Merge branch 'main' into next

Conflicts:
	vdpa/include/uapi/linux/vdpa.h

Signed-off-by: David Ahern <dsahern@kernel.org>

8 files changed, 309 insertions, 12 deletions

diff --git a/bridge/fdb.c b/bridge/fdb.c
index b71b20c8b..5f71bde08 100644
--- a/bridge/fdb.c
+++ b/bridge/fdb.c
@@ -575,6 +575,7 @@ static int fdb_get(int argc, char **argv)
 	char *addr = NULL;
 	short vlan = -1;
 	char *endptr;
+	int ret;
 
 	while (argc > 0) {
 		if ((strcmp(*argv, "brport") == 0) || strcmp(*argv, "dev") == 0) {
@@ -661,13 +662,15 @@ static int fdb_get(int argc, char **argv)
 	 * if -json was specified.
 	 */
 	new_json_obj(json);
+	ret = 0;
 	if (print_fdb(answer, stdout) < 0) {
 		fprintf(stderr, "An error :-)\n");
-		return -1;
+		ret = -1;
 	}
 	delete_json_obj();
+	free(answer);
 
-	return 0;
+	return ret;
 }
 
 static int fdb_flush(int argc, char **argv)
diff --git a/ip/ipaddress.c b/ip/ipaddress.c
index 610bdbde3..45955e1c0 100644
--- a/ip/ipaddress.c
+++ b/ip/ipaddress.c
@@ -2055,8 +2055,10 @@ static int ipaddr_link_get(int index, struct nlmsg_chain *linfo)
 
 	if (store_nlmsg(answer, linfo) < 0) {
 		fprintf(stderr, "Failed to process link information\n");
+		free(answer);
 		return 1;
 	}
+	free(answer);
 
 	return 0;
 }
diff --git a/ip/ipmptcp.c b/ip/ipmptcp.c
index 0033f329b..ce62ab9a4 100644
--- a/ip/ipmptcp.c
+++ b/ip/ipmptcp.c
@@ -337,6 +337,7 @@ static int mptcp_addr_show(int argc, char **argv)
 	new_json_obj(json);
 	ret = print_mptcp_addr(answer, stdout);
 	delete_json_obj();
+	free(answer);
 	fflush(stdout);
 	return ret;
 }
@@ -435,9 +436,13 @@ static int mptcp_limit_get_set(int argc, char **argv, int cmd)
 	if (rtnl_talk(&genl_rth, &req.n, do_get ? &answer : NULL) < 0)
 		return -2;
 
-	if (do_get)
-		return print_mptcp_limit(answer, stdout);
-	return 0;
+	ret = 0;
+	if (do_get) {
+		ret = print_mptcp_limit(answer, stdout);
+		free(answer);
+	}
+
+	return ret;
 }
 
 static const char * const event_to_str[] = {
diff --git a/ip/ipneigh.c b/ip/ipneigh.c
index 7facc399f..61b0a4a22 100644
--- a/ip/ipneigh.c
+++ b/ip/ipneigh.c
@@ -731,8 +731,10 @@ static int ipneigh_get(int argc, char **argv)
 	ipneigh_reset_filter(0);
 	if (print_neigh(answer, stdout) < 0) {
 		fprintf(stderr, "An error :-)\n");
+		free(answer);
 		return -1;
 	}
+	free(answer);
 
 	return 0;
 }
diff --git a/lib/bpf_glue.c b/lib/bpf_glue.c
index c1cf351b7..88a247513 100644
--- a/lib/bpf_glue.c
+++ b/lib/bpf_glue.c
@@ -7,6 +7,7 @@
 #include <sys/syscall.h>
 #include <limits.h>
 #include <unistd.h>
+#include <errno.h>
 
 #include "bpf_util.h"
 #ifdef HAVE_LIBBPF
diff --git a/rdma/include/uapi/rdma/ib_user_verbs.h b/rdma/include/uapi/rdma/ib_user_verbs.h
index 7ee73a065..7dd903d93 100644
--- a/rdma/include/uapi/rdma/ib_user_verbs.h
+++ b/rdma/include/uapi/rdma/ib_user_verbs.h
@@ -1298,4 +1298,46 @@ struct ib_uverbs_ex_modify_cq {
 
 #define IB_DEVICE_NAME_MAX 64
 
+/*
+ * bits 9, 15, 16, 19, 22, 27, 30, 31, 32, 33, 35 and 37 may be set by old
+ * kernels and should not be used.
+ */
+enum ib_uverbs_device_cap_flags {
+	IB_UVERBS_DEVICE_RESIZE_MAX_WR = 1 << 0,
+	IB_UVERBS_DEVICE_BAD_PKEY_CNTR = 1 << 1,
+	IB_UVERBS_DEVICE_BAD_QKEY_CNTR = 1 << 2,
+	IB_UVERBS_DEVICE_RAW_MULTI = 1 << 3,
+	IB_UVERBS_DEVICE_AUTO_PATH_MIG = 1 << 4,
+	IB_UVERBS_DEVICE_CHANGE_PHY_PORT = 1 << 5,
+	IB_UVERBS_DEVICE_UD_AV_PORT_ENFORCE = 1 << 6,
+	IB_UVERBS_DEVICE_CURR_QP_STATE_MOD = 1 << 7,
+	IB_UVERBS_DEVICE_SHUTDOWN_PORT = 1 << 8,
+	/* IB_UVERBS_DEVICE_INIT_TYPE = 1 << 9, (not in use) */
+	IB_UVERBS_DEVICE_PORT_ACTIVE_EVENT = 1 << 10,
+	IB_UVERBS_DEVICE_SYS_IMAGE_GUID = 1 << 11,
+	IB_UVERBS_DEVICE_RC_RNR_NAK_GEN = 1 << 12,
+	IB_UVERBS_DEVICE_SRQ_RESIZE = 1 << 13,
+	IB_UVERBS_DEVICE_N_NOTIFY_CQ = 1 << 14,
+	IB_UVERBS_DEVICE_MEM_WINDOW = 1 << 17,
+	IB_UVERBS_DEVICE_UD_IP_CSUM = 1 << 18,
+	IB_UVERBS_DEVICE_XRC = 1 << 20,
+	IB_UVERBS_DEVICE_MEM_MGT_EXTENSIONS = 1 << 21,
+	IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2A = 1 << 23,
+	IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2B = 1 << 24,
+	IB_UVERBS_DEVICE_RC_IP_CSUM = 1 << 25,
+	/* Deprecated. Please use IB_UVERBS_RAW_PACKET_CAP_IP_CSUM. */
+	IB_UVERBS_DEVICE_RAW_IP_CSUM = 1 << 26,
+	IB_UVERBS_DEVICE_MANAGED_FLOW_STEERING = 1 << 29,
+	/* Deprecated. Please use IB_UVERBS_RAW_PACKET_CAP_SCATTER_FCS. */
+	IB_UVERBS_DEVICE_RAW_SCATTER_FCS = 1ULL << 34,
+	IB_UVERBS_DEVICE_PCI_WRITE_END_PADDING = 1ULL << 36,
+};
+
+enum ib_uverbs_raw_packet_caps {
+	IB_UVERBS_RAW_PACKET_CAP_CVLAN_STRIPPING = 1 << 0,
+	IB_UVERBS_RAW_PACKET_CAP_SCATTER_FCS = 1 << 1,
+	IB_UVERBS_RAW_PACKET_CAP_IP_CSUM = 1 << 2,
+	IB_UVERBS_RAW_PACKET_CAP_DELAY_DROP = 1 << 3,
+};
+
 #endif /* IB_USER_VERBS_H */
diff --git a/vdpa/include/uapi/linux/virtio_ids.h b/vdpa/include/uapi/linux/virtio_ids.h
index 80d76b75b..7aa2eb766 100644
--- a/vdpa/include/uapi/linux/virtio_ids.h
+++ b/vdpa/include/uapi/linux/virtio_ids.h
@@ -73,12 +73,12 @@
  * Virtio Transitional IDs
  */
 
-#define VIRTIO_TRANS_ID_NET		1000 /* transitional virtio net */
-#define VIRTIO_TRANS_ID_BLOCK		1001 /* transitional virtio block */
-#define VIRTIO_TRANS_ID_BALLOON		1002 /* transitional virtio balloon */
-#define VIRTIO_TRANS_ID_CONSOLE		1003 /* transitional virtio console */
-#define VIRTIO_TRANS_ID_SCSI		1004 /* transitional virtio SCSI */
-#define VIRTIO_TRANS_ID_RNG		1005 /* transitional virtio rng */
-#define VIRTIO_TRANS_ID_9P		1009 /* transitional virtio 9p console */
+#define VIRTIO_TRANS_ID_NET		0x1000 /* transitional virtio net */
+#define VIRTIO_TRANS_ID_BLOCK		0x1001 /* transitional virtio block */
+#define VIRTIO_TRANS_ID_BALLOON		0x1002 /* transitional virtio balloon */
+#define VIRTIO_TRANS_ID_CONSOLE		0x1003 /* transitional virtio console */
+#define VIRTIO_TRANS_ID_SCSI		0x1004 /* transitional virtio SCSI */
+#define VIRTIO_TRANS_ID_RNG		0x1005 /* transitional virtio rng */
+#define VIRTIO_TRANS_ID_9P		0x1009 /* transitional virtio 9p console */
 
 #endif /* _LINUX_VIRTIO_IDS_H */
diff --git a/vdpa/include/uapi/linux/virtio_ring.h b/vdpa/include/uapi/linux/virtio_ring.h
new file mode 100644
index 000000000..010483437
--- /dev/null
+++ b/vdpa/include/uapi/linux/virtio_ring.h
@@ -0,0 +1,242 @@
+#ifndef _LINUX_VIRTIO_RING_H
+#define _LINUX_VIRTIO_RING_H
+/* An interface for efficient virtio implementation, currently for use by KVM,
+ * but hopefully others soon.  Do NOT change this since it will
+ * break existing servers and clients.
+ *
+ * This header is BSD licensed so anyone can use the definitions to implement
+ * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ *
+ * Copyright Rusty Russell IBM Corporation 2007. */
+#include <stdint.h>
+#include <linux/types.h>
+#include <linux/virtio_types.h>
+
+/* This marks a buffer as continuing via the next field. */
+#define VRING_DESC_F_NEXT	1
+/* This marks a buffer as write-only (otherwise read-only). */
+#define VRING_DESC_F_WRITE	2
+/* This means the buffer contains a list of buffer descriptors. */
+#define VRING_DESC_F_INDIRECT	4
+
+/*
+ * Mark a descriptor as available or used in packed ring.
+ * Notice: they are defined as shifts instead of shifted values.
+ */
+#define VRING_PACKED_DESC_F_AVAIL	7
+#define VRING_PACKED_DESC_F_USED	15
+
+/* The Host uses this in used->flags to advise the Guest: don't kick me when
+ * you add a buffer.  It's unreliable, so it's simply an optimization.  Guest
+ * will still kick if it's out of buffers. */
+#define VRING_USED_F_NO_NOTIFY	1
+/* The Guest uses this in avail->flags to advise the Host: don't interrupt me
+ * when you consume a buffer.  It's unreliable, so it's simply an
+ * optimization.  */
+#define VRING_AVAIL_F_NO_INTERRUPT	1
+
+/* Enable events in packed ring. */
+#define VRING_PACKED_EVENT_FLAG_ENABLE	0x0
+/* Disable events in packed ring. */
+#define VRING_PACKED_EVENT_FLAG_DISABLE	0x1
+/*
+ * Enable events for a specific descriptor in packed ring.
+ * (as specified by Descriptor Ring Change Event Offset/Wrap Counter).
+ * Only valid if VIRTIO_RING_F_EVENT_IDX has been negotiated.
+ */
+#define VRING_PACKED_EVENT_FLAG_DESC	0x2
+
+/*
+ * Wrap counter bit shift in event suppression structure
+ * of packed ring.
+ */
+#define VRING_PACKED_EVENT_F_WRAP_CTR	15
+
+/* We support indirect buffer descriptors */
+#define VIRTIO_RING_F_INDIRECT_DESC	28
+
+/* The Guest publishes the used index for which it expects an interrupt
+ * at the end of the avail ring. Host should ignore the avail->flags field. */
+/* The Host publishes the avail index for which it expects a kick
+ * at the end of the used ring. Guest should ignore the used->flags field. */
+#define VIRTIO_RING_F_EVENT_IDX		29
+
+/* Alignment requirements for vring elements.
+ * When using pre-virtio 1.0 layout, these fall out naturally.
+ */
+#define VRING_AVAIL_ALIGN_SIZE 2
+#define VRING_USED_ALIGN_SIZE 4
+#define VRING_DESC_ALIGN_SIZE 16
+
+/* Virtio ring descriptors: 16 bytes.  These can chain together via "next". */
+struct vring_desc {
+	/* Address (guest-physical). */
+	__virtio64 addr;
+	/* Length. */
+	__virtio32 len;
+	/* The flags as indicated above. */
+	__virtio16 flags;
+	/* We chain unused descriptors via this, too */
+	__virtio16 next;
+};
+
+struct vring_avail {
+	__virtio16 flags;
+	__virtio16 idx;
+	__virtio16 ring[];
+};
+
+/* u32 is used here for ids for padding reasons. */
+struct vring_used_elem {
+	/* Index of start of used descriptor chain. */
+	__virtio32 id;
+	/* Total length of the descriptor chain which was used (written to) */
+	__virtio32 len;
+};
+
+typedef struct vring_used_elem __attribute__((aligned(VRING_USED_ALIGN_SIZE)))
+	vring_used_elem_t;
+
+struct vring_used {
+	__virtio16 flags;
+	__virtio16 idx;
+	vring_used_elem_t ring[];
+};
+
+/*
+ * The ring element addresses are passed between components with different
+ * alignments assumptions. Thus, we might need to decrease the compiler-selected
+ * alignment, and so must use a typedef to make sure the aligned attribute
+ * actually takes hold:
+ *
+ * https://gcc.gnu.org/onlinedocs//gcc/Common-Type-Attributes.html#Common-Type-Attributes
+ *
+ * When used on a struct, or struct member, the aligned attribute can only
+ * increase the alignment; in order to decrease it, the packed attribute must
+ * be specified as well. When used as part of a typedef, the aligned attribute
+ * can both increase and decrease alignment, and specifying the packed
+ * attribute generates a warning.
+ */
+typedef struct vring_desc __attribute__((aligned(VRING_DESC_ALIGN_SIZE)))
+	vring_desc_t;
+typedef struct vring_avail __attribute__((aligned(VRING_AVAIL_ALIGN_SIZE)))
+	vring_avail_t;
+typedef struct vring_used __attribute__((aligned(VRING_USED_ALIGN_SIZE)))
+	vring_used_t;
+
+struct vring {
+	unsigned int num;
+
+	vring_desc_t *desc;
+
+	vring_avail_t *avail;
+
+	vring_used_t *used;
+};
+
+#ifndef VIRTIO_RING_NO_LEGACY
+
+/* The standard layout for the ring is a continuous chunk of memory which looks
+ * like this.  We assume num is a power of 2.
+ *
+ * struct vring
+ * {
+ *	// The actual descriptors (16 bytes each)
+ *	struct vring_desc desc[num];
+ *
+ *	// A ring of available descriptor heads with free-running index.
+ *	__virtio16 avail_flags;
+ *	__virtio16 avail_idx;
+ *	__virtio16 available[num];
+ *	__virtio16 used_event_idx;
+ *
+ *	// Padding to the next align boundary.
+ *	char pad[];
+ *
+ *	// A ring of used descriptor heads with free-running index.
+ *	__virtio16 used_flags;
+ *	__virtio16 used_idx;
+ *	struct vring_used_elem used[num];
+ *	__virtio16 avail_event_idx;
+ * };
+ */
+/* We publish the used event index at the end of the available ring, and vice
+ * versa. They are at the end for backwards compatibility. */
+#define vring_used_event(vr) ((vr)->avail->ring[(vr)->num])
+#define vring_avail_event(vr) (*(__virtio16 *)&(vr)->used->ring[(vr)->num])
+
+static __inline__ void vring_init(struct vring *vr, unsigned int num, void *p,
+			      unsigned long align)
+{
+	vr->num = num;
+	vr->desc = p;
+	vr->avail = (struct vring_avail *)((char *)p + num * sizeof(struct vring_desc));
+	vr->used = (void *)(((uintptr_t)&vr->avail->ring[num] + sizeof(__virtio16)
+		+ align-1) & ~(align - 1));
+}
+
+static __inline__ unsigned vring_size(unsigned int num, unsigned long align)
+{
+	return ((sizeof(struct vring_desc) * num + sizeof(__virtio16) * (3 + num)
+		 + align - 1) & ~(align - 1))
+		+ sizeof(__virtio16) * 3 + sizeof(struct vring_used_elem) * num;
+}
+
+#endif /* VIRTIO_RING_NO_LEGACY */
+
+/* The following is used with USED_EVENT_IDX and AVAIL_EVENT_IDX */
+/* Assuming a given event_idx value from the other side, if
+ * we have just incremented index from old to new_idx,
+ * should we trigger an event? */
+static __inline__ int vring_need_event(__u16 event_idx, __u16 new_idx, __u16 old)
+{
+	/* Note: Xen has similar logic for notification hold-off
+	 * in include/xen/interface/io/ring.h with req_event and req_prod
+	 * corresponding to event_idx + 1 and new_idx respectively.
+	 * Note also that req_event and req_prod in Xen start at 1,
+	 * event indexes in virtio start at 0. */
+	return (__u16)(new_idx - event_idx - 1) < (__u16)(new_idx - old);
+}
+
+struct vring_packed_desc_event {
+	/* Descriptor Ring Change Event Offset/Wrap Counter. */
+	__le16 off_wrap;
+	/* Descriptor Ring Change Event Flags. */
+	__le16 flags;
+};
+
+struct vring_packed_desc {
+	/* Buffer Address. */
+	__le64 addr;
+	/* Buffer Length. */
+	__le32 len;
+	/* Buffer ID. */
+	__le16 id;
+	/* The flags depending on descriptor type. */
+	__le16 flags;
+};
+
+#endif /* _LINUX_VIRTIO_RING_H */