xsk: Explicitly inline functions and move definitions

In order to reduce the number of function calls, the struct
xsk_buff_pool definition is moved to xsk_buff_pool.h. The functions
xp_get_dma(), xp_dma_sync_for_cpu(), xp_dma_sync_for_device(),
xp_validate_desc() and various helper functions are explicitly
inlined.

Further, move xp_get_handle() and xp_release() to xsk.c, to allow for
the compiler to perform inlining.

rfc->v1: Make sure xp_validate_desc() is inlined for Tx perf. (Maxim)

Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200520192103.355233-15-bjorn.topel@gmail.com

diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index 9f221b3..a4ff226 100644 (file)
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -4,6 +4,7 @@
 #ifndef XSK_BUFF_POOL_H_
 #define XSK_BUFF_POOL_H_
 
+#include <linux/if_xdp.h>
 #include <linux/types.h>
 #include <linux/dma-mapping.h>
 #include <net/xdp.h>
@@ -25,6 +26,27 @@ struct xdp_buff_xsk {
        struct list_head free_list_node;
 };
 
+struct xsk_buff_pool {
+       struct xsk_queue *fq;
+       struct list_head free_list;
+       dma_addr_t *dma_pages;
+       struct xdp_buff_xsk *heads;
+       u64 chunk_mask;
+       u64 addrs_cnt;
+       u32 free_list_cnt;
+       u32 dma_pages_cnt;
+       u32 heads_cnt;
+       u32 free_heads_cnt;
+       u32 headroom;
+       u32 chunk_size;
+       u32 frame_len;
+       bool cheap_dma;
+       bool unaligned;
+       void *addrs;
+       struct device *dev;
+       struct xdp_buff_xsk *free_heads[];
+};
+
 /* AF_XDP core. */
 struct xsk_buff_pool *xp_create(struct page **pages, u32 nr_pages, u32 chunks,
                                u32 chunk_size, u32 headroom, u64 size,
@@ -32,8 +54,6 @@ struct xsk_buff_pool *xp_create(struct page **pages, u32 nr_pages, u32 chunks,
 void xp_set_fq(struct xsk_buff_pool *pool, struct xsk_queue *fq);
 void xp_destroy(struct xsk_buff_pool *pool);
 void xp_release(struct xdp_buff_xsk *xskb);
-u64 xp_get_handle(struct xdp_buff_xsk *xskb);
-bool xp_validate_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc);
 
 /* AF_XDP, and XDP core. */
 void xp_free(struct xdp_buff_xsk *xskb);
@@ -47,10 +67,74 @@ struct xdp_buff *xp_alloc(struct xsk_buff_pool *pool);
 bool xp_can_alloc(struct xsk_buff_pool *pool, u32 count);
 void *xp_raw_get_data(struct xsk_buff_pool *pool, u64 addr);
 dma_addr_t xp_raw_get_dma(struct xsk_buff_pool *pool, u64 addr);
-dma_addr_t xp_get_dma(struct xdp_buff_xsk *xskb);
-dma_addr_t xp_get_frame_dma(struct xdp_buff_xsk *xskb);
-void xp_dma_sync_for_cpu(struct xdp_buff_xsk *xskb);
-void xp_dma_sync_for_device(struct xsk_buff_pool *pool, dma_addr_t dma,
-                           size_t size);
+static inline dma_addr_t xp_get_dma(struct xdp_buff_xsk *xskb)
+{
+       return xskb->dma;
+}
+
+static inline dma_addr_t xp_get_frame_dma(struct xdp_buff_xsk *xskb)
+{
+       return xskb->frame_dma;
+}
+
+void xp_dma_sync_for_cpu_slow(struct xdp_buff_xsk *xskb);
+static inline void xp_dma_sync_for_cpu(struct xdp_buff_xsk *xskb)
+{
+       if (xskb->pool->cheap_dma)
+               return;
+
+       xp_dma_sync_for_cpu_slow(xskb);
+}
+
+void xp_dma_sync_for_device_slow(struct xsk_buff_pool *pool, dma_addr_t dma,
+                                size_t size);
+static inline void xp_dma_sync_for_device(struct xsk_buff_pool *pool,
+                                         dma_addr_t dma, size_t size)
+{
+       if (pool->cheap_dma)
+               return;
+
+       xp_dma_sync_for_device_slow(pool, dma, size);
+}
+
+/* Masks for xdp_umem_page flags.
+ * The low 12-bits of the addr will be 0 since this is the page address, so we
+ * can use them for flags.
+ */
+#define XSK_NEXT_PG_CONTIG_SHIFT 0
+#define XSK_NEXT_PG_CONTIG_MASK BIT_ULL(XSK_NEXT_PG_CONTIG_SHIFT)
+
+static inline bool xp_desc_crosses_non_contig_pg(struct xsk_buff_pool *pool,
+                                                u64 addr, u32 len)
+{
+       bool cross_pg = (addr & (PAGE_SIZE - 1)) + len > PAGE_SIZE;
+
+       if (pool->dma_pages_cnt && cross_pg) {
+               return !(pool->dma_pages[addr >> PAGE_SHIFT] &
+                        XSK_NEXT_PG_CONTIG_MASK);
+       }
+       return false;
+}
+
+static inline u64 xp_aligned_extract_addr(struct xsk_buff_pool *pool, u64 addr)
+{
+       return addr & pool->chunk_mask;
+}
+
+static inline u64 xp_unaligned_extract_addr(u64 addr)
+{
+       return addr & XSK_UNALIGNED_BUF_ADDR_MASK;
+}
+
+static inline u64 xp_unaligned_extract_offset(u64 addr)
+{
+       return addr >> XSK_UNALIGNED_BUF_OFFSET_SHIFT;
+}
+
+static inline u64 xp_unaligned_add_offset_to_addr(u64 addr)
+{
+       return xp_unaligned_extract_addr(addr) +
+               xp_unaligned_extract_offset(addr);
+}
 
 #endif /* XSK_BUFF_POOL_H_ */

diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 3f2ab73..b6c0f08 100644 (file)
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -99,6 +99,21 @@ bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem)
 }
 EXPORT_SYMBOL(xsk_umem_uses_need_wakeup);
 
+void xp_release(struct xdp_buff_xsk *xskb)
+{
+       xskb->pool->free_heads[xskb->pool->free_heads_cnt++] = xskb;
+}
+
+static u64 xp_get_handle(struct xdp_buff_xsk *xskb)
+{
+       u64 offset = xskb->xdp.data - xskb->xdp.data_hard_start;
+
+       offset += xskb->pool->headroom;
+       if (!xskb->pool->unaligned)
+               return xskb->orig_addr + offset;
+       return xskb->orig_addr + (offset << XSK_UNALIGNED_BUF_OFFSET_SHIFT);
+}
+
 static int __xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 {
        struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);

diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 89dae78..540ed75 100644 (file)
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -8,34 +8,6 @@
 
 #include "xsk_queue.h"
 
-/* Masks for xdp_umem_page flags.
- * The low 12-bits of the addr will be 0 since this is the page address, so we
- * can use them for flags.
- */
-#define XSK_NEXT_PG_CONTIG_SHIFT 0
-#define XSK_NEXT_PG_CONTIG_MASK BIT_ULL(XSK_NEXT_PG_CONTIG_SHIFT)
-
-struct xsk_buff_pool {
-       struct xsk_queue *fq;
-       struct list_head free_list;
-       dma_addr_t *dma_pages;
-       struct xdp_buff_xsk *heads;
-       u64 chunk_mask;
-       u64 addrs_cnt;
-       u32 free_list_cnt;
-       u32 dma_pages_cnt;
-       u32 heads_cnt;
-       u32 free_heads_cnt;
-       u32 headroom;
-       u32 chunk_size;
-       u32 frame_len;
-       bool cheap_dma;
-       bool unaligned;
-       void *addrs;
-       struct device *dev;
-       struct xdp_buff_xsk *free_heads[];
-};
-
 static void xp_addr_unmap(struct xsk_buff_pool *pool)
 {
        vunmap(pool->addrs);
@@ -228,50 +200,12 @@ int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev,
 }
 EXPORT_SYMBOL(xp_dma_map);
 
-static bool xp_desc_crosses_non_contig_pg(struct xsk_buff_pool *pool,
-                                         u64 addr, u32 len)
-{
-       bool cross_pg = (addr & (PAGE_SIZE - 1)) + len > PAGE_SIZE;
-
-       if (pool->dma_pages_cnt && cross_pg) {
-               return !(pool->dma_pages[addr >> PAGE_SHIFT] &
-                        XSK_NEXT_PG_CONTIG_MASK);
-       }
-       return false;
-}
-
 static bool xp_addr_crosses_non_contig_pg(struct xsk_buff_pool *pool,
                                          u64 addr)
 {
        return xp_desc_crosses_non_contig_pg(pool, addr, pool->chunk_size);
 }
 
-void xp_release(struct xdp_buff_xsk *xskb)
-{
-       xskb->pool->free_heads[xskb->pool->free_heads_cnt++] = xskb;
-}
-
-static u64 xp_aligned_extract_addr(struct xsk_buff_pool *pool, u64 addr)
-{
-       return addr & pool->chunk_mask;
-}
-
-static u64 xp_unaligned_extract_addr(u64 addr)
-{
-       return addr & XSK_UNALIGNED_BUF_ADDR_MASK;
-}
-
-static u64 xp_unaligned_extract_offset(u64 addr)
-{
-       return addr >> XSK_UNALIGNED_BUF_OFFSET_SHIFT;
-}
-
-static u64 xp_unaligned_add_offset_to_addr(u64 addr)
-{
-       return xp_unaligned_extract_addr(addr) +
-               xp_unaligned_extract_offset(addr);
-}
-
 static bool xp_check_unaligned(struct xsk_buff_pool *pool, u64 *addr)
 {
        *addr = xp_unaligned_extract_addr(*addr);
@@ -370,60 +304,6 @@ void xp_free(struct xdp_buff_xsk *xskb)
 }
 EXPORT_SYMBOL(xp_free);
 
-static bool xp_aligned_validate_desc(struct xsk_buff_pool *pool,
-                                    struct xdp_desc *desc)
-{
-       u64 chunk, chunk_end;
-
-       chunk = xp_aligned_extract_addr(pool, desc->addr);
-       chunk_end = xp_aligned_extract_addr(pool, desc->addr + desc->len);
-       if (chunk != chunk_end)
-               return false;
-
-       if (chunk >= pool->addrs_cnt)
-               return false;
-
-       if (desc->options)
-               return false;
-       return true;
-}
-
-static bool xp_unaligned_validate_desc(struct xsk_buff_pool *pool,
-                                      struct xdp_desc *desc)
-{
-       u64 addr, base_addr;
-
-       base_addr = xp_unaligned_extract_addr(desc->addr);
-       addr = xp_unaligned_add_offset_to_addr(desc->addr);
-
-       if (desc->len > pool->chunk_size)
-               return false;
-
-       if (base_addr >= pool->addrs_cnt || addr >= pool->addrs_cnt ||
-           xp_desc_crosses_non_contig_pg(pool, addr, desc->len))
-               return false;
-
-       if (desc->options)
-               return false;
-       return true;
-}
-
-bool xp_validate_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc)
-{
-       return pool->unaligned ? xp_unaligned_validate_desc(pool, desc) :
-               xp_aligned_validate_desc(pool, desc);
-}
-
-u64 xp_get_handle(struct xdp_buff_xsk *xskb)
-{
-       u64 offset = xskb->xdp.data - xskb->xdp.data_hard_start;
-
-       offset += xskb->pool->headroom;
-       if (!xskb->pool->unaligned)
-               return xskb->orig_addr + offset;
-       return xskb->orig_addr + (offset << XSK_UNALIGNED_BUF_OFFSET_SHIFT);
-}
-
 void *xp_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
 {
        addr = pool->unaligned ? xp_unaligned_add_offset_to_addr(addr) : addr;
@@ -440,35 +320,17 @@ dma_addr_t xp_raw_get_dma(struct xsk_buff_pool *pool, u64 addr)
 }
 EXPORT_SYMBOL(xp_raw_get_dma);
 
-dma_addr_t xp_get_dma(struct xdp_buff_xsk *xskb)
-{
-       return xskb->dma;
-}
-EXPORT_SYMBOL(xp_get_dma);
-
-dma_addr_t xp_get_frame_dma(struct xdp_buff_xsk *xskb)
+void xp_dma_sync_for_cpu_slow(struct xdp_buff_xsk *xskb)
 {
-       return xskb->frame_dma;
-}
-EXPORT_SYMBOL(xp_get_frame_dma);
-
-void xp_dma_sync_for_cpu(struct xdp_buff_xsk *xskb)
-{
-       if (xskb->pool->cheap_dma)
-               return;
-
        dma_sync_single_range_for_cpu(xskb->pool->dev, xskb->dma, 0,
                                      xskb->pool->frame_len, DMA_BIDIRECTIONAL);
 }
-EXPORT_SYMBOL(xp_dma_sync_for_cpu);
+EXPORT_SYMBOL(xp_dma_sync_for_cpu_slow);
 
-void xp_dma_sync_for_device(struct xsk_buff_pool *pool, dma_addr_t dma,
-                           size_t size)
+void xp_dma_sync_for_device_slow(struct xsk_buff_pool *pool, dma_addr_t dma,
+                                size_t size)
 {
-       if (pool->cheap_dma)
-               return;
-
        dma_sync_single_range_for_device(pool->dev, dma, 0,
                                         size, DMA_BIDIRECTIONAL);
 }
-EXPORT_SYMBOL(xp_dma_sync_for_device);
+EXPORT_SYMBOL(xp_dma_sync_for_device_slow);

diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index 16bf158..5b5d24d 100644 (file)
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -118,6 +118,51 @@ static inline bool xskq_cons_read_addr_unchecked(struct xsk_queue *q, u64 *addr)
        return false;
 }
 
+static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool,
+                                           struct xdp_desc *desc)
+{
+       u64 chunk, chunk_end;
+
+       chunk = xp_aligned_extract_addr(pool, desc->addr);
+       chunk_end = xp_aligned_extract_addr(pool, desc->addr + desc->len);
+       if (chunk != chunk_end)
+               return false;
+
+       if (chunk >= pool->addrs_cnt)
+               return false;
+
+       if (desc->options)
+               return false;
+       return true;
+}
+
+static inline bool xp_unaligned_validate_desc(struct xsk_buff_pool *pool,
+                                             struct xdp_desc *desc)
+{
+       u64 addr, base_addr;
+
+       base_addr = xp_unaligned_extract_addr(desc->addr);
+       addr = xp_unaligned_add_offset_to_addr(desc->addr);
+
+       if (desc->len > pool->chunk_size)
+               return false;
+
+       if (base_addr >= pool->addrs_cnt || addr >= pool->addrs_cnt ||
+           xp_desc_crosses_non_contig_pg(pool, addr, desc->len))
+               return false;
+
+       if (desc->options)
+               return false;
+       return true;
+}
+
+static inline bool xp_validate_desc(struct xsk_buff_pool *pool,
+                                   struct xdp_desc *desc)
+{
+       return pool->unaligned ? xp_unaligned_validate_desc(pool, desc) :
+               xp_aligned_validate_desc(pool, desc);
+}
+
 static inline bool xskq_cons_is_valid_desc(struct xsk_queue *q,
                                           struct xdp_desc *d,
                                           struct xdp_umem *umem)