Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (163 commits)
  tracing: Fix compile issue for trace_sched_wakeup.c
  [S390] hardirq: remove pointless header file includes
  [IA64] Move local_softirq_pending() definition
  perf, powerpc: Fix power_pmu_event_init to not use event->ctx
  ftrace: Remove recursion between recordmcount and scripts/mod/empty
  jump_label: Add COND_STMT(), reducer wrappery
  perf: Optimize sw events
  perf: Use jump_labels to optimize the scheduler hooks
  jump_label: Add atomic_t interface
  jump_label: Use more consistent naming
  perf, hw_breakpoint: Fix crash in hw_breakpoint creation
  perf: Find task before event alloc
  perf: Fix task refcount bugs
  perf: Fix group moving
  irq_work: Add generic hardirq context callbacks
  perf_events: Fix transaction recovery in group_sched_in()
  perf_events: Fix bogus AMD64 generic TLB events
  perf_events: Fix bogus context time tracking
  tracing: Remove parent recording in latency tracer graph options
  tracing: Use one prologue for the preempt irqs off tracer function tracers
  ...

8 files changed, 747 insertions, 75 deletions

diff --git a/scripts/Makefile b/scripts/Makefile
index 842dbc2..2e08810 100644
--- a/scripts/Makefile
+++ b/scripts/Makefile
@@ -11,6 +11,7 @@ hostprogs-$(CONFIG_KALLSYMS)     += kallsyms
 hostprogs-$(CONFIG_LOGO)         += pnmtologo
 hostprogs-$(CONFIG_VT)           += conmakehash
 hostprogs-$(CONFIG_IKCONFIG)     += bin2c
+hostprogs-$(BUILD_C_RECORDMCOUNT) += recordmcount
 
 always		:= $(hostprogs-y) $(hostprogs-m)
 
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index a1a5cf9..843bd4f 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -209,12 +209,22 @@ cmd_modversions =								\
 endif
 
 ifdef CONFIG_FTRACE_MCOUNT_RECORD
+ifdef BUILD_C_RECORDMCOUNT
+# Due to recursion, we must skip empty.o.
+# The empty.o file is created in the make process in order to determine
+#  the target endianness and word size. It is made before all other C
+#  files, including recordmcount.
+cmd_record_mcount = if [ $(@) != "scripts/mod/empty.o" ]; then			\
+			$(objtree)/scripts/recordmcount "$(@)";			\
+		    fi;
+else
 cmd_record_mcount = set -e ; perl $(srctree)/scripts/recordmcount.pl "$(ARCH)" \
 	"$(if $(CONFIG_CPU_BIG_ENDIAN),big,little)" \
 	"$(if $(CONFIG_64BIT),64,32)" \
 	"$(OBJDUMP)" "$(OBJCOPY)" "$(CC)" "$(LD)" "$(NM)" "$(RM)" "$(MV)" \
 	"$(if $(part-of-module),1,0)" "$(@)";
 endif
+endif
 
 define rule_cc_o_c
 	$(call echo-cmd,checksrc) $(cmd_checksrc)			  \
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 54fd1b7..7bfcf1a 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -101,14 +101,6 @@ basename_flags = -D"KBUILD_BASENAME=KBUILD_STR($(call name-fix,$(basetarget)))"
 modname_flags  = $(if $(filter 1,$(words $(modname))),\
                  -D"KBUILD_MODNAME=KBUILD_STR($(call name-fix,$(modname)))")
 
-#hash values
-ifdef CONFIG_DYNAMIC_DEBUG
-debug_flags = -D"DEBUG_HASH=$(shell ./scripts/basic/hash djb2 $(@D)$(modname))"\
-              -D"DEBUG_HASH2=$(shell ./scripts/basic/hash r5 $(@D)$(modname))"
-else
-debug_flags =
-endif
-
 orig_c_flags   = $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) $(KBUILD_SUBDIR_CCFLAGS) \
                  $(ccflags-y) $(CFLAGS_$(basetarget).o)
 _c_flags       = $(filter-out $(CFLAGS_REMOVE_$(basetarget).o), $(orig_c_flags))
@@ -152,8 +144,7 @@ endif
 
 c_flags        = -Wp,-MD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE)     \
 		 $(__c_flags) $(modkern_cflags)                           \
-		 -D"KBUILD_STR(s)=\#s" $(basename_flags) $(modname_flags) \
-		  $(debug_flags)
+		 -D"KBUILD_STR(s)=\#s" $(basename_flags) $(modname_flags)
 
 a_flags        = -Wp,-MD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE)     \
 		 $(__a_flags) $(modkern_aflags)
diff --git a/scripts/basic/Makefile b/scripts/basic/Makefile
index 0955995..4c324a1 100644
--- a/scripts/basic/Makefile
+++ b/scripts/basic/Makefile
@@ -9,7 +9,7 @@
 # fixdep: 	 Used to generate dependency information during build process
 # docproc:	 Used in Documentation/DocBook
 
-hostprogs-y	:= fixdep docproc hash
+hostprogs-y	:= fixdep docproc
 always		:= $(hostprogs-y)
 
 # fixdep is needed to compile other host programs
diff --git a/scripts/basic/hash.c b/scripts/basic/hash.c
deleted file mode 100644
index 2ef5d3f..0000000
--- a/scripts/basic/hash.c
+++ /dev/null
@@ -1,64 +0,0 @@
-/*
- * Copyright (C) 2008 Red Hat, Inc., Jason Baron <jbaron@redhat.com>
- *
- */
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-
-#define DYNAMIC_DEBUG_HASH_BITS 6
-
-static const char *program;
-
-static void usage(void)
-{
-	printf("Usage: %s <djb2|r5> <modname>\n", program);
-	exit(1);
-}
-
-/* djb2 hashing algorithm by Dan Bernstein. From:
- * http://www.cse.yorku.ca/~oz/hash.html
- */
-
-static unsigned int djb2_hash(char *str)
-{
-	unsigned long hash = 5381;
-	int c;
-
-	c = *str;
-	while (c) {
-		hash = ((hash << 5) + hash) + c;
-		c = *++str;
-	}
-	return (unsigned int)(hash & ((1 << DYNAMIC_DEBUG_HASH_BITS) - 1));
-}
-
-static unsigned int r5_hash(char *str)
-{
-	unsigned long hash = 0;
-	int c;
-
-	c = *str;
-	while (c) {
-		hash = (hash + (c << 4) + (c >> 4)) * 11;
-		c = *++str;
-	}
-	return (unsigned int)(hash & ((1 << DYNAMIC_DEBUG_HASH_BITS) - 1));
-}
-
-int main(int argc, char *argv[])
-{
-	program = argv[0];
-
-	if (argc != 3)
-		usage();
-	if (!strcmp(argv[1], "djb2"))
-		printf("%d\n", djb2_hash(argv[2]));
-	else if (!strcmp(argv[1], "r5"))
-		printf("%d\n", r5_hash(argv[2]));
-	else
-		usage();
-	exit(0);
-}
-
diff --git a/scripts/gcc-goto.sh b/scripts/gcc-goto.sh
new file mode 100644
index 0000000..520d16b
--- /dev/null
+++ b/scripts/gcc-goto.sh
@@ -0,0 +1,5 @@
+#!/bin/sh
+# Test for gcc 'asm goto' suport
+# Copyright (C) 2010, Jason Baron <jbaron@redhat.com>
+
+echo "int main(void) { entry: asm goto (\"\"::::entry); return 0; }" | $@ -x c - -c -o /dev/null >/dev/null 2>&1 && echo "y"
diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c
new file mode 100644
index 0000000..26e1271
--- /dev/null
+++ b/scripts/recordmcount.c
@@ -0,0 +1,363 @@
+/*
+ * recordmcount.c: construct a table of the locations of calls to 'mcount'
+ * so that ftrace can find them quickly.
+ * Copyright 2009 John F. Reiser <jreiser@BitWagon.com>.  All rights reserved.
+ * Licensed under the GNU General Public License, version 2 (GPLv2).
+ *
+ * Restructured to fit Linux format, as well as other updates:
+ *  Copyright 2010 Steven Rostedt <srostedt@redhat.com>, Red Hat Inc.
+ */
+
+/*
+ * Strategy: alter the .o file in-place.
+ *
+ * Append a new STRTAB that has the new section names, followed by a new array
+ * ElfXX_Shdr[] that has the new section headers, followed by the section
+ * contents for __mcount_loc and its relocations.  The old shstrtab strings,
+ * and the old ElfXX_Shdr[] array, remain as "garbage" (commonly, a couple
+ * kilobytes.)  Subsequent processing by /bin/ld (or the kernel module loader)
+ * will ignore the garbage regions, because they are not designated by the
+ * new .e_shoff nor the new ElfXX_Shdr[].  [In order to remove the garbage,
+ * then use "ld -r" to create a new file that omits the garbage.]
+ */
+
+#include <sys/types.h>
+#include <sys/mman.h>
+#include <sys/stat.h>
+#include <elf.h>
+#include <fcntl.h>
+#include <setjmp.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+static int fd_map;	/* File descriptor for file being modified. */
+static int mmap_failed; /* Boolean flag. */
+static void *ehdr_curr; /* current ElfXX_Ehdr *  for resource cleanup */
+static char gpfx;	/* prefix for global symbol name (sometimes '_') */
+static struct stat sb;	/* Remember .st_size, etc. */
+static jmp_buf jmpenv;	/* setjmp/longjmp per-file error escape */
+
+/* setjmp() return values */
+enum {
+	SJ_SETJMP = 0,  /* hardwired first return */
+	SJ_FAIL,
+	SJ_SUCCEED
+};
+
+/* Per-file resource cleanup when multiple files. */
+static void
+cleanup(void)
+{
+	if (!mmap_failed)
+		munmap(ehdr_curr, sb.st_size);
+	else
+		free(ehdr_curr);
+	close(fd_map);
+}
+
+static void __attribute__((noreturn))
+fail_file(void)
+{
+	cleanup();
+	longjmp(jmpenv, SJ_FAIL);
+}
+
+static void __attribute__((noreturn))
+succeed_file(void)
+{
+	cleanup();
+	longjmp(jmpenv, SJ_SUCCEED);
+}
+
+/* ulseek, uread, ...:  Check return value for errors. */
+
+static off_t
+ulseek(int const fd, off_t const offset, int const whence)
+{
+	off_t const w = lseek(fd, offset, whence);
+	if ((off_t)-1 == w) {
+		perror("lseek");
+		fail_file();
+	}
+	return w;
+}
+
+static size_t
+uread(int const fd, void *const buf, size_t const count)
+{
+	size_t const n = read(fd, buf, count);
+	if (n != count) {
+		perror("read");
+		fail_file();
+	}
+	return n;
+}
+
+static size_t
+uwrite(int const fd, void const *const buf, size_t const count)
+{
+	size_t const n = write(fd, buf, count);
+	if (n != count) {
+		perror("write");
+		fail_file();
+	}
+	return n;
+}
+
+static void *
+umalloc(size_t size)
+{
+	void *const addr = malloc(size);
+	if (0 == addr) {
+		fprintf(stderr, "malloc failed: %zu bytes\n", size);
+		fail_file();
+	}
+	return addr;
+}
+
+/*
+ * Get the whole file as a programming convenience in order to avoid
+ * malloc+lseek+read+free of many pieces.  If successful, then mmap
+ * avoids copying unused pieces; else just read the whole file.
+ * Open for both read and write; new info will be appended to the file.
+ * Use MAP_PRIVATE so that a few changes to the in-memory ElfXX_Ehdr
+ * do not propagate to the file until an explicit overwrite at the last.
+ * This preserves most aspects of consistency (all except .st_size)
+ * for simultaneous readers of the file while we are appending to it.
+ * However, multiple writers still are bad.  We choose not to use
+ * locking because it is expensive and the use case of kernel build
+ * makes multiple writers unlikely.
+ */
+static void *mmap_file(char const *fname)
+{
+	void *addr;
+
+	fd_map = open(fname, O_RDWR);
+	if (0 > fd_map || 0 > fstat(fd_map, &sb)) {
+		perror(fname);
+		fail_file();
+	}
+	if (!S_ISREG(sb.st_mode)) {
+		fprintf(stderr, "not a regular file: %s\n", fname);
+		fail_file();
+	}
+	addr = mmap(0, sb.st_size, PROT_READ|PROT_WRITE, MAP_PRIVATE,
+		    fd_map, 0);
+	mmap_failed = 0;
+	if (MAP_FAILED == addr) {
+		mmap_failed = 1;
+		addr = umalloc(sb.st_size);
+		uread(fd_map, addr, sb.st_size);
+	}
+	return addr;
+}
+
+/* w8rev, w8nat, ...: Handle endianness. */
+
+static uint64_t w8rev(uint64_t const x)
+{
+	return   ((0xff & (x >> (0 * 8))) << (7 * 8))
+	       | ((0xff & (x >> (1 * 8))) << (6 * 8))
+	       | ((0xff & (x >> (2 * 8))) << (5 * 8))
+	       | ((0xff & (x >> (3 * 8))) << (4 * 8))
+	       | ((0xff & (x >> (4 * 8))) << (3 * 8))
+	       | ((0xff & (x >> (5 * 8))) << (2 * 8))
+	       | ((0xff & (x >> (6 * 8))) << (1 * 8))
+	       | ((0xff & (x >> (7 * 8))) << (0 * 8));
+}
+
+static uint32_t w4rev(uint32_t const x)
+{
+	return   ((0xff & (x >> (0 * 8))) << (3 * 8))
+	       | ((0xff & (x >> (1 * 8))) << (2 * 8))
+	       | ((0xff & (x >> (2 * 8))) << (1 * 8))
+	       | ((0xff & (x >> (3 * 8))) << (0 * 8));
+}
+
+static uint32_t w2rev(uint16_t const x)
+{
+	return   ((0xff & (x >> (0 * 8))) << (1 * 8))
+	       | ((0xff & (x >> (1 * 8))) << (0 * 8));
+}
+
+static uint64_t w8nat(uint64_t const x)
+{
+	return x;
+}
+
+static uint32_t w4nat(uint32_t const x)
+{
+	return x;
+}
+
+static uint32_t w2nat(uint16_t const x)
+{
+	return x;
+}
+
+static uint64_t (*w8)(uint64_t);
+static uint32_t (*w)(uint32_t);
+static uint32_t (*w2)(uint16_t);
+
+/* Names of the sections that could contain calls to mcount. */
+static int
+is_mcounted_section_name(char const *const txtname)
+{
+	return 0 == strcmp(".text",          txtname) ||
+		0 == strcmp(".sched.text",    txtname) ||
+		0 == strcmp(".spinlock.text", txtname) ||
+		0 == strcmp(".irqentry.text", txtname) ||
+		0 == strcmp(".text.unlikely", txtname);
+}
+
+/* 32 bit and 64 bit are very similar */
+#include "recordmcount.h"
+#define RECORD_MCOUNT_64
+#include "recordmcount.h"
+
+static void
+do_file(char const *const fname)
+{
+	Elf32_Ehdr *const ehdr = mmap_file(fname);
+	unsigned int reltype = 0;
+
+	ehdr_curr = ehdr;
+	w = w4nat;
+	w2 = w2nat;
+	w8 = w8nat;
+	switch (ehdr->e_ident[EI_DATA]) {
+		static unsigned int const endian = 1;
+	default: {
+		fprintf(stderr, "unrecognized ELF data encoding %d: %s\n",
+			ehdr->e_ident[EI_DATA], fname);
+		fail_file();
+	} break;
+	case ELFDATA2LSB: {
+		if (1 != *(unsigned char const *)&endian) {
+			/* main() is big endian, file.o is little endian. */
+			w = w4rev;
+			w2 = w2rev;
+			w8 = w8rev;
+		}
+	} break;
+	case ELFDATA2MSB: {
+		if (0 != *(unsigned char const *)&endian) {
+			/* main() is little endian, file.o is big endian. */
+			w = w4rev;
+			w2 = w2rev;
+			w8 = w8rev;
+		}
+	} break;
+	}  /* end switch */
+	if (0 != memcmp(ELFMAG, ehdr->e_ident, SELFMAG)
+	||  ET_REL != w2(ehdr->e_type)
+	||  EV_CURRENT != ehdr->e_ident[EI_VERSION]) {
+		fprintf(stderr, "unrecognized ET_REL file %s\n", fname);
+		fail_file();
+	}
+
+	gpfx = 0;
+	switch (w2(ehdr->e_machine)) {
+	default: {
+		fprintf(stderr, "unrecognized e_machine %d %s\n",
+			w2(ehdr->e_machine), fname);
+		fail_file();
+	} break;
+	case EM_386:	 reltype = R_386_32;                   break;
+	case EM_ARM:	 reltype = R_ARM_ABS32;                break;
+	case EM_IA_64:	 reltype = R_IA64_IMM64;   gpfx = '_'; break;
+	case EM_PPC:	 reltype = R_PPC_ADDR32;   gpfx = '_'; break;
+	case EM_PPC64:	 reltype = R_PPC64_ADDR64; gpfx = '_'; break;
+	case EM_S390:    /* reltype: e_class    */ gpfx = '_'; break;
+	case EM_SH:	 reltype = R_SH_DIR32;                 break;
+	case EM_SPARCV9: reltype = R_SPARC_64;     gpfx = '_'; break;
+	case EM_X86_64:	 reltype = R_X86_64_64;                break;
+	}  /* end switch */
+
+	switch (ehdr->e_ident[EI_CLASS]) {
+	default: {
+		fprintf(stderr, "unrecognized ELF class %d %s\n",
+			ehdr->e_ident[EI_CLASS], fname);
+		fail_file();
+	} break;
+	case ELFCLASS32: {
+		if (sizeof(Elf32_Ehdr) != w2(ehdr->e_ehsize)
+		||  sizeof(Elf32_Shdr) != w2(ehdr->e_shentsize)) {
+			fprintf(stderr,
+				"unrecognized ET_REL file: %s\n", fname);
+			fail_file();
+		}
+		if (EM_S390 == w2(ehdr->e_machine))
+			reltype = R_390_32;
+		do32(ehdr, fname, reltype);
+	} break;
+	case ELFCLASS64: {
+		Elf64_Ehdr *const ghdr = (Elf64_Ehdr *)ehdr;
+		if (sizeof(Elf64_Ehdr) != w2(ghdr->e_ehsize)
+		||  sizeof(Elf64_Shdr) != w2(ghdr->e_shentsize)) {
+			fprintf(stderr,
+				"unrecognized ET_REL file: %s\n", fname);
+			fail_file();
+		}
+		if (EM_S390 == w2(ghdr->e_machine))
+			reltype = R_390_64;
+		do64(ghdr, fname, reltype);
+	} break;
+	}  /* end switch */
+
+	cleanup();
+}
+
+int
+main(int argc, char const *argv[])
+{
+	const char ftrace[] = "kernel/trace/ftrace.o";
+	int ftrace_size = sizeof(ftrace) - 1;
+	int n_error = 0;  /* gcc-4.3.0 false positive complaint */
+
+	if (argc <= 1) {
+		fprintf(stderr, "usage: recordmcount file.o...\n");
+		return 0;
+	}
+
+	/* Process each file in turn, allowing deep failure. */
+	for (--argc, ++argv; 0 < argc; --argc, ++argv) {
+		int const sjval = setjmp(jmpenv);
+		int len;
+
+		/*
+		 * The file kernel/trace/ftrace.o references the mcount
+		 * function but does not call it. Since ftrace.o should
+		 * not be traced anyway, we just skip it.
+		 */
+		len = strlen(argv[0]);
+		if (len >= ftrace_size &&
+		    strcmp(argv[0] + (len - ftrace_size), ftrace) == 0)
+			continue;
+
+		switch (sjval) {
+		default: {
+			fprintf(stderr, "internal error: %s\n", argv[0]);
+			exit(1);
+		} break;
+		case SJ_SETJMP: {  /* normal sequence */
+			/* Avoid problems if early cleanup() */
+			fd_map = -1;
+			ehdr_curr = NULL;
+			mmap_failed = 1;
+			do_file(argv[0]);
+		} break;
+		case SJ_FAIL: {  /* error in do_file or below */
+			++n_error;
+		} break;
+		case SJ_SUCCEED: {  /* premature success */
+			/* do nothing */
+		} break;
+		}  /* end switch */
+	}
+	return !!n_error;
+}
+
+
diff --git a/scripts/recordmcount.h b/scripts/recordmcount.h
new file mode 100644
index 0000000..7f39d09
--- /dev/null
+++ b/scripts/recordmcount.h
@@ -0,0 +1,366 @@
+/*
+ * recordmcount.h
+ *
+ * This code was taken out of recordmcount.c written by
+ * Copyright 2009 John F. Reiser <jreiser@BitWagon.com>.  All rights reserved.
+ *
+ * The original code had the same algorithms for both 32bit
+ * and 64bit ELF files, but the code was duplicated to support
+ * the difference in structures that were used. This
+ * file creates a macro of everything that is different between
+ * the 64 and 32 bit code, such that by including this header
+ * twice we can create both sets of functions by including this
+ * header once with RECORD_MCOUNT_64 undefined, and again with
+ * it defined.
+ *
+ * This conversion to macros was done by:
+ * Copyright 2010 Steven Rostedt <srostedt@redhat.com>, Red Hat Inc.
+ *
+ * Licensed under the GNU General Public License, version 2 (GPLv2).
+ */
+#undef append_func
+#undef sift_rel_mcount
+#undef find_secsym_ndx
+#undef __has_rel_mcount
+#undef has_rel_mcount
+#undef tot_relsize
+#undef do_func
+#undef Elf_Ehdr
+#undef Elf_Shdr
+#undef Elf_Rel
+#undef Elf_Rela
+#undef Elf_Sym
+#undef ELF_R_SYM
+#undef ELF_R_INFO
+#undef ELF_ST_BIND
+#undef uint_t
+#undef _w
+#undef _align
+#undef _size
+
+#ifdef RECORD_MCOUNT_64
+# define append_func		append64
+# define sift_rel_mcount	sift64_rel_mcount
+# define find_secsym_ndx	find64_secsym_ndx
+# define __has_rel_mcount	__has64_rel_mcount
+# define has_rel_mcount		has64_rel_mcount
+# define tot_relsize		tot64_relsize
+# define do_func		do64
+# define Elf_Ehdr		Elf64_Ehdr
+# define Elf_Shdr		Elf64_Shdr
+# define Elf_Rel		Elf64_Rel
+# define Elf_Rela		Elf64_Rela
+# define Elf_Sym		Elf64_Sym
+# define ELF_R_SYM		ELF64_R_SYM
+# define ELF_R_INFO		ELF64_R_INFO
+# define ELF_ST_BIND		ELF64_ST_BIND
+# define uint_t			uint64_t
+# define _w			w8
+# define _align			7u
+# define _size			8
+#else
+# define append_func		append32
+# define sift_rel_mcount	sift32_rel_mcount
+# define find_secsym_ndx	find32_secsym_ndx
+# define __has_rel_mcount	__has32_rel_mcount
+# define has_rel_mcount		has32_rel_mcount
+# define tot_relsize		tot32_relsize
+# define do_func		do32
+# define Elf_Ehdr		Elf32_Ehdr
+# define Elf_Shdr		Elf32_Shdr
+# define Elf_Rel		Elf32_Rel
+# define Elf_Rela		Elf32_Rela
+# define Elf_Sym		Elf32_Sym
+# define ELF_R_SYM		ELF32_R_SYM
+# define ELF_R_INFO		ELF32_R_INFO
+# define ELF_ST_BIND		ELF32_ST_BIND
+# define uint_t			uint32_t
+# define _w			w
+# define _align			3u
+# define _size			4
+#endif
+
+/* Append the new shstrtab, Elf_Shdr[], __mcount_loc and its relocations. */
+static void append_func(Elf_Ehdr *const ehdr,
+			Elf_Shdr *const shstr,
+			uint_t const *const mloc0,
+			uint_t const *const mlocp,
+			Elf_Rel const *const mrel0,
+			Elf_Rel const *const mrelp,
+			unsigned int const rel_entsize,
+			unsigned int const symsec_sh_link)
+{
+	/* Begin constructing output file */
+	Elf_Shdr mcsec;
+	char const *mc_name = (sizeof(Elf_Rela) == rel_entsize)
+		? ".rela__mcount_loc"
+		:  ".rel__mcount_loc";
+	unsigned const old_shnum = w2(ehdr->e_shnum);
+	uint_t const old_shoff = _w(ehdr->e_shoff);
+	uint_t const old_shstr_sh_size   = _w(shstr->sh_size);
+	uint_t const old_shstr_sh_offset = _w(shstr->sh_offset);
+	uint_t t = 1 + strlen(mc_name) + _w(shstr->sh_size);
+	uint_t new_e_shoff;
+
+	shstr->sh_size = _w(t);
+	shstr->sh_offset = _w(sb.st_size);
+	t += sb.st_size;
+	t += (_align & -t);  /* word-byte align */
+	new_e_shoff = t;
+
+	/* body for new shstrtab */
+	ulseek(fd_map, sb.st_size, SEEK_SET);
+	uwrite(fd_map, old_shstr_sh_offset + (void *)ehdr, old_shstr_sh_size);
+	uwrite(fd_map, mc_name, 1 + strlen(mc_name));
+
+	/* old(modified) Elf_Shdr table, word-byte aligned */
+	ulseek(fd_map, t, SEEK_SET);
+	t += sizeof(Elf_Shdr) * old_shnum;
+	uwrite(fd_map, old_shoff + (void *)ehdr,
+	       sizeof(Elf_Shdr) * old_shnum);
+
+	/* new sections __mcount_loc and .rel__mcount_loc */
+	t += 2*sizeof(mcsec);
+	mcsec.sh_name = w((sizeof(Elf_Rela) == rel_entsize) + strlen(".rel")
+		+ old_shstr_sh_size);
+	mcsec.sh_type = w(SHT_PROGBITS);
+	mcsec.sh_flags = _w(SHF_ALLOC);
+	mcsec.sh_addr = 0;
+	mcsec.sh_offset = _w(t);
+	mcsec.sh_size = _w((void *)mlocp - (void *)mloc0);
+	mcsec.sh_link = 0;
+	mcsec.sh_info = 0;
+	mcsec.sh_addralign = _w(_size);
+	mcsec.sh_entsize = _w(_size);
+	uwrite(fd_map, &mcsec, sizeof(mcsec));
+
+	mcsec.sh_name = w(old_shstr_sh_size);
+	mcsec.sh_type = (sizeof(Elf_Rela) == rel_entsize)
+		? w(SHT_RELA)
+		: w(SHT_REL);
+	mcsec.sh_flags = 0;
+	mcsec.sh_addr = 0;
+	mcsec.sh_offset = _w((void *)mlocp - (void *)mloc0 + t);
+	mcsec.sh_size   = _w((void *)mrelp - (void *)mrel0);
+	mcsec.sh_link = w(symsec_sh_link);
+	mcsec.sh_info = w(old_shnum);
+	mcsec.sh_addralign = _w(_size);
+	mcsec.sh_entsize = _w(rel_entsize);
+	uwrite(fd_map, &mcsec, sizeof(mcsec));
+
+	uwrite(fd_map, mloc0, (void *)mlocp - (void *)mloc0);
+	uwrite(fd_map, mrel0, (void *)mrelp - (void *)mrel0);
+
+	ehdr->e_shoff = _w(new_e_shoff);
+	ehdr->e_shnum = w2(2 + w2(ehdr->e_shnum));  /* {.rel,}__mcount_loc */
+	ulseek(fd_map, 0, SEEK_SET);
+	uwrite(fd_map, ehdr, sizeof(*ehdr));
+}
+
+
+/*
+ * Look at the relocations in order to find the calls to mcount.
+ * Accumulate the section offsets that are found, and their relocation info,
+ * onto the end of the existing arrays.
+ */
+static uint_t *sift_rel_mcount(uint_t *mlocp,
+			       unsigned const offbase,
+			       Elf_Rel **const mrelpp,
+			       Elf_Shdr const *const relhdr,
+			       Elf_Ehdr const *const ehdr,
+			       unsigned const recsym,
+			       uint_t const recval,
+			       unsigned const reltype)
+{
+	uint_t *const mloc0 = mlocp;
+	Elf_Rel *mrelp = *mrelpp;
+	Elf_Shdr *const shdr0 = (Elf_Shdr *)(_w(ehdr->e_shoff)
+		+ (void *)ehdr);
+	unsigned const symsec_sh_link = w(relhdr->sh_link);
+	Elf_Shdr const *const symsec = &shdr0[symsec_sh_link];
+	Elf_Sym const *const sym0 = (Elf_Sym const *)(_w(symsec->sh_offset)
+		+ (void *)ehdr);
+
+	Elf_Shdr const *const strsec = &shdr0[w(symsec->sh_link)];
+	char const *const str0 = (char const *)(_w(strsec->sh_offset)
+		+ (void *)ehdr);
+
+	Elf_Rel const *const rel0 = (Elf_Rel const *)(_w(relhdr->sh_offset)
+		+ (void *)ehdr);
+	unsigned rel_entsize = _w(relhdr->sh_entsize);
+	unsigned const nrel = _w(relhdr->sh_size) / rel_entsize;
+	Elf_Rel const *relp = rel0;
+
+	unsigned mcountsym = 0;
+	unsigned t;
+
+	for (t = nrel; t; --t) {
+		if (!mcountsym) {
+			Elf_Sym const *const symp =
+				&sym0[ELF_R_SYM(_w(relp->r_info))];
+			char const *symname = &str0[w(symp->st_name)];
+
+			if ('.' == symname[0])
+				++symname;  /* ppc64 hack */
+			if (0 == strcmp((('_' == gpfx) ? "_mcount" : "mcount"),
+					symname))
+				mcountsym = ELF_R_SYM(_w(relp->r_info));
+		}
+
+		if (mcountsym == ELF_R_SYM(_w(relp->r_info))) {
+			uint_t const addend = _w(_w(relp->r_offset) - recval);
+
+			mrelp->r_offset = _w(offbase
+				+ ((void *)mlocp - (void *)mloc0));
+			mrelp->r_info = _w(ELF_R_INFO(recsym, reltype));
+			if (sizeof(Elf_Rela) == rel_entsize) {
+				((Elf_Rela *)mrelp)->r_addend = addend;
+				*mlocp++ = 0;
+			} else
+				*mlocp++ = addend;
+
+			mrelp = (Elf_Rel *)(rel_entsize + (void *)mrelp);
+		}
+		relp = (Elf_Rel const *)(rel_entsize + (void *)relp);
+	}
+	*mrelpp = mrelp;
+	return mlocp;
+}
+
+
+/*
+ * Find a symbol in the given section, to be used as the base for relocating
+ * the table of offsets of calls to mcount.  A local or global symbol suffices,
+ * but avoid a Weak symbol because it may be overridden; the change in value
+ * would invalidate the relocations of the offsets of the calls to mcount.
+ * Often the found symbol will be the unnamed local symbol generated by
+ * GNU 'as' for the start of each section.  For example:
+ *    Num:    Value  Size Type    Bind   Vis      Ndx Name
+ *      2: 00000000     0 SECTION LOCAL  DEFAULT    1
+ */
+static unsigned find_secsym_ndx(unsigned const txtndx,
+				char const *const txtname,
+				uint_t *const recvalp,
+				Elf_Shdr const *const symhdr,
+				Elf_Ehdr const *const ehdr)
+{
+	Elf_Sym const *const sym0 = (Elf_Sym const *)(_w(symhdr->sh_offset)
+		+ (void *)ehdr);
+	unsigned const nsym = _w(symhdr->sh_size) / _w(symhdr->sh_entsize);
+	Elf_Sym const *symp;
+	unsigned t;
+
+	for (symp = sym0, t = nsym; t; --t, ++symp) {
+		unsigned int const st_bind = ELF_ST_BIND(symp->st_info);
+
+		if (txtndx == w2(symp->st_shndx)
+			/* avoid STB_WEAK */
+		    && (STB_LOCAL == st_bind || STB_GLOBAL == st_bind)) {
+			*recvalp = _w(symp->st_value);
+			return symp - sym0;
+		}
+	}
+	fprintf(stderr, "Cannot find symbol for section %d: %s.\n",
+		txtndx, txtname);
+	fail_file();
+}
+
+
+/* Evade ISO C restriction: no declaration after statement in has_rel_mcount. */
+static char const *
+__has_rel_mcount(Elf_Shdr const *const relhdr,  /* is SHT_REL or SHT_RELA */
+		 Elf_Shdr const *const shdr0,
+		 char const *const shstrtab,
+		 char const *const fname)
+{
+	/* .sh_info depends on .sh_type == SHT_REL[,A] */
+	Elf_Shdr const *const txthdr = &shdr0[w(relhdr->sh_info)];
+	char const *const txtname = &shstrtab[w(txthdr->sh_name)];
+
+	if (0 == strcmp("__mcount_loc", txtname)) {
+		fprintf(stderr, "warning: __mcount_loc already exists: %s\n",
+			fname);
+		succeed_file();
+	}
+	if (SHT_PROGBITS != w(txthdr->sh_type) ||
+	    !is_mcounted_section_name(txtname))
+		return NULL;
+	return txtname;
+}
+
+static char const *has_rel_mcount(Elf_Shdr const *const relhdr,
+				  Elf_Shdr const *const shdr0,
+				  char const *const shstrtab,
+				  char const *const fname)
+{
+	if (SHT_REL  != w(relhdr->sh_type) && SHT_RELA != w(relhdr->sh_type))
+		return NULL;
+	return __has_rel_mcount(relhdr, shdr0, shstrtab, fname);
+}
+
+
+static unsigned tot_relsize(Elf_Shdr const *const shdr0,
+			    unsigned nhdr,
+			    const char *const shstrtab,
+			    const char *const fname)
+{
+	unsigned totrelsz = 0;
+	Elf_Shdr const *shdrp = shdr0;
+
+	for (; nhdr; --nhdr, ++shdrp) {
+		if (has_rel_mcount(shdrp, shdr0, shstrtab, fname))
+			totrelsz += _w(shdrp->sh_size);
+	}
+	return totrelsz;
+}
+
+
+/* Overall supervision for Elf32 ET_REL file. */
+static void
+do_func(Elf_Ehdr *const ehdr, char const *const fname, unsigned const reltype)
+{
+	Elf_Shdr *const shdr0 = (Elf_Shdr *)(_w(ehdr->e_shoff)
+		+ (void *)ehdr);
+	unsigned const nhdr = w2(ehdr->e_shnum);
+	Elf_Shdr *const shstr = &shdr0[w2(ehdr->e_shstrndx)];
+	char const *const shstrtab = (char const *)(_w(shstr->sh_offset)
+		+ (void *)ehdr);
+
+	Elf_Shdr const *relhdr;
+	unsigned k;
+
+	/* Upper bound on space: assume all relevant relocs are for mcount. */
+	unsigned const totrelsz = tot_relsize(shdr0, nhdr, shstrtab, fname);
+	Elf_Rel *const mrel0 = umalloc(totrelsz);
+	Elf_Rel *      mrelp = mrel0;
+
+	/* 2*sizeof(address) <= sizeof(Elf_Rel) */
+	uint_t *const mloc0 = umalloc(totrelsz>>1);
+	uint_t *      mlocp = mloc0;
+
+	unsigned rel_entsize = 0;
+	unsigned symsec_sh_link = 0;
+
+	for (relhdr = shdr0, k = nhdr; k; --k, ++relhdr) {
+		char const *const txtname = has_rel_mcount(relhdr, shdr0,
+			shstrtab, fname);
+		if (txtname) {
+			uint_t recval = 0;
+			unsigned const recsym = find_secsym_ndx(
+				w(relhdr->sh_info), txtname, &recval,
+				&shdr0[symsec_sh_link = w(relhdr->sh_link)],
+				ehdr);
+
+			rel_entsize = _w(relhdr->sh_entsize);
+			mlocp = sift_rel_mcount(mlocp,
+				(void *)mlocp - (void *)mloc0, &mrelp,
+				relhdr, ehdr, recsym, recval, reltype);
+		}
+	}
+	if (mloc0 != mlocp) {
+		append_func(ehdr, shstr, mloc0, mlocp, mrel0, mrelp,
+			    rel_entsize, symsec_sh_link);
+	}
+	free(mrel0);
+	free(mloc0);
+}