diff mbox series

[bpf-next,v8,4/6] memcg: Use trylock to access memcg stock_lock.

Message ID 20250213033556.9534-5-alexei.starovoitov@gmail.com (mailing list archive)
State Changes Requested
Delegated to: BPF
Headers show
Series bpf, mm: Introduce try_alloc_pages() | expand

Checks

Context Check Description
bpf/vmtest-bpf-next-PR success PR summary
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for bpf-next, async
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
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 fail Errors and warnings before: 0 this patch: 1
netdev/build_tools success No tools touched, skip
netdev/cc_maintainers warning 4 maintainers not CCed: cgroups@vger.kernel.org muchun.song@linux.dev mhocko@kernel.org roman.gushchin@linux.dev
netdev/build_clang fail Errors and warnings before: 4 this patch: 5
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 fail Errors and warnings before: 4 this patch: 5
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 145 lines checked
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc fail Errors and warnings before: 16 this patch: 17
netdev/source_inline success Was 0 now: 0
bpf/vmtest-bpf-next-VM_Test-0 success Logs for Lint
bpf/vmtest-bpf-next-VM_Test-2 success Logs for Unittests
bpf/vmtest-bpf-next-VM_Test-1 success Logs for ShellCheck
bpf/vmtest-bpf-next-VM_Test-3 success Logs for Validate matrix.py
bpf/vmtest-bpf-next-VM_Test-4 success Logs for aarch64-gcc / GCC BPF
bpf/vmtest-bpf-next-VM_Test-5 success Logs for aarch64-gcc / build / build for aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-6 success Logs for aarch64-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-12 success Logs for aarch64-gcc / veristat-meta
bpf/vmtest-bpf-next-VM_Test-11 success Logs for aarch64-gcc / veristat-kernel
bpf/vmtest-bpf-next-VM_Test-7 success Logs for aarch64-gcc / test (test_maps, false, 360) / test_maps on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-10 success Logs for aarch64-gcc / test (test_verifier, false, 360) / test_verifier on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-13 success Logs for s390x-gcc / GCC BPF
bpf/vmtest-bpf-next-VM_Test-14 success Logs for s390x-gcc / build / build for s390x with gcc
bpf/vmtest-bpf-next-VM_Test-15 success Logs for s390x-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-18 success Logs for s390x-gcc / test (test_verifier, false, 360) / test_verifier on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-19 success Logs for s390x-gcc / veristat-kernel
bpf/vmtest-bpf-next-VM_Test-20 success Logs for s390x-gcc / veristat-meta
bpf/vmtest-bpf-next-VM_Test-21 success Logs for set-matrix
bpf/vmtest-bpf-next-VM_Test-23 success Logs for x86_64-gcc / build / build for x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-24 success Logs for x86_64-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-34 success Logs for x86_64-llvm-17 / build / build for x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-35 success Logs for x86_64-llvm-17 / build-release / build for x86_64 with llvm-17-O2
bpf/vmtest-bpf-next-VM_Test-40 success Logs for x86_64-llvm-17 / veristat-kernel
bpf/vmtest-bpf-next-VM_Test-41 success Logs for x86_64-llvm-17 / veristat-meta
bpf/vmtest-bpf-next-VM_Test-43 success Logs for x86_64-llvm-18 / build / build for x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-44 success Logs for x86_64-llvm-18 / build-release / build for x86_64 with llvm-18-O2
bpf/vmtest-bpf-next-VM_Test-50 success Logs for x86_64-llvm-18 / veristat-kernel
bpf/vmtest-bpf-next-VM_Test-51 success Logs for x86_64-llvm-18 / veristat-meta
bpf/vmtest-bpf-next-VM_Test-8 success Logs for aarch64-gcc / test (test_progs, false, 360) / test_progs on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-9 success Logs for aarch64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-16 success Logs for s390x-gcc / test (test_progs, false, 360) / test_progs on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-17 success Logs for s390x-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-25 success Logs for x86_64-gcc / test (test_maps, false, 360) / test_maps on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-30 success Logs for x86_64-gcc / test (test_verifier, false, 360) / test_verifier on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-31 success Logs for x86_64-gcc / veristat-kernel / x86_64-gcc veristat_kernel
bpf/vmtest-bpf-next-VM_Test-32 success Logs for x86_64-gcc / veristat-meta / x86_64-gcc veristat_meta
bpf/vmtest-bpf-next-VM_Test-39 success Logs for x86_64-llvm-17 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-22 success Logs for x86_64-gcc / GCC BPF / GCC BPF
bpf/vmtest-bpf-next-VM_Test-26 success Logs for x86_64-gcc / test (test_progs, false, 360) / test_progs on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-27 success Logs for x86_64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-28 success Logs for x86_64-gcc / test (test_progs_no_alu32_parallel, true, 30) / test_progs_no_alu32_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-29 success Logs for x86_64-gcc / test (test_progs_parallel, true, 30) / test_progs_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-33 success Logs for x86_64-llvm-17 / GCC BPF / GCC BPF
bpf/vmtest-bpf-next-VM_Test-36 success Logs for x86_64-llvm-17 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-37 success Logs for x86_64-llvm-17 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-38 success Logs for x86_64-llvm-17 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-42 success Logs for x86_64-llvm-18 / GCC BPF / GCC BPF
bpf/vmtest-bpf-next-VM_Test-45 success Logs for x86_64-llvm-18 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-49 success Logs for x86_64-llvm-18 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-46 success Logs for x86_64-llvm-18 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-47 success Logs for x86_64-llvm-18 / test (test_progs_cpuv4, false, 360) / test_progs_cpuv4 on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-48 success Logs for x86_64-llvm-18 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-18

Commit Message

Alexei Starovoitov Feb. 13, 2025, 3:35 a.m. UTC 
From: Alexei Starovoitov <ast@kernel.org>

Teach memcg to operate under trylock conditions when spinning locks
cannot be used.

localtry_trylock might fail and this would lead to charge cache bypass
if the calling context doesn't allow spinning (gfpflags_allow_spinning).
In those cases charge the memcg counter directly and fail early if
that is not possible. This might cause a pre-mature charge failing
but it will allow an opportunistic charging that is safe from
try_alloc_pages path.

Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Shakeel Butt <shakeel.butt@linux.dev>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 mm/memcontrol.c | 52 ++++++++++++++++++++++++++++++++++---------------
 1 file changed, 36 insertions(+), 16 deletions(-)
diff mbox series

Patch

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 46f8b372d212..7587511b92cc 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1739,7 +1739,7 @@  void mem_cgroup_print_oom_group(struct mem_cgroup *memcg)
 }
 
 struct memcg_stock_pcp {
-	local_lock_t stock_lock;
+	localtry_lock_t stock_lock;
 	struct mem_cgroup *cached; /* this never be root cgroup */
 	unsigned int nr_pages;
 
@@ -1754,7 +1754,7 @@  struct memcg_stock_pcp {
 #define FLUSHING_CACHED_CHARGE	0
 };
 static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock) = {
-	.stock_lock = INIT_LOCAL_LOCK(stock_lock),
+	.stock_lock = INIT_LOCALTRY_LOCK(stock_lock),
 };
 static DEFINE_MUTEX(percpu_charge_mutex);
 
@@ -1773,7 +1773,8 @@  static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
  *
  * returns true if successful, false otherwise.
  */
-static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
+static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages,
+			  gfp_t gfp_mask)
 {
 	struct memcg_stock_pcp *stock;
 	unsigned int stock_pages;
@@ -1783,7 +1784,11 @@  static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 	if (nr_pages > MEMCG_CHARGE_BATCH)
 		return ret;
 
-	local_lock_irqsave(&memcg_stock.stock_lock, flags);
+	if (!localtry_trylock_irqsave(&memcg_stock.stock_lock, flags)) {
+		if (!gfpflags_allow_spinning(gfp_mask))
+			return ret;
+		localtry_lock_irqsave(&memcg_stock.stock_lock, flags);
+	}
 
 	stock = this_cpu_ptr(&memcg_stock);
 	stock_pages = READ_ONCE(stock->nr_pages);
@@ -1792,7 +1797,7 @@  static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 		ret = true;
 	}
 
-	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+	localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags);
 
 	return ret;
 }
@@ -1831,14 +1836,14 @@  static void drain_local_stock(struct work_struct *dummy)
 	 * drain_stock races is that we always operate on local CPU stock
 	 * here with IRQ disabled
 	 */
-	local_lock_irqsave(&memcg_stock.stock_lock, flags);
+	localtry_lock_irqsave(&memcg_stock.stock_lock, flags);
 
 	stock = this_cpu_ptr(&memcg_stock);
 	old = drain_obj_stock(stock);
 	drain_stock(stock);
 	clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags);
 
-	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+	localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags);
 	obj_cgroup_put(old);
 }
 
@@ -1868,9 +1873,20 @@  static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 {
 	unsigned long flags;
 
-	local_lock_irqsave(&memcg_stock.stock_lock, flags);
+	if (!localtry_trylock_irqsave(&memcg_stock.stock_lock, flags)) {
+		/*
+		 * In case of unlikely failure to lock percpu stock_lock
+		 * uncharge memcg directly.
+		 */
+		if (mem_cgroup_is_root(memcg))
+			return;
+		page_counter_uncharge(&memcg->memory, nr_pages);
+		if (do_memsw_account())
+			page_counter_uncharge(&memcg->memsw, nr_pages);
+		return;
+	}
 	__refill_stock(memcg, nr_pages);
-	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+	localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags);
 }
 
 /*
@@ -2213,9 +2229,13 @@  int try_charge_memcg(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	unsigned long pflags;
 
 retry:
-	if (consume_stock(memcg, nr_pages))
+	if (consume_stock(memcg, nr_pages, gfp_mask))
 		return 0;
 
+	if (!gfpflags_allow_spinning(gfp_mask))
+		/* Avoid the refill and flush of the older stock */
+		batch = nr_pages;
+
 	if (!do_memsw_account() ||
 	    page_counter_try_charge(&memcg->memsw, batch, &counter)) {
 		if (page_counter_try_charge(&memcg->memory, batch, &counter))
@@ -2699,7 +2719,7 @@  static void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat,
 	unsigned long flags;
 	int *bytes;
 
-	local_lock_irqsave(&memcg_stock.stock_lock, flags);
+	localtry_lock_irqsave(&memcg_stock.stock_lock, flags);
 	stock = this_cpu_ptr(&memcg_stock);
 
 	/*
@@ -2752,7 +2772,7 @@  static void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat,
 	if (nr)
 		__mod_objcg_mlstate(objcg, pgdat, idx, nr);
 
-	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+	localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags);
 	obj_cgroup_put(old);
 }
 
@@ -2762,7 +2782,7 @@  static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes)
 	unsigned long flags;
 	bool ret = false;
 
-	local_lock_irqsave(&memcg_stock.stock_lock, flags);
+	localtry_lock_irqsave(&memcg_stock.stock_lock, flags);
 
 	stock = this_cpu_ptr(&memcg_stock);
 	if (objcg == READ_ONCE(stock->cached_objcg) && stock->nr_bytes >= nr_bytes) {
@@ -2770,7 +2790,7 @@  static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes)
 		ret = true;
 	}
 
-	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+	localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags);
 
 	return ret;
 }
@@ -2862,7 +2882,7 @@  static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes,
 	unsigned long flags;
 	unsigned int nr_pages = 0;
 
-	local_lock_irqsave(&memcg_stock.stock_lock, flags);
+	localtry_lock_irqsave(&memcg_stock.stock_lock, flags);
 
 	stock = this_cpu_ptr(&memcg_stock);
 	if (READ_ONCE(stock->cached_objcg) != objcg) { /* reset if necessary */
@@ -2880,7 +2900,7 @@  static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes,
 		stock->nr_bytes &= (PAGE_SIZE - 1);
 	}
 
-	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+	localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags);
 	obj_cgroup_put(old);
 
 	if (nr_pages)