--- /dev/null
+From 1d0cb4c8864addc362bae98e8ffa5500c87e1227 Mon Sep 17 00:00:00 2001
+From: Catalin Marinas <catalin.marinas@arm.com>
+Date: Tue, 17 May 2022 10:35:32 +0100
+Subject: arm64: mte: Ensure the cleared tags are visible before setting the PTE
+
+From: Catalin Marinas <catalin.marinas@arm.com>
+
+commit 1d0cb4c8864addc362bae98e8ffa5500c87e1227 upstream.
+
+As an optimisation, only pages mapped with PROT_MTE in user space have
+the MTE tags zeroed. This is done lazily at the set_pte_at() time via
+mte_sync_tags(). However, this function is missing a barrier and another
+CPU may see the PTE updated before the zeroed tags are visible. Add an
+smp_wmb() barrier if the mapping is Normal Tagged.
+
+Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
+Fixes: 34bfeea4a9e9 ("arm64: mte: Clear the tags when a page is mapped in user-space with PROT_MTE")
+Cc: <stable@vger.kernel.org> # 5.10.x
+Reported-by: Vladimir Murzin <vladimir.murzin@arm.com>
+Cc: Will Deacon <will@kernel.org>
+Reviewed-by: Steven Price <steven.price@arm.com>
+Tested-by: Vladimir Murzin <vladimir.murzin@arm.com>
+Link: https://lore.kernel.org/r/20220517093532.127095-1-catalin.marinas@arm.com
+Signed-off-by: Will Deacon <will@kernel.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ arch/arm64/kernel/mte.c | 3 +++
+ 1 file changed, 3 insertions(+)
+
+--- a/arch/arm64/kernel/mte.c
++++ b/arch/arm64/kernel/mte.c
+@@ -45,6 +45,9 @@ void mte_sync_tags(pte_t *ptep, pte_t pt
+ if (!test_and_set_bit(PG_mte_tagged, &page->flags))
+ mte_sync_page_tags(page, ptep, check_swap);
+ }
++
++ /* ensure the tags are visible before the PTE is set */
++ smp_wmb();
+ }
+
+ int memcmp_pages(struct page *page1, struct page *page2)
--- /dev/null
+From 19bef63f951e47dd4ba54810e6f7c7ff9344a3ef Mon Sep 17 00:00:00 2001
+From: Prakruthi Deepak Heragu <quic_pheragu@quicinc.com>
+Date: Fri, 13 May 2022 10:46:54 -0700
+Subject: arm64: paravirt: Use RCU read locks to guard stolen_time
+
+From: Prakruthi Deepak Heragu <quic_pheragu@quicinc.com>
+
+commit 19bef63f951e47dd4ba54810e6f7c7ff9344a3ef upstream.
+
+During hotplug, the stolen time data structure is unmapped and memset.
+There is a possibility of the timer IRQ being triggered before memset
+and stolen time is getting updated as part of this timer IRQ handler. This
+causes the below crash in timer handler -
+
+ [ 3457.473139][ C5] Unable to handle kernel paging request at virtual address ffffffc03df05148
+ ...
+ [ 3458.154398][ C5] Call trace:
+ [ 3458.157648][ C5] para_steal_clock+0x30/0x50
+ [ 3458.162319][ C5] irqtime_account_process_tick+0x30/0x194
+ [ 3458.168148][ C5] account_process_tick+0x3c/0x280
+ [ 3458.173274][ C5] update_process_times+0x5c/0xf4
+ [ 3458.178311][ C5] tick_sched_timer+0x180/0x384
+ [ 3458.183164][ C5] __run_hrtimer+0x160/0x57c
+ [ 3458.187744][ C5] hrtimer_interrupt+0x258/0x684
+ [ 3458.192698][ C5] arch_timer_handler_virt+0x5c/0xa0
+ [ 3458.198002][ C5] handle_percpu_devid_irq+0xdc/0x414
+ [ 3458.203385][ C5] handle_domain_irq+0xa8/0x168
+ [ 3458.208241][ C5] gic_handle_irq.34493+0x54/0x244
+ [ 3458.213359][ C5] call_on_irq_stack+0x40/0x70
+ [ 3458.218125][ C5] do_interrupt_handler+0x60/0x9c
+ [ 3458.223156][ C5] el1_interrupt+0x34/0x64
+ [ 3458.227560][ C5] el1h_64_irq_handler+0x1c/0x2c
+ [ 3458.232503][ C5] el1h_64_irq+0x7c/0x80
+ [ 3458.236736][ C5] free_vmap_area_noflush+0x108/0x39c
+ [ 3458.242126][ C5] remove_vm_area+0xbc/0x118
+ [ 3458.246714][ C5] vm_remove_mappings+0x48/0x2a4
+ [ 3458.251656][ C5] __vunmap+0x154/0x278
+ [ 3458.255796][ C5] stolen_time_cpu_down_prepare+0xc0/0xd8
+ [ 3458.261542][ C5] cpuhp_invoke_callback+0x248/0xc34
+ [ 3458.266842][ C5] cpuhp_thread_fun+0x1c4/0x248
+ [ 3458.271696][ C5] smpboot_thread_fn+0x1b0/0x400
+ [ 3458.276638][ C5] kthread+0x17c/0x1e0
+ [ 3458.280691][ C5] ret_from_fork+0x10/0x20
+
+As a fix, introduce rcu lock to update stolen time structure.
+
+Fixes: 75df529bec91 ("arm64: paravirt: Initialize steal time when cpu is online")
+Cc: stable@vger.kernel.org
+Suggested-by: Will Deacon <will@kernel.org>
+Signed-off-by: Prakruthi Deepak Heragu <quic_pheragu@quicinc.com>
+Signed-off-by: Elliot Berman <quic_eberman@quicinc.com>
+Reviewed-by: Srivatsa S. Bhat (VMware) <srivatsa@csail.mit.edu>
+Link: https://lore.kernel.org/r/20220513174654.362169-1-quic_eberman@quicinc.com
+Signed-off-by: Will Deacon <will@kernel.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ arch/arm64/kernel/paravirt.c | 29 +++++++++++++++++++++--------
+ 1 file changed, 21 insertions(+), 8 deletions(-)
+
+--- a/arch/arm64/kernel/paravirt.c
++++ b/arch/arm64/kernel/paravirt.c
+@@ -30,7 +30,7 @@ struct paravirt_patch_template pv_ops;
+ EXPORT_SYMBOL_GPL(pv_ops);
+
+ struct pv_time_stolen_time_region {
+- struct pvclock_vcpu_stolen_time *kaddr;
++ struct pvclock_vcpu_stolen_time __rcu *kaddr;
+ };
+
+ static DEFINE_PER_CPU(struct pv_time_stolen_time_region, stolen_time_region);
+@@ -47,7 +47,9 @@ early_param("no-steal-acc", parse_no_ste
+ /* return stolen time in ns by asking the hypervisor */
+ static u64 pv_steal_clock(int cpu)
+ {
++ struct pvclock_vcpu_stolen_time *kaddr = NULL;
+ struct pv_time_stolen_time_region *reg;
++ u64 ret = 0;
+
+ reg = per_cpu_ptr(&stolen_time_region, cpu);
+
+@@ -56,28 +58,37 @@ static u64 pv_steal_clock(int cpu)
+ * online notification callback runs. Until the callback
+ * has run we just return zero.
+ */
+- if (!reg->kaddr)
++ rcu_read_lock();
++ kaddr = rcu_dereference(reg->kaddr);
++ if (!kaddr) {
++ rcu_read_unlock();
+ return 0;
++ }
+
+- return le64_to_cpu(READ_ONCE(reg->kaddr->stolen_time));
++ ret = le64_to_cpu(READ_ONCE(kaddr->stolen_time));
++ rcu_read_unlock();
++ return ret;
+ }
+
+ static int stolen_time_cpu_down_prepare(unsigned int cpu)
+ {
++ struct pvclock_vcpu_stolen_time *kaddr = NULL;
+ struct pv_time_stolen_time_region *reg;
+
+ reg = this_cpu_ptr(&stolen_time_region);
+ if (!reg->kaddr)
+ return 0;
+
+- memunmap(reg->kaddr);
+- memset(reg, 0, sizeof(*reg));
++ kaddr = rcu_replace_pointer(reg->kaddr, NULL, true);
++ synchronize_rcu();
++ memunmap(kaddr);
+
+ return 0;
+ }
+
+ static int stolen_time_cpu_online(unsigned int cpu)
+ {
++ struct pvclock_vcpu_stolen_time *kaddr = NULL;
+ struct pv_time_stolen_time_region *reg;
+ struct arm_smccc_res res;
+
+@@ -88,17 +99,19 @@ static int stolen_time_cpu_online(unsign
+ if (res.a0 == SMCCC_RET_NOT_SUPPORTED)
+ return -EINVAL;
+
+- reg->kaddr = memremap(res.a0,
++ kaddr = memremap(res.a0,
+ sizeof(struct pvclock_vcpu_stolen_time),
+ MEMREMAP_WB);
+
++ rcu_assign_pointer(reg->kaddr, kaddr);
++
+ if (!reg->kaddr) {
+ pr_warn("Failed to map stolen time data structure\n");
+ return -ENOMEM;
+ }
+
+- if (le32_to_cpu(reg->kaddr->revision) != 0 ||
+- le32_to_cpu(reg->kaddr->attributes) != 0) {
++ if (le32_to_cpu(kaddr->revision) != 0 ||
++ le32_to_cpu(kaddr->attributes) != 0) {
+ pr_warn_once("Unexpected revision or attributes in stolen time data\n");
+ return -ENXIO;
+ }
--- /dev/null
+From 16287397ec5c08aa58db6acf7dbc55470d78087d Mon Sep 17 00:00:00 2001
+From: Ondrej Mosnacek <omosnace@redhat.com>
+Date: Tue, 3 May 2022 13:50:10 +0200
+Subject: crypto: qcom-rng - fix infinite loop on requests not multiple of WORD_SZ
+
+From: Ondrej Mosnacek <omosnace@redhat.com>
+
+commit 16287397ec5c08aa58db6acf7dbc55470d78087d upstream.
+
+The commit referenced in the Fixes tag removed the 'break' from the else
+branch in qcom_rng_read(), causing an infinite loop whenever 'max' is
+not a multiple of WORD_SZ. This can be reproduced e.g. by running:
+
+ kcapi-rng -b 67 >/dev/null
+
+There are many ways to fix this without adding back the 'break', but
+they all seem more awkward than simply adding it back, so do just that.
+
+Tested on a machine with Qualcomm Amberwing processor.
+
+Fixes: a680b1832ced ("crypto: qcom-rng - ensure buffer for generate is completely filled")
+Cc: stable@vger.kernel.org
+Signed-off-by: Ondrej Mosnacek <omosnace@redhat.com>
+Reviewed-by: Brian Masney <bmasney@redhat.com>
+Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ drivers/crypto/qcom-rng.c | 1 +
+ 1 file changed, 1 insertion(+)
+
+--- a/drivers/crypto/qcom-rng.c
++++ b/drivers/crypto/qcom-rng.c
+@@ -65,6 +65,7 @@ static int qcom_rng_read(struct qcom_rng
+ } else {
+ /* copy only remaining bytes */
+ memcpy(data, &val, max - currsize);
++ break;
+ }
+ } while (currsize < max);
+
--- /dev/null
+From 7c3e9fcad9c7d8bb5d69a576044fb16b1d2e8a01 Mon Sep 17 00:00:00 2001
+From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Pouiller?= <jerome.pouiller@silabs.com>
+Date: Tue, 17 May 2022 09:27:08 +0200
+Subject: dma-buf: fix use of DMA_BUF_SET_NAME_{A,B} in userspace
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+From: Jérôme Pouiller <jerome.pouiller@silabs.com>
+
+commit 7c3e9fcad9c7d8bb5d69a576044fb16b1d2e8a01 upstream.
+
+The typedefs u32 and u64 are not available in userspace. Thus user get
+an error he try to use DMA_BUF_SET_NAME_A or DMA_BUF_SET_NAME_B:
+
+ $ gcc -Wall -c -MMD -c -o ioctls_list.o ioctls_list.c
+ In file included from /usr/include/x86_64-linux-gnu/asm/ioctl.h:1,
+ from /usr/include/linux/ioctl.h:5,
+ from /usr/include/asm-generic/ioctls.h:5,
+ from ioctls_list.c:11:
+ ioctls_list.c:463:29: error: ‘u32’ undeclared here (not in a function)
+ 463 | { "DMA_BUF_SET_NAME_A", DMA_BUF_SET_NAME_A, -1, -1 }, // linux/dma-buf.h
+ | ^~~~~~~~~~~~~~~~~~
+ ioctls_list.c:464:29: error: ‘u64’ undeclared here (not in a function)
+ 464 | { "DMA_BUF_SET_NAME_B", DMA_BUF_SET_NAME_B, -1, -1 }, // linux/dma-buf.h
+ | ^~~~~~~~~~~~~~~~~~
+
+The issue was initially reported here[1].
+
+[1]: https://github.com/jerome-pouiller/ioctl/pull/14
+
+Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
+Reviewed-by: Christian König <christian.koenig@amd.com>
+Fixes: a5bff92eaac4 ("dma-buf: Fix SET_NAME ioctl uapi")
+CC: stable@vger.kernel.org
+Link: https://patchwork.freedesktop.org/patch/msgid/20220517072708.245265-1-Jerome.Pouiller@silabs.com
+Signed-off-by: Christian König <christian.koenig@amd.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ include/uapi/linux/dma-buf.h | 4 ++--
+ 1 file changed, 2 insertions(+), 2 deletions(-)
+
+--- a/include/uapi/linux/dma-buf.h
++++ b/include/uapi/linux/dma-buf.h
+@@ -44,7 +44,7 @@ struct dma_buf_sync {
+ * between them in actual uapi, they're just different numbers.
+ */
+ #define DMA_BUF_SET_NAME _IOW(DMA_BUF_BASE, 1, const char *)
+-#define DMA_BUF_SET_NAME_A _IOW(DMA_BUF_BASE, 1, u32)
+-#define DMA_BUF_SET_NAME_B _IOW(DMA_BUF_BASE, 1, u64)
++#define DMA_BUF_SET_NAME_A _IOW(DMA_BUF_BASE, 1, __u32)
++#define DMA_BUF_SET_NAME_B _IOW(DMA_BUF_BASE, 1, __u64)
+
+ #endif
--- /dev/null
+From 6e03b13cc7d9427c2c77feed1549191015615202 Mon Sep 17 00:00:00 2001
+From: Hangyu Hua <hbh25y@gmail.com>
+Date: Mon, 16 May 2022 11:20:42 +0800
+Subject: drm/dp/mst: fix a possible memory leak in fetch_monitor_name()
+
+From: Hangyu Hua <hbh25y@gmail.com>
+
+commit 6e03b13cc7d9427c2c77feed1549191015615202 upstream.
+
+drm_dp_mst_get_edid call kmemdup to create mst_edid. So mst_edid need to be
+freed after use.
+
+Signed-off-by: Hangyu Hua <hbh25y@gmail.com>
+Reviewed-by: Lyude Paul <lyude@redhat.com>
+Signed-off-by: Lyude Paul <lyude@redhat.com>
+Cc: stable@vger.kernel.org
+Link: https://patchwork.freedesktop.org/patch/msgid/20220516032042.13166-1-hbh25y@gmail.com
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ drivers/gpu/drm/drm_dp_mst_topology.c | 1 +
+ 1 file changed, 1 insertion(+)
+
+--- a/drivers/gpu/drm/drm_dp_mst_topology.c
++++ b/drivers/gpu/drm/drm_dp_mst_topology.c
+@@ -4792,6 +4792,7 @@ static void fetch_monitor_name(struct dr
+
+ mst_edid = drm_dp_mst_get_edid(port->connector, mgr, port);
+ drm_edid_get_monitor_name(mst_edid, name, namelen);
++ kfree(mst_edid);
+ }
+
+ /**
--- /dev/null
+From fb4554c2232e44d595920f4d5c66cf8f7d13f9bc Mon Sep 17 00:00:00 2001
+From: Al Viro <viro@zeniv.linux.org.uk>
+Date: Mon, 16 May 2022 16:42:13 +0800
+Subject: Fix double fget() in vhost_net_set_backend()
+
+From: Al Viro <viro@zeniv.linux.org.uk>
+
+commit fb4554c2232e44d595920f4d5c66cf8f7d13f9bc upstream.
+
+Descriptor table is a shared resource; two fget() on the same descriptor
+may return different struct file references. get_tap_ptr_ring() is
+called after we'd found (and pinned) the socket we'll be using and it
+tries to find the private tun/tap data structures associated with it.
+Redoing the lookup by the same file descriptor we'd used to get the
+socket is racy - we need to same struct file.
+
+Thanks to Jason for spotting a braino in the original variant of patch -
+I'd missed the use of fd == -1 for disabling backend, and in that case
+we can end up with sock == NULL and sock != oldsock.
+
+Cc: stable@kernel.org
+Acked-by: Michael S. Tsirkin <mst@redhat.com>
+Signed-off-by: Jason Wang <jasowang@redhat.com>
+Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ drivers/vhost/net.c | 15 +++++++--------
+ 1 file changed, 7 insertions(+), 8 deletions(-)
+
+--- a/drivers/vhost/net.c
++++ b/drivers/vhost/net.c
+@@ -1450,13 +1450,9 @@ err:
+ return ERR_PTR(r);
+ }
+
+-static struct ptr_ring *get_tap_ptr_ring(int fd)
++static struct ptr_ring *get_tap_ptr_ring(struct file *file)
+ {
+ struct ptr_ring *ring;
+- struct file *file = fget(fd);
+-
+- if (!file)
+- return NULL;
+ ring = tun_get_tx_ring(file);
+ if (!IS_ERR(ring))
+ goto out;
+@@ -1465,7 +1461,6 @@ static struct ptr_ring *get_tap_ptr_ring
+ goto out;
+ ring = NULL;
+ out:
+- fput(file);
+ return ring;
+ }
+
+@@ -1552,8 +1547,12 @@ static long vhost_net_set_backend(struct
+ r = vhost_net_enable_vq(n, vq);
+ if (r)
+ goto err_used;
+- if (index == VHOST_NET_VQ_RX)
+- nvq->rx_ring = get_tap_ptr_ring(fd);
++ if (index == VHOST_NET_VQ_RX) {
++ if (sock)
++ nvq->rx_ring = get_tap_ptr_ring(sock->file);
++ else
++ nvq->rx_ring = NULL;
++ }
+
+ oldubufs = nvq->ubufs;
+ nvq->ubufs = ubufs;
--- /dev/null
+From b28cb0cd2c5e80a8c0feb408a0e4b0dbb6d132c5 Mon Sep 17 00:00:00 2001
+From: Sean Christopherson <seanjc@google.com>
+Date: Wed, 11 May 2022 14:51:22 +0000
+Subject: KVM: x86/mmu: Update number of zapped pages even if page list is stable
+
+From: Sean Christopherson <seanjc@google.com>
+
+commit b28cb0cd2c5e80a8c0feb408a0e4b0dbb6d132c5 upstream.
+
+When zapping obsolete pages, update the running count of zapped pages
+regardless of whether or not the list has become unstable due to zapping
+a shadow page with its own child shadow pages. If the VM is backed by
+mostly 4kb pages, KVM can zap an absurd number of SPTEs without bumping
+the batch count and thus without yielding. In the worst case scenario,
+this can cause a soft lokcup.
+
+ watchdog: BUG: soft lockup - CPU#12 stuck for 22s! [dirty_log_perf_:13020]
+ RIP: 0010:workingset_activation+0x19/0x130
+ mark_page_accessed+0x266/0x2e0
+ kvm_set_pfn_accessed+0x31/0x40
+ mmu_spte_clear_track_bits+0x136/0x1c0
+ drop_spte+0x1a/0xc0
+ mmu_page_zap_pte+0xef/0x120
+ __kvm_mmu_prepare_zap_page+0x205/0x5e0
+ kvm_mmu_zap_all_fast+0xd7/0x190
+ kvm_mmu_invalidate_zap_pages_in_memslot+0xe/0x10
+ kvm_page_track_flush_slot+0x5c/0x80
+ kvm_arch_flush_shadow_memslot+0xe/0x10
+ kvm_set_memslot+0x1a8/0x5d0
+ __kvm_set_memory_region+0x337/0x590
+ kvm_vm_ioctl+0xb08/0x1040
+
+Fixes: fbb158cb88b6 ("KVM: x86/mmu: Revert "Revert "KVM: MMU: zap pages in batch""")
+Reported-by: David Matlack <dmatlack@google.com>
+Reviewed-by: Ben Gardon <bgardon@google.com>
+Cc: stable@vger.kernel.org
+Signed-off-by: Sean Christopherson <seanjc@google.com>
+Message-Id: <20220511145122.3133334-1-seanjc@google.com>
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ arch/x86/kvm/mmu/mmu.c | 10 ++++++----
+ 1 file changed, 6 insertions(+), 4 deletions(-)
+
+--- a/arch/x86/kvm/mmu/mmu.c
++++ b/arch/x86/kvm/mmu/mmu.c
+@@ -5375,6 +5375,7 @@ static void kvm_zap_obsolete_pages(struc
+ {
+ struct kvm_mmu_page *sp, *node;
+ int nr_zapped, batch = 0;
++ bool unstable;
+
+ restart:
+ list_for_each_entry_safe_reverse(sp, node,
+@@ -5406,11 +5407,12 @@ restart:
+ goto restart;
+ }
+
+- if (__kvm_mmu_prepare_zap_page(kvm, sp,
+- &kvm->arch.zapped_obsolete_pages, &nr_zapped)) {
+- batch += nr_zapped;
++ unstable = __kvm_mmu_prepare_zap_page(kvm, sp,
++ &kvm->arch.zapped_obsolete_pages, &nr_zapped);
++ batch += nr_zapped;
++
++ if (unstable)
+ goto restart;
+- }
+ }
+
+ /*
--- /dev/null
+From 75dbb685f4e8786c33ddef8279bab0eadfb0731f Mon Sep 17 00:00:00 2001
+From: Ilya Dryomov <idryomov@gmail.com>
+Date: Sat, 14 May 2022 12:16:47 +0200
+Subject: libceph: fix potential use-after-free on linger ping and resends
+
+From: Ilya Dryomov <idryomov@gmail.com>
+
+commit 75dbb685f4e8786c33ddef8279bab0eadfb0731f upstream.
+
+request_reinit() is not only ugly as the comment rightfully suggests,
+but also unsafe. Even though it is called with osdc->lock held for
+write in all cases, resetting the OSD request refcount can still race
+with handle_reply() and result in use-after-free. Taking linger ping
+as an example:
+
+ handle_timeout thread handle_reply thread
+
+ down_read(&osdc->lock)
+ req = lookup_request(...)
+ ...
+ finish_request(req) # unregisters
+ up_read(&osdc->lock)
+ __complete_request(req)
+ linger_ping_cb(req)
+
+ # req->r_kref == 2 because handle_reply still holds its ref
+
+ down_write(&osdc->lock)
+ send_linger_ping(lreq)
+ req = lreq->ping_req # same req
+ # cancel_linger_request is NOT
+ # called - handle_reply already
+ # unregistered
+ request_reinit(req)
+ WARN_ON(req->r_kref != 1) # fires
+ request_init(req)
+ kref_init(req->r_kref)
+
+ # req->r_kref == 1 after kref_init
+
+ ceph_osdc_put_request(req)
+ kref_put(req->r_kref)
+
+ # req->r_kref == 0 after kref_put, req is freed
+
+ <further req initialization/use> !!!
+
+This happens because send_linger_ping() always (re)uses the same OSD
+request for watch ping requests, relying on cancel_linger_request() to
+unregister it from the OSD client and rip its messages out from the
+messenger. send_linger() does the same for watch/notify registration
+and watch reconnect requests. Unfortunately cancel_request() doesn't
+guarantee that after it returns the OSD client would be completely done
+with the OSD request -- a ref could still be held and the callback (if
+specified) could still be invoked too.
+
+The original motivation for request_reinit() was inability to deal with
+allocation failures in send_linger() and send_linger_ping(). Switching
+to using osdc->req_mempool (currently only used by CephFS) respects that
+and allows us to get rid of request_reinit().
+
+Cc: stable@vger.kernel.org
+Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
+Reviewed-by: Xiubo Li <xiubli@redhat.com>
+Acked-by: Jeff Layton <jlayton@kernel.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ include/linux/ceph/osd_client.h | 3
+ net/ceph/osd_client.c | 302 +++++++++++++++-------------------------
+ 2 files changed, 122 insertions(+), 183 deletions(-)
+
+--- a/include/linux/ceph/osd_client.h
++++ b/include/linux/ceph/osd_client.h
+@@ -287,6 +287,9 @@ struct ceph_osd_linger_request {
+ rados_watcherrcb_t errcb;
+ void *data;
+
++ struct ceph_pagelist *request_pl;
++ struct page **notify_id_pages;
++
+ struct page ***preply_pages;
+ size_t *preply_len;
+ };
+--- a/net/ceph/osd_client.c
++++ b/net/ceph/osd_client.c
+@@ -537,43 +537,6 @@ static void request_init(struct ceph_osd
+ target_init(&req->r_t);
+ }
+
+-/*
+- * This is ugly, but it allows us to reuse linger registration and ping
+- * requests, keeping the structure of the code around send_linger{_ping}()
+- * reasonable. Setting up a min_nr=2 mempool for each linger request
+- * and dealing with copying ops (this blasts req only, watch op remains
+- * intact) isn't any better.
+- */
+-static void request_reinit(struct ceph_osd_request *req)
+-{
+- struct ceph_osd_client *osdc = req->r_osdc;
+- bool mempool = req->r_mempool;
+- unsigned int num_ops = req->r_num_ops;
+- u64 snapid = req->r_snapid;
+- struct ceph_snap_context *snapc = req->r_snapc;
+- bool linger = req->r_linger;
+- struct ceph_msg *request_msg = req->r_request;
+- struct ceph_msg *reply_msg = req->r_reply;
+-
+- dout("%s req %p\n", __func__, req);
+- WARN_ON(kref_read(&req->r_kref) != 1);
+- request_release_checks(req);
+-
+- WARN_ON(kref_read(&request_msg->kref) != 1);
+- WARN_ON(kref_read(&reply_msg->kref) != 1);
+- target_destroy(&req->r_t);
+-
+- request_init(req);
+- req->r_osdc = osdc;
+- req->r_mempool = mempool;
+- req->r_num_ops = num_ops;
+- req->r_snapid = snapid;
+- req->r_snapc = snapc;
+- req->r_linger = linger;
+- req->r_request = request_msg;
+- req->r_reply = reply_msg;
+-}
+-
+ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
+ struct ceph_snap_context *snapc,
+ unsigned int num_ops,
+@@ -918,14 +881,30 @@ EXPORT_SYMBOL(osd_req_op_xattr_init);
+ * @watch_opcode: CEPH_OSD_WATCH_OP_*
+ */
+ static void osd_req_op_watch_init(struct ceph_osd_request *req, int which,
+- u64 cookie, u8 watch_opcode)
++ u8 watch_opcode, u64 cookie, u32 gen)
+ {
+ struct ceph_osd_req_op *op;
+
+ op = osd_req_op_init(req, which, CEPH_OSD_OP_WATCH, 0);
+ op->watch.cookie = cookie;
+ op->watch.op = watch_opcode;
+- op->watch.gen = 0;
++ op->watch.gen = gen;
++}
++
++/*
++ * prot_ver, timeout and notify payload (may be empty) should already be
++ * encoded in @request_pl
++ */
++static void osd_req_op_notify_init(struct ceph_osd_request *req, int which,
++ u64 cookie, struct ceph_pagelist *request_pl)
++{
++ struct ceph_osd_req_op *op;
++
++ op = osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY, 0);
++ op->notify.cookie = cookie;
++
++ ceph_osd_data_pagelist_init(&op->notify.request_data, request_pl);
++ op->indata_len = request_pl->length;
+ }
+
+ /*
+@@ -2727,10 +2706,13 @@ static void linger_release(struct kref *
+ WARN_ON(!list_empty(&lreq->pending_lworks));
+ WARN_ON(lreq->osd);
+
+- if (lreq->reg_req)
+- ceph_osdc_put_request(lreq->reg_req);
+- if (lreq->ping_req)
+- ceph_osdc_put_request(lreq->ping_req);
++ if (lreq->request_pl)
++ ceph_pagelist_release(lreq->request_pl);
++ if (lreq->notify_id_pages)
++ ceph_release_page_vector(lreq->notify_id_pages, 1);
++
++ ceph_osdc_put_request(lreq->reg_req);
++ ceph_osdc_put_request(lreq->ping_req);
+ target_destroy(&lreq->t);
+ kfree(lreq);
+ }
+@@ -2999,6 +2981,12 @@ static void linger_commit_cb(struct ceph
+ struct ceph_osd_linger_request *lreq = req->r_priv;
+
+ mutex_lock(&lreq->lock);
++ if (req != lreq->reg_req) {
++ dout("%s lreq %p linger_id %llu unknown req (%p != %p)\n",
++ __func__, lreq, lreq->linger_id, req, lreq->reg_req);
++ goto out;
++ }
++
+ dout("%s lreq %p linger_id %llu result %d\n", __func__, lreq,
+ lreq->linger_id, req->r_result);
+ linger_reg_commit_complete(lreq, req->r_result);
+@@ -3022,6 +3010,7 @@ static void linger_commit_cb(struct ceph
+ }
+ }
+
++out:
+ mutex_unlock(&lreq->lock);
+ linger_put(lreq);
+ }
+@@ -3044,6 +3033,12 @@ static void linger_reconnect_cb(struct c
+ struct ceph_osd_linger_request *lreq = req->r_priv;
+
+ mutex_lock(&lreq->lock);
++ if (req != lreq->reg_req) {
++ dout("%s lreq %p linger_id %llu unknown req (%p != %p)\n",
++ __func__, lreq, lreq->linger_id, req, lreq->reg_req);
++ goto out;
++ }
++
+ dout("%s lreq %p linger_id %llu result %d last_error %d\n", __func__,
+ lreq, lreq->linger_id, req->r_result, lreq->last_error);
+ if (req->r_result < 0) {
+@@ -3053,46 +3048,64 @@ static void linger_reconnect_cb(struct c
+ }
+ }
+
++out:
+ mutex_unlock(&lreq->lock);
+ linger_put(lreq);
+ }
+
+ static void send_linger(struct ceph_osd_linger_request *lreq)
+ {
+- struct ceph_osd_request *req = lreq->reg_req;
+- struct ceph_osd_req_op *op = &req->r_ops[0];
++ struct ceph_osd_client *osdc = lreq->osdc;
++ struct ceph_osd_request *req;
++ int ret;
+
+- verify_osdc_wrlocked(req->r_osdc);
++ verify_osdc_wrlocked(osdc);
++ mutex_lock(&lreq->lock);
+ dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id);
+
+- if (req->r_osd)
+- cancel_linger_request(req);
++ if (lreq->reg_req) {
++ if (lreq->reg_req->r_osd)
++ cancel_linger_request(lreq->reg_req);
++ ceph_osdc_put_request(lreq->reg_req);
++ }
++
++ req = ceph_osdc_alloc_request(osdc, NULL, 1, true, GFP_NOIO);
++ BUG_ON(!req);
+
+- request_reinit(req);
+ target_copy(&req->r_t, &lreq->t);
+ req->r_mtime = lreq->mtime;
+
+- mutex_lock(&lreq->lock);
+ if (lreq->is_watch && lreq->committed) {
+- WARN_ON(op->op != CEPH_OSD_OP_WATCH ||
+- op->watch.cookie != lreq->linger_id);
+- op->watch.op = CEPH_OSD_WATCH_OP_RECONNECT;
+- op->watch.gen = ++lreq->register_gen;
++ osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_RECONNECT,
++ lreq->linger_id, ++lreq->register_gen);
+ dout("lreq %p reconnect register_gen %u\n", lreq,
+- op->watch.gen);
++ req->r_ops[0].watch.gen);
+ req->r_callback = linger_reconnect_cb;
+ } else {
+- if (!lreq->is_watch)
++ if (lreq->is_watch) {
++ osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_WATCH,
++ lreq->linger_id, 0);
++ } else {
+ lreq->notify_id = 0;
+- else
+- WARN_ON(op->watch.op != CEPH_OSD_WATCH_OP_WATCH);
++
++ refcount_inc(&lreq->request_pl->refcnt);
++ osd_req_op_notify_init(req, 0, lreq->linger_id,
++ lreq->request_pl);
++ ceph_osd_data_pages_init(
++ osd_req_op_data(req, 0, notify, response_data),
++ lreq->notify_id_pages, PAGE_SIZE, 0, false, false);
++ }
+ dout("lreq %p register\n", lreq);
+ req->r_callback = linger_commit_cb;
+ }
+- mutex_unlock(&lreq->lock);
++
++ ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
++ BUG_ON(ret);
+
+ req->r_priv = linger_get(lreq);
+ req->r_linger = true;
++ lreq->reg_req = req;
++ mutex_unlock(&lreq->lock);
+
+ submit_request(req, true);
+ }
+@@ -3102,6 +3115,12 @@ static void linger_ping_cb(struct ceph_o
+ struct ceph_osd_linger_request *lreq = req->r_priv;
+
+ mutex_lock(&lreq->lock);
++ if (req != lreq->ping_req) {
++ dout("%s lreq %p linger_id %llu unknown req (%p != %p)\n",
++ __func__, lreq, lreq->linger_id, req, lreq->ping_req);
++ goto out;
++ }
++
+ dout("%s lreq %p linger_id %llu result %d ping_sent %lu last_error %d\n",
+ __func__, lreq, lreq->linger_id, req->r_result, lreq->ping_sent,
+ lreq->last_error);
+@@ -3117,6 +3136,7 @@ static void linger_ping_cb(struct ceph_o
+ lreq->register_gen, req->r_ops[0].watch.gen);
+ }
+
++out:
+ mutex_unlock(&lreq->lock);
+ linger_put(lreq);
+ }
+@@ -3124,8 +3144,8 @@ static void linger_ping_cb(struct ceph_o
+ static void send_linger_ping(struct ceph_osd_linger_request *lreq)
+ {
+ struct ceph_osd_client *osdc = lreq->osdc;
+- struct ceph_osd_request *req = lreq->ping_req;
+- struct ceph_osd_req_op *op = &req->r_ops[0];
++ struct ceph_osd_request *req;
++ int ret;
+
+ if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD)) {
+ dout("%s PAUSERD\n", __func__);
+@@ -3137,19 +3157,26 @@ static void send_linger_ping(struct ceph
+ __func__, lreq, lreq->linger_id, lreq->ping_sent,
+ lreq->register_gen);
+
+- if (req->r_osd)
+- cancel_linger_request(req);
++ if (lreq->ping_req) {
++ if (lreq->ping_req->r_osd)
++ cancel_linger_request(lreq->ping_req);
++ ceph_osdc_put_request(lreq->ping_req);
++ }
+
+- request_reinit(req);
+- target_copy(&req->r_t, &lreq->t);
++ req = ceph_osdc_alloc_request(osdc, NULL, 1, true, GFP_NOIO);
++ BUG_ON(!req);
+
+- WARN_ON(op->op != CEPH_OSD_OP_WATCH ||
+- op->watch.cookie != lreq->linger_id ||
+- op->watch.op != CEPH_OSD_WATCH_OP_PING);
+- op->watch.gen = lreq->register_gen;
++ target_copy(&req->r_t, &lreq->t);
++ osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_PING, lreq->linger_id,
++ lreq->register_gen);
+ req->r_callback = linger_ping_cb;
++
++ ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
++ BUG_ON(ret);
++
+ req->r_priv = linger_get(lreq);
+ req->r_linger = true;
++ lreq->ping_req = req;
+
+ ceph_osdc_get_request(req);
+ account_request(req);
+@@ -3165,12 +3192,6 @@ static void linger_submit(struct ceph_os
+
+ down_write(&osdc->lock);
+ linger_register(lreq);
+- if (lreq->is_watch) {
+- lreq->reg_req->r_ops[0].watch.cookie = lreq->linger_id;
+- lreq->ping_req->r_ops[0].watch.cookie = lreq->linger_id;
+- } else {
+- lreq->reg_req->r_ops[0].notify.cookie = lreq->linger_id;
+- }
+
+ calc_target(osdc, &lreq->t, false);
+ osd = lookup_create_osd(osdc, lreq->t.osd, true);
+@@ -3202,9 +3223,9 @@ static void cancel_linger_map_check(stru
+ */
+ static void __linger_cancel(struct ceph_osd_linger_request *lreq)
+ {
+- if (lreq->is_watch && lreq->ping_req->r_osd)
++ if (lreq->ping_req && lreq->ping_req->r_osd)
+ cancel_linger_request(lreq->ping_req);
+- if (lreq->reg_req->r_osd)
++ if (lreq->reg_req && lreq->reg_req->r_osd)
+ cancel_linger_request(lreq->reg_req);
+ cancel_linger_map_check(lreq);
+ unlink_linger(lreq->osd, lreq);
+@@ -4651,43 +4672,6 @@ again:
+ }
+ EXPORT_SYMBOL(ceph_osdc_sync);
+
+-static struct ceph_osd_request *
+-alloc_linger_request(struct ceph_osd_linger_request *lreq)
+-{
+- struct ceph_osd_request *req;
+-
+- req = ceph_osdc_alloc_request(lreq->osdc, NULL, 1, false, GFP_NOIO);
+- if (!req)
+- return NULL;
+-
+- ceph_oid_copy(&req->r_base_oid, &lreq->t.base_oid);
+- ceph_oloc_copy(&req->r_base_oloc, &lreq->t.base_oloc);
+- return req;
+-}
+-
+-static struct ceph_osd_request *
+-alloc_watch_request(struct ceph_osd_linger_request *lreq, u8 watch_opcode)
+-{
+- struct ceph_osd_request *req;
+-
+- req = alloc_linger_request(lreq);
+- if (!req)
+- return NULL;
+-
+- /*
+- * Pass 0 for cookie because we don't know it yet, it will be
+- * filled in by linger_submit().
+- */
+- osd_req_op_watch_init(req, 0, 0, watch_opcode);
+-
+- if (ceph_osdc_alloc_messages(req, GFP_NOIO)) {
+- ceph_osdc_put_request(req);
+- return NULL;
+- }
+-
+- return req;
+-}
+-
+ /*
+ * Returns a handle, caller owns a ref.
+ */
+@@ -4717,18 +4701,6 @@ ceph_osdc_watch(struct ceph_osd_client *
+ lreq->t.flags = CEPH_OSD_FLAG_WRITE;
+ ktime_get_real_ts64(&lreq->mtime);
+
+- lreq->reg_req = alloc_watch_request(lreq, CEPH_OSD_WATCH_OP_WATCH);
+- if (!lreq->reg_req) {
+- ret = -ENOMEM;
+- goto err_put_lreq;
+- }
+-
+- lreq->ping_req = alloc_watch_request(lreq, CEPH_OSD_WATCH_OP_PING);
+- if (!lreq->ping_req) {
+- ret = -ENOMEM;
+- goto err_put_lreq;
+- }
+-
+ linger_submit(lreq);
+ ret = linger_reg_commit_wait(lreq);
+ if (ret) {
+@@ -4766,8 +4738,8 @@ int ceph_osdc_unwatch(struct ceph_osd_cl
+ ceph_oloc_copy(&req->r_base_oloc, &lreq->t.base_oloc);
+ req->r_flags = CEPH_OSD_FLAG_WRITE;
+ ktime_get_real_ts64(&req->r_mtime);
+- osd_req_op_watch_init(req, 0, lreq->linger_id,
+- CEPH_OSD_WATCH_OP_UNWATCH);
++ osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_UNWATCH,
++ lreq->linger_id, 0);
+
+ ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
+ if (ret)
+@@ -4853,35 +4825,6 @@ out_put_req:
+ }
+ EXPORT_SYMBOL(ceph_osdc_notify_ack);
+
+-static int osd_req_op_notify_init(struct ceph_osd_request *req, int which,
+- u64 cookie, u32 prot_ver, u32 timeout,
+- void *payload, u32 payload_len)
+-{
+- struct ceph_osd_req_op *op;
+- struct ceph_pagelist *pl;
+- int ret;
+-
+- op = osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY, 0);
+- op->notify.cookie = cookie;
+-
+- pl = ceph_pagelist_alloc(GFP_NOIO);
+- if (!pl)
+- return -ENOMEM;
+-
+- ret = ceph_pagelist_encode_32(pl, 1); /* prot_ver */
+- ret |= ceph_pagelist_encode_32(pl, timeout);
+- ret |= ceph_pagelist_encode_32(pl, payload_len);
+- ret |= ceph_pagelist_append(pl, payload, payload_len);
+- if (ret) {
+- ceph_pagelist_release(pl);
+- return -ENOMEM;
+- }
+-
+- ceph_osd_data_pagelist_init(&op->notify.request_data, pl);
+- op->indata_len = pl->length;
+- return 0;
+-}
+-
+ /*
+ * @timeout: in seconds
+ *
+@@ -4900,7 +4843,6 @@ int ceph_osdc_notify(struct ceph_osd_cli
+ size_t *preply_len)
+ {
+ struct ceph_osd_linger_request *lreq;
+- struct page **pages;
+ int ret;
+
+ WARN_ON(!timeout);
+@@ -4913,41 +4855,35 @@ int ceph_osdc_notify(struct ceph_osd_cli
+ if (!lreq)
+ return -ENOMEM;
+
+- lreq->preply_pages = preply_pages;
+- lreq->preply_len = preply_len;
+-
+- ceph_oid_copy(&lreq->t.base_oid, oid);
+- ceph_oloc_copy(&lreq->t.base_oloc, oloc);
+- lreq->t.flags = CEPH_OSD_FLAG_READ;
+-
+- lreq->reg_req = alloc_linger_request(lreq);
+- if (!lreq->reg_req) {
++ lreq->request_pl = ceph_pagelist_alloc(GFP_NOIO);
++ if (!lreq->request_pl) {
+ ret = -ENOMEM;
+ goto out_put_lreq;
+ }
+
+- /*
+- * Pass 0 for cookie because we don't know it yet, it will be
+- * filled in by linger_submit().
+- */
+- ret = osd_req_op_notify_init(lreq->reg_req, 0, 0, 1, timeout,
+- payload, payload_len);
+- if (ret)
++ ret = ceph_pagelist_encode_32(lreq->request_pl, 1); /* prot_ver */
++ ret |= ceph_pagelist_encode_32(lreq->request_pl, timeout);
++ ret |= ceph_pagelist_encode_32(lreq->request_pl, payload_len);
++ ret |= ceph_pagelist_append(lreq->request_pl, payload, payload_len);
++ if (ret) {
++ ret = -ENOMEM;
+ goto out_put_lreq;
++ }
+
+ /* for notify_id */
+- pages = ceph_alloc_page_vector(1, GFP_NOIO);
+- if (IS_ERR(pages)) {
+- ret = PTR_ERR(pages);
++ lreq->notify_id_pages = ceph_alloc_page_vector(1, GFP_NOIO);
++ if (IS_ERR(lreq->notify_id_pages)) {
++ ret = PTR_ERR(lreq->notify_id_pages);
++ lreq->notify_id_pages = NULL;
+ goto out_put_lreq;
+ }
+- ceph_osd_data_pages_init(osd_req_op_data(lreq->reg_req, 0, notify,
+- response_data),
+- pages, PAGE_SIZE, 0, false, true);
+
+- ret = ceph_osdc_alloc_messages(lreq->reg_req, GFP_NOIO);
+- if (ret)
+- goto out_put_lreq;
++ lreq->preply_pages = preply_pages;
++ lreq->preply_len = preply_len;
++
++ ceph_oid_copy(&lreq->t.base_oid, oid);
++ ceph_oloc_copy(&lreq->t.base_oloc, oloc);
++ lreq->t.flags = CEPH_OSD_FLAG_READ;
+
+ linger_submit(lreq);
+ ret = linger_reg_commit_wait(lreq);
--- /dev/null
+From 92597f97a40bf661bebceb92e26ff87c76d562d4 Mon Sep 17 00:00:00 2001
+From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
+Date: Thu, 31 Mar 2022 19:38:51 +0200
+Subject: PCI/PM: Avoid putting Elo i2 PCIe Ports in D3cold
+
+From: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+
+commit 92597f97a40bf661bebceb92e26ff87c76d562d4 upstream.
+
+If a Root Port on Elo i2 is put into D3cold and then back into D0, the
+downstream device becomes permanently inaccessible, so add a bridge D3 DMI
+quirk for that system.
+
+This was exposed by 14858dcc3b35 ("PCI: Use pci_update_current_state() in
+pci_enable_device_flags()"), but before that commit the Root Port in
+question had never been put into D3cold for real due to a mismatch between
+its power state retrieved from the PCI_PM_CTRL register (which was
+accessible even though the platform firmware indicated that the port was in
+D3cold) and the state of an ACPI power resource involved in its power
+management.
+
+BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=215715
+Link: https://lore.kernel.org/r/11980172.O9o76ZdvQC@kreacher
+Reported-by: Stefan Gottwald <gottwald@igel.com>
+Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
+Cc: stable@vger.kernel.org # v5.15+
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ drivers/pci/pci.c | 10 ++++++++++
+ 1 file changed, 10 insertions(+)
+
+--- a/drivers/pci/pci.c
++++ b/drivers/pci/pci.c
+@@ -2829,6 +2829,16 @@ static const struct dmi_system_id bridge
+ DMI_MATCH(DMI_BOARD_VENDOR, "Gigabyte Technology Co., Ltd."),
+ DMI_MATCH(DMI_BOARD_NAME, "X299 DESIGNARE EX-CF"),
+ },
++ /*
++ * Downstream device is not accessible after putting a root port
++ * into D3cold and back into D0 on Elo i2.
++ */
++ .ident = "Elo i2",
++ .matches = {
++ DMI_MATCH(DMI_SYS_VENDOR, "Elo Touch Solutions"),
++ DMI_MATCH(DMI_PRODUCT_NAME, "Elo i2"),
++ DMI_MATCH(DMI_PRODUCT_VERSION, "RevB"),
++ },
+ },
+ #endif
+ { }
--- /dev/null
+From 3ac6487e584a1eb54071dbe1212e05b884136704 Mon Sep 17 00:00:00 2001
+From: Peter Zijlstra <peterz@infradead.org>
+Date: Fri, 20 May 2022 20:38:06 +0200
+Subject: perf: Fix sys_perf_event_open() race against self
+
+From: Peter Zijlstra <peterz@infradead.org>
+
+commit 3ac6487e584a1eb54071dbe1212e05b884136704 upstream.
+
+Norbert reported that it's possible to race sys_perf_event_open() such
+that the looser ends up in another context from the group leader,
+triggering many WARNs.
+
+The move_group case checks for races against itself, but the
+!move_group case doesn't, seemingly relying on the previous
+group_leader->ctx == ctx check. However, that check is racy due to not
+holding any locks at that time.
+
+Therefore, re-check the result after acquiring locks and bailing
+if they no longer match.
+
+Additionally, clarify the not_move_group case from the
+move_group-vs-move_group race.
+
+Fixes: f63a8daa5812 ("perf: Fix event->ctx locking")
+Reported-by: Norbert Slusarek <nslusarek@gmx.net>
+Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ kernel/events/core.c | 14 ++++++++++++++
+ 1 file changed, 14 insertions(+)
+
+--- a/kernel/events/core.c
++++ b/kernel/events/core.c
+@@ -11946,6 +11946,9 @@ SYSCALL_DEFINE5(perf_event_open,
+ * Do not allow to attach to a group in a different task
+ * or CPU context. If we're moving SW events, we'll fix
+ * this up later, so allow that.
++ *
++ * Racy, not holding group_leader->ctx->mutex, see comment with
++ * perf_event_ctx_lock().
+ */
+ if (!move_group && group_leader->ctx != ctx)
+ goto err_context;
+@@ -12013,6 +12016,7 @@ SYSCALL_DEFINE5(perf_event_open,
+ } else {
+ perf_event_ctx_unlock(group_leader, gctx);
+ move_group = 0;
++ goto not_move_group;
+ }
+ }
+
+@@ -12029,7 +12033,17 @@ SYSCALL_DEFINE5(perf_event_open,
+ }
+ } else {
+ mutex_lock(&ctx->mutex);
++
++ /*
++ * Now that we hold ctx->lock, (re)validate group_leader->ctx == ctx,
++ * see the group_leader && !move_group test earlier.
++ */
++ if (group_leader && group_leader->ctx != ctx) {
++ err = -EINVAL;
++ goto err_locked;
++ }
+ }
++not_move_group:
+
+ if (ctx->task == TASK_TOMBSTONE) {
+ err = -ESRCH;
--- /dev/null
+From 6254bd3db316c9ccb3b05caa8b438be63245466f Mon Sep 17 00:00:00 2001
+From: Ondrej Mosnacek <omosnace@redhat.com>
+Date: Tue, 17 May 2022 14:08:16 +0200
+Subject: selinux: fix bad cleanup on error in hashtab_duplicate()
+
+From: Ondrej Mosnacek <omosnace@redhat.com>
+
+commit 6254bd3db316c9ccb3b05caa8b438be63245466f upstream.
+
+The code attempts to free the 'new' pointer using kmem_cache_free(),
+which is wrong because this function isn't responsible of freeing it.
+Instead, the function should free new->htable and clear the contents of
+*new (to prevent double-free).
+
+Cc: stable@vger.kernel.org
+Fixes: c7c556f1e81b ("selinux: refactor changing booleans")
+Reported-by: Wander Lairson Costa <wander@redhat.com>
+Signed-off-by: Ondrej Mosnacek <omosnace@redhat.com>
+Signed-off-by: Paul Moore <paul@paul-moore.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ security/selinux/ss/hashtab.c | 3 ++-
+ 1 file changed, 2 insertions(+), 1 deletion(-)
+
+--- a/security/selinux/ss/hashtab.c
++++ b/security/selinux/ss/hashtab.c
+@@ -178,7 +178,8 @@ int hashtab_duplicate(struct hashtab *ne
+ kmem_cache_free(hashtab_node_cachep, cur);
+ }
+ }
+- kmem_cache_free(hashtab_node_cachep, new);
++ kfree(new->htable);
++ memset(new, 0, sizeof(*new));
+ return -ENOMEM;
+ }
+
alsa-usb-audio-restore-rane-sl-1-quirk.patch
alsa-wavefront-proper-check-of-get_user-error.patch
alsa-hda-realtek-add-quirk-for-tongfang-devices-with-pop-noise.patch
+perf-fix-sys_perf_event_open-race-against-self.patch
+selinux-fix-bad-cleanup-on-error-in-hashtab_duplicate.patch
+fix-double-fget-in-vhost_net_set_backend.patch
+pci-pm-avoid-putting-elo-i2-pcie-ports-in-d3cold.patch
+kvm-x86-mmu-update-number-of-zapped-pages-even-if-page-list-is-stable.patch
+arm64-paravirt-use-rcu-read-locks-to-guard-stolen_time.patch
+arm64-mte-ensure-the-cleared-tags-are-visible-before-setting-the-pte.patch
+crypto-qcom-rng-fix-infinite-loop-on-requests-not-multiple-of-word_sz.patch
+libceph-fix-potential-use-after-free-on-linger-ping-and-resends.patch
+drm-dp-mst-fix-a-possible-memory-leak-in-fetch_monitor_name.patch
+dma-buf-fix-use-of-dma_buf_set_name_-a-b-in-userspace.patch
projects / thirdparty / kernel / stable-queue.git / commitdiff
