Message ID | 20210111182801.12609-1-alobakin@pm.me (mailing list archive) |
---|---|
State | Changes Requested |
Delegated to: | Netdev Maintainers |
Headers | show |
Series | skbuff: introduce skbuff_heads bulking and reusing | expand |
Context | Check | Description |
---|---|---|
netdev/cover_letter | success | Link |
netdev/fixes_present | success | Link |
netdev/patch_count | success | Link |
netdev/tree_selection | success | Clearly marked for net-next |
netdev/subject_prefix | success | Link |
netdev/cc_maintainers | success | CCed 11 of 11 maintainers |
netdev/source_inline | success | Was 0 now: 0 |
netdev/verify_signedoff | success | Link |
netdev/module_param | success | Was 0 now: 0 |
netdev/build_32bit | success | Errors and warnings before: 1 this patch: 1 |
netdev/kdoc | success | Errors and warnings before: 0 this patch: 0 |
netdev/verify_fixes | success | Link |
netdev/checkpatch | success | total: 0 errors, 0 warnings, 0 checks, 51 lines checked |
netdev/build_allmodconfig_warn | success | Errors and warnings before: 1 this patch: 1 |
netdev/header_inline | success | Link |
netdev/stable | success | Stable not CCed |
On Mon, Jan 11, 2021 at 06:28:21PM +0000, Alexander Lobakin wrote: > skb_cache and skb_count fields are used to store skbuff_heads queued > for freeing to flush them by bulks, and aren't related to allocation > path. Give them more obvious names to improve code understanding and > allow to expand this struct with more allocation-related elements. I don't think prefixing these with flush_ is the correct approach; flush is just an operation on the structure, not a property of the structure itself. It especially becomes confusing in the later patches when the cache is used on the allocation path.
From: Jonathan Lemon <jonathan.lemon@gmail.com> Date: Mon, 11 Jan 2021 10:49:45 -0800 > On Mon, Jan 11, 2021 at 06:28:21PM +0000, Alexander Lobakin wrote: >> skb_cache and skb_count fields are used to store skbuff_heads queued >> for freeing to flush them by bulks, and aren't related to allocation >> path. Give them more obvious names to improve code understanding and >> allow to expand this struct with more allocation-related elements. > > I don't think prefixing these with flush_ is the correct approach; > flush is just an operation on the structure, not a property of the > structure itself. It especially becomes confusing in the later > patches when the cache is used on the allocation path. Agree, but didn't come up with anything more fitting. Any suggestions maybe? > -- > Jonathan Thanks, Al
diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 7626a33cce59..17ae5e90f103 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -366,9 +366,9 @@ EXPORT_SYMBOL(build_skb_around); #define NAPI_SKB_CACHE_SIZE 64 struct napi_alloc_cache { - struct page_frag_cache page; - unsigned int skb_count; - void *skb_cache[NAPI_SKB_CACHE_SIZE]; + struct page_frag_cache page; + u32 flush_skb_count; + void *flush_skb_cache[NAPI_SKB_CACHE_SIZE]; }; static DEFINE_PER_CPU(struct page_frag_cache, netdev_alloc_cache); @@ -860,11 +860,11 @@ void __kfree_skb_flush(void) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); - /* flush skb_cache if containing objects */ - if (nc->skb_count) { - kmem_cache_free_bulk(skbuff_head_cache, nc->skb_count, - nc->skb_cache); - nc->skb_count = 0; + /* flush flush_skb_cache if containing objects */ + if (nc->flush_skb_count) { + kmem_cache_free_bulk(skbuff_head_cache, nc->flush_skb_count, + nc->flush_skb_cache); + nc->flush_skb_count = 0; } } @@ -876,18 +876,18 @@ static inline void _kfree_skb_defer(struct sk_buff *skb) skb_release_all(skb); /* record skb to CPU local list */ - nc->skb_cache[nc->skb_count++] = skb; + nc->flush_skb_cache[nc->flush_skb_count++] = skb; #ifdef CONFIG_SLUB /* SLUB writes into objects when freeing */ prefetchw(skb); #endif - /* flush skb_cache if it is filled */ - if (unlikely(nc->skb_count == NAPI_SKB_CACHE_SIZE)) { + /* flush flush_skb_cache if it is filled */ + if (unlikely(nc->flush_skb_count == NAPI_SKB_CACHE_SIZE)) { kmem_cache_free_bulk(skbuff_head_cache, NAPI_SKB_CACHE_SIZE, - nc->skb_cache); - nc->skb_count = 0; + nc->flush_skb_cache); + nc->flush_skb_count = 0; } } void __kfree_skb_defer(struct sk_buff *skb)
skb_cache and skb_count fields are used to store skbuff_heads queued for freeing to flush them by bulks, and aren't related to allocation path. Give them more obvious names to improve code understanding and allow to expand this struct with more allocation-related elements. Misc: indent struct napi_alloc_cache declaration for better reading. Signed-off-by: Alexander Lobakin <alobakin@pm.me> --- net/core/skbuff.c | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-)