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: (107 commits)
  perf stat: Add more cache-miss percentage printouts
  perf stat: Add -d -d and -d -d -d options to show more CPU events
  ftrace/kbuild: Add recordmcount files to force full build
  ftrace: Add self-tests for multiple function trace users
  ftrace: Modify ftrace_set_filter/notrace to take ops
  ftrace: Allow dynamically allocated function tracers
  ftrace: Implement separate user function filtering
  ftrace: Free hash with call_rcu_sched()
  ftrace: Have global_ops store the functions that are to be traced
  ftrace: Add ops parameter to ftrace_startup/shutdown functions
  ftrace: Add enabled_functions file
  ftrace: Use counters to enable functions to trace
  ftrace: Separate hash allocation and assignment
  ftrace: Create a global_ops to hold the filter and notrace hashes
  ftrace: Use hash instead for FTRACE_FL_FILTER
  ftrace: Replace FTRACE_FL_NOTRACE flag with a hash of ignored functions
  perf bench, x86: Add alternatives-asm.h wrapper
  x86, 64-bit: Fix copy_[to/from]_user() checks for the userspace address limit
  x86, mem: memset_64.S: Optimize memset by enhanced REP MOVSB/STOSB
  x86, mem: memmove_64.S: Optimize memmove by enhanced REP MOVSB/STOSB
  ...

4 files changed, 266 insertions, 93 deletions

diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index d5f925abe4d2..6165622c3e29 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -244,14 +244,19 @@ endif
 
 ifdef CONFIG_FTRACE_MCOUNT_RECORD
 ifdef BUILD_C_RECORDMCOUNT
+ifeq ("$(origin RECORDMCOUNT_WARN)", "command line")
+  RECORDMCOUNT_FLAGS = -w
+endif
 # 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.
 sub_cmd_record_mcount =					\
 	if [ $(@) != "scripts/mod/empty.o" ]; then	\
-		$(objtree)/scripts/recordmcount "$(@)";	\
+		$(objtree)/scripts/recordmcount $(RECORDMCOUNT_FLAGS) "$(@)";	\
 	fi;
+recordmcount_source := $(srctree)/scripts/recordmcount.c \
+		    $(srctree)/scripts/recordmcount.h
 else
 sub_cmd_record_mcount = set -e ; perl $(srctree)/scripts/recordmcount.pl "$(ARCH)" \
 	"$(if $(CONFIG_CPU_BIG_ENDIAN),big,little)" \
@@ -259,6 +264,7 @@ sub_cmd_record_mcount = set -e ; perl $(srctree)/scripts/recordmcount.pl "$(ARCH
 	"$(OBJDUMP)" "$(OBJCOPY)" "$(CC) $(KBUILD_CFLAGS)" \
 	"$(LD)" "$(NM)" "$(RM)" "$(MV)" \
 	"$(if $(part-of-module),1,0)" "$(@)";
+recordmcount_source := $(srctree)/scripts/recordmcount.pl
 endif
 cmd_record_mcount = 						\
 	if [ "$(findstring -pg,$(_c_flags))" = "-pg" ]; then	\
@@ -279,13 +285,13 @@ define rule_cc_o_c
 endef
 
 # Built-in and composite module parts
-$(obj)/%.o: $(src)/%.c FORCE
+$(obj)/%.o: $(src)/%.c $(recordmcount_source) FORCE
 	$(call cmd,force_checksrc)
 	$(call if_changed_rule,cc_o_c)
 
 # Single-part modules are special since we need to mark them in $(MODVERDIR)
 
-$(single-used-m): $(obj)/%.o: $(src)/%.c FORCE
+$(single-used-m): $(obj)/%.o: $(src)/%.c $(recordmcount_source) FORCE
 	$(call cmd,force_checksrc)
 	$(call if_changed_rule,cc_o_c)
 	@{ echo $(@:.o=.ko); echo $@; } > $(MODVERDIR)/$(@F:.o=.mod)
diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c
index f9f6f52db772..ee52cb8e17ad 100644
--- a/scripts/recordmcount.c
+++ b/scripts/recordmcount.c
@@ -24,6 +24,7 @@
 #include <sys/types.h>
 #include <sys/mman.h>
 #include <sys/stat.h>
+#include <getopt.h>
 #include <elf.h>
 #include <fcntl.h>
 #include <setjmp.h>
@@ -39,6 +40,7 @@ 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 */
 static const char *altmcount;	/* alternate mcount symbol name */
+static int warn_on_notrace_sect; /* warn when section has mcount not being recorded */
 
 /* setjmp() return values */
 enum {
@@ -78,7 +80,7 @@ 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) {
+	if (w == (off_t)-1) {
 		perror("lseek");
 		fail_file();
 	}
@@ -111,13 +113,41 @@ static void *
 umalloc(size_t size)
 {
 	void *const addr = malloc(size);
-	if (0 == addr) {
+	if (addr == 0) {
 		fprintf(stderr, "malloc failed: %zu bytes\n", size);
 		fail_file();
 	}
 	return addr;
 }
 
+static unsigned char ideal_nop5_x86_64[5] = { 0x0f, 0x1f, 0x44, 0x00, 0x00 };
+static unsigned char ideal_nop5_x86_32[5] = { 0x3e, 0x8d, 0x74, 0x26, 0x00 };
+static unsigned char *ideal_nop;
+
+static char rel_type_nop;
+
+static int (*make_nop)(void *map, size_t const offset);
+
+static int make_nop_x86(void *map, size_t const offset)
+{
+	uint32_t *ptr;
+	unsigned char *op;
+
+	/* Confirm we have 0xe8 0x0 0x0 0x0 0x0 */
+	ptr = map + offset;
+	if (*ptr != 0)
+		return -1;
+
+	op = map + offset - 1;
+	if (*op != 0xe8)
+		return -1;
+
+	/* convert to nop */
+	ulseek(fd_map, offset - 1, SEEK_SET);
+	uwrite(fd_map, ideal_nop, 5);
+	return 0;
+}
+
 /*
  * Get the whole file as a programming convenience in order to avoid
  * malloc+lseek+read+free of many pieces.  If successful, then mmap
@@ -136,7 +166,7 @@ static void *mmap_file(char const *fname)
 	void *addr;
 
 	fd_map = open(fname, O_RDWR);
-	if (0 > fd_map || 0 > fstat(fd_map, &sb)) {
+	if (fd_map < 0 || fstat(fd_map, &sb) < 0) {
 		perror(fname);
 		fail_file();
 	}
@@ -147,7 +177,7 @@ static void *mmap_file(char const *fname)
 	addr = mmap(0, sb.st_size, PROT_READ|PROT_WRITE, MAP_PRIVATE,
 		    fd_map, 0);
 	mmap_failed = 0;
-	if (MAP_FAILED == addr) {
+	if (addr == MAP_FAILED) {
 		mmap_failed = 1;
 		addr = umalloc(sb.st_size);
 		uread(fd_map, addr, sb.st_size);
@@ -206,12 +236,13 @@ static uint32_t (*w2)(uint16_t);
 static int
 is_mcounted_section_name(char const *const txtname)
 {
-	return 0 == strcmp(".text",           txtname) ||
-		0 == strcmp(".ref.text",      txtname) ||
-		0 == strcmp(".sched.text",    txtname) ||
-		0 == strcmp(".spinlock.text", txtname) ||
-		0 == strcmp(".irqentry.text", txtname) ||
-		0 == strcmp(".text.unlikely", txtname);
+	return strcmp(".text",           txtname) == 0 ||
+		strcmp(".ref.text",      txtname) == 0 ||
+		strcmp(".sched.text",    txtname) == 0 ||
+		strcmp(".spinlock.text", txtname) == 0 ||
+		strcmp(".irqentry.text", txtname) == 0 ||
+		strcmp(".kprobes.text", txtname) == 0 ||
+		strcmp(".text.unlikely", txtname) == 0;
 }
 
 /* 32 bit and 64 bit are very similar */
@@ -264,43 +295,48 @@ do_file(char const *const fname)
 	w8 = w8nat;
 	switch (ehdr->e_ident[EI_DATA]) {
 		static unsigned int const endian = 1;
-	default: {
+	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) {
+		break;
+	case ELFDATA2LSB:
+		if (*(unsigned char const *)&endian != 1) {
 			/* main() is big endian, file.o is little endian. */
 			w = w4rev;
 			w2 = w2rev;
 			w8 = w8rev;
 		}
-	} break;
-	case ELFDATA2MSB: {
-		if (0 != *(unsigned char const *)&endian) {
+		break;
+	case ELFDATA2MSB:
+		if (*(unsigned char const *)&endian != 0) {
 			/* main() is little endian, file.o is big endian. */
 			w = w4rev;
 			w2 = w2rev;
 			w8 = w8rev;
 		}
-	} break;
+		break;
 	}  /* end switch */
-	if (0 != memcmp(ELFMAG, ehdr->e_ident, SELFMAG)
-	||  ET_REL != w2(ehdr->e_type)
-	||  EV_CURRENT != ehdr->e_ident[EI_VERSION]) {
+	if (memcmp(ELFMAG, ehdr->e_ident, SELFMAG) != 0
+	||  w2(ehdr->e_type) != ET_REL
+	||  ehdr->e_ident[EI_VERSION] != EV_CURRENT) {
 		fprintf(stderr, "unrecognized ET_REL file %s\n", fname);
 		fail_file();
 	}
 
 	gpfx = 0;
 	switch (w2(ehdr->e_machine)) {
-	default: {
+	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;
+		break;
+	case EM_386:
+		reltype = R_386_32;
+		make_nop = make_nop_x86;
+		ideal_nop = ideal_nop5_x86_32;
+		mcount_adjust_32 = -1;
+		break;
 	case EM_ARM:	 reltype = R_ARM_ABS32;
 			 altmcount = "__gnu_mcount_nc";
 			 break;
@@ -311,67 +347,91 @@ do_file(char const *const fname)
 	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;
+	case EM_X86_64:
+		make_nop = make_nop_x86;
+		ideal_nop = ideal_nop5_x86_64;
+		reltype = R_X86_64_64;
+		mcount_adjust_64 = -1;
+		break;
 	}  /* end switch */
 
 	switch (ehdr->e_ident[EI_CLASS]) {
-	default: {
+	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)) {
+		break;
+	case ELFCLASS32:
+		if (w2(ehdr->e_ehsize) != sizeof(Elf32_Ehdr)
+		||  w2(ehdr->e_shentsize) != sizeof(Elf32_Shdr)) {
 			fprintf(stderr,
 				"unrecognized ET_REL file: %s\n", fname);
 			fail_file();
 		}
-		if (EM_S390 == w2(ehdr->e_machine))
+		if (w2(ehdr->e_machine) == EM_S390) {
 			reltype = R_390_32;
-		if (EM_MIPS == w2(ehdr->e_machine)) {
+			mcount_adjust_32 = -4;
+		}
+		if (w2(ehdr->e_machine) == EM_MIPS) {
 			reltype = R_MIPS_32;
 			is_fake_mcount32 = MIPS32_is_fake_mcount;
 		}
 		do32(ehdr, fname, reltype);
-	} break;
+		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)) {
+		if (w2(ghdr->e_ehsize) != sizeof(Elf64_Ehdr)
+		||  w2(ghdr->e_shentsize) != sizeof(Elf64_Shdr)) {
 			fprintf(stderr,
 				"unrecognized ET_REL file: %s\n", fname);
 			fail_file();
 		}
-		if (EM_S390 == w2(ghdr->e_machine))
+		if (w2(ghdr->e_machine) == EM_S390) {
 			reltype = R_390_64;
-		if (EM_MIPS == w2(ghdr->e_machine)) {
+			mcount_adjust_64 = -8;
+		}
+		if (w2(ghdr->e_machine) == EM_MIPS) {
 			reltype = R_MIPS_64;
 			Elf64_r_sym = MIPS64_r_sym;
 			Elf64_r_info = MIPS64_r_info;
 			is_fake_mcount64 = MIPS64_is_fake_mcount;
 		}
 		do64(ghdr, fname, reltype);
-	} break;
+		break;
+	}
 	}  /* end switch */
 
 	cleanup();
 }
 
 int
-main(int argc, char const *argv[])
+main(int argc, char *argv[])
 {
 	const char ftrace[] = "/ftrace.o";
 	int ftrace_size = sizeof(ftrace) - 1;
 	int n_error = 0;  /* gcc-4.3.0 false positive complaint */
+	int c;
+	int i;
+
+	while ((c = getopt(argc, argv, "w")) >= 0) {
+		switch (c) {
+		case 'w':
+			warn_on_notrace_sect = 1;
+			break;
+		default:
+			fprintf(stderr, "usage: recordmcount [-w] file.o...\n");
+			return 0;
+		}
+	}
 
-	if (argc <= 1) {
-		fprintf(stderr, "usage: recordmcount file.o...\n");
+	if ((argc - optind) < 1) {
+		fprintf(stderr, "usage: recordmcount [-w] file.o...\n");
 		return 0;
 	}
 
 	/* Process each file in turn, allowing deep failure. */
-	for (--argc, ++argv; 0 < argc; --argc, ++argv) {
+	for (i = optind; i < argc; i++) {
+		char *file = argv[i];
 		int const sjval = setjmp(jmpenv);
 		int len;
 
@@ -380,29 +440,29 @@ main(int argc, char const *argv[])
 		 * function but does not call it. Since ftrace.o should
 		 * not be traced anyway, we just skip it.
 		 */
-		len = strlen(argv[0]);
+		len = strlen(file);
 		if (len >= ftrace_size &&
-		    strcmp(argv[0] + (len - ftrace_size), ftrace) == 0)
+		    strcmp(file + (len - ftrace_size), ftrace) == 0)
 			continue;
 
 		switch (sjval) {
-		default: {
-			fprintf(stderr, "internal error: %s\n", argv[0]);
+		default:
+			fprintf(stderr, "internal error: %s\n", file);
 			exit(1);
-		} break;
-		case SJ_SETJMP: {  /* normal sequence */
+			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 */
+			do_file(file);
+			break;
+		case SJ_FAIL:    /* error in do_file or below */
 			++n_error;
-		} break;
-		case SJ_SUCCEED: {  /* premature success */
+			break;
+		case SJ_SUCCEED:    /* premature success */
 			/* do nothing */
-		} break;
+			break;
 		}  /* end switch */
 	}
 	return !!n_error;
diff --git a/scripts/recordmcount.h b/scripts/recordmcount.h
index baf187bee983..4be60364a405 100644
--- a/scripts/recordmcount.h
+++ b/scripts/recordmcount.h
@@ -22,11 +22,15 @@
 #undef is_fake_mcount
 #undef fn_is_fake_mcount
 #undef MIPS_is_fake_mcount
+#undef mcount_adjust
 #undef sift_rel_mcount
+#undef nop_mcount
 #undef find_secsym_ndx
 #undef __has_rel_mcount
 #undef has_rel_mcount
 #undef tot_relsize
+#undef get_mcountsym
+#undef get_sym_str_and_relp
 #undef do_func
 #undef Elf_Addr
 #undef Elf_Ehdr
@@ -49,14 +53,18 @@
 #ifdef RECORD_MCOUNT_64
 # define append_func		append64
 # define sift_rel_mcount	sift64_rel_mcount
+# define nop_mcount		nop_mcount_64
 # 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 get_sym_str_and_relp	get_sym_str_and_relp_64
 # define do_func		do64
+# define get_mcountsym		get_mcountsym_64
 # define is_fake_mcount		is_fake_mcount64
 # define fn_is_fake_mcount	fn_is_fake_mcount64
 # define MIPS_is_fake_mcount	MIPS64_is_fake_mcount
+# define mcount_adjust		mcount_adjust_64
 # define Elf_Addr		Elf64_Addr
 # define Elf_Ehdr		Elf64_Ehdr
 # define Elf_Shdr		Elf64_Shdr
@@ -77,14 +85,18 @@
 #else
 # define append_func		append32
 # define sift_rel_mcount	sift32_rel_mcount
+# define nop_mcount		nop_mcount_32
 # 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 get_sym_str_and_relp	get_sym_str_and_relp_32
 # define do_func		do32
+# define get_mcountsym		get_mcountsym_32
 # define is_fake_mcount		is_fake_mcount32
 # define fn_is_fake_mcount	fn_is_fake_mcount32
 # define MIPS_is_fake_mcount	MIPS32_is_fake_mcount
+# define mcount_adjust		mcount_adjust_32
 # define Elf_Addr		Elf32_Addr
 # define Elf_Ehdr		Elf32_Ehdr
 # define Elf_Shdr		Elf32_Shdr
@@ -123,6 +135,8 @@ static void fn_ELF_R_INFO(Elf_Rel *const rp, unsigned sym, unsigned type)
 }
 static void (*Elf_r_info)(Elf_Rel *const rp, unsigned sym, unsigned type) = fn_ELF_R_INFO;
 
+static int mcount_adjust = 0;
+
 /*
  * MIPS mcount long call has 2 _mcount symbols, only the position of the 1st
  * _mcount symbol is needed for dynamic function tracer, with it, to disable
@@ -234,6 +248,49 @@ static void append_func(Elf_Ehdr *const ehdr,
 	uwrite(fd_map, ehdr, sizeof(*ehdr));
 }
 
+static unsigned get_mcountsym(Elf_Sym const *const sym0,
+			      Elf_Rel const *relp,
+			      char const *const str0)
+{
+	unsigned mcountsym = 0;
+
+	Elf_Sym const *const symp =
+		&sym0[Elf_r_sym(relp)];
+	char const *symname = &str0[w(symp->st_name)];
+	char const *mcount = gpfx == '_' ? "_mcount" : "mcount";
+
+	if (symname[0] == '.')
+		++symname;  /* ppc64 hack */
+	if (strcmp(mcount, symname) == 0 ||
+	    (altmcount && strcmp(altmcount, symname) == 0))
+		mcountsym = Elf_r_sym(relp);
+
+	return mcountsym;
+}
+
+static void get_sym_str_and_relp(Elf_Shdr const *const relhdr,
+				 Elf_Ehdr const *const ehdr,
+				 Elf_Sym const **sym0,
+				 char const **str0,
+				 Elf_Rel const **relp)
+{
+	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_Shdr const *const strsec = &shdr0[w(symsec->sh_link)];
+	Elf_Rel const *const rel0 = (Elf_Rel const *)(_w(relhdr->sh_offset)
+		+ (void *)ehdr);
+
+	*sym0 = (Elf_Sym const *)(_w(symsec->sh_offset)
+				  + (void *)ehdr);
+
+	*str0 = (char const *)(_w(strsec->sh_offset)
+			       + (void *)ehdr);
+
+	*relp = rel0;
+}
+
 /*
  * Look at the relocations in order to find the calls to mcount.
  * Accumulate the section offsets that are found, and their relocation info,
@@ -250,47 +307,27 @@ static uint_t *sift_rel_mcount(uint_t *mlocp,
 {
 	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);
+	Elf_Sym const *sym0;
+	char const *str0;
+	Elf_Rel const *relp;
 	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;
 
+	get_sym_str_and_relp(relhdr, ehdr, &sym0, &str0, &relp);
+
 	for (t = nrel; t; --t) {
-		if (!mcountsym) {
-			Elf_Sym const *const symp =
-				&sym0[Elf_r_sym(relp)];
-			char const *symname = &str0[w(symp->st_name)];
-			char const *mcount = '_' == gpfx ? "_mcount" : "mcount";
-
-			if ('.' == symname[0])
-				++symname;  /* ppc64 hack */
-			if (0 == strcmp(mcount, symname) ||
-			    (altmcount && 0 == strcmp(altmcount, symname)))
-				mcountsym = Elf_r_sym(relp);
-		}
+		if (!mcountsym)
+			mcountsym = get_mcountsym(sym0, relp, str0);
 
 		if (mcountsym == Elf_r_sym(relp) && !is_fake_mcount(relp)) {
-			uint_t const addend = _w(_w(relp->r_offset) - recval);
-
+			uint_t const addend =
+				_w(_w(relp->r_offset) - recval + mcount_adjust);
 			mrelp->r_offset = _w(offbase
 				+ ((void *)mlocp - (void *)mloc0));
 			Elf_r_info(mrelp, recsym, reltype);
-			if (sizeof(Elf_Rela) == rel_entsize) {
+			if (rel_entsize == sizeof(Elf_Rela)) {
 				((Elf_Rela *)mrelp)->r_addend = addend;
 				*mlocp++ = 0;
 			} else
@@ -304,6 +341,63 @@ static uint_t *sift_rel_mcount(uint_t *mlocp,
 	return mlocp;
 }
 
+/*
+ * Read the relocation table again, but this time its called on sections
+ * that are not going to be traced. The mcount calls here will be converted
+ * into nops.
+ */
+static void nop_mcount(Elf_Shdr const *const relhdr,
+		       Elf_Ehdr const *const ehdr,
+		       const char *const txtname)
+{
+	Elf_Shdr *const shdr0 = (Elf_Shdr *)(_w(ehdr->e_shoff)
+		+ (void *)ehdr);
+	Elf_Sym const *sym0;
+	char const *str0;
+	Elf_Rel const *relp;
+	Elf_Shdr const *const shdr = &shdr0[w(relhdr->sh_info)];
+	unsigned rel_entsize = _w(relhdr->sh_entsize);
+	unsigned const nrel = _w(relhdr->sh_size) / rel_entsize;
+	unsigned mcountsym = 0;
+	unsigned t;
+	int once = 0;
+
+	get_sym_str_and_relp(relhdr, ehdr, &sym0, &str0, &relp);
+
+	for (t = nrel; t; --t) {
+		int ret = -1;
+
+		if (!mcountsym)
+			mcountsym = get_mcountsym(sym0, relp, str0);
+
+		if (mcountsym == Elf_r_sym(relp) && !is_fake_mcount(relp)) {
+			if (make_nop)
+				ret = make_nop((void *)ehdr, shdr->sh_offset + relp->r_offset);
+			if (warn_on_notrace_sect && !once) {
+				printf("Section %s has mcount callers being ignored\n",
+				       txtname);
+				once = 1;
+				/* just warn? */
+				if (!make_nop)
+					return;
+			}
+		}
+
+		/*
+		 * If we successfully removed the mcount, mark the relocation
+		 * as a nop (don't do anything with it).
+		 */
+		if (!ret) {
+			Elf_Rel rel;
+			rel = *(Elf_Rel *)relp;
+			Elf_r_info(&rel, Elf_r_sym(relp), rel_type_nop);
+			ulseek(fd_map, (void *)relp - (void *)ehdr, SEEK_SET);
+			uwrite(fd_map, &rel, sizeof(rel));
+		}
+		relp = (Elf_Rel const *)(rel_entsize + (void *)relp);
+	}
+}
+
 
 /*
  * Find a symbol in the given section, to be used as the base for relocating
@@ -354,13 +448,13 @@ __has_rel_mcount(Elf_Shdr const *const relhdr,  /* is SHT_REL or SHT_RELA */
 	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)) {
+	if (strcmp("__mcount_loc", txtname) == 0) {
 		fprintf(stderr, "warning: __mcount_loc already exists: %s\n",
 			fname);
 		succeed_file();
 	}
-	if (SHT_PROGBITS != w(txthdr->sh_type) ||
-	    !is_mcounted_section_name(txtname))
+	if (w(txthdr->sh_type) != SHT_PROGBITS ||
+	    !(w(txthdr->sh_flags) & SHF_EXECINSTR))
 		return NULL;
 	return txtname;
 }
@@ -370,7 +464,7 @@ static char const *has_rel_mcount(Elf_Shdr const *const relhdr,
 				  char const *const shstrtab,
 				  char const *const fname)
 {
-	if (SHT_REL  != w(relhdr->sh_type) && SHT_RELA != w(relhdr->sh_type))
+	if (w(relhdr->sh_type) != SHT_REL && w(relhdr->sh_type) != SHT_RELA)
 		return NULL;
 	return __has_rel_mcount(relhdr, shdr0, shstrtab, fname);
 }
@@ -383,9 +477,11 @@ static unsigned tot_relsize(Elf_Shdr const *const shdr0,
 {
 	unsigned totrelsz = 0;
 	Elf_Shdr const *shdrp = shdr0;
+	char const *txtname;
 
 	for (; nhdr; --nhdr, ++shdrp) {
-		if (has_rel_mcount(shdrp, shdr0, shstrtab, fname))
+		txtname = has_rel_mcount(shdrp, shdr0, shstrtab, fname);
+		if (txtname && is_mcounted_section_name(txtname))
 			totrelsz += _w(shdrp->sh_size);
 	}
 	return totrelsz;
@@ -421,7 +517,7 @@ do_func(Elf_Ehdr *const ehdr, char const *const fname, unsigned const reltype)
 	for (relhdr = shdr0, k = nhdr; k; --k, ++relhdr) {
 		char const *const txtname = has_rel_mcount(relhdr, shdr0,
 			shstrtab, fname);
-		if (txtname) {
+		if (txtname && is_mcounted_section_name(txtname)) {
 			uint_t recval = 0;
 			unsigned const recsym = find_secsym_ndx(
 				w(relhdr->sh_info), txtname, &recval,
@@ -432,6 +528,12 @@ do_func(Elf_Ehdr *const ehdr, char const *const fname, unsigned const reltype)
 			mlocp = sift_rel_mcount(mlocp,
 				(void *)mlocp - (void *)mloc0, &mrelp,
 				relhdr, ehdr, recsym, recval, reltype);
+		} else if (txtname && (warn_on_notrace_sect || make_nop)) {
+			/*
+			 * This section is ignored by ftrace, but still
+			 * has mcount calls. Convert them to nops now.
+			 */
+			nop_mcount(relhdr, ehdr, txtname);
 		}
 	}
 	if (mloc0 != mlocp) {
diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
index 4be0deea71ca..858966ab019c 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -134,6 +134,7 @@ my %text_sections = (
      ".sched.text" => 1,
      ".spinlock.text" => 1,
      ".irqentry.text" => 1,
+     ".kprobes.text" => 1,
      ".text.unlikely" => 1,
 );
 
@@ -222,6 +223,7 @@ if ($arch eq "x86_64") {
     $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\smcount([+-]0x[0-9a-zA-Z]+)?\$";
     $type = ".quad";
     $alignment = 8;
+    $mcount_adjust = -1;
 
     # force flags for this arch
     $ld .= " -m elf_x86_64";
@@ -231,6 +233,7 @@ if ($arch eq "x86_64") {
 
 } elsif ($arch eq "i386") {
     $alignment = 4;
+    $mcount_adjust = -1;
 
     # force flags for this arch
     $ld .= " -m elf_i386";
@@ -240,12 +243,14 @@ if ($arch eq "x86_64") {
 
 } elsif ($arch eq "s390" && $bits == 32) {
     $mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*R_390_32\\s+_mcount\$";
+    $mcount_adjust = -4;
     $alignment = 4;
     $ld .= " -m elf_s390";
     $cc .= " -m31";
 
 } elsif ($arch eq "s390" && $bits == 64) {
     $mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*R_390_(PC|PLT)32DBL\\s+_mcount\\+0x2\$";
+    $mcount_adjust = -8;
     $alignment = 8;
     $type = ".quad";
     $ld .= " -m elf64_s390";