Initial import

5 files changed, 466 insertions, 0 deletions

diff --git a/Documentation/vDSO/.gitignore b/Documentation/vDSO/.gitignore
new file mode 100644
index 000000000..133bf9ee9
--- /dev/null
+++ b/Documentation/vDSO/.gitignore
@@ -0,0 +1,2 @@
+vdso_test
+vdso_standalone_test_x86
diff --git a/Documentation/vDSO/Makefile b/Documentation/vDSO/Makefile
new file mode 100644
index 000000000..ee075c3d2
--- /dev/null
+++ b/Documentation/vDSO/Makefile
@@ -0,0 +1,15 @@
+# vdso_test won't build for glibc < 2.16, so disable it
+# hostprogs-y := vdso_test
+hostprogs-$(CONFIG_X86) := vdso_standalone_test_x86
+vdso_standalone_test_x86-objs := vdso_standalone_test_x86.o parse_vdso.o
+vdso_test-objs := parse_vdso.o vdso_test.o
+
+# Tell kbuild to always build the programs
+always := $(hostprogs-y)
+
+HOSTCFLAGS := -I$(objtree)/usr/include -std=gnu99
+HOSTCFLAGS_vdso_standalone_test_x86.o := -fno-asynchronous-unwind-tables -fno-stack-protector
+HOSTLOADLIBES_vdso_standalone_test_x86 := -nostdlib
+ifeq ($(CONFIG_X86_32),y)
+HOSTLOADLIBES_vdso_standalone_test_x86 += -lgcc_s
+endif
diff --git a/Documentation/vDSO/parse_vdso.c b/Documentation/vDSO/parse_vdso.c
new file mode 100644
index 000000000..1dbb4b872
--- /dev/null
+++ b/Documentation/vDSO/parse_vdso.c
@@ -0,0 +1,269 @@
+/*
+ * parse_vdso.c: Linux reference vDSO parser
+ * Written by Andrew Lutomirski, 2011-2014.
+ *
+ * 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.  In principle it should work on any
+ * architecture that has a vDSO.
+ */
+
+#include <stdbool.h>
+#include <stdint.h>
+#include <string.h>
+#include <limits.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 ELF_BITS
+# if ULONG_MAX > 0xffffffffUL
+#  define ELF_BITS 64
+# else
+#  define ELF_BITS 32
+# endif
+#endif
+
+#define ELF_BITS_XFORM2(bits, x) Elf##bits##_##x
+#define ELF_BITS_XFORM(bits, x) ELF_BITS_XFORM2(bits, x)
+#define ELF(x) ELF_BITS_XFORM(ELF_BITS, x)
+
+static struct vdso_info
+{
+	bool valid;
+
+	/* Load information */
+	uintptr_t load_addr;
+	uintptr_t load_offset;  /* load_addr - recorded vaddr */
+
+	/* Symbol table */
+	ELF(Sym) *symtab;
+	const char *symstrings;
+	ELF(Word) *bucket, *chain;
+	ELF(Word) nbucket, nchain;
+
+	/* Version table */
+	ELF(Versym) *versym;
+	ELF(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;
+
+	ELF(Ehdr) *hdr = (ELF(Ehdr)*)base;
+	if (hdr->e_ident[EI_CLASS] !=
+	    (ELF_BITS == 32 ? ELFCLASS32 : ELFCLASS64)) {
+		return;  /* Wrong ELF class -- check ELF_BITS */
+	}
+
+	ELF(Phdr) *pt = (ELF(Phdr)*)(vdso_info.load_addr + hdr->e_phoff);
+	ELF(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 = (ELF(Dyn)*)(base + pt[i].p_offset);
+		}
+	}
+
+	if (!found_vaddr || !dyn)
+		return;  /* Failed */
+
+	/*
+	 * Fish out the useful bits of the dynamic table.
+	 */
+	ELF(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 = (ELF(Sym) *)
+				((uintptr_t)dyn[i].d_un.d_ptr
+				 + vdso_info.load_offset);
+			break;
+		case DT_HASH:
+			hash = (ELF(Word) *)
+				((uintptr_t)dyn[i].d_un.d_ptr
+				 + vdso_info.load_offset);
+			break;
+		case DT_VERSYM:
+			vdso_info.versym = (ELF(Versym) *)
+				((uintptr_t)dyn[i].d_un.d_ptr
+				 + vdso_info.load_offset);
+			break;
+		case DT_VERDEF:
+			vdso_info.verdef = (ELF(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(ELF(Versym) ver,
+			       const char *name, ELF(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" */
+	ELF(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 = (ELF(Verdef) *)((char *)def + def->vd_next);
+	}
+
+	/* Now figure out whether it matches. */
+	ELF(Verdaux) *aux = (ELF(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);
+	ELF(Word) chain = vdso_info.bucket[elf_hash(name) % vdso_info.nbucket];
+
+	for (; chain != STN_UNDEF; chain = vdso_info.chain[chain]) {
+		ELF(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)
+{
+	ELF(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;
+}
diff --git a/Documentation/vDSO/vdso_standalone_test_x86.c b/Documentation/vDSO/vdso_standalone_test_x86.c
new file mode 100644
index 000000000..93b0ebf8c
--- /dev/null
+++ b/Documentation/vDSO/vdso_standalone_test_x86.c
@@ -0,0 +1,128 @@
+/*
+ * vdso_test.c: Sample code to test parse_vdso.c on x86
+ * Copyright (c) 2011-2014 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 -lgcc_s
+ *      vdso_standalone_test_x86.c parse_vdso.c
+ * to generate a small binary.  On x86_64, you can omit -lgcc_s
+ * if you want the binary to be completely standalone.
+ */
+
+#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-specific. */
+static inline long x86_syscall3(long nr, long a0, long a1, long a2)
+{
+	long ret;
+#ifdef __x86_64__
+	asm volatile ("syscall" : "=a" (ret) : "a" (nr),
+		      "D" (a0), "S" (a1), "d" (a2) :
+		      "cc", "memory", "rcx",
+		      "r8", "r9", "r10", "r11" );
+#else
+	asm volatile ("int $0x80" : "=a" (ret) : "a" (nr),
+		      "b" (a0), "c" (a1), "d" (a2) :
+		      "cc", "memory" );
+#endif
+	return ret;
+}
+
+static inline long linux_write(int fd, const void *data, size_t len)
+{
+	return x86_syscall3(__NR_write, fd, (long)data, (long)len);
+}
+
+static inline void linux_exit(int code)
+{
+	x86_syscall3(__NR_exit, code, 0, 0);
+}
+
+void to_base10(char *lastdig, time_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"
+#ifdef __x86_64__
+	"mov %rsp,%rdi\n\t"
+	"jmp c_main"
+#else
+	"push %esp\n\t"
+	"call c_main\n\t"
+	"int $3"
+#endif
+	);
diff --git a/Documentation/vDSO/vdso_test.c b/Documentation/vDSO/vdso_test.c
new file mode 100644
index 000000000..8daeb7d70
--- /dev/null
+++ b/Documentation/vDSO/vdso_test.c
@@ -0,0 +1,52 @@
+/*
+ * vdso_test.c: Sample code to test parse_vdso.c
+ * Copyright (c) 2014 Andy Lutomirski
+ * Subject to the GNU General Public License, version 2
+ *
+ * Compile with:
+ * gcc -std=gnu99 vdso_test.c parse_vdso.c
+ *
+ * Tested on x86, 32-bit and 64-bit.  It may work on other architectures, too.
+ */
+
+#include <stdint.h>
+#include <elf.h>
+#include <stdio.h>
+#include <sys/auxv.h>
+#include <sys/time.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);
+
+int main(int argc, char **argv)
+{
+	unsigned long sysinfo_ehdr = getauxval(AT_SYSINFO_EHDR);
+	if (!sysinfo_ehdr) {
+		printf("AT_SYSINFO_EHDR is not present!\n");
+		return 0;
+	}
+
+	vdso_init_from_sysinfo_ehdr(getauxval(AT_SYSINFO_EHDR));
+
+	/* 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) {
+		printf("Could not find __vdso_gettimeofday\n");
+		return 1;
+	}
+
+	struct timeval tv;
+	long ret = gtod(&tv, 0);
+
+	if (ret == 0) {
+		printf("The time is %lld.%06lld\n",
+		       (long long)tv.tv_sec, (long long)tv.tv_usec);
+	} else {
+		printf("__vdso_gettimeofday failed\n");
+	}
+
+	return 0;
+}