Merge remote-tracking branch 'origin/pve-kernel-5.11' into buster-pve-kernel-5.11

Makefile

@@ -4,9 +4,9 @@ KERNEL_MIN=11
 KERNEL_PATCHLEVEL=22
 # increment KREL if the ABI changes (abicheck target in debian/rules)
 # rebuild packages with new KREL and run 'make abiupdate'
-KREL=4
+KREL=5
 
-PKGREL=8~bpo10+1
+PKGREL=10~bpo10+1
 
 KERNEL_MAJMIN=$(KERNEL_MAJ).$(KERNEL_MIN)
 KERNEL_VER=$(KERNEL_MAJMIN).$(KERNEL_PATCHLEVEL)

debian/changelog

@@ -1,3 +1,31 @@
+pve-kernel (5.11.22-10~bpo10+1) buster-backports; urgency=medium
+
+  * Rebuild for Debian Buster based releases
+
+ -- Proxmox Support Team <support@proxmox.com>  Tue, 28 Sep 2021 10:30:51 +0200
+
+pve-kernel (5.11.22-10) bullseye; urgency=medium
+
+  * update sources to Ubuntu-5.11.0-38.42
+
+  * update ZFS to 2.0.6
+
+  * bump ABI to 5.11.22-5
+
+  * fix #3558: backport "bnx2x: Fix enabling network interfaces without VFs"
+
+ -- Proxmox Support Team <support@proxmox.com>  Tue, 28 Sep 2021 08:15:41 +0200
+
+pve-kernel (5.11.22-9) bullseye; urgency=medium
+
+  * backport "blk-mq: fix kernel panic during iterating over flush
+    request"
+
+  * d/rules: kconfig: enable SQUASHFS_DECOMP_MULTI_PERCPU to speed up
+    decompression of mounted squashfs images
+
+ -- Proxmox Support Team <support@proxmox.com>  Wed, 22 Sep 2021 10:11:11 +0200
+
 pve-kernel (5.11.22-8~bpo10+1) buster-backports; urgency=medium
 
   * Rebuild for buster-backports.

debian/rules

@@ -35,6 +35,7 @@ PVE_CONFIG_OPTS= \
 -m CONFIG_HFS_FS \
 -m CONFIG_HFSPLUS_FS \
 -e CIFS_SMB_DIRECT \
+-e CONFIG_SQUASHFS_DECOMP_MULTI_PERCPU \
 -e CONFIG_BRIDGE \
 -e CONFIG_BRIDGE_NETFILTER \
 -e CONFIG_BLK_DEV_SD \

patches/kernel/0001-Make-mkcompile_h-accept-an-alternate-timestamp-strin.patch

@@ -21,7 +21,7 @@ Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
  1 file changed, 7 insertions(+), 3 deletions(-)
 
 diff --git a/scripts/mkcompile_h b/scripts/mkcompile_h
-index 4ae735039daf..5a1abe7b4169 100755
+index a72b154de7b0..4dd111086466 100755
 --- a/scripts/mkcompile_h
 +++ b/scripts/mkcompile_h
 @@ -24,10 +24,14 @@ else

patches/kernel/0003-pci-Enable-overrides-for-missing-ACS-capabilities-4..patch

@@ -75,10 +75,10 @@ index ee85be64b680..a38a8e44422e 100644
  				Safety option to keep boot IRQs enabled. This
  				should never be necessary.
 diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
-index f32e521ade1e..4f3558d0c00a 100644
+index 6e9f3c366298..cc0e3a76168e 100644
 --- a/drivers/pci/quirks.c
 +++ b/drivers/pci/quirks.c
-@@ -192,6 +192,106 @@ static int __init pci_apply_final_quirks(void)
+@@ -193,6 +193,106 @@ static int __init pci_apply_final_quirks(void)
  }
  fs_initcall_sync(pci_apply_final_quirks);
  
@@ -185,7 +185,7 @@ index f32e521ade1e..4f3558d0c00a 100644
  /*
   * Decoding should be disabled for a PCI device during BAR sizing to avoid
   * conflict. But doing so may cause problems on host bridge and perhaps other
-@@ -4857,6 +4957,8 @@ static const struct pci_dev_acs_enabled {
+@@ -4869,6 +4969,8 @@ static const struct pci_dev_acs_enabled {
  	{ PCI_VENDOR_ID_CAVIUM, PCI_ANY_ID, pci_quirk_cavium_acs },
  	/* APM X-Gene */
  	{ PCI_VENDOR_ID_AMCC, 0xE004, pci_quirk_xgene_acs },

patches/kernel/0004-kvm-disable-default-dynamic-halt-polling-growth.patch

@@ -13,7 +13,7 @@ Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
  1 file changed, 1 insertion(+), 1 deletion(-)
 
 diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
-index 14e6c73a6031..c191c9e50735 100644
+index 16c777d45eb9..8c5341f9a271 100644
 --- a/virt/kvm/kvm_main.c
 +++ b/virt/kvm/kvm_main.c
 @@ -77,7 +77,7 @@ module_param(halt_poll_ns, uint, 0644);

patches/kernel/0005-net-core-downgrade-unregister_netdevice-refcount-lea.patch

@@ -10,10 +10,10 @@ Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
  1 file changed, 1 insertion(+), 1 deletion(-)
 
 diff --git a/net/core/dev.c b/net/core/dev.c
-index b91b76890cbc..cb7ffc3e848b 100644
+index 5cc9226f8e67..7dd94b012533 100644
 --- a/net/core/dev.c
 +++ b/net/core/dev.c
-@@ -10365,7 +10365,7 @@ static void netdev_wait_allrefs(struct net_device *dev)
+@@ -10392,7 +10392,7 @@ static void netdev_wait_allrefs(struct net_device *dev)
  		refcnt = netdev_refcnt_read(dev);
  
  		if (refcnt && time_after(jiffies, warning_time + 10 * HZ)) {

patches/kernel/0006-io_uring-don-t-block-level-reissue-off-completion-pa.patch

@@ -27,10 +27,10 @@ Signed-off-by: Fabian Ebner <f.ebner@proxmox.com>
  1 file changed, 7 insertions(+)
 
 diff --git a/fs/io_uring.c b/fs/io_uring.c
-index a0d42aea3aa1..ce5cf51a5667 100644
+index d24eb8e53c4c..b5192f2f8178 100644
 --- a/fs/io_uring.c
 +++ b/fs/io_uring.c
-@@ -2731,6 +2731,13 @@ static bool io_rw_reissue(struct io_kiocb *req, long res)
+@@ -2743,6 +2743,13 @@ static bool io_rw_reissue(struct io_kiocb *req, long res)
  	if (percpu_ref_is_dying(&req->ctx->refs))
  		return false;
  

patches/kernel/0006-net-bridge-sync-fdb-to-new-unicast-filtering-ports.patch

@@ -1,68 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Wolfgang Bumiller <w.bumiller@proxmox.com>
-Date: Fri, 2 Jul 2021 14:07:36 +0200
-Subject: [PATCH] net: bridge: sync fdb to new unicast-filtering ports
-
-Since commit 2796d0c648c9 ("bridge: Automatically manage
-port promiscuous mode.")
-bridges with `vlan_filtering 1` and only 1 auto-port don't
-set IFF_PROMISC for unicast-filtering-capable ports.
-
-Normally on port changes `br_manage_promisc` is called to
-update the promisc flags and unicast filters if necessary,
-but it cannot distinguish between *new* ports and ones
-losing their promisc flag, and new ports end up not
-receiving the MAC address list.
-
-Fix this by calling `br_fdb_sync_static` in `br_add_if`
-after the port promisc flags are updated and the unicast
-filter was supposed to have been filled.
-
-Fixes: 2796d0c648c9 ("bridge: Automatically manage port promiscuous mode.")
-Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
----
- net/bridge/br_if.c | 17 ++++++++++++++++-
- 1 file changed, 16 insertions(+), 1 deletion(-)
-
-diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
-index f7d2f472ae24..6e4a32354a13 100644
---- a/net/bridge/br_if.c
-+++ b/net/bridge/br_if.c
-@@ -562,7 +562,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev,
- 	struct net_bridge_port *p;
- 	int err = 0;
- 	unsigned br_hr, dev_hr;
--	bool changed_addr;
-+	bool changed_addr, fdb_synced = false;
- 
- 	/* Don't allow bridging non-ethernet like devices. */
- 	if ((dev->flags & IFF_LOOPBACK) ||
-@@ -652,6 +652,19 @@ int br_add_if(struct net_bridge *br, struct net_device *dev,
- 	list_add_rcu(&p->list, &br->port_list);
- 
- 	nbp_update_port_count(br);
-+	if (!br_promisc_port(p) && (p->dev->priv_flags & IFF_UNICAST_FLT)) {
-+		/* When updating the port count we also update all ports'
-+		 * promiscuous mode.
-+		 * A port leaving promiscuous mode normally gets the bridge's
-+		 * fdb synced to the unicast filter (if supported), however,
-+		 * `br_port_clear_promisc` does not distinguish between
-+		 * non-promiscuous ports and *new* ports, so we need to
-+		 * sync explicitly here.
-+		 */
-+		fdb_synced = br_fdb_sync_static(br, p) == 0;
-+		if (!fdb_synced)
-+			netdev_err(dev, "failed to sync bridge static fdb addresses to this port\n");
-+	}
- 
- 	netdev_update_features(br->dev);
- 
-@@ -701,6 +714,8 @@ int br_add_if(struct net_bridge *br, struct net_device *dev,
- 	return 0;
- 
- err7:
-+	if (fdb_synced)
-+		br_fdb_unsync_static(br, p);
- 	list_del_rcu(&p->list);
- 	br_fdb_delete_by_port(br, p, 0, 1);
- 	nbp_update_port_count(br);

patches/kernel/0009-blk-mq-fix-kernel-panic-during-iterating-over-flush-.patch

@@ -0,0 +1,75 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Ming Lei <ming.lei@redhat.com>
+Date: Fri, 10 Sep 2021 14:30:15 +0200
+Subject: [PATCH] blk-mq: fix kernel panic during iterating over flush request
+
+commit c2da19ed50554ce52ecbad3655c98371fe58599f upstream.
+
+For fixing use-after-free during iterating over requests, we grabbed
+request's refcount before calling ->fn in commit 2e315dc07df0 ("blk-mq:
+grab rq->refcount before calling ->fn in blk_mq_tagset_busy_iter").
+Turns out this way may cause kernel panic when iterating over one flush
+request:
+
+1) old flush request's tag is just released, and this tag is reused by
+one new request, but ->rqs[] isn't updated yet
+
+2) the flush request can be re-used for submitting one new flush command,
+so blk_rq_init() is called at the same time
+
+3) meantime blk_mq_queue_tag_busy_iter() is called, and old flush request
+is retrieved from ->rqs[tag]; when blk_mq_put_rq_ref() is called,
+flush_rq->end_io may not be updated yet, so NULL pointer dereference
+is triggered in blk_mq_put_rq_ref().
+
+Fix the issue by calling refcount_set(&flush_rq->ref, 1) after
+flush_rq->end_io is set. So far the only other caller of blk_rq_init() is
+scsi_ioctl_reset() in which the request doesn't enter block IO stack and
+the request reference count isn't used, so the change is safe.
+
+Fixes: 2e315dc07df0 ("blk-mq: grab rq->refcount before calling ->fn in blk_mq_tagset_busy_iter")
+Reported-by: "Blank-Burian, Markus, Dr." <blankburian@uni-muenster.de>
+Tested-by: "Blank-Burian, Markus, Dr." <blankburian@uni-muenster.de>
+Signed-off-by: Ming Lei <ming.lei@redhat.com>
+Reviewed-by: Christoph Hellwig <hch@lst.de>
+Reviewed-by: John Garry <john.garry@huawei.com>
+Link: https://lore.kernel.org/r/20210811142624.618598-1-ming.lei@redhat.com
+Signed-off-by: Jens Axboe <axboe@kernel.dk>
+Cc: Yi Zhang <yi.zhang@redhat.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ block/blk-core.c  | 1 -
+ block/blk-flush.c | 8 ++++++++
+ 2 files changed, 8 insertions(+), 1 deletion(-)
+
+diff --git a/block/blk-core.c b/block/blk-core.c
+index ce3b75f8b56d..9658caafddc2 100644
+--- a/block/blk-core.c
++++ b/block/blk-core.c
+@@ -121,7 +121,6 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
+ 	rq->internal_tag = BLK_MQ_NO_TAG;
+ 	rq->start_time_ns = ktime_get_ns();
+ 	rq->part = NULL;
+-	refcount_set(&rq->ref, 1);
+ 	blk_crypto_rq_set_defaults(rq);
+ }
+ EXPORT_SYMBOL(blk_rq_init);
+diff --git a/block/blk-flush.c b/block/blk-flush.c
+index e89d007dbf6a..8b11ab3b3762 100644
+--- a/block/blk-flush.c
++++ b/block/blk-flush.c
+@@ -329,6 +329,14 @@ static void blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq,
+ 	flush_rq->rq_flags |= RQF_FLUSH_SEQ;
+ 	flush_rq->rq_disk = first_rq->rq_disk;
+ 	flush_rq->end_io = flush_end_io;
++	/*
++	 * Order WRITE ->end_io and WRITE rq->ref, and its pair is the one
++	 * implied in refcount_inc_not_zero() called from
++	 * blk_mq_find_and_get_req(), which orders WRITE/READ flush_rq->ref
++	 * and READ flush_rq->end_io
++	 */
++	smp_wmb();
++	refcount_set(&flush_rq->ref, 1);
+ 
+ 	blk_flush_queue_rq(flush_rq, false);
+ }

patches/kernel/0010-blk-mq-fix-is_flush_rq.patch

@@ -0,0 +1,91 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Ming Lei <ming.lei@redhat.com>
+Date: Fri, 10 Sep 2021 14:30:16 +0200
+Subject: [PATCH] blk-mq: fix is_flush_rq
+
+commit a9ed27a764156929efe714033edb3e9023c5f321 upstream.
+
+is_flush_rq() is called from bt_iter()/bt_tags_iter(), and runs the
+following check:
+
+	hctx->fq->flush_rq == req
+
+but the passed hctx from bt_iter()/bt_tags_iter() may be NULL because:
+
+1) memory re-order in blk_mq_rq_ctx_init():
+
+	rq->mq_hctx = data->hctx;
+	...
+	refcount_set(&rq->ref, 1);
+
+OR
+
+2) tag re-use and ->rqs[] isn't updated with new request.
+
+Fix the issue by re-writing is_flush_rq() as:
+
+	return rq->end_io == flush_end_io;
+
+which turns out simpler to follow and immune to data race since we have
+ordered WRITE rq->end_io and refcount_set(&rq->ref, 1).
+
+Fixes: 2e315dc07df0 ("blk-mq: grab rq->refcount before calling ->fn in blk_mq_tagset_busy_iter")
+Cc: "Blank-Burian, Markus, Dr." <blankburian@uni-muenster.de>
+Cc: Yufen Yu <yuyufen@huawei.com>
+Signed-off-by: Ming Lei <ming.lei@redhat.com>
+Link: https://lore.kernel.org/r/20210818010925.607383-1-ming.lei@redhat.com
+Signed-off-by: Jens Axboe <axboe@kernel.dk>
+Cc: Yi Zhang <yi.zhang@redhat.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ block/blk-flush.c | 5 +++++
+ block/blk-mq.c    | 2 +-
+ block/blk.h       | 6 +-----
+ 3 files changed, 7 insertions(+), 6 deletions(-)
+
+diff --git a/block/blk-flush.c b/block/blk-flush.c
+index 8b11ab3b3762..705ee6c99020 100644
+--- a/block/blk-flush.c
++++ b/block/blk-flush.c
+@@ -262,6 +262,11 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error)
+ 	spin_unlock_irqrestore(&fq->mq_flush_lock, flags);
+ }
+ 
++bool is_flush_rq(struct request *rq)
++{
++	return rq->end_io == flush_end_io;
++}
++
+ /**
+  * blk_kick_flush - consider issuing flush request
+  * @q: request_queue being kicked
+diff --git a/block/blk-mq.c b/block/blk-mq.c
+index 82db8595bdaa..7dd1b6973c79 100644
+--- a/block/blk-mq.c
++++ b/block/blk-mq.c
+@@ -937,7 +937,7 @@ static bool blk_mq_req_expired(struct request *rq, unsigned long *next)
+ 
+ void blk_mq_put_rq_ref(struct request *rq)
+ {
+-	if (is_flush_rq(rq, rq->mq_hctx))
++	if (is_flush_rq(rq))
+ 		rq->end_io(rq, 0);
+ 	else if (refcount_dec_and_test(&rq->ref))
+ 		__blk_mq_free_request(rq);
+diff --git a/block/blk.h b/block/blk.h
+index 7550364c326c..4a4ffd992790 100644
+--- a/block/blk.h
++++ b/block/blk.h
+@@ -43,11 +43,7 @@ static inline void __blk_get_queue(struct request_queue *q)
+ 	kobject_get(&q->kobj);
+ }
+ 
+-static inline bool
+-is_flush_rq(struct request *req, struct blk_mq_hw_ctx *hctx)
+-{
+-	return hctx->fq->flush_rq == req;
+-}
++bool is_flush_rq(struct request *req);
+ 
+ struct blk_flush_queue *blk_alloc_flush_queue(int node, int cmd_size,
+ 					      gfp_t flags);

patches/kernel/0011-bnx2x-Fix-enabling-network-interfaces-without-VFs.patch

@@ -0,0 +1,34 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Adrian Bunk <bunk@kernel.org>
+Date: Sun, 12 Sep 2021 22:05:23 +0300
+Subject: [PATCH] bnx2x: Fix enabling network interfaces without VFs
+
+This function is called to enable SR-IOV when available,
+not enabling interfaces without VFs was a regression.
+
+Fixes: 65161c35554f ("bnx2x: Fix missing error code in bnx2x_iov_init_one()")
+Signed-off-by: Adrian Bunk <bunk@kernel.org>
+Reported-by: YunQiang Su <wzssyqa@gmail.com>
+Tested-by: YunQiang Su <wzssyqa@gmail.com>
+Cc: stable@vger.kernel.org
+Acked-by: Shai Malin <smalin@marvell.com>
+Link: https://lore.kernel.org/r/20210912190523.27991-1-bunk@kernel.org
+Signed-off-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+---
+ drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+index f255fd0b16db..6fbf735fca31 100644
+--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
++++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+@@ -1224,7 +1224,7 @@ int bnx2x_iov_init_one(struct bnx2x *bp, int int_mode_param,
+ 
+ 	/* SR-IOV capability was enabled but there are no VFs*/
+ 	if (iov->total == 0) {
+-		err = -EINVAL;
++		err = 0;
+ 		goto failed;
+ 	}
+ 

submodules/ubuntu-hirsute

@@ -1 +1 @@
-Subproject commit 9fb3242fa6a38d072949cbaa9183f65d56675231
+Subproject commit 7d7783039af74cad199b3a39673ae012077bfd11

submodules/zfsonlinux

@@ -1 +1 @@
-Subproject commit 19953df19b39b71abc7c9c2d507644f4fc0596f1
+Subproject commit b7ce537d241e315db3907160482fd7ffc1989194