* 'x86-vdso-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
x86-64, vdso: Do not allocate memory for the vDSO
clocksource: Change __ARCH_HAS_CLOCKSOURCE_DATA to a CONFIG option
x86, vdso: Drop now wrong comment
Document the vDSO and add a reference parser
ia64: Replace clocksource.fsys_mmio with generic arch data
x86-64: Move vread_tsc and vread_hpet into the vDSO
clocksource: Replace vread with generic arch data
x86-64: Add --no-undefined to vDSO build
x86-64: Allow alternative patching in the vDSO
x86: Make alternative instruction pointers relative
x86-64: Improve vsyscall emulation CS and RIP handling
x86-64: Emulate legacy vsyscalls
x86-64: Fill unused parts of the vsyscall page with 0xcc
x86-64: Remove vsyscall number 3 (venosys)
x86-64: Map the HPET NX
x86-64: Remove kernel.vsyscall64 sysctl
x86-64: Give vvars their own page
x86-64: Document some of entry_64.S
x86-64: Fix alignment of jiffies variable
--- /dev/null
+On some architectures, when the kernel loads any userspace program it
+maps an ELF DSO into that program's address space. This DSO is called
+the vDSO and it often contains useful and highly-optimized alternatives
+to real syscalls.
+
+These functions are called just like ordinary C function according to
+your platform's ABI. Call them from a sensible context. (For example,
+if you set CS on x86 to something strange, the vDSO functions are
+within their rights to crash.) In addition, if you pass a bad
+pointer to a vDSO function, you might get SIGSEGV instead of -EFAULT.
+
+To find the DSO, parse the auxiliary vector passed to the program's
+entry point. The AT_SYSINFO_EHDR entry will point to the vDSO.
+
+The vDSO uses symbol versioning; whenever you request a symbol from the
+vDSO, specify the version you are expecting.
+
+Programs that dynamically link to glibc will use the vDSO automatically.
+Otherwise, you can use the reference parser in Documentation/vDSO/parse_vdso.c.
+
+Unless otherwise noted, the set of symbols with any given version and the
+ABI of those symbols is considered stable. It may vary across architectures,
+though.
+
+(As of this writing, this ABI documentation as been confirmed for x86_64.
+ The maintainers of the other vDSO-using architectures should confirm
+ that it is correct for their architecture.)
\ No newline at end of file
--- /dev/null
+/*
+ * parse_vdso.c: Linux reference vDSO parser
+ * Written by Andrew Lutomirski, 2011.
+ *
+ * This code is meant to be linked in to various programs that run on Linux.
+ * As such, it is available with as few restrictions as possible. This file
+ * is licensed under the Creative Commons Zero License, version 1.0,
+ * available at http://creativecommons.org/publicdomain/zero/1.0/legalcode
+ *
+ * The vDSO is a regular ELF DSO that the kernel maps into user space when
+ * it starts a program. It works equally well in statically and dynamically
+ * linked binaries.
+ *
+ * This code is tested on x86_64. In principle it should work on any 64-bit
+ * architecture that has a vDSO.
+ */
+
+#include <stdbool.h>
+#include <stdint.h>
+#include <string.h>
+#include <elf.h>
+
+/*
+ * To use this vDSO parser, first call one of the vdso_init_* functions.
+ * If you've already parsed auxv, then pass the value of AT_SYSINFO_EHDR
+ * to vdso_init_from_sysinfo_ehdr. Otherwise pass auxv to vdso_init_from_auxv.
+ * Then call vdso_sym for each symbol you want. For example, to look up
+ * gettimeofday on x86_64, use:
+ *
+ * <some pointer> = vdso_sym("LINUX_2.6", "gettimeofday");
+ * or
+ * <some pointer> = vdso_sym("LINUX_2.6", "__vdso_gettimeofday");
+ *
+ * vdso_sym will return 0 if the symbol doesn't exist or if the init function
+ * failed or was not called. vdso_sym is a little slow, so its return value
+ * should be cached.
+ *
+ * vdso_sym is threadsafe; the init functions are not.
+ *
+ * These are the prototypes:
+ */
+extern void vdso_init_from_auxv(void *auxv);
+extern void vdso_init_from_sysinfo_ehdr(uintptr_t base);
+extern void *vdso_sym(const char *version, const char *name);
+
+
+/* And here's the code. */
+
+#ifndef __x86_64__
+# error Not yet ported to non-x86_64 architectures
+#endif
+
+static struct vdso_info
+{
+ bool valid;
+
+ /* Load information */
+ uintptr_t load_addr;
+ uintptr_t load_offset; /* load_addr - recorded vaddr */
+
+ /* Symbol table */
+ Elf64_Sym *symtab;
+ const char *symstrings;
+ Elf64_Word *bucket, *chain;
+ Elf64_Word nbucket, nchain;
+
+ /* Version table */
+ Elf64_Versym *versym;
+ Elf64_Verdef *verdef;
+} vdso_info;
+
+/* Straight from the ELF specification. */
+static unsigned long elf_hash(const unsigned char *name)
+{
+ unsigned long h = 0, g;
+ while (*name)
+ {
+ h = (h << 4) + *name++;
+ if (g = h & 0xf0000000)
+ h ^= g >> 24;
+ h &= ~g;
+ }
+ return h;
+}
+
+void vdso_init_from_sysinfo_ehdr(uintptr_t base)
+{
+ size_t i;
+ bool found_vaddr = false;
+
+ vdso_info.valid = false;
+
+ vdso_info.load_addr = base;
+
+ Elf64_Ehdr *hdr = (Elf64_Ehdr*)base;
+ Elf64_Phdr *pt = (Elf64_Phdr*)(vdso_info.load_addr + hdr->e_phoff);
+ Elf64_Dyn *dyn = 0;
+
+ /*
+ * We need two things from the segment table: the load offset
+ * and the dynamic table.
+ */
+ for (i = 0; i < hdr->e_phnum; i++)
+ {
+ if (pt[i].p_type == PT_LOAD && !found_vaddr) {
+ found_vaddr = true;
+ vdso_info.load_offset = base
+ + (uintptr_t)pt[i].p_offset
+ - (uintptr_t)pt[i].p_vaddr;
+ } else if (pt[i].p_type == PT_DYNAMIC) {
+ dyn = (Elf64_Dyn*)(base + pt[i].p_offset);
+ }
+ }
+
+ if (!found_vaddr || !dyn)
+ return; /* Failed */
+
+ /*
+ * Fish out the useful bits of the dynamic table.
+ */
+ Elf64_Word *hash = 0;
+ vdso_info.symstrings = 0;
+ vdso_info.symtab = 0;
+ vdso_info.versym = 0;
+ vdso_info.verdef = 0;
+ for (i = 0; dyn[i].d_tag != DT_NULL; i++) {
+ switch (dyn[i].d_tag) {
+ case DT_STRTAB:
+ vdso_info.symstrings = (const char *)
+ ((uintptr_t)dyn[i].d_un.d_ptr
+ + vdso_info.load_offset);
+ break;
+ case DT_SYMTAB:
+ vdso_info.symtab = (Elf64_Sym *)
+ ((uintptr_t)dyn[i].d_un.d_ptr
+ + vdso_info.load_offset);
+ break;
+ case DT_HASH:
+ hash = (Elf64_Word *)
+ ((uintptr_t)dyn[i].d_un.d_ptr
+ + vdso_info.load_offset);
+ break;
+ case DT_VERSYM:
+ vdso_info.versym = (Elf64_Versym *)
+ ((uintptr_t)dyn[i].d_un.d_ptr
+ + vdso_info.load_offset);
+ break;
+ case DT_VERDEF:
+ vdso_info.verdef = (Elf64_Verdef *)
+ ((uintptr_t)dyn[i].d_un.d_ptr
+ + vdso_info.load_offset);
+ break;
+ }
+ }
+ if (!vdso_info.symstrings || !vdso_info.symtab || !hash)
+ return; /* Failed */
+
+ if (!vdso_info.verdef)
+ vdso_info.versym = 0;
+
+ /* Parse the hash table header. */
+ vdso_info.nbucket = hash[0];
+ vdso_info.nchain = hash[1];
+ vdso_info.bucket = &hash[2];
+ vdso_info.chain = &hash[vdso_info.nbucket + 2];
+
+ /* That's all we need. */
+ vdso_info.valid = true;
+}
+
+static bool vdso_match_version(Elf64_Versym ver,
+ const char *name, Elf64_Word hash)
+{
+ /*
+ * This is a helper function to check if the version indexed by
+ * ver matches name (which hashes to hash).
+ *
+ * The version definition table is a mess, and I don't know how
+ * to do this in better than linear time without allocating memory
+ * to build an index. I also don't know why the table has
+ * variable size entries in the first place.
+ *
+ * For added fun, I can't find a comprehensible specification of how
+ * to parse all the weird flags in the table.
+ *
+ * So I just parse the whole table every time.
+ */
+
+ /* First step: find the version definition */
+ ver &= 0x7fff; /* Apparently bit 15 means "hidden" */
+ Elf64_Verdef *def = vdso_info.verdef;
+ while(true) {
+ if ((def->vd_flags & VER_FLG_BASE) == 0
+ && (def->vd_ndx & 0x7fff) == ver)
+ break;
+
+ if (def->vd_next == 0)
+ return false; /* No definition. */
+
+ def = (Elf64_Verdef *)((char *)def + def->vd_next);
+ }
+
+ /* Now figure out whether it matches. */
+ Elf64_Verdaux *aux = (Elf64_Verdaux*)((char *)def + def->vd_aux);
+ return def->vd_hash == hash
+ && !strcmp(name, vdso_info.symstrings + aux->vda_name);
+}
+
+void *vdso_sym(const char *version, const char *name)
+{
+ unsigned long ver_hash;
+ if (!vdso_info.valid)
+ return 0;
+
+ ver_hash = elf_hash(version);
+ Elf64_Word chain = vdso_info.bucket[elf_hash(name) % vdso_info.nbucket];
+
+ for (; chain != STN_UNDEF; chain = vdso_info.chain[chain]) {
+ Elf64_Sym *sym = &vdso_info.symtab[chain];
+
+ /* Check for a defined global or weak function w/ right name. */
+ if (ELF64_ST_TYPE(sym->st_info) != STT_FUNC)
+ continue;
+ if (ELF64_ST_BIND(sym->st_info) != STB_GLOBAL &&
+ ELF64_ST_BIND(sym->st_info) != STB_WEAK)
+ continue;
+ if (sym->st_shndx == SHN_UNDEF)
+ continue;
+ if (strcmp(name, vdso_info.symstrings + sym->st_name))
+ continue;
+
+ /* Check symbol version. */
+ if (vdso_info.versym
+ && !vdso_match_version(vdso_info.versym[chain],
+ version, ver_hash))
+ continue;
+
+ return (void *)(vdso_info.load_offset + sym->st_value);
+ }
+
+ return 0;
+}
+
+void vdso_init_from_auxv(void *auxv)
+{
+ Elf64_auxv_t *elf_auxv = auxv;
+ for (int i = 0; elf_auxv[i].a_type != AT_NULL; i++)
+ {
+ if (elf_auxv[i].a_type == AT_SYSINFO_EHDR) {
+ vdso_init_from_sysinfo_ehdr(elf_auxv[i].a_un.a_val);
+ return;
+ }
+ }
+
+ vdso_info.valid = false;
+}
--- /dev/null
+/*
+ * vdso_test.c: Sample code to test parse_vdso.c on x86_64
+ * Copyright (c) 2011 Andy Lutomirski
+ * Subject to the GNU General Public License, version 2
+ *
+ * You can amuse yourself by compiling with:
+ * gcc -std=gnu99 -nostdlib
+ * -Os -fno-asynchronous-unwind-tables -flto
+ * vdso_test.c parse_vdso.c -o vdso_test
+ * to generate a small binary with no dependencies at all.
+ */
+
+#include <sys/syscall.h>
+#include <sys/time.h>
+#include <unistd.h>
+#include <stdint.h>
+
+extern void *vdso_sym(const char *version, const char *name);
+extern void vdso_init_from_sysinfo_ehdr(uintptr_t base);
+extern void vdso_init_from_auxv(void *auxv);
+
+/* We need a libc functions... */
+int strcmp(const char *a, const char *b)
+{
+ /* This implementation is buggy: it never returns -1. */
+ while (*a || *b) {
+ if (*a != *b)
+ return 1;
+ if (*a == 0 || *b == 0)
+ return 1;
+ a++;
+ b++;
+ }
+
+ return 0;
+}
+
+/* ...and two syscalls. This is x86_64-specific. */
+static inline long linux_write(int fd, const void *data, size_t len)
+{
+
+ long ret;
+ asm volatile ("syscall" : "=a" (ret) : "a" (__NR_write),
+ "D" (fd), "S" (data), "d" (len) :
+ "cc", "memory", "rcx",
+ "r8", "r9", "r10", "r11" );
+ return ret;
+}
+
+static inline void linux_exit(int code)
+{
+ asm volatile ("syscall" : : "a" (__NR_exit), "D" (code));
+}
+
+void to_base10(char *lastdig, uint64_t n)
+{
+ while (n) {
+ *lastdig = (n % 10) + '0';
+ n /= 10;
+ lastdig--;
+ }
+}
+
+__attribute__((externally_visible)) void c_main(void **stack)
+{
+ /* Parse the stack */
+ long argc = (long)*stack;
+ stack += argc + 2;
+
+ /* Now we're pointing at the environment. Skip it. */
+ while(*stack)
+ stack++;
+ stack++;
+
+ /* Now we're pointing at auxv. Initialize the vDSO parser. */
+ vdso_init_from_auxv((void *)stack);
+
+ /* Find gettimeofday. */
+ typedef long (*gtod_t)(struct timeval *tv, struct timezone *tz);
+ gtod_t gtod = (gtod_t)vdso_sym("LINUX_2.6", "__vdso_gettimeofday");
+
+ if (!gtod)
+ linux_exit(1);
+
+ struct timeval tv;
+ long ret = gtod(&tv, 0);
+
+ if (ret == 0) {
+ char buf[] = "The time is .000000\n";
+ to_base10(buf + 31, tv.tv_sec);
+ to_base10(buf + 38, tv.tv_usec);
+ linux_write(1, buf, sizeof(buf) - 1);
+ } else {
+ linux_exit(ret);
+ }
+
+ linux_exit(0);
+}
+
+/*
+ * This is the real entry point. It passes the initial stack into
+ * the C entry point.
+ */
+asm (
+ ".text\n"
+ ".global _start\n"
+ ".type _start,@function\n"
+ "_start:\n\t"
+ "mov %rsp,%rdi\n\t"
+ "jmp c_main"
+ );
--- /dev/null
+This file documents some of the kernel entries in
+arch/x86/kernel/entry_64.S. A lot of this explanation is adapted from
+an email from Ingo Molnar:
+
+http://lkml.kernel.org/r/<20110529191055.GC9835%40elte.hu>
+
+The x86 architecture has quite a few different ways to jump into
+kernel code. Most of these entry points are registered in
+arch/x86/kernel/traps.c and implemented in arch/x86/kernel/entry_64.S
+and arch/x86/ia32/ia32entry.S.
+
+The IDT vector assignments are listed in arch/x86/include/irq_vectors.h.
+
+Some of these entries are:
+
+ - system_call: syscall instruction from 64-bit code.
+
+ - ia32_syscall: int 0x80 from 32-bit or 64-bit code; compat syscall
+ either way.
+
+ - ia32_syscall, ia32_sysenter: syscall and sysenter from 32-bit
+ code
+
+ - interrupt: An array of entries. Every IDT vector that doesn't
+ explicitly point somewhere else gets set to the corresponding
+ value in interrupts. These point to a whole array of
+ magically-generated functions that make their way to do_IRQ with
+ the interrupt number as a parameter.
+
+ - emulate_vsyscall: int 0xcc, a special non-ABI entry used by
+ vsyscall emulation.
+
+ - APIC interrupts: Various special-purpose interrupts for things
+ like TLB shootdown.
+
+ - Architecturally-defined exceptions like divide_error.
+
+There are a few complexities here. The different x86-64 entries
+have different calling conventions. The syscall and sysenter
+instructions have their own peculiar calling conventions. Some of
+the IDT entries push an error code onto the stack; others don't.
+IDT entries using the IST alternative stack mechanism need their own
+magic to get the stack frames right. (You can find some
+documentation in the AMD APM, Volume 2, Chapter 8 and the Intel SDM,
+Volume 3, Chapter 6.)
+
+Dealing with the swapgs instruction is especially tricky. Swapgs
+toggles whether gs is the kernel gs or the user gs. The swapgs
+instruction is rather fragile: it must nest perfectly and only in
+single depth, it should only be used if entering from user mode to
+kernel mode and then when returning to user-space, and precisely
+so. If we mess that up even slightly, we crash.
+
+So when we have a secondary entry, already in kernel mode, we *must
+not* use SWAPGS blindly - nor must we forget doing a SWAPGS when it's
+not switched/swapped yet.
+
+Now, there's a secondary complication: there's a cheap way to test
+which mode the CPU is in and an expensive way.
+
+The cheap way is to pick this info off the entry frame on the kernel
+stack, from the CS of the ptregs area of the kernel stack:
+
+ xorl %ebx,%ebx
+ testl $3,CS+8(%rsp)
+ je error_kernelspace
+ SWAPGS
+
+The expensive (paranoid) way is to read back the MSR_GS_BASE value
+(which is what SWAPGS modifies):
+
+ movl $1,%ebx
+ movl $MSR_GS_BASE,%ecx
+ rdmsr
+ testl %edx,%edx
+ js 1f /* negative -> in kernel */
+ SWAPGS
+ xorl %ebx,%ebx
+1: ret
+
+and the whole paranoid non-paranoid macro complexity is about whether
+to suffer that RDMSR cost.
+
+If we are at an interrupt or user-trap/gate-alike boundary then we can
+use the faster check: the stack will be a reliable indicator of
+whether SWAPGS was already done: if we see that we are a secondary
+entry interrupting kernel mode execution, then we know that the GS
+base has already been switched. If it says that we interrupted
+user-space execution then we must do the SWAPGS.
+
+But if we are in an NMI/MCE/DEBUG/whatever super-atomic entry context,
+which might have triggered right after a normal entry wrote CS to the
+stack but before we executed SWAPGS, then the only safe way to check
+for GS is the slower method: the RDMSR.
+
+So we try only to mark those entry methods 'paranoid' that absolutely
+need the more expensive check for the GS base - and we generate all
+'normal' entry points with the regular (faster) entry macros.
bool
default y
+config ARCH_CLOCKSOURCE_DATA
+ def_bool y
+
config SCHED_OMIT_FRAME_POINTER
bool
default y
--- /dev/null
+/* IA64-specific clocksource additions */
+
+#ifndef _ASM_IA64_CLOCKSOURCE_H
+#define _ASM_IA64_CLOCKSOURCE_H
+
+struct arch_clocksource_data {
+ void *fsys_mmio; /* used by fsyscall asm code */
+};
+
+#endif /* _ASM_IA64_CLOCKSOURCE_H */
}
/* initialize last tick */
cyclone_mc = cyclone_timer;
- clocksource_cyclone.fsys_mmio = cyclone_timer;
+ clocksource_cyclone.archdata.fsys_mmio = cyclone_timer;
clocksource_register_hz(&clocksource_cyclone, CYCLONE_TIMER_FREQ);
return 0;
fsyscall_gtod_data.clk_mask = c->mask;
fsyscall_gtod_data.clk_mult = mult;
fsyscall_gtod_data.clk_shift = c->shift;
- fsyscall_gtod_data.clk_fsys_mmio = c->fsys_mmio;
+ fsyscall_gtod_data.clk_fsys_mmio = c->archdata.fsys_mmio;
fsyscall_gtod_data.clk_cycle_last = c->cycle_last;
/* copy kernel time structures */
void __init sn_timer_init(void)
{
- clocksource_sn2.fsys_mmio = RTC_COUNTER_ADDR;
+ clocksource_sn2.archdata.fsys_mmio = RTC_COUNTER_ADDR;
clocksource_register_hz(&clocksource_sn2, sn_rtc_cycles_per_second);
ia64_udelay = &ia64_sn_udelay;
config GENERIC_CLOCKEVENTS
def_bool y
+config ARCH_CLOCKSOURCE_DATA
+ def_bool y
+ depends on X86_64
+
config GENERIC_CLOCKEVENTS_BROADCAST
def_bool y
depends on X86_64 || (X86_32 && X86_LOCAL_APIC)
.macro altinstruction_entry orig alt feature orig_len alt_len
.align 8
- .quad \orig
- .quad \alt
+ .long \orig - .
+ .long \alt - .
.word \feature
.byte \orig_len
.byte \alt_len
#endif
struct alt_instr {
- u8 *instr; /* original instruction */
- u8 *replacement;
+ s32 instr_offset; /* original instruction */
+ s32 repl_offset; /* offset to replacement instruction */
u16 cpuid; /* cpuid bit set for replacement */
u8 instrlen; /* length of original instruction */
u8 replacementlen; /* length of new instruction, <= instrlen */
"661:\n\t" oldinstr "\n662:\n" \
".section .altinstructions,\"a\"\n" \
_ASM_ALIGN "\n" \
- _ASM_PTR "661b\n" /* label */ \
- _ASM_PTR "663f\n" /* new instruction */ \
+ " .long 661b - .\n" /* label */ \
+ " .long 663f - .\n" /* new instruction */ \
" .word " __stringify(feature) "\n" /* feature bit */ \
" .byte 662b-661b\n" /* sourcelen */ \
" .byte 664f-663f\n" /* replacementlen */ \
--- /dev/null
+/* x86-specific clocksource additions */
+
+#ifndef _ASM_X86_CLOCKSOURCE_H
+#define _ASM_X86_CLOCKSOURCE_H
+
+#ifdef CONFIG_X86_64
+
+#define VCLOCK_NONE 0 /* No vDSO clock available. */
+#define VCLOCK_TSC 1 /* vDSO should use vread_tsc. */
+#define VCLOCK_HPET 2 /* vDSO should use vread_hpet. */
+
+struct arch_clocksource_data {
+ int vclock_mode;
+};
+
+#endif /* CONFIG_X86_64 */
+
+#endif /* _ASM_X86_CLOCKSOURCE_H */
"2:\n"
".section .altinstructions,\"a\"\n"
_ASM_ALIGN "\n"
- _ASM_PTR "1b\n"
- _ASM_PTR "0\n" /* no replacement */
+ " .long 1b - .\n"
+ " .long 0\n" /* no replacement */
" .word %P0\n" /* feature bit */
" .byte 2b - 1b\n" /* source len */
" .byte 0\n" /* replacement len */
"2:\n"
".section .altinstructions,\"a\"\n"
_ASM_ALIGN "\n"
- _ASM_PTR "1b\n"
- _ASM_PTR "3f\n"
+ " .long 1b - .\n"
+ " .long 3f - .\n"
" .word %P1\n" /* feature bit */
" .byte 2b - 1b\n" /* source len */
" .byte 4f - 3f\n" /* replacement len */
VSYSCALL_LAST_PAGE,
VSYSCALL_FIRST_PAGE = VSYSCALL_LAST_PAGE
+ ((VSYSCALL_END-VSYSCALL_START) >> PAGE_SHIFT) - 1,
+ VVAR_PAGE,
VSYSCALL_HPET,
#endif
FIX_DBGP_BASE,
* Vectors 0 ... 31 : system traps and exceptions - hardcoded events
* Vectors 32 ... 127 : device interrupts
* Vector 128 : legacy int80 syscall interface
- * Vectors 129 ... INVALIDATE_TLB_VECTOR_START-1 : device interrupts
+ * Vector 204 : legacy x86_64 vsyscall emulation
+ * Vectors 129 ... INVALIDATE_TLB_VECTOR_START-1 except 204 : device interrupts
* Vectors INVALIDATE_TLB_VECTOR_START ... 255 : special interrupts
*
* 64-bit x86 has per CPU IDT tables, 32-bit has one shared IDT table.
#ifdef CONFIG_X86_32
# define SYSCALL_VECTOR 0x80
#endif
+#ifdef CONFIG_X86_64
+# define VSYSCALL_EMU_VECTOR 0xcc
+#endif
/*
* Vectors 0x30-0x3f are used for ISA interrupts.
#define __PAGE_KERNEL_NOCACHE (__PAGE_KERNEL | _PAGE_PCD | _PAGE_PWT)
#define __PAGE_KERNEL_UC_MINUS (__PAGE_KERNEL | _PAGE_PCD)
#define __PAGE_KERNEL_VSYSCALL (__PAGE_KERNEL_RX | _PAGE_USER)
-#define __PAGE_KERNEL_VSYSCALL_NOCACHE (__PAGE_KERNEL_VSYSCALL | _PAGE_PCD | _PAGE_PWT)
+#define __PAGE_KERNEL_VVAR (__PAGE_KERNEL_RO | _PAGE_USER)
+#define __PAGE_KERNEL_VVAR_NOCACHE (__PAGE_KERNEL_VVAR | _PAGE_PCD | _PAGE_PWT)
#define __PAGE_KERNEL_LARGE (__PAGE_KERNEL | _PAGE_PSE)
#define __PAGE_KERNEL_LARGE_NOCACHE (__PAGE_KERNEL | _PAGE_CACHE_UC | _PAGE_PSE)
#define __PAGE_KERNEL_LARGE_EXEC (__PAGE_KERNEL_EXEC | _PAGE_PSE)
#define PAGE_KERNEL_LARGE_NOCACHE __pgprot(__PAGE_KERNEL_LARGE_NOCACHE)
#define PAGE_KERNEL_LARGE_EXEC __pgprot(__PAGE_KERNEL_LARGE_EXEC)
#define PAGE_KERNEL_VSYSCALL __pgprot(__PAGE_KERNEL_VSYSCALL)
-#define PAGE_KERNEL_VSYSCALL_NOCACHE __pgprot(__PAGE_KERNEL_VSYSCALL_NOCACHE)
+#define PAGE_KERNEL_VVAR __pgprot(__PAGE_KERNEL_VVAR)
+#define PAGE_KERNEL_VVAR_NOCACHE __pgprot(__PAGE_KERNEL_VVAR_NOCACHE)
#define PAGE_KERNEL_IO __pgprot(__PAGE_KERNEL_IO)
#define PAGE_KERNEL_IO_NOCACHE __pgprot(__PAGE_KERNEL_IO_NOCACHE)
#ifndef _ASM_X86_TRAPS_H
#define _ASM_X86_TRAPS_H
+#include <linux/kprobes.h>
+
#include <asm/debugreg.h>
#include <asm/siginfo.h> /* TRAP_TRACE, ... */
asmlinkage void machine_check(void);
#endif /* CONFIG_X86_MCE */
asmlinkage void simd_coprocessor_error(void);
+asmlinkage void emulate_vsyscall(void);
dotraplinkage void do_divide_error(struct pt_regs *, long);
dotraplinkage void do_debug(struct pt_regs *, long);
dotraplinkage void do_machine_check(struct pt_regs *, long);
#endif
dotraplinkage void do_simd_coprocessor_error(struct pt_regs *, long);
+dotraplinkage void do_emulate_vsyscall(struct pt_regs *, long);
#ifdef CONFIG_X86_32
dotraplinkage void do_iret_error(struct pt_regs *, long);
#endif
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:
time_t wall_time_sec;
u32 wall_time_nsec;
- int sysctl_enabled;
struct timezone sys_tz;
struct { /* extract of a clocksource struct */
- cycle_t (*vread)(void);
+ int vclock_mode;
cycle_t cycle_last;
cycle_t mask;
u32 mult;
#ifdef __KERNEL__
#include <linux/seqlock.h>
-/* Definitions for CONFIG_GENERIC_TIME definitions */
-#define __vsyscall_fn \
- __attribute__ ((unused, __section__(".vsyscall_fn"))) notrace
-
#define VGETCPU_RDTSCP 1
#define VGETCPU_LSL 2
* 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.)
+ * These variables live in a page of kernel data that has an extra RO
+ * mapping for userspace. Each variable needs a unique offset within
+ * that page; specify that offset with the DECLARE_VVAR macro. (If
+ * you mess up, the linker will catch it.)
*/
-/* Offset of vars within vsyscall page */
-#define VSYSCALL_VARS_OFFSET (3072 + 128)
+/* Base address of vvars. This is not ABI. */
+#define VVAR_ADDRESS (-10*1024*1024 - 4096)
#if defined(__VVAR_KERNEL_LDS)
* right place.
*/
#define DECLARE_VVAR(offset, type, name) \
- EMIT_VVAR(name, VSYSCALL_VARS_OFFSET + offset)
+ EMIT_VVAR(name, offset)
#else
#define DECLARE_VVAR(offset, type, name) \
static type const * const vvaraddr_ ## name = \
- (void *)(VSYSCALL_START + VSYSCALL_VARS_OFFSET + (offset));
+ (void *)(VVAR_ADDRESS + (offset));
#define DEFINE_VVAR(type, name) \
- type __vvar_ ## name \
- __attribute__((section(".vsyscall_var_" #name), aligned(16)))
+ type name \
+ __attribute__((section(".vvar_" #name), aligned(16)))
#define VVAR(name) (*vvaraddr_ ## name)
/* DECLARE_VVAR(offset, type, name) */
DECLARE_VVAR(0, volatile unsigned long, jiffies)
-DECLARE_VVAR(8, int, vgetcpu_mode)
+DECLARE_VVAR(16, int, vgetcpu_mode)
DECLARE_VVAR(128, struct vsyscall_gtod_data, vsyscall_gtod_data)
#undef DECLARE_VVAR
-#undef VSYSCALL_VARS_OFFSET
nostackp := $(call cc-option, -fno-stack-protector)
CFLAGS_vsyscall_64.o := $(PROFILING) -g0 $(nostackp)
CFLAGS_hpet.o := $(nostackp)
-CFLAGS_vread_tsc_64.o := $(nostackp)
CFLAGS_paravirt.o := $(nostackp)
GCOV_PROFILE_vsyscall_64.o := n
GCOV_PROFILE_hpet.o := n
GCOV_PROFILE_tsc.o := n
-GCOV_PROFILE_vread_tsc_64.o := n
GCOV_PROFILE_paravirt.o := n
-# vread_tsc_64 is hot and should be fully optimized:
-CFLAGS_REMOVE_vread_tsc_64.o = -pg -fno-optimize-sibling-calls
-
obj-y := process_$(BITS).o signal.o entry_$(BITS).o
obj-y += traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
obj-y += time.o ioport.o ldt.o dumpstack.o
obj-y += probe_roms.o
obj-$(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 vread_tsc_64.o
+obj-$(CONFIG_X86_64) += syscall_64.o vsyscall_64.o
+obj-$(CONFIG_X86_64) += vsyscall_emu_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
#include <asm/pgtable.h>
#include <asm/mce.h>
#include <asm/nmi.h>
-#include <asm/vsyscall.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include <asm/io.h>
extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
extern s32 __smp_locks[], __smp_locks_end[];
-extern char __vsyscall_0;
void *text_poke_early(void *addr, const void *opcode, size_t len);
/* Replace instructions with better alternatives for this CPU type.
struct alt_instr *end)
{
struct alt_instr *a;
+ u8 *instr, *replacement;
u8 insnbuf[MAX_PATCH_LEN];
DPRINTK("%s: alt table %p -> %p\n", __func__, start, end);
* order.
*/
for (a = start; a < end; a++) {
- u8 *instr = a->instr;
+ instr = (u8 *)&a->instr_offset + a->instr_offset;
+ replacement = (u8 *)&a->repl_offset + a->repl_offset;
BUG_ON(a->replacementlen > a->instrlen);
BUG_ON(a->instrlen > sizeof(insnbuf));
BUG_ON(a->cpuid >= NCAPINTS*32);
if (!boot_cpu_has(a->cpuid))
continue;
-#ifdef CONFIG_X86_64
- /* vsyscall code is not mapped yet. resolve it manually. */
- if (instr >= (u8 *)VSYSCALL_START && instr < (u8*)VSYSCALL_END) {
- instr = __va(instr - (u8*)VSYSCALL_START + (u8*)__pa_symbol(&__vsyscall_0));
- DPRINTK("%s: vsyscall fixup: %p => %p\n",
- __func__, a->instr, instr);
- }
-#endif
- memcpy(insnbuf, a->replacement, a->replacementlen);
+
+ memcpy(insnbuf, replacement, a->replacementlen);
+
+ /* 0xe8 is a relative jump; fix the offset. */
if (*insnbuf == 0xe8 && a->replacementlen == 5)
- *(s32 *)(insnbuf + 1) += a->replacement - a->instr;
+ *(s32 *)(insnbuf + 1) += replacement - instr;
+
add_nops(insnbuf + a->replacementlen,
a->instrlen - a->replacementlen);
+
text_poke_early(instr, insnbuf, a->instrlen);
}
}
/*
* entry.S contains the system-call and fault low-level handling routines.
*
+ * Some of this is documented in Documentation/x86/entry_64.txt
+ *
* NOTE: This code handles signal-recognition, which happens every time
* after an interrupt and after each system call.
*
zeroentry coprocessor_error do_coprocessor_error
errorentry alignment_check do_alignment_check
zeroentry simd_coprocessor_error do_simd_coprocessor_error
+zeroentry emulate_vsyscall do_emulate_vsyscall
+
/* Reload gs selector with exception handling */
/* edi: new selector */
{
hpet_virt_address = ioremap_nocache(hpet_address, HPET_MMAP_SIZE);
#ifdef CONFIG_X86_64
- __set_fixmap(VSYSCALL_HPET, hpet_address, PAGE_KERNEL_VSYSCALL_NOCACHE);
+ __set_fixmap(VSYSCALL_HPET, hpet_address, PAGE_KERNEL_VVAR_NOCACHE);
#endif
}
return (cycle_t)hpet_readl(HPET_COUNTER);
}
-#ifdef CONFIG_X86_64
-static cycle_t __vsyscall_fn vread_hpet(void)
-{
- return readl((const void __iomem *)fix_to_virt(VSYSCALL_HPET) + 0xf0);
-}
-#endif
-
static struct clocksource clocksource_hpet = {
.name = "hpet",
.rating = 250,
.flags = CLOCK_SOURCE_IS_CONTINUOUS,
.resume = hpet_resume_counter,
#ifdef CONFIG_X86_64
- .vread = vread_hpet,
+ .archdata = { .vclock_mode = VCLOCK_HPET },
#endif
};
set_bit(SYSCALL_VECTOR, used_vectors);
#endif
+#ifdef CONFIG_X86_64
+ BUG_ON(test_bit(VSYSCALL_EMU_VECTOR, used_vectors));
+ set_system_intr_gate(VSYSCALL_EMU_VECTOR, &emulate_vsyscall);
+ set_bit(VSYSCALL_EMU_VECTOR, used_vectors);
+#endif
+
/*
* Should be a barrier for any external CPU state:
*/
.flags = CLOCK_SOURCE_IS_CONTINUOUS |
CLOCK_SOURCE_MUST_VERIFY,
#ifdef CONFIG_X86_64
- .vread = vread_tsc,
+ .archdata = { .vclock_mode = VCLOCK_TSC },
#endif
};
#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 = .;
. = VSYSCALL_ADDR;
- .vsyscall_0 : AT(VLOAD(.vsyscall_0)) {
+ .vsyscall : AT(VLOAD(.vsyscall)) {
*(.vsyscall_0)
- } :user
- . = ALIGN(L1_CACHE_BYTES);
- .vsyscall_fn : AT(VLOAD(.vsyscall_fn)) {
- *(.vsyscall_fn)
- }
-
- .vsyscall_1 ADDR(.vsyscall_0) + 1024: AT(VLOAD(.vsyscall_1)) {
+ . = 1024;
*(.vsyscall_1)
- }
- .vsyscall_2 ADDR(.vsyscall_0) + 2048: AT(VLOAD(.vsyscall_2)) {
- *(.vsyscall_2)
- }
- .vsyscall_3 ADDR(.vsyscall_0) + 3072: AT(VLOAD(.vsyscall_3)) {
- *(.vsyscall_3)
- }
-
-#define __VVAR_KERNEL_LDS
-#include <asm/vvar.h>
-#undef __VVAR_KERNEL_LDS
+ . = 2048;
+ *(.vsyscall_2)
- . = __vsyscall_0 + PAGE_SIZE;
+ . = 4096; /* Pad the whole page. */
+ } :user =0xcc
+ . = ALIGN(__vsyscall_0 + PAGE_SIZE, PAGE_SIZE);
#undef VSYSCALL_ADDR
#undef VLOAD_OFFSET
#undef VLOAD
#undef VVIRT_OFFSET
#undef VVIRT
+
+ __vvar_page = .;
+
+ .vvar : AT(ADDR(.vvar) - LOAD_OFFSET) {
+
+ /* Place all vvars at the offsets in asm/vvar.h. */
+#define EMIT_VVAR(name, offset) \
+ . = offset; \
+ *(.vvar_ ## name)
+#define __VVAR_KERNEL_LDS
+#include <asm/vvar.h>
+#undef __VVAR_KERNEL_LDS
#undef EMIT_VVAR
+ } :data
+
+ . = ALIGN(__vvar_page + PAGE_SIZE, PAGE_SIZE);
+
#endif /* CONFIG_X86_64 */
/* Init code and data - will be freed after init */
+++ /dev/null
-/* 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;
-}
* Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE
* Copyright 2003 Andi Kleen, SuSE Labs.
*
+ * [ NOTE: this mechanism is now deprecated in favor of the vDSO. ]
+ *
* Thanks to hpa@transmeta.com for some useful hint.
* Special thanks to Ingo Molnar for his early experience with
* a different vsyscall implementation for Linux/IA32 and for the name.
* vsyscalls. One vsyscall can reserve more than 1 slot to avoid
* jumping out of line if necessary. We cannot add more with this
* mechanism because older kernels won't return -ENOSYS.
- * If we want more than four we need a vDSO.
*
- * Note: the concept clashes with user mode linux. If you use UML and
- * want per guest time just set the kernel.vsyscall64 sysctl to 0.
+ * Note: the concept clashes with user mode linux. UML users should
+ * use the vDSO.
*/
/* Disable profiling for userspace code: */
#include <linux/cpu.h>
#include <linux/smp.h>
#include <linux/notifier.h>
+#include <linux/syscalls.h>
+#include <linux/ratelimit.h>
#include <asm/vsyscall.h>
#include <asm/pgtable.h>
+#include <asm/compat.h>
#include <asm/page.h>
#include <asm/unistd.h>
#include <asm/fixmap.h>
#include <asm/desc.h>
#include <asm/topology.h>
#include <asm/vgtod.h>
-
-#define __vsyscall(nr) \
- __attribute__ ((unused, __section__(".vsyscall_" #nr))) notrace
-#define __syscall_clobber "r11","cx","memory"
+#include <asm/traps.h>
DEFINE_VVAR(int, vgetcpu_mode);
DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data) =
{
.lock = __SEQLOCK_UNLOCKED(__vsyscall_gtod_data.lock),
- .sysctl_enabled = 1,
};
void update_vsyscall_tz(void)
unsigned long flags;
write_seqlock_irqsave(&vsyscall_gtod_data.lock, flags);
+
/* copy vsyscall data */
- vsyscall_gtod_data.clock.vread = clock->vread;
- vsyscall_gtod_data.clock.cycle_last = clock->cycle_last;
- vsyscall_gtod_data.clock.mask = clock->mask;
- vsyscall_gtod_data.clock.mult = mult;
- vsyscall_gtod_data.clock.shift = clock->shift;
- vsyscall_gtod_data.wall_time_sec = wall_time->tv_sec;
- vsyscall_gtod_data.wall_time_nsec = wall_time->tv_nsec;
- vsyscall_gtod_data.wall_to_monotonic = *wtm;
- vsyscall_gtod_data.wall_time_coarse = __current_kernel_time();
+ vsyscall_gtod_data.clock.vclock_mode = clock->archdata.vclock_mode;
+ vsyscall_gtod_data.clock.cycle_last = clock->cycle_last;
+ vsyscall_gtod_data.clock.mask = clock->mask;
+ vsyscall_gtod_data.clock.mult = mult;
+ vsyscall_gtod_data.clock.shift = clock->shift;
+ vsyscall_gtod_data.wall_time_sec = wall_time->tv_sec;
+ vsyscall_gtod_data.wall_time_nsec = wall_time->tv_nsec;
+ vsyscall_gtod_data.wall_to_monotonic = *wtm;
+ vsyscall_gtod_data.wall_time_coarse = __current_kernel_time();
+
write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags);
}
-/* RED-PEN may want to readd seq locking, but then the variable should be
- * write-once.
- */
-static __always_inline void do_get_tz(struct timezone * tz)
+static void warn_bad_vsyscall(const char *level, struct pt_regs *regs,
+ const char *message)
{
- *tz = VVAR(vsyscall_gtod_data).sys_tz;
-}
+ static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST);
+ struct task_struct *tsk;
-static __always_inline int gettimeofday(struct timeval *tv, struct timezone *tz)
-{
- int ret;
- asm volatile("syscall"
- : "=a" (ret)
- : "0" (__NR_gettimeofday),"D" (tv),"S" (tz)
- : __syscall_clobber );
- return ret;
-}
+ if (!show_unhandled_signals || !__ratelimit(&rs))
+ return;
-static __always_inline long time_syscall(long *t)
-{
- long secs;
- asm volatile("syscall"
- : "=a" (secs)
- : "0" (__NR_time),"D" (t) : __syscall_clobber);
- return secs;
-}
+ tsk = current;
-static __always_inline void do_vgettimeofday(struct timeval * tv)
-{
- cycle_t now, base, mask, cycle_delta;
- unsigned seq;
- unsigned long mult, shift, nsec;
- cycle_t (*vread)(void);
- do {
- seq = read_seqbegin(&VVAR(vsyscall_gtod_data).lock);
-
- vread = VVAR(vsyscall_gtod_data).clock.vread;
- if (unlikely(!VVAR(vsyscall_gtod_data).sysctl_enabled ||
- !vread)) {
- gettimeofday(tv,NULL);
- return;
- }
-
- now = vread();
- 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 = 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;
- /* convert to nsecs: */
- nsec += (cycle_delta * mult) >> shift;
-
- while (nsec >= NSEC_PER_SEC) {
- tv->tv_sec += 1;
- nsec -= NSEC_PER_SEC;
- }
- tv->tv_usec = nsec / NSEC_PER_USEC;
+ printk("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n",
+ level, tsk->comm, task_pid_nr(tsk),
+ message, regs->ip - 2, regs->cs,
+ regs->sp, regs->ax, regs->si, regs->di);
}
-int __vsyscall(0) vgettimeofday(struct timeval * tv, struct timezone * tz)
+static int addr_to_vsyscall_nr(unsigned long addr)
{
- if (tv)
- do_vgettimeofday(tv);
- if (tz)
- do_get_tz(tz);
- return 0;
-}
+ int nr;
-/* This will break when the xtime seconds get inaccurate, but that is
- * unlikely */
-time_t __vsyscall(1) vtime(time_t *t)
-{
- unsigned seq;
- time_t result;
- if (unlikely(!VVAR(vsyscall_gtod_data).sysctl_enabled))
- return time_syscall(t);
+ if ((addr & ~0xC00UL) != VSYSCALL_START)
+ return -EINVAL;
- do {
- seq = read_seqbegin(&VVAR(vsyscall_gtod_data).lock);
+ nr = (addr & 0xC00UL) >> 10;
+ if (nr >= 3)
+ return -EINVAL;
- result = VVAR(vsyscall_gtod_data).wall_time_sec;
+ return nr;
+}
- } while (read_seqretry(&VVAR(vsyscall_gtod_data).lock, seq));
+void dotraplinkage do_emulate_vsyscall(struct pt_regs *regs, long error_code)
+{
+ struct task_struct *tsk;
+ unsigned long caller;
+ int vsyscall_nr;
+ long ret;
+
+ local_irq_enable();
+
+ /*
+ * Real 64-bit user mode code has cs == __USER_CS. Anything else
+ * is bogus.
+ */
+ if (regs->cs != __USER_CS) {
+ /*
+ * If we trapped from kernel mode, we might as well OOPS now
+ * instead of returning to some random address and OOPSing
+ * then.
+ */
+ BUG_ON(!user_mode(regs));
+
+ /* Compat mode and non-compat 32-bit CS should both segfault. */
+ warn_bad_vsyscall(KERN_WARNING, regs,
+ "illegal int 0xcc from 32-bit mode");
+ goto sigsegv;
+ }
- if (t)
- *t = result;
- return result;
-}
+ /*
+ * x86-ism here: regs->ip points to the instruction after the int 0xcc,
+ * and int 0xcc is two bytes long.
+ */
+ vsyscall_nr = addr_to_vsyscall_nr(regs->ip - 2);
+ if (vsyscall_nr < 0) {
+ warn_bad_vsyscall(KERN_WARNING, regs,
+ "illegal int 0xcc (exploit attempt?)");
+ goto sigsegv;
+ }
-/* Fast way to get current CPU and node.
- This helps to do per node and per CPU caches in user space.
- The result is not guaranteed without CPU affinity, but usually
- works out because the scheduler tries to keep a thread on the same
- CPU.
+ if (get_user(caller, (unsigned long __user *)regs->sp) != 0) {
+ warn_bad_vsyscall(KERN_WARNING, regs, "int 0xcc with bad stack (exploit attempt?)");
+ goto sigsegv;
+ }
- tcache must point to a two element sized long array.
- All arguments can be NULL. */
-long __vsyscall(2)
-vgetcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *tcache)
-{
- unsigned int p;
- unsigned long j = 0;
-
- /* Fast cache - only recompute value once per jiffies and avoid
- relatively costly rdtscp/cpuid otherwise.
- This works because the scheduler usually keeps the process
- on the same CPU and this syscall doesn't guarantee its
- results anyways.
- 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 = VVAR(jiffies))) {
- p = tcache->blob[1];
- } else 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));
+ tsk = current;
+ if (seccomp_mode(&tsk->seccomp))
+ do_exit(SIGKILL);
+
+ switch (vsyscall_nr) {
+ case 0:
+ ret = sys_gettimeofday(
+ (struct timeval __user *)regs->di,
+ (struct timezone __user *)regs->si);
+ break;
+
+ case 1:
+ ret = sys_time((time_t __user *)regs->di);
+ break;
+
+ case 2:
+ ret = sys_getcpu((unsigned __user *)regs->di,
+ (unsigned __user *)regs->si,
+ 0);
+ break;
}
- if (tcache) {
- tcache->blob[0] = j;
- tcache->blob[1] = p;
+
+ if (ret == -EFAULT) {
+ /*
+ * Bad news -- userspace fed a bad pointer to a vsyscall.
+ *
+ * With a real vsyscall, that would have caused SIGSEGV.
+ * To make writing reliable exploits using the emulated
+ * vsyscalls harder, generate SIGSEGV here as well.
+ */
+ warn_bad_vsyscall(KERN_INFO, regs,
+ "vsyscall fault (exploit attempt?)");
+ goto sigsegv;
}
- if (cpu)
- *cpu = p & 0xfff;
- if (node)
- *node = p >> 12;
- return 0;
-}
-static long __vsyscall(3) venosys_1(void)
-{
- return -ENOSYS;
-}
+ regs->ax = ret;
-#ifdef CONFIG_SYSCTL
-static ctl_table kernel_table2[] = {
- { .procname = "vsyscall64",
- .data = &vsyscall_gtod_data.sysctl_enabled, .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec },
- {}
-};
+ /* Emulate a ret instruction. */
+ regs->ip = caller;
+ regs->sp += 8;
-static ctl_table kernel_root_table2[] = {
- { .procname = "kernel", .mode = 0555,
- .child = kernel_table2 },
- {}
-};
-#endif
+ local_irq_disable();
+ return;
+
+sigsegv:
+ regs->ip -= 2; /* The faulting instruction should be the int 0xcc. */
+ force_sig(SIGSEGV, current);
+ local_irq_disable();
+}
-/* Assume __initcall executes before all user space. Hopefully kmod
- doesn't violate that. We'll find out if it does. */
+/*
+ * Assume __initcall executes before all user space. Hopefully kmod
+ * doesn't violate that. We'll find out if it does.
+ */
static void __cpuinit vsyscall_set_cpu(int cpu)
{
unsigned long d;
if (cpu_has(&cpu_data(cpu), X86_FEATURE_RDTSCP))
write_rdtscp_aux((node << 12) | cpu);
- /* Store cpu number in limit so that it can be loaded quickly
- in user space in vgetcpu.
- 12 bits for the CPU and 8 bits for the node. */
+ /*
+ * Store cpu number in limit so that it can be loaded quickly
+ * in user space in vgetcpu. (12 bits for the CPU and 8 bits for the node)
+ */
d = 0x0f40000000000ULL;
d |= cpu;
d |= (node & 0xf) << 12;
d |= (node >> 4) << 48;
+
write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_PER_CPU, &d, DESCTYPE_S);
}
cpu_vsyscall_notifier(struct notifier_block *n, unsigned long action, void *arg)
{
long cpu = (long)arg;
+
if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN)
smp_call_function_single(cpu, cpu_vsyscall_init, NULL, 1);
+
return NOTIFY_DONE;
}
{
extern char __vsyscall_0;
unsigned long physaddr_page0 = __pa_symbol(&__vsyscall_0);
+ extern char __vvar_page;
+ unsigned long physaddr_vvar_page = __pa_symbol(&__vvar_page);
/* Note that VSYSCALL_MAPPED_PAGES must agree with the code below. */
__set_fixmap(VSYSCALL_FIRST_PAGE, physaddr_page0, PAGE_KERNEL_VSYSCALL);
+ __set_fixmap(VVAR_PAGE, physaddr_vvar_page, PAGE_KERNEL_VVAR);
+ BUILD_BUG_ON((unsigned long)__fix_to_virt(VVAR_PAGE) != (unsigned long)VVAR_ADDRESS);
}
static int __init vsyscall_init(void)
{
- BUG_ON(((unsigned long) &vgettimeofday !=
- VSYSCALL_ADDR(__NR_vgettimeofday)));
- BUG_ON((unsigned long) &vtime != VSYSCALL_ADDR(__NR_vtime));
- BUG_ON((VSYSCALL_ADDR(0) != __fix_to_virt(VSYSCALL_FIRST_PAGE)));
- BUG_ON((unsigned long) &vgetcpu != VSYSCALL_ADDR(__NR_vgetcpu));
-#ifdef CONFIG_SYSCTL
- register_sysctl_table(kernel_root_table2);
-#endif
+ BUG_ON(VSYSCALL_ADDR(0) != __fix_to_virt(VSYSCALL_FIRST_PAGE));
+
on_each_cpu(cpu_vsyscall_init, NULL, 1);
/* notifier priority > KVM */
hotcpu_notifier(cpu_vsyscall_notifier, 30);
+
return 0;
}
-
__initcall(vsyscall_init);
--- /dev/null
+/*
+ * vsyscall_emu_64.S: Vsyscall emulation page
+ *
+ * Copyright (c) 2011 Andy Lutomirski
+ *
+ * Subject to the GNU General Public License, version 2
+ */
+
+#include <linux/linkage.h>
+#include <asm/irq_vectors.h>
+
+/* The unused parts of the page are filled with 0xcc by the linker script. */
+
+.section .vsyscall_0, "a"
+ENTRY(vsyscall_0)
+ int $VSYSCALL_EMU_VECTOR
+END(vsyscall_0)
+
+.section .vsyscall_1, "a"
+ENTRY(vsyscall_1)
+ int $VSYSCALL_EMU_VECTOR
+END(vsyscall_1)
+
+.section .vsyscall_2, "a"
+ENTRY(vsyscall_2)
+ int $VSYSCALL_EMU_VECTOR
+END(vsyscall_2)
#include <linux/linkage.h>
#include <asm/dwarf2.h>
+#include <asm/alternative-asm.h>
ALIGN
copy_page_c:
2:
.previous
.section .altinstructions,"a"
- .align 8
- .quad copy_page
- .quad 1b
- .word X86_FEATURE_REP_GOOD
- .byte .Lcopy_page_end - copy_page
- .byte 2b - 1b
+ altinstruction_entry copy_page, 1b, X86_FEATURE_REP_GOOD, \
+ .Lcopy_page_end-copy_page, 2b-1b
.previous
#include <linux/linkage.h>
#include <asm/dwarf2.h>
#include <asm/cpufeature.h>
+#include <asm/alternative-asm.h>
#undef memmove
.previous
.section .altinstructions,"a"
- .align 8
- .quad .Lmemmove_begin_forward
- .quad .Lmemmove_begin_forward_efs
- .word X86_FEATURE_ERMS
- .byte .Lmemmove_end_forward-.Lmemmove_begin_forward
- .byte .Lmemmove_end_forward_efs-.Lmemmove_begin_forward_efs
+ altinstruction_entry .Lmemmove_begin_forward, \
+ .Lmemmove_begin_forward_efs,X86_FEATURE_ERMS, \
+ .Lmemmove_end_forward-.Lmemmove_begin_forward, \
+ .Lmemmove_end_forward_efs-.Lmemmove_begin_forward_efs
.previous
ENDPROC(memmove)
export CPPFLAGS_vdso.lds += -P -C
VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \
+ -Wl,--no-undefined \
-Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096
$(obj)/vdso.o: $(src)/vdso.S $(obj)/vdso.so
*
* The code should have no internal unresolved relocations.
* Check with readelf after changing.
- * Also alternative() doesn't work.
*/
/* Disable profiling for userspace code: */
#include <linux/time.h>
#include <linux/string.h>
#include <asm/vsyscall.h>
+#include <asm/fixmap.h>
#include <asm/vgtod.h>
#include <asm/timex.h>
#include <asm/hpet.h>
#define gtod (&VVAR(vsyscall_gtod_data))
+notrace static cycle_t 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;
+}
+
+static notrace cycle_t vread_hpet(void)
+{
+ return readl((const void __iomem *)fix_to_virt(VSYSCALL_HPET) + 0xf0);
+}
+
notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
{
long ret;
notrace static inline long vgetns(void)
{
long v;
- cycles_t (*vread)(void);
- vread = gtod->clock.vread;
- v = (vread() - gtod->clock.cycle_last) & gtod->clock.mask;
+ cycles_t cycles;
+ if (gtod->clock.vclock_mode == VCLOCK_TSC)
+ cycles = vread_tsc();
+ else
+ cycles = vread_hpet();
+ v = (cycles - gtod->clock.cycle_last) & gtod->clock.mask;
return (v * gtod->clock.mult) >> gtod->clock.shift;
}
notrace int __vdso_clock_gettime(clockid_t clock, struct timespec *ts)
{
- if (likely(gtod->sysctl_enabled))
- switch (clock) {
- case CLOCK_REALTIME:
- if (likely(gtod->clock.vread))
- return do_realtime(ts);
- break;
- case CLOCK_MONOTONIC:
- if (likely(gtod->clock.vread))
- return do_monotonic(ts);
- break;
- case CLOCK_REALTIME_COARSE:
- return do_realtime_coarse(ts);
- case CLOCK_MONOTONIC_COARSE:
- return do_monotonic_coarse(ts);
- }
+ switch (clock) {
+ case CLOCK_REALTIME:
+ if (likely(gtod->clock.vclock_mode != VCLOCK_NONE))
+ return do_realtime(ts);
+ break;
+ case CLOCK_MONOTONIC:
+ if (likely(gtod->clock.vclock_mode != VCLOCK_NONE))
+ return do_monotonic(ts);
+ break;
+ case CLOCK_REALTIME_COARSE:
+ return do_realtime_coarse(ts);
+ case CLOCK_MONOTONIC_COARSE:
+ return do_monotonic_coarse(ts);
+ }
+
return vdso_fallback_gettime(clock, ts);
}
int clock_gettime(clockid_t, struct timespec *)
notrace int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
{
long ret;
- if (likely(gtod->sysctl_enabled && gtod->clock.vread)) {
+ if (likely(gtod->clock.vclock_mode != VCLOCK_NONE)) {
if (likely(tv != NULL)) {
BUILD_BUG_ON(offsetof(struct timeval, tv_usec) !=
offsetof(struct timespec, tv_nsec) ||
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;
-}
-
+/*
+ * This will break when the xtime seconds get inaccurate, but that is
+ * unlikely
+ */
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);
+ time_t result = ACCESS_ONCE(VVAR(vsyscall_gtod_data).wall_time_sec);
if (t)
*t = result;
+#include <asm/page_types.h>
+#include <linux/linkage.h>
#include <linux/init.h>
-__INITDATA
+__PAGE_ALIGNED_DATA
.globl vdso_start, vdso_end
+ .align PAGE_SIZE
vdso_start:
.incbin "arch/x86/vdso/vdso.so"
vdso_end:
-__FINIT
+.previous
+
+ .globl vdso_pages
+ .bss
+ .align 8
+ .type vdso_pages, @object
+vdso_pages:
+ .zero (vdso_end - vdso_start + PAGE_SIZE - 1) / PAGE_SIZE * 8
+ .size vdso_pages, .-vdso_pages
#include <asm/vgtod.h>
#include <asm/proto.h>
#include <asm/vdso.h>
+#include <asm/page.h>
unsigned int __read_mostly vdso_enabled = 1;
extern char vdso_start[], vdso_end[];
extern unsigned short vdso_sync_cpuid;
-static struct page **vdso_pages;
+extern struct page *vdso_pages[];
static unsigned vdso_size;
-static int __init init_vdso_vars(void)
+static void __init patch_vdso(void *vdso, size_t len)
+{
+ Elf64_Ehdr *hdr = vdso;
+ Elf64_Shdr *sechdrs, *alt_sec = 0;
+ char *secstrings;
+ void *alt_data;
+ int i;
+
+ BUG_ON(len < sizeof(Elf64_Ehdr));
+ BUG_ON(memcmp(hdr->e_ident, ELFMAG, SELFMAG) != 0);
+
+ sechdrs = (void *)hdr + hdr->e_shoff;
+ secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
+
+ for (i = 1; i < hdr->e_shnum; i++) {
+ Elf64_Shdr *shdr = &sechdrs[i];
+ if (!strcmp(secstrings + shdr->sh_name, ".altinstructions")) {
+ alt_sec = shdr;
+ goto found;
+ }
+ }
+
+ /* If we get here, it's probably a bug. */
+ pr_warning("patch_vdso: .altinstructions not found\n");
+ return; /* nothing to patch */
+
+found:
+ alt_data = (void *)hdr + alt_sec->sh_offset;
+ apply_alternatives(alt_data, alt_data + alt_sec->sh_size);
+}
+
+static int __init init_vdso(void)
{
int npages = (vdso_end - vdso_start + PAGE_SIZE - 1) / PAGE_SIZE;
int i;
+ patch_vdso(vdso_start, vdso_end - vdso_start);
+
vdso_size = npages << PAGE_SHIFT;
- vdso_pages = kmalloc(sizeof(struct page *) * npages, GFP_KERNEL);
- if (!vdso_pages)
- goto oom;
- for (i = 0; i < npages; i++) {
- struct page *p;
- p = alloc_page(GFP_KERNEL);
- if (!p)
- goto oom;
- vdso_pages[i] = p;
- copy_page(page_address(p), vdso_start + i*PAGE_SIZE);
- }
+ for (i = 0; i < npages; i++)
+ vdso_pages[i] = virt_to_page(vdso_start + i*PAGE_SIZE);
return 0;
-
- oom:
- printk("Cannot allocate vdso\n");
- vdso_enabled = 0;
- return -ENOMEM;
}
-subsys_initcall(init_vdso_vars);
+subsys_initcall(init_vdso);
struct linux_binprm;
#ifdef CONFIG_IA64
if (!hpet_clocksource) {
hpet_mctr = (void __iomem *)&hpetp->hp_hpet->hpet_mc;
- CLKSRC_FSYS_MMIO_SET(clocksource_hpet.fsys_mmio, hpet_mctr);
+ clocksource_hpet.archdata.fsys_mmio = hpet_mctr;
clocksource_register_hz(&clocksource_hpet, hpetp->hp_tick_freq);
hpetp->hp_clocksource = &clocksource_hpet;
hpet_clocksource = &clocksource_hpet;
typedef u64 cycle_t;
struct clocksource;
+#ifdef CONFIG_ARCH_CLOCKSOURCE_DATA
+#include <asm/clocksource.h>
+#endif
+
/**
* struct cyclecounter - hardware abstraction for a free running counter
* Provides completely state-free accessors to the underlying hardware.
* @shift: cycle to nanosecond divisor (power of two)
* @max_idle_ns: max idle time permitted by the clocksource (nsecs)
* @flags: flags describing special properties
- * @vread: vsyscall based read
+ * @archdata: arch-specific data
* @suspend: suspend function for the clocksource, if necessary
* @resume: resume function for the clocksource, if necessary
*/
u32 shift;
u64 max_idle_ns;
-#ifdef CONFIG_IA64
- void *fsys_mmio; /* used by fsyscall asm code */
-#define CLKSRC_FSYS_MMIO_SET(mmio, addr) ((mmio) = (addr))
-#else
-#define CLKSRC_FSYS_MMIO_SET(mmio, addr) do { } while (0)
+#ifdef CONFIG_ARCH_CLOCKSOURCE_DATA
+ struct arch_clocksource_data archdata;
#endif
+
const char *name;
struct list_head list;
int rating;
- cycle_t (*vread)(void);
int (*enable)(struct clocksource *cs);
void (*disable)(struct clocksource *cs);
unsigned long flags;
extern long prctl_get_seccomp(void);
extern long prctl_set_seccomp(unsigned long);
+static inline int seccomp_mode(seccomp_t *s)
+{
+ return s->mode;
+}
+
#else /* CONFIG_SECCOMP */
#include <linux/errno.h>
return -EINVAL;
}
+static inline int seccomp_mode(seccomp_t *s)
+{
+ return 0;
+}
+
#endif /* CONFIG_SECCOMP */
#endif /* _LINUX_SECCOMP_H */
git.openpandora.org / pandora-kernel.git / commitdiff