Merge branch 'bpf: Add kprobe multi link'

Jiri Olsa says:

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

hi,
this patchset adds new link type BPF_TRACE_KPROBE_MULTI that attaches
kprobe program through fprobe API [1] instroduced by Masami.

The fprobe API allows to attach probe on multiple functions at once very
fast, because it works on top of ftrace. On the other hand this limits
the probe point to the function entry or return.

With bpftrace support I see following attach speed:

  # perf stat --null -r 5 ./src/bpftrace -e 'kprobe:x* { } i:ms:1 { exit(); } '
  Attaching 2 probes...
  Attaching 3342 functions
  ...

  1.4960 +- 0.0285 seconds time elapsed  ( +-  1.91% )

v3 changes:
  - based on latest fprobe post from Masami [2]
  - add acks
  - add extra comment to kprobe_multi_link_handler wrt entry ip setup [Masami]
  - keep swap_words_64 static and swap values directly in
    bpf_kprobe_multi_cookie_swap [Andrii]
  - rearrange locking/migrate setup in kprobe_multi_link_prog_run [Andrii]
  - move uapi fields [Andrii]
  - add bpf_program__attach_kprobe_multi_opts function [Andrii]
  - many small test changes [Andrii]
  - added tests for bpf_program__attach_kprobe_multi_opts
  - make kallsyms_lookup_name check for empty string [Andrii]

v2 changes:
  - based on latest fprobe changes [1]
  - renaming the uapi interface to kprobe multi
  - adding support for sort_r to pass user pointer for swap functions
    and using that in cookie support to keep just single functions array
  - moving new link to kernel/trace/bpf_trace.c file
  - using single fprobe callback function for entry and exit
  - using kvzalloc, libbpf_ensure_mem functions
  - adding new k[ret]probe.multi sections instead of using current kprobe
  - used glob_match from test_progs.c, added '?' matching
  - move bpf_get_func_ip verifier inline change to seprate change
  - couple of other minor fixes

Also available at:
  https://git.kernel.org/pub/scm/linux/kernel/git/jolsa/perf.git
  bpf/kprobe_multi

thanks,
jirka

[1] https://lore.kernel.org/bpf/164458044634.586276.3261555265565111183.stgit@devnote2/
[2] https://lore.kernel.org/bpf/164735281449.1084943.12438881786173547153.stgit@devnote2/
====================

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

1 files changed, 30 insertions, 10 deletions

diff --git a/lib/sort.c b/lib/sort.c
index aa18153864d2..b399bf10d675 100644
--- a/lib/sort.c
+++ b/lib/sort.c
@@ -122,16 +122,27 @@ static void swap_bytes(void *a, void *b, size_t n)
  * a pointer, but small integers make for the smallest compare
  * instructions.
  */
-#define SWAP_WORDS_64 (swap_func_t)0
-#define SWAP_WORDS_32 (swap_func_t)1
-#define SWAP_BYTES    (swap_func_t)2
+#define SWAP_WORDS_64 (swap_r_func_t)0
+#define SWAP_WORDS_32 (swap_r_func_t)1
+#define SWAP_BYTES    (swap_r_func_t)2
+#define SWAP_WRAPPER  (swap_r_func_t)3
+
+struct wrapper {
+	cmp_func_t cmp;
+	swap_func_t swap;
+};
 
 /*
  * The function pointer is last to make tail calls most efficient if the
  * compiler decides not to inline this function.
  */
-static void do_swap(void *a, void *b, size_t size, swap_func_t swap_func)
+static void do_swap(void *a, void *b, size_t size, swap_r_func_t swap_func, const void *priv)
 {
+	if (swap_func == SWAP_WRAPPER) {
+		((const struct wrapper *)priv)->swap(a, b, (int)size);
+		return;
+	}
+
 	if (swap_func == SWAP_WORDS_64)
 		swap_words_64(a, b, size);
 	else if (swap_func == SWAP_WORDS_32)
@@ -139,7 +150,7 @@ static void do_swap(void *a, void *b, size_t size, swap_func_t swap_func)
 	else if (swap_func == SWAP_BYTES)
 		swap_bytes(a, b, size);
 	else
-		swap_func(a, b, (int)size);
+		swap_func(a, b, (int)size, priv);
 }
 
 #define _CMP_WRAPPER ((cmp_r_func_t)0L)
@@ -147,7 +158,7 @@ static void do_swap(void *a, void *b, size_t size, swap_func_t swap_func)
 static int do_cmp(const void *a, const void *b, cmp_r_func_t cmp, const void *priv)
 {
 	if (cmp == _CMP_WRAPPER)
-		return ((cmp_func_t)(priv))(a, b);
+		return ((const struct wrapper *)priv)->cmp(a, b);
 	return cmp(a, b, priv);
 }
 
@@ -198,7 +209,7 @@ static size_t parent(size_t i, unsigned int lsbit, size_t size)
  */
 void sort_r(void *base, size_t num, size_t size,
 	    cmp_r_func_t cmp_func,
-	    swap_func_t swap_func,
+	    swap_r_func_t swap_func,
 	    const void *priv)
 {
 	/* pre-scale counters for performance */
@@ -208,6 +219,10 @@ void sort_r(void *base, size_t num, size_t size,
 	if (!a)		/* num < 2 || size == 0 */
 		return;
 
+	/* called from 'sort' without swap function, let's pick the default */
+	if (swap_func == SWAP_WRAPPER && !((struct wrapper *)priv)->swap)
+		swap_func = NULL;
+
 	if (!swap_func) {
 		if (is_aligned(base, size, 8))
 			swap_func = SWAP_WORDS_64;
@@ -230,7 +245,7 @@ void sort_r(void *base, size_t num, size_t size,
 		if (a)			/* Building heap: sift down --a */
 			a -= size;
 		else if (n -= size)	/* Sorting: Extract root to --n */
-			do_swap(base, base + n, size, swap_func);
+			do_swap(base, base + n, size, swap_func, priv);
 		else			/* Sort complete */
 			break;
 
@@ -257,7 +272,7 @@ void sort_r(void *base, size_t num, size_t size,
 		c = b;			/* Where "a" belongs */
 		while (b != a) {	/* Shift it into place */
 			b = parent(b, lsbit, size);
-			do_swap(base + b, base + c, size, swap_func);
+			do_swap(base + b, base + c, size, swap_func, priv);
 		}
 	}
 }
@@ -267,6 +282,11 @@ void sort(void *base, size_t num, size_t size,
 	  cmp_func_t cmp_func,
 	  swap_func_t swap_func)
 {
-	return sort_r(base, num, size, _CMP_WRAPPER, swap_func, cmp_func);
+	struct wrapper w = {
+		.cmp  = cmp_func,
+		.swap = swap_func,
+	};
+
+	return sort_r(base, num, size, _CMP_WRAPPER, SWAP_WRAPPER, &w);
 }
 EXPORT_SYMBOL(sort);