diff options
author | Stephen Rothwell <sfr@canb.auug.org.au> | 2008-07-03 16:57:27 +1000 |
---|---|---|
committer | Stephen Rothwell <sfr@canb.auug.org.au> | 2008-07-03 16:57:27 +1000 |
commit | f7417ec0f28dbd9b0a2781e249c184d0b4b41047 (patch) | |
tree | 1e553c5367ba30ac9d76714f5c229f2f8eb15955 /include | |
parent | 7faeea8df2b4e995a53b0fb61549a287ec39a1a2 (diff) | |
parent | 9c2ed7fb6ad02f7d77db8f460612f58f5d2f6567 (diff) |
Merge commit 'generic-ipi/auto-generic-ipi-next'
Conflicts:
arch/powerpc/mm/slice.c
arch/s390/kernel/time.c
arch/x86/kvm/vmx.c
init/main.c
kernel/sched_rt.c
net/iucv/iucv.c
virt/kvm/kvm_main.c
Diffstat (limited to 'include')
43 files changed, 740 insertions, 173 deletions
diff --git a/include/asm-alpha/smp.h b/include/asm-alpha/smp.h index 286e1d844f63..544c69af8168 100644 --- a/include/asm-alpha/smp.h +++ b/include/asm-alpha/smp.h @@ -47,12 +47,13 @@ extern struct cpuinfo_alpha cpu_data[NR_CPUS]; extern int smp_num_cpus; #define cpu_possible_map cpu_present_map -int smp_call_function_on_cpu(void (*func) (void *info), void *info,int retry, int wait, cpumask_t cpu); +extern void arch_send_call_function_single_ipi(int cpu); +extern void arch_send_call_function_ipi(cpumask_t mask); #else /* CONFIG_SMP */ #define hard_smp_processor_id() 0 -#define smp_call_function_on_cpu(func,info,retry,wait,cpu) ({ 0; }) +#define smp_call_function_on_cpu(func,info,wait,cpu) ({ 0; }) #endif /* CONFIG_SMP */ diff --git a/include/asm-alpha/thread_info.h b/include/asm-alpha/thread_info.h index fb3185196298..fde5f56cd770 100644 --- a/include/asm-alpha/thread_info.h +++ b/include/asm-alpha/thread_info.h @@ -57,7 +57,7 @@ register struct thread_info *__current_thread_info __asm__("$8"); #endif /* __ASSEMBLY__ */ -#define PREEMPT_ACTIVE 0x40000000 +#define PREEMPT_ACTIVE 0x10000000 /* * Thread information flags: diff --git a/include/asm-arm/smp.h b/include/asm-arm/smp.h index af99636db400..7fffa2404b8e 100644 --- a/include/asm-arm/smp.h +++ b/include/asm-arm/smp.h @@ -101,6 +101,9 @@ extern void platform_cpu_die(unsigned int cpu); extern int platform_cpu_kill(unsigned int cpu); extern void platform_cpu_enable(unsigned int cpu); +extern void arch_send_call_function_single_ipi(int cpu); +extern void arch_send_call_function_ipi(cpumask_t mask); + /* * Local timer interrupt handling function (can be IPI'ed). */ diff --git a/include/asm-ia64/smp.h b/include/asm-ia64/smp.h index 2984e262fc6c..12d96e0cd513 100644 --- a/include/asm-ia64/smp.h +++ b/include/asm-ia64/smp.h @@ -39,9 +39,6 @@ ia64_get_lid (void) return lid.f.id << 8 | lid.f.eid; } -extern int smp_call_function_mask(cpumask_t mask, void (*func)(void *), - void *info, int wait); - #define hard_smp_processor_id() ia64_get_lid() #ifdef CONFIG_SMP @@ -126,11 +123,12 @@ extern void smp_do_timer (struct pt_regs *regs); extern irqreturn_t handle_IPI(int irq, void *dev_id); extern void smp_send_reschedule (int cpu); -extern void lock_ipi_calllock(void); -extern void unlock_ipi_calllock(void); extern void identify_siblings (struct cpuinfo_ia64 *); extern int is_multithreading_enabled(void); +extern void arch_send_call_function_single_ipi(int cpu); +extern void arch_send_call_function_ipi(cpumask_t mask); + #else /* CONFIG_SMP */ #define cpu_logical_id(i) 0 diff --git a/include/asm-m32r/smp.h b/include/asm-m32r/smp.h index 078e1a51a042..c5dd66916692 100644 --- a/include/asm-m32r/smp.h +++ b/include/asm-m32r/smp.h @@ -89,6 +89,9 @@ static __inline__ unsigned int num_booting_cpus(void) extern void smp_send_timer(void); extern unsigned long send_IPI_mask_phys(cpumask_t, int, int); +extern void arch_send_call_function_single_ipi(int cpu); +extern void arch_send_call_function_ipi(cpumask_t mask); + #endif /* not __ASSEMBLY__ */ #define NO_PROC_ID (0xff) /* No processor magic marker */ @@ -104,6 +107,7 @@ extern unsigned long send_IPI_mask_phys(cpumask_t, int, int); #define LOCAL_TIMER_IPI (M32R_IRQ_IPI3-M32R_IRQ_IPI0) #define INVALIDATE_CACHE_IPI (M32R_IRQ_IPI4-M32R_IRQ_IPI0) #define CPU_BOOT_IPI (M32R_IRQ_IPI5-M32R_IRQ_IPI0) +#define CALL_FUNC_SINGLE_IPI (M32R_IRQ_IPI6-M32R_IRQ_IPI0) #define IPI_SHIFT (0) #define NR_IPIS (8) diff --git a/include/asm-mips/smp.h b/include/asm-mips/smp.h index 84fef1aeec0c..0ff5b523ea77 100644 --- a/include/asm-mips/smp.h +++ b/include/asm-mips/smp.h @@ -35,16 +35,6 @@ extern int __cpu_logical_map[NR_CPUS]; #define NO_PROC_ID (-1) -struct call_data_struct { - void (*func)(void *); - void *info; - atomic_t started; - atomic_t finished; - int wait; -}; - -extern struct call_data_struct *call_data; - #define SMP_RESCHEDULE_YOURSELF 0x1 /* XXX braindead */ #define SMP_CALL_FUNCTION 0x2 @@ -67,4 +57,7 @@ static inline void smp_send_reschedule(int cpu) extern asmlinkage void smp_call_function_interrupt(void); +extern void arch_send_call_function_single_ipi(int cpu); +extern void arch_send_call_function_ipi(cpumask_t mask); + #endif /* __ASM_SMP_H */ diff --git a/include/asm-parisc/smp.h b/include/asm-parisc/smp.h index 306f4950e32e..398cdbaf4e54 100644 --- a/include/asm-parisc/smp.h +++ b/include/asm-parisc/smp.h @@ -30,6 +30,9 @@ extern cpumask_t cpu_online_map; extern void smp_send_reschedule(int cpu); extern void smp_send_all_nop(void); +extern void arch_send_call_function_single_ipi(int cpu); +extern void arch_send_call_function_ipi(cpumask_t mask); + #endif /* !ASSEMBLY */ /* diff --git a/include/asm-powerpc/smp.h b/include/asm-powerpc/smp.h index 1cd43e3d94fb..416d4c288cea 100644 --- a/include/asm-powerpc/smp.h +++ b/include/asm-powerpc/smp.h @@ -69,10 +69,7 @@ DECLARE_PER_CPU(cpumask_t, cpu_sibling_map); * in /proc/interrupts will be wrong!!! --Troy */ #define PPC_MSG_CALL_FUNCTION 0 #define PPC_MSG_RESCHEDULE 1 -/* This is unused now */ -#if 0 -#define PPC_MSG_MIGRATE_TASK 2 -#endif +#define PPC_MSG_CALL_FUNC_SINGLE 2 #define PPC_MSG_DEBUGGER_BREAK 3 void smp_init_iSeries(void); @@ -119,6 +116,9 @@ extern void smp_generic_take_timebase(void); extern struct smp_ops_t *smp_ops; +extern void arch_send_call_function_single_ipi(int cpu); +extern void arch_send_call_function_ipi(cpumask_t mask); + #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/include/asm-sh/smp.h b/include/asm-sh/smp.h index 9c8d34b07ebf..593343cd26ee 100644 --- a/include/asm-sh/smp.h +++ b/include/asm-sh/smp.h @@ -26,18 +26,10 @@ extern int __cpu_logical_map[NR_CPUS]; #define NO_PROC_ID (-1) -struct smp_fn_call_struct { - spinlock_t lock; - atomic_t finished; - void (*fn)(void *); - void *data; -}; - -extern struct smp_fn_call_struct smp_fn_call; - #define SMP_MSG_FUNCTION 0 #define SMP_MSG_RESCHEDULE 1 -#define SMP_MSG_NR 2 +#define SMP_MSG_FUNCTION_SINGLE 2 +#define SMP_MSG_NR 3 void plat_smp_setup(void); void plat_prepare_cpus(unsigned int max_cpus); @@ -46,6 +38,8 @@ void plat_start_cpu(unsigned int cpu, unsigned long entry_point); void plat_send_ipi(unsigned int cpu, unsigned int message); int plat_register_ipi_handler(unsigned int message, void (*handler)(void *), void *arg); +extern void arch_send_call_function_single_ipi(int cpu); +extern void arch_send_call_function_ipi(cpumask_t mask); #else diff --git a/include/asm-sparc/smp.h b/include/asm-sparc/smp.h index e6d561599726..b61e74bea06a 100644 --- a/include/asm-sparc/smp.h +++ b/include/asm-sparc/smp.h @@ -72,7 +72,7 @@ static inline void xc5(smpfunc_t func, unsigned long arg1, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) { smp_cross_call(func, arg1, arg2, arg3, arg4, arg5); } -static inline int smp_call_function(void (*func)(void *info), void *info, int nonatomic, int wait) +static inline int smp_call_function(void (*func)(void *info), void *info, int wait) { xc1((smpfunc_t)func, (unsigned long)info); return 0; diff --git a/include/asm-x86/amd_iommu.h b/include/asm-x86/amd_iommu.h new file mode 100644 index 000000000000..30a12049353b --- /dev/null +++ b/include/asm-x86/amd_iommu.h @@ -0,0 +1,32 @@ +/* + * Copyright (C) 2007-2008 Advanced Micro Devices, Inc. + * Author: Joerg Roedel <joerg.roedel@amd.com> + * Leo Duran <leo.duran@amd.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#ifndef _ASM_X86_AMD_IOMMU_H +#define _ASM_X86_AMD_IOMMU_H + +#ifdef CONFIG_AMD_IOMMU +extern int amd_iommu_init(void); +extern int amd_iommu_init_dma_ops(void); +extern void amd_iommu_detect(void); +#else +static inline int amd_iommu_init(void) { return -ENODEV; } +static inline void amd_iommu_detect(void) { } +#endif + +#endif diff --git a/include/asm-x86/amd_iommu_types.h b/include/asm-x86/amd_iommu_types.h new file mode 100644 index 000000000000..0f395501ab8e --- /dev/null +++ b/include/asm-x86/amd_iommu_types.h @@ -0,0 +1,242 @@ +/* + * Copyright (C) 2007-2008 Advanced Micro Devices, Inc. + * Author: Joerg Roedel <joerg.roedel@amd.com> + * Leo Duran <leo.duran@amd.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#ifndef __AMD_IOMMU_TYPES_H__ +#define __AMD_IOMMU_TYPES_H__ + +#include <linux/types.h> +#include <linux/list.h> +#include <linux/spinlock.h> + +/* + * some size calculation constants + */ +#define DEV_TABLE_ENTRY_SIZE 256 +#define ALIAS_TABLE_ENTRY_SIZE 2 +#define RLOOKUP_TABLE_ENTRY_SIZE (sizeof(void *)) + +/* helper macros */ +#define LOW_U32(x) ((x) & ((1ULL << 32)-1)) +#define HIGH_U32(x) (LOW_U32((x) >> 32)) + +/* Length of the MMIO region for the AMD IOMMU */ +#define MMIO_REGION_LENGTH 0x4000 + +/* Capability offsets used by the driver */ +#define MMIO_CAP_HDR_OFFSET 0x00 +#define MMIO_RANGE_OFFSET 0x0c + +/* Masks, shifts and macros to parse the device range capability */ +#define MMIO_RANGE_LD_MASK 0xff000000 +#define MMIO_RANGE_FD_MASK 0x00ff0000 +#define MMIO_RANGE_BUS_MASK 0x0000ff00 +#define MMIO_RANGE_LD_SHIFT 24 +#define MMIO_RANGE_FD_SHIFT 16 +#define MMIO_RANGE_BUS_SHIFT 8 +#define MMIO_GET_LD(x) (((x) & MMIO_RANGE_LD_MASK) >> MMIO_RANGE_LD_SHIFT) +#define MMIO_GET_FD(x) (((x) & MMIO_RANGE_FD_MASK) >> MMIO_RANGE_FD_SHIFT) +#define MMIO_GET_BUS(x) (((x) & MMIO_RANGE_BUS_MASK) >> MMIO_RANGE_BUS_SHIFT) + +/* Flag masks for the AMD IOMMU exclusion range */ +#define MMIO_EXCL_ENABLE_MASK 0x01ULL +#define MMIO_EXCL_ALLOW_MASK 0x02ULL + +/* Used offsets into the MMIO space */ +#define MMIO_DEV_TABLE_OFFSET 0x0000 +#define MMIO_CMD_BUF_OFFSET 0x0008 +#define MMIO_EVT_BUF_OFFSET 0x0010 +#define MMIO_CONTROL_OFFSET 0x0018 +#define MMIO_EXCL_BASE_OFFSET 0x0020 +#define MMIO_EXCL_LIMIT_OFFSET 0x0028 +#define MMIO_CMD_HEAD_OFFSET 0x2000 +#define MMIO_CMD_TAIL_OFFSET 0x2008 +#define MMIO_EVT_HEAD_OFFSET 0x2010 +#define MMIO_EVT_TAIL_OFFSET 0x2018 +#define MMIO_STATUS_OFFSET 0x2020 + +/* feature control bits */ +#define CONTROL_IOMMU_EN 0x00ULL +#define CONTROL_HT_TUN_EN 0x01ULL +#define CONTROL_EVT_LOG_EN 0x02ULL +#define CONTROL_EVT_INT_EN 0x03ULL +#define CONTROL_COMWAIT_EN 0x04ULL +#define CONTROL_PASSPW_EN 0x08ULL +#define CONTROL_RESPASSPW_EN 0x09ULL +#define CONTROL_COHERENT_EN 0x0aULL +#define CONTROL_ISOC_EN 0x0bULL +#define CONTROL_CMDBUF_EN 0x0cULL +#define CONTROL_PPFLOG_EN 0x0dULL +#define CONTROL_PPFINT_EN 0x0eULL + +/* command specific defines */ +#define CMD_COMPL_WAIT 0x01 +#define CMD_INV_DEV_ENTRY 0x02 +#define CMD_INV_IOMMU_PAGES 0x03 + +#define CMD_COMPL_WAIT_STORE_MASK 0x01 +#define CMD_INV_IOMMU_PAGES_SIZE_MASK 0x01 +#define CMD_INV_IOMMU_PAGES_PDE_MASK 0x02 + +/* macros and definitions for device table entries */ +#define DEV_ENTRY_VALID 0x00 +#define DEV_ENTRY_TRANSLATION 0x01 +#define DEV_ENTRY_IR 0x3d +#define DEV_ENTRY_IW 0x3e +#define DEV_ENTRY_EX 0x67 +#define DEV_ENTRY_SYSMGT1 0x68 +#define DEV_ENTRY_SYSMGT2 0x69 +#define DEV_ENTRY_INIT_PASS 0xb8 +#define DEV_ENTRY_EINT_PASS 0xb9 +#define DEV_ENTRY_NMI_PASS 0xba +#define DEV_ENTRY_LINT0_PASS 0xbe +#define DEV_ENTRY_LINT1_PASS 0xbf + +/* constants to configure the command buffer */ +#define CMD_BUFFER_SIZE 8192 +#define CMD_BUFFER_ENTRIES 512 +#define MMIO_CMD_SIZE_SHIFT 56 +#define MMIO_CMD_SIZE_512 (0x9ULL << MMIO_CMD_SIZE_SHIFT) + +#define PAGE_MODE_1_LEVEL 0x01 +#define PAGE_MODE_2_LEVEL 0x02 +#define PAGE_MODE_3_LEVEL 0x03 + +#define IOMMU_PDE_NL_0 0x000ULL +#define IOMMU_PDE_NL_1 0x200ULL +#define IOMMU_PDE_NL_2 0x400ULL +#define IOMMU_PDE_NL_3 0x600ULL + +#define IOMMU_PTE_L2_INDEX(address) (((address) >> 30) & 0x1ffULL) +#define IOMMU_PTE_L1_INDEX(address) (((address) >> 21) & 0x1ffULL) +#define IOMMU_PTE_L0_INDEX(address) (((address) >> 12) & 0x1ffULL) + +#define IOMMU_MAP_SIZE_L1 (1ULL << 21) +#define IOMMU_MAP_SIZE_L2 (1ULL << 30) +#define IOMMU_MAP_SIZE_L3 (1ULL << 39) + +#define IOMMU_PTE_P (1ULL << 0) +#define IOMMU_PTE_U (1ULL << 59) +#define IOMMU_PTE_FC (1ULL << 60) +#define IOMMU_PTE_IR (1ULL << 61) +#define IOMMU_PTE_IW (1ULL << 62) + +#define IOMMU_L1_PDE(address) \ + ((address) | IOMMU_PDE_NL_1 | IOMMU_PTE_P | IOMMU_PTE_IR | IOMMU_PTE_IW) +#define IOMMU_L2_PDE(address) \ + ((address) | IOMMU_PDE_NL_2 | IOMMU_PTE_P | IOMMU_PTE_IR | IOMMU_PTE_IW) + +#define IOMMU_PAGE_MASK (((1ULL << 52) - 1) & ~0xfffULL) +#define IOMMU_PTE_PRESENT(pte) ((pte) & IOMMU_PTE_P) +#define IOMMU_PTE_PAGE(pte) (phys_to_virt((pte) & IOMMU_PAGE_MASK)) +#define IOMMU_PTE_MODE(pte) (((pte) >> 9) & 0x07) + +#define IOMMU_PROT_MASK 0x03 +#define IOMMU_PROT_IR 0x01 +#define IOMMU_PROT_IW 0x02 + +/* IOMMU capabilities */ +#define IOMMU_CAP_IOTLB 24 +#define IOMMU_CAP_NPCACHE 26 + +#define MAX_DOMAIN_ID 65536 + +struct protection_domain { + spinlock_t lock; + u16 id; + int mode; + u64 *pt_root; + void *priv; +}; + +struct dma_ops_domain { + struct list_head list; + struct protection_domain domain; + unsigned long aperture_size; + unsigned long next_bit; + unsigned long *bitmap; + u64 **pte_pages; +}; + +struct amd_iommu { + struct list_head list; + spinlock_t lock; + + u16 devid; + u16 cap_ptr; + + u64 mmio_phys; + u8 *mmio_base; + u32 cap; + u16 first_device; + u16 last_device; + u64 exclusion_start; + u64 exclusion_length; + + u8 *cmd_buf; + u32 cmd_buf_size; + + int need_sync; + + struct dma_ops_domain *default_dom; +}; + +extern struct list_head amd_iommu_list; + +struct dev_table_entry { + u32 data[8]; +}; + +struct unity_map_entry { + struct list_head list; + u16 devid_start; + u16 devid_end; + u64 address_start; + u64 address_end; + int prot; +}; + +extern struct list_head amd_iommu_unity_map; + +/* data structures for device handling */ +extern struct dev_table_entry *amd_iommu_dev_table; +extern u16 *amd_iommu_alias_table; +extern struct amd_iommu **amd_iommu_rlookup_table; + +extern unsigned amd_iommu_aperture_order; + +extern u16 amd_iommu_last_bdf; + +/* data structures for protection domain handling */ +extern struct protection_domain **amd_iommu_pd_table; +extern unsigned long *amd_iommu_pd_alloc_bitmap; + +extern int amd_iommu_isolate; + +static inline void print_devid(u16 devid, int nl) +{ + int bus = devid >> 8; + int dev = devid >> 3 & 0x1f; + int fn = devid & 0x07; + + printk("%02x:%02x.%x", bus, dev, fn); + if (nl) + printk("\n"); +} + +#endif diff --git a/include/asm-x86/cmpxchg_64.h b/include/asm-x86/cmpxchg_64.h index d9b26b9a28cf..17463ccf8166 100644 --- a/include/asm-x86/cmpxchg_64.h +++ b/include/asm-x86/cmpxchg_64.h @@ -93,6 +93,39 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old, return old; } +/* + * Always use locked operations when touching memory shared with a + * hypervisor, since the system may be SMP even if the guest kernel + * isn't. + */ +static inline unsigned long __sync_cmpxchg(volatile void *ptr, + unsigned long old, + unsigned long new, int size) +{ + unsigned long prev; + switch (size) { + case 1: + asm volatile("lock; cmpxchgb %b1,%2" + : "=a"(prev) + : "q"(new), "m"(*__xg(ptr)), "0"(old) + : "memory"); + return prev; + case 2: + asm volatile("lock; cmpxchgw %w1,%2" + : "=a"(prev) + : "r"(new), "m"(*__xg(ptr)), "0"(old) + : "memory"); + return prev; + case 4: + asm volatile("lock; cmpxchgl %1,%2" + : "=a"(prev) + : "r"(new), "m"(*__xg(ptr)), "0"(old) + : "memory"); + return prev; + } + return old; +} + static inline unsigned long __cmpxchg_local(volatile void *ptr, unsigned long old, unsigned long new, int size) @@ -139,6 +172,10 @@ static inline unsigned long __cmpxchg_local(volatile void *ptr, ((__typeof__(*(ptr)))__cmpxchg_local((ptr), (unsigned long)(o), \ (unsigned long)(n), \ sizeof(*(ptr)))) +#define sync_cmpxchg(ptr, o, n) \ + ((__typeof__(*(ptr)))__sync_cmpxchg((ptr), (unsigned long)(o), \ + (unsigned long)(n), \ + sizeof(*(ptr)))) #define cmpxchg64_local(ptr, o, n) \ ({ \ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ diff --git a/include/asm-x86/desc_defs.h b/include/asm-x86/desc_defs.h index eccb4ea1f918..f7bacf357dac 100644 --- a/include/asm-x86/desc_defs.h +++ b/include/asm-x86/desc_defs.h @@ -75,10 +75,14 @@ struct ldttss_desc64 { typedef struct gate_struct64 gate_desc; typedef struct ldttss_desc64 ldt_desc; typedef struct ldttss_desc64 tss_desc; +#define gate_offset(g) ((g).offset_low | ((unsigned long)(g).offset_middle << 16) | ((unsigned long)(g).offset_high << 32)) +#define gate_segment(g) ((g).segment) #else typedef struct desc_struct gate_desc; typedef struct desc_struct ldt_desc; typedef struct desc_struct tss_desc; +#define gate_offset(g) (((g).b & 0xffff0000) | ((g).a & 0x0000ffff)) +#define gate_segment(g) ((g).a >> 16) #endif struct desc_ptr { diff --git a/include/asm-x86/elf.h b/include/asm-x86/elf.h index 8f232dc5b5fe..7be4733c793e 100644 --- a/include/asm-x86/elf.h +++ b/include/asm-x86/elf.h @@ -83,9 +83,9 @@ extern unsigned int vdso_enabled; (((x)->e_machine == EM_386) || ((x)->e_machine == EM_486)) #include <asm/processor.h> +#include <asm/system.h> #ifdef CONFIG_X86_32 -#include <asm/system.h> /* for savesegment */ #include <asm/desc.h> #define elf_check_arch(x) elf_check_arch_ia32(x) diff --git a/include/asm-x86/fixmap_64.h b/include/asm-x86/fixmap_64.h index 626098823a0c..1a0b61eb02ff 100644 --- a/include/asm-x86/fixmap_64.h +++ b/include/asm-x86/fixmap_64.h @@ -46,9 +46,25 @@ enum fixed_addresses { FIX_EFI_IO_MAP_LAST_PAGE, FIX_EFI_IO_MAP_FIRST_PAGE = FIX_EFI_IO_MAP_LAST_PAGE + MAX_EFI_IO_PAGES - 1, +#ifdef CONFIG_PARAVIRT + FIX_PARAVIRT_BOOTMAP, +#endif #ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT FIX_OHCI1394_BASE, #endif + __end_of_permanent_fixed_addresses, + /* + * 256 temporary boot-time mappings, used by early_ioremap(), + * before ioremap() is functional. + * + * We round it up to the next 512 pages boundary so that we + * can have a single pgd entry and a single pte table: + */ +#define NR_FIX_BTMAPS 64 +#define FIX_BTMAPS_NESTING 4 + FIX_BTMAP_END = __end_of_permanent_fixed_addresses + 512 - + (__end_of_permanent_fixed_addresses & 511), + FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS*FIX_BTMAPS_NESTING - 1, __end_of_fixed_addresses }; diff --git a/include/asm-x86/gart.h b/include/asm-x86/gart.h index eeca2f51fd8f..417f76ea677b 100644 --- a/include/asm-x86/gart.h +++ b/include/asm-x86/gart.h @@ -22,8 +22,9 @@ extern int gart_iommu_aperture_allowed; extern int gart_iommu_aperture_disabled; extern int fix_aperture; #else -#define gart_iommu_aperture 0 -#define gart_iommu_aperture_allowed 0 +#define gart_iommu_aperture 0 +#define gart_iommu_aperture_allowed 0 +#define gart_iommu_aperture_disabled 1 static inline void early_gart_iommu_check(void) { diff --git a/include/asm-x86/hw_irq.h b/include/asm-x86/hw_irq.h index 18f067c310f7..77ba51df5668 100644 --- a/include/asm-x86/hw_irq.h +++ b/include/asm-x86/hw_irq.h @@ -48,6 +48,7 @@ extern void irq_move_cleanup_interrupt(void); extern void threshold_interrupt(void); extern void call_function_interrupt(void); +extern void call_function_single_interrupt(void); /* PIC specific functions */ extern void disable_8259A_irq(unsigned int irq); diff --git a/include/asm-x86/io.h b/include/asm-x86/io.h index 8e9eca93f9b9..c63563df4ac8 100644 --- a/include/asm-x86/io.h +++ b/include/asm-x86/io.h @@ -72,4 +72,17 @@ extern int ioremap_change_attr(unsigned long vaddr, unsigned long size, unsigned long prot_val); extern void __iomem *ioremap_wc(unsigned long offset, unsigned long size); +/* + * early_ioremap() and early_iounmap() are for temporary early boot-time + * mappings, before the real ioremap() is functional. + * A boot-time mapping is currently limited to at most 16 pages. + */ +extern void early_ioremap_init(void); +extern void early_ioremap_clear(void); +extern void early_ioremap_reset(void); +extern void *early_ioremap(unsigned long offset, unsigned long size); +extern void early_iounmap(void *addr, unsigned long size); +extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys); + + #endif /* _ASM_X86_IO_H */ diff --git a/include/asm-x86/io_32.h b/include/asm-x86/io_32.h index d71be8df9797..4df44ed54077 100644 --- a/include/asm-x86/io_32.h +++ b/include/asm-x86/io_32.h @@ -122,18 +122,6 @@ static inline void __iomem *ioremap(resource_size_t offset, unsigned long size) extern void iounmap(volatile void __iomem *addr); /* - * early_ioremap() and early_iounmap() are for temporary early boot-time - * mappings, before the real ioremap() is functional. - * A boot-time mapping is currently limited to at most 16 pages. - */ -extern void early_ioremap_init(void); -extern void early_ioremap_clear(void); -extern void early_ioremap_reset(void); -extern void *early_ioremap(unsigned long offset, unsigned long size); -extern void early_iounmap(void *addr, unsigned long size); -extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys); - -/* * ISA I/O bus memory addresses are 1:1 with the physical address. */ #define isa_virt_to_bus virt_to_phys diff --git a/include/asm-x86/irq_vectors.h b/include/asm-x86/irq_vectors.h index b58581e2e24e..3f723c796f9f 100644 --- a/include/asm-x86/irq_vectors.h +++ b/include/asm-x86/irq_vectors.h @@ -64,6 +64,7 @@ # define INVALIDATE_TLB_VECTOR 0xfd # define RESCHEDULE_VECTOR 0xfc # define CALL_FUNCTION_VECTOR 0xfb +# define CALL_FUNCTION_SINGLE_VECTOR 0xfa # define THERMAL_APIC_VECTOR 0xf0 #else @@ -72,6 +73,7 @@ #define ERROR_APIC_VECTOR 0xfe #define RESCHEDULE_VECTOR 0xfd #define CALL_FUNCTION_VECTOR 0xfc +#define CALL_FUNCTION_SINGLE_VECTOR 0xfb #define THERMAL_APIC_VECTOR 0xfa #define THRESHOLD_APIC_VECTOR 0xf9 #define INVALIDATE_TLB_VECTOR_END 0xf7 diff --git a/include/asm-x86/irqflags.h b/include/asm-x86/irqflags.h index 24d71b1eb189..60d13fe56560 100644 --- a/include/asm-x86/irqflags.h +++ b/include/asm-x86/irqflags.h @@ -51,6 +51,61 @@ static inline void native_halt(void) #endif +#ifdef CONFIG_X86_64 +/* + * Only returns from a trap or exception to a NMI context (intra-privilege + * level near return) to the same SS and CS segments. Should be used + * upon trap or exception return when nested over a NMI context so no iret is + * issued. It takes care of modifying the eflags, rsp and returning to the + * previous function. + * + * The stack, at that point, looks like : + * + * 0(rsp) RIP + * 8(rsp) CS + * 16(rsp) EFLAGS + * 24(rsp) RSP + * 32(rsp) SS + * + * Upon execution : + * Copy EIP to the top of the return stack + * Update top of return stack address + * Pop eflags into the eflags register + * Make the return stack current + * Near return (popping the return address from the return stack) + */ +#define NATIVE_INTERRUPT_RETURN_NMI_SAFE pushq %rax; \ + movq %rsp, %rax; \ + movq 24+8(%rax), %rsp; \ + pushq 0+8(%rax); \ + pushq 16+8(%rax); \ + movq (%rax), %rax; \ + popfq; \ + ret +#else +/* + * Protected mode only, no V8086. Implies that protected mode must + * be entered before NMIs or MCEs are enabled. Only returns from a trap or + * exception to a NMI context (intra-privilege level far return). Should be used + * upon trap or exception return when nested over a NMI context so no iret is + * issued. + * + * The stack, at that point, looks like : + * + * 0(esp) EIP + * 4(esp) CS + * 8(esp) EFLAGS + * + * Upon execution : + * Copy the stack eflags to top of stack + * Pop eflags into the eflags register + * Far return: pop EIP and CS into their register, and additionally pop EFLAGS. + */ +#define NATIVE_INTERRUPT_RETURN_NMI_SAFE pushl 8(%esp); \ + popfl; \ + lret $4 +#endif + #ifdef CONFIG_PARAVIRT #include <asm/paravirt.h> #else @@ -109,16 +164,25 @@ static inline unsigned long __raw_local_irq_save(void) #define ENABLE_INTERRUPTS(x) sti #define DISABLE_INTERRUPTS(x) cli +#define INTERRUPT_RETURN_NMI_SAFE NATIVE_INTERRUPT_RETURN_NMI_SAFE #ifdef CONFIG_X86_64 +#define SWAPGS_UNSAFE_STACK swapgs #define INTERRUPT_RETURN iretq -#define ENABLE_INTERRUPTS_SYSCALL_RET \ - movq %gs:pda_oldrsp, %rsp; \ - swapgs; \ - sysretq; +#define USERGS_SYSRET64 \ + swapgs; \ + sysretq; +#define USERGS_SYSRET32 \ + swapgs; \ + sysretl +#define ENABLE_INTERRUPTS_SYSEXIT32 \ + swapgs; \ + sti; \ + sysexit + #else #define INTERRUPT_RETURN iret -#define ENABLE_INTERRUPTS_SYSCALL_RET sti; sysexit +#define ENABLE_INTERRUPTS_SYSEXIT sti; sysexit #define GET_CR0_INTO_EAX movl %cr0, %eax #endif @@ -178,7 +242,8 @@ static inline void trace_hardirqs_fixup(void) * Either way, this is a good way to document that we don't * have a reliable stack. x86_64 only. */ -#define SWAPGS_UNSAFE_STACK swapgs +#define ARCH_TRACE_IRQS_ON call trace_hardirqs_on_thunk +#define ARCH_TRACE_IRQS_OFF call trace_hardirqs_off_thunk #define ARCH_LOCKDEP_SYS_EXIT call lockdep_sys_exit_thunk #define ARCH_LOCKDEP_SYS_EXIT_IRQ \ TRACE_IRQS_ON; \ diff --git a/include/asm-x86/mach-default/entry_arch.h b/include/asm-x86/mach-default/entry_arch.h index bc861469bdba..9283b60a1dd2 100644 --- a/include/asm-x86/mach-default/entry_arch.h +++ b/include/asm-x86/mach-default/entry_arch.h @@ -13,6 +13,7 @@ BUILD_INTERRUPT(reschedule_interrupt,RESCHEDULE_VECTOR) BUILD_INTERRUPT(invalidate_interrupt,INVALIDATE_TLB_VECTOR) BUILD_INTERRUPT(call_function_interrupt,CALL_FUNCTION_VECTOR) +BUILD_INTERRUPT(call_function_single_interrupt,CALL_FUNCTION_SINGLE_VECTOR) #endif /* diff --git a/include/asm-x86/mach-voyager/entry_arch.h b/include/asm-x86/mach-voyager/entry_arch.h index 4a1e1e8c10b6..ae52624b5937 100644 --- a/include/asm-x86/mach-voyager/entry_arch.h +++ b/include/asm-x86/mach-voyager/entry_arch.h @@ -23,4 +23,4 @@ BUILD_INTERRUPT(qic_invalidate_interrupt, QIC_INVALIDATE_CPI); BUILD_INTERRUPT(qic_reschedule_interrupt, QIC_RESCHEDULE_CPI); BUILD_INTERRUPT(qic_enable_irq_interrupt, QIC_ENABLE_IRQ_CPI); BUILD_INTERRUPT(qic_call_function_interrupt, QIC_CALL_FUNCTION_CPI); - +BUILD_INTERRUPT(qic_call_function_single_interrupt, QIC_CALL_FUNCTION_SINGLE_CPI); diff --git a/include/asm-x86/mmu_context.h b/include/asm-x86/mmu_context.h index 6598450da6c6..fac57014e7c6 100644 --- a/include/asm-x86/mmu_context.h +++ b/include/asm-x86/mmu_context.h @@ -1,5 +1,37 @@ +#ifndef __ASM_X86_MMU_CONTEXT_H +#define __ASM_X86_MMU_CONTEXT_H + +#include <asm/desc.h> +#include <asm/atomic.h> +#include <asm/pgalloc.h> +#include <asm/tlbflush.h> +#include <asm/paravirt.h> +#ifndef CONFIG_PARAVIRT +#include <asm-generic/mm_hooks.h> + +static inline void paravirt_activate_mm(struct mm_struct *prev, + struct mm_struct *next) +{ +} +#endif /* !CONFIG_PARAVIRT */ + +/* + * Used for LDT copy/destruction. + */ +int init_new_context(struct task_struct *tsk, struct mm_struct *mm); +void destroy_context(struct mm_struct *mm); + #ifdef CONFIG_X86_32 # include "mmu_context_32.h" #else # include "mmu_context_64.h" #endif + +#define activate_mm(prev, next) \ +do { \ + paravirt_activate_mm((prev), (next)); \ + switch_mm((prev), (next), NULL); \ +} while (0); + + +#endif /* __ASM_X86_MMU_CONTEXT_H */ diff --git a/include/asm-x86/mmu_context_32.h b/include/asm-x86/mmu_context_32.h index 9756ae0f1dd3..824fc575c6d8 100644 --- a/include/asm-x86/mmu_context_32.h +++ b/include/asm-x86/mmu_context_32.h @@ -1,28 +1,6 @@ #ifndef __I386_SCHED_H #define __I386_SCHED_H -#include <asm/desc.h> -#include <asm/atomic.h> -#include <asm/pgalloc.h> -#include <asm/tlbflush.h> -#include <asm/paravirt.h> -#ifndef CONFIG_PARAVIRT -#include <asm-generic/mm_hooks.h> - -static inline void paravirt_activate_mm(struct mm_struct *prev, - struct mm_struct *next) -{ -} -#endif /* !CONFIG_PARAVIRT */ - - -/* - * Used for LDT copy/destruction. - */ -int init_new_context(struct task_struct *tsk, struct mm_struct *mm); -void destroy_context(struct mm_struct *mm); - - static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) { #ifdef CONFIG_SMP @@ -75,10 +53,4 @@ static inline void switch_mm(struct mm_struct *prev, #define deactivate_mm(tsk, mm) \ asm("movl %0,%%gs": :"r" (0)); -#define activate_mm(prev, next) \ -do { \ - paravirt_activate_mm((prev), (next)); \ - switch_mm((prev), (next), NULL); \ -} while (0); - #endif diff --git a/include/asm-x86/mmu_context_64.h b/include/asm-x86/mmu_context_64.h index ca44c71e7fb3..c7000634ccae 100644 --- a/include/asm-x86/mmu_context_64.h +++ b/include/asm-x86/mmu_context_64.h @@ -1,21 +1,7 @@ #ifndef __X86_64_MMU_CONTEXT_H #define __X86_64_MMU_CONTEXT_H -#include <asm/desc.h> -#include <asm/atomic.h> -#include <asm/pgalloc.h> #include <asm/pda.h> -#include <asm/pgtable.h> -#include <asm/tlbflush.h> -#ifndef CONFIG_PARAVIRT -#include <asm-generic/mm_hooks.h> -#endif - -/* - * possibly do the LDT unload here? - */ -int init_new_context(struct task_struct *tsk, struct mm_struct *mm); -void destroy_context(struct mm_struct *mm); static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) { @@ -65,8 +51,4 @@ do { \ asm volatile("movl %0,%%fs"::"r"(0)); \ } while (0) -#define activate_mm(prev, next) \ - switch_mm((prev), (next), NULL) - - #endif diff --git a/include/asm-x86/msr.h b/include/asm-x86/msr.h index 2b5f2c91db25..ca110ee73f07 100644 --- a/include/asm-x86/msr.h +++ b/include/asm-x86/msr.h @@ -66,7 +66,7 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr, static inline void native_write_msr(unsigned int msr, unsigned low, unsigned high) { - asm volatile("wrmsr" : : "c" (msr), "a"(low), "d" (high)); + asm volatile("wrmsr" : : "c" (msr), "a"(low), "d" (high) : "memory"); } static inline int native_write_msr_safe(unsigned int msr, @@ -81,7 +81,8 @@ static inline int native_write_msr_safe(unsigned int msr, _ASM_EXTABLE(2b, 3b) : "=a" (err) : "c" (msr), "0" (low), "d" (high), - "i" (-EFAULT)); + "i" (-EFAULT) + : "memory"); return err; } diff --git a/include/asm-x86/page_64.h b/include/asm-x86/page_64.h index cac5b9e78265..010d12db80dc 100644 --- a/include/asm-x86/page_64.h +++ b/include/asm-x86/page_64.h @@ -26,7 +26,13 @@ #define PUD_PAGE_SIZE (_AC(1, UL) << PUD_SHIFT) #define PUD_PAGE_MASK (~(PUD_PAGE_SIZE-1)) -#define __PAGE_OFFSET _AC(0xffff810000000000, UL) +/* + * Set __PAGE_OFFSET to the most negative possible address + + * PGDIR_SIZE*16 (pgd slot 272). The gap is to allow a space for a + * hypervisor to fit. Choosing 16 slots here is arbitrary, but it's + * what Xen requires. + */ +#define __PAGE_OFFSET _AC(0xffff880000000000, UL) #define __PHYSICAL_START CONFIG_PHYSICAL_START #define __KERNEL_ALIGN 0x200000 diff --git a/include/asm-x86/paravirt.h b/include/asm-x86/paravirt.h index 41f5447efd88..dd7f2a4c59d2 100644 --- a/include/asm-x86/paravirt.h +++ b/include/asm-x86/paravirt.h @@ -115,6 +115,9 @@ struct pv_cpu_ops { void (*set_ldt)(const void *desc, unsigned entries); unsigned long (*store_tr)(void); void (*load_tls)(struct thread_struct *t, unsigned int cpu); +#ifdef CONFIG_X86_64 + void (*load_gs_index)(unsigned int idx); +#endif void (*write_ldt_entry)(struct desc_struct *ldt, int entrynum, const void *desc); void (*write_gdt_entry)(struct desc_struct *, @@ -141,10 +144,37 @@ struct pv_cpu_ops { u64 (*read_pmc)(int counter); unsigned long long (*read_tscp)(unsigned int *aux); - /* These two are jmp to, not actually called. */ - void (*irq_enable_syscall_ret)(void); + /* + * Atomically enable interrupts and return to userspace. This + * is only ever used to return to 32-bit processes; in a + * 64-bit kernel, it's used for 32-on-64 compat processes, but + * never native 64-bit processes. (Jump, not call.) + */ + void (*irq_enable_sysexit)(void); + + /* + * Switch to usermode gs and return to 64-bit usermode using + * sysret. Only used in 64-bit kernels to return to 64-bit + * processes. Usermode register state, including %rsp, must + * already be restored. + */ + void (*usergs_sysret64)(void); + + /* + * Switch to usermode gs and return to 32-bit usermode using + * sysret. Used to return to 32-on-64 compat processes. + * Other usermode register state, including %esp, must already + * be restored. + */ + void (*usergs_sysret32)(void); + + /* Normal iret. Jump to this with the standard iret stack + frame set up. */ void (*iret)(void); + /* Return from NMI. (?) */ + void (*nmi_return)(void); + void (*swapgs)(void); struct pv_lazy_ops lazy_mode; @@ -165,6 +195,10 @@ struct pv_irq_ops { void (*irq_enable)(void); void (*safe_halt)(void); void (*halt)(void); + +#ifdef CONFIG_X86_64 + void (*adjust_exception_frame)(void); +#endif }; struct pv_apic_ops { @@ -219,7 +253,14 @@ struct pv_mmu_ops { void (*flush_tlb_others)(const cpumask_t *cpus, struct mm_struct *mm, unsigned long va); - /* Hooks for allocating/releasing pagetable pages */ + /* Hooks for allocating and freeing a pagetable top-level */ + int (*pgd_alloc)(struct mm_struct *mm); + void (*pgd_free)(struct mm_struct *mm, pgd_t *pgd); + + /* + * Hooks for allocating/releasing pagetable pages when they're + * attached to a pagetable + */ void (*alloc_pte)(struct mm_struct *mm, u32 pfn); void (*alloc_pmd)(struct mm_struct *mm, u32 pfn); void (*alloc_pmd_clone)(u32 pfn, u32 clonepfn, u32 start, u32 count); @@ -452,10 +493,17 @@ int paravirt_disable_iospace(void); #define VEXTRA_CLOBBERS , "rax", "r8", "r9", "r10", "r11" #endif +#ifdef CONFIG_PARAVIRT_DEBUG +#define PVOP_TEST_NULL(op) BUG_ON(op == NULL) +#else +#define PVOP_TEST_NULL(op) ((void)op) +#endif + #define __PVOP_CALL(rettype, op, pre, post, ...) \ ({ \ rettype __ret; \ PVOP_CALL_ARGS; \ + PVOP_TEST_NULL(op); \ /* This is 32-bit specific, but is okay in 64-bit */ \ /* since this condition will never hold */ \ if (sizeof(rettype) > sizeof(unsigned long)) { \ @@ -484,6 +532,7 @@ int paravirt_disable_iospace(void); #define __PVOP_VCALL(op, pre, post, ...) \ ({ \ PVOP_VCALL_ARGS; \ + PVOP_TEST_NULL(op); \ asm volatile(pre \ paravirt_alt(PARAVIRT_CALL) \ post \ @@ -802,6 +851,13 @@ static inline void load_TLS(struct thread_struct *t, unsigned cpu) PVOP_VCALL2(pv_cpu_ops.load_tls, t, cpu); } +#ifdef CONFIG_X86_64 +static inline void load_gs_index(unsigned int gs) +{ + PVOP_VCALL1(pv_cpu_ops.load_gs_index, gs); +} +#endif + static inline void write_ldt_entry(struct desc_struct *dt, int entry, const void *desc) { @@ -925,6 +981,16 @@ static inline void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm, PVOP_VCALL3(pv_mmu_ops.flush_tlb_others, &cpumask, mm, va); } +static inline int paravirt_pgd_alloc(struct mm_struct *mm) +{ + return PVOP_CALL1(int, pv_mmu_ops.pgd_alloc, mm); +} + +static inline void paravirt_pgd_free(struct mm_struct *mm, pgd_t *pgd) +{ + PVOP_VCALL2(pv_mmu_ops.pgd_free, mm, pgd); +} + static inline void paravirt_alloc_pte(struct mm_struct *mm, unsigned pfn) { PVOP_VCALL2(pv_mmu_ops.alloc_pte, mm, pfn); @@ -1430,54 +1496,90 @@ static inline unsigned long __raw_local_irq_save(void) #define PV_RESTORE_REGS popq %rdx; popq %rcx; popq %rdi; popq %rax #define PARA_PATCH(struct, off) ((PARAVIRT_PATCH_##struct + (off)) / 8) #define PARA_SITE(ptype, clobbers, ops) _PVSITE(ptype, clobbers, ops, .quad, 8) +#define PARA_INDIRECT(addr) *addr(%rip) #else #define PV_SAVE_REGS pushl %eax; pushl %edi; pushl %ecx; pushl %edx #define PV_RESTORE_REGS popl %edx; popl %ecx; popl %edi; popl %eax #define PARA_PATCH(struct, off) ((PARAVIRT_PATCH_##struct + (off)) / 4) #define PARA_SITE(ptype, clobbers, ops) _PVSITE(ptype, clobbers, ops, .long, 4) +#define PARA_INDIRECT(addr) *%cs:addr #endif #define INTERRUPT_RETURN \ PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_iret), CLBR_NONE, \ - jmp *%cs:pv_cpu_ops+PV_CPU_iret) + jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_iret)) + +#define INTERRUPT_RETURN_NMI_SAFE \ + PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_nmi_return), CLBR_NONE, \ + jmp *%cs:pv_cpu_ops+PV_CPU_nmi_return) #define DISABLE_INTERRUPTS(clobbers) \ PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_disable), clobbers, \ - PV_SAVE_REGS; \ - call *%cs:pv_irq_ops+PV_IRQ_irq_disable; \ + PV_SAVE_REGS; \ + call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_disable); \ PV_RESTORE_REGS;) \ #define ENABLE_INTERRUPTS(clobbers) \ PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_enable), clobbers, \ - PV_SAVE_REGS; \ - call *%cs:pv_irq_ops+PV_IRQ_irq_enable; \ + PV_SAVE_REGS; \ + call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_enable); \ PV_RESTORE_REGS;) -#define ENABLE_INTERRUPTS_SYSCALL_RET \ - PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_irq_enable_syscall_ret),\ +#define USERGS_SYSRET32 \ + PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret32), \ CLBR_NONE, \ - jmp *%cs:pv_cpu_ops+PV_CPU_irq_enable_syscall_ret) - + jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret32)) #ifdef CONFIG_X86_32 -#define GET_CR0_INTO_EAX \ - push %ecx; push %edx; \ - call *pv_cpu_ops+PV_CPU_read_cr0; \ +#define GET_CR0_INTO_EAX \ + push %ecx; push %edx; \ + call PARA_INDIRECT(pv_cpu_ops+PV_CPU_read_cr0); \ pop %edx; pop %ecx -#else + +#define ENABLE_INTERRUPTS_SYSEXIT \ + PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_irq_enable_sysexit), \ + CLBR_NONE, \ + jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_irq_enable_sysexit)) + + +#else /* !CONFIG_X86_32 */ + +/* + * If swapgs is used while the userspace stack is still current, + * there's no way to call a pvop. The PV replacement *must* be + * inlined, or the swapgs instruction must be trapped and emulated. + */ +#define SWAPGS_UNSAFE_STACK \ + PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), CLBR_NONE, \ + swapgs) + #define SWAPGS \ PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), CLBR_NONE, \ PV_SAVE_REGS; \ - call *pv_cpu_ops+PV_CPU_swapgs; \ + call PARA_INDIRECT(pv_cpu_ops+PV_CPU_swapgs); \ PV_RESTORE_REGS \ ) -#define GET_CR2_INTO_RCX \ - call *pv_mmu_ops+PV_MMU_read_cr2; \ - movq %rax, %rcx; \ +#define GET_CR2_INTO_RCX \ + call PARA_INDIRECT(pv_mmu_ops+PV_MMU_read_cr2); \ + movq %rax, %rcx; \ xorq %rax, %rax; -#endif +#define PARAVIRT_ADJUST_EXCEPTION_FRAME \ + PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_adjust_exception_frame), \ + CLBR_NONE, \ + call PARA_INDIRECT(pv_irq_ops+PV_IRQ_adjust_exception_frame)) + +#define USERGS_SYSRET64 \ + PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret64), \ + CLBR_NONE, \ + jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64)) + +#define ENABLE_INTERRUPTS_SYSEXIT32 \ + PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_irq_enable_sysexit), \ + CLBR_NONE, \ + jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_irq_enable_sysexit)) +#endif /* CONFIG_X86_32 */ #endif /* __ASSEMBLY__ */ #endif /* CONFIG_PARAVIRT */ diff --git a/include/asm-x86/pgalloc.h b/include/asm-x86/pgalloc.h index 91e4641f3f31..d63ea431cb3b 100644 --- a/include/asm-x86/pgalloc.h +++ b/include/asm-x86/pgalloc.h @@ -5,9 +5,13 @@ #include <linux/mm.h> /* for struct page */ #include <linux/pagemap.h> +static inline int __paravirt_pgd_alloc(struct mm_struct *mm) { return 0; } + #ifdef CONFIG_PARAVIRT #include <asm/paravirt.h> #else +#define paravirt_pgd_alloc(mm) __paravirt_pgd_alloc(mm) +static inline void paravirt_pgd_free(struct mm_struct *mm, pgd_t *pgd) {} static inline void paravirt_alloc_pte(struct mm_struct *mm, unsigned long pfn) {} static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned long pfn) {} static inline void paravirt_alloc_pmd_clone(unsigned long pfn, unsigned long clonepfn, diff --git a/include/asm-x86/pgtable.h b/include/asm-x86/pgtable.h index 39329257ed88..b03aaed85f4a 100644 --- a/include/asm-x86/pgtable.h +++ b/include/asm-x86/pgtable.h @@ -357,6 +357,26 @@ void set_pte_vaddr(unsigned long vaddr, pte_t pte); # include "pgtable_64.h" #endif +/* + * the pgd page can be thought of an array like this: pgd_t[PTRS_PER_PGD] + * + * this macro returns the index of the entry in the pgd page which would + * control the given virtual address + */ +#define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1)) + +/* + * pgd_offset() returns a (pgd_t *) + * pgd_index() is used get the offset into the pgd page's array of pgd_t's; + */ +#define pgd_offset(mm, address) ((mm)->pgd + pgd_index((address))) +/* + * a shortcut which implies the use of the kernel's pgd, instead + * of a process's + */ +#define pgd_offset_k(address) pgd_offset(&init_mm, (address)) + + #define KERNEL_PGD_BOUNDARY pgd_index(PAGE_OFFSET) #define KERNEL_PGD_PTRS (PTRS_PER_PGD - KERNEL_PGD_BOUNDARY) @@ -425,6 +445,8 @@ static inline void native_set_pte_at(struct mm_struct *mm, unsigned long addr, * race with other CPU's that might be updating the dirty * bit at the same time. */ +struct vm_area_struct; + #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, diff --git a/include/asm-x86/pgtable_32.h b/include/asm-x86/pgtable_32.h index d7248132caf4..8b5f6589f46e 100644 --- a/include/asm-x86/pgtable_32.h +++ b/include/asm-x86/pgtable_32.h @@ -119,26 +119,6 @@ extern unsigned long pg0[]; */ #define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot)) -/* - * the pgd page can be thought of an array like this: pgd_t[PTRS_PER_PGD] - * - * this macro returns the index of the entry in the pgd page which would - * control the given virtual address - */ -#define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1)) -#define pgd_index_k(addr) pgd_index((addr)) - -/* - * pgd_offset() returns a (pgd_t *) - * pgd_index() is used get the offset into the pgd page's array of pgd_t's; - */ -#define pgd_offset(mm, address) ((mm)->pgd + pgd_index((address))) - -/* - * a shortcut which implies the use of the kernel's pgd, instead - * of a process's - */ -#define pgd_offset_k(address) pgd_offset(&init_mm, (address)) static inline int pud_large(pud_t pud) { return 0; } diff --git a/include/asm-x86/pgtable_64.h b/include/asm-x86/pgtable_64.h index 7836ccc28cf2..7388fd8d51f1 100644 --- a/include/asm-x86/pgtable_64.h +++ b/include/asm-x86/pgtable_64.h @@ -70,6 +70,9 @@ extern void paging_init(void); struct mm_struct; +void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte); + + static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { @@ -196,12 +199,9 @@ static inline int pmd_bad(pmd_t pmd) #define pgd_page_vaddr(pgd) \ ((unsigned long)__va((unsigned long)pgd_val((pgd)) & PTE_MASK)) #define pgd_page(pgd) (pfn_to_page(pgd_val((pgd)) >> PAGE_SHIFT)) -#define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1)) -#define pgd_offset(mm, address) ((mm)->pgd + pgd_index((address))) -#define pgd_offset_k(address) (init_level4_pgt + pgd_index((address))) #define pgd_present(pgd) (pgd_val(pgd) & _PAGE_PRESENT) static inline int pgd_large(pgd_t pgd) { return 0; } -#define mk_kernel_pgd(address) ((pgd_t){ (address) | _KERNPG_TABLE }) +#define mk_kernel_pgd(address) __pgd((address) | _KERNPG_TABLE) /* PUD - Level3 access */ /* to find an entry in a page-table-directory. */ diff --git a/include/asm-x86/processor.h b/include/asm-x86/processor.h index 7f96eaafb832..f5dada2d4a91 100644 --- a/include/asm-x86/processor.h +++ b/include/asm-x86/processor.h @@ -536,6 +536,8 @@ static inline void load_sp0(struct tss_struct *tss, #define set_iopl_mask native_set_iopl_mask #define SWAPGS swapgs + +#define PARAVIRT_ADJUST_EXCEPTION_FRAME /* */ #endif /* CONFIG_PARAVIRT */ /* diff --git a/include/asm-x86/required-features.h b/include/asm-x86/required-features.h index 8c387198ca88..adec887dd7cd 100644 --- a/include/asm-x86/required-features.h +++ b/include/asm-x86/required-features.h @@ -42,7 +42,7 @@ #endif #ifdef CONFIG_X86_64 -#define NEED_PSE (1<<(X86_FEATURE_PSE & 31)) +#define NEED_PSE 0 #define NEED_MSR (1<<(X86_FEATURE_MSR & 31)) #define NEED_PGE (1<<(X86_FEATURE_PGE & 31)) #define NEED_FXSR (1<<(X86_FEATURE_FXSR & 31)) diff --git a/include/asm-x86/setup.h b/include/asm-x86/setup.h index 269ba7fe21d1..1d121c632d9e 100644 --- a/include/asm-x86/setup.h +++ b/include/asm-x86/setup.h @@ -56,6 +56,10 @@ extern void probe_roms(void); extern unsigned long init_pg_tables_start; extern unsigned long init_pg_tables_end; +#else +void __init x86_64_start_kernel(char *real_mode); +void __init x86_64_start_reservations(char *real_mode_data); + #endif /* __i386__ */ #endif /* _SETUP */ #endif /* __ASSEMBLY__ */ diff --git a/include/asm-x86/smp.h b/include/asm-x86/smp.h index fad45f6a193f..b3860ea91333 100644 --- a/include/asm-x86/smp.h +++ b/include/asm-x86/smp.h @@ -50,9 +50,9 @@ struct smp_ops { void (*smp_send_stop)(void); void (*smp_send_reschedule)(int cpu); - int (*smp_call_function_mask)(cpumask_t mask, - void (*func)(void *info), void *info, - int wait); + + void (*send_call_func_ipi)(cpumask_t mask); + void (*send_call_func_single_ipi)(int cpu); }; /* Globals due to paravirt */ @@ -94,17 +94,22 @@ static inline void smp_send_reschedule(int cpu) smp_ops.smp_send_reschedule(cpu); } -static inline int smp_call_function_mask(cpumask_t mask, - void (*func) (void *info), void *info, - int wait) +static inline void arch_send_call_function_single_ipi(int cpu) +{ + smp_ops.send_call_func_single_ipi(cpu); +} + +static inline void arch_send_call_function_ipi(cpumask_t mask) { - return smp_ops.smp_call_function_mask(mask, func, info, wait); + smp_ops.send_call_func_ipi(mask); } void native_smp_prepare_boot_cpu(void); void native_smp_prepare_cpus(unsigned int max_cpus); void native_smp_cpus_done(unsigned int max_cpus); int native_cpu_up(unsigned int cpunum); +void native_send_call_func_ipi(cpumask_t mask); +void native_send_call_func_single_ipi(int cpu); extern int __cpu_disable(void); extern void __cpu_die(unsigned int cpu); @@ -191,7 +196,5 @@ static inline int hard_smp_processor_id(void) extern void cpu_uninit(void); #endif -extern void lock_ipi_call_lock(void); -extern void unlock_ipi_call_lock(void); #endif /* __ASSEMBLY__ */ #endif diff --git a/include/asm-x86/system.h b/include/asm-x86/system.h index 91f3ab98dbaa..45641bcf738a 100644 --- a/include/asm-x86/system.h +++ b/include/asm-x86/system.h @@ -140,7 +140,7 @@ __asm__ __volatile__ ("movw %%dx,%1\n\t" \ #define set_base(ldt, base) _set_base(((char *)&(ldt)) , (base)) #define set_limit(ldt, limit) _set_limit(((char *)&(ldt)) , ((limit)-1)) -extern void load_gs_index(unsigned); +extern void native_load_gs_index(unsigned); /* * Load a segment. Fall back on loading the zero @@ -157,14 +157,14 @@ extern void load_gs_index(unsigned); "jmp 2b\n" \ ".previous\n" \ _ASM_EXTABLE(1b,3b) \ - : :"r" (value), "r" (0)) + : :"r" (value), "r" (0) : "memory") /* * Save a segment register away */ #define savesegment(seg, value) \ - asm volatile("mov %%" #seg ",%0":"=rm" (value)) + asm("mov %%" #seg ",%0":"=rm" (value) : : "memory") static inline unsigned long get_limit(unsigned long segment) { @@ -286,6 +286,7 @@ static inline void native_wbinvd(void) #ifdef CONFIG_X86_64 #define read_cr8() (native_read_cr8()) #define write_cr8(x) (native_write_cr8(x)) +#define load_gs_index native_load_gs_index #endif /* Clear the 'TS' bit */ diff --git a/include/asm-x86/xen/events.h b/include/asm-x86/xen/events.h index 596312a7bfc9..f8d57ea1f05f 100644 --- a/include/asm-x86/xen/events.h +++ b/include/asm-x86/xen/events.h @@ -4,6 +4,7 @@ enum ipi_vector { XEN_RESCHEDULE_VECTOR, XEN_CALL_FUNCTION_VECTOR, + XEN_CALL_FUNCTION_SINGLE_VECTOR, XEN_NR_IPIS, }; diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index 181006cc94a0..b39f49d9d303 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -22,10 +22,13 @@ * PREEMPT_MASK: 0x000000ff * SOFTIRQ_MASK: 0x0000ff00 * HARDIRQ_MASK: 0x0fff0000 + * HARDNMI_MASK: 0x40000000 */ #define PREEMPT_BITS 8 #define SOFTIRQ_BITS 8 +#define HARDNMI_BITS 1 + #ifndef HARDIRQ_BITS #define HARDIRQ_BITS 12 @@ -45,16 +48,19 @@ #define PREEMPT_SHIFT 0 #define SOFTIRQ_SHIFT (PREEMPT_SHIFT + PREEMPT_BITS) #define HARDIRQ_SHIFT (SOFTIRQ_SHIFT + SOFTIRQ_BITS) +#define HARDNMI_SHIFT (30) #define __IRQ_MASK(x) ((1UL << (x))-1) #define PREEMPT_MASK (__IRQ_MASK(PREEMPT_BITS) << PREEMPT_SHIFT) #define SOFTIRQ_MASK (__IRQ_MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT) #define HARDIRQ_MASK (__IRQ_MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT) +#define HARDNMI_MASK (__IRQ_MASK(HARDNMI_BITS) << HARDNMI_SHIFT) #define PREEMPT_OFFSET (1UL << PREEMPT_SHIFT) #define SOFTIRQ_OFFSET (1UL << SOFTIRQ_SHIFT) #define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT) +#define HARDNMI_OFFSET (1UL << HARDNMI_SHIFT) #if PREEMPT_ACTIVE < (1 << (HARDIRQ_SHIFT + HARDIRQ_BITS)) #error PREEMPT_ACTIVE is too low! @@ -62,7 +68,9 @@ #define hardirq_count() (preempt_count() & HARDIRQ_MASK) #define softirq_count() (preempt_count() & SOFTIRQ_MASK) -#define irq_count() (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK)) +#define irq_count() \ + (preempt_count() & (HARDNMI_MASK | HARDIRQ_MASK | SOFTIRQ_MASK)) +#define hardnmi_count() (preempt_count() & HARDNMI_MASK) /* * Are we doing bottom half or hardware interrupt processing? @@ -71,6 +79,7 @@ #define in_irq() (hardirq_count()) #define in_softirq() (softirq_count()) #define in_interrupt() (irq_count()) +#define in_nmi() (hardnmi_count()) #if defined(CONFIG_PREEMPT) # define PREEMPT_INATOMIC_BASE kernel_locked() @@ -161,7 +170,19 @@ extern void irq_enter(void); */ extern void irq_exit(void); -#define nmi_enter() do { lockdep_off(); __irq_enter(); } while (0) -#define nmi_exit() do { __irq_exit(); lockdep_on(); } while (0) +#define nmi_enter() \ + do { \ + lockdep_off(); \ + BUG_ON(hardnmi_count()); \ + add_preempt_count(HARDNMI_OFFSET); \ + __irq_enter(); \ + } while (0) + +#define nmi_exit() \ + do { \ + __irq_exit(); \ + sub_preempt_count(HARDNMI_OFFSET); \ + lockdep_on(); \ + } while (0) #endif /* LINUX_HARDIRQ_H */ diff --git a/include/linux/smp.h b/include/linux/smp.h index 55232ccf9cfd..55261101d09a 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -7,9 +7,19 @@ */ #include <linux/errno.h> +#include <linux/list.h> +#include <linux/spinlock.h> +#include <linux/cpumask.h> extern void cpu_idle(void); +struct call_single_data { + struct list_head list; + void (*func) (void *info); + void *info; + unsigned int flags; +}; + #ifdef CONFIG_SMP #include <linux/preempt.h> @@ -52,15 +62,34 @@ extern void smp_cpus_done(unsigned int max_cpus); /* * Call a function on all other processors */ -int smp_call_function(void(*func)(void *info), void *info, int retry, int wait); - +int smp_call_function(void(*func)(void *info), void *info, int wait); +int smp_call_function_mask(cpumask_t mask, void(*func)(void *info), void *info, + int wait); int smp_call_function_single(int cpuid, void (*func) (void *info), void *info, - int retry, int wait); + int wait); +void __smp_call_function_single(int cpuid, struct call_single_data *data); + +/* + * Generic and arch helpers + */ +#ifdef CONFIG_USE_GENERIC_SMP_HELPERS +void generic_smp_call_function_single_interrupt(void); +void generic_smp_call_function_interrupt(void); +void init_call_single_data(void); +void ipi_call_lock(void); +void ipi_call_unlock(void); +void ipi_call_lock_irq(void); +void ipi_call_unlock_irq(void); +#else +static inline void init_call_single_data(void) +{ +} +#endif /* * Call a function on all processors */ -int on_each_cpu(void (*func) (void *info), void *info, int retry, int wait); +int on_each_cpu(void (*func) (void *info), void *info, int wait); #define MSG_ALL_BUT_SELF 0x8000 /* Assume <32768 CPU's */ #define MSG_ALL 0x8001 @@ -90,9 +119,9 @@ static inline int up_smp_call_function(void (*func)(void *), void *info) { return 0; } -#define smp_call_function(func, info, retry, wait) \ +#define smp_call_function(func, info, wait) \ (up_smp_call_function(func, info)) -#define on_each_cpu(func,info,retry,wait) \ +#define on_each_cpu(func,info,wait) \ ({ \ local_irq_disable(); \ func(info); \ @@ -102,7 +131,7 @@ static inline int up_smp_call_function(void (*func)(void *), void *info) static inline void smp_send_reschedule(int cpu) { } #define num_booting_cpus() 1 #define smp_prepare_boot_cpu() do {} while (0) -#define smp_call_function_single(cpuid, func, info, retry, wait) \ +#define smp_call_function_single(cpuid, func, info, wait) \ ({ \ WARN_ON(cpuid != 0); \ local_irq_disable(); \ @@ -112,7 +141,9 @@ static inline void smp_send_reschedule(int cpu) { } }) #define smp_call_function_mask(mask, func, info, wait) \ (up_smp_call_function(func, info)) - +static inline void init_call_single_data(void) +{ +} #endif /* !SMP */ /* diff --git a/include/linux/stringify.h b/include/linux/stringify.h index 0b4388356c87..de04a96c50de 100644 --- a/include/linux/stringify.h +++ b/include/linux/stringify.h @@ -6,7 +6,12 @@ * converts to "bar". */ +#ifdef __STDC__ +#define __stringify_1(x...) #x +#define __stringify(x...) __stringify_1(x) +#else /* Support gcc -traditional, without commas. */ #define __stringify_1(x) #x #define __stringify(x) __stringify_1(x) +#endif #endif /* !__LINUX_STRINGIFY_H */ |