diff options
| author | Paolo Abeni | 2022-02-04 12:28:37 +0100 |
|---|---|---|
| committer | David S. Miller | 2022-02-05 15:13:52 +0000 |
| commit | de5a1f3ce4c862150dc442530dba19e1d1dc6bc2 (patch) | |
| tree | e17d79dcb5e9da6ab7fa80a4e506c1437415648b /include | |
| parent | 7881453e4adf497cf9109c84fa21eedda9ac6164 (diff) | |
net: gro: minor optimization for dev_gro_receive()
While inspecting some perf report, I noticed that the compiler
emits suboptimal code for the napi CB initialization, fetching
and storing multiple times the memory for flags bitfield.
This is with gcc 10.3.1, but I observed the same with older compiler
versions.
We can help the compiler to do a nicer work clearing several
fields at once using an u32 alias. The generated code is quite
smaller, with the same number of conditional.
Before:
objdump -t net/core/gro.o | grep " F .text"
0000000000000bb0 l F .text 0000000000000357 dev_gro_receive
After:
0000000000000bb0 l F .text 000000000000033c dev_gro_receive
v1 -> v2:
- use struct_group (Alexander and Alex)
RFC -> v1:
- use __struct_group to delimit the zeroed area (Alexander)
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'include')
| -rw-r--r-- | include/net/gro.h | 52 |
1 files changed, 28 insertions, 24 deletions
diff --git a/include/net/gro.h b/include/net/gro.h index 8f75802d50fd..a765fedda5c4 100644 --- a/include/net/gro.h +++ b/include/net/gro.h @@ -29,46 +29,50 @@ struct napi_gro_cb { /* Number of segments aggregated. */ u16 count; - /* Start offset for remote checksum offload */ - u16 gro_remcsum_start; + /* Used in ipv6_gro_receive() and foo-over-udp */ + u16 proto; /* jiffies when first packet was created/queued */ unsigned long age; - /* Used in ipv6_gro_receive() and foo-over-udp */ - u16 proto; + /* portion of the cb set to zero at every gro iteration */ + struct_group(zeroed, + + /* Start offset for remote checksum offload */ + u16 gro_remcsum_start; - /* This is non-zero if the packet may be of the same flow. */ - u8 same_flow:1; + /* This is non-zero if the packet may be of the same flow. */ + u8 same_flow:1; - /* Used in tunnel GRO receive */ - u8 encap_mark:1; + /* Used in tunnel GRO receive */ + u8 encap_mark:1; - /* GRO checksum is valid */ - u8 csum_valid:1; + /* GRO checksum is valid */ + u8 csum_valid:1; - /* Number of checksums via CHECKSUM_UNNECESSARY */ - u8 csum_cnt:3; + /* Number of checksums via CHECKSUM_UNNECESSARY */ + u8 csum_cnt:3; - /* Free the skb? */ - u8 free:2; + /* Free the skb? */ + u8 free:2; #define NAPI_GRO_FREE 1 #define NAPI_GRO_FREE_STOLEN_HEAD 2 - /* Used in foo-over-udp, set in udp[46]_gro_receive */ - u8 is_ipv6:1; + /* Used in foo-over-udp, set in udp[46]_gro_receive */ + u8 is_ipv6:1; - /* Used in GRE, set in fou/gue_gro_receive */ - u8 is_fou:1; + /* Used in GRE, set in fou/gue_gro_receive */ + u8 is_fou:1; - /* Used to determine if flush_id can be ignored */ - u8 is_atomic:1; + /* Used to determine if flush_id can be ignored */ + u8 is_atomic:1; - /* Number of gro_receive callbacks this packet already went through */ - u8 recursion_counter:4; + /* Number of gro_receive callbacks this packet already went through */ + u8 recursion_counter:4; - /* GRO is done by frag_list pointer chaining. */ - u8 is_flist:1; + /* GRO is done by frag_list pointer chaining. */ + u8 is_flist:1; + ); /* used to support CHECKSUM_COMPLETE for tunneling protocols */ __wsum csum; |