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

Pull perf/core improvements and fixes from Jiri Olsa:

  * Honor user freq/interval properly in record command (Namhyung Kim)

  * Speedup DWARF unwind (Jiri Olsa)

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

7 files changed, 322 insertions, 32 deletions

diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 64453d63b971..819f10414f08 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -1,3 +1,6 @@
+#include <asm/bug.h>
+#include <sys/time.h>
+#include <sys/resource.h>
 #include "symbol.h"
 #include "dso.h"
 #include "machine.h"
@@ -136,7 +139,48 @@ int dso__read_binary_type_filename(const struct dso *dso,
         return ret;
 }
 
-static int open_dso(struct dso *dso, struct machine *machine)
+/*
+ * Global list of open DSOs and the counter.
+ */
+static LIST_HEAD(dso__data_open);
+static long dso__data_open_cnt;
+
+static void dso__list_add(struct dso *dso)
+{
+        list_add_tail(&dso->data.open_entry, &dso__data_open);
+        dso__data_open_cnt++;
+}
+
+static void dso__list_del(struct dso *dso)
+{
+        list_del(&dso->data.open_entry);
+        WARN_ONCE(dso__data_open_cnt <= 0,
+                  "DSO data fd counter out of bounds.");
+        dso__data_open_cnt--;
+}
+
+static void close_first_dso(void);
+
+static int do_open(char *name)
+{
+        int fd;
+
+        do {
+                fd = open(name, O_RDONLY);
+                if (fd >= 0)
+                        return fd;
+
+                pr_debug("dso open failed, mmap: %s\n", strerror(errno));
+                if (!dso__data_open_cnt || errno != EMFILE)
+                        break;
+
+                close_first_dso();
+        } while (1);
+
+        return -1;
+}
+
+static int __open_dso(struct dso *dso, struct machine *machine)
 {
         int fd;
         char *root_dir = (char *)"";
@@ -154,11 +198,130 @@ static int open_dso(struct dso *dso, struct machine *machine)
                 return -EINVAL;
         }
 
-        fd = open(name, O_RDONLY);
+        fd = do_open(name);
         free(name);
         return fd;
 }
 
+static void check_data_close(void);
+
+/**
+ * dso_close - Open DSO data file
+ * @dso: dso object
+ *
+ * Open @dso's data file descriptor and updates
+ * list/count of open DSO objects.
+ */
+static int open_dso(struct dso *dso, struct machine *machine)
+{
+        int fd = __open_dso(dso, machine);
+
+        if (fd > 0) {
+                dso__list_add(dso);
+                /*
+                 * Check if we crossed the allowed number
+                 * of opened DSOs and close one if needed.
+                 */
+                check_data_close();
+        }
+
+        return fd;
+}
+
+static void close_data_fd(struct dso *dso)
+{
+        if (dso->data.fd >= 0) {
+                close(dso->data.fd);
+                dso->data.fd = -1;
+                dso->data.file_size = 0;
+                dso__list_del(dso);
+        }
+}
+
+/**
+ * dso_close - Close DSO data file
+ * @dso: dso object
+ *
+ * Close @dso's data file descriptor and updates
+ * list/count of open DSO objects.
+ */
+static void close_dso(struct dso *dso)
+{
+        close_data_fd(dso);
+}
+
+static void close_first_dso(void)
+{
+        struct dso *dso;
+
+        dso = list_first_entry(&dso__data_open, struct dso, data.open_entry);
+        close_dso(dso);
+}
+
+static rlim_t get_fd_limit(void)
+{
+        struct rlimit l;
+        rlim_t limit = 0;
+
+        /* Allow half of the current open fd limit. */
+        if (getrlimit(RLIMIT_NOFILE, &l) == 0) {
+                if (l.rlim_cur == RLIM_INFINITY)
+                        limit = l.rlim_cur;
+                else
+                        limit = l.rlim_cur / 2;
+        } else {
+                pr_err("failed to get fd limit\n");
+                limit = 1;
+        }
+
+        return limit;
+}
+
+static bool may_cache_fd(void)
+{
+        static rlim_t limit;
+
+        if (!limit)
+                limit = get_fd_limit();
+
+        if (limit == RLIM_INFINITY)
+                return true;
+
+        return limit > (rlim_t) dso__data_open_cnt;
+}
+
+/*
+ * Check and close LRU dso if we crossed allowed limit
+ * for opened dso file descriptors. The limit is half
+ * of the RLIMIT_NOFILE files opened.
+*/
+static void check_data_close(void)
+{
+        bool cache_fd = may_cache_fd();
+
+        if (!cache_fd)
+                close_first_dso();
+}
+
+/**
+ * dso__data_close - Close DSO data file
+ * @dso: dso object
+ *
+ * External interface to close @dso's data file descriptor.
+ */
+void dso__data_close(struct dso *dso)
+{
+        close_dso(dso);
+}
+
+/**
+ * dso__data_fd - Get dso's data file descriptor
+ * @dso: dso object
+ * @machine: machine object
+ *
+ * External interface to find dso's file, open it and
+ * returns file descriptor.
+ */
 int dso__data_fd(struct dso *dso, struct machine *machine)
 {
         enum dso_binary_type binary_type_data[] = {
@@ -168,8 +331,13 @@ int dso__data_fd(struct dso *dso, struct machine *machine)
         };
         int i = 0;
 
-        if (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND)
-                return open_dso(dso, machine);
+        if (dso->data.fd >= 0)
+                return dso->data.fd;
+
+        if (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND) {
+                dso->data.fd = open_dso(dso, machine);
+                return dso->data.fd;
+        }
 
         do {
                 int fd;
@@ -178,7 +346,7 @@ int dso__data_fd(struct dso *dso, struct machine *machine)
 
                 fd = open_dso(dso, machine);
                 if (fd >= 0)
-                        return fd;
+                        return dso->data.fd = fd;
 
         } while (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND);
 
@@ -260,16 +428,10 @@ dso_cache__memcpy(struct dso_cache *cache, u64 offset,
 }
 
 static ssize_t
-dso_cache__read(struct dso *dso, struct machine *machine,
-                 u64 offset, u8 *data, ssize_t size)
+dso_cache__read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
 {
         struct dso_cache *cache;
         ssize_t ret;
-        int fd;
-
-        fd = dso__data_fd(dso, machine);
-        if (fd < 0)
-                return -1;
 
         do {
                 u64 cache_offset;
@@ -283,16 +445,16 @@ dso_cache__read(struct dso *dso, struct machine *machine,
                 cache_offset = offset & DSO__DATA_CACHE_MASK;
                 ret = -EINVAL;
 
-                if (-1 == lseek(fd, cache_offset, SEEK_SET))
+                if (-1 == lseek(dso->data.fd, cache_offset, SEEK_SET))
                         break;
 
-                ret = read(fd, cache->data, DSO__DATA_CACHE_SIZE);
+                ret = read(dso->data.fd, cache->data, DSO__DATA_CACHE_SIZE);
                 if (ret <= 0)
                         break;
 
                 cache->offset = cache_offset;
                 cache->size   = ret;
-                dso_cache__insert(&dso->cache, cache);
+                dso_cache__insert(&dso->data.cache, cache);
 
                 ret = dso_cache__memcpy(cache, offset, data, size);
 
@@ -301,24 +463,27 @@ dso_cache__read(struct dso *dso, struct machine *machine,
         if (ret <= 0)
                 free(cache);
 
-        close(fd);
         return ret;
 }
 
-static ssize_t dso_cache_read(struct dso *dso, struct machine *machine,
-                              u64 offset, u8 *data, ssize_t size)
+static ssize_t dso_cache_read(struct dso *dso, u64 offset,
+                              u8 *data, ssize_t size)
 {
         struct dso_cache *cache;
 
-        cache = dso_cache__find(&dso->cache, offset);
+        cache = dso_cache__find(&dso->data.cache, offset);
         if (cache)
                 return dso_cache__memcpy(cache, offset, data, size);
         else
-                return dso_cache__read(dso, machine, offset, data, size);
+                return dso_cache__read(dso, offset, data, size);
 }
 
-ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
-                              u64 offset, u8 *data, ssize_t size)
+/*
+ * Reads and caches dso data DSO__DATA_CACHE_SIZE size chunks
+ * in the rb_tree. Any read to already cached data is served
+ * by cached data.
+ */
+static ssize_t cached_read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
 {
         ssize_t r = 0;
         u8 *p = data;
@@ -326,7 +491,7 @@ ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
         do {
                 ssize_t ret;
 
-                ret = dso_cache_read(dso, machine, offset, p, size);
+                ret = dso_cache_read(dso, offset, p, size);
                 if (ret < 0)
                         return ret;
 
@@ -346,6 +511,67 @@ ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
         return r;
 }
 
+static int data_file_size(struct dso *dso)
+{
+        struct stat st;
+
+        if (!dso->data.file_size) {
+                if (fstat(dso->data.fd, &st)) {
+                        pr_err("dso mmap failed, fstat: %s\n", strerror(errno));
+                        return -1;
+                }
+                dso->data.file_size = st.st_size;
+        }
+
+        return 0;
+}
+
+static ssize_t data_read_offset(struct dso *dso, u64 offset,
+                                u8 *data, ssize_t size)
+{
+        if (data_file_size(dso))
+                return -1;
+
+        /* Check the offset sanity. */
+        if (offset > dso->data.file_size)
+                return -1;
+
+        if (offset + size < offset)
+                return -1;
+
+        return cached_read(dso, offset, data, size);
+}
+
+/**
+ * dso__data_read_offset - Read data from dso file offset
+ * @dso: dso object
+ * @machine: machine object
+ * @offset: file offset
+ * @data: buffer to store data
+ * @size: size of the @data buffer
+ *
+ * External interface to read data from dso file offset. Open
+ * dso data file and use cached_read to get the data.
+ */
+ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
+                              u64 offset, u8 *data, ssize_t size)
+{
+        if (dso__data_fd(dso, machine) < 0)
+                return -1;
+
+        return data_read_offset(dso, offset, data, size);
+}
+
+/**
+ * dso__data_read_addr - Read data from dso address
+ * @dso: dso object
+ * @machine: machine object
+ * @add: virtual memory address
+ * @data: buffer to store data
+ * @size: size of the @data buffer
+ *
+ * External interface to read data from dso address.
+ */
 ssize_t dso__data_read_addr(struct dso *dso, struct map *map,
                             struct machine *machine, u64 addr,
                             u8 *data, ssize_t size)
@@ -473,7 +699,8 @@ struct dso *dso__new(const char *name)
                 dso__set_short_name(dso, dso->name, false);
                 for (i = 0; i < MAP__NR_TYPES; ++i)
                         dso->symbols[i] = dso->symbol_names[i] = RB_ROOT;
-                dso->cache = RB_ROOT;
+                dso->data.cache = RB_ROOT;
+                dso->data.fd = -1;
                 dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
                 dso->binary_type = DSO_BINARY_TYPE__NOT_FOUND;
                 dso->loaded = 0;
@@ -485,6 +712,7 @@ struct dso *dso__new(const char *name)
                 dso->kernel = DSO_TYPE_USER;
                 dso->needs_swap = DSO_SWAP__UNSET;
                 INIT_LIST_HEAD(&dso->node);
+                INIT_LIST_HEAD(&dso->data.open_entry);
         }
 
         return dso;
@@ -506,7 +734,8 @@ void dso__delete(struct dso *dso)
                 dso->long_name_allocated = false;
         }
 
-        dso_cache__free(&dso->cache);
+        dso__data_close(dso);
+        dso_cache__free(&dso->data.cache);
         dso__free_a2l(dso);
         zfree(&dso->symsrc_filename);
         free(dso);
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 38efe95a7fdd..ad553ba257bf 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -76,7 +76,6 @@ struct dso {
         struct list_head node;
         struct rb_root   symbols[MAP__NR_TYPES];
         struct rb_root   symbol_names[MAP__NR_TYPES];
-        struct rb_root   cache;
         void             *a2l;
         char             *symsrc_filename;
         unsigned int     a2l_fails;
@@ -99,6 +98,15 @@ struct dso {
         const char       *long_name;
         u16              long_name_len;
         u16              short_name_len;
+
+        /* dso data file */
+        struct {
+                struct rb_root   cache;
+                int              fd;
+                size_t           file_size;
+                struct list_head open_entry;
+        } data;
+
         char             name[0];
 };
 
@@ -141,7 +149,47 @@ char dso__symtab_origin(const struct dso *dso);
 int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type type,
                                    char *root_dir, char *filename, size_t size);
 
+/*
+ * The dso__data_* external interface provides following functions:
+ *   dso__data_fd
+ *   dso__data_close
+ *   dso__data_read_offset
+ *   dso__data_read_addr
+ *
+ * Please refer to the dso.c object code for each function and
+ * arguments documentation. Following text tries to explain the
+ * dso file descriptor caching.
+ *
+ * The dso__data* interface allows caching of opened file descriptors
+ * to speed up the dso data accesses. The idea is to leave the file
+ * descriptor opened ideally for the whole life of the dso object.
+ *
+ * The current usage of the dso__data_* interface is as follows:
+ *
+ * Get DSO's fd:
+ *   int fd = dso__data_fd(dso, machine);
+ *   USE 'fd' SOMEHOW
+ *
+ * Read DSO's data:
+ *   n = dso__data_read_offset(dso_0, &machine, 0, buf, BUFSIZE);
+ *   n = dso__data_read_addr(dso_0, &machine, 0, buf, BUFSIZE);
+ *
+ * Eventually close DSO's fd:
+ *   dso__data_close(dso);
+ *
+ * It is not necessary to close the DSO object data file. Each time new
+ * DSO data file is opened, the limit (RLIMIT_NOFILE/2) is checked. Once
+ * it is crossed, the oldest opened DSO object is closed.
+ *
+ * The dso__delete function calls close_dso function to ensure the
+ * data file descriptor gets closed/unmapped before the dso object
+ * is freed.
+ *
+ * TODO
+*/
 int dso__data_fd(struct dso *dso, struct machine *machine);
+void dso__data_close(struct dso *dso);
+
 ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
                               u64 offset, u8 *data, ssize_t size);
 ssize_t dso__data_read_addr(struct dso *dso, struct map *map,
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 9ba2eb3bdcfd..e5dd40addb30 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -7,6 +7,7 @@
 #include "../perf.h"
 #include "map.h"
 #include "build-id.h"
+#include "perf_regs.h"
 
 struct mmap_event {
         struct perf_event_header header;
@@ -89,6 +90,10 @@ struct regs_dump {
         u64 abi;
         u64 mask;
         u64 *regs;
+
+        /* Cached values/mask filled by first register access. */
+        u64 cache_regs[PERF_REGS_MAX];
+        u64 cache_mask;
 };
 
 struct stack_dump {
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 21154dabc5fa..8606175fe1e8 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -589,10 +589,10 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
         }
 
         /*
-         * We default some events to a 1 default interval. But keep
+         * We default some events to have a default interval. But keep
          * it a weak assumption overridable by the user.
          */
-        if (!attr->sample_period || (opts->user_freq != UINT_MAX &&
+        if (!attr->sample_period || (opts->user_freq != UINT_MAX ||
                                      opts->user_interval != ULLONG_MAX)) {
                 if (opts->freq) {
                         perf_evsel__set_sample_bit(evsel, PERIOD);
diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c
index a3539ef30b15..43168fb0d9a2 100644
--- a/tools/perf/util/perf_regs.c
+++ b/tools/perf/util/perf_regs.c
@@ -1,11 +1,15 @@
 #include <errno.h>
 #include "perf_regs.h"
+#include "event.h"
 
 int perf_reg_value(u64 *valp, struct regs_dump *regs, int id)
 {
         int i, idx = 0;
         u64 mask = regs->mask;
 
+        if (regs->cache_mask & (1 << id))
+                goto out;
+
         if (!(mask & (1 << id)))
                 return -EINVAL;
 
@@ -14,6 +18,10 @@ int perf_reg_value(u64 *valp, struct regs_dump *regs, int id)
                         idx++;
         }
 
-        *valp = regs->regs[idx];
+        regs->cache_mask |= (1 << id);
+        regs->cache_regs[id] = regs->regs[idx];
+
+out:
+        *valp = regs->cache_regs[id];
         return 0;
 }
diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h
index 79c78f74e0cf..980dbf76bc98 100644
--- a/tools/perf/util/perf_regs.h
+++ b/tools/perf/util/perf_regs.h
@@ -2,7 +2,8 @@
 #define __PERF_REGS_H
 
 #include <linux/types.h>
-#include "event.h"
+
+struct regs_dump;
 
 #ifdef HAVE_PERF_REGS_SUPPORT
 #include <perf_regs.h>
@@ -11,6 +12,7 @@ int perf_reg_value(u64 *valp, struct regs_dump *regs, int id);
 
 #else
 #define PERF_REGS_MASK  0
+#define PERF_REGS_MAX   0
 
 static inline const char *perf_reg_name(int id __maybe_unused)
 {
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index bd5768d74f01..25578b98f5c5 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -250,7 +250,6 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct machine *machine,
 
         /* Check the .eh_frame section for unwinding info */
         offset = elf_section_offset(fd, ".eh_frame_hdr");
-        close(fd);
 
         if (offset)
                 ret = unwind_spec_ehframe(dso, machine, offset,
@@ -271,7 +270,6 @@ static int read_unwind_spec_debug_frame(struct dso *dso,
 
         /* Check the .debug_frame section for unwinding info */
         *offset = elf_section_offset(fd, ".debug_frame");
-        close(fd);
 
         if (*offset)
                 return 0;