Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2019-07-03

The following pull-request contains BPF updates for your *net-next* tree.

There is a minor merge conflict in mlx5 due to 8960b38932be ("linux/dim:
Rename externally used net_dim members") which has been pulled into your
tree in the meantime, but resolution seems not that bad ... getting current
bpf-next out now before there's coming more on mlx5. ;) I'm Cc'ing Saeed
just so he's aware of the resolution below:

** First conflict in drivers/net/ethernet/mellanox/mlx5/core/en_main.c:

  <<<<<<< HEAD
  static int mlx5e_open_cq(struct mlx5e_channel *c,
                           struct dim_cq_moder moder,
                           struct mlx5e_cq_param *param,
                           struct mlx5e_cq *cq)
  =======
  int mlx5e_open_cq(struct mlx5e_channel *c, struct net_dim_cq_moder moder,
                    struct mlx5e_cq_param *param, struct mlx5e_cq *cq)
  >>>>>>> e5a3e259ef239f443951d401db10db7d426c9497

Resolution is to take the second chunk and rename net_dim_cq_moder into
dim_cq_moder. Also the signature for mlx5e_open_cq() in ...

  drivers/net/ethernet/mellanox/mlx5/core/en.h +977

... and in mlx5e_open_xsk() ...

  drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c +64

... needs the same rename from net_dim_cq_moder into dim_cq_moder.

** Second conflict in drivers/net/ethernet/mellanox/mlx5/core/en_main.c:

  <<<<<<< HEAD
          int cpu = cpumask_first(mlx5_comp_irq_get_affinity_mask(priv->mdev, ix));
          struct dim_cq_moder icocq_moder = {0, 0};
          struct net_device *netdev = priv->netdev;
          struct mlx5e_channel *c;
          unsigned int irq;
  =======
          struct net_dim_cq_moder icocq_moder = {0, 0};
  >>>>>>> e5a3e259ef239f443951d401db10db7d426c9497

Take the second chunk and rename net_dim_cq_moder into dim_cq_moder
as well.

Let me know if you run into any issues. Anyway, the main changes are:

1) Long-awaited AF_XDP support for mlx5e driver, from Maxim.

2) Addition of two new per-cgroup BPF hooks for getsockopt and
   setsockopt along with a new sockopt program type which allows more
   fine-grained pass/reject settings for containers. Also add a sock_ops
   callback that can be selectively enabled on a per-socket basis and is
   executed for every RTT to help tracking TCP statistics, both features
   from Stanislav.

3) Follow-up fix from loops in precision tracking which was not propagating
   precision marks and as a result verifier assumed that some branches were
   not taken and therefore wrongly removed as dead code, from Alexei.

4) Fix BPF cgroup release synchronization race which could lead to a
   double-free if a leaf's cgroup_bpf object is released and a new BPF
   program is attached to the one of ancestor cgroups in parallel, from Roman.

5) Support for bulking XDP_TX on veth devices which improves performance
   in some cases by around 9%, from Toshiaki.

6) Allow for lookups into BPF devmap and improve feedback when calling into
   bpf_redirect_map() as lookup is now performed right away in the helper
   itself, from Toke.

7) Add support for fq's Earliest Departure Time to the Host Bandwidth
   Manager (HBM) sample BPF program, from Lawrence.

8) Various cleanups and minor fixes all over the place from many others.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 140 insertions, 15 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 3281ace5e126..f0d77eb66acf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -137,6 +137,7 @@ struct page_pool;
 #define MLX5E_MAX_NUM_CHANNELS         (MLX5E_INDIR_RQT_SIZE >> 1)
 #define MLX5E_MAX_NUM_SQS              (MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC)
 #define MLX5E_TX_CQ_POLL_BUDGET        128
+#define MLX5E_TX_XSK_POLL_BUDGET       64
 #define MLX5E_SQ_RECOVER_MIN_INTERVAL  500 /* msecs */
 
 #define MLX5E_UMR_WQE_INLINE_SZ \
@@ -155,6 +156,11 @@ do {                                                            \
 			    ##__VA_ARGS__);                     \
 } while (0)
 
+enum mlx5e_rq_group {
+	MLX5E_RQ_GROUP_REGULAR,
+	MLX5E_RQ_GROUP_XSK,
+	MLX5E_NUM_RQ_GROUPS /* Keep last. */
+};
 
 static inline u16 mlx5_min_rx_wqes(int wq_type, u32 wq_size)
 {
@@ -179,7 +185,8 @@ static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev)
 /* Use this function to get max num channels after netdev was created */
 static inline int mlx5e_get_netdev_max_channels(struct net_device *netdev)
 {
-	return min_t(unsigned int, netdev->num_rx_queues,
+	return min_t(unsigned int,
+		     netdev->num_rx_queues / MLX5E_NUM_RQ_GROUPS,
 		     netdev->num_tx_queues);
 }
 
@@ -250,6 +257,7 @@ struct mlx5e_params {
 	u32 lro_timeout;
 	u32 pflags;
 	struct bpf_prog *xdp_prog;
+	struct mlx5e_xsk *xsk;
 	unsigned int sw_mtu;
 	int hard_mtu;
 };
@@ -348,6 +356,13 @@ enum {
 
 struct mlx5e_sq_wqe_info {
 	u8  opcode;
+
+	/* Auxiliary data for different opcodes. */
+	union {
+		struct {
+			struct mlx5e_rq *rq;
+		} umr;
+	};
 };
 
 struct mlx5e_txqsq {
@@ -392,14 +407,55 @@ struct mlx5e_txqsq {
 } ____cacheline_aligned_in_smp;
 
 struct mlx5e_dma_info {
-	struct page     *page;
-	dma_addr_t      addr;
+	dma_addr_t addr;
+	union {
+		struct page *page;
+		struct {
+			u64 handle;
+			void *data;
+		} xsk;
+	};
+};
+
+/* XDP packets can be transmitted in different ways. On completion, we need to
+ * distinguish between them to clean up things in a proper way.
+ */
+enum mlx5e_xdp_xmit_mode {
+	/* An xdp_frame was transmitted due to either XDP_REDIRECT from another
+	 * device or XDP_TX from an XSK RQ. The frame has to be unmapped and
+	 * returned.
+	 */
+	MLX5E_XDP_XMIT_MODE_FRAME,
+
+	/* The xdp_frame was created in place as a result of XDP_TX from a
+	 * regular RQ. No DMA remapping happened, and the page belongs to us.
+	 */
+	MLX5E_XDP_XMIT_MODE_PAGE,
+
+	/* No xdp_frame was created at all, the transmit happened from a UMEM
+	 * page. The UMEM Completion Ring producer pointer has to be increased.
+	 */
+	MLX5E_XDP_XMIT_MODE_XSK,
 };
 
 struct mlx5e_xdp_info {
-	struct xdp_frame      *xdpf;
-	dma_addr_t            dma_addr;
-	struct mlx5e_dma_info di;
+	enum mlx5e_xdp_xmit_mode mode;
+	union {
+		struct {
+			struct xdp_frame *xdpf;
+			dma_addr_t dma_addr;
+		} frame;
+		struct {
+			struct mlx5e_rq *rq;
+			struct mlx5e_dma_info di;
+		} page;
+	};
+};
+
+struct mlx5e_xdp_xmit_data {
+	dma_addr_t  dma_addr;
+	void       *data;
+	u32         len;
 };
 
 struct mlx5e_xdp_info_fifo {
@@ -425,8 +481,12 @@ struct mlx5e_xdp_mpwqe {
 };
 
 struct mlx5e_xdpsq;
-typedef bool (*mlx5e_fp_xmit_xdp_frame)(struct mlx5e_xdpsq*,
-					struct mlx5e_xdp_info*);
+typedef int (*mlx5e_fp_xmit_xdp_frame_check)(struct mlx5e_xdpsq *);
+typedef bool (*mlx5e_fp_xmit_xdp_frame)(struct mlx5e_xdpsq *,
+					struct mlx5e_xdp_xmit_data *,
+					struct mlx5e_xdp_info *,
+					int);
+
 struct mlx5e_xdpsq {
 	/* data path */
 
@@ -443,8 +503,10 @@ struct mlx5e_xdpsq {
 	struct mlx5e_cq            cq;
 
 	/* read only */
+	struct xdp_umem           *umem;
 	struct mlx5_wq_cyc         wq;
 	struct mlx5e_xdpsq_stats  *stats;
+	mlx5e_fp_xmit_xdp_frame_check xmit_xdp_frame_check;
 	mlx5e_fp_xmit_xdp_frame    xmit_xdp_frame;
 	struct {
 		struct mlx5e_xdp_wqe_info *wqe_info;
@@ -571,9 +633,11 @@ struct mlx5e_rq {
 			u8                     log_stride_sz;
 			u8                     umr_in_progress;
 			u8                     umr_last_bulk;
+			u8                     umr_completed;
 		} mpwqe;
 	};
 	struct {
+		u16            umem_headroom;
 		u16            headroom;
 		u8             map_dir;   /* dma map direction */
 	} buff;
@@ -600,10 +664,14 @@ struct mlx5e_rq {
 
 	/* XDP */
 	struct bpf_prog       *xdp_prog;
-	struct mlx5e_xdpsq     xdpsq;
+	struct mlx5e_xdpsq    *xdpsq;
 	DECLARE_BITMAP(flags, 8);
 	struct page_pool      *page_pool;
 
+	/* AF_XDP zero-copy */
+	struct zero_copy_allocator zca;
+	struct xdp_umem       *umem;
+
 	/* control */
 	struct mlx5_wq_ctrl    wq_ctrl;
 	__be32                 mkey_be;
@@ -616,9 +684,15 @@ struct mlx5e_rq {
 	struct xdp_rxq_info    xdp_rxq;
 } ____cacheline_aligned_in_smp;
 
+enum mlx5e_channel_state {
+	MLX5E_CHANNEL_STATE_XSK,
+	MLX5E_CHANNEL_NUM_STATES
+};
+
 struct mlx5e_channel {
 	/* data path */
 	struct mlx5e_rq            rq;
+	struct mlx5e_xdpsq         rq_xdpsq;
 	struct mlx5e_txqsq         sq[MLX5E_MAX_NUM_TC];
 	struct mlx5e_icosq         icosq;   /* internal control operations */
 	bool                       xdp;
@@ -631,6 +705,13 @@ struct mlx5e_channel {
 	/* XDP_REDIRECT */
 	struct mlx5e_xdpsq         xdpsq;
 
+	/* AF_XDP zero-copy */
+	struct mlx5e_rq            xskrq;
+	struct mlx5e_xdpsq         xsksq;
+	struct mlx5e_icosq         xskicosq;
+	/* xskicosq can be accessed from any CPU - the spinlock protects it. */
+	spinlock_t                 xskicosq_lock;
+
 	/* data path - accessed per napi poll */
 	struct irq_desc *irq_desc;
 	struct mlx5e_ch_stats     *stats;
@@ -639,6 +720,7 @@ struct mlx5e_channel {
 	struct mlx5e_priv         *priv;
 	struct mlx5_core_dev      *mdev;
 	struct hwtstamp_config    *tstamp;
+	DECLARE_BITMAP(state, MLX5E_CHANNEL_NUM_STATES);
 	int                        ix;
 	int                        cpu;
 	cpumask_var_t              xps_cpumask;
@@ -654,14 +736,17 @@ struct mlx5e_channel_stats {
 	struct mlx5e_ch_stats ch;
 	struct mlx5e_sq_stats sq[MLX5E_MAX_NUM_TC];
 	struct mlx5e_rq_stats rq;
+	struct mlx5e_rq_stats xskrq;
 	struct mlx5e_xdpsq_stats rq_xdpsq;
 	struct mlx5e_xdpsq_stats xdpsq;
+	struct mlx5e_xdpsq_stats xsksq;
 } ____cacheline_aligned_in_smp;
 
 enum {
 	MLX5E_STATE_OPENED,
 	MLX5E_STATE_DESTROYING,
 	MLX5E_STATE_XDP_TX_ENABLED,
+	MLX5E_STATE_XDP_OPEN,
 };
 
 struct mlx5e_rqt {
@@ -694,6 +779,17 @@ struct mlx5e_modify_sq_param {
 	int rl_index;
 };
 
+struct mlx5e_xsk {
+	/* UMEMs are stored separately from channels, because we don't want to
+	 * lose them when channels are recreated. The kernel also stores UMEMs,
+	 * but it doesn't distinguish between zero-copy and non-zero-copy UMEMs,
+	 * so rely on our mechanism.
+	 */
+	struct xdp_umem **umems;
+	u16 refcnt;
+	bool ever_used;
+};
+
 struct mlx5e_priv {
 	/* priv data path fields - start */
 	struct mlx5e_txqsq *txq2sq[MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC];
@@ -714,6 +810,7 @@ struct mlx5e_priv {
 	struct mlx5e_tir           indir_tir[MLX5E_NUM_INDIR_TIRS];
 	struct mlx5e_tir           inner_indir_tir[MLX5E_NUM_INDIR_TIRS];
 	struct mlx5e_tir           direct_tir[MLX5E_MAX_NUM_CHANNELS];
+	struct mlx5e_tir           xsk_tir[MLX5E_MAX_NUM_CHANNELS];
 	struct mlx5e_rss_params    rss_params;
 	u32                        tx_rates[MLX5E_MAX_NUM_SQS];
 
@@ -750,6 +847,7 @@ struct mlx5e_priv {
 	struct mlx5e_tls          *tls;
 #endif
 	struct devlink_health_reporter *tx_reporter;
+	struct mlx5e_xsk           xsk;
 };
 
 struct mlx5e_profile {
@@ -794,11 +892,13 @@ bool mlx5e_striding_rq_possible(struct mlx5_core_dev *mdev,
 				struct mlx5e_params *params);
 
 void mlx5e_page_dma_unmap(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info);
-void mlx5e_page_release(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info,
-			bool recycle);
+void mlx5e_page_release_dynamic(struct mlx5e_rq *rq,
+				struct mlx5e_dma_info *dma_info,
+				bool recycle);
 void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq);
+void mlx5e_poll_ico_cq(struct mlx5e_cq *cq);
 bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq);
 void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix);
 void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix);
@@ -854,6 +954,30 @@ void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_rss_params *rss_params,
 void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen);
 struct mlx5e_tirc_config mlx5e_tirc_get_default_config(enum mlx5e_traffic_types tt);
 
+struct mlx5e_xsk_param;
+
+struct mlx5e_rq_param;
+int mlx5e_open_rq(struct mlx5e_channel *c, struct mlx5e_params *params,
+		  struct mlx5e_rq_param *param, struct mlx5e_xsk_param *xsk,
+		  struct xdp_umem *umem, struct mlx5e_rq *rq);
+int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time);
+void mlx5e_deactivate_rq(struct mlx5e_rq *rq);
+void mlx5e_close_rq(struct mlx5e_rq *rq);
+
+struct mlx5e_sq_param;
+int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params,
+		     struct mlx5e_sq_param *param, struct mlx5e_icosq *sq);
+void mlx5e_close_icosq(struct mlx5e_icosq *sq);
+int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params,
+		     struct mlx5e_sq_param *param, struct xdp_umem *umem,
+		     struct mlx5e_xdpsq *sq, bool is_redirect);
+void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq);
+
+struct mlx5e_cq_param;
+int mlx5e_open_cq(struct mlx5e_channel *c, struct dim_cq_moder moder,
+		  struct mlx5e_cq_param *param, struct mlx5e_cq *cq);
+void mlx5e_close_cq(struct mlx5e_cq *cq);
+
 int mlx5e_open_locked(struct net_device *netdev);
 int mlx5e_close_locked(struct net_device *netdev);
 
@@ -1024,10 +1148,10 @@ int mlx5e_create_indirect_rqt(struct mlx5e_priv *priv);
 int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc);
 void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc);
 
-int mlx5e_create_direct_rqts(struct mlx5e_priv *priv);
-void mlx5e_destroy_direct_rqts(struct mlx5e_priv *priv);
-int mlx5e_create_direct_tirs(struct mlx5e_priv *priv);
-void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv);
+int mlx5e_create_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs);
+void mlx5e_destroy_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs);
+int mlx5e_create_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs);
+void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs);
 void mlx5e_destroy_rqt(struct mlx5e_priv *priv, struct mlx5e_rqt *rqt);
 
 int mlx5e_create_tis(struct mlx5_core_dev *mdev, int tc,
@@ -1097,6 +1221,7 @@ void mlx5e_detach_netdev(struct mlx5e_priv *priv);
 void mlx5e_destroy_netdev(struct mlx5e_priv *priv);
 void mlx5e_set_netdev_mtu_boundaries(struct mlx5e_priv *priv);
 void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
+			    struct mlx5e_xsk *xsk,
 			    struct mlx5e_rss_params *rss_params,
 			    struct mlx5e_params *params,
 			    u16 max_channels, u16 mtu);