From: Alexei Starovoitov <alexei.starovoitov@gmail.com>
To: davem@davemloft.net
Cc: daniel@iogearbox.net, andrii@kernel.org, tj@kernel.org,
memxor@gmail.com, delyank@fb.com, linux-mm@kvack.org,
bpf@vger.kernel.org, kernel-team@fb.com
Subject: [PATCH v3 bpf-next 11/15] bpf: Convert percpu hash map to per-cpu bpf_mem_alloc.
Date: Fri, 19 Aug 2022 14:42:28 -0700 [thread overview]
Message-ID: <20220819214232.18784-12-alexei.starovoitov@gmail.com> (raw)
In-Reply-To: <20220819214232.18784-1-alexei.starovoitov@gmail.com>
From: Alexei Starovoitov <ast@kernel.org>
Convert dynamic allocations in percpu hash map from alloc_percpu() to
bpf_mem_cache_alloc() from per-cpu bpf_mem_alloc. Since bpf_mem_alloc frees
objects after RCU gp the call_rcu() is removed. pcpu_init_value() now needs to
zero-fill per-cpu allocations, since dynamically allocated map elements are now
similar to full prealloc, since alloc_percpu() is not called inline and the
elements are reused in the freelist.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
kernel/bpf/hashtab.c | 45 +++++++++++++++++++-------------------------
1 file changed, 19 insertions(+), 26 deletions(-)
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 8daa1132d43c..89f26cbddef5 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -94,6 +94,7 @@ struct bucket {
struct bpf_htab {
struct bpf_map map;
struct bpf_mem_alloc ma;
+ struct bpf_mem_alloc pcpu_ma;
struct bucket *buckets;
void *elems;
union {
@@ -121,14 +122,14 @@ struct htab_elem {
struct {
void *padding;
union {
- struct bpf_htab *htab;
struct pcpu_freelist_node fnode;
struct htab_elem *batch_flink;
};
};
};
union {
- struct rcu_head rcu;
+ /* pointer to per-cpu pointer */
+ void *ptr_to_pptr;
struct bpf_lru_node lru_node;
};
u32 hash;
@@ -435,8 +436,6 @@ static int htab_map_alloc_check(union bpf_attr *attr)
bool zero_seed = (attr->map_flags & BPF_F_ZERO_SEED);
int numa_node = bpf_map_attr_numa_node(attr);
- BUILD_BUG_ON(offsetof(struct htab_elem, htab) !=
- offsetof(struct htab_elem, hash_node.pprev));
BUILD_BUG_ON(offsetof(struct htab_elem, fnode.next) !=
offsetof(struct htab_elem, hash_node.pprev));
@@ -597,6 +596,12 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
err = bpf_mem_alloc_init(&htab->ma, htab->elem_size, false);
if (err)
goto free_map_locked;
+ if (percpu) {
+ err = bpf_mem_alloc_init(&htab->pcpu_ma,
+ round_up(htab->map.value_size, 8), true);
+ if (err)
+ goto free_map_locked;
+ }
}
return &htab->map;
@@ -607,6 +612,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++)
free_percpu(htab->map_locked[i]);
bpf_map_area_free(htab->buckets);
+ bpf_mem_alloc_destroy(&htab->pcpu_ma);
bpf_mem_alloc_destroy(&htab->ma);
free_htab:
lockdep_unregister_key(&htab->lockdep_key);
@@ -882,19 +888,11 @@ static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
static void htab_elem_free(struct bpf_htab *htab, struct htab_elem *l)
{
if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH)
- free_percpu(htab_elem_get_ptr(l, htab->map.key_size));
+ bpf_mem_cache_free(&htab->pcpu_ma, l->ptr_to_pptr);
check_and_free_fields(htab, l);
bpf_mem_cache_free(&htab->ma, l);
}
-static void htab_elem_free_rcu(struct rcu_head *head)
-{
- struct htab_elem *l = container_of(head, struct htab_elem, rcu);
- struct bpf_htab *htab = l->htab;
-
- htab_elem_free(htab, l);
-}
-
static void htab_put_fd_value(struct bpf_htab *htab, struct htab_elem *l)
{
struct bpf_map *map = &htab->map;
@@ -940,12 +938,7 @@ static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
__pcpu_freelist_push(&htab->freelist, &l->fnode);
} else {
dec_elem_count(htab);
- if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH) {
- l->htab = htab;
- call_rcu(&l->rcu, htab_elem_free_rcu);
- } else {
- htab_elem_free(htab, l);
- }
+ htab_elem_free(htab, l);
}
}
@@ -970,13 +963,12 @@ static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr,
static void pcpu_init_value(struct bpf_htab *htab, void __percpu *pptr,
void *value, bool onallcpus)
{
- /* When using prealloc and not setting the initial value on all cpus,
- * zero-fill element values for other cpus (just as what happens when
- * not using prealloc). Otherwise, bpf program has no way to ensure
+ /* When not setting the initial value on all cpus, zero-fill element
+ * values for other cpus. Otherwise, bpf program has no way to ensure
* known initial values for cpus other than current one
* (onallcpus=false always when coming from bpf prog).
*/
- if (htab_is_prealloc(htab) && !onallcpus) {
+ if (!onallcpus) {
u32 size = round_up(htab->map.value_size, 8);
int current_cpu = raw_smp_processor_id();
int cpu;
@@ -1047,18 +1039,18 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
memcpy(l_new->key, key, key_size);
if (percpu) {
- size = round_up(size, 8);
if (prealloc) {
pptr = htab_elem_get_ptr(l_new, key_size);
} else {
/* alloc_percpu zero-fills */
- pptr = bpf_map_alloc_percpu(&htab->map, size, 8,
- GFP_NOWAIT | __GFP_NOWARN);
+ pptr = bpf_mem_cache_alloc(&htab->pcpu_ma);
if (!pptr) {
bpf_mem_cache_free(&htab->ma, l_new);
l_new = ERR_PTR(-ENOMEM);
goto dec_count;
}
+ l_new->ptr_to_pptr = pptr;
+ pptr = *(void **)pptr;
}
pcpu_init_value(htab, pptr, value, onallcpus);
@@ -1550,6 +1542,7 @@ static void htab_map_free(struct bpf_map *map)
bpf_map_free_kptr_off_tab(map);
free_percpu(htab->extra_elems);
bpf_map_area_free(htab->buckets);
+ bpf_mem_alloc_destroy(&htab->pcpu_ma);
bpf_mem_alloc_destroy(&htab->ma);
if (htab->use_percpu_counter)
percpu_counter_destroy(&htab->pcount);
--
2.30.2
next prev parent reply other threads:[~2022-08-19 21:43 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-08-19 21:42 [PATCH v3 bpf-next 00/15] bpf: BPF specific memory allocator Alexei Starovoitov
2022-08-19 21:42 ` [PATCH v3 bpf-next 01/15] bpf: Introduce any context " Alexei Starovoitov
2022-08-19 21:42 ` [PATCH v3 bpf-next 02/15] bpf: Convert hash map to bpf_mem_alloc Alexei Starovoitov
2022-08-19 21:42 ` [PATCH v3 bpf-next 03/15] selftests/bpf: Improve test coverage of test_maps Alexei Starovoitov
2022-08-19 21:42 ` [PATCH v3 bpf-next 04/15] samples/bpf: Reduce syscall overhead in map_perf_test Alexei Starovoitov
2022-08-19 21:42 ` [PATCH v3 bpf-next 05/15] bpf: Relax the requirement to use preallocated hash maps in tracing progs Alexei Starovoitov
2022-08-19 21:42 ` [PATCH v3 bpf-next 06/15] bpf: Optimize element count in non-preallocated hash map Alexei Starovoitov
2022-08-19 21:42 ` [PATCH v3 bpf-next 07/15] bpf: Optimize call_rcu " Alexei Starovoitov
2022-08-19 21:42 ` [PATCH v3 bpf-next 08/15] bpf: Adjust low/high watermarks in bpf_mem_cache Alexei Starovoitov
2022-08-19 21:42 ` [PATCH v3 bpf-next 09/15] bpf: Batch call_rcu callbacks instead of SLAB_TYPESAFE_BY_RCU Alexei Starovoitov
2022-08-24 19:58 ` Kumar Kartikeya Dwivedi
2022-08-25 0:13 ` Alexei Starovoitov
2022-08-25 0:35 ` Joel Fernandes
2022-08-25 0:49 ` Joel Fernandes
2022-08-19 21:42 ` [PATCH v3 bpf-next 10/15] bpf: Add percpu allocation support to bpf_mem_alloc Alexei Starovoitov
2022-08-19 21:42 ` Alexei Starovoitov [this message]
2022-08-19 21:42 ` [PATCH v3 bpf-next 12/15] bpf: Remove tracing program restriction on map types Alexei Starovoitov
2022-08-19 21:42 ` [PATCH v3 bpf-next 13/15] bpf: Prepare bpf_mem_alloc to be used by sleepable bpf programs Alexei Starovoitov
2022-08-19 22:21 ` Kumar Kartikeya Dwivedi
2022-08-19 22:43 ` Alexei Starovoitov
2022-08-19 22:56 ` Kumar Kartikeya Dwivedi
2022-08-19 23:01 ` Alexei Starovoitov
2022-08-24 19:49 ` Kumar Kartikeya Dwivedi
2022-08-25 0:08 ` Alexei Starovoitov
2022-08-19 21:42 ` [PATCH v3 bpf-next 14/15] bpf: Remove prealloc-only restriction for " Alexei Starovoitov
2022-08-19 21:42 ` [PATCH v3 bpf-next 15/15] bpf: Introduce sysctl kernel.bpf_force_dyn_alloc Alexei Starovoitov
2022-08-24 20:03 ` [PATCH v3 bpf-next 00/15] bpf: BPF specific memory allocator Kumar Kartikeya Dwivedi
2022-08-25 0:16 ` Alexei Starovoitov
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=20220819214232.18784-12-alexei.starovoitov@gmail.com \
--to=alexei.starovoitov@gmail.com \
--cc=andrii@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=davem@davemloft.net \
--cc=delyank@fb.com \
--cc=kernel-team@fb.com \
--cc=linux-mm@kvack.org \
--cc=memxor@gmail.com \
--cc=tj@kernel.org \
/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