public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Ian Rogers <irogers@google.com>
To: "Peter Zijlstra" <peterz@infradead.org>,
	"Ingo Molnar" <mingo@redhat.com>,
	"Arnaldo Carvalho de Melo" <acme@kernel.org>,
	"Namhyung Kim" <namhyung@kernel.org>,
	"Mark Rutland" <mark.rutland@arm.com>,
	"Alexander Shishkin" <alexander.shishkin@linux.intel.com>,
	"Jiri Olsa" <jolsa@kernel.org>, "Ian Rogers" <irogers@google.com>,
	"Adrian Hunter" <adrian.hunter@intel.com>,
	"Kan Liang" <kan.liang@linux.intel.com>,
	"Sam James" <sam@gentoo.org>,
	"Jesper Juhl" <jesperjuhl76@gmail.com>,
	"James Clark" <james.clark@linaro.org>,
	"Zhongqiu Han" <quic_zhonhan@quicinc.com>,
	"Yicong Yang" <yangyicong@hisilicon.com>,
	"Thomas Richter" <tmricht@linux.ibm.com>,
	"Michael Petlan" <mpetlan@redhat.com>,
	"Veronika Molnarova" <vmolnaro@redhat.com>,
	"Anne Macedo" <retpolanne@posteo.net>,
	"Dominique Martinet" <asmadeus@codewreck.org>,
	"Jean-Philippe Romain" <jean-philippe.romain@foss.st.com>,
	"Junhao He" <hejunhao3@huawei.com>,
	linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
	"Krzysztof Łopatowski" <krzysztof.m.lopatowski@gmail.com>
Subject: [PATCH v2 1/7] tools lib api: Add io_dir an allocation free readdir alternative
Date: Fri,  7 Feb 2025 15:24:42 -0800	[thread overview]
Message-ID: <20250207232452.994822-2-irogers@google.com> (raw)
In-Reply-To: <20250207232452.994822-1-irogers@google.com>

glibc's opendir allocates a minimum of 32kb, when called recursively
for a directory tree the memory consumption can add up - nearly 300kb
during perf start-up when processing modules. Add a stack allocated
variant of readdir sized a little more than 1kb.

As getdents64 may be missing from libc, add support using syscall.
Note, an earlier version of this patch had a feature test for
getdents64 but there were problems on certains distros where
getdents64 would be #define renamed to getdents breaking the code. The
syscall use was made uncondtional to work around this. There is
context in:
https://lore.kernel.org/lkml/20231207050433.1426834-1-irogers@google.com/

Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/lib/api/Makefile |  2 +-
 tools/lib/api/io_dir.h | 93 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 94 insertions(+), 1 deletion(-)
 create mode 100644 tools/lib/api/io_dir.h

diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile
index 7f6396087b46..8665c799e0fa 100644
--- a/tools/lib/api/Makefile
+++ b/tools/lib/api/Makefile
@@ -95,7 +95,7 @@ install_lib: $(LIBFILE)
 		$(call do_install_mkdir,$(libdir_SQ)); \
 		cp -fpR $(LIBFILE) $(DESTDIR)$(libdir_SQ)
 
-HDRS := cpu.h debug.h io.h
+HDRS := cpu.h debug.h io.h io_dir.h
 FD_HDRS := fd/array.h
 FS_HDRS := fs/fs.h fs/tracing_path.h
 INSTALL_HDRS_PFX := $(DESTDIR)$(prefix)/include/api
diff --git a/tools/lib/api/io_dir.h b/tools/lib/api/io_dir.h
new file mode 100644
index 000000000000..c84738923c96
--- /dev/null
+++ b/tools/lib/api/io_dir.h
@@ -0,0 +1,93 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+/*
+ * Lightweight directory reading library.
+ */
+#ifndef __API_IO_DIR__
+#define __API_IO_DIR__
+
+#include <dirent.h>
+#include <fcntl.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+
+#if !defined(SYS_getdents64)
+#if defined(__x86_64__)
+#define SYS_getdents64 217
+#elif defined(__aarch64__)
+#define SYS_getdents64 61
+#endif
+#endif
+
+static inline ssize_t perf_getdents64(int fd, void *dirp, size_t count)
+{
+#ifdef MEMORY_SANITIZER
+	memset(dirp, 0, count);
+#endif
+	return syscall(SYS_getdents64, fd, dirp, count);
+}
+#endif
+
+struct io_dirent64 {
+	ino64_t        d_ino;    /* 64-bit inode number */
+	off64_t        d_off;    /* 64-bit offset to next structure */
+	unsigned short d_reclen; /* Size of this dirent */
+	unsigned char  d_type;   /* File type */
+	char           d_name[NAME_MAX + 1]; /* Filename (null-terminated) */
+};
+
+struct io_dir {
+	int dirfd;
+	ssize_t available_bytes;
+	struct io_dirent64 *next;
+	struct io_dirent64 buff[4];
+};
+
+static inline void io_dir__init(struct io_dir *iod, int dirfd)
+{
+	iod->dirfd = dirfd;
+	iod->available_bytes = 0;
+}
+
+static inline void io_dir__rewinddir(struct io_dir *iod)
+{
+	lseek(iod->dirfd, 0, SEEK_SET);
+	iod->available_bytes = 0;
+}
+
+static inline struct io_dirent64 *io_dir__readdir(struct io_dir *iod)
+{
+	struct io_dirent64 *entry;
+
+	if (iod->available_bytes <= 0) {
+		ssize_t rc = perf_getdents64(iod->dirfd, iod->buff, sizeof(iod->buff));
+
+		if (rc <= 0)
+			return NULL;
+		iod->available_bytes = rc;
+		iod->next = iod->buff;
+	}
+	entry = iod->next;
+	iod->next = (struct io_dirent64 *)((char *)entry + entry->d_reclen);
+	iod->available_bytes -= entry->d_reclen;
+	return entry;
+}
+
+static inline bool io_dir__is_dir(const struct io_dir *iod, struct io_dirent64 *dent)
+{
+	if (dent->d_type == DT_UNKNOWN) {
+		struct stat st;
+
+		if (fstatat(iod->dirfd, dent->d_name, &st, /*flags=*/0))
+			return false;
+
+		if (S_ISDIR(st.st_mode)) {
+			dent->d_type = DT_DIR;
+			return true;
+		}
+	}
+	return dent->d_type == DT_DIR;
+}
+
+#endif
-- 
2.48.1.502.g6dc24dfdaf-goog


  reply	other threads:[~2025-02-07 23:24 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-02-07 23:24 [PATCH v2 0/7] Add io_dir to avoid memory overhead from opendir Ian Rogers
2025-02-07 23:24 ` Ian Rogers [this message]
2025-02-08 17:02   ` [PATCH v2 1/7] tools lib api: Add io_dir() as an allocation free readdir() alternative Markus Elfring
2025-02-19 21:51   ` [PATCH v2 1/7] tools lib api: Add io_dir an allocation free readdir alternative Namhyung Kim
2025-02-19 22:21     ` Ian Rogers
2025-02-21  6:31       ` Namhyung Kim
2025-02-07 23:24 ` [PATCH v2 2/7] perf maps: Switch modules tree walk to io_dir__readdir Ian Rogers
2025-02-07 23:24 ` [PATCH v2 3/7] perf pmu: Switch " Ian Rogers
2025-02-07 23:24 ` [PATCH v2 4/7] perf header: Switch mem topology " Ian Rogers
2025-02-07 23:24 ` [PATCH v2 5/7] perf events: Remove scandir in thread synthesis Ian Rogers
2025-02-07 23:24 ` [PATCH v2 6/7] perf parse-events: Switch tracepoints to io_dir__readdir Ian Rogers
2025-02-07 23:24 ` [PATCH v2 7/7] perf hwmon_pmu: Switch event discovery " Ian Rogers
2025-02-08 10:58 ` [PATCH v2 0/7] Add io_dir to avoid memory overhead from opendir David Laight
2025-02-08 12:15   ` Ian Rogers
2025-02-19 21:54 ` Namhyung Kim

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20250207232452.994822-2-irogers@google.com \
    --to=irogers@google.com \
    --cc=acme@kernel.org \
    --cc=adrian.hunter@intel.com \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=asmadeus@codewreck.org \
    --cc=hejunhao3@huawei.com \
    --cc=james.clark@linaro.org \
    --cc=jean-philippe.romain@foss.st.com \
    --cc=jesperjuhl76@gmail.com \
    --cc=jolsa@kernel.org \
    --cc=kan.liang@linux.intel.com \
    --cc=krzysztof.m.lopatowski@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=mingo@redhat.com \
    --cc=mpetlan@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=peterz@infradead.org \
    --cc=quic_zhonhan@quicinc.com \
    --cc=retpolanne@posteo.net \
    --cc=sam@gentoo.org \
    --cc=tmricht@linux.ibm.com \
    --cc=vmolnaro@redhat.com \
    --cc=yangyicong@hisilicon.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox