Merge branch 'mlx5-rd-sgl' into rdma.git for-next

From Yamin Friedman:

====================
This series from Yamin implements long standing "TODO" existed in rw.c. It
allows the driver to specify a cut-over point where it is faster to build
a lkey MR rather than do a large SGL for RDMA READ operations.

mlx5 HW gets a notable performane boost by switching to MRs.
====================

Based on the mlx5-next branch from
git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux for
dependencies

* branch 'mlx5-rd-sgl': (3 commits)
  RDMA/mlx5: Add capability for max sge to get optimized performance
  RDMA/rw: Support threshold for registration vs scattering to local pages
  net/mlx5: Expose optimal performance scatter entries capability

15 files changed, 156 insertions, 34 deletions

diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index cf074bce3eb3..c94a9ff9f082 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -4,6 +4,13 @@
 #include <asm/types.h>
 #include <linux/bits.h>
 
+/* Set bits in the first 'n' bytes when loaded from memory */
+#ifdef __LITTLE_ENDIAN
+#  define aligned_byte_mask(n) ((1UL << 8*(n))-1)
+#else
+#  define aligned_byte_mask(n) (~0xffUL << (BITS_PER_LONG - 8 - 8*(n)))
+#endif
+
 #define BITS_PER_TYPE(type) (sizeof(type) * BITS_PER_BYTE)
 #define BITS_TO_LONGS(nr)	DIV_ROUND_UP(nr, BITS_PER_TYPE(long))
 
diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h
index 79435cfc20eb..897e799dbcb9 100644
--- a/include/linux/dsa/sja1105.h
+++ b/include/linux/dsa/sja1105.h
@@ -31,6 +31,8 @@
 #define SJA1105_META_SMAC			0x222222222222ull
 #define SJA1105_META_DMAC			0x0180C200000Eull
 
+#define SJA1105_HWTS_RX_EN			0
+
 /* Global tagger data: each struct sja1105_port has a reference to
  * the structure defined in struct sja1105_private.
  */
@@ -42,7 +44,7 @@ struct sja1105_tagger_data {
 	 * from taggers running on multiple ports on SMP systems
 	 */
 	spinlock_t meta_lock;
-	bool hwts_rx_en;
+	unsigned long state;
 };
 
 struct sja1105_skb_cb {
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index fcb46b3374c6..719fc3e15ea4 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1090,6 +1090,7 @@ enum kvm_stat_kind {
 
 struct kvm_stat_data {
 	int offset;
+	int mode;
 	struct kvm *kvm;
 };
 
@@ -1097,6 +1098,7 @@ struct kvm_stats_debugfs_item {
 	const char *name;
 	int offset;
 	enum kvm_stat_kind kind;
+	int mode;
 };
 extern struct kvm_stats_debugfs_item debugfs_entries[];
 extern struct dentry *kvm_debugfs_dir;
diff --git a/include/linux/mii.h b/include/linux/mii.h
index 5cd824c1c0ca..4ce8901a1af6 100644
--- a/include/linux/mii.h
+++ b/include/linux/mii.h
@@ -455,6 +455,15 @@ static inline void mii_lpa_mod_linkmode_lpa_t(unsigned long *lp_advertising,
 			 lp_advertising, lpa & LPA_LPACK);
 }
 
+static inline void mii_ctrl1000_mod_linkmode_adv_t(unsigned long *advertising,
+						   u32 ctrl1000)
+{
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, advertising,
+			 ctrl1000 & ADVERTISE_1000HALF);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, advertising,
+			 ctrl1000 & ADVERTISE_1000FULL);
+}
+
 /**
  * linkmode_adv_to_lcl_adv_t
  * @advertising:pointer to linkmode advertising
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 138c50d5a353..c0bfb1d90dd2 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1153,7 +1153,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         log_max_srq[0x5];
 	u8         reserved_at_b0[0x10];
 
-	u8         reserved_at_c0[0x8];
+	u8         max_sgl_for_optimized_performance[0x8];
 	u8         log_max_cq_sz[0x8];
 	u8         reserved_at_d0[0xb];
 	u8         log_max_cq[0x5];
diff --git a/include/linux/phy.h b/include/linux/phy.h
index a7ecbe0e55aa..9a0e981df502 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -678,6 +678,7 @@ static inline bool phy_is_started(struct phy_device *phydev)
 	return phydev->state >= PHY_UP;
 }
 
+void phy_resolve_aneg_pause(struct phy_device *phydev);
 void phy_resolve_aneg_linkmode(struct phy_device *phydev);
 
 /**
@@ -1076,6 +1077,7 @@ int genphy_config_eee_advert(struct phy_device *phydev);
 int __genphy_config_aneg(struct phy_device *phydev, bool changed);
 int genphy_aneg_done(struct phy_device *phydev);
 int genphy_update_link(struct phy_device *phydev);
+int genphy_read_lpa(struct phy_device *phydev);
 int genphy_read_status(struct phy_device *phydev);
 int genphy_suspend(struct phy_device *phydev);
 int genphy_resume(struct phy_device *phydev);
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index e7d3b1a513ef..4351577b14d7 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -4160,15 +4160,12 @@ static inline void __skb_ext_copy(struct sk_buff *d, const struct sk_buff *s) {}
 static inline void skb_ext_copy(struct sk_buff *dst, const struct sk_buff *s) {}
 #endif /* CONFIG_SKB_EXTENSIONS */
 
-static inline void nf_reset(struct sk_buff *skb)
+static inline void nf_reset_ct(struct sk_buff *skb)
 {
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 	nf_conntrack_put(skb_nfct(skb));
 	skb->_nfct = 0;
 #endif
-#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-	skb_ext_del(skb, SKB_EXT_BRIDGE_NF);
-#endif
 }
 
 static inline void nf_reset_trace(struct sk_buff *skb)
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 70bbdc38dc37..e47d0522a1f4 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -231,6 +231,76 @@ __copy_from_user_inatomic_nocache(void *to, const void __user *from,
 
 #endif		/* ARCH_HAS_NOCACHE_UACCESS */
 
+extern __must_check int check_zeroed_user(const void __user *from, size_t size);
+
+/**
+ * copy_struct_from_user: copy a struct from userspace
+ * @dst:   Destination address, in kernel space. This buffer must be @ksize
+ *         bytes long.
+ * @ksize: Size of @dst struct.
+ * @src:   Source address, in userspace.
+ * @usize: (Alleged) size of @src struct.
+ *
+ * Copies a struct from userspace to kernel space, in a way that guarantees
+ * backwards-compatibility for struct syscall arguments (as long as future
+ * struct extensions are made such that all new fields are *appended* to the
+ * old struct, and zeroed-out new fields have the same meaning as the old
+ * struct).
+ *
+ * @ksize is just sizeof(*dst), and @usize should've been passed by userspace.
+ * The recommended usage is something like the following:
+ *
+ *   SYSCALL_DEFINE2(foobar, const struct foo __user *, uarg, size_t, usize)
+ *   {
+ *      int err;
+ *      struct foo karg = {};
+ *
+ *      if (usize > PAGE_SIZE)
+ *        return -E2BIG;
+ *      if (usize < FOO_SIZE_VER0)
+ *        return -EINVAL;
+ *
+ *      err = copy_struct_from_user(&karg, sizeof(karg), uarg, usize);
+ *      if (err)
+ *        return err;
+ *
+ *      // ...
+ *   }
+ *
+ * There are three cases to consider:
+ *  * If @usize == @ksize, then it's copied verbatim.
+ *  * If @usize < @ksize, then the userspace has passed an old struct to a
+ *    newer kernel. The rest of the trailing bytes in @dst (@ksize - @usize)
+ *    are to be zero-filled.
+ *  * If @usize > @ksize, then the userspace has passed a new struct to an
+ *    older kernel. The trailing bytes unknown to the kernel (@usize - @ksize)
+ *    are checked to ensure they are zeroed, otherwise -E2BIG is returned.
+ *
+ * Returns (in all cases, some data may have been copied):
+ *  * -E2BIG:  (@usize > @ksize) and there are non-zero trailing bytes in @src.
+ *  * -EFAULT: access to userspace failed.
+ */
+static __always_inline __must_check int
+copy_struct_from_user(void *dst, size_t ksize, const void __user *src,
+		      size_t usize)
+{
+	size_t size = min(ksize, usize);
+	size_t rest = max(ksize, usize) - size;
+
+	/* Deal with trailing bytes. */
+	if (usize < ksize) {
+		memset(dst + size, 0, rest);
+	} else if (usize > ksize) {
+		int ret = check_zeroed_user(src + size, rest);
+		if (ret <= 0)
+			return ret ?: -E2BIG;
+	}
+	/* Copy the interoperable parts of the struct. */
+	if (copy_from_user(dst, src, size))
+		return -EFAULT;
+	return 0;
+}
+
 /*
  * probe_kernel_read(): safely attempt to read from a location
  * @dst: pointer to the buffer that shall take the data
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 6a47ba85c54c..a465fcae992b 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -445,6 +445,8 @@ struct ib_device_attr {
 	struct ib_tm_caps	tm_caps;
 	struct ib_cq_caps       cq_caps;
 	u64			max_dm_size;
+	/* Max entries for sgl for optimized performance per READ */
+	u32			max_sgl_rd;
 };
 
 enum ib_mtu {
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index a13a62db3565..edc5c887a44c 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -1068,7 +1068,7 @@ TRACE_EVENT(rxrpc_recvmsg,
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call->debug_id;
+		    __entry->call = call ? call->debug_id : 0;
 		    __entry->why = why;
 		    __entry->seq = seq;
 		    __entry->offset = offset;
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index c99b4f2482c6..4fe35d600ab8 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -1003,6 +1003,8 @@ struct drm_amdgpu_info_device {
 	__u64 high_va_max;
 	/* gfx10 pa_sc_tile_steering_override */
 	__u32 pa_sc_tile_steering_override;
+	/* disabled TCCs */
+	__u64 tcc_disabled_mask;
 };
 
 struct drm_amdgpu_info_hw_ip {
diff --git a/include/uapi/linux/nvme_ioctl.h b/include/uapi/linux/nvme_ioctl.h
index 1c215ea1798e..e168dc59e9a0 100644
--- a/include/uapi/linux/nvme_ioctl.h
+++ b/include/uapi/linux/nvme_ioctl.h
@@ -45,6 +45,27 @@ struct nvme_passthru_cmd {
 	__u32	result;
 };
 
+struct nvme_passthru_cmd64 {
+	__u8	opcode;
+	__u8	flags;
+	__u16	rsvd1;
+	__u32	nsid;
+	__u32	cdw2;
+	__u32	cdw3;
+	__u64	metadata;
+	__u64	addr;
+	__u32	metadata_len;
+	__u32	data_len;
+	__u32	cdw10;
+	__u32	cdw11;
+	__u32	cdw12;
+	__u32	cdw13;
+	__u32	cdw14;
+	__u32	cdw15;
+	__u32	timeout_ms;
+	__u64	result;
+};
+
 #define nvme_admin_cmd nvme_passthru_cmd
 
 #define NVME_IOCTL_ID		_IO('N', 0x40)
@@ -54,5 +75,7 @@ struct nvme_passthru_cmd {
 #define NVME_IOCTL_RESET	_IO('N', 0x44)
 #define NVME_IOCTL_SUBSYS_RESET	_IO('N', 0x45)
 #define NVME_IOCTL_RESCAN	_IO('N', 0x46)
+#define NVME_IOCTL_ADMIN64_CMD	_IOWR('N', 0x47, struct nvme_passthru_cmd64)
+#define NVME_IOCTL_IO64_CMD	_IOWR('N', 0x48, struct nvme_passthru_cmd64)
 
 #endif /* _UAPI_LINUX_NVME_IOCTL_H */
diff --git a/include/uapi/linux/pg.h b/include/uapi/linux/pg.h
index 364c350e85cd..62b6f69bd9fb 100644
--- a/include/uapi/linux/pg.h
+++ b/include/uapi/linux/pg.h
@@ -35,6 +35,9 @@
 
 */
 
+#ifndef _UAPI_LINUX_PG_H
+#define _UAPI_LINUX_PG_H
+
 #define PG_MAGIC	'P'
 #define PG_RESET	'Z'
 #define PG_COMMAND	'C'
@@ -61,4 +64,4 @@ struct pg_read_hdr {
 
 };
 
-/* end of pg.h */
+#endif /* _UAPI_LINUX_PG_H */
diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index b3105ac1381a..99335e1f4a27 100644
--- a/include/uapi/linux/sched.h
+++ b/include/uapi/linux/sched.h
@@ -33,8 +33,31 @@
 #define CLONE_NEWNET		0x40000000	/* New network namespace */
 #define CLONE_IO		0x80000000	/* Clone io context */
 
-/*
- * Arguments for the clone3 syscall
+#ifndef __ASSEMBLY__
+/**
+ * struct clone_args - arguments for the clone3 syscall
+ * @flags:       Flags for the new process as listed above.
+ *               All flags are valid except for CSIGNAL and
+ *               CLONE_DETACHED.
+ * @pidfd:       If CLONE_PIDFD is set, a pidfd will be
+ *               returned in this argument.
+ * @child_tid:   If CLONE_CHILD_SETTID is set, the TID of the
+ *               child process will be returned in the child's
+ *               memory.
+ * @parent_tid:  If CLONE_PARENT_SETTID is set, the TID of
+ *               the child process will be returned in the
+ *               parent's memory.
+ * @exit_signal: The exit_signal the parent process will be
+ *               sent when the child exits.
+ * @stack:       Specify the location of the stack for the
+ *               child process.
+ * @stack_size:  The size of the stack for the child process.
+ * @tls:         If CLONE_SETTLS is set, the tls descriptor
+ *               is set to tls.
+ *
+ * The structure is versioned by size and thus extensible.
+ * New struct members must go at the end of the struct and
+ * must be properly 64bit aligned.
  */
 struct clone_args {
 	__aligned_u64 flags;
@@ -46,6 +69,9 @@ struct clone_args {
 	__aligned_u64 stack_size;
 	__aligned_u64 tls;
 };
+#endif
+
+#define CLONE_ARGS_SIZE_VER0 64 /* sizeof first published struct */
 
 /*
  * Scheduling policies
diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h
index 98b30c1613b2..d89969aa9942 100644
--- a/include/xen/xen-ops.h
+++ b/include/xen/xen-ops.h
@@ -212,30 +212,7 @@ int xen_xlate_map_ballooned_pages(xen_pfn_t **pfns, void **vaddr,
 
 bool xen_running_on_version_or_later(unsigned int major, unsigned int minor);
 
-efi_status_t xen_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc);
-efi_status_t xen_efi_set_time(efi_time_t *tm);
-efi_status_t xen_efi_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending,
-				     efi_time_t *tm);
-efi_status_t xen_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm);
-efi_status_t xen_efi_get_variable(efi_char16_t *name, efi_guid_t *vendor,
-				  u32 *attr, unsigned long *data_size,
-				  void *data);
-efi_status_t xen_efi_get_next_variable(unsigned long *name_size,
-				       efi_char16_t *name, efi_guid_t *vendor);
-efi_status_t xen_efi_set_variable(efi_char16_t *name, efi_guid_t *vendor,
-				  u32 attr, unsigned long data_size,
-				  void *data);
-efi_status_t xen_efi_query_variable_info(u32 attr, u64 *storage_space,
-					 u64 *remaining_space,
-					 u64 *max_variable_size);
-efi_status_t xen_efi_get_next_high_mono_count(u32 *count);
-efi_status_t xen_efi_update_capsule(efi_capsule_header_t **capsules,
-				    unsigned long count, unsigned long sg_list);
-efi_status_t xen_efi_query_capsule_caps(efi_capsule_header_t **capsules,
-					unsigned long count, u64 *max_size,
-					int *reset_type);
-void xen_efi_reset_system(int reset_type, efi_status_t status,
-			  unsigned long data_size, efi_char16_t *data);
+void xen_efi_runtime_setup(void);
 
 
 #ifdef CONFIG_PREEMPT