Merge tag 'for-linus-unmerged' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma

Pull rdma updates from Jason Gunthorpe:
 "Doug and I are at a conference next week so if another PR is sent I
  expect it to only be bug fixes. Parav noted yesterday that there are
  some fringe case behavior changes in his work that he would like to
  fix, and I see that Intel has a number of rc looking patches for HFI1
  they posted yesterday.

  Parav is again the biggest contributor by patch count with his ongoing
  work to enable container support in the RDMA stack, followed by Leon
  doing syzkaller inspired cleanups, though most of the actual fixing
  went to RC.

  There is one uncomfortable series here fixing the user ABI to actually
  work as intended in 32 bit mode. There are lots of notes in the commit
  messages, but the basic summary is we don't think there is an actual
  32 bit kernel user of drivers/infiniband for several good reasons.

  However we are seeing people want to use a 32 bit user space with 64
  bit kernel, which didn't completely work today. So in fixing it we
  required a 32 bit rxe user to upgrade their userspace. rxe users are
  still already quite rare and we think a 32 bit one is non-existing.

   - Fix RDMA uapi headers to actually compile in userspace and be more
     complete

   - Three shared with netdev pull requests from Mellanox:

      * 7 patches, mostly to net with 1 IB related one at the back).
        This series addresses an IRQ performance issue (patch 1),
        cleanups related to the fix for the IRQ performance problem
        (patches 2-6), and then extends the fragmented completion queue
        support that already exists in the net side of the driver to the
        ib side of the driver (patch 7).

      * Mostly IB, with 5 patches to net that are needed to support the
        remaining 10 patches to the IB subsystem. This series extends
        the current 'representor' framework when the mlx5 driver is in
        switchdev mode from being a netdev only construct to being a
        netdev/IB dev construct. The IB dev is limited to raw Eth queue
        pairs only, but by having an IB dev of this type attached to the
        representor for a switchdev port, it enables DPDK to work on the
        switchdev device.

      * All net related, but needed as infrastructure for the rdma
        driver

   - Updates for the hns, i40iw, bnxt_re, cxgb3, cxgb4, hns drivers

   - SRP performance updates

   - IB uverbs write path cleanup patch series from Leon

   - Add RDMA_CM support to ib_srpt. This is disabled by default. Users
     need to set the port for ib_srpt to listen on in configfs in order
     for it to be enabled
     (/sys/kernel/config/target/srpt/discovery_auth/rdma_cm_port)

   - TSO and Scatter FCS support in mlx4

   - Refactor of modify_qp routine to resolve problems seen while
     working on new code that is forthcoming

   - More refactoring and updates of RDMA CM for containers support from
     Parav

   - mlx5 'fine grained packet pacing', 'ipsec offload' and 'device
     memory' user API features

   - Infrastructure updates for the new IOCTL interface, based on
     increased usage

   - ABI compatibility bug fixes to fully support 32 bit userspace on 64
     bit kernel as was originally intended. See the commit messages for
     extensive details

   - Syzkaller bugs and code cleanups motivated by them"

* tag 'for-linus-unmerged' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (199 commits)
  IB/rxe: Fix for oops in rxe_register_device on ppc64le arch
  IB/mlx5: Device memory mr registration support
  net/mlx5: Mkey creation command adjustments
  IB/mlx5: Device memory support in mlx5_ib
  net/mlx5: Query device memory capabilities
  IB/uverbs: Add device memory registration ioctl support
  IB/uverbs: Add alloc/free dm uverbs ioctl support
  IB/uverbs: Add device memory capabilities reporting
  IB/uverbs: Expose device memory capabilities to user
  RDMA/qedr: Fix wmb usage in qedr
  IB/rxe: Removed GID add/del dummy routines
  RDMA/qedr: Zero stack memory before copying to user space
  IB/mlx5: Add ability to hash by IPSEC_SPI when creating a TIR
  IB/mlx5: Add information for querying IPsec capabilities
  IB/mlx5: Add IPsec support for egress and ingress
  {net,IB}/mlx5: Add ipsec helper
  IB/mlx5: Add modify_flow_action_esp verb
  IB/mlx5: Add implementation for create and destroy action_xfrm
  IB/uverbs: Introduce ESP steering match filter
  IB/uverbs: Add modify ESP flow_action
  ...

1 files changed, 171 insertions, 41 deletions

diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 6eb174753acf..9fc8a825aa28 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -64,6 +64,8 @@
 #include <linux/cgroup_rdma.h>
 #include <uapi/rdma/ib_user_verbs.h>
 #include <rdma/restrack.h>
+#include <uapi/rdma/rdma_user_ioctl.h>
+#include <uapi/rdma/ib_user_ioctl_verbs.h>
 
 #define IB_FW_VERSION_NAME_MAX	ETHTOOL_FWVERS_LEN
 
@@ -90,8 +92,11 @@ enum ib_gid_type {
 
 #define ROCE_V2_UDP_DPORT      4791
 struct ib_gid_attr {
-	enum ib_gid_type	gid_type;
 	struct net_device	*ndev;
+	struct ib_device	*device;
+	enum ib_gid_type	gid_type;
+	u16			index;
+	u8			port_num;
 };
 
 enum rdma_node_type {
@@ -316,6 +321,18 @@ struct ib_cq_caps {
 	u16     max_cq_moderation_period;
 };
 
+struct ib_dm_mr_attr {
+	u64		length;
+	u64		offset;
+	u32		access_flags;
+};
+
+struct ib_dm_alloc_attr {
+	u64	length;
+	u32	alignment;
+	u32	flags;
+};
+
 struct ib_device_attr {
 	u64			fw_ver;
 	__be64			sys_image_guid;
@@ -367,6 +384,7 @@ struct ib_device_attr {
 	u32			raw_packet_caps; /* Use ib_raw_packet_caps enum */
 	struct ib_tm_caps	tm_caps;
 	struct ib_cq_caps       cq_caps;
+	u64			max_dm_size;
 };
 
 enum ib_mtu {
@@ -469,6 +487,9 @@ enum ib_port_speed {
 
 /**
  * struct rdma_hw_stats
+ * @lock - Mutex to protect parallel write access to lifespan and values
+ *    of counters, which are 64bits and not guaranteeed to be written
+ *    atomicaly on 32bits systems.
  * @timestamp - Used by the core code to track when the last update was
  * @lifespan - Used by the core code to determine how old the counters
  *   should be before being updated again.  Stored in jiffies, defaults
@@ -484,6 +505,7 @@ enum ib_port_speed {
  *   filled in by the drivers get_stats routine
  */
 struct rdma_hw_stats {
+	struct mutex	lock; /* Protect lifespan and values[] */
 	unsigned long	timestamp;
 	unsigned long	lifespan;
 	const char * const *names;
@@ -1755,6 +1777,14 @@ struct ib_qp {
 	struct rdma_restrack_entry     res;
 };
 
+struct ib_dm {
+	struct ib_device  *device;
+	u32		   length;
+	u32		   flags;
+	struct ib_uobject *uobject;
+	atomic_t	   usecnt;
+};
+
 struct ib_mr {
 	struct ib_device  *device;
 	struct ib_pd	  *pd;
@@ -1768,6 +1798,13 @@ struct ib_mr {
 		struct ib_uobject	*uobject;	/* user */
 		struct list_head	qp_entry;	/* FR */
 	};
+
+	struct ib_dm      *dm;
+
+	/*
+	 * Implementation details of the RDMA core, don't use in drivers:
+	 */
+	struct rdma_restrack_entry res;
 };
 
 struct ib_mw {
@@ -1810,6 +1847,7 @@ enum ib_flow_spec_type {
 	/* L3 header*/
 	IB_FLOW_SPEC_IPV4		= 0x30,
 	IB_FLOW_SPEC_IPV6		= 0x31,
+	IB_FLOW_SPEC_ESP                = 0x34,
 	/* L4 headers*/
 	IB_FLOW_SPEC_TCP		= 0x40,
 	IB_FLOW_SPEC_UDP		= 0x41,
@@ -1818,6 +1856,7 @@ enum ib_flow_spec_type {
 	/* Actions */
 	IB_FLOW_SPEC_ACTION_TAG         = 0x1000,
 	IB_FLOW_SPEC_ACTION_DROP        = 0x1001,
+	IB_FLOW_SPEC_ACTION_HANDLE	= 0x1002,
 };
 #define IB_FLOW_SPEC_LAYER_MASK	0xF0
 #define IB_FLOW_SPEC_SUPPORT_LAYERS 8
@@ -1835,7 +1874,8 @@ enum ib_flow_domain {
 
 enum ib_flow_flags {
 	IB_FLOW_ATTR_FLAGS_DONT_TRAP = 1UL << 1, /* Continue match, no steal */
-	IB_FLOW_ATTR_FLAGS_RESERVED  = 1UL << 2  /* Must be last */
+	IB_FLOW_ATTR_FLAGS_EGRESS = 1UL << 2, /* Egress flow */
+	IB_FLOW_ATTR_FLAGS_RESERVED  = 1UL << 3  /* Must be last */
 };
 
 struct ib_flow_eth_filter {
@@ -1940,6 +1980,20 @@ struct ib_flow_spec_tunnel {
 	struct ib_flow_tunnel_filter  mask;
 };
 
+struct ib_flow_esp_filter {
+	__be32	spi;
+	__be32  seq;
+	/* Must be last */
+	u8	real_sz[0];
+};
+
+struct ib_flow_spec_esp {
+	u32                           type;
+	u16			      size;
+	struct ib_flow_esp_filter     val;
+	struct ib_flow_esp_filter     mask;
+};
+
 struct ib_flow_spec_action_tag {
 	enum ib_flow_spec_type	      type;
 	u16			      size;
@@ -1951,6 +2005,12 @@ struct ib_flow_spec_action_drop {
 	u16			      size;
 };
 
+struct ib_flow_spec_action_handle {
+	enum ib_flow_spec_type	      type;
+	u16			      size;
+	struct ib_flow_action	     *act;
+};
+
 union ib_flow_spec {
 	struct {
 		u32			type;
@@ -1962,8 +2022,10 @@ union ib_flow_spec {
 	struct ib_flow_spec_tcp_udp	tcp_udp;
 	struct ib_flow_spec_ipv6        ipv6;
 	struct ib_flow_spec_tunnel      tunnel;
+	struct ib_flow_spec_esp		esp;
 	struct ib_flow_spec_action_tag  flow_tag;
 	struct ib_flow_spec_action_drop drop;
+	struct ib_flow_spec_action_handle action;
 };
 
 struct ib_flow_attr {
@@ -1984,6 +2046,64 @@ struct ib_flow {
 	struct ib_uobject	*uobject;
 };
 
+enum ib_flow_action_type {
+	IB_FLOW_ACTION_UNSPECIFIED,
+	IB_FLOW_ACTION_ESP = 1,
+};
+
+struct ib_flow_action_attrs_esp_keymats {
+	enum ib_uverbs_flow_action_esp_keymat			protocol;
+	union {
+		struct ib_uverbs_flow_action_esp_keymat_aes_gcm aes_gcm;
+	} keymat;
+};
+
+struct ib_flow_action_attrs_esp_replays {
+	enum ib_uverbs_flow_action_esp_replay			protocol;
+	union {
+		struct ib_uverbs_flow_action_esp_replay_bmp	bmp;
+	} replay;
+};
+
+enum ib_flow_action_attrs_esp_flags {
+	/* All user-space flags at the top: Use enum ib_uverbs_flow_action_esp_flags
+	 * This is done in order to share the same flags between user-space and
+	 * kernel and spare an unnecessary translation.
+	 */
+
+	/* Kernel flags */
+	IB_FLOW_ACTION_ESP_FLAGS_ESN_TRIGGERED	= 1ULL << 32,
+	IB_FLOW_ACTION_ESP_FLAGS_MOD_ESP_ATTRS	= 1ULL << 33,
+};
+
+struct ib_flow_spec_list {
+	struct ib_flow_spec_list	*next;
+	union ib_flow_spec		spec;
+};
+
+struct ib_flow_action_attrs_esp {
+	struct ib_flow_action_attrs_esp_keymats		*keymat;
+	struct ib_flow_action_attrs_esp_replays		*replay;
+	struct ib_flow_spec_list			*encap;
+	/* Used only if IB_FLOW_ACTION_ESP_FLAGS_ESN_TRIGGERED is enabled.
+	 * Value of 0 is a valid value.
+	 */
+	u32						esn;
+	u32						spi;
+	u32						seq;
+	u32						tfc_pad;
+	/* Use enum ib_flow_action_attrs_esp_flags */
+	u64						flags;
+	u64						hard_limit_pkts;
+};
+
+struct ib_flow_action {
+	struct ib_device		*device;
+	struct ib_uobject		*uobject;
+	enum ib_flow_action_type	type;
+	atomic_t			usecnt;
+};
+
 struct ib_mad_hdr;
 struct ib_grh;
 
@@ -2060,6 +2180,8 @@ struct ib_port_pkey_list {
 	struct list_head              pkey_list;
 };
 
+struct uverbs_attr_bundle;
+
 struct ib_device {
 	/* Do not access @dma_device directly from ULP nor from HW drivers. */
 	struct device                *dma_device;
@@ -2127,37 +2249,36 @@ struct ib_device {
 	 */
 	struct net_device	  *(*get_netdev)(struct ib_device *device,
 						 u8 port_num);
+	/* query_gid should be return GID value for @device, when @port_num
+	 * link layer is either IB or iWarp. It is no-op if @port_num port
+	 * is RoCE link layer.
+	 */
 	int		           (*query_gid)(struct ib_device *device,
 						u8 port_num, int index,
 						union ib_gid *gid);
-	/* When calling add_gid, the HW vendor's driver should
-	 * add the gid of device @device at gid index @index of
-	 * port @port_num to be @gid. Meta-info of that gid (for example,
-	 * the network device related to this gid is available
-	 * at @attr. @context allows the HW vendor driver to store extra
-	 * information together with a GID entry. The HW vendor may allocate
-	 * memory to contain this information and store it in @context when a
-	 * new GID entry is written to. Params are consistent until the next
-	 * call of add_gid or delete_gid. The function should return 0 on
+	/* When calling add_gid, the HW vendor's driver should add the gid
+	 * of device of port at gid index available at @attr. Meta-info of
+	 * that gid (for example, the network device related to this gid) is
+	 * available at @attr. @context allows the HW vendor driver to store
+	 * extra information together with a GID entry. The HW vendor driver may
+	 * allocate memory to contain this information and store it in @context
+	 * when a new GID entry is written to. Params are consistent until the
+	 * next call of add_gid or delete_gid. The function should return 0 on
 	 * success or error otherwise. The function could be called
-	 * concurrently for different ports. This function is only called
-	 * when roce_gid_table is used.
+	 * concurrently for different ports. This function is only called when
+	 * roce_gid_table is used.
 	 */
-	int		           (*add_gid)(struct ib_device *device,
-					      u8 port_num,
-					      unsigned int index,
-					      const union ib_gid *gid,
+	int		           (*add_gid)(const union ib_gid *gid,
 					      const struct ib_gid_attr *attr,
 					      void **context);
 	/* When calling del_gid, the HW vendor's driver should delete the
-	 * gid of device @device at gid index @index of port @port_num.
+	 * gid of device @device at gid index gid_index of port port_num
+	 * available in @attr.
 	 * Upon the deletion of a GID entry, the HW vendor must free any
 	 * allocated memory. The caller will clear @context afterwards.
 	 * This function is only called when roce_gid_table is used.
 	 */
-	int		           (*del_gid)(struct ib_device *device,
-					      u8 port_num,
-					      unsigned int index,
+	int		           (*del_gid)(const struct ib_gid_attr *attr,
 					      void **context);
 	int		           (*query_pkey)(struct ib_device *device,
 						 u8 port_num, u16 index, u16 *pkey);
@@ -2315,6 +2436,21 @@ struct ib_device {
 							   struct ib_rwq_ind_table_init_attr *init_attr,
 							   struct ib_udata *udata);
 	int                        (*destroy_rwq_ind_table)(struct ib_rwq_ind_table *wq_ind_table);
+	struct ib_flow_action *	   (*create_flow_action_esp)(struct ib_device *device,
+							     const struct ib_flow_action_attrs_esp *attr,
+							     struct uverbs_attr_bundle *attrs);
+	int			   (*destroy_flow_action)(struct ib_flow_action *action);
+	int			   (*modify_flow_action_esp)(struct ib_flow_action *action,
+							     const struct ib_flow_action_attrs_esp *attr,
+							     struct uverbs_attr_bundle *attrs);
+	struct ib_dm *             (*alloc_dm)(struct ib_device *device,
+					       struct ib_ucontext *context,
+					       struct ib_dm_alloc_attr *attr,
+					       struct uverbs_attr_bundle *attrs);
+	int                        (*dealloc_dm)(struct ib_dm *dm);
+	struct ib_mr *             (*reg_dm_mr)(struct ib_pd *pd, struct ib_dm *dm,
+						struct ib_dm_mr_attr *attr,
+						struct uverbs_attr_bundle *attrs);
 	/**
 	 * rdma netdev operation
 	 *
@@ -2376,6 +2512,7 @@ struct ib_device {
 						     int comp_vector);
 
 	struct uverbs_root_spec		*specs_root;
+	enum rdma_driver_id		driver_id;
 };
 
 struct ib_client {
@@ -2435,11 +2572,9 @@ static inline int ib_copy_to_udata(struct ib_udata *udata, void *src, size_t len
 	return copy_to_user(udata->outbuf, src, len) ? -EFAULT : 0;
 }
 
-static inline bool ib_is_udata_cleared(struct ib_udata *udata,
-				       size_t offset,
-				       size_t len)
+static inline bool ib_is_buffer_cleared(const void __user *p,
+					size_t len)
 {
-	const void __user *p = udata->inbuf + offset;
 	bool ret;
 	u8 *buf;
 
@@ -2455,6 +2590,13 @@ static inline bool ib_is_udata_cleared(struct ib_udata *udata,
 	return ret;
 }
 
+static inline bool ib_is_udata_cleared(struct ib_udata *udata,
+				       size_t offset,
+				       size_t len)
+{
+	return ib_is_buffer_cleared(udata->inbuf + offset, len);
+}
+
 /**
  * ib_modify_qp_is_ok - Check that the supplied attribute mask
  * contains all required attributes and no attributes not allowed for
@@ -2471,9 +2613,9 @@ static inline bool ib_is_udata_cleared(struct ib_udata *udata,
  * transition from cur_state to next_state is allowed by the IB spec,
  * and that the attribute mask supplied is allowed for the transition.
  */
-int ib_modify_qp_is_ok(enum ib_qp_state cur_state, enum ib_qp_state next_state,
-		       enum ib_qp_type type, enum ib_qp_attr_mask mask,
-		       enum rdma_link_layer ll);
+bool ib_modify_qp_is_ok(enum ib_qp_state cur_state, enum ib_qp_state next_state,
+			enum ib_qp_type type, enum ib_qp_attr_mask mask,
+			enum rdma_link_layer ll);
 
 void ib_register_event_handler(struct ib_event_handler *event_handler);
 void ib_unregister_event_handler(struct ib_event_handler *event_handler);
@@ -2848,7 +2990,7 @@ int ib_modify_port(struct ib_device *device,
 		   struct ib_port_modify *port_modify);
 
 int ib_find_gid(struct ib_device *device, union ib_gid *gid,
-		struct net_device *ndev, u8 *port_num, u16 *index);
+		u8 *port_num, u16 *index);
 
 int ib_find_pkey(struct ib_device *device,
 		 u8 port_num, u16 pkey, u16 *index);
@@ -3217,18 +3359,6 @@ static inline int ib_poll_cq(struct ib_cq *cq, int num_entries,
 }
 
 /**
- * ib_peek_cq - Returns the number of unreaped completions currently
- *   on the specified CQ.
- * @cq: The CQ to peek.
- * @wc_cnt: A minimum number of unreaped completions to check for.
- *
- * If the number of unreaped completions is greater than or equal to wc_cnt,
- * this function returns wc_cnt, otherwise, it returns the actual number of
- * unreaped completions.
- */
-int ib_peek_cq(struct ib_cq *cq, int wc_cnt);
-
-/**
  * ib_req_notify_cq - Request completion notification on a CQ.
  * @cq: The CQ to generate an event for.
  * @flags: