diff options
Diffstat (limited to 'arch/x86')
257 files changed, 7012 insertions, 4571 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index d5ed94d30aa..01115d54c5b 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -8,6 +8,7 @@ config 64BIT config X86_32 def_bool !64BIT + select CLKSRC_I8253 config X86_64 def_bool 64BIT @@ -64,9 +65,14 @@ config X86 select HAVE_TEXT_POKE_SMP select HAVE_GENERIC_HARDIRQS select HAVE_SPARSE_IRQ + select GENERIC_FIND_FIRST_BIT + select GENERIC_FIND_NEXT_BIT select GENERIC_IRQ_PROBE select GENERIC_PENDING_IRQ if SMP + select GENERIC_IRQ_SHOW + select IRQ_FORCED_THREADING select USE_GENERIC_SMP_HELPERS if SMP + select ARCH_NO_SYSDEV_OPS config INSTRUCTION_DECODER def_bool (KPROBES || PERF_EVENTS) @@ -119,7 +125,7 @@ config NEED_SG_DMA_LENGTH def_bool y config GENERIC_ISA_DMA - def_bool y + def_bool ISA_DMA_API config GENERIC_IOMAP def_bool y @@ -139,7 +145,7 @@ config GENERIC_GPIO bool config ARCH_MAY_HAVE_PC_FDC - def_bool y + def_bool ISA_DMA_API config RWSEM_GENERIC_SPINLOCK def_bool !X86_XADD @@ -217,10 +223,6 @@ config X86_HT def_bool y depends on SMP -config X86_TRAMPOLINE - def_bool y - depends on SMP || (64BIT && ACPI_SLEEP) - config X86_32_LAZY_GS def_bool y depends on X86_32 && !CC_STACKPROTECTOR @@ -382,6 +384,8 @@ config X86_INTEL_CE depends on X86_32 depends on X86_EXTENDED_PLATFORM select X86_REBOOTFIXUPS + select OF + select OF_EARLY_FLATTREE ---help--- Select for the Intel CE media processor (CE4100) SOC. This option compiles in support for the CE4100 SOC for settop @@ -811,7 +815,7 @@ config X86_LOCAL_APIC config X86_IO_APIC def_bool y - depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC + depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_IOAPIC config X86_VISWS_APIC def_bool y @@ -1705,7 +1709,7 @@ config HAVE_ARCH_EARLY_PFN_TO_NID depends on NUMA config USE_PERCPU_NUMA_NODE_ID - def_bool X86_64 + def_bool y depends on NUMA menu "Power management and ACPI options" @@ -2000,9 +2004,13 @@ source "drivers/pci/pcie/Kconfig" source "drivers/pci/Kconfig" -# x86_64 have no ISA slots, but do have ISA-style DMA. +# x86_64 have no ISA slots, but can have ISA-style DMA. config ISA_DMA_API - def_bool y + bool "ISA-style DMA support" if (X86_64 && EXPERT) + default y + help + Enables ISA-style DMA support for devices requiring such controllers. + If unsure, say Y. if X86_32 @@ -2066,9 +2074,10 @@ config SCx200HR_TIMER config OLPC bool "One Laptop Per Child support" + depends on !X86_PAE select GPIOLIB - select OLPC_OPENFIRMWARE - depends on !X86_64 && !X86_PAE + select OF + select OF_PROMTREE if PROC_DEVICETREE ---help--- Add support for detecting the unique features of the OLPC XO hardware. @@ -2079,21 +2088,6 @@ config OLPC_XO1 ---help--- Add support for non-essential features of the OLPC XO-1 laptop. -config OLPC_OPENFIRMWARE - bool "Support for OLPC's Open Firmware" - depends on !X86_64 && !X86_PAE - default n - select OF - help - This option adds support for the implementation of Open Firmware - that is used on the OLPC XO-1 Children's Machine. - If unsure, say N here. - -config OLPC_OPENFIRMWARE_DT - bool - default y if OLPC_OPENFIRMWARE && PROC_DEVICETREE - select OF_PROMTREE - endif # X86_32 config AMD_NB @@ -2104,6 +2098,16 @@ source "drivers/pcmcia/Kconfig" source "drivers/pci/hotplug/Kconfig" +config RAPIDIO + bool "RapidIO support" + depends on PCI + default n + help + If you say Y here, the kernel will include drivers and + infrastructure code to support RapidIO interconnect devices. + +source "drivers/rapidio/Kconfig" + endmenu @@ -2138,6 +2142,11 @@ config SYSVIPC_COMPAT def_bool y depends on COMPAT && SYSVIPC +config KEYS_COMPAT + bool + depends on COMPAT && KEYS + default y + endmenu diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 283c5a6a03a..d161e939df6 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -294,11 +294,6 @@ config X86_GENERIC endif -config X86_CPU - def_bool y - select GENERIC_FIND_FIRST_BIT - select GENERIC_FIND_NEXT_BIT - # # Define implied options from the CPU selection here config X86_INTERNODE_CACHE_SHIFT @@ -331,7 +326,7 @@ config X86_PPRO_FENCE Old PentiumPro multiprocessor systems had errata that could cause memory operations to violate the x86 ordering standard in rare cases. Enabling this option will attempt to work around some (but not all) - occurances of this problem, at the cost of much heavier spinlock and + occurrences of this problem, at the cost of much heavier spinlock and memory barrier operations. If unsure, say n here. Even distro kernels should think twice before @@ -371,7 +366,7 @@ config X86_INTEL_USERCOPY config X86_USE_PPRO_CHECKSUM def_bool y - depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MEFFICEON || MGEODE_LX || MCORE2 || MATOM + depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MVIAC7 || MEFFICEON || MGEODE_LX || MCORE2 || MATOM config X86_USE_3DNOW def_bool y diff --git a/arch/x86/boot/compressed/mkpiggy.c b/arch/x86/boot/compressed/mkpiggy.c index 646aa78ba5f..46a82388243 100644 --- a/arch/x86/boot/compressed/mkpiggy.c +++ b/arch/x86/boot/compressed/mkpiggy.c @@ -62,7 +62,12 @@ int main(int argc, char *argv[]) if (fseek(f, -4L, SEEK_END)) { perror(argv[1]); } - fread(&olen, sizeof olen, 1, f); + + if (fread(&olen, sizeof(olen), 1, f) != 1) { + perror(argv[1]); + return 1; + } + ilen = ftell(f); olen = getle32(&olen); fclose(f); diff --git a/arch/x86/boot/memory.c b/arch/x86/boot/memory.c index cae3feb1035..db75d07c364 100644 --- a/arch/x86/boot/memory.c +++ b/arch/x86/boot/memory.c @@ -91,7 +91,7 @@ static int detect_memory_e801(void) if (oreg.ax > 15*1024) { return -1; /* Bogus! */ } else if (oreg.ax == 15*1024) { - boot_params.alt_mem_k = (oreg.dx << 6) + oreg.ax; + boot_params.alt_mem_k = (oreg.bx << 6) + oreg.ax; } else { /* * This ignores memory above 16MB if we have a memory diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S index 8fe2a4966b7..be6d9e365a8 100644 --- a/arch/x86/crypto/aesni-intel_asm.S +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -1346,7 +1346,7 @@ _zero_cipher_left_decrypt: and $15, %r13 # %r13 = arg4 (mod 16) je _multiple_of_16_bytes_decrypt - # Handle the last <16 byte block seperately + # Handle the last <16 byte block separately paddd ONE(%rip), %xmm0 # increment CNT to get Yn movdqa SHUF_MASK(%rip), %xmm10 @@ -1355,7 +1355,7 @@ _zero_cipher_left_decrypt: ENCRYPT_SINGLE_BLOCK %xmm0, %xmm1 # E(K, Yn) sub $16, %r11 add %r13, %r11 - movdqu (%arg3,%r11,1), %xmm1 # recieve the last <16 byte block + movdqu (%arg3,%r11,1), %xmm1 # receive the last <16 byte block lea SHIFT_MASK+16(%rip), %r12 sub %r13, %r12 # adjust the shuffle mask pointer to be able to shift 16-%r13 bytes @@ -1607,11 +1607,12 @@ _zero_cipher_left_encrypt: and $15, %r13 # %r13 = arg4 (mod 16) je _multiple_of_16_bytes_encrypt - # Handle the last <16 Byte block seperately + # Handle the last <16 Byte block separately paddd ONE(%rip), %xmm0 # INCR CNT to get Yn movdqa SHUF_MASK(%rip), %xmm10 PSHUFB_XMM %xmm10, %xmm0 + ENCRYPT_SINGLE_BLOCK %xmm0, %xmm1 # Encrypt(K, Yn) sub $16, %r11 add %r13, %r11 @@ -1634,7 +1635,9 @@ _zero_cipher_left_encrypt: # GHASH computation for the last <16 byte block sub %r13, %r11 add $16, %r11 - PSHUFB_XMM %xmm10, %xmm1 + + movdqa SHUF_MASK(%rip), %xmm10 + PSHUFB_XMM %xmm10, %xmm0 # shuffle xmm0 back to output as ciphertext diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index e1e60c7d581..2577613fb32 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -828,9 +828,15 @@ static int rfc4106_init(struct crypto_tfm *tfm) struct cryptd_aead *cryptd_tfm; struct aesni_rfc4106_gcm_ctx *ctx = (struct aesni_rfc4106_gcm_ctx *) PTR_ALIGN((u8 *)crypto_tfm_ctx(tfm), AESNI_ALIGN); + struct crypto_aead *cryptd_child; + struct aesni_rfc4106_gcm_ctx *child_ctx; cryptd_tfm = cryptd_alloc_aead("__driver-gcm-aes-aesni", 0, 0); if (IS_ERR(cryptd_tfm)) return PTR_ERR(cryptd_tfm); + + cryptd_child = cryptd_aead_child(cryptd_tfm); + child_ctx = aesni_rfc4106_gcm_ctx_get(cryptd_child); + memcpy(child_ctx, ctx, sizeof(*ctx)); ctx->cryptd_tfm = cryptd_tfm; tfm->crt_aead.reqsize = sizeof(struct aead_request) + crypto_aead_reqsize(&cryptd_tfm->base); @@ -873,22 +879,18 @@ rfc4106_set_hash_subkey(u8 *hash_subkey, const u8 *key, unsigned int key_len) crypto_ablkcipher_clear_flags(ctr_tfm, ~0); ret = crypto_ablkcipher_setkey(ctr_tfm, key, key_len); - if (ret) { - crypto_free_ablkcipher(ctr_tfm); - return ret; - } + if (ret) + goto out_free_ablkcipher; + ret = -ENOMEM; req = ablkcipher_request_alloc(ctr_tfm, GFP_KERNEL); - if (!req) { - crypto_free_ablkcipher(ctr_tfm); - return -EINVAL; - } + if (!req) + goto out_free_ablkcipher; req_data = kmalloc(sizeof(*req_data), GFP_KERNEL); - if (!req_data) { - crypto_free_ablkcipher(ctr_tfm); - return -ENOMEM; - } + if (!req_data) + goto out_free_request; + memset(req_data->iv, 0, sizeof(req_data->iv)); /* Clear the data in the hash sub key container to zero.*/ @@ -913,8 +915,10 @@ rfc4106_set_hash_subkey(u8 *hash_subkey, const u8 *key, unsigned int key_len) if (!ret) ret = req_data->result.err; } - ablkcipher_request_free(req); kfree(req_data); +out_free_request: + ablkcipher_request_free(req); +out_free_ablkcipher: crypto_free_ablkcipher(ctr_tfm); return ret; } @@ -925,6 +929,9 @@ static int rfc4106_set_key(struct crypto_aead *parent, const u8 *key, int ret = 0; struct crypto_tfm *tfm = crypto_aead_tfm(parent); struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(parent); + struct crypto_aead *cryptd_child = cryptd_aead_child(ctx->cryptd_tfm); + struct aesni_rfc4106_gcm_ctx *child_ctx = + aesni_rfc4106_gcm_ctx_get(cryptd_child); u8 *new_key_mem = NULL; if (key_len < 4) { @@ -968,6 +975,7 @@ static int rfc4106_set_key(struct crypto_aead *parent, const u8 *key, goto exit; } ret = rfc4106_set_hash_subkey(ctx->hash_subkey, key, key_len); + memcpy(child_ctx, ctx, sizeof(*ctx)); exit: kfree(new_key_mem); return ret; @@ -999,7 +1007,6 @@ static int rfc4106_encrypt(struct aead_request *req) int ret; struct crypto_aead *tfm = crypto_aead_reqtfm(req); struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm); - struct crypto_aead *cryptd_child = cryptd_aead_child(ctx->cryptd_tfm); if (!irq_fpu_usable()) { struct aead_request *cryptd_req = @@ -1008,6 +1015,7 @@ static int rfc4106_encrypt(struct aead_request *req) aead_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base); return crypto_aead_encrypt(cryptd_req); } else { + struct crypto_aead *cryptd_child = cryptd_aead_child(ctx->cryptd_tfm); kernel_fpu_begin(); ret = cryptd_child->base.crt_aead.encrypt(req); kernel_fpu_end(); @@ -1020,7 +1028,6 @@ static int rfc4106_decrypt(struct aead_request *req) int ret; struct crypto_aead *tfm = crypto_aead_reqtfm(req); struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm); - struct crypto_aead *cryptd_child = cryptd_aead_child(ctx->cryptd_tfm); if (!irq_fpu_usable()) { struct aead_request *cryptd_req = @@ -1029,6 +1036,7 @@ static int rfc4106_decrypt(struct aead_request *req) aead_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base); return crypto_aead_decrypt(cryptd_req); } else { + struct crypto_aead *cryptd_child = cryptd_aead_child(ctx->cryptd_tfm); kernel_fpu_begin(); ret = cryptd_child->base.crt_aead.decrypt(req); kernel_fpu_end(); diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index 2d93bdbc9ac..fd843877e84 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -298,6 +298,7 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs) /* OK, This is the point of no return */ set_personality(PER_LINUX); set_thread_flag(TIF_IA32); + current->mm->context.ia32_compat = 1; setup_new_exec(bprm); diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 518bb99c339..849a9d23c71 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -25,6 +25,8 @@ #define sysretl_audit ia32_ret_from_sys_call #endif + .section .entry.text, "ax" + #define IA32_NR_syscalls ((ia32_syscall_end - ia32_sys_call_table)/8) .macro IA32_ARG_FIXUP noebp=0 @@ -126,26 +128,20 @@ ENTRY(ia32_sysenter_target) */ ENABLE_INTERRUPTS(CLBR_NONE) movl %ebp,%ebp /* zero extension */ - pushq $__USER32_DS - CFI_ADJUST_CFA_OFFSET 8 + pushq_cfi $__USER32_DS /*CFI_REL_OFFSET ss,0*/ - pushq %rbp - CFI_ADJUST_CFA_OFFSET 8 + pushq_cfi %rbp CFI_REL_OFFSET rsp,0 - pushfq - CFI_ADJUST_CFA_OFFSET 8 + pushfq_cfi /*CFI_REL_OFFSET rflags,0*/ movl 8*3-THREAD_SIZE+TI_sysenter_return(%rsp), %r10d CFI_REGISTER rip,r10 - pushq $__USER32_CS - CFI_ADJUST_CFA_OFFSET 8 + pushq_cfi $__USER32_CS /*CFI_REL_OFFSET cs,0*/ movl %eax, %eax - pushq %r10 - CFI_ADJUST_CFA_OFFSET 8 + pushq_cfi %r10 CFI_REL_OFFSET rip,0 - pushq %rax - CFI_ADJUST_CFA_OFFSET 8 + pushq_cfi %rax cld SAVE_ARGS 0,0,1 /* no need to do an access_ok check here because rbp has been @@ -182,11 +178,9 @@ sysexit_from_sys_call: xorq %r9,%r9 xorq %r10,%r10 xorq %r11,%r11 - popfq - CFI_ADJUST_CFA_OFFSET -8 + popfq_cfi /*CFI_RESTORE rflags*/ - popq %rcx /* User %esp */ - CFI_ADJUST_CFA_OFFSET -8 + popq_cfi %rcx /* User %esp */ CFI_REGISTER rsp,rcx TRACE_IRQS_ON ENABLE_INTERRUPTS_SYSEXIT32 @@ -421,8 +415,7 @@ ENTRY(ia32_syscall) */ ENABLE_INTERRUPTS(CLBR_NONE) movl %eax,%eax - pushq %rax - CFI_ADJUST_CFA_OFFSET 8 + pushq_cfi %rax cld /* note the registers are not zero extended to the sf. this could be a problem. */ @@ -851,4 +844,8 @@ ia32_sys_call_table: .quad sys_fanotify_init .quad sys32_fanotify_mark .quad sys_prlimit64 /* 340 */ + .quad sys_name_to_handle_at + .quad compat_sys_open_by_handle_at + .quad compat_sys_clock_adjtime + .quad sys_syncfs ia32_syscall_end: diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index 211ca3f7fd1..12e0e7dd869 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -29,6 +29,7 @@ #include <asm/processor.h> #include <asm/mmu.h> #include <asm/mpspec.h> +#include <asm/trampoline.h> #define COMPILER_DEPENDENT_INT64 long long #define COMPILER_DEPENDENT_UINT64 unsigned long long @@ -88,6 +89,7 @@ extern int acpi_disabled; extern int acpi_pci_disabled; extern int acpi_skip_timer_override; extern int acpi_use_timer_override; +extern int acpi_fix_pin2_polarity; extern u8 acpi_sci_flags; extern int acpi_sci_override_gsi; @@ -112,11 +114,11 @@ static inline void acpi_disable_pci(void) acpi_noirq_set(); } -/* routines for saving/restoring kernel state */ -extern int acpi_save_state_mem(void); -extern void acpi_restore_state_mem(void); +/* Low-level suspend routine. */ +extern int acpi_suspend_lowlevel(void); -extern unsigned long acpi_wakeup_address; +extern const unsigned char acpi_wakeup_code[]; +#define acpi_wakeup_address (__pa(TRAMPOLINE_SYM(acpi_wakeup_code))) /* early initialization routine */ extern void acpi_reserve_wakeup_memory(void); @@ -185,15 +187,7 @@ struct bootnode; #ifdef CONFIG_ACPI_NUMA extern int acpi_numa; -extern void acpi_get_nodes(struct bootnode *physnodes, unsigned long start, - unsigned long end); -extern int acpi_scan_nodes(unsigned long start, unsigned long end); -#define NR_NODE_MEMBLKS (MAX_NUMNODES*2) - -#ifdef CONFIG_NUMA_EMU -extern void acpi_fake_nodes(const struct bootnode *fake_nodes, - int num_nodes); -#endif +extern int x86_acpi_numa_init(void); #endif /* CONFIG_ACPI_NUMA */ #define acpi_unlazy_tlb(x) leave_mm(x) diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h index 64dc82ee19f..331682231bb 100644 --- a/arch/x86/include/asm/amd_nb.h +++ b/arch/x86/include/asm/amd_nb.h @@ -9,23 +9,20 @@ struct amd_nb_bus_dev_range { u8 dev_limit; }; -extern struct pci_device_id amd_nb_misc_ids[]; +extern const struct pci_device_id amd_nb_misc_ids[]; extern const struct amd_nb_bus_dev_range amd_nb_bus_dev_ranges[]; struct bootnode; -extern int early_is_amd_nb(u32 value); +extern bool early_is_amd_nb(u32 value); extern int amd_cache_northbridges(void); extern void amd_flush_garts(void); -extern int amd_numa_init(unsigned long start_pfn, unsigned long end_pfn); -extern int amd_scan_nodes(void); - -#ifdef CONFIG_NUMA_EMU -extern void amd_fake_nodes(const struct bootnode *nodes, int nr_nodes); -extern void amd_get_nodes(struct bootnode *nodes); -#endif +extern int amd_numa_init(void); +extern int amd_get_subcaches(int); +extern int amd_set_subcaches(int, int); struct amd_northbridge { struct pci_dev *misc; + struct pci_dev *link; }; struct amd_northbridge_info { @@ -35,17 +32,18 @@ struct amd_northbridge_info { }; extern struct amd_northbridge_info amd_northbridges; -#define AMD_NB_GART 0x1 -#define AMD_NB_L3_INDEX_DISABLE 0x2 +#define AMD_NB_GART BIT(0) +#define AMD_NB_L3_INDEX_DISABLE BIT(1) +#define AMD_NB_L3_PARTITIONING BIT(2) #ifdef CONFIG_AMD_NB -static inline int amd_nb_num(void) +static inline u16 amd_nb_num(void) { return amd_northbridges.num; } -static inline int amd_nb_has_feature(int feature) +static inline bool amd_nb_has_feature(unsigned feature) { return ((amd_northbridges.flags & feature) == feature); } diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 3c896946f4c..2b7d573be54 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -2,7 +2,6 @@ #define _ASM_X86_APIC_H #include <linux/cpumask.h> -#include <linux/delay.h> #include <linux/pm.h> #include <asm/alternative.h> @@ -220,7 +219,6 @@ extern void enable_IR_x2apic(void); extern int get_physical_broadcast(void); -extern void apic_disable(void); extern int lapic_get_maxlvt(void); extern void clear_local_APIC(void); extern void connect_bsp_APIC(void); @@ -228,7 +226,6 @@ extern void disconnect_bsp_APIC(int virt_wire_setup); extern void disable_local_APIC(void); extern void lapic_shutdown(void); extern int verify_local_APIC(void); -extern void cache_APIC_registers(void); extern void sync_Arb_IDs(void); extern void init_bsp_APIC(void); extern void setup_local_APIC(void); @@ -239,8 +236,7 @@ void register_lapic_address(unsigned long address); extern void setup_boot_APIC_clock(void); extern void setup_secondary_APIC_clock(void); extern int APIC_init_uniprocessor(void); -extern void enable_NMI_through_LVT0(void); -extern int apic_force_enable(void); +extern int apic_force_enable(unsigned long addr); /* * On 32bit this is mach-xxx local @@ -261,7 +257,6 @@ static inline void lapic_shutdown(void) { } #define local_apic_timer_c2_ok 1 static inline void init_apic_mappings(void) { } static inline void disable_local_APIC(void) { } -static inline void apic_disable(void) { } # define setup_boot_APIC_clock x86_init_noop # define setup_secondary_APIC_clock x86_init_noop #endif /* !CONFIG_X86_LOCAL_APIC */ @@ -307,8 +302,6 @@ struct apic { void (*setup_apic_routing)(void); int (*multi_timer_check)(int apic, int irq); - int (*apicid_to_node)(int logical_apicid); - int (*cpu_to_logical_apicid)(int cpu); int (*cpu_present_to_apicid)(int mps_cpu); void (*apicid_to_cpu_present)(int phys_apicid, physid_mask_t *retmap); void (*setup_portio_remap)(void); @@ -356,6 +349,23 @@ struct apic { void (*icr_write)(u32 low, u32 high); void (*wait_icr_idle)(void); u32 (*safe_wait_icr_idle)(void); + +#ifdef CONFIG_X86_32 + /* + * Called very early during boot from get_smp_config(). It should + * return the logical apicid. x86_[bios]_cpu_to_apicid is + * initialized before this function is called. + * + * If logical apicid can't be determined that early, the function + * may return BAD_APICID. Logical apicid will be configured after + * init_apic_ldr() while bringing up CPUs. Note that NUMA affinity + * won't be applied properly during early boot in this case. + */ + int (*x86_32_early_logical_apicid)(int cpu); + + /* determine CPU -> NUMA node mapping */ + int (*x86_32_numa_cpu_node)(int cpu); +#endif }; /* @@ -503,6 +513,11 @@ extern struct apic apic_noop; extern struct apic apic_default; +static inline int noop_x86_32_early_logical_apicid(int cpu) +{ + return BAD_APICID; +} + /* * Set up the logical destination ID. * @@ -522,7 +537,7 @@ static inline int default_phys_pkg_id(int cpuid_apic, int index_msb) return cpuid_apic >> index_msb; } -extern int default_apicid_to_node(int logical_apicid); +extern int default_x86_32_numa_cpu_node(int cpu); #endif @@ -558,12 +573,6 @@ static inline void default_ioapic_phys_id_map(physid_mask_t *phys_map, physid_ma *retmap = *phys_map; } -/* Mapping from cpu number to logical apicid */ -static inline int default_cpu_to_logical_apicid(int cpu) -{ - return 1 << cpu; -} - static inline int __default_cpu_present_to_apicid(int mps_cpu) { if (mps_cpu < nr_cpu_ids && cpu_present(mps_cpu)) @@ -596,8 +605,4 @@ extern int default_check_phys_apicid_present(int phys_apicid); #endif /* CONFIG_X86_LOCAL_APIC */ -#ifdef CONFIG_X86_32 -extern u8 cpu_2_logical_apicid[NR_CPUS]; -#endif - #endif /* _ASM_X86_APIC_H */ diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h index 47a30ff8e51..d87988bacf3 100644 --- a/arch/x86/include/asm/apicdef.h +++ b/arch/x86/include/asm/apicdef.h @@ -426,4 +426,16 @@ struct local_apic { #else #define BAD_APICID 0xFFFFu #endif + +enum ioapic_irq_destination_types { + dest_Fixed = 0, + dest_LowestPrio = 1, + dest_SMI = 2, + dest__reserved_1 = 3, + dest_NMI = 4, + dest_INIT = 5, + dest__reserved_2 = 6, + dest_ExtINT = 7 +}; + #endif /* _ASM_X86_APICDEF_H */ diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 903683b07e4..69d58131bc8 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -456,14 +456,12 @@ static inline int fls(int x) #ifdef __KERNEL__ -#include <asm-generic/bitops/ext2-non-atomic.h> +#include <asm-generic/bitops/le.h> #define ext2_set_bit_atomic(lock, nr, addr) \ test_and_set_bit((nr), (unsigned long *)(addr)) #define ext2_clear_bit_atomic(lock, nr, addr) \ test_and_clear_bit((nr), (unsigned long *)(addr)) -#include <asm-generic/bitops/minix.h> - #endif /* __KERNEL__ */ #endif /* _ASM_X86_BITOPS_H */ diff --git a/arch/x86/include/asm/bootparam.h b/arch/x86/include/asm/bootparam.h index c8bfe63a06d..e020d88ec02 100644 --- a/arch/x86/include/asm/bootparam.h +++ b/arch/x86/include/asm/bootparam.h @@ -12,6 +12,7 @@ /* setup data types */ #define SETUP_NONE 0 #define SETUP_E820_EXT 1 +#define SETUP_DTB 2 /* extensible setup data list node */ struct setup_data { diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h index 62f084478f7..4e12668711e 100644 --- a/arch/x86/include/asm/cacheflush.h +++ b/arch/x86/include/asm/cacheflush.h @@ -71,7 +71,7 @@ static inline void set_page_memtype(struct page *pg, unsigned long memtype) { } * Read/Write : ReadOnly, ReadWrite * Presence : NotPresent * - * Within a catagory, the attributes are mutually exclusive. + * Within a category, the attributes are mutually exclusive. * * The implementation of this API will take care of various aspects that * are associated with changing such attributes, such as: diff --git a/arch/x86/include/asm/ce4100.h b/arch/x86/include/asm/ce4100.h new file mode 100644 index 00000000000..e656ad8c0a2 --- /dev/null +++ b/arch/x86/include/asm/ce4100.h @@ -0,0 +1,6 @@ +#ifndef _ASM_CE4100_H_ +#define _ASM_CE4100_H_ + +int ce4100_pci_init(void); + +#endif diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 220e2ea08e8..91f3e087cf2 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -160,6 +160,7 @@ #define X86_FEATURE_NODEID_MSR (6*32+19) /* NodeId MSR */ #define X86_FEATURE_TBM (6*32+21) /* trailing bit manipulations */ #define X86_FEATURE_TOPOEXT (6*32+22) /* topology extensions CPUID leafs */ +#define X86_FEATURE_PERFCTR_CORE (6*32+23) /* core performance counter extensions */ /* * Auxiliary flags: Linux defined - For features scattered in various @@ -279,6 +280,7 @@ extern const char * const x86_power_flags[32]; #define cpu_has_xsave boot_cpu_has(X86_FEATURE_XSAVE) #define cpu_has_hypervisor boot_cpu_has(X86_FEATURE_HYPERVISOR) #define cpu_has_pclmulqdq boot_cpu_has(X86_FEATURE_PCLMULQDQ) +#define cpu_has_perfctr_core boot_cpu_has(X86_FEATURE_PERFCTR_CORE) #if defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_64) # define cpu_has_invlpg 1 diff --git a/arch/x86/include/asm/dma.h b/arch/x86/include/asm/dma.h index ca1098a7e58..057099e5fab 100644 --- a/arch/x86/include/asm/dma.h +++ b/arch/x86/include/asm/dma.h @@ -10,7 +10,6 @@ #include <linux/spinlock.h> /* And spinlocks */ #include <asm/io.h> /* need byte IO */ -#include <linux/delay.h> #ifdef HAVE_REALLY_SLOW_DMA_CONTROLLER #define dma_outb outb_p @@ -151,6 +150,7 @@ #define DMA_AUTOINIT 0x10 +#ifdef CONFIG_ISA_DMA_API extern spinlock_t dma_spin_lock; static inline unsigned long claim_dma_lock(void) @@ -164,6 +164,7 @@ static inline void release_dma_lock(unsigned long flags) { spin_unlock_irqrestore(&dma_spin_lock, flags); } +#endif /* CONFIG_ISA_DMA_API */ /* enable/disable a specific DMA channel */ static inline void enable_dma(unsigned int dmanr) @@ -303,9 +304,11 @@ static inline int get_dma_residue(unsigned int dmanr) } -/* These are in kernel/dma.c: */ +/* These are in kernel/dma.c because x86 uses CONFIG_GENERIC_ISA_DMA */ +#ifdef CONFIG_ISA_DMA_API extern int request_dma(unsigned int dmanr, const char *device_id); extern void free_dma(unsigned int dmanr); +#endif /* From PCI */ diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h index e99d55d74df..908b96957d8 100644 --- a/arch/x86/include/asm/e820.h +++ b/arch/x86/include/asm/e820.h @@ -96,7 +96,7 @@ extern void e820_setup_gap(void); extern int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize, unsigned long start_addr, unsigned long long end_addr); struct setup_data; -extern void parse_e820_ext(struct setup_data *data, unsigned long pa_data); +extern void parse_e820_ext(struct setup_data *data); #if defined(CONFIG_X86_64) || \ (defined(CONFIG_X86_32) && defined(CONFIG_HIBERNATION)) diff --git a/arch/x86/include/asm/entry_arch.h b/arch/x86/include/asm/entry_arch.h index 57650ab4a5f..1cd6d26a0a8 100644 --- a/arch/x86/include/asm/entry_arch.h +++ b/arch/x86/include/asm/entry_arch.h @@ -16,10 +16,13 @@ BUILD_INTERRUPT(call_function_single_interrupt,CALL_FUNCTION_SINGLE_VECTOR) BUILD_INTERRUPT(irq_move_cleanup_interrupt,IRQ_MOVE_CLEANUP_VECTOR) BUILD_INTERRUPT(reboot_interrupt,REBOOT_VECTOR) -.irpc idx, "01234567" +.irp idx,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15, \ + 16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31 +.if NUM_INVALIDATE_TLB_VECTORS > \idx BUILD_INTERRUPT3(invalidate_interrupt\idx, (INVALIDATE_TLB_VECTOR_START)+\idx, smp_invalidate_interrupt) +.endif .endr #endif diff --git a/arch/x86/include/asm/frame.h b/arch/x86/include/asm/frame.h index 06850a7194e..2c6fc9e6281 100644 --- a/arch/x86/include/asm/frame.h +++ b/arch/x86/include/asm/frame.h @@ -7,14 +7,12 @@ frame pointer later */ #ifdef CONFIG_FRAME_POINTER .macro FRAME - pushl %ebp - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %ebp CFI_REL_OFFSET ebp,0 movl %esp,%ebp .endm .macro ENDFRAME - popl %ebp - CFI_ADJUST_CFA_OFFSET -4 + popl_cfi %ebp CFI_RESTORE ebp .endm #else diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h index 1f11ce44e95..d09bb03653f 100644 --- a/arch/x86/include/asm/futex.h +++ b/arch/x86/include/asm/futex.h @@ -37,7 +37,7 @@ "+m" (*uaddr), "=&r" (tem) \ : "r" (oparg), "i" (-EFAULT), "1" (0)) -static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr) +static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) { int op = (encoded_op >> 28) & 7; int cmp = (encoded_op >> 24) & 15; @@ -48,7 +48,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr) if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) oparg = 1 << oparg; - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int))) + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; #if defined(CONFIG_X86_32) && !defined(CONFIG_X86_BSWAP) @@ -109,9 +109,10 @@ static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr) return ret; } -static inline int futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, - int newval) +static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, + u32 oldval, u32 newval) { + int ret = 0; #if defined(CONFIG_X86_32) && !defined(CONFIG_X86_BSWAP) /* Real i386 machines have no cmpxchg instruction */ @@ -119,21 +120,22 @@ static inline int futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, return -ENOSYS; #endif - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int))) + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; - asm volatile("1:\t" LOCK_PREFIX "cmpxchgl %3, %1\n" + asm volatile("1:\t" LOCK_PREFIX "cmpxchgl %4, %2\n" "2:\t.section .fixup, \"ax\"\n" - "3:\tmov %2, %0\n" + "3:\tmov %3, %0\n" "\tjmp 2b\n" "\t.previous\n" _ASM_EXTABLE(1b, 3b) - : "=a" (oldval), "+m" (*uaddr) - : "i" (-EFAULT), "r" (newval), "0" (oldval) + : "+r" (ret), "=a" (oldval), "+m" (*uaddr) + : "i" (-EFAULT), "r" (newval), "1" (oldval) : "memory" ); - return oldval; + *uval = oldval; + return ret; } #endif diff --git a/arch/x86/include/asm/gart.h b/arch/x86/include/asm/gart.h index 43085bfc99c..156cd5d18d2 100644 --- a/arch/x86/include/asm/gart.h +++ b/arch/x86/include/asm/gart.h @@ -66,7 +66,7 @@ static inline void gart_set_size_and_enable(struct pci_dev *dev, u32 order) * Don't enable translation but enable GART IO and CPU accesses. * Also, set DISTLBWALKPRB since GART tables memory is UC. */ - ctl = DISTLBWALKPRB | order << 1; + ctl = order << 1; pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl); } @@ -75,17 +75,17 @@ static inline void enable_gart_translation(struct pci_dev *dev, u64 addr) { u32 tmp, ctl; - /* address of the mappings table */ - addr >>= 12; - tmp = (u32) addr<<4; - tmp &= ~0xf; - pci_write_config_dword(dev, AMD64_GARTTABLEBASE, tmp); - - /* Enable GART translation for this hammer. */ - pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &ctl); - ctl |= GARTEN; - ctl &= ~(DISGARTCPU | DISGARTIO); - pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl); + /* address of the mappings table */ + addr >>= 12; + tmp = (u32) addr<<4; + tmp &= ~0xf; + pci_write_config_dword(dev, AMD64_GARTTABLEBASE, tmp); + + /* Enable GART translation for this hammer. */ + pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &ctl); + ctl |= GARTEN | DISTLBWALKPRB; + ctl &= ~(DISGARTCPU | DISGARTIO); + pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl); } static inline int aperture_valid(u64 aper_base, u32 aper_size, u32 min_size) diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index 0274ec5a7e6..bb9efe8706e 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -45,6 +45,30 @@ extern void invalidate_interrupt4(void); extern void invalidate_interrupt5(void); extern void invalidate_interrupt6(void); extern void invalidate_interrupt7(void); +extern void invalidate_interrupt8(void); +extern void invalidate_interrupt9(void); +extern void invalidate_interrupt10(void); +extern void invalidate_interrupt11(void); +extern void invalidate_interrupt12(void); +extern void invalidate_interrupt13(void); +extern void invalidate_interrupt14(void); +extern void invalidate_interrupt15(void); +extern void invalidate_interrupt16(void); +extern void invalidate_interrupt17(void); +extern void invalidate_interrupt18(void); +extern void invalidate_interrupt19(void); +extern void invalidate_interrupt20(void); +extern void invalidate_interrupt21(void); +extern void invalidate_interrupt22(void); +extern void invalidate_interrupt23(void); +extern void invalidate_interrupt24(void); +extern void invalidate_interrupt25(void); +extern void invalidate_interrupt26(void); +extern void invalidate_interrupt27(void); +extern void invalidate_interrupt28(void); +extern void invalidate_interrupt29(void); +extern void invalidate_interrupt30(void); +extern void invalidate_interrupt31(void); extern void irq_move_cleanup_interrupt(void); extern void reboot_interrupt(void); diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h index ef328901c80..c9e09ea0564 100644 --- a/arch/x86/include/asm/i387.h +++ b/arch/x86/include/asm/i387.h @@ -237,7 +237,7 @@ static inline void fpu_save_init(struct fpu *fpu) } else if (use_fxsr()) { fpu_fxsave(fpu); } else { - asm volatile("fsave %[fx]; fwait" + asm volatile("fnsave %[fx]; fwait" : [fx] "=m" (fpu->state->fsave)); return; } diff --git a/arch/x86/include/asm/i8253.h b/arch/x86/include/asm/i8253.h index fc1f579fb96..65aaa91d585 100644 --- a/arch/x86/include/asm/i8253.h +++ b/arch/x86/include/asm/i8253.h @@ -6,6 +6,8 @@ #define PIT_CH0 0x40 #define PIT_CH2 0x42 +#define PIT_LATCH LATCH + extern raw_spinlock_t i8253_lock; extern struct clock_event_device *global_clock_event; diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h index 36fb1a6a510..8dbe353e41e 100644 --- a/arch/x86/include/asm/init.h +++ b/arch/x86/include/asm/init.h @@ -11,8 +11,8 @@ kernel_physical_mapping_init(unsigned long start, unsigned long page_size_mask); -extern unsigned long __initdata e820_table_start; -extern unsigned long __meminitdata e820_table_end; -extern unsigned long __meminitdata e820_table_top; +extern unsigned long __initdata pgt_buf_start; +extern unsigned long __meminitdata pgt_buf_end; +extern unsigned long __meminitdata pgt_buf_top; #endif /* _ASM_X86_INIT_32_H */ diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h index f327d386d6c..a97a240f67f 100644 --- a/arch/x86/include/asm/io_apic.h +++ b/arch/x86/include/asm/io_apic.h @@ -63,17 +63,6 @@ union IO_APIC_reg_03 { } __attribute__ ((packed)) bits; }; -enum ioapic_irq_destination_types { - dest_Fixed = 0, - dest_LowestPrio = 1, - dest_SMI = 2, - dest__reserved_1 = 3, - dest_NMI = 4, - dest_INIT = 5, - dest__reserved_2 = 6, - dest_ExtINT = 7 -}; - struct IO_APIC_route_entry { __u32 vector : 8, delivery_mode : 3, /* 000: FIXED @@ -106,6 +95,10 @@ struct IR_IO_APIC_route_entry { index : 15; } __attribute__ ((packed)); +#define IOAPIC_AUTO -1 +#define IOAPIC_EDGE 0 +#define IOAPIC_LEVEL 1 + #ifdef CONFIG_X86_IO_APIC /* @@ -150,11 +143,6 @@ extern int timer_through_8259; #define io_apic_assign_pci_irqs \ (mp_irq_entries && !skip_ioapic_setup && io_apic_irqs) -extern u8 io_apic_unique_id(u8 id); -extern int io_apic_get_unique_id(int ioapic, int apic_id); -extern int io_apic_get_version(int ioapic); -extern int io_apic_get_redir_entries(int ioapic); - struct io_apic_irq_attr; extern int io_apic_set_pci_routing(struct device *dev, int irq, struct io_apic_irq_attr *irq_attr); @@ -162,6 +150,8 @@ void setup_IO_APIC_irq_extra(u32 gsi); extern void ioapic_and_gsi_init(void); extern void ioapic_insert_resources(void); +int io_apic_setup_irq_pin_once(unsigned int irq, int node, struct io_apic_irq_attr *attr); + extern struct IO_APIC_route_entry **alloc_ioapic_entries(void); extern void free_ioapic_entries(struct IO_APIC_route_entry **ioapic_entries); extern int save_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries); @@ -186,6 +176,8 @@ extern void __init pre_init_apic_IRQ0(void); extern void mp_save_irq(struct mpc_intsrc *m); +extern void disable_ioapic_support(void); + #else /* !CONFIG_X86_IO_APIC */ #define io_apic_assign_pci_irqs 0 @@ -199,6 +191,26 @@ static inline int mp_find_ioapic(u32 gsi) { return 0; } struct io_apic_irq_attr; static inline int io_apic_set_pci_routing(struct device *dev, int irq, struct io_apic_irq_attr *irq_attr) { return 0; } + +static inline struct IO_APIC_route_entry **alloc_ioapic_entries(void) +{ + return NULL; +} + +static inline void free_ioapic_entries(struct IO_APIC_route_entry **ent) { } +static inline int save_IO_APIC_setup(struct IO_APIC_route_entry **ent) +{ + return -ENOMEM; +} + +static inline void mask_IO_APIC_setup(struct IO_APIC_route_entry **ent) { } +static inline int restore_IO_APIC_setup(struct IO_APIC_route_entry **ent) +{ + return -ENOMEM; +} + +static inline void mp_save_irq(struct mpc_intsrc *m) { }; +static inline void disable_ioapic_support(void) { } #endif #endif /* _ASM_X86_IO_APIC_H */ diff --git a/arch/x86/include/asm/ipi.h b/arch/x86/include/asm/ipi.h index 0b7228268a6..615fa9061b5 100644 --- a/arch/x86/include/asm/ipi.h +++ b/arch/x86/include/asm/ipi.h @@ -123,10 +123,6 @@ extern void default_send_IPI_mask_sequence_phys(const struct cpumask *mask, int vector); extern void default_send_IPI_mask_allbutself_phys(const struct cpumask *mask, int vector); -extern void default_send_IPI_mask_sequence_logical(const struct cpumask *mask, - int vector); -extern void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask, - int vector); /* Avoid include hell */ #define NMI_VECTOR 0x02 @@ -150,6 +146,10 @@ static inline void __default_local_send_IPI_all(int vector) } #ifdef CONFIG_X86_32 +extern void default_send_IPI_mask_sequence_logical(const struct cpumask *mask, + int vector); +extern void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask, + int vector); extern void default_send_IPI_mask_logical(const struct cpumask *mask, int vector); extern void default_send_IPI_allbutself(int vector); diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index c704b38c57a..ba870bb6dd8 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -10,9 +10,6 @@ #include <asm/apicdef.h> #include <asm/irq_vectors.h> -/* Even though we don't support this, supply it to appease OF */ -static inline void irq_dispose_mapping(unsigned int virq) { } - static inline int irq_canonicalize(int irq) { return ((irq == 2) ? 9 : irq); diff --git a/arch/x86/include/asm/irq_controller.h b/arch/x86/include/asm/irq_controller.h new file mode 100644 index 00000000000..423bbbddf36 --- /dev/null +++ b/arch/x86/include/asm/irq_controller.h @@ -0,0 +1,12 @@ +#ifndef __IRQ_CONTROLLER__ +#define __IRQ_CONTROLLER__ + +struct irq_domain { + int (*xlate)(struct irq_domain *h, const u32 *intspec, u32 intsize, + u32 *out_hwirq, u32 *out_type); + void *priv; + struct device_node *controller; + struct list_head l; +}; + +#endif diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h index 6af0894dafb..6e976ee3b3e 100644 --- a/arch/x86/include/asm/irq_vectors.h +++ b/arch/x86/include/asm/irq_vectors.h @@ -1,6 +1,7 @@ #ifndef _ASM_X86_IRQ_VECTORS_H #define _ASM_X86_IRQ_VECTORS_H +#include <linux/threads.h> /* * Linux IRQ vector layout. * @@ -16,8 +17,8 @@ * Vectors 0 ... 31 : system traps and exceptions - hardcoded events * Vectors 32 ... 127 : device interrupts * Vector 128 : legacy int80 syscall interface - * Vectors 129 ... 237 : device interrupts - * Vectors 238 ... 255 : special interrupts + * Vectors 129 ... INVALIDATE_TLB_VECTOR_START-1 : device interrupts + * Vectors INVALIDATE_TLB_VECTOR_START ... 255 : special interrupts * * 64-bit x86 has per CPU IDT tables, 32-bit has one shared IDT table. * @@ -96,37 +97,43 @@ #define THRESHOLD_APIC_VECTOR 0xf9 #define REBOOT_VECTOR 0xf8 -/* f0-f7 used for spreading out TLB flushes: */ -#define INVALIDATE_TLB_VECTOR_END 0xf7 -#define INVALIDATE_TLB_VECTOR_START 0xf0 -#define NUM_INVALIDATE_TLB_VECTORS 8 - -/* - * Local APIC timer IRQ vector is on a different priority level, - * to work around the 'lost local interrupt if more than 2 IRQ - * sources per level' errata. - */ -#define LOCAL_TIMER_VECTOR 0xef - /* * Generic system vector for platform specific use */ -#define X86_PLATFORM_IPI_VECTOR 0xed +#define X86_PLATFORM_IPI_VECTOR 0xf7 /* * IRQ work vector: */ -#define IRQ_WORK_VECTOR 0xec +#define IRQ_WORK_VECTOR 0xf6 -#define UV_BAU_MESSAGE 0xea +#define UV_BAU_MESSAGE 0xf5 /* * Self IPI vector for machine checks */ -#define MCE_SELF_VECTOR 0xeb +#define MCE_SELF_VECTOR 0xf4 /* Xen vector callback to receive events in a HVM domain */ -#define XEN_HVM_EVTCHN_CALLBACK 0xe9 +#define XEN_HVM_EVTCHN_CALLBACK 0xf3 + +/* + * Local APIC timer IRQ vector is on a different priority level, + * to work around the 'lost local interrupt if more than 2 IRQ + * sources per level' errata. + */ +#define LOCAL_TIMER_VECTOR 0xef + +/* up to 32 vectors used for spreading out TLB flushes: */ +#if NR_CPUS <= 32 +# define NUM_INVALIDATE_TLB_VECTORS (NR_CPUS) +#else +# define NUM_INVALIDATE_TLB_VECTORS (32) +#endif + +#define INVALIDATE_TLB_VECTOR_END (0xee) +#define INVALIDATE_TLB_VECTOR_START \ + (INVALIDATE_TLB_VECTOR_END-NUM_INVALIDATE_TLB_VECTORS+1) #define NR_VECTORS 256 diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h index ca242d35e87..fe2cc6e105f 100644 --- a/arch/x86/include/asm/kdebug.h +++ b/arch/x86/include/asm/kdebug.h @@ -13,7 +13,6 @@ enum die_val { DIE_PANIC, DIE_NMI, DIE_DIE, - DIE_NMIWATCHDOG, DIE_KERNELDEBUG, DIE_TRAP, DIE_GPF, @@ -27,7 +26,7 @@ extern void die(const char *, struct pt_regs *,long); extern int __must_check __die(const char *, struct pt_regs *, long); extern void show_registers(struct pt_regs *regs); extern void show_trace(struct task_struct *t, struct pt_regs *regs, - unsigned long *sp); + unsigned long *sp, unsigned long bp); extern void __show_regs(struct pt_regs *regs, int all); extern void show_regs(struct pt_regs *regs); extern unsigned long oops_begin(void); diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 8e37deb1eb3..0f521356432 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -142,9 +142,9 @@ struct x86_emulate_ops { int (*pio_out_emulated)(int size, unsigned short port, const void *val, unsigned int count, struct kvm_vcpu *vcpu); - bool (*get_cached_descriptor)(struct desc_struct *desc, + bool (*get_cached_descriptor)(struct desc_struct *desc, u32 *base3, int seg, struct kvm_vcpu *vcpu); - void (*set_cached_descriptor)(struct desc_struct *desc, + void (*set_cached_descriptor)(struct desc_struct *desc, u32 base3, int seg, struct kvm_vcpu *vcpu); u16 (*get_segment_selector)(int seg, struct kvm_vcpu *vcpu); void (*set_segment_selector)(u16 sel, int seg, struct kvm_vcpu *vcpu); @@ -239,6 +239,7 @@ struct x86_emulate_ctxt { int interruptibility; bool perm_ok; /* do not check permissions if true */ + bool only_vendor_specific_insn; bool have_exception; struct x86_exception exception; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index ffd7f8d2918..c8af0991fdf 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -85,7 +85,7 @@ #define ASYNC_PF_PER_VCPU 64 -extern spinlock_t kvm_lock; +extern raw_spinlock_t kvm_lock; extern struct list_head vm_list; struct kvm_vcpu; @@ -255,6 +255,8 @@ struct kvm_mmu { int (*sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp); void (*invlpg)(struct kvm_vcpu *vcpu, gva_t gva); + void (*update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, + u64 *spte, const void *pte, unsigned long mmu_seq); hpa_t root_hpa; int root_level; int shadow_root_level; @@ -335,12 +337,6 @@ struct kvm_vcpu_arch { u64 *last_pte_updated; gfn_t last_pte_gfn; - struct { - gfn_t gfn; /* presumed gfn during guest pte update */ - pfn_t pfn; /* pfn corresponding to that gfn */ - unsigned long mmu_seq; - } update_pte; - struct fpu guest_fpu; u64 xcr0; @@ -448,7 +444,7 @@ struct kvm_arch { unsigned long irq_sources_bitmap; s64 kvmclock_offset; - spinlock_t tsc_write_lock; + raw_spinlock_t tsc_write_lock; u64 last_tsc_nsec; u64 last_tsc_offset; u64 last_tsc_write; diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h index 80a1dee5bea..aeff3e89b22 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -13,6 +13,12 @@ typedef struct { int size; struct mutex lock; void *vdso; + +#ifdef CONFIG_X86_64 + /* True if mm supports a task running in 32 bit compatibility mode. */ + unsigned short ia32_compat; +#endif + } mm_context_t; #ifdef CONFIG_SMP diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h index 0c90dd9f050..9c7d95f6174 100644 --- a/arch/x86/include/asm/mpspec.h +++ b/arch/x86/include/asm/mpspec.h @@ -25,7 +25,6 @@ extern int pic_mode; #define MAX_IRQ_SOURCES 256 extern unsigned int def_to_bigsmp; -extern u8 apicid_2_node[]; #ifdef CONFIG_X86_NUMAQ extern int mp_bus_id_to_node[MAX_MP_BUSSES]; @@ -33,8 +32,6 @@ extern int mp_bus_id_to_local[MAX_MP_BUSSES]; extern int quad_local_to_mp_bus_id [NR_CPUS/4][4]; #endif -#define MAX_APICID 256 - #else /* CONFIG_X86_64: */ #define MAX_MP_BUSSES 256 diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 4d0dfa0d998..3cce71413d0 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -36,8 +36,14 @@ #define MSR_IA32_PERFCTR1 0x000000c2 #define MSR_FSB_FREQ 0x000000cd +#define MSR_NHM_SNB_PKG_CST_CFG_CTL 0x000000e2 +#define NHM_C3_AUTO_DEMOTE (1UL << 25) +#define NHM_C1_AUTO_DEMOTE (1UL << 26) +#define ATM_LNC_C6_AUTO_DEMOTE (1UL << 25) + #define MSR_MTRRcap 0x000000fe #define MSR_IA32_BBL_CR_CTL 0x00000119 +#define MSR_IA32_BBL_CR_CTL3 0x0000011e #define MSR_IA32_SYSENTER_CS 0x00000174 #define MSR_IA32_SYSENTER_ESP 0x00000175 @@ -47,6 +53,9 @@ #define MSR_IA32_MCG_STATUS 0x0000017a #define MSR_IA32_MCG_CTL 0x0000017b +#define MSR_OFFCORE_RSP_0 0x000001a6 +#define MSR_OFFCORE_RSP_1 0x000001a7 + #define MSR_IA32_PEBS_ENABLE 0x000003f1 #define MSR_IA32_DS_AREA 0x00000600 #define MSR_IA32_PERF_CAPABILITIES 0x00000345 @@ -87,11 +96,15 @@ #define MSR_IA32_MC0_ADDR 0x00000402 #define MSR_IA32_MC0_MISC 0x00000403 +#define MSR_AMD64_MC0_MASK 0xc0010044 + #define MSR_IA32_MCx_CTL(x) (MSR_IA32_MC0_CTL + 4*(x)) #define MSR_IA32_MCx_STATUS(x) (MSR_IA32_MC0_STATUS + 4*(x)) #define MSR_IA32_MCx_ADDR(x) (MSR_IA32_MC0_ADDR + 4*(x)) #define MSR_IA32_MCx_MISC(x) (MSR_IA32_MC0_MISC + 4*(x)) +#define MSR_AMD64_MCx_MASK(x) (MSR_AMD64_MC0_MASK + (x)) + /* These are consecutive and not in the normal 4er MCE bank block */ #define MSR_IA32_MC0_CTL2 0x00000280 #define MSR_IA32_MCx_CTL2(x) (MSR_IA32_MC0_CTL2 + (x)) diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h index c76f5b92b84..4886a68f267 100644 --- a/arch/x86/include/asm/nmi.h +++ b/arch/x86/include/asm/nmi.h @@ -7,7 +7,6 @@ #ifdef CONFIG_X86_LOCAL_APIC -extern void die_nmi(char *str, struct pt_regs *regs, int do_panic); extern int avail_to_resrv_perfctr_nmi_bit(unsigned int); extern int reserve_perfctr_nmi(unsigned int); extern void release_perfctr_nmi(unsigned int); @@ -30,8 +29,8 @@ void arch_trigger_all_cpu_backtrace(void); * external nmis, because the local ones are more frequent. * * Also setup some default high/normal/low settings for - * subsystems to registers with. Using 4 bits to seperate - * the priorities. This can go alot higher if needed be. + * subsystems to registers with. Using 4 bits to separate + * the priorities. This can go a lot higher if needed be. */ #define NMI_LOCAL_SHIFT 16 /* randomly picked */ diff --git a/arch/x86/include/asm/nops.h b/arch/x86/include/asm/nops.h index 6d8723a766c..af788496020 100644 --- a/arch/x86/include/asm/nops.h +++ b/arch/x86/include/asm/nops.h @@ -38,7 +38,7 @@ #define K8_NOP8 K8_NOP4 K8_NOP4 /* K7 nops - uses eax dependencies (arbitary choice) + uses eax dependencies (arbitrary choice) 1: nop 2: movl %eax,%eax 3: leal (,%eax,1),%eax diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h index 27da400d313..a50fc9f493b 100644 --- a/arch/x86/include/asm/numa.h +++ b/arch/x86/include/asm/numa.h @@ -1,5 +1,57 @@ +#ifndef _ASM_X86_NUMA_H +#define _ASM_X86_NUMA_H + +#include <asm/topology.h> +#include <asm/apicdef.h> + +#ifdef CONFIG_NUMA + +#define NR_NODE_MEMBLKS (MAX_NUMNODES*2) + +/* + * __apicid_to_node[] stores the raw mapping between physical apicid and + * node and is used to initialize cpu_to_node mapping. + * + * The mapping may be overridden by apic->numa_cpu_node() on 32bit and thus + * should be accessed by the accessors - set_apicid_to_node() and + * numa_cpu_node(). + */ +extern s16 __apicid_to_node[MAX_LOCAL_APIC]; + +static inline void set_apicid_to_node(int apicid, s16 node) +{ + __apicid_to_node[apicid] = node; +} +#else /* CONFIG_NUMA */ +static inline void set_apicid_to_node(int apicid, s16 node) +{ +} +#endif /* CONFIG_NUMA */ + #ifdef CONFIG_X86_32 # include "numa_32.h" #else # include "numa_64.h" #endif + +#ifdef CONFIG_NUMA +extern void __cpuinit numa_set_node(int cpu, int node); +extern void __cpuinit numa_clear_node(int cpu); +extern void __init numa_init_array(void); +extern void __init init_cpu_to_node(void); +extern void __cpuinit numa_add_cpu(int cpu); +extern void __cpuinit numa_remove_cpu(int cpu); +#else /* CONFIG_NUMA */ +static inline void numa_set_node(int cpu, int node) { } +static inline void numa_clear_node(int cpu) { } +static inline void numa_init_array(void) { } +static inline void init_cpu_to_node(void) { } +static inline void numa_add_cpu(int cpu) { } +static inline void numa_remove_cpu(int cpu) { } +#endif /* CONFIG_NUMA */ + +#ifdef CONFIG_DEBUG_PER_CPU_MAPS +void debug_cpumask_set_cpu(int cpu, int node, bool enable); +#endif + +#endif /* _ASM_X86_NUMA_H */ diff --git a/arch/x86/include/asm/numa_32.h b/arch/x86/include/asm/numa_32.h index b0ef2b449a9..c6beed1ef10 100644 --- a/arch/x86/include/asm/numa_32.h +++ b/arch/x86/include/asm/numa_32.h @@ -4,7 +4,12 @@ extern int numa_off; extern int pxm_to_nid(int pxm); -extern void numa_remove_cpu(int cpu); + +#ifdef CONFIG_NUMA +extern int __cpuinit numa_cpu_node(int cpu); +#else /* CONFIG_NUMA */ +static inline int numa_cpu_node(int cpu) { return NUMA_NO_NODE; } +#endif /* CONFIG_NUMA */ #ifdef CONFIG_HIGHMEM extern void set_highmem_pages_init(void); diff --git a/arch/x86/include/asm/numa_64.h b/arch/x86/include/asm/numa_64.h index 0493be39607..344eb1790b4 100644 --- a/arch/x86/include/asm/numa_64.h +++ b/arch/x86/include/asm/numa_64.h @@ -2,23 +2,16 @@ #define _ASM_X86_NUMA_64_H #include <linux/nodemask.h> -#include <asm/apicdef.h> struct bootnode { u64 start; u64 end; }; -extern int compute_hash_shift(struct bootnode *nodes, int numblks, - int *nodeids); - #define ZONE_ALIGN (1UL << (MAX_ORDER+PAGE_SHIFT)) -extern void numa_init_array(void); extern int numa_off; -extern s16 apicid_to_node[MAX_LOCAL_APIC]; - extern unsigned long numa_free_all_bootmem(void); extern void setup_node_bootmem(int nodeid, unsigned long start, unsigned long end); @@ -31,11 +24,11 @@ extern void setup_node_bootmem(int nodeid, unsigned long start, */ #define NODE_MIN_SIZE (4*1024*1024) -extern void __init init_cpu_to_node(void); -extern void __cpuinit numa_set_node(int cpu, int node); -extern void __cpuinit numa_clear_node(int cpu); -extern void __cpuinit numa_add_cpu(int cpu); -extern void __cpuinit numa_remove_cpu(int cpu); +extern nodemask_t numa_nodes_parsed __initdata; + +extern int __cpuinit numa_cpu_node(int cpu); +extern int __init numa_add_memblk(int nodeid, u64 start, u64 end); +extern void __init numa_set_distance(int from, int to, int distance); #ifdef CONFIG_NUMA_EMU #define FAKE_NODE_MIN_SIZE ((u64)32 << 20) @@ -43,11 +36,7 @@ extern void __cpuinit numa_remove_cpu(int cpu); void numa_emu_cmdline(char *); #endif /* CONFIG_NUMA_EMU */ #else -static inline void init_cpu_to_node(void) { } -static inline void numa_set_node(int cpu, int node) { } -static inline void numa_clear_node(int cpu) { } -static inline void numa_add_cpu(int cpu, int node) { } -static inline void numa_remove_cpu(int cpu) { } +static inline int numa_cpu_node(int cpu) { return NUMA_NO_NODE; } #endif #endif /* _ASM_X86_NUMA_64_H */ diff --git a/arch/x86/include/asm/olpc.h b/arch/x86/include/asm/olpc.h index f482010350f..5ca6801b75f 100644 --- a/arch/x86/include/asm/olpc.h +++ b/arch/x86/include/asm/olpc.h @@ -20,7 +20,7 @@ extern struct olpc_platform_t olpc_platform_info; /* * OLPC board IDs contain the major build number within the mask 0x0ff0, - * and the minor build number withing 0x000f. Pre-builds have a minor + * and the minor build number within 0x000f. Pre-builds have a minor * number less than 8, and normal builds start at 8. For example, 0x0B10 * is a PreB1, and 0x0C18 is a C1. */ diff --git a/arch/x86/include/asm/olpc_ofw.h b/arch/x86/include/asm/olpc_ofw.h index 641988efe06..c5d3a5abbb9 100644 --- a/arch/x86/include/asm/olpc_ofw.h +++ b/arch/x86/include/asm/olpc_ofw.h @@ -6,7 +6,7 @@ #define OLPC_OFW_SIG 0x2057464F /* aka "OFW " */ -#ifdef CONFIG_OLPC_OPENFIRMWARE +#ifdef CONFIG_OLPC extern bool olpc_ofw_is_installed(void); @@ -26,19 +26,15 @@ extern void setup_olpc_ofw_pgd(void); /* check if OFW was detected during boot */ extern bool olpc_ofw_present(void); -#else /* !CONFIG_OLPC_OPENFIRMWARE */ - -static inline bool olpc_ofw_is_installed(void) { return false; } +#else /* !CONFIG_OLPC */ static inline void olpc_ofw_detect(void) { } static inline void setup_olpc_ofw_pgd(void) { } -static inline bool olpc_ofw_present(void) { return false; } - -#endif /* !CONFIG_OLPC_OPENFIRMWARE */ +#endif /* !CONFIG_OLPC */ -#ifdef CONFIG_OLPC_OPENFIRMWARE_DT +#ifdef CONFIG_OF_PROMTREE extern void olpc_dt_build_devicetree(void); #else static inline void olpc_dt_build_devicetree(void) { } -#endif /* CONFIG_OLPC_OPENFIRMWARE_DT */ +#endif #endif /* _ASM_X86_OLPC_OFW_H */ diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h index 1df66211fd1..bce688d54c1 100644 --- a/arch/x86/include/asm/page_types.h +++ b/arch/x86/include/asm/page_types.h @@ -2,6 +2,7 @@ #define _ASM_X86_PAGE_DEFS_H #include <linux/const.h> +#include <linux/types.h> /* PAGE_SHIFT determines the page size */ #define PAGE_SHIFT 12 @@ -45,11 +46,15 @@ extern int devmem_is_allowed(unsigned long pagenr); extern unsigned long max_low_pfn_mapped; extern unsigned long max_pfn_mapped; +static inline phys_addr_t get_max_mapped(void) +{ + return (phys_addr_t)max_pfn_mapped << PAGE_SHIFT; +} + extern unsigned long init_memory_mapping(unsigned long start, unsigned long end); -extern void initmem_init(unsigned long start_pfn, unsigned long end_pfn, - int acpi, int k8); +extern void initmem_init(void); extern void free_initmem(void); #endif /* !__ASSEMBLY__ */ diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index 7e172955ee5..d475b4398d8 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -45,7 +45,7 @@ #include <linux/stringify.h> #ifdef CONFIG_SMP -#define __percpu_arg(x) "%%"__stringify(__percpu_seg)":%P" #x +#define __percpu_prefix "%%"__stringify(__percpu_seg)":" #define __my_cpu_offset percpu_read(this_cpu_off) /* @@ -62,9 +62,11 @@ (typeof(*(ptr)) __kernel __force *)tcp_ptr__; \ }) #else -#define __percpu_arg(x) "%P" #x +#define __percpu_prefix "" #endif +#define __percpu_arg(x) __percpu_prefix "%P" #x + /* * Initialized pointers to per-cpu variables needed for the boot * processor need to use these macros to get the proper address @@ -451,6 +453,26 @@ do { \ #define irqsafe_cpu_cmpxchg_4(pcp, oval, nval) percpu_cmpxchg_op(pcp, oval, nval) #endif /* !CONFIG_M386 */ +#ifdef CONFIG_X86_CMPXCHG64 +#define percpu_cmpxchg8b_double(pcp1, o1, o2, n1, n2) \ +({ \ + char __ret; \ + typeof(o1) __o1 = o1; \ + typeof(o1) __n1 = n1; \ + typeof(o2) __o2 = o2; \ + typeof(o2) __n2 = n2; \ + typeof(o2) __dummy = n2; \ + asm volatile("cmpxchg8b "__percpu_arg(1)"\n\tsetz %0\n\t" \ + : "=a"(__ret), "=m" (pcp1), "=d"(__dummy) \ + : "b"(__n1), "c"(__n2), "a"(__o1), "d"(__o2)); \ + __ret; \ +}) + +#define __this_cpu_cmpxchg_double_4(pcp1, pcp2, o1, o2, n1, n2) percpu_cmpxchg8b_double(pcp1, o1, o2, n1, n2) +#define this_cpu_cmpxchg_double_4(pcp1, pcp2, o1, o2, n1, n2) percpu_cmpxchg8b_double(pcp1, o1, o2, n1, n2) +#define irqsafe_cpu_cmpxchg_double_4(pcp1, pcp2, o1, o2, n1, n2) percpu_cmpxchg8b_double(pcp1, o1, o2, n1, n2) +#endif /* CONFIG_X86_CMPXCHG64 */ + /* * Per cpu atomic 64 bit operations are only available under 64 bit. * 32 bit must fall back to generic operations. @@ -480,6 +502,34 @@ do { \ #define irqsafe_cpu_xor_8(pcp, val) percpu_to_op("xor", (pcp), val) #define irqsafe_cpu_xchg_8(pcp, nval) percpu_xchg_op(pcp, nval) #define irqsafe_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(pcp, oval, nval) + +/* + * Pretty complex macro to generate cmpxchg16 instruction. The instruction + * is not supported on early AMD64 processors so we must be able to emulate + * it in software. The address used in the cmpxchg16 instruction must be + * aligned to a 16 byte boundary. + */ +#define percpu_cmpxchg16b_double(pcp1, o1, o2, n1, n2) \ +({ \ + char __ret; \ + typeof(o1) __o1 = o1; \ + typeof(o1) __n1 = n1; \ + typeof(o2) __o2 = o2; \ + typeof(o2) __n2 = n2; \ + typeof(o2) __dummy; \ + alternative_io("call this_cpu_cmpxchg16b_emu\n\t" P6_NOP4, \ + "cmpxchg16b " __percpu_prefix "(%%rsi)\n\tsetz %0\n\t", \ + X86_FEATURE_CX16, \ + ASM_OUTPUT2("=a"(__ret), "=d"(__dummy)), \ + "S" (&pcp1), "b"(__n1), "c"(__n2), \ + "a"(__o1), "d"(__o2) : "memory"); \ + __ret; \ +}) + +#define __this_cpu_cmpxchg_double_8(pcp1, pcp2, o1, o2, n1, n2) percpu_cmpxchg16b_double(pcp1, o1, o2, n1, n2) +#define this_cpu_cmpxchg_double_8(pcp1, pcp2, o1, o2, n1, n2) percpu_cmpxchg16b_double(pcp1, o1, o2, n1, n2) +#define irqsafe_cpu_cmpxchg_double_8(pcp1, pcp2, o1, o2, n1, n2) percpu_cmpxchg16b_double(pcp1, o1, o2, n1, n2) + #endif /* This is not atomic against other CPUs -- CPU preemption needs to be off */ diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h index e2f6a99f14a..56fd9e3abbd 100644 --- a/arch/x86/include/asm/perf_event_p4.h +++ b/arch/x86/include/asm/perf_event_p4.h @@ -1,5 +1,5 @@ /* - * Netburst Perfomance Events (P4, old Xeon) + * Netburst Performance Events (P4, old Xeon) */ #ifndef PERF_EVENT_P4_H @@ -9,7 +9,7 @@ #include <linux/bitops.h> /* - * NetBurst has perfomance MSRs shared between + * NetBurst has performance MSRs shared between * threads if HT is turned on, ie for both logical * processors (mem: in turn in Atom with HT support * perf-MSRs are not shared and every thread has its @@ -22,6 +22,7 @@ #define ARCH_P4_CNTRVAL_BITS (40) #define ARCH_P4_CNTRVAL_MASK ((1ULL << ARCH_P4_CNTRVAL_BITS) - 1) +#define ARCH_P4_UNFLAGGED_BIT ((1ULL) << (ARCH_P4_CNTRVAL_BITS - 1)) #define P4_ESCR_EVENT_MASK 0x7e000000U #define P4_ESCR_EVENT_SHIFT 25 diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h index 94b979d1b58..effff47a3c8 100644 --- a/arch/x86/include/asm/pgtable-3level.h +++ b/arch/x86/include/asm/pgtable-3level.h @@ -69,8 +69,6 @@ static inline void native_pmd_clear(pmd_t *pmd) static inline void pud_clear(pud_t *pudp) { - unsigned long pgd; - set_pud(pudp, __pud(0)); /* @@ -79,13 +77,10 @@ static inline void pud_clear(pud_t *pudp) * section 8.1: in PAE mode we explicitly have to flush the * TLB via cr3 if the top-level pgd is changed... * - * Make sure the pud entry we're updating is within the - * current pgd to avoid unnecessary TLB flushes. + * Currently all places where pud_clear() is called either have + * flush_tlb_mm() followed or don't need TLB flush (x86_64 code or + * pud_clear_bad()), so we don't need TLB flush here. */ - pgd = read_cr3(); - if (__pa(pudp) >= pgd && __pa(pudp) < - (pgd + sizeof(pgd_t)*PTRS_PER_PGD)) - write_cr3(pgd); } #ifdef CONFIG_SMP diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h index 7a3e836eb2a..a898a2b6e10 100644 --- a/arch/x86/include/asm/processor-flags.h +++ b/arch/x86/include/asm/processor-flags.h @@ -7,7 +7,7 @@ */ #define X86_EFLAGS_CF 0x00000001 /* Carry Flag */ #define X86_EFLAGS_PF 0x00000004 /* Parity Flag */ -#define X86_EFLAGS_AF 0x00000010 /* Auxillary carry Flag */ +#define X86_EFLAGS_AF 0x00000010 /* Auxiliary carry Flag */ #define X86_EFLAGS_ZF 0x00000040 /* Zero Flag */ #define X86_EFLAGS_SF 0x00000080 /* Sign Flag */ #define X86_EFLAGS_TF 0x00000100 /* Trap Flag */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 45636cefa18..4c25ab48257 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -94,10 +94,6 @@ struct cpuinfo_x86 { int x86_cache_alignment; /* In bytes */ int x86_power; unsigned long loops_per_jiffy; -#ifdef CONFIG_SMP - /* cpus sharing the last level cache: */ - cpumask_var_t llc_shared_map; -#endif /* cpuid returned max cores value: */ u16 x86_max_cores; u16 apicid; diff --git a/arch/x86/include/asm/prom.h b/arch/x86/include/asm/prom.h index b4ec95f0751..971e0b46446 100644 --- a/arch/x86/include/asm/prom.h +++ b/arch/x86/include/asm/prom.h @@ -1 +1,69 @@ -/* dummy prom.h; here to make linux/of.h's #includes happy */ +/* + * Definitions for Device tree / OpenFirmware handling on X86 + * + * based on arch/powerpc/include/asm/prom.h which is + * Copyright (C) 1996-2005 Paul Mackerras. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef _ASM_X86_PROM_H +#define _ASM_X86_PROM_H +#ifndef __ASSEMBLY__ + +#include <linux/of.h> +#include <linux/types.h> +#include <linux/pci.h> + +#include <asm/irq.h> +#include <asm/atomic.h> +#include <asm/setup.h> +#include <asm/irq_controller.h> + +#ifdef CONFIG_OF +extern int of_ioapic; +extern u64 initial_dtb; +extern void add_dtb(u64 data); +extern void x86_add_irq_domains(void); +void __cpuinit x86_of_pci_init(void); +void x86_dtb_init(void); + +static inline struct device_node *pci_device_to_OF_node(struct pci_dev *pdev) +{ + return pdev ? pdev->dev.of_node : NULL; +} + +static inline struct device_node *pci_bus_to_OF_node(struct pci_bus *bus) +{ + return pci_device_to_OF_node(bus->self); +} + +#else +static inline void add_dtb(u64 data) { } +static inline void x86_add_irq_domains(void) { } +static inline void x86_of_pci_init(void) { } +static inline void x86_dtb_init(void) { } +#define of_ioapic 0 +#endif + +extern char cmd_line[COMMAND_LINE_SIZE]; + +#define pci_address_to_pio pci_address_to_pio +unsigned long pci_address_to_pio(phys_addr_t addr); + +/** + * irq_dispose_mapping - Unmap an interrupt + * @virq: linux virq number of the interrupt to unmap + * + * FIXME: We really should implement proper virq handling like power, + * but that's going to be major surgery. + */ +static inline void irq_dispose_mapping(unsigned int virq) { } + +#define HAVE_ARCH_DEVTREE_FIXUPS + +#endif /* __ASSEMBLY__ */ +#endif diff --git a/arch/x86/include/asm/ptrace-abi.h b/arch/x86/include/asm/ptrace-abi.h index 52b098a6eeb..7b0a55a8885 100644 --- a/arch/x86/include/asm/ptrace-abi.h +++ b/arch/x86/include/asm/ptrace-abi.h @@ -31,7 +31,7 @@ #define R12 24 #define RBP 32 #define RBX 40 -/* arguments: interrupts/non tracing syscalls only save upto here*/ +/* arguments: interrupts/non tracing syscalls only save up to here*/ #define R11 48 #define R10 56 #define R9 64 diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 78cd1ea9450..1babf8adecd 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -73,7 +73,7 @@ struct pt_regs { unsigned long r12; unsigned long rbp; unsigned long rbx; -/* arguments: non interrupts/non tracing syscalls only save upto here*/ +/* arguments: non interrupts/non tracing syscalls only save up to here*/ unsigned long r11; unsigned long r10; unsigned long r9; @@ -103,7 +103,7 @@ struct pt_regs { unsigned long r12; unsigned long bp; unsigned long bx; -/* arguments: non interrupts/non tracing syscalls only save upto here*/ +/* arguments: non interrupts/non tracing syscalls only save up to here*/ unsigned long r11; unsigned long r10; unsigned long r9; diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h index 562d4fd31ba..3250e3d605d 100644 --- a/arch/x86/include/asm/reboot.h +++ b/arch/x86/include/asm/reboot.h @@ -18,7 +18,10 @@ extern struct machine_ops machine_ops; void native_machine_crash_shutdown(struct pt_regs *regs); void native_machine_shutdown(void); -void machine_real_restart(const unsigned char *code, int length); +void machine_real_restart(unsigned int type); +/* These must match dispatch_table in reboot_32.S */ +#define MRR_BIOS 0 +#define MRR_APM 1 typedef void (*nmi_shootdown_cb)(int, struct die_args*); void nmi_shootdown_cpus(nmi_shootdown_cb callback); diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h index d1e41b0f9b6..df4cd32b4cc 100644 --- a/arch/x86/include/asm/rwsem.h +++ b/arch/x86/include/asm/rwsem.h @@ -37,26 +37,9 @@ #endif #ifdef __KERNEL__ - -#include <linux/list.h> -#include <linux/spinlock.h> -#include <linux/lockdep.h> #include <asm/asm.h> -struct rwsem_waiter; - -extern asmregparm struct rw_semaphore * - rwsem_down_read_failed(struct rw_semaphore *sem); -extern asmregparm struct rw_semaphore * - rwsem_down_write_failed(struct rw_semaphore *sem); -extern asmregparm struct rw_semaphore * - rwsem_wake(struct rw_semaphore *); -extern asmregparm struct rw_semaphore * - rwsem_downgrade_wake(struct rw_semaphore *sem); - /* - * the semaphore definition - * * The bias values and the counter type limits the number of * potential readers/writers to 32767 for 32 bits and 2147483647 * for 64 bits. @@ -74,43 +57,6 @@ extern asmregparm struct rw_semaphore * #define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS #define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS) -typedef signed long rwsem_count_t; - -struct rw_semaphore { - rwsem_count_t count; - spinlock_t wait_lock; - struct list_head wait_list; -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lockdep_map dep_map; -#endif -}; - -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname } -#else -# define __RWSEM_DEP_MAP_INIT(lockname) -#endif - - -#define __RWSEM_INITIALIZER(name) \ -{ \ - RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait_lock), \ - LIST_HEAD_INIT((name).wait_list) __RWSEM_DEP_MAP_INIT(name) \ -} - -#define DECLARE_RWSEM(name) \ - struct rw_semaphore name = __RWSEM_INITIALIZER(name) - -extern void __init_rwsem(struct rw_semaphore *sem, const char *name, - struct lock_class_key *key); - -#define init_rwsem(sem) \ -do { \ - static struct lock_class_key __key; \ - \ - __init_rwsem((sem), #sem, &__key); \ -} while (0) - /* * lock for reading */ @@ -133,7 +79,7 @@ static inline void __down_read(struct rw_semaphore *sem) */ static inline int __down_read_trylock(struct rw_semaphore *sem) { - rwsem_count_t result, tmp; + long result, tmp; asm volatile("# beginning __down_read_trylock\n\t" " mov %0,%1\n\t" "1:\n\t" @@ -155,7 +101,7 @@ static inline int __down_read_trylock(struct rw_semaphore *sem) */ static inline void __down_write_nested(struct rw_semaphore *sem, int subclass) { - rwsem_count_t tmp; + long tmp; asm volatile("# beginning down_write\n\t" LOCK_PREFIX " xadd %1,(%2)\n\t" /* adds 0xffff0001, returns the old value */ @@ -180,9 +126,8 @@ static inline void __down_write(struct rw_semaphore *sem) */ static inline int __down_write_trylock(struct rw_semaphore *sem) { - rwsem_count_t ret = cmpxchg(&sem->count, - RWSEM_UNLOCKED_VALUE, - RWSEM_ACTIVE_WRITE_BIAS); + long ret = cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE, + RWSEM_ACTIVE_WRITE_BIAS); if (ret == RWSEM_UNLOCKED_VALUE) return 1; return 0; @@ -193,7 +138,7 @@ static inline int __down_write_trylock(struct rw_semaphore *sem) */ static inline void __up_read(struct rw_semaphore *sem) { - rwsem_count_t tmp; + long tmp; asm volatile("# beginning __up_read\n\t" LOCK_PREFIX " xadd %1,(%2)\n\t" /* subtracts 1, returns the old value */ @@ -211,7 +156,7 @@ static inline void __up_read(struct rw_semaphore *sem) */ static inline void __up_write(struct rw_semaphore *sem) { - rwsem_count_t tmp; + long tmp; asm volatile("# beginning __up_write\n\t" LOCK_PREFIX " xadd %1,(%2)\n\t" /* subtracts 0xffff0001, returns the old value */ @@ -247,8 +192,7 @@ static inline void __downgrade_write(struct rw_semaphore *sem) /* * implement atomic add functionality */ -static inline void rwsem_atomic_add(rwsem_count_t delta, - struct rw_semaphore *sem) +static inline void rwsem_atomic_add(long delta, struct rw_semaphore *sem) { asm volatile(LOCK_PREFIX _ASM_ADD "%1,%0" : "+m" (sem->count) @@ -258,10 +202,9 @@ static inline void rwsem_atomic_add(rwsem_count_t delta, /* * implement exchange and add functionality */ -static inline rwsem_count_t rwsem_atomic_update(rwsem_count_t delta, - struct rw_semaphore *sem) +static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem) { - rwsem_count_t tmp = delta; + long tmp = delta; asm volatile(LOCK_PREFIX "xadd %0,%1" : "+r" (tmp), "+m" (sem->count) @@ -270,10 +213,5 @@ static inline rwsem_count_t rwsem_atomic_update(rwsem_count_t delta, return tmp + delta; } -static inline int rwsem_is_locked(struct rw_semaphore *sem) -{ - return (sem->count != 0); -} - #endif /* __KERNEL__ */ #endif /* _ASM_X86_RWSEM_H */ diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index 231f1c1d660..cd84f7208f7 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -1,14 +1,16 @@ #ifndef _ASM_X86_SEGMENT_H #define _ASM_X86_SEGMENT_H +#include <linux/const.h> + /* Constructor for a conventional segment GDT (or LDT) entry */ /* This is a macro so it can be used in initializers */ #define GDT_ENTRY(flags, base, limit) \ - ((((base) & 0xff000000ULL) << (56-24)) | \ - (((flags) & 0x0000f0ffULL) << 40) | \ - (((limit) & 0x000f0000ULL) << (48-16)) | \ - (((base) & 0x00ffffffULL) << 16) | \ - (((limit) & 0x0000ffffULL))) + ((((base) & _AC(0xff000000,ULL)) << (56-24)) | \ + (((flags) & _AC(0x0000f0ff,ULL)) << 40) | \ + (((limit) & _AC(0x000f0000,ULL)) << (48-16)) | \ + (((base) & _AC(0x00ffffff,ULL)) << 16) | \ + (((limit) & _AC(0x0000ffff,ULL)))) /* Simple and small GDT entries for booting only */ diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 1f469513677..73b11bc0ae6 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -17,12 +17,24 @@ #endif #include <asm/thread_info.h> #include <asm/cpumask.h> +#include <asm/cpufeature.h> extern int smp_num_siblings; extern unsigned int num_processors; +static inline bool cpu_has_ht_siblings(void) +{ + bool has_siblings = false; +#ifdef CONFIG_SMP + has_siblings = cpu_has_ht && smp_num_siblings > 1; +#endif + return has_siblings; +} + DECLARE_PER_CPU(cpumask_var_t, cpu_sibling_map); DECLARE_PER_CPU(cpumask_var_t, cpu_core_map); +/* cpus sharing the last level cache: */ +DECLARE_PER_CPU(cpumask_var_t, cpu_llc_shared_map); DECLARE_PER_CPU(u16, cpu_llc_id); DECLARE_PER_CPU(int, cpu_number); @@ -36,8 +48,16 @@ static inline struct cpumask *cpu_core_mask(int cpu) return per_cpu(cpu_core_map, cpu); } +static inline struct cpumask *cpu_llc_shared_mask(int cpu) +{ + return per_cpu(cpu_llc_shared_map, cpu); +} + DECLARE_EARLY_PER_CPU(u16, x86_cpu_to_apicid); DECLARE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid); +#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32) +DECLARE_EARLY_PER_CPU(int, x86_cpu_to_logical_apicid); +#endif /* Static state in head.S used to set up a CPU */ extern unsigned long stack_start; /* Initial stack pointer address */ diff --git a/arch/x86/include/asm/smpboot_hooks.h b/arch/x86/include/asm/smpboot_hooks.h index 6c22bf353f2..725b7783199 100644 --- a/arch/x86/include/asm/smpboot_hooks.h +++ b/arch/x86/include/asm/smpboot_hooks.h @@ -34,7 +34,7 @@ static inline void smpboot_restore_warm_reset_vector(void) */ CMOS_WRITE(0, 0xf); - *((volatile long *)phys_to_virt(apic->trampoline_phys_low)) = 0; + *((volatile u32 *)phys_to_virt(apic->trampoline_phys_low)) = 0; } static inline void __init smpboot_setup_io_apic(void) diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index 52b5c7ed360..d7e89c83645 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -47,7 +47,7 @@ struct stacktrace_ops { }; void dump_trace(struct task_struct *tsk, struct pt_regs *regs, - unsigned long *stack, + unsigned long *stack, unsigned long bp, const struct stacktrace_ops *ops, void *data); #ifdef CONFIG_X86_32 @@ -86,11 +86,11 @@ stack_frame(struct task_struct *task, struct pt_regs *regs) extern void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, char *log_lvl); + unsigned long *stack, unsigned long bp, char *log_lvl); extern void show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *sp, char *log_lvl); + unsigned long *sp, unsigned long bp, char *log_lvl); extern unsigned int code_bytes; diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h index 33ecc3ea878..12569e691ce 100644 --- a/arch/x86/include/asm/system.h +++ b/arch/x86/include/asm/system.h @@ -98,8 +98,6 @@ do { \ */ #define HAVE_DISABLE_HLT #else -#define __SAVE(reg, offset) "movq %%" #reg ",(14-" #offset ")*8(%%rsp)\n\t" -#define __RESTORE(reg, offset) "movq (14-" #offset ")*8(%%rsp),%%" #reg "\n\t" /* frame pointer must be last for get_wchan */ #define SAVE_CONTEXT "pushf ; pushq %%rbp ; movq %%rsi,%%rbp\n\t" diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index f0b6e5dbc5a..1f2e61e2898 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -161,8 +161,14 @@ struct thread_info { #define __HAVE_ARCH_THREAD_INFO_ALLOCATOR -#define alloc_thread_info(tsk) \ - ((struct thread_info *)__get_free_pages(THREAD_FLAGS, THREAD_ORDER)) +#define alloc_thread_info_node(tsk, node) \ +({ \ + struct page *page = alloc_pages_node(node, THREAD_FLAGS, \ + THREAD_ORDER); \ + struct thread_info *ret = page ? page_address(page) : NULL; \ + \ + ret; \ +}) #ifdef CONFIG_X86_32 diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 21899cc31e5..910a7084f7f 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -47,21 +47,6 @@ #include <asm/mpspec.h> -#ifdef CONFIG_X86_32 - -/* Mappings between logical cpu number and node number */ -extern int cpu_to_node_map[]; - -/* Returns the number of the node containing CPU 'cpu' */ -static inline int __cpu_to_node(int cpu) -{ - return cpu_to_node_map[cpu]; -} -#define early_cpu_to_node __cpu_to_node -#define cpu_to_node __cpu_to_node - -#else /* CONFIG_X86_64 */ - /* Mappings between logical cpu number and node number */ DECLARE_EARLY_PER_CPU(int, x86_cpu_to_node_map); @@ -84,8 +69,6 @@ static inline int early_cpu_to_node(int cpu) #endif /* !CONFIG_DEBUG_PER_CPU_MAPS */ -#endif /* CONFIG_X86_64 */ - /* Mappings between node number and cpus on that node. */ extern cpumask_var_t node_to_cpumask_map[MAX_NUMNODES]; @@ -155,7 +138,7 @@ extern unsigned long node_remap_size[]; .balance_interval = 1, \ } -#ifdef CONFIG_X86_64_ACPI_NUMA +#ifdef CONFIG_X86_64 extern int __node_distance(int, int); #define node_distance(a, b) __node_distance(a, b) #endif diff --git a/arch/x86/include/asm/trampoline.h b/arch/x86/include/asm/trampoline.h index f4500fb3b48..feca3118a73 100644 --- a/arch/x86/include/asm/trampoline.h +++ b/arch/x86/include/asm/trampoline.h @@ -3,25 +3,36 @@ #ifndef __ASSEMBLY__ -#ifdef CONFIG_X86_TRAMPOLINE +#include <linux/types.h> +#include <asm/io.h> + /* - * Trampoline 80x86 program as an array. + * Trampoline 80x86 program as an array. These are in the init rodata + * segment, but that's okay, because we only care about the relative + * addresses of the symbols. */ -extern const unsigned char trampoline_data []; -extern const unsigned char trampoline_end []; -extern unsigned char *trampoline_base; +extern const unsigned char x86_trampoline_start []; +extern const unsigned char x86_trampoline_end []; +extern unsigned char *x86_trampoline_base; extern unsigned long init_rsp; extern unsigned long initial_code; extern unsigned long initial_gs; -#define TRAMPOLINE_SIZE roundup(trampoline_end - trampoline_data, PAGE_SIZE) +extern void __init setup_trampolines(void); + +extern const unsigned char trampoline_data[]; +extern const unsigned char trampoline_status[]; + +#define TRAMPOLINE_SYM(x) \ + ((void *)(x86_trampoline_base + \ + ((const unsigned char *)(x) - x86_trampoline_start))) -extern unsigned long setup_trampoline(void); -extern void __init reserve_trampoline_memory(void); -#else -static inline void reserve_trampoline_memory(void) {} -#endif /* CONFIG_X86_TRAMPOLINE */ +/* Address of the SMP trampoline */ +static inline unsigned long trampoline_address(void) +{ + return virt_to_phys(TRAMPOLINE_SYM(trampoline_data)); +} #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h index 1ca132fc0d0..83e2efd181e 100644 --- a/arch/x86/include/asm/tsc.h +++ b/arch/x86/include/asm/tsc.h @@ -35,7 +35,7 @@ static inline cycles_t get_cycles(void) static __always_inline cycles_t vget_cycles(void) { /* - * We only do VDSOs on TSC capable CPUs, so this shouldnt + * We only do VDSOs on TSC capable CPUs, so this shouldn't * access boot_cpu_data (which is not VDSO-safe): */ #ifndef CONFIG_X86_TSC diff --git a/arch/x86/include/asm/types.h b/arch/x86/include/asm/types.h index df1da20f453..8e8c23fef08 100644 --- a/arch/x86/include/asm/types.h +++ b/arch/x86/include/asm/types.h @@ -1,22 +1,6 @@ #ifndef _ASM_X86_TYPES_H #define _ASM_X86_TYPES_H -#define dma_addr_t dma_addr_t - #include <asm-generic/types.h> -#ifdef __KERNEL__ -#ifndef __ASSEMBLY__ - -typedef u64 dma64_addr_t; -#if defined(CONFIG_X86_64) || defined(CONFIG_HIGHMEM64G) -/* DMA addresses come in 32-bit and 64-bit flavours. */ -typedef u64 dma_addr_t; -#else -typedef u32 dma_addr_t; -#endif - -#endif /* __ASSEMBLY__ */ -#endif /* __KERNEL__ */ - #endif /* _ASM_X86_TYPES_H */ diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h index b766a5e8ba0..a755ef5e597 100644 --- a/arch/x86/include/asm/unistd_32.h +++ b/arch/x86/include/asm/unistd_32.h @@ -346,10 +346,14 @@ #define __NR_fanotify_init 338 #define __NR_fanotify_mark 339 #define __NR_prlimit64 340 +#define __NR_name_to_handle_at 341 +#define __NR_open_by_handle_at 342 +#define __NR_clock_adjtime 343 +#define __NR_syncfs 344 #ifdef __KERNEL__ -#define NR_syscalls 341 +#define NR_syscalls 345 #define __ARCH_WANT_IPC_PARSE_VERSION #define __ARCH_WANT_OLD_READDIR diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h index 363e9b8a715..160fa76bd57 100644 --- a/arch/x86/include/asm/unistd_64.h +++ b/arch/x86/include/asm/unistd_64.h @@ -669,6 +669,14 @@ __SYSCALL(__NR_fanotify_init, sys_fanotify_init) __SYSCALL(__NR_fanotify_mark, sys_fanotify_mark) #define __NR_prlimit64 302 __SYSCALL(__NR_prlimit64, sys_prlimit64) +#define __NR_name_to_handle_at 303 +__SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at) +#define __NR_open_by_handle_at 304 +__SYSCALL(__NR_open_by_handle_at, sys_open_by_handle_at) +#define __NR_clock_adjtime 305 +__SYSCALL(__NR_clock_adjtime, sys_clock_adjtime) +#define __NR_syncfs 306 +__SYSCALL(__NR_syncfs, sys_syncfs) #ifndef __NO_STUBS #define __ARCH_WANT_OLD_READDIR diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h index ce1d54c8a43..3e094af443c 100644 --- a/arch/x86/include/asm/uv/uv_bau.h +++ b/arch/x86/include/asm/uv/uv_bau.h @@ -176,7 +176,7 @@ struct bau_msg_payload { struct bau_msg_header { unsigned int dest_subnodeid:6; /* must be 0x10, for the LB */ /* bits 5:0 */ - unsigned int base_dest_nodeid:15; /* nasid (pnode<<1) of */ + unsigned int base_dest_nodeid:15; /* nasid of the */ /* bits 20:6 */ /* first bit in uvhub map */ unsigned int command:8; /* message type */ /* bits 28:21 */ diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 64642ad019f..643ebf2e2ad 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -83,11 +83,13 @@ struct x86_init_paging { * boot cpu * @tsc_pre_init: platform function called before TSC init * @timer_init: initialize the platform timer (default PIT/HPET) + * @wallclock_init: init the wallclock device */ struct x86_init_timers { void (*setup_percpu_clockev)(void); void (*tsc_pre_init)(void); void (*timer_init)(void); + void (*wallclock_init)(void); }; /** diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index a3c28ae4025..8508bfe5229 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -287,7 +287,7 @@ HYPERVISOR_fpu_taskswitch(int set) static inline int HYPERVISOR_sched_op(int cmd, void *arg) { - return _hypercall2(int, sched_op_new, cmd, arg); + return _hypercall2(int, sched_op, cmd, arg); } static inline long @@ -422,10 +422,17 @@ HYPERVISOR_set_segment_base(int reg, unsigned long value) #endif static inline int -HYPERVISOR_suspend(unsigned long srec) +HYPERVISOR_suspend(unsigned long start_info_mfn) { - return _hypercall3(int, sched_op, SCHEDOP_shutdown, - SHUTDOWN_suspend, srec); + struct sched_shutdown r = { .reason = SHUTDOWN_suspend }; + + /* + * For a PV guest the tools require that the start_info mfn be + * present in rdx/edx when the hypercall is made. Per the + * hypercall calling convention this is the third hypercall + * argument, which is start_info_mfn here. + */ + return _hypercall3(int, sched_op, SCHEDOP_shutdown, &r, start_info_mfn); } static inline int diff --git a/arch/x86/include/asm/xen/interface.h b/arch/x86/include/asm/xen/interface.h index 1c10c88ee4e..5d4922ad4b9 100644 --- a/arch/x86/include/asm/xen/interface.h +++ b/arch/x86/include/asm/xen/interface.h @@ -86,7 +86,7 @@ DEFINE_GUEST_HANDLE(void); * The privilege level specifies which modes may enter a trap via a software * interrupt. On x86/64, since rings 1 and 2 are unavailable, we allocate * privilege levels as follows: - * Level == 0: Noone may enter + * Level == 0: No one may enter * Level == 1: Kernel may enter * Level == 2: Kernel may enter * Level == 3: Everyone may enter diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index f25bdf238a3..c61934fbf22 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -29,8 +29,10 @@ typedef struct xpaddr { /**** MACHINE <-> PHYSICAL CONVERSION MACROS ****/ #define INVALID_P2M_ENTRY (~0UL) -#define FOREIGN_FRAME_BIT (1UL<<31) +#define FOREIGN_FRAME_BIT (1UL<<(BITS_PER_LONG-1)) +#define IDENTITY_FRAME_BIT (1UL<<(BITS_PER_LONG-2)) #define FOREIGN_FRAME(m) ((m) | FOREIGN_FRAME_BIT) +#define IDENTITY_FRAME(m) ((m) | IDENTITY_FRAME_BIT) /* Maximum amount of memory we can handle in a domain in pages */ #define MAX_DOMAIN_PAGES \ @@ -41,12 +43,18 @@ extern unsigned int machine_to_phys_order; extern unsigned long get_phys_to_machine(unsigned long pfn); extern bool set_phys_to_machine(unsigned long pfn, unsigned long mfn); +extern bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn); +extern unsigned long set_phys_range_identity(unsigned long pfn_s, + unsigned long pfn_e); extern int m2p_add_override(unsigned long mfn, struct page *page); extern int m2p_remove_override(struct page *page); extern struct page *m2p_find_override(unsigned long mfn); extern unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn); +#ifdef CONFIG_XEN_DEBUG_FS +extern int p2m_dump_show(struct seq_file *m, void *v); +#endif static inline unsigned long pfn_to_mfn(unsigned long pfn) { unsigned long mfn; @@ -57,7 +65,7 @@ static inline unsigned long pfn_to_mfn(unsigned long pfn) mfn = get_phys_to_machine(pfn); if (mfn != INVALID_P2M_ENTRY) - mfn &= ~FOREIGN_FRAME_BIT; + mfn &= ~(FOREIGN_FRAME_BIT | IDENTITY_FRAME_BIT); return mfn; } @@ -73,25 +81,44 @@ static inline int phys_to_machine_mapping_valid(unsigned long pfn) static inline unsigned long mfn_to_pfn(unsigned long mfn) { unsigned long pfn; + int ret = 0; if (xen_feature(XENFEAT_auto_translated_physmap)) return mfn; + if (unlikely((mfn >> machine_to_phys_order) != 0)) { + pfn = ~0; + goto try_override; + } pfn = 0; /* * The array access can fail (e.g., device space beyond end of RAM). * In such cases it doesn't matter what we return (we return garbage), * but we must handle the fault without crashing! */ - __get_user(pfn, &machine_to_phys_mapping[mfn]); - - /* - * If this appears to be a foreign mfn (because the pfn - * doesn't map back to the mfn), then check the local override - * table to see if there's a better pfn to use. + ret = __get_user(pfn, &machine_to_phys_mapping[mfn]); +try_override: + /* ret might be < 0 if there are no entries in the m2p for mfn */ + if (ret < 0) + pfn = ~0; + else if (get_phys_to_machine(pfn) != mfn) + /* + * If this appears to be a foreign mfn (because the pfn + * doesn't map back to the mfn), then check the local override + * table to see if there's a better pfn to use. + * + * m2p_find_override_pfn returns ~0 if it doesn't find anything. + */ + pfn = m2p_find_override_pfn(mfn, ~0); + + /* + * pfn is ~0 if there are no entries in the m2p for mfn or if the + * entry doesn't map back to the mfn and m2p_override doesn't have a + * valid entry for it. */ - if (get_phys_to_machine(pfn) != mfn) - pfn = m2p_find_override_pfn(mfn, pfn); + if (pfn == ~0 && + get_phys_to_machine(mfn) == IDENTITY_FRAME(mfn)) + pfn = mfn; return pfn; } diff --git a/arch/x86/include/asm/xen/pci.h b/arch/x86/include/asm/xen/pci.h index 2329b3eaf8d..aa862098916 100644 --- a/arch/x86/include/asm/xen/pci.h +++ b/arch/x86/include/asm/xen/pci.h @@ -27,16 +27,16 @@ static inline void __init xen_setup_pirqs(void) * its own functions. */ struct xen_pci_frontend_ops { - int (*enable_msi)(struct pci_dev *dev, int **vectors); + int (*enable_msi)(struct pci_dev *dev, int vectors[]); void (*disable_msi)(struct pci_dev *dev); - int (*enable_msix)(struct pci_dev *dev, int **vectors, int nvec); + int (*enable_msix)(struct pci_dev *dev, int vectors[], int nvec); void (*disable_msix)(struct pci_dev *dev); }; extern struct xen_pci_frontend_ops *xen_pci_frontend; static inline int xen_pci_frontend_enable_msi(struct pci_dev *dev, - int **vectors) + int vectors[]) { if (xen_pci_frontend && xen_pci_frontend->enable_msi) return xen_pci_frontend->enable_msi(dev, vectors); @@ -48,7 +48,7 @@ static inline void xen_pci_frontend_disable_msi(struct pci_dev *dev) xen_pci_frontend->disable_msi(dev); } static inline int xen_pci_frontend_enable_msix(struct pci_dev *dev, - int **vectors, int nvec) + int vectors[], int nvec) { if (xen_pci_frontend && xen_pci_frontend->enable_msix) return xen_pci_frontend->enable_msix(dev, vectors, nvec); diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 34244b2cd88..7338ef2218b 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -41,13 +41,13 @@ obj-$(CONFIG_X86_32) += sys_i386_32.o i386_ksyms_32.o obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o obj-$(CONFIG_X86_64) += syscall_64.o vsyscall_64.o obj-y += bootflag.o e820.o -obj-y += pci-dma.o quirks.o i8237.o topology.o kdebugfs.o +obj-y += pci-dma.o quirks.o topology.o kdebugfs.o obj-y += alternative.o i8253.o pci-nommu.o hw_breakpoint.o obj-y += tsc.o io_delay.o rtc.o obj-y += pci-iommu_table.o obj-y += resource.o -obj-$(CONFIG_X86_TRAMPOLINE) += trampoline.o +obj-y += trampoline.o trampoline_$(BITS).o obj-y += process.o obj-y += i387.o xsave.o obj-y += ptrace.o @@ -55,10 +55,12 @@ obj-$(CONFIG_X86_32) += tls.o obj-$(CONFIG_IA32_EMULATION) += tls.o obj-y += step.o obj-$(CONFIG_INTEL_TXT) += tboot.o +obj-$(CONFIG_ISA_DMA_API) += i8237.o obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-y += cpu/ obj-y += acpi/ obj-y += reboot.o +obj-$(CONFIG_X86_32) += reboot_32.o obj-$(CONFIG_MCA) += mca_32.o obj-$(CONFIG_X86_MSR) += msr.o obj-$(CONFIG_X86_CPUID) += cpuid.o @@ -66,10 +68,9 @@ obj-$(CONFIG_PCI) += early-quirks.o apm-y := apm_32.o obj-$(CONFIG_APM) += apm.o obj-$(CONFIG_SMP) += smp.o -obj-$(CONFIG_SMP) += smpboot.o tsc_sync.o +obj-$(CONFIG_SMP) += smpboot.o +obj-$(CONFIG_SMP) += tsc_sync.o obj-$(CONFIG_SMP) += setup_percpu.o -obj-$(CONFIG_X86_64_SMP) += tsc_sync.o -obj-$(CONFIG_X86_TRAMPOLINE) += trampoline_$(BITS).o obj-$(CONFIG_X86_MPPARSE) += mpparse.o obj-y += apic/ obj-$(CONFIG_X86_REBOOTFIXUPS) += reboot_fixups_32.o @@ -109,6 +110,7 @@ obj-$(CONFIG_MICROCODE) += microcode.o obj-$(CONFIG_X86_CHECK_BIOS_CORRUPTION) += check.o obj-$(CONFIG_SWIOTLB) += pci-swiotlb.o +obj-$(CONFIG_OF) += devicetree.o ### # 64 bit specific files diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index b3a71137983..9a966c579af 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -72,6 +72,7 @@ u8 acpi_sci_flags __initdata; int acpi_sci_override_gsi __initdata; int acpi_skip_timer_override __initdata; int acpi_use_timer_override __initdata; +int acpi_fix_pin2_polarity __initdata; #ifdef CONFIG_X86_LOCAL_APIC static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE; @@ -415,10 +416,15 @@ acpi_parse_int_src_ovr(struct acpi_subtable_header * header, return 0; } - if (acpi_skip_timer_override && - intsrc->source_irq == 0 && intsrc->global_irq == 2) { - printk(PREFIX "BIOS IRQ0 pin2 override ignored.\n"); - return 0; + if (intsrc->source_irq == 0 && intsrc->global_irq == 2) { + if (acpi_skip_timer_override) { + printk(PREFIX "BIOS IRQ0 pin2 override ignored.\n"); + return 0; + } + if (acpi_fix_pin2_polarity && (intsrc->inti_flags & ACPI_MADT_POLARITY_MASK)) { + intsrc->inti_flags &= ~ACPI_MADT_POLARITY_MASK; + printk(PREFIX "BIOS IRQ0 pin2 override: forcing polarity to high active.\n"); + } } mp_override_legacy_irq(intsrc->source_irq, @@ -589,14 +595,8 @@ static void acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) nid = acpi_get_node(handle); if (nid == -1 || !node_online(nid)) return; -#ifdef CONFIG_X86_64 - apicid_to_node[physid] = nid; + set_apicid_to_node(physid, nid); numa_set_node(cpu, nid); -#else /* CONFIG_X86_32 */ - apicid_2_node[physid] = nid; - cpu_to_node_map[cpu] = nid; -#endif - #endif } diff --git a/arch/x86/kernel/acpi/realmode/wakeup.S b/arch/x86/kernel/acpi/realmode/wakeup.S index 28595d6df47..ead21b66311 100644 --- a/arch/x86/kernel/acpi/realmode/wakeup.S +++ b/arch/x86/kernel/acpi/realmode/wakeup.S @@ -6,11 +6,17 @@ #include <asm/page_types.h> #include <asm/pgtable_types.h> #include <asm/processor-flags.h> +#include "wakeup.h" .code16 - .section ".header", "a" + .section ".jump", "ax" + .globl _start +_start: + cli + jmp wakeup_code /* This should match the structure in wakeup.h */ + .section ".header", "a" .globl wakeup_header wakeup_header: video_mode: .short 0 /* Video mode number */ @@ -30,14 +36,11 @@ wakeup_jmp: .byte 0xea /* ljmpw */ wakeup_jmp_off: .word 3f wakeup_jmp_seg: .word 0 wakeup_gdt: .quad 0, 0, 0 -signature: .long 0x51ee1111 +signature: .long WAKEUP_HEADER_SIGNATURE .text - .globl _start .code16 wakeup_code: -_start: - cli cld /* Apparently some dimwit BIOS programmers don't know how to @@ -77,12 +80,12 @@ _start: /* Check header signature... */ movl signature, %eax - cmpl $0x51ee1111, %eax + cmpl $WAKEUP_HEADER_SIGNATURE, %eax jne bogus_real_magic /* Check we really have everything... */ movl end_signature, %eax - cmpl $0x65a22c82, %eax + cmpl $WAKEUP_END_SIGNATURE, %eax jne bogus_real_magic /* Call the C code */ @@ -147,3 +150,7 @@ wakeup_heap: wakeup_stack: .space 2048 wakeup_stack_end: + + .section ".signature","a" +end_signature: + .long WAKEUP_END_SIGNATURE diff --git a/arch/x86/kernel/acpi/realmode/wakeup.h b/arch/x86/kernel/acpi/realmode/wakeup.h index 69d38d0b2b6..e1828c07e79 100644 --- a/arch/x86/kernel/acpi/realmode/wakeup.h +++ b/arch/x86/kernel/acpi/realmode/wakeup.h @@ -35,7 +35,8 @@ struct wakeup_header { extern struct wakeup_header wakeup_header; #endif -#define HEADER_OFFSET 0x3f00 -#define WAKEUP_SIZE 0x4000 +#define WAKEUP_HEADER_OFFSET 8 +#define WAKEUP_HEADER_SIGNATURE 0x51ee1111 +#define WAKEUP_END_SIGNATURE 0x65a22c82 #endif /* ARCH_X86_KERNEL_ACPI_RM_WAKEUP_H */ diff --git a/arch/x86/kernel/acpi/realmode/wakeup.lds.S b/arch/x86/kernel/acpi/realmode/wakeup.lds.S index 060fff8f5c5..d4f8010a5b1 100644 --- a/arch/x86/kernel/acpi/realmode/wakeup.lds.S +++ b/arch/x86/kernel/acpi/realmode/wakeup.lds.S @@ -13,9 +13,19 @@ ENTRY(_start) SECTIONS { . = 0; + .jump : { + *(.jump) + } = 0x90909090 + + . = WAKEUP_HEADER_OFFSET; + .header : { + *(.header) + } + + . = ALIGN(16); .text : { *(.text*) - } + } = 0x90909090 . = ALIGN(16); .rodata : { @@ -33,11 +43,6 @@ SECTIONS *(.data*) } - .signature : { - end_signature = .; - LONG(0x65a22c82) - } - . = ALIGN(16); .bss : { __bss_start = .; @@ -45,20 +50,13 @@ SECTIONS __bss_end = .; } - . = HEADER_OFFSET; - .header : { - *(.header) + .signature : { + *(.signature) } - . = ALIGN(16); _end = .; /DISCARD/ : { *(.note*) } - - /* - * The ASSERT() sink to . is intentional, for binutils 2.14 compatibility: - */ - . = ASSERT(_end <= WAKEUP_SIZE, "Wakeup too big!"); } diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 68d1537b8c8..ff93bc1b09c 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -18,37 +18,28 @@ #include "realmode/wakeup.h" #include "sleep.h" -unsigned long acpi_wakeup_address; unsigned long acpi_realmode_flags; -/* address in low memory of the wakeup routine. */ -static unsigned long acpi_realmode; - #if defined(CONFIG_SMP) && defined(CONFIG_64BIT) static char temp_stack[4096]; #endif /** - * acpi_save_state_mem - save kernel state + * acpi_suspend_lowlevel - save kernel state * * Create an identity mapped page table and copy the wakeup routine to * low memory. - * - * Note that this is too late to change acpi_wakeup_address. */ -int acpi_save_state_mem(void) +int acpi_suspend_lowlevel(void) { struct wakeup_header *header; + /* address in low memory of the wakeup routine. */ + char *acpi_realmode; - if (!acpi_realmode) { - printk(KERN_ERR "Could not allocate memory during boot, " - "S3 disabled\n"); - return -ENOMEM; - } - memcpy((void *)acpi_realmode, &wakeup_code_start, WAKEUP_SIZE); + acpi_realmode = TRAMPOLINE_SYM(acpi_wakeup_code); - header = (struct wakeup_header *)(acpi_realmode + HEADER_OFFSET); - if (header->signature != 0x51ee1111) { + header = (struct wakeup_header *)(acpi_realmode + WAKEUP_HEADER_OFFSET); + if (header->signature != WAKEUP_HEADER_SIGNATURE) { printk(KERN_ERR "wakeup header does not match\n"); return -EINVAL; } @@ -68,9 +59,7 @@ int acpi_save_state_mem(void) /* GDT[0]: GDT self-pointer */ header->wakeup_gdt[0] = (u64)(sizeof(header->wakeup_gdt) - 1) + - ((u64)(acpi_wakeup_address + - ((char *)&header->wakeup_gdt - (char *)acpi_realmode)) - << 16); + ((u64)__pa(&header->wakeup_gdt) << 16); /* GDT[1]: big real mode-like code segment */ header->wakeup_gdt[1] = GDT_ENTRY(0x809b, acpi_wakeup_address, 0xfffff); @@ -96,7 +85,7 @@ int acpi_save_state_mem(void) header->pmode_cr3 = (u32)__pa(&initial_page_table); saved_magic = 0x12345678; #else /* CONFIG_64BIT */ - header->trampoline_segment = setup_trampoline() >> 4; + header->trampoline_segment = trampoline_address() >> 4; #ifdef CONFIG_SMP stack_start = (unsigned long)temp_stack + sizeof(temp_stack); early_gdt_descr.address = @@ -107,56 +96,10 @@ int acpi_save_state_mem(void) saved_magic = 0x123456789abcdef0L; #endif /* CONFIG_64BIT */ + do_suspend_lowlevel(); return 0; } -/* - * acpi_restore_state - undo effects of acpi_save_state_mem - */ -void acpi_restore_state_mem(void) -{ -} - - -/** - * acpi_reserve_wakeup_memory - do _very_ early ACPI initialisation - * - * We allocate a page from the first 1MB of memory for the wakeup - * routine for when we come back from a sleep state. The - * runtime allocator allows specification of <16MB pages, but not - * <1MB pages. - */ -void __init acpi_reserve_wakeup_memory(void) -{ - phys_addr_t mem; - - if ((&wakeup_code_end - &wakeup_code_start) > WAKEUP_SIZE) { - printk(KERN_ERR - "ACPI: Wakeup code way too big, S3 disabled.\n"); - return; - } - - mem = memblock_find_in_range(0, 1<<20, WAKEUP_SIZE, PAGE_SIZE); - - if (mem == MEMBLOCK_ERROR) { - printk(KERN_ERR "ACPI: Cannot allocate lowmem, S3 disabled.\n"); - return; - } - acpi_realmode = (unsigned long) phys_to_virt(mem); - acpi_wakeup_address = mem; - memblock_x86_reserve_range(mem, mem + WAKEUP_SIZE, "ACPI WAKEUP"); -} - -int __init acpi_configure_wakeup_memory(void) -{ - if (acpi_realmode) - set_memory_x(acpi_realmode, WAKEUP_SIZE >> PAGE_SHIFT); - - return 0; -} -arch_initcall(acpi_configure_wakeup_memory); - - static int __init acpi_sleep_setup(char *str) { while ((str != NULL) && (*str != '\0')) { diff --git a/arch/x86/kernel/acpi/sleep.h b/arch/x86/kernel/acpi/sleep.h index adbcbaa6f1d..416d4be13fe 100644 --- a/arch/x86/kernel/acpi/sleep.h +++ b/arch/x86/kernel/acpi/sleep.h @@ -4,13 +4,12 @@ #include <asm/trampoline.h> -extern char wakeup_code_start, wakeup_code_end; - extern unsigned long saved_video_mode; extern long saved_magic; extern int wakeup_pmode_return; -extern char swsusp_pg_dir[PAGE_SIZE]; extern unsigned long acpi_copy_wakeup_routine(unsigned long); extern void wakeup_long64(void); + +extern void do_suspend_lowlevel(void); diff --git a/arch/x86/kernel/acpi/wakeup_rm.S b/arch/x86/kernel/acpi/wakeup_rm.S index 6ff3b573057..63b8ab524f2 100644 --- a/arch/x86/kernel/acpi/wakeup_rm.S +++ b/arch/x86/kernel/acpi/wakeup_rm.S @@ -2,9 +2,11 @@ * Wrapper script for the realmode binary as a transport object * before copying to low memory. */ - .section ".rodata","a" - .globl wakeup_code_start, wakeup_code_end -wakeup_code_start: +#include <asm/page_types.h> + + .section ".x86_trampoline","a" + .balign PAGE_SIZE + .globl acpi_wakeup_code +acpi_wakeup_code: .incbin "arch/x86/kernel/acpi/realmode/wakeup.bin" -wakeup_code_end: - .size wakeup_code_start, .-wakeup_code_start + .size acpi_wakeup_code, .-acpi_wakeup_code diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 7038b95d363..4a234677e21 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -199,7 +199,7 @@ void *text_poke_early(void *addr, const void *opcode, size_t len); /* Replace instructions with better alternatives for this CPU type. This runs before SMP is initialized to avoid SMP problems with - self modifying code. This implies that assymetric systems where + self modifying code. This implies that asymmetric systems where APs have less capabilities than the boot processor are not handled. Tough. Make sure you disable such features by hand. */ @@ -620,7 +620,12 @@ static int __kprobes stop_machine_text_poke(void *data) flush_icache_range((unsigned long)p->addr, (unsigned long)p->addr + p->len); } - + /* + * Intel Archiecture Software Developer's Manual section 7.1.3 specifies + * that a core serializing instruction such as "cpuid" should be + * executed on _each_ core before the new instruction is made visible. + */ + sync_core(); return 0; } diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c index 6e11c813415..246d727b65b 100644 --- a/arch/x86/kernel/amd_iommu_init.c +++ b/arch/x86/kernel/amd_iommu_init.c @@ -21,7 +21,7 @@ #include <linux/acpi.h> #include <linux/list.h> #include <linux/slab.h> -#include <linux/sysdev.h> +#include <linux/syscore_ops.h> #include <linux/interrupt.h> #include <linux/msi.h> #include <asm/pci-direct.h> @@ -1260,7 +1260,7 @@ static void disable_iommus(void) * disable suspend until real resume implemented */ -static int amd_iommu_resume(struct sys_device *dev) +static void amd_iommu_resume(void) { struct amd_iommu *iommu; @@ -1276,11 +1276,9 @@ static int amd_iommu_resume(struct sys_device *dev) */ amd_iommu_flush_all_devices(); amd_iommu_flush_all_domains(); - - return 0; } -static int amd_iommu_suspend(struct sys_device *dev, pm_message_t state) +static int amd_iommu_suspend(void) { /* disable IOMMUs to go out of the way for BIOS */ disable_iommus(); @@ -1288,17 +1286,11 @@ static int amd_iommu_suspend(struct sys_device *dev, pm_message_t state) return 0; } -static struct sysdev_class amd_iommu_sysdev_class = { - .name = "amd_iommu", +static struct syscore_ops amd_iommu_syscore_ops = { .suspend = amd_iommu_suspend, .resume = amd_iommu_resume, }; -static struct sys_device device_amd_iommu = { - .id = 0, - .cls = &amd_iommu_sysdev_class, -}; - /* * This is the core init function for AMD IOMMU hardware in the system. * This function is called from the generic x86 DMA layer initialization @@ -1415,14 +1407,6 @@ static int __init amd_iommu_init(void) goto free; } - ret = sysdev_class_register(&amd_iommu_sysdev_class); - if (ret) - goto free; - - ret = sysdev_register(&device_amd_iommu); - if (ret) - goto free; - ret = amd_iommu_init_devices(); if (ret) goto free; @@ -1441,6 +1425,8 @@ static int __init amd_iommu_init(void) amd_iommu_init_notifier(); + register_syscore_ops(&amd_iommu_syscore_ops); + if (iommu_pass_through) goto out; diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 0a99f7198bc..4c39baa8fac 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -12,14 +12,19 @@ static u32 *flush_words; -struct pci_device_id amd_nb_misc_ids[] = { +const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_MISC) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F3) }, {} }; EXPORT_SYMBOL(amd_nb_misc_ids); +static struct pci_device_id amd_nb_link_ids[] = { + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F4) }, + {} +}; + const struct amd_nb_bus_dev_range amd_nb_bus_dev_ranges[] __initconst = { { 0x00, 0x18, 0x20 }, { 0xff, 0x00, 0x20 }, @@ -31,7 +36,7 @@ struct amd_northbridge_info amd_northbridges; EXPORT_SYMBOL(amd_northbridges); static struct pci_dev *next_northbridge(struct pci_dev *dev, - struct pci_device_id *ids) + const struct pci_device_id *ids) { do { dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev); @@ -43,9 +48,9 @@ static struct pci_dev *next_northbridge(struct pci_dev *dev, int amd_cache_northbridges(void) { - int i = 0; + u16 i = 0; struct amd_northbridge *nb; - struct pci_dev *misc; + struct pci_dev *misc, *link; if (amd_nb_num()) return 0; @@ -64,10 +69,12 @@ int amd_cache_northbridges(void) amd_northbridges.nb = nb; amd_northbridges.num = i; - misc = NULL; + link = misc = NULL; for (i = 0; i != amd_nb_num(); i++) { node_to_amd_nb(i)->misc = misc = next_northbridge(misc, amd_nb_misc_ids); + node_to_amd_nb(i)->link = link = + next_northbridge(link, amd_nb_link_ids); } /* some CPU families (e.g. family 0x11) do not support GART */ @@ -85,26 +92,95 @@ int amd_cache_northbridges(void) boot_cpu_data.x86_mask >= 0x1)) amd_northbridges.flags |= AMD_NB_L3_INDEX_DISABLE; + if (boot_cpu_data.x86 == 0x15) + amd_northbridges.flags |= AMD_NB_L3_INDEX_DISABLE; + + /* L3 cache partitioning is supported on family 0x15 */ + if (boot_cpu_data.x86 == 0x15) + amd_northbridges.flags |= AMD_NB_L3_PARTITIONING; + return 0; } EXPORT_SYMBOL_GPL(amd_cache_northbridges); -/* Ignores subdevice/subvendor but as far as I can figure out - they're useless anyways */ -int __init early_is_amd_nb(u32 device) +/* + * Ignores subdevice/subvendor but as far as I can figure out + * they're useless anyways + */ +bool __init early_is_amd_nb(u32 device) { - struct pci_device_id *id; + const struct pci_device_id *id; u32 vendor = device & 0xffff; + device >>= 16; for (id = amd_nb_misc_ids; id->vendor; id++) if (vendor == id->vendor && device == id->device) - return 1; + return true; + return false; +} + +int amd_get_subcaches(int cpu) +{ + struct pci_dev *link = node_to_amd_nb(amd_get_nb_id(cpu))->link; + unsigned int mask; + int cuid = 0; + + if (!amd_nb_has_feature(AMD_NB_L3_PARTITIONING)) + return 0; + + pci_read_config_dword(link, 0x1d4, &mask); + +#ifdef CONFIG_SMP + cuid = cpu_data(cpu).compute_unit_id; +#endif + return (mask >> (4 * cuid)) & 0xf; +} + +int amd_set_subcaches(int cpu, int mask) +{ + static unsigned int reset, ban; + struct amd_northbridge *nb = node_to_amd_nb(amd_get_nb_id(cpu)); + unsigned int reg; + int cuid = 0; + + if (!amd_nb_has_feature(AMD_NB_L3_PARTITIONING) || mask > 0xf) + return -EINVAL; + + /* if necessary, collect reset state of L3 partitioning and BAN mode */ + if (reset == 0) { + pci_read_config_dword(nb->link, 0x1d4, &reset); + pci_read_config_dword(nb->misc, 0x1b8, &ban); + ban &= 0x180000; + } + + /* deactivate BAN mode if any subcaches are to be disabled */ + if (mask != 0xf) { + pci_read_config_dword(nb->misc, 0x1b8, ®); + pci_write_config_dword(nb->misc, 0x1b8, reg & ~0x180000); + } + +#ifdef CONFIG_SMP + cuid = cpu_data(cpu).compute_unit_id; +#endif + mask <<= 4 * cuid; + mask |= (0xf ^ (1 << cuid)) << 26; + + pci_write_config_dword(nb->link, 0x1d4, mask); + + /* reset BAN mode if L3 partitioning returned to reset state */ + pci_read_config_dword(nb->link, 0x1d4, ®); + if (reg == reset) { + pci_read_config_dword(nb->misc, 0x1b8, ®); + reg &= ~0x180000; + pci_write_config_dword(nb->misc, 0x1b8, reg | ban); + } + return 0; } -int amd_cache_gart(void) +static int amd_cache_gart(void) { - int i; + u16 i; if (!amd_nb_has_feature(AMD_NB_GART)) return 0; diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c index 29ebf5a3b19..289e92862fd 100644 --- a/arch/x86/kernel/apb_timer.c +++ b/arch/x86/kernel/apb_timer.c @@ -283,7 +283,7 @@ static int __init apbt_clockevent_register(void) memcpy(&adev->evt, &apbt_clockevent, sizeof(struct clock_event_device)); if (mrst_timer_options == MRST_TIMER_LAPIC_APBT) { - apbt_clockevent.rating = APBT_CLOCKEVENT_RATING - 100; + adev->evt.rating = APBT_CLOCKEVENT_RATING - 100; global_clock_event = &adev->evt; printk(KERN_DEBUG "%s clockevent registered as global\n", global_clock_event->name); @@ -315,7 +315,7 @@ static void apbt_setup_irq(struct apbt_dev *adev) irq_modify_status(adev->irq, 0, IRQ_MOVE_PCNTXT); irq_set_affinity(adev->irq, cpumask_of(adev->cpu)); /* APB timer irqs are set up as mp_irqs, timer is edge type */ - __set_irq_handler(adev->irq, handle_edge_irq, 0, "edge"); + __irq_set_handler(adev->irq, handle_edge_irq, 0, "edge"); if (system_state == SYSTEM_BOOTING) { if (request_irq(adev->irq, apbt_interrupt_handler, @@ -507,64 +507,12 @@ static int apbt_next_event(unsigned long delta, return 0; } -/* - * APB timer clock is not in sync with pclk on Langwell, which translates to - * unreliable read value caused by sampling error. the error does not add up - * overtime and only happens when sampling a 0 as a 1 by mistake. so the time - * would go backwards. the following code is trying to prevent time traveling - * backwards. little bit paranoid. - */ static cycle_t apbt_read_clocksource(struct clocksource *cs) { - unsigned long t0, t1, t2; - static unsigned long last_read; - -bad_count: - t1 = apbt_readl(phy_cs_timer_id, - APBTMR_N_CURRENT_VALUE); - t2 = apbt_readl(phy_cs_timer_id, - APBTMR_N_CURRENT_VALUE); - if (unlikely(t1 < t2)) { - pr_debug("APBT: read current count error %lx:%lx:%lx\n", - t1, t2, t2 - t1); - goto bad_count; - } - /* - * check against cached last read, makes sure time does not go back. - * it could be a normal rollover but we will do tripple check anyway - */ - if (unlikely(t2 > last_read)) { - /* check if we have a normal rollover */ - unsigned long raw_intr_status = - apbt_readl_reg(APBTMRS_RAW_INT_STATUS); - /* - * cs timer interrupt is masked but raw intr bit is set if - * rollover occurs. then we read EOI reg to clear it. - */ - if (raw_intr_status & (1 << phy_cs_timer_id)) { - apbt_readl(phy_cs_timer_id, APBTMR_N_EOI); - goto out; - } - pr_debug("APB CS going back %lx:%lx:%lx ", - t2, last_read, t2 - last_read); -bad_count_x3: - pr_debug("triple check enforced\n"); - t0 = apbt_readl(phy_cs_timer_id, - APBTMR_N_CURRENT_VALUE); - udelay(1); - t1 = apbt_readl(phy_cs_timer_id, - APBTMR_N_CURRENT_VALUE); - udelay(1); - t2 = apbt_readl(phy_cs_timer_id, - APBTMR_N_CURRENT_VALUE); - if ((t2 > t1) || (t1 > t0)) { - printk(KERN_ERR "Error: APB CS tripple check failed\n"); - goto bad_count_x3; - } - } -out: - last_read = t2; - return (cycle_t)~t2; + unsigned long current_count; + + current_count = apbt_readl(phy_cs_timer_id, APBTMR_N_CURRENT_VALUE); + return (cycle_t)~current_count; } static int apbt_clocksource_register(void) diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 5955a7800a9..73fb469908c 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -13,7 +13,7 @@ #include <linux/kernel.h> #include <linux/types.h> #include <linux/init.h> -#include <linux/bootmem.h> +#include <linux/memblock.h> #include <linux/mmzone.h> #include <linux/pci_ids.h> #include <linux/pci.h> @@ -57,7 +57,7 @@ static void __init insert_aperture_resource(u32 aper_base, u32 aper_size) static u32 __init allocate_aperture(void) { u32 aper_size; - void *p; + unsigned long addr; /* aper_size should <= 1G */ if (fallback_aper_order > 5) @@ -73,7 +73,7 @@ static u32 __init allocate_aperture(void) /* * using 512M as goal, in case kexec will load kernel_big * that will do the on position decompress, and could overlap with - * that positon with gart that is used. + * that position with gart that is used. * sequende: * kernel_small * ==> kexec (with kdump trigger path or previous doesn't shutdown gart) @@ -83,27 +83,26 @@ static u32 __init allocate_aperture(void) * so don't use 512M below as gart iommu, leave the space for kernel * code for safe */ - p = __alloc_bootmem_nopanic(aper_size, aper_size, 512ULL<<20); + addr = memblock_find_in_range(0, 1ULL<<32, aper_size, 512ULL<<20); + if (addr == MEMBLOCK_ERROR || addr + aper_size > 0xffffffff) { + printk(KERN_ERR + "Cannot allocate aperture memory hole (%lx,%uK)\n", + addr, aper_size>>10); + return 0; + } + memblock_x86_reserve_range(addr, addr + aper_size, "aperture64"); /* * Kmemleak should not scan this block as it may not be mapped via the * kernel direct mapping. */ - kmemleak_ignore(p); - if (!p || __pa(p)+aper_size > 0xffffffff) { - printk(KERN_ERR - "Cannot allocate aperture memory hole (%p,%uK)\n", - p, aper_size>>10); - if (p) - free_bootmem(__pa(p), aper_size); - return 0; - } + kmemleak_ignore(phys_to_virt(addr)); printk(KERN_INFO "Mapping aperture over %d KB of RAM @ %lx\n", - aper_size >> 10, __pa(p)); - insert_aperture_resource((u32)__pa(p), aper_size); - register_nosave_region((u32)__pa(p) >> PAGE_SHIFT, - (u32)__pa(p+aper_size) >> PAGE_SHIFT); + aper_size >> 10, addr); + insert_aperture_resource((u32)addr, aper_size); + register_nosave_region(addr >> PAGE_SHIFT, + (addr+aper_size) >> PAGE_SHIFT); - return (u32)__pa(p); + return (u32)addr; } @@ -500,7 +499,7 @@ out: * Don't enable translation yet but enable GART IO and CPU * accesses and set DISTLBWALKPRB since GART table memory is UC. */ - u32 ctl = DISTLBWALKPRB | aper_order << 1; + u32 ctl = aper_order << 1; bus = amd_nb_bus_dev_ranges[i].bus; dev_base = amd_nb_bus_dev_ranges[i].dev_base; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 76b96d74978..fabf01eff77 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -24,7 +24,7 @@ #include <linux/ftrace.h> #include <linux/ioport.h> #include <linux/module.h> -#include <linux/sysdev.h> +#include <linux/syscore_ops.h> #include <linux/delay.h> #include <linux/timex.h> #include <linux/dmar.h> @@ -43,6 +43,7 @@ #include <asm/i8259.h> #include <asm/proto.h> #include <asm/apic.h> +#include <asm/io_apic.h> #include <asm/desc.h> #include <asm/hpet.h> #include <asm/idle.h> @@ -78,12 +79,21 @@ EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_apicid); EXPORT_EARLY_PER_CPU_SYMBOL(x86_bios_cpu_apicid); #ifdef CONFIG_X86_32 + +/* + * On x86_32, the mapping between cpu and logical apicid may vary + * depending on apic in use. The following early percpu variable is + * used for the mapping. This is where the behaviors of x86_64 and 32 + * actually diverge. Let's keep it ugly for now. + */ +DEFINE_EARLY_PER_CPU(int, x86_cpu_to_logical_apicid, BAD_APICID); + /* * Knob to control our willingness to enable the local APIC. * * +1=force-enable */ -static int force_enable_local_apic; +static int force_enable_local_apic __initdata; /* * APIC command line parameters */ @@ -153,7 +163,7 @@ early_param("nox2apic", setup_nox2apic); unsigned long mp_lapic_addr; int disable_apic; /* Disable local APIC timer from the kernel commandline or via dmi quirk */ -static int disable_apic_timer __cpuinitdata; +static int disable_apic_timer __initdata; /* Local APIC timer works in C2 */ int local_apic_timer_c2_ok; EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok); @@ -177,29 +187,8 @@ static struct resource lapic_resource = { static unsigned int calibration_result; -static int lapic_next_event(unsigned long delta, - struct clock_event_device *evt); -static void lapic_timer_setup(enum clock_event_mode mode, - struct clock_event_device *evt); -static void lapic_timer_broadcast(const struct cpumask *mask); static void apic_pm_activate(void); -/* - * The local apic timer can be used for any function which is CPU local. - */ -static struct clock_event_device lapic_clockevent = { - .name = "lapic", - .features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT - | CLOCK_EVT_FEAT_C3STOP | CLOCK_EVT_FEAT_DUMMY, - .shift = 32, - .set_mode = lapic_timer_setup, - .set_next_event = lapic_next_event, - .broadcast = lapic_timer_broadcast, - .rating = 100, - .irq = -1, -}; -static DEFINE_PER_CPU(struct clock_event_device, lapic_events); - static unsigned long apic_phys; /* @@ -238,7 +227,7 @@ static int modern_apic(void) * right after this call apic become NOOP driven * so apic->write/read doesn't do anything */ -void apic_disable(void) +static void __init apic_disable(void) { pr_info("APIC: switched to apic NOOP\n"); apic = &apic_noop; @@ -282,23 +271,6 @@ u64 native_apic_icr_read(void) return icr1 | ((u64)icr2 << 32); } -/** - * enable_NMI_through_LVT0 - enable NMI through local vector table 0 - */ -void __cpuinit enable_NMI_through_LVT0(void) -{ - unsigned int v; - - /* unmask and set to NMI */ - v = APIC_DM_NMI; - - /* Level triggered for 82489DX (32bit mode) */ - if (!lapic_is_integrated()) - v |= APIC_LVT_LEVEL_TRIGGER; - - apic_write(APIC_LVT0, v); -} - #ifdef CONFIG_X86_32 /** * get_physical_broadcast - Get number of physical broadcast IDs @@ -508,6 +480,23 @@ static void lapic_timer_broadcast(const struct cpumask *mask) #endif } + +/* + * The local apic timer can be used for any function which is CPU local. + */ +static struct clock_event_device lapic_clockevent = { + .name = "lapic", + .features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT + | CLOCK_EVT_FEAT_C3STOP | CLOCK_EVT_FEAT_DUMMY, + .shift = 32, + .set_mode = lapic_timer_setup, + .set_next_event = lapic_next_event, + .broadcast = lapic_timer_broadcast, + .rating = 100, + .irq = -1, +}; +static DEFINE_PER_CPU(struct clock_event_device, lapic_events); + /* * Setup the local APIC timer for this CPU. Copy the initialized values * of the boot CPU and register the clock event in the framework. @@ -1209,7 +1198,7 @@ void __cpuinit setup_local_APIC(void) rdtscll(tsc); if (disable_apic) { - arch_disable_smp_support(); + disable_ioapic_support(); return; } @@ -1237,6 +1226,19 @@ void __cpuinit setup_local_APIC(void) */ apic->init_apic_ldr(); +#ifdef CONFIG_X86_32 + /* + * APIC LDR is initialized. If logical_apicid mapping was + * initialized during get_smp_config(), make sure it matches the + * actual value. + */ + i = early_per_cpu(x86_cpu_to_logical_apicid, cpu); + WARN_ON(i != BAD_APICID && i != logical_smp_processor_id()); + /* always use the value from LDR */ + early_per_cpu(x86_cpu_to_logical_apicid, cpu) = + logical_smp_processor_id(); +#endif + /* * Set Task Priority to 'accept all'. We never change this * later on. @@ -1448,7 +1450,7 @@ int __init enable_IR(void) void __init enable_IR_x2apic(void) { unsigned long flags; - struct IO_APIC_route_entry **ioapic_entries = NULL; + struct IO_APIC_route_entry **ioapic_entries; int ret, x2apic_enabled = 0; int dmar_table_init_ret; @@ -1537,7 +1539,7 @@ static int __init detect_init_APIC(void) } #else -static int apic_verify(void) +static int __init apic_verify(void) { u32 features, h, l; @@ -1562,7 +1564,7 @@ static int apic_verify(void) return 0; } -int apic_force_enable(void) +int __init apic_force_enable(unsigned long addr) { u32 h, l; @@ -1578,7 +1580,7 @@ int apic_force_enable(void) if (!(l & MSR_IA32_APICBASE_ENABLE)) { pr_info("Local APIC disabled by BIOS -- reenabling.\n"); l &= ~MSR_IA32_APICBASE_BASE; - l |= MSR_IA32_APICBASE_ENABLE | APIC_DEFAULT_PHYS_BASE; + l |= MSR_IA32_APICBASE_ENABLE | addr; wrmsr(MSR_IA32_APICBASE, l, h); enabled_via_apicbase = 1; } @@ -1619,7 +1621,7 @@ static int __init detect_init_APIC(void) "you can enable it with \"lapic\"\n"); return -1; } - if (apic_force_enable()) + if (apic_force_enable(APIC_DEFAULT_PHYS_BASE)) return -1; } else { if (apic_verify()) @@ -1930,17 +1932,6 @@ void __cpuinit generic_processor_info(int apicid, int version) { int cpu; - /* - * Validate version - */ - if (version == 0x0) { - pr_warning("BIOS bug, APIC version is 0 for CPU#%d! " - "fixing up to 0x10. (tell your hw vendor)\n", - version); - version = 0x10; - } - apic_version[apicid] = version; - if (num_processors >= nr_cpu_ids) { int max = nr_cpu_ids; int thiscpu = max + disabled_cpus; @@ -1954,22 +1945,34 @@ void __cpuinit generic_processor_info(int apicid, int version) } num_processors++; - cpu = cpumask_next_zero(-1, cpu_present_mask); - - if (version != apic_version[boot_cpu_physical_apicid]) - WARN_ONCE(1, - "ACPI: apic version mismatch, bootcpu: %x cpu %d: %x\n", - apic_version[boot_cpu_physical_apicid], cpu, version); - - physid_set(apicid, phys_cpu_present_map); if (apicid == boot_cpu_physical_apicid) { /* * x86_bios_cpu_apicid is required to have processors listed * in same order as logical cpu numbers. Hence the first * entry is BSP, and so on. + * boot_cpu_init() already hold bit 0 in cpu_present_mask + * for BSP. */ cpu = 0; + } else + cpu = cpumask_next_zero(-1, cpu_present_mask); + + /* + * Validate version + */ + if (version == 0x0) { + pr_warning("BIOS bug: APIC version is 0 for CPU %d/0x%x, fixing up to 0x10\n", + cpu, apicid); + version = 0x10; + } + apic_version[apicid] = version; + + if (version != apic_version[boot_cpu_physical_apicid]) { + pr_warning("BIOS bug: APIC version mismatch, boot CPU: %x, CPU %d: version %x\n", + apic_version[boot_cpu_physical_apicid], cpu, version); } + + physid_set(apicid, phys_cpu_present_map); if (apicid > max_physical_apicid) max_physical_apicid = apicid; @@ -1977,7 +1980,10 @@ void __cpuinit generic_processor_info(int apicid, int version) early_per_cpu(x86_cpu_to_apicid, cpu) = apicid; early_per_cpu(x86_bios_cpu_apicid, cpu) = apicid; #endif - +#ifdef CONFIG_X86_32 + early_per_cpu(x86_cpu_to_logical_apicid, cpu) = + apic->x86_32_early_logical_apicid(cpu); +#endif set_cpu_possible(cpu, true); set_cpu_present(cpu, true); } @@ -1998,10 +2004,14 @@ void default_init_apic_ldr(void) } #ifdef CONFIG_X86_32 -int default_apicid_to_node(int logical_apicid) +int default_x86_32_numa_cpu_node(int cpu) { -#ifdef CONFIG_SMP - return apicid_2_node[hard_smp_processor_id()]; +#ifdef CONFIG_NUMA + int apicid = early_per_cpu(x86_cpu_to_apicid, cpu); + + if (apicid != BAD_APICID) + return __apicid_to_node[apicid]; + return NUMA_NO_NODE; #else return 0; #endif @@ -2036,7 +2046,7 @@ static struct { unsigned int apic_thmr; } apic_pm_state; -static int lapic_suspend(struct sys_device *dev, pm_message_t state) +static int lapic_suspend(void) { unsigned long flags; int maxlvt; @@ -2074,23 +2084,21 @@ static int lapic_suspend(struct sys_device *dev, pm_message_t state) return 0; } -static int lapic_resume(struct sys_device *dev) +static void lapic_resume(void) { unsigned int l, h; unsigned long flags; - int maxlvt; - int ret = 0; + int maxlvt, ret; struct IO_APIC_route_entry **ioapic_entries = NULL; if (!apic_pm_state.active) - return 0; + return; local_irq_save(flags); if (intr_remapping_enabled) { ioapic_entries = alloc_ioapic_entries(); if (!ioapic_entries) { WARN(1, "Alloc ioapic_entries in lapic resume failed."); - ret = -ENOMEM; goto restore; } @@ -2152,8 +2160,6 @@ static int lapic_resume(struct sys_device *dev) } restore: local_irq_restore(flags); - - return ret; } /* @@ -2161,17 +2167,11 @@ restore: * are needed on every CPU up until machine_halt/restart/poweroff. */ -static struct sysdev_class lapic_sysclass = { - .name = "lapic", +static struct syscore_ops lapic_syscore_ops = { .resume = lapic_resume, .suspend = lapic_suspend, }; -static struct sys_device device_lapic = { - .id = 0, - .cls = &lapic_sysclass, -}; - static void __cpuinit apic_pm_activate(void) { apic_pm_state.active = 1; @@ -2179,16 +2179,11 @@ static void __cpuinit apic_pm_activate(void) static int __init init_lapic_sysfs(void) { - int error; - - if (!cpu_has_apic) - return 0; /* XXX: remove suspend/resume procs if !apic_pm_state.active? */ + if (cpu_has_apic) + register_syscore_ops(&lapic_syscore_ops); - error = sysdev_class_register(&lapic_sysclass); - if (!error) - error = sysdev_register(&device_lapic); - return error; + return 0; } /* local apic needs to resume before other devices access its registers. */ diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index 09d3b17ce0c..5652d31fe10 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -185,8 +185,6 @@ struct apic apic_flat = { .ioapic_phys_id_map = NULL, .setup_apic_routing = NULL, .multi_timer_check = NULL, - .apicid_to_node = NULL, - .cpu_to_logical_apicid = NULL, .cpu_present_to_apicid = default_cpu_present_to_apicid, .apicid_to_cpu_present = NULL, .setup_portio_remap = NULL, @@ -337,8 +335,6 @@ struct apic apic_physflat = { .ioapic_phys_id_map = NULL, .setup_apic_routing = NULL, .multi_timer_check = NULL, - .apicid_to_node = NULL, - .cpu_to_logical_apicid = NULL, .cpu_present_to_apicid = default_cpu_present_to_apicid, .apicid_to_cpu_present = NULL, .setup_portio_remap = NULL, diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index e31b9ffe25f..f1baa2dc087 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -54,11 +54,6 @@ static u64 noop_apic_icr_read(void) return 0; } -static int noop_cpu_to_logical_apicid(int cpu) -{ - return 0; -} - static int noop_phys_pkg_id(int cpuid_apic, int index_msb) { return 0; @@ -113,12 +108,6 @@ static void noop_vector_allocation_domain(int cpu, struct cpumask *retmask) cpumask_set_cpu(cpu, retmask); } -int noop_apicid_to_node(int logical_apicid) -{ - /* we're always on node 0 */ - return 0; -} - static u32 noop_apic_read(u32 reg) { WARN_ON_ONCE((cpu_has_apic && !disable_apic)); @@ -130,6 +119,14 @@ static void noop_apic_write(u32 reg, u32 v) WARN_ON_ONCE(cpu_has_apic && !disable_apic); } +#ifdef CONFIG_X86_32 +static int noop_x86_32_numa_cpu_node(int cpu) +{ + /* we're always on node 0 */ + return 0; +} +#endif + struct apic apic_noop = { .name = "noop", .probe = noop_probe, @@ -153,9 +150,7 @@ struct apic apic_noop = { .ioapic_phys_id_map = default_ioapic_phys_id_map, .setup_apic_routing = NULL, .multi_timer_check = NULL, - .apicid_to_node = noop_apicid_to_node, - .cpu_to_logical_apicid = noop_cpu_to_logical_apicid, .cpu_present_to_apicid = default_cpu_present_to_apicid, .apicid_to_cpu_present = physid_set_mask_of_physid, @@ -197,4 +192,9 @@ struct apic apic_noop = { .icr_write = noop_apic_icr_write, .wait_icr_idle = noop_apic_wait_icr_idle, .safe_wait_icr_idle = noop_safe_apic_wait_icr_idle, + +#ifdef CONFIG_X86_32 + .x86_32_early_logical_apicid = noop_x86_32_early_logical_apicid, + .x86_32_numa_cpu_node = noop_x86_32_numa_cpu_node, +#endif }; diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index cb804c5091b..541a2e43165 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -45,6 +45,12 @@ static unsigned long bigsmp_check_apicid_present(int bit) return 1; } +static int bigsmp_early_logical_apicid(int cpu) +{ + /* on bigsmp, logical apicid is the same as physical */ + return early_per_cpu(x86_cpu_to_apicid, cpu); +} + static inline unsigned long calculate_ldr(int cpu) { unsigned long val, id; @@ -80,11 +86,6 @@ static void bigsmp_setup_apic_routing(void) nr_ioapics); } -static int bigsmp_apicid_to_node(int logical_apicid) -{ - return apicid_2_node[hard_smp_processor_id()]; -} - static int bigsmp_cpu_present_to_apicid(int mps_cpu) { if (mps_cpu < nr_cpu_ids) @@ -93,14 +94,6 @@ static int bigsmp_cpu_present_to_apicid(int mps_cpu) return BAD_APICID; } -/* Mapping from cpu number to logical apicid */ -static inline int bigsmp_cpu_to_logical_apicid(int cpu) -{ - if (cpu >= nr_cpu_ids) - return BAD_APICID; - return cpu_physical_id(cpu); -} - static void bigsmp_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap) { /* For clustered we don't have a good way to do this yet - hack */ @@ -115,7 +108,11 @@ static int bigsmp_check_phys_apicid_present(int phys_apicid) /* As we are using single CPU as destination, pick only one CPU here */ static unsigned int bigsmp_cpu_mask_to_apicid(const struct cpumask *cpumask) { - return bigsmp_cpu_to_logical_apicid(cpumask_first(cpumask)); + int cpu = cpumask_first(cpumask); + + if (cpu < nr_cpu_ids) + return cpu_physical_id(cpu); + return BAD_APICID; } static unsigned int bigsmp_cpu_mask_to_apicid_and(const struct cpumask *cpumask, @@ -129,9 +126,9 @@ static unsigned int bigsmp_cpu_mask_to_apicid_and(const struct cpumask *cpumask, */ for_each_cpu_and(cpu, cpumask, andmask) { if (cpumask_test_cpu(cpu, cpu_online_mask)) - break; + return cpu_physical_id(cpu); } - return bigsmp_cpu_to_logical_apicid(cpu); + return BAD_APICID; } static int bigsmp_phys_pkg_id(int cpuid_apic, int index_msb) @@ -219,8 +216,6 @@ struct apic apic_bigsmp = { .ioapic_phys_id_map = bigsmp_ioapic_phys_id_map, .setup_apic_routing = bigsmp_setup_apic_routing, .multi_timer_check = NULL, - .apicid_to_node = bigsmp_apicid_to_node, - .cpu_to_logical_apicid = bigsmp_cpu_to_logical_apicid, .cpu_present_to_apicid = bigsmp_cpu_present_to_apicid, .apicid_to_cpu_present = physid_set_mask_of_physid, .setup_portio_remap = NULL, @@ -256,4 +251,7 @@ struct apic apic_bigsmp = { .icr_write = native_apic_icr_write, .wait_icr_idle = native_apic_wait_icr_idle, .safe_wait_icr_idle = native_safe_apic_wait_icr_idle, + + .x86_32_early_logical_apicid = bigsmp_early_logical_apicid, + .x86_32_numa_cpu_node = default_x86_32_numa_cpu_node, }; diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c index 8593582d802..3e9de4854c5 100644 --- a/arch/x86/kernel/apic/es7000_32.c +++ b/arch/x86/kernel/apic/es7000_32.c @@ -460,6 +460,12 @@ static unsigned long es7000_check_apicid_present(int bit) return physid_isset(bit, phys_cpu_present_map); } +static int es7000_early_logical_apicid(int cpu) +{ + /* on es7000, logical apicid is the same as physical */ + return early_per_cpu(x86_bios_cpu_apicid, cpu); +} + static unsigned long calculate_ldr(int cpu) { unsigned long id = per_cpu(x86_bios_cpu_apicid, cpu); @@ -504,12 +510,11 @@ static void es7000_setup_apic_routing(void) nr_ioapics, cpumask_bits(es7000_target_cpus())[0]); } -static int es7000_apicid_to_node(int logical_apicid) +static int es7000_numa_cpu_node(int cpu) { return 0; } - static int es7000_cpu_present_to_apicid(int mps_cpu) { if (!mps_cpu) @@ -528,18 +533,6 @@ static void es7000_apicid_to_cpu_present(int phys_apicid, physid_mask_t *retmap) ++cpu_id; } -/* Mapping from cpu number to logical apicid */ -static int es7000_cpu_to_logical_apicid(int cpu) -{ -#ifdef CONFIG_SMP - if (cpu >= nr_cpu_ids) - return BAD_APICID; - return cpu_2_logical_apicid[cpu]; -#else - return logical_smp_processor_id(); -#endif -} - static void es7000_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap) { /* For clustered we don't have a good way to do this yet - hack */ @@ -561,7 +554,7 @@ static unsigned int es7000_cpu_mask_to_apicid(const struct cpumask *cpumask) * The cpus in the mask must all be on the apic cluster. */ for_each_cpu(cpu, cpumask) { - int new_apicid = es7000_cpu_to_logical_apicid(cpu); + int new_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu); if (round && APIC_CLUSTER(apicid) != APIC_CLUSTER(new_apicid)) { WARN(1, "Not a valid mask!"); @@ -578,7 +571,7 @@ static unsigned int es7000_cpu_mask_to_apicid_and(const struct cpumask *inmask, const struct cpumask *andmask) { - int apicid = es7000_cpu_to_logical_apicid(0); + int apicid = early_per_cpu(x86_cpu_to_logical_apicid, 0); cpumask_var_t cpumask; if (!alloc_cpumask_var(&cpumask, GFP_ATOMIC)) @@ -655,8 +648,6 @@ struct apic __refdata apic_es7000_cluster = { .ioapic_phys_id_map = es7000_ioapic_phys_id_map, .setup_apic_routing = es7000_setup_apic_routing, .multi_timer_check = NULL, - .apicid_to_node = es7000_apicid_to_node, - .cpu_to_logical_apicid = es7000_cpu_to_logical_apicid, .cpu_present_to_apicid = es7000_cpu_present_to_apicid, .apicid_to_cpu_present = es7000_apicid_to_cpu_present, .setup_portio_remap = NULL, @@ -695,6 +686,9 @@ struct apic __refdata apic_es7000_cluster = { .icr_write = native_apic_icr_write, .wait_icr_idle = native_apic_wait_icr_idle, .safe_wait_icr_idle = native_safe_apic_wait_icr_idle, + + .x86_32_early_logical_apicid = es7000_early_logical_apicid, + .x86_32_numa_cpu_node = es7000_numa_cpu_node, }; struct apic __refdata apic_es7000 = { @@ -720,8 +714,6 @@ struct apic __refdata apic_es7000 = { .ioapic_phys_id_map = es7000_ioapic_phys_id_map, .setup_apic_routing = es7000_setup_apic_routing, .multi_timer_check = NULL, - .apicid_to_node = es7000_apicid_to_node, - .cpu_to_logical_apicid = es7000_cpu_to_logical_apicid, .cpu_present_to_apicid = es7000_cpu_present_to_apicid, .apicid_to_cpu_present = es7000_apicid_to_cpu_present, .setup_portio_remap = NULL, @@ -758,4 +750,7 @@ struct apic __refdata apic_es7000 = { .icr_write = native_apic_icr_write, .wait_icr_idle = native_apic_wait_icr_idle, .safe_wait_icr_idle = native_safe_apic_wait_icr_idle, + + .x86_32_early_logical_apicid = es7000_early_logical_apicid, + .x86_32_numa_cpu_node = es7000_numa_cpu_node, }; diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c index 79fd43ca6f9..5260fe91bcb 100644 --- a/arch/x86/kernel/apic/hw_nmi.c +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -16,6 +16,7 @@ #include <linux/kprobes.h> #include <linux/nmi.h> #include <linux/module.h> +#include <linux/delay.h> #ifdef CONFIG_HARDLOCKUP_DETECTOR u64 hw_nmi_get_sample_period(void) @@ -83,7 +84,6 @@ arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self, arch_spin_lock(&lock); printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu); show_regs(regs); - dump_stack(); arch_spin_unlock(&lock); cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask)); return NOTIFY_STOP; diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index ca9e2a3545a..45fd33d1fd3 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -30,7 +30,7 @@ #include <linux/compiler.h> #include <linux/acpi.h> #include <linux/module.h> -#include <linux/sysdev.h> +#include <linux/syscore_ops.h> #include <linux/msi.h> #include <linux/htirq.h> #include <linux/freezer.h> @@ -108,7 +108,10 @@ DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES); int skip_ioapic_setup; -void arch_disable_smp_support(void) +/** + * disable_ioapic_support() - disables ioapic support at runtime + */ +void disable_ioapic_support(void) { #ifdef CONFIG_PCI noioapicquirk = 1; @@ -120,11 +123,14 @@ void arch_disable_smp_support(void) static int __init parse_noapic(char *str) { /* disable IO-APIC */ - arch_disable_smp_support(); + disable_ioapic_support(); return 0; } early_param("noapic", parse_noapic); +static int io_apic_setup_irq_pin(unsigned int irq, int node, + struct io_apic_irq_attr *attr); + /* Will be called in mpparse/acpi/sfi codes for saving IRQ info */ void mp_save_irq(struct mpc_intsrc *m) { @@ -181,7 +187,7 @@ int __init arch_early_irq_init(void) irq_reserve_irqs(0, legacy_pic->nr_legacy_irqs); for (i = 0; i < count; i++) { - set_irq_chip_data(i, &cfg[i]); + irq_set_chip_data(i, &cfg[i]); zalloc_cpumask_var_node(&cfg[i].domain, GFP_KERNEL, node); zalloc_cpumask_var_node(&cfg[i].old_domain, GFP_KERNEL, node); /* @@ -200,7 +206,7 @@ int __init arch_early_irq_init(void) #ifdef CONFIG_SPARSE_IRQ static struct irq_cfg *irq_cfg(unsigned int irq) { - return get_irq_chip_data(irq); + return irq_get_chip_data(irq); } static struct irq_cfg *alloc_irq_cfg(unsigned int irq, int node) @@ -226,7 +232,7 @@ static void free_irq_cfg(unsigned int at, struct irq_cfg *cfg) { if (!cfg) return; - set_irq_chip_data(at, NULL); + irq_set_chip_data(at, NULL); free_cpumask_var(cfg->domain); free_cpumask_var(cfg->old_domain); kfree(cfg); @@ -256,14 +262,14 @@ static struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node) if (res < 0) { if (res != -EEXIST) return NULL; - cfg = get_irq_chip_data(at); + cfg = irq_get_chip_data(at); if (cfg) return cfg; } cfg = alloc_irq_cfg(at, node); if (cfg) - set_irq_chip_data(at, cfg); + irq_set_chip_data(at, cfg); else irq_free_desc(at); return cfg; @@ -818,7 +824,7 @@ static int EISA_ELCR(unsigned int irq) #define default_MCA_trigger(idx) (1) #define default_MCA_polarity(idx) default_ISA_polarity(idx) -static int MPBIOS_polarity(int idx) +static int irq_polarity(int idx) { int bus = mp_irqs[idx].srcbus; int polarity; @@ -860,7 +866,7 @@ static int MPBIOS_polarity(int idx) return polarity; } -static int MPBIOS_trigger(int idx) +static int irq_trigger(int idx) { int bus = mp_irqs[idx].srcbus; int trigger; @@ -932,16 +938,6 @@ static int MPBIOS_trigger(int idx) return trigger; } -static inline int irq_polarity(int idx) -{ - return MPBIOS_polarity(idx); -} - -static inline int irq_trigger(int idx) -{ - return MPBIOS_trigger(idx); -} - static int pin_2_irq(int idx, int apic, int pin) { int irq; @@ -1189,7 +1185,7 @@ void __setup_vector_irq(int cpu) raw_spin_lock(&vector_lock); /* Mark the inuse vectors */ for_each_active_irq(irq) { - cfg = get_irq_chip_data(irq); + cfg = irq_get_chip_data(irq); if (!cfg) continue; /* @@ -1220,10 +1216,6 @@ void __setup_vector_irq(int cpu) static struct irq_chip ioapic_chip; static struct irq_chip ir_ioapic_chip; -#define IOAPIC_AUTO -1 -#define IOAPIC_EDGE 0 -#define IOAPIC_LEVEL 1 - #ifdef CONFIG_X86_32 static inline int IO_APIC_irq_trigger(int irq) { @@ -1248,35 +1240,31 @@ static inline int IO_APIC_irq_trigger(int irq) } #endif -static void ioapic_register_intr(unsigned int irq, unsigned long trigger) +static void ioapic_register_intr(unsigned int irq, struct irq_cfg *cfg, + unsigned long trigger) { + struct irq_chip *chip = &ioapic_chip; + irq_flow_handler_t hdl; + bool fasteoi; if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) || - trigger == IOAPIC_LEVEL) + trigger == IOAPIC_LEVEL) { irq_set_status_flags(irq, IRQ_LEVEL); - else + fasteoi = true; + } else { irq_clear_status_flags(irq, IRQ_LEVEL); + fasteoi = false; + } - if (irq_remapped(get_irq_chip_data(irq))) { + if (irq_remapped(cfg)) { irq_set_status_flags(irq, IRQ_MOVE_PCNTXT); - if (trigger) - set_irq_chip_and_handler_name(irq, &ir_ioapic_chip, - handle_fasteoi_irq, - "fasteoi"); - else - set_irq_chip_and_handler_name(irq, &ir_ioapic_chip, - handle_edge_irq, "edge"); - return; + chip = &ir_ioapic_chip; + fasteoi = trigger != 0; } - if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) || - trigger == IOAPIC_LEVEL) - set_irq_chip_and_handler_name(irq, &ioapic_chip, - handle_fasteoi_irq, - "fasteoi"); - else - set_irq_chip_and_handler_name(irq, &ioapic_chip, - handle_edge_irq, "edge"); + hdl = fasteoi ? handle_fasteoi_irq : handle_edge_irq; + irq_set_chip_and_handler_name(irq, chip, hdl, + fasteoi ? "fasteoi" : "edge"); } static int setup_ioapic_entry(int apic_id, int irq, @@ -1374,7 +1362,7 @@ static void setup_ioapic_irq(int apic_id, int pin, unsigned int irq, return; } - ioapic_register_intr(irq, trigger); + ioapic_register_intr(irq, cfg, trigger); if (irq < legacy_pic->nr_legacy_irqs) legacy_pic->mask(irq); @@ -1385,33 +1373,26 @@ static struct { DECLARE_BITMAP(pin_programmed, MP_MAX_IOAPIC_PIN + 1); } mp_ioapic_routing[MAX_IO_APICS]; -static void __init setup_IO_APIC_irqs(void) +static bool __init io_apic_pin_not_connected(int idx, int apic_id, int pin) { - int apic_id, pin, idx, irq, notcon = 0; - int node = cpu_to_node(0); - struct irq_cfg *cfg; + if (idx != -1) + return false; - apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n"); + apic_printk(APIC_VERBOSE, KERN_DEBUG " apic %d pin %d not connected\n", + mp_ioapics[apic_id].apicid, pin); + return true; +} + +static void __init __io_apic_setup_irqs(unsigned int apic_id) +{ + int idx, node = cpu_to_node(0); + struct io_apic_irq_attr attr; + unsigned int pin, irq; - for (apic_id = 0; apic_id < nr_ioapics; apic_id++) for (pin = 0; pin < nr_ioapic_registers[apic_id]; pin++) { idx = find_irq_entry(apic_id, pin, mp_INT); - if (idx == -1) { - if (!notcon) { - notcon = 1; - apic_printk(APIC_VERBOSE, - KERN_DEBUG " %d-%d", - mp_ioapics[apic_id].apicid, pin); - } else - apic_printk(APIC_VERBOSE, " %d-%d", - mp_ioapics[apic_id].apicid, pin); + if (io_apic_pin_not_connected(idx, apic_id, pin)) continue; - } - if (notcon) { - apic_printk(APIC_VERBOSE, - " (apicid-pin) not connected\n"); - notcon = 0; - } irq = pin_2_irq(idx, apic_id, pin); @@ -1423,25 +1404,24 @@ static void __init setup_IO_APIC_irqs(void) * installed and if it returns 1: */ if (apic->multi_timer_check && - apic->multi_timer_check(apic_id, irq)) + apic->multi_timer_check(apic_id, irq)) continue; - cfg = alloc_irq_and_cfg_at(irq, node); - if (!cfg) - continue; + set_io_apic_irq_attr(&attr, apic_id, pin, irq_trigger(idx), + irq_polarity(idx)); - add_pin_to_irq_node(cfg, node, apic_id, pin); - /* - * don't mark it in pin_programmed, so later acpi could - * set it correctly when irq < 16 - */ - setup_ioapic_irq(apic_id, pin, irq, cfg, irq_trigger(idx), - irq_polarity(idx)); + io_apic_setup_irq_pin(irq, node, &attr); } +} - if (notcon) - apic_printk(APIC_VERBOSE, - " (apicid-pin) not connected\n"); +static void __init setup_IO_APIC_irqs(void) +{ + unsigned int apic_id; + + apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n"); + + for (apic_id = 0; apic_id < nr_ioapics; apic_id++) + __io_apic_setup_irqs(apic_id); } /* @@ -1452,7 +1432,7 @@ static void __init setup_IO_APIC_irqs(void) void setup_IO_APIC_irq_extra(u32 gsi) { int apic_id = 0, pin, idx, irq, node = cpu_to_node(0); - struct irq_cfg *cfg; + struct io_apic_irq_attr attr; /* * Convert 'gsi' to 'ioapic.pin'. @@ -1472,21 +1452,10 @@ void setup_IO_APIC_irq_extra(u32 gsi) if (apic_id == 0 || irq < NR_IRQS_LEGACY) return; - cfg = alloc_irq_and_cfg_at(irq, node); - if (!cfg) - return; - - add_pin_to_irq_node(cfg, node, apic_id, pin); - - if (test_bit(pin, mp_ioapic_routing[apic_id].pin_programmed)) { - pr_debug("Pin %d-%d already programmed\n", - mp_ioapics[apic_id].apicid, pin); - return; - } - set_bit(pin, mp_ioapic_routing[apic_id].pin_programmed); + set_io_apic_irq_attr(&attr, apic_id, pin, irq_trigger(idx), + irq_polarity(idx)); - setup_ioapic_irq(apic_id, pin, irq, cfg, - irq_trigger(idx), irq_polarity(idx)); + io_apic_setup_irq_pin_once(irq, node, &attr); } /* @@ -1518,7 +1487,8 @@ static void __init setup_timer_IRQ0_pin(unsigned int apic_id, unsigned int pin, * The timer IRQ doesn't have to know that behind the * scene we may have a 8259A-master in AEOI mode ... */ - set_irq_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq, "edge"); + irq_set_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq, + "edge"); /* * Add it to the IO-APIC irq-routing table: @@ -1625,7 +1595,7 @@ __apicdebuginit(void) print_IO_APIC(void) for_each_active_irq(irq) { struct irq_pin_list *entry; - cfg = get_irq_chip_data(irq); + cfg = irq_get_chip_data(irq); if (!cfg) continue; entry = cfg->irq_2_pin; @@ -1916,7 +1886,7 @@ void disable_IO_APIC(void) * * With interrupt-remapping, for now we will use virtual wire A mode, * as virtual wire B is little complex (need to configure both - * IOAPIC RTE aswell as interrupt-remapping table entry). + * IOAPIC RTE as well as interrupt-remapping table entry). * As this gets called during crash dump, keep this simple for now. */ if (ioapic_i8259.pin != -1 && !intr_remapping_enabled) { @@ -2391,7 +2361,7 @@ static void irq_complete_move(struct irq_cfg *cfg) void irq_force_complete_move(int irq) { - struct irq_cfg *cfg = get_irq_chip_data(irq); + struct irq_cfg *cfg = irq_get_chip_data(irq); if (!cfg) return; @@ -2405,7 +2375,7 @@ static inline void irq_complete_move(struct irq_cfg *cfg) { } static void ack_apic_edge(struct irq_data *data) { irq_complete_move(data->chip_data); - move_native_irq(data->irq); + irq_move_irq(data); ack_APIC_irq(); } @@ -2462,7 +2432,7 @@ static void ack_apic_level(struct irq_data *data) irq_complete_move(cfg); #ifdef CONFIG_GENERIC_PENDING_IRQ /* If we are moving the irq we need to mask it */ - if (unlikely(irq_to_desc(irq)->status & IRQ_MOVE_PENDING)) { + if (unlikely(irqd_is_setaffinity_pending(data))) { do_unmask_irq = 1; mask_ioapic(cfg); } @@ -2551,7 +2521,7 @@ static void ack_apic_level(struct irq_data *data) * and you can go talk to the chipset vendor about it. */ if (!io_apic_level_ack_pending(cfg)) - move_masked_irq(irq); + irq_move_masked_irq(data); unmask_ioapic(cfg); } } @@ -2614,7 +2584,7 @@ static inline void init_IO_APIC_traps(void) * 0x80, because int 0x80 is hm, kind of importantish. ;) */ for_each_active_irq(irq) { - cfg = get_irq_chip_data(irq); + cfg = irq_get_chip_data(irq); if (IO_APIC_IRQ(irq) && cfg && !cfg->vector) { /* * Hmm.. We don't have an entry for this, @@ -2625,7 +2595,7 @@ static inline void init_IO_APIC_traps(void) legacy_pic->make_irq(irq); else /* Strange. Oh, well.. */ - set_irq_chip(irq, &no_irq_chip); + irq_set_chip(irq, &no_irq_chip); } } } @@ -2665,7 +2635,7 @@ static struct irq_chip lapic_chip __read_mostly = { static void lapic_register_intr(int irq) { irq_clear_status_flags(irq, IRQ_LEVEL); - set_irq_chip_and_handler_name(irq, &lapic_chip, handle_edge_irq, + irq_set_chip_and_handler_name(irq, &lapic_chip, handle_edge_irq, "edge"); } @@ -2749,7 +2719,7 @@ int timer_through_8259 __initdata; */ static inline void __init check_timer(void) { - struct irq_cfg *cfg = get_irq_chip_data(0); + struct irq_cfg *cfg = irq_get_chip_data(0); int node = cpu_to_node(0); int apic1, pin1, apic2, pin2; unsigned long flags; @@ -2935,7 +2905,7 @@ void __init setup_IO_APIC(void) } /* - * Called after all the initialization is done. If we didnt find any + * Called after all the initialization is done. If we didn't find any * APIC bugs then we can allow the modify fast path */ @@ -2948,89 +2918,84 @@ static int __init io_apic_bug_finalize(void) late_initcall(io_apic_bug_finalize); -struct sysfs_ioapic_data { - struct sys_device dev; - struct IO_APIC_route_entry entry[0]; -}; -static struct sysfs_ioapic_data * mp_ioapic_data[MAX_IO_APICS]; +static struct IO_APIC_route_entry *ioapic_saved_data[MAX_IO_APICS]; -static int ioapic_suspend(struct sys_device *dev, pm_message_t state) +static void suspend_ioapic(int ioapic_id) { - struct IO_APIC_route_entry *entry; - struct sysfs_ioapic_data *data; + struct IO_APIC_route_entry *saved_data = ioapic_saved_data[ioapic_id]; int i; - data = container_of(dev, struct sysfs_ioapic_data, dev); - entry = data->entry; - for (i = 0; i < nr_ioapic_registers[dev->id]; i ++, entry ++ ) - *entry = ioapic_read_entry(dev->id, i); + if (!saved_data) + return; + + for (i = 0; i < nr_ioapic_registers[ioapic_id]; i++) + saved_data[i] = ioapic_read_entry(ioapic_id, i); +} + +static int ioapic_suspend(void) +{ + int ioapic_id; + + for (ioapic_id = 0; ioapic_id < nr_ioapics; ioapic_id++) + suspend_ioapic(ioapic_id); return 0; } -static int ioapic_resume(struct sys_device *dev) +static void resume_ioapic(int ioapic_id) { - struct IO_APIC_route_entry *entry; - struct sysfs_ioapic_data *data; + struct IO_APIC_route_entry *saved_data = ioapic_saved_data[ioapic_id]; unsigned long flags; union IO_APIC_reg_00 reg_00; int i; - data = container_of(dev, struct sysfs_ioapic_data, dev); - entry = data->entry; + if (!saved_data) + return; raw_spin_lock_irqsave(&ioapic_lock, flags); - reg_00.raw = io_apic_read(dev->id, 0); - if (reg_00.bits.ID != mp_ioapics[dev->id].apicid) { - reg_00.bits.ID = mp_ioapics[dev->id].apicid; - io_apic_write(dev->id, 0, reg_00.raw); + reg_00.raw = io_apic_read(ioapic_id, 0); + if (reg_00.bits.ID != mp_ioapics[ioapic_id].apicid) { + reg_00.bits.ID = mp_ioapics[ioapic_id].apicid; + io_apic_write(ioapic_id, 0, reg_00.raw); } raw_spin_unlock_irqrestore(&ioapic_lock, flags); - for (i = 0; i < nr_ioapic_registers[dev->id]; i++) - ioapic_write_entry(dev->id, i, entry[i]); + for (i = 0; i < nr_ioapic_registers[ioapic_id]; i++) + ioapic_write_entry(ioapic_id, i, saved_data[i]); +} - return 0; +static void ioapic_resume(void) +{ + int ioapic_id; + + for (ioapic_id = nr_ioapics - 1; ioapic_id >= 0; ioapic_id--) + resume_ioapic(ioapic_id); } -static struct sysdev_class ioapic_sysdev_class = { - .name = "ioapic", +static struct syscore_ops ioapic_syscore_ops = { .suspend = ioapic_suspend, .resume = ioapic_resume, }; -static int __init ioapic_init_sysfs(void) +static int __init ioapic_init_ops(void) { - struct sys_device * dev; - int i, size, error; + int i; - error = sysdev_class_register(&ioapic_sysdev_class); - if (error) - return error; + for (i = 0; i < nr_ioapics; i++) { + unsigned int size; - for (i = 0; i < nr_ioapics; i++ ) { - size = sizeof(struct sys_device) + nr_ioapic_registers[i] + size = nr_ioapic_registers[i] * sizeof(struct IO_APIC_route_entry); - mp_ioapic_data[i] = kzalloc(size, GFP_KERNEL); - if (!mp_ioapic_data[i]) { - printk(KERN_ERR "Can't suspend/resume IOAPIC %d\n", i); - continue; - } - dev = &mp_ioapic_data[i]->dev; - dev->id = i; - dev->cls = &ioapic_sysdev_class; - error = sysdev_register(dev); - if (error) { - kfree(mp_ioapic_data[i]); - mp_ioapic_data[i] = NULL; - printk(KERN_ERR "Can't suspend/resume IOAPIC %d\n", i); - continue; - } + ioapic_saved_data[i] = kzalloc(size, GFP_KERNEL); + if (!ioapic_saved_data[i]) + pr_err("IOAPIC %d: suspend/resume impossible!\n", i); } + register_syscore_ops(&ioapic_syscore_ops); + return 0; } -device_initcall(ioapic_init_sysfs); +device_initcall(ioapic_init_ops); /* * Dynamic irq allocate and deallocation @@ -3060,7 +3025,7 @@ unsigned int create_irq_nr(unsigned int from, int node) raw_spin_unlock_irqrestore(&vector_lock, flags); if (ret) { - set_irq_chip_data(irq, cfg); + irq_set_chip_data(irq, cfg); irq_clear_status_flags(irq, IRQ_NOREQUEST); } else { free_irq_at(irq, cfg); @@ -3085,7 +3050,7 @@ int create_irq(void) void destroy_irq(unsigned int irq) { - struct irq_cfg *cfg = get_irq_chip_data(irq); + struct irq_cfg *cfg = irq_get_chip_data(irq); unsigned long flags; irq_set_status_flags(irq, IRQ_NOREQUEST|IRQ_NOPROBE); @@ -3119,7 +3084,7 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, dest = apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus()); - if (irq_remapped(get_irq_chip_data(irq))) { + if (irq_remapped(cfg)) { struct irte irte; int ir_index; u16 sub_handle; @@ -3291,6 +3256,7 @@ static int msi_alloc_irte(struct pci_dev *dev, int irq, int nvec) static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq) { + struct irq_chip *chip = &msi_chip; struct msi_msg msg; int ret; @@ -3298,14 +3264,15 @@ static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq) if (ret < 0) return ret; - set_irq_msi(irq, msidesc); + irq_set_msi_desc(irq, msidesc); write_msi_msg(irq, &msg); - if (irq_remapped(get_irq_chip_data(irq))) { + if (irq_remapped(irq_get_chip_data(irq))) { irq_set_status_flags(irq, IRQ_MOVE_PCNTXT); - set_irq_chip_and_handler_name(irq, &msi_ir_chip, handle_edge_irq, "edge"); - } else - set_irq_chip_and_handler_name(irq, &msi_chip, handle_edge_irq, "edge"); + chip = &msi_ir_chip; + } + + irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge"); dev_printk(KERN_DEBUG, &dev->dev, "irq %d for MSI/MSI-X\n", irq); @@ -3423,8 +3390,8 @@ int arch_setup_dmar_msi(unsigned int irq) if (ret < 0) return ret; dmar_msi_write(irq, &msg); - set_irq_chip_and_handler_name(irq, &dmar_msi_type, handle_edge_irq, - "edge"); + irq_set_chip_and_handler_name(irq, &dmar_msi_type, handle_edge_irq, + "edge"); return 0; } #endif @@ -3482,6 +3449,7 @@ static struct irq_chip hpet_msi_type = { int arch_setup_hpet_msi(unsigned int irq, unsigned int id) { + struct irq_chip *chip = &hpet_msi_type; struct msi_msg msg; int ret; @@ -3501,15 +3469,12 @@ int arch_setup_hpet_msi(unsigned int irq, unsigned int id) if (ret < 0) return ret; - hpet_msi_write(get_irq_data(irq), &msg); + hpet_msi_write(irq_get_handler_data(irq), &msg); irq_set_status_flags(irq, IRQ_MOVE_PCNTXT); - if (irq_remapped(get_irq_chip_data(irq))) - set_irq_chip_and_handler_name(irq, &ir_hpet_msi_type, - handle_edge_irq, "edge"); - else - set_irq_chip_and_handler_name(irq, &hpet_msi_type, - handle_edge_irq, "edge"); + if (irq_remapped(irq_get_chip_data(irq))) + chip = &ir_hpet_msi_type; + irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge"); return 0; } #endif @@ -3596,7 +3561,7 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev) write_ht_irq_msg(irq, &msg); - set_irq_chip_and_handler_name(irq, &ht_irq_chip, + irq_set_chip_and_handler_name(irq, &ht_irq_chip, handle_edge_irq, "edge"); dev_printk(KERN_DEBUG, &dev->dev, "irq %d for HT\n", irq); @@ -3605,7 +3570,40 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev) } #endif /* CONFIG_HT_IRQ */ -int __init io_apic_get_redir_entries (int ioapic) +static int +io_apic_setup_irq_pin(unsigned int irq, int node, struct io_apic_irq_attr *attr) +{ + struct irq_cfg *cfg = alloc_irq_and_cfg_at(irq, node); + int ret; + + if (!cfg) + return -EINVAL; + ret = __add_pin_to_irq_node(cfg, node, attr->ioapic, attr->ioapic_pin); + if (!ret) + setup_ioapic_irq(attr->ioapic, attr->ioapic_pin, irq, cfg, + attr->trigger, attr->polarity); + return ret; +} + +int io_apic_setup_irq_pin_once(unsigned int irq, int node, + struct io_apic_irq_attr *attr) +{ + unsigned int id = attr->ioapic, pin = attr->ioapic_pin; + int ret; + + /* Avoid redundant programming */ + if (test_bit(pin, mp_ioapic_routing[id].pin_programmed)) { + pr_debug("Pin %d-%d already programmed\n", + mp_ioapics[id].apicid, pin); + return 0; + } + ret = io_apic_setup_irq_pin(irq, node, attr); + if (!ret) + set_bit(pin, mp_ioapic_routing[id].pin_programmed); + return ret; +} + +static int __init io_apic_get_redir_entries(int ioapic) { union IO_APIC_reg_01 reg_01; unsigned long flags; @@ -3659,96 +3657,24 @@ int __init arch_probe_nr_irqs(void) } #endif -static int __io_apic_set_pci_routing(struct device *dev, int irq, - struct io_apic_irq_attr *irq_attr) +int io_apic_set_pci_routing(struct device *dev, int irq, + struct io_apic_irq_attr *irq_attr) { - struct irq_cfg *cfg; int node; - int ioapic, pin; - int trigger, polarity; - ioapic = irq_attr->ioapic; if (!IO_APIC_IRQ(irq)) { apic_printk(APIC_QUIET,KERN_ERR "IOAPIC[%d]: Invalid reference to IRQ 0\n", - ioapic); + irq_attr->ioapic); return -EINVAL; } - if (dev) - node = dev_to_node(dev); - else - node = cpu_to_node(0); - - cfg = alloc_irq_and_cfg_at(irq, node); - if (!cfg) - return 0; - - pin = irq_attr->ioapic_pin; - trigger = irq_attr->trigger; - polarity = irq_attr->polarity; - - /* - * IRQs < 16 are already in the irq_2_pin[] map - */ - if (irq >= legacy_pic->nr_legacy_irqs) { - if (__add_pin_to_irq_node(cfg, node, ioapic, pin)) { - printk(KERN_INFO "can not add pin %d for irq %d\n", - pin, irq); - return 0; - } - } - - setup_ioapic_irq(ioapic, pin, irq, cfg, trigger, polarity); + node = dev ? dev_to_node(dev) : cpu_to_node(0); - return 0; + return io_apic_setup_irq_pin_once(irq, node, irq_attr); } -int io_apic_set_pci_routing(struct device *dev, int irq, - struct io_apic_irq_attr *irq_attr) -{ - int ioapic, pin; - /* - * Avoid pin reprogramming. PRTs typically include entries - * with redundant pin->gsi mappings (but unique PCI devices); - * we only program the IOAPIC on the first. - */ - ioapic = irq_attr->ioapic; - pin = irq_attr->ioapic_pin; - if (test_bit(pin, mp_ioapic_routing[ioapic].pin_programmed)) { - pr_debug("Pin %d-%d already programmed\n", - mp_ioapics[ioapic].apicid, pin); - return 0; - } - set_bit(pin, mp_ioapic_routing[ioapic].pin_programmed); - - return __io_apic_set_pci_routing(dev, irq, irq_attr); -} - -u8 __init io_apic_unique_id(u8 id) -{ #ifdef CONFIG_X86_32 - if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && - !APIC_XAPIC(apic_version[boot_cpu_physical_apicid])) - return io_apic_get_unique_id(nr_ioapics, id); - else - return id; -#else - int i; - DECLARE_BITMAP(used, 256); - - bitmap_zero(used, 256); - for (i = 0; i < nr_ioapics; i++) { - struct mpc_ioapic *ia = &mp_ioapics[i]; - __set_bit(ia->apicid, used); - } - if (!test_bit(id, used)) - return id; - return find_first_zero_bit(used, 256); -#endif -} - -#ifdef CONFIG_X86_32 -int __init io_apic_get_unique_id(int ioapic, int apic_id) +static int __init io_apic_get_unique_id(int ioapic, int apic_id) { union IO_APIC_reg_00 reg_00; static physid_mask_t apic_id_map = PHYSID_MASK_NONE; @@ -3821,9 +3747,33 @@ int __init io_apic_get_unique_id(int ioapic, int apic_id) return apic_id; } + +static u8 __init io_apic_unique_id(u8 id) +{ + if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && + !APIC_XAPIC(apic_version[boot_cpu_physical_apicid])) + return io_apic_get_unique_id(nr_ioapics, id); + else + return id; +} +#else +static u8 __init io_apic_unique_id(u8 id) +{ + int i; + DECLARE_BITMAP(used, 256); + + bitmap_zero(used, 256); + for (i = 0; i < nr_ioapics; i++) { + struct mpc_ioapic *ia = &mp_ioapics[i]; + __set_bit(ia->apicid, used); + } + if (!test_bit(id, used)) + return id; + return find_first_zero_bit(used, 256); +} #endif -int __init io_apic_get_version(int ioapic) +static int __init io_apic_get_version(int ioapic) { union IO_APIC_reg_01 reg_01; unsigned long flags; @@ -3868,8 +3818,8 @@ int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity) void __init setup_ioapic_dest(void) { int pin, ioapic, irq, irq_entry; - struct irq_desc *desc; const struct cpumask *mask; + struct irq_data *idata; if (skip_ioapic_setup == 1) return; @@ -3884,21 +3834,20 @@ void __init setup_ioapic_dest(void) if ((ioapic > 0) && (irq > 16)) continue; - desc = irq_to_desc(irq); + idata = irq_get_irq_data(irq); /* * Honour affinities which have been set in early boot */ - if (desc->status & - (IRQ_NO_BALANCING | IRQ_AFFINITY_SET)) - mask = desc->irq_data.affinity; + if (!irqd_can_balance(idata) || irqd_affinity_was_set(idata)) + mask = idata->affinity; else mask = apic->target_cpus(); if (intr_remapping_enabled) - ir_ioapic_set_affinity(&desc->irq_data, mask, false); + ir_ioapic_set_affinity(idata, mask, false); else - ioapic_set_affinity(&desc->irq_data, mask, false); + ioapic_set_affinity(idata, mask, false); } } @@ -4026,10 +3975,10 @@ int mp_find_ioapic_pin(int ioapic, u32 gsi) return gsi - mp_gsi_routing[ioapic].gsi_base; } -static int bad_ioapic(unsigned long address) +static __init int bad_ioapic(unsigned long address) { if (nr_ioapics >= MAX_IO_APICS) { - printk(KERN_WARNING "WARING: Max # of I/O APICs (%d) exceeded " + printk(KERN_WARNING "WARNING: Max # of I/O APICs (%d) exceeded " "(found %d), skipping\n", MAX_IO_APICS, nr_ioapics); return 1; } @@ -4086,20 +4035,16 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base) /* Enable IOAPIC early just for system timer */ void __init pre_init_apic_IRQ0(void) { - struct irq_cfg *cfg; + struct io_apic_irq_attr attr = { 0, 0, 0, 0 }; printk(KERN_INFO "Early APIC setup for system timer0\n"); #ifndef CONFIG_SMP physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map); #endif - /* Make sure the irq descriptor is set up */ - cfg = alloc_irq_and_cfg_at(0, 0); - setup_local_APIC(); - add_pin_to_irq_node(cfg, 0, 0, 0); - set_irq_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq, "edge"); - - setup_ioapic_irq(0, 0, 0, cfg, 0, 0); + io_apic_setup_irq_pin(0, 0, &attr); + irq_set_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq, + "edge"); } diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c index 08385e090a6..cce91bf2667 100644 --- a/arch/x86/kernel/apic/ipi.c +++ b/arch/x86/kernel/apic/ipi.c @@ -56,6 +56,8 @@ void default_send_IPI_mask_allbutself_phys(const struct cpumask *mask, local_irq_restore(flags); } +#ifdef CONFIG_X86_32 + void default_send_IPI_mask_sequence_logical(const struct cpumask *mask, int vector) { @@ -71,8 +73,8 @@ void default_send_IPI_mask_sequence_logical(const struct cpumask *mask, local_irq_save(flags); for_each_cpu(query_cpu, mask) __default_send_IPI_dest_field( - apic->cpu_to_logical_apicid(query_cpu), vector, - apic->dest_logical); + early_per_cpu(x86_cpu_to_logical_apicid, query_cpu), + vector, apic->dest_logical); local_irq_restore(flags); } @@ -90,14 +92,12 @@ void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask, if (query_cpu == this_cpu) continue; __default_send_IPI_dest_field( - apic->cpu_to_logical_apicid(query_cpu), vector, - apic->dest_logical); + early_per_cpu(x86_cpu_to_logical_apicid, query_cpu), + vector, apic->dest_logical); } local_irq_restore(flags); } -#ifdef CONFIG_X86_32 - /* * This is only used on smaller machines. */ diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c index 960f26ab5c9..6273eee5134 100644 --- a/arch/x86/kernel/apic/numaq_32.c +++ b/arch/x86/kernel/apic/numaq_32.c @@ -373,13 +373,6 @@ static inline void numaq_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask return physids_promote(0xFUL, retmap); } -static inline int numaq_cpu_to_logical_apicid(int cpu) -{ - if (cpu >= nr_cpu_ids) - return BAD_APICID; - return cpu_2_logical_apicid[cpu]; -} - /* * Supporting over 60 cpus on NUMA-Q requires a locality-dependent * cpu to APIC ID relation to properly interact with the intelligent @@ -398,6 +391,15 @@ static inline int numaq_apicid_to_node(int logical_apicid) return logical_apicid >> 4; } +static int numaq_numa_cpu_node(int cpu) +{ + int logical_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu); + + if (logical_apicid != BAD_APICID) + return numaq_apicid_to_node(logical_apicid); + return NUMA_NO_NODE; +} + static void numaq_apicid_to_cpu_present(int logical_apicid, physid_mask_t *retmap) { int node = numaq_apicid_to_node(logical_apicid); @@ -508,8 +510,6 @@ struct apic __refdata apic_numaq = { .ioapic_phys_id_map = numaq_ioapic_phys_id_map, .setup_apic_routing = numaq_setup_apic_routing, .multi_timer_check = numaq_multi_timer_check, - .apicid_to_node = numaq_apicid_to_node, - .cpu_to_logical_apicid = numaq_cpu_to_logical_apicid, .cpu_present_to_apicid = numaq_cpu_present_to_apicid, .apicid_to_cpu_present = numaq_apicid_to_cpu_present, .setup_portio_remap = numaq_setup_portio_remap, @@ -547,4 +547,7 @@ struct apic __refdata apic_numaq = { .icr_write = native_apic_icr_write, .wait_icr_idle = native_apic_wait_icr_idle, .safe_wait_icr_idle = native_safe_apic_wait_icr_idle, + + .x86_32_early_logical_apicid = noop_x86_32_early_logical_apicid, + .x86_32_numa_cpu_node = numaq_numa_cpu_node, }; diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index 99d2fe01608..fc84c7b6110 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -77,6 +77,11 @@ void __init default_setup_apic_routing(void) apic->setup_apic_routing(); } +static int default_x86_32_early_logical_apicid(int cpu) +{ + return 1 << cpu; +} + static void setup_apic_flat_routing(void) { #ifdef CONFIG_X86_IO_APIC @@ -130,8 +135,6 @@ struct apic apic_default = { .ioapic_phys_id_map = default_ioapic_phys_id_map, .setup_apic_routing = setup_apic_flat_routing, .multi_timer_check = NULL, - .apicid_to_node = default_apicid_to_node, - .cpu_to_logical_apicid = default_cpu_to_logical_apicid, .cpu_present_to_apicid = default_cpu_present_to_apicid, .apicid_to_cpu_present = physid_set_mask_of_physid, .setup_portio_remap = NULL, @@ -167,6 +170,9 @@ struct apic apic_default = { .icr_write = native_apic_icr_write, .wait_icr_idle = native_apic_wait_icr_idle, .safe_wait_icr_idle = native_safe_apic_wait_icr_idle, + + .x86_32_early_logical_apicid = default_x86_32_early_logical_apicid, + .x86_32_numa_cpu_node = default_x86_32_numa_cpu_node, }; extern struct apic apic_numaq; diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c index 9b419263d90..e4b8059b414 100644 --- a/arch/x86/kernel/apic/summit_32.c +++ b/arch/x86/kernel/apic/summit_32.c @@ -194,11 +194,10 @@ static unsigned long summit_check_apicid_present(int bit) return 1; } -static void summit_init_apic_ldr(void) +static int summit_early_logical_apicid(int cpu) { - unsigned long val, id; int count = 0; - u8 my_id = (u8)hard_smp_processor_id(); + u8 my_id = early_per_cpu(x86_cpu_to_apicid, cpu); u8 my_cluster = APIC_CLUSTER(my_id); #ifdef CONFIG_SMP u8 lid; @@ -206,7 +205,7 @@ static void summit_init_apic_ldr(void) /* Create logical APIC IDs by counting CPUs already in cluster. */ for (count = 0, i = nr_cpu_ids; --i >= 0; ) { - lid = cpu_2_logical_apicid[i]; + lid = early_per_cpu(x86_cpu_to_logical_apicid, i); if (lid != BAD_APICID && APIC_CLUSTER(lid) == my_cluster) ++count; } @@ -214,7 +213,15 @@ static void summit_init_apic_ldr(void) /* We only have a 4 wide bitmap in cluster mode. If a deranged * BIOS puts 5 CPUs in one APIC cluster, we're hosed. */ BUG_ON(count >= XAPIC_DEST_CPUS_SHIFT); - id = my_cluster | (1UL << count); + return my_cluster | (1UL << count); +} + +static void summit_init_apic_ldr(void) +{ + int cpu = smp_processor_id(); + unsigned long id = early_per_cpu(x86_cpu_to_logical_apicid, cpu); + unsigned long val; + apic_write(APIC_DFR, SUMMIT_APIC_DFR_VALUE); val = apic_read(APIC_LDR) & ~APIC_LDR_MASK; val |= SET_APIC_LOGICAL_ID(id); @@ -232,27 +239,6 @@ static void summit_setup_apic_routing(void) nr_ioapics); } -static int summit_apicid_to_node(int logical_apicid) -{ -#ifdef CONFIG_SMP - return apicid_2_node[hard_smp_processor_id()]; -#else - return 0; -#endif -} - -/* Mapping from cpu number to logical apicid */ -static inline int summit_cpu_to_logical_apicid(int cpu) -{ -#ifdef CONFIG_SMP - if (cpu >= nr_cpu_ids) - return BAD_APICID; - return cpu_2_logical_apicid[cpu]; -#else - return logical_smp_processor_id(); -#endif -} - static int summit_cpu_present_to_apicid(int mps_cpu) { if (mps_cpu < nr_cpu_ids) @@ -286,7 +272,7 @@ static unsigned int summit_cpu_mask_to_apicid(const struct cpumask *cpumask) * The cpus in the mask must all be on the apic cluster. */ for_each_cpu(cpu, cpumask) { - int new_apicid = summit_cpu_to_logical_apicid(cpu); + int new_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu); if (round && APIC_CLUSTER(apicid) != APIC_CLUSTER(new_apicid)) { printk("%s: Not a valid mask!\n", __func__); @@ -301,7 +287,7 @@ static unsigned int summit_cpu_mask_to_apicid(const struct cpumask *cpumask) static unsigned int summit_cpu_mask_to_apicid_and(const struct cpumask *inmask, const struct cpumask *andmask) { - int apicid = summit_cpu_to_logical_apicid(0); + int apicid = early_per_cpu(x86_cpu_to_logical_apicid, 0); cpumask_var_t cpumask; if (!alloc_cpumask_var(&cpumask, GFP_ATOMIC)) @@ -528,8 +514,6 @@ struct apic apic_summit = { .ioapic_phys_id_map = summit_ioapic_phys_id_map, .setup_apic_routing = summit_setup_apic_routing, .multi_timer_check = NULL, - .apicid_to_node = summit_apicid_to_node, - .cpu_to_logical_apicid = summit_cpu_to_logical_apicid, .cpu_present_to_apicid = summit_cpu_present_to_apicid, .apicid_to_cpu_present = summit_apicid_to_cpu_present, .setup_portio_remap = NULL, @@ -565,4 +549,7 @@ struct apic apic_summit = { .icr_write = native_apic_icr_write, .wait_icr_idle = native_apic_wait_icr_idle, .safe_wait_icr_idle = native_safe_apic_wait_icr_idle, + + .x86_32_early_logical_apicid = summit_early_logical_apicid, + .x86_32_numa_cpu_node = default_x86_32_numa_cpu_node, }; diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index cf69c59f491..90949bbd566 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -206,8 +206,6 @@ struct apic apic_x2apic_cluster = { .ioapic_phys_id_map = NULL, .setup_apic_routing = NULL, .multi_timer_check = NULL, - .apicid_to_node = NULL, - .cpu_to_logical_apicid = NULL, .cpu_present_to_apicid = default_cpu_present_to_apicid, .apicid_to_cpu_present = NULL, .setup_portio_remap = NULL, diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index 8972f38c5ce..c7e6d6645bf 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -195,8 +195,6 @@ struct apic apic_x2apic_phys = { .ioapic_phys_id_map = NULL, .setup_apic_routing = NULL, .multi_timer_check = NULL, - .apicid_to_node = NULL, - .cpu_to_logical_apicid = NULL, .cpu_present_to_apicid = default_cpu_present_to_apicid, .apicid_to_cpu_present = NULL, .setup_portio_remap = NULL, diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index bd16b58b885..33b10a0fc09 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -23,6 +23,8 @@ #include <linux/io.h> #include <linux/pci.h> #include <linux/kdebug.h> +#include <linux/delay.h> +#include <linux/crash_dump.h> #include <asm/uv/uv_mmrs.h> #include <asm/uv/uv_hub.h> @@ -34,6 +36,7 @@ #include <asm/ipi.h> #include <asm/smp.h> #include <asm/x86_init.h> +#include <asm/emergency-restart.h> DEFINE_PER_CPU(int, x2apic_extra_bits); @@ -338,8 +341,6 @@ struct apic __refdata apic_x2apic_uv_x = { .ioapic_phys_id_map = NULL, .setup_apic_routing = NULL, .multi_timer_check = NULL, - .apicid_to_node = NULL, - .cpu_to_logical_apicid = NULL, .cpu_present_to_apicid = default_cpu_present_to_apicid, .apicid_to_cpu_present = NULL, .setup_portio_remap = NULL, @@ -812,4 +813,11 @@ void __init uv_system_init(void) /* register Legacy VGA I/O redirection handler */ pci_register_set_vga_state(uv_set_vga_state); + + /* + * For a kdump kernel the reset must be BOOT_ACPI, not BOOT_EFI, as + * EFI is not enabled in the kdump kernel. + */ + if (is_kdump_kernel()) + reboot_type = BOOT_ACPI; } diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 0e4f24c2a74..adee12e0da1 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -66,7 +66,7 @@ * 1.5: Fix segment register reloading (in case of bad segments saved * across BIOS call). * Stephen Rothwell - * 1.6: Cope with complier/assembler differences. + * 1.6: Cope with compiler/assembler differences. * Only try to turn off the first display device. * Fix OOPS at power off with no APM BIOS by Jan Echternach * <echter@informatik.uni-rostock.de> @@ -227,6 +227,8 @@ #include <linux/suspend.h> #include <linux/kthread.h> #include <linux/jiffies.h> +#include <linux/acpi.h> +#include <linux/syscore_ops.h> #include <asm/system.h> #include <asm/uaccess.h> @@ -975,20 +977,10 @@ recalc: static void apm_power_off(void) { - unsigned char po_bios_call[] = { - 0xb8, 0x00, 0x10, /* movw $0x1000,ax */ - 0x8e, 0xd0, /* movw ax,ss */ - 0xbc, 0x00, 0xf0, /* movw $0xf000,sp */ - 0xb8, 0x07, 0x53, /* movw $0x5307,ax */ - 0xbb, 0x01, 0x00, /* movw $0x0001,bx */ - 0xb9, 0x03, 0x00, /* movw $0x0003,cx */ - 0xcd, 0x15 /* int $0x15 */ - }; - /* Some bioses don't like being called from CPU != 0 */ if (apm_info.realmode_power_off) { set_cpus_allowed_ptr(current, cpumask_of(0)); - machine_real_restart(po_bios_call, sizeof(po_bios_call)); + machine_real_restart(MRR_APM); } else { (void)set_system_power_state(APM_STATE_OFF); } @@ -1247,6 +1239,7 @@ static int suspend(int vetoable) local_irq_disable(); sysdev_suspend(PMSG_SUSPEND); + syscore_suspend(); local_irq_enable(); @@ -1264,6 +1257,7 @@ static int suspend(int vetoable) apm_error("suspend", err); err = (err == APM_SUCCESS) ? 0 : -EIO; + syscore_resume(); sysdev_resume(); local_irq_enable(); @@ -1289,6 +1283,7 @@ static void standby(void) local_irq_disable(); sysdev_suspend(PMSG_SUSPEND); + syscore_suspend(); local_irq_enable(); err = set_system_power_state(APM_STATE_STANDBY); @@ -1296,6 +1291,7 @@ static void standby(void) apm_error("standby", err); local_irq_disable(); + syscore_resume(); sysdev_resume(); local_irq_enable(); @@ -2331,12 +2327,11 @@ static int __init apm_init(void) apm_info.disabled = 1; return -ENODEV; } - if (pm_flags & PM_ACPI) { + if (!acpi_disabled) { printk(KERN_NOTICE "apm: overridden by ACPI.\n"); apm_info.disabled = 1; return -ENODEV; } - pm_flags |= PM_APM; /* * Set up the long jump entry point to the APM BIOS, which is called @@ -2428,7 +2423,6 @@ static void __exit apm_exit(void) kthread_stop(kapmd_task); kapmd_task = NULL; } - pm_flags &= ~PM_APM; } module_init(apm_init); diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index cfa82c899f4..4f13fafc526 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -1,5 +1,70 @@ +/* + * Generate definitions needed by assembly language modules. + * This code generates raw asm output which is post-processed to extract + * and format the required data. + */ +#define COMPILE_OFFSETS + +#include <linux/crypto.h> +#include <linux/sched.h> +#include <linux/stddef.h> +#include <linux/hardirq.h> +#include <linux/suspend.h> +#include <linux/kbuild.h> +#include <asm/processor.h> +#include <asm/thread_info.h> +#include <asm/sigframe.h> +#include <asm/bootparam.h> +#include <asm/suspend.h> + +#ifdef CONFIG_XEN +#include <xen/interface/xen.h> +#endif + #ifdef CONFIG_X86_32 # include "asm-offsets_32.c" #else # include "asm-offsets_64.c" #endif + +void common(void) { + BLANK(); + OFFSET(TI_flags, thread_info, flags); + OFFSET(TI_status, thread_info, status); + OFFSET(TI_addr_limit, thread_info, addr_limit); + OFFSET(TI_preempt_count, thread_info, preempt_count); + + BLANK(); + OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx); + + BLANK(); + OFFSET(pbe_address, pbe, address); + OFFSET(pbe_orig_address, pbe, orig_address); + OFFSET(pbe_next, pbe, next); + +#ifdef CONFIG_PARAVIRT + BLANK(); + OFFSET(PARAVIRT_enabled, pv_info, paravirt_enabled); + OFFSET(PARAVIRT_PATCH_pv_cpu_ops, paravirt_patch_template, pv_cpu_ops); + OFFSET(PARAVIRT_PATCH_pv_irq_ops, paravirt_patch_template, pv_irq_ops); + OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable); + OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable); + OFFSET(PV_CPU_iret, pv_cpu_ops, iret); + OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit); + OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0); + OFFSET(PV_MMU_read_cr2, pv_mmu_ops, read_cr2); +#endif + +#ifdef CONFIG_XEN + BLANK(); + OFFSET(XEN_vcpu_info_mask, vcpu_info, evtchn_upcall_mask); + OFFSET(XEN_vcpu_info_pending, vcpu_info, evtchn_upcall_pending); +#endif + + BLANK(); + OFFSET(BP_scratch, boot_params, scratch); + OFFSET(BP_loadflags, boot_params, hdr.loadflags); + OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch); + OFFSET(BP_version, boot_params, hdr.version); + OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment); +} diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index 1a4088dda37..c29d631af6f 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -1,26 +1,4 @@ -/* - * Generate definitions needed by assembly language modules. - * This code generates raw asm output which is post-processed - * to extract and format the required data. - */ - -#include <linux/crypto.h> -#include <linux/sched.h> -#include <linux/signal.h> -#include <linux/personality.h> -#include <linux/suspend.h> -#include <linux/kbuild.h> #include <asm/ucontext.h> -#include <asm/sigframe.h> -#include <asm/pgtable.h> -#include <asm/fixmap.h> -#include <asm/processor.h> -#include <asm/thread_info.h> -#include <asm/bootparam.h> -#include <asm/elf.h> -#include <asm/suspend.h> - -#include <xen/interface/xen.h> #include <linux/lguest.h> #include "../../../drivers/lguest/lg.h" @@ -51,21 +29,10 @@ void foo(void) OFFSET(CPUINFO_x86_vendor_id, cpuinfo_x86, x86_vendor_id); BLANK(); - OFFSET(TI_task, thread_info, task); - OFFSET(TI_exec_domain, thread_info, exec_domain); - OFFSET(TI_flags, thread_info, flags); - OFFSET(TI_status, thread_info, status); - OFFSET(TI_preempt_count, thread_info, preempt_count); - OFFSET(TI_addr_limit, thread_info, addr_limit); - OFFSET(TI_restart_block, thread_info, restart_block); OFFSET(TI_sysenter_return, thread_info, sysenter_return); OFFSET(TI_cpu, thread_info, cpu); BLANK(); - OFFSET(GDS_size, desc_ptr, size); - OFFSET(GDS_address, desc_ptr, address); - BLANK(); - OFFSET(PT_EBX, pt_regs, bx); OFFSET(PT_ECX, pt_regs, cx); OFFSET(PT_EDX, pt_regs, dx); @@ -85,42 +52,13 @@ void foo(void) OFFSET(PT_OLDSS, pt_regs, ss); BLANK(); - OFFSET(EXEC_DOMAIN_handler, exec_domain, handler); OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe, uc.uc_mcontext); BLANK(); - OFFSET(pbe_address, pbe, address); - OFFSET(pbe_orig_address, pbe, orig_address); - OFFSET(pbe_next, pbe, next); - /* Offset from the sysenter stack to tss.sp0 */ DEFINE(TSS_sysenter_sp0, offsetof(struct tss_struct, x86_tss.sp0) - sizeof(struct tss_struct)); - DEFINE(PAGE_SIZE_asm, PAGE_SIZE); - DEFINE(PAGE_SHIFT_asm, PAGE_SHIFT); - DEFINE(THREAD_SIZE_asm, THREAD_SIZE); - - OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx); - -#ifdef CONFIG_PARAVIRT - BLANK(); - OFFSET(PARAVIRT_enabled, pv_info, paravirt_enabled); - OFFSET(PARAVIRT_PATCH_pv_cpu_ops, paravirt_patch_template, pv_cpu_ops); - OFFSET(PARAVIRT_PATCH_pv_irq_ops, paravirt_patch_template, pv_irq_ops); - OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable); - OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable); - OFFSET(PV_CPU_iret, pv_cpu_ops, iret); - OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit); - OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0); -#endif - -#ifdef CONFIG_XEN - BLANK(); - OFFSET(XEN_vcpu_info_mask, vcpu_info, evtchn_upcall_mask); - OFFSET(XEN_vcpu_info_pending, vcpu_info, evtchn_upcall_pending); -#endif - #if defined(CONFIG_LGUEST) || defined(CONFIG_LGUEST_GUEST) || defined(CONFIG_LGUEST_MODULE) BLANK(); OFFSET(LGUEST_DATA_irq_enabled, lguest_data, irq_enabled); @@ -139,11 +77,4 @@ void foo(void) OFFSET(LGUEST_PAGES_regs_errcode, lguest_pages, regs.errcode); OFFSET(LGUEST_PAGES_regs, lguest_pages, regs); #endif - - BLANK(); - OFFSET(BP_scratch, boot_params, scratch); - OFFSET(BP_loadflags, boot_params, hdr.loadflags); - OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch); - OFFSET(BP_version, boot_params, hdr.version); - OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment); } diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index 4a6aeedcd96..e72a1194af2 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -1,27 +1,4 @@ -/* - * Generate definitions needed by assembly language modules. - * This code generates raw asm output which is post-processed to extract - * and format the required data. - */ -#define COMPILE_OFFSETS - -#include <linux/crypto.h> -#include <linux/sched.h> -#include <linux/stddef.h> -#include <linux/errno.h> -#include <linux/hardirq.h> -#include <linux/suspend.h> -#include <linux/kbuild.h> -#include <asm/processor.h> -#include <asm/segment.h> -#include <asm/thread_info.h> #include <asm/ia32.h> -#include <asm/bootparam.h> -#include <asm/suspend.h> - -#include <xen/interface/xen.h> - -#include <asm/sigframe.h> #define __NO_STUBS 1 #undef __SYSCALL @@ -33,41 +10,19 @@ static char syscalls[] = { int main(void) { -#define ENTRY(entry) DEFINE(tsk_ ## entry, offsetof(struct task_struct, entry)) - ENTRY(state); - ENTRY(flags); - ENTRY(pid); - BLANK(); -#undef ENTRY -#define ENTRY(entry) DEFINE(TI_ ## entry, offsetof(struct thread_info, entry)) - ENTRY(flags); - ENTRY(addr_limit); - ENTRY(preempt_count); - ENTRY(status); -#ifdef CONFIG_IA32_EMULATION - ENTRY(sysenter_return); -#endif - BLANK(); -#undef ENTRY #ifdef CONFIG_PARAVIRT - BLANK(); - OFFSET(PARAVIRT_enabled, pv_info, paravirt_enabled); - OFFSET(PARAVIRT_PATCH_pv_cpu_ops, paravirt_patch_template, pv_cpu_ops); - OFFSET(PARAVIRT_PATCH_pv_irq_ops, paravirt_patch_template, pv_irq_ops); - OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable); - OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable); OFFSET(PV_IRQ_adjust_exception_frame, pv_irq_ops, adjust_exception_frame); - OFFSET(PV_CPU_iret, pv_cpu_ops, iret); OFFSET(PV_CPU_usergs_sysret32, pv_cpu_ops, usergs_sysret32); OFFSET(PV_CPU_usergs_sysret64, pv_cpu_ops, usergs_sysret64); - OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit); OFFSET(PV_CPU_swapgs, pv_cpu_ops, swapgs); - OFFSET(PV_MMU_read_cr2, pv_mmu_ops, read_cr2); + BLANK(); #endif - #ifdef CONFIG_IA32_EMULATION -#define ENTRY(entry) DEFINE(IA32_SIGCONTEXT_ ## entry, offsetof(struct sigcontext_ia32, entry)) + OFFSET(TI_sysenter_return, thread_info, sysenter_return); + BLANK(); + +#define ENTRY(entry) OFFSET(IA32_SIGCONTEXT_ ## entry, sigcontext_ia32, entry) ENTRY(ax); ENTRY(bx); ENTRY(cx); @@ -79,15 +34,12 @@ int main(void) ENTRY(ip); BLANK(); #undef ENTRY - DEFINE(IA32_RT_SIGFRAME_sigcontext, - offsetof (struct rt_sigframe_ia32, uc.uc_mcontext)); + + OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe_ia32, uc.uc_mcontext); BLANK(); #endif - DEFINE(pbe_address, offsetof(struct pbe, address)); - DEFINE(pbe_orig_address, offsetof(struct pbe, orig_address)); - DEFINE(pbe_next, offsetof(struct pbe, next)); - BLANK(); -#define ENTRY(entry) DEFINE(pt_regs_ ## entry, offsetof(struct pt_regs, entry)) + +#define ENTRY(entry) OFFSET(pt_regs_ ## entry, pt_regs, entry) ENTRY(bx); ENTRY(bx); ENTRY(cx); @@ -107,7 +59,8 @@ int main(void) ENTRY(flags); BLANK(); #undef ENTRY -#define ENTRY(entry) DEFINE(saved_context_ ## entry, offsetof(struct saved_context, entry)) + +#define ENTRY(entry) OFFSET(saved_context_ ## entry, saved_context, entry) ENTRY(cr0); ENTRY(cr2); ENTRY(cr3); @@ -115,26 +68,11 @@ int main(void) ENTRY(cr8); BLANK(); #undef ENTRY - DEFINE(TSS_ist, offsetof(struct tss_struct, x86_tss.ist)); - BLANK(); - DEFINE(crypto_tfm_ctx_offset, offsetof(struct crypto_tfm, __crt_ctx)); - BLANK(); - DEFINE(__NR_syscall_max, sizeof(syscalls) - 1); + OFFSET(TSS_ist, tss_struct, x86_tss.ist); BLANK(); - OFFSET(BP_scratch, boot_params, scratch); - OFFSET(BP_loadflags, boot_params, hdr.loadflags); - OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch); - OFFSET(BP_version, boot_params, hdr.version); - OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment); - BLANK(); - DEFINE(PAGE_SIZE_asm, PAGE_SIZE); -#ifdef CONFIG_XEN - BLANK(); - OFFSET(XEN_vcpu_info_mask, vcpu_info, evtchn_upcall_mask); - OFFSET(XEN_vcpu_info_pending, vcpu_info, evtchn_upcall_pending); -#undef ENTRY -#endif + DEFINE(__NR_syscall_max, sizeof(syscalls) - 1); + return 0; } diff --git a/arch/x86/kernel/check.c b/arch/x86/kernel/check.c index 13a38917951..452932d3473 100644 --- a/arch/x86/kernel/check.c +++ b/arch/x86/kernel/check.c @@ -106,8 +106,8 @@ void __init setup_bios_corruption_check(void) addr += size; } - printk(KERN_INFO "Scanning %d areas for low memory corruption\n", - num_scan_areas); + if (num_scan_areas) + printk(KERN_INFO "Scanning %d areas for low memory corruption\n", num_scan_areas); } @@ -143,12 +143,12 @@ static void check_corruption(struct work_struct *dummy) { check_for_bios_corruption(); schedule_delayed_work(&bios_check_work, - round_jiffies_relative(corruption_check_period*HZ)); + round_jiffies_relative(corruption_check_period*HZ)); } static int start_periodic_check_for_corruption(void) { - if (!memory_corruption_check || corruption_check_period == 0) + if (!num_scan_areas || !memory_corruption_check || corruption_check_period == 0) return 0; printk(KERN_INFO "Scanning for low memory corruption every %d seconds\n", diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 7c7bedb83c5..bb9eb29a52d 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -233,18 +233,22 @@ static void __cpuinit init_amd_k7(struct cpuinfo_x86 *c) } #endif -#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64) +#ifdef CONFIG_NUMA +/* + * To workaround broken NUMA config. Read the comment in + * srat_detect_node(). + */ static int __cpuinit nearby_node(int apicid) { int i, node; for (i = apicid - 1; i >= 0; i--) { - node = apicid_to_node[i]; + node = __apicid_to_node[i]; if (node != NUMA_NO_NODE && node_online(node)) return node; } for (i = apicid + 1; i < MAX_LOCAL_APIC; i++) { - node = apicid_to_node[i]; + node = __apicid_to_node[i]; if (node != NUMA_NO_NODE && node_online(node)) return node; } @@ -261,7 +265,7 @@ static int __cpuinit nearby_node(int apicid) #ifdef CONFIG_X86_HT static void __cpuinit amd_get_topology(struct cpuinfo_x86 *c) { - u32 nodes; + u32 nodes, cores_per_cu = 1; u8 node_id; int cpu = smp_processor_id(); @@ -276,6 +280,7 @@ static void __cpuinit amd_get_topology(struct cpuinfo_x86 *c) /* get compute unit information */ smp_num_siblings = ((ebx >> 8) & 3) + 1; c->compute_unit_id = ebx & 0xff; + cores_per_cu += ((ebx >> 8) & 3); } else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) { u64 value; @@ -288,15 +293,18 @@ static void __cpuinit amd_get_topology(struct cpuinfo_x86 *c) /* fixup multi-node processor information */ if (nodes > 1) { u32 cores_per_node; + u32 cus_per_node; set_cpu_cap(c, X86_FEATURE_AMD_DCM); cores_per_node = c->x86_max_cores / nodes; + cus_per_node = cores_per_node / cores_per_cu; /* store NodeID, use llc_shared_map to store sibling info */ per_cpu(cpu_llc_id, cpu) = node_id; - /* core id to be in range from 0 to (cores_per_node - 1) */ - c->cpu_core_id = c->cpu_core_id % cores_per_node; + /* core id has to be in the [0 .. cores_per_node - 1] range */ + c->cpu_core_id %= cores_per_node; + c->compute_unit_id %= cus_per_node; } } #endif @@ -334,31 +342,40 @@ EXPORT_SYMBOL_GPL(amd_get_nb_id); static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c) { -#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64) +#ifdef CONFIG_NUMA int cpu = smp_processor_id(); int node; unsigned apicid = c->apicid; - node = per_cpu(cpu_llc_id, cpu); + node = numa_cpu_node(cpu); + if (node == NUMA_NO_NODE) + node = per_cpu(cpu_llc_id, cpu); - if (apicid_to_node[apicid] != NUMA_NO_NODE) - node = apicid_to_node[apicid]; if (!node_online(node)) { - /* Two possibilities here: - - The CPU is missing memory and no node was created. - In that case try picking one from a nearby CPU - - The APIC IDs differ from the HyperTransport node IDs - which the K8 northbridge parsing fills in. - Assume they are all increased by a constant offset, - but in the same order as the HT nodeids. - If that doesn't result in a usable node fall back to the - path for the previous case. */ - + /* + * Two possibilities here: + * + * - The CPU is missing memory and no node was created. In + * that case try picking one from a nearby CPU. + * + * - The APIC IDs differ from the HyperTransport node IDs + * which the K8 northbridge parsing fills in. Assume + * they are all increased by a constant offset, but in + * the same order as the HT nodeids. If that doesn't + * result in a usable node fall back to the path for the + * previous case. + * + * This workaround operates directly on the mapping between + * APIC ID and NUMA node, assuming certain relationship + * between APIC ID, HT node ID and NUMA topology. As going + * through CPU mapping may alter the outcome, directly + * access __apicid_to_node[]. + */ int ht_nodeid = c->initial_apicid; if (ht_nodeid >= 0 && - apicid_to_node[ht_nodeid] != NUMA_NO_NODE) - node = apicid_to_node[ht_nodeid]; + __apicid_to_node[ht_nodeid] != NUMA_NO_NODE) + node = __apicid_to_node[ht_nodeid]; /* Pick a nearby node */ if (!node_online(node)) node = nearby_node(apicid); @@ -594,6 +611,29 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) } } #endif + + /* As a rule processors have APIC timer running in deep C states */ + if (c->x86 >= 0xf && !cpu_has_amd_erratum(amd_erratum_400)) + set_cpu_cap(c, X86_FEATURE_ARAT); + + /* + * Disable GART TLB Walk Errors on Fam10h. We do this here + * because this is always needed when GART is enabled, even in a + * kernel which has no MCE support built in. + */ + if (c->x86 == 0x10) { + /* + * BIOS should disable GartTlbWlk Errors themself. If + * it doesn't do it here as suggested by the BKDG. + * + * Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=33012 + */ + u64 mask; + + rdmsrl(MSR_AMD64_MCx_MASK(4), mask); + mask |= (1 << 10); + wrmsrl(MSR_AMD64_MCx_MASK(4), mask); + } } #ifdef CONFIG_X86_32 @@ -658,7 +698,7 @@ cpu_dev_register(amd_cpu_dev); */ const int amd_erratum_400[] = - AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0xf, 0x41, 0x2, 0xff, 0xf), + AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0x0f, 0x4, 0x2, 0xff, 0xf), AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0xff, 0xf)); EXPORT_SYMBOL_GPL(amd_erratum_400); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 1d59834396b..e2ced0074a4 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -675,7 +675,7 @@ void __init early_cpu_init(void) const struct cpu_dev *const *cdev; int count = 0; -#ifdef PROCESSOR_SELECT +#ifdef CONFIG_PROCESSOR_SELECT printk(KERN_INFO "KERNEL supported cpus:\n"); #endif @@ -687,7 +687,7 @@ void __init early_cpu_init(void) cpu_devs[count] = cpudev; count++; -#ifdef PROCESSOR_SELECT +#ifdef CONFIG_PROCESSOR_SELECT { unsigned int j; @@ -869,7 +869,7 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c) select_idle_routine(c); -#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64) +#ifdef CONFIG_NUMA numa_add_cpu(smp_processor_id()); #endif } diff --git a/arch/x86/kernel/cpu/cpufreq/longhaul.c b/arch/x86/kernel/cpu/cpufreq/longhaul.c index 03162dac627..cf48cdd6907 100644 --- a/arch/x86/kernel/cpu/cpufreq/longhaul.c +++ b/arch/x86/kernel/cpu/cpufreq/longhaul.c @@ -444,7 +444,7 @@ static int __cpuinit longhaul_get_ranges(void) return -EINVAL; } /* Get max multiplier - as we always did. - * Longhaul MSR is usefull only when voltage scaling is enabled. + * Longhaul MSR is useful only when voltage scaling is enabled. * C3 is booting at max anyway. */ maxmult = mult; /* Get min multiplier */ @@ -1011,7 +1011,7 @@ static void __exit longhaul_exit(void) * trigger frequency transition in some cases. */ module_param(disable_acpi_c3, int, 0644); MODULE_PARM_DESC(disable_acpi_c3, "Don't use ACPI C3 support"); -/* Change CPU voltage with frequency. Very usefull to save +/* Change CPU voltage with frequency. Very useful to save * power, but most VIA C3 processors aren't supporting it. */ module_param(scale_voltage, int, 0644); MODULE_PARM_DESC(scale_voltage, "Scale voltage of processor"); diff --git a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c index bd1cac747f6..52c93648e49 100644 --- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c +++ b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c @@ -158,9 +158,9 @@ static unsigned int cpufreq_p4_get_frequency(struct cpuinfo_x86 *c) { if (c->x86 == 0x06) { if (cpu_has(c, X86_FEATURE_EST)) - printk(KERN_WARNING PFX "Warning: EST-capable CPU " - "detected. The acpi-cpufreq module offers " - "voltage scaling in addition of frequency " + printk_once(KERN_WARNING PFX "Warning: EST-capable " + "CPU detected. The acpi-cpufreq module offers " + "voltage scaling in addition to frequency " "scaling. You should use that instead of " "p4-clockmod, if possible.\n"); switch (c->x86_model) { diff --git a/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c index 4f6f679f279..755a31e0f5b 100644 --- a/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c +++ b/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c @@ -195,7 +195,7 @@ static unsigned int pcc_get_freq(unsigned int cpu) cmd_incomplete: iowrite16(0, &pcch_hdr->status); spin_unlock(&pcc_lock); - return -EINVAL; + return 0; } static int pcc_cpufreq_target(struct cpufreq_policy *policy, @@ -315,8 +315,6 @@ static int __init pcc_cpufreq_do_osc(acpi_handle *handle) input.count = 4; input.pointer = in_params; - input.count = 4; - input.pointer = in_params; in_params[0].type = ACPI_TYPE_BUFFER; in_params[0].buffer.length = 16; in_params[0].buffer.pointer = OSC_UUID; diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c index 35c7e65e59b..2368e38327b 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c @@ -630,8 +630,7 @@ static void print_basics(struct powernow_k8_data *data) data->powernow_table[j].frequency/1000); } else { printk(KERN_INFO PFX - " %d : fid 0x%x (%d MHz), vid 0x%x\n", - j, + "fid 0x%x (%d MHz), vid 0x%x\n", data->powernow_table[j].index & 0xff, data->powernow_table[j].frequency/1000, data->powernow_table[j].index >> 8); @@ -1276,7 +1275,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) if (powernow_k8_cpu_init_acpi(data)) { /* - * Use the PSB BIOS structure. This is only availabe on + * Use the PSB BIOS structure. This is only available on * an UP version, and is deprecated by AMD. */ if (num_online_cpus() != 1) { @@ -1537,6 +1536,7 @@ static struct notifier_block cpb_nb = { static int __cpuinit powernowk8_init(void) { unsigned int i, supported_cpus = 0, cpu; + int rv; for_each_online_cpu(i) { int rc; @@ -1555,14 +1555,14 @@ static int __cpuinit powernowk8_init(void) cpb_capable = true; - register_cpu_notifier(&cpb_nb); - msrs = msrs_alloc(); if (!msrs) { printk(KERN_ERR "%s: Error allocating msrs!\n", __func__); return -ENOMEM; } + register_cpu_notifier(&cpb_nb); + rdmsr_on_cpus(cpu_online_mask, MSR_K7_HWCR, msrs); for_each_cpu(cpu, cpu_online_mask) { @@ -1574,7 +1574,13 @@ static int __cpuinit powernowk8_init(void) (cpb_enabled ? "on" : "off")); } - return cpufreq_register_driver(&cpufreq_amd64_driver); + rv = cpufreq_register_driver(&cpufreq_amd64_driver); + if (rv < 0 && boot_cpu_has(X86_FEATURE_CPB)) { + unregister_cpu_notifier(&cpb_nb); + msrs_free(msrs); + msrs = NULL; + } + return rv; } /* driver entry point for term */ diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c b/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c index 8abd869baab..91bc25b67bc 100644 --- a/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c +++ b/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c @@ -292,7 +292,7 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy) result = speedstep_smi_ownership(); if (result) { - dprintk("fails in aquiring ownership of a SMI interface.\n"); + dprintk("fails in acquiring ownership of a SMI interface.\n"); return -EINVAL; } @@ -360,7 +360,7 @@ static int speedstep_resume(struct cpufreq_policy *policy) int result = speedstep_smi_ownership(); if (result) - dprintk("fails in re-aquiring ownership of a SMI interface.\n"); + dprintk("fails in re-acquiring ownership of a SMI interface.\n"); return result; } diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index d16c2c53d6b..df86bc8c859 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -276,14 +276,13 @@ static void __cpuinit intel_workarounds(struct cpuinfo_x86 *c) static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c) { -#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64) +#ifdef CONFIG_NUMA unsigned node; int cpu = smp_processor_id(); - int apicid = cpu_has_apic ? hard_smp_processor_id() : c->apicid; /* Don't do the funky fallback heuristics the AMD version employs for now. */ - node = apicid_to_node[apicid]; + node = numa_cpu_node(cpu); if (node == NUMA_NO_NODE || !node_online(node)) { /* reuse the value from init_cpu_to_node() */ node = cpu_to_node(cpu); diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index ec2c19a7b8e..1ce1af2899d 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -304,8 +304,9 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax, struct _cache_attr { struct attribute attr; - ssize_t (*show)(struct _cpuid4_info *, char *); - ssize_t (*store)(struct _cpuid4_info *, const char *, size_t count); + ssize_t (*show)(struct _cpuid4_info *, char *, unsigned int); + ssize_t (*store)(struct _cpuid4_info *, const char *, size_t count, + unsigned int); }; #ifdef CONFIG_AMD_NB @@ -400,7 +401,8 @@ static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf, #define SHOW_CACHE_DISABLE(slot) \ static ssize_t \ -show_cache_disable_##slot(struct _cpuid4_info *this_leaf, char *buf) \ +show_cache_disable_##slot(struct _cpuid4_info *this_leaf, char *buf, \ + unsigned int cpu) \ { \ return show_cache_disable(this_leaf, buf, slot); \ } @@ -512,7 +514,8 @@ static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf, #define STORE_CACHE_DISABLE(slot) \ static ssize_t \ store_cache_disable_##slot(struct _cpuid4_info *this_leaf, \ - const char *buf, size_t count) \ + const char *buf, size_t count, \ + unsigned int cpu) \ { \ return store_cache_disable(this_leaf, buf, count, slot); \ } @@ -524,6 +527,39 @@ static struct _cache_attr cache_disable_0 = __ATTR(cache_disable_0, 0644, static struct _cache_attr cache_disable_1 = __ATTR(cache_disable_1, 0644, show_cache_disable_1, store_cache_disable_1); +static ssize_t +show_subcaches(struct _cpuid4_info *this_leaf, char *buf, unsigned int cpu) +{ + if (!this_leaf->l3 || !amd_nb_has_feature(AMD_NB_L3_PARTITIONING)) + return -EINVAL; + + return sprintf(buf, "%x\n", amd_get_subcaches(cpu)); +} + +static ssize_t +store_subcaches(struct _cpuid4_info *this_leaf, const char *buf, size_t count, + unsigned int cpu) +{ + unsigned long val; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (!this_leaf->l3 || !amd_nb_has_feature(AMD_NB_L3_PARTITIONING)) + return -EINVAL; + + if (strict_strtoul(buf, 16, &val) < 0) + return -EINVAL; + + if (amd_set_subcaches(cpu, val)) + return -EINVAL; + + return count; +} + +static struct _cache_attr subcaches = + __ATTR(subcaches, 0644, show_subcaches, store_subcaches); + #else /* CONFIG_AMD_NB */ #define amd_init_l3_cache(x, y) #endif /* CONFIG_AMD_NB */ @@ -532,9 +568,9 @@ static int __cpuinit cpuid4_cache_lookup_regs(int index, struct _cpuid4_info_regs *this_leaf) { - union _cpuid4_leaf_eax eax; - union _cpuid4_leaf_ebx ebx; - union _cpuid4_leaf_ecx ecx; + union _cpuid4_leaf_eax eax; + union _cpuid4_leaf_ebx ebx; + union _cpuid4_leaf_ecx ecx; unsigned edx; if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { @@ -732,11 +768,11 @@ static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index) struct cpuinfo_x86 *c = &cpu_data(cpu); if ((index == 3) && (c->x86_vendor == X86_VENDOR_AMD)) { - for_each_cpu(i, c->llc_shared_map) { + for_each_cpu(i, cpu_llc_shared_mask(cpu)) { if (!per_cpu(ici_cpuid4_info, i)) continue; this_leaf = CPUID4_INFO_IDX(i, index); - for_each_cpu(sibling, c->llc_shared_map) { + for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) { if (!cpu_online(sibling)) continue; set_bit(sibling, this_leaf->shared_cpu_map); @@ -870,8 +906,8 @@ static DEFINE_PER_CPU(struct _index_kobject *, ici_index_kobject); #define INDEX_KOBJECT_PTR(x, y) (&((per_cpu(ici_index_kobject, x))[y])) #define show_one_plus(file_name, object, val) \ -static ssize_t show_##file_name \ - (struct _cpuid4_info *this_leaf, char *buf) \ +static ssize_t show_##file_name(struct _cpuid4_info *this_leaf, char *buf, \ + unsigned int cpu) \ { \ return sprintf(buf, "%lu\n", (unsigned long)this_leaf->object + val); \ } @@ -882,7 +918,8 @@ show_one_plus(physical_line_partition, ebx.split.physical_line_partition, 1); show_one_plus(ways_of_associativity, ebx.split.ways_of_associativity, 1); show_one_plus(number_of_sets, ecx.split.number_of_sets, 1); -static ssize_t show_size(struct _cpuid4_info *this_leaf, char *buf) +static ssize_t show_size(struct _cpuid4_info *this_leaf, char *buf, + unsigned int cpu) { return sprintf(buf, "%luK\n", this_leaf->size / 1024); } @@ -906,17 +943,20 @@ static ssize_t show_shared_cpu_map_func(struct _cpuid4_info *this_leaf, return n; } -static inline ssize_t show_shared_cpu_map(struct _cpuid4_info *leaf, char *buf) +static inline ssize_t show_shared_cpu_map(struct _cpuid4_info *leaf, char *buf, + unsigned int cpu) { return show_shared_cpu_map_func(leaf, 0, buf); } -static inline ssize_t show_shared_cpu_list(struct _cpuid4_info *leaf, char *buf) +static inline ssize_t show_shared_cpu_list(struct _cpuid4_info *leaf, char *buf, + unsigned int cpu) { return show_shared_cpu_map_func(leaf, 1, buf); } -static ssize_t show_type(struct _cpuid4_info *this_leaf, char *buf) +static ssize_t show_type(struct _cpuid4_info *this_leaf, char *buf, + unsigned int cpu) { switch (this_leaf->eax.split.type) { case CACHE_TYPE_DATA: @@ -974,6 +1014,9 @@ static struct attribute ** __cpuinit amd_l3_attrs(void) if (amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE)) n += 2; + if (amd_nb_has_feature(AMD_NB_L3_PARTITIONING)) + n += 1; + attrs = kzalloc(n * sizeof (struct attribute *), GFP_KERNEL); if (attrs == NULL) return attrs = default_attrs; @@ -986,6 +1029,9 @@ static struct attribute ** __cpuinit amd_l3_attrs(void) attrs[n++] = &cache_disable_1.attr; } + if (amd_nb_has_feature(AMD_NB_L3_PARTITIONING)) + attrs[n++] = &subcaches.attr; + return attrs; } #endif @@ -998,7 +1044,7 @@ static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buf) ret = fattr->show ? fattr->show(CPUID4_INFO_IDX(this_leaf->cpu, this_leaf->index), - buf) : + buf, this_leaf->cpu) : 0; return ret; } @@ -1012,7 +1058,7 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr, ret = fattr->store ? fattr->store(CPUID4_INFO_IDX(this_leaf->cpu, this_leaf->index), - buf, count) : + buf, count, this_leaf->cpu) : 0; return ret; } diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mcheck/mce-apei.c index 8209472b27a..83930deec3c 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-apei.c +++ b/arch/x86/kernel/cpu/mcheck/mce-apei.c @@ -106,24 +106,34 @@ int apei_write_mce(struct mce *m) ssize_t apei_read_mce(struct mce *m, u64 *record_id) { struct cper_mce_record rcd; - ssize_t len; - - len = erst_read_next(&rcd.hdr, sizeof(rcd)); - if (len <= 0) - return len; - /* Can not skip other records in storage via ERST unless clear them */ - else if (len != sizeof(rcd) || - uuid_le_cmp(rcd.hdr.creator_id, CPER_CREATOR_MCE)) { - if (printk_ratelimit()) - pr_warning( - "MCE-APEI: Can not skip the unknown record in ERST"); - return -EIO; - } - + int rc, pos; + + rc = erst_get_record_id_begin(&pos); + if (rc) + return rc; +retry: + rc = erst_get_record_id_next(&pos, record_id); + if (rc) + goto out; + /* no more record */ + if (*record_id == APEI_ERST_INVALID_RECORD_ID) + goto out; + rc = erst_read(*record_id, &rcd.hdr, sizeof(rcd)); + /* someone else has cleared the record, try next one */ + if (rc == -ENOENT) + goto retry; + else if (rc < 0) + goto out; + /* try to skip other type records in storage */ + else if (rc != sizeof(rcd) || + uuid_le_cmp(rcd.hdr.creator_id, CPER_CREATOR_MCE)) + goto retry; memcpy(m, &rcd.mce, sizeof(*m)); - *record_id = rcd.hdr.record_id; + rc = sizeof(*m); +out: + erst_get_record_id_end(); - return sizeof(*m); + return rc; } /* Check whether there is record in ERST */ diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c index a7797197956..0ed633c5048 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-inject.c +++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c @@ -32,7 +32,7 @@ static void inject_mce(struct mce *m) { struct mce *i = &per_cpu(injectm, m->extcpu); - /* Make sure noone reads partially written injectm */ + /* Make sure no one reads partially written injectm */ i->finished = 0; mb(); m->finished = 0; diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index d916183b7f9..3385ea26f68 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -21,6 +21,7 @@ #include <linux/percpu.h> #include <linux/string.h> #include <linux/sysdev.h> +#include <linux/syscore_ops.h> #include <linux/delay.h> #include <linux/ctype.h> #include <linux/sched.h> @@ -881,7 +882,7 @@ reset: * Check if the address reported by the CPU is in a format we can parse. * It would be possible to add code for most other cases, but all would * be somewhat complicated (e.g. segment offset would require an instruction - * parser). So only support physical addresses upto page granuality for now. + * parser). So only support physical addresses up to page granuality for now. */ static int mce_usable_address(struct mce *m) { @@ -1625,7 +1626,7 @@ out: static unsigned int mce_poll(struct file *file, poll_table *wait) { poll_wait(file, &mce_wait, wait); - if (rcu_dereference_check_mce(mcelog.next)) + if (rcu_access_index(mcelog.next)) return POLLIN | POLLRDNORM; if (!mce_apei_read_done && apei_check_mce()) return POLLIN | POLLRDNORM; @@ -1749,14 +1750,14 @@ static int mce_disable_error_reporting(void) return 0; } -static int mce_suspend(struct sys_device *dev, pm_message_t state) +static int mce_suspend(void) { return mce_disable_error_reporting(); } -static int mce_shutdown(struct sys_device *dev) +static void mce_shutdown(void) { - return mce_disable_error_reporting(); + mce_disable_error_reporting(); } /* @@ -1764,14 +1765,18 @@ static int mce_shutdown(struct sys_device *dev) * Only one CPU is active at this time, the others get re-added later using * CPU hotplug: */ -static int mce_resume(struct sys_device *dev) +static void mce_resume(void) { __mcheck_cpu_init_generic(); __mcheck_cpu_init_vendor(__this_cpu_ptr(&cpu_info)); - - return 0; } +static struct syscore_ops mce_syscore_ops = { + .suspend = mce_suspend, + .shutdown = mce_shutdown, + .resume = mce_resume, +}; + static void mce_cpu_restart(void *data) { del_timer_sync(&__get_cpu_var(mce_timer)); @@ -1808,9 +1813,6 @@ static void mce_enable_ce(void *all) } static struct sysdev_class mce_sysclass = { - .suspend = mce_suspend, - .shutdown = mce_shutdown, - .resume = mce_resume, .name = "machinecheck", }; @@ -2139,6 +2141,7 @@ static __init int mcheck_init_device(void) return err; } + register_syscore_ops(&mce_syscore_ops); register_hotcpu_notifier(&mce_cpu_notifier); misc_register(&mce_log_device); diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 5bf2fac52ac..167f97b5596 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -527,15 +527,12 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) int i, err = 0; struct threshold_bank *b = NULL; char name[32]; -#ifdef CONFIG_SMP - struct cpuinfo_x86 *c = &cpu_data(cpu); -#endif sprintf(name, "threshold_bank%i", bank); #ifdef CONFIG_SMP if (cpu_data(cpu).cpu_core_id && shared_bank[bank]) { /* symlink */ - i = cpumask_first(c->llc_shared_map); + i = cpumask_first(cpu_llc_shared_mask(cpu)); /* first core not up yet */ if (cpu_data(i).cpu_core_id) @@ -555,7 +552,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) if (err) goto out; - cpumask_copy(b->cpus, c->llc_shared_map); + cpumask_copy(b->cpus, cpu_llc_shared_mask(cpu)); per_cpu(threshold_banks, cpu)[bank] = b; goto out; diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 9f27228ceff..a71efcdbb09 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -1,6 +1,6 @@ /* * This only handles 32bit MTRR on 32bit hosts. This is strictly wrong - * because MTRRs can span upto 40 bits (36bits on most modern x86) + * because MTRRs can span up to 40 bits (36bits on most modern x86) */ #define DEBUG diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index bebabec5b44..929739a653d 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -45,6 +45,7 @@ #include <linux/cpu.h> #include <linux/pci.h> #include <linux/smp.h> +#include <linux/syscore_ops.h> #include <asm/processor.h> #include <asm/e820.h> @@ -292,14 +293,24 @@ set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type typ /* * HACK! - * We use this same function to initialize the mtrrs on boot. - * The state of the boot cpu's mtrrs has been saved, and we want - * to replicate across all the APs. - * If we're doing that @reg is set to something special... + * + * We use this same function to initialize the mtrrs during boot, + * resume, runtime cpu online and on an explicit request to set a + * specific MTRR. + * + * During boot or suspend, the state of the boot cpu's mtrrs has been + * saved, and we want to replicate that across all the cpus that come + * online (either at the end of boot or resume or during a runtime cpu + * online). If we're doing that, @reg is set to something special and on + * this cpu we still do mtrr_if->set_all(). During boot/resume, this + * is unnecessary if at this point we are still on the cpu that started + * the boot/resume sequence. But there is no guarantee that we are still + * on the same cpu. So we do mtrr_if->set_all() on this cpu aswell to be + * sure that we are in sync with everyone else. */ if (reg != ~0U) mtrr_if->set(reg, base, size, type); - else if (!mtrr_aps_delayed_init) + else mtrr_if->set_all(); /* Wait for the others */ @@ -630,7 +641,7 @@ struct mtrr_value { static struct mtrr_value mtrr_value[MTRR_MAX_VAR_RANGES]; -static int mtrr_save(struct sys_device *sysdev, pm_message_t state) +static int mtrr_save(void) { int i; @@ -642,7 +653,7 @@ static int mtrr_save(struct sys_device *sysdev, pm_message_t state) return 0; } -static int mtrr_restore(struct sys_device *sysdev) +static void mtrr_restore(void) { int i; @@ -653,12 +664,11 @@ static int mtrr_restore(struct sys_device *sysdev) mtrr_value[i].ltype); } } - return 0; } -static struct sysdev_driver mtrr_sysdev_driver = { +static struct syscore_ops mtrr_syscore_ops = { .suspend = mtrr_save, .resume = mtrr_restore, }; @@ -839,7 +849,7 @@ static int __init mtrr_init_finialize(void) * TBD: is there any system with such CPU which supports * suspend/resume? If no, we should remove the code. */ - sysdev_driver_register(&cpu_sysdev_class, &mtrr_sysdev_driver); + register_syscore_ops(&mtrr_syscore_ops); return 0; } diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 9d977a2ea69..e638689279d 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -30,6 +30,7 @@ #include <asm/stacktrace.h> #include <asm/nmi.h> #include <asm/compat.h> +#include <asm/smp.h> #if 0 #undef wrmsrl @@ -93,6 +94,8 @@ struct amd_nb { struct event_constraint event_constraints[X86_PMC_IDX_MAX]; }; +struct intel_percore; + #define MAX_LBR_ENTRIES 16 struct cpu_hw_events { @@ -128,6 +131,13 @@ struct cpu_hw_events { struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES]; /* + * Intel percore register state. + * Coordinate shared resources between HT threads. + */ + int percore_used; /* Used by this CPU? */ + struct intel_percore *per_core; + + /* * AMD specific bits */ struct amd_nb *amd_nb; @@ -166,7 +176,7 @@ struct cpu_hw_events { /* * Constraint on the Event code + UMask */ -#define PEBS_EVENT_CONSTRAINT(c, n) \ +#define INTEL_UEVENT_CONSTRAINT(c, n) \ EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK) #define EVENT_CONSTRAINT_END \ @@ -175,6 +185,28 @@ struct cpu_hw_events { #define for_each_event_constraint(e, c) \ for ((e) = (c); (e)->weight; (e)++) +/* + * Extra registers for specific events. + * Some events need large masks and require external MSRs. + * Define a mapping to these extra registers. + */ +struct extra_reg { + unsigned int event; + unsigned int msr; + u64 config_mask; + u64 valid_mask; +}; + +#define EVENT_EXTRA_REG(e, ms, m, vm) { \ + .event = (e), \ + .msr = (ms), \ + .config_mask = (m), \ + .valid_mask = (vm), \ + } +#define INTEL_EVENT_EXTRA_REG(event, msr, vm) \ + EVENT_EXTRA_REG(event, msr, ARCH_PERFMON_EVENTSEL_EVENT, vm) +#define EVENT_EXTRA_END EVENT_EXTRA_REG(0, 0, 0, 0) + union perf_capabilities { struct { u64 lbr_format : 6; @@ -219,6 +251,7 @@ struct x86_pmu { void (*put_event_constraints)(struct cpu_hw_events *cpuc, struct perf_event *event); struct event_constraint *event_constraints; + struct event_constraint *percore_constraints; void (*quirks)(void); int perfctr_second_write; @@ -247,6 +280,11 @@ struct x86_pmu { */ unsigned long lbr_tos, lbr_from, lbr_to; /* MSR base regs */ int lbr_nr; /* hardware stack size */ + + /* + * Extra registers for events + */ + struct extra_reg *extra_regs; }; static struct x86_pmu x86_pmu __read_mostly; @@ -271,6 +309,10 @@ static u64 __read_mostly hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX]; +static u64 __read_mostly hw_cache_extra_regs + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX]; /* * Propagate event elapsed time into the generic event. @@ -298,7 +340,7 @@ x86_perf_event_update(struct perf_event *event) */ again: prev_raw_count = local64_read(&hwc->prev_count); - rdmsrl(hwc->event_base + idx, new_raw_count); + rdmsrl(hwc->event_base, new_raw_count); if (local64_cmpxchg(&hwc->prev_count, prev_raw_count, new_raw_count) != prev_raw_count) @@ -321,6 +363,49 @@ again: return new_raw_count; } +/* using X86_FEATURE_PERFCTR_CORE to later implement ALTERNATIVE() here */ +static inline int x86_pmu_addr_offset(int index) +{ + if (boot_cpu_has(X86_FEATURE_PERFCTR_CORE)) + return index << 1; + return index; +} + +static inline unsigned int x86_pmu_config_addr(int index) +{ + return x86_pmu.eventsel + x86_pmu_addr_offset(index); +} + +static inline unsigned int x86_pmu_event_addr(int index) +{ + return x86_pmu.perfctr + x86_pmu_addr_offset(index); +} + +/* + * Find and validate any extra registers to set up. + */ +static int x86_pmu_extra_regs(u64 config, struct perf_event *event) +{ + struct extra_reg *er; + + event->hw.extra_reg = 0; + event->hw.extra_config = 0; + + if (!x86_pmu.extra_regs) + return 0; + + for (er = x86_pmu.extra_regs; er->msr; er++) { + if (er->event != (config & er->config_mask)) + continue; + if (event->attr.config1 & ~er->valid_mask) + return -EINVAL; + event->hw.extra_reg = er->msr; + event->hw.extra_config = event->attr.config1; + break; + } + return 0; +} + static atomic_t active_events; static DEFINE_MUTEX(pmc_reserve_mutex); @@ -331,12 +416,12 @@ static bool reserve_pmc_hardware(void) int i; for (i = 0; i < x86_pmu.num_counters; i++) { - if (!reserve_perfctr_nmi(x86_pmu.perfctr + i)) + if (!reserve_perfctr_nmi(x86_pmu_event_addr(i))) goto perfctr_fail; } for (i = 0; i < x86_pmu.num_counters; i++) { - if (!reserve_evntsel_nmi(x86_pmu.eventsel + i)) + if (!reserve_evntsel_nmi(x86_pmu_config_addr(i))) goto eventsel_fail; } @@ -344,13 +429,13 @@ static bool reserve_pmc_hardware(void) eventsel_fail: for (i--; i >= 0; i--) - release_evntsel_nmi(x86_pmu.eventsel + i); + release_evntsel_nmi(x86_pmu_config_addr(i)); i = x86_pmu.num_counters; perfctr_fail: for (i--; i >= 0; i--) - release_perfctr_nmi(x86_pmu.perfctr + i); + release_perfctr_nmi(x86_pmu_event_addr(i)); return false; } @@ -360,8 +445,8 @@ static void release_pmc_hardware(void) int i; for (i = 0; i < x86_pmu.num_counters; i++) { - release_perfctr_nmi(x86_pmu.perfctr + i); - release_evntsel_nmi(x86_pmu.eventsel + i); + release_perfctr_nmi(x86_pmu_event_addr(i)); + release_evntsel_nmi(x86_pmu_config_addr(i)); } } @@ -382,7 +467,7 @@ static bool check_hw_exists(void) * complain and bail. */ for (i = 0; i < x86_pmu.num_counters; i++) { - reg = x86_pmu.eventsel + i; + reg = x86_pmu_config_addr(i); ret = rdmsrl_safe(reg, &val); if (ret) goto msr_fail; @@ -407,20 +492,25 @@ static bool check_hw_exists(void) * that don't trap on the MSR access and always return 0s. */ val = 0xabcdUL; - ret = checking_wrmsrl(x86_pmu.perfctr, val); - ret |= rdmsrl_safe(x86_pmu.perfctr, &val_new); + ret = checking_wrmsrl(x86_pmu_event_addr(0), val); + ret |= rdmsrl_safe(x86_pmu_event_addr(0), &val_new); if (ret || val != val_new) goto msr_fail; return true; bios_fail: - printk(KERN_CONT "Broken BIOS detected, using software events only.\n"); + /* + * We still allow the PMU driver to operate: + */ + printk(KERN_CONT "Broken BIOS detected, complain to your hardware vendor.\n"); printk(KERN_ERR FW_BUG "the BIOS has corrupted hw-PMU resources (MSR %x is %Lx)\n", reg, val); - return false; + + return true; msr_fail: printk(KERN_CONT "Broken PMU hardware detected, using software events only.\n"); + return false; } @@ -442,8 +532,9 @@ static inline int x86_pmu_initialized(void) } static inline int -set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event_attr *attr) +set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event *event) { + struct perf_event_attr *attr = &event->attr; unsigned int cache_type, cache_op, cache_result; u64 config, val; @@ -470,8 +561,8 @@ set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event_attr *attr) return -EINVAL; hwc->config |= val; - - return 0; + attr->config1 = hw_cache_extra_regs[cache_type][cache_op][cache_result]; + return x86_pmu_extra_regs(val, event); } static int x86_setup_perfctr(struct perf_event *event) @@ -495,11 +586,15 @@ static int x86_setup_perfctr(struct perf_event *event) return -EOPNOTSUPP; } + /* + * Do not allow config1 (extended registers) to propagate, + * there's no sane user-space generalization yet: + */ if (attr->type == PERF_TYPE_RAW) return 0; if (attr->type == PERF_TYPE_HW_CACHE) - return set_ext_hw_attr(hwc, attr); + return set_ext_hw_attr(hwc, event); if (attr->config >= x86_pmu.max_events) return -EINVAL; @@ -518,8 +613,8 @@ static int x86_setup_perfctr(struct perf_event *event) /* * Branch tracing: */ - if ((attr->config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS) && - (hwc->sample_period == 1)) { + if (attr->config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS && + !attr->freq && hwc->sample_period == 1) { /* BTS is not supported by this architecture. */ if (!x86_pmu.bts_active) return -EOPNOTSUPP; @@ -617,11 +712,11 @@ static void x86_pmu_disable_all(void) if (!test_bit(idx, cpuc->active_mask)) continue; - rdmsrl(x86_pmu.eventsel + idx, val); + rdmsrl(x86_pmu_config_addr(idx), val); if (!(val & ARCH_PERFMON_EVENTSEL_ENABLE)) continue; val &= ~ARCH_PERFMON_EVENTSEL_ENABLE; - wrmsrl(x86_pmu.eventsel + idx, val); + wrmsrl(x86_pmu_config_addr(idx), val); } } @@ -642,21 +737,26 @@ static void x86_pmu_disable(struct pmu *pmu) x86_pmu.disable_all(); } +static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, + u64 enable_mask) +{ + if (hwc->extra_reg) + wrmsrl(hwc->extra_reg, hwc->extra_config); + wrmsrl(hwc->config_base, hwc->config | enable_mask); +} + static void x86_pmu_enable_all(int added) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); int idx; for (idx = 0; idx < x86_pmu.num_counters; idx++) { - struct perf_event *event = cpuc->events[idx]; - u64 val; + struct hw_perf_event *hwc = &cpuc->events[idx]->hw; if (!test_bit(idx, cpuc->active_mask)) continue; - val = event->hw.config; - val |= ARCH_PERFMON_EVENTSEL_ENABLE; - wrmsrl(x86_pmu.eventsel + idx, val); + __x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE); } } @@ -821,15 +921,10 @@ static inline void x86_assign_hw_event(struct perf_event *event, hwc->event_base = 0; } else if (hwc->idx >= X86_PMC_IDX_FIXED) { hwc->config_base = MSR_ARCH_PERFMON_FIXED_CTR_CTRL; - /* - * We set it so that event_base + idx in wrmsr/rdmsr maps to - * MSR_ARCH_PERFMON_FIXED_CTR0 ... CTR2: - */ - hwc->event_base = - MSR_ARCH_PERFMON_FIXED_CTR0 - X86_PMC_IDX_FIXED; + hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0 + (hwc->idx - X86_PMC_IDX_FIXED); } else { - hwc->config_base = x86_pmu.eventsel; - hwc->event_base = x86_pmu.perfctr; + hwc->config_base = x86_pmu_config_addr(hwc->idx); + hwc->event_base = x86_pmu_event_addr(hwc->idx); } } @@ -915,17 +1010,11 @@ static void x86_pmu_enable(struct pmu *pmu) x86_pmu.enable_all(added); } -static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, - u64 enable_mask) -{ - wrmsrl(hwc->config_base + hwc->idx, hwc->config | enable_mask); -} - static inline void x86_pmu_disable_event(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; - wrmsrl(hwc->config_base + hwc->idx, hwc->config); + wrmsrl(hwc->config_base, hwc->config); } static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left); @@ -978,7 +1067,7 @@ x86_perf_event_set_period(struct perf_event *event) */ local64_set(&hwc->prev_count, (u64)-left); - wrmsrl(hwc->event_base + idx, (u64)(-left) & x86_pmu.cntval_mask); + wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask); /* * Due to erratum on certan cpu we need @@ -986,7 +1075,7 @@ x86_perf_event_set_period(struct perf_event *event) * is updated properly */ if (x86_pmu.perfctr_second_write) { - wrmsrl(hwc->event_base + idx, + wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask); } @@ -1029,7 +1118,7 @@ static int x86_pmu_add(struct perf_event *event, int flags) /* * If group events scheduling transaction was started, - * skip the schedulability test here, it will be peformed + * skip the schedulability test here, it will be performed * at commit time (->commit_txn) as a whole */ if (cpuc->group_flag & PERF_EVENT_TXN) @@ -1113,8 +1202,8 @@ void perf_event_print_debug(void) pr_info("CPU#%d: active: %016llx\n", cpu, *(u64 *)cpuc->active_mask); for (idx = 0; idx < x86_pmu.num_counters; idx++) { - rdmsrl(x86_pmu.eventsel + idx, pmc_ctrl); - rdmsrl(x86_pmu.perfctr + idx, pmc_count); + rdmsrl(x86_pmu_config_addr(idx), pmc_ctrl); + rdmsrl(x86_pmu_event_addr(idx), pmc_count); prev_left = per_cpu(pmc_prev_left[idx], cpu); @@ -1199,6 +1288,16 @@ static int x86_pmu_handle_irq(struct pt_regs *regs) cpuc = &__get_cpu_var(cpu_hw_events); + /* + * Some chipsets need to unmask the LVTPC in a particular spot + * inside the nmi handler. As a result, the unmasking was pushed + * into all the nmi handlers. + * + * This generic handler doesn't seem to have any issues where the + * unmasking occurs so it was left at the top. + */ + apic_write(APIC_LVTPC, APIC_DM_NMI); + for (idx = 0; idx < x86_pmu.num_counters; idx++) { if (!test_bit(idx, cpuc->active_mask)) { /* @@ -1285,8 +1384,6 @@ perf_event_nmi_handler(struct notifier_block *self, return NOTIFY_DONE; } - apic_write(APIC_LVTPC, APIC_DM_NMI); - handled = x86_pmu.handle_irq(args->regs); if (!handled) return NOTIFY_DONE; @@ -1389,7 +1486,7 @@ static void __init pmu_check_apic(void) pr_info("no hardware sampling interrupt available.\n"); } -int __init init_hw_perf_events(void) +static int __init init_hw_perf_events(void) { struct event_constraint *c; int err; @@ -1608,7 +1705,7 @@ out: return ret; } -int x86_pmu_event_init(struct perf_event *event) +static int x86_pmu_event_init(struct perf_event *event) { struct pmu *tmp; int err; @@ -1710,7 +1807,7 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs) perf_callchain_store(entry, regs->ip); - dump_trace(NULL, regs, NULL, &backtrace_ops, entry); + dump_trace(NULL, regs, NULL, 0, &backtrace_ops, entry); } #ifdef CONFIG_COMPAT diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index 67e2202a603..cf4e369cea6 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -8,7 +8,7 @@ static __initconst const u64 amd_hw_cache_event_ids [ C(L1D) ] = { [ C(OP_READ) ] = { [ C(RESULT_ACCESS) ] = 0x0040, /* Data Cache Accesses */ - [ C(RESULT_MISS) ] = 0x0041, /* Data Cache Misses */ + [ C(RESULT_MISS) ] = 0x0141, /* Data Cache Misses */ }, [ C(OP_WRITE) ] = { [ C(RESULT_ACCESS) ] = 0x0142, /* Data Cache Refills :system */ @@ -127,6 +127,11 @@ static int amd_pmu_hw_config(struct perf_event *event) /* * AMD64 events are detected based on their event codes. */ +static inline unsigned int amd_get_event_code(struct hw_perf_event *hwc) +{ + return ((hwc->config >> 24) & 0x0f00) | (hwc->config & 0x00ff); +} + static inline int amd_is_nb_event(struct hw_perf_event *hwc) { return (hwc->config & 0xe0) == 0xe0; @@ -385,13 +390,195 @@ static __initconst const struct x86_pmu amd_pmu = { .cpu_dead = amd_pmu_cpu_dead, }; +/* AMD Family 15h */ + +#define AMD_EVENT_TYPE_MASK 0x000000F0ULL + +#define AMD_EVENT_FP 0x00000000ULL ... 0x00000010ULL +#define AMD_EVENT_LS 0x00000020ULL ... 0x00000030ULL +#define AMD_EVENT_DC 0x00000040ULL ... 0x00000050ULL +#define AMD_EVENT_CU 0x00000060ULL ... 0x00000070ULL +#define AMD_EVENT_IC_DE 0x00000080ULL ... 0x00000090ULL +#define AMD_EVENT_EX_LS 0x000000C0ULL +#define AMD_EVENT_DE 0x000000D0ULL +#define AMD_EVENT_NB 0x000000E0ULL ... 0x000000F0ULL + +/* + * AMD family 15h event code/PMC mappings: + * + * type = event_code & 0x0F0: + * + * 0x000 FP PERF_CTL[5:3] + * 0x010 FP PERF_CTL[5:3] + * 0x020 LS PERF_CTL[5:0] + * 0x030 LS PERF_CTL[5:0] + * 0x040 DC PERF_CTL[5:0] + * 0x050 DC PERF_CTL[5:0] + * 0x060 CU PERF_CTL[2:0] + * 0x070 CU PERF_CTL[2:0] + * 0x080 IC/DE PERF_CTL[2:0] + * 0x090 IC/DE PERF_CTL[2:0] + * 0x0A0 --- + * 0x0B0 --- + * 0x0C0 EX/LS PERF_CTL[5:0] + * 0x0D0 DE PERF_CTL[2:0] + * 0x0E0 NB NB_PERF_CTL[3:0] + * 0x0F0 NB NB_PERF_CTL[3:0] + * + * Exceptions: + * + * 0x000 FP PERF_CTL[3], PERF_CTL[5:3] (*) + * 0x003 FP PERF_CTL[3] + * 0x004 FP PERF_CTL[3], PERF_CTL[5:3] (*) + * 0x00B FP PERF_CTL[3] + * 0x00D FP PERF_CTL[3] + * 0x023 DE PERF_CTL[2:0] + * 0x02D LS PERF_CTL[3] + * 0x02E LS PERF_CTL[3,0] + * 0x043 CU PERF_CTL[2:0] + * 0x045 CU PERF_CTL[2:0] + * 0x046 CU PERF_CTL[2:0] + * 0x054 CU PERF_CTL[2:0] + * 0x055 CU PERF_CTL[2:0] + * 0x08F IC PERF_CTL[0] + * 0x187 DE PERF_CTL[0] + * 0x188 DE PERF_CTL[0] + * 0x0DB EX PERF_CTL[5:0] + * 0x0DC LS PERF_CTL[5:0] + * 0x0DD LS PERF_CTL[5:0] + * 0x0DE LS PERF_CTL[5:0] + * 0x0DF LS PERF_CTL[5:0] + * 0x1D6 EX PERF_CTL[5:0] + * 0x1D8 EX PERF_CTL[5:0] + * + * (*) depending on the umask all FPU counters may be used + */ + +static struct event_constraint amd_f15_PMC0 = EVENT_CONSTRAINT(0, 0x01, 0); +static struct event_constraint amd_f15_PMC20 = EVENT_CONSTRAINT(0, 0x07, 0); +static struct event_constraint amd_f15_PMC3 = EVENT_CONSTRAINT(0, 0x08, 0); +static struct event_constraint amd_f15_PMC30 = EVENT_CONSTRAINT(0, 0x09, 0); +static struct event_constraint amd_f15_PMC50 = EVENT_CONSTRAINT(0, 0x3F, 0); +static struct event_constraint amd_f15_PMC53 = EVENT_CONSTRAINT(0, 0x38, 0); + +static struct event_constraint * +amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + unsigned int event_code = amd_get_event_code(hwc); + + switch (event_code & AMD_EVENT_TYPE_MASK) { + case AMD_EVENT_FP: + switch (event_code) { + case 0x000: + if (!(hwc->config & 0x0000F000ULL)) + break; + if (!(hwc->config & 0x00000F00ULL)) + break; + return &amd_f15_PMC3; + case 0x004: + if (hweight_long(hwc->config & ARCH_PERFMON_EVENTSEL_UMASK) <= 1) + break; + return &amd_f15_PMC3; + case 0x003: + case 0x00B: + case 0x00D: + return &amd_f15_PMC3; + } + return &amd_f15_PMC53; + case AMD_EVENT_LS: + case AMD_EVENT_DC: + case AMD_EVENT_EX_LS: + switch (event_code) { + case 0x023: + case 0x043: + case 0x045: + case 0x046: + case 0x054: + case 0x055: + return &amd_f15_PMC20; + case 0x02D: + return &amd_f15_PMC3; + case 0x02E: + return &amd_f15_PMC30; + default: + return &amd_f15_PMC50; + } + case AMD_EVENT_CU: + case AMD_EVENT_IC_DE: + case AMD_EVENT_DE: + switch (event_code) { + case 0x08F: + case 0x187: + case 0x188: + return &amd_f15_PMC0; + case 0x0DB ... 0x0DF: + case 0x1D6: + case 0x1D8: + return &amd_f15_PMC50; + default: + return &amd_f15_PMC20; + } + case AMD_EVENT_NB: + /* not yet implemented */ + return &emptyconstraint; + default: + return &emptyconstraint; + } +} + +static __initconst const struct x86_pmu amd_pmu_f15h = { + .name = "AMD Family 15h", + .handle_irq = x86_pmu_handle_irq, + .disable_all = x86_pmu_disable_all, + .enable_all = x86_pmu_enable_all, + .enable = x86_pmu_enable_event, + .disable = x86_pmu_disable_event, + .hw_config = amd_pmu_hw_config, + .schedule_events = x86_schedule_events, + .eventsel = MSR_F15H_PERF_CTL, + .perfctr = MSR_F15H_PERF_CTR, + .event_map = amd_pmu_event_map, + .max_events = ARRAY_SIZE(amd_perfmon_event_map), + .num_counters = 6, + .cntval_bits = 48, + .cntval_mask = (1ULL << 48) - 1, + .apic = 1, + /* use highest bit to detect overflow */ + .max_period = (1ULL << 47) - 1, + .get_event_constraints = amd_get_event_constraints_f15h, + /* nortbridge counters not yet implemented: */ +#if 0 + .put_event_constraints = amd_put_event_constraints, + + .cpu_prepare = amd_pmu_cpu_prepare, + .cpu_starting = amd_pmu_cpu_starting, + .cpu_dead = amd_pmu_cpu_dead, +#endif +}; + static __init int amd_pmu_init(void) { /* Performance-monitoring supported from K7 and later: */ if (boot_cpu_data.x86 < 6) return -ENODEV; - x86_pmu = amd_pmu; + /* + * If core performance counter extensions exists, it must be + * family 15h, otherwise fail. See x86_pmu_addr_offset(). + */ + switch (boot_cpu_data.x86) { + case 0x15: + if (!cpu_has_perfctr_core) + return -ENODEV; + x86_pmu = amd_pmu_f15h; + break; + default: + if (cpu_has_perfctr_core) + return -ENODEV; + x86_pmu = amd_pmu; + break; + } /* Events are common for all AMDs */ memcpy(hw_cache_event_ids, amd_hw_cache_event_ids, diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 008835c1d79..447a28de6f0 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1,9 +1,31 @@ #ifdef CONFIG_CPU_SUP_INTEL +#define MAX_EXTRA_REGS 2 + +/* + * Per register state. + */ +struct er_account { + int ref; /* reference count */ + unsigned int extra_reg; /* extra MSR number */ + u64 extra_config; /* extra MSR config */ +}; + +/* + * Per core state + * This used to coordinate shared registers for HT threads. + */ +struct intel_percore { + raw_spinlock_t lock; /* protect structure */ + struct er_account regs[MAX_EXTRA_REGS]; + int refcnt; /* number of threads */ + unsigned core_id; +}; + /* * Intel PerfMon, used on Core and later. */ -static const u64 intel_perfmon_event_map[] = +static u64 intel_perfmon_event_map[PERF_COUNT_HW_MAX] __read_mostly = { [PERF_COUNT_HW_CPU_CYCLES] = 0x003c, [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, @@ -64,6 +86,18 @@ static struct event_constraint intel_nehalem_event_constraints[] = EVENT_CONSTRAINT_END }; +static struct extra_reg intel_nehalem_extra_regs[] = +{ + INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff), + EVENT_EXTRA_END +}; + +static struct event_constraint intel_nehalem_percore_constraints[] = +{ + INTEL_EVENT_CONSTRAINT(0xb7, 0), + EVENT_CONSTRAINT_END +}; + static struct event_constraint intel_westmere_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ @@ -76,6 +110,33 @@ static struct event_constraint intel_westmere_event_constraints[] = EVENT_CONSTRAINT_END }; +static struct event_constraint intel_snb_event_constraints[] = +{ + FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ + FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ + /* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */ + INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.PENDING */ + INTEL_EVENT_CONSTRAINT(0xb7, 0x1), /* OFF_CORE_RESPONSE_0 */ + INTEL_EVENT_CONSTRAINT(0xbb, 0x8), /* OFF_CORE_RESPONSE_1 */ + INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */ + INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */ + EVENT_CONSTRAINT_END +}; + +static struct extra_reg intel_westmere_extra_regs[] = +{ + INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff), + INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0xffff), + EVENT_EXTRA_END +}; + +static struct event_constraint intel_westmere_percore_constraints[] = +{ + INTEL_EVENT_CONSTRAINT(0xb7, 0), + INTEL_EVENT_CONSTRAINT(0xbb, 0), + EVENT_CONSTRAINT_END +}; + static struct event_constraint intel_gen_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ @@ -89,6 +150,103 @@ static u64 intel_pmu_event_map(int hw_event) return intel_perfmon_event_map[hw_event]; } +static __initconst const u64 snb_hw_cache_event_ids + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(L1D) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0xf1d0, /* MEM_UOP_RETIRED.LOADS */ + [ C(RESULT_MISS) ] = 0x0151, /* L1D.REPLACEMENT */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0xf2d0, /* MEM_UOP_RETIRED.STORES */ + [ C(RESULT_MISS) ] = 0x0851, /* L1D.ALL_M_REPLACEMENT */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x024e, /* HW_PRE_REQ.DL1_MISS */ + }, + }, + [ C(L1I ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0280, /* ICACHE.MISSES */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(LL ) ] = { + [ C(OP_READ) ] = { + /* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */ + [ C(RESULT_ACCESS) ] = 0x01b7, + /* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */ + [ C(RESULT_MISS) ] = 0x01b7, + }, + [ C(OP_WRITE) ] = { + /* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */ + [ C(RESULT_ACCESS) ] = 0x01b7, + /* OFFCORE_RESPONSE.ANY_RFO.ANY_LLC_MISS */ + [ C(RESULT_MISS) ] = 0x01b7, + }, + [ C(OP_PREFETCH) ] = { + /* OFFCORE_RESPONSE.PREFETCH.LOCAL_CACHE */ + [ C(RESULT_ACCESS) ] = 0x01b7, + /* OFFCORE_RESPONSE.PREFETCH.ANY_LLC_MISS */ + [ C(RESULT_MISS) ] = 0x01b7, + }, + }, + [ C(DTLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x81d0, /* MEM_UOP_RETIRED.ALL_LOADS */ + [ C(RESULT_MISS) ] = 0x0108, /* DTLB_LOAD_MISSES.CAUSES_A_WALK */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x82d0, /* MEM_UOP_RETIRED.ALL_STORES */ + [ C(RESULT_MISS) ] = 0x0149, /* DTLB_STORE_MISSES.MISS_CAUSES_A_WALK */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(ITLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x1085, /* ITLB_MISSES.STLB_HIT */ + [ C(RESULT_MISS) ] = 0x0185, /* ITLB_MISSES.CAUSES_A_WALK */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(BPU ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ALL_BRANCHES */ + [ C(RESULT_MISS) ] = 0x00c5, /* BR_MISP_RETIRED.ALL_BRANCHES */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, +}; + static __initconst const u64 westmere_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] @@ -124,16 +282,26 @@ static __initconst const u64 westmere_hw_cache_event_ids }, [ C(LL ) ] = { [ C(OP_READ) ] = { - [ C(RESULT_ACCESS) ] = 0x0324, /* L2_RQSTS.LOADS */ - [ C(RESULT_MISS) ] = 0x0224, /* L2_RQSTS.LD_MISS */ + /* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */ + [ C(RESULT_ACCESS) ] = 0x01b7, + /* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */ + [ C(RESULT_MISS) ] = 0x01b7, }, + /* + * Use RFO, not WRITEBACK, because a write miss would typically occur + * on RFO. + */ [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = 0x0c24, /* L2_RQSTS.RFOS */ - [ C(RESULT_MISS) ] = 0x0824, /* L2_RQSTS.RFO_MISS */ + /* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */ + [ C(RESULT_ACCESS) ] = 0x01b7, + /* OFFCORE_RESPONSE.ANY_RFO.ANY_LLC_MISS */ + [ C(RESULT_MISS) ] = 0x01b7, }, [ C(OP_PREFETCH) ] = { - [ C(RESULT_ACCESS) ] = 0x4f2e, /* LLC Reference */ - [ C(RESULT_MISS) ] = 0x412e, /* LLC Misses */ + /* OFFCORE_RESPONSE.PREFETCH.LOCAL_CACHE */ + [ C(RESULT_ACCESS) ] = 0x01b7, + /* OFFCORE_RESPONSE.PREFETCH.ANY_LLC_MISS */ + [ C(RESULT_MISS) ] = 0x01b7, }, }, [ C(DTLB) ] = { @@ -180,6 +348,59 @@ static __initconst const u64 westmere_hw_cache_event_ids }, }; +/* + * Nehalem/Westmere MSR_OFFCORE_RESPONSE bits; + * See IA32 SDM Vol 3B 30.6.1.3 + */ + +#define NHM_DMND_DATA_RD (1 << 0) +#define NHM_DMND_RFO (1 << 1) +#define NHM_DMND_IFETCH (1 << 2) +#define NHM_DMND_WB (1 << 3) +#define NHM_PF_DATA_RD (1 << 4) +#define NHM_PF_DATA_RFO (1 << 5) +#define NHM_PF_IFETCH (1 << 6) +#define NHM_OFFCORE_OTHER (1 << 7) +#define NHM_UNCORE_HIT (1 << 8) +#define NHM_OTHER_CORE_HIT_SNP (1 << 9) +#define NHM_OTHER_CORE_HITM (1 << 10) + /* reserved */ +#define NHM_REMOTE_CACHE_FWD (1 << 12) +#define NHM_REMOTE_DRAM (1 << 13) +#define NHM_LOCAL_DRAM (1 << 14) +#define NHM_NON_DRAM (1 << 15) + +#define NHM_ALL_DRAM (NHM_REMOTE_DRAM|NHM_LOCAL_DRAM) + +#define NHM_DMND_READ (NHM_DMND_DATA_RD) +#define NHM_DMND_WRITE (NHM_DMND_RFO|NHM_DMND_WB) +#define NHM_DMND_PREFETCH (NHM_PF_DATA_RD|NHM_PF_DATA_RFO) + +#define NHM_L3_HIT (NHM_UNCORE_HIT|NHM_OTHER_CORE_HIT_SNP|NHM_OTHER_CORE_HITM) +#define NHM_L3_MISS (NHM_NON_DRAM|NHM_ALL_DRAM|NHM_REMOTE_CACHE_FWD) +#define NHM_L3_ACCESS (NHM_L3_HIT|NHM_L3_MISS) + +static __initconst const u64 nehalem_hw_cache_extra_regs + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(LL ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = NHM_DMND_READ|NHM_L3_ACCESS, + [ C(RESULT_MISS) ] = NHM_DMND_READ|NHM_L3_MISS, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = NHM_DMND_WRITE|NHM_L3_ACCESS, + [ C(RESULT_MISS) ] = NHM_DMND_WRITE|NHM_L3_MISS, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = NHM_DMND_PREFETCH|NHM_L3_ACCESS, + [ C(RESULT_MISS) ] = NHM_DMND_PREFETCH|NHM_L3_MISS, + }, + } +}; + static __initconst const u64 nehalem_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] @@ -187,12 +408,12 @@ static __initconst const u64 nehalem_hw_cache_event_ids { [ C(L1D) ] = { [ C(OP_READ) ] = { - [ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI */ - [ C(RESULT_MISS) ] = 0x0140, /* L1D_CACHE_LD.I_STATE */ + [ C(RESULT_ACCESS) ] = 0x010b, /* MEM_INST_RETIRED.LOADS */ + [ C(RESULT_MISS) ] = 0x0151, /* L1D.REPL */ }, [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI */ - [ C(RESULT_MISS) ] = 0x0141, /* L1D_CACHE_ST.I_STATE */ + [ C(RESULT_ACCESS) ] = 0x020b, /* MEM_INST_RETURED.STORES */ + [ C(RESULT_MISS) ] = 0x0251, /* L1D.M_REPL */ }, [ C(OP_PREFETCH) ] = { [ C(RESULT_ACCESS) ] = 0x014e, /* L1D_PREFETCH.REQUESTS */ @@ -215,16 +436,26 @@ static __initconst const u64 nehalem_hw_cache_event_ids }, [ C(LL ) ] = { [ C(OP_READ) ] = { - [ C(RESULT_ACCESS) ] = 0x0324, /* L2_RQSTS.LOADS */ - [ C(RESULT_MISS) ] = 0x0224, /* L2_RQSTS.LD_MISS */ + /* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */ + [ C(RESULT_ACCESS) ] = 0x01b7, + /* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */ + [ C(RESULT_MISS) ] = 0x01b7, }, + /* + * Use RFO, not WRITEBACK, because a write miss would typically occur + * on RFO. + */ [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = 0x0c24, /* L2_RQSTS.RFOS */ - [ C(RESULT_MISS) ] = 0x0824, /* L2_RQSTS.RFO_MISS */ + /* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */ + [ C(RESULT_ACCESS) ] = 0x01b7, + /* OFFCORE_RESPONSE.ANY_RFO.ANY_LLC_MISS */ + [ C(RESULT_MISS) ] = 0x01b7, }, [ C(OP_PREFETCH) ] = { - [ C(RESULT_ACCESS) ] = 0x4f2e, /* LLC Reference */ - [ C(RESULT_MISS) ] = 0x412e, /* LLC Misses */ + /* OFFCORE_RESPONSE.PREFETCH.LOCAL_CACHE */ + [ C(RESULT_ACCESS) ] = 0x01b7, + /* OFFCORE_RESPONSE.PREFETCH.ANY_LLC_MISS */ + [ C(RESULT_MISS) ] = 0x01b7, }, }, [ C(DTLB) ] = { @@ -691,8 +922,8 @@ static void intel_pmu_reset(void) printk("clearing PMU state on CPU#%d\n", smp_processor_id()); for (idx = 0; idx < x86_pmu.num_counters; idx++) { - checking_wrmsrl(x86_pmu.eventsel + idx, 0ull); - checking_wrmsrl(x86_pmu.perfctr + idx, 0ull); + checking_wrmsrl(x86_pmu_config_addr(idx), 0ull); + checking_wrmsrl(x86_pmu_event_addr(idx), 0ull); } for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++) checking_wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull); @@ -719,6 +950,16 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) cpuc = &__get_cpu_var(cpu_hw_events); + /* + * Some chipsets need to unmask the LVTPC in a particular spot + * inside the nmi handler. As a result, the unmasking was pushed + * into all the nmi handlers. + * + * This handler doesn't seem to have any issues with the unmasking + * so it was left at the top. + */ + apic_write(APIC_LVTPC, APIC_DM_NMI); + intel_pmu_disable_all(); handled = intel_pmu_drain_bts_buffer(); status = intel_pmu_get_status(); @@ -784,6 +1025,9 @@ intel_bts_constraints(struct perf_event *event) struct hw_perf_event *hwc = &event->hw; unsigned int hw_event, bts_event; + if (event->attr.freq) + return NULL; + hw_event = hwc->config & INTEL_ARCH_EVENT_MASK; bts_event = x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS); @@ -794,6 +1038,67 @@ intel_bts_constraints(struct perf_event *event) } static struct event_constraint * +intel_percore_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + unsigned int e = hwc->config & ARCH_PERFMON_EVENTSEL_EVENT; + struct event_constraint *c; + struct intel_percore *pc; + struct er_account *era; + int i; + int free_slot; + int found; + + if (!x86_pmu.percore_constraints || hwc->extra_alloc) + return NULL; + + for (c = x86_pmu.percore_constraints; c->cmask; c++) { + if (e != c->code) + continue; + + /* + * Allocate resource per core. + */ + pc = cpuc->per_core; + if (!pc) + break; + c = &emptyconstraint; + raw_spin_lock(&pc->lock); + free_slot = -1; + found = 0; + for (i = 0; i < MAX_EXTRA_REGS; i++) { + era = &pc->regs[i]; + if (era->ref > 0 && hwc->extra_reg == era->extra_reg) { + /* Allow sharing same config */ + if (hwc->extra_config == era->extra_config) { + era->ref++; + cpuc->percore_used = 1; + hwc->extra_alloc = 1; + c = NULL; + } + /* else conflict */ + found = 1; + break; + } else if (era->ref == 0 && free_slot == -1) + free_slot = i; + } + if (!found && free_slot != -1) { + era = &pc->regs[free_slot]; + era->ref = 1; + era->extra_reg = hwc->extra_reg; + era->extra_config = hwc->extra_config; + cpuc->percore_used = 1; + hwc->extra_alloc = 1; + c = NULL; + } + raw_spin_unlock(&pc->lock); + return c; + } + + return NULL; +} + +static struct event_constraint * intel_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) { struct event_constraint *c; @@ -806,9 +1111,51 @@ intel_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event if (c) return c; + c = intel_percore_constraints(cpuc, event); + if (c) + return c; + return x86_get_event_constraints(cpuc, event); } +static void intel_put_event_constraints(struct cpu_hw_events *cpuc, + struct perf_event *event) +{ + struct extra_reg *er; + struct intel_percore *pc; + struct er_account *era; + struct hw_perf_event *hwc = &event->hw; + int i, allref; + + if (!cpuc->percore_used) + return; + + for (er = x86_pmu.extra_regs; er->msr; er++) { + if (er->event != (hwc->config & er->config_mask)) + continue; + + pc = cpuc->per_core; + raw_spin_lock(&pc->lock); + for (i = 0; i < MAX_EXTRA_REGS; i++) { + era = &pc->regs[i]; + if (era->ref > 0 && + era->extra_config == hwc->extra_config && + era->extra_reg == er->msr) { + era->ref--; + hwc->extra_alloc = 0; + break; + } + } + allref = 0; + for (i = 0; i < MAX_EXTRA_REGS; i++) + allref += pc->regs[i].ref; + if (allref == 0) + cpuc->percore_used = 0; + raw_spin_unlock(&pc->lock); + break; + } +} + static int intel_pmu_hw_config(struct perf_event *event) { int ret = x86_pmu_hw_config(event); @@ -880,20 +1227,67 @@ static __initconst const struct x86_pmu core_pmu = { */ .max_period = (1ULL << 31) - 1, .get_event_constraints = intel_get_event_constraints, + .put_event_constraints = intel_put_event_constraints, .event_constraints = intel_core_event_constraints, }; +static int intel_pmu_cpu_prepare(int cpu) +{ + struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); + + if (!cpu_has_ht_siblings()) + return NOTIFY_OK; + + cpuc->per_core = kzalloc_node(sizeof(struct intel_percore), + GFP_KERNEL, cpu_to_node(cpu)); + if (!cpuc->per_core) + return NOTIFY_BAD; + + raw_spin_lock_init(&cpuc->per_core->lock); + cpuc->per_core->core_id = -1; + return NOTIFY_OK; +} + static void intel_pmu_cpu_starting(int cpu) { + struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); + int core_id = topology_core_id(cpu); + int i; + init_debug_store_on_cpu(cpu); /* * Deal with CPUs that don't clear their LBRs on power-up. */ intel_pmu_lbr_reset(); + + if (!cpu_has_ht_siblings()) + return; + + for_each_cpu(i, topology_thread_cpumask(cpu)) { + struct intel_percore *pc = per_cpu(cpu_hw_events, i).per_core; + + if (pc && pc->core_id == core_id) { + kfree(cpuc->per_core); + cpuc->per_core = pc; + break; + } + } + + cpuc->per_core->core_id = core_id; + cpuc->per_core->refcnt++; } static void intel_pmu_cpu_dying(int cpu) { + struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); + struct intel_percore *pc = cpuc->per_core; + + if (pc) { + if (pc->core_id == -1 || --pc->refcnt == 0) + kfree(pc); + cpuc->per_core = NULL; + } + fini_debug_store_on_cpu(cpu); } @@ -918,7 +1312,9 @@ static __initconst const struct x86_pmu intel_pmu = { */ .max_period = (1ULL << 31) - 1, .get_event_constraints = intel_get_event_constraints, + .put_event_constraints = intel_put_event_constraints, + .cpu_prepare = intel_pmu_cpu_prepare, .cpu_starting = intel_pmu_cpu_starting, .cpu_dying = intel_pmu_cpu_dying, }; @@ -939,7 +1335,7 @@ static void intel_clovertown_quirks(void) * AJ106 could possibly be worked around by not allowing LBR * usage from PEBS, including the fixup. * AJ68 could possibly be worked around by always programming - * a pebs_event_reset[0] value and coping with the lost events. + * a pebs_event_reset[0] value and coping with the lost events. * * But taken together it might just make sense to not enable PEBS on * these chips. @@ -1024,6 +1420,7 @@ static __init int intel_pmu_init(void) intel_pmu_lbr_init_core(); x86_pmu.event_constraints = intel_core2_event_constraints; + x86_pmu.pebs_constraints = intel_core2_pebs_event_constraints; pr_cont("Core2 events, "); break; @@ -1032,11 +1429,28 @@ static __init int intel_pmu_init(void) case 46: /* 45 nm nehalem-ex, "Beckton" */ memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs, + sizeof(hw_cache_extra_regs)); intel_pmu_lbr_init_nhm(); x86_pmu.event_constraints = intel_nehalem_event_constraints; + x86_pmu.pebs_constraints = intel_nehalem_pebs_event_constraints; + x86_pmu.percore_constraints = intel_nehalem_percore_constraints; x86_pmu.enable_all = intel_pmu_nhm_enable_all; + x86_pmu.extra_regs = intel_nehalem_extra_regs; + + if (ebx & 0x40) { + /* + * Erratum AAJ80 detected, we work it around by using + * the BR_MISP_EXEC.ANY event. This will over-count + * branch-misses, but it's still much better than the + * architectural event which is often completely bogus: + */ + intel_perfmon_event_map[PERF_COUNT_HW_BRANCH_MISSES] = 0x7f89; + + pr_cont("erratum AAJ80 worked around, "); + } pr_cont("Nehalem events, "); break; @@ -1047,21 +1461,39 @@ static __init int intel_pmu_init(void) intel_pmu_lbr_init_atom(); x86_pmu.event_constraints = intel_gen_event_constraints; + x86_pmu.pebs_constraints = intel_atom_pebs_event_constraints; pr_cont("Atom events, "); break; case 37: /* 32 nm nehalem, "Clarkdale" */ case 44: /* 32 nm nehalem, "Gulftown" */ + case 47: /* 32 nm Xeon E7 */ memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs, + sizeof(hw_cache_extra_regs)); intel_pmu_lbr_init_nhm(); x86_pmu.event_constraints = intel_westmere_event_constraints; + x86_pmu.percore_constraints = intel_westmere_percore_constraints; x86_pmu.enable_all = intel_pmu_nhm_enable_all; + x86_pmu.pebs_constraints = intel_westmere_pebs_event_constraints; + x86_pmu.extra_regs = intel_westmere_extra_regs; pr_cont("Westmere events, "); break; + case 42: /* SandyBridge */ + memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, + sizeof(hw_cache_event_ids)); + + intel_pmu_lbr_init_nhm(); + + x86_pmu.event_constraints = intel_snb_event_constraints; + x86_pmu.pebs_constraints = intel_snb_pebs_events; + pr_cont("SandyBridge events, "); + break; + default: /* * default constraints for v2 and up diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index b7dcd9f2b8a..bab491b8ee2 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -361,30 +361,70 @@ static int intel_pmu_drain_bts_buffer(void) /* * PEBS */ +static struct event_constraint intel_core2_pebs_event_constraints[] = { + INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */ + INTEL_UEVENT_CONSTRAINT(0xfec1, 0x1), /* X87_OPS_RETIRED.ANY */ + INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */ + INTEL_UEVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */ + INTEL_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */ + EVENT_CONSTRAINT_END +}; + +static struct event_constraint intel_atom_pebs_event_constraints[] = { + INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */ + INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */ + INTEL_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */ + EVENT_CONSTRAINT_END +}; -static struct event_constraint intel_core_pebs_events[] = { - PEBS_EVENT_CONSTRAINT(0x00c0, 0x1), /* INSTR_RETIRED.ANY */ - PEBS_EVENT_CONSTRAINT(0xfec1, 0x1), /* X87_OPS_RETIRED.ANY */ - PEBS_EVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */ - PEBS_EVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */ - PEBS_EVENT_CONSTRAINT(0x01cb, 0x1), /* MEM_LOAD_RETIRED.L1D_MISS */ - PEBS_EVENT_CONSTRAINT(0x02cb, 0x1), /* MEM_LOAD_RETIRED.L1D_LINE_MISS */ - PEBS_EVENT_CONSTRAINT(0x04cb, 0x1), /* MEM_LOAD_RETIRED.L2_MISS */ - PEBS_EVENT_CONSTRAINT(0x08cb, 0x1), /* MEM_LOAD_RETIRED.L2_LINE_MISS */ - PEBS_EVENT_CONSTRAINT(0x10cb, 0x1), /* MEM_LOAD_RETIRED.DTLB_MISS */ +static struct event_constraint intel_nehalem_pebs_event_constraints[] = { + INTEL_EVENT_CONSTRAINT(0x0b, 0xf), /* MEM_INST_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */ + INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */ + INTEL_EVENT_CONSTRAINT(0xc0, 0xf), /* INST_RETIRED.ANY */ + INTEL_EVENT_CONSTRAINT(0xc2, 0xf), /* UOPS_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */ + INTEL_UEVENT_CONSTRAINT(0x02c5, 0xf), /* BR_MISP_RETIRED.NEAR_CALL */ + INTEL_EVENT_CONSTRAINT(0xc7, 0xf), /* SSEX_UOPS_RETIRED.* */ + INTEL_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */ + INTEL_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */ EVENT_CONSTRAINT_END }; -static struct event_constraint intel_nehalem_pebs_events[] = { - PEBS_EVENT_CONSTRAINT(0x00c0, 0xf), /* INSTR_RETIRED.ANY */ - PEBS_EVENT_CONSTRAINT(0xfec1, 0xf), /* X87_OPS_RETIRED.ANY */ - PEBS_EVENT_CONSTRAINT(0x00c5, 0xf), /* BR_INST_RETIRED.MISPRED */ - PEBS_EVENT_CONSTRAINT(0x1fc7, 0xf), /* SIMD_INST_RETURED.ANY */ - PEBS_EVENT_CONSTRAINT(0x01cb, 0xf), /* MEM_LOAD_RETIRED.L1D_MISS */ - PEBS_EVENT_CONSTRAINT(0x02cb, 0xf), /* MEM_LOAD_RETIRED.L1D_LINE_MISS */ - PEBS_EVENT_CONSTRAINT(0x04cb, 0xf), /* MEM_LOAD_RETIRED.L2_MISS */ - PEBS_EVENT_CONSTRAINT(0x08cb, 0xf), /* MEM_LOAD_RETIRED.L2_LINE_MISS */ - PEBS_EVENT_CONSTRAINT(0x10cb, 0xf), /* MEM_LOAD_RETIRED.DTLB_MISS */ +static struct event_constraint intel_westmere_pebs_event_constraints[] = { + INTEL_EVENT_CONSTRAINT(0x0b, 0xf), /* MEM_INST_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */ + INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */ + INTEL_EVENT_CONSTRAINT(0xc0, 0xf), /* INSTR_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xc2, 0xf), /* UOPS_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xc7, 0xf), /* SSEX_UOPS_RETIRED.* */ + INTEL_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */ + INTEL_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */ + EVENT_CONSTRAINT_END +}; + +static struct event_constraint intel_snb_pebs_events[] = { + INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ + INTEL_UEVENT_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ + INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */ + INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.* */ + INTEL_UEVENT_CONSTRAINT(0x11d0, 0xf), /* MEM_UOP_RETIRED.STLB_MISS_LOADS */ + INTEL_UEVENT_CONSTRAINT(0x12d0, 0xf), /* MEM_UOP_RETIRED.STLB_MISS_STORES */ + INTEL_UEVENT_CONSTRAINT(0x21d0, 0xf), /* MEM_UOP_RETIRED.LOCK_LOADS */ + INTEL_UEVENT_CONSTRAINT(0x22d0, 0xf), /* MEM_UOP_RETIRED.LOCK_STORES */ + INTEL_UEVENT_CONSTRAINT(0x41d0, 0xf), /* MEM_UOP_RETIRED.SPLIT_LOADS */ + INTEL_UEVENT_CONSTRAINT(0x42d0, 0xf), /* MEM_UOP_RETIRED.SPLIT_STORES */ + INTEL_UEVENT_CONSTRAINT(0x81d0, 0xf), /* MEM_UOP_RETIRED.ANY_LOADS */ + INTEL_UEVENT_CONSTRAINT(0x82d0, 0xf), /* MEM_UOP_RETIRED.ANY_STORES */ + INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ + INTEL_UEVENT_CONSTRAINT(0x02d4, 0xf), /* MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS */ EVENT_CONSTRAINT_END }; @@ -695,20 +735,17 @@ static void intel_ds_init(void) printk(KERN_CONT "PEBS fmt0%c, ", pebs_type); x86_pmu.pebs_record_size = sizeof(struct pebs_record_core); x86_pmu.drain_pebs = intel_pmu_drain_pebs_core; - x86_pmu.pebs_constraints = intel_core_pebs_events; break; case 1: printk(KERN_CONT "PEBS fmt1%c, ", pebs_type); x86_pmu.pebs_record_size = sizeof(struct pebs_record_nhm); x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm; - x86_pmu.pebs_constraints = intel_nehalem_pebs_events; break; default: printk(KERN_CONT "no PEBS fmt%d%c, ", format, pebs_type); x86_pmu.pebs = 0; - break; } } } diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c index f7a0993c1e7..e93fcd55fae 100644 --- a/arch/x86/kernel/cpu/perf_event_p4.c +++ b/arch/x86/kernel/cpu/perf_event_p4.c @@ -1,5 +1,5 @@ /* - * Netburst Perfomance Events (P4, old Xeon) + * Netburst Performance Events (P4, old Xeon) * * Copyright (C) 2010 Parallels, Inc., Cyrill Gorcunov <gorcunov@openvz.org> * Copyright (C) 2010 Intel Corporation, Lin Ming <ming.m.lin@intel.com> @@ -679,7 +679,7 @@ static int p4_validate_raw_event(struct perf_event *event) */ /* - * if an event is shared accross the logical threads + * if an event is shared across the logical threads * the user needs special permissions to be able to use it */ if (p4_ht_active() && p4_event_bind_map[v].shared) { @@ -764,15 +764,21 @@ static inline int p4_pmu_clear_cccr_ovf(struct hw_perf_event *hwc) u64 v; /* an official way for overflow indication */ - rdmsrl(hwc->config_base + hwc->idx, v); + rdmsrl(hwc->config_base, v); if (v & P4_CCCR_OVF) { - wrmsrl(hwc->config_base + hwc->idx, v & ~P4_CCCR_OVF); + wrmsrl(hwc->config_base, v & ~P4_CCCR_OVF); return 1; } - /* it might be unflagged overflow */ - rdmsrl(hwc->event_base + hwc->idx, v); - if (!(v & ARCH_P4_CNTRVAL_MASK)) + /* + * In some circumstances the overflow might issue an NMI but did + * not set P4_CCCR_OVF bit. Because a counter holds a negative value + * we simply check for high bit being set, if it's cleared it means + * the counter has reached zero value and continued counting before + * real NMI signal was received: + */ + rdmsrl(hwc->event_base, v); + if (!(v & ARCH_P4_UNFLAGGED_BIT)) return 1; return 0; @@ -785,13 +791,13 @@ static void p4_pmu_disable_pebs(void) * * It's still allowed that two threads setup same cache * events so we can't simply clear metrics until we knew - * noone is depending on us, so we need kind of counter + * no one is depending on us, so we need kind of counter * for "ReplayEvent" users. * * What is more complex -- RAW events, if user (for some * reason) will pass some cache event metric with improper * event opcode -- it's fine from hardware point of view - * but completely nonsence from "meaning" of such action. + * but completely nonsense from "meaning" of such action. * * So at moment let leave metrics turned on forever -- it's * ok for now but need to be revisited! @@ -810,7 +816,7 @@ static inline void p4_pmu_disable_event(struct perf_event *event) * state we need to clear P4_CCCR_OVF, otherwise interrupt get * asserted again and again */ - (void)checking_wrmsrl(hwc->config_base + hwc->idx, + (void)checking_wrmsrl(hwc->config_base, (u64)(p4_config_unpack_cccr(hwc->config)) & ~P4_CCCR_ENABLE & ~P4_CCCR_OVF & ~P4_CCCR_RESERVED); } @@ -880,7 +886,7 @@ static void p4_pmu_enable_event(struct perf_event *event) p4_pmu_enable_pebs(hwc->config); (void)checking_wrmsrl(escr_addr, escr_conf); - (void)checking_wrmsrl(hwc->config_base + hwc->idx, + (void)checking_wrmsrl(hwc->config_base, (cccr & ~P4_CCCR_RESERVED) | P4_CCCR_ENABLE); } @@ -941,14 +947,23 @@ static int p4_pmu_handle_irq(struct pt_regs *regs) if (!x86_perf_event_set_period(event)) continue; if (perf_event_overflow(event, 1, &data, regs)) - p4_pmu_disable_event(event); + x86_pmu_stop(event, 0); } - if (handled) { - /* p4 quirk: unmask it again */ - apic_write(APIC_LVTPC, apic_read(APIC_LVTPC) & ~APIC_LVT_MASKED); + if (handled) inc_irq_stat(apic_perf_irqs); - } + + /* + * When dealing with the unmasking of the LVTPC on P4 perf hw, it has + * been observed that the OVF bit flag has to be cleared first _before_ + * the LVTPC can be unmasked. + * + * The reason is the NMI line will continue to be asserted while the OVF + * bit is set. This causes a second NMI to generate if the LVTPC is + * unmasked before the OVF bit is cleared, leading to unknown NMI + * messages. + */ + apic_write(APIC_LVTPC, APIC_DM_NMI); return handled; } diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c index 34ba07be2cd..20c097e3386 100644 --- a/arch/x86/kernel/cpu/perf_event_p6.c +++ b/arch/x86/kernel/cpu/perf_event_p6.c @@ -68,7 +68,7 @@ p6_pmu_disable_event(struct perf_event *event) if (cpuc->enabled) val |= ARCH_PERFMON_EVENTSEL_ENABLE; - (void)checking_wrmsrl(hwc->config_base + hwc->idx, val); + (void)checking_wrmsrl(hwc->config_base, val); } static void p6_pmu_enable_event(struct perf_event *event) @@ -81,7 +81,7 @@ static void p6_pmu_enable_event(struct perf_event *event) if (cpuc->enabled) val |= ARCH_PERFMON_EVENTSEL_ENABLE; - (void)checking_wrmsrl(hwc->config_base + hwc->idx, val); + (void)checking_wrmsrl(hwc->config_base, val); } static __initconst const struct x86_pmu p6_pmu = { diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c index d5a23661550..966512b2cac 100644 --- a/arch/x86/kernel/cpu/perfctr-watchdog.c +++ b/arch/x86/kernel/cpu/perfctr-watchdog.c @@ -46,6 +46,8 @@ static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr) /* returns the bit offset of the performance counter register */ switch (boot_cpu_data.x86_vendor) { case X86_VENDOR_AMD: + if (msr >= MSR_F15H_PERF_CTR) + return (msr - MSR_F15H_PERF_CTR) >> 1; return msr - MSR_K7_PERFCTR0; case X86_VENDOR_INTEL: if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) @@ -70,6 +72,8 @@ static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr) /* returns the bit offset of the event selection register */ switch (boot_cpu_data.x86_vendor) { case X86_VENDOR_AMD: + if (msr >= MSR_F15H_PERF_CTL) + return (msr - MSR_F15H_PERF_CTL) >> 1; return msr - MSR_K7_EVNTSEL0; case X86_VENDOR_INTEL: if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 227b0448960..d22d0c4edcf 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -86,7 +86,7 @@ static void __init vmware_platform_setup(void) } /* - * While checking the dmi string infomation, just checking the product + * While checking the dmi string information, just checking the product * serial key should be enough, as this will always have a VMware * specific string when running under VMware hypervisor. */ diff --git a/arch/x86/kernel/crash_dump_32.c b/arch/x86/kernel/crash_dump_32.c index d5cd13945d5..642f75a68cd 100644 --- a/arch/x86/kernel/crash_dump_32.c +++ b/arch/x86/kernel/crash_dump_32.c @@ -14,9 +14,6 @@ static void *kdump_buf_page; -/* Stores the physical address of elf header of crash image. */ -unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX; - static inline bool is_crashed_pfn_valid(unsigned long pfn) { #ifndef CONFIG_X86_PAE diff --git a/arch/x86/kernel/crash_dump_64.c b/arch/x86/kernel/crash_dump_64.c index 994828899e0..afa64adb75e 100644 --- a/arch/x86/kernel/crash_dump_64.c +++ b/arch/x86/kernel/crash_dump_64.c @@ -10,9 +10,6 @@ #include <linux/uaccess.h> #include <linux/io.h> -/* Stores the physical address of elf header of crash image. */ -unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX; - /** * copy_oldmem_page - copy one page from "oldmem" * @pfn: page frame number to be copied diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c new file mode 100644 index 00000000000..e90f08458e6 --- /dev/null +++ b/arch/x86/kernel/devicetree.c @@ -0,0 +1,439 @@ +/* + * Architecture specific OF callbacks. + */ +#include <linux/bootmem.h> +#include <linux/io.h> +#include <linux/interrupt.h> +#include <linux/list.h> +#include <linux/of.h> +#include <linux/of_fdt.h> +#include <linux/of_address.h> +#include <linux/of_platform.h> +#include <linux/of_irq.h> +#include <linux/slab.h> +#include <linux/pci.h> +#include <linux/of_pci.h> + +#include <asm/hpet.h> +#include <asm/irq_controller.h> +#include <asm/apic.h> +#include <asm/pci_x86.h> + +__initdata u64 initial_dtb; +char __initdata cmd_line[COMMAND_LINE_SIZE]; +static LIST_HEAD(irq_domains); +static DEFINE_RAW_SPINLOCK(big_irq_lock); + +int __initdata of_ioapic; + +#ifdef CONFIG_X86_IO_APIC +static void add_interrupt_host(struct irq_domain *ih) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&big_irq_lock, flags); + list_add(&ih->l, &irq_domains); + raw_spin_unlock_irqrestore(&big_irq_lock, flags); +} +#endif + +static struct irq_domain *get_ih_from_node(struct device_node *controller) +{ + struct irq_domain *ih, *found = NULL; + unsigned long flags; + + raw_spin_lock_irqsave(&big_irq_lock, flags); + list_for_each_entry(ih, &irq_domains, l) { + if (ih->controller == controller) { + found = ih; + break; + } + } + raw_spin_unlock_irqrestore(&big_irq_lock, flags); + return found; +} + +unsigned int irq_create_of_mapping(struct device_node *controller, + const u32 *intspec, unsigned int intsize) +{ + struct irq_domain *ih; + u32 virq, type; + int ret; + + ih = get_ih_from_node(controller); + if (!ih) + return 0; + ret = ih->xlate(ih, intspec, intsize, &virq, &type); + if (ret) + return 0; + if (type == IRQ_TYPE_NONE) + return virq; + irq_set_irq_type(virq, type); + return virq; +} +EXPORT_SYMBOL_GPL(irq_create_of_mapping); + +unsigned long pci_address_to_pio(phys_addr_t address) +{ + /* + * The ioport address can be directly used by inX / outX + */ + BUG_ON(address >= (1 << 16)); + return (unsigned long)address; +} +EXPORT_SYMBOL_GPL(pci_address_to_pio); + +void __init early_init_dt_scan_chosen_arch(unsigned long node) +{ + BUG(); +} + +void __init early_init_dt_add_memory_arch(u64 base, u64 size) +{ + BUG(); +} + +void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align) +{ + return __alloc_bootmem(size, align, __pa(MAX_DMA_ADDRESS)); +} + +void __init add_dtb(u64 data) +{ + initial_dtb = data + offsetof(struct setup_data, data); +} + +/* + * CE4100 ids. Will be moved to machine_device_initcall() once we have it. + */ +static struct of_device_id __initdata ce4100_ids[] = { + { .compatible = "intel,ce4100-cp", }, + { .compatible = "isa", }, + { .compatible = "pci", }, + {}, +}; + +static int __init add_bus_probe(void) +{ + if (!of_have_populated_dt()) + return 0; + + return of_platform_bus_probe(NULL, ce4100_ids, NULL); +} +module_init(add_bus_probe); + +#ifdef CONFIG_PCI +static int x86_of_pci_irq_enable(struct pci_dev *dev) +{ + struct of_irq oirq; + u32 virq; + int ret; + u8 pin; + + ret = pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin); + if (ret) + return ret; + if (!pin) + return 0; + + ret = of_irq_map_pci(dev, &oirq); + if (ret) + return ret; + + virq = irq_create_of_mapping(oirq.controller, oirq.specifier, + oirq.size); + if (virq == 0) + return -EINVAL; + dev->irq = virq; + return 0; +} + +static void x86_of_pci_irq_disable(struct pci_dev *dev) +{ +} + +void __cpuinit x86_of_pci_init(void) +{ + struct device_node *np; + + pcibios_enable_irq = x86_of_pci_irq_enable; + pcibios_disable_irq = x86_of_pci_irq_disable; + + for_each_node_by_type(np, "pci") { + const void *prop; + struct pci_bus *bus; + unsigned int bus_min; + struct device_node *child; + + prop = of_get_property(np, "bus-range", NULL); + if (!prop) + continue; + bus_min = be32_to_cpup(prop); + + bus = pci_find_bus(0, bus_min); + if (!bus) { + printk(KERN_ERR "Can't find a node for bus %s.\n", + np->full_name); + continue; + } + + if (bus->self) + bus->self->dev.of_node = np; + else + bus->dev.of_node = np; + + for_each_child_of_node(np, child) { + struct pci_dev *dev; + u32 devfn; + + prop = of_get_property(child, "reg", NULL); + if (!prop) + continue; + + devfn = (be32_to_cpup(prop) >> 8) & 0xff; + dev = pci_get_slot(bus, devfn); + if (!dev) + continue; + dev->dev.of_node = child; + pci_dev_put(dev); + } + } +} +#endif + +static void __init dtb_setup_hpet(void) +{ +#ifdef CONFIG_HPET_TIMER + struct device_node *dn; + struct resource r; + int ret; + + dn = of_find_compatible_node(NULL, NULL, "intel,ce4100-hpet"); + if (!dn) + return; + ret = of_address_to_resource(dn, 0, &r); + if (ret) { + WARN_ON(1); + return; + } + hpet_address = r.start; +#endif +} + +static void __init dtb_lapic_setup(void) +{ +#ifdef CONFIG_X86_LOCAL_APIC + struct device_node *dn; + struct resource r; + int ret; + + dn = of_find_compatible_node(NULL, NULL, "intel,ce4100-lapic"); + if (!dn) + return; + + ret = of_address_to_resource(dn, 0, &r); + if (WARN_ON(ret)) + return; + + /* Did the boot loader setup the local APIC ? */ + if (!cpu_has_apic) { + if (apic_force_enable(r.start)) + return; + } + smp_found_config = 1; + pic_mode = 1; + register_lapic_address(r.start); + generic_processor_info(boot_cpu_physical_apicid, + GET_APIC_VERSION(apic_read(APIC_LVR))); +#endif +} + +#ifdef CONFIG_X86_IO_APIC +static unsigned int ioapic_id; + +static void __init dtb_add_ioapic(struct device_node *dn) +{ + struct resource r; + int ret; + + ret = of_address_to_resource(dn, 0, &r); + if (ret) { + printk(KERN_ERR "Can't obtain address from node %s.\n", + dn->full_name); + return; + } + mp_register_ioapic(++ioapic_id, r.start, gsi_top); +} + +static void __init dtb_ioapic_setup(void) +{ + struct device_node *dn; + + for_each_compatible_node(dn, NULL, "intel,ce4100-ioapic") + dtb_add_ioapic(dn); + + if (nr_ioapics) { + of_ioapic = 1; + return; + } + printk(KERN_ERR "Error: No information about IO-APIC in OF.\n"); +} +#else +static void __init dtb_ioapic_setup(void) {} +#endif + +static void __init dtb_apic_setup(void) +{ + dtb_lapic_setup(); + dtb_ioapic_setup(); +} + +#ifdef CONFIG_OF_FLATTREE +static void __init x86_flattree_get_config(void) +{ + u32 size, map_len; + void *new_dtb; + + if (!initial_dtb) + return; + + map_len = max(PAGE_SIZE - (initial_dtb & ~PAGE_MASK), + (u64)sizeof(struct boot_param_header)); + + initial_boot_params = early_memremap(initial_dtb, map_len); + size = be32_to_cpu(initial_boot_params->totalsize); + if (map_len < size) { + early_iounmap(initial_boot_params, map_len); + initial_boot_params = early_memremap(initial_dtb, size); + map_len = size; + } + + new_dtb = alloc_bootmem(size); + memcpy(new_dtb, initial_boot_params, size); + early_iounmap(initial_boot_params, map_len); + + initial_boot_params = new_dtb; + + /* root level address cells */ + of_scan_flat_dt(early_init_dt_scan_root, NULL); + + unflatten_device_tree(); +} +#else +static inline void x86_flattree_get_config(void) { } +#endif + +void __init x86_dtb_init(void) +{ + x86_flattree_get_config(); + + if (!of_have_populated_dt()) + return; + + dtb_setup_hpet(); + dtb_apic_setup(); +} + +#ifdef CONFIG_X86_IO_APIC + +struct of_ioapic_type { + u32 out_type; + u32 trigger; + u32 polarity; +}; + +static struct of_ioapic_type of_ioapic_type[] = +{ + { + .out_type = IRQ_TYPE_EDGE_RISING, + .trigger = IOAPIC_EDGE, + .polarity = 1, + }, + { + .out_type = IRQ_TYPE_LEVEL_LOW, + .trigger = IOAPIC_LEVEL, + .polarity = 0, + }, + { + .out_type = IRQ_TYPE_LEVEL_HIGH, + .trigger = IOAPIC_LEVEL, + .polarity = 1, + }, + { + .out_type = IRQ_TYPE_EDGE_FALLING, + .trigger = IOAPIC_EDGE, + .polarity = 0, + }, +}; + +static int ioapic_xlate(struct irq_domain *id, const u32 *intspec, u32 intsize, + u32 *out_hwirq, u32 *out_type) +{ + struct io_apic_irq_attr attr; + struct of_ioapic_type *it; + u32 line, idx, type; + + if (intsize < 2) + return -EINVAL; + + line = *intspec; + idx = (u32) id->priv; + *out_hwirq = line + mp_gsi_routing[idx].gsi_base; + + intspec++; + type = *intspec; + + if (type >= ARRAY_SIZE(of_ioapic_type)) + return -EINVAL; + + it = of_ioapic_type + type; + *out_type = it->out_type; + + set_io_apic_irq_attr(&attr, idx, line, it->trigger, it->polarity); + + return io_apic_setup_irq_pin_once(*out_hwirq, cpu_to_node(0), &attr); +} + +static void __init ioapic_add_ofnode(struct device_node *np) +{ + struct resource r; + int i, ret; + + ret = of_address_to_resource(np, 0, &r); + if (ret) { + printk(KERN_ERR "Failed to obtain address for %s\n", + np->full_name); + return; + } + + for (i = 0; i < nr_ioapics; i++) { + if (r.start == mp_ioapics[i].apicaddr) { + struct irq_domain *id; + + id = kzalloc(sizeof(*id), GFP_KERNEL); + BUG_ON(!id); + id->controller = np; + id->xlate = ioapic_xlate; + id->priv = (void *)i; + add_interrupt_host(id); + return; + } + } + printk(KERN_ERR "IOxAPIC at %s is not registered.\n", np->full_name); +} + +void __init x86_add_irq_domains(void) +{ + struct device_node *dp; + + if (!of_have_populated_dt()) + return; + + for_each_node_with_property(dp, "interrupt-controller") { + if (of_device_is_compatible(dp, "intel,ce4100-ioapic")) + ioapic_add_ofnode(dp); + } +} +#else +void __init x86_add_irq_domains(void) { } +#endif diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index df20723a6a1..e2a3f0606da 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -27,7 +27,7 @@ static int die_counter; void printk_address(unsigned long address, int reliable) { - printk(" [<%p>] %s%pS\n", (void *) address, + printk(" [<%p>] %s%pB\n", (void *) address, reliable ? "" : "? ", (void *) address); } @@ -175,21 +175,21 @@ static const struct stacktrace_ops print_trace_ops = { void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, char *log_lvl) + unsigned long *stack, unsigned long bp, char *log_lvl) { printk("%sCall Trace:\n", log_lvl); - dump_trace(task, regs, stack, &print_trace_ops, log_lvl); + dump_trace(task, regs, stack, bp, &print_trace_ops, log_lvl); } void show_trace(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack) + unsigned long *stack, unsigned long bp) { - show_trace_log_lvl(task, regs, stack, ""); + show_trace_log_lvl(task, regs, stack, bp, ""); } void show_stack(struct task_struct *task, unsigned long *sp) { - show_stack_log_lvl(task, NULL, sp, ""); + show_stack_log_lvl(task, NULL, sp, 0, ""); } /* @@ -197,14 +197,16 @@ void show_stack(struct task_struct *task, unsigned long *sp) */ void dump_stack(void) { + unsigned long bp; unsigned long stack; + bp = stack_frame(current, NULL); printk("Pid: %d, comm: %.20s %s %s %.*s\n", current->pid, current->comm, print_tainted(), init_utsname()->release, (int)strcspn(init_utsname()->version, " "), init_utsname()->version); - show_trace(NULL, NULL, &stack); + show_trace(NULL, NULL, &stack, bp); } EXPORT_SYMBOL(dump_stack); @@ -320,41 +322,6 @@ void die(const char *str, struct pt_regs *regs, long err) oops_end(flags, regs, sig); } -void notrace __kprobes -die_nmi(char *str, struct pt_regs *regs, int do_panic) -{ - unsigned long flags; - - if (notify_die(DIE_NMIWATCHDOG, str, regs, 0, 2, SIGINT) == NOTIFY_STOP) - return; - - /* - * We are in trouble anyway, lets at least try - * to get a message out. - */ - flags = oops_begin(); - printk(KERN_EMERG "%s", str); - printk(" on CPU%d, ip %08lx, registers:\n", - smp_processor_id(), regs->ip); - show_registers(regs); - oops_end(flags, regs, 0); - if (do_panic || panic_on_oops) - panic("Non maskable interrupt"); - nmi_exit(); - local_irq_enable(); - do_exit(SIGBUS); -} - -static int __init oops_setup(char *s) -{ - if (!s) - return -EINVAL; - if (!strcmp(s, "panic")) - panic_on_oops = 1; - return 0; -} -early_param("oops", oops_setup); - static int __init kstack_setup(char *s) { if (!s) diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index 74cc1eda384..3b97a80ce32 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -17,12 +17,11 @@ #include <asm/stacktrace.h> -void dump_trace(struct task_struct *task, - struct pt_regs *regs, unsigned long *stack, +void dump_trace(struct task_struct *task, struct pt_regs *regs, + unsigned long *stack, unsigned long bp, const struct stacktrace_ops *ops, void *data) { int graph = 0; - unsigned long bp; if (!task) task = current; @@ -35,7 +34,9 @@ void dump_trace(struct task_struct *task, stack = (unsigned long *)task->thread.sp; } - bp = stack_frame(task, regs); + if (!bp) + bp = stack_frame(task, regs); + for (;;) { struct thread_info *context; @@ -55,7 +56,7 @@ EXPORT_SYMBOL(dump_trace); void show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *sp, char *log_lvl) + unsigned long *sp, unsigned long bp, char *log_lvl) { unsigned long *stack; int i; @@ -77,7 +78,7 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, touch_nmi_watchdog(); } printk(KERN_CONT "\n"); - show_trace_log_lvl(task, regs, sp, log_lvl); + show_trace_log_lvl(task, regs, sp, bp, log_lvl); } @@ -102,7 +103,7 @@ void show_registers(struct pt_regs *regs) u8 *ip; printk(KERN_EMERG "Stack:\n"); - show_stack_log_lvl(NULL, regs, ®s->sp, KERN_EMERG); + show_stack_log_lvl(NULL, regs, ®s->sp, 0, KERN_EMERG); printk(KERN_EMERG "Code: "); diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index a6b6fcf7f0a..e71c98d3c0d 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -139,8 +139,8 @@ fixup_bp_irq_link(unsigned long bp, unsigned long *stack, * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack */ -void dump_trace(struct task_struct *task, - struct pt_regs *regs, unsigned long *stack, +void dump_trace(struct task_struct *task, struct pt_regs *regs, + unsigned long *stack, unsigned long bp, const struct stacktrace_ops *ops, void *data) { const unsigned cpu = get_cpu(); @@ -150,7 +150,6 @@ void dump_trace(struct task_struct *task, struct thread_info *tinfo; int graph = 0; unsigned long dummy; - unsigned long bp; if (!task) task = current; @@ -161,7 +160,8 @@ void dump_trace(struct task_struct *task, stack = (unsigned long *)task->thread.sp; } - bp = stack_frame(task, regs); + if (!bp) + bp = stack_frame(task, regs); /* * Print function call entries in all stacks, starting at the * current stack address. If the stacks consist of nested @@ -225,7 +225,7 @@ EXPORT_SYMBOL(dump_trace); void show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *sp, char *log_lvl) + unsigned long *sp, unsigned long bp, char *log_lvl) { unsigned long *irq_stack_end; unsigned long *irq_stack; @@ -269,7 +269,7 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, preempt_enable(); printk(KERN_CONT "\n"); - show_trace_log_lvl(task, regs, sp, log_lvl); + show_trace_log_lvl(task, regs, sp, bp, log_lvl); } void show_registers(struct pt_regs *regs) @@ -298,7 +298,7 @@ void show_registers(struct pt_regs *regs) printk(KERN_EMERG "Stack:\n"); show_stack_log_lvl(NULL, regs, (unsigned long *)sp, - KERN_EMERG); + 0, KERN_EMERG); printk(KERN_EMERG "Code: "); diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 294f26da0c0..3e2ef842531 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -11,6 +11,7 @@ #include <linux/kernel.h> #include <linux/types.h> #include <linux/init.h> +#include <linux/crash_dump.h> #include <linux/bootmem.h> #include <linux/pfn.h> #include <linux/suspend.h> @@ -667,21 +668,15 @@ __init void e820_setup_gap(void) * boot_params.e820_map, others are passed via SETUP_E820_EXT node of * linked list of struct setup_data, which is parsed here. */ -void __init parse_e820_ext(struct setup_data *sdata, unsigned long pa_data) +void __init parse_e820_ext(struct setup_data *sdata) { - u32 map_len; int entries; struct e820entry *extmap; entries = sdata->len / sizeof(struct e820entry); - map_len = sdata->len + sizeof(struct setup_data); - if (map_len > PAGE_SIZE) - sdata = early_ioremap(pa_data, map_len); extmap = (struct e820entry *)(sdata->data); __append_e820_map(extmap, entries); sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); - if (map_len > PAGE_SIZE) - early_iounmap(sdata, map_len); printk(KERN_INFO "extended physical RAM map:\n"); e820_print_map("extended"); } @@ -847,15 +842,21 @@ static int __init parse_memopt(char *p) if (!p) return -EINVAL; -#ifdef CONFIG_X86_32 if (!strcmp(p, "nopentium")) { +#ifdef CONFIG_X86_32 setup_clear_cpu_cap(X86_FEATURE_PSE); return 0; - } +#else + printk(KERN_WARNING "mem=nopentium ignored! (only supported on x86_32)\n"); + return -EINVAL; #endif + } userdef = 1; mem_size = memparse(p, &p); + /* don't remove all of memory when handling "mem={invalid}" param */ + if (mem_size == 0) + return -EINVAL; e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1); return 0; diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 76b8cd953de..3755ef49439 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -143,15 +143,10 @@ static void __init ati_bugs(int num, int slot, int func) static u32 __init ati_sbx00_rev(int num, int slot, int func) { - u32 old, d; + u32 d; - d = read_pci_config(num, slot, func, 0x70); - old = d; - d &= ~(1<<8); - write_pci_config(num, slot, func, 0x70, d); d = read_pci_config(num, slot, func, 0x8); d &= 0xff; - write_pci_config(num, slot, func, 0x70, old); return d; } @@ -160,11 +155,19 @@ static void __init ati_bugs_contd(int num, int slot, int func) { u32 d, rev; - if (acpi_use_timer_override) + rev = ati_sbx00_rev(num, slot, func); + if (rev >= 0x40) + acpi_fix_pin2_polarity = 1; + + /* + * SB600: revisions 0x11, 0x12, 0x13, 0x14, ... + * SB700: revisions 0x39, 0x3a, ... + * SB800: revisions 0x40, 0x41, ... + */ + if (rev >= 0x39) return; - rev = ati_sbx00_rev(num, slot, func); - if (rev > 0x13) + if (acpi_use_timer_override) return; /* check for IRQ0 interrupt swap */ diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index c8b4efad7eb..5c1a9197491 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -65,6 +65,8 @@ #define sysexit_audit syscall_exit_work #endif + .section .entry.text, "ax" + /* * We use macros for low-level operations which need to be overridden * for paravirtualization. The following will never clobber any registers: @@ -395,7 +397,7 @@ sysenter_past_esp: * A tiny bit of offset fixup is necessary - 4*4 means the 4 words * pushed above; +8 corresponds to copy_thread's esp0 setting. */ - pushl_cfi ((TI_sysenter_return)-THREAD_SIZE_asm+8+4*4)(%esp) + pushl_cfi ((TI_sysenter_return)-THREAD_SIZE+8+4*4)(%esp) CFI_REL_OFFSET eip, 0 pushl_cfi %eax @@ -788,7 +790,7 @@ ENDPROC(ptregs_clone) */ .section .init.rodata,"a" ENTRY(interrupt) -.text +.section .entry.text, "ax" .p2align 5 .p2align CONFIG_X86_L1_CACHE_SHIFT ENTRY(irq_entries_start) @@ -807,7 +809,7 @@ vector=FIRST_EXTERNAL_VECTOR .endif .previous .long 1b - .text + .section .entry.text, "ax" vector=vector+1 .endif .endr @@ -1409,11 +1411,10 @@ END(general_protection) #ifdef CONFIG_KVM_GUEST ENTRY(async_page_fault) RING0_EC_FRAME - pushl $do_async_page_fault - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi $do_async_page_fault jmp error_code CFI_ENDPROC -END(apf_page_fault) +END(async_page_fault) #endif /* diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index aed1ffbeb0c..8a445a0c989 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -18,7 +18,7 @@ * A note on terminology: * - top of stack: Architecture defined interrupt frame from SS to RIP * at the top of the kernel process stack. - * - partial stack frame: partially saved registers upto R11. + * - partial stack frame: partially saved registers up to R11. * - full stack frame: Like partial stack frame, but all register saved. * * Some macro usage: @@ -61,6 +61,8 @@ #define __AUDIT_ARCH_LE 0x40000000 .code64 + .section .entry.text, "ax" + #ifdef CONFIG_FUNCTION_TRACER #ifdef CONFIG_DYNAMIC_FTRACE ENTRY(mcount) @@ -420,7 +422,7 @@ ENTRY(ret_from_fork) END(ret_from_fork) /* - * System call entry. Upto 6 arguments in registers are supported. + * System call entry. Up to 6 arguments in registers are supported. * * SYSCALL does not save anything on the stack and does not change the * stack pointer. @@ -744,7 +746,7 @@ END(stub_rt_sigreturn) */ .section .init.rodata,"a" ENTRY(interrupt) - .text + .section .entry.text .p2align 5 .p2align CONFIG_X86_L1_CACHE_SHIFT ENTRY(irq_entries_start) @@ -763,7 +765,7 @@ vector=FIRST_EXTERNAL_VECTOR .endif .previous .quad 1b - .text + .section .entry.text vector=vector+1 .endif .endr @@ -975,9 +977,12 @@ apicinterrupt X86_PLATFORM_IPI_VECTOR \ x86_platform_ipi smp_x86_platform_ipi #ifdef CONFIG_SMP -.irpc idx, "01234567" +.irp idx,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15, \ + 16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31 +.if NUM_INVALIDATE_TLB_VECTORS > \idx apicinterrupt (INVALIDATE_TLB_VECTOR_START)+\idx \ invalidate_interrupt\idx smp_invalidate_interrupt +.endif .endr #endif @@ -1248,7 +1253,7 @@ ENTRY(xen_do_hypervisor_callback) # do_hypervisor_callback(struct *pt_regs) decl PER_CPU_VAR(irq_count) jmp error_exit CFI_ENDPROC -END(do_hypervisor_callback) +END(xen_do_hypervisor_callback) /* * Hypervisor uses this for application faults while it executes. diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 382eb2936d4..a93742a5746 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -437,18 +437,19 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, return; } - if (ftrace_push_return_trace(old, self_addr, &trace.depth, - frame_pointer) == -EBUSY) { - *parent = old; - return; - } - trace.func = self_addr; + trace.depth = current->curr_ret_stack + 1; /* Only trace if the calling function expects to */ if (!ftrace_graph_entry(&trace)) { - current->curr_ret_stack--; *parent = old; + return; + } + + if (ftrace_push_return_trace(old, self_addr, &trace.depth, + frame_pointer) == -EBUSY) { + *parent = old; + return; } } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index 7f138b3c3c5..d6d6bb36193 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -34,15 +34,6 @@ void __init i386_start_kernel(void) { memblock_init(); -#ifdef CONFIG_X86_TRAMPOLINE - /* - * But first pinch a few for the stack/trampoline stuff - * FIXME: Don't need the extra page at 4K, but need to fix - * trampoline before removing it. (see the GDT stuff) - */ - memblock_x86_reserve_range(PAGE_SIZE, PAGE_SIZE + PAGE_SIZE, "EX TRAMPOLINE"); -#endif - memblock_x86_reserve_range(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS"); #ifdef CONFIG_BLK_DEV_INITRD diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 2d2673c28af..5655c2272ad 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -77,9 +77,6 @@ void __init x86_64_start_kernel(char * real_mode_data) /* Make NULL pointers segfault */ zap_identity_mappings(); - /* Cleanup the over mapped high alias */ - cleanup_highmap(); - max_pfn_mapped = KERNEL_IMAGE_SIZE >> PAGE_SHIFT; for (i = 0; i < NUM_EXCEPTION_VECTORS; i++) { diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 767d6c43de3..ce0be7cd085 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -73,7 +73,7 @@ MAPPING_BEYOND_END = PAGE_TABLE_SIZE(LOWMEM_PAGES) << PAGE_SHIFT */ KERNEL_PAGES = LOWMEM_PAGES -INIT_MAP_SIZE = PAGE_TABLE_SIZE(KERNEL_PAGES) * PAGE_SIZE_asm +INIT_MAP_SIZE = PAGE_TABLE_SIZE(KERNEL_PAGES) * PAGE_SIZE RESERVE_BRK(pagetables, INIT_MAP_SIZE) /* @@ -137,7 +137,7 @@ ENTRY(startup_32) movsl 1: -#ifdef CONFIG_OLPC_OPENFIRMWARE +#ifdef CONFIG_OLPC /* save OFW's pgdir table for later use when calling into OFW */ movl %cr3, %eax movl %eax, pa(olpc_ofw_pgd) @@ -623,7 +623,7 @@ ENTRY(initial_code) * BSS section */ __PAGE_ALIGNED_BSS - .align PAGE_SIZE_asm + .align PAGE_SIZE #ifdef CONFIG_X86_PAE initial_pg_pmd: .fill 1024*KPMDS,4,0 @@ -644,7 +644,7 @@ ENTRY(swapper_pg_dir) #ifdef CONFIG_X86_PAE __PAGE_ALIGNED_DATA /* Page-aligned for the benefit of paravirt? */ - .align PAGE_SIZE_asm + .align PAGE_SIZE ENTRY(initial_page_table) .long pa(initial_pg_pmd+PGD_IDENT_ATTR),0 /* low identity map */ # if KPMDS == 3 @@ -662,7 +662,7 @@ ENTRY(initial_page_table) # else # error "Kernel PMDs should be 1, 2 or 3" # endif - .align PAGE_SIZE_asm /* needs to be page-sized too */ + .align PAGE_SIZE /* needs to be page-sized too */ #endif .data diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 239046bd447..e11e39478a4 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -136,10 +136,9 @@ ident_complete: /* Fixup phys_base */ addq %rbp, phys_base(%rip) -#ifdef CONFIG_X86_TRAMPOLINE + /* Fixup trampoline */ addq %rbp, trampoline_level4_pgt + 0(%rip) addq %rbp, trampoline_level4_pgt + (511*8)(%rip) -#endif /* Due to ENTRY(), sometimes the empty space gets filled with * zeros. Better take a jmp than relying on empty space being diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 4ff5968f12d..bfe8f729e08 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -503,7 +503,7 @@ static int hpet_assign_irq(struct hpet_dev *dev) if (!irq) return -EINVAL; - set_irq_data(irq, dev); + irq_set_handler_data(irq, dev); if (hpet_setup_msi_irq(irq)) return -EINVAL; diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index e60c38cc0ee..12aff253768 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -145,7 +145,7 @@ EXPORT_SYMBOL_GPL(fpu_finit); * The _current_ task is using the FPU for the first time * so initialize it and set the mxcsr to its default * value at reset if we support XMM instructions and then - * remeber the current task has used the FPU. + * remember the current task has used the FPU. */ int init_fpu(struct task_struct *tsk) { diff --git a/arch/x86/kernel/i8237.c b/arch/x86/kernel/i8237.c index b42ca694dc6..8eeaa81de06 100644 --- a/arch/x86/kernel/i8237.c +++ b/arch/x86/kernel/i8237.c @@ -10,7 +10,7 @@ */ #include <linux/init.h> -#include <linux/sysdev.h> +#include <linux/syscore_ops.h> #include <asm/dma.h> @@ -21,7 +21,7 @@ * in asm/dma.h. */ -static int i8237A_resume(struct sys_device *dev) +static void i8237A_resume(void) { unsigned long flags; int i; @@ -41,31 +41,15 @@ static int i8237A_resume(struct sys_device *dev) enable_dma(4); release_dma_lock(flags); - - return 0; } -static int i8237A_suspend(struct sys_device *dev, pm_message_t state) -{ - return 0; -} - -static struct sysdev_class i8237_sysdev_class = { - .name = "i8237", - .suspend = i8237A_suspend, +static struct syscore_ops i8237_syscore_ops = { .resume = i8237A_resume, }; -static struct sys_device device_i8237A = { - .id = 0, - .cls = &i8237_sysdev_class, -}; - -static int __init i8237A_init_sysfs(void) +static int __init i8237A_init_ops(void) { - int error = sysdev_class_register(&i8237_sysdev_class); - if (!error) - error = sysdev_register(&device_i8237A); - return error; + register_syscore_ops(&i8237_syscore_ops); + return 0; } -device_initcall(i8237A_init_sysfs); +device_initcall(i8237A_init_ops); diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c index 212fe6590aa..577e90cadae 100644 --- a/arch/x86/kernel/i8253.c +++ b/arch/x86/kernel/i8253.c @@ -117,79 +117,6 @@ void __init setup_pit_timer(void) } #ifndef CONFIG_X86_64 -/* - * Since the PIT overflows every tick, its not very useful - * to just read by itself. So use jiffies to emulate a free - * running counter: - */ -static cycle_t pit_read(struct clocksource *cs) -{ - static int old_count; - static u32 old_jifs; - unsigned long flags; - int count; - u32 jifs; - - raw_spin_lock_irqsave(&i8253_lock, flags); - /* - * Although our caller may have the read side of xtime_lock, - * this is now a seqlock, and we are cheating in this routine - * by having side effects on state that we cannot undo if - * there is a collision on the seqlock and our caller has to - * retry. (Namely, old_jifs and old_count.) So we must treat - * jiffies as volatile despite the lock. We read jiffies - * before latching the timer count to guarantee that although - * the jiffies value might be older than the count (that is, - * the counter may underflow between the last point where - * jiffies was incremented and the point where we latch the - * count), it cannot be newer. - */ - jifs = jiffies; - outb_pit(0x00, PIT_MODE); /* latch the count ASAP */ - count = inb_pit(PIT_CH0); /* read the latched count */ - count |= inb_pit(PIT_CH0) << 8; - - /* VIA686a test code... reset the latch if count > max + 1 */ - if (count > LATCH) { - outb_pit(0x34, PIT_MODE); - outb_pit(LATCH & 0xff, PIT_CH0); - outb_pit(LATCH >> 8, PIT_CH0); - count = LATCH - 1; - } - - /* - * It's possible for count to appear to go the wrong way for a - * couple of reasons: - * - * 1. The timer counter underflows, but we haven't handled the - * resulting interrupt and incremented jiffies yet. - * 2. Hardware problem with the timer, not giving us continuous time, - * the counter does small "jumps" upwards on some Pentium systems, - * (see c't 95/10 page 335 for Neptun bug.) - * - * Previous attempts to handle these cases intelligently were - * buggy, so we just do the simple thing now. - */ - if (count > old_count && jifs == old_jifs) - count = old_count; - - old_count = count; - old_jifs = jifs; - - raw_spin_unlock_irqrestore(&i8253_lock, flags); - - count = (LATCH - 1) - count; - - return (cycle_t)(jifs * LATCH) + count; -} - -static struct clocksource pit_cs = { - .name = "pit", - .rating = 110, - .read = pit_read, - .mask = CLOCKSOURCE_MASK(32), -}; - static int __init init_pit_clocksource(void) { /* @@ -203,8 +130,7 @@ static int __init init_pit_clocksource(void) pit_ce.mode != CLOCK_EVT_MODE_PERIODIC) return 0; - return clocksource_register_hz(&pit_cs, CLOCK_TICK_RATE); + return clocksource_i8253_init(); } arch_initcall(init_pit_clocksource); - #endif /* !CONFIG_X86_64 */ diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index 20757cb2efa..65b8f5c2eeb 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -8,7 +8,7 @@ #include <linux/random.h> #include <linux/init.h> #include <linux/kernel_stat.h> -#include <linux/sysdev.h> +#include <linux/syscore_ops.h> #include <linux/bitops.h> #include <linux/acpi.h> #include <linux/io.h> @@ -112,7 +112,7 @@ static void make_8259A_irq(unsigned int irq) { disable_irq_nosync(irq); io_apic_irqs &= ~(1<<irq); - set_irq_chip_and_handler_name(irq, &i8259A_chip, handle_level_irq, + irq_set_chip_and_handler_name(irq, &i8259A_chip, handle_level_irq, i8259A_chip.name); enable_irq(irq); } @@ -245,20 +245,19 @@ static void save_ELCR(char *trigger) trigger[1] = inb(0x4d1) & 0xDE; } -static int i8259A_resume(struct sys_device *dev) +static void i8259A_resume(void) { init_8259A(i8259A_auto_eoi); restore_ELCR(irq_trigger); - return 0; } -static int i8259A_suspend(struct sys_device *dev, pm_message_t state) +static int i8259A_suspend(void) { save_ELCR(irq_trigger); return 0; } -static int i8259A_shutdown(struct sys_device *dev) +static void i8259A_shutdown(void) { /* Put the i8259A into a quiescent state that * the kernel initialization code can get it @@ -266,21 +265,14 @@ static int i8259A_shutdown(struct sys_device *dev) */ outb(0xff, PIC_MASTER_IMR); /* mask all of 8259A-1 */ outb(0xff, PIC_SLAVE_IMR); /* mask all of 8259A-1 */ - return 0; } -static struct sysdev_class i8259_sysdev_class = { - .name = "i8259", +static struct syscore_ops i8259_syscore_ops = { .suspend = i8259A_suspend, .resume = i8259A_resume, .shutdown = i8259A_shutdown, }; -static struct sys_device device_i8259A = { - .id = 0, - .cls = &i8259_sysdev_class, -}; - static void mask_8259A(void) { unsigned long flags; @@ -399,17 +391,12 @@ struct legacy_pic default_legacy_pic = { struct legacy_pic *legacy_pic = &default_legacy_pic; -static int __init i8259A_init_sysfs(void) +static int __init i8259A_init_ops(void) { - int error; - - if (legacy_pic != &default_legacy_pic) - return 0; + if (legacy_pic == &default_legacy_pic) + register_syscore_ops(&i8259_syscore_ops); - error = sysdev_class_register(&i8259_sysdev_class); - if (!error) - error = sysdev_register(&device_i8259A); - return error; + return 0; } -device_initcall(i8259A_init_sysfs); +device_initcall(i8259A_init_ops); diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c index 8eec0ec59af..8c968974253 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -14,22 +14,9 @@ #include <linux/slab.h> #include <linux/thread_info.h> #include <linux/syscalls.h> +#include <linux/bitmap.h> #include <asm/syscalls.h> -/* Set EXTENT bits starting at BASE in BITMAP to value TURN_ON. */ -static void set_bitmap(unsigned long *bitmap, unsigned int base, - unsigned int extent, int new_value) -{ - unsigned int i; - - for (i = base; i < base + extent; i++) { - if (new_value) - __set_bit(i, bitmap); - else - __clear_bit(i, bitmap); - } -} - /* * this changes the io permissions bitmap in the current task. */ @@ -69,7 +56,10 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on) */ tss = &per_cpu(init_tss, get_cpu()); - set_bitmap(t->io_bitmap_ptr, from, num, !turn_on); + if (turn_on) + bitmap_clear(t->io_bitmap_ptr, from, num); + else + bitmap_set(t->io_bitmap_ptr, from, num); /* * Search for a (possibly new) maximum. This is simple and stupid, diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 387b6a0c9e8..1cb0b9fc78d 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -8,6 +8,7 @@ #include <linux/seq_file.h> #include <linux/smp.h> #include <linux/ftrace.h> +#include <linux/delay.h> #include <asm/apic.h> #include <asm/io_apic.h> @@ -44,9 +45,9 @@ void ack_bad_irq(unsigned int irq) #define irq_stats(x) (&per_cpu(irq_stat, x)) /* - * /proc/interrupts printing: + * /proc/interrupts printing for arch specific interrupts */ -static int show_other_interrupts(struct seq_file *p, int prec) +int arch_show_interrupts(struct seq_file *p, int prec) { int j; @@ -122,59 +123,6 @@ static int show_other_interrupts(struct seq_file *p, int prec) return 0; } -int show_interrupts(struct seq_file *p, void *v) -{ - unsigned long flags, any_count = 0; - int i = *(loff_t *) v, j, prec; - struct irqaction *action; - struct irq_desc *desc; - - if (i > nr_irqs) - return 0; - - for (prec = 3, j = 1000; prec < 10 && j <= nr_irqs; ++prec) - j *= 10; - - if (i == nr_irqs) - return show_other_interrupts(p, prec); - - /* print header */ - if (i == 0) { - seq_printf(p, "%*s", prec + 8, ""); - for_each_online_cpu(j) - seq_printf(p, "CPU%-8d", j); - seq_putc(p, '\n'); - } - - desc = irq_to_desc(i); - if (!desc) - return 0; - - raw_spin_lock_irqsave(&desc->lock, flags); - for_each_online_cpu(j) - any_count |= kstat_irqs_cpu(i, j); - action = desc->action; - if (!action && !any_count) - goto out; - - seq_printf(p, "%*d: ", prec, i); - for_each_online_cpu(j) - seq_printf(p, "%10u ", kstat_irqs_cpu(i, j)); - seq_printf(p, " %8s", desc->irq_data.chip->name); - seq_printf(p, "-%-8s", desc->name); - - if (action) { - seq_printf(p, " %s", action->name); - while ((action = action->next) != NULL) - seq_printf(p, ", %s", action->name); - } - - seq_putc(p, '\n'); -out: - raw_spin_unlock_irqrestore(&desc->lock, flags); - return 0; -} - /* * /proc/stat helpers */ @@ -276,15 +224,6 @@ void smp_x86_platform_ipi(struct pt_regs *regs) EXPORT_SYMBOL_GPL(vector_used_by_percpu_irq); -#ifdef CONFIG_OF -unsigned int irq_create_of_mapping(struct device_node *controller, - const u32 *intspec, unsigned int intsize) -{ - return intspec[0]; -} -EXPORT_SYMBOL_GPL(irq_create_of_mapping); -#endif - #ifdef CONFIG_HOTPLUG_CPU /* A cpu has been removed from cpu_online_mask. Reset irq affinities. */ void fixup_irqs(void) @@ -293,6 +232,7 @@ void fixup_irqs(void) static int warned; struct irq_desc *desc; struct irq_data *data; + struct irq_chip *chip; for_each_irq_desc(irq, desc) { int break_affinity = 0; @@ -307,10 +247,10 @@ void fixup_irqs(void) /* interrupt's are disabled at this point */ raw_spin_lock(&desc->lock); - data = &desc->irq_data; + data = irq_desc_get_irq_data(desc); affinity = data->affinity; if (!irq_has_action(irq) || - cpumask_equal(affinity, cpu_online_mask)) { + cpumask_subset(affinity, cpu_online_mask)) { raw_spin_unlock(&desc->lock); continue; } @@ -327,16 +267,17 @@ void fixup_irqs(void) affinity = cpu_all_mask; } - if (!(desc->status & IRQ_MOVE_PCNTXT) && data->chip->irq_mask) - data->chip->irq_mask(data); + chip = irq_data_get_irq_chip(data); + if (!irqd_can_move_in_process_context(data) && chip->irq_mask) + chip->irq_mask(data); - if (data->chip->irq_set_affinity) - data->chip->irq_set_affinity(data, affinity, true); + if (chip->irq_set_affinity) + chip->irq_set_affinity(data, affinity, true); else if (!(warned++)) set_affinity = 0; - if (!(desc->status & IRQ_MOVE_PCNTXT) && data->chip->irq_unmask) - data->chip->irq_unmask(data); + if (!irqd_can_move_in_process_context(data) && chip->irq_unmask) + chip->irq_unmask(data); raw_spin_unlock(&desc->lock); @@ -368,10 +309,11 @@ void fixup_irqs(void) irq = __this_cpu_read(vector_irq[vector]); desc = irq_to_desc(irq); - data = &desc->irq_data; + data = irq_desc_get_irq_data(desc); + chip = irq_data_get_irq_chip(data); raw_spin_lock(&desc->lock); - if (data->chip->irq_retrigger) - data->chip->irq_retrigger(data); + if (chip->irq_retrigger) + chip->irq_retrigger(data); raw_spin_unlock(&desc->lock); } } diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 9974d21048f..72090705a65 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -172,7 +172,7 @@ asmlinkage void do_softirq(void) call_on_stack(__do_softirq, isp); /* - * Shouldnt happen, we returned above if in_interrupt(): + * Shouldn't happen, we returned above if in_interrupt(): */ WARN_ON_ONCE(softirq_count()); } diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index c752e973958..f470e4ef993 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -25,6 +25,7 @@ #include <asm/setup.h> #include <asm/i8259.h> #include <asm/traps.h> +#include <asm/prom.h> /* * ISA PIC or low IO-APIC triggered (INTA-cycle or APIC) interrupts: @@ -71,6 +72,7 @@ static irqreturn_t math_error_irq(int cpl, void *dev_id) static struct irqaction fpu_irq = { .handler = math_error_irq, .name = "fpu", + .flags = IRQF_NO_THREAD, }; #endif @@ -80,6 +82,7 @@ static struct irqaction fpu_irq = { static struct irqaction irq2 = { .handler = no_action, .name = "cascade", + .flags = IRQF_NO_THREAD, }; DEFINE_PER_CPU(vector_irq_t, vector_irq) = { @@ -110,7 +113,7 @@ void __init init_ISA_irqs(void) legacy_pic->init(0); for (i = 0; i < legacy_pic->nr_legacy_irqs; i++) - set_irq_chip_and_handler_name(i, chip, handle_level_irq, name); + irq_set_chip_and_handler_name(i, chip, handle_level_irq, name); } void __init init_IRQ(void) @@ -118,6 +121,12 @@ void __init init_IRQ(void) int i; /* + * We probably need a better place for this, but it works for + * now ... + */ + x86_add_irq_domains(); + + /* * On cpu 0, Assign IRQ0_VECTOR..IRQ15_VECTOR's to IRQ 0..15. * If these IRQ's are handled by legacy interrupt-controllers like PIC, * then this configuration will likely be static after the boot. If @@ -164,14 +173,77 @@ static void __init smp_intr_init(void) alloc_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt); /* IPIs for invalidation */ - alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+0, invalidate_interrupt0); - alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+1, invalidate_interrupt1); - alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+2, invalidate_interrupt2); - alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+3, invalidate_interrupt3); - alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+4, invalidate_interrupt4); - alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+5, invalidate_interrupt5); - alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+6, invalidate_interrupt6); - alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+7, invalidate_interrupt7); +#define ALLOC_INVTLB_VEC(NR) \ + alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+NR, \ + invalidate_interrupt##NR) + + switch (NUM_INVALIDATE_TLB_VECTORS) { + default: + ALLOC_INVTLB_VEC(31); + case 31: + ALLOC_INVTLB_VEC(30); + case 30: + ALLOC_INVTLB_VEC(29); + case 29: + ALLOC_INVTLB_VEC(28); + case 28: + ALLOC_INVTLB_VEC(27); + case 27: + ALLOC_INVTLB_VEC(26); + case 26: + ALLOC_INVTLB_VEC(25); + case 25: + ALLOC_INVTLB_VEC(24); + case 24: + ALLOC_INVTLB_VEC(23); + case 23: + ALLOC_INVTLB_VEC(22); + case 22: + ALLOC_INVTLB_VEC(21); + case 21: + ALLOC_INVTLB_VEC(20); + case 20: + ALLOC_INVTLB_VEC(19); + case 19: + ALLOC_INVTLB_VEC(18); + case 18: + ALLOC_INVTLB_VEC(17); + case 17: + ALLOC_INVTLB_VEC(16); + case 16: + ALLOC_INVTLB_VEC(15); + case 15: + ALLOC_INVTLB_VEC(14); + case 14: + ALLOC_INVTLB_VEC(13); + case 13: + ALLOC_INVTLB_VEC(12); + case 12: + ALLOC_INVTLB_VEC(11); + case 11: + ALLOC_INVTLB_VEC(10); + case 10: + ALLOC_INVTLB_VEC(9); + case 9: + ALLOC_INVTLB_VEC(8); + case 8: + ALLOC_INVTLB_VEC(7); + case 7: + ALLOC_INVTLB_VEC(6); + case 6: + ALLOC_INVTLB_VEC(5); + case 5: + ALLOC_INVTLB_VEC(4); + case 4: + ALLOC_INVTLB_VEC(3); + case 3: + ALLOC_INVTLB_VEC(2); + case 2: + ALLOC_INVTLB_VEC(1); + case 1: + ALLOC_INVTLB_VEC(0); + break; + } /* IPI for generic function call */ alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt); @@ -243,7 +315,7 @@ void __init native_init_IRQ(void) set_intr_gate(i, interrupt[i-FIRST_EXTERNAL_VECTOR]); } - if (!acpi_ioapic) + if (!acpi_ioapic && !of_ioapic) setup_irq(2, &irq2); #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index a4130005028..5f9ecff328b 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -121,8 +121,8 @@ char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs) memcpy(mem, (void *)regs + dbg_reg_def[regno].offset, dbg_reg_def[regno].size); - switch (regno) { #ifdef CONFIG_X86_32 + switch (regno) { case GDB_SS: if (!user_mode_vm(regs)) *(unsigned long *)mem = __KERNEL_DS; @@ -135,8 +135,8 @@ char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs) case GDB_FS: *(unsigned long *)mem = 0xFFFF; break; -#endif } +#endif return dbg_reg_def[regno].name; } @@ -278,7 +278,7 @@ static int hw_break_release_slot(int breakno) pevent = per_cpu_ptr(breakinfo[breakno].pev, cpu); if (dbg_release_bp_slot(*pevent)) /* - * The debugger is responisble for handing the retry on + * The debugger is responsible for handing the retry on * remove failure. */ return -1; @@ -533,15 +533,6 @@ static int __kgdb_notify(struct die_args *args, unsigned long cmd) } return NOTIFY_DONE; - case DIE_NMIWATCHDOG: - if (atomic_read(&kgdb_active) != -1) { - /* KGDB CPU roundup: */ - kgdb_nmicallback(raw_smp_processor_id(), regs); - return NOTIFY_STOP; - } - /* Enter debugger: */ - break; - case DIE_DEBUG: if (atomic_read(&kgdb_cpu_doing_single_step) != -1) { if (user_mode(regs)) diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index d91c477b3f6..c969fd9d156 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -1276,6 +1276,14 @@ static int __kprobes can_optimize(unsigned long paddr) if (!kallsyms_lookup_size_offset(paddr, &size, &offset)) return 0; + /* + * Do not optimize in the entry code due to the unstable + * stack handling. + */ + if ((paddr >= (unsigned long )__entry_text_start) && + (paddr < (unsigned long )__entry_text_end)) + return 0; + /* Check there is enough space for a relative jump. */ if (size - offset < RELATIVEJUMP_SIZE) return 0; diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 8dc44662394..33c07b0b122 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -493,7 +493,7 @@ static void __init kvm_smp_prepare_boot_cpu(void) native_smp_prepare_boot_cpu(); } -static void kvm_guest_cpu_online(void *dummy) +static void __cpuinit kvm_guest_cpu_online(void *dummy) { kvm_guest_cpu_init(); } diff --git a/arch/x86/kernel/mca_32.c b/arch/x86/kernel/mca_32.c index 63eaf659623..177183cbb6a 100644 --- a/arch/x86/kernel/mca_32.c +++ b/arch/x86/kernel/mca_32.c @@ -259,7 +259,7 @@ static int __init mca_init(void) /* * WARNING: Be careful when making changes here. Putting an adapter * and the motherboard simultaneously into setup mode may result in - * damage to chips (according to The Indispensible PC Hardware Book + * damage to chips (according to The Indispensable PC Hardware Book * by Hans-Peter Messmer). Also, we disable system interrupts (so * that we are not disturbed in the middle of this). */ diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index 0fe6d1a66c3..c5610384ab1 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -66,7 +66,6 @@ struct microcode_amd { unsigned int mpb[0]; }; -#define UCODE_MAX_SIZE 2048 #define UCODE_CONTAINER_SECTION_HDR 8 #define UCODE_CONTAINER_HEADER_SIZE 12 @@ -77,20 +76,20 @@ static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig) struct cpuinfo_x86 *c = &cpu_data(cpu); u32 dummy; - memset(csig, 0, sizeof(*csig)); if (c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) { - pr_warning("microcode: CPU%d: AMD CPU family 0x%x not " - "supported\n", cpu, c->x86); + pr_warning("CPU%d: family %d not supported\n", cpu, c->x86); return -1; } + rdmsr(MSR_AMD64_PATCH_LEVEL, csig->rev, dummy); - pr_info("CPU%d: patch_level=0x%x\n", cpu, csig->rev); + pr_info("CPU%d: patch_level=0x%08x\n", cpu, csig->rev); + return 0; } -static int get_matching_microcode(int cpu, void *mc, int rev) +static int get_matching_microcode(int cpu, struct microcode_header_amd *mc_hdr, + int rev) { - struct microcode_header_amd *mc_header = mc; unsigned int current_cpu_id; u16 equiv_cpu_id = 0; unsigned int i = 0; @@ -109,17 +108,17 @@ static int get_matching_microcode(int cpu, void *mc, int rev) if (!equiv_cpu_id) return 0; - if (mc_header->processor_rev_id != equiv_cpu_id) + if (mc_hdr->processor_rev_id != equiv_cpu_id) return 0; /* ucode might be chipset specific -- currently we don't support this */ - if (mc_header->nb_dev_id || mc_header->sb_dev_id) { - pr_err("CPU%d: loading of chipset specific code not yet supported\n", + if (mc_hdr->nb_dev_id || mc_hdr->sb_dev_id) { + pr_err("CPU%d: chipset specific code not yet supported\n", cpu); return 0; } - if (mc_header->patch_id <= rev) + if (mc_hdr->patch_id <= rev) return 0; return 1; @@ -144,71 +143,93 @@ static int apply_microcode_amd(int cpu) /* check current patch id and patch's id for match */ if (rev != mc_amd->hdr.patch_id) { - pr_err("CPU%d: update failed (for patch_level=0x%x)\n", + pr_err("CPU%d: update failed for patch_level=0x%08x\n", cpu, mc_amd->hdr.patch_id); return -1; } - pr_info("CPU%d: updated (new patch_level=0x%x)\n", cpu, rev); + pr_info("CPU%d: new patch_level=0x%08x\n", cpu, rev); uci->cpu_sig.rev = rev; return 0; } -static void * -get_next_ucode(const u8 *buf, unsigned int size, unsigned int *mc_size) +static unsigned int verify_ucode_size(int cpu, const u8 *buf, unsigned int size) { - unsigned int total_size; - u8 section_hdr[UCODE_CONTAINER_SECTION_HDR]; - void *mc; + struct cpuinfo_x86 *c = &cpu_data(cpu); + unsigned int max_size, actual_size; + +#define F1XH_MPB_MAX_SIZE 2048 +#define F14H_MPB_MAX_SIZE 1824 +#define F15H_MPB_MAX_SIZE 4096 + + switch (c->x86) { + case 0x14: + max_size = F14H_MPB_MAX_SIZE; + break; + case 0x15: + max_size = F15H_MPB_MAX_SIZE; + break; + default: + max_size = F1XH_MPB_MAX_SIZE; + break; + } - get_ucode_data(section_hdr, buf, UCODE_CONTAINER_SECTION_HDR); + actual_size = buf[4] + (buf[5] << 8); - if (section_hdr[0] != UCODE_UCODE_TYPE) { - pr_err("error: invalid type field in container file section header\n"); - return NULL; + if (actual_size > size || actual_size > max_size) { + pr_err("section size mismatch\n"); + return 0; } - total_size = (unsigned long) (section_hdr[4] + (section_hdr[5] << 8)); + return actual_size; +} - if (total_size > size || total_size > UCODE_MAX_SIZE) { - pr_err("error: size mismatch\n"); - return NULL; +static struct microcode_header_amd * +get_next_ucode(int cpu, const u8 *buf, unsigned int size, unsigned int *mc_size) +{ + struct microcode_header_amd *mc = NULL; + unsigned int actual_size = 0; + + if (buf[0] != UCODE_UCODE_TYPE) { + pr_err("invalid type field in container file section header\n"); + goto out; } - mc = vzalloc(UCODE_MAX_SIZE); + actual_size = verify_ucode_size(cpu, buf, size); + if (!actual_size) + goto out; + + mc = vzalloc(actual_size); if (!mc) - return NULL; + goto out; - get_ucode_data(mc, buf + UCODE_CONTAINER_SECTION_HDR, total_size); - *mc_size = total_size + UCODE_CONTAINER_SECTION_HDR; + get_ucode_data(mc, buf + UCODE_CONTAINER_SECTION_HDR, actual_size); + *mc_size = actual_size + UCODE_CONTAINER_SECTION_HDR; +out: return mc; } static int install_equiv_cpu_table(const u8 *buf) { - u8 *container_hdr[UCODE_CONTAINER_HEADER_SIZE]; - unsigned int *buf_pos = (unsigned int *)container_hdr; - unsigned long size; - - get_ucode_data(&container_hdr, buf, UCODE_CONTAINER_HEADER_SIZE); - - size = buf_pos[2]; - - if (buf_pos[1] != UCODE_EQUIV_CPU_TABLE_TYPE || !size) { - pr_err("error: invalid type field in container file section header\n"); - return 0; + unsigned int *ibuf = (unsigned int *)buf; + unsigned int type = ibuf[1]; + unsigned int size = ibuf[2]; + + if (type != UCODE_EQUIV_CPU_TABLE_TYPE || !size) { + pr_err("empty section/" + "invalid type field in container file section header\n"); + return -EINVAL; } equiv_cpu_table = vmalloc(size); if (!equiv_cpu_table) { pr_err("failed to allocate equivalent CPU table\n"); - return 0; + return -ENOMEM; } - buf += UCODE_CONTAINER_HEADER_SIZE; - get_ucode_data(equiv_cpu_table, buf, size); + get_ucode_data(equiv_cpu_table, buf + UCODE_CONTAINER_HEADER_SIZE, size); return size + UCODE_CONTAINER_HEADER_SIZE; /* add header length */ } @@ -223,16 +244,16 @@ static enum ucode_state generic_load_microcode(int cpu, const u8 *data, size_t size) { struct ucode_cpu_info *uci = ucode_cpu_info + cpu; + struct microcode_header_amd *mc_hdr = NULL; + unsigned int mc_size, leftover; + int offset; const u8 *ucode_ptr = data; void *new_mc = NULL; - void *mc; - int new_rev = uci->cpu_sig.rev; - unsigned int leftover; - unsigned long offset; + unsigned int new_rev = uci->cpu_sig.rev; enum ucode_state state = UCODE_OK; offset = install_equiv_cpu_table(ucode_ptr); - if (!offset) { + if (offset < 0) { pr_err("failed to create equivalent cpu table\n"); return UCODE_ERROR; } @@ -241,64 +262,65 @@ generic_load_microcode(int cpu, const u8 *data, size_t size) leftover = size - offset; while (leftover) { - unsigned int uninitialized_var(mc_size); - struct microcode_header_amd *mc_header; - - mc = get_next_ucode(ucode_ptr, leftover, &mc_size); - if (!mc) + mc_hdr = get_next_ucode(cpu, ucode_ptr, leftover, &mc_size); + if (!mc_hdr) break; - mc_header = (struct microcode_header_amd *)mc; - if (get_matching_microcode(cpu, mc, new_rev)) { + if (get_matching_microcode(cpu, mc_hdr, new_rev)) { vfree(new_mc); - new_rev = mc_header->patch_id; - new_mc = mc; + new_rev = mc_hdr->patch_id; + new_mc = mc_hdr; } else - vfree(mc); + vfree(mc_hdr); ucode_ptr += mc_size; leftover -= mc_size; } - if (new_mc) { - if (!leftover) { - vfree(uci->mc); - uci->mc = new_mc; - pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n", - cpu, new_rev, uci->cpu_sig.rev); - } else { - vfree(new_mc); - state = UCODE_ERROR; - } - } else + if (!new_mc) { state = UCODE_NFOUND; + goto free_table; + } + if (!leftover) { + vfree(uci->mc); + uci->mc = new_mc; + pr_debug("CPU%d update ucode (0x%08x -> 0x%08x)\n", + cpu, uci->cpu_sig.rev, new_rev); + } else { + vfree(new_mc); + state = UCODE_ERROR; + } + +free_table: free_equiv_cpu_table(); return state; } -static enum ucode_state request_microcode_fw(int cpu, struct device *device) +static enum ucode_state request_microcode_amd(int cpu, struct device *device) { const char *fw_name = "amd-ucode/microcode_amd.bin"; - const struct firmware *firmware; - enum ucode_state ret; + const struct firmware *fw; + enum ucode_state ret = UCODE_NFOUND; - if (request_firmware(&firmware, fw_name, device)) { - printk(KERN_ERR "microcode: failed to load file %s\n", fw_name); - return UCODE_NFOUND; + if (request_firmware(&fw, fw_name, device)) { + pr_err("failed to load file %s\n", fw_name); + goto out; } - if (*(u32 *)firmware->data != UCODE_MAGIC) { - pr_err("invalid UCODE_MAGIC (0x%08x)\n", - *(u32 *)firmware->data); - return UCODE_ERROR; + ret = UCODE_ERROR; + if (*(u32 *)fw->data != UCODE_MAGIC) { + pr_err("invalid magic value (0x%08x)\n", *(u32 *)fw->data); + goto fw_release; } - ret = generic_load_microcode(cpu, firmware->data, firmware->size); + ret = generic_load_microcode(cpu, fw->data, fw->size); - release_firmware(firmware); +fw_release: + release_firmware(fw); +out: return ret; } @@ -319,7 +341,7 @@ static void microcode_fini_cpu_amd(int cpu) static struct microcode_ops microcode_amd_ops = { .request_microcode_user = request_microcode_user, - .request_microcode_fw = request_microcode_fw, + .request_microcode_fw = request_microcode_amd, .collect_cpu_info = collect_cpu_info_amd, .apply_microcode = apply_microcode_amd, .microcode_fini_cpu = microcode_fini_cpu_amd, diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c index 1cca374a2ba..f9242800bc8 100644 --- a/arch/x86/kernel/microcode_core.c +++ b/arch/x86/kernel/microcode_core.c @@ -82,6 +82,7 @@ #include <linux/cpu.h> #include <linux/fs.h> #include <linux/mm.h> +#include <linux/syscore_ops.h> #include <asm/microcode.h> #include <asm/processor.h> @@ -417,8 +418,10 @@ static int mc_sysdev_add(struct sys_device *sys_dev) if (err) return err; - if (microcode_init_cpu(cpu) == UCODE_ERROR) - err = -EINVAL; + if (microcode_init_cpu(cpu) == UCODE_ERROR) { + sysfs_remove_group(&sys_dev->kobj, &mc_attr_group); + return -EINVAL; + } return err; } @@ -436,33 +439,25 @@ static int mc_sysdev_remove(struct sys_device *sys_dev) return 0; } -static int mc_sysdev_resume(struct sys_device *dev) +static struct sysdev_driver mc_sysdev_driver = { + .add = mc_sysdev_add, + .remove = mc_sysdev_remove, +}; + +/** + * mc_bp_resume - Update boot CPU microcode during resume. + */ +static void mc_bp_resume(void) { - int cpu = dev->id; + int cpu = smp_processor_id(); struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - if (!cpu_online(cpu)) - return 0; - - /* - * All non-bootup cpus are still disabled, - * so only CPU 0 will apply ucode here. - * - * Moreover, there can be no concurrent - * updates from any other places at this point. - */ - WARN_ON(cpu != 0); - if (uci->valid && uci->mc) microcode_ops->apply_microcode(cpu); - - return 0; } -static struct sysdev_driver mc_sysdev_driver = { - .add = mc_sysdev_add, - .remove = mc_sysdev_remove, - .resume = mc_sysdev_resume, +static struct syscore_ops mc_syscore_ops = { + .resume = mc_bp_resume, }; static __cpuinit int @@ -540,6 +535,7 @@ static int __init microcode_init(void) if (error) return error; + register_syscore_ops(&mc_syscore_ops); register_hotcpu_notifier(&mc_cpu_notifier); pr_info("Microcode Update Driver: v" MICROCODE_VERSION @@ -554,6 +550,7 @@ static void __exit microcode_exit(void) microcode_dev_exit(); unregister_hotcpu_notifier(&mc_cpu_notifier); + unregister_syscore_ops(&mc_syscore_ops); get_online_cpus(); mutex_lock(µcode_mutex); diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 01b0f6d0645..5a532ce646b 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -714,10 +714,6 @@ static void __init check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) *nr_m_spare += 1; } } -#else /* CONFIG_X86_IO_APIC */ -static -inline void __init check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) {} -#endif /* CONFIG_X86_IO_APIC */ static int check_slot(unsigned long mpc_new_phys, unsigned long mpc_new_length, int count) @@ -731,6 +727,10 @@ check_slot(unsigned long mpc_new_phys, unsigned long mpc_new_length, int count) return ret; } +#else /* CONFIG_X86_IO_APIC */ +static +inline void __init check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) {} +#endif /* CONFIG_X86_IO_APIC */ static int __init replace_intsrc_all(struct mpc_table *mpc, unsigned long mpc_new_phys, @@ -883,7 +883,7 @@ static int __init update_mp_table(void) if (!mpc_new_phys) { unsigned char old, new; - /* check if we can change the postion */ + /* check if we can change the position */ mpc->checksum = 0; old = mpf_checksum((unsigned char *)mpc, mpc->length); mpc->checksum = 0xff; @@ -892,7 +892,7 @@ static int __init update_mp_table(void) printk(KERN_INFO "mpc is readonly, please try alloc_mptable instead\n"); return 0; } - printk(KERN_INFO "use in-positon replacing\n"); + printk(KERN_INFO "use in-position replacing\n"); } else { mpf->physptr = mpc_new_phys; mpc_new = phys_to_virt(mpc_new_phys); diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index f56a117cef6..e8c33a30200 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -1279,7 +1279,7 @@ static int __init calgary_bus_has_devices(int bus, unsigned short pci_dev) if (pci_dev == PCI_DEVICE_ID_IBM_CALIOC2) { /* - * FIXME: properly scan for devices accross the + * FIXME: properly scan for devices across the * PCI-to-PCI bridge on every CalIOC2 port. */ return 1; @@ -1295,7 +1295,7 @@ static int __init calgary_bus_has_devices(int bus, unsigned short pci_dev) /* * calgary_init_bitmap_from_tce_table(): - * Funtion for kdump case. In the second/kdump kernel initialize + * Function for kdump case. In the second/kdump kernel initialize * the bitmap based on the tce table entries obtained from first kernel */ static void calgary_init_bitmap_from_tce_table(struct iommu_table *tbl) diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index c01ffa5b9b8..b117efd24f7 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -27,7 +27,7 @@ #include <linux/kdebug.h> #include <linux/scatterlist.h> #include <linux/iommu-helper.h> -#include <linux/sysdev.h> +#include <linux/syscore_ops.h> #include <linux/io.h> #include <linux/gfp.h> #include <asm/atomic.h> @@ -81,6 +81,9 @@ static u32 gart_unmapped_entry; #define AGPEXTERN #endif +/* GART can only remap to physical addresses < 1TB */ +#define GART_MAX_PHYS_ADDR (1ULL << 40) + /* backdoor interface to AGP driver */ AGPEXTERN int agp_memory_reserved; AGPEXTERN __u32 *agp_gatt_table; @@ -212,9 +215,13 @@ static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem, size_t size, int dir, unsigned long align_mask) { unsigned long npages = iommu_num_pages(phys_mem, size, PAGE_SIZE); - unsigned long iommu_page = alloc_iommu(dev, npages, align_mask); + unsigned long iommu_page; int i; + if (unlikely(phys_mem + size > GART_MAX_PHYS_ADDR)) + return bad_dma_addr; + + iommu_page = alloc_iommu(dev, npages, align_mask); if (iommu_page == -1) { if (!nonforced_iommu(dev, phys_mem, size)) return phys_mem; @@ -589,7 +596,7 @@ void set_up_gart_resume(u32 aper_order, u32 aper_alloc) aperture_alloc = aper_alloc; } -static void gart_fixup_northbridges(struct sys_device *dev) +static void gart_fixup_northbridges(void) { int i; @@ -613,33 +620,20 @@ static void gart_fixup_northbridges(struct sys_device *dev) } } -static int gart_resume(struct sys_device *dev) +static void gart_resume(void) { pr_info("PCI-DMA: Resuming GART IOMMU\n"); - gart_fixup_northbridges(dev); + gart_fixup_northbridges(); enable_gart_translations(); - - return 0; } -static int gart_suspend(struct sys_device *dev, pm_message_t state) -{ - return 0; -} - -static struct sysdev_class gart_sysdev_class = { - .name = "gart", - .suspend = gart_suspend, +static struct syscore_ops gart_syscore_ops = { .resume = gart_resume, }; -static struct sys_device device_gart = { - .cls = &gart_sysdev_class, -}; - /* * Private Northbridge GATT initialization in case we cannot use the * AGP driver for some reason. @@ -650,7 +644,7 @@ static __init int init_amd_gatt(struct agp_kern_info *info) unsigned aper_base, new_aper_base; struct pci_dev *dev; void *gatt; - int i, error; + int i; pr_info("PCI-DMA: Disabling AGP.\n"); @@ -685,12 +679,7 @@ static __init int init_amd_gatt(struct agp_kern_info *info) agp_gatt_table = gatt; - error = sysdev_class_register(&gart_sysdev_class); - if (!error) - error = sysdev_register(&device_gart); - if (error) - panic("Could not register gart_sysdev -- " - "would corrupt data on next suspend"); + register_syscore_ops(&gart_syscore_ops); flush_gart(); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index ff455419898..d46cbe46b7a 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -87,7 +87,7 @@ void exit_thread(void) void show_regs(struct pt_regs *regs) { show_registers(regs); - show_trace(NULL, regs, (unsigned long *)kernel_stack_pointer(regs)); + show_trace(NULL, regs, (unsigned long *)kernel_stack_pointer(regs), 0); } void show_regs_common(void) @@ -110,12 +110,9 @@ void show_regs_common(void) init_utsname()->release, (int)strcspn(init_utsname()->version, " "), init_utsname()->version); - printk(KERN_CONT " "); - printk(KERN_CONT "%s %s", vendor, product); - if (board) { - printk(KERN_CONT "/"); - printk(KERN_CONT "%s", board); - } + printk(KERN_CONT " %s %s", vendor, product); + if (board) + printk(KERN_CONT "/%s", board); printk(KERN_CONT "\n"); } diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index bd387e8f73b..6c9dd922ac0 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -501,6 +501,10 @@ void set_personality_64bit(void) /* Make sure to be in 64bit mode */ clear_thread_flag(TIF_IA32); + /* Ensure the corresponding mm is not marked. */ + if (current->mm) + current->mm->context.ia32_compat = 0; + /* TBD: overwrites user setup. Should have two bits. But 64bit processes have always behaved this way, so it's not too bad. The main problem is just that @@ -516,6 +520,10 @@ void set_personality_ia32(void) set_thread_flag(TIF_IA32); current->personality |= force_personality32; + /* Mark the associated mm as containing 32-bit tasks. */ + if (current->mm) + current->mm->context.ia32_compat = 1; + /* Prepare the first "return" to user space */ current_thread_info()->status |= TS_COMPAT; } diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 45892dc4b72..f65e5b521db 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -608,6 +608,9 @@ static int ptrace_write_dr7(struct task_struct *tsk, unsigned long data) unsigned len, type; struct perf_event *bp; + if (ptrace_get_breakpoints(tsk) < 0) + return -ESRCH; + data &= ~DR_CONTROL_RESERVED; old_dr7 = ptrace_get_dr7(thread->ptrace_bps); restore: @@ -655,6 +658,9 @@ restore: } goto restore; } + + ptrace_put_breakpoints(tsk); + return ((orig_ret < 0) ? orig_ret : rc); } @@ -668,10 +674,17 @@ static unsigned long ptrace_get_debugreg(struct task_struct *tsk, int n) if (n < HBP_NUM) { struct perf_event *bp; + + if (ptrace_get_breakpoints(tsk) < 0) + return -ESRCH; + bp = thread->ptrace_bps[n]; if (!bp) - return 0; - val = bp->hw.info.address; + val = 0; + else + val = bp->hw.info.address; + + ptrace_put_breakpoints(tsk); } else if (n == 6) { val = thread->debugreg6; } else if (n == 7) { @@ -686,6 +699,10 @@ static int ptrace_set_breakpoint_addr(struct task_struct *tsk, int nr, struct perf_event *bp; struct thread_struct *t = &tsk->thread; struct perf_event_attr attr; + int err = 0; + + if (ptrace_get_breakpoints(tsk) < 0) + return -ESRCH; if (!t->ptrace_bps[nr]) { ptrace_breakpoint_init(&attr); @@ -709,24 +726,23 @@ static int ptrace_set_breakpoint_addr(struct task_struct *tsk, int nr, * writing for the user. And anyway this is the previous * behaviour. */ - if (IS_ERR(bp)) - return PTR_ERR(bp); + if (IS_ERR(bp)) { + err = PTR_ERR(bp); + goto put; + } t->ptrace_bps[nr] = bp; } else { - int err; - bp = t->ptrace_bps[nr]; attr = bp->attr; attr.bp_addr = addr; err = modify_user_hw_breakpoint(bp, &attr); - if (err) - return err; } - - return 0; +put: + ptrace_put_breakpoints(tsk); + return err; } /* diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index fc7aae1e2bc..08c44b08bf5 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -6,6 +6,7 @@ #include <linux/dmi.h> #include <linux/sched.h> #include <linux/tboot.h> +#include <linux/delay.h> #include <acpi/reboot.h> #include <asm/io.h> #include <asm/apic.h> @@ -285,6 +286,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_BOARD_NAME, "P4S800"), }, }, + { /* Handle problems with rebooting on VersaLogic Menlow boards */ + .callback = set_bios_reboot, + .ident = "VersaLogic Menlow based board", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "VersaLogic Corporation"), + DMI_MATCH(DMI_BOARD_NAME, "VersaLogic Menlow board"), + }, + }, { } }; @@ -295,68 +304,16 @@ static int __init reboot_init(void) } core_initcall(reboot_init); -/* The following code and data reboots the machine by switching to real - mode and jumping to the BIOS reset entry point, as if the CPU has - really been reset. The previous version asked the keyboard - controller to pulse the CPU reset line, which is more thorough, but - doesn't work with at least one type of 486 motherboard. It is easy - to stop this code working; hence the copious comments. */ -static const unsigned long long -real_mode_gdt_entries [3] = -{ - 0x0000000000000000ULL, /* Null descriptor */ - 0x00009b000000ffffULL, /* 16-bit real-mode 64k code at 0x00000000 */ - 0x000093000100ffffULL /* 16-bit real-mode 64k data at 0x00000100 */ -}; +extern const unsigned char machine_real_restart_asm[]; +extern const u64 machine_real_restart_gdt[3]; -static const struct desc_ptr -real_mode_gdt = { sizeof (real_mode_gdt_entries) - 1, (long)real_mode_gdt_entries }, -real_mode_idt = { 0x3ff, 0 }; - -/* This is 16-bit protected mode code to disable paging and the cache, - switch to real mode and jump to the BIOS reset code. - - The instruction that switches to real mode by writing to CR0 must be - followed immediately by a far jump instruction, which set CS to a - valid value for real mode, and flushes the prefetch queue to avoid - running instructions that have already been decoded in protected - mode. - - Clears all the flags except ET, especially PG (paging), PE - (protected-mode enable) and TS (task switch for coprocessor state - save). Flushes the TLB after paging has been disabled. Sets CD and - NW, to disable the cache on a 486, and invalidates the cache. This - is more like the state of a 486 after reset. I don't know if - something else should be done for other chips. - - More could be done here to set up the registers as if a CPU reset had - occurred; hopefully real BIOSs don't assume much. */ -static const unsigned char real_mode_switch [] = -{ - 0x66, 0x0f, 0x20, 0xc0, /* movl %cr0,%eax */ - 0x66, 0x83, 0xe0, 0x11, /* andl $0x00000011,%eax */ - 0x66, 0x0d, 0x00, 0x00, 0x00, 0x60, /* orl $0x60000000,%eax */ - 0x66, 0x0f, 0x22, 0xc0, /* movl %eax,%cr0 */ - 0x66, 0x0f, 0x22, 0xd8, /* movl %eax,%cr3 */ - 0x66, 0x0f, 0x20, 0xc3, /* movl %cr0,%ebx */ - 0x66, 0x81, 0xe3, 0x00, 0x00, 0x00, 0x60, /* andl $0x60000000,%ebx */ - 0x74, 0x02, /* jz f */ - 0x0f, 0x09, /* wbinvd */ - 0x24, 0x10, /* f: andb $0x10,al */ - 0x66, 0x0f, 0x22, 0xc0 /* movl %eax,%cr0 */ -}; -static const unsigned char jump_to_bios [] = +void machine_real_restart(unsigned int type) { - 0xea, 0x00, 0x00, 0xff, 0xff /* ljmp $0xffff,$0x0000 */ -}; + void *restart_va; + unsigned long restart_pa; + void (*restart_lowmem)(unsigned int); + u64 *lowmem_gdt; -/* - * Switch to real mode and then execute the code - * specified by the code and length parameters. - * We assume that length will aways be less that 100! - */ -void machine_real_restart(const unsigned char *code, int length) -{ local_irq_disable(); /* Write zero to CMOS register number 0x0f, which the BIOS POST @@ -384,41 +341,23 @@ void machine_real_restart(const unsigned char *code, int length) too. */ *((unsigned short *)0x472) = reboot_mode; - /* For the switch to real mode, copy some code to low memory. It has - to be in the first 64k because it is running in 16-bit mode, and it - has to have the same physical and virtual address, because it turns - off paging. Copy it near the end of the first page, out of the way - of BIOS variables. */ - memcpy((void *)(0x1000 - sizeof(real_mode_switch) - 100), - real_mode_switch, sizeof (real_mode_switch)); - memcpy((void *)(0x1000 - 100), code, length); - - /* Set up the IDT for real mode. */ - load_idt(&real_mode_idt); - - /* Set up a GDT from which we can load segment descriptors for real - mode. The GDT is not used in real mode; it is just needed here to - prepare the descriptors. */ - load_gdt(&real_mode_gdt); - - /* Load the data segment registers, and thus the descriptors ready for - real mode. The base address of each segment is 0x100, 16 times the - selector value being loaded here. This is so that the segment - registers don't have to be reloaded after switching to real mode: - the values are consistent for real mode operation already. */ - __asm__ __volatile__ ("movl $0x0010,%%eax\n" - "\tmovl %%eax,%%ds\n" - "\tmovl %%eax,%%es\n" - "\tmovl %%eax,%%fs\n" - "\tmovl %%eax,%%gs\n" - "\tmovl %%eax,%%ss" : : : "eax"); - - /* Jump to the 16-bit code that we copied earlier. It disables paging - and the cache, switches to real mode, and jumps to the BIOS reset - entry point. */ - __asm__ __volatile__ ("ljmp $0x0008,%0" - : - : "i" ((void *)(0x1000 - sizeof (real_mode_switch) - 100))); + /* Patch the GDT in the low memory trampoline */ + lowmem_gdt = TRAMPOLINE_SYM(machine_real_restart_gdt); + + restart_va = TRAMPOLINE_SYM(machine_real_restart_asm); + restart_pa = virt_to_phys(restart_va); + restart_lowmem = (void (*)(unsigned int))restart_pa; + + /* GDT[0]: GDT self-pointer */ + lowmem_gdt[0] = + (u64)(sizeof(machine_real_restart_gdt) - 1) + + ((u64)virt_to_phys(lowmem_gdt) << 16); + /* GDT[1]: 64K real mode code segment */ + lowmem_gdt[1] = + GDT_ENTRY(0x009b, restart_pa, 0xffff); + + /* Jump to the identity-mapped low memory code */ + restart_lowmem(type); } #ifdef CONFIG_APM_MODULE EXPORT_SYMBOL(machine_real_restart); @@ -573,7 +512,7 @@ static void native_machine_emergency_restart(void) #ifdef CONFIG_X86_32 case BOOT_BIOS: - machine_real_restart(jump_to_bios, sizeof(jump_to_bios)); + machine_real_restart(MRR_BIOS); reboot_type = BOOT_KBD; break; diff --git a/arch/x86/kernel/reboot_32.S b/arch/x86/kernel/reboot_32.S new file mode 100644 index 00000000000..1d5c46df0d7 --- /dev/null +++ b/arch/x86/kernel/reboot_32.S @@ -0,0 +1,135 @@ +#include <linux/linkage.h> +#include <linux/init.h> +#include <asm/segment.h> +#include <asm/page_types.h> + +/* + * The following code and data reboots the machine by switching to real + * mode and jumping to the BIOS reset entry point, as if the CPU has + * really been reset. The previous version asked the keyboard + * controller to pulse the CPU reset line, which is more thorough, but + * doesn't work with at least one type of 486 motherboard. It is easy + * to stop this code working; hence the copious comments. + * + * This code is called with the restart type (0 = BIOS, 1 = APM) in %eax. + */ + .section ".x86_trampoline","a" + .balign 16 + .code32 +ENTRY(machine_real_restart_asm) +r_base = . + /* Get our own relocated address */ + call 1f +1: popl %ebx + subl $(1b - r_base), %ebx + + /* Compute the equivalent real-mode segment */ + movl %ebx, %ecx + shrl $4, %ecx + + /* Patch post-real-mode segment jump */ + movw (dispatch_table - r_base)(%ebx,%eax,2),%ax + movw %ax, (101f - r_base)(%ebx) + movw %cx, (102f - r_base)(%ebx) + + /* Set up the IDT for real mode. */ + lidtl (machine_real_restart_idt - r_base)(%ebx) + + /* + * Set up a GDT from which we can load segment descriptors for real + * mode. The GDT is not used in real mode; it is just needed here to + * prepare the descriptors. + */ + lgdtl (machine_real_restart_gdt - r_base)(%ebx) + + /* + * Load the data segment registers with 16-bit compatible values + */ + movl $16, %ecx + movl %ecx, %ds + movl %ecx, %es + movl %ecx, %fs + movl %ecx, %gs + movl %ecx, %ss + ljmpl $8, $1f - r_base + +/* + * This is 16-bit protected mode code to disable paging and the cache, + * switch to real mode and jump to the BIOS reset code. + * + * The instruction that switches to real mode by writing to CR0 must be + * followed immediately by a far jump instruction, which set CS to a + * valid value for real mode, and flushes the prefetch queue to avoid + * running instructions that have already been decoded in protected + * mode. + * + * Clears all the flags except ET, especially PG (paging), PE + * (protected-mode enable) and TS (task switch for coprocessor state + * save). Flushes the TLB after paging has been disabled. Sets CD and + * NW, to disable the cache on a 486, and invalidates the cache. This + * is more like the state of a 486 after reset. I don't know if + * something else should be done for other chips. + * + * More could be done here to set up the registers as if a CPU reset had + * occurred; hopefully real BIOSs don't assume much. This is not the + * actual BIOS entry point, anyway (that is at 0xfffffff0). + * + * Most of this work is probably excessive, but it is what is tested. + */ + .code16 +1: + xorl %ecx, %ecx + movl %cr0, %eax + andl $0x00000011, %eax + orl $0x60000000, %eax + movl %eax, %cr0 + movl %ecx, %cr3 + movl %cr0, %edx + andl $0x60000000, %edx /* If no cache bits -> no wbinvd */ + jz 2f + wbinvd +2: + andb $0x10, %al + movl %eax, %cr0 + .byte 0xea /* ljmpw */ +101: .word 0 /* Offset */ +102: .word 0 /* Segment */ + +bios: + ljmpw $0xf000, $0xfff0 + +apm: + movw $0x1000, %ax + movw %ax, %ss + movw $0xf000, %sp + movw $0x5307, %ax + movw $0x0001, %bx + movw $0x0003, %cx + int $0x15 + +END(machine_real_restart_asm) + + .balign 16 + /* These must match <asm/reboot.h */ +dispatch_table: + .word bios - r_base + .word apm - r_base +END(dispatch_table) + + .balign 16 +machine_real_restart_idt: + .word 0xffff /* Length - real mode default value */ + .long 0 /* Base - real mode default value */ +END(machine_real_restart_idt) + + .balign 16 +ENTRY(machine_real_restart_gdt) + .quad 0 /* Self-pointer, filled in by PM code */ + .quad 0 /* 16-bit code segment, filled in by PM code */ + /* + * 16-bit data segment with the selector value 16 = 0x10 and + * base value 0x100; since this is consistent with real mode + * semantics we don't have to reload the segments once CR0.PE = 0. + */ + .quad GDT_ENTRY(0x0093, 0x100, 0xffff) +END(machine_real_restart_gdt) diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index 6f39cab052d..3f2ad2640d8 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -6,6 +6,7 @@ #include <linux/acpi.h> #include <linux/bcd.h> #include <linux/pnp.h> +#include <linux/of.h> #include <asm/vsyscall.h> #include <asm/x86_init.h> @@ -236,6 +237,8 @@ static __init int add_rtc_cmos(void) } } #endif + if (of_have_populated_dt()) + return 0; platform_device_register(&rtc_device); dev_info(&rtc_device.dev, diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index d3cfe26c025..4be9b398470 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -113,6 +113,7 @@ #endif #include <asm/mce.h> #include <asm/alternative.h> +#include <asm/prom.h> /* * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries. @@ -297,6 +298,9 @@ static void __init init_gbpages(void) static inline void init_gbpages(void) { } +static void __init cleanup_highmap(void) +{ +} #endif static void __init reserve_brk(void) @@ -429,16 +433,30 @@ static void __init parse_setup_data(void) return; pa_data = boot_params.hdr.setup_data; while (pa_data) { - data = early_memremap(pa_data, PAGE_SIZE); + u32 data_len, map_len; + + map_len = max(PAGE_SIZE - (pa_data & ~PAGE_MASK), + (u64)sizeof(struct setup_data)); + data = early_memremap(pa_data, map_len); + data_len = data->len + sizeof(struct setup_data); + if (data_len > map_len) { + early_iounmap(data, map_len); + data = early_memremap(pa_data, data_len); + map_len = data_len; + } + switch (data->type) { case SETUP_E820_EXT: - parse_e820_ext(data, pa_data); + parse_e820_ext(data); + break; + case SETUP_DTB: + add_dtb(pa_data); break; default: break; } pa_data = data->next; - early_iounmap(data, PAGE_SIZE); + early_iounmap(data, map_len); } } @@ -601,28 +619,6 @@ void __init reserve_standard_io_resources(void) } -/* - * Note: elfcorehdr_addr is not just limited to vmcore. It is also used by - * is_kdump_kernel() to determine if we are booting after a panic. Hence - * ifdef it under CONFIG_CRASH_DUMP and not CONFIG_PROC_VMCORE. - */ - -#ifdef CONFIG_CRASH_DUMP -/* elfcorehdr= specifies the location of elf core header - * stored by the crashed kernel. This option will be passed - * by kexec loader to the capture kernel. - */ -static int __init setup_elfcorehdr(char *arg) -{ - char *end; - if (!arg) - return -EINVAL; - elfcorehdr_addr = memparse(arg, &end); - return end > arg ? 0 : -EINVAL; -} -early_param("elfcorehdr", setup_elfcorehdr); -#endif - static __init void reserve_ibft_region(void) { unsigned long addr, size = 0; @@ -680,15 +676,6 @@ static int __init parse_reservelow(char *p) early_param("reservelow", parse_reservelow); -static u64 __init get_max_mapped(void) -{ - u64 end = max_pfn_mapped; - - end <<= PAGE_SHIFT; - - return end; -} - /* * Determine if we were loaded by an EFI loader. If so, then we have also been * passed the efi memmap, systab, etc., so we should use these data structures @@ -704,8 +691,6 @@ static u64 __init get_max_mapped(void) void __init setup_arch(char **cmdline_p) { - int acpi = 0; - int amd = 0; unsigned long flags; #ifdef CONFIG_X86_32 @@ -922,6 +907,8 @@ void __init setup_arch(char **cmdline_p) */ reserve_brk(); + cleanup_highmap(); + memblock.current_limit = get_max_mapped(); memblock_x86_fill(); @@ -935,15 +922,8 @@ void __init setup_arch(char **cmdline_p) printk(KERN_DEBUG "initial memory mapped : 0 - %08lx\n", max_pfn_mapped<<PAGE_SHIFT); - reserve_trampoline_memory(); + setup_trampolines(); -#ifdef CONFIG_ACPI_SLEEP - /* - * Reserve low memory region for sleep support. - * even before init_memory_mapping - */ - acpi_reserve_wakeup_memory(); -#endif init_gbpages(); /* max_pfn_mapped is updated here */ @@ -984,19 +964,7 @@ void __init setup_arch(char **cmdline_p) early_acpi_boot_init(); -#ifdef CONFIG_ACPI_NUMA - /* - * Parse SRAT to discover nodes. - */ - acpi = acpi_numa_init(); -#endif - -#ifdef CONFIG_AMD_NUMA - if (!acpi) - amd = !amd_numa_init(0, max_pfn); -#endif - - initmem_init(0, max_pfn, acpi, amd); + initmem_init(); memblock_find_dma_reserve(); dma32_reserve_bootmem(); @@ -1008,6 +976,11 @@ void __init setup_arch(char **cmdline_p) paging_init(); x86_init.paging.pagetable_setup_done(swapper_pg_dir); + if (boot_cpu_data.cpuid_level >= 0) { + /* A CPU has %cr4 if and only if it has CPUID */ + mmu_cr4_features = read_cr4(); + } + #ifdef CONFIG_X86_32 /* sync back kernel address range */ clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY, @@ -1029,8 +1002,8 @@ void __init setup_arch(char **cmdline_p) * Read APIC and some other early information from ACPI tables. */ acpi_boot_init(); - sfi_init(); + x86_dtb_init(); /* * get boot-time SMP configuration: @@ -1040,9 +1013,7 @@ void __init setup_arch(char **cmdline_p) prefill_possible_map(); -#ifdef CONFIG_X86_64 init_cpu_to_node(); -#endif init_apic_mappings(); ioapic_and_gsi_init(); @@ -1066,6 +1037,8 @@ void __init setup_arch(char **cmdline_p) #endif x86_init.oem.banner(); + x86_init.timers.wallclock_init(); + mcheck_init(); local_irq_save(flags); diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 002b79685f7..71f4727da37 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -225,10 +225,15 @@ void __init setup_per_cpu_areas(void) per_cpu(x86_bios_cpu_apicid, cpu) = early_per_cpu_map(x86_bios_cpu_apicid, cpu); #endif +#ifdef CONFIG_X86_32 + per_cpu(x86_cpu_to_logical_apicid, cpu) = + early_per_cpu_map(x86_cpu_to_logical_apicid, cpu); +#endif #ifdef CONFIG_X86_64 per_cpu(irq_stack_ptr, cpu) = per_cpu(irq_stack_union.irq_stack, cpu) + IRQ_STACK_SIZE - 64; +#endif #ifdef CONFIG_NUMA per_cpu(x86_cpu_to_node_map, cpu) = early_per_cpu_map(x86_cpu_to_node_map, cpu); @@ -242,7 +247,6 @@ void __init setup_per_cpu_areas(void) */ set_cpu_numa_node(cpu, early_cpu_to_node(cpu)); #endif -#endif /* * Up to this point, the boot CPU has been using .init.data * area. Reload any changed state for the boot CPU. @@ -256,7 +260,10 @@ void __init setup_per_cpu_areas(void) early_per_cpu_ptr(x86_cpu_to_apicid) = NULL; early_per_cpu_ptr(x86_bios_cpu_apicid) = NULL; #endif -#if defined(CONFIG_X86_64) && defined(CONFIG_NUMA) +#ifdef CONFIG_X86_32 + early_per_cpu_ptr(x86_cpu_to_logical_apicid) = NULL; +#endif +#ifdef CONFIG_NUMA early_per_cpu_ptr(x86_cpu_to_node_map) = NULL; #endif diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 08776a95348..c2871d3c71b 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -64,6 +64,7 @@ #include <asm/mtrr.h> #include <asm/mwait.h> #include <asm/apic.h> +#include <asm/io_apic.h> #include <asm/setup.h> #include <asm/uv/uv.h> #include <linux/mc146818rtc.h> @@ -71,10 +72,6 @@ #include <asm/smpboot_hooks.h> #include <asm/i8259.h> -#ifdef CONFIG_X86_32 -u8 apicid_2_node[MAX_APICID]; -#endif - /* State of each CPU */ DEFINE_PER_CPU(int, cpu_state) = { 0 }; @@ -130,68 +127,14 @@ EXPORT_PER_CPU_SYMBOL(cpu_sibling_map); DEFINE_PER_CPU(cpumask_var_t, cpu_core_map); EXPORT_PER_CPU_SYMBOL(cpu_core_map); +DEFINE_PER_CPU(cpumask_var_t, cpu_llc_shared_map); + /* Per CPU bogomips and other parameters */ DEFINE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info); EXPORT_PER_CPU_SYMBOL(cpu_info); atomic_t init_deasserted; -#if defined(CONFIG_NUMA) && defined(CONFIG_X86_32) -/* which node each logical CPU is on */ -int cpu_to_node_map[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = 0 }; -EXPORT_SYMBOL(cpu_to_node_map); - -/* set up a mapping between cpu and node. */ -static void map_cpu_to_node(int cpu, int node) -{ - printk(KERN_INFO "Mapping cpu %d to node %d\n", cpu, node); - cpumask_set_cpu(cpu, node_to_cpumask_map[node]); - cpu_to_node_map[cpu] = node; -} - -/* undo a mapping between cpu and node. */ -static void unmap_cpu_to_node(int cpu) -{ - int node; - - printk(KERN_INFO "Unmapping cpu %d from all nodes\n", cpu); - for (node = 0; node < MAX_NUMNODES; node++) - cpumask_clear_cpu(cpu, node_to_cpumask_map[node]); - cpu_to_node_map[cpu] = 0; -} -#else /* !(CONFIG_NUMA && CONFIG_X86_32) */ -#define map_cpu_to_node(cpu, node) ({}) -#define unmap_cpu_to_node(cpu) ({}) -#endif - -#ifdef CONFIG_X86_32 -static int boot_cpu_logical_apicid; - -u8 cpu_2_logical_apicid[NR_CPUS] __read_mostly = - { [0 ... NR_CPUS-1] = BAD_APICID }; - -static void map_cpu_to_logical_apicid(void) -{ - int cpu = smp_processor_id(); - int apicid = logical_smp_processor_id(); - int node = apic->apicid_to_node(apicid); - - if (!node_online(node)) - node = first_online_node; - - cpu_2_logical_apicid[cpu] = apicid; - map_cpu_to_node(cpu, node); -} - -void numa_remove_cpu(int cpu) -{ - cpu_2_logical_apicid[cpu] = BAD_APICID; - unmap_cpu_to_node(cpu); -} -#else -#define map_cpu_to_logical_apicid() do {} while (0) -#endif - /* * Report back to the Boot Processor. * Running on AP. @@ -259,7 +202,6 @@ static void __cpuinit smp_callin(void) apic->smp_callin_clear_local_apic(); setup_local_APIC(); end_local_APIC_setup(); - map_cpu_to_logical_apicid(); /* * Need to setup vector mappings before we enable interrupts. @@ -355,23 +297,6 @@ notrace static void __cpuinit start_secondary(void *unused) cpu_idle(); } -#ifdef CONFIG_CPUMASK_OFFSTACK -/* In this case, llc_shared_map is a pointer to a cpumask. */ -static inline void copy_cpuinfo_x86(struct cpuinfo_x86 *dst, - const struct cpuinfo_x86 *src) -{ - struct cpumask *llc = dst->llc_shared_map; - *dst = *src; - dst->llc_shared_map = llc; -} -#else -static inline void copy_cpuinfo_x86(struct cpuinfo_x86 *dst, - const struct cpuinfo_x86 *src) -{ - *dst = *src; -} -#endif /* CONFIG_CPUMASK_OFFSTACK */ - /* * The bootstrap kernel entry code has set these up. Save them for * a given CPU @@ -381,7 +306,7 @@ void __cpuinit smp_store_cpu_info(int id) { struct cpuinfo_x86 *c = &cpu_data(id); - copy_cpuinfo_x86(c, &boot_cpu_data); + *c = boot_cpu_data; c->cpu_index = id; if (id != 0) identify_secondary_cpu(c); @@ -389,15 +314,12 @@ void __cpuinit smp_store_cpu_info(int id) static void __cpuinit link_thread_siblings(int cpu1, int cpu2) { - struct cpuinfo_x86 *c1 = &cpu_data(cpu1); - struct cpuinfo_x86 *c2 = &cpu_data(cpu2); - cpumask_set_cpu(cpu1, cpu_sibling_mask(cpu2)); cpumask_set_cpu(cpu2, cpu_sibling_mask(cpu1)); cpumask_set_cpu(cpu1, cpu_core_mask(cpu2)); cpumask_set_cpu(cpu2, cpu_core_mask(cpu1)); - cpumask_set_cpu(cpu1, c2->llc_shared_map); - cpumask_set_cpu(cpu2, c1->llc_shared_map); + cpumask_set_cpu(cpu1, cpu_llc_shared_mask(cpu2)); + cpumask_set_cpu(cpu2, cpu_llc_shared_mask(cpu1)); } @@ -414,6 +336,7 @@ void __cpuinit set_cpu_sibling_map(int cpu) if (cpu_has(c, X86_FEATURE_TOPOEXT)) { if (c->phys_proc_id == o->phys_proc_id && + per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i) && c->compute_unit_id == o->compute_unit_id) link_thread_siblings(cpu, i); } else if (c->phys_proc_id == o->phys_proc_id && @@ -425,7 +348,7 @@ void __cpuinit set_cpu_sibling_map(int cpu) cpumask_set_cpu(cpu, cpu_sibling_mask(cpu)); } - cpumask_set_cpu(cpu, c->llc_shared_map); + cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu)); if (__this_cpu_read(cpu_info.x86_max_cores) == 1) { cpumask_copy(cpu_core_mask(cpu), cpu_sibling_mask(cpu)); @@ -436,8 +359,8 @@ void __cpuinit set_cpu_sibling_map(int cpu) for_each_cpu(i, cpu_sibling_setup_mask) { if (per_cpu(cpu_llc_id, cpu) != BAD_APICID && per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) { - cpumask_set_cpu(i, c->llc_shared_map); - cpumask_set_cpu(cpu, cpu_data(i).llc_shared_map); + cpumask_set_cpu(i, cpu_llc_shared_mask(cpu)); + cpumask_set_cpu(cpu, cpu_llc_shared_mask(i)); } if (c->phys_proc_id == cpu_data(i).phys_proc_id) { cpumask_set_cpu(i, cpu_core_mask(cpu)); @@ -476,7 +399,7 @@ const struct cpumask *cpu_coregroup_mask(int cpu) !(cpu_has(c, X86_FEATURE_AMD_DCM))) return cpu_core_mask(cpu); else - return c->llc_shared_map; + return cpu_llc_shared_mask(cpu); } static void impress_friends(void) @@ -788,7 +711,7 @@ do_rest: stack_start = c_idle.idle->thread.sp; /* start_ip had better be page-aligned! */ - start_ip = setup_trampoline(); + start_ip = trampoline_address(); /* So we see what's up */ announce_cpu(cpu, apicid); @@ -798,6 +721,8 @@ do_rest: * the targeted processor. */ + printk(KERN_DEBUG "smpboot cpu %d: start_ip = %lx\n", cpu, start_ip); + atomic_set(&init_deasserted, 0); if (get_uv_system_type() != UV_NON_UNIQUE_APIC) { @@ -851,8 +776,8 @@ do_rest: pr_debug("CPU%d: has booted.\n", cpu); else { boot_error = 1; - if (*((volatile unsigned char *)trampoline_base) - == 0xA5) + if (*(volatile u32 *)TRAMPOLINE_SYM(trampoline_status) + == 0xA5A5A5A5) /* trampoline started but...? */ pr_err("CPU%d: Stuck ??\n", cpu); else @@ -878,7 +803,7 @@ do_rest: } /* mark "stuck" area as not stuck */ - *((volatile unsigned long *)trampoline_base) = 0; + *(volatile u32 *)TRAMPOLINE_SYM(trampoline_status) = 0; if (get_uv_system_type() != UV_NON_UNIQUE_APIC) { /* @@ -945,6 +870,14 @@ int __cpuinit native_cpu_up(unsigned int cpu) return 0; } +/** + * arch_disable_smp_support() - disables SMP support for x86 at runtime + */ +void arch_disable_smp_support(void) +{ + disable_ioapic_support(); +} + /* * Fall back to non SMP mode after errors. * @@ -960,7 +893,6 @@ static __init void disable_smp(void) physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map); else physid_set_mask_of_physid(0, &phys_cpu_present_map); - map_cpu_to_logical_apicid(); cpumask_set_cpu(0, cpu_sibling_mask(0)); cpumask_set_cpu(0, cpu_core_mask(0)); } @@ -1045,7 +977,7 @@ static int __init smp_sanity_check(unsigned max_cpus) "(tell your hw vendor)\n"); } smpboot_clear_io_apic(); - arch_disable_smp_support(); + disable_ioapic_support(); return -1; } @@ -1089,21 +1021,19 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) preempt_disable(); smp_cpu_index_default(); - memcpy(__this_cpu_ptr(&cpu_info), &boot_cpu_data, sizeof(cpu_info)); - cpumask_copy(cpu_callin_mask, cpumask_of(0)); - mb(); + /* * Setup boot CPU information */ smp_store_cpu_info(0); /* Final full version of the data */ -#ifdef CONFIG_X86_32 - boot_cpu_logical_apicid = logical_smp_processor_id(); -#endif + cpumask_copy(cpu_callin_mask, cpumask_of(0)); + mb(); + current_thread_info()->cpu = 0; /* needed? */ for_each_possible_cpu(i) { zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL); zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL); - zalloc_cpumask_var(&cpu_data(i).llc_shared_map, GFP_KERNEL); + zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL); } set_cpu_sibling_map(0); @@ -1139,8 +1069,6 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) bsp_end_local_APIC_setup(); - map_cpu_to_logical_apicid(); - if (apic->setup_portio_remap) apic->setup_portio_remap(); diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index 938c8e10a19..6515733a289 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -73,7 +73,7 @@ static const struct stacktrace_ops save_stack_ops_nosched = { */ void save_stack_trace(struct stack_trace *trace) { - dump_trace(current, NULL, NULL, &save_stack_ops, trace); + dump_trace(current, NULL, NULL, 0, &save_stack_ops, trace); if (trace->nr_entries < trace->max_entries) trace->entries[trace->nr_entries++] = ULONG_MAX; } @@ -81,14 +81,14 @@ EXPORT_SYMBOL_GPL(save_stack_trace); void save_stack_trace_regs(struct stack_trace *trace, struct pt_regs *regs) { - dump_trace(current, regs, NULL, &save_stack_ops, trace); + dump_trace(current, regs, NULL, 0, &save_stack_ops, trace); if (trace->nr_entries < trace->max_entries) trace->entries[trace->nr_entries++] = ULONG_MAX; } void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) { - dump_trace(tsk, NULL, NULL, &save_stack_ops_nosched, trace); + dump_trace(tsk, NULL, NULL, 0, &save_stack_ops_nosched, trace); if (trace->nr_entries < trace->max_entries) trace->entries[trace->nr_entries++] = ULONG_MAX; } diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index 58de45ee08b..7977f0cfe33 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -166,7 +166,7 @@ static void enable_step(struct task_struct *child, bool block) * Make sure block stepping (BTF) is not enabled unless it should be. * Note that we don't try to worry about any is_setting_trap_flag() * instructions after the first when using block stepping. - * So noone should try to use debugger block stepping in a program + * So no one should try to use debugger block stepping in a program * that uses user-mode single stepping itself. */ if (enable_single_step(child) && block) { diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S index b35786dc9b8..abce34d5c79 100644 --- a/arch/x86/kernel/syscall_table_32.S +++ b/arch/x86/kernel/syscall_table_32.S @@ -340,3 +340,7 @@ ENTRY(sys_call_table) .long sys_fanotify_init .long sys_fanotify_mark .long sys_prlimit64 /* 340 */ + .long sys_name_to_handle_at + .long sys_open_by_handle_at + .long sys_clock_adjtime + .long sys_syncfs diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c index 7e4515957a1..8927486a464 100644 --- a/arch/x86/kernel/topology.c +++ b/arch/x86/kernel/topology.c @@ -39,7 +39,7 @@ int __ref arch_register_cpu(int num) /* * CPU0 cannot be offlined due to several * restrictions and assumptions in kernel. This basically - * doesnt add a control file, one cannot attempt to offline + * doesn't add a control file, one cannot attempt to offline * BSP. * * Also certain PCI quirks require not to enable hotplug control diff --git a/arch/x86/kernel/trampoline.c b/arch/x86/kernel/trampoline.c index a375616d77f..a91ae7709b4 100644 --- a/arch/x86/kernel/trampoline.c +++ b/arch/x86/kernel/trampoline.c @@ -2,39 +2,41 @@ #include <linux/memblock.h> #include <asm/trampoline.h> +#include <asm/cacheflush.h> #include <asm/pgtable.h> -#if defined(CONFIG_X86_64) && defined(CONFIG_ACPI_SLEEP) -#define __trampinit -#define __trampinitdata -#else -#define __trampinit __cpuinit -#define __trampinitdata __cpuinitdata -#endif +unsigned char *x86_trampoline_base; -/* ready for x86_64 and x86 */ -unsigned char *__trampinitdata trampoline_base; - -void __init reserve_trampoline_memory(void) +void __init setup_trampolines(void) { phys_addr_t mem; + size_t size = PAGE_ALIGN(x86_trampoline_end - x86_trampoline_start); /* Has to be in very low memory so we can execute real-mode AP code. */ - mem = memblock_find_in_range(0, 1<<20, TRAMPOLINE_SIZE, PAGE_SIZE); + mem = memblock_find_in_range(0, 1<<20, size, PAGE_SIZE); if (mem == MEMBLOCK_ERROR) panic("Cannot allocate trampoline\n"); - trampoline_base = __va(mem); - memblock_x86_reserve_range(mem, mem + TRAMPOLINE_SIZE, "TRAMPOLINE"); + x86_trampoline_base = __va(mem); + memblock_x86_reserve_range(mem, mem + size, "TRAMPOLINE"); + + printk(KERN_DEBUG "Base memory trampoline at [%p] %llx size %zu\n", + x86_trampoline_base, (unsigned long long)mem, size); + + memcpy(x86_trampoline_base, x86_trampoline_start, size); } /* - * Currently trivial. Write the real->protected mode - * bootstrap into the page concerned. The caller - * has made sure it's suitably aligned. + * setup_trampolines() gets called very early, to guarantee the + * availability of low memory. This is before the proper kernel page + * tables are set up, so we cannot set page permissions in that + * function. Thus, we use an arch_initcall instead. */ -unsigned long __trampinit setup_trampoline(void) +static int __init configure_trampolines(void) { - memcpy(trampoline_base, trampoline_data, TRAMPOLINE_SIZE); - return virt_to_phys(trampoline_base); + size_t size = PAGE_ALIGN(x86_trampoline_end - x86_trampoline_start); + + set_memory_x((unsigned long)x86_trampoline_base, size >> PAGE_SHIFT); + return 0; } +arch_initcall(configure_trampolines); diff --git a/arch/x86/kernel/trampoline_32.S b/arch/x86/kernel/trampoline_32.S index 8508237e8e4..451c0a7ef7f 100644 --- a/arch/x86/kernel/trampoline_32.S +++ b/arch/x86/kernel/trampoline_32.S @@ -32,9 +32,11 @@ #include <asm/segment.h> #include <asm/page_types.h> -/* We can free up trampoline after bootup if cpu hotplug is not supported. */ -__CPUINITRODATA -.code16 +#ifdef CONFIG_SMP + + .section ".x86_trampoline","a" + .balign PAGE_SIZE + .code16 ENTRY(trampoline_data) r_base = . @@ -44,7 +46,7 @@ r_base = . cli # We should be safe anyway - movl $0xA5A5A5A5, trampoline_data - r_base + movl $0xA5A5A5A5, trampoline_status - r_base # write marker for master knows we're running /* GDT tables in non default location kernel can be beyond 16MB and @@ -72,5 +74,10 @@ boot_idt_descr: .word 0 # idt limit = 0 .long 0 # idt base = 0L +ENTRY(trampoline_status) + .long 0 + .globl trampoline_end trampoline_end: + +#endif /* CONFIG_SMP */ diff --git a/arch/x86/kernel/trampoline_64.S b/arch/x86/kernel/trampoline_64.S index 075d130efcf..09ff51799e9 100644 --- a/arch/x86/kernel/trampoline_64.S +++ b/arch/x86/kernel/trampoline_64.S @@ -32,13 +32,9 @@ #include <asm/segment.h> #include <asm/processor-flags.h> -#ifdef CONFIG_ACPI_SLEEP -.section .rodata, "a", @progbits -#else -/* We can free up the trampoline after bootup if cpu hotplug is not supported. */ -__CPUINITRODATA -#endif -.code16 + .section ".x86_trampoline","a" + .balign PAGE_SIZE + .code16 ENTRY(trampoline_data) r_base = . @@ -50,7 +46,7 @@ r_base = . mov %ax, %ss - movl $0xA5A5A5A5, trampoline_data - r_base + movl $0xA5A5A5A5, trampoline_status - r_base # write marker for master knows we're running # Setup stack @@ -64,10 +60,13 @@ r_base = . movzx %ax, %esi # Find the 32bit trampoline location shll $4, %esi - # Fixup the vectors - addl %esi, startup_32_vector - r_base - addl %esi, startup_64_vector - r_base - addl %esi, tgdt + 2 - r_base # Fixup the gdt pointer + # Fixup the absolute vectors + leal (startup_32 - r_base)(%esi), %eax + movl %eax, startup_32_vector - r_base + leal (startup_64 - r_base)(%esi), %eax + movl %eax, startup_64_vector - r_base + leal (tgdt - r_base)(%esi), %eax + movl %eax, (tgdt + 2 - r_base) /* * GDT tables in non default location kernel can be beyond 16MB and @@ -129,6 +128,7 @@ no_longmode: jmp no_longmode #include "verify_cpu.S" + .balign 4 # Careful these need to be in the same 64K segment as the above; tidt: .word 0 # idt limit = 0 @@ -156,6 +156,10 @@ startup_64_vector: .long startup_64 - r_base .word __KERNEL_CS, 0 + .balign 4 +ENTRY(trampoline_status) + .long 0 + trampoline_stack: .org 0x1000 trampoline_stack_end: diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index ffe5755caa8..9335bf7dd2e 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -427,7 +427,7 @@ unsigned long native_calibrate_tsc(void) * the delta to the previous read. We keep track of the min * and max values of that delta. The delta is mostly defined * by the IO time of the PIT access, so we can detect when a - * SMI/SMM disturbance happend between the two reads. If the + * SMI/SMM disturbance happened between the two reads. If the * maximum time is significantly larger than the minimum time, * then we discard the result and have another try. * @@ -900,7 +900,7 @@ static DECLARE_DELAYED_WORK(tsc_irqwork, tsc_refine_calibration_work); * timer based, instead of loop based, we don't block the boot * process while this longer calibration is done. * - * If there are any calibration anomolies (too many SMIs, etc), + * If there are any calibration anomalies (too many SMIs, etc), * or the refined calibration is off by 1% of the fast early * calibration, we throw out the new calibration and use the * early calibration. diff --git a/arch/x86/kernel/verify_cpu.S b/arch/x86/kernel/verify_cpu.S index 0edefc19a11..b9242bacbe5 100644 --- a/arch/x86/kernel/verify_cpu.S +++ b/arch/x86/kernel/verify_cpu.S @@ -18,7 +18,7 @@ * This file is expected to run in 32bit code. Currently: * * arch/x86/boot/compressed/head_64.S: Boot cpu verification - * arch/x86/kernel/trampoline_64.S: secondary processor verfication + * arch/x86/kernel/trampoline_64.S: secondary processor verification * arch/x86/kernel/head_32.S: processor startup * * verify_cpu, returns the status of longmode and SSE in register %eax. diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index bf470075518..624a2016198 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -105,6 +105,7 @@ SECTIONS SCHED_TEXT LOCK_TEXT KPROBES_TEXT + ENTRY_TEXT IRQENTRY_TEXT *(.fixup) *(.gnu.warning) @@ -230,7 +231,7 @@ SECTIONS * output PHDR, so the next output section - .init.text - should * start another segment - init. */ - PERCPU_VADDR(0, :percpu) + PERCPU_VADDR(INTERNODE_CACHE_BYTES, 0, :percpu) #endif INIT_TEXT_SECTION(PAGE_SIZE) @@ -240,6 +241,18 @@ SECTIONS INIT_DATA_SECTION(16) + /* + * Code and data for a variety of lowlevel trampolines, to be + * copied into base memory (< 1 MiB) during initialization. + * Since it is copied early, the main copy can be discarded + * afterwards. + */ + .x86_trampoline : AT(ADDR(.x86_trampoline) - LOAD_OFFSET) { + x86_trampoline_start = .; + *(.x86_trampoline) + x86_trampoline_end = .; + } + .x86_cpu_dev.init : AT(ADDR(.x86_cpu_dev.init) - LOAD_OFFSET) { __x86_cpu_dev_start = .; *(.x86_cpu_dev.init) @@ -291,6 +304,7 @@ SECTIONS *(.iommu_table) __iommu_table_end = .; } + . = ALIGN(8); /* * .exit.text is discard at runtime, not link time, to deal with @@ -305,7 +319,7 @@ SECTIONS } #if !defined(CONFIG_X86_64) || !defined(CONFIG_SMP) - PERCPU(THREAD_SIZE) + PERCPU(INTERNODE_CACHE_BYTES, PAGE_SIZE) #endif . = ALIGN(PAGE_SIZE); diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c index 1b950d151e5..9796c2f3d07 100644 --- a/arch/x86/kernel/x8664_ksyms_64.c +++ b/arch/x86/kernel/x8664_ksyms_64.c @@ -52,6 +52,7 @@ extern void *__memcpy(void *, const void *, __kernel_size_t); EXPORT_SYMBOL(memset); EXPORT_SYMBOL(memcpy); EXPORT_SYMBOL(__memcpy); +EXPORT_SYMBOL(memmove); EXPORT_SYMBOL(empty_zero_page); #ifndef CONFIG_PARAVIRT diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index ceb2911aa43..c11514e9128 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -70,6 +70,7 @@ struct x86_init_ops x86_init __initdata = { .setup_percpu_clockev = setup_boot_APIC_clock, .tsc_pre_init = x86_init_noop, .timer_init = hpet_time_init, + .wallclock_init = x86_init_noop, }, .iommu = { diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index 547128546cc..a3911343976 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -53,7 +53,7 @@ void __sanitize_i387_state(struct task_struct *tsk) /* * None of the feature bits are in init state. So nothing else - * to do for us, as the memory layout is upto date. + * to do for us, as the memory layout is up to date. */ if ((xstate_bv & pcntxt_mask) == pcntxt_mask) return; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index caf966781d2..0ad47b819a8 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -76,6 +76,7 @@ #define Group (1<<14) /* Bits 3:5 of modrm byte extend opcode */ #define GroupDual (1<<15) /* Alternate decoding of mod == 3 */ /* Misc flags */ +#define VendorSpecific (1<<22) /* Vendor specific instruction */ #define NoAccess (1<<23) /* Don't access memory (lea/invlpg/verr etc) */ #define Op3264 (1<<24) /* Operand is 64b in long mode, 32b otherwise */ #define Undefined (1<<25) /* No Such Instruction */ @@ -877,7 +878,8 @@ static void get_descriptor_table_ptr(struct x86_emulate_ctxt *ctxt, if (selector & 1 << 2) { struct desc_struct desc; memset (dt, 0, sizeof *dt); - if (!ops->get_cached_descriptor(&desc, VCPU_SREG_LDTR, ctxt->vcpu)) + if (!ops->get_cached_descriptor(&desc, NULL, VCPU_SREG_LDTR, + ctxt->vcpu)) return; dt->size = desc_limit_scaled(&desc); /* what if limit > 65535? */ @@ -929,6 +931,7 @@ static int write_segment_descriptor(struct x86_emulate_ctxt *ctxt, return ret; } +/* Does not support long mode */ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops, u16 selector, int seg) @@ -1040,7 +1043,7 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, } load: ops->set_segment_selector(selector, seg, ctxt->vcpu); - ops->set_cached_descriptor(&seg_desc, seg, ctxt->vcpu); + ops->set_cached_descriptor(&seg_desc, 0, seg, ctxt->vcpu); return X86EMUL_CONTINUE; exception: emulate_exception(ctxt, err_vec, err_code, true); @@ -1560,7 +1563,7 @@ setup_syscalls_segments(struct x86_emulate_ctxt *ctxt, struct desc_struct *ss) { memset(cs, 0, sizeof(struct desc_struct)); - ops->get_cached_descriptor(cs, VCPU_SREG_CS, ctxt->vcpu); + ops->get_cached_descriptor(cs, NULL, VCPU_SREG_CS, ctxt->vcpu); memset(ss, 0, sizeof(struct desc_struct)); cs->l = 0; /* will be adjusted later */ @@ -1607,9 +1610,9 @@ emulate_syscall(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) cs.d = 0; cs.l = 1; } - ops->set_cached_descriptor(&cs, VCPU_SREG_CS, ctxt->vcpu); + ops->set_cached_descriptor(&cs, 0, VCPU_SREG_CS, ctxt->vcpu); ops->set_segment_selector(cs_sel, VCPU_SREG_CS, ctxt->vcpu); - ops->set_cached_descriptor(&ss, VCPU_SREG_SS, ctxt->vcpu); + ops->set_cached_descriptor(&ss, 0, VCPU_SREG_SS, ctxt->vcpu); ops->set_segment_selector(ss_sel, VCPU_SREG_SS, ctxt->vcpu); c->regs[VCPU_REGS_RCX] = c->eip; @@ -1679,9 +1682,9 @@ emulate_sysenter(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) cs.l = 1; } - ops->set_cached_descriptor(&cs, VCPU_SREG_CS, ctxt->vcpu); + ops->set_cached_descriptor(&cs, 0, VCPU_SREG_CS, ctxt->vcpu); ops->set_segment_selector(cs_sel, VCPU_SREG_CS, ctxt->vcpu); - ops->set_cached_descriptor(&ss, VCPU_SREG_SS, ctxt->vcpu); + ops->set_cached_descriptor(&ss, 0, VCPU_SREG_SS, ctxt->vcpu); ops->set_segment_selector(ss_sel, VCPU_SREG_SS, ctxt->vcpu); ops->get_msr(ctxt->vcpu, MSR_IA32_SYSENTER_EIP, &msr_data); @@ -1736,9 +1739,9 @@ emulate_sysexit(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) cs_sel |= SELECTOR_RPL_MASK; ss_sel |= SELECTOR_RPL_MASK; - ops->set_cached_descriptor(&cs, VCPU_SREG_CS, ctxt->vcpu); + ops->set_cached_descriptor(&cs, 0, VCPU_SREG_CS, ctxt->vcpu); ops->set_segment_selector(cs_sel, VCPU_SREG_CS, ctxt->vcpu); - ops->set_cached_descriptor(&ss, VCPU_SREG_SS, ctxt->vcpu); + ops->set_cached_descriptor(&ss, 0, VCPU_SREG_SS, ctxt->vcpu); ops->set_segment_selector(ss_sel, VCPU_SREG_SS, ctxt->vcpu); c->eip = c->regs[VCPU_REGS_RDX]; @@ -1764,24 +1767,28 @@ static bool emulator_io_port_access_allowed(struct x86_emulate_ctxt *ctxt, u16 port, u16 len) { struct desc_struct tr_seg; + u32 base3; int r; - u16 io_bitmap_ptr; - u8 perm, bit_idx = port & 0x7; + u16 io_bitmap_ptr, perm, bit_idx = port & 0x7; unsigned mask = (1 << len) - 1; + unsigned long base; - ops->get_cached_descriptor(&tr_seg, VCPU_SREG_TR, ctxt->vcpu); + ops->get_cached_descriptor(&tr_seg, &base3, VCPU_SREG_TR, ctxt->vcpu); if (!tr_seg.p) return false; if (desc_limit_scaled(&tr_seg) < 103) return false; - r = ops->read_std(get_desc_base(&tr_seg) + 102, &io_bitmap_ptr, 2, - ctxt->vcpu, NULL); + base = get_desc_base(&tr_seg); +#ifdef CONFIG_X86_64 + base |= ((u64)base3) << 32; +#endif + r = ops->read_std(base + 102, &io_bitmap_ptr, 2, ctxt->vcpu, NULL); if (r != X86EMUL_CONTINUE) return false; if (io_bitmap_ptr + port/8 > desc_limit_scaled(&tr_seg)) return false; - r = ops->read_std(get_desc_base(&tr_seg) + io_bitmap_ptr + port/8, - &perm, 1, ctxt->vcpu, NULL); + r = ops->read_std(base + io_bitmap_ptr + port/8, &perm, 2, ctxt->vcpu, + NULL); if (r != X86EMUL_CONTINUE) return false; if ((perm >> bit_idx) & mask) @@ -2126,7 +2133,7 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt, } ops->set_cr(0, ops->get_cr(0, ctxt->vcpu) | X86_CR0_TS, ctxt->vcpu); - ops->set_cached_descriptor(&next_tss_desc, VCPU_SREG_TR, ctxt->vcpu); + ops->set_cached_descriptor(&next_tss_desc, 0, VCPU_SREG_TR, ctxt->vcpu); ops->set_segment_selector(tss_selector, VCPU_SREG_TR, ctxt->vcpu); if (has_error_code) { @@ -2365,7 +2372,8 @@ static struct group_dual group7 = { { D(SrcMem16 | ModRM | Mov | Priv), D(SrcMem | ModRM | ByteOp | Priv | NoAccess), }, { - D(SrcNone | ModRM | Priv), N, N, D(SrcNone | ModRM | Priv), + D(SrcNone | ModRM | Priv | VendorSpecific), N, + N, D(SrcNone | ModRM | Priv | VendorSpecific), D(SrcNone | ModRM | DstMem | Mov), N, D(SrcMem16 | ModRM | Mov | Priv), N, } }; @@ -2489,7 +2497,7 @@ static struct opcode opcode_table[256] = { static struct opcode twobyte_table[256] = { /* 0x00 - 0x0F */ N, GD(0, &group7), N, N, - N, D(ImplicitOps), D(ImplicitOps | Priv), N, + N, D(ImplicitOps | VendorSpecific), D(ImplicitOps | Priv), N, D(ImplicitOps | Priv), D(ImplicitOps | Priv), N, N, N, D(ImplicitOps | ModRM), N, N, /* 0x10 - 0x1F */ @@ -2502,7 +2510,8 @@ static struct opcode twobyte_table[256] = { /* 0x30 - 0x3F */ D(ImplicitOps | Priv), I(ImplicitOps, em_rdtsc), D(ImplicitOps | Priv), N, - D(ImplicitOps), D(ImplicitOps | Priv), N, N, + D(ImplicitOps | VendorSpecific), D(ImplicitOps | Priv | VendorSpecific), + N, N, N, N, N, N, N, N, N, N, /* 0x40 - 0x4F */ X16(D(DstReg | SrcMem | ModRM | Mov)), @@ -2741,6 +2750,9 @@ done_prefixes: if (c->d == 0 || (c->d & Undefined)) return -1; + if (!(c->d & VendorSpecific) && ctxt->only_vendor_specific_insn) + return -1; + if (mode == X86EMUL_MODE_PROT64 && (c->d & Stack)) c->op_bytes = 8; diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 3cece05e4ac..19fe855e795 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -62,9 +62,6 @@ static void pic_unlock(struct kvm_pic *s) } if (!found) - found = s->kvm->bsp_vcpu; - - if (!found) return; kvm_make_request(KVM_REQ_EVENT, found); @@ -75,7 +72,6 @@ static void pic_unlock(struct kvm_pic *s) static void pic_clear_isr(struct kvm_kpic_state *s, int irq) { s->isr &= ~(1 << irq); - s->isr_ack |= (1 << irq); if (s != &s->pics_state->pics[0]) irq += 8; /* @@ -89,16 +85,6 @@ static void pic_clear_isr(struct kvm_kpic_state *s, int irq) pic_lock(s->pics_state); } -void kvm_pic_clear_isr_ack(struct kvm *kvm) -{ - struct kvm_pic *s = pic_irqchip(kvm); - - pic_lock(s); - s->pics[0].isr_ack = 0xff; - s->pics[1].isr_ack = 0xff; - pic_unlock(s); -} - /* * set irq level. If an edge is detected, then the IRR is set to 1 */ @@ -281,7 +267,6 @@ void kvm_pic_reset(struct kvm_kpic_state *s) s->irr = 0; s->imr = 0; s->isr = 0; - s->isr_ack = 0xff; s->priority_add = 0; s->irq_base = 0; s->read_reg_select = 0; @@ -545,15 +530,11 @@ static int picdev_read(struct kvm_io_device *this, */ static void pic_irq_request(struct kvm *kvm, int level) { - struct kvm_vcpu *vcpu = kvm->bsp_vcpu; struct kvm_pic *s = pic_irqchip(kvm); - int irq = pic_get_irq(&s->pics[0]); - s->output = level; - if (vcpu && level && (s->pics[0].isr_ack & (1 << irq))) { - s->pics[0].isr_ack &= ~(1 << irq); + if (!s->output) s->wakeup_needed = true; - } + s->output = level; } static const struct kvm_io_device_ops picdev_ops = { @@ -575,8 +556,6 @@ struct kvm_pic *kvm_create_pic(struct kvm *kvm) s->pics[1].elcr_mask = 0xde; s->pics[0].pics_state = s; s->pics[1].pics_state = s; - s->pics[0].isr_ack = 0xff; - s->pics[1].isr_ack = 0xff; /* * Initialize PIO device diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 93cf9d0d365..2b2255b1f04 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -417,10 +417,6 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, case APIC_DM_INIT: if (level) { result = 1; - if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE) - printk(KERN_DEBUG - "INIT on a runnable vcpu %d\n", - vcpu->vcpu_id); vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED; kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_vcpu_kick(vcpu); @@ -875,8 +871,8 @@ void kvm_free_lapic(struct kvm_vcpu *vcpu) hrtimer_cancel(&vcpu->arch.apic->lapic_timer.timer); - if (vcpu->arch.apic->regs_page) - __free_page(vcpu->arch.apic->regs_page); + if (vcpu->arch.apic->regs) + free_page((unsigned long)vcpu->arch.apic->regs); kfree(vcpu->arch.apic); } @@ -1065,13 +1061,12 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu) vcpu->arch.apic = apic; - apic->regs_page = alloc_page(GFP_KERNEL|__GFP_ZERO); - if (apic->regs_page == NULL) { + apic->regs = (void *)get_zeroed_page(GFP_KERNEL); + if (!apic->regs) { printk(KERN_ERR "malloc apic regs error for vcpu %x\n", vcpu->vcpu_id); goto nomem_free_apic; } - apic->regs = page_address(apic->regs_page); apic->vcpu = vcpu; hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC, diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index f5fe32c5eda..52c9e6b9e72 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -13,7 +13,6 @@ struct kvm_lapic { u32 divide_count; struct kvm_vcpu *vcpu; bool irr_pending; - struct page *regs_page; void *regs; gpa_t vapic_addr; struct page *vapic_page; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index f02b8edc3d4..22fae7593ee 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -111,9 +111,6 @@ module_param(oos_shadow, bool, 0644); #define PT64_LEVEL_SHIFT(level) \ (PAGE_SHIFT + (level - 1) * PT64_LEVEL_BITS) -#define PT64_LEVEL_MASK(level) \ - (((1ULL << PT64_LEVEL_BITS) - 1) << PT64_LEVEL_SHIFT(level)) - #define PT64_INDEX(address, level)\ (((address) >> PT64_LEVEL_SHIFT(level)) & ((1 << PT64_LEVEL_BITS) - 1)) @@ -123,8 +120,6 @@ module_param(oos_shadow, bool, 0644); #define PT32_LEVEL_SHIFT(level) \ (PAGE_SHIFT + (level - 1) * PT32_LEVEL_BITS) -#define PT32_LEVEL_MASK(level) \ - (((1ULL << PT32_LEVEL_BITS) - 1) << PT32_LEVEL_SHIFT(level)) #define PT32_LVL_OFFSET_MASK(level) \ (PT32_BASE_ADDR_MASK & ((1ULL << (PAGE_SHIFT + (((level) - 1) \ * PT32_LEVEL_BITS))) - 1)) @@ -379,15 +374,15 @@ static void mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc, static int mmu_topup_memory_cache_page(struct kvm_mmu_memory_cache *cache, int min) { - struct page *page; + void *page; if (cache->nobjs >= min) return 0; while (cache->nobjs < ARRAY_SIZE(cache->objects)) { - page = alloc_page(GFP_KERNEL); + page = (void *)__get_free_page(GFP_KERNEL); if (!page) return -ENOMEM; - cache->objects[cache->nobjs++] = page_address(page); + cache->objects[cache->nobjs++] = page; } return 0; } @@ -554,13 +549,23 @@ static int host_mapping_level(struct kvm *kvm, gfn_t gfn) return ret; } -static bool mapping_level_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t large_gfn) +static struct kvm_memory_slot * +gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn, + bool no_dirty_log) { struct kvm_memory_slot *slot; - slot = gfn_to_memslot(vcpu->kvm, large_gfn); - if (slot && slot->dirty_bitmap) - return true; - return false; + + slot = gfn_to_memslot(vcpu->kvm, gfn); + if (!slot || slot->flags & KVM_MEMSLOT_INVALID || + (no_dirty_log && slot->dirty_bitmap)) + slot = NULL; + + return slot; +} + +static bool mapping_level_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t large_gfn) +{ + return gfn_to_memslot_dirty_bitmap(vcpu, large_gfn, true); } static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn) @@ -1032,9 +1037,9 @@ static void kvm_mmu_free_page(struct kvm *kvm, struct kvm_mmu_page *sp) ASSERT(is_empty_shadow_page(sp->spt)); hlist_del(&sp->hash_link); list_del(&sp->link); - __free_page(virt_to_page(sp->spt)); + free_page((unsigned long)sp->spt); if (!sp->role.direct) - __free_page(virt_to_page(sp->gfns)); + free_page((unsigned long)sp->gfns); kmem_cache_free(mmu_page_header_cache, sp); kvm_mod_used_mmu_pages(kvm, -1); } @@ -1199,6 +1204,13 @@ static void nonpaging_invlpg(struct kvm_vcpu *vcpu, gva_t gva) { } +static void nonpaging_update_pte(struct kvm_vcpu *vcpu, + struct kvm_mmu_page *sp, u64 *spte, + const void *pte, unsigned long mmu_seq) +{ + WARN_ON(1); +} + #define KVM_PAGE_ARRAY_NR 16 struct kvm_mmu_pages { @@ -2150,26 +2162,13 @@ static void nonpaging_new_cr3(struct kvm_vcpu *vcpu) { } -static struct kvm_memory_slot * -pte_prefetch_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn, bool no_dirty_log) -{ - struct kvm_memory_slot *slot; - - slot = gfn_to_memslot(vcpu->kvm, gfn); - if (!slot || slot->flags & KVM_MEMSLOT_INVALID || - (no_dirty_log && slot->dirty_bitmap)) - slot = NULL; - - return slot; -} - static pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, bool no_dirty_log) { struct kvm_memory_slot *slot; unsigned long hva; - slot = pte_prefetch_gfn_to_memslot(vcpu, gfn, no_dirty_log); + slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, no_dirty_log); if (!slot) { get_page(bad_page); return page_to_pfn(bad_page); @@ -2190,7 +2189,7 @@ static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu, gfn_t gfn; gfn = kvm_mmu_page_get_gfn(sp, start - sp->spt); - if (!pte_prefetch_gfn_to_memslot(vcpu, gfn, access & ACC_WRITE_MASK)) + if (!gfn_to_memslot_dirty_bitmap(vcpu, gfn, access & ACC_WRITE_MASK)) return -1; ret = gfn_to_page_many_atomic(vcpu->kvm, gfn, pages, end - start); @@ -2804,6 +2803,7 @@ static int nonpaging_init_context(struct kvm_vcpu *vcpu, context->prefetch_page = nonpaging_prefetch_page; context->sync_page = nonpaging_sync_page; context->invlpg = nonpaging_invlpg; + context->update_pte = nonpaging_update_pte; context->root_level = 0; context->shadow_root_level = PT32E_ROOT_LEVEL; context->root_hpa = INVALID_PAGE; @@ -2933,6 +2933,7 @@ static int paging64_init_context_common(struct kvm_vcpu *vcpu, context->prefetch_page = paging64_prefetch_page; context->sync_page = paging64_sync_page; context->invlpg = paging64_invlpg; + context->update_pte = paging64_update_pte; context->free = paging_free; context->root_level = level; context->shadow_root_level = level; @@ -2961,6 +2962,7 @@ static int paging32_init_context(struct kvm_vcpu *vcpu, context->prefetch_page = paging32_prefetch_page; context->sync_page = paging32_sync_page; context->invlpg = paging32_invlpg; + context->update_pte = paging32_update_pte; context->root_level = PT32_ROOT_LEVEL; context->shadow_root_level = PT32E_ROOT_LEVEL; context->root_hpa = INVALID_PAGE; @@ -2985,6 +2987,7 @@ static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) context->prefetch_page = nonpaging_prefetch_page; context->sync_page = nonpaging_sync_page; context->invlpg = nonpaging_invlpg; + context->update_pte = nonpaging_update_pte; context->shadow_root_level = kvm_x86_ops->get_tdp_level(); context->root_hpa = INVALID_PAGE; context->direct_map = true; @@ -3089,8 +3092,6 @@ static int init_kvm_nested_mmu(struct kvm_vcpu *vcpu) static int init_kvm_mmu(struct kvm_vcpu *vcpu) { - vcpu->arch.update_pte.pfn = bad_pfn; - if (mmu_is_nested(vcpu)) return init_kvm_nested_mmu(vcpu); else if (tdp_enabled) @@ -3164,7 +3165,7 @@ static void mmu_pte_write_zap_pte(struct kvm_vcpu *vcpu, static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, u64 *spte, - const void *new) + const void *new, unsigned long mmu_seq) { if (sp->role.level != PT_PAGE_TABLE_LEVEL) { ++vcpu->kvm->stat.mmu_pde_zapped; @@ -3172,10 +3173,7 @@ static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu, } ++vcpu->kvm->stat.mmu_pte_updated; - if (!sp->role.cr4_pae) - paging32_update_pte(vcpu, sp, spte, new); - else - paging64_update_pte(vcpu, sp, spte, new); + vcpu->arch.mmu.update_pte(vcpu, sp, spte, new, mmu_seq); } static bool need_remote_flush(u64 old, u64 new) @@ -3210,28 +3208,6 @@ static bool last_updated_pte_accessed(struct kvm_vcpu *vcpu) return !!(spte && (*spte & shadow_accessed_mask)); } -static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, - u64 gpte) -{ - gfn_t gfn; - pfn_t pfn; - - if (!is_present_gpte(gpte)) - return; - gfn = (gpte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT; - - vcpu->arch.update_pte.mmu_seq = vcpu->kvm->mmu_notifier_seq; - smp_rmb(); - pfn = gfn_to_pfn(vcpu->kvm, gfn); - - if (is_error_pfn(pfn)) { - kvm_release_pfn_clean(pfn); - return; - } - vcpu->arch.update_pte.gfn = gfn; - vcpu->arch.update_pte.pfn = pfn; -} - static void kvm_mmu_access_page(struct kvm_vcpu *vcpu, gfn_t gfn) { u64 *spte = vcpu->arch.last_pte_updated; @@ -3253,21 +3229,14 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_mmu_page *sp; struct hlist_node *node; LIST_HEAD(invalid_list); - u64 entry, gentry; - u64 *spte; - unsigned offset = offset_in_page(gpa); - unsigned pte_size; - unsigned page_offset; - unsigned misaligned; - unsigned quadrant; - int level; - int flooded = 0; - int npte; - int r; - int invlpg_counter; + unsigned long mmu_seq; + u64 entry, gentry, *spte; + unsigned pte_size, page_offset, misaligned, quadrant, offset; + int level, npte, invlpg_counter, r, flooded = 0; bool remote_flush, local_flush, zap_page; zap_page = remote_flush = local_flush = false; + offset = offset_in_page(gpa); pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes); @@ -3275,9 +3244,8 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, /* * Assume that the pte write on a page table of the same type - * as the current vcpu paging mode. This is nearly always true - * (might be false while changing modes). Note it is verified later - * by update_pte(). + * as the current vcpu paging mode since we update the sptes only + * when they have the same mode. */ if ((is_pae(vcpu) && bytes == 4) || !new) { /* Handle a 32-bit guest writing two halves of a 64-bit gpte */ @@ -3303,15 +3271,17 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, break; } - mmu_guess_page_from_pte_write(vcpu, gpa, gentry); + mmu_seq = vcpu->kvm->mmu_notifier_seq; + smp_rmb(); + spin_lock(&vcpu->kvm->mmu_lock); if (atomic_read(&vcpu->kvm->arch.invlpg_counter) != invlpg_counter) gentry = 0; - kvm_mmu_access_page(vcpu, gfn); kvm_mmu_free_some_pages(vcpu); ++vcpu->kvm->stat.mmu_pte_write; trace_kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE); if (guest_initiated) { + kvm_mmu_access_page(vcpu, gfn); if (gfn == vcpu->arch.last_pt_write_gfn && !last_updated_pte_accessed(vcpu)) { ++vcpu->arch.last_pt_write_count; @@ -3375,7 +3345,8 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, if (gentry && !((sp->role.word ^ vcpu->arch.mmu.base_role.word) & mask.word)) - mmu_pte_write_new_pte(vcpu, sp, spte, &gentry); + mmu_pte_write_new_pte(vcpu, sp, spte, &gentry, + mmu_seq); if (!remote_flush && need_remote_flush(entry, *spte)) remote_flush = true; ++spte; @@ -3385,10 +3356,6 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); trace_kvm_mmu_audit(vcpu, AUDIT_POST_PTE_WRITE); spin_unlock(&vcpu->kvm->mmu_lock); - if (!is_error_pfn(vcpu->arch.update_pte.pfn)) { - kvm_release_pfn_clean(vcpu->arch.update_pte.pfn); - vcpu->arch.update_pte.pfn = bad_pfn; - } } int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva) @@ -3538,14 +3505,23 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot) if (!test_bit(slot, sp->slot_bitmap)) continue; - if (sp->role.level != PT_PAGE_TABLE_LEVEL) - continue; - pt = sp->spt; - for (i = 0; i < PT64_ENT_PER_PAGE; ++i) + for (i = 0; i < PT64_ENT_PER_PAGE; ++i) { + if (!is_shadow_present_pte(pt[i]) || + !is_last_spte(pt[i], sp->role.level)) + continue; + + if (is_large_pte(pt[i])) { + drop_spte(kvm, &pt[i], + shadow_trap_nonpresent_pte); + --kvm->stat.lpages; + continue; + } + /* avoid RMW */ if (is_writable_pte(pt[i])) update_spte(&pt[i], pt[i] & ~PT_WRITABLE_MASK); + } } kvm_flush_remote_tlbs(kvm); } @@ -3583,7 +3559,7 @@ static int mmu_shrink(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask) if (nr_to_scan == 0) goto out; - spin_lock(&kvm_lock); + raw_spin_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { int idx, freed_pages; @@ -3606,7 +3582,7 @@ static int mmu_shrink(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask) if (kvm_freed) list_move_tail(&kvm_freed->vm_list, &vm_list); - spin_unlock(&kvm_lock); + raw_spin_unlock(&kvm_lock); out: return percpu_counter_read_positive(&kvm_total_used_mmu_pages); diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 6bccc24c418..c6397795d86 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -31,7 +31,6 @@ #define PT_LVL_ADDR_MASK(lvl) PT64_LVL_ADDR_MASK(lvl) #define PT_LVL_OFFSET_MASK(lvl) PT64_LVL_OFFSET_MASK(lvl) #define PT_INDEX(addr, level) PT64_INDEX(addr, level) - #define PT_LEVEL_MASK(level) PT64_LEVEL_MASK(level) #define PT_LEVEL_BITS PT64_LEVEL_BITS #ifdef CONFIG_X86_64 #define PT_MAX_FULL_LEVELS 4 @@ -48,7 +47,6 @@ #define PT_LVL_ADDR_MASK(lvl) PT32_LVL_ADDR_MASK(lvl) #define PT_LVL_OFFSET_MASK(lvl) PT32_LVL_OFFSET_MASK(lvl) #define PT_INDEX(addr, level) PT32_INDEX(addr, level) - #define PT_LEVEL_MASK(level) PT32_LEVEL_MASK(level) #define PT_LEVEL_BITS PT32_LEVEL_BITS #define PT_MAX_FULL_LEVELS 2 #define CMPXCHG cmpxchg @@ -327,7 +325,7 @@ no_present: } static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, - u64 *spte, const void *pte) + u64 *spte, const void *pte, unsigned long mmu_seq) { pt_element_t gpte; unsigned pte_access; @@ -339,16 +337,16 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, pgprintk("%s: gpte %llx spte %p\n", __func__, (u64)gpte, spte); pte_access = sp->role.access & FNAME(gpte_access)(vcpu, gpte); - if (gpte_to_gfn(gpte) != vcpu->arch.update_pte.gfn) + pfn = gfn_to_pfn_atomic(vcpu->kvm, gpte_to_gfn(gpte)); + if (is_error_pfn(pfn)) { + kvm_release_pfn_clean(pfn); return; - pfn = vcpu->arch.update_pte.pfn; - if (is_error_pfn(pfn)) - return; - if (mmu_notifier_retry(vcpu, vcpu->arch.update_pte.mmu_seq)) + } + if (mmu_notifier_retry(vcpu, mmu_seq)) return; - kvm_get_pfn(pfn); + /* - * we call mmu_set_spte() with host_writable = true beacuse that + * we call mmu_set_spte() with host_writable = true because that * vcpu->arch.update_pte.pfn was fetched from get_user_pages(write = 1). */ mmu_set_spte(vcpu, spte, sp->role.access, pte_access, 0, 0, @@ -829,7 +827,6 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) #undef FNAME #undef PT_BASE_ADDR_MASK #undef PT_INDEX -#undef PT_LEVEL_MASK #undef PT_LVL_ADDR_MASK #undef PT_LVL_OFFSET_MASK #undef PT_LEVEL_BITS diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 54ce246a383..6bb15d583e4 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -135,6 +135,8 @@ struct vcpu_svm { u32 *msrpm; + ulong nmi_iret_rip; + struct nested_state nested; bool nmi_singlestep; @@ -1153,8 +1155,10 @@ static void svm_vcpu_put(struct kvm_vcpu *vcpu) wrmsrl(MSR_KERNEL_GS_BASE, current->thread.gs); load_gs_index(svm->host.gs); #else +#ifdef CONFIG_X86_32_LAZY_GS loadsegment(gs, svm->host.gs); #endif +#endif for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) wrmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]); } @@ -2653,6 +2657,7 @@ static int iret_interception(struct vcpu_svm *svm) ++svm->vcpu.stat.nmi_window_exits; clr_intercept(svm, INTERCEPT_IRET); svm->vcpu.arch.hflags |= HF_IRET_MASK; + svm->nmi_iret_rip = kvm_rip_read(&svm->vcpu); return 1; } @@ -2777,6 +2782,8 @@ static int dr_interception(struct vcpu_svm *svm) kvm_register_write(&svm->vcpu, reg, val); } + skip_emulated_instruction(&svm->vcpu); + return 1; } @@ -3472,7 +3479,12 @@ static void svm_complete_interrupts(struct vcpu_svm *svm) svm->int3_injected = 0; - if (svm->vcpu.arch.hflags & HF_IRET_MASK) { + /* + * If we've made progress since setting HF_IRET_MASK, we've + * executed an IRET and can allow NMI injection. + */ + if ((svm->vcpu.arch.hflags & HF_IRET_MASK) + && kvm_rip_read(&svm->vcpu) != svm->nmi_iret_rip) { svm->vcpu.arch.hflags &= ~(HF_NMI_MASK | HF_IRET_MASK); kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); } @@ -3639,19 +3651,30 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) wrmsrl(MSR_GS_BASE, svm->host.gs_base); #else loadsegment(fs, svm->host.fs); +#ifndef CONFIG_X86_32_LAZY_GS + loadsegment(gs, svm->host.gs); +#endif #endif reload_tss(vcpu); local_irq_disable(); - stgi(); - vcpu->arch.cr2 = svm->vmcb->save.cr2; vcpu->arch.regs[VCPU_REGS_RAX] = svm->vmcb->save.rax; vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp; vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip; + if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI)) + kvm_before_handle_nmi(&svm->vcpu); + + stgi(); + + /* Any pending NMI will happen here */ + + if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI)) + kvm_after_handle_nmi(&svm->vcpu); + sync_cr8_to_lapic(vcpu); svm->next_rip = 0; diff --git a/arch/x86/kvm/timer.c b/arch/x86/kvm/timer.c index fc7a101c4a3..abd86e865be 100644 --- a/arch/x86/kvm/timer.c +++ b/arch/x86/kvm/timer.c @@ -25,7 +25,7 @@ static int __kvm_timer_fn(struct kvm_vcpu *vcpu, struct kvm_timer *ktimer) /* * There is a race window between reading and incrementing, but we do - * not care about potentially loosing timer events in the !reinject + * not care about potentially losing timer events in the !reinject * case anyway. Note: KVM_REQ_PENDING_TIMER is implicitly checked * in vcpu_enter_guest. */ diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 1357d7cf4ec..db932760ea8 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -62,21 +62,21 @@ TRACE_EVENT(kvm_hv_hypercall, TP_ARGS(code, fast, rep_cnt, rep_idx, ingpa, outgpa), TP_STRUCT__entry( - __field( __u16, code ) - __field( bool, fast ) __field( __u16, rep_cnt ) __field( __u16, rep_idx ) __field( __u64, ingpa ) __field( __u64, outgpa ) + __field( __u16, code ) + __field( bool, fast ) ), TP_fast_assign( - __entry->code = code; - __entry->fast = fast; __entry->rep_cnt = rep_cnt; __entry->rep_idx = rep_idx; __entry->ingpa = ingpa; __entry->outgpa = outgpa; + __entry->code = code; + __entry->fast = fast; ), TP_printk("code 0x%x %s cnt 0x%x idx 0x%x in 0x%llx out 0x%llx", diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index bf89ec2cfb8..5b4cdcbd154 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -93,14 +93,14 @@ module_param(yield_on_hlt, bool, S_IRUGO); * These 2 parameters are used to config the controls for Pause-Loop Exiting: * ple_gap: upper bound on the amount of time between two successive * executions of PAUSE in a loop. Also indicate if ple enabled. - * According to test, this time is usually small than 41 cycles. + * According to test, this time is usually smaller than 128 cycles. * ple_window: upper bound on the amount of time a guest is allowed to execute * in a PAUSE loop. Tests indicate that most spinlocks are held for * less than 2^12 cycles * Time is measured based on a counter that runs at the same rate as the TSC, * refer SDM volume 3b section 21.6.13 & 22.1.3. */ -#define KVM_VMX_DEFAULT_PLE_GAP 41 +#define KVM_VMX_DEFAULT_PLE_GAP 128 #define KVM_VMX_DEFAULT_PLE_WINDOW 4096 static int ple_gap = KVM_VMX_DEFAULT_PLE_GAP; module_param(ple_gap, int, S_IRUGO); @@ -176,11 +176,11 @@ static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu) return container_of(vcpu, struct vcpu_vmx, vcpu); } -static int init_rmode(struct kvm *kvm); static u64 construct_eptp(unsigned long root_hpa); static void kvm_cpu_vmxon(u64 addr); static void kvm_cpu_vmxoff(void); static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3); +static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr); static DEFINE_PER_CPU(struct vmcs *, vmxarea); static DEFINE_PER_CPU(struct vmcs *, current_vmcs); @@ -1333,19 +1333,25 @@ static __init int vmx_disabled_by_bios(void) rdmsrl(MSR_IA32_FEATURE_CONTROL, msr); if (msr & FEATURE_CONTROL_LOCKED) { + /* launched w/ TXT and VMX disabled */ if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX) && tboot_enabled()) return 1; + /* launched w/o TXT and VMX only enabled w/ TXT */ if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX) + && (msr & FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX) && !tboot_enabled()) { printk(KERN_WARNING "kvm: disable TXT in the BIOS or " - " activate TXT before enabling KVM\n"); + "activate TXT before enabling KVM\n"); return 1; } + /* launched w/o TXT and VMX disabled */ + if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX) + && !tboot_enabled()) + return 1; } return 0; - /* locked but not enabled */ } static void kvm_cpu_vmxon(u64 addr) @@ -1683,6 +1689,7 @@ static void enter_pmode(struct kvm_vcpu *vcpu) vmx->emulation_required = 1; vmx->rmode.vm86_active = 0; + vmcs_write16(GUEST_TR_SELECTOR, vmx->rmode.tr.selector); vmcs_writel(GUEST_TR_BASE, vmx->rmode.tr.base); vmcs_write32(GUEST_TR_LIMIT, vmx->rmode.tr.limit); vmcs_write32(GUEST_TR_AR_BYTES, vmx->rmode.tr.ar); @@ -1756,6 +1763,19 @@ static void enter_rmode(struct kvm_vcpu *vcpu) vmx->emulation_required = 1; vmx->rmode.vm86_active = 1; + /* + * Very old userspace does not call KVM_SET_TSS_ADDR before entering + * vcpu. Call it here with phys address pointing 16M below 4G. + */ + if (!vcpu->kvm->arch.tss_addr) { + printk_once(KERN_WARNING "kvm: KVM_SET_TSS_ADDR need to be " + "called before entering vcpu\n"); + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + vmx_set_tss_addr(vcpu->kvm, 0xfeffd000); + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + } + + vmx->rmode.tr.selector = vmcs_read16(GUEST_TR_SELECTOR); vmx->rmode.tr.base = vmcs_readl(GUEST_TR_BASE); vmcs_writel(GUEST_TR_BASE, rmode_tss_base(vcpu->kvm)); @@ -1794,7 +1814,6 @@ static void enter_rmode(struct kvm_vcpu *vcpu) continue_rmode: kvm_mmu_reset_context(vcpu); - init_rmode(vcpu->kvm); } static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer) @@ -2030,23 +2049,40 @@ static void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) vmcs_writel(GUEST_CR4, hw_cr4); } -static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg) -{ - struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; - - return vmcs_readl(sf->base); -} - static void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) { + struct vcpu_vmx *vmx = to_vmx(vcpu); struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; + struct kvm_save_segment *save; u32 ar; + if (vmx->rmode.vm86_active + && (seg == VCPU_SREG_TR || seg == VCPU_SREG_ES + || seg == VCPU_SREG_DS || seg == VCPU_SREG_FS + || seg == VCPU_SREG_GS) + && !emulate_invalid_guest_state) { + switch (seg) { + case VCPU_SREG_TR: save = &vmx->rmode.tr; break; + case VCPU_SREG_ES: save = &vmx->rmode.es; break; + case VCPU_SREG_DS: save = &vmx->rmode.ds; break; + case VCPU_SREG_FS: save = &vmx->rmode.fs; break; + case VCPU_SREG_GS: save = &vmx->rmode.gs; break; + default: BUG(); + } + var->selector = save->selector; + var->base = save->base; + var->limit = save->limit; + ar = save->ar; + if (seg == VCPU_SREG_TR + || var->selector == vmcs_read16(sf->selector)) + goto use_saved_rmode_seg; + } var->base = vmcs_readl(sf->base); var->limit = vmcs_read32(sf->limit); var->selector = vmcs_read16(sf->selector); ar = vmcs_read32(sf->ar_bytes); +use_saved_rmode_seg: if ((ar & AR_UNUSABLE_MASK) && !emulate_invalid_guest_state) ar = 0; var->type = ar & 15; @@ -2060,6 +2096,18 @@ static void vmx_get_segment(struct kvm_vcpu *vcpu, var->unusable = (ar >> 16) & 1; } +static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg) +{ + struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; + struct kvm_segment s; + + if (to_vmx(vcpu)->rmode.vm86_active) { + vmx_get_segment(vcpu, &s, seg); + return s.base; + } + return vmcs_readl(sf->base); +} + static int vmx_get_cpl(struct kvm_vcpu *vcpu) { if (!is_protmode(vcpu)) @@ -2101,6 +2149,7 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu, u32 ar; if (vmx->rmode.vm86_active && seg == VCPU_SREG_TR) { + vmcs_write16(sf->selector, var->selector); vmx->rmode.tr.selector = var->selector; vmx->rmode.tr.base = var->base; vmx->rmode.tr.limit = var->limit; @@ -2361,11 +2410,12 @@ static bool guest_state_valid(struct kvm_vcpu *vcpu) static int init_rmode_tss(struct kvm *kvm) { - gfn_t fn = rmode_tss_base(kvm) >> PAGE_SHIFT; + gfn_t fn; u16 data = 0; - int ret = 0; - int r; + int r, idx, ret = 0; + idx = srcu_read_lock(&kvm->srcu); + fn = rmode_tss_base(kvm) >> PAGE_SHIFT; r = kvm_clear_guest_page(kvm, fn, 0, PAGE_SIZE); if (r < 0) goto out; @@ -2389,12 +2439,13 @@ static int init_rmode_tss(struct kvm *kvm) ret = 1; out: + srcu_read_unlock(&kvm->srcu, idx); return ret; } static int init_rmode_identity_map(struct kvm *kvm) { - int i, r, ret; + int i, idx, r, ret; pfn_t identity_map_pfn; u32 tmp; @@ -2409,6 +2460,7 @@ static int init_rmode_identity_map(struct kvm *kvm) return 1; ret = 0; identity_map_pfn = kvm->arch.ept_identity_map_addr >> PAGE_SHIFT; + idx = srcu_read_lock(&kvm->srcu); r = kvm_clear_guest_page(kvm, identity_map_pfn, 0, PAGE_SIZE); if (r < 0) goto out; @@ -2424,6 +2476,7 @@ static int init_rmode_identity_map(struct kvm *kvm) kvm->arch.ept_identity_pagetable_done = true; ret = 1; out: + srcu_read_unlock(&kvm->srcu, idx); return ret; } @@ -2699,22 +2752,6 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) return 0; } -static int init_rmode(struct kvm *kvm) -{ - int idx, ret = 0; - - idx = srcu_read_lock(&kvm->srcu); - if (!init_rmode_tss(kvm)) - goto exit; - if (!init_rmode_identity_map(kvm)) - goto exit; - - ret = 1; -exit: - srcu_read_unlock(&kvm->srcu, idx); - return ret; -} - static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -2722,10 +2759,6 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) int ret; vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP)); - if (!init_rmode(vmx->vcpu.kvm)) { - ret = -ENOMEM; - goto out; - } vmx->rmode.vm86_active = 0; @@ -2805,7 +2838,7 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0); if (vm_need_tpr_shadow(vmx->vcpu.kvm)) vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, - page_to_phys(vmx->vcpu.arch.apic->regs_page)); + __pa(vmx->vcpu.arch.apic->regs)); vmcs_write32(TPR_THRESHOLD, 0); } @@ -2971,6 +3004,9 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) if (ret) return ret; kvm->arch.tss_addr = addr; + if (!init_rmode_tss(kvm)) + return -ENOMEM; + return 0; } @@ -3962,7 +3998,7 @@ static void vmx_cancel_injection(struct kvm_vcpu *vcpu) #define Q "l" #endif -static void vmx_vcpu_run(struct kvm_vcpu *vcpu) +static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -3991,6 +4027,7 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) asm( /* Store host registers */ "push %%"R"dx; push %%"R"bp;" + "push %%"R"cx \n\t" /* placeholder for guest rcx */ "push %%"R"cx \n\t" "cmp %%"R"sp, %c[host_rsp](%0) \n\t" "je 1f \n\t" @@ -4032,10 +4069,11 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) ".Llaunched: " __ex(ASM_VMX_VMRESUME) "\n\t" ".Lkvm_vmx_return: " /* Save guest registers, load host registers, keep flags */ - "xchg %0, (%%"R"sp) \n\t" + "mov %0, %c[wordsize](%%"R"sp) \n\t" + "pop %0 \n\t" "mov %%"R"ax, %c[rax](%0) \n\t" "mov %%"R"bx, %c[rbx](%0) \n\t" - "push"Q" (%%"R"sp); pop"Q" %c[rcx](%0) \n\t" + "pop"Q" %c[rcx](%0) \n\t" "mov %%"R"dx, %c[rdx](%0) \n\t" "mov %%"R"si, %c[rsi](%0) \n\t" "mov %%"R"di, %c[rdi](%0) \n\t" @@ -4053,7 +4091,7 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) "mov %%cr2, %%"R"ax \n\t" "mov %%"R"ax, %c[cr2](%0) \n\t" - "pop %%"R"bp; pop %%"R"bp; pop %%"R"dx \n\t" + "pop %%"R"bp; pop %%"R"dx \n\t" "setbe %c[fail](%0) \n\t" : : "c"(vmx), "d"((unsigned long)HOST_RSP), [launched]"i"(offsetof(struct vcpu_vmx, launched)), @@ -4076,7 +4114,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) [r14]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R14])), [r15]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R15])), #endif - [cr2]"i"(offsetof(struct vcpu_vmx, vcpu.arch.cr2)) + [cr2]"i"(offsetof(struct vcpu_vmx, vcpu.arch.cr2)), + [wordsize]"i"(sizeof(ulong)) : "cc", "memory" , R"ax", R"bx", R"di", R"si" #ifdef CONFIG_X86_64 @@ -4183,8 +4222,11 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) if (!kvm->arch.ept_identity_map_addr) kvm->arch.ept_identity_map_addr = VMX_EPT_IDENTITY_PAGETABLE_ADDR; + err = -ENOMEM; if (alloc_identity_pagetable(kvm) != 0) goto free_vmcs; + if (!init_rmode_identity_map(kvm)) + goto free_vmcs; } return &vmx->vcpu; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index bcc0efce85b..934b4c6b0bf 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -81,9 +81,10 @@ * - enable LME and LMA per default on 64 bit KVM */ #ifdef CONFIG_X86_64 -static u64 __read_mostly efer_reserved_bits = 0xfffffffffffffafeULL; +static +u64 __read_mostly efer_reserved_bits = ~((u64)(EFER_SCE | EFER_LME | EFER_LMA)); #else -static u64 __read_mostly efer_reserved_bits = 0xfffffffffffffffeULL; +static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE); #endif #define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM @@ -360,8 +361,8 @@ void kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) void kvm_inject_nmi(struct kvm_vcpu *vcpu) { + kvm_make_request(KVM_REQ_NMI, vcpu); kvm_make_request(KVM_REQ_EVENT, vcpu); - vcpu->arch.nmi_pending = 1; } EXPORT_SYMBOL_GPL(kvm_inject_nmi); @@ -525,8 +526,10 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) kvm_x86_ops->set_cr0(vcpu, cr0); - if ((cr0 ^ old_cr0) & X86_CR0_PG) + if ((cr0 ^ old_cr0) & X86_CR0_PG) { kvm_clear_async_pf_completion_queue(vcpu); + kvm_async_pf_hash_reset(vcpu); + } if ((cr0 ^ old_cr0) & update_bits) kvm_mmu_reset_context(vcpu); @@ -1017,7 +1020,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data) unsigned long flags; s64 sdiff; - spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags); + raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags); offset = data - native_read_tsc(); ns = get_kernel_ns(); elapsed = ns - kvm->arch.last_tsc_nsec; @@ -1028,7 +1031,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data) /* * Special case: close write to TSC within 5 seconds of * another CPU is interpreted as an attempt to synchronize - * The 5 seconds is to accomodate host load / swapping as + * The 5 seconds is to accommodate host load / swapping as * well as any reset of TSC during the boot process. * * In that case, for a reliable TSC, we can match TSC offsets, @@ -1050,7 +1053,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data) kvm->arch.last_tsc_write = data; kvm->arch.last_tsc_offset = offset; kvm_x86_ops->write_tsc_offset(vcpu, offset); - spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); + raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); /* Reset of TSC must disable overshoot protection below */ vcpu->arch.hv_clock.tsc_timestamp = 0; @@ -1453,6 +1456,14 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) return 0; } +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; + } +} + int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) { switch (msr) { @@ -1510,10 +1521,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) break; case MSR_KVM_SYSTEM_TIME_NEW: case MSR_KVM_SYSTEM_TIME: { - if (vcpu->arch.time_page) { - kvm_release_page_dirty(vcpu->arch.time_page); - vcpu->arch.time_page = NULL; - } + kvmclock_reset(vcpu); vcpu->arch.time = data; kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); @@ -1592,6 +1600,12 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) } else return set_msr_hyperv(vcpu, msr, data); break; + case MSR_IA32_BBL_CR_CTL3: + /* Drop writes to this legacy MSR -- see rdmsr + * counterpart for further detail. + */ + pr_unimpl(vcpu, "ignored wrmsr: 0x%x data %llx\n", msr, data); + break; default: if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr)) return xen_hvm_config(vcpu, data); @@ -1846,6 +1860,19 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) } else return get_msr_hyperv(vcpu, msr, pdata); break; + case MSR_IA32_BBL_CR_CTL3: + /* This legacy MSR exists but isn't fully documented in current + * silicon. It is however accessed by winxp in very narrow + * scenarios where it sets bit #19, itself documented as + * a "reserved" bit. Best effort attempt to source coherent + * read data here should the balance of the register be + * interpreted by the guest: + * + * L2 cache control register 3: 64GB range, 256KB size, + * enabled, latency 0x1, configured + */ + data = 0xbe702111; + break; default: if (!ignore_msrs) { pr_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr); @@ -2100,8 +2127,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (check_tsc_unstable()) { kvm_x86_ops->adjust_tsc_offset(vcpu, -tsc_delta); vcpu->arch.tsc_catchup = 1; - kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); } + kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); if (vcpu->cpu != cpu) kvm_migrate_timers(vcpu); vcpu->cpu = cpu; @@ -2368,9 +2395,9 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, int i; entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - for (i = 1; *nent < maxnent; ++i) { - if (entry[i - 1].eax == 0 && i != 2) - break; + for (i = 1; *nent < maxnent && i < 64; ++i) { + if (entry[i].eax == 0) + continue; do_cpuid_1_ent(&entry[i], function, i); entry[i].flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; @@ -2575,9 +2602,6 @@ static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu, if (mce->status & MCI_STATUS_UC) { if ((vcpu->arch.mcg_status & MCG_STATUS_MCIP) || !kvm_read_cr4_bits(vcpu, X86_CR4_MCE)) { - printk(KERN_DEBUG "kvm: set_mce: " - "injects mce exception while " - "previous one is in progress!\n"); kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); return 0; } @@ -2648,8 +2672,6 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, vcpu->arch.interrupt.pending = events->interrupt.injected; vcpu->arch.interrupt.nr = events->interrupt.nr; vcpu->arch.interrupt.soft = events->interrupt.soft; - if (vcpu->arch.interrupt.pending && irqchip_in_kernel(vcpu->kvm)) - kvm_pic_clear_isr_ack(vcpu->kvm); if (events->flags & KVM_VCPUEVENT_VALID_SHADOW) kvm_x86_ops->set_interrupt_shadow(vcpu, events->interrupt.shadow); @@ -4140,8 +4162,8 @@ static unsigned long emulator_get_cached_segment_base(int seg, return get_segment_base(vcpu, seg); } -static bool emulator_get_cached_descriptor(struct desc_struct *desc, int seg, - struct kvm_vcpu *vcpu) +static bool emulator_get_cached_descriptor(struct desc_struct *desc, u32 *base3, + int seg, struct kvm_vcpu *vcpu) { struct kvm_segment var; @@ -4154,6 +4176,10 @@ static bool emulator_get_cached_descriptor(struct desc_struct *desc, int seg, var.limit >>= 12; set_desc_limit(desc, var.limit); set_desc_base(desc, (unsigned long)var.base); +#ifdef CONFIG_X86_64 + if (base3) + *base3 = var.base >> 32; +#endif desc->type = var.type; desc->s = var.s; desc->dpl = var.dpl; @@ -4166,8 +4192,8 @@ static bool emulator_get_cached_descriptor(struct desc_struct *desc, int seg, return true; } -static void emulator_set_cached_descriptor(struct desc_struct *desc, int seg, - struct kvm_vcpu *vcpu) +static void emulator_set_cached_descriptor(struct desc_struct *desc, u32 base3, + int seg, struct kvm_vcpu *vcpu) { struct kvm_segment var; @@ -4175,6 +4201,9 @@ static void emulator_set_cached_descriptor(struct desc_struct *desc, int seg, kvm_get_segment(vcpu, &var, seg); var.base = get_desc_base(desc); +#ifdef CONFIG_X86_64 + var.base |= ((u64)base3) << 32; +#endif var.limit = get_desc_limit(desc); if (desc->g) var.limit = (var.limit << 12) | 0xfff; @@ -4390,41 +4419,16 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, vcpu->arch.emulate_ctxt.have_exception = false; vcpu->arch.emulate_ctxt.perm_ok = false; + vcpu->arch.emulate_ctxt.only_vendor_specific_insn + = emulation_type & EMULTYPE_TRAP_UD; + r = x86_decode_insn(&vcpu->arch.emulate_ctxt, insn, insn_len); - if (r == X86EMUL_PROPAGATE_FAULT) - goto done; trace_kvm_emulate_insn_start(vcpu); - - /* Only allow emulation of specific instructions on #UD - * (namely VMMCALL, sysenter, sysexit, syscall)*/ - if (emulation_type & EMULTYPE_TRAP_UD) { - if (!c->twobyte) - return EMULATE_FAIL; - switch (c->b) { - case 0x01: /* VMMCALL */ - if (c->modrm_mod != 3 || c->modrm_rm != 1) - return EMULATE_FAIL; - break; - case 0x34: /* sysenter */ - case 0x35: /* sysexit */ - if (c->modrm_mod != 0 || c->modrm_rm != 0) - return EMULATE_FAIL; - break; - case 0x05: /* syscall */ - if (c->modrm_mod != 0 || c->modrm_rm != 0) - return EMULATE_FAIL; - break; - default: - return EMULATE_FAIL; - } - - if (!(c->modrm_reg == 0 || c->modrm_reg == 3)) - return EMULATE_FAIL; - } - ++vcpu->stat.insn_emulation; if (r) { + if (emulation_type & EMULTYPE_TRAP_UD) + return EMULATE_FAIL; if (reexecute_instruction(vcpu, cr2)) return EMULATE_DONE; if (emulation_type & EMULTYPE_SKIP) @@ -4452,7 +4456,6 @@ restart: return handle_emulation_failure(vcpu); } -done: if (vcpu->arch.emulate_ctxt.have_exception) { inject_emulated_exception(vcpu); r = EMULATE_DONE; @@ -4562,7 +4565,7 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va smp_call_function_single(freq->cpu, tsc_khz_changed, freq, 1); - spin_lock(&kvm_lock); + raw_spin_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->cpu != freq->cpu) @@ -4572,7 +4575,7 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va send_ipi = 1; } } - spin_unlock(&kvm_lock); + raw_spin_unlock(&kvm_lock); if (freq->old < freq->new && send_ipi) { /* @@ -4955,12 +4958,6 @@ struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, best = e; break; } - /* - * Both basic or both extended? - */ - if (((e->function ^ function) & 0x80000000) == 0) - if (!best || e->function > best->function) - best = e; } return best; } @@ -4980,6 +4977,27 @@ not_found: return 36; } +/* + * If no match is found, check whether we exceed the vCPU's limit + * and return the content of the highest valid _standard_ leaf instead. + * This is to satisfy the CPUID specification. + */ +static struct kvm_cpuid_entry2* check_cpuid_limit(struct kvm_vcpu *vcpu, + u32 function, u32 index) +{ + struct kvm_cpuid_entry2 *maxlevel; + + maxlevel = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0); + if (!maxlevel || maxlevel->eax >= function) + return NULL; + if (function & 0x80000000) { + maxlevel = kvm_find_cpuid_entry(vcpu, 0, 0); + if (!maxlevel) + return NULL; + } + return kvm_find_cpuid_entry(vcpu, maxlevel->eax, index); +} + void kvm_emulate_cpuid(struct kvm_vcpu *vcpu) { u32 function, index; @@ -4992,6 +5010,10 @@ void kvm_emulate_cpuid(struct kvm_vcpu *vcpu) kvm_register_write(vcpu, VCPU_REGS_RCX, 0); kvm_register_write(vcpu, VCPU_REGS_RDX, 0); best = kvm_find_cpuid_entry(vcpu, function, index); + + if (!best) + best = check_cpuid_limit(vcpu, function, index); + if (best) { kvm_register_write(vcpu, VCPU_REGS_RAX, best->eax); kvm_register_write(vcpu, VCPU_REGS_RBX, best->ebx); @@ -5185,6 +5207,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) r = 1; goto out; } + if (kvm_check_request(KVM_REQ_NMI, vcpu)) + vcpu->arch.nmi_pending = true; } r = kvm_mmu_reload(vcpu); @@ -5213,14 +5237,18 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_load_guest_fpu(vcpu); kvm_load_guest_xcr0(vcpu); - atomic_set(&vcpu->guest_mode, 1); - smp_wmb(); + vcpu->mode = IN_GUEST_MODE; + + /* We should set ->mode before check ->requests, + * see the comment in make_all_cpus_request. + */ + smp_mb(); local_irq_disable(); - if (!atomic_read(&vcpu->guest_mode) || vcpu->requests + if (vcpu->mode == EXITING_GUEST_MODE || vcpu->requests || need_resched() || signal_pending(current)) { - atomic_set(&vcpu->guest_mode, 0); + vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); local_irq_enable(); preempt_enable(); @@ -5256,7 +5284,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_get_msr(vcpu, MSR_IA32_TSC, &vcpu->arch.last_guest_tsc); - atomic_set(&vcpu->guest_mode, 0); + vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); local_irq_enable(); @@ -5574,7 +5602,7 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { int mmu_reset_needed = 0; - int pending_vec, max_bits; + int pending_vec, max_bits, idx; struct desc_ptr dt; dt.size = sregs->idt.limit; @@ -5603,10 +5631,13 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, kvm_x86_ops->set_cr4(vcpu, sregs->cr4); if (sregs->cr4 & X86_CR4_OSXSAVE) update_cpuid(vcpu); + + idx = srcu_read_lock(&vcpu->kvm->srcu); if (!is_long_mode(vcpu) && is_pae(vcpu)) { load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)); mmu_reset_needed = 1; } + srcu_read_unlock(&vcpu->kvm->srcu, idx); if (mmu_reset_needed) kvm_mmu_reset_context(vcpu); @@ -5617,8 +5648,6 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, if (pending_vec < max_bits) { kvm_queue_interrupt(vcpu, pending_vec, false); pr_debug("Set back pending irq %d\n", pending_vec); - if (irqchip_in_kernel(vcpu->kvm)) - kvm_pic_clear_isr_ack(vcpu->kvm); } kvm_set_segment(vcpu, &sregs->cs, VCPU_SREG_CS); @@ -5814,10 +5843,7 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) { - if (vcpu->arch.time_page) { - kvm_release_page_dirty(vcpu->arch.time_page); - vcpu->arch.time_page = NULL; - } + kvmclock_reset(vcpu); free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); fx_free(vcpu); @@ -5878,6 +5904,8 @@ int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu) kvm_make_request(KVM_REQ_EVENT, vcpu); vcpu->arch.apf.msr_val = 0; + kvmclock_reset(vcpu); + kvm_clear_async_pf_completion_queue(vcpu); kvm_async_pf_hash_reset(vcpu); vcpu->arch.apf.halted = false; @@ -6005,7 +6033,7 @@ int kvm_arch_init_vm(struct kvm *kvm) /* Reserve bit 0 of irq_sources_bitmap for userspace irq source */ set_bit(KVM_USERSPACE_IRQ_SOURCE_ID, &kvm->arch.irq_sources_bitmap); - spin_lock_init(&kvm->arch.tsc_write_lock); + raw_spin_lock_init(&kvm->arch.tsc_write_lock); return 0; } @@ -6103,7 +6131,7 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, int user_alloc) { - int npages = mem->memory_size >> PAGE_SHIFT; + int nr_mmu_pages = 0, npages = mem->memory_size >> PAGE_SHIFT; if (!user_alloc && !old.user_alloc && old.rmap && !npages) { int ret; @@ -6118,12 +6146,12 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, "failed to munmap memory\n"); } + if (!kvm->arch.n_requested_mmu_pages) + nr_mmu_pages = kvm_mmu_calculate_mmu_pages(kvm); + spin_lock(&kvm->mmu_lock); - if (!kvm->arch.n_requested_mmu_pages) { - unsigned int nr_mmu_pages = kvm_mmu_calculate_mmu_pages(kvm); + if (nr_mmu_pages) kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages); - } - kvm_mmu_slot_remove_write_access(kvm, mem->slot); spin_unlock(&kvm->mmu_lock); } @@ -6157,7 +6185,7 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu) me = get_cpu(); if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) - if (atomic_xchg(&vcpu->guest_mode, 0)) + if (kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE) smp_send_reschedule(cpu); put_cpu(); } diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 5b96fd95bda..4e0068ead6b 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -397,7 +397,7 @@ static void lguest_load_tr_desc(void) * instead we just use the real "cpuid" instruction. Then I pretty much turned * off feature bits until the Guest booted. (Don't say that: you'll damage * lguest sales!) Shut up, inner voice! (Hey, just pointing out that this is - * hardly future proof.) Noone's listening! They don't like you anyway, + * hardly future proof.) No one's listening! They don't like you anyway, * parenthetic weirdo! * * Replacing the cpuid so we can turn features off is great for the kernel, but @@ -847,7 +847,7 @@ static void __init lguest_init_IRQ(void) void lguest_setup_irq(unsigned int irq) { irq_alloc_desc_at(irq, 0); - set_irq_chip_and_handler_name(irq, &lguest_irq_controller, + irq_set_chip_and_handler_name(irq, &lguest_irq_controller, handle_level_irq, "level"); } @@ -993,7 +993,7 @@ static void lguest_time_irq(unsigned int irq, struct irq_desc *desc) static void lguest_time_init(void) { /* Set up the timer interrupt (0) to go to our simple timer routine */ - set_irq_handler(0, lguest_time_irq); + irq_set_handler(0, lguest_time_irq); clocksource_register_hz(&lguest_clock, NSEC_PER_SEC); diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index e10cf070ede..f2479f19ddd 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -42,4 +42,5 @@ else lib-y += memmove_64.o memset_64.o lib-y += copy_user_64.o rwlock_64.o copy_user_nocache_64.o lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem_64.o + lib-y += cmpxchg16b_emu.o endif diff --git a/arch/x86/lib/atomic64_386_32.S b/arch/x86/lib/atomic64_386_32.S index 2cda60a06e6..e8e7e0d06f4 100644 --- a/arch/x86/lib/atomic64_386_32.S +++ b/arch/x86/lib/atomic64_386_32.S @@ -15,14 +15,12 @@ /* if you want SMP support, implement these with real spinlocks */ .macro LOCK reg - pushfl - CFI_ADJUST_CFA_OFFSET 4 + pushfl_cfi cli .endm .macro UNLOCK reg - popfl - CFI_ADJUST_CFA_OFFSET -4 + popfl_cfi .endm #define BEGIN(op) \ diff --git a/arch/x86/lib/atomic64_cx8_32.S b/arch/x86/lib/atomic64_cx8_32.S index 71e080de335..391a083674b 100644 --- a/arch/x86/lib/atomic64_cx8_32.S +++ b/arch/x86/lib/atomic64_cx8_32.S @@ -14,14 +14,12 @@ #include <asm/dwarf2.h> .macro SAVE reg - pushl %\reg - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %\reg CFI_REL_OFFSET \reg, 0 .endm .macro RESTORE reg - popl %\reg - CFI_ADJUST_CFA_OFFSET -4 + popl_cfi %\reg CFI_RESTORE \reg .endm diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S index adbccd0bbb7..78d16a554db 100644 --- a/arch/x86/lib/checksum_32.S +++ b/arch/x86/lib/checksum_32.S @@ -50,11 +50,9 @@ unsigned int csum_partial(const unsigned char * buff, int len, unsigned int sum) */ ENTRY(csum_partial) CFI_STARTPROC - pushl %esi - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %esi CFI_REL_OFFSET esi, 0 - pushl %ebx - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %ebx CFI_REL_OFFSET ebx, 0 movl 20(%esp),%eax # Function arg: unsigned int sum movl 16(%esp),%ecx # Function arg: int len @@ -132,11 +130,9 @@ ENTRY(csum_partial) jz 8f roll $8, %eax 8: - popl %ebx - CFI_ADJUST_CFA_OFFSET -4 + popl_cfi %ebx CFI_RESTORE ebx - popl %esi - CFI_ADJUST_CFA_OFFSET -4 + popl_cfi %esi CFI_RESTORE esi ret CFI_ENDPROC @@ -148,11 +144,9 @@ ENDPROC(csum_partial) ENTRY(csum_partial) CFI_STARTPROC - pushl %esi - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %esi CFI_REL_OFFSET esi, 0 - pushl %ebx - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %ebx CFI_REL_OFFSET ebx, 0 movl 20(%esp),%eax # Function arg: unsigned int sum movl 16(%esp),%ecx # Function arg: int len @@ -260,11 +254,9 @@ ENTRY(csum_partial) jz 90f roll $8, %eax 90: - popl %ebx - CFI_ADJUST_CFA_OFFSET -4 + popl_cfi %ebx CFI_RESTORE ebx - popl %esi - CFI_ADJUST_CFA_OFFSET -4 + popl_cfi %esi CFI_RESTORE esi ret CFI_ENDPROC @@ -309,14 +301,11 @@ ENTRY(csum_partial_copy_generic) CFI_STARTPROC subl $4,%esp CFI_ADJUST_CFA_OFFSET 4 - pushl %edi - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %edi CFI_REL_OFFSET edi, 0 - pushl %esi - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %esi CFI_REL_OFFSET esi, 0 - pushl %ebx - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %ebx CFI_REL_OFFSET ebx, 0 movl ARGBASE+16(%esp),%eax # sum movl ARGBASE+12(%esp),%ecx # len @@ -426,17 +415,13 @@ DST( movb %cl, (%edi) ) .previous - popl %ebx - CFI_ADJUST_CFA_OFFSET -4 + popl_cfi %ebx CFI_RESTORE ebx - popl %esi - CFI_ADJUST_CFA_OFFSET -4 + popl_cfi %esi CFI_RESTORE esi - popl %edi - CFI_ADJUST_CFA_OFFSET -4 + popl_cfi %edi CFI_RESTORE edi - popl %ecx # equivalent to addl $4,%esp - CFI_ADJUST_CFA_OFFSET -4 + popl_cfi %ecx # equivalent to addl $4,%esp ret CFI_ENDPROC ENDPROC(csum_partial_copy_generic) @@ -459,14 +444,11 @@ ENDPROC(csum_partial_copy_generic) ENTRY(csum_partial_copy_generic) CFI_STARTPROC - pushl %ebx - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %ebx CFI_REL_OFFSET ebx, 0 - pushl %edi - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %edi CFI_REL_OFFSET edi, 0 - pushl %esi - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %esi CFI_REL_OFFSET esi, 0 movl ARGBASE+4(%esp),%esi #src movl ARGBASE+8(%esp),%edi #dst @@ -527,14 +509,11 @@ DST( movb %dl, (%edi) ) jmp 7b .previous - popl %esi - CFI_ADJUST_CFA_OFFSET -4 + popl_cfi %esi CFI_RESTORE esi - popl %edi - CFI_ADJUST_CFA_OFFSET -4 + popl_cfi %edi CFI_RESTORE edi - popl %ebx - CFI_ADJUST_CFA_OFFSET -4 + popl_cfi %ebx CFI_RESTORE ebx ret CFI_ENDPROC diff --git a/arch/x86/lib/cmpxchg16b_emu.S b/arch/x86/lib/cmpxchg16b_emu.S new file mode 100644 index 00000000000..1e572c507d0 --- /dev/null +++ b/arch/x86/lib/cmpxchg16b_emu.S @@ -0,0 +1,65 @@ +/* + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + * + */ +#include <linux/linkage.h> +#include <asm/alternative-asm.h> +#include <asm/frame.h> +#include <asm/dwarf2.h> + +#ifdef CONFIG_SMP +#define SEG_PREFIX %gs: +#else +#define SEG_PREFIX +#endif + +.text + +/* + * Inputs: + * %rsi : memory location to compare + * %rax : low 64 bits of old value + * %rdx : high 64 bits of old value + * %rbx : low 64 bits of new value + * %rcx : high 64 bits of new value + * %al : Operation successful + */ +ENTRY(this_cpu_cmpxchg16b_emu) +CFI_STARTPROC + +# +# Emulate 'cmpxchg16b %gs:(%rsi)' except we return the result in %al not +# via the ZF. Caller will access %al to get result. +# +# Note that this is only useful for a cpuops operation. Meaning that we +# do *not* have a fully atomic operation but just an operation that is +# *atomic* on a single cpu (as provided by the this_cpu_xx class of +# macros). +# +this_cpu_cmpxchg16b_emu: + pushf + cli + + cmpq SEG_PREFIX(%rsi), %rax + jne not_same + cmpq SEG_PREFIX 8(%rsi), %rdx + jne not_same + + movq %rbx, SEG_PREFIX(%rsi) + movq %rcx, SEG_PREFIX 8(%rsi) + + popf + mov $1, %al + ret + + not_same: + popf + xor %al,%al + ret + +CFI_ENDPROC + +ENDPROC(this_cpu_cmpxchg16b_emu) diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index a460158b5ac..99e48261519 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -117,7 +117,7 @@ ENDPROC(bad_from_user) * rdx count * * Output: - * eax uncopied bytes or 0 if successfull. + * eax uncopied bytes or 0 if successful. */ ENTRY(copy_user_generic_unrolled) CFI_STARTPROC diff --git a/arch/x86/lib/csum-copy_64.S b/arch/x86/lib/csum-copy_64.S index f0dba36578e..fb903b758da 100644 --- a/arch/x86/lib/csum-copy_64.S +++ b/arch/x86/lib/csum-copy_64.S @@ -1,6 +1,6 @@ /* - * Copyright 2002,2003 Andi Kleen, SuSE Labs. - * + * Copyright 2002, 2003 Andi Kleen, SuSE Labs. + * * This file is subject to the terms and conditions of the GNU General Public * License. See the file COPYING in the main directory of this archive * for more details. No warranty for anything given at all. @@ -11,82 +11,82 @@ /* * Checksum copy with exception handling. - * On exceptions src_err_ptr or dst_err_ptr is set to -EFAULT and the + * On exceptions src_err_ptr or dst_err_ptr is set to -EFAULT and the * destination is zeroed. - * + * * Input * rdi source * rsi destination * edx len (32bit) - * ecx sum (32bit) + * ecx sum (32bit) * r8 src_err_ptr (int) * r9 dst_err_ptr (int) * * Output * eax 64bit sum. undefined in case of exception. - * - * Wrappers need to take care of valid exception sum and zeroing. + * + * Wrappers need to take care of valid exception sum and zeroing. * They also should align source or destination to 8 bytes. */ .macro source 10: - .section __ex_table,"a" + .section __ex_table, "a" .align 8 - .quad 10b,.Lbad_source + .quad 10b, .Lbad_source .previous .endm - + .macro dest 20: - .section __ex_table,"a" + .section __ex_table, "a" .align 8 - .quad 20b,.Lbad_dest + .quad 20b, .Lbad_dest .previous .endm - + .macro ignore L=.Lignore 30: - .section __ex_table,"a" + .section __ex_table, "a" .align 8 - .quad 30b,\L + .quad 30b, \L .previous .endm - - + + ENTRY(csum_partial_copy_generic) CFI_STARTPROC - cmpl $3*64,%edx - jle .Lignore + cmpl $3*64, %edx + jle .Lignore -.Lignore: - subq $7*8,%rsp +.Lignore: + subq $7*8, %rsp CFI_ADJUST_CFA_OFFSET 7*8 - movq %rbx,2*8(%rsp) + movq %rbx, 2*8(%rsp) CFI_REL_OFFSET rbx, 2*8 - movq %r12,3*8(%rsp) + movq %r12, 3*8(%rsp) CFI_REL_OFFSET r12, 3*8 - movq %r14,4*8(%rsp) + movq %r14, 4*8(%rsp) CFI_REL_OFFSET r14, 4*8 - movq %r13,5*8(%rsp) + movq %r13, 5*8(%rsp) CFI_REL_OFFSET r13, 5*8 - movq %rbp,6*8(%rsp) + movq %rbp, 6*8(%rsp) CFI_REL_OFFSET rbp, 6*8 - movq %r8,(%rsp) - movq %r9,1*8(%rsp) - - movl %ecx,%eax - movl %edx,%ecx + movq %r8, (%rsp) + movq %r9, 1*8(%rsp) - xorl %r9d,%r9d - movq %rcx,%r12 + movl %ecx, %eax + movl %edx, %ecx - shrq $6,%r12 - jz .Lhandle_tail /* < 64 */ + xorl %r9d, %r9d + movq %rcx, %r12 + + shrq $6, %r12 + jz .Lhandle_tail /* < 64 */ clc - + /* main loop. clear in 64 byte blocks */ /* r9: zero, r8: temp2, rbx: temp1, rax: sum, rcx: saved length */ /* r11: temp3, rdx: temp4, r12 loopcnt */ @@ -94,156 +94,156 @@ ENTRY(csum_partial_copy_generic) .p2align 4 .Lloop: source - movq (%rdi),%rbx + movq (%rdi), %rbx source - movq 8(%rdi),%r8 + movq 8(%rdi), %r8 source - movq 16(%rdi),%r11 + movq 16(%rdi), %r11 source - movq 24(%rdi),%rdx + movq 24(%rdi), %rdx source - movq 32(%rdi),%r10 + movq 32(%rdi), %r10 source - movq 40(%rdi),%rbp + movq 40(%rdi), %rbp source - movq 48(%rdi),%r14 + movq 48(%rdi), %r14 source - movq 56(%rdi),%r13 - + movq 56(%rdi), %r13 + ignore 2f prefetcht0 5*64(%rdi) -2: - adcq %rbx,%rax - adcq %r8,%rax - adcq %r11,%rax - adcq %rdx,%rax - adcq %r10,%rax - adcq %rbp,%rax - adcq %r14,%rax - adcq %r13,%rax +2: + adcq %rbx, %rax + adcq %r8, %rax + adcq %r11, %rax + adcq %rdx, %rax + adcq %r10, %rax + adcq %rbp, %rax + adcq %r14, %rax + adcq %r13, %rax decl %r12d - + dest - movq %rbx,(%rsi) + movq %rbx, (%rsi) dest - movq %r8,8(%rsi) + movq %r8, 8(%rsi) dest - movq %r11,16(%rsi) + movq %r11, 16(%rsi) dest - movq %rdx,24(%rsi) + movq %rdx, 24(%rsi) dest - movq %r10,32(%rsi) + movq %r10, 32(%rsi) dest - movq %rbp,40(%rsi) + movq %rbp, 40(%rsi) dest - movq %r14,48(%rsi) + movq %r14, 48(%rsi) dest - movq %r13,56(%rsi) - + movq %r13, 56(%rsi) + 3: - - leaq 64(%rdi),%rdi - leaq 64(%rsi),%rsi - jnz .Lloop + leaq 64(%rdi), %rdi + leaq 64(%rsi), %rsi - adcq %r9,%rax + jnz .Lloop - /* do last upto 56 bytes */ + adcq %r9, %rax + + /* do last up to 56 bytes */ .Lhandle_tail: /* ecx: count */ - movl %ecx,%r10d - andl $63,%ecx - shrl $3,%ecx - jz .Lfold + movl %ecx, %r10d + andl $63, %ecx + shrl $3, %ecx + jz .Lfold clc .p2align 4 -.Lloop_8: +.Lloop_8: source - movq (%rdi),%rbx - adcq %rbx,%rax + movq (%rdi), %rbx + adcq %rbx, %rax decl %ecx dest - movq %rbx,(%rsi) - leaq 8(%rsi),%rsi /* preserve carry */ - leaq 8(%rdi),%rdi + movq %rbx, (%rsi) + leaq 8(%rsi), %rsi /* preserve carry */ + leaq 8(%rdi), %rdi jnz .Lloop_8 - adcq %r9,%rax /* add in carry */ + adcq %r9, %rax /* add in carry */ .Lfold: /* reduce checksum to 32bits */ - movl %eax,%ebx - shrq $32,%rax - addl %ebx,%eax - adcl %r9d,%eax + movl %eax, %ebx + shrq $32, %rax + addl %ebx, %eax + adcl %r9d, %eax - /* do last upto 6 bytes */ + /* do last up to 6 bytes */ .Lhandle_7: - movl %r10d,%ecx - andl $7,%ecx - shrl $1,%ecx + movl %r10d, %ecx + andl $7, %ecx + shrl $1, %ecx jz .Lhandle_1 - movl $2,%edx - xorl %ebx,%ebx - clc + movl $2, %edx + xorl %ebx, %ebx + clc .p2align 4 -.Lloop_1: +.Lloop_1: source - movw (%rdi),%bx - adcl %ebx,%eax + movw (%rdi), %bx + adcl %ebx, %eax decl %ecx dest - movw %bx,(%rsi) - leaq 2(%rdi),%rdi - leaq 2(%rsi),%rsi + movw %bx, (%rsi) + leaq 2(%rdi), %rdi + leaq 2(%rsi), %rsi jnz .Lloop_1 - adcl %r9d,%eax /* add in carry */ - + adcl %r9d, %eax /* add in carry */ + /* handle last odd byte */ .Lhandle_1: - testl $1,%r10d + testl $1, %r10d jz .Lende - xorl %ebx,%ebx + xorl %ebx, %ebx source - movb (%rdi),%bl + movb (%rdi), %bl dest - movb %bl,(%rsi) - addl %ebx,%eax - adcl %r9d,%eax /* carry */ - + movb %bl, (%rsi) + addl %ebx, %eax + adcl %r9d, %eax /* carry */ + CFI_REMEMBER_STATE .Lende: - movq 2*8(%rsp),%rbx + movq 2*8(%rsp), %rbx CFI_RESTORE rbx - movq 3*8(%rsp),%r12 + movq 3*8(%rsp), %r12 CFI_RESTORE r12 - movq 4*8(%rsp),%r14 + movq 4*8(%rsp), %r14 CFI_RESTORE r14 - movq 5*8(%rsp),%r13 + movq 5*8(%rsp), %r13 CFI_RESTORE r13 - movq 6*8(%rsp),%rbp + movq 6*8(%rsp), %rbp CFI_RESTORE rbp - addq $7*8,%rsp + addq $7*8, %rsp CFI_ADJUST_CFA_OFFSET -7*8 ret CFI_RESTORE_STATE /* Exception handlers. Very simple, zeroing is done in the wrappers */ .Lbad_source: - movq (%rsp),%rax - testq %rax,%rax + movq (%rsp), %rax + testq %rax, %rax jz .Lende - movl $-EFAULT,(%rax) + movl $-EFAULT, (%rax) jmp .Lende - + .Lbad_dest: - movq 8(%rsp),%rax - testq %rax,%rax - jz .Lende - movl $-EFAULT,(%rax) + movq 8(%rsp), %rax + testq %rax, %rax + jz .Lende + movl $-EFAULT, (%rax) jmp .Lende CFI_ENDPROC ENDPROC(csum_partial_copy_generic) diff --git a/arch/x86/lib/csum-partial_64.c b/arch/x86/lib/csum-partial_64.c index bf51144d97e..9845371c5c3 100644 --- a/arch/x86/lib/csum-partial_64.c +++ b/arch/x86/lib/csum-partial_64.c @@ -84,7 +84,7 @@ static unsigned do_csum(const unsigned char *buff, unsigned len) count64--; } - /* last upto 7 8byte blocks */ + /* last up to 7 8byte blocks */ count %= 8; while (count) { asm("addq %1,%0\n\t" diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S new file mode 100644 index 00000000000..0ecb8433e5a --- /dev/null +++ b/arch/x86/lib/memmove_64.S @@ -0,0 +1,197 @@ +/* + * Normally compiler builtins are used, but sometimes the compiler calls out + * of line code. Based on asm-i386/string.h. + * + * This assembly file is re-written from memmove_64.c file. + * - Copyright 2011 Fenghua Yu <fenghua.yu@intel.com> + */ +#define _STRING_C +#include <linux/linkage.h> +#include <asm/dwarf2.h> + +#undef memmove + +/* + * Implement memmove(). This can handle overlap between src and dst. + * + * Input: + * rdi: dest + * rsi: src + * rdx: count + * + * Output: + * rax: dest + */ +ENTRY(memmove) + CFI_STARTPROC + /* Handle more 32bytes in loop */ + mov %rdi, %rax + cmp $0x20, %rdx + jb 1f + + /* Decide forward/backward copy mode */ + cmp %rdi, %rsi + jb 2f + + /* + * movsq instruction have many startup latency + * so we handle small size by general register. + */ + cmp $680, %rdx + jb 3f + /* + * movsq instruction is only good for aligned case. + */ + + cmpb %dil, %sil + je 4f +3: + sub $0x20, %rdx + /* + * We gobble 32byts forward in each loop. + */ +5: + sub $0x20, %rdx + movq 0*8(%rsi), %r11 + movq 1*8(%rsi), %r10 + movq 2*8(%rsi), %r9 + movq 3*8(%rsi), %r8 + leaq 4*8(%rsi), %rsi + + movq %r11, 0*8(%rdi) + movq %r10, 1*8(%rdi) + movq %r9, 2*8(%rdi) + movq %r8, 3*8(%rdi) + leaq 4*8(%rdi), %rdi + jae 5b + addq $0x20, %rdx + jmp 1f + /* + * Handle data forward by movsq. + */ + .p2align 4 +4: + movq %rdx, %rcx + movq -8(%rsi, %rdx), %r11 + lea -8(%rdi, %rdx), %r10 + shrq $3, %rcx + rep movsq + movq %r11, (%r10) + jmp 13f + /* + * Handle data backward by movsq. + */ + .p2align 4 +7: + movq %rdx, %rcx + movq (%rsi), %r11 + movq %rdi, %r10 + leaq -8(%rsi, %rdx), %rsi + leaq -8(%rdi, %rdx), %rdi + shrq $3, %rcx + std + rep movsq + cld + movq %r11, (%r10) + jmp 13f + + /* + * Start to prepare for backward copy. + */ + .p2align 4 +2: + cmp $680, %rdx + jb 6f + cmp %dil, %sil + je 7b +6: + /* + * Calculate copy position to tail. + */ + addq %rdx, %rsi + addq %rdx, %rdi + subq $0x20, %rdx + /* + * We gobble 32byts backward in each loop. + */ +8: + subq $0x20, %rdx + movq -1*8(%rsi), %r11 + movq -2*8(%rsi), %r10 + movq -3*8(%rsi), %r9 + movq -4*8(%rsi), %r8 + leaq -4*8(%rsi), %rsi + + movq %r11, -1*8(%rdi) + movq %r10, -2*8(%rdi) + movq %r9, -3*8(%rdi) + movq %r8, -4*8(%rdi) + leaq -4*8(%rdi), %rdi + jae 8b + /* + * Calculate copy position to head. + */ + addq $0x20, %rdx + subq %rdx, %rsi + subq %rdx, %rdi +1: + cmpq $16, %rdx + jb 9f + /* + * Move data from 16 bytes to 31 bytes. + */ + movq 0*8(%rsi), %r11 + movq 1*8(%rsi), %r10 + movq -2*8(%rsi, %rdx), %r9 + movq -1*8(%rsi, %rdx), %r8 + movq %r11, 0*8(%rdi) + movq %r10, 1*8(%rdi) + movq %r9, -2*8(%rdi, %rdx) + movq %r8, -1*8(%rdi, %rdx) + jmp 13f + .p2align 4 +9: + cmpq $8, %rdx + jb 10f + /* + * Move data from 8 bytes to 15 bytes. + */ + movq 0*8(%rsi), %r11 + movq -1*8(%rsi, %rdx), %r10 + movq %r11, 0*8(%rdi) + movq %r10, -1*8(%rdi, %rdx) + jmp 13f +10: + cmpq $4, %rdx + jb 11f + /* + * Move data from 4 bytes to 7 bytes. + */ + movl (%rsi), %r11d + movl -4(%rsi, %rdx), %r10d + movl %r11d, (%rdi) + movl %r10d, -4(%rdi, %rdx) + jmp 13f +11: + cmp $2, %rdx + jb 12f + /* + * Move data from 2 bytes to 3 bytes. + */ + movw (%rsi), %r11w + movw -2(%rsi, %rdx), %r10w + movw %r11w, (%rdi) + movw %r10w, -2(%rdi, %rdx) + jmp 13f +12: + cmp $1, %rdx + jb 13f + /* + * Move data for 1 byte. + */ + movb (%rsi), %r11b + movb %r11b, (%rdi) +13: + retq + CFI_ENDPROC +ENDPROC(memmove) diff --git a/arch/x86/lib/memmove_64.c b/arch/x86/lib/memmove_64.c deleted file mode 100644 index 6d0f0ec41b3..00000000000 --- a/arch/x86/lib/memmove_64.c +++ /dev/null @@ -1,192 +0,0 @@ -/* Normally compiler builtins are used, but sometimes the compiler calls out - of line code. Based on asm-i386/string.h. - */ -#define _STRING_C -#include <linux/string.h> -#include <linux/module.h> - -#undef memmove -void *memmove(void *dest, const void *src, size_t count) -{ - unsigned long d0,d1,d2,d3,d4,d5,d6,d7; - char *ret; - - __asm__ __volatile__( - /* Handle more 32bytes in loop */ - "mov %2, %3\n\t" - "cmp $0x20, %0\n\t" - "jb 1f\n\t" - - /* Decide forward/backward copy mode */ - "cmp %2, %1\n\t" - "jb 2f\n\t" - - /* - * movsq instruction have many startup latency - * so we handle small size by general register. - */ - "cmp $680, %0\n\t" - "jb 3f\n\t" - /* - * movsq instruction is only good for aligned case. - */ - "cmpb %%dil, %%sil\n\t" - "je 4f\n\t" - "3:\n\t" - "sub $0x20, %0\n\t" - /* - * We gobble 32byts forward in each loop. - */ - "5:\n\t" - "sub $0x20, %0\n\t" - "movq 0*8(%1), %4\n\t" - "movq 1*8(%1), %5\n\t" - "movq 2*8(%1), %6\n\t" - "movq 3*8(%1), %7\n\t" - "leaq 4*8(%1), %1\n\t" - - "movq %4, 0*8(%2)\n\t" - "movq %5, 1*8(%2)\n\t" - "movq %6, 2*8(%2)\n\t" - "movq %7, 3*8(%2)\n\t" - "leaq 4*8(%2), %2\n\t" - "jae 5b\n\t" - "addq $0x20, %0\n\t" - "jmp 1f\n\t" - /* - * Handle data forward by movsq. - */ - ".p2align 4\n\t" - "4:\n\t" - "movq %0, %8\n\t" - "movq -8(%1, %0), %4\n\t" - "lea -8(%2, %0), %5\n\t" - "shrq $3, %8\n\t" - "rep movsq\n\t" - "movq %4, (%5)\n\t" - "jmp 13f\n\t" - /* - * Handle data backward by movsq. - */ - ".p2align 4\n\t" - "7:\n\t" - "movq %0, %8\n\t" - "movq (%1), %4\n\t" - "movq %2, %5\n\t" - "leaq -8(%1, %0), %1\n\t" - "leaq -8(%2, %0), %2\n\t" - "shrq $3, %8\n\t" - "std\n\t" - "rep movsq\n\t" - "cld\n\t" - "movq %4, (%5)\n\t" - "jmp 13f\n\t" - - /* - * Start to prepare for backward copy. - */ - ".p2align 4\n\t" - "2:\n\t" - "cmp $680, %0\n\t" - "jb 6f \n\t" - "cmp %%dil, %%sil\n\t" - "je 7b \n\t" - "6:\n\t" - /* - * Calculate copy position to tail. - */ - "addq %0, %1\n\t" - "addq %0, %2\n\t" - "subq $0x20, %0\n\t" - /* - * We gobble 32byts backward in each loop. - */ - "8:\n\t" - "subq $0x20, %0\n\t" - "movq -1*8(%1), %4\n\t" - "movq -2*8(%1), %5\n\t" - "movq -3*8(%1), %6\n\t" - "movq -4*8(%1), %7\n\t" - "leaq -4*8(%1), %1\n\t" - - "movq %4, -1*8(%2)\n\t" - "movq %5, -2*8(%2)\n\t" - "movq %6, -3*8(%2)\n\t" - "movq %7, -4*8(%2)\n\t" - "leaq -4*8(%2), %2\n\t" - "jae 8b\n\t" - /* - * Calculate copy position to head. - */ - "addq $0x20, %0\n\t" - "subq %0, %1\n\t" - "subq %0, %2\n\t" - "1:\n\t" - "cmpq $16, %0\n\t" - "jb 9f\n\t" - /* - * Move data from 16 bytes to 31 bytes. - */ - "movq 0*8(%1), %4\n\t" - "movq 1*8(%1), %5\n\t" - "movq -2*8(%1, %0), %6\n\t" - "movq -1*8(%1, %0), %7\n\t" - "movq %4, 0*8(%2)\n\t" - "movq %5, 1*8(%2)\n\t" - "movq %6, -2*8(%2, %0)\n\t" - "movq %7, -1*8(%2, %0)\n\t" - "jmp 13f\n\t" - ".p2align 4\n\t" - "9:\n\t" - "cmpq $8, %0\n\t" - "jb 10f\n\t" - /* - * Move data from 8 bytes to 15 bytes. - */ - "movq 0*8(%1), %4\n\t" - "movq -1*8(%1, %0), %5\n\t" - "movq %4, 0*8(%2)\n\t" - "movq %5, -1*8(%2, %0)\n\t" - "jmp 13f\n\t" - "10:\n\t" - "cmpq $4, %0\n\t" - "jb 11f\n\t" - /* - * Move data from 4 bytes to 7 bytes. - */ - "movl (%1), %4d\n\t" - "movl -4(%1, %0), %5d\n\t" - "movl %4d, (%2)\n\t" - "movl %5d, -4(%2, %0)\n\t" - "jmp 13f\n\t" - "11:\n\t" - "cmp $2, %0\n\t" - "jb 12f\n\t" - /* - * Move data from 2 bytes to 3 bytes. - */ - "movw (%1), %4w\n\t" - "movw -2(%1, %0), %5w\n\t" - "movw %4w, (%2)\n\t" - "movw %5w, -2(%2, %0)\n\t" - "jmp 13f\n\t" - "12:\n\t" - "cmp $1, %0\n\t" - "jb 13f\n\t" - /* - * Move data for 1 byte. - */ - "movb (%1), %4b\n\t" - "movb %4b, (%2)\n\t" - "13:\n\t" - : "=&d" (d0), "=&S" (d1), "=&D" (d2), "=&a" (ret) , - "=r"(d3), "=r"(d4), "=r"(d5), "=r"(d6), "=&c" (d7) - :"0" (count), - "1" (src), - "2" (dest) - :"memory"); - - return ret; - -} -EXPORT_SYMBOL(memmove); diff --git a/arch/x86/lib/rwsem_64.S b/arch/x86/lib/rwsem_64.S index 41fcf00e49d..67743977398 100644 --- a/arch/x86/lib/rwsem_64.S +++ b/arch/x86/lib/rwsem_64.S @@ -23,43 +23,50 @@ #include <asm/dwarf2.h> #define save_common_regs \ - pushq %rdi; \ - pushq %rsi; \ - pushq %rcx; \ - pushq %r8; \ - pushq %r9; \ - pushq %r10; \ - pushq %r11 + pushq_cfi %rdi; CFI_REL_OFFSET rdi, 0; \ + pushq_cfi %rsi; CFI_REL_OFFSET rsi, 0; \ + pushq_cfi %rcx; CFI_REL_OFFSET rcx, 0; \ + pushq_cfi %r8; CFI_REL_OFFSET r8, 0; \ + pushq_cfi %r9; CFI_REL_OFFSET r9, 0; \ + pushq_cfi %r10; CFI_REL_OFFSET r10, 0; \ + pushq_cfi %r11; CFI_REL_OFFSET r11, 0 #define restore_common_regs \ - popq %r11; \ - popq %r10; \ - popq %r9; \ - popq %r8; \ - popq %rcx; \ - popq %rsi; \ - popq %rdi + popq_cfi %r11; CFI_RESTORE r11; \ + popq_cfi %r10; CFI_RESTORE r10; \ + popq_cfi %r9; CFI_RESTORE r9; \ + popq_cfi %r8; CFI_RESTORE r8; \ + popq_cfi %rcx; CFI_RESTORE rcx; \ + popq_cfi %rsi; CFI_RESTORE rsi; \ + popq_cfi %rdi; CFI_RESTORE rdi /* Fix up special calling conventions */ ENTRY(call_rwsem_down_read_failed) + CFI_STARTPROC save_common_regs - pushq %rdx + pushq_cfi %rdx + CFI_REL_OFFSET rdx, 0 movq %rax,%rdi call rwsem_down_read_failed - popq %rdx + popq_cfi %rdx + CFI_RESTORE rdx restore_common_regs ret - ENDPROC(call_rwsem_down_read_failed) + CFI_ENDPROC +ENDPROC(call_rwsem_down_read_failed) ENTRY(call_rwsem_down_write_failed) + CFI_STARTPROC save_common_regs movq %rax,%rdi call rwsem_down_write_failed restore_common_regs ret - ENDPROC(call_rwsem_down_write_failed) + CFI_ENDPROC +ENDPROC(call_rwsem_down_write_failed) ENTRY(call_rwsem_wake) + CFI_STARTPROC decl %edx /* do nothing if still outstanding active readers */ jnz 1f save_common_regs @@ -67,15 +74,20 @@ ENTRY(call_rwsem_wake) call rwsem_wake restore_common_regs 1: ret - ENDPROC(call_rwsem_wake) + CFI_ENDPROC +ENDPROC(call_rwsem_wake) /* Fix up special calling conventions */ ENTRY(call_rwsem_downgrade_wake) + CFI_STARTPROC save_common_regs - pushq %rdx + pushq_cfi %rdx + CFI_REL_OFFSET rdx, 0 movq %rax,%rdi call rwsem_downgrade_wake - popq %rdx + popq_cfi %rdx + CFI_RESTORE rdx restore_common_regs ret - ENDPROC(call_rwsem_downgrade_wake) + CFI_ENDPROC +ENDPROC(call_rwsem_downgrade_wake) diff --git a/arch/x86/lib/semaphore_32.S b/arch/x86/lib/semaphore_32.S index 648fe474178..06691daa410 100644 --- a/arch/x86/lib/semaphore_32.S +++ b/arch/x86/lib/semaphore_32.S @@ -36,7 +36,7 @@ */ #ifdef CONFIG_SMP ENTRY(__write_lock_failed) - CFI_STARTPROC simple + CFI_STARTPROC FRAME 2: LOCK_PREFIX addl $ RW_LOCK_BIAS,(%eax) @@ -74,29 +74,23 @@ ENTRY(__read_lock_failed) /* Fix up special calling conventions */ ENTRY(call_rwsem_down_read_failed) CFI_STARTPROC - push %ecx - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %ecx CFI_REL_OFFSET ecx,0 - push %edx - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %edx CFI_REL_OFFSET edx,0 call rwsem_down_read_failed - pop %edx - CFI_ADJUST_CFA_OFFSET -4 - pop %ecx - CFI_ADJUST_CFA_OFFSET -4 + popl_cfi %edx + popl_cfi %ecx ret CFI_ENDPROC ENDPROC(call_rwsem_down_read_failed) ENTRY(call_rwsem_down_write_failed) CFI_STARTPROC - push %ecx - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %ecx CFI_REL_OFFSET ecx,0 calll rwsem_down_write_failed - pop %ecx - CFI_ADJUST_CFA_OFFSET -4 + popl_cfi %ecx ret CFI_ENDPROC ENDPROC(call_rwsem_down_write_failed) @@ -105,12 +99,10 @@ ENTRY(call_rwsem_wake) CFI_STARTPROC decw %dx /* do nothing if still outstanding active readers */ jnz 1f - push %ecx - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %ecx CFI_REL_OFFSET ecx,0 call rwsem_wake - pop %ecx - CFI_ADJUST_CFA_OFFSET -4 + popl_cfi %ecx 1: ret CFI_ENDPROC ENDPROC(call_rwsem_wake) @@ -118,17 +110,13 @@ ENTRY(call_rwsem_wake) /* Fix up special calling conventions */ ENTRY(call_rwsem_downgrade_wake) CFI_STARTPROC - push %ecx - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %ecx CFI_REL_OFFSET ecx,0 - push %edx - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %edx CFI_REL_OFFSET edx,0 call rwsem_downgrade_wake - pop %edx - CFI_ADJUST_CFA_OFFSET -4 - pop %ecx - CFI_ADJUST_CFA_OFFSET -4 + popl_cfi %edx + popl_cfi %ecx ret CFI_ENDPROC ENDPROC(call_rwsem_downgrade_wake) diff --git a/arch/x86/lib/thunk_32.S b/arch/x86/lib/thunk_32.S index 650b11e00ec..2930ae05d77 100644 --- a/arch/x86/lib/thunk_32.S +++ b/arch/x86/lib/thunk_32.S @@ -7,24 +7,6 @@ #include <linux/linkage.h> -#define ARCH_TRACE_IRQS_ON \ - pushl %eax; \ - pushl %ecx; \ - pushl %edx; \ - call trace_hardirqs_on; \ - popl %edx; \ - popl %ecx; \ - popl %eax; - -#define ARCH_TRACE_IRQS_OFF \ - pushl %eax; \ - pushl %ecx; \ - pushl %edx; \ - call trace_hardirqs_off; \ - popl %edx; \ - popl %ecx; \ - popl %eax; - #ifdef CONFIG_TRACE_IRQFLAGS /* put return address in eax (arg1) */ .macro thunk_ra name,func diff --git a/arch/x86/lib/thunk_64.S b/arch/x86/lib/thunk_64.S index bf9a7d5a542..782b082c9ff 100644 --- a/arch/x86/lib/thunk_64.S +++ b/arch/x86/lib/thunk_64.S @@ -22,26 +22,6 @@ CFI_ENDPROC .endm - /* rdi: arg1 ... normal C conventions. rax is passed from C. */ - .macro thunk_retrax name,func - .globl \name -\name: - CFI_STARTPROC - SAVE_ARGS - call \func - jmp restore_norax - CFI_ENDPROC - .endm - - - .section .sched.text, "ax" -#ifdef CONFIG_RWSEM_XCHGADD_ALGORITHM - thunk rwsem_down_read_failed_thunk,rwsem_down_read_failed - thunk rwsem_down_write_failed_thunk,rwsem_down_write_failed - thunk rwsem_wake_thunk,rwsem_wake - thunk rwsem_downgrade_thunk,rwsem_downgrade_wake -#endif - #ifdef CONFIG_TRACE_IRQFLAGS /* put return address in rdi (arg1) */ .macro thunk_ra name,func @@ -72,10 +52,3 @@ restore: RESTORE_ARGS ret CFI_ENDPROC - - CFI_STARTPROC - SAVE_ARGS -restore_norax: - RESTORE_ARGS 1 - ret - CFI_ENDPROC diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 09df2f9a3d6..3e608edf995 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -25,6 +25,7 @@ obj-$(CONFIG_MMIOTRACE_TEST) += testmmiotrace.o obj-$(CONFIG_NUMA) += numa.o numa_$(BITS).o obj-$(CONFIG_AMD_NUMA) += amdtopology_64.o obj-$(CONFIG_ACPI_NUMA) += srat_$(BITS).o +obj-$(CONFIG_NUMA_EMU) += numa_emulation.o obj-$(CONFIG_HAVE_MEMBLOCK) += memblock.o diff --git a/arch/x86/mm/amdtopology_64.c b/arch/x86/mm/amdtopology_64.c index f21962c435e..0919c26820d 100644 --- a/arch/x86/mm/amdtopology_64.c +++ b/arch/x86/mm/amdtopology_64.c @@ -26,9 +26,7 @@ #include <asm/apic.h> #include <asm/amd_nb.h> -static struct bootnode __initdata nodes[8]; static unsigned char __initdata nodeids[8]; -static nodemask_t __initdata nodes_parsed = NODE_MASK_NONE; static __init int find_northbridge(void) { @@ -51,7 +49,7 @@ static __init int find_northbridge(void) return num; } - return -1; + return -ENOENT; } static __init void early_get_boot_cpu_id(void) @@ -69,17 +67,18 @@ static __init void early_get_boot_cpu_id(void) #endif } -int __init amd_numa_init(unsigned long start_pfn, unsigned long end_pfn) +int __init amd_numa_init(void) { - unsigned long start = PFN_PHYS(start_pfn); - unsigned long end = PFN_PHYS(end_pfn); + unsigned long start = PFN_PHYS(0); + unsigned long end = PFN_PHYS(max_pfn); unsigned numnodes; unsigned long prevbase; - int i, nb, found = 0; + int i, j, nb; u32 nodeid, reg; + unsigned int bits, cores, apicid_base; if (!early_pci_allowed()) - return -1; + return -EINVAL; nb = find_northbridge(); if (nb < 0) @@ -90,7 +89,7 @@ int __init amd_numa_init(unsigned long start_pfn, unsigned long end_pfn) reg = read_pci_config(0, nb, 0, 0x60); numnodes = ((reg >> 4) & 0xF) + 1; if (numnodes <= 1) - return -1; + return -ENOENT; pr_info("Number of physical nodes %d\n", numnodes); @@ -121,9 +120,9 @@ int __init amd_numa_init(unsigned long start_pfn, unsigned long end_pfn) if ((base >> 8) & 3 || (limit >> 8) & 3) { pr_err("Node %d using interleaving mode %lx/%lx\n", nodeid, (base >> 8) & 3, (limit >> 8) & 3); - return -1; + return -EINVAL; } - if (node_isset(nodeid, nodes_parsed)) { + if (node_isset(nodeid, numa_nodes_parsed)) { pr_info("Node %d already present, skipping\n", nodeid); continue; @@ -160,117 +159,28 @@ int __init amd_numa_init(unsigned long start_pfn, unsigned long end_pfn) if (prevbase > base) { pr_err("Node map not sorted %lx,%lx\n", prevbase, base); - return -1; + return -EINVAL; } pr_info("Node %d MemBase %016lx Limit %016lx\n", nodeid, base, limit); - found++; - - nodes[nodeid].start = base; - nodes[nodeid].end = limit; - prevbase = base; - - node_set(nodeid, nodes_parsed); - } - - if (!found) - return -1; - return 0; -} - -#ifdef CONFIG_NUMA_EMU -static s16 fake_apicid_to_node[MAX_LOCAL_APIC] __initdata = { - [0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE -}; - -void __init amd_get_nodes(struct bootnode *physnodes) -{ - int i; - - for_each_node_mask(i, nodes_parsed) { - physnodes[i].start = nodes[i].start; - physnodes[i].end = nodes[i].end; + numa_add_memblk(nodeid, base, limit); + node_set(nodeid, numa_nodes_parsed); } -} - -static int __init find_node_by_addr(unsigned long addr) -{ - int ret = NUMA_NO_NODE; - int i; - - for (i = 0; i < 8; i++) - if (addr >= nodes[i].start && addr < nodes[i].end) { - ret = i; - break; - } - return ret; -} -/* - * For NUMA emulation, fake proximity domain (_PXM) to node id mappings must be - * setup to represent the physical topology but reflect the emulated - * environment. For each emulated node, the real node which it appears on is - * found and a fake pxm to nid mapping is created which mirrors the actual - * locality. node_distance() then represents the correct distances between - * emulated nodes by using the fake acpi mappings to pxms. - */ -void __init amd_fake_nodes(const struct bootnode *nodes, int nr_nodes) -{ - unsigned int bits; - unsigned int cores; - unsigned int apicid_base = 0; - int i; + if (!nodes_weight(numa_nodes_parsed)) + return -ENOENT; + /* + * We seem to have valid NUMA configuration. Map apicids to nodes + * using the coreid bits from early_identify_cpu. + */ bits = boot_cpu_data.x86_coreid_bits; cores = 1 << bits; - early_get_boot_cpu_id(); - if (boot_cpu_physical_apicid > 0) - apicid_base = boot_cpu_physical_apicid; - - for (i = 0; i < nr_nodes; i++) { - int index; - int nid; - int j; - - nid = find_node_by_addr(nodes[i].start); - if (nid == NUMA_NO_NODE) - continue; - - index = nodeids[nid] << bits; - if (fake_apicid_to_node[index + apicid_base] == NUMA_NO_NODE) - for (j = apicid_base; j < cores + apicid_base; j++) - fake_apicid_to_node[index + j] = i; -#ifdef CONFIG_ACPI_NUMA - __acpi_map_pxm_to_node(nid, i); -#endif - } - memcpy(apicid_to_node, fake_apicid_to_node, sizeof(apicid_to_node)); -} -#endif /* CONFIG_NUMA_EMU */ - -int __init amd_scan_nodes(void) -{ - unsigned int bits; - unsigned int cores; - unsigned int apicid_base; - int i; - - BUG_ON(nodes_empty(nodes_parsed)); - node_possible_map = nodes_parsed; - memnode_shift = compute_hash_shift(nodes, 8, NULL); - if (memnode_shift < 0) { - pr_err("No NUMA node hash function found. Contact maintainer\n"); - return -1; - } - pr_info("Using node hash shift of %d\n", memnode_shift); - - /* use the coreid bits from early_identify_cpu */ - bits = boot_cpu_data.x86_coreid_bits; - cores = (1<<bits); apicid_base = 0; + /* get the APIC ID of the BSP early for systems with apicid lifting */ early_get_boot_cpu_id(); if (boot_cpu_physical_apicid > 0) { @@ -278,17 +188,9 @@ int __init amd_scan_nodes(void) apicid_base = boot_cpu_physical_apicid; } - for_each_node_mask(i, node_possible_map) { - int j; - - memblock_x86_register_active_regions(i, - nodes[i].start >> PAGE_SHIFT, - nodes[i].end >> PAGE_SHIFT); + for_each_node_mask(i, numa_nodes_parsed) for (j = apicid_base; j < cores + apicid_base; j++) - apicid_to_node[(i << bits) + j] = i; - setup_node_bootmem(i, nodes[i].start, nodes[i].end); - } + set_apicid_to_node((i << bits) + j, i); - numa_init_array(); return 0; } diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 7d90ceb882a..20e3f8702d1 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -229,15 +229,14 @@ void vmalloc_sync_all(void) for (address = VMALLOC_START & PMD_MASK; address >= TASK_SIZE && address < FIXADDR_TOP; address += PMD_SIZE) { - - unsigned long flags; struct page *page; - spin_lock_irqsave(&pgd_lock, flags); + spin_lock(&pgd_lock); list_for_each_entry(page, &pgd_list, lru) { spinlock_t *pgt_lock; pmd_t *ret; + /* the pgt_lock only for Xen */ pgt_lock = &pgd_page_get_mm(page)->page_table_lock; spin_lock(pgt_lock); @@ -247,7 +246,7 @@ void vmalloc_sync_all(void) if (!ret) break; } - spin_unlock_irqrestore(&pgd_lock, flags); + spin_unlock(&pgd_lock); } } @@ -828,6 +827,13 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, unsigned long address, unsigned int fault) { if (fault & VM_FAULT_OOM) { + /* Kernel mode? Handle exceptions or die: */ + if (!(error_code & PF_USER)) { + up_read(¤t->mm->mmap_sem); + no_context(regs, error_code, address); + return; + } + out_of_memory(regs, error_code, address); } else { if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON| diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 069ce7c37c0..d4203988504 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -326,7 +326,7 @@ try_again: if (mm->free_area_cache < len) goto fail; - /* either no address requested or cant fit in requested address hole */ + /* either no address requested or can't fit in requested address hole */ addr = (mm->free_area_cache - len) & huge_page_mask(h); do { /* diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 947f42abe82..286d289b039 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -18,9 +18,9 @@ DEFINE_PER_CPU(struct mmu_gather, mmu_gathers); -unsigned long __initdata e820_table_start; -unsigned long __meminitdata e820_table_end; -unsigned long __meminitdata e820_table_top; +unsigned long __initdata pgt_buf_start; +unsigned long __meminitdata pgt_buf_end; +unsigned long __meminitdata pgt_buf_top; int after_bootmem; @@ -33,7 +33,7 @@ int direct_gbpages static void __init find_early_table_space(unsigned long end, int use_pse, int use_gbpages) { - unsigned long puds, pmds, ptes, tables, start; + unsigned long puds, pmds, ptes, tables, start = 0, good_end = end; phys_addr_t base; puds = (end + PUD_SIZE - 1) >> PUD_SHIFT; @@ -65,29 +65,20 @@ static void __init find_early_table_space(unsigned long end, int use_pse, #ifdef CONFIG_X86_32 /* for fixmap */ tables += roundup(__end_of_fixed_addresses * sizeof(pte_t), PAGE_SIZE); -#endif - /* - * RED-PEN putting page tables only on node 0 could - * cause a hotspot and fill up ZONE_DMA. The page tables - * need roughly 0.5KB per GB. - */ -#ifdef CONFIG_X86_32 - start = 0x7000; -#else - start = 0x8000; + good_end = max_pfn_mapped << PAGE_SHIFT; #endif - base = memblock_find_in_range(start, max_pfn_mapped<<PAGE_SHIFT, - tables, PAGE_SIZE); + + base = memblock_find_in_range(start, good_end, tables, PAGE_SIZE); if (base == MEMBLOCK_ERROR) panic("Cannot find space for the kernel page tables"); - e820_table_start = base >> PAGE_SHIFT; - e820_table_end = e820_table_start; - e820_table_top = e820_table_start + (tables >> PAGE_SHIFT); + pgt_buf_start = base >> PAGE_SHIFT; + pgt_buf_end = pgt_buf_start; + pgt_buf_top = pgt_buf_start + (tables >> PAGE_SHIFT); printk(KERN_DEBUG "kernel direct mapping tables up to %lx @ %lx-%lx\n", - end, e820_table_start << PAGE_SHIFT, e820_table_top << PAGE_SHIFT); + end, pgt_buf_start << PAGE_SHIFT, pgt_buf_top << PAGE_SHIFT); } struct map_range { @@ -279,30 +270,11 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, load_cr3(swapper_pg_dir); #endif -#ifdef CONFIG_X86_64 - if (!after_bootmem && !start) { - pud_t *pud; - pmd_t *pmd; - - mmu_cr4_features = read_cr4(); - - /* - * _brk_end cannot change anymore, but it and _end may be - * located on different 2M pages. cleanup_highmap(), however, - * can only consider _end when it runs, so destroy any - * mappings beyond _brk_end here. - */ - pud = pud_offset(pgd_offset_k(_brk_end), _brk_end); - pmd = pmd_offset(pud, _brk_end - 1); - while (++pmd <= pmd_offset(pud, (unsigned long)_end - 1)) - pmd_clear(pmd); - } -#endif __flush_tlb_all(); - if (!after_bootmem && e820_table_end > e820_table_start) - memblock_x86_reserve_range(e820_table_start << PAGE_SHIFT, - e820_table_end << PAGE_SHIFT, "PGTABLE"); + if (!after_bootmem && pgt_buf_end > pgt_buf_start) + memblock_x86_reserve_range(pgt_buf_start << PAGE_SHIFT, + pgt_buf_end << PAGE_SHIFT, "PGTABLE"); if (!after_bootmem) early_memtest(start, end); diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index c821074b7f0..80088f99419 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -62,10 +62,10 @@ bool __read_mostly __vmalloc_start_set = false; static __init void *alloc_low_page(void) { - unsigned long pfn = e820_table_end++; + unsigned long pfn = pgt_buf_end++; void *adr; - if (pfn >= e820_table_top) + if (pfn >= pgt_buf_top) panic("alloc_low_page: ran out of memory"); adr = __va(pfn * PAGE_SIZE); @@ -163,8 +163,8 @@ static pte_t *__init page_table_kmap_check(pte_t *pte, pmd_t *pmd, if (pmd_idx_kmap_begin != pmd_idx_kmap_end && (vaddr >> PMD_SHIFT) >= pmd_idx_kmap_begin && (vaddr >> PMD_SHIFT) <= pmd_idx_kmap_end - && ((__pa(pte) >> PAGE_SHIFT) < e820_table_start - || (__pa(pte) >> PAGE_SHIFT) >= e820_table_end)) { + && ((__pa(pte) >> PAGE_SHIFT) < pgt_buf_start + || (__pa(pte) >> PAGE_SHIFT) >= pgt_buf_end)) { pte_t *newpte; int i; @@ -644,8 +644,7 @@ void __init find_low_pfn_range(void) } #ifndef CONFIG_NEED_MULTIPLE_NODES -void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn, - int acpi, int k8) +void __init initmem_init(void) { #ifdef CONFIG_HIGHMEM highstart_pfn = highend_pfn = max_pfn; @@ -918,7 +917,7 @@ static void mark_nxdata_nx(void) { /* * When this called, init has already been executed and released, - * so everything past _etext sould be NX. + * so everything past _etext should be NX. */ unsigned long start = PFN_ALIGN(_etext); /* diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 71a59296af8..79423358728 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -51,6 +51,8 @@ #include <asm/numa.h> #include <asm/cacheflush.h> #include <asm/init.h> +#include <asm/uv/uv.h> +#include <asm/setup.h> static int __init parse_direct_gbpages_off(char *arg) { @@ -105,18 +107,18 @@ void sync_global_pgds(unsigned long start, unsigned long end) for (address = start; address <= end; address += PGDIR_SIZE) { const pgd_t *pgd_ref = pgd_offset_k(address); - unsigned long flags; struct page *page; if (pgd_none(*pgd_ref)) continue; - spin_lock_irqsave(&pgd_lock, flags); + spin_lock(&pgd_lock); list_for_each_entry(page, &pgd_list, lru) { pgd_t *pgd; spinlock_t *pgt_lock; pgd = (pgd_t *)page_address(page) + pgd_index(address); + /* the pgt_lock only for Xen */ pgt_lock = &pgd_page_get_mm(page)->page_table_lock; spin_lock(pgt_lock); @@ -128,7 +130,7 @@ void sync_global_pgds(unsigned long start, unsigned long end) spin_unlock(pgt_lock); } - spin_unlock_irqrestore(&pgd_lock, flags); + spin_unlock(&pgd_lock); } } @@ -293,18 +295,18 @@ void __init init_extra_mapping_uc(unsigned long phys, unsigned long size) * to the compile time generated pmds. This results in invalid pmds up * to the point where we hit the physaddr 0 mapping. * - * We limit the mappings to the region from _text to _end. _end is - * rounded up to the 2MB boundary. This catches the invalid pmds as + * We limit the mappings to the region from _text to _brk_end. _brk_end + * is rounded up to the 2MB boundary. This catches the invalid pmds as * well, as they are located before _text: */ void __init cleanup_highmap(void) { unsigned long vaddr = __START_KERNEL_map; - unsigned long end = roundup((unsigned long)_end, PMD_SIZE) - 1; + unsigned long vaddr_end = __START_KERNEL_map + (max_pfn_mapped << PAGE_SHIFT); + unsigned long end = roundup((unsigned long)_brk_end, PMD_SIZE) - 1; pmd_t *pmd = level2_kernel_pgt; - pmd_t *last_pmd = pmd + PTRS_PER_PMD; - for (; pmd < last_pmd; pmd++, vaddr += PMD_SIZE) { + for (; vaddr + PMD_SIZE - 1 < vaddr_end; pmd++, vaddr += PMD_SIZE) { if (pmd_none(*pmd)) continue; if (vaddr < (unsigned long) _text || vaddr > end) @@ -314,7 +316,7 @@ void __init cleanup_highmap(void) static __ref void *alloc_low_page(unsigned long *phys) { - unsigned long pfn = e820_table_end++; + unsigned long pfn = pgt_buf_end++; void *adr; if (after_bootmem) { @@ -324,7 +326,7 @@ static __ref void *alloc_low_page(unsigned long *phys) return adr; } - if (pfn >= e820_table_top) + if (pfn >= pgt_buf_top) panic("alloc_low_page: ran out of memory"); adr = early_memremap(pfn * PAGE_SIZE, PAGE_SIZE); @@ -333,12 +335,28 @@ static __ref void *alloc_low_page(unsigned long *phys) return adr; } +static __ref void *map_low_page(void *virt) +{ + void *adr; + unsigned long phys, left; + + if (after_bootmem) + return virt; + + phys = __pa(virt); + left = phys & (PAGE_SIZE - 1); + adr = early_memremap(phys & PAGE_MASK, PAGE_SIZE); + adr = (void *)(((unsigned long)adr) | left); + + return adr; +} + static __ref void unmap_low_page(void *adr) { if (after_bootmem) return; - early_iounmap(adr, PAGE_SIZE); + early_iounmap((void *)((unsigned long)adr & PAGE_MASK), PAGE_SIZE); } static unsigned long __meminit @@ -386,15 +404,6 @@ phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end, } static unsigned long __meminit -phys_pte_update(pmd_t *pmd, unsigned long address, unsigned long end, - pgprot_t prot) -{ - pte_t *pte = (pte_t *)pmd_page_vaddr(*pmd); - - return phys_pte_init(pte, address, end, prot); -} - -static unsigned long __meminit phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end, unsigned long page_size_mask, pgprot_t prot) { @@ -420,8 +429,10 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end, if (pmd_val(*pmd)) { if (!pmd_large(*pmd)) { spin_lock(&init_mm.page_table_lock); - last_map_addr = phys_pte_update(pmd, address, + pte = map_low_page((pte_t *)pmd_page_vaddr(*pmd)); + last_map_addr = phys_pte_init(pte, address, end, prot); + unmap_low_page(pte); spin_unlock(&init_mm.page_table_lock); continue; } @@ -468,18 +479,6 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end, } static unsigned long __meminit -phys_pmd_update(pud_t *pud, unsigned long address, unsigned long end, - unsigned long page_size_mask, pgprot_t prot) -{ - pmd_t *pmd = pmd_offset(pud, 0); - unsigned long last_map_addr; - - last_map_addr = phys_pmd_init(pmd, address, end, page_size_mask, prot); - __flush_tlb_all(); - return last_map_addr; -} - -static unsigned long __meminit phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end, unsigned long page_size_mask) { @@ -504,8 +503,11 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end, if (pud_val(*pud)) { if (!pud_large(*pud)) { - last_map_addr = phys_pmd_update(pud, addr, end, + pmd = map_low_page(pmd_offset(pud, 0)); + last_map_addr = phys_pmd_init(pmd, addr, end, page_size_mask, prot); + unmap_low_page(pmd); + __flush_tlb_all(); continue; } /* @@ -553,17 +555,6 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end, return last_map_addr; } -static unsigned long __meminit -phys_pud_update(pgd_t *pgd, unsigned long addr, unsigned long end, - unsigned long page_size_mask) -{ - pud_t *pud; - - pud = (pud_t *)pgd_page_vaddr(*pgd); - - return phys_pud_init(pud, addr, end, page_size_mask); -} - unsigned long __meminit kernel_physical_mapping_init(unsigned long start, unsigned long end, @@ -587,8 +578,10 @@ kernel_physical_mapping_init(unsigned long start, next = end; if (pgd_val(*pgd)) { - last_map_addr = phys_pud_update(pgd, __pa(start), + pud = map_low_page((pud_t *)pgd_page_vaddr(*pgd)); + last_map_addr = phys_pud_init(pud, __pa(start), __pa(end), page_size_mask); + unmap_low_page(pud); continue; } @@ -612,10 +605,9 @@ kernel_physical_mapping_init(unsigned long start, } #ifndef CONFIG_NUMA -void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn, - int acpi, int k8) +void __init initmem_init(void) { - memblock_x86_register_active_regions(0, start_pfn, end_pfn); + memblock_x86_register_active_regions(0, 0, max_pfn); } #endif @@ -870,18 +862,18 @@ static struct vm_area_struct gate_vma = { .vm_flags = VM_READ | VM_EXEC }; -struct vm_area_struct *get_gate_vma(struct task_struct *tsk) +struct vm_area_struct *get_gate_vma(struct mm_struct *mm) { #ifdef CONFIG_IA32_EMULATION - if (test_tsk_thread_flag(tsk, TIF_IA32)) + if (!mm || mm->context.ia32_compat) return NULL; #endif return &gate_vma; } -int in_gate_area(struct task_struct *task, unsigned long addr) +int in_gate_area(struct mm_struct *mm, unsigned long addr) { - struct vm_area_struct *vma = get_gate_vma(task); + struct vm_area_struct *vma = get_gate_vma(mm); if (!vma) return 0; @@ -890,11 +882,11 @@ int in_gate_area(struct task_struct *task, unsigned long addr) } /* - * Use this when you have no reliable task/vma, typically from interrupt - * context. It is less reliable than using the task's vma and may give - * false positives: + * Use this when you have no reliable mm, typically from interrupt + * context. It is less reliable than using a task's mm and may give + * false positives. */ -int in_gate_area_no_task(unsigned long addr) +int in_gate_area_no_mm(unsigned long addr) { return (addr >= VSYSCALL_START) && (addr < VSYSCALL_END); } @@ -908,6 +900,19 @@ const char *arch_vma_name(struct vm_area_struct *vma) return NULL; } +#ifdef CONFIG_X86_UV +#define MIN_MEMORY_BLOCK_SIZE (1 << SECTION_SIZE_BITS) + +unsigned long memory_block_size_bytes(void) +{ + if (is_uv_system()) { + printk(KERN_INFO "UV: memory block size 2GB\n"); + return 2UL * 1024 * 1024 * 1024; + } + return MIN_MEMORY_BLOCK_SIZE; +} +#endif + #ifdef CONFIG_SPARSEMEM_VMEMMAP /* * Initialise the sparsemem vmemmap using huge-pages at the PMD level. diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index ebf6d7887a3..745258dfc4d 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -26,12 +26,50 @@ static __init int numa_setup(char *opt) early_param("numa", numa_setup); /* - * Which logical CPUs are on which nodes + * apicid, cpu, node mappings */ +s16 __apicid_to_node[MAX_LOCAL_APIC] __cpuinitdata = { + [0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE +}; + cpumask_var_t node_to_cpumask_map[MAX_NUMNODES]; EXPORT_SYMBOL(node_to_cpumask_map); /* + * Map cpu index to node index + */ +DEFINE_EARLY_PER_CPU(int, x86_cpu_to_node_map, NUMA_NO_NODE); +EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_node_map); + +void __cpuinit numa_set_node(int cpu, int node) +{ + int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map); + + /* early setting, no percpu area yet */ + if (cpu_to_node_map) { + cpu_to_node_map[cpu] = node; + return; + } + +#ifdef CONFIG_DEBUG_PER_CPU_MAPS + if (cpu >= nr_cpu_ids || !cpu_possible(cpu)) { + printk(KERN_ERR "numa_set_node: invalid cpu# (%d)\n", cpu); + dump_stack(); + return; + } +#endif + per_cpu(x86_cpu_to_node_map, cpu) = node; + + if (node != NUMA_NO_NODE) + set_cpu_numa_node(cpu, node); +} + +void __cpuinit numa_clear_node(int cpu) +{ + numa_set_node(cpu, NUMA_NO_NODE); +} + +/* * Allocate node_to_cpumask_map based on number of available nodes * Requires node_possible_map to be valid. * @@ -57,7 +95,169 @@ void __init setup_node_to_cpumask_map(void) pr_debug("Node to cpumask map for %d nodes\n", nr_node_ids); } -#ifdef CONFIG_DEBUG_PER_CPU_MAPS +/* + * There are unfortunately some poorly designed mainboards around that + * only connect memory to a single CPU. This breaks the 1:1 cpu->node + * mapping. To avoid this fill in the mapping for all possible CPUs, + * as the number of CPUs is not known yet. We round robin the existing + * nodes. + */ +void __init numa_init_array(void) +{ + int rr, i; + + rr = first_node(node_online_map); + for (i = 0; i < nr_cpu_ids; i++) { + if (early_cpu_to_node(i) != NUMA_NO_NODE) + continue; + numa_set_node(i, rr); + rr = next_node(rr, node_online_map); + if (rr == MAX_NUMNODES) + rr = first_node(node_online_map); + } +} + +static __init int find_near_online_node(int node) +{ + int n, val; + int min_val = INT_MAX; + int best_node = -1; + + for_each_online_node(n) { + val = node_distance(node, n); + + if (val < min_val) { + min_val = val; + best_node = n; + } + } + + return best_node; +} + +/* + * Setup early cpu_to_node. + * + * Populate cpu_to_node[] only if x86_cpu_to_apicid[], + * and apicid_to_node[] tables have valid entries for a CPU. + * This means we skip cpu_to_node[] initialisation for NUMA + * emulation and faking node case (when running a kernel compiled + * for NUMA on a non NUMA box), which is OK as cpu_to_node[] + * is already initialized in a round robin manner at numa_init_array, + * prior to this call, and this initialization is good enough + * for the fake NUMA cases. + * + * Called before the per_cpu areas are setup. + */ +void __init init_cpu_to_node(void) +{ + int cpu; + u16 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid); + + BUG_ON(cpu_to_apicid == NULL); + + for_each_possible_cpu(cpu) { + int node = numa_cpu_node(cpu); + + if (node == NUMA_NO_NODE) + continue; + if (!node_online(node)) + node = find_near_online_node(node); + numa_set_node(cpu, node); + } +} + +#ifndef CONFIG_DEBUG_PER_CPU_MAPS + +# ifndef CONFIG_NUMA_EMU +void __cpuinit numa_add_cpu(int cpu) +{ + cpumask_set_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]); +} + +void __cpuinit numa_remove_cpu(int cpu) +{ + cpumask_clear_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]); +} +# endif /* !CONFIG_NUMA_EMU */ + +#else /* !CONFIG_DEBUG_PER_CPU_MAPS */ + +int __cpu_to_node(int cpu) +{ + if (early_per_cpu_ptr(x86_cpu_to_node_map)) { + printk(KERN_WARNING + "cpu_to_node(%d): usage too early!\n", cpu); + dump_stack(); + return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu]; + } + return per_cpu(x86_cpu_to_node_map, cpu); +} +EXPORT_SYMBOL(__cpu_to_node); + +/* + * Same function as cpu_to_node() but used if called before the + * per_cpu areas are setup. + */ +int early_cpu_to_node(int cpu) +{ + if (early_per_cpu_ptr(x86_cpu_to_node_map)) + return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu]; + + if (!cpu_possible(cpu)) { + printk(KERN_WARNING + "early_cpu_to_node(%d): no per_cpu area!\n", cpu); + dump_stack(); + return NUMA_NO_NODE; + } + return per_cpu(x86_cpu_to_node_map, cpu); +} + +void debug_cpumask_set_cpu(int cpu, int node, bool enable) +{ + struct cpumask *mask; + char buf[64]; + + if (node == NUMA_NO_NODE) { + /* early_cpu_to_node() already emits a warning and trace */ + return; + } + mask = node_to_cpumask_map[node]; + if (!mask) { + pr_err("node_to_cpumask_map[%i] NULL\n", node); + dump_stack(); + return; + } + + if (enable) + cpumask_set_cpu(cpu, mask); + else + cpumask_clear_cpu(cpu, mask); + + cpulist_scnprintf(buf, sizeof(buf), mask); + printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n", + enable ? "numa_add_cpu" : "numa_remove_cpu", + cpu, node, buf); + return; +} + +# ifndef CONFIG_NUMA_EMU +static void __cpuinit numa_set_cpumask(int cpu, bool enable) +{ + debug_cpumask_set_cpu(cpu, early_cpu_to_node(cpu), enable); +} + +void __cpuinit numa_add_cpu(int cpu) +{ + numa_set_cpumask(cpu, true); +} + +void __cpuinit numa_remove_cpu(int cpu) +{ + numa_set_cpumask(cpu, false); +} +# endif /* !CONFIG_NUMA_EMU */ + /* * Returns a pointer to the bitmask of CPUs on Node 'node'. */ @@ -80,4 +280,5 @@ const struct cpumask *cpumask_of_node(int node) return node_to_cpumask_map[node]; } EXPORT_SYMBOL(cpumask_of_node); -#endif + +#endif /* !CONFIG_DEBUG_PER_CPU_MAPS */ diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c index 84a3e4c9f27..bde3906420d 100644 --- a/arch/x86/mm/numa_32.c +++ b/arch/x86/mm/numa_32.c @@ -110,6 +110,12 @@ void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags); static unsigned long kva_start_pfn; static unsigned long kva_pages; + +int __cpuinit numa_cpu_node(int cpu) +{ + return apic->x86_32_numa_cpu_node(cpu); +} + /* * FLAT - support for basic PC memory model with discontig enabled, essentially * a single node with all available processors in it with a flat @@ -346,8 +352,7 @@ static void init_remap_allocator(int nid) (ulong) node_remap_end_vaddr[nid]); } -void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn, - int acpi, int k8) +void __init initmem_init(void) { int nid; long kva_target_pfn; @@ -361,6 +366,7 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn, */ get_memcfg_numa(); + numa_init_array(); kva_pages = roundup(calculate_numa_remap_pages(), PTRS_PER_PTE); diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c index 95ea1551eeb..85b52fc0308 100644 --- a/arch/x86/mm/numa_64.c +++ b/arch/x86/mm/numa_64.c @@ -13,31 +13,30 @@ #include <linux/module.h> #include <linux/nodemask.h> #include <linux/sched.h> +#include <linux/acpi.h> #include <asm/e820.h> #include <asm/proto.h> #include <asm/dma.h> -#include <asm/numa.h> #include <asm/acpi.h> #include <asm/amd_nb.h> +#include "numa_internal.h" + struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; EXPORT_SYMBOL(node_data); -struct memnode memnode; +nodemask_t numa_nodes_parsed __initdata; -s16 apicid_to_node[MAX_LOCAL_APIC] __cpuinitdata = { - [0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE -}; +struct memnode memnode; static unsigned long __initdata nodemap_addr; static unsigned long __initdata nodemap_size; -/* - * Map cpu index to node index - */ -DEFINE_EARLY_PER_CPU(int, x86_cpu_to_node_map, NUMA_NO_NODE); -EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_node_map); +static struct numa_meminfo numa_meminfo __initdata; + +static int numa_distance_cnt; +static u8 *numa_distance; /* * Given a shift value, try to populate memnodemap[] @@ -46,16 +45,15 @@ EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_node_map); * 0 if memnodmap[] too small (of shift too small) * -1 if node overlap or lost ram (shift too big) */ -static int __init populate_memnodemap(const struct bootnode *nodes, - int numnodes, int shift, int *nodeids) +static int __init populate_memnodemap(const struct numa_meminfo *mi, int shift) { unsigned long addr, end; int i, res = -1; memset(memnodemap, 0xff, sizeof(s16)*memnodemapsize); - for (i = 0; i < numnodes; i++) { - addr = nodes[i].start; - end = nodes[i].end; + for (i = 0; i < mi->nr_blks; i++) { + addr = mi->blk[i].start; + end = mi->blk[i].end; if (addr >= end) continue; if ((end >> shift) >= memnodemapsize) @@ -63,12 +61,7 @@ static int __init populate_memnodemap(const struct bootnode *nodes, do { if (memnodemap[addr >> shift] != NUMA_NO_NODE) return -1; - - if (!nodeids) - memnodemap[addr >> shift] = i; - else - memnodemap[addr >> shift] = nodeids[i]; - + memnodemap[addr >> shift] = mi->blk[i].nid; addr += (1UL << shift); } while (addr < end); res = 1; @@ -86,7 +79,7 @@ static int __init allocate_cachealigned_memnodemap(void) addr = 0x8000; nodemap_size = roundup(sizeof(s16) * memnodemapsize, L1_CACHE_BYTES); - nodemap_addr = memblock_find_in_range(addr, max_pfn<<PAGE_SHIFT, + nodemap_addr = memblock_find_in_range(addr, get_max_mapped(), nodemap_size, L1_CACHE_BYTES); if (nodemap_addr == MEMBLOCK_ERROR) { printk(KERN_ERR @@ -106,16 +99,15 @@ static int __init allocate_cachealigned_memnodemap(void) * The LSB of all start and end addresses in the node map is the value of the * maximum possible shift. */ -static int __init extract_lsb_from_nodes(const struct bootnode *nodes, - int numnodes) +static int __init extract_lsb_from_nodes(const struct numa_meminfo *mi) { int i, nodes_used = 0; unsigned long start, end; unsigned long bitfield = 0, memtop = 0; - for (i = 0; i < numnodes; i++) { - start = nodes[i].start; - end = nodes[i].end; + for (i = 0; i < mi->nr_blks; i++) { + start = mi->blk[i].start; + end = mi->blk[i].end; if (start >= end) continue; bitfield |= start; @@ -131,18 +123,17 @@ static int __init extract_lsb_from_nodes(const struct bootnode *nodes, return i; } -int __init compute_hash_shift(struct bootnode *nodes, int numnodes, - int *nodeids) +static int __init compute_hash_shift(const struct numa_meminfo *mi) { int shift; - shift = extract_lsb_from_nodes(nodes, numnodes); + shift = extract_lsb_from_nodes(mi); if (allocate_cachealigned_memnodemap()) return -1; printk(KERN_DEBUG "NUMA: Using %d for the hash shift.\n", shift); - if (populate_memnodemap(nodes, numnodes, shift, nodeids) != 1) { + if (populate_memnodemap(mi, shift) != 1) { printk(KERN_INFO "Your memory is not aligned you need to " "rebuild your kernel with a bigger NODEMAPSIZE " "shift=%d\n", shift); @@ -188,6 +179,63 @@ static void * __init early_node_mem(int nodeid, unsigned long start, return NULL; } +static int __init numa_add_memblk_to(int nid, u64 start, u64 end, + struct numa_meminfo *mi) +{ + /* ignore zero length blks */ + if (start == end) + return 0; + + /* whine about and ignore invalid blks */ + if (start > end || nid < 0 || nid >= MAX_NUMNODES) { + pr_warning("NUMA: Warning: invalid memblk node %d (%Lx-%Lx)\n", + nid, start, end); + return 0; + } + + if (mi->nr_blks >= NR_NODE_MEMBLKS) { + pr_err("NUMA: too many memblk ranges\n"); + return -EINVAL; + } + + mi->blk[mi->nr_blks].start = start; + mi->blk[mi->nr_blks].end = end; + mi->blk[mi->nr_blks].nid = nid; + mi->nr_blks++; + return 0; +} + +/** + * numa_remove_memblk_from - Remove one numa_memblk from a numa_meminfo + * @idx: Index of memblk to remove + * @mi: numa_meminfo to remove memblk from + * + * Remove @idx'th numa_memblk from @mi by shifting @mi->blk[] and + * decrementing @mi->nr_blks. + */ +void __init numa_remove_memblk_from(int idx, struct numa_meminfo *mi) +{ + mi->nr_blks--; + memmove(&mi->blk[idx], &mi->blk[idx + 1], + (mi->nr_blks - idx) * sizeof(mi->blk[0])); +} + +/** + * numa_add_memblk - Add one numa_memblk to numa_meminfo + * @nid: NUMA node ID of the new memblk + * @start: Start address of the new memblk + * @end: End address of the new memblk + * + * Add a new memblk to the default numa_meminfo. + * + * RETURNS: + * 0 on success, -errno on failure. + */ +int __init numa_add_memblk(int nid, u64 start, u64 end) +{ + return numa_add_memblk_to(nid, start, end, &numa_meminfo); +} + /* Initialize bootmem allocator for a node */ void __init setup_node_bootmem(int nodeid, unsigned long start, unsigned long end) @@ -234,696 +282,386 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end) node_set_online(nodeid); } -/* - * There are unfortunately some poorly designed mainboards around that - * only connect memory to a single CPU. This breaks the 1:1 cpu->node - * mapping. To avoid this fill in the mapping for all possible CPUs, - * as the number of CPUs is not known yet. We round robin the existing - * nodes. +/** + * numa_cleanup_meminfo - Cleanup a numa_meminfo + * @mi: numa_meminfo to clean up + * + * Sanitize @mi by merging and removing unncessary memblks. Also check for + * conflicts and clear unused memblks. + * + * RETURNS: + * 0 on success, -errno on failure. */ -void __init numa_init_array(void) +int __init numa_cleanup_meminfo(struct numa_meminfo *mi) { - int rr, i; + const u64 low = 0; + const u64 high = (u64)max_pfn << PAGE_SHIFT; + int i, j, k; - rr = first_node(node_online_map); - for (i = 0; i < nr_cpu_ids; i++) { - if (early_cpu_to_node(i) != NUMA_NO_NODE) - continue; - numa_set_node(i, rr); - rr = next_node(rr, node_online_map); - if (rr == MAX_NUMNODES) - rr = first_node(node_online_map); - } -} - -#ifdef CONFIG_NUMA_EMU -/* Numa emulation */ -static struct bootnode nodes[MAX_NUMNODES] __initdata; -static struct bootnode physnodes[MAX_NUMNODES] __cpuinitdata; -static char *cmdline __initdata; + for (i = 0; i < mi->nr_blks; i++) { + struct numa_memblk *bi = &mi->blk[i]; -void __init numa_emu_cmdline(char *str) -{ - cmdline = str; -} + /* make sure all blocks are inside the limits */ + bi->start = max(bi->start, low); + bi->end = min(bi->end, high); -static int __init setup_physnodes(unsigned long start, unsigned long end, - int acpi, int amd) -{ - int ret = 0; - int i; - - memset(physnodes, 0, sizeof(physnodes)); -#ifdef CONFIG_ACPI_NUMA - if (acpi) - acpi_get_nodes(physnodes, start, end); -#endif -#ifdef CONFIG_AMD_NUMA - if (amd) - amd_get_nodes(physnodes); -#endif - /* - * Basic sanity checking on the physical node map: there may be errors - * if the SRAT or AMD code incorrectly reported the topology or the mem= - * kernel parameter is used. - */ - for (i = 0; i < MAX_NUMNODES; i++) { - if (physnodes[i].start == physnodes[i].end) - continue; - if (physnodes[i].start > end) { - physnodes[i].end = physnodes[i].start; - continue; - } - if (physnodes[i].end < start) { - physnodes[i].start = physnodes[i].end; + /* and there's no empty block */ + if (bi->start >= bi->end) { + numa_remove_memblk_from(i--, mi); continue; } - if (physnodes[i].start < start) - physnodes[i].start = start; - if (physnodes[i].end > end) - physnodes[i].end = end; - ret++; - } - - /* - * If no physical topology was detected, a single node is faked to cover - * the entire address space. - */ - if (!ret) { - physnodes[ret].start = start; - physnodes[ret].end = end; - ret = 1; - } - return ret; -} - -static void __init fake_physnodes(int acpi, int amd, int nr_nodes) -{ - int i; - - BUG_ON(acpi && amd); -#ifdef CONFIG_ACPI_NUMA - if (acpi) - acpi_fake_nodes(nodes, nr_nodes); -#endif -#ifdef CONFIG_AMD_NUMA - if (amd) - amd_fake_nodes(nodes, nr_nodes); -#endif - if (!acpi && !amd) - for (i = 0; i < nr_cpu_ids; i++) - numa_set_node(i, 0); -} - -/* - * Setups up nid to range from addr to addr + size. If the end - * boundary is greater than max_addr, then max_addr is used instead. - * The return value is 0 if there is additional memory left for - * allocation past addr and -1 otherwise. addr is adjusted to be at - * the end of the node. - */ -static int __init setup_node_range(int nid, u64 *addr, u64 size, u64 max_addr) -{ - int ret = 0; - nodes[nid].start = *addr; - *addr += size; - if (*addr >= max_addr) { - *addr = max_addr; - ret = -1; - } - nodes[nid].end = *addr; - node_set(nid, node_possible_map); - printk(KERN_INFO "Faking node %d at %016Lx-%016Lx (%LuMB)\n", nid, - nodes[nid].start, nodes[nid].end, - (nodes[nid].end - nodes[nid].start) >> 20); - return ret; -} - -/* - * Sets up nr_nodes fake nodes interleaved over physical nodes ranging from addr - * to max_addr. The return value is the number of nodes allocated. - */ -static int __init split_nodes_interleave(u64 addr, u64 max_addr, int nr_nodes) -{ - nodemask_t physnode_mask = NODE_MASK_NONE; - u64 size; - int big; - int ret = 0; - int i; - - if (nr_nodes <= 0) - return -1; - if (nr_nodes > MAX_NUMNODES) { - pr_info("numa=fake=%d too large, reducing to %d\n", - nr_nodes, MAX_NUMNODES); - nr_nodes = MAX_NUMNODES; - } - - size = (max_addr - addr - memblock_x86_hole_size(addr, max_addr)) / nr_nodes; - /* - * Calculate the number of big nodes that can be allocated as a result - * of consolidating the remainder. - */ - big = ((size & ~FAKE_NODE_MIN_HASH_MASK) * nr_nodes) / - FAKE_NODE_MIN_SIZE; - - size &= FAKE_NODE_MIN_HASH_MASK; - if (!size) { - pr_err("Not enough memory for each node. " - "NUMA emulation disabled.\n"); - return -1; - } - for (i = 0; i < MAX_NUMNODES; i++) - if (physnodes[i].start != physnodes[i].end) - node_set(i, physnode_mask); - - /* - * Continue to fill physical nodes with fake nodes until there is no - * memory left on any of them. - */ - while (nodes_weight(physnode_mask)) { - for_each_node_mask(i, physnode_mask) { - u64 end = physnodes[i].start + size; - u64 dma32_end = PFN_PHYS(MAX_DMA32_PFN); - - if (ret < big) - end += FAKE_NODE_MIN_SIZE; + for (j = i + 1; j < mi->nr_blks; j++) { + struct numa_memblk *bj = &mi->blk[j]; + unsigned long start, end; /* - * Continue to add memory to this fake node if its - * non-reserved memory is less than the per-node size. + * See whether there are overlapping blocks. Whine + * about but allow overlaps of the same nid. They + * will be merged below. */ - while (end - physnodes[i].start - - memblock_x86_hole_size(physnodes[i].start, end) < size) { - end += FAKE_NODE_MIN_SIZE; - if (end > physnodes[i].end) { - end = physnodes[i].end; - break; + if (bi->end > bj->start && bi->start < bj->end) { + if (bi->nid != bj->nid) { + pr_err("NUMA: node %d (%Lx-%Lx) overlaps with node %d (%Lx-%Lx)\n", + bi->nid, bi->start, bi->end, + bj->nid, bj->start, bj->end); + return -EINVAL; } + pr_warning("NUMA: Warning: node %d (%Lx-%Lx) overlaps with itself (%Lx-%Lx)\n", + bi->nid, bi->start, bi->end, + bj->start, bj->end); } /* - * If there won't be at least FAKE_NODE_MIN_SIZE of - * non-reserved memory in ZONE_DMA32 for the next node, - * this one must extend to the boundary. + * Join together blocks on the same node, holes + * between which don't overlap with memory on other + * nodes. */ - if (end < dma32_end && dma32_end - end - - memblock_x86_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE) - end = dma32_end; - - /* - * If there won't be enough non-reserved memory for the - * next node, this one must extend to the end of the - * physical node. - */ - if (physnodes[i].end - end - - memblock_x86_hole_size(end, physnodes[i].end) < size) - end = physnodes[i].end; - - /* - * Avoid allocating more nodes than requested, which can - * happen as a result of rounding down each node's size - * to FAKE_NODE_MIN_SIZE. - */ - if (nodes_weight(physnode_mask) + ret >= nr_nodes) - end = physnodes[i].end; - - if (setup_node_range(ret++, &physnodes[i].start, - end - physnodes[i].start, - physnodes[i].end) < 0) - node_clear(i, physnode_mask); + if (bi->nid != bj->nid) + continue; + start = max(min(bi->start, bj->start), low); + end = min(max(bi->end, bj->end), high); + for (k = 0; k < mi->nr_blks; k++) { + struct numa_memblk *bk = &mi->blk[k]; + + if (bi->nid == bk->nid) + continue; + if (start < bk->end && end > bk->start) + break; + } + if (k < mi->nr_blks) + continue; + printk(KERN_INFO "NUMA: Node %d [%Lx,%Lx) + [%Lx,%Lx) -> [%lx,%lx)\n", + bi->nid, bi->start, bi->end, bj->start, bj->end, + start, end); + bi->start = start; + bi->end = end; + numa_remove_memblk_from(j--, mi); } } - return ret; -} -/* - * Returns the end address of a node so that there is at least `size' amount of - * non-reserved memory or `max_addr' is reached. - */ -static u64 __init find_end_of_node(u64 start, u64 max_addr, u64 size) -{ - u64 end = start + size; - - while (end - start - memblock_x86_hole_size(start, end) < size) { - end += FAKE_NODE_MIN_SIZE; - if (end > max_addr) { - end = max_addr; - break; - } + for (i = mi->nr_blks; i < ARRAY_SIZE(mi->blk); i++) { + mi->blk[i].start = mi->blk[i].end = 0; + mi->blk[i].nid = NUMA_NO_NODE; } - return end; + + return 0; } /* - * Sets up fake nodes of `size' interleaved over physical nodes ranging from - * `addr' to `max_addr'. The return value is the number of nodes allocated. + * Set nodes, which have memory in @mi, in *@nodemask. */ -static int __init split_nodes_size_interleave(u64 addr, u64 max_addr, u64 size) +static void __init numa_nodemask_from_meminfo(nodemask_t *nodemask, + const struct numa_meminfo *mi) { - nodemask_t physnode_mask = NODE_MASK_NONE; - u64 min_size; - int ret = 0; int i; - if (!size) - return -1; - /* - * The limit on emulated nodes is MAX_NUMNODES, so the size per node is - * increased accordingly if the requested size is too small. This - * creates a uniform distribution of node sizes across the entire - * machine (but not necessarily over physical nodes). - */ - min_size = (max_addr - addr - memblock_x86_hole_size(addr, max_addr)) / - MAX_NUMNODES; - min_size = max(min_size, FAKE_NODE_MIN_SIZE); - if ((min_size & FAKE_NODE_MIN_HASH_MASK) < min_size) - min_size = (min_size + FAKE_NODE_MIN_SIZE) & - FAKE_NODE_MIN_HASH_MASK; - if (size < min_size) { - pr_err("Fake node size %LuMB too small, increasing to %LuMB\n", - size >> 20, min_size >> 20); - size = min_size; - } - size &= FAKE_NODE_MIN_HASH_MASK; - - for (i = 0; i < MAX_NUMNODES; i++) - if (physnodes[i].start != physnodes[i].end) - node_set(i, physnode_mask); - /* - * Fill physical nodes with fake nodes of size until there is no memory - * left on any of them. - */ - while (nodes_weight(physnode_mask)) { - for_each_node_mask(i, physnode_mask) { - u64 dma32_end = MAX_DMA32_PFN << PAGE_SHIFT; - u64 end; - - end = find_end_of_node(physnodes[i].start, - physnodes[i].end, size); - /* - * If there won't be at least FAKE_NODE_MIN_SIZE of - * non-reserved memory in ZONE_DMA32 for the next node, - * this one must extend to the boundary. - */ - if (end < dma32_end && dma32_end - end - - memblock_x86_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE) - end = dma32_end; + for (i = 0; i < ARRAY_SIZE(mi->blk); i++) + if (mi->blk[i].start != mi->blk[i].end && + mi->blk[i].nid != NUMA_NO_NODE) + node_set(mi->blk[i].nid, *nodemask); +} - /* - * If there won't be enough non-reserved memory for the - * next node, this one must extend to the end of the - * physical node. - */ - if (physnodes[i].end - end - - memblock_x86_hole_size(end, physnodes[i].end) < size) - end = physnodes[i].end; +/** + * numa_reset_distance - Reset NUMA distance table + * + * The current table is freed. The next numa_set_distance() call will + * create a new one. + */ +void __init numa_reset_distance(void) +{ + size_t size = numa_distance_cnt * numa_distance_cnt * sizeof(numa_distance[0]); - /* - * Setup the fake node that will be allocated as bootmem - * later. If setup_node_range() returns non-zero, there - * is no more memory available on this physical node. - */ - if (setup_node_range(ret++, &physnodes[i].start, - end - physnodes[i].start, - physnodes[i].end) < 0) - node_clear(i, physnode_mask); - } - } - return ret; + /* numa_distance could be 1LU marking allocation failure, test cnt */ + if (numa_distance_cnt) + memblock_x86_free_range(__pa(numa_distance), + __pa(numa_distance) + size); + numa_distance_cnt = 0; + numa_distance = NULL; /* enable table creation */ } -/* - * Sets up the system RAM area from start_pfn to last_pfn according to the - * numa=fake command-line option. - */ -static int __init numa_emulation(unsigned long start_pfn, - unsigned long last_pfn, int acpi, int amd) +static int __init numa_alloc_distance(void) { - u64 addr = start_pfn << PAGE_SHIFT; - u64 max_addr = last_pfn << PAGE_SHIFT; - int num_nodes; - int i; + nodemask_t nodes_parsed; + size_t size; + int i, j, cnt = 0; + u64 phys; - /* - * If the numa=fake command-line contains a 'M' or 'G', it represents - * the fixed node size. Otherwise, if it is just a single number N, - * split the system RAM into N fake nodes. - */ - if (strchr(cmdline, 'M') || strchr(cmdline, 'G')) { - u64 size; + /* size the new table and allocate it */ + nodes_parsed = numa_nodes_parsed; + numa_nodemask_from_meminfo(&nodes_parsed, &numa_meminfo); - size = memparse(cmdline, &cmdline); - num_nodes = split_nodes_size_interleave(addr, max_addr, size); - } else { - unsigned long n; + for_each_node_mask(i, nodes_parsed) + cnt = i; + cnt++; + size = cnt * cnt * sizeof(numa_distance[0]); - n = simple_strtoul(cmdline, NULL, 0); - num_nodes = split_nodes_interleave(addr, max_addr, n); + phys = memblock_find_in_range(0, (u64)max_pfn_mapped << PAGE_SHIFT, + size, PAGE_SIZE); + if (phys == MEMBLOCK_ERROR) { + pr_warning("NUMA: Warning: can't allocate distance table!\n"); + /* don't retry until explicitly reset */ + numa_distance = (void *)1LU; + return -ENOMEM; } + memblock_x86_reserve_range(phys, phys + size, "NUMA DIST"); - if (num_nodes < 0) - return num_nodes; - memnode_shift = compute_hash_shift(nodes, num_nodes, NULL); - if (memnode_shift < 0) { - memnode_shift = 0; - printk(KERN_ERR "No NUMA hash function found. NUMA emulation " - "disabled.\n"); - return -1; - } + numa_distance = __va(phys); + numa_distance_cnt = cnt; + + /* fill with the default distances */ + for (i = 0; i < cnt; i++) + for (j = 0; j < cnt; j++) + numa_distance[i * cnt + j] = i == j ? + LOCAL_DISTANCE : REMOTE_DISTANCE; + printk(KERN_DEBUG "NUMA: Initialized distance table, cnt=%d\n", cnt); - /* - * We need to vacate all active ranges that may have been registered for - * the e820 memory map. - */ - remove_all_active_ranges(); - for_each_node_mask(i, node_possible_map) { - memblock_x86_register_active_regions(i, nodes[i].start >> PAGE_SHIFT, - nodes[i].end >> PAGE_SHIFT); - setup_node_bootmem(i, nodes[i].start, nodes[i].end); - } - setup_physnodes(addr, max_addr, acpi, amd); - fake_physnodes(acpi, amd, num_nodes); - numa_init_array(); return 0; } -#endif /* CONFIG_NUMA_EMU */ -void __init initmem_init(unsigned long start_pfn, unsigned long last_pfn, - int acpi, int amd) +/** + * numa_set_distance - Set NUMA distance from one NUMA to another + * @from: the 'from' node to set distance + * @to: the 'to' node to set distance + * @distance: NUMA distance + * + * Set the distance from node @from to @to to @distance. If distance table + * doesn't exist, one which is large enough to accommodate all the currently + * known nodes will be created. + * + * If such table cannot be allocated, a warning is printed and further + * calls are ignored until the distance table is reset with + * numa_reset_distance(). + * + * If @from or @to is higher than the highest known node at the time of + * table creation or @distance doesn't make sense, the call is ignored. + * This is to allow simplification of specific NUMA config implementations. + */ +void __init numa_set_distance(int from, int to, int distance) { - int i; - - nodes_clear(node_possible_map); - nodes_clear(node_online_map); - -#ifdef CONFIG_NUMA_EMU - setup_physnodes(start_pfn << PAGE_SHIFT, last_pfn << PAGE_SHIFT, - acpi, amd); - if (cmdline && !numa_emulation(start_pfn, last_pfn, acpi, amd)) + if (!numa_distance && numa_alloc_distance() < 0) return; - setup_physnodes(start_pfn << PAGE_SHIFT, last_pfn << PAGE_SHIFT, - acpi, amd); - nodes_clear(node_possible_map); - nodes_clear(node_online_map); -#endif -#ifdef CONFIG_ACPI_NUMA - if (!numa_off && acpi && !acpi_scan_nodes(start_pfn << PAGE_SHIFT, - last_pfn << PAGE_SHIFT)) + if (from >= numa_distance_cnt || to >= numa_distance_cnt) { + printk_once(KERN_DEBUG "NUMA: Debug: distance out of bound, from=%d to=%d distance=%d\n", + from, to, distance); return; - nodes_clear(node_possible_map); - nodes_clear(node_online_map); -#endif + } -#ifdef CONFIG_AMD_NUMA - if (!numa_off && amd && !amd_scan_nodes()) + if ((u8)distance != distance || + (from == to && distance != LOCAL_DISTANCE)) { + pr_warn_once("NUMA: Warning: invalid distance parameter, from=%d to=%d distance=%d\n", + from, to, distance); return; - nodes_clear(node_possible_map); - nodes_clear(node_online_map); -#endif - printk(KERN_INFO "%s\n", - numa_off ? "NUMA turned off" : "No NUMA configuration found"); + } - printk(KERN_INFO "Faking a node at %016lx-%016lx\n", - start_pfn << PAGE_SHIFT, - last_pfn << PAGE_SHIFT); - /* setup dummy node covering all memory */ - memnode_shift = 63; - memnodemap = memnode.embedded_map; - memnodemap[0] = 0; - node_set_online(0); - node_set(0, node_possible_map); - for (i = 0; i < nr_cpu_ids; i++) - numa_set_node(i, 0); - memblock_x86_register_active_regions(0, start_pfn, last_pfn); - setup_node_bootmem(0, start_pfn << PAGE_SHIFT, last_pfn << PAGE_SHIFT); + numa_distance[from * numa_distance_cnt + to] = distance; } -unsigned long __init numa_free_all_bootmem(void) +int __node_distance(int from, int to) { - unsigned long pages = 0; - int i; + if (from >= numa_distance_cnt || to >= numa_distance_cnt) + return from == to ? LOCAL_DISTANCE : REMOTE_DISTANCE; + return numa_distance[from * numa_distance_cnt + to]; +} +EXPORT_SYMBOL(__node_distance); - for_each_online_node(i) - pages += free_all_bootmem_node(NODE_DATA(i)); +/* + * Sanity check to catch more bad NUMA configurations (they are amazingly + * common). Make sure the nodes cover all memory. + */ +static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi) +{ + unsigned long numaram, e820ram; + int i; - pages += free_all_memory_core_early(MAX_NUMNODES); + numaram = 0; + for (i = 0; i < mi->nr_blks; i++) { + unsigned long s = mi->blk[i].start >> PAGE_SHIFT; + unsigned long e = mi->blk[i].end >> PAGE_SHIFT; + numaram += e - s; + numaram -= __absent_pages_in_range(mi->blk[i].nid, s, e); + if ((long)numaram < 0) + numaram = 0; + } - return pages; + e820ram = max_pfn - (memblock_x86_hole_size(0, + max_pfn << PAGE_SHIFT) >> PAGE_SHIFT); + /* We seem to lose 3 pages somewhere. Allow 1M of slack. */ + if ((long)(e820ram - numaram) >= (1 << (20 - PAGE_SHIFT))) { + printk(KERN_ERR "NUMA: nodes only cover %luMB of your %luMB e820 RAM. Not used.\n", + (numaram << PAGE_SHIFT) >> 20, + (e820ram << PAGE_SHIFT) >> 20); + return false; + } + return true; } -#ifdef CONFIG_NUMA - -static __init int find_near_online_node(int node) +static int __init numa_register_memblks(struct numa_meminfo *mi) { - int n, val; - int min_val = INT_MAX; - int best_node = -1; + int i, nid; - for_each_online_node(n) { - val = node_distance(node, n); + /* Account for nodes with cpus and no memory */ + node_possible_map = numa_nodes_parsed; + numa_nodemask_from_meminfo(&node_possible_map, mi); + if (WARN_ON(nodes_empty(node_possible_map))) + return -EINVAL; + + memnode_shift = compute_hash_shift(mi); + if (memnode_shift < 0) { + printk(KERN_ERR "NUMA: No NUMA node hash function found. Contact maintainer\n"); + return -EINVAL; + } - if (val < min_val) { - min_val = val; - best_node = n; + for (i = 0; i < mi->nr_blks; i++) + memblock_x86_register_active_regions(mi->blk[i].nid, + mi->blk[i].start >> PAGE_SHIFT, + mi->blk[i].end >> PAGE_SHIFT); + + /* for out of order entries */ + sort_node_map(); + if (!numa_meminfo_cover_memory(mi)) + return -EINVAL; + + /* Finally register nodes. */ + for_each_node_mask(nid, node_possible_map) { + u64 start = (u64)max_pfn << PAGE_SHIFT; + u64 end = 0; + + for (i = 0; i < mi->nr_blks; i++) { + if (nid != mi->blk[i].nid) + continue; + start = min(mi->blk[i].start, start); + end = max(mi->blk[i].end, end); } + + if (start < end) + setup_node_bootmem(nid, start, end); } - return best_node; + return 0; } -/* - * Setup early cpu_to_node. +/** + * dummy_numma_init - Fallback dummy NUMA init * - * Populate cpu_to_node[] only if x86_cpu_to_apicid[], - * and apicid_to_node[] tables have valid entries for a CPU. - * This means we skip cpu_to_node[] initialisation for NUMA - * emulation and faking node case (when running a kernel compiled - * for NUMA on a non NUMA box), which is OK as cpu_to_node[] - * is already initialized in a round robin manner at numa_init_array, - * prior to this call, and this initialization is good enough - * for the fake NUMA cases. + * Used if there's no underlying NUMA architecture, NUMA initialization + * fails, or NUMA is disabled on the command line. * - * Called before the per_cpu areas are setup. + * Must online at least one node and add memory blocks that cover all + * allowed memory. This function must not fail. */ -void __init init_cpu_to_node(void) +static int __init dummy_numa_init(void) { - int cpu; - u16 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid); - - BUG_ON(cpu_to_apicid == NULL); + printk(KERN_INFO "%s\n", + numa_off ? "NUMA turned off" : "No NUMA configuration found"); + printk(KERN_INFO "Faking a node at %016lx-%016lx\n", + 0LU, max_pfn << PAGE_SHIFT); - for_each_possible_cpu(cpu) { - int node; - u16 apicid = cpu_to_apicid[cpu]; + node_set(0, numa_nodes_parsed); + numa_add_memblk(0, 0, (u64)max_pfn << PAGE_SHIFT); - if (apicid == BAD_APICID) - continue; - node = apicid_to_node[apicid]; - if (node == NUMA_NO_NODE) - continue; - if (!node_online(node)) - node = find_near_online_node(node); - numa_set_node(cpu, node); - } + return 0; } -#endif - -void __cpuinit numa_set_node(int cpu, int node) +static int __init numa_init(int (*init_func)(void)) { - int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map); - - /* early setting, no percpu area yet */ - if (cpu_to_node_map) { - cpu_to_node_map[cpu] = node; - return; - } - -#ifdef CONFIG_DEBUG_PER_CPU_MAPS - if (cpu >= nr_cpu_ids || !cpu_possible(cpu)) { - printk(KERN_ERR "numa_set_node: invalid cpu# (%d)\n", cpu); - dump_stack(); - return; - } -#endif - per_cpu(x86_cpu_to_node_map, cpu) = node; + int i; + int ret; - if (node != NUMA_NO_NODE) - set_cpu_numa_node(cpu, node); -} + for (i = 0; i < MAX_LOCAL_APIC; i++) + set_apicid_to_node(i, NUMA_NO_NODE); -void __cpuinit numa_clear_node(int cpu) -{ - numa_set_node(cpu, NUMA_NO_NODE); -} + nodes_clear(numa_nodes_parsed); + nodes_clear(node_possible_map); + nodes_clear(node_online_map); + memset(&numa_meminfo, 0, sizeof(numa_meminfo)); + remove_all_active_ranges(); + numa_reset_distance(); -#ifndef CONFIG_DEBUG_PER_CPU_MAPS + ret = init_func(); + if (ret < 0) + return ret; + ret = numa_cleanup_meminfo(&numa_meminfo); + if (ret < 0) + return ret; -#ifndef CONFIG_NUMA_EMU -void __cpuinit numa_add_cpu(int cpu) -{ - cpumask_set_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]); -} + numa_emulation(&numa_meminfo, numa_distance_cnt); -void __cpuinit numa_remove_cpu(int cpu) -{ - cpumask_clear_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]); -} -#else -void __cpuinit numa_add_cpu(int cpu) -{ - unsigned long addr; - u16 apicid; - int physnid; - int nid = NUMA_NO_NODE; + ret = numa_register_memblks(&numa_meminfo); + if (ret < 0) + return ret; - apicid = early_per_cpu(x86_cpu_to_apicid, cpu); - if (apicid != BAD_APICID) - nid = apicid_to_node[apicid]; - if (nid == NUMA_NO_NODE) - nid = early_cpu_to_node(cpu); - BUG_ON(nid == NUMA_NO_NODE || !node_online(nid)); - - /* - * Use the starting address of the emulated node to find which physical - * node it is allocated on. - */ - addr = node_start_pfn(nid) << PAGE_SHIFT; - for (physnid = 0; physnid < MAX_NUMNODES; physnid++) - if (addr >= physnodes[physnid].start && - addr < physnodes[physnid].end) - break; + for (i = 0; i < nr_cpu_ids; i++) { + int nid = early_cpu_to_node(i); - /* - * Map the cpu to each emulated node that is allocated on the physical - * node of the cpu's apic id. - */ - for_each_online_node(nid) { - addr = node_start_pfn(nid) << PAGE_SHIFT; - if (addr >= physnodes[physnid].start && - addr < physnodes[physnid].end) - cpumask_set_cpu(cpu, node_to_cpumask_map[nid]); + if (nid == NUMA_NO_NODE) + continue; + if (!node_online(nid)) + numa_clear_node(i); } + numa_init_array(); + return 0; } -void __cpuinit numa_remove_cpu(int cpu) +void __init initmem_init(void) { - int i; + int ret; - for_each_online_node(i) - cpumask_clear_cpu(cpu, node_to_cpumask_map[i]); -} -#endif /* !CONFIG_NUMA_EMU */ - -#else /* CONFIG_DEBUG_PER_CPU_MAPS */ -static struct cpumask __cpuinit *debug_cpumask_set_cpu(int cpu, int enable) -{ - int node = early_cpu_to_node(cpu); - struct cpumask *mask; - char buf[64]; - - mask = node_to_cpumask_map[node]; - if (!mask) { - pr_err("node_to_cpumask_map[%i] NULL\n", node); - dump_stack(); - return NULL; + if (!numa_off) { +#ifdef CONFIG_ACPI_NUMA + ret = numa_init(x86_acpi_numa_init); + if (!ret) + return; +#endif +#ifdef CONFIG_AMD_NUMA + ret = numa_init(amd_numa_init); + if (!ret) + return; +#endif } - cpulist_scnprintf(buf, sizeof(buf), mask); - printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n", - enable ? "numa_add_cpu" : "numa_remove_cpu", - cpu, node, buf); - return mask; + numa_init(dummy_numa_init); } -/* - * --------- debug versions of the numa functions --------- - */ -#ifndef CONFIG_NUMA_EMU -static void __cpuinit numa_set_cpumask(int cpu, int enable) -{ - struct cpumask *mask; - - mask = debug_cpumask_set_cpu(cpu, enable); - if (!mask) - return; - - if (enable) - cpumask_set_cpu(cpu, mask); - else - cpumask_clear_cpu(cpu, mask); -} -#else -static void __cpuinit numa_set_cpumask(int cpu, int enable) +unsigned long __init numa_free_all_bootmem(void) { - int node = early_cpu_to_node(cpu); - struct cpumask *mask; + unsigned long pages = 0; int i; - for_each_online_node(i) { - unsigned long addr; - - addr = node_start_pfn(i) << PAGE_SHIFT; - if (addr < physnodes[node].start || - addr >= physnodes[node].end) - continue; - mask = debug_cpumask_set_cpu(cpu, enable); - if (!mask) - return; - - if (enable) - cpumask_set_cpu(cpu, mask); - else - cpumask_clear_cpu(cpu, mask); - } -} -#endif /* CONFIG_NUMA_EMU */ + for_each_online_node(i) + pages += free_all_bootmem_node(NODE_DATA(i)); -void __cpuinit numa_add_cpu(int cpu) -{ - numa_set_cpumask(cpu, 1); -} + pages += free_all_memory_core_early(MAX_NUMNODES); -void __cpuinit numa_remove_cpu(int cpu) -{ - numa_set_cpumask(cpu, 0); + return pages; } -int __cpu_to_node(int cpu) +int __cpuinit numa_cpu_node(int cpu) { - if (early_per_cpu_ptr(x86_cpu_to_node_map)) { - printk(KERN_WARNING - "cpu_to_node(%d): usage too early!\n", cpu); - dump_stack(); - return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu]; - } - return per_cpu(x86_cpu_to_node_map, cpu); -} -EXPORT_SYMBOL(__cpu_to_node); + int apicid = early_per_cpu(x86_cpu_to_apicid, cpu); -/* - * Same function as cpu_to_node() but used if called before the - * per_cpu areas are setup. - */ -int early_cpu_to_node(int cpu) -{ - if (early_per_cpu_ptr(x86_cpu_to_node_map)) - return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu]; - - if (!cpu_possible(cpu)) { - printk(KERN_WARNING - "early_cpu_to_node(%d): no per_cpu area!\n", cpu); - dump_stack(); - return NUMA_NO_NODE; - } - return per_cpu(x86_cpu_to_node_map, cpu); + if (apicid != BAD_APICID) + return __apicid_to_node[apicid]; + return NUMA_NO_NODE; } - -/* - * --------- end of debug versions of the numa functions --------- - */ - -#endif /* CONFIG_DEBUG_PER_CPU_MAPS */ diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c new file mode 100644 index 00000000000..de84cc14037 --- /dev/null +++ b/arch/x86/mm/numa_emulation.c @@ -0,0 +1,486 @@ +/* + * NUMA emulation + */ +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/topology.h> +#include <linux/memblock.h> +#include <asm/dma.h> + +#include "numa_internal.h" + +static int emu_nid_to_phys[MAX_NUMNODES] __cpuinitdata; +static char *emu_cmdline __initdata; + +void __init numa_emu_cmdline(char *str) +{ + emu_cmdline = str; +} + +static int __init emu_find_memblk_by_nid(int nid, const struct numa_meminfo *mi) +{ + int i; + + for (i = 0; i < mi->nr_blks; i++) + if (mi->blk[i].nid == nid) + return i; + return -ENOENT; +} + +/* + * Sets up nid to range from @start to @end. The return value is -errno if + * something went wrong, 0 otherwise. + */ +static int __init emu_setup_memblk(struct numa_meminfo *ei, + struct numa_meminfo *pi, + int nid, int phys_blk, u64 size) +{ + struct numa_memblk *eb = &ei->blk[ei->nr_blks]; + struct numa_memblk *pb = &pi->blk[phys_blk]; + + if (ei->nr_blks >= NR_NODE_MEMBLKS) { + pr_err("NUMA: Too many emulated memblks, failing emulation\n"); + return -EINVAL; + } + + ei->nr_blks++; + eb->start = pb->start; + eb->end = pb->start + size; + eb->nid = nid; + + if (emu_nid_to_phys[nid] == NUMA_NO_NODE) + emu_nid_to_phys[nid] = pb->nid; + + pb->start += size; + if (pb->start >= pb->end) { + WARN_ON_ONCE(pb->start > pb->end); + numa_remove_memblk_from(phys_blk, pi); + } + + printk(KERN_INFO "Faking node %d at %016Lx-%016Lx (%LuMB)\n", nid, + eb->start, eb->end, (eb->end - eb->start) >> 20); + return 0; +} + +/* + * Sets up nr_nodes fake nodes interleaved over physical nodes ranging from addr + * to max_addr. The return value is the number of nodes allocated. + */ +static int __init split_nodes_interleave(struct numa_meminfo *ei, + struct numa_meminfo *pi, + u64 addr, u64 max_addr, int nr_nodes) +{ + nodemask_t physnode_mask = NODE_MASK_NONE; + u64 size; + int big; + int nid = 0; + int i, ret; + + if (nr_nodes <= 0) + return -1; + if (nr_nodes > MAX_NUMNODES) { + pr_info("numa=fake=%d too large, reducing to %d\n", + nr_nodes, MAX_NUMNODES); + nr_nodes = MAX_NUMNODES; + } + + size = (max_addr - addr - memblock_x86_hole_size(addr, max_addr)) / nr_nodes; + /* + * Calculate the number of big nodes that can be allocated as a result + * of consolidating the remainder. + */ + big = ((size & ~FAKE_NODE_MIN_HASH_MASK) * nr_nodes) / + FAKE_NODE_MIN_SIZE; + + size &= FAKE_NODE_MIN_HASH_MASK; + if (!size) { + pr_err("Not enough memory for each node. " + "NUMA emulation disabled.\n"); + return -1; + } + + for (i = 0; i < pi->nr_blks; i++) + node_set(pi->blk[i].nid, physnode_mask); + + /* + * Continue to fill physical nodes with fake nodes until there is no + * memory left on any of them. + */ + while (nodes_weight(physnode_mask)) { + for_each_node_mask(i, physnode_mask) { + u64 dma32_end = PFN_PHYS(MAX_DMA32_PFN); + u64 start, limit, end; + int phys_blk; + + phys_blk = emu_find_memblk_by_nid(i, pi); + if (phys_blk < 0) { + node_clear(i, physnode_mask); + continue; + } + start = pi->blk[phys_blk].start; + limit = pi->blk[phys_blk].end; + end = start + size; + + if (nid < big) + end += FAKE_NODE_MIN_SIZE; + + /* + * Continue to add memory to this fake node if its + * non-reserved memory is less than the per-node size. + */ + while (end - start - + memblock_x86_hole_size(start, end) < size) { + end += FAKE_NODE_MIN_SIZE; + if (end > limit) { + end = limit; + break; + } + } + + /* + * If there won't be at least FAKE_NODE_MIN_SIZE of + * non-reserved memory in ZONE_DMA32 for the next node, + * this one must extend to the boundary. + */ + if (end < dma32_end && dma32_end - end - + memblock_x86_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE) + end = dma32_end; + + /* + * If there won't be enough non-reserved memory for the + * next node, this one must extend to the end of the + * physical node. + */ + if (limit - end - + memblock_x86_hole_size(end, limit) < size) + end = limit; + + ret = emu_setup_memblk(ei, pi, nid++ % nr_nodes, + phys_blk, + min(end, limit) - start); + if (ret < 0) + return ret; + } + } + return 0; +} + +/* + * Returns the end address of a node so that there is at least `size' amount of + * non-reserved memory or `max_addr' is reached. + */ +static u64 __init find_end_of_node(u64 start, u64 max_addr, u64 size) +{ + u64 end = start + size; + + while (end - start - memblock_x86_hole_size(start, end) < size) { + end += FAKE_NODE_MIN_SIZE; + if (end > max_addr) { + end = max_addr; + break; + } + } + return end; +} + +/* + * Sets up fake nodes of `size' interleaved over physical nodes ranging from + * `addr' to `max_addr'. The return value is the number of nodes allocated. + */ +static int __init split_nodes_size_interleave(struct numa_meminfo *ei, + struct numa_meminfo *pi, + u64 addr, u64 max_addr, u64 size) +{ + nodemask_t physnode_mask = NODE_MASK_NONE; + u64 min_size; + int nid = 0; + int i, ret; + + if (!size) + return -1; + /* + * The limit on emulated nodes is MAX_NUMNODES, so the size per node is + * increased accordingly if the requested size is too small. This + * creates a uniform distribution of node sizes across the entire + * machine (but not necessarily over physical nodes). + */ + min_size = (max_addr - addr - memblock_x86_hole_size(addr, max_addr)) / + MAX_NUMNODES; + min_size = max(min_size, FAKE_NODE_MIN_SIZE); + if ((min_size & FAKE_NODE_MIN_HASH_MASK) < min_size) + min_size = (min_size + FAKE_NODE_MIN_SIZE) & + FAKE_NODE_MIN_HASH_MASK; + if (size < min_size) { + pr_err("Fake node size %LuMB too small, increasing to %LuMB\n", + size >> 20, min_size >> 20); + size = min_size; + } + size &= FAKE_NODE_MIN_HASH_MASK; + + for (i = 0; i < pi->nr_blks; i++) + node_set(pi->blk[i].nid, physnode_mask); + + /* + * Fill physical nodes with fake nodes of size until there is no memory + * left on any of them. + */ + while (nodes_weight(physnode_mask)) { + for_each_node_mask(i, physnode_mask) { + u64 dma32_end = MAX_DMA32_PFN << PAGE_SHIFT; + u64 start, limit, end; + int phys_blk; + + phys_blk = emu_find_memblk_by_nid(i, pi); + if (phys_blk < 0) { + node_clear(i, physnode_mask); + continue; + } + start = pi->blk[phys_blk].start; + limit = pi->blk[phys_blk].end; + + end = find_end_of_node(start, limit, size); + /* + * If there won't be at least FAKE_NODE_MIN_SIZE of + * non-reserved memory in ZONE_DMA32 for the next node, + * this one must extend to the boundary. + */ + if (end < dma32_end && dma32_end - end - + memblock_x86_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE) + end = dma32_end; + + /* + * If there won't be enough non-reserved memory for the + * next node, this one must extend to the end of the + * physical node. + */ + if (limit - end - + memblock_x86_hole_size(end, limit) < size) + end = limit; + + ret = emu_setup_memblk(ei, pi, nid++ % MAX_NUMNODES, + phys_blk, + min(end, limit) - start); + if (ret < 0) + return ret; + } + } + return 0; +} + +/** + * numa_emulation - Emulate NUMA nodes + * @numa_meminfo: NUMA configuration to massage + * @numa_dist_cnt: The size of the physical NUMA distance table + * + * Emulate NUMA nodes according to the numa=fake kernel parameter. + * @numa_meminfo contains the physical memory configuration and is modified + * to reflect the emulated configuration on success. @numa_dist_cnt is + * used to determine the size of the physical distance table. + * + * On success, the following modifications are made. + * + * - @numa_meminfo is updated to reflect the emulated nodes. + * + * - __apicid_to_node[] is updated such that APIC IDs are mapped to the + * emulated nodes. + * + * - NUMA distance table is rebuilt to represent distances between emulated + * nodes. The distances are determined considering how emulated nodes + * are mapped to physical nodes and match the actual distances. + * + * - emu_nid_to_phys[] reflects how emulated nodes are mapped to physical + * nodes. This is used by numa_add_cpu() and numa_remove_cpu(). + * + * If emulation is not enabled or fails, emu_nid_to_phys[] is filled with + * identity mapping and no other modification is made. + */ +void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) +{ + static struct numa_meminfo ei __initdata; + static struct numa_meminfo pi __initdata; + const u64 max_addr = max_pfn << PAGE_SHIFT; + u8 *phys_dist = NULL; + size_t phys_size = numa_dist_cnt * numa_dist_cnt * sizeof(phys_dist[0]); + int max_emu_nid, dfl_phys_nid; + int i, j, ret; + + if (!emu_cmdline) + goto no_emu; + + memset(&ei, 0, sizeof(ei)); + pi = *numa_meminfo; + + for (i = 0; i < MAX_NUMNODES; i++) + emu_nid_to_phys[i] = NUMA_NO_NODE; + + /* + * If the numa=fake command-line contains a 'M' or 'G', it represents + * the fixed node size. Otherwise, if it is just a single number N, + * split the system RAM into N fake nodes. + */ + if (strchr(emu_cmdline, 'M') || strchr(emu_cmdline, 'G')) { + u64 size; + + size = memparse(emu_cmdline, &emu_cmdline); + ret = split_nodes_size_interleave(&ei, &pi, 0, max_addr, size); + } else { + unsigned long n; + + n = simple_strtoul(emu_cmdline, NULL, 0); + ret = split_nodes_interleave(&ei, &pi, 0, max_addr, n); + } + + if (ret < 0) + goto no_emu; + + if (numa_cleanup_meminfo(&ei) < 0) { + pr_warning("NUMA: Warning: constructed meminfo invalid, disabling emulation\n"); + goto no_emu; + } + + /* copy the physical distance table */ + if (numa_dist_cnt) { + u64 phys; + + phys = memblock_find_in_range(0, + (u64)max_pfn_mapped << PAGE_SHIFT, + phys_size, PAGE_SIZE); + if (phys == MEMBLOCK_ERROR) { + pr_warning("NUMA: Warning: can't allocate copy of distance table, disabling emulation\n"); + goto no_emu; + } + memblock_x86_reserve_range(phys, phys + phys_size, "TMP NUMA DIST"); + phys_dist = __va(phys); + + for (i = 0; i < numa_dist_cnt; i++) + for (j = 0; j < numa_dist_cnt; j++) + phys_dist[i * numa_dist_cnt + j] = + node_distance(i, j); + } + + /* + * Determine the max emulated nid and the default phys nid to use + * for unmapped nodes. + */ + max_emu_nid = 0; + dfl_phys_nid = NUMA_NO_NODE; + for (i = 0; i < ARRAY_SIZE(emu_nid_to_phys); i++) { + if (emu_nid_to_phys[i] != NUMA_NO_NODE) { + max_emu_nid = i; + if (dfl_phys_nid == NUMA_NO_NODE) + dfl_phys_nid = emu_nid_to_phys[i]; + } + } + if (dfl_phys_nid == NUMA_NO_NODE) { + pr_warning("NUMA: Warning: can't determine default physical node, disabling emulation\n"); + goto no_emu; + } + + /* commit */ + *numa_meminfo = ei; + + /* + * Transform __apicid_to_node table to use emulated nids by + * reverse-mapping phys_nid. The maps should always exist but fall + * back to zero just in case. + */ + for (i = 0; i < ARRAY_SIZE(__apicid_to_node); i++) { + if (__apicid_to_node[i] == NUMA_NO_NODE) + continue; + for (j = 0; j < ARRAY_SIZE(emu_nid_to_phys); j++) + if (__apicid_to_node[i] == emu_nid_to_phys[j]) + break; + __apicid_to_node[i] = j < ARRAY_SIZE(emu_nid_to_phys) ? j : 0; + } + + /* make sure all emulated nodes are mapped to a physical node */ + for (i = 0; i < ARRAY_SIZE(emu_nid_to_phys); i++) + if (emu_nid_to_phys[i] == NUMA_NO_NODE) + emu_nid_to_phys[i] = dfl_phys_nid; + + /* transform distance table */ + numa_reset_distance(); + for (i = 0; i < max_emu_nid + 1; i++) { + for (j = 0; j < max_emu_nid + 1; j++) { + int physi = emu_nid_to_phys[i]; + int physj = emu_nid_to_phys[j]; + int dist; + + if (physi >= numa_dist_cnt || physj >= numa_dist_cnt) + dist = physi == physj ? + LOCAL_DISTANCE : REMOTE_DISTANCE; + else + dist = phys_dist[physi * numa_dist_cnt + physj]; + + numa_set_distance(i, j, dist); + } + } + + /* free the copied physical distance table */ + if (phys_dist) + memblock_x86_free_range(__pa(phys_dist), __pa(phys_dist) + phys_size); + return; + +no_emu: + /* No emulation. Build identity emu_nid_to_phys[] for numa_add_cpu() */ + for (i = 0; i < ARRAY_SIZE(emu_nid_to_phys); i++) + emu_nid_to_phys[i] = i; +} + +#ifndef CONFIG_DEBUG_PER_CPU_MAPS +void __cpuinit numa_add_cpu(int cpu) +{ + int physnid, nid; + + nid = early_cpu_to_node(cpu); + BUG_ON(nid == NUMA_NO_NODE || !node_online(nid)); + + physnid = emu_nid_to_phys[nid]; + + /* + * Map the cpu to each emulated node that is allocated on the physical + * node of the cpu's apic id. + */ + for_each_online_node(nid) + if (emu_nid_to_phys[nid] == physnid) + cpumask_set_cpu(cpu, node_to_cpumask_map[nid]); +} + +void __cpuinit numa_remove_cpu(int cpu) +{ + int i; + + for_each_online_node(i) + cpumask_clear_cpu(cpu, node_to_cpumask_map[i]); +} +#else /* !CONFIG_DEBUG_PER_CPU_MAPS */ +static void __cpuinit numa_set_cpumask(int cpu, bool enable) +{ + int nid, physnid; + + nid = early_cpu_to_node(cpu); + if (nid == NUMA_NO_NODE) { + /* early_cpu_to_node() already emits a warning and trace */ + return; + } + + physnid = emu_nid_to_phys[nid]; + + for_each_online_node(nid) { + if (emu_nid_to_phys[nid] != physnid) + continue; + + debug_cpumask_set_cpu(cpu, nid, enable); + } +} + +void __cpuinit numa_add_cpu(int cpu) +{ + numa_set_cpumask(cpu, true); +} + +void __cpuinit numa_remove_cpu(int cpu) +{ + numa_set_cpumask(cpu, false); +} +#endif /* !CONFIG_DEBUG_PER_CPU_MAPS */ diff --git a/arch/x86/mm/numa_internal.h b/arch/x86/mm/numa_internal.h new file mode 100644 index 00000000000..ef2d97377d7 --- /dev/null +++ b/arch/x86/mm/numa_internal.h @@ -0,0 +1,31 @@ +#ifndef __X86_MM_NUMA_INTERNAL_H +#define __X86_MM_NUMA_INTERNAL_H + +#include <linux/types.h> +#include <asm/numa.h> + +struct numa_memblk { + u64 start; + u64 end; + int nid; +}; + +struct numa_meminfo { + int nr_blks; + struct numa_memblk blk[NR_NODE_MEMBLKS]; +}; + +void __init numa_remove_memblk_from(int idx, struct numa_meminfo *mi); +int __init numa_cleanup_meminfo(struct numa_meminfo *mi); +void __init numa_reset_distance(void); + +#ifdef CONFIG_NUMA_EMU +void __init numa_emulation(struct numa_meminfo *numa_meminfo, + int numa_dist_cnt); +#else +static inline void numa_emulation(struct numa_meminfo *numa_meminfo, + int numa_dist_cnt) +{ } +#endif + +#endif /* __X86_MM_NUMA_INTERNAL_H */ diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index d343b3c81f3..f9e526742fa 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -57,12 +57,10 @@ static unsigned long direct_pages_count[PG_LEVEL_NUM]; void update_page_count(int level, unsigned long pages) { - unsigned long flags; - /* Protect against CPA */ - spin_lock_irqsave(&pgd_lock, flags); + spin_lock(&pgd_lock); direct_pages_count[level] += pages; - spin_unlock_irqrestore(&pgd_lock, flags); + spin_unlock(&pgd_lock); } static void split_page_count(int level) @@ -312,7 +310,7 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address, * these shared mappings are made of small page mappings. * Thus this don't enforce !RW mapping for small page kernel * text mapping logic will help Linux Xen parvirt guest boot - * aswell. + * as well. */ if (lookup_address(address, &level) && (level != PG_LEVEL_4K)) pgprot_val(forbidden) |= _PAGE_RW; @@ -394,7 +392,7 @@ static int try_preserve_large_page(pte_t *kpte, unsigned long address, struct cpa_data *cpa) { - unsigned long nextpage_addr, numpages, pmask, psize, flags, addr, pfn; + unsigned long nextpage_addr, numpages, pmask, psize, addr, pfn; pte_t new_pte, old_pte, *tmp; pgprot_t old_prot, new_prot, req_prot; int i, do_split = 1; @@ -403,7 +401,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, if (cpa->force_split) return 1; - spin_lock_irqsave(&pgd_lock, flags); + spin_lock(&pgd_lock); /* * Check for races, another CPU might have split this page * up already: @@ -498,14 +496,14 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, } out_unlock: - spin_unlock_irqrestore(&pgd_lock, flags); + spin_unlock(&pgd_lock); return do_split; } static int split_large_page(pte_t *kpte, unsigned long address) { - unsigned long flags, pfn, pfninc = 1; + unsigned long pfn, pfninc = 1; unsigned int i, level; pte_t *pbase, *tmp; pgprot_t ref_prot; @@ -519,7 +517,7 @@ static int split_large_page(pte_t *kpte, unsigned long address) if (!base) return -ENOMEM; - spin_lock_irqsave(&pgd_lock, flags); + spin_lock(&pgd_lock); /* * Check for races, another CPU might have split this page * up for us already: @@ -591,7 +589,7 @@ out_unlock: */ if (base) __free_page(base); - spin_unlock_irqrestore(&pgd_lock, flags); + spin_unlock(&pgd_lock); return 0; } diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 500242d3c96..8573b83a63d 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -121,14 +121,12 @@ static void pgd_ctor(struct mm_struct *mm, pgd_t *pgd) static void pgd_dtor(pgd_t *pgd) { - unsigned long flags; /* can be called from interrupt context */ - if (SHARED_KERNEL_PMD) return; - spin_lock_irqsave(&pgd_lock, flags); + spin_lock(&pgd_lock); pgd_list_del(pgd); - spin_unlock_irqrestore(&pgd_lock, flags); + spin_unlock(&pgd_lock); } /* @@ -170,8 +168,7 @@ void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd) * section 8.1: in PAE mode we explicitly have to flush the * TLB via cr3 if the top-level pgd is changed... */ - if (mm == current->active_mm) - write_cr3(read_cr3()); + flush_tlb_mm(mm); } #else /* !CONFIG_X86_PAE */ @@ -260,7 +257,6 @@ pgd_t *pgd_alloc(struct mm_struct *mm) { pgd_t *pgd; pmd_t *pmds[PREALLOCATED_PMDS]; - unsigned long flags; pgd = (pgd_t *)__get_free_page(PGALLOC_GFP); @@ -280,12 +276,12 @@ pgd_t *pgd_alloc(struct mm_struct *mm) * respect to anything walking the pgd_list, so that they * never see a partially populated pgd. */ - spin_lock_irqsave(&pgd_lock, flags); + spin_lock(&pgd_lock); pgd_ctor(mm, pgd); pgd_prepopulate_pmd(mm, pgd, pmds); - spin_unlock_irqrestore(&pgd_lock, flags); + spin_unlock(&pgd_lock); return pgd; diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c index ae96e7b8051..364f36bdfad 100644 --- a/arch/x86/mm/srat_32.c +++ b/arch/x86/mm/srat_32.c @@ -57,7 +57,7 @@ struct node_memory_chunk_s { static struct node_memory_chunk_s __initdata node_memory_chunk[MAXCHUNKS]; static int __initdata num_memory_chunks; /* total number of memory chunks */ -static u8 __initdata apicid_to_pxm[MAX_APICID]; +static u8 __initdata apicid_to_pxm[MAX_LOCAL_APIC]; int acpi_numa __initdata; @@ -211,10 +211,12 @@ int __init get_memcfg_from_srat(void) { int i, j, nid; - if (srat_disabled()) goto out_fail; + if (acpi_numa_init() < 0) + goto out_fail; + if (num_memory_chunks == 0) { printk(KERN_DEBUG "could not find any ACPI SRAT memory areas.\n"); @@ -254,8 +256,8 @@ int __init get_memcfg_from_srat(void) printk(KERN_DEBUG "Number of memory chunks in system = %d\n", num_memory_chunks); - for (i = 0; i < MAX_APICID; i++) - apicid_2_node[i] = pxm_to_node(apicid_to_pxm[i]); + for (i = 0; i < MAX_LOCAL_APIC; i++) + set_apicid_to_node(i, pxm_to_node(apicid_to_pxm[i])); for (j = 0; j < num_memory_chunks; j++){ struct node_memory_chunk_s * chunk = &node_memory_chunk[j]; diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c index 603d285d1da..8e9d3394f6d 100644 --- a/arch/x86/mm/srat_64.c +++ b/arch/x86/mm/srat_64.c @@ -26,88 +26,34 @@ int acpi_numa __initdata; -static struct acpi_table_slit *acpi_slit; - -static nodemask_t nodes_parsed __initdata; -static nodemask_t cpu_nodes_parsed __initdata; -static struct bootnode nodes[MAX_NUMNODES] __initdata; static struct bootnode nodes_add[MAX_NUMNODES]; -static int num_node_memblks __initdata; -static struct bootnode node_memblk_range[NR_NODE_MEMBLKS] __initdata; -static int memblk_nodeid[NR_NODE_MEMBLKS] __initdata; - static __init int setup_node(int pxm) { return acpi_map_pxm_to_node(pxm); } -static __init int conflicting_memblks(unsigned long start, unsigned long end) -{ - int i; - for (i = 0; i < num_node_memblks; i++) { - struct bootnode *nd = &node_memblk_range[i]; - if (nd->start == nd->end) - continue; - if (nd->end > start && nd->start < end) - return memblk_nodeid[i]; - if (nd->end == end && nd->start == start) - return memblk_nodeid[i]; - } - return -1; -} - -static __init void cutoff_node(int i, unsigned long start, unsigned long end) -{ - struct bootnode *nd = &nodes[i]; - - if (nd->start < start) { - nd->start = start; - if (nd->end < nd->start) - nd->start = nd->end; - } - if (nd->end > end) { - nd->end = end; - if (nd->start > nd->end) - nd->start = nd->end; - } -} - static __init void bad_srat(void) { - int i; printk(KERN_ERR "SRAT: SRAT not used.\n"); acpi_numa = -1; - for (i = 0; i < MAX_LOCAL_APIC; i++) - apicid_to_node[i] = NUMA_NO_NODE; - for (i = 0; i < MAX_NUMNODES; i++) { - nodes[i].start = nodes[i].end = 0; - nodes_add[i].start = nodes_add[i].end = 0; - } - remove_all_active_ranges(); + memset(nodes_add, 0, sizeof(nodes_add)); } static __init inline int srat_disabled(void) { - return numa_off || acpi_numa < 0; + return acpi_numa < 0; } /* Callback for SLIT parsing */ void __init acpi_numa_slit_init(struct acpi_table_slit *slit) { - unsigned length; - unsigned long phys; - - length = slit->header.length; - phys = memblock_find_in_range(0, max_pfn_mapped<<PAGE_SHIFT, length, - PAGE_SIZE); - - if (phys == MEMBLOCK_ERROR) - panic(" Can not save slit!\n"); + int i, j; - acpi_slit = __va(phys); - memcpy(acpi_slit, slit, length); - memblock_x86_reserve_range(phys, phys + length, "ACPI SLIT"); + for (i = 0; i < slit->locality_count; i++) + for (j = 0; j < slit->locality_count; j++) + numa_set_distance(pxm_to_node(i), pxm_to_node(j), + slit->entry[slit->locality_count * i + j]); } /* Callback for Proximity Domain -> x2APIC mapping */ @@ -138,8 +84,8 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa) printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%04x -> Node %u skipped apicid that is too big\n", pxm, apic_id, node); return; } - apicid_to_node[apic_id] = node; - node_set(node, cpu_nodes_parsed); + set_apicid_to_node(apic_id, node); + node_set(node, numa_nodes_parsed); acpi_numa = 1; printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%04x -> Node %u\n", pxm, apic_id, node); @@ -178,8 +124,8 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) return; } - apicid_to_node[apic_id] = node; - node_set(node, cpu_nodes_parsed); + set_apicid_to_node(apic_id, node); + node_set(node, numa_nodes_parsed); acpi_numa = 1; printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%02x -> Node %u\n", pxm, apic_id, node); @@ -241,7 +187,7 @@ update_nodes_add(int node, unsigned long start, unsigned long end) } if (changed) { - node_set(node, cpu_nodes_parsed); + node_set(node, numa_nodes_parsed); printk(KERN_INFO "SRAT: hot plug zone found %Lx - %Lx\n", nd->start, nd->end); } @@ -251,10 +197,8 @@ update_nodes_add(int node, unsigned long start, unsigned long end) void __init acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) { - struct bootnode *nd, oldnode; unsigned long start, end; int node, pxm; - int i; if (srat_disabled()) return; @@ -276,300 +220,31 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) bad_srat(); return; } - i = conflicting_memblks(start, end); - if (i == node) { - printk(KERN_WARNING - "SRAT: Warning: PXM %d (%lx-%lx) overlaps with itself (%Lx-%Lx)\n", - pxm, start, end, nodes[i].start, nodes[i].end); - } else if (i >= 0) { - printk(KERN_ERR - "SRAT: PXM %d (%lx-%lx) overlaps with PXM %d (%Lx-%Lx)\n", - pxm, start, end, node_to_pxm(i), - nodes[i].start, nodes[i].end); + + if (numa_add_memblk(node, start, end) < 0) { bad_srat(); return; } - nd = &nodes[node]; - oldnode = *nd; - if (!node_test_and_set(node, nodes_parsed)) { - nd->start = start; - nd->end = end; - } else { - if (start < nd->start) - nd->start = start; - if (nd->end < end) - nd->end = end; - } printk(KERN_INFO "SRAT: Node %u PXM %u %lx-%lx\n", node, pxm, start, end); - if (ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) { + if (ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) update_nodes_add(node, start, end); - /* restore nodes[node] */ - *nd = oldnode; - if ((nd->start | nd->end) == 0) - node_clear(node, nodes_parsed); - } - - node_memblk_range[num_node_memblks].start = start; - node_memblk_range[num_node_memblks].end = end; - memblk_nodeid[num_node_memblks] = node; - num_node_memblks++; -} - -/* Sanity check to catch more bad SRATs (they are amazingly common). - Make sure the PXMs cover all memory. */ -static int __init nodes_cover_memory(const struct bootnode *nodes) -{ - int i; - unsigned long pxmram, e820ram; - - pxmram = 0; - for_each_node_mask(i, nodes_parsed) { - unsigned long s = nodes[i].start >> PAGE_SHIFT; - unsigned long e = nodes[i].end >> PAGE_SHIFT; - pxmram += e - s; - pxmram -= __absent_pages_in_range(i, s, e); - if ((long)pxmram < 0) - pxmram = 0; - } - - e820ram = max_pfn - (memblock_x86_hole_size(0, max_pfn<<PAGE_SHIFT)>>PAGE_SHIFT); - /* We seem to lose 3 pages somewhere. Allow 1M of slack. */ - if ((long)(e820ram - pxmram) >= (1<<(20 - PAGE_SHIFT))) { - printk(KERN_ERR - "SRAT: PXMs only cover %luMB of your %luMB e820 RAM. Not used.\n", - (pxmram << PAGE_SHIFT) >> 20, - (e820ram << PAGE_SHIFT) >> 20); - return 0; - } - return 1; } void __init acpi_numa_arch_fixup(void) {} -#ifdef CONFIG_NUMA_EMU -void __init acpi_get_nodes(struct bootnode *physnodes, unsigned long start, - unsigned long end) -{ - int i; - - for_each_node_mask(i, nodes_parsed) { - cutoff_node(i, start, end); - physnodes[i].start = nodes[i].start; - physnodes[i].end = nodes[i].end; - } -} -#endif /* CONFIG_NUMA_EMU */ - -/* Use the information discovered above to actually set up the nodes. */ -int __init acpi_scan_nodes(unsigned long start, unsigned long end) +int __init x86_acpi_numa_init(void) { - int i; - - if (acpi_numa <= 0) - return -1; - - /* First clean up the node list */ - for (i = 0; i < MAX_NUMNODES; i++) - cutoff_node(i, start, end); - - /* - * Join together blocks on the same node, holes between - * which don't overlap with memory on other nodes. - */ - for (i = 0; i < num_node_memblks; ++i) { - int j, k; - - for (j = i + 1; j < num_node_memblks; ++j) { - unsigned long start, end; - - if (memblk_nodeid[i] != memblk_nodeid[j]) - continue; - start = min(node_memblk_range[i].end, - node_memblk_range[j].end); - end = max(node_memblk_range[i].start, - node_memblk_range[j].start); - for (k = 0; k < num_node_memblks; ++k) { - if (memblk_nodeid[i] == memblk_nodeid[k]) - continue; - if (start < node_memblk_range[k].end && - end > node_memblk_range[k].start) - break; - } - if (k < num_node_memblks) - continue; - start = min(node_memblk_range[i].start, - node_memblk_range[j].start); - end = max(node_memblk_range[i].end, - node_memblk_range[j].end); - printk(KERN_INFO "SRAT: Node %d " - "[%Lx,%Lx) + [%Lx,%Lx) -> [%lx,%lx)\n", - memblk_nodeid[i], - node_memblk_range[i].start, - node_memblk_range[i].end, - node_memblk_range[j].start, - node_memblk_range[j].end, - start, end); - node_memblk_range[i].start = start; - node_memblk_range[i].end = end; - k = --num_node_memblks - j; - memmove(memblk_nodeid + j, memblk_nodeid + j+1, - k * sizeof(*memblk_nodeid)); - memmove(node_memblk_range + j, node_memblk_range + j+1, - k * sizeof(*node_memblk_range)); - --j; - } - } - - memnode_shift = compute_hash_shift(node_memblk_range, num_node_memblks, - memblk_nodeid); - if (memnode_shift < 0) { - printk(KERN_ERR - "SRAT: No NUMA node hash function found. Contact maintainer\n"); - bad_srat(); - return -1; - } - - for (i = 0; i < num_node_memblks; i++) - memblock_x86_register_active_regions(memblk_nodeid[i], - node_memblk_range[i].start >> PAGE_SHIFT, - node_memblk_range[i].end >> PAGE_SHIFT); - - /* for out of order entries in SRAT */ - sort_node_map(); - if (!nodes_cover_memory(nodes)) { - bad_srat(); - return -1; - } + int ret; - /* Account for nodes with cpus and no memory */ - nodes_or(node_possible_map, nodes_parsed, cpu_nodes_parsed); - - /* Finally register nodes */ - for_each_node_mask(i, node_possible_map) - setup_node_bootmem(i, nodes[i].start, nodes[i].end); - /* Try again in case setup_node_bootmem missed one due - to missing bootmem */ - for_each_node_mask(i, node_possible_map) - if (!node_online(i)) - setup_node_bootmem(i, nodes[i].start, nodes[i].end); - - for (i = 0; i < nr_cpu_ids; i++) { - int node = early_cpu_to_node(i); - - if (node == NUMA_NO_NODE) - continue; - if (!node_online(node)) - numa_clear_node(i); - } - numa_init_array(); - return 0; -} - -#ifdef CONFIG_NUMA_EMU -static int fake_node_to_pxm_map[MAX_NUMNODES] __initdata = { - [0 ... MAX_NUMNODES-1] = PXM_INVAL -}; -static s16 fake_apicid_to_node[MAX_LOCAL_APIC] __initdata = { - [0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE -}; -static int __init find_node_by_addr(unsigned long addr) -{ - int ret = NUMA_NO_NODE; - int i; - - for_each_node_mask(i, nodes_parsed) { - /* - * Find the real node that this emulated node appears on. For - * the sake of simplicity, we only use a real node's starting - * address to determine which emulated node it appears on. - */ - if (addr >= nodes[i].start && addr < nodes[i].end) { - ret = i; - break; - } - } - return ret; + ret = acpi_numa_init(); + if (ret < 0) + return ret; + return srat_disabled() ? -EINVAL : 0; } -/* - * In NUMA emulation, we need to setup proximity domain (_PXM) to node ID - * mappings that respect the real ACPI topology but reflect our emulated - * environment. For each emulated node, we find which real node it appears on - * and create PXM to NID mappings for those fake nodes which mirror that - * locality. SLIT will now represent the correct distances between emulated - * nodes as a result of the real topology. - */ -void __init acpi_fake_nodes(const struct bootnode *fake_nodes, int num_nodes) -{ - int i, j; - - for (i = 0; i < num_nodes; i++) { - int nid, pxm; - - nid = find_node_by_addr(fake_nodes[i].start); - if (nid == NUMA_NO_NODE) - continue; - pxm = node_to_pxm(nid); - if (pxm == PXM_INVAL) - continue; - fake_node_to_pxm_map[i] = pxm; - /* - * For each apicid_to_node mapping that exists for this real - * node, it must now point to the fake node ID. - */ - for (j = 0; j < MAX_LOCAL_APIC; j++) - if (apicid_to_node[j] == nid && - fake_apicid_to_node[j] == NUMA_NO_NODE) - fake_apicid_to_node[j] = i; - } - - /* - * If there are apicid-to-node mappings for physical nodes that do not - * have a corresponding emulated node, it should default to a guaranteed - * value. - */ - for (i = 0; i < MAX_LOCAL_APIC; i++) - if (apicid_to_node[i] != NUMA_NO_NODE && - fake_apicid_to_node[i] == NUMA_NO_NODE) - fake_apicid_to_node[i] = 0; - - for (i = 0; i < num_nodes; i++) - __acpi_map_pxm_to_node(fake_node_to_pxm_map[i], i); - memcpy(apicid_to_node, fake_apicid_to_node, sizeof(apicid_to_node)); - - nodes_clear(nodes_parsed); - for (i = 0; i < num_nodes; i++) - if (fake_nodes[i].start != fake_nodes[i].end) - node_set(i, nodes_parsed); -} - -static int null_slit_node_compare(int a, int b) -{ - return node_to_pxm(a) == node_to_pxm(b); -} -#else -static int null_slit_node_compare(int a, int b) -{ - return a == b; -} -#endif /* CONFIG_NUMA_EMU */ - -int __node_distance(int a, int b) -{ - int index; - - if (!acpi_slit) - return null_slit_node_compare(a, b) ? LOCAL_DISTANCE : - REMOTE_DISTANCE; - index = acpi_slit->locality_count * node_to_pxm(a); - return acpi_slit->entry[index + node_to_pxm(b)]; -} - -EXPORT_SYMBOL(__node_distance); - #if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) || defined(CONFIG_ACPI_HOTPLUG_MEMORY) int memory_add_physaddr_to_nid(u64 start) { diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 6acc724d5d8..d6c0418c3e4 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -179,12 +179,8 @@ static void flush_tlb_others_ipi(const struct cpumask *cpumask, sender = this_cpu_read(tlb_vector_offset); f = &flush_state[sender]; - /* - * Could avoid this lock when - * num_online_cpus() <= NUM_INVALIDATE_TLB_VECTORS, but it is - * probably not worth checking this for a cache-hot lock. - */ - raw_spin_lock(&f->tlbstate_lock); + if (nr_cpu_ids > NUM_INVALIDATE_TLB_VECTORS) + raw_spin_lock(&f->tlbstate_lock); f->flush_mm = mm; f->flush_va = va; @@ -202,7 +198,8 @@ static void flush_tlb_others_ipi(const struct cpumask *cpumask, f->flush_mm = NULL; f->flush_va = 0; - raw_spin_unlock(&f->tlbstate_lock); + if (nr_cpu_ids > NUM_INVALIDATE_TLB_VECTORS) + raw_spin_unlock(&f->tlbstate_lock); } void native_flush_tlb_others(const struct cpumask *cpumask, @@ -211,11 +208,10 @@ void native_flush_tlb_others(const struct cpumask *cpumask, if (is_uv_system()) { unsigned int cpu; - cpu = get_cpu(); + cpu = smp_processor_id(); cpumask = uv_flush_tlb_others(cpumask, mm, va, cpu); if (cpumask) flush_tlb_others_ipi(cpumask, mm, va); - put_cpu(); return; } flush_tlb_others_ipi(cpumask, mm, va); diff --git a/arch/x86/oprofile/backtrace.c b/arch/x86/oprofile/backtrace.c index 72cbec14d78..2d49d4e19a3 100644 --- a/arch/x86/oprofile/backtrace.c +++ b/arch/x86/oprofile/backtrace.c @@ -126,7 +126,7 @@ x86_backtrace(struct pt_regs * const regs, unsigned int depth) if (!user_mode_vm(regs)) { unsigned long stack = kernel_stack_pointer(regs); if (depth) - dump_trace(NULL, regs, (unsigned long *)stack, + dump_trace(NULL, regs, (unsigned long *)stack, 0, &backtrace_ops, &depth); return; } diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index e2b7b0c06cd..cf9750004a0 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -15,7 +15,7 @@ #include <linux/notifier.h> #include <linux/smp.h> #include <linux/oprofile.h> -#include <linux/sysdev.h> +#include <linux/syscore_ops.h> #include <linux/slab.h> #include <linux/moduleparam.h> #include <linux/kdebug.h> @@ -49,6 +49,10 @@ u64 op_x86_get_ctrl(struct op_x86_model_spec const *model, val |= counter_config->user ? ARCH_PERFMON_EVENTSEL_USR : 0; val |= counter_config->kernel ? ARCH_PERFMON_EVENTSEL_OS : 0; val |= (counter_config->unit_mask & 0xFF) << 8; + counter_config->extra &= (ARCH_PERFMON_EVENTSEL_INV | + ARCH_PERFMON_EVENTSEL_EDGE | + ARCH_PERFMON_EVENTSEL_CMASK); + val |= counter_config->extra; event &= model->event_mask ? model->event_mask : 0xFF; val |= event & 0xFF; val |= (event & 0x0F00) << 24; @@ -440,6 +444,7 @@ static int nmi_create_files(struct super_block *sb, struct dentry *root) oprofilefs_create_ulong(sb, dir, "unit_mask", &counter_config[i].unit_mask); oprofilefs_create_ulong(sb, dir, "kernel", &counter_config[i].kernel); oprofilefs_create_ulong(sb, dir, "user", &counter_config[i].user); + oprofilefs_create_ulong(sb, dir, "extra", &counter_config[i].extra); } return 0; @@ -536,7 +541,7 @@ static void nmi_shutdown(void) #ifdef CONFIG_PM -static int nmi_suspend(struct sys_device *dev, pm_message_t state) +static int nmi_suspend(void) { /* Only one CPU left, just stop that one */ if (nmi_enabled == 1) @@ -544,49 +549,31 @@ static int nmi_suspend(struct sys_device *dev, pm_message_t state) return 0; } -static int nmi_resume(struct sys_device *dev) +static void nmi_resume(void) { if (nmi_enabled == 1) nmi_cpu_start(NULL); - return 0; } -static struct sysdev_class oprofile_sysclass = { - .name = "oprofile", +static struct syscore_ops oprofile_syscore_ops = { .resume = nmi_resume, .suspend = nmi_suspend, }; -static struct sys_device device_oprofile = { - .id = 0, - .cls = &oprofile_sysclass, -}; - -static int __init init_sysfs(void) +static void __init init_suspend_resume(void) { - int error; - - error = sysdev_class_register(&oprofile_sysclass); - if (error) - return error; - - error = sysdev_register(&device_oprofile); - if (error) - sysdev_class_unregister(&oprofile_sysclass); - - return error; + register_syscore_ops(&oprofile_syscore_ops); } -static void exit_sysfs(void) +static void exit_suspend_resume(void) { - sysdev_unregister(&device_oprofile); - sysdev_class_unregister(&oprofile_sysclass); + unregister_syscore_ops(&oprofile_syscore_ops); } #else -static inline int init_sysfs(void) { return 0; } -static inline void exit_sysfs(void) { } +static inline void init_suspend_resume(void) { } +static inline void exit_suspend_resume(void) { } #endif /* CONFIG_PM */ @@ -789,9 +776,7 @@ int __init op_nmi_init(struct oprofile_operations *ops) mux_init(ops); - ret = init_sysfs(); - if (ret) - return ret; + init_suspend_resume(); printk(KERN_INFO "oprofile: using NMI interrupt.\n"); return 0; @@ -799,5 +784,5 @@ int __init op_nmi_init(struct oprofile_operations *ops) void op_nmi_exit(void) { - exit_sysfs(); + exit_suspend_resume(); } diff --git a/arch/x86/oprofile/op_counter.h b/arch/x86/oprofile/op_counter.h index e28398df0df..0b7b7b179cb 100644 --- a/arch/x86/oprofile/op_counter.h +++ b/arch/x86/oprofile/op_counter.h @@ -22,6 +22,7 @@ struct op_counter_config { unsigned long kernel; unsigned long user; unsigned long unit_mask; + unsigned long extra; }; extern struct op_counter_config counter_config[]; diff --git a/arch/x86/oprofile/op_model_p4.c b/arch/x86/oprofile/op_model_p4.c index 9fadec07414..98ab13058f8 100644 --- a/arch/x86/oprofile/op_model_p4.c +++ b/arch/x86/oprofile/op_model_p4.c @@ -50,7 +50,7 @@ static inline void setup_num_counters(void) #endif } -static int inline addr_increment(void) +static inline int addr_increment(void) { #ifdef CONFIG_SMP return smp_num_siblings == 2 ? 2 : 1; diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c index e27dffbbb1a..026e4931d16 100644 --- a/arch/x86/pci/amd_bus.c +++ b/arch/x86/pci/amd_bus.c @@ -350,7 +350,7 @@ static int __init early_fill_mp_bus_info(void) #define ENABLE_CF8_EXT_CFG (1ULL << 46) -static void enable_pci_io_ecs(void *unused) +static void __cpuinit enable_pci_io_ecs(void *unused) { u64 reg; rdmsrl(MSR_AMD64_NB_CFG, reg); diff --git a/arch/x86/pci/ce4100.c b/arch/x86/pci/ce4100.c index 85b68ef5e80..67858be4b52 100644 --- a/arch/x86/pci/ce4100.c +++ b/arch/x86/pci/ce4100.c @@ -34,6 +34,7 @@ #include <linux/pci.h> #include <linux/init.h> +#include <asm/ce4100.h> #include <asm/pci_x86.h> struct sim_reg { @@ -254,7 +255,7 @@ int bridge_read(unsigned int devfn, int reg, int len, u32 *value) static int ce4100_conf_read(unsigned int seg, unsigned int bus, unsigned int devfn, int reg, int len, u32 *value) { - int i, retval = 1; + int i; if (bus == 1) { for (i = 0; i < ARRAY_SIZE(bus1_fixups); i++) { @@ -306,10 +307,10 @@ struct pci_raw_ops ce4100_pci_conf = { .write = ce4100_conf_write, }; -static int __init ce4100_pci_init(void) +int __init ce4100_pci_init(void) { init_sim_regs(); raw_pci_ops = &ce4100_pci_conf; - return 0; + /* Indicate caller that it should invoke pci_legacy_init() */ + return 1; } -subsys_initcall(ce4100_pci_init); diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index b1805b78842..494f2e7ea2b 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -241,7 +241,7 @@ void __init pcibios_resource_survey(void) e820_reserve_resources_late(); /* * Insert the IO APIC resources after PCI initialization has - * occured to handle IO APICS that are mapped in on a BAR in + * occurred to handle IO APICS that are mapped in on a BAR in * PCI space, but before trying to assign unassigned pci res. */ ioapic_insert_resources(); @@ -304,7 +304,7 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, /* * ioremap() and ioremap_nocache() defaults to UC MINUS for now. * To avoid attribute conflicts, request UC MINUS here - * aswell. + * as well. */ prot |= _PAGE_CACHE_UC_MINUS; diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index 87e6c832311..8201165bae2 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -597,21 +597,18 @@ static __init int intel_router_probe(struct irq_router *r, struct pci_dev *route return 1; } - if ((device >= PCI_DEVICE_ID_INTEL_5_3400_SERIES_LPC_MIN) && - (device <= PCI_DEVICE_ID_INTEL_5_3400_SERIES_LPC_MAX)) { + if ((device >= PCI_DEVICE_ID_INTEL_5_3400_SERIES_LPC_MIN && + device <= PCI_DEVICE_ID_INTEL_5_3400_SERIES_LPC_MAX) + || (device >= PCI_DEVICE_ID_INTEL_COUGARPOINT_LPC_MIN && + device <= PCI_DEVICE_ID_INTEL_COUGARPOINT_LPC_MAX) + || (device >= PCI_DEVICE_ID_INTEL_DH89XXCC_LPC_MIN && + device <= PCI_DEVICE_ID_INTEL_DH89XXCC_LPC_MAX)) { r->name = "PIIX/ICH"; r->get = pirq_piix_get; r->set = pirq_piix_set; return 1; } - if ((device >= PCI_DEVICE_ID_INTEL_COUGARPOINT_LPC_MIN) && - (device <= PCI_DEVICE_ID_INTEL_COUGARPOINT_LPC_MAX)) { - r->name = "PIIX/ICH"; - r->get = pirq_piix_get; - r->set = pirq_piix_set; - return 1; - } return 0; } diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 25cd4a07d09..e37b407a0ee 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -20,7 +20,8 @@ #include <asm/xen/pci.h> #ifdef CONFIG_ACPI -static int xen_hvm_register_pirq(u32 gsi, int triggering) +static int acpi_register_gsi_xen_hvm(struct device *dev, u32 gsi, + int trigger, int polarity) { int rc, irq; struct physdev_map_pirq map_irq; @@ -41,7 +42,7 @@ static int xen_hvm_register_pirq(u32 gsi, int triggering) return -1; } - if (triggering == ACPI_EDGE_SENSITIVE) { + if (trigger == ACPI_EDGE_SENSITIVE) { shareable = 0; name = "ioapic-edge"; } else { @@ -49,18 +50,12 @@ static int xen_hvm_register_pirq(u32 gsi, int triggering) name = "ioapic-level"; } - irq = xen_map_pirq_gsi(map_irq.pirq, gsi, shareable, name); + irq = xen_bind_pirq_gsi_to_irq(gsi, map_irq.pirq, shareable, name); printk(KERN_DEBUG "xen: --> irq=%d, pirq=%d\n", irq, map_irq.pirq); return irq; } - -static int acpi_register_gsi_xen_hvm(struct device *dev, u32 gsi, - int trigger, int polarity) -{ - return xen_hvm_register_pirq(gsi, trigger); -} #endif #if defined(CONFIG_PCI_MSI) @@ -91,7 +86,7 @@ static void xen_msi_compose_msg(struct pci_dev *pdev, unsigned int pirq, static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) { - int irq, pirq, ret = 0; + int irq, pirq; struct msi_desc *msidesc; struct msi_msg msg; @@ -99,39 +94,32 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) __read_msi_msg(msidesc, &msg); pirq = MSI_ADDR_EXT_DEST_ID(msg.address_hi) | ((msg.address_lo >> MSI_ADDR_DEST_ID_SHIFT) & 0xff); - if (xen_irq_from_pirq(pirq) >= 0 && msg.data == XEN_PIRQ_MSI_DATA) { - xen_allocate_pirq_msi((type == PCI_CAP_ID_MSIX) ? - "msi-x" : "msi", &irq, &pirq, XEN_ALLOC_IRQ); - if (irq < 0) + if (msg.data != XEN_PIRQ_MSI_DATA || + xen_irq_from_pirq(pirq) < 0) { + pirq = xen_allocate_pirq_msi(dev, msidesc); + if (pirq < 0) goto error; - ret = set_irq_msi(irq, msidesc); - if (ret < 0) - goto error_while; - printk(KERN_DEBUG "xen: msi already setup: msi --> irq=%d" - " pirq=%d\n", irq, pirq); - return 0; + xen_msi_compose_msg(dev, pirq, &msg); + __write_msi_msg(msidesc, &msg); + dev_dbg(&dev->dev, "xen: msi bound to pirq=%d\n", pirq); + } else { + dev_dbg(&dev->dev, + "xen: msi already bound to pirq=%d\n", pirq); } - xen_allocate_pirq_msi((type == PCI_CAP_ID_MSIX) ? - "msi-x" : "msi", &irq, &pirq, (XEN_ALLOC_IRQ | XEN_ALLOC_PIRQ)); - if (irq < 0 || pirq < 0) + irq = xen_bind_pirq_msi_to_irq(dev, msidesc, pirq, 0, + (type == PCI_CAP_ID_MSIX) ? + "msi-x" : "msi"); + if (irq < 0) goto error; - printk(KERN_DEBUG "xen: msi --> irq=%d, pirq=%d\n", irq, pirq); - xen_msi_compose_msg(dev, pirq, &msg); - ret = set_irq_msi(irq, msidesc); - if (ret < 0) - goto error_while; - write_msi_msg(irq, &msg); + dev_dbg(&dev->dev, + "xen: msi --> pirq=%d --> irq=%d\n", pirq, irq); } return 0; -error_while: - unbind_from_irqhandler(irq, NULL); error: - if (ret == -ENODEV) - dev_err(&dev->dev, "Xen PCI frontend has not registered" \ - " MSI/MSI-X support!\n"); - - return ret; + dev_err(&dev->dev, + "Xen PCI frontend has not registered MSI/MSI-X support!\n"); + return -ENODEV; } /* @@ -150,35 +138,26 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) return -ENOMEM; if (type == PCI_CAP_ID_MSIX) - ret = xen_pci_frontend_enable_msix(dev, &v, nvec); + ret = xen_pci_frontend_enable_msix(dev, v, nvec); else - ret = xen_pci_frontend_enable_msi(dev, &v); + ret = xen_pci_frontend_enable_msi(dev, v); if (ret) goto error; i = 0; list_for_each_entry(msidesc, &dev->msi_list, list) { - irq = xen_allocate_pirq(v[i], 0, /* not sharable */ - (type == PCI_CAP_ID_MSIX) ? - "pcifront-msi-x" : "pcifront-msi"); - if (irq < 0) { - ret = -1; + irq = xen_bind_pirq_msi_to_irq(dev, msidesc, v[i], 0, + (type == PCI_CAP_ID_MSIX) ? + "pcifront-msi-x" : + "pcifront-msi"); + if (irq < 0) goto free; - } - - ret = set_irq_msi(irq, msidesc); - if (ret) - goto error_while; i++; } kfree(v); return 0; -error_while: - unbind_from_irqhandler(irq, NULL); error: - if (ret == -ENODEV) - dev_err(&dev->dev, "Xen PCI frontend has not registered" \ - " MSI/MSI-X support!\n"); + dev_err(&dev->dev, "Xen PCI frontend has not registered MSI/MSI-X support!\n"); free: kfree(v); return ret; @@ -193,6 +172,9 @@ static void xen_teardown_msi_irqs(struct pci_dev *dev) xen_pci_frontend_disable_msix(dev); else xen_pci_frontend_disable_msi(dev); + + /* Free the IRQ's and the msidesc using the generic code. */ + default_teardown_msi_irqs(dev); } static void xen_teardown_msi_irq(unsigned int irq) @@ -200,47 +182,91 @@ static void xen_teardown_msi_irq(unsigned int irq) xen_destroy_irq(irq); } +#ifdef CONFIG_XEN_DOM0 static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) { - int irq, ret; + int ret = 0; struct msi_desc *msidesc; list_for_each_entry(msidesc, &dev->msi_list, list) { - irq = xen_create_msi_irq(dev, msidesc, type); - if (irq < 0) - return -1; + struct physdev_map_pirq map_irq; - ret = set_irq_msi(irq, msidesc); - if (ret) - goto error; - } - return 0; + memset(&map_irq, 0, sizeof(map_irq)); + map_irq.domid = DOMID_SELF; + map_irq.type = MAP_PIRQ_TYPE_MSI; + map_irq.index = -1; + map_irq.pirq = -1; + map_irq.bus = dev->bus->number; + map_irq.devfn = dev->devfn; -error: - xen_destroy_irq(irq); + if (type == PCI_CAP_ID_MSIX) { + int pos; + u32 table_offset, bir; + + pos = pci_find_capability(dev, PCI_CAP_ID_MSIX); + + pci_read_config_dword(dev, pos + PCI_MSIX_TABLE, + &table_offset); + bir = (u8)(table_offset & PCI_MSIX_FLAGS_BIRMASK); + + map_irq.table_base = pci_resource_start(dev, bir); + map_irq.entry_nr = msidesc->msi_attrib.entry_nr; + } + + ret = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, &map_irq); + if (ret) { + dev_warn(&dev->dev, "xen map irq failed %d\n", ret); + goto out; + } + + ret = xen_bind_pirq_msi_to_irq(dev, msidesc, + map_irq.pirq, map_irq.index, + (type == PCI_CAP_ID_MSIX) ? + "msi-x" : "msi"); + if (ret < 0) + goto out; + } + ret = 0; +out: return ret; } #endif +#endif static int xen_pcifront_enable_irq(struct pci_dev *dev) { int rc; int share = 1; + int pirq; + u8 gsi; - dev_info(&dev->dev, "Xen PCI enabling IRQ: %d\n", dev->irq); + rc = pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &gsi); + if (rc < 0) { + dev_warn(&dev->dev, "Xen PCI: failed to read interrupt line: %d\n", + rc); + return rc; + } - if (dev->irq < 0) - return -EINVAL; + rc = xen_allocate_pirq_gsi(gsi); + if (rc < 0) { + dev_warn(&dev->dev, "Xen PCI: failed to allocate a PIRQ for GSI%d: %d\n", + gsi, rc); + return rc; + } + pirq = rc; - if (dev->irq < NR_IRQS_LEGACY) + if (gsi < NR_IRQS_LEGACY) share = 0; - rc = xen_allocate_pirq(dev->irq, share, "pcifront"); + rc = xen_bind_pirq_gsi_to_irq(gsi, pirq, share, "pcifront"); if (rc < 0) { - dev_warn(&dev->dev, "Xen PCI IRQ: %d, failed to register:%d\n", - dev->irq, rc); + dev_warn(&dev->dev, "Xen PCI: failed to bind GSI%d (PIRQ%d) to IRQ: %d\n", + gsi, pirq, rc); return rc; } + + dev->irq = rc; + dev_info(&dev->dev, "Xen PCI mapped GSI%d to IRQ%d\n", gsi, dev->irq); return 0; } @@ -292,7 +318,7 @@ int __init pci_xen_hvm_init(void) #ifdef CONFIG_XEN_DOM0 static int xen_register_pirq(u32 gsi, int triggering) { - int rc, irq; + int rc, pirq, irq = -1; struct physdev_map_pirq map_irq; int shareable = 0; char *name; @@ -308,17 +334,20 @@ static int xen_register_pirq(u32 gsi, int triggering) name = "ioapic-level"; } - irq = xen_allocate_pirq(gsi, shareable, name); - - printk(KERN_DEBUG "xen: --> irq=%d\n", irq); + pirq = xen_allocate_pirq_gsi(gsi); + if (pirq < 0) + goto out; + irq = xen_bind_pirq_gsi_to_irq(gsi, pirq, shareable, name); if (irq < 0) goto out; + printk(KERN_DEBUG "xen: --> pirq=%d -> irq=%d\n", pirq, irq); + map_irq.domid = DOMID_SELF; map_irq.type = MAP_PIRQ_TYPE_GSI; map_irq.index = gsi; - map_irq.pirq = irq; + map_irq.pirq = pirq; rc = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, &map_irq); if (rc) { @@ -405,13 +434,18 @@ static int __init pci_xen_initial_domain(void) void __init xen_setup_pirqs(void) { - int irq; + int pirq, irq; pci_xen_initial_domain(); if (0 == nr_ioapics) { - for (irq = 0; irq < NR_IRQS_LEGACY; irq++) - xen_allocate_pirq(irq, 0, "xt-pic"); + for (irq = 0; irq < NR_IRQS_LEGACY; irq++) { + pirq = xen_allocate_pirq_gsi(irq); + if (WARN(pirq < 0, + "Could not allocate PIRQ for legacy interrupt\n")) + break; + irq = xen_bind_pirq_gsi_to_irq(irq, pirq, 0, "xt-pic"); + } return; } diff --git a/arch/x86/platform/ce4100/ce4100.c b/arch/x86/platform/ce4100/ce4100.c index d2c0d51a717..28071bb31db 100644 --- a/arch/x86/platform/ce4100/ce4100.c +++ b/arch/x86/platform/ce4100/ce4100.c @@ -15,21 +15,20 @@ #include <linux/serial_reg.h> #include <linux/serial_8250.h> +#include <asm/ce4100.h> +#include <asm/prom.h> #include <asm/setup.h> +#include <asm/i8259.h> #include <asm/io.h> +#include <asm/io_apic.h> static int ce4100_i8042_detect(void) { return 0; } -static void __init sdv_find_smp_config(void) -{ -} - #ifdef CONFIG_SERIAL_8250 - static unsigned int mem_serial_in(struct uart_port *p, int offset) { offset = offset << p->regshift; @@ -118,6 +117,15 @@ static void __init sdv_arch_setup(void) sdv_serial_fixup(); } +#ifdef CONFIG_X86_IO_APIC +static void __cpuinit sdv_pci_init(void) +{ + x86_of_pci_init(); + /* We can't set this earlier, because we need to calibrate the timer */ + legacy_pic = &null_legacy_pic; +} +#endif + /* * CE4100 specific x86_init function overrides and early setup * calls. @@ -128,5 +136,11 @@ void __init x86_ce4100_early_setup(void) x86_platform.i8042_detect = ce4100_i8042_detect; x86_init.resources.probe_roms = x86_init_noop; x86_init.mpparse.get_smp_config = x86_init_uint_noop; - x86_init.mpparse.find_smp_config = sdv_find_smp_config; + x86_init.mpparse.find_smp_config = x86_init_noop; + x86_init.pci.init = ce4100_pci_init; + +#ifdef CONFIG_X86_IO_APIC + x86_init.pci.init_irq = sdv_pci_init; + x86_init.mpparse.setup_ioapic_ids = setup_ioapic_ids_from_mpc_nocheck; +#endif } diff --git a/arch/x86/platform/ce4100/falconfalls.dts b/arch/x86/platform/ce4100/falconfalls.dts new file mode 100644 index 00000000000..e70be38ce03 --- /dev/null +++ b/arch/x86/platform/ce4100/falconfalls.dts @@ -0,0 +1,430 @@ +/* + * CE4100 on Falcon Falls + * + * (c) Copyright 2010 Intel Corporation + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; version 2 of the License. + */ +/dts-v1/; +/ { + model = "intel,falconfalls"; + compatible = "intel,falconfalls"; + #address-cells = <1>; + #size-cells = <1>; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu@0 { + device_type = "cpu"; + compatible = "intel,ce4100"; + reg = <0>; + lapic = <&lapic0>; + }; + }; + + soc@0 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "intel,ce4100-cp"; + ranges; + + ioapic1: interrupt-controller@fec00000 { + #interrupt-cells = <2>; + compatible = "intel,ce4100-ioapic"; + interrupt-controller; + reg = <0xfec00000 0x1000>; + }; + + timer@fed00000 { + compatible = "intel,ce4100-hpet"; + reg = <0xfed00000 0x200>; + }; + + lapic0: interrupt-controller@fee00000 { + compatible = "intel,ce4100-lapic"; + reg = <0xfee00000 0x1000>; + }; + + pci@3fc { + #address-cells = <3>; + #size-cells = <2>; + compatible = "intel,ce4100-pci", "pci"; + device_type = "pci"; + bus-range = <0 0>; + ranges = <0x2000000 0 0xbffff000 0xbffff000 0 0x1000 + 0x2000000 0 0xdffe0000 0xdffe0000 0 0x1000 + 0x0000000 0 0x0 0x0 0 0x100>; + + /* Secondary IO-APIC */ + ioapic2: interrupt-controller@0,1 { + #interrupt-cells = <2>; + compatible = "intel,ce4100-ioapic"; + interrupt-controller; + reg = <0x100 0x0 0x0 0x0 0x0>; + assigned-addresses = <0x02000000 0x0 0xbffff000 0x0 0x1000>; + }; + + pci@1,0 { + #address-cells = <3>; + #size-cells = <2>; + compatible = "intel,ce4100-pci", "pci"; + device_type = "pci"; + bus-range = <1 1>; + reg = <0x0800 0x0 0x0 0x0 0x0>; + ranges = <0x2000000 0 0xdffe0000 0x2000000 0 0xdffe0000 0 0x1000>; + + interrupt-parent = <&ioapic2>; + + display@2,0 { + compatible = "pci8086,2e5b.2", + "pci8086,2e5b", + "pciclass038000", + "pciclass0380"; + + reg = <0x11000 0x0 0x0 0x0 0x0>; + interrupts = <0 1>; + }; + + multimedia@3,0 { + compatible = "pci8086,2e5c.2", + "pci8086,2e5c", + "pciclass048000", + "pciclass0480"; + + reg = <0x11800 0x0 0x0 0x0 0x0>; + interrupts = <2 1>; + }; + + multimedia@4,0 { + compatible = "pci8086,2e5d.2", + "pci8086,2e5d", + "pciclass048000", + "pciclass0480"; + + reg = <0x12000 0x0 0x0 0x0 0x0>; + interrupts = <4 1>; + }; + + multimedia@4,1 { + compatible = "pci8086,2e5e.2", + "pci8086,2e5e", + "pciclass048000", + "pciclass0480"; + + reg = <0x12100 0x0 0x0 0x0 0x0>; + interrupts = <5 1>; + }; + + sound@6,0 { + compatible = "pci8086,2e5f.2", + "pci8086,2e5f", + "pciclass040100", + "pciclass0401"; + + reg = <0x13000 0x0 0x0 0x0 0x0>; + interrupts = <6 1>; + }; + + sound@6,1 { + compatible = "pci8086,2e5f.2", + "pci8086,2e5f", + "pciclass040100", + "pciclass0401"; + + reg = <0x13100 0x0 0x0 0x0 0x0>; + interrupts = <7 1>; + }; + + sound@6,2 { + compatible = "pci8086,2e60.2", + "pci8086,2e60", + "pciclass040100", + "pciclass0401"; + + reg = <0x13200 0x0 0x0 0x0 0x0>; + interrupts = <8 1>; + }; + + display@8,0 { + compatible = "pci8086,2e61.2", + "pci8086,2e61", + "pciclass038000", + "pciclass0380"; + + reg = <0x14000 0x0 0x0 0x0 0x0>; + interrupts = <9 1>; + }; + + display@8,1 { + compatible = "pci8086,2e62.2", + "pci8086,2e62", + "pciclass038000", + "pciclass0380"; + + reg = <0x14100 0x0 0x0 0x0 0x0>; + interrupts = <10 1>; + }; + + multimedia@8,2 { + compatible = "pci8086,2e63.2", + "pci8086,2e63", + "pciclass048000", + "pciclass0480"; + + reg = <0x14200 0x0 0x0 0x0 0x0>; + interrupts = <11 1>; + }; + + entertainment-encryption@9,0 { + compatible = "pci8086,2e64.2", + "pci8086,2e64", + "pciclass101000", + "pciclass1010"; + + reg = <0x14800 0x0 0x0 0x0 0x0>; + interrupts = <12 1>; + }; + + localbus@a,0 { + compatible = "pci8086,2e65.2", + "pci8086,2e65", + "pciclassff0000", + "pciclassff00"; + + reg = <0x15000 0x0 0x0 0x0 0x0>; + }; + + serial@b,0 { + compatible = "pci8086,2e66.2", + "pci8086,2e66", + "pciclass070003", + "pciclass0700"; + + reg = <0x15800 0x0 0x0 0x0 0x0>; + interrupts = <14 1>; + }; + + gpio@b,1 { + compatible = "pci8086,2e67.2", + "pci8086,2e67", + "pciclassff0000", + "pciclassff00"; + + #gpio-cells = <2>; + reg = <0x15900 0x0 0x0 0x0 0x0>; + interrupts = <15 1>; + gpio-controller; + }; + + i2c-controller@b,2 { + #address-cells = <2>; + #size-cells = <1>; + compatible = "pci8086,2e68.2", + "pci8086,2e68", + "pciclass,ff0000", + "pciclass,ff00"; + + reg = <0x15a00 0x0 0x0 0x0 0x0>; + interrupts = <16 1>; + ranges = <0 0 0x02000000 0 0xdffe0500 0x100 + 1 0 0x02000000 0 0xdffe0600 0x100 + 2 0 0x02000000 0 0xdffe0700 0x100>; + + i2c@0 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "intel,ce4100-i2c-controller"; + reg = <0 0 0x100>; + }; + + i2c@1 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "intel,ce4100-i2c-controller"; + reg = <1 0 0x100>; + + gpio@26 { + #gpio-cells = <2>; + compatible = "ti,pcf8575"; + reg = <0x26>; + gpio-controller; + }; + }; + + i2c@2 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "intel,ce4100-i2c-controller"; + reg = <2 0 0x100>; + + gpio@26 { + #gpio-cells = <2>; + compatible = "ti,pcf8575"; + reg = <0x26>; + gpio-controller; + }; + }; + }; + + smard-card@b,3 { + compatible = "pci8086,2e69.2", + "pci8086,2e69", + "pciclass070500", + "pciclass0705"; + + reg = <0x15b00 0x0 0x0 0x0 0x0>; + interrupts = <15 1>; + }; + + spi-controller@b,4 { + #address-cells = <1>; + #size-cells = <0>; + compatible = + "pci8086,2e6a.2", + "pci8086,2e6a", + "pciclass,ff0000", + "pciclass,ff00"; + + reg = <0x15c00 0x0 0x0 0x0 0x0>; + interrupts = <15 1>; + + dac@0 { + compatible = "ti,pcm1755"; + reg = <0>; + spi-max-frequency = <115200>; + }; + + dac@1 { + compatible = "ti,pcm1609a"; + reg = <1>; + spi-max-frequency = <115200>; + }; + + eeprom@2 { + compatible = "atmel,at93c46"; + reg = <2>; + spi-max-frequency = <115200>; + }; + }; + + multimedia@b,7 { + compatible = "pci8086,2e6d.2", + "pci8086,2e6d", + "pciclassff0000", + "pciclassff00"; + + reg = <0x15f00 0x0 0x0 0x0 0x0>; + }; + + ethernet@c,0 { + compatible = "pci8086,2e6e.2", + "pci8086,2e6e", + "pciclass020000", + "pciclass0200"; + + reg = <0x16000 0x0 0x0 0x0 0x0>; + interrupts = <21 1>; + }; + + clock@c,1 { + compatible = "pci8086,2e6f.2", + "pci8086,2e6f", + "pciclassff0000", + "pciclassff00"; + + reg = <0x16100 0x0 0x0 0x0 0x0>; + interrupts = <3 1>; + }; + + usb@d,0 { + compatible = "pci8086,2e70.2", + "pci8086,2e70", + "pciclass0c0320", + "pciclass0c03"; + + reg = <0x16800 0x0 0x0 0x0 0x0>; + interrupts = <22 1>; + }; + + usb@d,1 { + compatible = "pci8086,2e70.2", + "pci8086,2e70", + "pciclass0c0320", + "pciclass0c03"; + + reg = <0x16900 0x0 0x0 0x0 0x0>; + interrupts = <22 1>; + }; + + sata@e,0 { + compatible = "pci8086,2e71.0", + "pci8086,2e71", + "pciclass010601", + "pciclass0106"; + + reg = <0x17000 0x0 0x0 0x0 0x0>; + interrupts = <23 1>; + }; + + flash@f,0 { + compatible = "pci8086,701.1", + "pci8086,701", + "pciclass050100", + "pciclass0501"; + + reg = <0x17800 0x0 0x0 0x0 0x0>; + interrupts = <13 1>; + }; + + entertainment-encryption@10,0 { + compatible = "pci8086,702.1", + "pci8086,702", + "pciclass101000", + "pciclass1010"; + + reg = <0x18000 0x0 0x0 0x0 0x0>; + }; + + co-processor@11,0 { + compatible = "pci8086,703.1", + "pci8086,703", + "pciclass0b4000", + "pciclass0b40"; + + reg = <0x18800 0x0 0x0 0x0 0x0>; + interrupts = <1 1>; + }; + + multimedia@12,0 { + compatible = "pci8086,704.0", + "pci8086,704", + "pciclass048000", + "pciclass0480"; + + reg = <0x19000 0x0 0x0 0x0 0x0>; + }; + }; + + isa@1f,0 { + #address-cells = <2>; + #size-cells = <1>; + compatible = "isa"; + reg = <0xf800 0x0 0x0 0x0 0x0>; + ranges = <1 0 0 0 0 0x100>; + + rtc@70 { + compatible = "intel,ce4100-rtc", "motorola,mc146818"; + interrupts = <8 3>; + interrupt-parent = <&ioapic1>; + ctrl-reg = <2>; + freq-reg = <0x26>; + reg = <1 0x70 2>; + }; + }; + }; + }; +}; diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c index ea6529e93c6..275dbc19e2c 100644 --- a/arch/x86/platform/mrst/mrst.c +++ b/arch/x86/platform/mrst/mrst.c @@ -31,6 +31,7 @@ #include <asm/apic.h> #include <asm/io_apic.h> #include <asm/mrst.h> +#include <asm/mrst-vrtc.h> #include <asm/io.h> #include <asm/i8259.h> #include <asm/intel_scu_ipc.h> @@ -96,11 +97,11 @@ static int __init sfi_parse_mtmr(struct sfi_table_header *table) pentry->freq_hz, pentry->irq); if (!pentry->irq) continue; - mp_irq.type = MP_IOAPIC; + mp_irq.type = MP_INTSRC; mp_irq.irqtype = mp_INT; /* triggering mode edge bit 2-3, active high polarity bit 0-1 */ mp_irq.irqflag = 5; - mp_irq.srcbus = 0; + mp_irq.srcbus = MP_BUS_ISA; mp_irq.srcbusirq = pentry->irq; /* IRQ */ mp_irq.dstapic = MP_APIC_ALL; mp_irq.dstirq = pentry->irq; @@ -167,10 +168,10 @@ int __init sfi_parse_mrtc(struct sfi_table_header *table) for (totallen = 0; totallen < sfi_mrtc_num; totallen++, pentry++) { pr_debug("RTC[%d]: paddr = 0x%08x, irq = %d\n", totallen, (u32)pentry->phys_addr, pentry->irq); - mp_irq.type = MP_IOAPIC; + mp_irq.type = MP_INTSRC; mp_irq.irqtype = mp_INT; mp_irq.irqflag = 0xf; /* level trigger and active low */ - mp_irq.srcbus = 0; + mp_irq.srcbus = MP_BUS_ISA; mp_irq.srcbusirq = pentry->irq; /* IRQ */ mp_irq.dstapic = MP_APIC_ALL; mp_irq.dstirq = pentry->irq; @@ -268,6 +269,7 @@ void __init x86_mrst_early_setup(void) x86_platform.calibrate_tsc = mrst_calibrate_tsc; x86_platform.i8042_detect = mrst_i8042_detect; + x86_init.timers.wallclock_init = mrst_rtc_init; x86_init.pci.init = pci_mrst_init; x86_init.pci.fixup_irqs = x86_init_noop; @@ -280,7 +282,7 @@ void __init x86_mrst_early_setup(void) /* Avoid searching for BIOS MP tables */ x86_init.mpparse.find_smp_config = x86_init_noop; x86_init.mpparse.get_smp_config = x86_init_uint_noop; - + set_bit(MP_BUS_ISA, mp_bus_not_pci); } /* diff --git a/arch/x86/platform/mrst/vrtc.c b/arch/x86/platform/mrst/vrtc.c index 32cd7edd71a..73d70d65e76 100644 --- a/arch/x86/platform/mrst/vrtc.c +++ b/arch/x86/platform/mrst/vrtc.c @@ -100,22 +100,16 @@ int vrtc_set_mmss(unsigned long nowtime) void __init mrst_rtc_init(void) { - unsigned long rtc_paddr; - void __iomem *virt_base; + unsigned long vrtc_paddr; sfi_table_parse(SFI_SIG_MRTC, NULL, NULL, sfi_parse_mrtc); - if (!sfi_mrtc_num) - return; - - rtc_paddr = sfi_mrtc_array[0].phys_addr; - /* vRTC's register address may not be page aligned */ - set_fixmap_nocache(FIX_LNW_VRTC, rtc_paddr); - - virt_base = (void __iomem *)__fix_to_virt(FIX_LNW_VRTC); - virt_base += rtc_paddr & ~PAGE_MASK; - vrtc_virt_base = virt_base; + vrtc_paddr = sfi_mrtc_array[0].phys_addr; + if (!sfi_mrtc_num || !vrtc_paddr) + return; + vrtc_virt_base = (void __iomem *)set_fixmap_offset_nocache(FIX_LNW_VRTC, + vrtc_paddr); x86_platform.get_wallclock = vrtc_get_time; x86_platform.set_wallclock = vrtc_set_mmss; } diff --git a/arch/x86/platform/olpc/Makefile b/arch/x86/platform/olpc/Makefile index e797428b163..c2a8cab65e5 100644 --- a/arch/x86/platform/olpc/Makefile +++ b/arch/x86/platform/olpc/Makefile @@ -1,4 +1,4 @@ obj-$(CONFIG_OLPC) += olpc.o obj-$(CONFIG_OLPC_XO1) += olpc-xo1.o -obj-$(CONFIG_OLPC_OPENFIRMWARE) += olpc_ofw.o -obj-$(CONFIG_OLPC_OPENFIRMWARE_DT) += olpc_dt.o +obj-$(CONFIG_OLPC) += olpc_ofw.o +obj-$(CONFIG_OF_PROMTREE) += olpc_dt.o diff --git a/arch/x86/platform/olpc/olpc-xo1.c b/arch/x86/platform/olpc/olpc-xo1.c index 127775696d6..ab81fb27176 100644 --- a/arch/x86/platform/olpc/olpc-xo1.c +++ b/arch/x86/platform/olpc/olpc-xo1.c @@ -15,6 +15,7 @@ #include <linux/module.h> #include <linux/platform_device.h> #include <linux/pm.h> +#include <linux/mfd/core.h> #include <asm/io.h> #include <asm/olpc.h> @@ -56,25 +57,24 @@ static void xo1_power_off(void) static int __devinit olpc_xo1_probe(struct platform_device *pdev) { struct resource *res; + int err; /* don't run on non-XOs */ if (!machine_is_olpc()) return -ENODEV; + err = mfd_cell_enable(pdev); + if (err) + return err; + res = platform_get_resource(pdev, IORESOURCE_IO, 0); if (!res) { dev_err(&pdev->dev, "can't fetch device resource info\n"); return -EIO; } - - if (!request_region(res->start, resource_size(res), DRV_NAME)) { - dev_err(&pdev->dev, "can't request region\n"); - return -EIO; - } - if (strcmp(pdev->name, "cs5535-pms") == 0) pms_base = res->start; - else if (strcmp(pdev->name, "cs5535-acpi") == 0) + else if (strcmp(pdev->name, "olpc-xo1-pm-acpi") == 0) acpi_base = res->start; /* If we have both addresses, we can override the poweroff hook */ @@ -88,14 +88,11 @@ static int __devinit olpc_xo1_probe(struct platform_device *pdev) static int __devexit olpc_xo1_remove(struct platform_device *pdev) { - struct resource *r; - - r = platform_get_resource(pdev, IORESOURCE_IO, 0); - release_region(r->start, resource_size(r)); + mfd_cell_disable(pdev); if (strcmp(pdev->name, "cs5535-pms") == 0) pms_base = 0; - else if (strcmp(pdev->name, "cs5535-acpi") == 0) + else if (strcmp(pdev->name, "olpc-xo1-pm-acpi") == 0) acpi_base = 0; pm_power_off = NULL; @@ -113,7 +110,7 @@ static struct platform_driver cs5535_pms_drv = { static struct platform_driver cs5535_acpi_drv = { .driver = { - .name = "cs5535-acpi", + .name = "olpc-xo1-pm-acpi", .owner = THIS_MODULE, }, .probe = olpc_xo1_probe, @@ -143,7 +140,7 @@ static void __exit olpc_xo1_exit(void) MODULE_AUTHOR("Daniel Drake <dsd@laptop.org>"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("platform:olpc-xo1"); +MODULE_ALIAS("platform:cs5535-pms"); module_init(olpc_xo1_init); module_exit(olpc_xo1_exit); diff --git a/arch/x86/platform/olpc/olpc_dt.c b/arch/x86/platform/olpc/olpc_dt.c index dab87464753..044bda5b317 100644 --- a/arch/x86/platform/olpc/olpc_dt.c +++ b/arch/x86/platform/olpc/olpc_dt.c @@ -140,8 +140,7 @@ void * __init prom_early_alloc(unsigned long size) * wasted bootmem) and hand off chunks of it to callers. */ res = alloc_bootmem(chunk_size); - if (!res) - return NULL; + BUG_ON(!res); prom_early_allocated += chunk_size; memset(res, 0, chunk_size); free_mem = chunk_size; diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index df58e9cad96..7cb6424317f 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -11,6 +11,7 @@ #include <linux/debugfs.h> #include <linux/kernel.h> #include <linux/slab.h> +#include <linux/delay.h> #include <asm/mmu_context.h> #include <asm/uv/uv.h> @@ -1364,11 +1365,11 @@ uv_activation_descriptor_init(int node, int pnode) memset(bd2, 0, sizeof(struct bau_desc)); bd2->header.sw_ack_flag = 1; /* - * base_dest_nodeid is the nasid (pnode<<1) of the first uvhub + * base_dest_nodeid is the nasid of the first uvhub * in the partition. The bit map will indicate uvhub numbers, * which are 0-N in a partition. Pnodes are unique system-wide. */ - bd2->header.base_dest_nodeid = uv_partition_base_pnode << 1; + bd2->header.base_dest_nodeid = UV_PNODE_TO_NASID(uv_partition_base_pnode); bd2->header.dest_subnodeid = 0x10; /* the LB */ bd2->header.command = UV_NET_ENDPOINT_INTD; bd2->header.int_both = 1; diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c index 7b24460917d..374a05d8ad2 100644 --- a/arch/x86/platform/uv/uv_irq.c +++ b/arch/x86/platform/uv/uv_irq.c @@ -131,7 +131,7 @@ arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade, unsigned long mmr_offset, int limit) { const struct cpumask *eligible_cpu = cpumask_of(cpu); - struct irq_cfg *cfg = get_irq_chip_data(irq); + struct irq_cfg *cfg = irq_get_chip_data(irq); unsigned long mmr_value; struct uv_IO_APIC_route_entry *entry; int mmr_pnode, err; @@ -148,7 +148,7 @@ arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade, else irq_set_status_flags(irq, IRQ_MOVE_PCNTXT); - set_irq_chip_and_handler_name(irq, &uv_irq_chip, handle_percpu_irq, + irq_set_chip_and_handler_name(irq, &uv_irq_chip, handle_percpu_irq, irq_name); mmr_value = 0; diff --git a/arch/x86/platform/visws/visws_quirks.c b/arch/x86/platform/visws/visws_quirks.c index 63203767174..c7abf13a213 100644 --- a/arch/x86/platform/visws/visws_quirks.c +++ b/arch/x86/platform/visws/visws_quirks.c @@ -471,15 +471,7 @@ static unsigned int startup_piix4_master_irq(struct irq_data *data) { legacy_pic->init(0); enable_cobalt_irq(data); -} - -static void end_piix4_master_irq(struct irq_data *data) -{ - unsigned long flags; - - spin_lock_irqsave(&cobalt_lock, flags); - enable_cobalt_irq(data); - spin_unlock_irqrestore(&cobalt_lock, flags); + return 0; } static struct irq_chip piix4_master_irq_type = { @@ -492,7 +484,7 @@ static void pii4_mask(struct irq_data *data) { } static struct irq_chip piix4_virtual_irq_type = { .name = "PIIX4-virtual", - .mask = pii4_mask, + .irq_mask = pii4_mask, }; /* @@ -569,18 +561,20 @@ out_unlock: static struct irqaction master_action = { .handler = piix4_master_intr, .name = "PIIX4-8259", + .flags = IRQF_NO_THREAD, }; static struct irqaction cascade_action = { .handler = no_action, .name = "cascade", + .flags = IRQF_NO_THREAD, }; static inline void set_piix4_virtual_irq_type(void) { - piix4_virtual_irq_type.enable = i8259A_chip.unmask; - piix4_virtual_irq_type.disable = i8259A_chip.mask; - piix4_virtual_irq_type.unmask = i8259A_chip.unmask; + piix4_virtual_irq_type.irq_enable = i8259A_chip.irq_unmask; + piix4_virtual_irq_type.irq_disable = i8259A_chip.irq_mask; + piix4_virtual_irq_type.irq_unmask = i8259A_chip.irq_unmask; } static void __init visws_pre_intr_init(void) @@ -597,7 +591,7 @@ static void __init visws_pre_intr_init(void) else if (i == CO_IRQ_IDE0) chip = &cobalt_irq_type; else if (i == CO_IRQ_IDE1) - >chip = &cobalt_irq_type; + chip = &cobalt_irq_type; else if (i == CO_IRQ_8259) chip = &piix4_master_irq_type; else if (i < CO_IRQ_APIC0) @@ -606,7 +600,7 @@ static void __init visws_pre_intr_init(void) chip = &cobalt_irq_type; if (chip) - set_irq_chip(i, chip); + irq_set_chip(i, chip); } setup_irq(CO_IRQ_8259, &master_action); diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c index 36df991985b..468d591dde3 100644 --- a/arch/x86/vdso/vdso32-setup.c +++ b/arch/x86/vdso/vdso32-setup.c @@ -417,24 +417,25 @@ const char *arch_vma_name(struct vm_area_struct *vma) return NULL; } -struct vm_area_struct *get_gate_vma(struct task_struct *tsk) +struct vm_area_struct *get_gate_vma(struct mm_struct *mm) { - struct mm_struct *mm = tsk->mm; - - /* Check to see if this task was created in compat vdso mode */ + /* + * Check to see if the corresponding task was created in compat vdso + * mode. + */ if (mm && mm->context.vdso == (void *)VDSO_HIGH_BASE) return &gate_vma; return NULL; } -int in_gate_area(struct task_struct *task, unsigned long addr) +int in_gate_area(struct mm_struct *mm, unsigned long addr) { - const struct vm_area_struct *vma = get_gate_vma(task); + const struct vm_area_struct *vma = get_gate_vma(mm); return vma && addr >= vma->vm_start && addr < vma->vm_end; } -int in_gate_area_no_task(unsigned long addr) +int in_gate_area_no_mm(unsigned long addr) { return 0; } diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index 5b54892e4bc..5cc821cb2e0 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -38,7 +38,8 @@ config XEN_MAX_DOMAIN_MEMORY config XEN_SAVE_RESTORE bool - depends on XEN && PM + depends on XEN + select HIBERNATE_CALLBACKS default y config XEN_DEBUG_FS @@ -48,3 +49,11 @@ config XEN_DEBUG_FS help Enable statistics output and various tuning options in debugfs. Enabling this option may incur a significant performance overhead. + +config XEN_DEBUG + bool "Enable Xen debug checks" + depends on XEN + default n + help + Enable various WARN_ON checks in the Xen MMU code. + Enabling this option WILL incur a significant performance overhead. diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 50542efe45f..e3c6a06cf72 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -238,6 +238,7 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx, static __init void xen_init_cpuid_mask(void) { unsigned int ax, bx, cx, dx; + unsigned int xsave_mask; cpuid_leaf1_edx_mask = ~((1 << X86_FEATURE_MCE) | /* disable MCE */ @@ -249,24 +250,16 @@ static __init void xen_init_cpuid_mask(void) cpuid_leaf1_edx_mask &= ~((1 << X86_FEATURE_APIC) | /* disable local APIC */ (1 << X86_FEATURE_ACPI)); /* disable ACPI */ - ax = 1; - cx = 0; xen_cpuid(&ax, &bx, &cx, &dx); - /* cpuid claims we support xsave; try enabling it to see what happens */ - if (cx & (1 << (X86_FEATURE_XSAVE % 32))) { - unsigned long cr4; - - set_in_cr4(X86_CR4_OSXSAVE); - - cr4 = read_cr4(); - - if ((cr4 & X86_CR4_OSXSAVE) == 0) - cpuid_leaf1_ecx_mask &= ~(1 << (X86_FEATURE_XSAVE % 32)); + xsave_mask = + (1 << (X86_FEATURE_XSAVE % 32)) | + (1 << (X86_FEATURE_OSXSAVE % 32)); - clear_in_cr4(X86_CR4_OSXSAVE); - } + /* Xen will set CR4.OSXSAVE if supported and not disabled by force */ + if ((cx & xsave_mask) != xsave_mask) + cpuid_leaf1_ecx_mask &= ~xsave_mask; /* disable XSAVE & OSXSAVE */ } static void xen_set_debugreg(int reg, unsigned long val) @@ -1284,15 +1277,14 @@ static int init_hvm_pv_info(int *major, int *minor) xen_setup_features(); - pv_info = xen_info; - pv_info.kernel_rpl = 0; + pv_info.name = "Xen HVM"; xen_domain_type = XEN_HVM_DOMAIN; return 0; } -void xen_hvm_init_shared_info(void) +void __ref xen_hvm_init_shared_info(void) { int cpu; struct xen_add_to_physmap xatp; @@ -1331,6 +1323,8 @@ static int __cpuinit xen_hvm_cpu_notify(struct notifier_block *self, switch (action) { case CPU_UP_PREPARE: per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu]; + if (xen_have_vector_callback) + xen_init_lock_cpu(cpu); break; default: break; @@ -1355,6 +1349,7 @@ static void __init xen_hvm_guest_init(void) if (xen_feature(XENFEAT_hvm_callback_vector)) xen_have_vector_callback = 1; + xen_hvm_smp_init(); register_cpu_notifier(&xen_hvm_cpu_notifier); xen_unplug_emulated_devices(); have_vcpu_info_placement = 0; diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 5e92b61ad57..55c965b38c2 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -46,6 +46,7 @@ #include <linux/module.h> #include <linux/gfp.h> #include <linux/memblock.h> +#include <linux/seq_file.h> #include <asm/pgtable.h> #include <asm/tlbflush.h> @@ -78,8 +79,7 @@ /* * Protects atomic reservation decrease/increase against concurrent increases. - * Also protects non-atomic updates of current_pages and driver_pages, and - * balloon lists. + * Also protects non-atomic updates of current_pages and balloon lists. */ DEFINE_SPINLOCK(xen_reservation_lock); @@ -416,8 +416,12 @@ static pteval_t pte_pfn_to_mfn(pteval_t val) if (val & _PAGE_PRESENT) { unsigned long pfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT; pteval_t flags = val & PTE_FLAGS_MASK; - unsigned long mfn = pfn_to_mfn(pfn); + unsigned long mfn; + if (!xen_feature(XENFEAT_auto_translated_physmap)) + mfn = get_phys_to_machine(pfn); + else + mfn = pfn; /* * If there's no mfn for the pfn, then just create an * empty non-present pte. Unfortunately this loses @@ -427,8 +431,18 @@ static pteval_t pte_pfn_to_mfn(pteval_t val) if (unlikely(mfn == INVALID_P2M_ENTRY)) { mfn = 0; flags = 0; + } else { + /* + * Paramount to do this test _after_ the + * INVALID_P2M_ENTRY as INVALID_P2M_ENTRY & + * IDENTITY_FRAME_BIT resolves to true. + */ + mfn &= ~FOREIGN_FRAME_BIT; + if (mfn & IDENTITY_FRAME_BIT) { + mfn &= ~IDENTITY_FRAME_BIT; + flags |= _PAGE_IOMAP; + } } - val = ((pteval_t)mfn << PAGE_SHIFT) | flags; } @@ -532,6 +546,41 @@ pte_t xen_make_pte(pteval_t pte) } PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte); +#ifdef CONFIG_XEN_DEBUG +pte_t xen_make_pte_debug(pteval_t pte) +{ + phys_addr_t addr = (pte & PTE_PFN_MASK); + phys_addr_t other_addr; + bool io_page = false; + pte_t _pte; + + if (pte & _PAGE_IOMAP) + io_page = true; + + _pte = xen_make_pte(pte); + + if (!addr) + return _pte; + + if (io_page && + (xen_initial_domain() || addr >= ISA_END_ADDRESS)) { + other_addr = pfn_to_mfn(addr >> PAGE_SHIFT) << PAGE_SHIFT; + WARN_ONCE(addr != other_addr, + "0x%lx is using VM_IO, but it is 0x%lx!\n", + (unsigned long)addr, (unsigned long)other_addr); + } else { + pteval_t iomap_set = (_pte.pte & PTE_FLAGS_MASK) & _PAGE_IOMAP; + other_addr = (_pte.pte & PTE_PFN_MASK); + WARN_ONCE((addr == other_addr) && (!io_page) && (!iomap_set), + "0x%lx is missing VM_IO (and wasn't fixed)!\n", + (unsigned long)addr); + } + + return _pte; +} +PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte_debug); +#endif + pgd_t xen_make_pgd(pgdval_t pgd) { pgd = pte_pfn_to_mfn(pgd); @@ -986,10 +1035,9 @@ static void xen_pgd_pin(struct mm_struct *mm) */ void xen_mm_pin_all(void) { - unsigned long flags; struct page *page; - spin_lock_irqsave(&pgd_lock, flags); + spin_lock(&pgd_lock); list_for_each_entry(page, &pgd_list, lru) { if (!PagePinned(page)) { @@ -998,7 +1046,7 @@ void xen_mm_pin_all(void) } } - spin_unlock_irqrestore(&pgd_lock, flags); + spin_unlock(&pgd_lock); } /* @@ -1099,10 +1147,9 @@ static void xen_pgd_unpin(struct mm_struct *mm) */ void xen_mm_unpin_all(void) { - unsigned long flags; struct page *page; - spin_lock_irqsave(&pgd_lock, flags); + spin_lock(&pgd_lock); list_for_each_entry(page, &pgd_list, lru) { if (PageSavePinned(page)) { @@ -1112,7 +1159,7 @@ void xen_mm_unpin_all(void) } } - spin_unlock_irqrestore(&pgd_lock, flags); + spin_unlock(&pgd_lock); } void xen_activate_mm(struct mm_struct *prev, struct mm_struct *next) @@ -1416,6 +1463,119 @@ static int xen_pgd_alloc(struct mm_struct *mm) return ret; } +#ifdef CONFIG_X86_64 +static __initdata u64 __last_pgt_set_rw = 0; +static __initdata u64 __pgt_buf_start = 0; +static __initdata u64 __pgt_buf_end = 0; +static __initdata u64 __pgt_buf_top = 0; +/* + * As a consequence of the commit: + * + * commit 4b239f458c229de044d6905c2b0f9fe16ed9e01e + * Author: Yinghai Lu <yinghai@kernel.org> + * Date: Fri Dec 17 16:58:28 2010 -0800 + * + * x86-64, mm: Put early page table high + * + * at some point init_memory_mapping is going to reach the pagetable pages + * area and map those pages too (mapping them as normal memory that falls + * in the range of addresses passed to init_memory_mapping as argument). + * Some of those pages are already pagetable pages (they are in the range + * pgt_buf_start-pgt_buf_end) therefore they are going to be mapped RO and + * everything is fine. + * Some of these pages are not pagetable pages yet (they fall in the range + * pgt_buf_end-pgt_buf_top; for example the page at pgt_buf_end) so they + * are going to be mapped RW. When these pages become pagetable pages and + * are hooked into the pagetable, xen will find that the guest has already + * a RW mapping of them somewhere and fail the operation. + * The reason Xen requires pagetables to be RO is that the hypervisor needs + * to verify that the pagetables are valid before using them. The validation + * operations are called "pinning". + * + * In order to fix the issue we mark all the pages in the entire range + * pgt_buf_start-pgt_buf_top as RO, however when the pagetable allocation + * is completed only the range pgt_buf_start-pgt_buf_end is reserved by + * init_memory_mapping. Hence the kernel is going to crash as soon as one + * of the pages in the range pgt_buf_end-pgt_buf_top is reused (b/c those + * ranges are RO). + * + * For this reason, 'mark_rw_past_pgt' is introduced which is called _after_ + * the init_memory_mapping has completed (in a perfect world we would + * call this function from init_memory_mapping, but lets ignore that). + * + * Because we are called _after_ init_memory_mapping the pgt_buf_[start, + * end,top] have all changed to new values (b/c init_memory_mapping + * is called and setting up another new page-table). Hence, the first time + * we enter this function, we save away the pgt_buf_start value and update + * the pgt_buf_[end,top]. + * + * When we detect that the "old" pgt_buf_start through pgt_buf_end + * PFNs have been reserved (so memblock_x86_reserve_range has been called), + * we immediately set out to RW the "old" pgt_buf_end through pgt_buf_top. + * + * And then we update those "old" pgt_buf_[end|top] with the new ones + * so that we can redo this on the next pagetable. + */ +static __init void mark_rw_past_pgt(void) { + + if (pgt_buf_end > pgt_buf_start) { + u64 addr, size; + + /* Save it away. */ + if (!__pgt_buf_start) { + __pgt_buf_start = pgt_buf_start; + __pgt_buf_end = pgt_buf_end; + __pgt_buf_top = pgt_buf_top; + return; + } + /* If we get the range that starts at __pgt_buf_end that means + * the range is reserved, and that in 'init_memory_mapping' + * the 'memblock_x86_reserve_range' has been called with the + * outdated __pgt_buf_start, __pgt_buf_end (the "new" + * pgt_buf_[start|end|top] refer now to a new pagetable. + * Note: we are called _after_ the pgt_buf_[..] have been + * updated.*/ + + addr = memblock_x86_find_in_range_size(PFN_PHYS(__pgt_buf_start), + &size, PAGE_SIZE); + + /* Still not reserved, meaning 'memblock_x86_reserve_range' + * hasn't been called yet. Update the _end and _top.*/ + if (addr == PFN_PHYS(__pgt_buf_start)) { + __pgt_buf_end = pgt_buf_end; + __pgt_buf_top = pgt_buf_top; + return; + } + + /* OK, the area is reserved, meaning it is time for us to + * set RW for the old end->top PFNs. */ + + /* ..unless we had already done this. */ + if (__pgt_buf_end == __last_pgt_set_rw) + return; + + addr = PFN_PHYS(__pgt_buf_end); + + /* set as RW the rest */ + printk(KERN_DEBUG "xen: setting RW the range %llx - %llx\n", + PFN_PHYS(__pgt_buf_end), PFN_PHYS(__pgt_buf_top)); + + while (addr < PFN_PHYS(__pgt_buf_top)) { + make_lowmem_page_readwrite(__va(addr)); + addr += PAGE_SIZE; + } + /* And update everything so that we are ready for the next + * pagetable (the one created for regions past 4GB) */ + __last_pgt_set_rw = __pgt_buf_end; + __pgt_buf_start = pgt_buf_start; + __pgt_buf_end = pgt_buf_end; + __pgt_buf_top = pgt_buf_top; + } + return; +} +#else +static __init void mark_rw_past_pgt(void) { } +#endif static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd) { #ifdef CONFIG_X86_64 @@ -1426,28 +1586,43 @@ static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd) #endif } +#ifdef CONFIG_X86_32 static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte) { - unsigned long pfn = pte_pfn(pte); - -#ifdef CONFIG_X86_32 /* If there's an existing pte, then don't allow _PAGE_RW to be set */ if (pte_val_ma(*ptep) & _PAGE_PRESENT) pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) & pte_val_ma(pte)); -#endif + + return pte; +} +#else /* CONFIG_X86_64 */ +static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte) +{ + unsigned long pfn = pte_pfn(pte); /* + * A bit of optimization. We do not need to call the workaround + * when xen_set_pte_init is called with a PTE with 0 as PFN. + * That is b/c the pagetable at that point are just being populated + * with empty values and we can save some cycles by not calling + * the 'memblock' code.*/ + if (pfn) + mark_rw_past_pgt(); + /* * If the new pfn is within the range of the newly allocated * kernel pagetable, and it isn't being mapped into an - * early_ioremap fixmap slot, make sure it is RO. + * early_ioremap fixmap slot as a freshly allocated page, make sure + * it is RO. */ - if (!is_early_ioremap_ptep(ptep) && - pfn >= e820_table_start && pfn < e820_table_end) + if (((!is_early_ioremap_ptep(ptep) && + pfn >= pgt_buf_start && pfn < pgt_buf_top)) || + (is_early_ioremap_ptep(ptep) && pfn != (pgt_buf_end - 1))) pte = pte_wrprotect(pte); return pte; } +#endif /* CONFIG_X86_64 */ /* Init-time set_pte while constructing initial pagetables, which doesn't allow RO pagetable pages to be remapped RW */ @@ -1653,9 +1828,6 @@ static __init void xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn) for (pteidx = 0; pteidx < PTRS_PER_PTE; pteidx++, pfn++) { pte_t pte; - if (pfn > max_pfn_mapped) - max_pfn_mapped = pfn; - if (!pte_none(pte_page[pteidx])) continue; @@ -1697,7 +1869,7 @@ static void convert_pfn_mfn(void *v) } /* - * Set up the inital kernel pagetable. + * Set up the initial kernel pagetable. * * We can construct this by grafting the Xen provided pagetable into * head_64.S's preconstructed pagetables. We copy the Xen L2's into @@ -1713,6 +1885,12 @@ __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, pud_t *l3; pmd_t *l2; + /* max_pfn_mapped is the last pfn mapped in the initial memory + * mappings. Considering that on Xen after the kernel mappings we + * have the mappings of some pages that don't exist in pfn space, we + * set max_pfn_mapped to the last real pfn mapped. */ + max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->mfn_list)); + /* Zap identity mapping */ init_level4_pgt[0] = __pgd(0); @@ -1817,9 +1995,7 @@ __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, initial_kernel_pmd = extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE); - max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->pt_base) + - xen_start_info->nr_pt_frames * PAGE_SIZE + - 512*1024); + max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->mfn_list)); kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd); memcpy(initial_kernel_pmd, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD); @@ -1942,6 +2118,11 @@ __init void xen_ident_map_ISA(void) static __init void xen_post_allocator_init(void) { + mark_rw_past_pgt(); + +#ifdef CONFIG_XEN_DEBUG + pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte_debug); +#endif pv_mmu_ops.set_pte = xen_set_pte; pv_mmu_ops.set_pmd = xen_set_pmd; pv_mmu_ops.set_pud = xen_set_pud; @@ -2074,7 +2255,7 @@ static void xen_zap_pfn_range(unsigned long vaddr, unsigned int order, in_frames[i] = virt_to_mfn(vaddr); MULTI_update_va_mapping(mcs.mc, vaddr, VOID_PTE, 0); - set_phys_to_machine(virt_to_pfn(vaddr), INVALID_P2M_ENTRY); + __set_phys_to_machine(virt_to_pfn(vaddr), INVALID_P2M_ENTRY); if (out_frames) out_frames[i] = virt_to_pfn(vaddr); @@ -2353,6 +2534,18 @@ EXPORT_SYMBOL_GPL(xen_remap_domain_mfn_range); #ifdef CONFIG_XEN_DEBUG_FS +static int p2m_dump_open(struct inode *inode, struct file *filp) +{ + return single_open(filp, p2m_dump_show, NULL); +} + +static const struct file_operations p2m_dump_fops = { + .open = p2m_dump_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + static struct dentry *d_mmu_debug; static int __init xen_mmu_debugfs(void) @@ -2408,6 +2601,7 @@ static int __init xen_mmu_debugfs(void) debugfs_create_u32("prot_commit_batched", 0444, d_mmu_debug, &mmu_stats.prot_commit_batched); + debugfs_create_file("p2m", 0600, d_mmu_debug, NULL, &p2m_dump_fops); return 0; } fs_initcall(xen_mmu_debugfs); diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index fd12d7ce7ff..141eb0de8b0 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -23,6 +23,129 @@ * P2M_PER_PAGE depends on the architecture, as a mfn is always * unsigned long (8 bytes on 64-bit, 4 bytes on 32), leading to * 512 and 1024 entries respectively. + * + * In short, these structures contain the Machine Frame Number (MFN) of the PFN. + * + * However not all entries are filled with MFNs. Specifically for all other + * leaf entries, or for the top root, or middle one, for which there is a void + * entry, we assume it is "missing". So (for example) + * pfn_to_mfn(0x90909090)=INVALID_P2M_ENTRY. + * + * We also have the possibility of setting 1-1 mappings on certain regions, so + * that: + * pfn_to_mfn(0xc0000)=0xc0000 + * + * The benefit of this is, that we can assume for non-RAM regions (think + * PCI BARs, or ACPI spaces), we can create mappings easily b/c we + * get the PFN value to match the MFN. + * + * For this to work efficiently we have one new page p2m_identity and + * allocate (via reserved_brk) any other pages we need to cover the sides + * (1GB or 4MB boundary violations). All entries in p2m_identity are set to + * INVALID_P2M_ENTRY type (Xen toolstack only recognizes that and MFNs, + * no other fancy value). + * + * On lookup we spot that the entry points to p2m_identity and return the + * identity value instead of dereferencing and returning INVALID_P2M_ENTRY. + * If the entry points to an allocated page, we just proceed as before and + * return the PFN. If the PFN has IDENTITY_FRAME_BIT set we unmask that in + * appropriate functions (pfn_to_mfn). + * + * The reason for having the IDENTITY_FRAME_BIT instead of just returning the + * PFN is that we could find ourselves where pfn_to_mfn(pfn)==pfn for a + * non-identity pfn. To protect ourselves against we elect to set (and get) the + * IDENTITY_FRAME_BIT on all identity mapped PFNs. + * + * This simplistic diagram is used to explain the more subtle piece of code. + * There is also a digram of the P2M at the end that can help. + * Imagine your E820 looking as so: + * + * 1GB 2GB + * /-------------------+---------\/----\ /----------\ /---+-----\ + * | System RAM | Sys RAM ||ACPI| | reserved | | Sys RAM | + * \-------------------+---------/\----/ \----------/ \---+-----/ + * ^- 1029MB ^- 2001MB + * + * [1029MB = 263424 (0x40500), 2001MB = 512256 (0x7D100), + * 2048MB = 524288 (0x80000)] + * + * And dom0_mem=max:3GB,1GB is passed in to the guest, meaning memory past 1GB + * is actually not present (would have to kick the balloon driver to put it in). + * + * When we are told to set the PFNs for identity mapping (see patch: "xen/setup: + * Set identity mapping for non-RAM E820 and E820 gaps.") we pass in the start + * of the PFN and the end PFN (263424 and 512256 respectively). The first step + * is to reserve_brk a top leaf page if the p2m[1] is missing. The top leaf page + * covers 512^2 of page estate (1GB) and in case the start or end PFN is not + * aligned on 512^2*PAGE_SIZE (1GB) we loop on aligned 1GB PFNs from start pfn + * to end pfn. We reserve_brk top leaf pages if they are missing (means they + * point to p2m_mid_missing). + * + * With the E820 example above, 263424 is not 1GB aligned so we allocate a + * reserve_brk page which will cover the PFNs estate from 0x40000 to 0x80000. + * Each entry in the allocate page is "missing" (points to p2m_missing). + * + * Next stage is to determine if we need to do a more granular boundary check + * on the 4MB (or 2MB depending on architecture) off the start and end pfn's. + * We check if the start pfn and end pfn violate that boundary check, and if + * so reserve_brk a middle (p2m[x][y]) leaf page. This way we have a much finer + * granularity of setting which PFNs are missing and which ones are identity. + * In our example 263424 and 512256 both fail the check so we reserve_brk two + * pages. Populate them with INVALID_P2M_ENTRY (so they both have "missing" + * values) and assign them to p2m[1][2] and p2m[1][488] respectively. + * + * At this point we would at minimum reserve_brk one page, but could be up to + * three. Each call to set_phys_range_identity has at maximum a three page + * cost. If we were to query the P2M at this stage, all those entries from + * start PFN through end PFN (so 1029MB -> 2001MB) would return + * INVALID_P2M_ENTRY ("missing"). + * + * The next step is to walk from the start pfn to the end pfn setting + * the IDENTITY_FRAME_BIT on each PFN. This is done in set_phys_range_identity. + * If we find that the middle leaf is pointing to p2m_missing we can swap it + * over to p2m_identity - this way covering 4MB (or 2MB) PFN space. At this + * point we do not need to worry about boundary aligment (so no need to + * reserve_brk a middle page, figure out which PFNs are "missing" and which + * ones are identity), as that has been done earlier. If we find that the + * middle leaf is not occupied by p2m_identity or p2m_missing, we dereference + * that page (which covers 512 PFNs) and set the appropriate PFN with + * IDENTITY_FRAME_BIT. In our example 263424 and 512256 end up there, and we + * set from p2m[1][2][256->511] and p2m[1][488][0->256] with + * IDENTITY_FRAME_BIT set. + * + * All other regions that are void (or not filled) either point to p2m_missing + * (considered missing) or have the default value of INVALID_P2M_ENTRY (also + * considered missing). In our case, p2m[1][2][0->255] and p2m[1][488][257->511] + * contain the INVALID_P2M_ENTRY value and are considered "missing." + * + * This is what the p2m ends up looking (for the E820 above) with this + * fabulous drawing: + * + * p2m /--------------\ + * /-----\ | &mfn_list[0],| /-----------------\ + * | 0 |------>| &mfn_list[1],| /---------------\ | ~0, ~0, .. | + * |-----| | ..., ~0, ~0 | | ~0, ~0, [x]---+----->| IDENTITY [@256] | + * | 1 |---\ \--------------/ | [p2m_identity]+\ | IDENTITY [@257] | + * |-----| \ | [p2m_identity]+\\ | .... | + * | 2 |--\ \-------------------->| ... | \\ \----------------/ + * |-----| \ \---------------/ \\ + * | 3 |\ \ \\ p2m_identity + * |-----| \ \-------------------->/---------------\ /-----------------\ + * | .. +->+ | [p2m_identity]+-->| ~0, ~0, ~0, ... | + * \-----/ / | [p2m_identity]+-->| ..., ~0 | + * / /---------------\ | .... | \-----------------/ + * / | IDENTITY[@0] | /-+-[x], ~0, ~0.. | + * / | IDENTITY[@256]|<----/ \---------------/ + * / | ~0, ~0, .... | + * | \---------------/ + * | + * p2m_missing p2m_missing + * /------------------\ /------------\ + * | [p2m_mid_missing]+---->| ~0, ~0, ~0 | + * | [p2m_mid_missing]+---->| ..., ~0 | + * \------------------/ \------------/ + * + * where ~0 is INVALID_P2M_ENTRY. IDENTITY is (PFN | IDENTITY_BIT) */ #include <linux/init.h> @@ -30,6 +153,7 @@ #include <linux/list.h> #include <linux/hash.h> #include <linux/sched.h> +#include <linux/seq_file.h> #include <asm/cache.h> #include <asm/setup.h> @@ -59,9 +183,15 @@ static RESERVE_BRK_ARRAY(unsigned long **, p2m_top, P2M_TOP_PER_PAGE); static RESERVE_BRK_ARRAY(unsigned long, p2m_top_mfn, P2M_TOP_PER_PAGE); static RESERVE_BRK_ARRAY(unsigned long *, p2m_top_mfn_p, P2M_TOP_PER_PAGE); +static RESERVE_BRK_ARRAY(unsigned long, p2m_identity, P2M_PER_PAGE); + RESERVE_BRK(p2m_mid, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE))); RESERVE_BRK(p2m_mid_mfn, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE))); +/* We might hit two boundary violations at the start and end, at max each + * boundary violation will require three middle nodes. */ +RESERVE_BRK(p2m_mid_identity, PAGE_SIZE * 2 * 3); + static inline unsigned p2m_top_index(unsigned long pfn) { BUG_ON(pfn >= MAX_P2M_PFN); @@ -136,7 +266,7 @@ static void p2m_init(unsigned long *p2m) * - After resume we're called from within stop_machine, but the mfn * tree should alreay be completely allocated. */ -void xen_build_mfn_list_list(void) +void __ref xen_build_mfn_list_list(void) { unsigned long pfn; @@ -221,6 +351,9 @@ void __init xen_build_dynamic_phys_to_machine(void) p2m_top = extend_brk(PAGE_SIZE, PAGE_SIZE); p2m_top_init(p2m_top); + p2m_identity = extend_brk(PAGE_SIZE, PAGE_SIZE); + p2m_init(p2m_identity); + /* * The domain builder gives us a pre-constructed p2m array in * mfn_list for all the pages initially given to us, so we just @@ -266,6 +399,14 @@ unsigned long get_phys_to_machine(unsigned long pfn) mididx = p2m_mid_index(pfn); idx = p2m_index(pfn); + /* + * The INVALID_P2M_ENTRY is filled in both p2m_*identity + * and in p2m_*missing, so returning the INVALID_P2M_ENTRY + * would be wrong. + */ + if (p2m_top[topidx][mididx] == p2m_identity) + return IDENTITY_FRAME(pfn); + return p2m_top[topidx][mididx][idx]; } EXPORT_SYMBOL_GPL(get_phys_to_machine); @@ -335,9 +476,11 @@ static bool alloc_p2m(unsigned long pfn) p2m_top_mfn_p[topidx] = mid_mfn; } - if (p2m_top[topidx][mididx] == p2m_missing) { + if (p2m_top[topidx][mididx] == p2m_identity || + p2m_top[topidx][mididx] == p2m_missing) { /* p2m leaf page is missing */ unsigned long *p2m; + unsigned long *p2m_orig = p2m_top[topidx][mididx]; p2m = alloc_p2m_page(); if (!p2m) @@ -345,7 +488,7 @@ static bool alloc_p2m(unsigned long pfn) p2m_init(p2m); - if (cmpxchg(&mid[mididx], p2m_missing, p2m) != p2m_missing) + if (cmpxchg(&mid[mididx], p2m_orig, p2m) != p2m_orig) free_p2m_page(p2m); else mid_mfn[mididx] = virt_to_mfn(p2m); @@ -354,11 +497,91 @@ static bool alloc_p2m(unsigned long pfn) return true; } +static bool __init __early_alloc_p2m(unsigned long pfn) +{ + unsigned topidx, mididx, idx; + + topidx = p2m_top_index(pfn); + mididx = p2m_mid_index(pfn); + idx = p2m_index(pfn); + + /* Pfff.. No boundary cross-over, lets get out. */ + if (!idx) + return false; + + WARN(p2m_top[topidx][mididx] == p2m_identity, + "P2M[%d][%d] == IDENTITY, should be MISSING (or alloced)!\n", + topidx, mididx); + + /* + * Could be done by xen_build_dynamic_phys_to_machine.. + */ + if (p2m_top[topidx][mididx] != p2m_missing) + return false; + + /* Boundary cross-over for the edges: */ + if (idx) { + unsigned long *p2m = extend_brk(PAGE_SIZE, PAGE_SIZE); + + p2m_init(p2m); + + p2m_top[topidx][mididx] = p2m; + + } + return idx != 0; +} +unsigned long __init set_phys_range_identity(unsigned long pfn_s, + unsigned long pfn_e) +{ + unsigned long pfn; + + if (unlikely(pfn_s >= MAX_P2M_PFN || pfn_e >= MAX_P2M_PFN)) + return 0; + + if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) + return pfn_e - pfn_s; + + if (pfn_s > pfn_e) + return 0; + + for (pfn = (pfn_s & ~(P2M_MID_PER_PAGE * P2M_PER_PAGE - 1)); + pfn < ALIGN(pfn_e, (P2M_MID_PER_PAGE * P2M_PER_PAGE)); + pfn += P2M_MID_PER_PAGE * P2M_PER_PAGE) + { + unsigned topidx = p2m_top_index(pfn); + if (p2m_top[topidx] == p2m_mid_missing) { + unsigned long **mid = extend_brk(PAGE_SIZE, PAGE_SIZE); + + p2m_mid_init(mid); + + p2m_top[topidx] = mid; + } + } + + __early_alloc_p2m(pfn_s); + __early_alloc_p2m(pfn_e); + + for (pfn = pfn_s; pfn < pfn_e; pfn++) + if (!__set_phys_to_machine(pfn, IDENTITY_FRAME(pfn))) + break; + + if (!WARN((pfn - pfn_s) != (pfn_e - pfn_s), + "Identity mapping failed. We are %ld short of 1-1 mappings!\n", + (pfn_e - pfn_s) - (pfn - pfn_s))) + printk(KERN_DEBUG "1-1 mapping on %lx->%lx\n", pfn_s, pfn); + + return pfn - pfn_s; +} + /* Try to install p2m mapping; fail if intermediate bits missing */ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) { unsigned topidx, mididx, idx; + if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) { + BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY); + return true; + } if (unlikely(pfn >= MAX_P2M_PFN)) { BUG_ON(mfn != INVALID_P2M_ENTRY); return true; @@ -368,6 +591,21 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) mididx = p2m_mid_index(pfn); idx = p2m_index(pfn); + /* For sparse holes were the p2m leaf has real PFN along with + * PCI holes, stick in the PFN as the MFN value. + */ + if (mfn != INVALID_P2M_ENTRY && (mfn & IDENTITY_FRAME_BIT)) { + if (p2m_top[topidx][mididx] == p2m_identity) + return true; + + /* Swap over from MISSING to IDENTITY if needed. */ + if (p2m_top[topidx][mididx] == p2m_missing) { + WARN_ON(cmpxchg(&p2m_top[topidx][mididx], p2m_missing, + p2m_identity) != p2m_missing); + return true; + } + } + if (p2m_top[topidx][mididx] == p2m_missing) return mfn == INVALID_P2M_ENTRY; @@ -378,11 +616,6 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) bool set_phys_to_machine(unsigned long pfn, unsigned long mfn) { - if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) { - BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY); - return true; - } - if (unlikely(!__set_phys_to_machine(pfn, mfn))) { if (!alloc_p2m(pfn)) return false; @@ -421,7 +654,7 @@ int m2p_add_override(unsigned long mfn, struct page *page) { unsigned long flags; unsigned long pfn; - unsigned long address; + unsigned long uninitialized_var(address); unsigned level; pte_t *ptep = NULL; @@ -438,7 +671,9 @@ int m2p_add_override(unsigned long mfn, struct page *page) page->private = mfn; page->index = pfn_to_mfn(pfn); - __set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)); + if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)))) + return -ENOMEM; + if (!PageHighMem(page)) /* Just zap old mapping for now */ pte_clear(&init_mm, address, ptep); @@ -455,7 +690,7 @@ int m2p_remove_override(struct page *page) unsigned long flags; unsigned long mfn; unsigned long pfn; - unsigned long address; + unsigned long uninitialized_var(address); unsigned level; pte_t *ptep = NULL; @@ -476,7 +711,7 @@ int m2p_remove_override(struct page *page) spin_lock_irqsave(&m2p_override_lock, flags); list_del(&page->lru); spin_unlock_irqrestore(&m2p_override_lock, flags); - __set_phys_to_machine(pfn, page->index); + set_phys_to_machine(pfn, page->index); if (!PageHighMem(page)) set_pte_at(&init_mm, address, ptep, @@ -520,3 +755,80 @@ unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn) return ret; } EXPORT_SYMBOL_GPL(m2p_find_override_pfn); + +#ifdef CONFIG_XEN_DEBUG_FS + +int p2m_dump_show(struct seq_file *m, void *v) +{ + static const char * const level_name[] = { "top", "middle", + "entry", "abnormal" }; + static const char * const type_name[] = { "identity", "missing", + "pfn", "abnormal"}; +#define TYPE_IDENTITY 0 +#define TYPE_MISSING 1 +#define TYPE_PFN 2 +#define TYPE_UNKNOWN 3 + unsigned long pfn, prev_pfn_type = 0, prev_pfn_level = 0; + unsigned int uninitialized_var(prev_level); + unsigned int uninitialized_var(prev_type); + + if (!p2m_top) + return 0; + + for (pfn = 0; pfn < MAX_DOMAIN_PAGES; pfn++) { + unsigned topidx = p2m_top_index(pfn); + unsigned mididx = p2m_mid_index(pfn); + unsigned idx = p2m_index(pfn); + unsigned lvl, type; + + lvl = 4; + type = TYPE_UNKNOWN; + if (p2m_top[topidx] == p2m_mid_missing) { + lvl = 0; type = TYPE_MISSING; + } else if (p2m_top[topidx] == NULL) { + lvl = 0; type = TYPE_UNKNOWN; + } else if (p2m_top[topidx][mididx] == NULL) { + lvl = 1; type = TYPE_UNKNOWN; + } else if (p2m_top[topidx][mididx] == p2m_identity) { + lvl = 1; type = TYPE_IDENTITY; + } else if (p2m_top[topidx][mididx] == p2m_missing) { + lvl = 1; type = TYPE_MISSING; + } else if (p2m_top[topidx][mididx][idx] == 0) { + lvl = 2; type = TYPE_UNKNOWN; + } else if (p2m_top[topidx][mididx][idx] == IDENTITY_FRAME(pfn)) { + lvl = 2; type = TYPE_IDENTITY; + } else if (p2m_top[topidx][mididx][idx] == INVALID_P2M_ENTRY) { + lvl = 2; type = TYPE_MISSING; + } else if (p2m_top[topidx][mididx][idx] == pfn) { + lvl = 2; type = TYPE_PFN; + } else if (p2m_top[topidx][mididx][idx] != pfn) { + lvl = 2; type = TYPE_PFN; + } + if (pfn == 0) { + prev_level = lvl; + prev_type = type; + } + if (pfn == MAX_DOMAIN_PAGES-1) { + lvl = 3; + type = TYPE_UNKNOWN; + } + if (prev_type != type) { + seq_printf(m, " [0x%lx->0x%lx] %s\n", + prev_pfn_type, pfn, type_name[prev_type]); + prev_pfn_type = pfn; + prev_type = type; + } + if (prev_level != lvl) { + seq_printf(m, " [0x%lx->0x%lx] level %s\n", + prev_pfn_level, pfn, level_name[prev_level]); + prev_pfn_level = pfn; + prev_level = lvl; + } + } + return 0; +#undef TYPE_IDENTITY +#undef TYPE_MISSING +#undef TYPE_PFN +#undef TYPE_UNKNOWN +} +#endif diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index a8a66a50d44..90bac0aac3a 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -52,6 +52,8 @@ phys_addr_t xen_extra_mem_start, xen_extra_mem_size; static __init void xen_add_extra_mem(unsigned long pages) { + unsigned long pfn; + u64 size = (u64)pages * PAGE_SIZE; u64 extra_start = xen_extra_mem_start + xen_extra_mem_size; @@ -66,6 +68,9 @@ static __init void xen_add_extra_mem(unsigned long pages) xen_extra_mem_size += size; xen_max_p2m_pfn = PFN_DOWN(extra_start + size); + + for (pfn = PFN_DOWN(extra_start); pfn <= xen_max_p2m_pfn; pfn++) + __set_phys_to_machine(pfn, INVALID_P2M_ENTRY); } static unsigned long __init xen_release_chunk(phys_addr_t start_addr, @@ -104,7 +109,7 @@ static unsigned long __init xen_release_chunk(phys_addr_t start_addr, WARN(ret != 1, "Failed to release memory %lx-%lx err=%d\n", start, end, ret); if (ret == 1) { - set_phys_to_machine(pfn, INVALID_P2M_ENTRY); + __set_phys_to_machine(pfn, INVALID_P2M_ENTRY); len++; } } @@ -138,12 +143,55 @@ static unsigned long __init xen_return_unused_memory(unsigned long max_pfn, return released; } +static unsigned long __init xen_set_identity(const struct e820entry *list, + ssize_t map_size) +{ + phys_addr_t last = xen_initial_domain() ? 0 : ISA_END_ADDRESS; + phys_addr_t start_pci = last; + const struct e820entry *entry; + unsigned long identity = 0; + int i; + + for (i = 0, entry = list; i < map_size; i++, entry++) { + phys_addr_t start = entry->addr; + phys_addr_t end = start + entry->size; + + if (start < last) + start = last; + + if (end <= start) + continue; + + /* Skip over the 1MB region. */ + if (last > end) + continue; + + if (entry->type == E820_RAM) { + if (start > start_pci) + identity += set_phys_range_identity( + PFN_UP(start_pci), PFN_DOWN(start)); + + /* Without saving 'last' we would gooble RAM too + * at the end of the loop. */ + last = end; + start_pci = end; + continue; + } + start_pci = min(start, start_pci); + last = end; + } + if (last > start_pci) + identity += set_phys_range_identity( + PFN_UP(start_pci), PFN_DOWN(last)); + return identity; +} /** * machine_specific_memory_setup - Hook for machine specific memory setup. **/ char * __init xen_memory_setup(void) { static struct e820entry map[E820MAX] __initdata; + static struct e820entry map_raw[E820MAX] __initdata; unsigned long max_pfn = xen_start_info->nr_pages; unsigned long long mem_end; @@ -151,6 +199,7 @@ char * __init xen_memory_setup(void) struct xen_memory_map memmap; unsigned long extra_pages = 0; unsigned long extra_limit; + unsigned long identity_pages = 0; int i; int op; @@ -176,8 +225,9 @@ char * __init xen_memory_setup(void) } BUG_ON(rc); + memcpy(map_raw, map, sizeof(map)); e820.nr_map = 0; - xen_extra_mem_start = mem_end; + xen_extra_mem_start = max((1ULL << 32), mem_end); for (i = 0; i < memmap.nr_entries; i++) { unsigned long long end; @@ -194,6 +244,15 @@ char * __init xen_memory_setup(void) end -= delta; extra_pages += PFN_DOWN(delta); + /* + * Set RAM below 4GB that is not for us to be unusable. + * This prevents "System RAM" address space from being + * used as potential resource for I/O address (happens + * when 'allocate_resource' is called). + */ + if (delta && + (xen_initial_domain() && end < 0x100000000ULL)) + e820_add_region(end, delta, E820_UNUSABLE); } if (map[i].size > 0 && end > xen_extra_mem_start) @@ -251,6 +310,13 @@ char * __init xen_memory_setup(void) xen_add_extra_mem(extra_pages); + /* + * Set P2M for all non-RAM pages and E820 gaps to be identity + * type PFNs. We supply it with the non-sanitized version + * of the E820. + */ + identity_pages = xen_set_identity(map_raw, memmap.nr_entries); + printk(KERN_INFO "Set %ld page(s) to 1-1 mapping.\n", identity_pages); return "Xen"; } diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 72a4c795904..30612441ed9 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -509,3 +509,41 @@ void __init xen_smp_init(void) xen_fill_possible_map(); xen_init_spinlocks(); } + +static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus) +{ + native_smp_prepare_cpus(max_cpus); + WARN_ON(xen_smp_intr_init(0)); + + if (!xen_have_vector_callback) + return; + xen_init_lock_cpu(0); + xen_init_spinlocks(); +} + +static int __cpuinit xen_hvm_cpu_up(unsigned int cpu) +{ + int rc; + rc = native_cpu_up(cpu); + WARN_ON (xen_smp_intr_init(cpu)); + return rc; +} + +static void xen_hvm_cpu_die(unsigned int cpu) +{ + unbind_from_irqhandler(per_cpu(xen_resched_irq, cpu), NULL); + unbind_from_irqhandler(per_cpu(xen_callfunc_irq, cpu), NULL); + unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu), NULL); + unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu), NULL); + native_cpu_die(cpu); +} + +void __init xen_hvm_smp_init(void) +{ + smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus; + smp_ops.smp_send_reschedule = xen_smp_send_reschedule; + smp_ops.cpu_up = xen_hvm_cpu_up; + smp_ops.cpu_die = xen_hvm_cpu_die; + smp_ops.send_call_func_ipi = xen_smp_send_call_function_ipi; + smp_ops.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi; +} diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index 9bbd63a129b..45329c8c226 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -12,7 +12,7 @@ #include "xen-ops.h" #include "mmu.h" -void xen_pre_suspend(void) +void xen_arch_pre_suspend(void) { xen_start_info->store_mfn = mfn_to_pfn(xen_start_info->store_mfn); xen_start_info->console.domU.mfn = @@ -26,8 +26,9 @@ void xen_pre_suspend(void) BUG(); } -void xen_hvm_post_suspend(int suspend_cancelled) +void xen_arch_hvm_post_suspend(int suspend_cancelled) { +#ifdef CONFIG_XEN_PVHVM int cpu; xen_hvm_init_shared_info(); xen_callback_vector(); @@ -37,9 +38,10 @@ void xen_hvm_post_suspend(int suspend_cancelled) xen_setup_runstate_info(cpu); } } +#endif } -void xen_post_suspend(int suspend_cancelled) +void xen_arch_post_suspend(int suspend_cancelled) { xen_build_mfn_list_list(); diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index 04e11597a8c..c532d280ce3 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -393,7 +393,9 @@ void xen_setup_timer(int cpu) name = "<timer kasprintf failed>"; irq = bind_virq_to_irqhandler(VIRQ_TIMER, cpu, xen_timer_interrupt, - IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING|IRQF_TIMER, + IRQF_DISABLED|IRQF_PERCPU| + IRQF_NOBALANCING|IRQF_TIMER| + IRQF_FORCE_RESUME, name, NULL); evt = &per_cpu(xen_clock_events, cpu); diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index 1a5ff24e29c..aaa7291c925 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -28,9 +28,9 @@ ENTRY(startup_xen) __FINIT .pushsection .text - .align PAGE_SIZE_asm + .align PAGE_SIZE ENTRY(hypercall_page) - .skip PAGE_SIZE_asm + .skip PAGE_SIZE .popsection ELFNOTE(Xen, XEN_ELFNOTE_GUEST_OS, .asciz "linux") diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 9d41bf98575..3112f55638c 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -64,10 +64,12 @@ void xen_setup_vcpu_info_placement(void); #ifdef CONFIG_SMP void xen_smp_init(void); +void __init xen_hvm_smp_init(void); extern cpumask_var_t xen_cpu_initialized_map; #else static inline void xen_smp_init(void) {} +static inline void xen_hvm_smp_init(void) {} #endif #ifdef CONFIG_PARAVIRT_SPINLOCKS |