
+ENDPROC(crc_pcl)
+
################################################################
## PCLMULQDQ tables
## Table is 128 entries x 2 quad words each
diff --git a/arch/x86/crypto/ghash-clmulni-intel_asm.S b/arch/x86/crypto/ghash-clmulni-intel_asm.S
index 1eb7f90cb7b..586f41aac36 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_asm.S
+++ b/arch/x86/crypto/ghash-clmulni-intel_asm.S
@@ -94,6 +94,7 @@ __clmul_gf128mul_ble:
pxor T2, T1
pxor T1, DATA
ret
+ENDPROC(__clmul_gf128mul_ble)
/* void clmul_ghash_mul(char *dst, const be128 *shash) */
ENTRY(clmul_ghash_mul)
@@ -105,6 +106,7 @@ ENTRY(clmul_ghash_mul)
PSHUFB_XMM BSWAP DATA
movups DATA, (%rdi)
ret
+ENDPROC(clmul_ghash_mul)
/*
* void clmul_ghash_update(char *dst, const char *src, unsigned int srclen,
@@ -131,6 +133,7 @@ ENTRY(clmul_ghash_update)
movups DATA, (%rdi)
.Lupdate_just_ret:
ret
+ENDPROC(clmul_ghash_update)
/*
* void clmul_ghash_setkey(be128 *shash, const u8 *key);
@@ -155,3 +158,4 @@ ENTRY(clmul_ghash_setkey)
pxor %xmm1, %xmm0
movups %xmm0, (%rdi)
ret
+ENDPROC(clmul_ghash_setkey)
diff --git a/arch/x86/crypto/salsa20-i586-asm_32.S b/arch/x86/crypto/salsa20-i586-asm_32.S
index 72eb306680b..329452b8f79 100644
--- a/arch/x86/crypto/salsa20-i586-asm_32.S
+++ b/arch/x86/crypto/salsa20-i586-asm_32.S
@@ -2,11 +2,12 @@
# D. J. Bernstein
# Public domain.
-# enter ECRYPT_encrypt_bytes
+#include <linux/linkage.h>
+
.text
-.p2align 5
-.globl ECRYPT_encrypt_bytes
-ECRYPT_encrypt_bytes:
+
+# enter salsa20_encrypt_bytes
+ENTRY(salsa20_encrypt_bytes)
mov %esp,%eax
and $31,%eax
add $256,%eax
@@ -933,11 +934,10 @@ ECRYPT_encrypt_bytes:
add $64,%esi
# goto bytesatleast1
jmp ._bytesatleast1
-# enter ECRYPT_keysetup
-.text
-.p2align 5
-.globl ECRYPT_keysetup
-ECRYPT_keysetup:
+ENDPROC(salsa20_encrypt_bytes)
+
+# enter salsa20_keysetup
+ENTRY(salsa20_keysetup)
mov %esp,%eax
and $31,%eax
add $256,%eax
@@ -1060,11 +1060,10 @@ ECRYPT_keysetup:
# leave
add %eax,%esp
ret
-# enter ECRYPT_ivsetup
-.text
-.p2align 5
-.globl ECRYPT_ivsetup
-ECRYPT_ivsetup:
+ENDPROC(salsa20_keysetup)
+
+# enter salsa20_ivsetup
+ENTRY(salsa20_ivsetup)
mov %esp,%eax
and $31,%eax
add $256,%eax
@@ -1112,3 +1111,4 @@ ECRYPT_ivsetup:
# leave
add %eax,%esp
ret
+ENDPROC(salsa20_ivsetup)
diff --git a/arch/x86/crypto/salsa20-x86_64-asm_64.S b/arch/x86/crypto/salsa20-x86_64-asm_64.S
index 6214a9b0970..9279e0b2d60 100644
--- a/arch/x86/crypto/salsa20-x86_64-asm_64.S
+++ b/arch/x86/crypto/salsa20-x86_64-asm_64.S
@@ -1,8 +1,7 @@
-# enter ECRYPT_encrypt_bytes
-.text
-.p2align 5
-.globl ECRYPT_encrypt_bytes
-ECRYPT_encrypt_bytes:
+#include <linux/linkage.h>
+
+# enter salsa20_encrypt_bytes
+ENTRY(salsa20_encrypt_bytes)
mov %rsp,%r11
and $31,%r11
add $256,%r11
@@ -802,11 +801,10 @@ ECRYPT_encrypt_bytes:
# comment:fp stack unchanged by jump
# goto bytesatleast1
jmp ._bytesatleast1
-# enter ECRYPT_keysetup
-.text
-.p2align 5
-.globl ECRYPT_keysetup
-ECRYPT_keysetup:
+ENDPROC(salsa20_encrypt_bytes)
+
+# enter salsa20_keysetup
+ENTRY(salsa20_keysetup)
mov %rsp,%r11
and $31,%r11
add $256,%r11
@@ -892,11 +890,10 @@ ECRYPT_keysetup:
mov %rdi,%rax
mov %rsi,%rdx
ret
-# enter ECRYPT_ivsetup
-.text
-.p2align 5
-.globl ECRYPT_ivsetup
-ECRYPT_ivsetup:
+ENDPROC(salsa20_keysetup)
+
+# enter salsa20_ivsetup
+ENTRY(salsa20_ivsetup)
mov %rsp,%r11
and $31,%r11
add $256,%r11
@@ -918,3 +915,4 @@ ECRYPT_ivsetup:
mov %rdi,%rax
mov %rsi,%rdx
ret
+ENDPROC(salsa20_ivsetup)
diff --git a/arch/x86/crypto/salsa20_glue.c b/arch/x86/crypto/salsa20_glue.c
index a3a3c0205c1..5e8e67739bb 100644
--- a/arch/x86/crypto/salsa20_glue.c
+++ b/arch/x86/crypto/salsa20_glue.c
@@ -26,11 +26,6 @@
#define SALSA20_MIN_KEY_SIZE 16U
#define SALSA20_MAX_KEY_SIZE 32U
-// use the ECRYPT_* function names
-#define salsa20_keysetup ECRYPT_keysetup
-#define salsa20_ivsetup ECRYPT_ivsetup
-#define salsa20_encrypt_bytes ECRYPT_encrypt_bytes
-
struct salsa20_ctx
{
u32 input[16];
diff --git a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
index 02b0e9fe997..43c938612b7 100644
--- a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
@@ -24,6 +24,7 @@
*
*/
+#include <linux/linkage.h>
#include "glue_helper-asm-avx.S"
.file "serpent-avx-x86_64-asm_64.S"
@@ -566,8 +567,6 @@
transpose_4x4(x0, x1, x2, x3, t0, t1, t2)
.align 8
-.type __serpent_enc_blk8_avx,@function;
-
__serpent_enc_blk8_avx:
/* input:
* %rdi: ctx, CTX
@@ -619,10 +618,9 @@ __serpent_enc_blk8_avx:
write_blocks(RA2, RB2, RC2, RD2, RK0, RK1, RK2);
ret;
+ENDPROC(__serpent_enc_blk8_avx)
.align 8
-.type __serpent_dec_blk8_avx,@function;
-
__serpent_dec_blk8_avx:
/* input:
* %rdi: ctx, CTX
@@ -674,12 +672,9 @@ __serpent_dec_blk8_avx:
write_blocks(RC2, RD2, RB2, RE2, RK0, RK1, RK2);
ret;
+ENDPROC(__serpent_dec_blk8_avx)
-.align 8
-.global serpent_ecb_enc_8way_avx
-.type serpent_ecb_enc_8way_avx,@function;
-
-serpent_ecb_enc_8way_avx:
+ENTRY(serpent_ecb_enc_8way_avx)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
@@ -693,12 +688,9 @@ serpent_ecb_enc_8way_avx:
store_8way(%rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
ret;
+ENDPROC(serpent_ecb_enc_8way_avx)
-.align 8
-.global serpent_ecb_dec_8way_avx
-.type serpent_ecb_dec_8way_avx,@function;
-
-serpent_ecb_dec_8way_avx:
+ENTRY(serpent_ecb_dec_8way_avx)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
@@ -712,12 +704,9 @@ serpent_ecb_dec_8way_avx:
store_8way(%rsi, RC1, RD1, RB1, RE1, RC2, RD2, RB2, RE2);
ret;
+ENDPROC(serpent_ecb_dec_8way_avx)
-.align 8
-.global serpent_cbc_dec_8way_avx
-.type serpent_cbc_dec_8way_avx,@function;
-
-serpent_cbc_dec_8way_avx:
+ENTRY(serpent_cbc_dec_8way_avx)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
@@ -731,12 +720,9 @@ serpent_cbc_dec_8way_avx:
store_cbc_8way(%rdx, %rsi, RC1, RD1, RB1, RE1, RC2, RD2, RB2, RE2);
ret;
+ENDPROC(serpent_cbc_dec_8way_avx)
-.align 8
-.global serpent_ctr_8way_avx
-.type serpent_ctr_8way_avx,@function;
-
-serpent_ctr_8way_avx:
+ENTRY(serpent_ctr_8way_avx)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
@@ -752,3 +738,4 @@ serpent_ctr_8way_avx:
store_ctr_8way(%rdx, %rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
ret;
+ENDPROC(serpent_ctr_8way_avx)
diff --git a/arch/x86/crypto/serpent-sse2-i586-asm_32.S b/arch/x86/crypto/serpent-sse2-i586-asm_32.S
index c00053d42f9..d348f1553a7 100644
--- a/arch/x86/crypto/serpent-sse2-i586-asm_32.S
+++ b/arch/x86/crypto/serpent-sse2-i586-asm_32.S
@@ -24,6 +24,8 @@
*
*/
+#include <linux/linkage.h>
+
.file "serpent-sse2-i586-asm_32.S"
.text
@@ -510,11 +512,7 @@
pxor t0, x3; \
movdqu x3, (3*4*4)(out);
-.align 8
-.global __serpent_enc_blk_4way
-.type __serpent_enc_blk_4way,@function;
-
-__serpent_enc_blk_4way:
+ENTRY(__serpent_enc_blk_4way)
/* input:
* arg_ctx(%esp): ctx, CTX
* arg_dst(%esp): dst
@@ -566,22 +564,19 @@ __serpent_enc_blk_4way:
movl arg_dst(%esp), %eax;
cmpb $0, arg_xor(%esp);
- jnz __enc_xor4;
+ jnz .L__enc_xor4;
write_blocks(%eax, RA, RB, RC, RD, RT0, RT1, RE);
ret;
-__enc_xor4:
+.L__enc_xor4:
xor_blocks(%eax, RA, RB, RC, RD, RT0, RT1, RE);
ret;
+ENDPROC(__serpent_enc_blk_4way)
-.align 8
-.global serpent_dec_blk_4way
-.type serpent_dec_blk_4way,@function;
-
-serpent_dec_blk_4way:
+ENTRY(serpent_dec_blk_4way)
/* input:
* arg_ctx(%esp): ctx, CTX
* arg_dst(%esp): dst
@@ -633,3 +628,4 @@ serpent_dec_blk_4way:
write_blocks(%eax, RC, RD, RB, RE, RT0, RT1, RA);
ret;
+ENDPROC(serpent_dec_blk_4way)
diff --git a/arch/x86/crypto/serpent-sse2-x86_64-asm_64.S b/arch/x86/crypto/serpent-sse2-x86_64-asm_64.S
index 3ee1ff04d3e..acc066c7c6b 100644
--- a/arch/x86/crypto/serpent-sse2-x86_64-asm_64.S
+++ b/arch/x86/crypto/serpent-sse2-x86_64-asm_64.S
@@ -24,6 +24,8 @@
*
*/
+#include <linux/linkage.h>
+
.file "serpent-sse2-x86_64-asm_64.S"
.text
@@ -632,11 +634,7 @@
pxor t0, x3; \
movdqu x3, (3*4*4)(out);
-.align 8
-.global __serpent_enc_blk_8way
-.type __serpent_enc_blk_8way,@function;
-
-__serpent_enc_blk_8way:
+ENTRY(__serpent_enc_blk_8way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
@@ -687,24 +685,21 @@ __serpent_enc_blk_8way:
leaq (4*4*4)(%rsi), %rax;
testb %cl, %cl;
- jnz __enc_xor8;
+ jnz .L__enc_xor8;
write_blocks(%rsi, RA1, RB1, RC1, RD1, RK0, RK1, RK2);
write_blocks(%rax, RA2, RB2, RC2, RD2, RK0, RK1, RK2);
ret;
-__enc_xor8:
+.L__enc_xor8:
xor_blocks(%rsi, RA1, RB1, RC1, RD1, RK0, RK1, RK2);
xor_blocks(%rax, RA2, RB2, RC2, RD2, RK0, RK1, RK2);
ret;
+ENDPROC(__serpent_enc_blk_8way)
-.align 8
-.global serpent_dec_blk_8way
-.type serpent_dec_blk_8way,@function;
-
-serpent_dec_blk_8way:
+ENTRY(serpent_dec_blk_8way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
@@ -756,3 +751,4 @@ serpent_dec_blk_8way:
write_blocks(%rax, RC2, RD2, RB2, RE2, RK0, RK1, RK2);
ret;
+ENDPROC(serpent_dec_blk_8way)
diff --git a/arch/x86/crypto/sha1_ssse3_asm.S b/arch/x86/crypto/sha1_ssse3_asm.S
index 49d6987a73d..a4109506a5e 100644
--- a/arch/x86/crypto/sha1_ssse3_asm.S
+++ b/arch/x86/crypto/sha1_ssse3_asm.S
@@ -28,6 +28,8 @@
* (at your option) any later version.
*/
+#include <linux/linkage.h>
+
#define CTX %rdi // arg1
#define BUF %rsi // arg2
#define CNT %rdx // arg3
@@ -69,10 +71,8 @@
* param: function's name
*/
.macro SHA1_VECTOR_ASM name
- .global \name
- .type \name, @function
- .align 32
-\name:
+ ENTRY(\name)
+
push %rbx
push %rbp
push %r12
@@ -106,7 +106,7 @@
pop %rbx
ret
- .size \name, .-\name
+ ENDPROC(\name)
.endm
/*
diff --git a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
index ebac16bfa83..8d3e113b2c9 100644
--- a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
@@ -23,6 +23,7 @@
*
*/
+#include <linux/linkage.h>
#include "glue_helper-asm-avx.S"
.file "twofish-avx-x86_64-asm_64.S"
@@ -243,8 +244,6 @@
vpxor x3, wkey, x3;
.align 8
-.type __twofish_enc_blk8,@function;
-
__twofish_enc_blk8:
/* input:
* %rdi: ctx, CTX
@@ -284,10 +283,9 @@ __twofish_enc_blk8:
outunpack_blocks(RC2, RD2, RA2, RB2, RK1, RX0, RY0, RK2);
ret;
+ENDPROC(__twofish_enc_blk8)
.align 8
-.type __twofish_dec_blk8,@function;
-
__twofish_dec_blk8:
/* input:
* %rdi: ctx, CTX
@@ -325,12 +323,9 @@ __twofish_dec_blk8:
outunpack_blocks(RA2, RB2, RC2, RD2, RK1, RX0, RY0, RK2);
ret;
+ENDPROC(__twofish_dec_blk8)
-.align 8
-.global twofish_ecb_enc_8way
-.type twofish_ecb_enc_8way,@function;
-
-twofish_ecb_enc_8way:
+ENTRY(twofish_ecb_enc_8way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
@@ -346,12 +341,9 @@ twofish_ecb_enc_8way:
store_8way(%r11, RC1, RD1, RA1, RB1, RC2, RD2, RA2, RB2);
ret;
+ENDPROC(twofish_ecb_enc_8way)
-.align 8
-.global twofish_ecb_dec_8way
-.type twofish_ecb_dec_8way,@function;
-
-twofish_ecb_dec_8way:
+ENTRY(twofish_ecb_dec_8way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
@@ -367,12 +359,9 @@ twofish_ecb_dec_8way:
store_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
ret;
+ENDPROC(twofish_ecb_dec_8way)
-.align 8
-.global twofish_cbc_dec_8way
-.type twofish_cbc_dec_8way,@function;
-
-twofish_cbc_dec_8way:
+ENTRY(twofish_cbc_dec_8way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
@@ -393,12 +382,9 @@ twofish_cbc_dec_8way:
popq %r12;
ret;
+ENDPROC(twofish_cbc_dec_8way)
-.align 8
-.global twofish_ctr_8way
-.type twofish_ctr_8way,@function;
-
-twofish_ctr_8way:
+ENTRY(twofish_ctr_8way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
@@ -421,3 +407,4 @@ twofish_ctr_8way:
popq %r12;
ret;
+ENDPROC(twofish_ctr_8way)
diff --git a/arch/x86/crypto/twofish-i586-asm_32.S b/arch/x86/crypto/twofish-i586-asm_32.S
index 658af4bb35c..694ea4587ba 100644
--- a/arch/x86/crypto/twofish-i586-asm_32.S
+++ b/arch/x86/crypto/twofish-i586-asm_32.S
@@ -20,6 +20,7 @@
.file "twofish-i586-asm.S"
.text
+#include <linux/linkage.h>
#include <asm/asm-offsets.h>
/* return address at 0 */
@@ -219,11 +220,7 @@
xor %esi, d ## D;\
ror $1, d ## D;
-.align 4
-.global twofish_enc_blk
-.global twofish_dec_blk
-
-twofish_enc_blk:
+ENTRY(twofish_enc_blk)
push %ebp /* save registers according to calling convention*/
push %ebx
push %esi
@@ -277,8 +274,9 @@ twofish_enc_blk:
pop %ebp
mov $1, %eax
ret
+ENDPROC(twofish_enc_blk)
-twofish_dec_blk:
+ENTRY(twofish_dec_blk)
push %ebp /* save registers according to calling convention*/
push %ebx
push %esi
@@ -333,3 +331,4 @@ twofish_dec_blk:
pop %ebp
mov $1, %eax
ret
+ENDPROC(twofish_dec_blk)
diff --git a/arch/x86/crypto/twofish-x86_64-asm_64-3way.S b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
index 5b012a2c511..1c3b7ceb36d 100644
--- a/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
+++ b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
@@ -20,6 +20,8 @@
*
*/
+#include <linux/linkage.h>
+
.file "twofish-x86_64-asm-3way.S"
.text
@@ -214,11 +216,7 @@
rorq $32, RAB2; \
outunpack3(mov, RIO, 2, RAB, 2);
-.align 8
-.global __twofish_enc_blk_3way
-.type __twofish_enc_blk_3way,@function;
-
-__twofish_enc_blk_3way:
+ENTRY(__twofish_enc_blk_3way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
@@ -250,7 +248,7 @@ __twofish_enc_blk_3way:
popq %rbp; /* bool xor */
testb %bpl, %bpl;
- jnz __enc_xor3;
+ jnz .L__enc_xor3;
outunpack_enc3(mov);
@@ -262,7 +260,7 @@ __twofish_enc_blk_3way:
popq %r15;
ret;
-__enc_xor3:
+.L__enc_xor3:
outunpack_enc3(xor);
popq %rbx;
@@ -272,11 +270,9 @@ __enc_xor3:
popq %r14;
popq %r15;
ret;
+ENDPROC(__twofish_enc_blk_3way)
-.global twofish_dec_blk_3way
-.type twofish_dec_blk_3way,@function;
-
-twofish_dec_blk_3way:
+ENTRY(twofish_dec_blk_3way)
/* input:
* %rdi: ctx, CTX
* %rsi: dst
@@ -313,4 +309,4 @@ twofish_dec_blk_3way:
popq %r14;
popq %r15;
ret;
-
+ENDPROC(twofish_dec_blk_3way)
diff --git a/arch/x86/crypto/twofish-x86_64-asm_64.S b/arch/x86/crypto/twofish-x86_64-asm_64.S
index 7bcf3fcc366..a039d21986a 100644
--- a/arch/x86/crypto/twofish-x86_64-asm_64.S
+++ b/arch/x86/crypto/twofish-x86_64-asm_64.S
@@ -20,6 +20,7 @@
.file "twofish-x86_64-asm.S"
.text
+#include <linux/linkage.h>
#include <asm/asm-offsets.h>
#define a_offset 0
@@ -214,11 +215,7 @@
xor %r8d, d ## D;\
ror $1, d ## D;
-.align 8
-.global twofish_enc_blk
-.global twofish_dec_blk
-
-twofish_enc_blk:
+ENTRY(twofish_enc_blk)
pushq R1
/* %rdi contains the ctx address */
@@ -269,8 +266,9 @@ twofish_enc_blk:
popq R1
movq $1,%rax
ret
+ENDPROC(twofish_enc_blk)
-twofish_dec_blk:
+ENTRY(twofish_dec_blk)
pushq R1
/* %rdi contains the ctx address */
@@ -320,3 +318,4 @@ twofish_dec_blk:
popq R1
movq $1,%rax
ret
+ENDPROC(twofish_dec_blk)
diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index a703af19c28..03abf9b7001 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -271,7 +271,7 @@ static int load_aout_binary(struct linux_binprm *bprm)
if ((N_MAGIC(ex) != ZMAGIC && N_MAGIC(ex) != OMAGIC &&
N_MAGIC(ex) != QMAGIC && N_MAGIC(ex) != NMAGIC) ||
N_TRSIZE(ex) || N_DRSIZE(ex) ||
- i_size_read(bprm->file->f_path.dentry->d_inode) <
+ i_size_read(file_inode(bprm->file)) <
ex.a_text+ex.a_data+N_SYMSIZE(ex)+N_TXTOFF(ex)) {
return -ENOEXEC;
}
@@ -425,12 +425,10 @@ beyond_if:
static int load_aout_library(struct file *file)
{
- struct inode *inode;
unsigned long bss, start_addr, len, error;
int retval;
struct exec ex;
- inode = file->f_path.dentry->d_inode;
retval = -ENOEXEC;
error = kernel_read(file, 0, (char *) &ex, sizeof(ex));
@@ -440,7 +438,7 @@ static int load_aout_library(struct file *file)
/* We come in here for the regular a.out style of shared libraries */
if ((N_MAGIC(ex) != ZMAGIC && N_MAGIC(ex) != QMAGIC) || N_TRSIZE(ex) ||
N_DRSIZE(ex) || ((ex.a_entry & 0xfff) && N_MAGIC(ex) == ZMAGIC) ||
- i_size_read(inode) <
+ i_size_read(file_inode(file)) <
ex.a_text+ex.a_data+N_SYMSIZE(ex)+N_TXTOFF(ex)) {
goto out;
}
diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c
index 592f5a9a9c0..ad7a20cbc69 100644
--- a/arch/x86/ia32/sys_ia32.c
+++ b/arch/x86/ia32/sys_ia32.c
@@ -218,11 +218,6 @@ asmlinkage long sys32_sendfile(int out_fd, int in_fd,
* Some system calls that need sign extended arguments. This could be
* done by a generic wrapper.
*/
-long sys32_lseek(unsigned int fd, int offset, unsigned int whence)
-{
- return sys_lseek(fd, offset, whence);
-}
-
long sys32_kill(int pid, int sig)
{
return sys_kill(pid, sig);
diff --git a/arch/x86/include/asm/bootparam_utils.h b/arch/x86/include/asm/bootparam_utils.h
index 5b5e9cb774b..653668d140f 100644
--- a/arch/x86/include/asm/bootparam_utils.h
+++ b/arch/x86/include/asm/bootparam_utils.h
@@ -14,13 +14,29 @@
* analysis of kexec-tools; if other broken bootloaders initialize a
* different set of fields we will need to figure out how to disambiguate.
*
+ * Note: efi_info is commonly left uninitialized, but that field has a
+ * private magic, so it is better to leave it unchanged.
*/
static void sanitize_boot_params(struct boot_params *boot_params)
{
+ /*
+ * IMPORTANT NOTE TO BOOTLOADER AUTHORS: do not simply clear
+ * this field. The purpose of this field is to guarantee
+ * compliance with the x86 boot spec located in
+ * Documentation/x86/boot.txt . That spec says that the
+ * *whole* structure should be cleared, after which only the
+ * portion defined by struct setup_header (boot_params->hdr)
+ * should be copied in.
+ *
+ * If you're having an issue because the sentinel is set, you
+ * need to change the whole structure to be cleared, not this
+ * (or any other) individual field, or you will soon have
+ * problems again.
+ */
if (boot_params->sentinel) {
- /*fields in boot_params are not valid, clear them */
+ /* fields in boot_params are left uninitialized, clear them */
memset(&boot_params->olpc_ofw_header, 0,
- (char *)&boot_params->alt_mem_k -
+ (char *)&boot_params->efi_info -
(char *)&boot_params->olpc_ofw_header);
memset(&boot_params->kbd_status, 0,
(char *)&boot_params->hdr -
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 28677c55113..60c89f30c72 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -102,7 +102,14 @@ extern void efi_call_phys_epilog(void);
extern void efi_unmap_memmap(void);
extern void efi_memory_uc(u64 addr, unsigned long size);
-#ifndef CONFIG_EFI
+#ifdef CONFIG_EFI
+
+static inline bool efi_is_native(void)
+{
+ return IS_ENABLED(CONFIG_X86_64) == efi_enabled(EFI_64BIT);
+}
+
+#else
/*
* IF EFI is not configured, have the EFI calls return -ENOSYS.
*/
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index 86cb51e1ca9..0525a8bdf65 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -72,4 +72,28 @@ int ftrace_int3_handler(struct pt_regs *regs);
#endif /* __ASSEMBLY__ */
#endif /* CONFIG_FUNCTION_TRACER */
+
+#if !defined(__ASSEMBLY__) && !defined(COMPILE_OFFSETS)
+
+#if defined(CONFIG_FTRACE_SYSCALLS) && defined(CONFIG_IA32_EMULATION)
+#include <asm/compat.h>
+
+/*
+ * Because ia32 syscalls do not map to x86_64 syscall numbers
+ * this screws up the trace output when tracing a ia32 task.
+ * Instead of reporting bogus syscalls, just do not trace them.
+ *
+ * If the user realy wants these, then they should use the
+ * raw syscall tracepoints with filtering.
+ */
+#define ARCH_TRACE_IGNORE_COMPAT_SYSCALLS 1
+static inline bool arch_trace_is_compat_syscall(struct pt_regs *regs)
+{
+ if (is_compat_task())
+ return true;
+ return false;
+}
+#endif /* CONFIG_FTRACE_SYSCALLS && CONFIG_IA32_EMULATION */
+#endif /* !__ASSEMBLY__ && !COMPILE_OFFSETS */
+
#endif /* _ASM_X86_FTRACE_H */
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index d3ddd17405d..5a6d2873f80 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -77,6 +77,7 @@ struct arch_specific_insn {
* a post_handler or break_handler).
*/
int boostable;
+ bool if_modifier;
};
struct arch_optimized_insn {
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 635a74d2240..4979778cc7f 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -414,8 +414,8 @@ struct kvm_vcpu_arch {
gpa_t time;
struct pvclock_vcpu_time_info hv_clock;
unsigned int hw_tsc_khz;
- unsigned int time_offset;
- struct page *time_page;
+ struct gfn_to_hva_cache pv_time;
+ bool pv_time_enabled;
/* set guest stopped flag in pvclock flags field */
bool pvclock_set_guest_stopped_request;
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index c28fd02f4bf..d9e9e6c7ed3 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -14,6 +14,9 @@
struct pci_sysdata {
int domain; /* PCI domain */
int node; /* NUMA node */
+#ifdef CONFIG_ACPI
+ void *acpi; /* ACPI-specific data */
+#endif
#ifdef CONFIG_X86_64
void *iommu; /* IOMMU private data */
#endif
diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h
index 747e5a38b59..fa1195dae42 100644
--- a/arch/x86/include/asm/pci_x86.h
+++ b/arch/x86/include/asm/pci_x86.h
@@ -54,7 +54,6 @@ void pcibios_set_cache_line_size(void);
/* pci-pc.c */
extern int pcibios_last_bus;
-extern struct pci_bus *pci_root_bus;
extern struct pci_ops pci_root_ops;
void pcibios_scan_specific_bus(int busn);
diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h
index 0218d917f50..8459efc3968 100644
--- a/arch/x86/include/asm/sys_ia32.h
+++ b/arch/x86/include/asm/sys_ia32.h
@@ -43,7 +43,6 @@ asmlinkage long sys32_pwrite(unsigned int, const char __user *, u32, u32, u32);
asmlinkage long sys32_personality(unsigned long);
asmlinkage long sys32_sendfile(int, int, compat_off_t __user *, s32);
-long sys32_lseek(unsigned int, int, unsigned int);
long sys32_kill(int, int);
long sys32_fadvise64_64(int, __u32, __u32, __u32, __u32, int);
long sys32_vm86_warning(void);
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index 1ace47b6259..2e188d68397 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -29,13 +29,13 @@ extern const unsigned long sys_call_table[];
*/
static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs)
{
- return regs->orig_ax & __SYSCALL_MASK;
+ return regs->orig_ax;
}
static inline void syscall_rollback(struct task_struct *task,
struct pt_regs *regs)
{
- regs->ax = regs->orig_ax & __SYSCALL_MASK;
+ regs->ax = regs->orig_ax;
}
static inline long syscall_get_error(struct task_struct *task,
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 2d946e63ee8..2cd056e3ada 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -20,7 +20,6 @@
struct task_struct;
struct exec_domain;
#include <asm/processor.h>
-#include <asm/ftrace.h>
#include <linux/atomic.h>
struct thread_info {
diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h
index 892ce40a747..7a060f4b411 100644
--- a/arch/x86/include/uapi/asm/msr-index.h
+++ b/arch/x86/include/uapi/asm/msr-index.h
@@ -44,6 +44,7 @@
#define SNB_C1_AUTO_UNDEMOTE (1UL << 27)
#define SNB_C3_AUTO_UNDEMOTE (1UL << 28)
+#define MSR_PLATFORM_INFO 0x000000ce
#define MSR_MTRRcap 0x000000fe
#define MSR_IA32_BBL_CR_CTL 0x00000119
#define MSR_IA32_BBL_CR_CTL3 0x0000011e
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index a5b4dce1b7a..904611bf0e5 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -131,7 +131,7 @@ static int __init parse_lapic(char *arg)
{
if (config_enabled(CONFIG_X86_32) && !arg)
force_enable_local_apic = 1;
- else if (!strncmp(arg, "notscdeadline", 13))
+ else if (arg && !strncmp(arg, "notscdeadline", 13))
setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
return 0;
}
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index edd77e7508b..fa96eb0d02f 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -219,8 +219,7 @@ static void __cpuinit amd_k7_smp_check(struct cpuinfo_x86 *c)
*/
WARN_ONCE(1, "WARNING: This combination of AMD"
" processors is not suitable for SMP.\n");
- if (!test_taint(TAINT_UNSAFE_SMP))
- add_taint(TAINT_UNSAFE_SMP);
+ add_taint(TAINT_UNSAFE_SMP, LOCKDEP_NOW_UNRELIABLE);
valid_k7:
;
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index fc7608a89d9..7bc126346ac 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1082,7 +1082,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
/*
* Set taint even when machine check was not enabled.
*/
- add_taint(TAINT_MACHINE_CHECK);
+ add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
severity = mce_severity(&m, cfg->tolerant, NULL);
diff --git a/arch/x86/kernel/cpu/mcheck/p5.c b/arch/x86/kernel/cpu/mcheck/p5.c
index 2d5454cd2c4..1c044b1ccc5 100644
--- a/arch/x86/kernel/cpu/mcheck/p5.c
+++ b/arch/x86/kernel/cpu/mcheck/p5.c
@@ -33,7 +33,7 @@ static void pentium_machine_check(struct pt_regs *regs, long error_code)
smp_processor_id());
}
- add_taint(TAINT_MACHINE_CHECK);
+ add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
}
/* Set up machine check reporting for processors with Intel style MCE: */
diff --git a/arch/x86/kernel/cpu/mcheck/winchip.c b/arch/x86/kernel/cpu/mcheck/winchip.c
index 2d7998fb628..e9a701aecaa 100644
--- a/arch/x86/kernel/cpu/mcheck/winchip.c
+++ b/arch/x86/kernel/cpu/mcheck/winchip.c
@@ -15,7 +15,7 @@
static void winchip_machine_check(struct pt_regs *regs, long error_code)
{
printk(KERN_EMERG "CPU0: Machine Check Exception.\n");
- add_taint(TAINT_MACHINE_CHECK);
+ add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
}
/* Set up machine check reporting on the Winchip C6 series */
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index e9fe907cd24..fa72a39e5d4 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -542,7 +542,7 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base,
if (tmp != mask_lo) {
printk(KERN_WARNING "mtrr: your BIOS has configured an incorrect mask, fixing it.\n");
- add_taint(TAINT_FIRMWARE_WORKAROUND);
+ add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
mask_lo = tmp;
}
}
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 4914e94ad6e..dab7580c47a 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -101,12 +101,37 @@ static struct event_constraint intel_snb_event_constraints[] __read_mostly =
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
+ INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_DISPATCH */
+ INTEL_UEVENT_CONSTRAINT(0x05a3, 0xf), /* CYCLE_ACTIVITY.STALLS_L2_PENDING */
+ INTEL_UEVENT_CONSTRAINT(0x02a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */
+ INTEL_UEVENT_CONSTRAINT(0x06a3, 0x4), /* CYCLE_ACTIVITY.STALLS_L1D_PENDING */
INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.PENDING */
INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
EVENT_CONSTRAINT_END
};
+static struct event_constraint intel_ivb_event_constraints[] __read_mostly =
+{
+ FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
+ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
+ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
+ INTEL_UEVENT_CONSTRAINT(0x0148, 0x4), /* L1D_PEND_MISS.PENDING */
+ INTEL_UEVENT_CONSTRAINT(0x0279, 0xf), /* IDQ.EMTPY */
+ INTEL_UEVENT_CONSTRAINT(0x019c, 0xf), /* IDQ_UOPS_NOT_DELIVERED.CORE */
+ INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_EXECUTE */
+ INTEL_UEVENT_CONSTRAINT(0x05a3, 0xf), /* CYCLE_ACTIVITY.STALLS_L2_PENDING */
+ INTEL_UEVENT_CONSTRAINT(0x06a3, 0xf), /* CYCLE_ACTIVITY.STALLS_LDM_PENDING */
+ INTEL_UEVENT_CONSTRAINT(0x08a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */
+ INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4), /* CYCLE_ACTIVITY.STALLS_L1D_PENDING */
+ INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
+ INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */
+ EVENT_CONSTRAINT_END
+};
+
static struct extra_reg intel_westmere_extra_regs[] __read_mostly =
{
INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0),
@@ -2095,7 +2120,7 @@ __init int intel_pmu_init(void)
intel_pmu_lbr_init_snb();
- x86_pmu.event_constraints = intel_snb_event_constraints;
+ x86_pmu.event_constraints = intel_ivb_event_constraints;
x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints;
x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
x86_pmu.extra_regs = intel_snb_extra_regs;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 826054a4f2e..b05a575d56f 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -729,3 +729,13 @@ void intel_ds_init(void)
}
}
}
+
+void perf_restore_debug_store(void)
+{
+ struct debug_store *ds = __this_cpu_read(cpu_hw_events.ds);
+
+ if (!x86_pmu.bts && !x86_pmu.pebs)
+ return;
+
+ wrmsrl(MSR_IA32_DS_AREA, (unsigned long)ds);
+}
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index 60c78917190..1e4dbcfe6d3 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -85,7 +85,7 @@ static ssize_t cpuid_read(struct file *file, char __user *buf,
{
char __user *tmp = buf;
struct cpuid_regs cmd;
- int cpu = iminor(file->f_path.dentry->d_inode);
+ int cpu = iminor(file_inode(file));
u64 pos = *ppos;
ssize_t bytes = 0;
int err = 0;
@@ -116,7 +116,7 @@ static int cpuid_open(struct inode *inode, struct file *file)
unsigned int cpu;
struct cpuinfo_x86 *c;
- cpu = iminor(file->f_path.dentry->d_inode);
+ cpu = iminor(file_inode(file));
if (cpu >= nr_cpu_ids || !cpu_online(cpu))
return -ENXIO; /* No such CPU */
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index ae42418bc50..c8797d55b24 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -232,7 +232,7 @@ void __kprobes oops_end(unsigned long flags, struct pt_regs *regs, int signr)
bust_spinlocks(0);
die_owner = -1;
- add_taint(TAINT_DIE);
+ add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE);
die_nest_count--;
if (!die_nest_count)
/* Nest count reaches zero, release the lock. */
diff --git a/arch/x86/kernel/head.c b/arch/x86/kernel/head.c
index 48d9d4ea102..992f442ca15 100644
--- a/arch/x86/kernel/head.c
+++ b/arch/x86/kernel/head.c
@@ -5,8 +5,6 @@
#include <asm/setup.h>
#include <asm/bios_ebda.h>
-#define BIOS_LOWMEM_KILOBYTES 0x413
-
/*
* The BIOS places the EBDA/XBDA at the top of conventional
* memory, and usually decreases the reported amount of
@@ -16,17 +14,30 @@
* chipset: reserve a page before VGA to prevent PCI prefetch
* into it (errata #56). Usually the page is reserved anyways,
* unless you have no PS/2 mouse plugged in.
+ *
+ * This functions is deliberately very conservative. Losing
+ * memory in the bottom megabyte is rarely a problem, as long
+ * as we have enough memory to install the trampoline. Using
+ * memory that is in use by the BIOS or by some DMA device
+ * the BIOS didn't shut down *is* a big problem.
*/
+
+#define BIOS_LOWMEM_KILOBYTES 0x413
+#define LOWMEM_CAP 0x9f000U /* Absolute maximum */
+#define INSANE_CUTOFF 0x20000U /* Less than this = insane */
+
void __init reserve_ebda_region(void)
{
unsigned int lowmem, ebda_addr;
- /* To determine the position of the EBDA and the */
- /* end of conventional memory, we need to look at */
- /* the BIOS data area. In a paravirtual environment */
- /* that area is absent. We'll just have to assume */
- /* that the paravirt case can handle memory setup */
- /* correctly, without our help. */
+ /*
+ * To determine the position of the EBDA and the
+ * end of conventional memory, we need to look at
+ * the BIOS data area. In a paravirtual environment
+ * that area is absent. We'll just have to assume
+ * that the paravirt case can handle memory setup
+ * correctly, without our help.
+ */
if (paravirt_enabled())
return;
@@ -37,19 +48,23 @@ void __init reserve_ebda_region(void)
/* start of EBDA area */
ebda_addr = get_bios_ebda();
- /* Fixup: bios puts an EBDA in the top 64K segment */
- /* of conventional memory, but does not adjust lowmem. */
- if ((lowmem - ebda_addr) <= 0x10000)
- lowmem = ebda_addr;
+ /*
+ * Note: some old Dells seem to need 4k EBDA without
+ * reporting so, so just consider the memory above 0x9f000
+ * to be off limits (bugzilla 2990).
+ */
+
+ /* If the EBDA address is below 128K, assume it is bogus */
+ if (ebda_addr < INSANE_CUTOFF)
+ ebda_addr = LOWMEM_CAP;
- /* Fixup: bios does not report an EBDA at all. */
- /* Some old Dells seem to need 4k anyhow (bugzilla 2990) */
- if ((ebda_addr == 0) && (lowmem >= 0x9f000))
- lowmem = 0x9f000;
+ /* If lowmem is less than 128K, assume it is bogus */
+ if (lowmem < INSANE_CUTOFF)
+ lowmem = LOWMEM_CAP;
- /* Paranoia: should never happen, but... */
- if ((lowmem == 0) || (lowmem >= 0x100000))
- lowmem = 0x9f000;
+ /* Use the lower of the lowmem and EBDA markers as the cutoff */
+ lowmem = min(lowmem, ebda_addr);
+ lowmem = min(lowmem, LOWMEM_CAP); /* Absolute cap */
/* reserve all memory between lowmem and the 1MB mark */
memblock_reserve(lowmem, 0x100000 - lowmem);
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index b7de3b25adb..6859e962644 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -48,7 +48,7 @@ L3_START_KERNEL = pud_index(__START_KERNEL_map)
.globl startup_64
startup_64:
/*
- * At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 1,
+ * At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 0,
* and someone has loaded an identity mapped page table
* for us. These identity mapped page tables map all of the
* kernel pages and possibly all of memory.
@@ -159,7 +159,7 @@ startup_64:
jmp 1f
ENTRY(secondary_startup_64)
/*
- * At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 1,
+ * At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 0,
* and someone has loaded a mapped page table.
*
* %rsi holds a physical pointer to real_mode_data.
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index e124554598e..7bfe318d3d8 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -375,6 +375,9 @@ static void __kprobes arch_copy_kprobe(struct kprobe *p)
else
p->ainsn.boostable = -1;
+ /* Check whether the instruction modifies Interrupt Flag or not */
+ p->ainsn.if_modifier = is_IF_modifier(p->ainsn.insn);
+
/* Also, displacement change doesn't affect the first byte */
p->opcode = p->ainsn.insn[0];
}
@@ -434,7 +437,7 @@ static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
__this_cpu_write(current_kprobe, p);
kcb->kprobe_saved_flags = kcb->kprobe_old_flags
= (regs->flags & (X86_EFLAGS_TF | X86_EFLAGS_IF));
- if (is_IF_modifier(p->ainsn.insn))
+ if (p->ainsn.if_modifier)
kcb->kprobe_saved_flags &= ~X86_EFLAGS_IF;
}
@@ -652,7 +655,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
{
struct kretprobe_instance *ri = NULL;
struct hlist_head *head, empty_rp;
- struct hlist_node *node, *tmp;
+ struct hlist_node *tmp;
unsigned long flags, orig_ret_address = 0;
unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline;
kprobe_opcode_t *correct_ret_addr = NULL;
@@ -682,7 +685,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
* will be the real return address, and all the rest will
* point to kretprobe_trampoline.
*/
- hlist_for_each_entry_safe(ri, node, tmp, head, hlist) {
+ hlist_for_each_entry_safe(ri, tmp, head, hlist) {
if (ri->task != current)
/* another task is sharing our hash bucket */
continue;
@@ -701,7 +704,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
kretprobe_assert(ri, orig_ret_address, trampoline_address);
correct_ret_addr = ri->ret_addr;
- hlist_for_each_entry_safe(ri, node, tmp, head, hlist) {
+ hlist_for_each_entry_safe(ri, tmp, head, hlist) {
if (ri->task != current)
/* another task is sharing our hash bucket */
continue;
@@ -728,7 +731,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
kretprobe_hash_unlock(current, &flags);
- hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) {
+ hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
hlist_del(&ri->hlist);
kfree(ri);
}
diff --git a/arch/x86/kernel/microcode_intel_early.c b/arch/x86/kernel/microcode_intel_early.c
index 7890bc83895..d893e8ed8ac 100644
--- a/arch/x86/kernel/microcode_intel_early.c
+++ b/arch/x86/kernel/microcode_intel_early.c
@@ -90,13 +90,13 @@ microcode_phys(struct microcode_intel **mc_saved_tmp,
struct microcode_intel ***mc_saved;
mc_saved = (struct microcode_intel ***)
- __pa_symbol(&mc_saved_data->mc_saved);
+ __pa_nodebug(&mc_saved_data->mc_saved);
for (i = 0; i < mc_saved_data->mc_saved_count; i++) {
struct microcode_intel *p;
p = *(struct microcode_intel **)
- __pa(mc_saved_data->mc_saved + i);
- mc_saved_tmp[i] = (struct microcode_intel *)__pa(p);
+ __pa_nodebug(mc_saved_data->mc_saved + i);
+ mc_saved_tmp[i] = (struct microcode_intel *)__pa_nodebug(p);
}
}
#endif
@@ -562,7 +562,7 @@ scan_microcode(unsigned long start, unsigned long end,
struct cpio_data cd;
long offset = 0;
#ifdef CONFIG_X86_32
- char *p = (char *)__pa_symbol(ucode_name);
+ char *p = (char *)__pa_nodebug(ucode_name);
#else
char *p = ucode_name;
#endif
@@ -630,8 +630,8 @@ static void __cpuinit print_ucode(struct ucode_cpu_info *uci)
if (mc_intel == NULL)
return;
- delay_ucode_info_p = (int *)__pa_symbol(&delay_ucode_info);
- current_mc_date_p = (int *)__pa_symbol(&current_mc_date);
+ delay_ucode_info_p = (int *)__pa_nodebug(&delay_ucode_info);
+ current_mc_date_p = (int *)__pa_nodebug(&current_mc_date);
*delay_ucode_info_p = 1;
*current_mc_date_p = mc_intel->hdr.date;
@@ -659,8 +659,8 @@ static inline void __cpuinit print_ucode(struct ucode_cpu_info *uci)
}
#endif
-static int apply_microcode_early(struct mc_saved_data *mc_saved_data,
- struct ucode_cpu_info *uci)
+static int __cpuinit apply_microcode_early(struct mc_saved_data *mc_saved_data,
+ struct ucode_cpu_info *uci)
{
struct microcode_intel *mc_intel;
unsigned int val[2];
@@ -741,15 +741,15 @@ load_ucode_intel_bsp(void)
#ifdef CONFIG_X86_32
struct boot_params *boot_params_p;
- boot_params_p = (struct boot_params *)__pa_symbol(&boot_params);
+ boot_params_p = (struct boot_params *)__pa_nodebug(&boot_params);
ramdisk_image = boot_params_p->hdr.ramdisk_image;
ramdisk_size = boot_params_p->hdr.ramdisk_size;
initrd_start_early = ramdisk_image;
initrd_end_early = initrd_start_early + ramdisk_size;
_load_ucode_intel_bsp(
- (struct mc_saved_data *)__pa_symbol(&mc_saved_data),
- (unsigned long *)__pa_symbol(&mc_saved_in_initrd),
+ (struct mc_saved_data *)__pa_nodebug(&mc_saved_data),
+ (unsigned long *)__pa_nodebug(&mc_saved_in_initrd),
initrd_start_early, initrd_end_early, &uci);
#else
ramdisk_image = boot_params.hdr.ramdisk_image;
@@ -772,10 +772,10 @@ void __cpuinit load_ucode_intel_ap(void)
unsigned long *initrd_start_p;
mc_saved_in_initrd_p =
- (unsigned long *)__pa_symbol(mc_saved_in_initrd);
- mc_saved_data_p = (struct mc_saved_data *)__pa_symbol(&mc_saved_data);
- initrd_start_p = (unsigned long *)__pa_symbol(&initrd_start);
- initrd_start_addr = (unsigned long)__pa_symbol(*initrd_start_p);
+ (unsigned long *)__pa_nodebug(mc_saved_in_initrd);
+ mc_saved_data_p = (struct mc_saved_data *)__pa_nodebug(&mc_saved_data);
+ initrd_start_p = (unsigned long *)__pa_nodebug(&initrd_start);
+ initrd_start_addr = (unsigned long)__pa_nodebug(*initrd_start_p);
#else
mc_saved_data_p = &mc_saved_data;
mc_saved_in_initrd_p = mc_saved_in_initrd;
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index 4929502c137..ce130493b80 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -71,7 +71,7 @@ static ssize_t msr_read(struct file *file, char __user *buf,
u32 __user *tmp = (u32 __user *) buf;
u32 data[2];
u32 reg = *ppos;
- int cpu = iminor(file->f_path.dentry->d_inode);
+ int cpu = iminor(file_inode(file));
int err = 0;
ssize_t bytes = 0;
@@ -99,7 +99,7 @@ static ssize_t msr_write(struct file *file, const char __user *buf,
const u32 __user *tmp = (const u32 __user *)buf;
u32 data[2];
u32 reg = *ppos;
- int cpu = iminor(file->f_path.dentry->d_inode);
+ int cpu = iminor(file_inode(file));
int err = 0;
ssize_t bytes = 0;
@@ -125,7 +125,7 @@ static long msr_ioctl(struct file *file, unsigned int ioc, unsigned long arg)
{
u32 __user *uregs = (u32 __user *)arg;
u32 regs[8];
- int cpu = iminor(file->f_path.dentry->d_inode);
+ int cpu = iminor(file_inode(file));
int err;
switch (ioc) {
@@ -171,13 +171,12 @@ static long msr_ioctl(struct file *file, unsigned int ioc, unsigned long arg)
static int msr_open(struct inode *inode, struct file *file)
{
- unsigned int cpu;
+ unsigned int cpu = iminor(file_inode(file));
struct cpuinfo_x86 *c;
if (!capable(CAP_SYS_RAWIO))
return -EPERM;
- cpu = iminor(file->f_path.dentry->d_inode);
if (cpu >= nr_cpu_ids || !cpu_online(cpu))
return -ENXIO; /* No such CPU */
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index f84f5c57de3..60308053fdb 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -509,3 +509,4 @@ void local_touch_nmi(void)
{
__this_cpu_write(last_nmi_rip, 0);
}
+EXPORT_SYMBOL_GPL(local_touch_nmi);
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index 85c39590c1a..2cb9470ea85 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -185,7 +185,7 @@ int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i,
for (idx = 0; idx <= (PVCLOCK_FIXMAP_END-PVCLOCK_FIXMAP_BEGIN); idx++) {
__set_fixmap(PVCLOCK_FIXMAP_BEGIN + idx,
- __pa_symbol(i) + (idx*PAGE_SIZE),
+ __pa(i) + (idx*PAGE_SIZE),
PAGE_KERNEL_VVAR);
}
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 9c857f05cef..90d8cc930f5 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -171,9 +171,15 @@ static struct resource bss_resource = {
#ifdef CONFIG_X86_32
/* cpu data as detected by the assembly code in head.S */
-struct cpuinfo_x86 new_cpu_data __cpuinitdata = {0, 0, 0, 0, -1, 1, 0, 0, -1};
+struct cpuinfo_x86 new_cpu_data __cpuinitdata = {
+ .wp_works_ok = -1,
+ .fdiv_bug = -1,
+};
/* common cpu data for all cpus */
-struct cpuinfo_x86 boot_cpu_data __read_mostly = {0, 0, 0, 0, -1, 1, 0, 0, -1};
+struct cpuinfo_x86 boot_cpu_data __read_mostly = {
+ .wp_works_ok = -1,
+ .fdiv_bug = -1,
+};
EXPORT_SYMBOL(boot_cpu_data);
unsigned int def_to_bigsmp;
@@ -1056,15 +1062,6 @@ void __init setup_arch(char **cmdline_p)
setup_bios_corruption_check();
#endif
- /*
- * In the memory hotplug case, the kernel needs info from SRAT to
- * determine which memory is hotpluggable before allocating memory
- * using memblock.
- */
- acpi_boot_table_init();
- early_acpi_boot_init();
- early_parse_srat();
-
#ifdef CONFIG_X86_32
printk(KERN_DEBUG "initial memory mapped: [mem 0x00000000-%#010lx]\n",
(max_pfn_mapped<<PAGE_SHIFT) - 1);
@@ -1110,6 +1107,10 @@ void __init setup_arch(char **cmdline_p)
/*
* Parse the ACPI tables for possible boot-time SMP configuration.
*/
+ acpi_boot_table_init();
+
+ early_acpi_boot_init();
+
initmem_init();
memblock_find_dma_reserve();
@@ -1196,8 +1197,7 @@ void __init setup_arch(char **cmdline_p)
* mismatched firmware/kernel archtectures since there is no
* support for runtime services.
*/
- if (efi_enabled(EFI_BOOT) &&
- IS_ENABLED(CONFIG_X86_64) != efi_enabled(EFI_64BIT)) {
+ if (efi_enabled(EFI_BOOT) && !efi_is_native()) {
pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n");
efi_unmap_memmap();
}
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index a6ceaedc396..9f190a2a00e 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1365,9 +1365,8 @@ static inline void mwait_play_dead(void)
unsigned int eax, ebx, ecx, edx;
unsigned int highest_cstate = 0;
unsigned int highest_subcstate = 0;
- int i;
void *mwait_ptr;
- struct cpuinfo_x86 *c = __this_cpu_ptr(&cpu_info);
+ int i;
if (!this_cpu_has(X86_FEATURE_MWAIT))
return;
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 02b51dd4e4a..f77df1c5de6 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1857,7 +1857,7 @@ int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data)
if (!pv_eoi_enabled(vcpu))
return 0;
return kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.pv_eoi.data,
- addr);
+ addr, sizeof(u8));
}
void kvm_lapic_init(void)
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 4ed3edbe06b..956ca358108 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1644,13 +1644,13 @@ static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp,
static void kvm_mmu_commit_zap_page(struct kvm *kvm,
struct list_head *invalid_list);
-#define for_each_gfn_sp(kvm, sp, gfn, pos) \
- hlist_for_each_entry(sp, pos, \
+#define for_each_gfn_sp(kvm, sp, gfn) \
+ hlist_for_each_entry(sp, \
&(kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)], hash_link) \
if ((sp)->gfn != (gfn)) {} else
-#define for_each_gfn_indirect_valid_sp(kvm, sp, gfn, pos) \
- hlist_for_each_entry(sp, pos, \
+#define for_each_gfn_indirect_valid_sp(kvm, sp, gfn) \
+ hlist_for_each_entry(sp, \
&(kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)], hash_link) \
if ((sp)->gfn != (gfn) || (sp)->role.direct || \
(sp)->role.invalid) {} else
@@ -1706,11 +1706,10 @@ static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
static void kvm_sync_pages(struct kvm_vcpu *vcpu, gfn_t gfn)
{
struct kvm_mmu_page *s;
- struct hlist_node *node;
LIST_HEAD(invalid_list);
bool flush = false;
- for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn, node) {
+ for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn) {
if (!s->unsync)
continue;
@@ -1848,7 +1847,6 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
union kvm_mmu_page_role role;
unsigned quadrant;
struct kvm_mmu_page *sp;
- struct hlist_node *node;
bool need_sync = false;
role = vcpu->arch.mmu.base_role;
@@ -1863,7 +1861,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1;
role.quadrant = quadrant;
}
- for_each_gfn_sp(vcpu->kvm, sp, gfn, node) {
+ for_each_gfn_sp(vcpu->kvm, sp, gfn) {
if (!need_sync && sp->unsync)
need_sync = true;
@@ -2151,14 +2149,13 @@ void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int goal_nr_mmu_pages)
int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
{
struct kvm_mmu_page *sp;
- struct hlist_node *node;
LIST_HEAD(invalid_list);
int r;
pgprintk("%s: looking for gfn %llx\n", __func__, gfn);
r = 0;
spin_lock(&kvm->mmu_lock);
- for_each_gfn_indirect_valid_sp(kvm, sp, gfn, node) {
+ for_each_gfn_indirect_valid_sp(kvm, sp, gfn) {
pgprintk("%s: gfn %llx role %x\n", __func__, gfn,
sp->role.word);
r = 1;
@@ -2288,9 +2285,8 @@ static void __kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
static void kvm_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn)
{
struct kvm_mmu_page *s;
- struct hlist_node *node;
- for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn, node) {
+ for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn) {
if (s->unsync)
continue;
WARN_ON(s->role.level != PT_PAGE_TABLE_LEVEL);
@@ -2302,10 +2298,9 @@ static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn,
bool can_unsync)
{
struct kvm_mmu_page *s;
- struct hlist_node *node;
bool need_unsync = false;
- for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn, node) {
+ for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn) {
if (!can_unsync)
return 1;
@@ -3933,7 +3928,6 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
gfn_t gfn = gpa >> PAGE_SHIFT;
union kvm_mmu_page_role mask = { .word = 0 };
struct kvm_mmu_page *sp;
- struct hlist_node *node;
LIST_HEAD(invalid_list);
u64 entry, gentry, *spte;
int npte;
@@ -3964,7 +3958,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE);
mask.cr0_wp = mask.cr4_pae = mask.nxe = 1;
- for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn, node) {
+ for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) {
if (detect_write_misaligned(sp, gpa, bytes) ||
detect_write_flooding(sp)) {
zap_page |= !!kvm_mmu_prepare_zap_page(vcpu->kvm, sp,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f71500af1f8..e1721324c27 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1406,25 +1406,15 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
unsigned long flags, this_tsc_khz;
struct kvm_vcpu_arch *vcpu = &v->arch;
struct kvm_arch *ka = &v->kvm->arch;
- void *shared_kaddr;
s64 kernel_ns, max_kernel_ns;
u64 tsc_timestamp, host_tsc;
- struct pvclock_vcpu_time_info *guest_hv_clock;
+ struct pvclock_vcpu_time_info guest_hv_clock;
u8 pvclock_flags;
bool use_master_clock;
kernel_ns = 0;
host_tsc = 0;
- /* Keep irq disabled to prevent changes to the clock */
- local_irq_save(flags);
- this_tsc_khz = __get_cpu_var(cpu_tsc_khz);
- if (unlikely(this_tsc_khz == 0)) {
- local_irq_restore(flags);
- kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
- return 1;
- }
-
/*
* If the host uses TSC clock, then passthrough TSC as stable
* to the guest.
@@ -1436,6 +1426,15 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
kernel_ns = ka->master_kernel_ns;
}
spin_unlock(&ka->pvclock_gtod_sync_lock);
+
+ /* Keep irq disabled to prevent changes to the clock */
+ local_irq_save(flags);
+ this_tsc_khz = __get_cpu_var(cpu_tsc_khz);
+ if (unlikely(this_tsc_khz == 0)) {
+ local_irq_restore(flags);
+ kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
+ return 1;
+ }
if (!use_master_clock) {
host_tsc = native_read_tsc();
kernel_ns = get_kernel_ns();
@@ -1463,7 +1462,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
local_irq_restore(flags);
- if (!vcpu->time_page)
+ if (!vcpu->pv_time_enabled)
return 0;
/*
@@ -1525,12 +1524,12 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
*/
vcpu->hv_clock.version += 2;
- shared_kaddr = kmap_atomic(vcpu->time_page);
-
- guest_hv_clock = shared_kaddr + vcpu->time_offset;
+ if (unlikely(kvm_read_guest_cached(v->kvm, &vcpu->pv_time,
+ &guest_hv_clock, sizeof(guest_hv_clock))))
+ return 0;
/* retain PVCLOCK_GUEST_STOPPED if set in guest copy */
- pvclock_flags = (guest_hv_clock->flags & PVCLOCK_GUEST_STOPPED);
+ pvclock_flags = (guest_hv_clock.flags & PVCLOCK_GUEST_STOPPED);
if (vcpu->pvclock_set_guest_stopped_request) {
pvclock_flags |= PVCLOCK_GUEST_STOPPED;
@@ -1543,12 +1542,9 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
vcpu->hv_clock.flags = pvclock_flags;
- memcpy(shared_kaddr + vcpu->time_offset, &vcpu->hv_clock,
- sizeof(vcpu->hv_clock));
-
- kunmap_atomic(shared_kaddr);
-
- mark_page_dirty(v->kvm, vcpu->time >> PAGE_SHIFT);
+ kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
+ &vcpu->hv_clock,
+ sizeof(vcpu->hv_clock));
return 0;
}
@@ -1827,7 +1823,8 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
return 0;
}
- if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa))
+ if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa,
+ sizeof(u32)))
return 1;
vcpu->arch.apf.send_user_only = !(data & KVM_ASYNC_PF_SEND_ALWAYS);
@@ -1837,10 +1834,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
static void kvmclock_reset(struct kvm_vcpu *vcpu)
{
- if (vcpu->arch.time_page) {
- kvm_release_page_dirty(vcpu->arch.time_page);
- vcpu->arch.time_page = NULL;
- }
+ vcpu->arch.pv_time_enabled = false;
}
static void accumulate_steal_time(struct kvm_vcpu *vcpu)
@@ -1947,6 +1941,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
break;
case MSR_KVM_SYSTEM_TIME_NEW:
case MSR_KVM_SYSTEM_TIME: {
+ u64 gpa_offset;
kvmclock_reset(vcpu);
vcpu->arch.time = data;
@@ -1956,14 +1951,14 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
if (!(data & 1))
break;
- /* ...but clean it before doing the actual write */
- vcpu->arch.time_offset = data & ~(PAGE_MASK | 1);
-
- vcpu->arch.time_page =
- gfn_to_page(vcpu->kvm, data >> PAGE_SHIFT);
+ gpa_offset = data & ~(PAGE_MASK | 1);
- if (is_error_page(vcpu->arch.time_page))
- vcpu->arch.time_page = NULL;
+ if (kvm_gfn_to_hva_cache_init(vcpu->kvm,
+ &vcpu->arch.pv_time, data & ~1ULL,
+ sizeof(struct pvclock_vcpu_time_info)))
+ vcpu->arch.pv_time_enabled = false;
+ else
+ vcpu->arch.pv_time_enabled = true;
break;
}
@@ -1980,7 +1975,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
return 1;
if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.st.stime,
- data & KVM_STEAL_VALID_BITS))
+ data & KVM_STEAL_VALID_BITS,
+ sizeof(struct kvm_steal_time)))
return 1;
vcpu->arch.st.msr_val = data;
@@ -2967,7 +2963,7 @@ static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu,
*/
static int kvm_set_guest_paused(struct kvm_vcpu *vcpu)
{
- if (!vcpu->arch.time_page)
+ if (!vcpu->arch.pv_time_enabled)
return -EINVAL;
vcpu->arch.pvclock_set_guest_stopped_request = true;
kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
@@ -6718,6 +6714,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
goto fail_free_wbinvd_dirty_mask;
vcpu->arch.ia32_tsc_adjust_msr = 0x0;
+ vcpu->arch.pv_time_enabled = false;
kvm_async_pf_hash_reset(vcpu);
kvm_pmu_init(vcpu);
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index 05928aae911..906fea31579 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -74,10 +74,10 @@ copy_user_handle_tail(char *to, char *from, unsigned len, unsigned zerorest)
char c;
unsigned zero_len;
- for (; len; --len) {
+ for (; len; --len, to++) {
if (__get_user_nocheck(c, from++, sizeof(char)))
break;
- if (__put_user_nocheck(c, to++, sizeof(char)))
+ if (__put_user_nocheck(c, to, sizeof(char)))
break;
}
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index fb674fd3fc2..2b97525246d 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -939,14 +939,8 @@ spurious_fault(unsigned long error_code, unsigned long address)
if (pmd_large(*pmd))
return spurious_fault_check(error_code, (pte_t *) pmd);
- /*
- * Note: don't use pte_present() here, since it returns true
- * if the _PAGE_PROTNONE bit is set. However, this aliases the
- * _PAGE_GLOBAL bit, which for kernel pages give false positives
- * when CONFIG_DEBUG_PAGEALLOC is used.
- */
pte = pte_offset_kernel(pmd, address);
- if (!(pte_flags(*pte) & _PAGE_PRESENT))
+ if (!pte_present(*pte))
return 0;
ret = spurious_fault_check(error_code, pte);
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 4903a03ae87..59b7fc45327 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -410,9 +410,8 @@ void __init init_mem_mapping(void)
/* the ISA range is always mapped regardless of memory holes */
init_memory_mapping(0, ISA_END_ADDRESS);
- /* xen has big range in reserved near end of ram, skip it at first */
- addr = memblock_find_in_range(ISA_END_ADDRESS, end, PMD_SIZE,
- PAGE_SIZE);
+ /* xen has big range in reserved near end of ram, skip it at first.*/
+ addr = memblock_find_in_range(ISA_END_ADDRESS, end, PMD_SIZE, PMD_SIZE);
real_end = addr + PMD_SIZE;
/* step_size need to be small so pgt_buf from BRK could cover it */
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index dfd30259eb8..72fe01e9e41 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -97,8 +97,7 @@ void numa_set_node(int cpu, int node)
#endif
per_cpu(x86_cpu_to_node_map, cpu) = node;
- if (node != NUMA_NO_NODE)
- set_cpu_numa_node(cpu, node);
+ set_cpu_numa_node(cpu, node);
}
void numa_clear_node(int cpu)
@@ -213,9 +212,10 @@ static void __init setup_node_data(int nid, u64 start, u64 end)
* Allocate node data. Try node-local memory and then any node.
* Never allocate in DMA zone.
*/
- nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid);
+ nd_pa = memblock_alloc_nid(nd_size, SMP_CACHE_BYTES, nid);
if (!nd_pa) {
- pr_err("Cannot find %zu bytes in any node\n", nd_size);
+ pr_err("Cannot find %zu bytes in node %d\n",
+ nd_size, nid);
return;
}
nd = __va(nd_pa);
@@ -560,12 +560,10 @@ static int __init numa_init(int (*init_func)(void))
for (i = 0; i < MAX_LOCAL_APIC; i++)
set_apicid_to_node(i, NUMA_NO_NODE);
- /*
- * Do not clear numa_nodes_parsed or zero numa_meminfo here, because
- * SRAT was parsed earlier in early_parse_srat().
- */
+ nodes_clear(numa_nodes_parsed);
nodes_clear(node_possible_map);
nodes_clear(node_online_map);
+ memset(&numa_meminfo, 0, sizeof(numa_meminfo));
WARN_ON(memblock_set_node(0, ULLONG_MAX, MAX_NUMNODES));
numa_reset_distance();
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index ca1f1c2bb7b..091934e1d0d 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -473,6 +473,19 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
pgprot_val(req_prot) |= pgprot_val(cpa->mask_set);
/*
+ * Set the PSE and GLOBAL flags only if the PRESENT flag is
+ * set otherwise pmd_present/pmd_huge will return true even on
+ * a non present pmd. The canon_pgprot will clear _PAGE_GLOBAL
+ * for the ancient hardware that doesn't support it.
+ */
+ if (pgprot_val(new_prot) & _PAGE_PRESENT)
+ pgprot_val(new_prot) |= _PAGE_PSE | _PAGE_GLOBAL;
+ else
+ pgprot_val(new_prot) &= ~(_PAGE_PSE | _PAGE_GLOBAL);
+
+ new_prot = canon_pgprot(new_prot);
+
+ /*
* old_pte points to the large page base address. So we need
* to add the offset of the virtual address:
*/
@@ -517,7 +530,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
* The address is aligned and the number of pages
* covers the full page.
*/
- new_pte = pfn_pte(pte_pfn(old_pte), canon_pgprot(new_prot));
+ new_pte = pfn_pte(pte_pfn(old_pte), new_prot);
__set_pmd_pte(kpte, address, new_pte);
cpa->flags |= CPA_FLUSHTLB;
do_split = 0;
@@ -561,16 +574,35 @@ int __split_large_page(pte_t *kpte, unsigned long address, pte_t *pbase)
#ifdef CONFIG_X86_64
if (level == PG_LEVEL_1G) {
pfninc = PMD_PAGE_SIZE >> PAGE_SHIFT;
- pgprot_val(ref_prot) |= _PAGE_PSE;
+ /*
+ * Set the PSE flags only if the PRESENT flag is set
+ * otherwise pmd_present/pmd_huge will return true
+ * even on a non present pmd.
+ */
+ if (pgprot_val(ref_prot) & _PAGE_PRESENT)
+ pgprot_val(ref_prot) |= _PAGE_PSE;
+ else
+ pgprot_val(ref_prot) &= ~_PAGE_PSE;
}
#endif
/*
+ * Set the GLOBAL flags only if the PRESENT flag is set
+ * otherwise pmd/pte_present will return true even on a non
+ * present pmd/pte. The canon_pgprot will clear _PAGE_GLOBAL
+ * for the ancient hardware that doesn't support it.
+ */
+ if (pgprot_val(ref_prot) & _PAGE_PRESENT)
+ pgprot_val(ref_prot) |= _PAGE_GLOBAL;
+ else
+ pgprot_val(ref_prot) &= ~_PAGE_GLOBAL;
+
+ /*
* Get the target pfn from the original entry:
*/
pfn = pte_pfn(*kpte);
for (i = 0; i < PTRS_PER_PTE; i++, pfn += pfninc)
- set_pte(&pbase[i], pfn_pte(pfn, ref_prot));
+ set_pte(&pbase[i], pfn_pte(pfn, canon_pgprot(ref_prot)));
if (pfn_range_is_mapped(PFN_DOWN(__pa(address)),
PFN_DOWN(__pa(address)) + 1))
@@ -685,6 +717,18 @@ repeat:
new_prot = static_protections(new_prot, address, pfn);
/*
+ * Set the GLOBAL flags only if the PRESENT flag is
+ * set otherwise pte_present will return true even on
+ * a non present pte. The canon_pgprot will clear
+ * _PAGE_GLOBAL for the ancient hardware that doesn't
+ * support it.
+ */
+ if (pgprot_val(new_prot) & _PAGE_PRESENT)
+ pgprot_val(new_prot) |= _PAGE_GLOBAL;
+ else
+ pgprot_val(new_prot) &= ~_PAGE_GLOBAL;
+
+ /*
* We need to keep the pfn from the existing PTE,
* after all we're only going to change it's attributes
* not the memory it points to
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 2610bd93c89..657438858e8 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -563,6 +563,13 @@ int kernel_map_sync_memtype(u64 base, unsigned long size, unsigned long flags)
if (base > __pa(high_memory-1))
return 0;
+ /*
+ * some areas in the middle of the kernel identity range
+ * are not mapped, like the PCI space.
+ */
+ if (!page_is_ram(base >> PAGE_SHIFT))
+ return 0;
+
id_sz = (__pa(high_memory-1) <= base + size) ?
__pa(high_memory) - base :
size;
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index 79836d01f78..cdd0da9dd53 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -141,126 +141,11 @@ static inline int save_add_info(void) {return 1;}
static inline int save_add_info(void) {return 0;}
#endif
-#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
-static void __init
-handle_movablemem(int node, u64 start, u64 end, u32 hotpluggable)
-{
- int overlap, i;
- unsigned long start_pfn, end_pfn;
-
- start_pfn = PFN_DOWN(start);
- end_pfn = PFN_UP(end);
-
- /*
- * For movablemem_map=acpi:
- *
- * SRAT: |_____| |_____| |_________| |_________| ......
- * node id: 0 1 1 2
- * hotpluggable: n y y n
- * movablemem_map: |_____| |_________|
- *
- * Using movablemem_map, we can prevent memblock from allocating memory
- * on ZONE_MOVABLE at boot time.
- *
- * Before parsing SRAT, memblock has already reserve some memory ranges
- * for other purposes, such as for kernel image. We cannot prevent
- * kernel from using these memory, so we need to exclude these memory
- * even if it is hotpluggable.
- * Furthermore, to ensure the kernel has enough memory to boot, we make
- * all the memory on the node which the kernel resides in
- * un-hotpluggable.
- */
- if (hotpluggable && movablemem_map.acpi) {
- /* Exclude ranges reserved by memblock. */
- struct memblock_type *rgn = &memblock.reserved;
-
- for (i = 0; i < rgn->cnt; i++) {
- if (end <= rgn->regions[i].base ||
- start >= rgn->regions[i].base +
- rgn->regions[i].size)
- continue;
-
- /*
- * If the memory range overlaps the memory reserved by
- * memblock, then the kernel resides in this node.
- */
- node_set(node, movablemem_map.numa_nodes_kernel);
-
- goto out;
- }
-
- /*
- * If the kernel resides in this node, then the whole node
- * should not be hotpluggable.
- */
- if (node_isset(node, movablemem_map.numa_nodes_kernel))
- goto out;
-
- insert_movablemem_map(start_pfn, end_pfn);
-
- /*
- * numa_nodes_hotplug nodemask represents which nodes are put
- * into movablemem_map.map[].
- */
- node_set(node, movablemem_map.numa_nodes_hotplug);
- goto out;
- }
-
- /*
- * For movablemem_map=nn[KMG]@ss[KMG]:
- *
- * SRAT: |_____| |_____| |_________| |_________| ......
- * node id: 0 1 1 2
- * user specified: |__| |___|
- * movablemem_map: |___| |_________| |______| ......
- *
- * Using movablemem_map, we can prevent memblock from allocating memory
- * on ZONE_MOVABLE at boot time.
- *
- * NOTE: In this case, SRAT info will be ingored.
- */
- overlap = movablemem_map_overlap(start_pfn, end_pfn);
- if (overlap >= 0) {
- /*
- * If part of this range is in movablemem_map, we need to
- * add the range after it to extend the range to the end
- * of the node, because from the min address specified to
- * the end of the node will be ZONE_MOVABLE.
- */
- start_pfn = max(start_pfn,
- movablemem_map.map[overlap].start_pfn);
- insert_movablemem_map(start_pfn, end_pfn);
-
- /*
- * Set the nodemask, so that if the address range on one node
- * is not continuse, we can add the subsequent ranges on the
- * same node into movablemem_map.
- */
- node_set(node, movablemem_map.numa_nodes_hotplug);
- } else {
- if (node_isset(node, movablemem_map.numa_nodes_hotplug))
- /*
- * Insert the range if we already have movable ranges
- * on the same node.
- */
- insert_movablemem_map(start_pfn, end_pfn);
- }
-out:
- return;
-}
-#else /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
-static inline void
-handle_movablemem(int node, u64 start, u64 end, u32 hotpluggable)
-{
-}
-#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
-
/* Callback for parsing of the Proximity Domain <-> Memory Area mappings */
int __init
acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
{
u64 start, end;
- u32 hotpluggable;
int node, pxm;
if (srat_disabled())
@@ -269,8 +154,7 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
goto out_err_bad_srat;
if ((ma->flags & ACPI_SRAT_MEM_ENABLED) == 0)
goto out_err;
- hotpluggable = ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE;
- if (hotpluggable && !save_add_info())
+ if ((ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) && !save_add_info())
goto out_err;
start = ma->base_address;
@@ -290,12 +174,9 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
node_set(node, numa_nodes_parsed);
- printk(KERN_INFO "SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx] %s\n",
+ printk(KERN_INFO "SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]\n",
node, pxm,
- (unsigned long long) start, (unsigned long long) end - 1,
- hotpluggable ? "Hot Pluggable": "");
-
- handle_movablemem(node, start, end, hotpluggable);
+ (unsigned long long) start, (unsigned long long) end - 1);
return 0;
out_err_bad_srat:
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index 53ea60458e0..3e724256dbe 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -521,6 +521,7 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)
sd = &info->sd;
sd->domain = domain;
sd->node = node;
+ sd->acpi = device->handle;
/*
* Maybe the desired pci bus has been already scanned. In such case
* it is unnecessary to scan the pci bus with the given domain,busnum.
@@ -592,6 +593,14 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)
return bus;
}
+int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge)
+{
+ struct pci_sysdata *sd = bridge->bus->sysdata;
+
+ ACPI_HANDLE_SET(&bridge->dev, sd->acpi);
+ return 0;
+}
+
int __init pci_acpi_init(void)
{
struct pci_dev *dev = NULL;
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index ccd0ab3ab89..901177d75ff 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -34,7 +34,6 @@ int noioapicreroute = 1;
#endif
int pcibios_last_bus = -1;
unsigned long pirq_table_addr;
-struct pci_bus *pci_root_bus;
const struct pci_raw_ops *__read_mostly raw_pci_ops;
const struct pci_raw_ops *__read_mostly raw_pci_ext_ops;
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index dd8ca6f7223..94919e307f8 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -51,6 +51,7 @@ struct pcibios_fwaddrmap {
static LIST_HEAD(pcibios_fwaddrmappings);
static DEFINE_SPINLOCK(pcibios_fwaddrmap_lock);
+static bool pcibios_fw_addr_done;
/* Must be called with 'pcibios_fwaddrmap_lock' lock held. */
static struct pcibios_fwaddrmap *pcibios_fwaddrmap_lookup(struct pci_dev *dev)
@@ -72,6 +73,9 @@ pcibios_save_fw_addr(struct pci_dev *dev, int idx, resource_size_t fw_addr)
unsigned long flags;
struct pcibios_fwaddrmap *map;
+ if (pcibios_fw_addr_done)
+ return;
+
spin_lock_irqsave(&pcibios_fwaddrmap_lock, flags);
map = pcibios_fwaddrmap_lookup(dev);
if (!map) {
@@ -97,6 +101,9 @@ resource_size_t pcibios_retrieve_fw_addr(struct pci_dev *dev, int idx)
struct pcibios_fwaddrmap *map;
resource_size_t fw_addr = 0;
+ if (pcibios_fw_addr_done)
+ return 0;
+
spin_lock_irqsave(&pcibios_fwaddrmap_lock, flags);
map = pcibios_fwaddrmap_lookup(dev);
if (map)
@@ -106,7 +113,7 @@ resource_size_t pcibios_retrieve_fw_addr(struct pci_dev *dev, int idx)
return fw_addr;
}
-static void pcibios_fw_addr_list_del(void)
+static void __init pcibios_fw_addr_list_del(void)
{
unsigned long flags;
struct pcibios_fwaddrmap *entry, *next;
@@ -118,6 +125,7 @@ static void pcibios_fw_addr_list_del(void)
kfree(entry);
}
spin_unlock_irqrestore(&pcibios_fwaddrmap_lock, flags);
+ pcibios_fw_addr_done = true;
}
static int
@@ -193,46 +201,46 @@ EXPORT_SYMBOL(pcibios_align_resource);
* as well.
*/
-static void __init pcibios_allocate_bus_resources(struct list_head *bus_list)
+static void pcibios_allocate_bridge_resources(struct pci_dev *dev)
{
- struct pci_bus *bus;
- struct pci_dev *dev;
int idx;
struct resource *r;
- /* Depth-First Search on bus tree */
- list_for_each_entry(bus, bus_list, node) {
- if ((dev = bus->self)) {
- for (idx = PCI_BRIDGE_RESOURCES;
- idx < PCI_NUM_RESOURCES; idx++) {
- r = &dev->resource[idx];
- if (!r->flags)
- continue;
- if (!r->start ||
- pci_claim_resource(dev, idx) < 0) {
- /*
- * Something is wrong with the region.
- * Invalidate the resource to prevent
- * child resource allocations in this
- * range.
- */
- r->start = r->end = 0;
- r->flags = 0;
- }
- }
+ for (idx = PCI_BRIDGE_RESOURCES; idx < PCI_NUM_RESOURCES; idx++) {
+ r = &dev->resource[idx];
+ if (!r->flags)
+ continue;
+ if (!r->start || pci_claim_resource(dev, idx) < 0) {
+ /*
+ * Something is wrong with the region.
+ * Invalidate the resource to prevent
+ * child resource allocations in this
+ * range.
+ */
+ r->start = r->end = 0;
+ r->flags = 0;
}
- pcibios_allocate_bus_resources(&bus->children);
}
}
+static void pcibios_allocate_bus_resources(struct pci_bus *bus)
+{
+ struct pci_bus *child;
+
+ /* Depth-First Search on bus tree */
+ if (bus->self)
+ pcibios_allocate_bridge_resources(bus->self);
+ list_for_each_entry(child, &bus->children, node)
+ pcibios_allocate_bus_resources(child);
+}
+
struct pci_check_idx_range {
int start;
int end;
};
-static void __init pcibios_allocate_resources(int pass)
+static void pcibios_allocate_dev_resources(struct pci_dev *dev, int pass)
{
- struct pci_dev *dev = NULL;
int idx, disabled, i;
u16 command;
struct resource *r;
@@ -244,14 +252,13 @@ static void __init pcibios_allocate_resources(int pass)
#endif
};
- for_each_pci_dev(dev) {
- pci_read_config_word(dev, PCI_COMMAND, &command);
- for (i = 0; i < ARRAY_SIZE(idx_range); i++)
+ pci_read_config_word(dev, PCI_COMMAND, &command);
+ for (i = 0; i < ARRAY_SIZE(idx_range); i++)
for (idx = idx_range[i].start; idx <= idx_range[i].end; idx++) {
r = &dev->resource[idx];
- if (r->parent) /* Already allocated */
+ if (r->parent) /* Already allocated */
continue;
- if (!r->start) /* Address not assigned at all */
+ if (!r->start) /* Address not assigned at all */
continue;
if (r->flags & IORESOURCE_IO)
disabled = !(command & PCI_COMMAND_IO);
@@ -270,44 +277,74 @@ static void __init pcibios_allocate_resources(int pass)
}
}
}
- if (!pass) {
- r = &dev->resource[PCI_ROM_RESOURCE];
- if (r->flags & IORESOURCE_ROM_ENABLE) {
- /* Turn the ROM off, leave the resource region,
- * but keep it unregistered. */
- u32 reg;
- dev_dbg(&dev->dev, "disabling ROM %pR\n", r);
- r->flags &= ~IORESOURCE_ROM_ENABLE;
- pci_read_config_dword(dev,
- dev->rom_base_reg, &reg);
- pci_write_config_dword(dev, dev->rom_base_reg,
+ if (!pass) {
+ r = &dev->resource[PCI_ROM_RESOURCE];
+ if (r->flags & IORESOURCE_ROM_ENABLE) {
+ /* Turn the ROM off, leave the resource region,
+ * but keep it unregistered. */
+ u32 reg;
+ dev_dbg(&dev->dev, "disabling ROM %pR\n", r);
+ r->flags &= ~IORESOURCE_ROM_ENABLE;
+ pci_read_config_dword(dev, dev->rom_base_reg, &reg);
+ pci_write_config_dword(dev, dev->rom_base_reg,
reg & ~PCI_ROM_ADDRESS_ENABLE);
- }
}
}
}
-static int __init pcibios_assign_resources(void)
+static void pcibios_allocate_resources(struct pci_bus *bus, int pass)
+{
+ struct pci_dev *dev;
+ struct pci_bus *child;
+
+ list_for_each_entry(dev, &bus->devices, bus_list) {
+ pcibios_allocate_dev_resources(dev, pass);
+
+ child = dev->subordinate;
+ if (child)
+ pcibios_allocate_resources(child, pass);
+ }
+}
+
+static void pcibios_allocate_dev_rom_resource(struct pci_dev *dev)
{
- struct pci_dev *dev = NULL;
struct resource *r;
- if (!(pci_probe & PCI_ASSIGN_ROMS)) {
- /*
- * Try to use BIOS settings for ROMs, otherwise let
- * pci_assign_unassigned_resources() allocate the new
- * addresses.
- */
- for_each_pci_dev(dev) {
- r = &dev->resource[PCI_ROM_RESOURCE];
- if (!r->flags || !r->start)
- continue;
- if (pci_claim_resource(dev, PCI_ROM_RESOURCE) < 0) {
- r->end -= r->start;
- r->start = 0;
- }
- }
+ /*
+ * Try to use BIOS settings for ROMs, otherwise let
+ * pci_assign_unassigned_resources() allocate the new
+ * addresses.
+ */
+ r = &dev->resource[PCI_ROM_RESOURCE];
+ if (!r->flags || !r->start)
+ return;
+
+ if (pci_claim_resource(dev, PCI_ROM_RESOURCE) < 0) {
+ r->end -= r->start;
+ r->start = 0;
}
+}
+static void pcibios_allocate_rom_resources(struct pci_bus *bus)
+{
+ struct pci_dev *dev;
+ struct pci_bus *child;
+
+ list_for_each_entry(dev, &bus->devices, bus_list) {
+ pcibios_allocate_dev_rom_resource(dev);
+
+ child = dev->subordinate;
+ if (child)
+ pcibios_allocate_rom_resources(child);
+ }
+}
+
+static int __init pcibios_assign_resources(void)
+{
+ struct pci_bus *bus;
+
+ if (!(pci_probe & PCI_ASSIGN_ROMS))
+ list_for_each_entry(bus, &pci_root_buses, node)
+ pcibios_allocate_rom_resources(bus);
pci_assign_unassigned_resources();
pcibios_fw_addr_list_del();
@@ -315,12 +352,32 @@ static int __init pcibios_assign_resources(void)
return 0;
}
+void pcibios_resource_survey_bus(struct pci_bus *bus)
+{
+ dev_printk(KERN_DEBUG, &bus->dev, "Allocating resources\n");
+
+ pcibios_allocate_bus_resources(bus);
+
+ pcibios_allocate_resources(bus, 0);
+ pcibios_allocate_resources(bus, 1);
+
+ if (!(pci_probe & PCI_ASSIGN_ROMS))
+ pcibios_allocate_rom_resources(bus);
+}
+
void __init pcibios_resource_survey(void)
{
+ struct pci_bus *bus;
+
DBG("PCI: Allocating resources\n");
- pcibios_allocate_bus_resources(&pci_root_buses);
- pcibios_allocate_resources(0);
- pcibios_allocate_resources(1);
+
+ list_for_each_entry(bus, &pci_root_buses, node)
+ pcibios_allocate_bus_resources(bus);
+
+ list_for_each_entry(bus, &pci_root_buses, node)
+ pcibios_allocate_resources(bus, 0);
+ list_for_each_entry(bus, &pci_root_buses, node)
+ pcibios_allocate_resources(bus, 1);
e820_reserve_resources_late();
/*
diff --git a/arch/x86/pci/legacy.c b/arch/x86/pci/legacy.c
index 4a2ab9cb365..4db96fb1c23 100644
--- a/arch/x86/pci/legacy.c
+++ b/arch/x86/pci/legacy.c
@@ -30,7 +30,7 @@ int __init pci_legacy_init(void)
}
printk("PCI: Probing PCI hardware\n");
- pci_root_bus = pcibios_scan_root(0);
+ pcibios_scan_root(0);
return 0;
}
diff --git a/arch/x86/pci/numaq_32.c b/arch/x86/pci/numaq_32.c
index b96b14c250b..72c229f9ebc 100644
--- a/arch/x86/pci/numaq_32.c
+++ b/arch/x86/pci/numaq_32.c
@@ -152,7 +152,7 @@ int __init pci_numaq_init(void)
raw_pci_ops = &pci_direct_conf1_mq;
- pci_root_bus = pcibios_scan_root(0);
+ pcibios_scan_root(0);
if (num_online_nodes() > 1)
for_each_online_node(quad) {
if (quad == 0)
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 70b2a3a305d..5f2ecaf3f9d 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -69,11 +69,6 @@ struct efi_memory_map memmap;
static struct efi efi_phys __initdata;
static efi_system_table_t efi_systab __initdata;
-static inline bool efi_is_native(void)
-{
- return IS_ENABLED(CONFIG_X86_64) == efi_enabled(EFI_64BIT);
-}
-
unsigned long x86_efi_facility;
/*
@@ -85,9 +80,10 @@ int efi_enabled(int facility)
}
EXPORT_SYMBOL(efi_enabled);
+static bool __initdata disable_runtime = false;
static int __init setup_noefi(char *arg)
{
- clear_bit(EFI_RUNTIME_SERVICES, &x86_efi_facility);
+ disable_runtime = true;
return 0;
}
early_param("noefi", setup_noefi);
@@ -734,7 +730,7 @@ void __init efi_init(void)
if (!efi_is_native())
pr_info("No EFI runtime due to 32/64-bit mismatch with kernel\n");
else {
- if (efi_runtime_init())
+ if (disable_runtime || efi_runtime_init())
return;
set_bit(EFI_RUNTIME_SERVICES, &x86_efi_facility);
}
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 120cee1c3f8..3c68768d7a7 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -11,6 +11,7 @@
#include <linux/suspend.h>
#include <linux/export.h>
#include <linux/smp.h>
+#include <linux/perf_event.h>
#include <asm/pgtable.h>
#include <asm/proto.h>
@@ -228,6 +229,7 @@ static void __restore_processor_state(struct saved_context *ctxt)
do_fpu_end();
x86_platform.restore_sched_clock_state();
mtrr_bp_restore();
+ perf_restore_debug_store();
}
/* Needed by apm.c */
diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/syscalls/syscall_32.tbl
index f2fe78ff22c..e6d55f0064d 100644
--- a/arch/x86/syscalls/syscall_32.tbl
+++ b/arch/x86/syscalls/syscall_32.tbl
@@ -25,7 +25,7 @@
16 i386 lchown sys_lchown16
17 i386 break
18 i386 oldstat sys_stat
-19 i386 lseek sys_lseek sys32_lseek
+19 i386 lseek sys_lseek compat_sys_lseek
20 i386 getpid sys_getpid
21 i386 mount sys_mount compat_sys_mount
22 i386 umount sys_oldumount
@@ -98,8 +98,8 @@
89 i386 readdir sys_old_readdir compat_sys_old_readdir
90 i386 mmap sys_old_mmap sys32_mmap
91 i386 munmap sys_munmap
-92 i386 truncate sys_truncate
-93 i386 ftruncate sys_ftruncate
+92 i386 truncate sys_truncate compat_sys_truncate
+93 i386 ftruncate sys_ftruncate compat_sys_ftruncate
94 i386 fchmod sys_fchmod
95 i386 fchown sys_fchown16
96 i386 getpriority sys_getpriority