Merge branch 'perf: Add mmap2 build id support'

Jiri Olsa says:

====================

hi,
adding the support to have buildid stored in mmap2 event,
so we can bypass the final perf record hunt on build ids.

This patchset allows perf to record build ID in mmap2 event,
and adds perf tooling to store/download binaries to .debug
cache based on these build IDs.

Note that the build id retrieval code is stolen from bpf
code, where it's been used (together with file offsets)
to replace IPs in user space stack traces. It's now added
under lib directory.

v7 changes:
  - included only missing kernel patches, cc-ed bpf@vger and
    rebased on bpf-next/master [Alexei]

v6 changes:
  - last 4 patches rebased Arnaldo's perf/core

v5 changes:
  - rebased on latest perf/core
  - several patches already pulled in
  - fixed trace+probe_vfs_getname.sh output redirection
  - fixed changelogs [Arnaldo]
  - renamed BUILD_ID_SIZE to BUILD_ID_SIZE_MAX [Song]

v4 changes:
  - fixed typo in changelog [Namhyung]
  - removed force_download bool from struct dso_store_data,
    because it's not used  [Namhyung]

v3 changes:
  - added acks
  - removed forgotten debug code [Arnaldo]
  - fixed readlink termination [Ian]
  - fixed doc for --debuginfod=URLs [Ian]
  - adopted kernel's memchr_inv function and used
    it in build_id__is_defined function [Arnaldo]

On recording server:

  - on the recording server we can run record with --buildid-mmap
    option to store build ids in mmap2 events:

    # perf record --buildid-mmap
    ^C[ perf record: Woken up 2 times to write data ]
    [ perf record: Captured and wrote 0.836 MB perf.data ]

  - it stores nothing to ~/.debug cache:

    # find ~/.debug
    find: ‘/root/.debug’: No such file or directory

  - and still reports properly:

    # perf report --stdio
    ...
    99.82%  swapper          [kernel.kallsyms]  [k] native_safe_halt
     0.03%  swapper          [kernel.kallsyms]  [k] finish_task_switch
     0.02%  swapper          [kernel.kallsyms]  [k] __softirqentry_text_start
     0.01%  kcompactd0       [kernel.kallsyms]  [k] _raw_spin_unlock_irqrestore
     0.01%  ksoftirqd/6      [kernel.kallsyms]  [k] slab_free_freelist_hook
     0.01%  kworker/17:1H-x  [kernel.kallsyms]  [k] slab_free_freelist_hook

  - display used/hit build ids:

    # perf buildid-list | head -5
    5dcec522abf136fcfd3128f47e131f2365834dd7 /proc/kcore
    589e403a34f55486bcac848a45e00bcdeedd1ca8 /usr/lib64/libcrypto.so.1.1.1g
    94569566d4eac7e9c87ba029d43d4e2158f9527e /usr/lib64/libpthread-2.30.so
    559b9702bebe31c6d132c8dc5cc887673d65d5b5 /usr/lib64/libc-2.30.so
    40da7abe89f631f60538a17686a7d65c6a02ed31 /usr/lib64/ld-2.30.so

  - store build id binaries into build id cache:

    # perf buildid-cache -a perf.data
    OK   5dcec522abf136fcfd3128f47e131f2365834dd7 /proc/kcore
    OK   589e403a34f55486bcac848a45e00bcdeedd1ca8 /usr/lib64/libcrypto.so.1.1.1g
    OK   94569566d4eac7e9c87ba029d43d4e2158f9527e /usr/lib64/libpthread-2.30.so
    OK   559b9702bebe31c6d132c8dc5cc887673d65d5b5 /usr/lib64/libc-2.30.so
    OK   40da7abe89f631f60538a17686a7d65c6a02ed31 /usr/lib64/ld-2.30.so
    OK   a674f7a47c78e35a088104647b9640710277b489 /usr/sbin/sshd
    OK   e5cb4ca25f46485bdbc691c3a92e7e111dac3ef2 /usr/bin/bash
    OK   9bc8589108223c944b452f0819298a0c3cba6215 /usr/bin/find

    # find ~/.debug | head -5
    /root/.debug
    /root/.debug/proc
    /root/.debug/proc/kcore
    /root/.debug/proc/kcore/5dcec522abf136fcfd3128f47e131f2365834dd7
    /root/.debug/proc/kcore/5dcec522abf136fcfd3128f47e131f2365834dd7/kallsyms

  - run debuginfod daemon to provide binaries to another server (below)
    (the initialization could take some time)

    # debuginfod -F /

On another server:

  - copy perf.data from 'record' server and run:

    $ find ~/.debug/
    find: ‘/home/jolsa/.debug/’: No such file or directory

    $ perf buildid-list | head -5
    No kallsyms or vmlinux with build-id 5dcec522abf136fcfd3128f47e131f2365834dd7 was found
    5dcec522abf136fcfd3128f47e131f2365834dd7 [kernel.kallsyms]
    5784f813b727a50cfd3363234aef9fcbab685cc4 /lib/modules/5.10.0-rc2speed+/kernel/fs/xfs/xfs.ko
    589e403a34f55486bcac848a45e00bcdeedd1ca8 /usr/lib64/libcrypto.so.1.1.1g
    94569566d4eac7e9c87ba029d43d4e2158f9527e /usr/lib64/libpthread-2.30.so
    559b9702bebe31c6d132c8dc5cc887673d65d5b5 /usr/lib64/libc-2.30.so

  - report does not show anything (kernel build id does not match):

   $ perf report --stdio
   ...
    76.73%  swapper          [kernel.kallsyms]    [k] 0xffffffff81aa8ebe
     1.89%  find             [kernel.kallsyms]    [k] 0xffffffff810f2167
     0.93%  sshd             [kernel.kallsyms]    [k] 0xffffffff8153380c
     0.83%  swapper          [kernel.kallsyms]    [k] 0xffffffff81104b0b
     0.71%  kworker/u40:2-e  [kernel.kallsyms]    [k] 0xffffffff810f3850
     0.70%  kworker/u40:0-e  [kernel.kallsyms]    [k] 0xffffffff810f3850
     0.64%  find             [kernel.kallsyms]    [k] 0xffffffff81a9ba0a
     0.63%  find             [kernel.kallsyms]    [k] 0xffffffff81aa93b0

  - add build ids does not work, because existing binaries (on another server)
    have different build ids:

    $ perf buildid-cache -a perf.data
    No kallsyms or vmlinux with build-id 5dcec522abf136fcfd3128f47e131f2365834dd7 was found
    FAIL 5dcec522abf136fcfd3128f47e131f2365834dd7 [kernel.kallsyms]
    FAIL 5784f813b727a50cfd3363234aef9fcbab685cc4 /lib/modules/5.10.0-rc2speed+/kernel/fs/xfs/xfs.ko
    FAIL 589e403a34f55486bcac848a45e00bcdeedd1ca8 /usr/lib64/libcrypto.so.1.1.1g
    FAIL 94569566d4eac7e9c87ba029d43d4e2158f9527e /usr/lib64/libpthread-2.30.so
    FAIL 559b9702bebe31c6d132c8dc5cc887673d65d5b5 /usr/lib64/libc-2.30.so
    FAIL 40da7abe89f631f60538a17686a7d65c6a02ed31 /usr/lib64/ld-2.30.so
    FAIL a674f7a47c78e35a088104647b9640710277b489 /usr/sbin/sshd
    FAIL e5cb4ca25f46485bdbc691c3a92e7e111dac3ef2 /usr/bin/bash
    FAIL 9bc8589108223c944b452f0819298a0c3cba6215 /usr/bin/find

  - add build ids with debuginfod setup pointing to record server:

    $ perf buildid-cache -a perf.data --debuginfod http://192.168.122.174:8002
    No kallsyms or vmlinux with build-id 5dcec522abf136fcfd3128f47e131f2365834dd7 was found
    OK   5dcec522abf136fcfd3128f47e131f2365834dd7 [kernel.kallsyms]
    OK   5784f813b727a50cfd3363234aef9fcbab685cc4 /lib/modules/5.10.0-rc2speed+/kernel/fs/xfs/xfs.ko
    OK   589e403a34f55486bcac848a45e00bcdeedd1ca8 /usr/lib64/libcrypto.so.1.1.1g
    OK   94569566d4eac7e9c87ba029d43d4e2158f9527e /usr/lib64/libpthread-2.30.so
    OK   559b9702bebe31c6d132c8dc5cc887673d65d5b5 /usr/lib64/libc-2.30.so
    OK   40da7abe89f631f60538a17686a7d65c6a02ed31 /usr/lib64/ld-2.30.so
    OK   a674f7a47c78e35a088104647b9640710277b489 /usr/sbin/sshd
    OK   e5cb4ca25f46485bdbc691c3a92e7e111dac3ef2 /usr/bin/bash
    OK   9bc8589108223c944b452f0819298a0c3cba6215 /usr/bin/find

  - and report works:

    $ perf report --stdio
    ...
    76.73%  swapper          [kernel.kallsyms]    [k] native_safe_halt
     1.91%  find             [kernel.kallsyms]    [k] queue_work_on
     0.93%  sshd             [kernel.kallsyms]    [k] iowrite16
     0.83%  swapper          [kernel.kallsyms]    [k] finish_task_switch
     0.72%  kworker/u40:2-e  [kernel.kallsyms]    [k] process_one_work
     0.70%  kworker/u40:0-e  [kernel.kallsyms]    [k] process_one_work
     0.64%  find             [kernel.kallsyms]    [k] syscall_enter_from_user_mode
     0.63%  find             [kernel.kallsyms]    [k] _raw_spin_unlock_irqrestore

  - because we have the data in build id cache:

    $ find ~/.debug | head -10
    .../.debug
    .../.debug/home
    .../.debug/home/jolsa
    .../.debug/home/jolsa/.cache
    .../.debug/home/jolsa/.cache/debuginfod_client
    .../.debug/home/jolsa/.cache/debuginfod_client/5dcec522abf136fcfd3128f47e131f2365834dd7
    .../.debug/home/jolsa/.cache/debuginfod_client/5dcec522abf136fcfd3128f47e131f2365834dd7/executable
    .../.debug/home/jolsa/.cache/debuginfod_client/5dcec522abf136fcfd3128f47e131f2365834dd7/executable/5dcec522abf136fcfd3128f47e131f2365834dd7
    .../.debug/home/jolsa/.cache/debuginfod_client/5dcec522abf136fcfd3128f47e131f2365834dd7/executable/5dcec522abf136fcfd3128f47e131f2365834dd7/elf
    .../.debug/home/jolsa/.cache/debuginfod_client/5dcec522abf136fcfd3128f47e131f2365834dd7/executable/5dcec522abf136fcfd3128f47e131f2365834dd7/debug

Available also in:
  git://git.kernel.org/pub/scm/linux/kernel/git/jolsa/perf.git
  perf/build_id

thanks,
jirka
====================

Signed-off-by: Alexei Starovoitov <ast@kernel.org>

2 files changed, 151 insertions, 1 deletions

diff --git a/lib/Makefile b/lib/Makefile
index afeff05fa8c5..a6b160c3a4fa 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -36,7 +36,8 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 flex_proportions.o ratelimit.o show_mem.o \
 	 is_single_threaded.o plist.o decompress.o kobject_uevent.o \
 	 earlycpio.o seq_buf.o siphash.o dec_and_lock.o \
-	 nmi_backtrace.o nodemask.o win_minmax.o memcat_p.o
+	 nmi_backtrace.o nodemask.o win_minmax.o memcat_p.o \
+	 buildid.o
 
 lib-$(CONFIG_PRINTK) += dump_stack.o
 lib-$(CONFIG_SMP) += cpumask.o
diff --git a/lib/buildid.c b/lib/buildid.c
new file mode 100644
index 000000000000..6156997c3895
--- /dev/null
+++ b/lib/buildid.c
@@ -0,0 +1,149 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/buildid.h>
+#include <linux/elf.h>
+#include <linux/pagemap.h>
+
+#define BUILD_ID 3
+/*
+ * Parse build id from the note segment. This logic can be shared between
+ * 32-bit and 64-bit system, because Elf32_Nhdr and Elf64_Nhdr are
+ * identical.
+ */
+static inline int parse_build_id(void *page_addr,
+				 unsigned char *build_id,
+				 __u32 *size,
+				 void *note_start,
+				 Elf32_Word note_size)
+{
+	Elf32_Word note_offs = 0, new_offs;
+
+	/* check for overflow */
+	if (note_start < page_addr || note_start + note_size < note_start)
+		return -EINVAL;
+
+	/* only supports note that fits in the first page */
+	if (note_start + note_size > page_addr + PAGE_SIZE)
+		return -EINVAL;
+
+	while (note_offs + sizeof(Elf32_Nhdr) < note_size) {
+		Elf32_Nhdr *nhdr = (Elf32_Nhdr *)(note_start + note_offs);
+
+		if (nhdr->n_type == BUILD_ID &&
+		    nhdr->n_namesz == sizeof("GNU") &&
+		    nhdr->n_descsz > 0 &&
+		    nhdr->n_descsz <= BUILD_ID_SIZE_MAX) {
+			memcpy(build_id,
+			       note_start + note_offs +
+			       ALIGN(sizeof("GNU"), 4) + sizeof(Elf32_Nhdr),
+			       nhdr->n_descsz);
+			memset(build_id + nhdr->n_descsz, 0,
+			       BUILD_ID_SIZE_MAX - nhdr->n_descsz);
+			if (size)
+				*size = nhdr->n_descsz;
+			return 0;
+		}
+		new_offs = note_offs + sizeof(Elf32_Nhdr) +
+			ALIGN(nhdr->n_namesz, 4) + ALIGN(nhdr->n_descsz, 4);
+		if (new_offs <= note_offs)  /* overflow */
+			break;
+		note_offs = new_offs;
+	}
+	return -EINVAL;
+}
+
+/* Parse build ID from 32-bit ELF */
+static int get_build_id_32(void *page_addr, unsigned char *build_id,
+			   __u32 *size)
+{
+	Elf32_Ehdr *ehdr = (Elf32_Ehdr *)page_addr;
+	Elf32_Phdr *phdr;
+	int i;
+
+	/* only supports phdr that fits in one page */
+	if (ehdr->e_phnum >
+	    (PAGE_SIZE - sizeof(Elf32_Ehdr)) / sizeof(Elf32_Phdr))
+		return -EINVAL;
+
+	phdr = (Elf32_Phdr *)(page_addr + sizeof(Elf32_Ehdr));
+
+	for (i = 0; i < ehdr->e_phnum; ++i) {
+		if (phdr[i].p_type == PT_NOTE &&
+		    !parse_build_id(page_addr, build_id, size,
+				    page_addr + phdr[i].p_offset,
+				    phdr[i].p_filesz))
+			return 0;
+	}
+	return -EINVAL;
+}
+
+/* Parse build ID from 64-bit ELF */
+static int get_build_id_64(void *page_addr, unsigned char *build_id,
+			   __u32 *size)
+{
+	Elf64_Ehdr *ehdr = (Elf64_Ehdr *)page_addr;
+	Elf64_Phdr *phdr;
+	int i;
+
+	/* only supports phdr that fits in one page */
+	if (ehdr->e_phnum >
+	    (PAGE_SIZE - sizeof(Elf64_Ehdr)) / sizeof(Elf64_Phdr))
+		return -EINVAL;
+
+	phdr = (Elf64_Phdr *)(page_addr + sizeof(Elf64_Ehdr));
+
+	for (i = 0; i < ehdr->e_phnum; ++i) {
+		if (phdr[i].p_type == PT_NOTE &&
+		    !parse_build_id(page_addr, build_id, size,
+				    page_addr + phdr[i].p_offset,
+				    phdr[i].p_filesz))
+			return 0;
+	}
+	return -EINVAL;
+}
+
+/*
+ * Parse build ID of ELF file mapped to vma
+ * @vma:      vma object
+ * @build_id: buffer to store build id, at least BUILD_ID_SIZE long
+ * @size:     returns actual build id size in case of success
+ *
+ * Returns 0 on success, otherwise error (< 0).
+ */
+int build_id_parse(struct vm_area_struct *vma, unsigned char *build_id,
+		   __u32 *size)
+{
+	Elf32_Ehdr *ehdr;
+	struct page *page;
+	void *page_addr;
+	int ret;
+
+	/* only works for page backed storage  */
+	if (!vma->vm_file)
+		return -EINVAL;
+
+	page = find_get_page(vma->vm_file->f_mapping, 0);
+	if (!page)
+		return -EFAULT;	/* page not mapped */
+
+	ret = -EINVAL;
+	page_addr = kmap_atomic(page);
+	ehdr = (Elf32_Ehdr *)page_addr;
+
+	/* compare magic x7f "ELF" */
+	if (memcmp(ehdr->e_ident, ELFMAG, SELFMAG) != 0)
+		goto out;
+
+	/* only support executable file and shared object file */
+	if (ehdr->e_type != ET_EXEC && ehdr->e_type != ET_DYN)
+		goto out;
+
+	if (ehdr->e_ident[EI_CLASS] == ELFCLASS32)
+		ret = get_build_id_32(page_addr, build_id, size);
+	else if (ehdr->e_ident[EI_CLASS] == ELFCLASS64)
+		ret = get_build_id_64(page_addr, build_id, size);
+out:
+	kunmap_atomic(page_addr);
+	put_page(page);
+	return ret;
+}