Merge branch 'bpf-add-a-generic-bits-iterator'

Yafang Shao says:

====================
bpf: Add a generic bits iterator

Three new kfuncs, namely bpf_iter_bits_{new,next,destroy}, have been
added for the new bpf_iter_bits functionality. These kfuncs enable the
iteration of the bits from a given address and a given number of bits.

- bpf_iter_bits_new
  Initialize a new bits iterator for a given memory area. Due to the
  limitation of bpf memalloc, the max number of bits to be iterated
  over is (4096 * 8).
- bpf_iter_bits_next
  Get the next bit in a bpf_iter_bits
- bpf_iter_bits_destroy
  Destroy a bpf_iter_bits

The bits iterator can be used in any context and on any address.

Changes:
- v7->v8:
  Refine the interface to avoid dealing with endianness (Andrii)
- v6->v7:
  Fix endianness error for non-long-aligned data (Andrii)
- v5->v6:
  Add positive tests (Andrii)
- v4->v5:
  Simplify test cases (Andrii)
- v3->v4:
  - Fix endianness error on s390x (Andrii)
  - zero-initialize kit->bits_copy and zero out nr_bits (Andrii)
- v2->v3:
  Optimization for u64/u32 mask (Andrii)
- v1->v2:
  Simplify the CPU number verification code to avoid the failure on s390x
  (Eduard)
- bpf: Add bpf_iter_cpumask
  https://lwn.net/Articles/961104/
- bpf: Add new bpf helper bpf_for_each_cpu
  https://lwn.net/Articles/939939/
====================

Link: https://lore.kernel.org/r/20240517023034.48138-1-laoar.shao@gmail.com
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>

kernel/bpf/helpers.c

@@ -2744,6 +2744,122 @@ __bpf_kfunc void bpf_preempt_enable(void)
 	preempt_enable();
 }
 
+struct bpf_iter_bits {
+	__u64 __opaque[2];
+} __aligned(8);
+
+struct bpf_iter_bits_kern {
+	union {
+		unsigned long *bits;
+		unsigned long bits_copy;
+	};
+	u32 nr_bits;
+	int bit;
+} __aligned(8);
+
+/**
+ * bpf_iter_bits_new() - Initialize a new bits iterator for a given memory area
+ * @it: The new bpf_iter_bits to be created
+ * @unsafe_ptr__ign: A pointer pointing to a memory area to be iterated over
+ * @nr_words: The size of the specified memory area, measured in 8-byte units.
+ * Due to the limitation of memalloc, it can't be greater than 512.
+ *
+ * This function initializes a new bpf_iter_bits structure for iterating over
+ * a memory area which is specified by the @unsafe_ptr__ign and @nr_words. It
+ * copies the data of the memory area to the newly created bpf_iter_bits @it for
+ * subsequent iteration operations.
+ *
+ * On success, 0 is returned. On failure, ERR is returned.
+ */
+__bpf_kfunc int
+bpf_iter_bits_new(struct bpf_iter_bits *it, const u64 *unsafe_ptr__ign, u32 nr_words)
+{
+	struct bpf_iter_bits_kern *kit = (void *)it;
+	u32 nr_bytes = nr_words * sizeof(u64);
+	u32 nr_bits = BYTES_TO_BITS(nr_bytes);
+	int err;
+
+	BUILD_BUG_ON(sizeof(struct bpf_iter_bits_kern) != sizeof(struct bpf_iter_bits));
+	BUILD_BUG_ON(__alignof__(struct bpf_iter_bits_kern) !=
+		     __alignof__(struct bpf_iter_bits));
+
+	kit->nr_bits = 0;
+	kit->bits_copy = 0;
+	kit->bit = -1;
+
+	if (!unsafe_ptr__ign || !nr_words)
+		return -EINVAL;
+
+	/* Optimization for u64 mask */
+	if (nr_bits == 64) {
+		err = bpf_probe_read_kernel_common(&kit->bits_copy, nr_bytes, unsafe_ptr__ign);
+		if (err)
+			return -EFAULT;
+
+		kit->nr_bits = nr_bits;
+		return 0;
+	}
+
+	/* Fallback to memalloc */
+	kit->bits = bpf_mem_alloc(&bpf_global_ma, nr_bytes);
+	if (!kit->bits)
+		return -ENOMEM;
+
+	err = bpf_probe_read_kernel_common(kit->bits, nr_bytes, unsafe_ptr__ign);
+	if (err) {
+		bpf_mem_free(&bpf_global_ma, kit->bits);
+		return err;
+	}
+
+	kit->nr_bits = nr_bits;
+	return 0;
+}
+
+/**
+ * bpf_iter_bits_next() - Get the next bit in a bpf_iter_bits
+ * @it: The bpf_iter_bits to be checked
+ *
+ * This function returns a pointer to a number representing the value of the
+ * next bit in the bits.
+ *
+ * If there are no further bits available, it returns NULL.
+ */
+__bpf_kfunc int *bpf_iter_bits_next(struct bpf_iter_bits *it)
+{
+	struct bpf_iter_bits_kern *kit = (void *)it;
+	u32 nr_bits = kit->nr_bits;
+	const unsigned long *bits;
+	int bit;
+
+	if (nr_bits == 0)
+		return NULL;
+
+	bits = nr_bits == 64 ? &kit->bits_copy : kit->bits;
+	bit = find_next_bit(bits, nr_bits, kit->bit + 1);
+	if (bit >= nr_bits) {
+		kit->nr_bits = 0;
+		return NULL;
+	}
+
+	kit->bit = bit;
+	return &kit->bit;
+}
+
+/**
+ * bpf_iter_bits_destroy() - Destroy a bpf_iter_bits
+ * @it: The bpf_iter_bits to be destroyed
+ *
+ * Destroy the resource associated with the bpf_iter_bits.
+ */
+__bpf_kfunc void bpf_iter_bits_destroy(struct bpf_iter_bits *it)
+{
+	struct bpf_iter_bits_kern *kit = (void *)it;
+
+	if (kit->nr_bits <= 64)
+		return;
+	bpf_mem_free(&bpf_global_ma, kit->bits);
+}
+
 __bpf_kfunc_end_defs();
 
 BTF_KFUNCS_START(generic_btf_ids)
@@ -2826,6 +2942,9 @@ BTF_ID_FLAGS(func, bpf_wq_set_callback_impl)
 BTF_ID_FLAGS(func, bpf_wq_start)
 BTF_ID_FLAGS(func, bpf_preempt_disable)
 BTF_ID_FLAGS(func, bpf_preempt_enable)
+BTF_ID_FLAGS(func, bpf_iter_bits_new, KF_ITER_NEW)
+BTF_ID_FLAGS(func, bpf_iter_bits_next, KF_ITER_NEXT | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_iter_bits_destroy, KF_ITER_DESTROY)
 BTF_KFUNCS_END(common_btf_ids)
 
 static const struct btf_kfunc_id_set common_kfunc_set = {

tools/testing/selftests/bpf/prog_tests/verifier.c

@@ -85,6 +85,7 @@
 #include "verifier_xadd.skel.h"
 #include "verifier_xdp.skel.h"
 #include "verifier_xdp_direct_packet_access.skel.h"
+#include "verifier_bits_iter.skel.h"
 
 #define MAX_ENTRIES 11
 
@@ -200,6 +201,7 @@ void test_verifier_var_off(void)              { RUN(verifier_var_off); }
 void test_verifier_xadd(void)                 { RUN(verifier_xadd); }
 void test_verifier_xdp(void)                  { RUN(verifier_xdp); }
 void test_verifier_xdp_direct_packet_access(void) { RUN(verifier_xdp_direct_packet_access); }
+void test_verifier_bits_iter(void) { RUN(verifier_bits_iter); }
 
 static int init_test_val_map(struct bpf_object *obj, char *map_name)
 {

tools/testing/selftests/bpf/progs/verifier_bits_iter.c

@@ -0,0 +1,153 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2024 Yafang Shao <laoar.shao@gmail.com> */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#include "bpf_misc.h"
+#include "task_kfunc_common.h"
+
+char _license[] SEC("license") = "GPL";
+
+int bpf_iter_bits_new(struct bpf_iter_bits *it, const u64 *unsafe_ptr__ign,
+		      u32 nr_bits) __ksym __weak;
+int *bpf_iter_bits_next(struct bpf_iter_bits *it) __ksym __weak;
+void bpf_iter_bits_destroy(struct bpf_iter_bits *it) __ksym __weak;
+
+SEC("iter.s/cgroup")
+__description("bits iter without destroy")
+__failure __msg("Unreleased reference")
+int BPF_PROG(no_destroy, struct bpf_iter_meta *meta, struct cgroup *cgrp)
+{
+	struct bpf_iter_bits it;
+	u64 data = 1;
+
+	bpf_iter_bits_new(&it, &data, 1);
+	bpf_iter_bits_next(&it);
+	return 0;
+}
+
+SEC("iter/cgroup")
+__description("uninitialized iter in ->next()")
+__failure __msg("expected an initialized iter_bits as arg #1")
+int BPF_PROG(next_uninit, struct bpf_iter_meta *meta, struct cgroup *cgrp)
+{
+	struct bpf_iter_bits *it = NULL;
+
+	bpf_iter_bits_next(it);
+	return 0;
+}
+
+SEC("iter/cgroup")
+__description("uninitialized iter in ->destroy()")
+__failure __msg("expected an initialized iter_bits as arg #1")
+int BPF_PROG(destroy_uninit, struct bpf_iter_meta *meta, struct cgroup *cgrp)
+{
+	struct bpf_iter_bits it = {};
+
+	bpf_iter_bits_destroy(&it);
+	return 0;
+}
+
+SEC("syscall")
+__description("null pointer")
+__success __retval(0)
+int null_pointer(void)
+{
+	int nr = 0;
+	int *bit;
+
+	bpf_for_each(bits, bit, NULL, 1)
+		nr++;
+	return nr;
+}
+
+SEC("syscall")
+__description("bits copy")
+__success __retval(10)
+int bits_copy(void)
+{
+	u64 data = 0xf7310UL; /* 4 + 3 + 2 + 1 + 0*/
+	int nr = 0;
+	int *bit;
+
+	bpf_for_each(bits, bit, &data, 1)
+		nr++;
+	return nr;
+}
+
+SEC("syscall")
+__description("bits memalloc")
+__success __retval(64)
+int bits_memalloc(void)
+{
+	u64 data[2];
+	int nr = 0;
+	int *bit;
+
+	__builtin_memset(&data, 0xf0, sizeof(data)); /* 4 * 16 */
+	bpf_for_each(bits, bit, &data[0], sizeof(data) / sizeof(u64))
+		nr++;
+	return nr;
+}
+
+SEC("syscall")
+__description("bit index")
+__success __retval(8)
+int bit_index(void)
+{
+	u64 data = 0x100;
+	int bit_idx = 0;
+	int *bit;
+
+	bpf_for_each(bits, bit, &data, 1) {
+		if (*bit == 0)
+			continue;
+		bit_idx = *bit;
+	}
+	return bit_idx;
+}
+
+SEC("syscall")
+__description("bits nomem")
+__success __retval(0)
+int bits_nomem(void)
+{
+	u64 data[4];
+	int nr = 0;
+	int *bit;
+
+	__builtin_memset(&data, 0xff, sizeof(data));
+	bpf_for_each(bits, bit, &data[0], 513) /* Be greater than 512 */
+		nr++;
+	return nr;
+}
+
+SEC("syscall")
+__description("fewer words")
+__success __retval(1)
+int fewer_words(void)
+{
+	u64 data[2] = {0x1, 0xff};
+	int nr = 0;
+	int *bit;
+
+	bpf_for_each(bits, bit, &data[0], 1)
+		nr++;
+	return nr;
+}
+
+SEC("syscall")
+__description("zero words")
+__success __retval(0)
+int zero_words(void)
+{
+	u64 data[2] = {0x1, 0xff};
+	int nr = 0;
+	int *bit;
+
+	bpf_for_each(bits, bit, &data[0], 0)
+		nr++;
+	return nr;
+}