diff mbox series

[v2,bpf-next,06/13] bpf: Optimize moving objects from free_by_rcu_ttrace to waiting_for_gp_ttrace.

Message ID 20230624031333.96597-7-alexei.starovoitov@gmail.com (mailing list archive)
State Superseded
Delegated to: BPF
Headers show
Series bpf: Introduce bpf_mem_cache_free_rcu(). | 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
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for bpf-next
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: 13 this patch: 13
netdev/cc_maintainers warning 8 maintainers not CCed: yhs@fb.com kpsingh@kernel.org martin.lau@linux.dev john.fastabend@gmail.com song@kernel.org sdf@google.com jolsa@kernel.org haoluo@google.com
netdev/build_clang success Errors and warnings before: 8 this patch: 8
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: 13 this patch: 13
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 38 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-9 success Logs for test_maps on x86_64 with gcc
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-15 success Logs for test_progs_no_alu32 on aarch64 with gcc
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-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-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-25 success Logs for test_verifier on aarch64 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-10 success Logs for test_maps on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-14 success Logs for test_progs on x86_64 with llvm-16
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-21 success Logs for test_progs_no_alu32_parallel on x86_64 with llvm-16
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-26 success Logs for test_verifier on s390x 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
bpf/vmtest-bpf-next-VM_Test-1 success Logs for ${{ matrix.test }} on ${{ matrix.arch }} with ${{ matrix.toolchain_full }}
bpf/vmtest-bpf-next-VM_Test-2 success Logs for ShellCheck
bpf/vmtest-bpf-next-VM_Test-3 success Logs for build for aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-4 fail Logs for build for s390x with gcc
bpf/vmtest-bpf-next-VM_Test-5 success Logs for build for x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-6 success Logs for build for x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-7 success Logs for set-matrix
bpf/vmtest-bpf-next-VM_Test-8 success Logs for veristat

Commit Message

Alexei Starovoitov June 24, 2023, 3:13 a.m. UTC 
From: Alexei Starovoitov <ast@kernel.org>

Optimize moving objects from free_by_rcu_ttrace to waiting_for_gp_ttrace
by remembering the tail.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/memalloc.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)
diff mbox series

Patch

diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index b07368d77343..4fd79bd51f5a 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -101,6 +101,7 @@  struct bpf_mem_cache {
 
 	/* list of objects to be freed after RCU tasks trace GP */
 	struct llist_head free_by_rcu_ttrace;
+	struct llist_node *free_by_rcu_ttrace_tail;
 	struct llist_head waiting_for_gp_ttrace;
 	struct rcu_head rcu_ttrace;
 	atomic_t call_rcu_ttrace_in_progress;
@@ -273,24 +274,27 @@  static void enque_to_free(struct bpf_mem_cache *c, void *obj)
 	/* bpf_mem_cache is a per-cpu object. Freeing happens in irq_work.
 	 * Nothing races to add to free_by_rcu_ttrace list.
 	 */
-	__llist_add(llnode, &c->free_by_rcu_ttrace);
+	if (__llist_add(llnode, &c->free_by_rcu_ttrace))
+		c->free_by_rcu_ttrace_tail = llnode;
 }
 
 static void do_call_rcu_ttrace(struct bpf_mem_cache *c)
 {
-	struct llist_node *llnode, *t;
+	struct llist_node *llnode;
 
 	if (atomic_xchg(&c->call_rcu_ttrace_in_progress, 1))
 		return;
 
 	WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp_ttrace));
-	llist_for_each_safe(llnode, t, __llist_del_all(&c->free_by_rcu_ttrace))
+	llnode = __llist_del_all(&c->free_by_rcu_ttrace);
+	if (llnode)
 		/* There is no concurrent __llist_add(waiting_for_gp_ttrace) access.
 		 * It doesn't race with llist_del_all either.
 		 * But there could be two concurrent llist_del_all(waiting_for_gp_ttrace):
 		 * from __free_rcu() and from drain_mem_cache().
 		 */
-		__llist_add(llnode, &c->waiting_for_gp_ttrace);
+		__llist_add_batch(llnode, c->free_by_rcu_ttrace_tail,
+				  &c->waiting_for_gp_ttrace);
 	/* Use call_rcu_tasks_trace() to wait for sleepable progs to finish.
 	 * If RCU Tasks Trace grace period implies RCU grace period, free
 	 * these elements directly, else use call_rcu() to wait for normal