update ABI file for 5.13.19-6-pve

(generated with debian/scripts/abi-generate)

Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>

Makefile

@@ -4,9 +4,9 @@ KERNEL_MIN=13
 KERNEL_PATCHLEVEL=19
 # increment KREL if the ABI changes (abicheck target in debian/rules)
 # rebuild packages with new KREL and run 'make abiupdate'
-KREL=2
+KREL=6
 
-PKGREL=4
+PKGREL=14
 
 KERNEL_MAJMIN=$(KERNEL_MAJ).$(KERNEL_MIN)
 KERNEL_VER=$(KERNEL_MAJMIN).$(KERNEL_PATCHLEVEL)

debian/changelog

@@ -1,3 +1,72 @@
+pve-kernel (5.13.19-14) bullseye; urgency=medium
+
+  * update to Ubuntu-5.13.0-36.41
+
+  * bump ABI to 5.13.19-6
+
+ -- Proxmox Support Team <support@proxmox.com>  Thu, 10 Mar 2022 16:24:52 +0100
+
+pve-kernel (5.13.19-13) bullseye; urgency=medium
+
+  * backport "KVM: VMX: prepare sync_pir_to_irr for running with APICv
+    disabled" to avoid breaking some Windows VMs startup
+
+ -- Proxmox Support Team <support@proxmox.com>  Tue, 08 Mar 2022 07:32:25 +0100
+
+pve-kernel (5.13.19-12) bullseye; urgency=medium
+
+  * Revert "PCI/MSI: Mask MSI-X vectors only on success" as it's causing PCI-E
+    initialization failures on some systems.
+
+ -- Proxmox Support Team <support@proxmox.com>  Mon, 07 Mar 2022 15:54:28 +0100
+
+pve-kernel (5.13.19-11) bullseye; urgency=medium
+
+  * backport "lib/iov_iter: initialize "flags" in new pipe_buffer" fixing
+    CVE-2022-0847 "dirty pipe"
+
+ -- Proxmox Support Team <support@proxmox.com>  Mon, 07 Mar 2022 13:28:22 +0100
+
+pve-kernel (5.13.19-10) bullseye; urgency=medium
+
+  * update to Ubuntu-5.13.0-31.34
+
+ -- Proxmox Support Team <support@proxmox.com>  Mon, 21 Feb 2022 09:26:12 +0100
+
+pve-kernel (5.13.19-9) bullseye; urgency=medium
+
+  * update to Ubuntu-5.13.0-30.33
+    revert a problematic patch causing issues with releasing block devices
+
+ -- Proxmox Support Team <support@proxmox.com>  Mon, 07 Feb 2022 11:01:14 +0100
+
+pve-kernel (5.13.19-8) bullseye; urgency=medium
+
+  * update sources to Ubuntu-5.13.0-29.32
+
+  * bump ABI to 5.13.19-4
+
+ -- Proxmox Support Team <support@proxmox.com>  Mon, 31 Jan 2022 10:09:37 +0100
+
+pve-kernel (5.13.19-7) bullseye; urgency=medium
+
+  * backport "vfs: fs_context: fix up param length parsing in
+    legacy_parse_param"
+
+ -- Proxmox Support Team <support@proxmox.com>  Thu, 20 Jan 2022 16:37:56 +0100
+
+pve-kernel (5.13.19-6) bullseye; urgency=medium
+
+  * update sources to Ubuntu-5.13.0-24.24
+
+  * bump ABI to 5.13.19-3
+
+  * update ZFS to 2.1.2
+
+  * ZFS: cherry-pick lock-inversion patch for zvol_open
+
+ -- Proxmox Support Team <support@proxmox.com>  Tue, 11 Jan 2022 16:44:47 +0100
+
 pve-kernel (5.13.19-4) bullseye; urgency=medium
 
   * update sources to Ubuntu-5.13.0-23.23

debian/control.in

@@ -32,7 +32,8 @@ Build-Depends: asciidoc-base,
                sphinx-common,
                tar,
                xmlto,
-               zlib1g-dev
+               zlib1g-dev,
+               zstd,
 Build-Conflicts: pve-headers-@KVNAME@
 Vcs-Git: git://git.proxmox.com/git/pve-kernel
 Vcs-Browser: https://git.proxmox.com/?p=pve-kernel.git
@@ -50,7 +51,7 @@ Package: pve-headers-@KVNAME@
 Section: devel
 Priority: optional
 Architecture: any
-Provides: linux-headers
+Provides: linux-headers-@KVNAME@-amd64
 Depends: coreutils | fileutils (>= 4.0)
 Description: The Proxmox PVE Kernel Headers
  This package contains the linux kernel headers
@@ -59,7 +60,7 @@ Package: pve-kernel-@KVNAME@
 Section: admin
 Priority: optional
 Architecture: any
-Provides: linux-image
+Provides: linux-image-@KVNAME@-amd64
 Suggests: pve-firmware
 Depends: busybox, initramfs-tools
 Recommends: grub-pc | grub-efi-amd64 | grub-efi-ia32 | grub-efi-arm64

fwlist-previous

@@ -990,7 +990,9 @@ mediatek/mt7668pr2h.bin kernel/drivers/bluetooth/btusb.ko
 mediatek/mt7915_rom_patch.bin kernel/drivers/net/wireless/mediatek/mt76/mt7915/mt7915e.ko
 mediatek/mt7915_wa.bin kernel/drivers/net/wireless/mediatek/mt76/mt7915/mt7915e.ko
 mediatek/mt7915_wm.bin kernel/drivers/net/wireless/mediatek/mt76/mt7915/mt7915e.ko
+mediatek/WIFI_MT7922_patch_mcu_1_1_hdr.bin kernel/drivers/net/wireless/mediatek/mt76/mt7921/mt7921e.ko
 mediatek/WIFI_MT7961_patch_mcu_1_2_hdr.bin kernel/drivers/net/wireless/mediatek/mt76/mt7921/mt7921e.ko
+mediatek/WIFI_RAM_CODE_MT7922_1.bin kernel/drivers/net/wireless/mediatek/mt76/mt7921/mt7921e.ko
 mediatek/WIFI_RAM_CODE_MT7961_1.bin kernel/drivers/net/wireless/mediatek/mt76/mt7921/mt7921e.ko
 mellanox/mlxsw_spectrum-13.2008.2406.mfa2 kernel/drivers/net/ethernet/mellanox/mlxsw/mlxsw_spectrum.ko
 mellanox/mlxsw_spectrum2-29.2008.2406.mfa2 kernel/drivers/net/ethernet/mellanox/mlxsw/mlxsw_spectrum.ko

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

@@ -55,10 +55,10 @@ Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
  2 files changed, 111 insertions(+)
 
 diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
-index 8deb4cd7b133..291885ea26dd 100644
+index 550f341daf99..478530b48cf1 100644
 --- a/Documentation/admin-guide/kernel-parameters.txt
 +++ b/Documentation/admin-guide/kernel-parameters.txt
-@@ -3808,6 +3808,15 @@
+@@ -3814,6 +3814,15 @@
  				Also, it enforces the PCI Local Bus spec
  				rule that those bits should be 0 in system reset
  				events (useful for kexec/kdump cases).
@@ -75,7 +75,7 @@ index 8deb4cd7b133..291885ea26dd 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 d44037a6e109..1f576ba148dd 100644
+index 444ba11f3e79..5843ba2cad8e 100644
 --- a/drivers/pci/quirks.c
 +++ b/drivers/pci/quirks.c
 @@ -193,6 +193,106 @@ static int __init pci_apply_final_quirks(void)
@@ -185,7 +185,7 @@ index d44037a6e109..1f576ba148dd 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
-@@ -4875,6 +4975,8 @@ static const struct pci_dev_acs_enabled {
+@@ -4876,6 +4976,8 @@ static const struct pci_dev_acs_enabled {
  	{ PCI_VENDOR_ID_CAVIUM, 0xA060, pci_quirk_mf_endpoint_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 3b316cb42554..71aba634a6a8 100644
+index b86d4bce9793..946643fa1aa1 100644
 --- a/virt/kvm/kvm_main.c
 +++ b/virt/kvm/kvm_main.c
 @@ -78,7 +78,7 @@ 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 156b44f35102..66014d76a61b 100644
+index 7bac7947d8b8..4196ce468b10 100644
 --- a/net/core/dev.c
 +++ b/net/core/dev.c
-@@ -10521,7 +10521,7 @@ static void netdev_wait_allrefs(struct net_device *dev)
+@@ -10533,7 +10533,7 @@ static void netdev_wait_allrefs(struct net_device *dev)
  		if (refcnt != 1 &&
  		    time_after(jiffies, warning_time +
  			       netdev_unregister_timeout_secs * HZ)) {

patches/kernel/0006-Revert-PCI-Coalesce-host-bridge-contiguous-apertures.patch

@@ -15,11 +15,11 @@ Link: https://lore.kernel.org/r/20210709231529.GA3270116@roeck-us.net
 Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
 Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
 ---
- drivers/pci/probe.c | 50 ++++-----------------------------------------
+ drivers/pci/probe.c | 52 +++++----------------------------------------
- 1 file changed, 4 insertions(+), 46 deletions(-)
+ 1 file changed, 5 insertions(+), 47 deletions(-)
 
 diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
-index f6046a16dac1..275204646c68 100644
+index 59ef93f1d953..b38a345c5df6 100644
 --- a/drivers/pci/probe.c
 +++ b/drivers/pci/probe.c
 @@ -19,7 +19,6 @@
@@ -92,13 +92,14 @@ index f6046a16dac1..275204646c68 100644
 -
  	/* Add initial resources to the bus */
  	resource_list_for_each_entry_safe(window, n, &resources) {
-+		list_move_tail(&window->node, &bridge->windows);
+-		offset = window->offset;
- 		offset = window->offset;
+-		res = window->res;
- 		res = window->res;
 -		if (!res->end)
 -			continue;
 -
--		list_move_tail(&window->node, &bridge->windows);
+ 		list_move_tail(&window->node, &bridge->windows);
++		offset = window->offset;
++		res = window->res;
  
  		if (res->flags & IORESOURCE_BUS)
  			pci_bus_insert_busn_res(bus, bus->number, res->end);

patches/kernel/0007-PCI-Reinstate-PCI-Coalesce-host-bridge-contiguous-ap.patch

@@ -50,12 +50,13 @@ Cc: Guenter Roeck <linux@roeck-us.net>
 Suggested-by: Bjorn Helgaas <bhelgaas@google.com>
 Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
 Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
 ---
- drivers/pci/probe.c | 31 +++++++++++++++++++++++++++----
+ drivers/pci/probe.c | 33 ++++++++++++++++++++++++++++-----
- 1 file changed, 27 insertions(+), 4 deletions(-)
+ 1 file changed, 28 insertions(+), 5 deletions(-)
 
 diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
-index 275204646c68..944c35d87258 100644
+index b38a345c5df6..485167ca62a1 100644
 --- a/drivers/pci/probe.c
 +++ b/drivers/pci/probe.c
 @@ -877,11 +877,11 @@ static void pci_set_bus_msi_domain(struct pci_bus *bus)
@@ -99,13 +100,14 @@ index 275204646c68..944c35d87258 100644
 +
  	/* Add initial resources to the bus */
  	resource_list_for_each_entry_safe(window, n, &resources) {
--		list_move_tail(&window->node, &bridge->windows);
++		offset = window->offset;
- 		offset = window->offset;
++		res = window->res;
- 		res = window->res;
 +		if (!res->end)
 +			continue;
 +
-+		list_move_tail(&window->node, &bridge->windows);
+ 		list_move_tail(&window->node, &bridge->windows);
+-		offset = window->offset;
+-		res = window->res;
  
  		if (res->flags & IORESOURCE_BUS)
  			pci_bus_insert_busn_res(bus, bus->number, res->end);

patches/kernel/0008-Revert-block-remove-the-ERESTARTSYS-handling-in-blkd.patch

@@ -1,40 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Thomas Lamprecht <t.lamprecht@proxmox.com>
-Date: Tue, 9 Nov 2021 12:01:12 +0100
-Subject: [PATCH] Revert "block: remove the -ERESTARTSYS handling in
- blkdev_get_by_dev"
-
-This reverts commit a8ed1a0607cfa5478ff6009539f44790c4d0956d.
-
-It breaks ZFS sometimes:
-https://github.com/openzfs/zfs/issues/12301#issuecomment-873303739
-
-Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
----
- fs/block_dev.c | 6 ++++++
- 1 file changed, 6 insertions(+)
-
-diff --git a/fs/block_dev.c b/fs/block_dev.c
-index e4a80bd4ddf1..4a14d28dd923 100644
---- a/fs/block_dev.c
-+++ b/fs/block_dev.c
-@@ -1436,6 +1436,10 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
- 	if (ret)
- 		return ERR_PTR(ret);
- 
-+	/*
-+	 * If we lost a race with 'disk' being deleted, try again.  See md.c.
-+	 */
-+retry:
- 	bdev = blkdev_get_no_open(dev);
- 	if (!bdev)
- 		return ERR_PTR(-ENXIO);
-@@ -1482,6 +1486,8 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
- 	disk_unblock_events(disk);
- put_blkdev:
- 	blkdev_put_no_open(bdev);
-+	if (ret == -ERESTARTSYS)
-+		goto retry;
- 	return ERR_PTR(ret);
- }
- EXPORT_SYMBOL(blkdev_get_by_dev);

patches/kernel/0008-io-wq-split-bounded-and-unbounded-work-into-separate.patch

@@ -17,12 +17,13 @@ Fixes: ecc53c48c13d ("io-wq: check max_worker limits if a worker transitions bou
 Signed-off-by: Jens Axboe <axboe@kernel.dk>
 [backport]
 Signed-off-by: Fabian Ebner <f.ebner@proxmox.com>
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
 ---
- fs/io-wq.c | 156 +++++++++++++++++++++++------------------------------
+ fs/io-wq.c | 160 +++++++++++++++++++++++------------------------------
- 1 file changed, 68 insertions(+), 88 deletions(-)
+ 1 file changed, 70 insertions(+), 90 deletions(-)
 
 diff --git a/fs/io-wq.c b/fs/io-wq.c
-index 33678185f3bc..2496d8781ea1 100644
+index ba7aaf2b95d0..6710da3d4445 100644
 --- a/fs/io-wq.c
 +++ b/fs/io-wq.c
 @@ -34,7 +34,7 @@ enum {
@@ -34,7 +35,7 @@ index 33678185f3bc..2496d8781ea1 100644
  };
  
  /*
-@@ -73,25 +73,24 @@ struct io_wqe_acct {
+@@ -73,26 +73,25 @@ struct io_wqe_acct {
  	unsigned max_workers;
  	int index;
  	atomic_t nr_running;
@@ -57,14 +58,16 @@ index 33678185f3bc..2496d8781ea1 100644
 -		struct io_wq_work_list work_list;
 -		unsigned flags;
 -	} ____cacheline_aligned_in_smp;
+-
+-	int node;
 +	raw_spinlock_t lock;
-+	struct io_wqe_acct acct[2];
+ 	struct io_wqe_acct acct[2];
- 
- 	int node;
--	struct io_wqe_acct acct[2];
  
++	int node;
++
  	struct hlist_nulls_head free_list;
  	struct list_head all_list;
+ 
 @@ -196,11 +195,10 @@ static void io_worker_exit(struct io_worker *worker)
  	do_exit(0);
  }
@@ -140,8 +143,8 @@ index 33678185f3bc..2496d8781ea1 100644
  }
  
  /*
-@@ -417,44 +401,23 @@ static void io_wait_on_hash(struct io_wqe *wqe, unsigned int hash)
+@@ -420,44 +404,23 @@ static bool io_wait_on_hash(struct io_wqe *wqe, unsigned int hash)
- 	spin_unlock(&wq->hash->wait.lock);
+ 	return ret;
  }
  
 -/*
@@ -189,7 +192,7 @@ index 33678185f3bc..2496d8781ea1 100644
  			return work;
  		}
  
-@@ -465,7 +428,7 @@ static struct io_wq_work *io_get_next_work(struct io_wqe *wqe,
+@@ -468,7 +431,7 @@ static struct io_wq_work *io_get_next_work(struct io_wqe *wqe,
  		/* hashed, can run if not already running */
  		if (!test_and_set_bit(hash, &wqe->wq->hash->map)) {
  			wqe->hash_tail[hash] = NULL;
@@ -198,16 +201,22 @@ index 33678185f3bc..2496d8781ea1 100644
  			return work;
  		}
  		if (stall_hash == -1U)
-@@ -479,7 +442,7 @@ static struct io_wq_work *io_get_next_work(struct io_wqe *wqe,
+@@ -484,12 +447,12 @@ static struct io_wq_work *io_get_next_work(struct io_wqe *wqe,
  		 * Set this before dropping the lock to avoid racing with new
  		 * work being added and clearing the stalled bit.
  		 */
 -		wqe->flags |= IO_WQE_FLAG_STALLED;
 +		set_bit(IO_ACCT_STALLED_BIT, &acct->flags);
  		raw_spin_unlock(&wqe->lock);
- 		io_wait_on_hash(wqe, stall_hash);
+ 		unstalled = io_wait_on_hash(wqe, stall_hash);
  		raw_spin_lock(&wqe->lock);
-@@ -516,6 +479,7 @@ static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work);
+ 		if (unstalled) {
+-			wqe->flags &= ~IO_WQE_FLAG_STALLED;
++			clear_bit(IO_ACCT_STALLED_BIT, &acct->flags);
+ 			if (wq_has_sleeper(&wqe->wq->hash->wait))
+ 				wake_up(&wqe->wq->hash->wait);
+ 		}
+@@ -526,6 +489,7 @@ static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work);
  static void io_worker_handle_work(struct io_worker *worker)
  	__releases(wqe->lock)
  {
@@ -215,7 +224,7 @@ index 33678185f3bc..2496d8781ea1 100644
  	struct io_wqe *wqe = worker->wqe;
  	struct io_wq *wq = wqe->wq;
  	bool do_kill = test_bit(IO_WQ_BIT_EXIT, &wq->state);
-@@ -530,7 +494,7 @@ static void io_worker_handle_work(struct io_worker *worker)
+@@ -540,7 +504,7 @@ static void io_worker_handle_work(struct io_worker *worker)
  		 * can't make progress, any work completion or insertion will
  		 * clear the stalled flag.
  		 */
@@ -224,19 +233,16 @@ index 33678185f3bc..2496d8781ea1 100644
  		if (work)
  			__io_worker_busy(wqe, worker, work);
  
-@@ -564,10 +528,10 @@ static void io_worker_handle_work(struct io_worker *worker)
+@@ -576,7 +540,7 @@ static void io_worker_handle_work(struct io_worker *worker)
- 
+ 				/* serialize hash clear with wake_up() */
- 			if (hash != -1U && !next_hashed) {
+ 				spin_lock_irq(&wq->hash->wait.lock);
  				clear_bit(hash, &wq->hash->map);
+-				wqe->flags &= ~IO_WQE_FLAG_STALLED;
 +				clear_bit(IO_ACCT_STALLED_BIT, &acct->flags);
+ 				spin_unlock_irq(&wq->hash->wait.lock);
  				if (wq_has_sleeper(&wq->hash->wait))
  					wake_up(&wq->hash->wait);
- 				raw_spin_lock_irq(&wqe->lock);
+@@ -595,6 +559,7 @@ static void io_worker_handle_work(struct io_worker *worker)
--				wqe->flags &= ~IO_WQE_FLAG_STALLED;
- 				/* skip unnecessary unlock-lock wqe->lock */
- 				if (!work)
- 					goto get_next;
-@@ -582,6 +546,7 @@ static void io_worker_handle_work(struct io_worker *worker)
  static int io_wqe_worker(void *data)
  {
  	struct io_worker *worker = data;
@@ -244,7 +250,7 @@ index 33678185f3bc..2496d8781ea1 100644
  	struct io_wqe *wqe = worker->wqe;
  	struct io_wq *wq = wqe->wq;
  	char buf[TASK_COMM_LEN];
-@@ -597,7 +562,7 @@ static int io_wqe_worker(void *data)
+@@ -610,7 +575,7 @@ static int io_wqe_worker(void *data)
  		set_current_state(TASK_INTERRUPTIBLE);
  loop:
  		raw_spin_lock_irq(&wqe->lock);
@@ -253,7 +259,7 @@ index 33678185f3bc..2496d8781ea1 100644
  			io_worker_handle_work(worker);
  			goto loop;
  		}
-@@ -623,7 +588,7 @@ static int io_wqe_worker(void *data)
+@@ -636,7 +601,7 @@ static int io_wqe_worker(void *data)
  
  	if (test_bit(IO_WQ_BIT_EXIT, &wq->state)) {
  		raw_spin_lock_irq(&wqe->lock);
@@ -262,7 +268,7 @@ index 33678185f3bc..2496d8781ea1 100644
  			io_worker_handle_work(worker);
  		else
  			raw_spin_unlock_irq(&wqe->lock);
-@@ -769,12 +734,13 @@ static void io_run_cancel(struct io_wq_work *work, struct io_wqe *wqe)
+@@ -782,12 +747,13 @@ static void io_run_cancel(struct io_wq_work *work, struct io_wqe *wqe)
  
  static void io_wqe_insert_work(struct io_wqe *wqe, struct io_wq_work *work)
  {
@@ -277,7 +283,7 @@ index 33678185f3bc..2496d8781ea1 100644
  		return;
  	}
  
-@@ -784,7 +750,7 @@ static void io_wqe_insert_work(struct io_wqe *wqe, struct io_wq_work *work)
+@@ -797,7 +763,7 @@ static void io_wqe_insert_work(struct io_wqe *wqe, struct io_wq_work *work)
  	if (!tail)
  		goto append;
  
@@ -286,7 +292,7 @@ index 33678185f3bc..2496d8781ea1 100644
  }
  
  static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work)
-@@ -806,10 +772,10 @@ static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work)
+@@ -819,10 +785,10 @@ static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work)
  
  	raw_spin_lock_irqsave(&wqe->lock, flags);
  	io_wqe_insert_work(wqe, work);
@@ -299,7 +305,7 @@ index 33678185f3bc..2496d8781ea1 100644
  	rcu_read_unlock();
  
  	raw_spin_unlock_irqrestore(&wqe->lock, flags);
-@@ -862,6 +828,7 @@ static inline void io_wqe_remove_pending(struct io_wqe *wqe,
+@@ -875,6 +841,7 @@ static inline void io_wqe_remove_pending(struct io_wqe *wqe,
  					 struct io_wq_work *work,
  					 struct io_wq_work_node *prev)
  {
@@ -307,7 +313,7 @@ index 33678185f3bc..2496d8781ea1 100644
  	unsigned int hash = io_get_work_hash(work);
  	struct io_wq_work *prev_work = NULL;
  
-@@ -873,7 +840,7 @@ static inline void io_wqe_remove_pending(struct io_wqe *wqe,
+@@ -886,7 +853,7 @@ static inline void io_wqe_remove_pending(struct io_wqe *wqe,
  		else
  			wqe->hash_tail[hash] = NULL;
  	}
@@ -316,7 +322,7 @@ index 33678185f3bc..2496d8781ea1 100644
  }
  
  static void io_wqe_cancel_pending_work(struct io_wqe *wqe,
-@@ -882,22 +849,27 @@ static void io_wqe_cancel_pending_work(struct io_wqe *wqe,
+@@ -895,22 +862,27 @@ static void io_wqe_cancel_pending_work(struct io_wqe *wqe,
  	struct io_wq_work_node *node, *prev;
  	struct io_wq_work *work;
  	unsigned long flags;
@@ -356,7 +362,7 @@ index 33678185f3bc..2496d8781ea1 100644
  	}
  	raw_spin_unlock_irqrestore(&wqe->lock, flags);
  }
-@@ -958,18 +930,24 @@ static int io_wqe_hash_wake(struct wait_queue_entry *wait, unsigned mode,
+@@ -971,18 +943,24 @@ static int io_wqe_hash_wake(struct wait_queue_entry *wait, unsigned mode,
  			    int sync, void *key)
  {
  	struct io_wqe *wqe = container_of(wait, struct io_wqe, wait);
@@ -383,7 +389,7 @@ index 33678185f3bc..2496d8781ea1 100644
  	struct io_wq *wq;
  
  	if (WARN_ON_ONCE(!data->free_work || !data->do_work))
-@@ -1006,18 +984,20 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
+@@ -1019,18 +997,20 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
  			goto err;
  		wq->wqes[node] = wqe;
  		wqe->node = alloc_node;

patches/kernel/0009-do-not-generate-split-BTF-type-info-per-default.patch

@@ -0,0 +1,28 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: =?UTF-8?q?Fabian=20Gr=C3=BCnbichler?= <f.gruenbichler@proxmox.com>
+Date: Thu, 14 Sep 2017 11:09:58 +0200
+Subject: [PATCH] do not generate split BTF type info per default
+
+This reverts commit a8ed1a0607cfa5478ff6009539f44790c4d0956d.
+
+It breaks ZFS sometimes:
+https://github.com/openzfs/zfs/issues/12301#issuecomment-873303739
+
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+---
+ lib/Kconfig.debug | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
+index 25dc20175bba..7ff51a3f65e6 100644
+--- a/lib/Kconfig.debug
++++ b/lib/Kconfig.debug
+@@ -314,7 +314,7 @@ config PAHOLE_HAS_SPLIT_BTF
+ 	def_bool $(success, test `$(PAHOLE) --version | sed -E 's/v([0-9]+)\.([0-9]+)/\1\2/'` -ge "119")
+ 
+ config DEBUG_INFO_BTF_MODULES
+-	def_bool y
++	def_bool n
+ 	depends on DEBUG_INFO_BTF && MODULES && PAHOLE_HAS_SPLIT_BTF
+ 	help
+ 	  Generate compact split BTF type information for kernel modules.

patches/kernel/0009-io-wq-fix-queue-stalling-race.patch

@@ -1,69 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Jens Axboe <axboe@kernel.dk>
-Date: Tue, 31 Aug 2021 13:53:00 -0600
-Subject: [PATCH] io-wq: fix queue stalling race
-
-We need to set the stalled bit early, before we drop the lock for adding
-us to the stall hash queue. If not, then we can race with new work being
-queued between adding us to the stall hash and io_worker_handle_work()
-marking us stalled.
-
-Signed-off-by: Jens Axboe <axboe@kernel.dk>
-[backport]
-Signed-off-by: Fabian Ebner <f.ebner@proxmox.com>
----
- fs/io-wq.c | 15 +++++++--------
- 1 file changed, 7 insertions(+), 8 deletions(-)
-
-diff --git a/fs/io-wq.c b/fs/io-wq.c
-index 6612d0aa497e..33678185f3bc 100644
---- a/fs/io-wq.c
-+++ b/fs/io-wq.c
-@@ -437,8 +437,7 @@ static bool io_worker_can_run_work(struct io_worker *worker,
- }
- 
- static struct io_wq_work *io_get_next_work(struct io_wqe *wqe,
--					   struct io_worker *worker,
--					   bool *stalled)
-+					   struct io_worker *worker)
- 	__must_hold(wqe->lock)
- {
- 	struct io_wq_work_node *node, *prev;
-@@ -476,10 +475,14 @@ static struct io_wq_work *io_get_next_work(struct io_wqe *wqe,
- 	}
- 
- 	if (stall_hash != -1U) {
-+		/*
-+		 * Set this before dropping the lock to avoid racing with new
-+		 * work being added and clearing the stalled bit.
-+		 */
-+		wqe->flags |= IO_WQE_FLAG_STALLED;
- 		raw_spin_unlock(&wqe->lock);
- 		io_wait_on_hash(wqe, stall_hash);
- 		raw_spin_lock(&wqe->lock);
--		*stalled = true;
- 	}
- 
- 	return NULL;
-@@ -519,7 +522,6 @@ static void io_worker_handle_work(struct io_worker *worker)
- 
- 	do {
- 		struct io_wq_work *work;
--		bool stalled;
- get_next:
- 		/*
- 		 * If we got some work, mark us as busy. If we didn't, but
-@@ -528,12 +530,9 @@ static void io_worker_handle_work(struct io_worker *worker)
- 		 * can't make progress, any work completion or insertion will
- 		 * clear the stalled flag.
- 		 */
--		stalled = false;
--		work = io_get_next_work(wqe, worker, &stalled);
-+		work = io_get_next_work(wqe, worker);
- 		if (work)
- 			__io_worker_busy(wqe, worker, work);
--		else if (stalled)
--			wqe->flags |= IO_WQE_FLAG_STALLED;
- 
- 		raw_spin_unlock_irq(&wqe->lock);
- 		if (!work)

patches/kernel/0010-KVM-VMX-prepare-sync_pir_to_irr-for-running-with-API.patch

@@ -0,0 +1,90 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Paolo Bonzini <pbonzini@redhat.com>
+Date: Mon, 22 Nov 2021 19:43:09 -0500
+Subject: [PATCH] KVM: VMX: prepare sync_pir_to_irr for running with APICv
+ disabled
+
+If APICv is disabled for this vCPU, assigned devices may still attempt to
+post interrupts.  In that case, we need to cancel the vmentry and deliver
+the interrupt with KVM_REQ_EVENT.  Extend the existing code that handles
+injection of L1 interrupts into L2 to cover this case as well.
+
+vmx_hwapic_irr_update is only called when APICv is active so it would be
+confusing to add a check for vcpu->arch.apicv_active in there.  Instead,
+just use vmx_set_rvi directly in vmx_sync_pir_to_irr.
+
+Cc: stable@vger.kernel.org
+Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
+Reviewed-by: David Matlack <dmatlack@google.com>
+Reviewed-by: Sean Christopherson <seanjc@google.com>
+Message-Id: <20211123004311.2954158-3-pbonzini@redhat.com>
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+(cherry picked from commit 7e1901f6c86c896acff6609e0176f93f756d8b2a)
+[ T: reused WARN instead of newer KVM_BUG_ON for minimal change ]
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+---
+ arch/x86/kvm/vmx/vmx.c | 39 +++++++++++++++++++++++++--------------
+ 1 file changed, 25 insertions(+), 14 deletions(-)
+
+diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
+index fc6fbaba1cb5..2f6db087e243 100644
+--- a/arch/x86/kvm/vmx/vmx.c
++++ b/arch/x86/kvm/vmx/vmx.c
+@@ -6331,9 +6331,9 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
+ {
+ 	struct vcpu_vmx *vmx = to_vmx(vcpu);
+ 	int max_irr;
+-	bool max_irr_updated;
++	bool got_posted_interrupt;
+ 
+-	WARN_ON(!vcpu->arch.apicv_active);
++	WARN_ON(!enable_apicv);
+ 	if (pi_test_on(&vmx->pi_desc)) {
+ 		pi_clear_on(&vmx->pi_desc);
+ 		/*
+@@ -6341,22 +6341,33 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
+ 		 * But on x86 this is just a compiler barrier anyway.
+ 		 */
+ 		smp_mb__after_atomic();
+-		max_irr_updated =
++		got_posted_interrupt =
+ 			kvm_apic_update_irr(vcpu, vmx->pi_desc.pir, &max_irr);
+-
+-		/*
+-		 * If we are running L2 and L1 has a new pending interrupt
+-		 * which can be injected, this may cause a vmexit or it may
+-		 * be injected into L2.  Either way, this interrupt will be
+-		 * processed via KVM_REQ_EVENT, not RVI, because we do not use
+-		 * virtual interrupt delivery to inject L1 interrupts into L2.
+-		 */
+-		if (is_guest_mode(vcpu) && max_irr_updated)
+-			kvm_make_request(KVM_REQ_EVENT, vcpu);
+ 	} else {
+ 		max_irr = kvm_lapic_find_highest_irr(vcpu);
++		got_posted_interrupt = false;
+ 	}
+-	vmx_hwapic_irr_update(vcpu, max_irr);
++
++	/*
++	 * Newly recognized interrupts are injected via either virtual interrupt
++	 * delivery (RVI) or KVM_REQ_EVENT.  Virtual interrupt delivery is
++	 * disabled in two cases:
++	 *
++	 * 1) If L2 is running and the vCPU has a new pending interrupt.  If L1
++	 * wants to exit on interrupts, KVM_REQ_EVENT is needed to synthesize a
++	 * VM-Exit to L1.  If L1 doesn't want to exit, the interrupt is injected
++	 * into L2, but KVM doesn't use virtual interrupt delivery to inject
++	 * interrupts into L2, and so KVM_REQ_EVENT is again needed.
++	 *
++	 * 2) If APICv is disabled for this vCPU, assigned devices may still
++	 * attempt to post interrupts.  The posted interrupt vector will cause
++	 * a VM-Exit and the subsequent entry will call sync_pir_to_irr.
++	 */
++	if (!is_guest_mode(vcpu) && kvm_vcpu_apicv_active(vcpu))
++		vmx_set_rvi(max_irr);
++	else if (got_posted_interrupt)
++		kvm_make_request(KVM_REQ_EVENT, vcpu);
++
+ 	return max_irr;
+ }
+ 

submodules/ubuntu-impish

@@ -1 +1 @@
-Subproject commit b188ba567fc92eebd36f679de7ba1b8c2354839d
+Subproject commit 168d1231d9f29e3331fa0bbed876ffdd148143b8

submodules/zfsonlinux

@@ -1 +1 @@
-Subproject commit 0ee31a51f6eaa0466b3e4d67f829a4469dc4d466
+Subproject commit 531eac33046f7e207226b428e399bcab173b7b6b