* [PATCH v2 bpf-next 1/2] bpf: Populate mmap-able array map memory lazily
2026-07-22 20:50 [PATCH v2 bpf-next 0/2] bpf: Populate mmap-able array maps lazily Song Liu
@ 2026-07-22 20:50 ` Song Liu
2026-07-22 20:50 ` [PATCH v2 bpf-next 2/2] selftests/bpf: Add mmap/munmap benchmark for array maps Song Liu
1 sibling, 0 replies; 3+ messages in thread
From: Song Liu @ 2026-07-22 20:50 UTC (permalink / raw)
To: bpf; +Cc: ast, daniel, andrii, eddyz87, memxor, kernel-team, Song Liu
An mmap-able BPF array map (BPF_F_MMAPABLE) has its backing memory
vmalloc'ed up front at map creation time. array_map_mmap() then wired up
the whole mapping eagerly via remap_vmalloc_range(), which calls
vm_insert_page() for every page of the map. For large maps this makes
every mmap() O(number of pages): an 8MiB map inserts 2048 PTEs per
mmap() and tears them all down again on munmap(), even when user space
only touches a few pages (or none at all).
Populate the mapping lazily instead, the same way the arena map already
does. array_map_mmap() now only performs the bounds check and returns,
leaving the PTEs unpopulated; the pages are inserted on demand by a new
array_map_mmap_fault() handler. Because the memory is already resident,
the fault handler simply resolves the vmalloc page and hands it to the
fault path.
To keep the existing VMA open/close accounting (VM_MAYWRITE write-active
tracking, freeze handling) centralized, the fault handler is reached
through a new optional ->map_mmap_fault callback dispatched from the
shared bpf_map_default_vmops, rather than each map installing its own
vm_operations_struct.
remap_vmalloc_range() previously guarded against offset overflow; since
it is no longer used, array_map_mmap() and the fault handler compute the
mapping offset with 64-bit arithmetic so that a large vm_pgoff cannot
overflow the bounds check on 32-bit architectures.
This turns mmap()/munmap() of an mmap-able array from O(map size) into
O(1). Callers that want the pages populated up front can still request
that explicitly with MAP_POPULATE, matching regular file semantics.
Kernel-side access to the map (via the vmalloc address) is unaffected.
Signed-off-by: Song Liu <song@kernel.org>
Assisted-by: Claude:claude-opus-4-8
---
include/linux/bpf.h | 1 +
kernel/bpf/arraymap.c | 43 +++++++++++++++++++++++++++++++++++++++----
kernel/bpf/syscall.c | 17 +++++++++++++++++
3 files changed, 57 insertions(+), 4 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index e066f44a9c05..b536f3c9e103 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -145,6 +145,7 @@ struct bpf_map_ops {
int (*map_direct_value_meta)(const struct bpf_map *map,
u64 imm, u32 *off);
int (*map_mmap)(struct bpf_map *map, struct vm_area_struct *vma);
+ vm_fault_t (*map_mmap_fault)(struct bpf_map *map, struct vm_fault *vmf);
__poll_t (*map_poll)(struct bpf_map *map, struct file *filp,
struct poll_table_struct *pts);
unsigned long (*map_get_unmapped_area)(struct file *filep, unsigned long addr,
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 248b4818178c..59fda56062a9 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -576,17 +576,51 @@ static int array_map_check_btf(struct bpf_map *map,
static int array_map_mmap(struct bpf_map *map, struct vm_area_struct *vma)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
- pgoff_t pgoff = PAGE_ALIGN(sizeof(*array)) >> PAGE_SHIFT;
if (!(map->map_flags & BPF_F_MMAPABLE))
return -EINVAL;
- if (vma->vm_pgoff * PAGE_SIZE + (vma->vm_end - vma->vm_start) >
+ /* use u64 math so the offset cannot overflow on 32-bit archs */
+ if ((u64)vma->vm_pgoff * PAGE_SIZE + (vma->vm_end - vma->vm_start) >
PAGE_ALIGN((u64)array->map.max_entries * array->elem_size))
return -EINVAL;
- return remap_vmalloc_range(vma, array_map_vmalloc_addr(array),
- vma->vm_pgoff + pgoff);
+ /*
+ * The backing memory is vmalloc'ed up front, so instead of wiring up
+ * every PTE here we let array_map_mmap_fault() insert pages on demand.
+ * remap_vmalloc_range_partial() used to set these flags for us; keep
+ * them to preserve behavior (no VMA expansion, excluded from coredump).
+ */
+ vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP);
+
+ return 0;
+}
+
+static vm_fault_t array_map_mmap_fault(struct bpf_map *map,
+ struct vm_fault *vmf)
+{
+ struct bpf_array *array = container_of(map, struct bpf_array, map);
+ pgoff_t pgoff = PAGE_ALIGN(sizeof(*array)) >> PAGE_SHIFT;
+ struct page *page;
+ void *kaddr;
+
+ /*
+ * vmf->pgoff is the page offset within the mapping (vma->vm_pgoff plus
+ * the offset of the faulting address). The data pages start after the
+ * bpf_array header, hence the extra pgoff. This mirrors the offset that
+ * remap_vmalloc_range(vma, ..., vma->vm_pgoff + pgoff) used to apply.
+ */
+ kaddr = array_map_vmalloc_addr(array) +
+ (((u64)vmf->pgoff + pgoff) << PAGE_SHIFT);
+
+ page = vmalloc_to_page(kaddr);
+ if (!page)
+ return VM_FAULT_SIGBUS;
+
+ get_page(page);
+ vmf->page = page;
+
+ return 0;
}
static bool array_map_meta_equal(const struct bpf_map *meta0,
@@ -812,6 +846,7 @@ const struct bpf_map_ops array_map_ops = {
.map_direct_value_addr = array_map_direct_value_addr,
.map_direct_value_meta = array_map_direct_value_meta,
.map_mmap = array_map_mmap,
+ .map_mmap_fault = array_map_mmap_fault,
.map_seq_show_elem = array_map_seq_show_elem,
.map_check_btf = array_map_check_btf,
.map_lookup_batch = generic_map_lookup_batch,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 0ff9e3aa293d..fb0e1f55c487 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1077,9 +1077,26 @@ static void bpf_map_mmap_close(struct vm_area_struct *vma)
bpf_map_write_active_dec(map);
}
+/*
+ * Called for maps that populate their memory-mapped region lazily, i.e. that
+ * return without wiring up any PTEs from their ->map_mmap callback. Maps that
+ * populate the whole VMA eagerly (e.g. via remap_vmalloc_range()) never reach
+ * here.
+ */
+static vm_fault_t bpf_map_mmap_fault(struct vm_fault *vmf)
+{
+ struct bpf_map *map = vmf->vma->vm_private_data;
+
+ if (!map->ops->map_mmap_fault)
+ return VM_FAULT_SIGBUS;
+
+ return map->ops->map_mmap_fault(map, vmf);
+}
+
static const struct vm_operations_struct bpf_map_default_vmops = {
.open = bpf_map_mmap_open,
.close = bpf_map_mmap_close,
+ .fault = bpf_map_mmap_fault,
};
static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma)
--
2.53.0-Meta
^ permalink raw reply related [flat|nested] 3+ messages in thread* [PATCH v2 bpf-next 2/2] selftests/bpf: Add mmap/munmap benchmark for array maps
2026-07-22 20:50 [PATCH v2 bpf-next 0/2] bpf: Populate mmap-able array maps lazily Song Liu
2026-07-22 20:50 ` [PATCH v2 bpf-next 1/2] bpf: Populate mmap-able array map memory lazily Song Liu
@ 2026-07-22 20:50 ` Song Liu
1 sibling, 0 replies; 3+ messages in thread
From: Song Liu @ 2026-07-22 20:50 UTC (permalink / raw)
To: bpf; +Cc: ast, daniel, andrii, eddyz87, memxor, kernel-team, Song Liu
Add a benchmark that repeatedly mmap()s and munmap()s an mmap-able BPF
array map (BPF_F_MMAPABLE). The number of worker threads is controlled
by the standard -p/--producers option, and the size of the map by
--map-size (default 8MiB).
The benchmark is useful to observe how the cost of mmap()/munmap()
scales with the mapping size, e.g. eager vs lazy page-table population.
Signed-off-by: Song Liu <song@kernel.org>
Assisted-by: Claude:claude-opus-4-8
---
tools/testing/selftests/bpf/Makefile | 1 +
tools/testing/selftests/bpf/bench.c | 4 +
.../bpf/benchs/bench_arraymap_mmap.c | 127 ++++++++++++++++++
.../bpf/benchs/run_bench_arraymap_mmap.sh | 15 +++
4 files changed, 147 insertions(+)
create mode 100644 tools/testing/selftests/bpf/benchs/bench_arraymap_mmap.c
create mode 100755 tools/testing/selftests/bpf/benchs/run_bench_arraymap_mmap.sh
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 55d394438705..b6593fb1135b 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -1003,6 +1003,7 @@ $(OUTPUT)/bench: $(OUTPUT)/bench.o \
$(OUTPUT)/bench_bpf_timing.o \
$(OUTPUT)/bench_bpf_nop.o \
$(OUTPUT)/bench_xdp_lb.o \
+ $(OUTPUT)/bench_arraymap_mmap.o \
$(OUTPUT)/usdt_1.o \
$(OUTPUT)/usdt_2.o \
#
diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c
index 3d9d2cd7764b..192d5fcb7a74 100644
--- a/tools/testing/selftests/bpf/bench.c
+++ b/tools/testing/selftests/bpf/bench.c
@@ -287,6 +287,7 @@ extern struct argp bench_crypto_argp;
extern struct argp bench_sockmap_argp;
extern struct argp bench_lpm_trie_map_argp;
extern struct argp bench_xdp_lb_argp;
+extern struct argp bench_arraymap_mmap_argp;
static const struct argp_child bench_parsers[] = {
{ &bench_ringbufs_argp, 0, "Ring buffers benchmark", 0 },
@@ -304,6 +305,7 @@ static const struct argp_child bench_parsers[] = {
{ &bench_sockmap_argp, 0, "bpf sockmap benchmark", 0 },
{ &bench_lpm_trie_map_argp, 0, "LPM trie map benchmark", 0 },
{ &bench_xdp_lb_argp, 0, "XDP load-balancer benchmark", 0 },
+ { &bench_arraymap_mmap_argp, 0, "arraymap-mmap benchmark", 0 },
{},
};
@@ -582,6 +584,7 @@ extern const struct bench bench_lpm_trie_delete;
extern const struct bench bench_lpm_trie_free;
extern const struct bench bench_bpf_nop;
extern const struct bench bench_xdp_lb;
+extern const struct bench bench_arraymap_mmap;
static const struct bench *benchs[] = {
&bench_count_global,
@@ -665,6 +668,7 @@ static const struct bench *benchs[] = {
&bench_lpm_trie_free,
&bench_bpf_nop,
&bench_xdp_lb,
+ &bench_arraymap_mmap,
};
static void find_benchmark(void)
diff --git a/tools/testing/selftests/bpf/benchs/bench_arraymap_mmap.c b/tools/testing/selftests/bpf/benchs/bench_arraymap_mmap.c
new file mode 100644
index 000000000000..d7c7615e2183
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/bench_arraymap_mmap.c
@@ -0,0 +1,127 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 Meta Platforms, Inc. */
+#include <argp.h>
+#include <sys/mman.h>
+#include "bench.h"
+
+/* Benchmark mmap()/munmap() of an mmap-able BPF array map from N threads. */
+
+static struct ctx {
+ int map_fd;
+ size_t mmap_sz;
+} ctx;
+
+static struct {
+ __u64 map_size;
+} args = {
+ .map_size = 8 * 1024 * 1024, /* 8 MiB */
+};
+
+enum {
+ ARG_MAP_SIZE = 5000,
+};
+
+static const struct argp_option opts[] = {
+ { "map-size", ARG_MAP_SIZE, "BYTES", 0,
+ "Size of the BPF array map in bytes (default 8388608)" },
+ {},
+};
+
+static error_t parse_arg(int key, char *arg, struct argp_state *state)
+{
+ switch (key) {
+ case ARG_MAP_SIZE:
+ args.map_size = strtoull(arg, NULL, 0);
+ if (args.map_size == 0) {
+ fprintf(stderr, "Invalid map-size: %s\n", arg);
+ argp_usage(state);
+ }
+ break;
+ default:
+ return ARGP_ERR_UNKNOWN;
+ }
+
+ return 0;
+}
+
+/* exported into benchmark runner */
+const struct argp bench_arraymap_mmap_argp = {
+ .options = opts,
+ .parser = parse_arg,
+};
+
+static void validate(void)
+{
+ if (env.consumer_cnt != 0) {
+ fprintf(stderr, "benchmark doesn't support consumer!\n");
+ exit(1);
+ }
+}
+
+static long hits;
+
+static void *producer(void *input)
+{
+ while (true) {
+ void *addr;
+
+ addr = mmap(NULL, ctx.mmap_sz, PROT_READ | PROT_WRITE,
+ MAP_SHARED, ctx.map_fd, 0);
+ if (addr == MAP_FAILED) {
+ fprintf(stderr, "mmap failed: %d\n", -errno);
+ exit(1);
+ }
+ if (munmap(addr, ctx.mmap_sz)) {
+ fprintf(stderr, "munmap failed: %d\n", -errno);
+ exit(1);
+ }
+ atomic_inc(&hits);
+ }
+
+ return NULL;
+}
+
+static void measure(struct bench_res *res)
+{
+ res->hits = atomic_swap(&hits, 0);
+}
+
+static void setup(void)
+{
+ LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_MMAPABLE);
+ long page_sz = sysconf(_SC_PAGESIZE);
+ __u32 value_size = sizeof(__u64);
+ __u32 max_entries;
+
+ setup_libbpf();
+
+ /*
+ * mmap-able array maps round the value size up to 8 bytes and expose
+ * PAGE_ALIGN(max_entries * elem_size) bytes to user space.
+ */
+ max_entries = (args.map_size + value_size - 1) / value_size;
+ ctx.mmap_sz = ((__u64)max_entries * value_size + page_sz - 1) &
+ ~(page_sz - 1);
+
+ ctx.map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "mmap_array",
+ sizeof(__u32), value_size, max_entries,
+ &opts);
+ if (ctx.map_fd < 0) {
+ fprintf(stderr, "failed to create map: %d\n", -errno);
+ exit(1);
+ }
+
+ printf("array map: %u entries, mmap size %zu bytes, %d threads\n",
+ max_entries, ctx.mmap_sz, env.producer_cnt);
+}
+
+const struct bench bench_arraymap_mmap = {
+ .name = "arraymap-mmap",
+ .argp = &bench_arraymap_mmap_argp,
+ .validate = validate,
+ .setup = setup,
+ .producer_thread = producer,
+ .measure = measure,
+ .report_progress = ops_report_progress,
+ .report_final = ops_report_final,
+};
diff --git a/tools/testing/selftests/bpf/benchs/run_bench_arraymap_mmap.sh b/tools/testing/selftests/bpf/benchs/run_bench_arraymap_mmap.sh
new file mode 100755
index 000000000000..22c569311137
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/run_bench_arraymap_mmap.sh
@@ -0,0 +1,15 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source ./benchs/run_common.sh
+
+set -eufo pipefail
+
+for t in 1 4 8 16; do
+for s in 1048576 8388608 67108864; do
+subtitle "nr_threads: $t, map_size: $s"
+ summarize_ops "arraymap-mmap: " \
+ "$($RUN_BENCH -p $t --map-size $s arraymap-mmap)"
+ printf "\n"
+done
+done
--
2.53.0-Meta
^ permalink raw reply related [flat|nested] 3+ messages in thread