Merge branch 'replace-config_dmabuf_sysfs_stats-with-bpf'

T.J. Mercier says:

====================
Replace CONFIG_DMABUF_SYSFS_STATS with BPF

Until CONFIG_DMABUF_SYSFS_STATS was added [1] it was only possible to
perform per-buffer accounting with debugfs which is not suitable for
production environments. Eventually we discovered the overhead with
per-buffer sysfs file creation/removal was significantly impacting
allocation and free times, and exacerbated kernfs lock contention. [2]
dma_buf_stats_setup() is responsible for 39% of single-page buffer
creation duration, or 74% of single-page dma_buf_export() duration when
stressing dmabuf allocations and frees.

I prototyped a change from per-buffer to per-exporter statistics with a
RCU protected list of exporter allocations that accommodates most (but
not all) of our use-cases and avoids almost all of the sysfs overhead.
While that adds less overhead than per-buffer sysfs, and less even than
the maintenance of the dmabuf debugfs_list, it's still *additional*
overhead on top of the debugfs_list and doesn't give us per-buffer info.

This series uses the existing dmabuf debugfs_list to implement a BPF
dmabuf iterator, which adds no overhead to buffer allocation/free and
provides per-buffer info. The list has been moved outside of
CONFIG_DEBUG_FS scope so that it is always populated. The BPF program
loaded by userspace that extracts per-buffer information gets to define
its own interface which avoids the lack of ABI stability with debugfs.

This will allow us to replace our use of CONFIG_DMABUF_SYSFS_STATS, and
the plan is to remove it from the kernel after the next longterm stable
release.

[1] https://lore.kernel.org/linux-media/20201210044400.1080308-1-hridya@google.com
[2] https://lore.kernel.org/all/20220516171315.2400578-1-tjmercier@google.com

v1: https://lore.kernel.org/all/20250414225227.3642618-1-tjmercier@google.com
v1 -> v2:
Make the DMA buffer list independent of CONFIG_DEBUG_FS per Christian
  König
Add CONFIG_DMA_SHARED_BUFFER check to kernel/bpf/Makefile per kernel
  test robot
Use BTF_ID_LIST_SINGLE instead of BTF_ID_LIST_GLOBAL_SINGLE per Song Liu
Fixup comment style, mixing code/declarations, and use ASSERT_OK_FD in
  selftest per Song Liu
Add BPF_ITER_RESCHED feature to bpf_dmabuf_reg_info per Alexei
  Starovoitov
Add open-coded iterator and selftest per Alexei Starovoitov
Add a second test buffer from the system dmabuf heap to selftests
Use the BPF program we'll use in production for selftest per Alexei
  Starovoitov
  https://r.android.com/c/platform/system/bpfprogs/+/3616123/2/dmabufIter.c
  https://r.android.com/c/platform/system/memory/libmeminfo/+/3614259/1/libdmabufinfo/dmabuf_bpf_stats.cpp
v2: https://lore.kernel.org/all/20250504224149.1033867-1-tjmercier@google.com
v2 -> v3:
Rebase onto bpf-next/master
Move get_next_dmabuf() into drivers/dma-buf/dma-buf.c, along with the
  new get_first_dmabuf(). This avoids having to expose the dmabuf list
  and mutex to the rest of the kernel, and keeps the dmabuf mutex
  operations near each other in the same file. (Christian König)
Add Christian's RB to dma-buf: Rename debugfs symbols
Drop RFC: dma-buf: Remove DMA-BUF statistics
v3: https://lore.kernel.org/all/20250507001036.2278781-1-tjmercier@google.com
v3 -> v4:
Fix selftest BPF program comment style (not kdoc) per Alexei Starovoitov
Fix dma-buf.c kdoc comment style per Alexei Starovoitov
Rename get_first_dmabuf / get_next_dmabuf to dma_buf_iter_begin /
  dma_buf_iter_next per Christian König
Add Christian's RB to bpf: Add dmabuf iterator
v4: https://lore.kernel.org/all/20250508182025.2961555-1-tjmercier@google.com
v4 -> v5:
Add Christian's Acks to all patches
Add Song Liu's Acks
Move BTF_ID_LIST_SINGLE and DEFINE_BPF_ITER_FUNC closer to usage per
  Song Liu
Fix open-coded iterator comment style per Song Liu
Move iterator termination check to its own subtest per Song Liu
Rework selftest buffer creation per Song Liu
Fix spacing in sanitize_string per BPF CI
v5: https://lore.kernel.org/all/20250512174036.266796-1-tjmercier@google.com
v5 -> v6:
Song Liu:
  Init test buffer FDs to -1
  Zero-init udmabuf_create for future proofing
  Bail early for iterator fd/FILE creation failure
  Dereference char ptr to check for NUL in sanitize_string()
  Move map insertion from create_test_buffers() to test_dmabuf_iter()
  Add ACK to selftests/bpf: Add test for open coded dmabuf_iter
v6: https://lore.kernel.org/all/20250513163601.812317-1-tjmercier@google.com
v6 -> v7:
Zero uninitialized name bytes following the end of name strings per
  s390x BPF CI
Reorder sanitize_string bounds checks per Song Liu
Add Song's Ack to: selftests/bpf: Add test for dmabuf_iter
Rebase onto bpf-next/master per BPF CI
====================

Link: https://patch.msgid.link/20250522230429.941193-1-tjmercier@google.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 285 insertions, 0 deletions

diff --git a/tools/testing/selftests/bpf/prog_tests/dmabuf_iter.c b/tools/testing/selftests/bpf/prog_tests/dmabuf_iter.c
new file mode 100644
index 000000000000..6c2b0c3dbcd8
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/dmabuf_iter.c
@@ -0,0 +1,285 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Google */
+
+#include <test_progs.h>
+#include <bpf/libbpf.h>
+#include <bpf/btf.h>
+#include "dmabuf_iter.skel.h"
+
+#include <fcntl.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <unistd.h>
+
+#include <linux/dma-buf.h>
+#include <linux/dma-heap.h>
+#include <linux/udmabuf.h>
+
+static int udmabuf = -1;
+static const char udmabuf_test_buffer_name[DMA_BUF_NAME_LEN] = "udmabuf_test_buffer_for_iter";
+static size_t udmabuf_test_buffer_size;
+static int sysheap_dmabuf = -1;
+static const char sysheap_test_buffer_name[DMA_BUF_NAME_LEN] = "sysheap_test_buffer_for_iter";
+static size_t sysheap_test_buffer_size;
+
+static int create_udmabuf(void)
+{
+	struct udmabuf_create create;
+	int dev_udmabuf, memfd, local_udmabuf;
+
+	udmabuf_test_buffer_size = 10 * getpagesize();
+
+	if (!ASSERT_LE(sizeof(udmabuf_test_buffer_name), DMA_BUF_NAME_LEN, "NAMETOOLONG"))
+		return -1;
+
+	memfd = memfd_create("memfd_test", MFD_ALLOW_SEALING);
+	if (!ASSERT_OK_FD(memfd, "memfd_create"))
+		return -1;
+
+	if (!ASSERT_OK(ftruncate(memfd, udmabuf_test_buffer_size), "ftruncate"))
+		goto close_memfd;
+
+	if (!ASSERT_OK(fcntl(memfd, F_ADD_SEALS, F_SEAL_SHRINK), "seal"))
+		goto close_memfd;
+
+	dev_udmabuf = open("/dev/udmabuf", O_RDONLY);
+	if (!ASSERT_OK_FD(dev_udmabuf, "open udmabuf"))
+		goto close_memfd;
+
+	memset(&create, 0, sizeof(create));
+	create.memfd = memfd;
+	create.flags = UDMABUF_FLAGS_CLOEXEC;
+	create.offset = 0;
+	create.size = udmabuf_test_buffer_size;
+
+	local_udmabuf = ioctl(dev_udmabuf, UDMABUF_CREATE, &create);
+	close(dev_udmabuf);
+	if (!ASSERT_OK_FD(local_udmabuf, "udmabuf_create"))
+		goto close_memfd;
+
+	if (!ASSERT_OK(ioctl(local_udmabuf, DMA_BUF_SET_NAME_B, udmabuf_test_buffer_name), "name"))
+		goto close_udmabuf;
+
+	return local_udmabuf;
+
+close_udmabuf:
+	close(local_udmabuf);
+close_memfd:
+	close(memfd);
+	return -1;
+}
+
+static int create_sys_heap_dmabuf(void)
+{
+	sysheap_test_buffer_size = 20 * getpagesize();
+
+	struct dma_heap_allocation_data data = {
+		.len = sysheap_test_buffer_size,
+		.fd = 0,
+		.fd_flags = O_RDWR | O_CLOEXEC,
+		.heap_flags = 0,
+	};
+	int heap_fd, ret;
+
+	if (!ASSERT_LE(sizeof(sysheap_test_buffer_name), DMA_BUF_NAME_LEN, "NAMETOOLONG"))
+		return -1;
+
+	heap_fd = open("/dev/dma_heap/system", O_RDONLY);
+	if (!ASSERT_OK_FD(heap_fd, "open dma heap"))
+		return -1;
+
+	ret = ioctl(heap_fd, DMA_HEAP_IOCTL_ALLOC, &data);
+	close(heap_fd);
+	if (!ASSERT_OK(ret, "syheap alloc"))
+		return -1;
+
+	if (!ASSERT_OK(ioctl(data.fd, DMA_BUF_SET_NAME_B, sysheap_test_buffer_name), "name"))
+		goto close_sysheap_dmabuf;
+
+	return data.fd;
+
+close_sysheap_dmabuf:
+	close(data.fd);
+	return -1;
+}
+
+static int create_test_buffers(void)
+{
+	udmabuf = create_udmabuf();
+	sysheap_dmabuf = create_sys_heap_dmabuf();
+
+	if (udmabuf < 0 || sysheap_dmabuf < 0)
+		return -1;
+
+	return 0;
+}
+
+static void destroy_test_buffers(void)
+{
+	close(udmabuf);
+	udmabuf = -1;
+
+	close(sysheap_dmabuf);
+	sysheap_dmabuf = -1;
+}
+
+enum Fields { INODE, SIZE, NAME, EXPORTER, FIELD_COUNT };
+struct DmabufInfo {
+	unsigned long inode;
+	unsigned long size;
+	char name[DMA_BUF_NAME_LEN];
+	char exporter[32];
+};
+
+static bool check_dmabuf_info(const struct DmabufInfo *bufinfo,
+			      unsigned long size,
+			      const char *name, const char *exporter)
+{
+	return size == bufinfo->size &&
+	       !strcmp(name, bufinfo->name) &&
+	       !strcmp(exporter, bufinfo->exporter);
+}
+
+static void subtest_dmabuf_iter_check_no_infinite_reads(struct dmabuf_iter *skel)
+{
+	int iter_fd;
+	char buf[256];
+
+	iter_fd = bpf_iter_create(bpf_link__fd(skel->links.dmabuf_collector));
+	if (!ASSERT_OK_FD(iter_fd, "iter_create"))
+		return;
+
+	while (read(iter_fd, buf, sizeof(buf)) > 0)
+		; /* Read out all contents */
+
+	/* Next reads should return 0 */
+	ASSERT_EQ(read(iter_fd, buf, sizeof(buf)), 0, "read");
+
+	close(iter_fd);
+}
+
+static void subtest_dmabuf_iter_check_default_iter(struct dmabuf_iter *skel)
+{
+	bool found_test_sysheap_dmabuf = false;
+	bool found_test_udmabuf = false;
+	struct DmabufInfo bufinfo;
+	size_t linesize = 0;
+	char *line = NULL;
+	FILE *iter_file;
+	int iter_fd, f = INODE;
+
+	iter_fd = bpf_iter_create(bpf_link__fd(skel->links.dmabuf_collector));
+	if (!ASSERT_OK_FD(iter_fd, "iter_create"))
+		return;
+
+	iter_file = fdopen(iter_fd, "r");
+	if (!ASSERT_OK_PTR(iter_file, "fdopen"))
+		goto close_iter_fd;
+
+	while (getline(&line, &linesize, iter_file) != -1) {
+		if (f % FIELD_COUNT == INODE) {
+			ASSERT_EQ(sscanf(line, "%ld", &bufinfo.inode), 1,
+				  "read inode");
+		} else if (f % FIELD_COUNT == SIZE) {
+			ASSERT_EQ(sscanf(line, "%ld", &bufinfo.size), 1,
+				  "read size");
+		} else if (f % FIELD_COUNT == NAME) {
+			ASSERT_EQ(sscanf(line, "%s", bufinfo.name), 1,
+				  "read name");
+		} else if (f % FIELD_COUNT == EXPORTER) {
+			ASSERT_EQ(sscanf(line, "%31s", bufinfo.exporter), 1,
+				  "read exporter");
+
+			if (check_dmabuf_info(&bufinfo,
+					      sysheap_test_buffer_size,
+					      sysheap_test_buffer_name,
+					      "system"))
+				found_test_sysheap_dmabuf = true;
+			else if (check_dmabuf_info(&bufinfo,
+						   udmabuf_test_buffer_size,
+						   udmabuf_test_buffer_name,
+						   "udmabuf"))
+				found_test_udmabuf = true;
+		}
+		++f;
+	}
+
+	ASSERT_EQ(f % FIELD_COUNT, INODE, "number of fields");
+
+	ASSERT_TRUE(found_test_sysheap_dmabuf, "found_test_sysheap_dmabuf");
+	ASSERT_TRUE(found_test_udmabuf, "found_test_udmabuf");
+
+	free(line);
+	fclose(iter_file);
+close_iter_fd:
+	close(iter_fd);
+}
+
+static void subtest_dmabuf_iter_check_open_coded(struct dmabuf_iter *skel, int map_fd)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	char key[DMA_BUF_NAME_LEN];
+	int err, fd;
+	bool found;
+
+	/* No need to attach it, just run it directly */
+	fd = bpf_program__fd(skel->progs.iter_dmabuf_for_each);
+
+	err = bpf_prog_test_run_opts(fd, &topts);
+	if (!ASSERT_OK(err, "test_run_opts err"))
+		return;
+	if (!ASSERT_OK(topts.retval, "test_run_opts retval"))
+		return;
+
+	if (!ASSERT_OK(bpf_map_get_next_key(map_fd, NULL, key), "get next key"))
+		return;
+
+	do {
+		ASSERT_OK(bpf_map_lookup_elem(map_fd, key, &found), "lookup");
+		ASSERT_TRUE(found, "found test buffer");
+	} while (bpf_map_get_next_key(map_fd, key, key));
+}
+
+void test_dmabuf_iter(void)
+{
+	struct dmabuf_iter *skel = NULL;
+	int map_fd;
+	const bool f = false;
+
+	skel = dmabuf_iter__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "dmabuf_iter__open_and_load"))
+		return;
+
+	map_fd = bpf_map__fd(skel->maps.testbuf_hash);
+	if (!ASSERT_OK_FD(map_fd, "map_fd"))
+		goto destroy_skel;
+
+	if (!ASSERT_OK(bpf_map_update_elem(map_fd, udmabuf_test_buffer_name, &f, BPF_ANY),
+		       "insert udmabuf"))
+		goto destroy_skel;
+	if (!ASSERT_OK(bpf_map_update_elem(map_fd, sysheap_test_buffer_name, &f, BPF_ANY),
+		       "insert sysheap buffer"))
+		goto destroy_skel;
+
+	if (!ASSERT_OK(create_test_buffers(), "create_test_buffers"))
+		goto destroy;
+
+	if (!ASSERT_OK(dmabuf_iter__attach(skel), "skel_attach"))
+		goto destroy;
+
+	if (test__start_subtest("no_infinite_reads"))
+		subtest_dmabuf_iter_check_no_infinite_reads(skel);
+	if (test__start_subtest("default_iter"))
+		subtest_dmabuf_iter_check_default_iter(skel);
+	if (test__start_subtest("open_coded"))
+		subtest_dmabuf_iter_check_open_coded(skel, map_fd);
+
+destroy:
+	destroy_test_buffers();
+destroy_skel:
+	dmabuf_iter__destroy(skel);
+}