diff mbox series

[v4,bpf-next,3/6] bpf: populate the per-cpu insertions/deletions counters for hashmaps

Message ID 20230705160139.19967-4-aspsk@isovalent.com (mailing list archive)
State Superseded
Delegated to: BPF
Headers show
Series bpf: add percpu stats for bpf_map | expand

Checks

Context Check Description
bpf/vmtest-bpf-next-PR success PR summary
bpf/vmtest-bpf-next-VM_Test-30 success Logs for test_verifier on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-31 success Logs for veristat
bpf/vmtest-bpf-next-VM_Test-1 success Logs for ShellCheck
bpf/vmtest-bpf-next-VM_Test-4 success Logs for build for x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-5 success Logs for build for x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-6 success Logs for set-matrix
bpf/vmtest-bpf-next-VM_Test-2 success Logs for build for aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-3 success Logs for build for s390x with gcc
bpf/vmtest-bpf-next-VM_Test-7 success Logs for test_maps on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-9 success Logs for test_maps on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-10 success Logs for test_maps on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-17 success Logs for test_progs_no_alu32 on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-18 success Logs for test_progs_no_alu32 on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-19 success Logs for test_progs_no_alu32_parallel on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-20 success Logs for test_progs_no_alu32_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-21 success Logs for test_progs_no_alu32_parallel on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-22 success Logs for test_progs_parallel on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-23 success Logs for test_progs_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-24 success Logs for test_progs_parallel on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-25 success Logs for test_verifier on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-26 success Logs for test_verifier on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-27 success Logs for test_verifier on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-28 success Logs for test_verifier on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-29 success Logs for veristat
bpf/vmtest-bpf-next-VM_Test-11 success Logs for test_progs on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-13 success Logs for test_progs on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-14 success Logs for test_progs on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-15 success Logs for test_progs_no_alu32 on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-16 success Logs for test_progs_no_alu32 on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-12 success Logs for test_progs on s390x with gcc
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for bpf-next, async
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 20 this patch: 20
netdev/cc_maintainers success CCed 12 of 12 maintainers
netdev/build_clang fail Errors and warnings before: 18 this patch: 18
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 20 this patch: 20
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 87 lines checked
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0
bpf/vmtest-bpf-next-VM_Test-8 success Logs for test_maps on s390x with gcc

Commit Message

Anton Protopopov July 5, 2023, 4:01 p.m. UTC
Initialize and utilize the per-cpu insertions/deletions counters for hash-based
maps. Non-trivial changes apply to preallocated maps for which the
{inc,dec}_elem_count functions are not called, as there's no need in counting
elements to sustain proper map operations.

To increase/decrease percpu counters for preallocated hash maps we add raw
calls to the bpf_map_{inc,dec}_elem_count functions so that the impact is
minimal. For dynamically allocated maps we add corresponding calls to the
existing {inc,dec}_elem_count functions.

For LRU maps bpf_map_{inc,dec}_elem_count added to the lru pop/free helpers.

Signed-off-by: Anton Protopopov <aspsk@isovalent.com>
---
 kernel/bpf/hashtab.c | 23 +++++++++++++++++++++--
 1 file changed, 21 insertions(+), 2 deletions(-)

Comments

Alexei Starovoitov July 6, 2023, 1:24 a.m. UTC | #1
On Wed, Jul 5, 2023 at 9:00 AM Anton Protopopov <aspsk@isovalent.com> wrote:
>
> Initialize and utilize the per-cpu insertions/deletions counters for hash-based
> maps. Non-trivial changes apply to preallocated maps for which the
> {inc,dec}_elem_count functions are not called, as there's no need in counting
> elements to sustain proper map operations.
>
> To increase/decrease percpu counters for preallocated hash maps we add raw
> calls to the bpf_map_{inc,dec}_elem_count functions so that the impact is
> minimal. For dynamically allocated maps we add corresponding calls to the
> existing {inc,dec}_elem_count functions.
>
> For LRU maps bpf_map_{inc,dec}_elem_count added to the lru pop/free helpers.
>
> Signed-off-by: Anton Protopopov <aspsk@isovalent.com>
> ---
>  kernel/bpf/hashtab.c | 23 +++++++++++++++++++++--
>  1 file changed, 21 insertions(+), 2 deletions(-)
>
> diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
> index 56d3da7d0bc6..c23557bf9a1a 100644
> --- a/kernel/bpf/hashtab.c
> +++ b/kernel/bpf/hashtab.c
> @@ -302,6 +302,7 @@ static struct htab_elem *prealloc_lru_pop(struct bpf_htab *htab, void *key,
>         struct htab_elem *l;
>
>         if (node) {
> +               bpf_map_inc_elem_count(&htab->map);
>                 l = container_of(node, struct htab_elem, lru_node);
>                 memcpy(l->key, key, htab->map.key_size);
>                 return l;
> @@ -581,10 +582,17 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
>                 }
>         }
>
> +       err = bpf_map_init_elem_count(&htab->map);
> +       if (err)
> +               goto free_extra_elements;
> +
>         return &htab->map;
>
> +free_extra_elements:
> +       free_percpu(htab->extra_elems);
>  free_prealloc:
> -       prealloc_destroy(htab);
> +       if (prealloc)
> +               prealloc_destroy(htab);

This is a bit difficult to read.
I think the logic would be easier to understand if bpf_map_init_elem_count
was done right before htab->buckets = bpf_map_area_alloc()
and if (err) goto free_htab
where you would add bpf_map_free_elem_count.
Anton Protopopov July 6, 2023, 5:47 a.m. UTC | #2
On Wed, Jul 05, 2023 at 06:24:44PM -0700, Alexei Starovoitov wrote:
> On Wed, Jul 5, 2023 at 9:00 AM Anton Protopopov <aspsk@isovalent.com> wrote:
> >
> > Initialize and utilize the per-cpu insertions/deletions counters for hash-based
> > maps. Non-trivial changes apply to preallocated maps for which the
> > {inc,dec}_elem_count functions are not called, as there's no need in counting
> > elements to sustain proper map operations.
> >
> > To increase/decrease percpu counters for preallocated hash maps we add raw
> > calls to the bpf_map_{inc,dec}_elem_count functions so that the impact is
> > minimal. For dynamically allocated maps we add corresponding calls to the
> > existing {inc,dec}_elem_count functions.
> >
> > For LRU maps bpf_map_{inc,dec}_elem_count added to the lru pop/free helpers.
> >
> > Signed-off-by: Anton Protopopov <aspsk@isovalent.com>
> > ---
> >  kernel/bpf/hashtab.c | 23 +++++++++++++++++++++--
> >  1 file changed, 21 insertions(+), 2 deletions(-)
> >
> > diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
> > index 56d3da7d0bc6..c23557bf9a1a 100644
> > --- a/kernel/bpf/hashtab.c
> > +++ b/kernel/bpf/hashtab.c
> > @@ -302,6 +302,7 @@ static struct htab_elem *prealloc_lru_pop(struct bpf_htab *htab, void *key,
> >         struct htab_elem *l;
> >
> >         if (node) {
> > +               bpf_map_inc_elem_count(&htab->map);
> >                 l = container_of(node, struct htab_elem, lru_node);
> >                 memcpy(l->key, key, htab->map.key_size);
> >                 return l;
> > @@ -581,10 +582,17 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
> >                 }
> >         }
> >
> > +       err = bpf_map_init_elem_count(&htab->map);
> > +       if (err)
> > +               goto free_extra_elements;
> > +
> >         return &htab->map;
> >
> > +free_extra_elements:
> > +       free_percpu(htab->extra_elems);
> >  free_prealloc:
> > -       prealloc_destroy(htab);
> > +       if (prealloc)
> > +               prealloc_destroy(htab);
> 
> This is a bit difficult to read.
> I think the logic would be easier to understand if bpf_map_init_elem_count
> was done right before htab->buckets = bpf_map_area_alloc()
> and if (err) goto free_htab
> where you would add bpf_map_free_elem_count.

Thanks, I will fix this.
diff mbox series

Patch

diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 56d3da7d0bc6..c23557bf9a1a 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -302,6 +302,7 @@  static struct htab_elem *prealloc_lru_pop(struct bpf_htab *htab, void *key,
 	struct htab_elem *l;
 
 	if (node) {
+		bpf_map_inc_elem_count(&htab->map);
 		l = container_of(node, struct htab_elem, lru_node);
 		memcpy(l->key, key, htab->map.key_size);
 		return l;
@@ -581,10 +582,17 @@  static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 		}
 	}
 
+	err = bpf_map_init_elem_count(&htab->map);
+	if (err)
+		goto free_extra_elements;
+
 	return &htab->map;
 
+free_extra_elements:
+	free_percpu(htab->extra_elems);
 free_prealloc:
-	prealloc_destroy(htab);
+	if (prealloc)
+		prealloc_destroy(htab);
 free_map_locked:
 	if (htab->use_percpu_counter)
 		percpu_counter_destroy(&htab->pcount);
@@ -804,6 +812,7 @@  static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node)
 		if (l == tgt_l) {
 			hlist_nulls_del_rcu(&l->hash_node);
 			check_and_free_fields(htab, l);
+			bpf_map_dec_elem_count(&htab->map);
 			break;
 		}
 
@@ -900,6 +909,8 @@  static bool is_map_full(struct bpf_htab *htab)
 
 static void inc_elem_count(struct bpf_htab *htab)
 {
+	bpf_map_inc_elem_count(&htab->map);
+
 	if (htab->use_percpu_counter)
 		percpu_counter_add_batch(&htab->pcount, 1, PERCPU_COUNTER_BATCH);
 	else
@@ -908,6 +919,8 @@  static void inc_elem_count(struct bpf_htab *htab)
 
 static void dec_elem_count(struct bpf_htab *htab)
 {
+	bpf_map_dec_elem_count(&htab->map);
+
 	if (htab->use_percpu_counter)
 		percpu_counter_add_batch(&htab->pcount, -1, PERCPU_COUNTER_BATCH);
 	else
@@ -920,6 +933,7 @@  static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
 	htab_put_fd_value(htab, l);
 
 	if (htab_is_prealloc(htab)) {
+		bpf_map_dec_elem_count(&htab->map);
 		check_and_free_fields(htab, l);
 		__pcpu_freelist_push(&htab->freelist, &l->fnode);
 	} else {
@@ -1000,6 +1014,7 @@  static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 			if (!l)
 				return ERR_PTR(-E2BIG);
 			l_new = container_of(l, struct htab_elem, fnode);
+			bpf_map_inc_elem_count(&htab->map);
 		}
 	} else {
 		if (is_map_full(htab))
@@ -1168,6 +1183,7 @@  static long htab_map_update_elem(struct bpf_map *map, void *key, void *value,
 static void htab_lru_push_free(struct bpf_htab *htab, struct htab_elem *elem)
 {
 	check_and_free_fields(htab, elem);
+	bpf_map_dec_elem_count(&htab->map);
 	bpf_lru_push_free(&htab->lru, &elem->lru_node);
 }
 
@@ -1357,8 +1373,10 @@  static long __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
 err:
 	htab_unlock_bucket(htab, b, hash, flags);
 err_lock_bucket:
-	if (l_new)
+	if (l_new) {
+		bpf_map_dec_elem_count(&htab->map);
 		bpf_lru_push_free(&htab->lru, &l_new->lru_node);
+	}
 	return ret;
 }
 
@@ -1523,6 +1541,7 @@  static void htab_map_free(struct bpf_map *map)
 		prealloc_destroy(htab);
 	}
 
+	bpf_map_free_elem_count(map);
 	free_percpu(htab->extra_elems);
 	bpf_map_area_free(htab->buckets);
 	bpf_mem_alloc_destroy(&htab->pcpu_ma);