summaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
diff options
context:
space:
mode:
authorBrenden Blanco <bblanco@plumgrid.com>2016-07-19 12:16:52 -0700
committerDavid S. Miller <davem@davemloft.net>2016-07-19 21:46:32 -0700
commitd576acf0a22890cf3f8f7a9b035f1558077f6770 (patch)
treecec17ffc7653bcd97cc8e559a2a03eb6712fa267 /drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
parent86af8b4191d20bb17e868d3167f4cf52ca9331d0 (diff)
net/mlx4_en: add page recycle to prepare rx ring for tx support
The mlx4 driver by default allocates order-3 pages for the ring to consume in multiple fragments. When the device has an xdp program, this behavior will prevent tx actions since the page must be re-mapped in TODEVICE mode, which cannot be done if the page is still shared. Start by making the allocator configurable based on whether xdp is running, such that order-0 pages are always used and never shared. Since this will stress the page allocator, add a simple page cache to each rx ring. Pages in the cache are left dma-mapped, and in drop-only stress tests the page allocator is eliminated from the perf report. Note that setting an xdp program will now require the rings to be reconfigured. Before: 26.91% ksoftirqd/0 [mlx4_en] [k] mlx4_en_process_rx_cq 17.88% ksoftirqd/0 [mlx4_en] [k] mlx4_en_alloc_frags 6.00% ksoftirqd/0 [mlx4_en] [k] mlx4_en_free_frag 4.49% ksoftirqd/0 [kernel.vmlinux] [k] get_page_from_freelist 3.21% swapper [kernel.vmlinux] [k] intel_idle 2.73% ksoftirqd/0 [kernel.vmlinux] [k] bpf_map_lookup_elem 2.57% swapper [mlx4_en] [k] mlx4_en_process_rx_cq After: 31.72% swapper [kernel.vmlinux] [k] intel_idle 8.79% swapper [mlx4_en] [k] mlx4_en_process_rx_cq 7.54% swapper [kernel.vmlinux] [k] poll_idle 6.36% swapper [mlx4_core] [k] mlx4_eq_int 4.21% swapper [kernel.vmlinux] [k] tasklet_action 4.03% swapper [kernel.vmlinux] [k] cpuidle_enter_state 3.43% swapper [mlx4_en] [k] mlx4_en_prepare_rx_desc 2.18% swapper [kernel.vmlinux] [k] native_irq_return_iret 1.37% swapper [kernel.vmlinux] [k] menu_select 1.09% swapper [kernel.vmlinux] [k] bpf_map_lookup_elem Signed-off-by: Brenden Blanco <bblanco@plumgrid.com> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'drivers/net/ethernet/mellanox/mlx4/mlx4_en.h')
-rw-r--r--drivers/net/ethernet/mellanox/mlx4/mlx4_en.h11
1 files changed, 10 insertions, 1 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index eb1238d05ca8..eff4be0279e6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -259,6 +259,12 @@ struct mlx4_en_rx_alloc {
u32 page_size;
};
+#define MLX4_EN_CACHE_SIZE (2 * NAPI_POLL_WEIGHT)
+struct mlx4_en_page_cache {
+ u32 index;
+ struct mlx4_en_rx_alloc buf[MLX4_EN_CACHE_SIZE];
+};
+
struct mlx4_en_tx_ring {
/* cache line used and dirtied in tx completion
* (mlx4_en_free_tx_buf())
@@ -324,6 +330,7 @@ struct mlx4_en_rx_ring {
void *buf;
void *rx_info;
struct bpf_prog *xdp_prog;
+ struct mlx4_en_page_cache page_cache;
unsigned long bytes;
unsigned long packets;
unsigned long csum_ok;
@@ -443,7 +450,9 @@ struct mlx4_en_mc_list {
struct mlx4_en_frag_info {
u16 frag_size;
u16 frag_prefix_size;
- u16 frag_stride;
+ u32 frag_stride;
+ enum dma_data_direction dma_dir;
+ int order;
};
#ifdef CONFIG_MLX4_EN_DCB