linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Arnaldo Carvalho de Melo <acme@kernel.org>
To: Ingo Molnar <mingo@kernel.org>, Thomas Gleixner <tglx@linutronix.de>
Cc: "Jiri Olsa" <jolsa@kernel.org>,
	"Namhyung Kim" <namhyung@kernel.org>,
	"Clark Williams" <williams@redhat.com>,
	linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
	"Arnaldo Carvalho de Melo" <acme@redhat.com>,
	"Adrian Hunter" <adrian.hunter@intel.com>,
	"Luis Cláudio Gonçalves" <lclaudio@redhat.com>
Subject: [PATCH 13/37] perf augmented_raw_syscalls: Support copying two string syscall args
Date: Mon, 22 Jul 2019 14:38:15 -0300	[thread overview]
Message-ID: <20190722173839.22898-14-acme@kernel.org> (raw)
In-Reply-To: <20190722173839.22898-1-acme@kernel.org>

From: Arnaldo Carvalho de Melo <acme@redhat.com>

Starting with the renameat and renameat2 syscall, that both receive as
second and fourth parameters a pathname:

  # perf trace -e rename* mv one ANOTHER
  LLVM: dumping /home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o
  mv: cannot stat 'one': No such file or directory
  renameat2(AT_FDCWD, "one", AT_FDCWD, "ANOTHER", RENAME_NOREPLACE) = -1 ENOENT (No such file or directory)
  #

Since the per CPU scratch buffer map has space for two maximum sized
pathnames, the verifier is satisfied that there will be no overrun.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-x2uboyg5kx2wqeru288209b6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c                    |  2 ++
 .../examples/bpf/augmented_raw_syscalls.c     | 20 +++++++++++++++++++
 2 files changed, 22 insertions(+)

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index a681b8c2ee4e..c64f7c99db15 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -873,9 +873,11 @@ static struct syscall_fmt {
 	{ .name	    = "recvmsg",
 	  .arg = { [2] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, },
 	{ .name	    = "renameat",
+	  .bpf_prog_name = { .sys_enter = "!syscalls:sys_enter_renameat", },
 	  .arg = { [0] = { .scnprintf = SCA_FDAT, /* olddirfd */ },
 		   [2] = { .scnprintf = SCA_FDAT, /* newdirfd */ }, }, },
 	{ .name	    = "renameat2",
+	  .bpf_prog_name = { .sys_enter = "!syscalls:sys_enter_renameat", },
 	  .arg = { [0] = { .scnprintf = SCA_FDAT, /* olddirfd */ },
 		   [2] = { .scnprintf = SCA_FDAT, /* newdirfd */ },
 		   [4] = { .scnprintf = SCA_RENAMEAT2_FLAGS, /* flags */ }, }, },
diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/examples/bpf/augmented_raw_syscalls.c
index ce308b9a317c..df52d92e1c69 100644
--- a/tools/perf/examples/bpf/augmented_raw_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c
@@ -70,6 +70,7 @@ pid_filter(pids_filtered);
 struct augmented_args_filename {
        struct syscall_enter_args args;
        struct augmented_filename filename;
+       struct augmented_filename filename2;
 };
 
 bpf_map(augmented_filename_map, PERCPU_ARRAY, int, struct augmented_args_filename, 1);
@@ -148,6 +149,25 @@ int sys_enter_openat(struct syscall_enter_args *args)
 	return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, augmented_args, len);
 }
 
+SEC("!syscalls:sys_enter_renameat")
+int sys_enter_renameat(struct syscall_enter_args *args)
+{
+	int key = 0;
+	struct augmented_args_filename *augmented_args = bpf_map_lookup_elem(&augmented_filename_map, &key);
+	const void *oldpath_arg = (const void *)args->args[1],
+		   *newpath_arg = (const void *)args->args[3];
+	unsigned int len = sizeof(augmented_args->args), oldpath_len;
+
+        if (augmented_args == NULL)
+                return 1; /* Failure: don't filter */
+
+	oldpath_len = augmented_filename__read(&augmented_args->filename, oldpath_arg, sizeof(augmented_args->filename.value));
+	len += oldpath_len + augmented_filename__read((void *)(&augmented_args->filename) + oldpath_len, newpath_arg, sizeof(augmented_args->filename.value));
+
+	/* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */
+	return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, augmented_args, len);
+}
+
 SEC("raw_syscalls:sys_enter")
 int sys_enter(struct syscall_enter_args *args)
 {
-- 
2.21.0


  parent reply	other threads:[~2019-07-22 17:40 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-07-22 17:38 [GIT PULL] perf/core improvements and fixes Arnaldo Carvalho de Melo
2019-07-22 17:38 ` [PATCH 01/37] perf include bpf: Add bpf_tail_call() prototype Arnaldo Carvalho de Melo
2019-07-22 17:38 ` [PATCH 02/37] perf bpf: Do not attach a BPF prog to a tracepoint if its name starts with ! Arnaldo Carvalho de Melo
2019-07-22 17:38 ` [PATCH 03/37] perf evsel: Store backpointer to attached bpf_object Arnaldo Carvalho de Melo
2019-07-22 17:38 ` [PATCH 04/37] perf trace: Add pointer to BPF object containing __augmented_syscalls__ Arnaldo Carvalho de Melo
2019-07-22 17:38 ` [PATCH 05/37] perf trace: Look up maps just on the __augmented_syscalls__ BPF object Arnaldo Carvalho de Melo
2019-07-22 17:38 ` [PATCH 06/37] perf trace: Order -e syscalls table Arnaldo Carvalho de Melo
2019-07-22 17:38 ` [PATCH 07/37] perf trace: Add BPF handler for unaugmented syscalls Arnaldo Carvalho de Melo
2019-07-22 17:38 ` [PATCH 08/37] perf trace: Allow specifying the bpf prog to augment specific syscalls Arnaldo Carvalho de Melo
2019-07-22 17:38 ` [PATCH 09/37] perf trace: Put the per-syscall entry/exit prog_array BPF map infrastructure in place Arnaldo Carvalho de Melo
2019-07-22 17:38 ` [PATCH 10/37] perf trace: Handle raw_syscalls:sys_enter just like the BPF_OUTPUT augmented event Arnaldo Carvalho de Melo
2019-07-22 17:38 ` [PATCH 11/37] perf augmented_raw_syscalls: Add handler for "openat" Arnaldo Carvalho de Melo
2019-07-22 17:38 ` [PATCH 12/37] perf augmented_raw_syscalls: Switch to using BPF_MAP_TYPE_PROG_ARRAY Arnaldo Carvalho de Melo
2019-07-22 17:38 ` Arnaldo Carvalho de Melo [this message]
2019-07-22 17:38 ` [PATCH 14/37] perf trace: Look for default name for entries in the syscalls prog array Arnaldo Carvalho de Melo
2019-07-22 17:38 ` [PATCH 15/37] perf augmented_raw_syscalls: Rename augmented_args_filename to augmented_args_payload Arnaldo Carvalho de Melo
2019-07-22 17:38 ` [PATCH 16/37] perf script: Fix --max-blocks man page description Arnaldo Carvalho de Melo
2019-07-22 17:38 ` [PATCH 17/37] perf script: Improve man page description of metrics Arnaldo Carvalho de Melo
2019-07-22 17:38 ` [PATCH 18/37] perf script: Fix off by one in brstackinsn IPC computation Arnaldo Carvalho de Melo
2019-07-22 17:38 ` [PATCH 19/37] perf tools: Fix proper buffer size for feature processing Arnaldo Carvalho de Melo
2019-07-22 17:38 ` [PATCH 20/37] perf stat: Fix segfault for event group in repeat mode Arnaldo Carvalho de Melo
2019-07-22 17:38 ` [PATCH 21/37] perf augmented_raw_syscalls: Augment sockaddr arg in 'connect' Arnaldo Carvalho de Melo
2019-07-22 17:38 ` [PATCH 22/37] perf trace beauty: Make connect's addrlen be printed as an int, not hex Arnaldo Carvalho de Melo
2019-07-22 17:38 ` [PATCH 23/37] perf trace beauty: Disable fd->pathname when close() not enabled Arnaldo Carvalho de Melo
2019-07-22 17:38 ` [PATCH 24/37] perf trace beauty: Do not try to use the fd->pathname beautifier for bind/connect fd arg Arnaldo Carvalho de Melo
2019-07-22 17:38 ` [PATCH 25/37] perf trace beauty: Beautify 'sendto's sockaddr arg Arnaldo Carvalho de Melo
2019-07-22 17:38 ` [PATCH 26/37] perf trace beauty: Beautify bind's " Arnaldo Carvalho de Melo
2019-07-22 17:38 ` [PATCH 27/37] perf stat: Always separate stalled cycles per insn Arnaldo Carvalho de Melo
2019-07-22 17:38 ` [PATCH 28/37] perf session: Fix loading of compressed data split across adjacent records Arnaldo Carvalho de Melo
2019-07-22 17:38 ` [PATCH 29/37] perf trace beauty: Add BPF augmenter for the 'rename' syscall Arnaldo Carvalho de Melo
2019-07-22 17:38 ` [PATCH 30/37] perf trace: Forward error codes when trying to read syscall info Arnaldo Carvalho de Melo
2019-07-22 17:38 ` [PATCH 31/37] perf trace: Mark syscall ids that are not allocated to avoid unnecessary error messages Arnaldo Carvalho de Melo
2019-07-22 17:38 ` [PATCH 32/37] perf trace: Preallocate the syscall table Arnaldo Carvalho de Melo
2019-07-22 17:38 ` [PATCH 33/37] perf trace: Reuse BPF augmenters from syscalls with similar args signature Arnaldo Carvalho de Melo
2019-07-22 17:38 ` [PATCH 34/37] perf trace: Add "sendfile64" alias to the "sendfile" syscall Arnaldo Carvalho de Melo
2019-07-22 17:38 ` [PATCH 35/37] perf probe: Set pev->nargs to zero after freeing pev->args entries Arnaldo Carvalho de Melo
2019-07-22 17:38 ` [PATCH 36/37] perf probe: Avoid calling freeing routine multiple times for same pointer Arnaldo Carvalho de Melo
2019-07-22 17:38 ` [PATCH 37/37] perf build: Do not use -Wshadow on gcc < 4.8 Arnaldo Carvalho de Melo

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=20190722173839.22898-14-acme@kernel.org \
    --to=acme@kernel.org \
    --cc=acme@redhat.com \
    --cc=adrian.hunter@intel.com \
    --cc=jolsa@kernel.org \
    --cc=lclaudio@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=namhyung@kernel.org \
    --cc=tglx@linutronix.de \
    --cc=williams@redhat.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;
as well as URLs for NNTP newsgroup(s).