diff options
Diffstat (limited to 'arch/x86')
34 files changed, 332 insertions, 528 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 483775f42d2..da349723d41 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -64,7 +64,6 @@ config X86 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 diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index 6f9872658dd..2bf18059fbe 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -10,7 +10,6 @@ CONFIG_TASK_IO_ACCOUNTING=y CONFIG_AUDIT=y CONFIG_LOG_BUF_SHIFT=18 CONFIG_CGROUPS=y -CONFIG_CGROUP_NS=y CONFIG_CGROUP_FREEZER=y CONFIG_CPUSETS=y CONFIG_CGROUP_CPUACCT=y diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index ee01a9d5d4f..22a0dc8e51d 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -11,7 +11,6 @@ CONFIG_TASK_IO_ACCOUNTING=y CONFIG_AUDIT=y CONFIG_LOG_BUF_SHIFT=18 CONFIG_CGROUPS=y -CONFIG_CGROUP_NS=y CONFIG_CGROUP_FREEZER=y CONFIG_CPUSETS=y CONFIG_CGROUP_CPUACCT=y diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 95f5826be45..c1870dddd32 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -849,4 +849,5 @@ ia32_sys_call_table: .quad compat_sys_clock_adjtime .quad sys_syncfs .quad compat_sys_sendmmsg /* 345 */ + .quad sys_setns ia32_syscall_end: diff --git a/arch/x86/include/asm/kgdb.h b/arch/x86/include/asm/kgdb.h index 396f5b5fc4d..77e95f54570 100644 --- a/arch/x86/include/asm/kgdb.h +++ b/arch/x86/include/asm/kgdb.h @@ -77,6 +77,7 @@ static inline void arch_kgdb_breakpoint(void) } #define BREAK_INSTR_SIZE 1 #define CACHE_FLUSH_IS_SAFE 1 +#define GDB_ADJUSTS_BREAK_OFFSET extern int kgdb_ll_trap(int cmd, const char *str, struct pt_regs *regs, long err, int trap, int sig); diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 1babf8adecd..94e7618fcac 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -136,6 +136,7 @@ struct cpuinfo_x86; struct task_struct; extern unsigned long profile_pc(struct pt_regs *regs); +#define profile_pc profile_pc extern unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs); @@ -202,20 +203,11 @@ static inline unsigned long kernel_stack_pointer(struct pt_regs *regs) #endif } -static inline unsigned long instruction_pointer(struct pt_regs *regs) -{ - return regs->ip; -} - -static inline unsigned long frame_pointer(struct pt_regs *regs) -{ - return regs->bp; -} +#define GET_IP(regs) ((regs)->ip) +#define GET_FP(regs) ((regs)->bp) +#define GET_USP(regs) ((regs)->sp) -static inline unsigned long user_stack_pointer(struct pt_regs *regs) -{ - return regs->sp; -} +#include <asm-generic/ptrace.h> /* Query offset/name of register from its name/offset */ extern int regs_query_register_offset(const char *name); diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h index fd921c3a684..487055c8c1a 100644 --- a/arch/x86/include/asm/suspend_32.h +++ b/arch/x86/include/asm/suspend_32.h @@ -9,8 +9,6 @@ #include <asm/desc.h> #include <asm/i387.h> -static inline int arch_prepare_suspend(void) { return 0; } - /* image of the saved processor state */ struct saved_context { u16 es, fs, gs, ss; diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h index 8d942afae68..09b0bf10415 100644 --- a/arch/x86/include/asm/suspend_64.h +++ b/arch/x86/include/asm/suspend_64.h @@ -9,11 +9,6 @@ #include <asm/desc.h> #include <asm/i387.h> -static inline int arch_prepare_suspend(void) -{ - return 0; -} - /* * Image of the saved processor state, used by the low level ACPI suspend to * RAM code and by the low level hibernation code. diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h index 83e2efd181e..9db5583b6d3 100644 --- a/arch/x86/include/asm/tsc.h +++ b/arch/x86/include/asm/tsc.h @@ -51,6 +51,10 @@ extern int unsynchronized_tsc(void); extern int check_tsc_unstable(void); extern unsigned long native_calibrate_tsc(void); +#ifdef CONFIG_X86_64 +extern cycles_t vread_tsc(void); +#endif + /* * Boot-time check whether the TSCs are synchronized across * all CPUs/cores: diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h index fb6a625c99b..593485b38ab 100644 --- a/arch/x86/include/asm/unistd_32.h +++ b/arch/x86/include/asm/unistd_32.h @@ -351,10 +351,11 @@ #define __NR_clock_adjtime 343 #define __NR_syncfs 344 #define __NR_sendmmsg 345 +#define __NR_setns 346 #ifdef __KERNEL__ -#define NR_syscalls 346 +#define NR_syscalls 347 #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 79f90eb15aa..705bf139288 100644 --- a/arch/x86/include/asm/unistd_64.h +++ b/arch/x86/include/asm/unistd_64.h @@ -679,6 +679,8 @@ __SYSCALL(__NR_clock_adjtime, sys_clock_adjtime) __SYSCALL(__NR_syncfs, sys_syncfs) #define __NR_sendmmsg 307 __SYSCALL(__NR_sendmmsg, sys_sendmmsg) +#define __NR_setns 308 +__SYSCALL(__NR_setns, sys_setns) #ifndef __NO_STUBS #define __ARCH_WANT_OLD_READDIR diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h index 9064052b73d..bb0522850b7 100644 --- a/arch/x86/include/asm/vdso.h +++ b/arch/x86/include/asm/vdso.h @@ -1,20 +1,6 @@ #ifndef _ASM_X86_VDSO_H #define _ASM_X86_VDSO_H -#ifdef CONFIG_X86_64 -extern const char VDSO64_PRELINK[]; - -/* - * Given a pointer to the vDSO image, find the pointer to VDSO64_name - * as that symbol is defined in the vDSO sources or linker script. - */ -#define VDSO64_SYMBOL(base, name) \ -({ \ - extern const char VDSO64_##name[]; \ - (void *)(VDSO64_##name - VDSO64_PRELINK + (unsigned long)(base)); \ -}) -#endif - #if defined CONFIG_X86_32 || defined CONFIG_COMPAT extern const char VDSO32_PRELINK[]; diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h index 3d61e204826..646b4c1ca69 100644 --- a/arch/x86/include/asm/vgtod.h +++ b/arch/x86/include/asm/vgtod.h @@ -23,8 +23,6 @@ struct vsyscall_gtod_data { struct timespec wall_to_monotonic; struct timespec wall_time_coarse; }; -extern struct vsyscall_gtod_data __vsyscall_gtod_data -__section_vsyscall_gtod_data; extern struct vsyscall_gtod_data vsyscall_gtod_data; #endif /* _ASM_X86_VGTOD_H */ diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h index d0983d255fb..d55597351f6 100644 --- a/arch/x86/include/asm/vsyscall.h +++ b/arch/x86/include/asm/vsyscall.h @@ -16,27 +16,19 @@ enum vsyscall_num { #ifdef __KERNEL__ #include <linux/seqlock.h> -#define __section_vgetcpu_mode __attribute__ ((unused, __section__ (".vgetcpu_mode"), aligned(16))) -#define __section_jiffies __attribute__ ((unused, __section__ (".jiffies"), aligned(16))) - /* Definitions for CONFIG_GENERIC_TIME definitions */ -#define __section_vsyscall_gtod_data __attribute__ \ - ((unused, __section__ (".vsyscall_gtod_data"),aligned(16))) -#define __section_vsyscall_clock __attribute__ \ - ((unused, __section__ (".vsyscall_clock"),aligned(16))) #define __vsyscall_fn \ __attribute__ ((unused, __section__(".vsyscall_fn"))) notrace #define VGETCPU_RDTSCP 1 #define VGETCPU_LSL 2 -extern int __vgetcpu_mode; -extern volatile unsigned long __jiffies; - /* kernel space (writeable) */ extern int vgetcpu_mode; extern struct timezone sys_tz; +#include <asm/vvar.h> + extern void map_vsyscall(void); #endif /* __KERNEL__ */ diff --git a/arch/x86/include/asm/vvar.h b/arch/x86/include/asm/vvar.h new file mode 100644 index 00000000000..341b3559452 --- /dev/null +++ b/arch/x86/include/asm/vvar.h @@ -0,0 +1,52 @@ +/* + * vvar.h: Shared vDSO/kernel variable declarations + * Copyright (c) 2011 Andy Lutomirski + * Subject to the GNU General Public License, version 2 + * + * A handful of variables are accessible (read-only) from userspace + * code in the vsyscall page and the vdso. They are declared here. + * Some other file must define them with DEFINE_VVAR. + * + * In normal kernel code, they are used like any other variable. + * In user code, they are accessed through the VVAR macro. + * + * Each of these variables lives in the vsyscall page, and each + * one needs a unique offset within the little piece of the page + * reserved for vvars. Specify that offset in DECLARE_VVAR. + * (There are 896 bytes available. If you mess up, the linker will + * catch it.) + */ + +/* Offset of vars within vsyscall page */ +#define VSYSCALL_VARS_OFFSET (3072 + 128) + +#if defined(__VVAR_KERNEL_LDS) + +/* The kernel linker script defines its own magic to put vvars in the + * right place. + */ +#define DECLARE_VVAR(offset, type, name) \ + EMIT_VVAR(name, VSYSCALL_VARS_OFFSET + offset) + +#else + +#define DECLARE_VVAR(offset, type, name) \ + static type const * const vvaraddr_ ## name = \ + (void *)(VSYSCALL_START + VSYSCALL_VARS_OFFSET + (offset)); + +#define DEFINE_VVAR(type, name) \ + type __vvar_ ## name \ + __attribute__((section(".vsyscall_var_" #name), aligned(16))) + +#define VVAR(name) (*vvaraddr_ ## name) + +#endif + +/* DECLARE_VVAR(offset, type, name) */ + +DECLARE_VVAR(0, volatile unsigned long, jiffies) +DECLARE_VVAR(8, int, vgetcpu_mode) +DECLARE_VVAR(128, struct vsyscall_gtod_data, vsyscall_gtod_data) + +#undef DECLARE_VVAR +#undef VSYSCALL_VARS_OFFSET diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 8508bfe5229..d240ea95051 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -447,6 +447,13 @@ HYPERVISOR_hvm_op(int op, void *arg) return _hypercall2(unsigned long, hvm_op, op, arg); } +static inline int +HYPERVISOR_tmem_op( + struct tmem_op *op) +{ + return _hypercall1(int, tmem_op, op); +} + static inline void MULTI_fpu_taskswitch(struct multicall_entry *mcl, int set) { diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 250806472a7..f5abe3a245b 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -8,7 +8,6 @@ CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE) ifdef CONFIG_FUNCTION_TRACER # Do not profile debug and lowlevel utilities -CFLAGS_REMOVE_tsc.o = -pg CFLAGS_REMOVE_rtc.o = -pg CFLAGS_REMOVE_paravirt-spinlocks.o = -pg CFLAGS_REMOVE_pvclock.o = -pg @@ -24,13 +23,16 @@ endif nostackp := $(call cc-option, -fno-stack-protector) CFLAGS_vsyscall_64.o := $(PROFILING) -g0 $(nostackp) CFLAGS_hpet.o := $(nostackp) -CFLAGS_tsc.o := $(nostackp) +CFLAGS_vread_tsc_64.o := $(nostackp) CFLAGS_paravirt.o := $(nostackp) GCOV_PROFILE_vsyscall_64.o := n GCOV_PROFILE_hpet.o := n GCOV_PROFILE_tsc.o := n GCOV_PROFILE_paravirt.o := n +# vread_tsc_64 is hot and should be fully optimized: +CFLAGS_REMOVE_vread_tsc_64.o = -pg -fno-optimize-sibling-calls + obj-y := process_$(BITS).o signal.o entry_$(BITS).o obj-y += traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o obj-y += time.o ioport.o ldt.o dumpstack.o @@ -39,7 +41,7 @@ obj-$(CONFIG_IRQ_WORK) += irq_work.o obj-y += probe_roms.o 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-$(CONFIG_X86_64) += syscall_64.o vsyscall_64.o +obj-$(CONFIG_X86_64) += syscall_64.o vsyscall_64.o vread_tsc_64.o obj-y += bootflag.o e820.o obj-y += pci-dma.o quirks.o topology.o kdebugfs.o obj-y += alternative.o i8253.o pci-nommu.o hw_breakpoint.o diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 0ba15a6cc57..c9a281f272f 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -123,7 +123,7 @@ static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) static atomic_t nmi_running = ATOMIC_INIT(0); static int mod_code_status; /* holds return value of text write */ static void *mod_code_ip; /* holds the IP to write to */ -static void *mod_code_newcode; /* holds the text to write to the IP */ +static const void *mod_code_newcode; /* holds the text to write to the IP */ static unsigned nmi_wait_count; static atomic_t nmi_update_count = ATOMIC_INIT(0); @@ -225,7 +225,7 @@ within(unsigned long addr, unsigned long start, unsigned long end) } static int -do_ftrace_mod_code(unsigned long ip, void *new_code) +do_ftrace_mod_code(unsigned long ip, const void *new_code) { /* * On x86_64, kernel text mappings are mapped read-only with @@ -266,8 +266,8 @@ static const unsigned char *ftrace_nop_replace(void) } static int -ftrace_modify_code(unsigned long ip, unsigned char *old_code, - unsigned char *new_code) +ftrace_modify_code(unsigned long ip, unsigned const char *old_code, + unsigned const char *new_code) { unsigned char replaced[MCOUNT_INSN_SIZE]; @@ -301,7 +301,7 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code, int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) { - unsigned char *new, *old; + unsigned const char *new, *old; unsigned long ip = rec->ip; old = ftrace_call_replace(ip, addr); @@ -312,7 +312,7 @@ int ftrace_make_nop(struct module *mod, int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { - unsigned char *new, *old; + unsigned const char *new, *old; unsigned long ip = rec->ip; old = ftrace_nop_replace(); diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S index 32cbffb0c49..fbb0a045a1a 100644 --- a/arch/x86/kernel/syscall_table_32.S +++ b/arch/x86/kernel/syscall_table_32.S @@ -345,3 +345,4 @@ ENTRY(sys_call_table) .long sys_clock_adjtime .long sys_syncfs .long sys_sendmmsg /* 345 */ + .long sys_setns diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index 25a28a24593..00cbb272627 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -23,7 +23,7 @@ #include <asm/time.h> #ifdef CONFIG_X86_64 -volatile unsigned long __jiffies __section_jiffies = INITIAL_JIFFIES; +DEFINE_VVAR(volatile unsigned long, jiffies) = INITIAL_JIFFIES; #endif unsigned long profile_pc(struct pt_regs *regs) diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 9335bf7dd2e..6cc6922262a 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -763,25 +763,6 @@ static cycle_t read_tsc(struct clocksource *cs) ret : clocksource_tsc.cycle_last; } -#ifdef CONFIG_X86_64 -static cycle_t __vsyscall_fn vread_tsc(void) -{ - cycle_t ret; - - /* - * Surround the RDTSC by barriers, to make sure it's not - * speculated to outside the seqlock critical section and - * does not cause time warps: - */ - rdtsc_barrier(); - ret = (cycle_t)vget_cycles(); - rdtsc_barrier(); - - return ret >= __vsyscall_gtod_data.clock.cycle_last ? - ret : __vsyscall_gtod_data.clock.cycle_last; -} -#endif - static void resume_tsc(struct clocksource *cs) { clocksource_tsc.cycle_last = 0; diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 61682f0ac26..89aed99aafc 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -161,6 +161,12 @@ SECTIONS #define VVIRT_OFFSET (VSYSCALL_ADDR - __vsyscall_0) #define VVIRT(x) (ADDR(x) - VVIRT_OFFSET) +#define EMIT_VVAR(x, offset) .vsyscall_var_ ## x \ + ADDR(.vsyscall_0) + offset \ + : AT(VLOAD(.vsyscall_var_ ## x)) { \ + *(.vsyscall_var_ ## x) \ + } \ + x = VVIRT(.vsyscall_var_ ## x); . = ALIGN(4096); __vsyscall_0 = .; @@ -175,18 +181,6 @@ SECTIONS *(.vsyscall_fn) } - . = ALIGN(L1_CACHE_BYTES); - .vsyscall_gtod_data : AT(VLOAD(.vsyscall_gtod_data)) { - *(.vsyscall_gtod_data) - } - - vsyscall_gtod_data = VVIRT(.vsyscall_gtod_data); - .vsyscall_clock : AT(VLOAD(.vsyscall_clock)) { - *(.vsyscall_clock) - } - vsyscall_clock = VVIRT(.vsyscall_clock); - - .vsyscall_1 ADDR(.vsyscall_0) + 1024: AT(VLOAD(.vsyscall_1)) { *(.vsyscall_1) } @@ -194,21 +188,14 @@ SECTIONS *(.vsyscall_2) } - .vgetcpu_mode : AT(VLOAD(.vgetcpu_mode)) { - *(.vgetcpu_mode) - } - vgetcpu_mode = VVIRT(.vgetcpu_mode); - - . = ALIGN(L1_CACHE_BYTES); - .jiffies : AT(VLOAD(.jiffies)) { - *(.jiffies) - } - jiffies = VVIRT(.jiffies); - .vsyscall_3 ADDR(.vsyscall_0) + 3072: AT(VLOAD(.vsyscall_3)) { *(.vsyscall_3) } +#define __VVAR_KERNEL_LDS +#include <asm/vvar.h> +#undef __VVAR_KERNEL_LDS + . = __vsyscall_0 + PAGE_SIZE; #undef VSYSCALL_ADDR @@ -216,6 +203,7 @@ SECTIONS #undef VLOAD #undef VVIRT_OFFSET #undef VVIRT +#undef EMIT_VVAR #endif /* CONFIG_X86_64 */ diff --git a/arch/x86/kernel/vread_tsc_64.c b/arch/x86/kernel/vread_tsc_64.c new file mode 100644 index 00000000000..a81aa9e9894 --- /dev/null +++ b/arch/x86/kernel/vread_tsc_64.c @@ -0,0 +1,36 @@ +/* This code runs in userspace. */ + +#define DISABLE_BRANCH_PROFILING +#include <asm/vgtod.h> + +notrace cycle_t __vsyscall_fn vread_tsc(void) +{ + cycle_t ret; + u64 last; + + /* + * Empirically, a fence (of type that depends on the CPU) + * before rdtsc is enough to ensure that rdtsc is ordered + * with respect to loads. The various CPU manuals are unclear + * as to whether rdtsc can be reordered with later loads, + * but no one has ever seen it happen. + */ + rdtsc_barrier(); + ret = (cycle_t)vget_cycles(); + + last = VVAR(vsyscall_gtod_data).clock.cycle_last; + + if (likely(ret >= last)) + return ret; + + /* + * GCC likes to generate cmov here, but this branch is extremely + * predictable (it's just a funciton of time and the likely is + * very likely) and there's a data dependence, so force GCC + * to generate a branch instead. I don't barrier() because + * we don't actually need a barrier, and if this function + * ever gets inlined it will generate worse code. + */ + asm volatile (""); + return last; +} diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index dcbb28c4b69..3e682184d76 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -49,17 +49,10 @@ __attribute__ ((unused, __section__(".vsyscall_" #nr))) notrace #define __syscall_clobber "r11","cx","memory" -/* - * vsyscall_gtod_data contains data that is : - * - readonly from vsyscalls - * - written by timer interrupt or systcl (/proc/sys/kernel/vsyscall64) - * Try to keep this structure as small as possible to avoid cache line ping pongs - */ -int __vgetcpu_mode __section_vgetcpu_mode; - -struct vsyscall_gtod_data __vsyscall_gtod_data __section_vsyscall_gtod_data = +DEFINE_VVAR(int, vgetcpu_mode); +DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data) = { - .lock = SEQLOCK_UNLOCKED, + .lock = __SEQLOCK_UNLOCKED(__vsyscall_gtod_data.lock), .sysctl_enabled = 1, }; @@ -97,7 +90,7 @@ void update_vsyscall(struct timespec *wall_time, struct timespec *wtm, */ static __always_inline void do_get_tz(struct timezone * tz) { - *tz = __vsyscall_gtod_data.sys_tz; + *tz = VVAR(vsyscall_gtod_data).sys_tz; } static __always_inline int gettimeofday(struct timeval *tv, struct timezone *tz) @@ -126,23 +119,24 @@ static __always_inline void do_vgettimeofday(struct timeval * tv) unsigned long mult, shift, nsec; cycle_t (*vread)(void); do { - seq = read_seqbegin(&__vsyscall_gtod_data.lock); + seq = read_seqbegin(&VVAR(vsyscall_gtod_data).lock); - vread = __vsyscall_gtod_data.clock.vread; - if (unlikely(!__vsyscall_gtod_data.sysctl_enabled || !vread)) { + vread = VVAR(vsyscall_gtod_data).clock.vread; + if (unlikely(!VVAR(vsyscall_gtod_data).sysctl_enabled || + !vread)) { gettimeofday(tv,NULL); return; } now = vread(); - base = __vsyscall_gtod_data.clock.cycle_last; - mask = __vsyscall_gtod_data.clock.mask; - mult = __vsyscall_gtod_data.clock.mult; - shift = __vsyscall_gtod_data.clock.shift; + base = VVAR(vsyscall_gtod_data).clock.cycle_last; + mask = VVAR(vsyscall_gtod_data).clock.mask; + mult = VVAR(vsyscall_gtod_data).clock.mult; + shift = VVAR(vsyscall_gtod_data).clock.shift; - tv->tv_sec = __vsyscall_gtod_data.wall_time_sec; - nsec = __vsyscall_gtod_data.wall_time_nsec; - } while (read_seqretry(&__vsyscall_gtod_data.lock, seq)); + tv->tv_sec = VVAR(vsyscall_gtod_data).wall_time_sec; + nsec = VVAR(vsyscall_gtod_data).wall_time_nsec; + } while (read_seqretry(&VVAR(vsyscall_gtod_data).lock, seq)); /* calculate interval: */ cycle_delta = (now - base) & mask; @@ -171,15 +165,15 @@ time_t __vsyscall(1) vtime(time_t *t) { unsigned seq; time_t result; - if (unlikely(!__vsyscall_gtod_data.sysctl_enabled)) + if (unlikely(!VVAR(vsyscall_gtod_data).sysctl_enabled)) return time_syscall(t); do { - seq = read_seqbegin(&__vsyscall_gtod_data.lock); + seq = read_seqbegin(&VVAR(vsyscall_gtod_data).lock); - result = __vsyscall_gtod_data.wall_time_sec; + result = VVAR(vsyscall_gtod_data).wall_time_sec; - } while (read_seqretry(&__vsyscall_gtod_data.lock, seq)); + } while (read_seqretry(&VVAR(vsyscall_gtod_data).lock, seq)); if (t) *t = result; @@ -208,9 +202,9 @@ vgetcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *tcache) We do this here because otherwise user space would do it on its own in a likely inferior way (no access to jiffies). If you don't like it pass NULL. */ - if (tcache && tcache->blob[0] == (j = __jiffies)) { + if (tcache && tcache->blob[0] == (j = VVAR(jiffies))) { p = tcache->blob[1]; - } else if (__vgetcpu_mode == VGETCPU_RDTSCP) { + } else if (VVAR(vgetcpu_mode) == VGETCPU_RDTSCP) { /* Load per CPU data from RDTSCP */ native_read_tscp(&p); } else { diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c index c3b8e24f2b1..9fd8a567fe1 100644 --- a/arch/x86/oprofile/op_model_amd.c +++ b/arch/x86/oprofile/op_model_amd.c @@ -316,16 +316,23 @@ static void op_amd_stop_ibs(void) wrmsrl(MSR_AMD64_IBSOPCTL, 0); } -static inline int eilvt_is_available(int offset) +static inline int get_eilvt(int offset) { - /* check if we may assign a vector */ return !setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_NMI, 1); } +static inline int put_eilvt(int offset) +{ + return !setup_APIC_eilvt(offset, 0, 0, 1); +} + static inline int ibs_eilvt_valid(void) { int offset; u64 val; + int valid = 0; + + preempt_disable(); rdmsrl(MSR_AMD64_IBSCTL, val); offset = val & IBSCTL_LVT_OFFSET_MASK; @@ -333,16 +340,20 @@ static inline int ibs_eilvt_valid(void) if (!(val & IBSCTL_LVT_OFFSET_VALID)) { pr_err(FW_BUG "cpu %d, invalid IBS interrupt offset %d (MSR%08X=0x%016llx)\n", smp_processor_id(), offset, MSR_AMD64_IBSCTL, val); - return 0; + goto out; } - if (!eilvt_is_available(offset)) { + if (!get_eilvt(offset)) { pr_err(FW_BUG "cpu %d, IBS interrupt offset %d not available (MSR%08X=0x%016llx)\n", smp_processor_id(), offset, MSR_AMD64_IBSCTL, val); - return 0; + goto out; } - return 1; + valid = 1; +out: + preempt_enable(); + + return valid; } static inline int get_ibs_offset(void) @@ -600,67 +611,69 @@ static int setup_ibs_ctl(int ibs_eilvt_off) static int force_ibs_eilvt_setup(void) { - int i; + int offset; int ret; - /* find the next free available EILVT entry */ - for (i = 1; i < 4; i++) { - if (!eilvt_is_available(i)) - continue; - ret = setup_ibs_ctl(i); - if (ret) - return ret; - pr_err(FW_BUG "using offset %d for IBS interrupts\n", i); - return 0; + /* + * find the next free available EILVT entry, skip offset 0, + * pin search to this cpu + */ + preempt_disable(); + for (offset = 1; offset < APIC_EILVT_NR_MAX; offset++) { + if (get_eilvt(offset)) + break; } + preempt_enable(); - printk(KERN_DEBUG "No EILVT entry available\n"); - - return -EBUSY; -} - -static int __init_ibs_nmi(void) -{ - int ret; - - if (ibs_eilvt_valid()) - return 0; + if (offset == APIC_EILVT_NR_MAX) { + printk(KERN_DEBUG "No EILVT entry available\n"); + return -EBUSY; + } - ret = force_ibs_eilvt_setup(); + ret = setup_ibs_ctl(offset); if (ret) - return ret; + goto out; - if (!ibs_eilvt_valid()) - return -EFAULT; + if (!ibs_eilvt_valid()) { + ret = -EFAULT; + goto out; + } + pr_err(FW_BUG "using offset %d for IBS interrupts\n", offset); pr_err(FW_BUG "workaround enabled for IBS LVT offset\n"); return 0; +out: + preempt_disable(); + put_eilvt(offset); + preempt_enable(); + return ret; } /* * check and reserve APIC extended interrupt LVT offset for IBS if * available - * - * init_ibs() preforms implicitly cpu-local operations, so pin this - * thread to its current CPU */ static void init_ibs(void) { - preempt_disable(); - ibs_caps = get_ibs_caps(); + if (!ibs_caps) + return; + + if (ibs_eilvt_valid()) goto out; - if (__init_ibs_nmi() < 0) - ibs_caps = 0; - else - printk(KERN_INFO "oprofile: AMD IBS detected (0x%08x)\n", ibs_caps); + if (!force_ibs_eilvt_setup()) + goto out; + + /* Failed to setup ibs */ + ibs_caps = 0; + return; out: - preempt_enable(); + printk(KERN_INFO "oprofile: AMD IBS detected (0x%08x)\n", ibs_caps); } static int (*create_arch_files)(struct super_block *sb, struct dentry *root); diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile index b6552b189bc..bef0bc96240 100644 --- a/arch/x86/vdso/Makefile +++ b/arch/x86/vdso/Makefile @@ -11,7 +11,7 @@ vdso-install-$(VDSO32-y) += $(vdso32-images) # files to link into the vdso -vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o vvar.o +vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o # files to link into kernel obj-$(VDSO64-y) += vma.o vdso.o @@ -37,11 +37,24 @@ $(obj)/%.so: OBJCOPYFLAGS := -S $(obj)/%.so: $(obj)/%.so.dbg FORCE $(call if_changed,objcopy) +# +# Don't omit frame pointers for ease of userspace debugging, but do +# optimize sibling calls. +# CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \ - $(filter -g%,$(KBUILD_CFLAGS)) $(call cc-option, -fno-stack-protector) + $(filter -g%,$(KBUILD_CFLAGS)) $(call cc-option, -fno-stack-protector) \ + -fno-omit-frame-pointer -foptimize-sibling-calls $(vobjs): KBUILD_CFLAGS += $(CFL) +# +# vDSO code runs in userspace and -pg doesn't help with profiling anyway. +# +CFLAGS_REMOVE_vdso-note.o = -pg +CFLAGS_REMOVE_vclock_gettime.o = -pg +CFLAGS_REMOVE_vgetcpu.o = -pg +CFLAGS_REMOVE_vvar.o = -pg + targets += vdso-syms.lds obj-$(VDSO64-y) += vdso-syms.lds diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c index ee55754cc3c..a724905fdae 100644 --- a/arch/x86/vdso/vclock_gettime.c +++ b/arch/x86/vdso/vclock_gettime.c @@ -2,7 +2,7 @@ * Copyright 2006 Andi Kleen, SUSE Labs. * Subject to the GNU Public License, v.2 * - * Fast user context implementation of clock_gettime and gettimeofday. + * Fast user context implementation of clock_gettime, gettimeofday, and time. * * The code should have no internal unresolved relocations. * Check with readelf after changing. @@ -22,9 +22,8 @@ #include <asm/hpet.h> #include <asm/unistd.h> #include <asm/io.h> -#include "vextern.h" -#define gtod vdso_vsyscall_gtod_data +#define gtod (&VVAR(vsyscall_gtod_data)) notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) { @@ -56,22 +55,6 @@ notrace static noinline int do_realtime(struct timespec *ts) return 0; } -/* Copy of the version in kernel/time.c which we cannot directly access */ -notrace static void -vset_normalized_timespec(struct timespec *ts, long sec, long nsec) -{ - while (nsec >= NSEC_PER_SEC) { - nsec -= NSEC_PER_SEC; - ++sec; - } - while (nsec < 0) { - nsec += NSEC_PER_SEC; - --sec; - } - ts->tv_sec = sec; - ts->tv_nsec = nsec; -} - notrace static noinline int do_monotonic(struct timespec *ts) { unsigned long seq, ns, secs; @@ -82,7 +65,17 @@ notrace static noinline int do_monotonic(struct timespec *ts) secs += gtod->wall_to_monotonic.tv_sec; ns += gtod->wall_to_monotonic.tv_nsec; } while (unlikely(read_seqretry(>od->lock, seq))); - vset_normalized_timespec(ts, secs, ns); + + /* wall_time_nsec, vgetns(), and wall_to_monotonic.tv_nsec + * are all guaranteed to be nonnegative. + */ + while (ns >= NSEC_PER_SEC) { + ns -= NSEC_PER_SEC; + ++secs; + } + ts->tv_sec = secs; + ts->tv_nsec = ns; + return 0; } @@ -107,7 +100,17 @@ notrace static noinline int do_monotonic_coarse(struct timespec *ts) secs += gtod->wall_to_monotonic.tv_sec; ns += gtod->wall_to_monotonic.tv_nsec; } while (unlikely(read_seqretry(>od->lock, seq))); - vset_normalized_timespec(ts, secs, ns); + + /* wall_time_nsec and wall_to_monotonic.tv_nsec are + * guaranteed to be between 0 and NSEC_PER_SEC. + */ + if (ns >= NSEC_PER_SEC) { + ns -= NSEC_PER_SEC; + ++secs; + } + ts->tv_sec = secs; + ts->tv_nsec = ns; + return 0; } @@ -157,3 +160,32 @@ notrace int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz) } int gettimeofday(struct timeval *, struct timezone *) __attribute__((weak, alias("__vdso_gettimeofday"))); + +/* This will break when the xtime seconds get inaccurate, but that is + * unlikely */ + +static __always_inline long time_syscall(long *t) +{ + long secs; + asm volatile("syscall" + : "=a" (secs) + : "0" (__NR_time), "D" (t) : "cc", "r11", "cx", "memory"); + return secs; +} + +notrace time_t __vdso_time(time_t *t) +{ + time_t result; + + if (unlikely(!VVAR(vsyscall_gtod_data).sysctl_enabled)) + return time_syscall(t); + + /* This is atomic on x86_64 so we don't need any locks. */ + result = ACCESS_ONCE(VVAR(vsyscall_gtod_data).wall_time_sec); + + if (t) + *t = result; + return result; +} +int time(time_t *t) + __attribute__((weak, alias("__vdso_time"))); diff --git a/arch/x86/vdso/vdso.lds.S b/arch/x86/vdso/vdso.lds.S index 4e5dd3b4de7..b96b2677cad 100644 --- a/arch/x86/vdso/vdso.lds.S +++ b/arch/x86/vdso/vdso.lds.S @@ -23,15 +23,10 @@ VERSION { __vdso_gettimeofday; getcpu; __vdso_getcpu; + time; + __vdso_time; local: *; }; } VDSO64_PRELINK = VDSO_PRELINK; - -/* - * Define VDSO64_x for each VEXTERN(x), for use via VDSO64_SYMBOL. - */ -#define VEXTERN(x) VDSO64_ ## x = vdso_ ## x; -#include "vextern.h" -#undef VEXTERN diff --git a/arch/x86/vdso/vextern.h b/arch/x86/vdso/vextern.h deleted file mode 100644 index 1683ba2ae3e..00000000000 --- a/arch/x86/vdso/vextern.h +++ /dev/null @@ -1,16 +0,0 @@ -#ifndef VEXTERN -#include <asm/vsyscall.h> -#define VEXTERN(x) \ - extern typeof(x) *vdso_ ## x __attribute__((visibility("hidden"))); -#endif - -#define VMAGIC 0xfeedbabeabcdefabUL - -/* Any kernel variables used in the vDSO must be exported in the main - kernel's vmlinux.lds.S/vsyscall.h/proper __section and - put into vextern.h and be referenced as a pointer with vdso prefix. - The main kernel later fills in the values. */ - -VEXTERN(jiffies) -VEXTERN(vgetcpu_mode) -VEXTERN(vsyscall_gtod_data) diff --git a/arch/x86/vdso/vgetcpu.c b/arch/x86/vdso/vgetcpu.c index 9fbc6b20026..5463ad55857 100644 --- a/arch/x86/vdso/vgetcpu.c +++ b/arch/x86/vdso/vgetcpu.c @@ -11,14 +11,13 @@ #include <linux/time.h> #include <asm/vsyscall.h> #include <asm/vgtod.h> -#include "vextern.h" notrace long __vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused) { unsigned int p; - if (*vdso_vgetcpu_mode == VGETCPU_RDTSCP) { + if (VVAR(vgetcpu_mode) == VGETCPU_RDTSCP) { /* Load per CPU data from RDTSCP */ native_read_tscp(&p); } else { diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c index 4b5d26f108b..7abd2be0f9b 100644 --- a/arch/x86/vdso/vma.c +++ b/arch/x86/vdso/vma.c @@ -15,9 +15,6 @@ #include <asm/proto.h> #include <asm/vdso.h> -#include "vextern.h" /* Just for VMAGIC. */ -#undef VEXTERN - unsigned int __read_mostly vdso_enabled = 1; extern char vdso_start[], vdso_end[]; @@ -26,20 +23,10 @@ extern unsigned short vdso_sync_cpuid; static struct page **vdso_pages; static unsigned vdso_size; -static inline void *var_ref(void *p, char *name) -{ - if (*(void **)p != (void *)VMAGIC) { - printk("VDSO: variable %s broken\n", name); - vdso_enabled = 0; - } - return p; -} - static int __init init_vdso_vars(void) { int npages = (vdso_end - vdso_start + PAGE_SIZE - 1) / PAGE_SIZE; int i; - char *vbase; vdso_size = npages << PAGE_SHIFT; vdso_pages = kmalloc(sizeof(struct page *) * npages, GFP_KERNEL); @@ -54,20 +41,6 @@ static int __init init_vdso_vars(void) copy_page(page_address(p), vdso_start + i*PAGE_SIZE); } - vbase = vmap(vdso_pages, npages, 0, PAGE_KERNEL); - if (!vbase) - goto oom; - - if (memcmp(vbase, "\177ELF", 4)) { - printk("VDSO: I'm broken; not ELF\n"); - vdso_enabled = 0; - } - -#define VEXTERN(x) \ - *(typeof(__ ## x) **) var_ref(VDSO64_SYMBOL(vbase, x), #x) = &__ ## x; -#include "vextern.h" -#undef VEXTERN - vunmap(vbase); return 0; oom: diff --git a/arch/x86/vdso/vvar.c b/arch/x86/vdso/vvar.c deleted file mode 100644 index 1b7e703684f..00000000000 --- a/arch/x86/vdso/vvar.c +++ /dev/null @@ -1,12 +0,0 @@ -/* Define pointer to external vDSO variables. - These are part of the vDSO. The kernel fills in the real addresses - at boot time. This is done because when the vdso is linked the - kernel isn't yet and we don't know the final addresses. */ -#include <linux/kernel.h> -#include <linux/time.h> -#include <asm/vsyscall.h> -#include <asm/timex.h> -#include <asm/vgtod.h> - -#define VEXTERN(x) typeof (__ ## x) *const vdso_ ## x = (void *)VMAGIC; -#include "vextern.h" diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 02d75246037..dc708dcc62f 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -75,67 +75,12 @@ #include "mmu.h" #include "debugfs.h" -#define MMU_UPDATE_HISTO 30 - /* * Protects atomic reservation decrease/increase against concurrent increases. * Also protects non-atomic updates of current_pages and balloon lists. */ DEFINE_SPINLOCK(xen_reservation_lock); -#ifdef CONFIG_XEN_DEBUG_FS - -static struct { - u32 pgd_update; - u32 pgd_update_pinned; - u32 pgd_update_batched; - - u32 pud_update; - u32 pud_update_pinned; - u32 pud_update_batched; - - u32 pmd_update; - u32 pmd_update_pinned; - u32 pmd_update_batched; - - u32 pte_update; - u32 pte_update_pinned; - u32 pte_update_batched; - - u32 mmu_update; - u32 mmu_update_extended; - u32 mmu_update_histo[MMU_UPDATE_HISTO]; - - u32 prot_commit; - u32 prot_commit_batched; - - u32 set_pte_at; - u32 set_pte_at_batched; - u32 set_pte_at_pinned; - u32 set_pte_at_current; - u32 set_pte_at_kernel; -} mmu_stats; - -static u8 zero_stats; - -static inline void check_zero(void) -{ - if (unlikely(zero_stats)) { - memset(&mmu_stats, 0, sizeof(mmu_stats)); - zero_stats = 0; - } -} - -#define ADD_STATS(elem, val) \ - do { check_zero(); mmu_stats.elem += (val); } while(0) - -#else /* !CONFIG_XEN_DEBUG_FS */ - -#define ADD_STATS(elem, val) do { (void)(val); } while(0) - -#endif /* CONFIG_XEN_DEBUG_FS */ - - /* * Identity map, in addition to plain kernel map. This needs to be * large enough to allocate page table pages to allocate the rest. @@ -243,11 +188,6 @@ static bool xen_page_pinned(void *ptr) return PagePinned(page); } -static bool xen_iomap_pte(pte_t pte) -{ - return pte_flags(pte) & _PAGE_IOMAP; -} - void xen_set_domain_pte(pte_t *ptep, pte_t pteval, unsigned domid) { struct multicall_space mcs; @@ -257,7 +197,7 @@ void xen_set_domain_pte(pte_t *ptep, pte_t pteval, unsigned domid) u = mcs.args; /* ptep might be kmapped when using 32-bit HIGHPTE */ - u->ptr = arbitrary_virt_to_machine(ptep).maddr; + u->ptr = virt_to_machine(ptep).maddr; u->val = pte_val_ma(pteval); MULTI_mmu_update(mcs.mc, mcs.args, 1, NULL, domid); @@ -266,11 +206,6 @@ void xen_set_domain_pte(pte_t *ptep, pte_t pteval, unsigned domid) } EXPORT_SYMBOL_GPL(xen_set_domain_pte); -static void xen_set_iomap_pte(pte_t *ptep, pte_t pteval) -{ - xen_set_domain_pte(ptep, pteval, DOMID_IO); -} - static void xen_extend_mmu_update(const struct mmu_update *update) { struct multicall_space mcs; @@ -279,27 +214,17 @@ static void xen_extend_mmu_update(const struct mmu_update *update) mcs = xen_mc_extend_args(__HYPERVISOR_mmu_update, sizeof(*u)); if (mcs.mc != NULL) { - ADD_STATS(mmu_update_extended, 1); - ADD_STATS(mmu_update_histo[mcs.mc->args[1]], -1); - mcs.mc->args[1]++; - - if (mcs.mc->args[1] < MMU_UPDATE_HISTO) - ADD_STATS(mmu_update_histo[mcs.mc->args[1]], 1); - else - ADD_STATS(mmu_update_histo[0], 1); } else { - ADD_STATS(mmu_update, 1); mcs = __xen_mc_entry(sizeof(*u)); MULTI_mmu_update(mcs.mc, mcs.args, 1, NULL, DOMID_SELF); - ADD_STATS(mmu_update_histo[1], 1); } u = mcs.args; *u = *update; } -void xen_set_pmd_hyper(pmd_t *ptr, pmd_t val) +static void xen_set_pmd_hyper(pmd_t *ptr, pmd_t val) { struct mmu_update u; @@ -312,17 +237,13 @@ void xen_set_pmd_hyper(pmd_t *ptr, pmd_t val) u.val = pmd_val_ma(val); xen_extend_mmu_update(&u); - ADD_STATS(pmd_update_batched, paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU); - xen_mc_issue(PARAVIRT_LAZY_MMU); preempt_enable(); } -void xen_set_pmd(pmd_t *ptr, pmd_t val) +static void xen_set_pmd(pmd_t *ptr, pmd_t val) { - ADD_STATS(pmd_update, 1); - /* If page is not pinned, we can just update the entry directly */ if (!xen_page_pinned(ptr)) { @@ -330,8 +251,6 @@ void xen_set_pmd(pmd_t *ptr, pmd_t val) return; } - ADD_STATS(pmd_update_pinned, 1); - xen_set_pmd_hyper(ptr, val); } @@ -344,35 +263,34 @@ void set_pte_mfn(unsigned long vaddr, unsigned long mfn, pgprot_t flags) set_pte_vaddr(vaddr, mfn_pte(mfn, flags)); } -void xen_set_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pteval) +static bool xen_batched_set_pte(pte_t *ptep, pte_t pteval) { - if (xen_iomap_pte(pteval)) { - xen_set_iomap_pte(ptep, pteval); - goto out; - } + struct mmu_update u; - ADD_STATS(set_pte_at, 1); -// ADD_STATS(set_pte_at_pinned, xen_page_pinned(ptep)); - ADD_STATS(set_pte_at_current, mm == current->mm); - ADD_STATS(set_pte_at_kernel, mm == &init_mm); + if (paravirt_get_lazy_mode() != PARAVIRT_LAZY_MMU) + return false; - if (mm == current->mm || mm == &init_mm) { - if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) { - struct multicall_space mcs; - mcs = xen_mc_entry(0); + xen_mc_batch(); - MULTI_update_va_mapping(mcs.mc, addr, pteval, 0); - ADD_STATS(set_pte_at_batched, 1); - xen_mc_issue(PARAVIRT_LAZY_MMU); - goto out; - } else - if (HYPERVISOR_update_va_mapping(addr, pteval, 0) == 0) - goto out; - } - xen_set_pte(ptep, pteval); + u.ptr = virt_to_machine(ptep).maddr | MMU_NORMAL_PT_UPDATE; + u.val = pte_val_ma(pteval); + xen_extend_mmu_update(&u); + + xen_mc_issue(PARAVIRT_LAZY_MMU); -out: return; + return true; +} + +static void xen_set_pte(pte_t *ptep, pte_t pteval) +{ + if (!xen_batched_set_pte(ptep, pteval)) + native_set_pte(ptep, pteval); +} + +static void xen_set_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pteval) +{ + xen_set_pte(ptep, pteval); } pte_t xen_ptep_modify_prot_start(struct mm_struct *mm, @@ -389,13 +307,10 @@ void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr, xen_mc_batch(); - u.ptr = arbitrary_virt_to_machine(ptep).maddr | MMU_PT_UPDATE_PRESERVE_AD; + u.ptr = virt_to_machine(ptep).maddr | MMU_PT_UPDATE_PRESERVE_AD; u.val = pte_val_ma(pte); xen_extend_mmu_update(&u); - ADD_STATS(prot_commit, 1); - ADD_STATS(prot_commit_batched, paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU); - xen_mc_issue(PARAVIRT_LAZY_MMU); } @@ -463,7 +378,7 @@ static pteval_t iomap_pte(pteval_t val) return val; } -pteval_t xen_pte_val(pte_t pte) +static pteval_t xen_pte_val(pte_t pte) { pteval_t pteval = pte.pte; @@ -480,7 +395,7 @@ pteval_t xen_pte_val(pte_t pte) } PV_CALLEE_SAVE_REGS_THUNK(xen_pte_val); -pgdval_t xen_pgd_val(pgd_t pgd) +static pgdval_t xen_pgd_val(pgd_t pgd) { return pte_mfn_to_pfn(pgd.pgd); } @@ -511,7 +426,7 @@ void xen_set_pat(u64 pat) WARN_ON(pat != 0x0007010600070106ull); } -pte_t xen_make_pte(pteval_t pte) +static pte_t xen_make_pte(pteval_t pte) { phys_addr_t addr = (pte & PTE_PFN_MASK); @@ -581,20 +496,20 @@ pte_t xen_make_pte_debug(pteval_t pte) PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte_debug); #endif -pgd_t xen_make_pgd(pgdval_t pgd) +static pgd_t xen_make_pgd(pgdval_t pgd) { pgd = pte_pfn_to_mfn(pgd); return native_make_pgd(pgd); } PV_CALLEE_SAVE_REGS_THUNK(xen_make_pgd); -pmdval_t xen_pmd_val(pmd_t pmd) +static pmdval_t xen_pmd_val(pmd_t pmd) { return pte_mfn_to_pfn(pmd.pmd); } PV_CALLEE_SAVE_REGS_THUNK(xen_pmd_val); -void xen_set_pud_hyper(pud_t *ptr, pud_t val) +static void xen_set_pud_hyper(pud_t *ptr, pud_t val) { struct mmu_update u; @@ -607,17 +522,13 @@ void xen_set_pud_hyper(pud_t *ptr, pud_t val) u.val = pud_val_ma(val); xen_extend_mmu_update(&u); - ADD_STATS(pud_update_batched, paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU); - xen_mc_issue(PARAVIRT_LAZY_MMU); preempt_enable(); } -void xen_set_pud(pud_t *ptr, pud_t val) +static void xen_set_pud(pud_t *ptr, pud_t val) { - ADD_STATS(pud_update, 1); - /* If page is not pinned, we can just update the entry directly */ if (!xen_page_pinned(ptr)) { @@ -625,56 +536,28 @@ void xen_set_pud(pud_t *ptr, pud_t val) return; } - ADD_STATS(pud_update_pinned, 1); - xen_set_pud_hyper(ptr, val); } -void xen_set_pte(pte_t *ptep, pte_t pte) -{ - if (xen_iomap_pte(pte)) { - xen_set_iomap_pte(ptep, pte); - return; - } - - ADD_STATS(pte_update, 1); -// ADD_STATS(pte_update_pinned, xen_page_pinned(ptep)); - ADD_STATS(pte_update_batched, paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU); - #ifdef CONFIG_X86_PAE - ptep->pte_high = pte.pte_high; - smp_wmb(); - ptep->pte_low = pte.pte_low; -#else - *ptep = pte; -#endif -} - -#ifdef CONFIG_X86_PAE -void xen_set_pte_atomic(pte_t *ptep, pte_t pte) +static void xen_set_pte_atomic(pte_t *ptep, pte_t pte) { - if (xen_iomap_pte(pte)) { - xen_set_iomap_pte(ptep, pte); - return; - } - set_64bit((u64 *)ptep, native_pte_val(pte)); } -void xen_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) +static void xen_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - ptep->pte_low = 0; - smp_wmb(); /* make sure low gets written first */ - ptep->pte_high = 0; + if (!xen_batched_set_pte(ptep, native_make_pte(0))) + native_pte_clear(mm, addr, ptep); } -void xen_pmd_clear(pmd_t *pmdp) +static void xen_pmd_clear(pmd_t *pmdp) { set_pmd(pmdp, __pmd(0)); } #endif /* CONFIG_X86_PAE */ -pmd_t xen_make_pmd(pmdval_t pmd) +static pmd_t xen_make_pmd(pmdval_t pmd) { pmd = pte_pfn_to_mfn(pmd); return native_make_pmd(pmd); @@ -682,13 +565,13 @@ pmd_t xen_make_pmd(pmdval_t pmd) PV_CALLEE_SAVE_REGS_THUNK(xen_make_pmd); #if PAGETABLE_LEVELS == 4 -pudval_t xen_pud_val(pud_t pud) +static pudval_t xen_pud_val(pud_t pud) { return pte_mfn_to_pfn(pud.pud); } PV_CALLEE_SAVE_REGS_THUNK(xen_pud_val); -pud_t xen_make_pud(pudval_t pud) +static pud_t xen_make_pud(pudval_t pud) { pud = pte_pfn_to_mfn(pud); @@ -696,7 +579,7 @@ pud_t xen_make_pud(pudval_t pud) } PV_CALLEE_SAVE_REGS_THUNK(xen_make_pud); -pgd_t *xen_get_user_pgd(pgd_t *pgd) +static pgd_t *xen_get_user_pgd(pgd_t *pgd) { pgd_t *pgd_page = (pgd_t *)(((unsigned long)pgd) & PAGE_MASK); unsigned offset = pgd - pgd_page; @@ -728,7 +611,7 @@ static void __xen_set_pgd_hyper(pgd_t *ptr, pgd_t val) * 2. It is always pinned * 3. It has no user pagetable attached to it */ -void __init xen_set_pgd_hyper(pgd_t *ptr, pgd_t val) +static void __init xen_set_pgd_hyper(pgd_t *ptr, pgd_t val) { preempt_disable(); @@ -741,12 +624,10 @@ void __init xen_set_pgd_hyper(pgd_t *ptr, pgd_t val) preempt_enable(); } -void xen_set_pgd(pgd_t *ptr, pgd_t val) +static void xen_set_pgd(pgd_t *ptr, pgd_t val) { pgd_t *user_ptr = xen_get_user_pgd(ptr); - ADD_STATS(pgd_update, 1); - /* If page is not pinned, we can just update the entry directly */ if (!xen_page_pinned(ptr)) { @@ -758,9 +639,6 @@ void xen_set_pgd(pgd_t *ptr, pgd_t val) return; } - ADD_STATS(pgd_update_pinned, 1); - ADD_STATS(pgd_update_batched, paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU); - /* If it's pinned, then we can at least batch the kernel and user updates together. */ xen_mc_batch(); @@ -1162,14 +1040,14 @@ void xen_mm_unpin_all(void) spin_unlock(&pgd_lock); } -void xen_activate_mm(struct mm_struct *prev, struct mm_struct *next) +static void xen_activate_mm(struct mm_struct *prev, struct mm_struct *next) { spin_lock(&next->page_table_lock); xen_pgd_pin(next); spin_unlock(&next->page_table_lock); } -void xen_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) +static void xen_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) { spin_lock(&mm->page_table_lock); xen_pgd_pin(mm); @@ -1256,7 +1134,7 @@ static void xen_drop_mm_ref(struct mm_struct *mm) * pagetable because of lazy tlb flushing. This means we need need to * switch all CPUs off this pagetable before we can unpin it. */ -void xen_exit_mmap(struct mm_struct *mm) +static void xen_exit_mmap(struct mm_struct *mm) { get_cpu(); /* make sure we don't move around */ xen_drop_mm_ref(mm); @@ -2371,7 +2249,7 @@ static int remap_area_mfn_pte_fn(pte_t *ptep, pgtable_t token, struct remap_data *rmd = data; pte_t pte = pte_mkspecial(pfn_pte(rmd->mfn++, rmd->prot)); - rmd->mmu_update->ptr = arbitrary_virt_to_machine(ptep).maddr; + rmd->mmu_update->ptr = virt_to_machine(ptep).maddr; rmd->mmu_update->val = pte_val_ma(pte); rmd->mmu_update++; @@ -2425,7 +2303,6 @@ out: 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); @@ -2437,65 +2314,4 @@ static const struct file_operations p2m_dump_fops = { .llseek = seq_lseek, .release = single_release, }; - -static struct dentry *d_mmu_debug; - -static int __init xen_mmu_debugfs(void) -{ - struct dentry *d_xen = xen_init_debugfs(); - - if (d_xen == NULL) - return -ENOMEM; - - d_mmu_debug = debugfs_create_dir("mmu", d_xen); - - debugfs_create_u8("zero_stats", 0644, d_mmu_debug, &zero_stats); - - debugfs_create_u32("pgd_update", 0444, d_mmu_debug, &mmu_stats.pgd_update); - debugfs_create_u32("pgd_update_pinned", 0444, d_mmu_debug, - &mmu_stats.pgd_update_pinned); - debugfs_create_u32("pgd_update_batched", 0444, d_mmu_debug, - &mmu_stats.pgd_update_pinned); - - debugfs_create_u32("pud_update", 0444, d_mmu_debug, &mmu_stats.pud_update); - debugfs_create_u32("pud_update_pinned", 0444, d_mmu_debug, - &mmu_stats.pud_update_pinned); - debugfs_create_u32("pud_update_batched", 0444, d_mmu_debug, - &mmu_stats.pud_update_pinned); - - debugfs_create_u32("pmd_update", 0444, d_mmu_debug, &mmu_stats.pmd_update); - debugfs_create_u32("pmd_update_pinned", 0444, d_mmu_debug, - &mmu_stats.pmd_update_pinned); - debugfs_create_u32("pmd_update_batched", 0444, d_mmu_debug, - &mmu_stats.pmd_update_pinned); - - debugfs_create_u32("pte_update", 0444, d_mmu_debug, &mmu_stats.pte_update); -// debugfs_create_u32("pte_update_pinned", 0444, d_mmu_debug, -// &mmu_stats.pte_update_pinned); - debugfs_create_u32("pte_update_batched", 0444, d_mmu_debug, - &mmu_stats.pte_update_pinned); - - debugfs_create_u32("mmu_update", 0444, d_mmu_debug, &mmu_stats.mmu_update); - debugfs_create_u32("mmu_update_extended", 0444, d_mmu_debug, - &mmu_stats.mmu_update_extended); - xen_debugfs_create_u32_array("mmu_update_histo", 0444, d_mmu_debug, - mmu_stats.mmu_update_histo, 20); - - debugfs_create_u32("set_pte_at", 0444, d_mmu_debug, &mmu_stats.set_pte_at); - debugfs_create_u32("set_pte_at_batched", 0444, d_mmu_debug, - &mmu_stats.set_pte_at_batched); - debugfs_create_u32("set_pte_at_current", 0444, d_mmu_debug, - &mmu_stats.set_pte_at_current); - debugfs_create_u32("set_pte_at_kernel", 0444, d_mmu_debug, - &mmu_stats.set_pte_at_kernel); - - debugfs_create_u32("prot_commit", 0444, d_mmu_debug, &mmu_stats.prot_commit); - 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); - -#endif /* CONFIG_XEN_DEBUG_FS */ +#endif /* CONFIG_XEN_DEBUG_FS */ diff --git a/arch/x86/xen/mmu.h b/arch/x86/xen/mmu.h index 537bb9aab77..73809bb951b 100644 --- a/arch/x86/xen/mmu.h +++ b/arch/x86/xen/mmu.h @@ -15,43 +15,6 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn); void set_pte_mfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags); - -void xen_activate_mm(struct mm_struct *prev, struct mm_struct *next); -void xen_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm); -void xen_exit_mmap(struct mm_struct *mm); - -pteval_t xen_pte_val(pte_t); -pmdval_t xen_pmd_val(pmd_t); -pgdval_t xen_pgd_val(pgd_t); - -pte_t xen_make_pte(pteval_t); -pmd_t xen_make_pmd(pmdval_t); -pgd_t xen_make_pgd(pgdval_t); - -void xen_set_pte(pte_t *ptep, pte_t pteval); -void xen_set_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pteval); - -#ifdef CONFIG_X86_PAE -void xen_set_pte_atomic(pte_t *ptep, pte_t pte); -void xen_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep); -void xen_pmd_clear(pmd_t *pmdp); -#endif /* CONFIG_X86_PAE */ - -void xen_set_pmd(pmd_t *pmdp, pmd_t pmdval); -void xen_set_pud(pud_t *ptr, pud_t val); -void xen_set_pmd_hyper(pmd_t *pmdp, pmd_t pmdval); -void xen_set_pud_hyper(pud_t *ptr, pud_t val); - -#if PAGETABLE_LEVELS == 4 -pudval_t xen_pud_val(pud_t pud); -pud_t xen_make_pud(pudval_t pudval); -void xen_set_pgd(pgd_t *pgdp, pgd_t pgd); -void xen_set_pgd_hyper(pgd_t *pgdp, pgd_t pgd); -#endif - -pgd_t *xen_get_user_pgd(pgd_t *pgd); - pte_t xen_ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr, pte_t *ptep); void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte); |