summaryrefslogtreecommitdiffstats
path: root/include
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2018-09-26 05:25:00 +0200
committerDavid S. Miller <davem@davemloft.net>2018-09-26 05:25:00 +0200
commit71f9b61c5b3f894fdc9dff9e511a961ada122862 (patch)
tree8c8e92d19ae9c3bb3cbafcde380c36075b0f90c0 /include
parentMerge branch 'Refactor-classifier-API-to-work-with-Qdisc-blocks-without-rtnl-... (diff)
parenti40e: disallow changing the number of descriptors when AF_XDP is on (diff)
downloadlinux-71f9b61c5b3f894fdc9dff9e511a961ada122862.tar.xz
linux-71f9b61c5b3f894fdc9dff9e511a961ada122862.zip
Merge branch '40GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue
Jeff Kirsher says: ==================== 40GbE Intel Wired LAN Driver Updates 2018-09-25 This series contains updates to i40e and xsk. Mariusz fixes an issue where the VF link state was not being updated properly when the PF is down or up. Also cleaned up the promiscuous configuration during a VF reset. Patryk simplifies the code a bit to use the variables for PF and HW that are declared, rather than using the VSI pointers. Cleaned up the message length parameter to several virtchnl functions, since it was not being used (or needed). Harshitha fixes two potential race conditions when trying to change VF settings by creating a helper function to validate that the VF is enabled and that the VSI is set up. Sergey corrects a double "link down" message by putting in a check for whether or not the link is up or going down. Björn addresses an AF_XDP zero-copy issue that buffers passed from userspace to the kernel was leaked when the hardware descriptor ring was torn down. A zero-copy capable driver picks buffers off the fill ring and places them on the hardware receive ring to be completed at a later point when DMA is complete. Similar on the transmit side; The driver picks buffers off the transmit ring and places them on the transmit hardware ring. In the typical flow, the receive buffer will be placed onto an receive ring (completed to the user), and the transmit buffer will be placed on the completion ring to notify the user that the transfer is done. However, if the driver needs to tear down the hardware rings for some reason (interface goes down, reconfiguration and such), the userspace buffers cannot be leaked. They have to be reused or completed back to userspace. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'include')
-rw-r--r--include/net/xdp_sock.h69
1 files changed, 69 insertions, 0 deletions
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index 932ca0dad6f3..70a115bea4f4 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -21,6 +21,12 @@ struct xdp_umem_page {
dma_addr_t dma;
};
+struct xdp_umem_fq_reuse {
+ u32 nentries;
+ u32 length;
+ u64 handles[];
+};
+
struct xdp_umem {
struct xsk_queue *fq;
struct xsk_queue *cq;
@@ -37,6 +43,7 @@ struct xdp_umem {
struct page **pgs;
u32 npgs;
struct net_device *dev;
+ struct xdp_umem_fq_reuse *fq_reuse;
u16 queue_id;
bool zc;
spinlock_t xsk_list_lock;
@@ -75,6 +82,10 @@ void xsk_umem_discard_addr(struct xdp_umem *umem);
void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries);
bool xsk_umem_consume_tx(struct xdp_umem *umem, dma_addr_t *dma, u32 *len);
void xsk_umem_consume_tx_done(struct xdp_umem *umem);
+struct xdp_umem_fq_reuse *xsk_reuseq_prepare(u32 nentries);
+struct xdp_umem_fq_reuse *xsk_reuseq_swap(struct xdp_umem *umem,
+ struct xdp_umem_fq_reuse *newq);
+void xsk_reuseq_free(struct xdp_umem_fq_reuse *rq);
static inline char *xdp_umem_get_data(struct xdp_umem *umem, u64 addr)
{
@@ -85,6 +96,35 @@ static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr)
{
return umem->pages[addr >> PAGE_SHIFT].dma + (addr & (PAGE_SIZE - 1));
}
+
+/* Reuse-queue aware version of FILL queue helpers */
+static inline u64 *xsk_umem_peek_addr_rq(struct xdp_umem *umem, u64 *addr)
+{
+ struct xdp_umem_fq_reuse *rq = umem->fq_reuse;
+
+ if (!rq->length)
+ return xsk_umem_peek_addr(umem, addr);
+
+ *addr = rq->handles[rq->length - 1];
+ return addr;
+}
+
+static inline void xsk_umem_discard_addr_rq(struct xdp_umem *umem)
+{
+ struct xdp_umem_fq_reuse *rq = umem->fq_reuse;
+
+ if (!rq->length)
+ xsk_umem_discard_addr(umem);
+ else
+ rq->length--;
+}
+
+static inline void xsk_umem_fq_reuse(struct xdp_umem *umem, u64 addr)
+{
+ struct xdp_umem_fq_reuse *rq = umem->fq_reuse;
+
+ rq->handles[rq->length++] = addr;
+}
#else
static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
{
@@ -128,6 +168,21 @@ static inline void xsk_umem_consume_tx_done(struct xdp_umem *umem)
{
}
+static inline struct xdp_umem_fq_reuse *xsk_reuseq_prepare(u32 nentries)
+{
+ return NULL;
+}
+
+static inline struct xdp_umem_fq_reuse *xsk_reuseq_swap(
+ struct xdp_umem *umem,
+ struct xdp_umem_fq_reuse *newq)
+{
+ return NULL;
+}
+static inline void xsk_reuseq_free(struct xdp_umem_fq_reuse *rq)
+{
+}
+
static inline char *xdp_umem_get_data(struct xdp_umem *umem, u64 addr)
{
return NULL;
@@ -137,6 +192,20 @@ static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr)
{
return 0;
}
+
+static inline u64 *xsk_umem_peek_addr_rq(struct xdp_umem *umem, u64 *addr)
+{
+ return NULL;
+}
+
+static inline void xsk_umem_discard_addr_rq(struct xdp_umem *umem)
+{
+}
+
+static inline void xsk_umem_fq_reuse(struct xdp_umem *umem, u64 addr)
+{
+}
+
#endif /* CONFIG_XDP_SOCKETS */
#endif /* _LINUX_XDP_SOCK_H */