diff mbox series

[bpf-next,01/10] bpf: rearrange bpf_func_state fields to save a bit of memory

Message ID 20231122011656.1105943-2-andrii@kernel.org (mailing list archive)
State Superseded
Delegated to: BPF
Headers show
Series BPF verifier retval logic fixes | expand

Checks

Context Check Description
bpf/vmtest-bpf-next-PR success PR summary
netdev/series_format success Posting correctly formatted
netdev/codegen success Generated files up to date
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: 1197 this patch: 1197
netdev/cc_maintainers warning 8 maintainers not CCed: yonghong.song@linux.dev song@kernel.org haoluo@google.com martin.lau@linux.dev jolsa@kernel.org kpsingh@kernel.org john.fastabend@gmail.com sdf@google.com
netdev/build_clang success Errors and warnings before: 1162 this patch: 1162
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: 1224 this patch: 1224
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 18 lines checked
netdev/build_clang_rust success No Rust files in patch. Skipping build
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-2 success Logs for Validate matrix.py
bpf/vmtest-bpf-next-VM_Test-1 success Logs for ShellCheck
bpf/vmtest-bpf-next-VM_Test-0 success Logs for Lint
bpf/vmtest-bpf-next-VM_Test-8 success Logs for aarch64-gcc / veristat
bpf/vmtest-bpf-next-VM_Test-3 success Logs for aarch64-gcc / build / build for aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-4 success Logs for aarch64-gcc / test (test_maps, false, 360) / test_maps on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-6 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-7 success Logs for aarch64-gcc / test (test_verifier, false, 360) / test_verifier on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-5 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 s390x-gcc / build / build for s390x with gcc
bpf/vmtest-bpf-next-VM_Test-14 success Logs for s390x-gcc / veristat
bpf/vmtest-bpf-next-VM_Test-15 success Logs for set-matrix
bpf/vmtest-bpf-next-VM_Test-16 success Logs for x86_64-gcc / build / build for x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-17 success Logs for x86_64-gcc / test (test_maps, false, 360) / test_maps on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-18 success Logs for x86_64-gcc / test (test_progs, false, 360) / test_progs on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-19 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-20 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-21 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-22 success Logs for x86_64-gcc / test (test_verifier, false, 360) / test_verifier on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-23 success Logs for x86_64-gcc / veristat / veristat on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-24 success Logs for x86_64-llvm-16 / build / build for x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-25 success Logs for x86_64-llvm-16 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-26 success Logs for x86_64-llvm-16 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-27 success Logs for x86_64-llvm-16 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-28 success Logs for x86_64-llvm-16 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-29 success Logs for x86_64-llvm-16 / veristat
bpf/vmtest-bpf-next-VM_Test-13 success Logs for s390x-gcc / test (test_verifier, false, 360) / test_verifier on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-12 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-10 success Logs for s390x-gcc / test (test_maps, false, 360) / test_maps on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-11 success Logs for s390x-gcc / test (test_progs, false, 360) / test_progs on s390x with gcc

Commit Message

Andrii Nakryiko Nov. 22, 2023, 1:16 a.m. UTC 
It's a trivial rearrangement saving 8 bytes. We have 4 bytes of padding
at the end which can be filled with another field without increasing
struct bpf_func_state.

copy_func_state() logic remains correct without any further changes.

BEFORE
======
struct bpf_func_state {
        struct bpf_reg_state       regs[11];             /*     0  1320 */
        /* --- cacheline 20 boundary (1280 bytes) was 40 bytes ago --- */
        int                        callsite;             /*  1320     4 */
        u32                        frameno;              /*  1324     4 */
        u32                        subprogno;            /*  1328     4 */
        u32                        async_entry_cnt;      /*  1332     4 */
        bool                       in_callback_fn;       /*  1336     1 */

        /* XXX 7 bytes hole, try to pack */

        /* --- cacheline 21 boundary (1344 bytes) --- */
        struct tnum                callback_ret_range;   /*  1344    16 */
        bool                       in_async_callback_fn; /*  1360     1 */
        bool                       in_exception_callback_fn; /*  1361     1 */

        /* XXX 2 bytes hole, try to pack */

        int                        acquired_refs;        /*  1364     4 */
        struct bpf_reference_state * refs;               /*  1368     8 */
        int                        allocated_stack;      /*  1376     4 */

        /* XXX 4 bytes hole, try to pack */

        struct bpf_stack_state *   stack;                /*  1384     8 */

        /* size: 1392, cachelines: 22, members: 13 */
        /* sum members: 1379, holes: 3, sum holes: 13 */
        /* last cacheline: 48 bytes */
};

AFTER
=====
struct bpf_func_state {
        struct bpf_reg_state       regs[11];             /*     0  1320 */
        /* --- cacheline 20 boundary (1280 bytes) was 40 bytes ago --- */
        int                        callsite;             /*  1320     4 */
        u32                        frameno;              /*  1324     4 */
        u32                        subprogno;            /*  1328     4 */
        u32                        async_entry_cnt;      /*  1332     4 */
        struct tnum                callback_ret_range;   /*  1336    16 */
        /* --- cacheline 21 boundary (1344 bytes) was 8 bytes ago --- */
        bool                       in_callback_fn;       /*  1352     1 */
        bool                       in_async_callback_fn; /*  1353     1 */
        bool                       in_exception_callback_fn; /*  1354     1 */

        /* XXX 1 byte hole, try to pack */

        int                        acquired_refs;        /*  1356     4 */
        struct bpf_reference_state * refs;               /*  1360     8 */
        struct bpf_stack_state *   stack;                /*  1368     8 */
        int                        allocated_stack;      /*  1376     4 */

        /* size: 1384, cachelines: 22, members: 13 */
        /* sum members: 1379, holes: 1, sum holes: 1 */
        /* padding: 4 */
        /* last cacheline: 40 bytes */
};

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
---
 include/linux/bpf_verifier.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

Comments

Eduard Zingerman Nov. 22, 2023, 3:12 p.m. UTC | #1 
On Tue, 2023-11-21 at 17:16 -0800, Andrii Nakryiko wrote:
> It's a trivial rearrangement saving 8 bytes. We have 4 bytes of padding
> at the end which can be filled with another field without increasing
> struct bpf_func_state.
> 
[...]
> 
> Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
> ---

Acked-by: Eduard Zingerman <eddyz87@gmail.com>

[...]
diff mbox series

Patch

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 39edc76f436e..f019da8bf423 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -297,16 +297,16 @@  struct bpf_func_state {
 	 * void foo(void) { bpf_timer_set_callback(,foo); }
 	 */
 	u32 async_entry_cnt;
-	bool in_callback_fn;
 	struct tnum callback_ret_range;
+	bool in_callback_fn;
 	bool in_async_callback_fn;
 	bool in_exception_callback_fn;
 
 	/* The following fields should be last. See copy_func_state() */
 	int acquired_refs;
 	struct bpf_reference_state *refs;
-	int allocated_stack;
 	struct bpf_stack_state *stack;
+	int allocated_stack;
 };
 
 struct bpf_idx_pair {