Merge tag 'net-6.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from CAN, netfilter, wireguard and IPsec.

  I'd like to highlight [ lowlight? - Linus ] Florian W stepping down as
  a netfilter maintainer due to constant stream of bug reports. Not sure
  what we can do but IIUC this is not the first such case.

  Current release - regressions:

   - rxrpc: fix use of page_frag_alloc_align(), it changed semantics and
     we added a new caller in a different subtree

   - xfrm: allow UDP encapsulation only in offload modes

  Current release - new code bugs:

   - tcp: fix refcnt handling in __inet_hash_connect()

   - Revert "net: Re-use and set mono_delivery_time bit for userspace
     tstamp packets", conflicted with some expectations in BPF uAPI

  Previous releases - regressions:

   - ipv4: raw: fix sending packets from raw sockets via IPsec tunnels

   - devlink: fix devlink's parallel command processing

   - veth: do not manipulate GRO when using XDP

   - esp: fix bad handling of pages from page_pool

  Previous releases - always broken:

   - report RCU QS for busy network kthreads (with Paul McK's blessing)

   - tcp/rds: fix use-after-free on netns with kernel TCP reqsk

   - virt: vmxnet3: fix missing reserved tailroom with XDP

  Misc:

   - couple of build fixes for Documentation"

* tag 'net-6.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (59 commits)
  selftests: forwarding: Fix ping failure due to short timeout
  MAINTAINERS: step down as netfilter maintainer
  netfilter: nf_tables: Fix a memory leak in nf_tables_updchain
  net: dsa: mt7530: fix handling of all link-local frames
  net: dsa: mt7530: fix link-local frames that ingress vlan filtering ports
  bpf: report RCU QS in cpumap kthread
  net: report RCU QS on threaded NAPI repolling
  rcu: add a helper to report consolidated flavor QS
  ionic: update documentation for XDP support
  lib/bitmap: Fix bitmap_scatter() and bitmap_gather() kernel doc
  netfilter: nf_tables: do not compare internal table flags on updates
  netfilter: nft_set_pipapo: release elements in clone only from destroy path
  octeontx2-af: Use separate handlers for interrupts
  octeontx2-pf: Send UP messages to VF only when VF is up.
  octeontx2-pf: Use default max_active works instead of one
  octeontx2-pf: Wait till detach_resources msg is complete
  octeontx2: Detect the mbox up or down message via register
  devlink: fix port new reply cmd type
  tcp: Clear req->syncookie in reqsk_alloc().
  net/bnx2x: Prevent access to a freed page in page_pool
  ...

1 files changed, 82 insertions, 37 deletions

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index e5fe67e7386551..b40bd0e4675148 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -292,8 +292,8 @@ static int otx2_pf_flr_init(struct otx2_nic *pf, int num_vfs)
 	return 0;
 }
 
-static void otx2_queue_work(struct mbox *mw, struct workqueue_struct *mbox_wq,
-			    int first, int mdevs, u64 intr, int type)
+static void otx2_queue_vf_work(struct mbox *mw, struct workqueue_struct *mbox_wq,
+			       int first, int mdevs, u64 intr)
 {
 	struct otx2_mbox_dev *mdev;
 	struct otx2_mbox *mbox;
@@ -307,40 +307,26 @@ static void otx2_queue_work(struct mbox *mw, struct workqueue_struct *mbox_wq,
 
 		mbox = &mw->mbox;
 		mdev = &mbox->dev[i];
-		if (type == TYPE_PFAF)
-			otx2_sync_mbox_bbuf(mbox, i);
 		hdr = mdev->mbase + mbox->rx_start;
 		/* The hdr->num_msgs is set to zero immediately in the interrupt
-		 * handler to  ensure that it holds a correct value next time
-		 * when the interrupt handler is called.
-		 * pf->mbox.num_msgs holds the data for use in pfaf_mbox_handler
-		 * pf>mbox.up_num_msgs holds the data for use in
-		 * pfaf_mbox_up_handler.
+		 * handler to ensure that it holds a correct value next time
+		 * when the interrupt handler is called. pf->mw[i].num_msgs
+		 * holds the data for use in otx2_pfvf_mbox_handler and
+		 * pf->mw[i].up_num_msgs holds the data for use in
+		 * otx2_pfvf_mbox_up_handler.
 		 */
 		if (hdr->num_msgs) {
 			mw[i].num_msgs = hdr->num_msgs;
 			hdr->num_msgs = 0;
-			if (type == TYPE_PFAF)
-				memset(mbox->hwbase + mbox->rx_start, 0,
-				       ALIGN(sizeof(struct mbox_hdr),
-					     sizeof(u64)));
-
 			queue_work(mbox_wq, &mw[i].mbox_wrk);
 		}
 
 		mbox = &mw->mbox_up;
 		mdev = &mbox->dev[i];
-		if (type == TYPE_PFAF)
-			otx2_sync_mbox_bbuf(mbox, i);
 		hdr = mdev->mbase + mbox->rx_start;
 		if (hdr->num_msgs) {
 			mw[i].up_num_msgs = hdr->num_msgs;
 			hdr->num_msgs = 0;
-			if (type == TYPE_PFAF)
-				memset(mbox->hwbase + mbox->rx_start, 0,
-				       ALIGN(sizeof(struct mbox_hdr),
-					     sizeof(u64)));
-
 			queue_work(mbox_wq, &mw[i].mbox_up_wrk);
 		}
 	}
@@ -356,8 +342,10 @@ static void otx2_forward_msg_pfvf(struct otx2_mbox_dev *mdev,
 	/* Msgs are already copied, trigger VF's mbox irq */
 	smp_wmb();
 
+	otx2_mbox_wait_for_zero(pfvf_mbox, devid);
+
 	offset = pfvf_mbox->trigger | (devid << pfvf_mbox->tr_shift);
-	writeq(1, (void __iomem *)pfvf_mbox->reg_base + offset);
+	writeq(MBOX_DOWN_MSG, (void __iomem *)pfvf_mbox->reg_base + offset);
 
 	/* Restore VF's mbox bounce buffer region address */
 	src_mdev->mbase = bbuf_base;
@@ -547,7 +535,7 @@ static void otx2_pfvf_mbox_up_handler(struct work_struct *work)
 end:
 		offset = mbox->rx_start + msg->next_msgoff;
 		if (mdev->msgs_acked == (vf_mbox->up_num_msgs - 1))
-			__otx2_mbox_reset(mbox, 0);
+			__otx2_mbox_reset(mbox, vf_idx);
 		mdev->msgs_acked++;
 	}
 }
@@ -564,8 +552,7 @@ static irqreturn_t otx2_pfvf_mbox_intr_handler(int irq, void *pf_irq)
 	if (vfs > 64) {
 		intr = otx2_read64(pf, RVU_PF_VFPF_MBOX_INTX(1));
 		otx2_write64(pf, RVU_PF_VFPF_MBOX_INTX(1), intr);
-		otx2_queue_work(mbox, pf->mbox_pfvf_wq, 64, vfs, intr,
-				TYPE_PFVF);
+		otx2_queue_vf_work(mbox, pf->mbox_pfvf_wq, 64, vfs, intr);
 		if (intr)
 			trace_otx2_msg_interrupt(mbox->mbox.pdev, "VF(s) to PF", intr);
 		vfs = 64;
@@ -574,7 +561,7 @@ static irqreturn_t otx2_pfvf_mbox_intr_handler(int irq, void *pf_irq)
 	intr = otx2_read64(pf, RVU_PF_VFPF_MBOX_INTX(0));
 	otx2_write64(pf, RVU_PF_VFPF_MBOX_INTX(0), intr);
 
-	otx2_queue_work(mbox, pf->mbox_pfvf_wq, 0, vfs, intr, TYPE_PFVF);
+	otx2_queue_vf_work(mbox, pf->mbox_pfvf_wq, 0, vfs, intr);
 
 	if (intr)
 		trace_otx2_msg_interrupt(mbox->mbox.pdev, "VF(s) to PF", intr);
@@ -597,8 +584,9 @@ static int otx2_pfvf_mbox_init(struct otx2_nic *pf, int numvfs)
 	if (!pf->mbox_pfvf)
 		return -ENOMEM;
 
-	pf->mbox_pfvf_wq = alloc_ordered_workqueue("otx2_pfvf_mailbox",
-						   WQ_HIGHPRI | WQ_MEM_RECLAIM);
+	pf->mbox_pfvf_wq = alloc_workqueue("otx2_pfvf_mailbox",
+					   WQ_UNBOUND | WQ_HIGHPRI |
+					   WQ_MEM_RECLAIM, 0);
 	if (!pf->mbox_pfvf_wq)
 		return -ENOMEM;
 
@@ -821,20 +809,22 @@ static void otx2_pfaf_mbox_handler(struct work_struct *work)
 	struct mbox *af_mbox;
 	struct otx2_nic *pf;
 	int offset, id;
+	u16 num_msgs;
 
 	af_mbox = container_of(work, struct mbox, mbox_wrk);
 	mbox = &af_mbox->mbox;
 	mdev = &mbox->dev[0];
 	rsp_hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start);
+	num_msgs = rsp_hdr->num_msgs;
 
 	offset = mbox->rx_start + ALIGN(sizeof(*rsp_hdr), MBOX_MSG_ALIGN);
 	pf = af_mbox->pfvf;
 
-	for (id = 0; id < af_mbox->num_msgs; id++) {
+	for (id = 0; id < num_msgs; id++) {
 		msg = (struct mbox_msghdr *)(mdev->mbase + offset);
 		otx2_process_pfaf_mbox_msg(pf, msg);
 		offset = mbox->rx_start + msg->next_msgoff;
-		if (mdev->msgs_acked == (af_mbox->num_msgs - 1))
+		if (mdev->msgs_acked == (num_msgs - 1))
 			__otx2_mbox_reset(mbox, 0);
 		mdev->msgs_acked++;
 	}
@@ -945,12 +935,14 @@ static void otx2_pfaf_mbox_up_handler(struct work_struct *work)
 	int offset, id, devid = 0;
 	struct mbox_hdr *rsp_hdr;
 	struct mbox_msghdr *msg;
+	u16 num_msgs;
 
 	rsp_hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start);
+	num_msgs = rsp_hdr->num_msgs;
 
 	offset = mbox->rx_start + ALIGN(sizeof(*rsp_hdr), MBOX_MSG_ALIGN);
 
-	for (id = 0; id < af_mbox->up_num_msgs; id++) {
+	for (id = 0; id < num_msgs; id++) {
 		msg = (struct mbox_msghdr *)(mdev->mbase + offset);
 
 		devid = msg->pcifunc & RVU_PFVF_FUNC_MASK;
@@ -959,10 +951,11 @@ static void otx2_pfaf_mbox_up_handler(struct work_struct *work)
 			otx2_process_mbox_msg_up(pf, msg);
 		offset = mbox->rx_start + msg->next_msgoff;
 	}
-	if (devid) {
+	/* Forward to VF iff VFs are really present */
+	if (devid && pci_num_vf(pf->pdev)) {
 		otx2_forward_vf_mbox_msgs(pf, &pf->mbox.mbox_up,
 					  MBOX_DIR_PFVF_UP, devid - 1,
-					  af_mbox->up_num_msgs);
+					  num_msgs);
 		return;
 	}
 
@@ -972,16 +965,49 @@ static void otx2_pfaf_mbox_up_handler(struct work_struct *work)
 static irqreturn_t otx2_pfaf_mbox_intr_handler(int irq, void *pf_irq)
 {
 	struct otx2_nic *pf = (struct otx2_nic *)pf_irq;
-	struct mbox *mbox;
+	struct mbox *mw = &pf->mbox;
+	struct otx2_mbox_dev *mdev;
+	struct otx2_mbox *mbox;
+	struct mbox_hdr *hdr;
+	u64 mbox_data;
 
 	/* Clear the IRQ */
 	otx2_write64(pf, RVU_PF_INT, BIT_ULL(0));
 
-	mbox = &pf->mbox;
 
-	trace_otx2_msg_interrupt(mbox->mbox.pdev, "AF to PF", BIT_ULL(0));
+	mbox_data = otx2_read64(pf, RVU_PF_PFAF_MBOX0);
+
+	if (mbox_data & MBOX_UP_MSG) {
+		mbox_data &= ~MBOX_UP_MSG;
+		otx2_write64(pf, RVU_PF_PFAF_MBOX0, mbox_data);
+
+		mbox = &mw->mbox_up;
+		mdev = &mbox->dev[0];
+		otx2_sync_mbox_bbuf(mbox, 0);
+
+		hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start);
+		if (hdr->num_msgs)
+			queue_work(pf->mbox_wq, &mw->mbox_up_wrk);
+
+		trace_otx2_msg_interrupt(pf->pdev, "UP message from AF to PF",
+					 BIT_ULL(0));
+	}
+
+	if (mbox_data & MBOX_DOWN_MSG) {
+		mbox_data &= ~MBOX_DOWN_MSG;
+		otx2_write64(pf, RVU_PF_PFAF_MBOX0, mbox_data);
+
+		mbox = &mw->mbox;
+		mdev = &mbox->dev[0];
+		otx2_sync_mbox_bbuf(mbox, 0);
+
+		hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start);
+		if (hdr->num_msgs)
+			queue_work(pf->mbox_wq, &mw->mbox_wrk);
 
-	otx2_queue_work(mbox, pf->mbox_wq, 0, 1, 1, TYPE_PFAF);
+		trace_otx2_msg_interrupt(pf->pdev, "DOWN reply from AF to PF",
+					 BIT_ULL(0));
+	}
 
 	return IRQ_HANDLED;
 }
@@ -3087,6 +3113,7 @@ static void otx2_vf_link_event_task(struct work_struct *work)
 	struct otx2_vf_config *config;
 	struct cgx_link_info_msg *req;
 	struct mbox_msghdr *msghdr;
+	struct delayed_work *dwork;
 	struct otx2_nic *pf;
 	int vf_idx;
 
@@ -3095,10 +3122,24 @@ static void otx2_vf_link_event_task(struct work_struct *work)
 	vf_idx = config - config->pf->vf_configs;
 	pf = config->pf;
 
+	if (config->intf_down)
+		return;
+
+	mutex_lock(&pf->mbox.lock);
+
+	dwork = &config->link_event_work;
+
+	if (!otx2_mbox_wait_for_zero(&pf->mbox_pfvf[0].mbox_up, vf_idx)) {
+		schedule_delayed_work(dwork, msecs_to_jiffies(100));
+		mutex_unlock(&pf->mbox.lock);
+		return;
+	}
+
 	msghdr = otx2_mbox_alloc_msg_rsp(&pf->mbox_pfvf[0].mbox_up, vf_idx,
 					 sizeof(*req), sizeof(struct msg_rsp));
 	if (!msghdr) {
 		dev_err(pf->dev, "Failed to create VF%d link event\n", vf_idx);
+		mutex_unlock(&pf->mbox.lock);
 		return;
 	}
 
@@ -3107,7 +3148,11 @@ static void otx2_vf_link_event_task(struct work_struct *work)
 	req->hdr.sig = OTX2_MBOX_REQ_SIG;
 	memcpy(&req->link_info, &pf->linfo, sizeof(req->link_info));
 
+	otx2_mbox_wait_for_zero(&pf->mbox_pfvf[0].mbox_up, vf_idx);
+
 	otx2_sync_mbox_up_msg(&pf->mbox_pfvf[0], vf_idx);
+
+	mutex_unlock(&pf->mbox.lock);
 }
 
 static int otx2_sriov_enable(struct pci_dev *pdev, int numvfs)