From 61a492fb1759f3e892ad0408e36d3575c5f890d0 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Tue, 23 Sep 2014 10:50:56 -0700 Subject: x86_64/vdso: Remove jiffies from the vvar page I think that the jiffies vvar was once used for the vgetcpu cache. That code is long gone, so let's just make jiffies be a normal variable. Signed-off-by: Andy Lutomirski Link: http://lkml.kernel.org/r/fcfee6f8749af14d96373a9e2656354ad0b95499.1411494540.git.luto@amacapital.net Signed-off-by: Ingo Molnar --- arch/x86/include/asm/vvar.h | 1 - 1 file changed, 1 deletion(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/vvar.h b/arch/x86/include/asm/vvar.h index 5d2b9ad2c6d2..5f6d40734a3b 100644 --- a/arch/x86/include/asm/vvar.h +++ b/arch/x86/include/asm/vvar.h @@ -44,7 +44,6 @@ extern char __vvar_page; /* DECLARE_VVAR(offset, type, name) */ -DECLARE_VVAR(0, volatile unsigned long, jiffies) DECLARE_VVAR(16, int, vgetcpu_mode) DECLARE_VVAR(128, struct vsyscall_gtod_data, vsyscall_gtod_data) -- cgit v1.2.3-59-g8ed1b From e76b027e6408f5570dc940b731ec9ae870c6188a Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Thu, 30 Oct 2014 14:58:01 -0700 Subject: x86,vdso: Use LSL unconditionally for vgetcpu LSL is faster than RDTSCP and works everywhere; there's no need to switch between them depending on CPU. Signed-off-by: Andy Lutomirski Cc: Andi Kleen Link: http://lkml.kernel.org/r/72f73d5ec4514e02bba345b9759177ef03742efb.1414706021.git.luto@amacapital.net Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/vgtod.h | 19 +++++++++++++++++++ arch/x86/include/asm/vsyscall.h | 29 ----------------------------- arch/x86/include/asm/vvar.h | 1 - arch/x86/kernel/cpu/common.c | 10 ---------- arch/x86/kernel/vsyscall_64.c | 2 -- arch/x86/vdso/vgetcpu.c | 1 - 6 files changed, 19 insertions(+), 43 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h index 3c3366c2e37f..e7e9682a33e9 100644 --- a/arch/x86/include/asm/vgtod.h +++ b/arch/x86/include/asm/vgtod.h @@ -70,4 +70,23 @@ static inline void gtod_write_end(struct vsyscall_gtod_data *s) ++s->seq; } +#ifdef CONFIG_X86_64 + +#define VGETCPU_CPU_MASK 0xfff + +static inline unsigned int __getcpu(void) +{ + unsigned int p; + + /* + * Load per CPU data from GDT. LSL is faster than RDTSCP and + * works on all CPUs. + */ + asm("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG)); + + return p; +} + +#endif /* CONFIG_X86_64 */ + #endif /* _ASM_X86_VGTOD_H */ diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h index 2a46ca720afc..34f7d8857542 100644 --- a/arch/x86/include/asm/vsyscall.h +++ b/arch/x86/include/asm/vsyscall.h @@ -4,15 +4,6 @@ #include #include -#define VGETCPU_RDTSCP 1 -#define VGETCPU_LSL 2 - -/* kernel space (writeable) */ -extern int vgetcpu_mode; -extern struct timezone sys_tz; - -#include - extern void map_vsyscall(void); /* @@ -21,24 +12,4 @@ extern void map_vsyscall(void); */ extern bool emulate_vsyscall(struct pt_regs *regs, unsigned long address); -#ifdef CONFIG_X86_64 - -#define VGETCPU_CPU_MASK 0xfff - -static inline unsigned int __getcpu(void) -{ - unsigned int p; - - if (VVAR(vgetcpu_mode) == VGETCPU_RDTSCP) { - /* Load per CPU data from RDTSCP */ - native_read_tscp(&p); - } else { - /* Load per CPU data from GDT */ - asm("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG)); - } - - return p; -} -#endif /* CONFIG_X86_64 */ - #endif /* _ASM_X86_VSYSCALL_H */ diff --git a/arch/x86/include/asm/vvar.h b/arch/x86/include/asm/vvar.h index 5f6d40734a3b..3f32dfc2ab73 100644 --- a/arch/x86/include/asm/vvar.h +++ b/arch/x86/include/asm/vvar.h @@ -44,7 +44,6 @@ extern char __vvar_page; /* DECLARE_VVAR(offset, type, name) */ -DECLARE_VVAR(16, int, vgetcpu_mode) DECLARE_VVAR(128, struct vsyscall_gtod_data, vsyscall_gtod_data) #undef DECLARE_VVAR diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 4b4f78c9ba19..175372b854be 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -956,14 +956,6 @@ static void identify_cpu(struct cpuinfo_x86 *c) } #ifdef CONFIG_X86_64 -static void vgetcpu_set_mode(void) -{ - if (cpu_has(&boot_cpu_data, X86_FEATURE_RDTSCP)) - vgetcpu_mode = VGETCPU_RDTSCP; - else - vgetcpu_mode = VGETCPU_LSL; -} - #ifdef CONFIG_IA32_EMULATION /* May not be __init: called during resume */ static void syscall32_cpu_init(void) @@ -1006,8 +998,6 @@ void __init identify_boot_cpu(void) #ifdef CONFIG_X86_32 sysenter_setup(); enable_sep_cpu(); -#else - vgetcpu_set_mode(); #endif cpu_detect_tlb(&boot_cpu_data); } diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index 2f9ef0c1d112..419e83b58436 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -52,8 +52,6 @@ #define CREATE_TRACE_POINTS #include "vsyscall_trace.h" -DEFINE_VVAR(int, vgetcpu_mode); - static enum { EMULATE, NATIVE, NONE } vsyscall_mode = EMULATE; static int __init vsyscall_setup(char *str) diff --git a/arch/x86/vdso/vgetcpu.c b/arch/x86/vdso/vgetcpu.c index add1d98d2477..8ec3d1f4ce9a 100644 --- a/arch/x86/vdso/vgetcpu.c +++ b/arch/x86/vdso/vgetcpu.c @@ -8,7 +8,6 @@ #include #include #include -#include #include notrace long -- cgit v1.2.3-59-g8ed1b From 1ad83c858c7d4ea210429142c99a1548e6715a35 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Wed, 29 Oct 2014 14:33:47 -0700 Subject: x86_64,vsyscall: Make vsyscall emulation configurable This adds CONFIG_X86_VSYSCALL_EMULATION, guarded by CONFIG_EXPERT. Turning it off completely disables vsyscall emulation, saving ~3.5k for vsyscall_64.c, 4k for vsyscall_emu_64.S (the fake vsyscall page), some tiny amount of core mm code that supports a gate area, and possibly 4k for a wasted pagetable. The latter is because the vsyscall addresses are misaligned and fit poorly in the fixmap. Signed-off-by: Andy Lutomirski Reviewed-by: Josh Triplett Cc: Konrad Rzeszutek Wilk Link: http://lkml.kernel.org/r/406db88b8dd5f0cbbf38216d11be34bbb43c7eae.1414618407.git.luto@amacapital.net Signed-off-by: Thomas Gleixner --- arch/x86/Kconfig | 18 ++++++++++++++++++ arch/x86/include/asm/fixmap.h | 2 ++ arch/x86/include/asm/page_64.h | 4 +++- arch/x86/include/asm/vsyscall.h | 8 ++++++++ arch/x86/kernel/Makefile | 3 +-- arch/x86/kernel/setup.c | 2 -- arch/x86/xen/mmu.c | 6 ++++-- 7 files changed, 36 insertions(+), 7 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index f2327e88e07c..cd10436d7d1c 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -984,6 +984,24 @@ config X86_ESPFIX64 def_bool y depends on X86_16BIT && X86_64 +config X86_VSYSCALL_EMULATION + bool "Enable vsyscall emulation" if EXPERT + default y + depends on X86_64 + ---help--- + This enables emulation of the legacy vsyscall page. Disabling + it is roughly equivalent to booting with vsyscall=none, except + that it will also disable the helpful warning if a program + tries to use a vsyscall. With this option set to N, offending + programs will just segfault, citing addresses of the form + 0xffffffffff600?00. + + This option is required by many programs built before 2013, and + care should be used even with newer programs if set to N. + + Disabling this option saves about 7K of kernel size and + possibly 4K of additional runtime pagetable memory. + config TOSHIBA tristate "Toshiba Laptop support" depends on X86_32 diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index ffb1733ac91f..d8d5bcb2a0b5 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -69,7 +69,9 @@ enum fixed_addresses { #ifdef CONFIG_X86_32 FIX_HOLE, #else +#ifdef CONFIG_X86_VSYSCALL_EMULATION VSYSCALL_PAGE = (FIXADDR_TOP - VSYSCALL_ADDR) >> PAGE_SHIFT, +#endif #ifdef CONFIG_PARAVIRT_CLOCK PVCLOCK_FIXMAP_BEGIN, PVCLOCK_FIXMAP_END = PVCLOCK_FIXMAP_BEGIN+PVCLOCK_VSYSCALL_NR_PAGES-1, diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h index f408caf73430..b3bebf9e5746 100644 --- a/arch/x86/include/asm/page_64.h +++ b/arch/x86/include/asm/page_64.h @@ -39,6 +39,8 @@ void copy_page(void *to, void *from); #endif /* !__ASSEMBLY__ */ -#define __HAVE_ARCH_GATE_AREA 1 +#ifdef CONFIG_X86_VSYSCALL_EMULATION +# define __HAVE_ARCH_GATE_AREA 1 +#endif #endif /* _ASM_X86_PAGE_64_H */ diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h index 34f7d8857542..6ba66ee79710 100644 --- a/arch/x86/include/asm/vsyscall.h +++ b/arch/x86/include/asm/vsyscall.h @@ -4,6 +4,7 @@ #include #include +#ifdef CONFIG_X86_VSYSCALL_EMULATION extern void map_vsyscall(void); /* @@ -11,5 +12,12 @@ extern void map_vsyscall(void); * Returns true if handled. */ extern bool emulate_vsyscall(struct pt_regs *regs, unsigned long address); +#else +static inline void map_vsyscall(void) {} +static inline bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) +{ + return false; +} +#endif #endif /* _ASM_X86_VSYSCALL_H */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 8f1e77440b2b..5d4502c8b983 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -28,8 +28,7 @@ obj-$(CONFIG_X86_32) += i386_ksyms_32.o obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o obj-$(CONFIG_X86_64) += mcount_64.o obj-y += syscall_$(BITS).o vsyscall_gtod.o -obj-$(CONFIG_X86_64) += vsyscall_64.o -obj-$(CONFIG_X86_64) += vsyscall_emu_64.o +obj-$(CONFIG_X86_VSYSCALL_EMULATION) += vsyscall_64.o vsyscall_emu_64.o obj-$(CONFIG_X86_ESPFIX64) += espfix_64.o obj-$(CONFIG_SYSFS) += ksysfs.o obj-y += bootflag.o e820.o diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 235cfd39e0d7..59a6f884fdad 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1190,9 +1190,7 @@ void __init setup_arch(char **cmdline_p) tboot_probe(); -#ifdef CONFIG_X86_64 map_vsyscall(); -#endif generic_apic_probe(); diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index a8a1a3d08d4d..8906cf0e536f 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1457,8 +1457,10 @@ static int xen_pgd_alloc(struct mm_struct *mm) page->private = (unsigned long)user_pgd; if (user_pgd != NULL) { +#ifdef CONFIG_X86_VSYSCALL_EMULATION user_pgd[pgd_index(VSYSCALL_ADDR)] = __pgd(__pa(level3_user_vsyscall) | _PAGE_TABLE); +#endif ret = 0; } @@ -2021,7 +2023,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) # ifdef CONFIG_HIGHMEM case FIX_KMAP_BEGIN ... FIX_KMAP_END: # endif -#else +#elif defined(CONFIG_X86_VSYSCALL_EMULATION) case VSYSCALL_PAGE: #endif case FIX_TEXT_POKE0: @@ -2060,7 +2062,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) __native_set_fixmap(idx, pte); -#ifdef CONFIG_X86_64 +#ifdef CONFIG_X86_VSYSCALL_EMULATION /* Replicate changes to map the vsyscall page into the user pagetable vsyscall mapping. */ if (idx == VSYSCALL_PAGE) { -- cgit v1.2.3-59-g8ed1b From 07114f0f1cda8b2ef6e884d0c7b268a32cce7903 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Tue, 4 Nov 2014 15:46:21 -0800 Subject: x86_64: Add a comment explaining the TASK_SIZE_MAX guard page That guard page is absolutely necessary; explain why for posterity. Signed-off-by: Andy Lutomirski Link: http://lkml.kernel.org/r/23320cb5017c2da8475ec20fcde8089d82aa2699.1415144745.git.luto@amacapital.net Signed-off-by: Ingo Molnar --- arch/x86/include/asm/processor.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index eb71ec794732..82d93ea13c0c 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -893,7 +893,13 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk); #else /* - * User space process size. 47bits minus one guard page. + * User space process size. 47bits minus one guard page. The guard + * page is necessary on Intel CPUs: if a SYSCALL instruction is at + * the highest possible canonical userspace address, then that + * syscall will enter the kernel with a non-canonical return + * address, and SYSRET will explode dangerously. We avoid this + * particular problem by preventing anything from being mapped + * at the maximum canonical address. */ #define TASK_SIZE_MAX ((1UL << 47) - PAGE_SIZE) -- cgit v1.2.3-59-g8ed1b