Merge tag 'perf-core-for-mingo-2' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

User visible changes:

- The mmap address range for the ring buffer now is calculated using the
  contents of /proc/sys/kernel/perf_event_mlock_kb.

  This fixes an -EPERM case where 'trace' was trying to use more than what
  is configured on perf_event_mlock_kb. (Arnaldo Carvalho de Melo)

Infrastructure changes:

- Move bitops definitions so that they match the header file hierarchy
  in the kernel sources where that code came from. (Arnaldo Carvalho de Melo)

- Adopt round{down,up}_pow_of_two from the kernel and use it instead of
  equivalent code, so that we reuse more kernel code and make tools/ look
  more like kernel source code, to encourage further contributions from
  kernel hackers (Arnaldo Carvalho de Melo)

- Fix use after free in filename__read_build_id (Mitchell Krome)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

7 files changed, 70 insertions, 207 deletions

diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 344c4d3d0a4a..83e2887f91a3 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -4,17 +4,31 @@ tools/lib/traceevent
 tools/lib/api
 tools/lib/symbol/kallsyms.c
 tools/lib/symbol/kallsyms.h
+tools/lib/util/find_next_bit.c
 tools/include/asm/bug.h
+tools/include/asm-generic/bitops/atomic.h
+tools/include/asm-generic/bitops/__ffs.h
+tools/include/asm-generic/bitops/__fls.h
+tools/include/asm-generic/bitops/find.h
+tools/include/asm-generic/bitops/fls64.h
+tools/include/asm-generic/bitops/fls.h
+tools/include/asm-generic/bitops.h
+tools/include/linux/bitops.h
 tools/include/linux/compiler.h
-tools/include/linux/hash.h
 tools/include/linux/export.h
+tools/include/linux/hash.h
+tools/include/linux/log2.h
 tools/include/linux/types.h
+include/asm-generic/bitops/fls64.h
+include/asm-generic/bitops/__fls.h
+include/asm-generic/bitops/fls.h
 include/linux/const.h
 include/linux/perf_event.h
 include/linux/rbtree.h
 include/linux/list.h
 include/linux/hash.h
 include/linux/stringify.h
+lib/find_next_bit.c
 lib/rbtree.c
 include/linux/swab.h
 arch/*/include/asm/unistd*.h
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 763e68fb5767..67a03a825b3c 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -231,8 +231,16 @@ LIB_H += ../../include/uapi/linux/const.h
 LIB_H += ../include/linux/hash.h
 LIB_H += ../../include/linux/stringify.h
 LIB_H += util/include/linux/bitmap.h
-LIB_H += util/include/linux/bitops.h
+LIB_H += ../include/linux/bitops.h
+LIB_H += ../include/asm-generic/bitops/atomic.h
+LIB_H += ../include/asm-generic/bitops/find.h
+LIB_H += ../include/asm-generic/bitops/fls64.h
+LIB_H += ../include/asm-generic/bitops/fls.h
+LIB_H += ../include/asm-generic/bitops/__ffs.h
+LIB_H += ../include/asm-generic/bitops/__fls.h
+LIB_H += ../include/asm-generic/bitops.h
 LIB_H += ../include/linux/compiler.h
+LIB_H += ../include/linux/log2.h
 LIB_H += util/include/linux/const.h
 LIB_H += util/include/linux/ctype.h
 LIB_H += util/include/linux/kernel.h
@@ -335,6 +343,7 @@ LIB_OBJS += $(OUTPUT)util/event.o
 LIB_OBJS += $(OUTPUT)util/evlist.o
 LIB_OBJS += $(OUTPUT)util/evsel.o
 LIB_OBJS += $(OUTPUT)util/exec_cmd.o
+LIB_OBJS += $(OUTPUT)util/find_next_bit.o
 LIB_OBJS += $(OUTPUT)util/help.o
 LIB_OBJS += $(OUTPUT)util/kallsyms.o
 LIB_OBJS += $(OUTPUT)util/levenshtein.o
@@ -734,6 +743,9 @@ $(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c $(OUTPUT)PERF-CFLAGS
 $(OUTPUT)util/rbtree.o: ../../lib/rbtree.c $(OUTPUT)PERF-CFLAGS
         $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
 
+$(OUTPUT)util/find_next_bit.o: ../lib/util/find_next_bit.c $(OUTPUT)PERF-CFLAGS
+        $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
+
 $(OUTPUT)util/parse-events.o: util/parse-events.c $(OUTPUT)PERF-CFLAGS
         $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-redundant-decls $<
 
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 327541e43c7f..badfabc6a01f 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2485,7 +2485,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
                         .user_freq     = UINT_MAX,
                         .user_interval = ULLONG_MAX,
                         .no_buffering  = true,
-                        .mmap_pages    = 1024,
+                        .mmap_pages    = UINT_MAX,
                 },
                 .output = stdout,
                 .show_comm = true,
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index bb5dfc5d1e75..cbab1fb77b1d 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -25,6 +25,7 @@
 
 #include <linux/bitops.h>
 #include <linux/hash.h>
+#include <linux/log2.h>
 
 static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx);
 static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx);
@@ -893,10 +894,24 @@ out_unmap:
 
 static size_t perf_evlist__mmap_size(unsigned long pages)
 {
-        /* 512 kiB: default amount of unprivileged mlocked memory */
-        if (pages == UINT_MAX)
-                pages = (512 * 1024) / page_size;
-        else if (!is_power_of_2(pages))
+        if (pages == UINT_MAX) {
+                int max;
+
+                if (sysctl__read_int("kernel/perf_event_mlock_kb", &max) < 0) {
+                        /*
+                         * Pick a once upon a time good value, i.e. things look
+                         * strange since we can't read a sysctl value, but lets not
+                         * die yet...
+                         */
+                        max = 512;
+                } else {
+                        max -= (page_size / 1024);
+                }
+
+                pages = (max * 1024) / page_size;
+                if (!is_power_of_2(pages))
+                        pages = rounddown_pow_of_two(pages);
+        } else if (!is_power_of_2(pages))
                 return 0;
 
         return (pages + 1) * page_size;
@@ -933,7 +948,7 @@ static long parse_pages_arg(const char *str, unsigned long min,
                 /* leave number of pages at 0 */
         } else if (!is_power_of_2(pages)) {
                 /* round pages up to next power of 2 */
-                pages = next_pow2_l(pages);
+                pages = roundup_pow_of_two(pages);
                 if (!pages)
                         return -EINVAL;
                 pr_info("rounding mmap pages size to %lu bytes (%lu pages)\n",
@@ -1487,16 +1502,25 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
 int perf_evlist__strerror_mmap(struct perf_evlist *evlist, int err, char *buf, size_t size)
 {
         char sbuf[STRERR_BUFSIZE], *emsg = strerror_r(err, sbuf, sizeof(sbuf));
-        int value;
+        int pages_attempted = evlist->mmap_len / 1024, pages_max_per_user, printed = 0;
 
         switch (err) {
         case EPERM:
-                sysctl__read_int("kernel/perf_event_mlock_kb", &value);
-                scnprintf(buf, size, "Error:\t%s.\n"
+                sysctl__read_int("kernel/perf_event_mlock_kb", &pages_max_per_user);
+                printed += scnprintf(buf + printed, size - printed,
+                                     "Error:\t%s.\n"
                                      "Hint:\tCheck /proc/sys/kernel/perf_event_mlock_kb (%d kB) setting.\n"
-                                     "Hint:\tTried using %zd kB.\n"
-                                     "Hint:\tTry using a bigger -m/--mmap-pages value.",
-                                     emsg, value, evlist->mmap_len / 1024);
+                                     "Hint:\tTried using %zd kB.\n",
+                                     emsg, pages_max_per_user, pages_attempted);
+
+                if (pages_attempted >= pages_max_per_user) {
+                        printed += scnprintf(buf + printed, size - printed,
+                                             "Hint:\tTry 'sudo sh -c \"echo %d > /proc/sys/kernel/perf_event_mlock_kb\"', or\n",
+                                             pages_max_per_user + pages_attempted);
+                }
+
+                printed += scnprintf(buf + printed, size - printed,
+                                     "Hint:\tTry using a smaller -m/--mmap-pages value.");
                 break;
         default:
                 scnprintf(buf, size, "%s", emsg);
diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h
deleted file mode 100644
index c3294163de17..000000000000
--- a/tools/perf/util/include/linux/bitops.h
+++ /dev/null
@@ -1,162 +0,0 @@
-#ifndef _PERF_LINUX_BITOPS_H_
-#define _PERF_LINUX_BITOPS_H_
-
-#include <linux/kernel.h>
-#include <linux/compiler.h>
-#include <asm/hweight.h>
-
-#ifndef __WORDSIZE
-#define __WORDSIZE (__SIZEOF_LONG__ * 8)
-#endif
-
-#define BITS_PER_LONG __WORDSIZE
-#define BITS_PER_BYTE           8
-#define BITS_TO_LONGS(nr)       DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
-#define BITS_TO_U64(nr)         DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u64))
-#define BITS_TO_U32(nr)         DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32))
-#define BITS_TO_BYTES(nr)       DIV_ROUND_UP(nr, BITS_PER_BYTE)
-#define BIT_WORD(nr)            ((nr) / BITS_PER_LONG)
-#define BIT_MASK(nr)            (1UL << ((nr) % BITS_PER_LONG))
-
-#define for_each_set_bit(bit, addr, size) \
-        for ((bit) = find_first_bit((addr), (size));            \
-             (bit) < (size);                                    \
-             (bit) = find_next_bit((addr), (size), (bit) + 1))
-
-/* same as for_each_set_bit() but use bit as value to start with */
-#define for_each_set_bit_from(bit, addr, size) \
-        for ((bit) = find_next_bit((addr), (size), (bit));      \
-             (bit) < (size);                                    \
-             (bit) = find_next_bit((addr), (size), (bit) + 1))
-
-static inline void set_bit(int nr, unsigned long *addr)
-{
-        addr[nr / BITS_PER_LONG] |= 1UL << (nr % BITS_PER_LONG);
-}
-
-static inline void clear_bit(int nr, unsigned long *addr)
-{
-        addr[nr / BITS_PER_LONG] &= ~(1UL << (nr % BITS_PER_LONG));
-}
-
-static __always_inline int test_bit(unsigned int nr, const unsigned long *addr)
-{
-        return ((1UL << (nr % BITS_PER_LONG)) &
-                (((unsigned long *)addr)[nr / BITS_PER_LONG])) != 0;
-}
-
-static inline unsigned long hweight_long(unsigned long w)
-{
-        return sizeof(w) == 4 ? hweight32(w) : hweight64(w);
-}
-
-#define BITOP_WORD(nr)          ((nr) / BITS_PER_LONG)
-
-/**
- * __ffs - find first bit in word.
- * @word: The word to search
- *
- * Undefined if no bit exists, so code should check against 0 first.
- */
-static __always_inline unsigned long __ffs(unsigned long word)
-{
-        int num = 0;
-
-#if BITS_PER_LONG == 64
-        if ((word & 0xffffffff) == 0) {
-                num += 32;
-                word >>= 32;
-        }
-#endif
-        if ((word & 0xffff) == 0) {
-                num += 16;
-                word >>= 16;
-        }
-        if ((word & 0xff) == 0) {
-                num += 8;
-                word >>= 8;
-        }
-        if ((word & 0xf) == 0) {
-                num += 4;
-                word >>= 4;
-        }
-        if ((word & 0x3) == 0) {
-                num += 2;
-                word >>= 2;
-        }
-        if ((word & 0x1) == 0)
-                num += 1;
-        return num;
-}
-
-typedef const unsigned long __attribute__((__may_alias__)) long_alias_t;
-
-/*
- * Find the first set bit in a memory region.
- */
-static inline unsigned long
-find_first_bit(const unsigned long *addr, unsigned long size)
-{
-        long_alias_t *p = (long_alias_t *) addr;
-        unsigned long result = 0;
-        unsigned long tmp;
-
-        while (size & ~(BITS_PER_LONG-1)) {
-                if ((tmp = *(p++)))
-                        goto found;
-                result += BITS_PER_LONG;
-                size -= BITS_PER_LONG;
-        }
-        if (!size)
-                return result;
-
-        tmp = (*p) & (~0UL >> (BITS_PER_LONG - size));
-        if (tmp == 0UL)         /* Are any bits set? */
-                return result + size;   /* Nope. */
-found:
-        return result + __ffs(tmp);
-}
-
-/*
- * Find the next set bit in a memory region.
- */
-static inline unsigned long
-find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset)
-{
-        const unsigned long *p = addr + BITOP_WORD(offset);
-        unsigned long result = offset & ~(BITS_PER_LONG-1);
-        unsigned long tmp;
-
-        if (offset >= size)
-                return size;
-        size -= result;
-        offset %= BITS_PER_LONG;
-        if (offset) {
-                tmp = *(p++);
-                tmp &= (~0UL << offset);
-                if (size < BITS_PER_LONG)
-                        goto found_first;
-                if (tmp)
-                        goto found_middle;
-                size -= BITS_PER_LONG;
-                result += BITS_PER_LONG;
-        }
-        while (size & ~(BITS_PER_LONG-1)) {
-                if ((tmp = *(p++)))
-                        goto found_middle;
-                result += BITS_PER_LONG;
-                size -= BITS_PER_LONG;
-        }
-        if (!size)
-                return result;
-        tmp = *p;
-
-found_first:
-        tmp &= (~0UL >> (BITS_PER_LONG - size));
-        if (tmp == 0UL)         /* Are any bits set? */
-                return result + size;   /* Nope. */
-found_middle:
-        return result + __ffs(tmp);
-}
-
-#endif
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index fa585c63f56a..d7efb03b3f9a 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -129,6 +129,7 @@ int filename__read_build_id(const char *filename, void *bf, size_t size)
 
                 for (i = 0, phdr = buf; i < ehdr.e_phnum; i++, phdr++) {
                         void *tmp;
+                        long offset;
 
                         if (need_swap) {
                                 phdr->p_type = bswap_32(phdr->p_type);
@@ -140,12 +141,13 @@ int filename__read_build_id(const char *filename, void *bf, size_t size)
                                 continue;
 
                         buf_size = phdr->p_filesz;
+                        offset = phdr->p_offset;
                         tmp = realloc(buf, buf_size);
                         if (tmp == NULL)
                                 goto out_free;
 
                         buf = tmp;
-                        fseek(fp, phdr->p_offset, SEEK_SET);
+                        fseek(fp, offset, SEEK_SET);
                         if (fread(buf, buf_size, 1, fp) != 1)
                                 goto out_free;
 
@@ -178,6 +180,7 @@ int filename__read_build_id(const char *filename, void *bf, size_t size)
 
                 for (i = 0, phdr = buf; i < ehdr.e_phnum; i++, phdr++) {
                         void *tmp;
+                        long offset;
 
                         if (need_swap) {
                                 phdr->p_type = bswap_32(phdr->p_type);
@@ -189,12 +192,13 @@ int filename__read_build_id(const char *filename, void *bf, size_t size)
                                 continue;
 
                         buf_size = phdr->p_filesz;
+                        offset = phdr->p_offset;
                         tmp = realloc(buf, buf_size);
                         if (tmp == NULL)
                                 goto out_free;
 
                         buf = tmp;
-                        fseek(fp, phdr->p_offset, SEEK_SET);
+                        fseek(fp, offset, SEEK_SET);
                         if (fread(buf, buf_size, 1, fp) != 1)
                                 goto out_free;
 
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 008b361b1758..be198ac27031 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -269,35 +269,6 @@ void event_attr_init(struct perf_event_attr *attr);
 #define _STR(x) #x
 #define STR(x) _STR(x)
 
-/*
- *  Determine whether some value is a power of two, where zero is
- * *not* considered a power of two.
- */
-
-static inline __attribute__((const))
-bool is_power_of_2(unsigned long n)
-{
-        return (n != 0 && ((n & (n - 1)) == 0));
-}
-
-static inline unsigned next_pow2(unsigned x)
-{
-        if (!x)
-                return 1;
-        return 1ULL << (32 - __builtin_clz(x - 1));
-}
-
-static inline unsigned long next_pow2_l(unsigned long x)
-{
-#if BITS_PER_LONG == 64
-        if (x <= (1UL << 31))
-                return next_pow2(x);
-        return (unsigned long)next_pow2(x >> 32) << 32;
-#else
-        return next_pow2(x);
-#endif
-}
-
 size_t hex_width(u64 v);
 int hex2u64(const char *ptr, u64 *val);