From: Stefano Garzarella sgarzare@redhat.com

[ Upstream commit 17dd1367389cfe7f150790c83247b68e0c19d106 ]

Before to call vdev->config->reset(vdev) we need to be sure that no one is accessing the device, for this reason, we add new variables in the struct virtio_vsock to stop the workers during the .remove().

This patch also add few comments before vdev->config->reset(vdev) and vdev->config->del_vqs(vdev).

Suggested-by: Stefan Hajnoczi stefanha@redhat.com Suggested-by: Michael S. Tsirkin mst@redhat.com Signed-off-by: Stefano Garzarella sgarzare@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/vmw_vsock/virtio_transport.c | 46 +++++++++++++++++++++++++++++++- 1 file changed, 45 insertions(+), 1 deletion(-)

diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 32ad7cfa5fa74..67aba63b5c96d 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -39,6 +39,7 @@ struct virtio_vsock { * must be accessed with tx_lock held. */ struct mutex tx_lock; + bool tx_run;

struct work_struct send_pkt_work; spinlock_t send_pkt_list_lock; @@ -50,6 +51,7 @@ struct virtio_vsock { * must be accessed with rx_lock held. */ struct mutex rx_lock; + bool rx_run; int rx_buf_nr; int rx_buf_max_nr;

@@ -57,6 +59,7 @@ struct virtio_vsock { * vqs[VSOCK_VQ_EVENT] must be accessed with event_lock held. */ struct mutex event_lock; + bool event_run; struct virtio_vsock_event event_list[8];

u32 guest_cid; @@ -91,6 +94,9 @@ virtio_transport_send_pkt_work(struct work_struct *work)

mutex_lock(&vsock->tx_lock);

+ if (!vsock->tx_run) + goto out; + vq = vsock->vqs[VSOCK_VQ_TX];

for (;;) { @@ -147,6 +153,7 @@ virtio_transport_send_pkt_work(struct work_struct *work) if (added) virtqueue_kick(vq);

+out: mutex_unlock(&vsock->tx_lock);

if (restart_rx) @@ -230,6 +237,10 @@ static void virtio_transport_tx_work(struct work_struct *work)

vq = vsock->vqs[VSOCK_VQ_TX]; mutex_lock(&vsock->tx_lock); + + if (!vsock->tx_run) + goto out; + do { struct virtio_vsock_pkt *pkt; unsigned int len; @@ -240,6 +251,8 @@ static void virtio_transport_tx_work(struct work_struct *work) added = true; } } while (!virtqueue_enable_cb(vq)); + +out: mutex_unlock(&vsock->tx_lock);

if (added) @@ -268,6 +281,9 @@ static void virtio_transport_rx_work(struct work_struct *work)

mutex_lock(&vsock->rx_lock);

+ if (!vsock->rx_run) + goto out; + do { virtqueue_disable_cb(vq); for (;;) { @@ -376,6 +392,9 @@ static void virtio_transport_event_work(struct work_struct *work)

mutex_lock(&vsock->event_lock);

+ if (!vsock->event_run) + goto out; + do { struct virtio_vsock_event *event; unsigned int len; @@ -390,7 +409,7 @@ static void virtio_transport_event_work(struct work_struct *work) } while (!virtqueue_enable_cb(vq));

virtqueue_kick(vsock->vqs[VSOCK_VQ_EVENT]); - +out: mutex_unlock(&vsock->event_lock); }

@@ -521,12 +540,18 @@ static int virtio_vsock_probe(struct virtio_device *vdev) INIT_WORK(&vsock->event_work, virtio_transport_event_work); INIT_WORK(&vsock->send_pkt_work, virtio_transport_send_pkt_work);

+ mutex_lock(&vsock->tx_lock); + vsock->tx_run = true; + mutex_unlock(&vsock->tx_lock); + mutex_lock(&vsock->rx_lock); virtio_vsock_rx_fill(vsock); + vsock->rx_run = true; mutex_unlock(&vsock->rx_lock);

mutex_lock(&vsock->event_lock); virtio_vsock_event_fill(vsock); + vsock->event_run = true; mutex_unlock(&vsock->event_lock);

vdev->priv = vsock; @@ -560,6 +585,24 @@ static void virtio_vsock_remove(struct virtio_device *vdev) /* Reset all connected sockets when the device disappear */ vsock_for_each_connected_socket(virtio_vsock_reset_sock);

+ /* Stop all work handlers to make sure no one is accessing the device, + * so we can safely call vdev->config->reset(). + */ + mutex_lock(&vsock->rx_lock); + vsock->rx_run = false; + mutex_unlock(&vsock->rx_lock); + + mutex_lock(&vsock->tx_lock); + vsock->tx_run = false; + mutex_unlock(&vsock->tx_lock); + + mutex_lock(&vsock->event_lock); + vsock->event_run = false; + mutex_unlock(&vsock->event_lock); + + /* Flush all device writes and interrupts, device will not use any + * more buffers. + */ vdev->config->reset(vdev);

mutex_lock(&vsock->rx_lock); @@ -581,6 +624,7 @@ static void virtio_vsock_remove(struct virtio_device *vdev) } spin_unlock_bh(&vsock->send_pkt_list_lock);

+ /* Delete virtqueues and flush outstanding callbacks if any */ vdev->config->del_vqs(vdev);

mutex_unlock(&the_virtio_vsock_mutex);

From: dillon min dillon.minfei@gmail.com

commit 214b0e1ad01abf4c1f6d8d28fa096bf167e47cef upstream.

The offset of regmap is incorrect, j * 8 is move to the wrong register.

for example:

asume i = 0, j = 1. we want to set KPY5 as interrupt falling edge mode, regmap[0][1] should be TC3589x_GPIOIBE1 0xcd but, regmap[i] + j * 8 = TC3589x_GPIOIBE0 + 8 ,point to 0xd4, this is TC3589x_GPIOIE2 not TC3589x_GPIOIBE1.

Fixes: d88b25be3584 ("gpio: Add TC35892 GPIO driver") Cc: Cc: stable@vger.kernel.org Signed-off-by: dillon min dillon.minfei@gmail.com Signed-off-by: Bartosz Golaszewski bgolaszewski@baylibre.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/gpio/gpio-tc3589x.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/gpio/gpio-tc3589x.c +++ b/drivers/gpio/gpio-tc3589x.c @@ -210,7 +210,7 @@ static void tc3589x_gpio_irq_sync_unlock continue;

tc3589x_gpio->oldregs[i][j] = new; - tc3589x_reg_write(tc3589x, regmap[i] + j * 8, new); + tc3589x_reg_write(tc3589x, regmap[i] + j, new); } }

From: Jean Delvare jdelvare@suse.de

commit a39d0d7bdf8c21ac7645c02e9676b5cb2b804c31 upstream.

A recent attempt to fix a ref count leak in amdgpu_display_crtc_set_config() turned out to be doing too much and "fixed" an intended decrease as if it were a leak. Undo that part to restore the proper balance. This is the very nature of this function to increase or decrease the power reference count depending on the situation.

Consequences of this bug is that the power reference would eventually get down to 0 while the display was still in use, resulting in that display switching off unexpectedly.

Signed-off-by: Jean Delvare jdelvare@suse.de Fixes: e008fa6fb415 ("drm/amdgpu: fix ref count leak in amdgpu_display_crtc_set_config") Cc: stable@vger.kernel.org Cc: Navid Emamdoost navid.emamdoost@gmail.com Cc: Alex Deucher alexander.deucher@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/gpu/drm/amd/amdgpu/amdgpu_display.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -283,7 +283,7 @@ int amdgpu_crtc_set_config(struct drm_mo take the current one */ if (active && !adev->have_disp_power_ref) { adev->have_disp_power_ref = true; - goto out; + return ret; } /* if we have no active crtcs, then drop the power ref we got before */

From: Olympia Giannou ogiannou@gmail.com

[ Upstream commit 4202c9fdf03d79dedaa94b2c4cf574f25793d669 ]

Some WinCE devices face connectivity issues via the NDIS interface. They fail to register, resulting in -110 timeout errors and failures during the probe procedure.

In this kind of WinCE devices, the Windows-side ndis driver needs quite more time to be loaded and configured, so that the linux rndis host queries to them fail to be responded correctly on time.

More specifically, when INIT is called on the WinCE side - no other requests can be served by the Client and this results in a failed QUERY afterwards.

The increase of the waiting time on the side of the linux rndis host in the command-response loop leaves the INIT process to complete and respond to a QUERY, which comes afterwards. The WinCE devices with this special "feature" in their ndis driver are satisfied by this fix.

Signed-off-by: Olympia Giannou olympia.giannou@leica-geosystems.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/usb/rndis_host.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/usb/rndis_host.c b/drivers/net/usb/rndis_host.c index 4f4f71b2966ba..9ccbdf1431063 100644 --- a/drivers/net/usb/rndis_host.c +++ b/drivers/net/usb/rndis_host.c @@ -213,7 +213,7 @@ int rndis_command(struct usbnet *dev, struct rndis_msg_hdr *buf, int buflen) dev_dbg(&info->control->dev, "rndis response error, code %d\n", retval); } - msleep(20); + msleep(40); } dev_dbg(&info->control->dev, "rndis response timeout\n"); return -ETIMEDOUT;

From: Xie He xie.he.0141@gmail.com

[ Upstream commit 9fb030a70431a2a2a1b292dbf0b2f399cc072c16 ]

This patch sets skb->protocol before transmitting frames on the HDLC device, so that a user listening on the HDLC device with an AF_PACKET socket will see outgoing frames' sll_protocol field correctly set and consistent with that of incoming frames.

1. Control frames in hdlc_cisco and hdlc_ppp

When these drivers send control frames, skb->protocol is not set.

This value should be set to htons(ETH_P_HDLC), because when receiving control frames, their skb->protocol is set to htons(ETH_P_HDLC).

When receiving, hdlc_type_trans in hdlc.h is called, which then calls cisco_type_trans or ppp_type_trans. The skb->protocol of control frames is set to htons(ETH_P_HDLC) so that the control frames can be received by hdlc_rcv in hdlc.c, which calls cisco_rx or ppp_rx to process the control frames.

2. hdlc_fr

When this driver sends control frames, skb->protocol is set to internal values used in this driver.

When this driver sends data frames (from upper stacked PVC devices), skb->protocol is the same as that of the user data packet being sent on the upper PVC device (for normal PVC devices), or is htons(ETH_P_802_3) (for Ethernet-emulating PVC devices).

However, skb->protocol for both control frames and data frames should be set to htons(ETH_P_HDLC), because when receiving, all frames received on the HDLC device will have their skb->protocol set to htons(ETH_P_HDLC).

When receiving, hdlc_type_trans in hdlc.h is called, and because this driver doesn't provide a type_trans function in struct hdlc_proto, all frames will have their skb->protocol set to htons(ETH_P_HDLC). The frames are then received by hdlc_rcv in hdlc.c, which calls fr_rx to process the frames (control frames are consumed and data frames are re-received on upper PVC devices).

Cc: Krzysztof Halasa khc@pm.waw.pl Signed-off-by: Xie He xie.he.0141@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wan/hdlc_cisco.c | 1 + drivers/net/wan/hdlc_fr.c | 3 +++ drivers/net/wan/hdlc_ppp.c | 1 + 3 files changed, 5 insertions(+)

diff --git a/drivers/net/wan/hdlc_cisco.c b/drivers/net/wan/hdlc_cisco.c index 7f99fb666f196..1587789ba9343 100644 --- a/drivers/net/wan/hdlc_cisco.c +++ b/drivers/net/wan/hdlc_cisco.c @@ -120,6 +120,7 @@ static void cisco_keepalive_send(struct net_device *dev, u32 type, skb_put(skb, sizeof(struct cisco_packet)); skb->priority = TC_PRIO_CONTROL; skb->dev = dev; + skb->protocol = htons(ETH_P_HDLC); skb_reset_network_header(skb);

dev_queue_xmit(skb); diff --git a/drivers/net/wan/hdlc_fr.c b/drivers/net/wan/hdlc_fr.c index b6e0cfb095d35..bba19d068207a 100644 --- a/drivers/net/wan/hdlc_fr.c +++ b/drivers/net/wan/hdlc_fr.c @@ -435,6 +435,8 @@ static netdev_tx_t pvc_xmit(struct sk_buff *skb, struct net_device *dev) if (pvc->state.fecn) /* TX Congestion counter */ dev->stats.tx_compressed++; skb->dev = pvc->frad; + skb->protocol = htons(ETH_P_HDLC); + skb_reset_network_header(skb); dev_queue_xmit(skb); return NETDEV_TX_OK; } @@ -557,6 +559,7 @@ static void fr_lmi_send(struct net_device *dev, int fullrep) skb_put(skb, i); skb->priority = TC_PRIO_CONTROL; skb->dev = dev; + skb->protocol = htons(ETH_P_HDLC); skb_reset_network_header(skb);

dev_queue_xmit(skb); diff --git a/drivers/net/wan/hdlc_ppp.c b/drivers/net/wan/hdlc_ppp.c index 63546d1317982..35589ee0cde11 100644 --- a/drivers/net/wan/hdlc_ppp.c +++ b/drivers/net/wan/hdlc_ppp.c @@ -254,6 +254,7 @@ static void ppp_tx_cp(struct net_device *dev, u16 pid, u8 code,

skb->priority = TC_PRIO_CONTROL; skb->dev = dev; + skb->protocol = htons(ETH_P_HDLC); skb_reset_network_header(skb); skb_queue_tail(&tx_queue, skb); }

From: Jeffrey Mitchell jeffrey.mitchell@starlab.io

[ Upstream commit d33030e2ee3508d65db5644551435310df86010e ]

nfs_readdir_page_filler() iterates over entries in a directory, reusing the same security label buffer, but does not reset the buffer's length. This causes decode_attr_security_label() to return -ERANGE if an entry's security label is longer than the previous one's. This error, in nfs4_decode_dirent(), only gets passed up as -EAGAIN, which causes another failed attempt to copy into the buffer. The second error is ignored and the remaining entries do not show up in ls, specifically the getdents64() syscall.

Reproduce by creating multiple files in NFS and giving one of the later files a longer security label. ls will not see that file nor any that are added afterwards, though they will exist on the backend.

In nfs_readdir_page_filler(), reset security label buffer length before every reuse

Signed-off-by: Jeffrey Mitchell jeffrey.mitchell@starlab.io Fixes: b4487b935452 ("nfs: Fix getxattr kernel panic and memory overflow") Signed-off-by: Trond Myklebust trond.myklebust@hammerspace.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/nfs/dir.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 2517fcd423b68..d405b5a14073a 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -583,6 +583,9 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);

do { + if (entry->label) + entry->label->len = NFS4_MAXLABELLEN; + status = xdr_decode(desc, entry, &stream); if (status != 0) { if (status == -EAGAIN)

From: Yu Kuai yukuai3@huawei.com

[ Upstream commit 1a26044954a6d1f4d375d5e62392446af663be7a ]

if of_find_device_by_node() succeed, exynos_iommu_of_xlate() doesn't have a corresponding put_device(). Thus add put_device() to fix the exception handling for this function implementation.

Fixes: aa759fd376fb ("iommu/exynos: Add callback for initializing devices from device tree") Signed-off-by: Yu Kuai yukuai3@huawei.com Acked-by: Marek Szyprowski m.szyprowski@samsung.com Link: https://lore.kernel.org/r/20200918011335.909141-1-yukuai3@huawei.com Signed-off-by: Joerg Roedel jroedel@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/iommu/exynos-iommu.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c index beef59eb94fa7..626b434e7967a 100644 --- a/drivers/iommu/exynos-iommu.c +++ b/drivers/iommu/exynos-iommu.c @@ -1265,13 +1265,17 @@ static int exynos_iommu_of_xlate(struct device *dev, return -ENODEV;

data = platform_get_drvdata(sysmmu); - if (!data) + if (!data) { + put_device(&sysmmu->dev); return -ENODEV; + }

if (!owner) { owner = kzalloc(sizeof(*owner), GFP_KERNEL); - if (!owner) + if (!owner) { + put_device(&sysmmu->dev); return -ENOMEM; + }

INIT_LIST_HEAD(&owner->controllers); dev->archdata.iommu = owner;

From: Thibaut Sautereau thibaut.sautereau@ssi.gouv.fr

[ Upstream commit 09a6b0bc3be793ca8cba580b7992d73e9f68f15d ]

Commit f227e3ec3b5c ("random32: update the net random state on interrupt and activity") broke compilation and was temporarily fixed by Linus in 83bdc7275e62 ("random32: remove net_rand_state from the latent entropy gcc plugin") by entirely moving net_rand_state out of the things handled by the latent_entropy GCC plugin.

From what I understand when reading the plugin code, using the

__latent_entropy attribute on a declaration was the wrong part and simply keeping the __latent_entropy attribute on the variable definition was the correct fix.

Fixes: 83bdc7275e62 ("random32: remove net_rand_state from the latent entropy gcc plugin") Acked-by: Willy Tarreau w@1wt.eu Cc: Emese Revfy re.emese@gmail.com Signed-off-by: Thibaut Sautereau thibaut.sautereau@ssi.gouv.fr Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- lib/random32.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/random32.c b/lib/random32.c index 889dab44bd747..d5c3137d93f49 100644 --- a/lib/random32.c +++ b/lib/random32.c @@ -47,7 +47,7 @@ static inline void prandom_state_selftest(void) } #endif

-DEFINE_PER_CPU(struct rnd_state, net_rand_state); +DEFINE_PER_CPU(struct rnd_state, net_rand_state) __latent_entropy;

/** * prandom_u32_state - seeded pseudo-random number generator.

From: Al Viro viro@zeniv.linux.org.uk

commit f8d4f44df056c5b504b0d49683fb7279218fd207 upstream.

Signed-off-by: Al Viro viro@zeniv.linux.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/eventpoll.c | 37 ++++++++++++++++++------------------- 1 file changed, 18 insertions(+), 19 deletions(-)

--- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1332,6 +1332,22 @@ static int ep_insert(struct eventpoll *e RCU_INIT_POINTER(epi->ws, NULL); }

+ /* Add the current item to the list of active epoll hook for this file */ + spin_lock(&tfile->f_lock); + list_add_tail_rcu(&epi->fllink, &tfile->f_ep_links); + spin_unlock(&tfile->f_lock); + + /* + * Add the current item to the RB tree. All RB tree operations are + * protected by "mtx", and ep_insert() is called with "mtx" held. + */ + ep_rbtree_insert(ep, epi); + + /* now check if we've created too many backpaths */ + error = -EINVAL; + if (full_check && reverse_path_check()) + goto error_remove_epi; + /* Initialize the poll table using the queue callback */ epq.epi = epi; init_poll_funcptr(&epq.pt, ep_ptable_queue_proc); @@ -1354,22 +1370,6 @@ static int ep_insert(struct eventpoll *e if (epi->nwait < 0) goto error_unregister;

- /* Add the current item to the list of active epoll hook for this file */ - spin_lock(&tfile->f_lock); - list_add_tail_rcu(&epi->fllink, &tfile->f_ep_links); - spin_unlock(&tfile->f_lock); - - /* - * Add the current item to the RB tree. All RB tree operations are - * protected by "mtx", and ep_insert() is called with "mtx" held. - */ - ep_rbtree_insert(ep, epi); - - /* now check if we've created too many backpaths */ - error = -EINVAL; - if (full_check && reverse_path_check()) - goto error_remove_epi; - /* We have to drop the new item inside our item list to keep track of it */ spin_lock_irqsave(&ep->lock, flags);

@@ -1395,6 +1395,8 @@ static int ep_insert(struct eventpoll *e

return 0;

+error_unregister: + ep_unregister_pollwait(ep, epi); error_remove_epi: spin_lock(&tfile->f_lock); list_del_rcu(&epi->fllink); @@ -1402,9 +1404,6 @@ error_remove_epi:

rb_erase(&epi->rbn, &ep->rbr);

-error_unregister: - ep_unregister_pollwait(ep, epi); - /* * We need to do this because an event could have been arrived on some * allocated wait queue. Note that we don't care about the ep->ovflist

From: Al Viro viro@zeniv.linux.org.uk

commit fe0a916c1eae8e17e86c3753d13919177d63ed7e upstream.

Checking for the lack of epitems refering to the epoll we want to insert into is not enough; we might have an insertion of that epoll into another one that has already collected the set of files to recheck for excessive reverse paths, but hasn't gotten to creating/inserting the epitem for it.

However, any such insertion in progress can be detected - it will update the generation count in our epoll when it's done looking through it for files to check. That gets done under ->mtx of our epoll and that allows us to detect that safely.

We are *not* holding epmutex here, so the generation count is not stable. However, since both the update of ep->gen by loop check and (later) insertion into ->f_ep_link are done with ep->mtx held, we are fine - the sequence is grab epmutex bump loop_check_gen ... grab tep->mtx // 1 tep->gen = loop_check_gen ... drop tep->mtx // 2 ... grab tep->mtx // 3 ... insert into ->f_ep_link ... drop tep->mtx // 4 bump loop_check_gen drop epmutex and if the fastpath check in another thread happens for that eventpoll, it can come * before (1) - in that case fastpath is just fine * after (4) - we'll see non-empty ->f_ep_link, slow path taken * between (2) and (3) - loop_check_gen is stable, with ->mtx providing barriers and we end up taking slow path.

Note that ->f_ep_link emptiness check is slightly racy - we are protected against insertions into that list, but removals can happen right under us. Not a problem - in the worst case we'll end up taking a slow path for no good reason.

Signed-off-by: Al Viro viro@zeniv.linux.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/eventpoll.c | 1 + 1 file changed, 1 insertion(+)

--- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1926,6 +1926,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, in mutex_lock_nested(&ep->mtx, 0); if (op == EPOLL_CTL_ADD) { if (!list_empty(&f.file->f_ep_links) || + ep->gen == loop_check_gen || is_file_epoll(tf.file)) { full_check = 1; mutex_unlock(&ep->mtx);

From: Will McVicker willmcvicker@google.com

commit 1cc5ef91d2ff94d2bf2de3b3585423e8a1051cb6 upstream.

The indexes to the nf_nat_l[34]protos arrays come from userspace. So check the tuple's family, e.g. l3num, when creating the conntrack in order to prevent an OOB memory access during setup. Here is an example kernel panic on 4.14.180 when userspace passes in an index greater than NFPROTO_NUMPROTO.

Internal error: Oops - BUG: 0 [#1] PREEMPT SMP Modules linked in:... Process poc (pid: 5614, stack limit = 0x00000000a3933121) CPU: 4 PID: 5614 Comm: poc Tainted: G S W O 4.14.180-g051355490483 Hardware name: Qualcomm Technologies, Inc. SM8150 V2 PM8150 Google Inc. MSM task: 000000002a3dfffe task.stack: 00000000a3933121 pc : __cfi_check_fail+0x1c/0x24 lr : __cfi_check_fail+0x1c/0x24 ... Call trace: __cfi_check_fail+0x1c/0x24 name_to_dev_t+0x0/0x468 nfnetlink_parse_nat_setup+0x234/0x258 ctnetlink_parse_nat_setup+0x4c/0x228 ctnetlink_new_conntrack+0x590/0xc40 nfnetlink_rcv_msg+0x31c/0x4d4 netlink_rcv_skb+0x100/0x184 nfnetlink_rcv+0xf4/0x180 netlink_unicast+0x360/0x770 netlink_sendmsg+0x5a0/0x6a4 ___sys_sendmsg+0x314/0x46c SyS_sendmsg+0xb4/0x108 el0_svc_naked+0x34/0x38

This crash is not happening since 5.4+, however, ctnetlink still allows for creating entries with unsupported layer 3 protocol number.

Fixes: c1d10adb4a521 ("[NETFILTER]: Add ctnetlink port for nf_conntrack") Signed-off-by: Will McVicker willmcvicker@google.com [pablo@netfilter.org: rebased original patch on top of nf.git] Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- net/netfilter/nf_conntrack_netlink.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1031,6 +1031,8 @@ ctnetlink_parse_tuple(const struct nlatt if (!tb[CTA_TUPLE_IP]) return -EINVAL;

+ if (l3num != NFPROTO_IPV4 && l3num != NFPROTO_IPV6) + return -EOPNOTSUPP; tuple->src.l3num = l3num;

err = ctnetlink_parse_tuple_ip(tb[CTA_TUPLE_IP], tuple);

From: Peilin Ye yepeilin.cs@gmail.com

commit 6735b4632def0640dbdf4eb9f99816aca18c4f16 upstream.

syzbot has reported an issue in the framebuffer layer, where a malicious user may overflow our built-in font data buffers.

In order to perform a reliable range check, subsystems need to know `FONTDATAMAX` for each built-in font. Unfortunately, our font descriptor, `struct console_font` does not contain `FONTDATAMAX`, and is part of the UAPI, making it infeasible to modify it.

For user-provided fonts, the framebuffer layer resolves this issue by reserving four extra words at the beginning of data buffers. Later, whenever a function needs to access them, it simply uses the following macros:

Recently we have gathered all the above macros to <linux/font.h>. Let us do the same thing for built-in fonts, prepend four extra words (including `FONTDATAMAX`) to their data buffers, so that subsystems can use these macros for all fonts, no matter built-in or user-provided.

This patch depends on patch "fbdev, newport_con: Move FONT_EXTRA_WORDS macros into linux/font.h".

Cc: stable@vger.kernel.org Link: https://syzkaller.appspot.com/bug?id=08b8be45afea11888776f897895aef9ad1c3ecf... Signed-off-by: Peilin Ye yepeilin.cs@gmail.com Reviewed-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Daniel Vetter daniel.vetter@ffwll.ch Link: https://patchwork.freedesktop.org/patch/msgid/ef18af00c35fb3cc826048a5f70924... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- include/linux/font.h | 5 +++++ lib/fonts/font_10x18.c | 9 ++++----- lib/fonts/font_6x10.c | 9 +++++---- lib/fonts/font_6x11.c | 9 ++++----- lib/fonts/font_7x14.c | 9 ++++----- lib/fonts/font_8x16.c | 9 ++++----- lib/fonts/font_8x8.c | 9 ++++----- lib/fonts/font_acorn_8x8.c | 9 ++++++--- lib/fonts/font_mini_4x6.c | 8 ++++---- lib/fonts/font_pearl_8x8.c | 9 ++++----- lib/fonts/font_sun12x22.c | 9 ++++----- lib/fonts/font_sun8x16.c | 7 ++++--- 12 files changed, 52 insertions(+), 49 deletions(-)

--- a/include/linux/font.h +++ b/include/linux/font.h @@ -65,4 +65,9 @@ extern const struct font_desc *get_defau

#define FONT_EXTRA_WORDS 4

+struct font_data { + unsigned int extra[FONT_EXTRA_WORDS]; + const unsigned char data[]; +} __packed; + #endif /* _VIDEO_FONT_H */ --- a/lib/fonts/font_10x18.c +++ b/lib/fonts/font_10x18.c @@ -7,8 +7,8 @@

#define FONTDATAMAX 9216

-static const unsigned char fontdata_10x18[FONTDATAMAX] = { - +static struct font_data fontdata_10x18 = { + { 0, 0, FONTDATAMAX, 0 }, { /* 0 0x00 '^@' */ 0x00, 0x00, /* 0000000000 */ 0x00, 0x00, /* 0000000000 */ @@ -5128,8 +5128,7 @@ static const unsigned char fontdata_10x1 0x00, 0x00, /* 0000000000 */ 0x00, 0x00, /* 0000000000 */ 0x00, 0x00, /* 0000000000 */ - -}; +} };

const struct font_desc font_10x18 = { @@ -5137,7 +5136,7 @@ const struct font_desc font_10x18 = { .name = "10x18", .width = 10, .height = 18, - .data = fontdata_10x18, + .data = fontdata_10x18.data, #ifdef __sparc__ .pref = 5, #else --- a/lib/fonts/font_6x10.c +++ b/lib/fonts/font_6x10.c @@ -1,7 +1,9 @@ #include <linux/font.h>

-static const unsigned char fontdata_6x10[] = { +#define FONTDATAMAX 2560

+static struct font_data fontdata_6x10 = { + { 0, 0, FONTDATAMAX, 0 }, { /* 0 0x00 '^@' */ 0x00, /* 00000000 */ 0x00, /* 00000000 */ @@ -3073,14 +3075,13 @@ static const unsigned char fontdata_6x10 0x00, /* 00000000 */ 0x00, /* 00000000 */ 0x00, /* 00000000 */ - -}; +} };

const struct font_desc font_6x10 = { .idx = FONT6x10_IDX, .name = "6x10", .width = 6, .height = 10, - .data = fontdata_6x10, + .data = fontdata_6x10.data, .pref = 0, }; --- a/lib/fonts/font_6x11.c +++ b/lib/fonts/font_6x11.c @@ -8,8 +8,8 @@

#define FONTDATAMAX (11*256)

-static const unsigned char fontdata_6x11[FONTDATAMAX] = { - +static struct font_data fontdata_6x11 = { + { 0, 0, FONTDATAMAX, 0 }, { /* 0 0x00 '^@' */ 0x00, /* 00000000 */ 0x00, /* 00000000 */ @@ -3337,8 +3337,7 @@ static const unsigned char fontdata_6x11 0x00, /* 00000000 */ 0x00, /* 00000000 */ 0x00, /* 00000000 */ - -}; +} };

const struct font_desc font_vga_6x11 = { @@ -3346,7 +3345,7 @@ const struct font_desc font_vga_6x11 = { .name = "ProFont6x11", .width = 6, .height = 11, - .data = fontdata_6x11, + .data = fontdata_6x11.data, /* Try avoiding this font if possible unless on MAC */ .pref = -2000, }; --- a/lib/fonts/font_7x14.c +++ b/lib/fonts/font_7x14.c @@ -7,8 +7,8 @@

#define FONTDATAMAX 3584

-static const unsigned char fontdata_7x14[FONTDATAMAX] = { - +static struct font_data fontdata_7x14 = { + { 0, 0, FONTDATAMAX, 0 }, { /* 0 0x00 '^@' */ 0x00, /* 0000000 */ 0x00, /* 0000000 */ @@ -4104,8 +4104,7 @@ static const unsigned char fontdata_7x14 0x00, /* 0000000 */ 0x00, /* 0000000 */ 0x00, /* 0000000 */ - -}; +} };

const struct font_desc font_7x14 = { @@ -4113,6 +4112,6 @@ const struct font_desc font_7x14 = { .name = "7x14", .width = 7, .height = 14, - .data = fontdata_7x14, + .data = fontdata_7x14.data, .pref = 0, }; --- a/lib/fonts/font_8x16.c +++ b/lib/fonts/font_8x16.c @@ -9,8 +9,8 @@

#define FONTDATAMAX 4096

-static const unsigned char fontdata_8x16[FONTDATAMAX] = { - +static struct font_data fontdata_8x16 = { + { 0, 0, FONTDATAMAX, 0 }, { /* 0 0x00 '^@' */ 0x00, /* 00000000 */ 0x00, /* 00000000 */ @@ -4618,8 +4618,7 @@ static const unsigned char fontdata_8x16 0x00, /* 00000000 */ 0x00, /* 00000000 */ 0x00, /* 00000000 */ - -}; +} };

const struct font_desc font_vga_8x16 = { @@ -4627,7 +4626,7 @@ const struct font_desc font_vga_8x16 = { .name = "VGA8x16", .width = 8, .height = 16, - .data = fontdata_8x16, + .data = fontdata_8x16.data, .pref = 0, }; EXPORT_SYMBOL(font_vga_8x16); --- a/lib/fonts/font_8x8.c +++ b/lib/fonts/font_8x8.c @@ -8,8 +8,8 @@

#define FONTDATAMAX 2048

-static const unsigned char fontdata_8x8[FONTDATAMAX] = { - +static struct font_data fontdata_8x8 = { + { 0, 0, FONTDATAMAX, 0 }, { /* 0 0x00 '^@' */ 0x00, /* 00000000 */ 0x00, /* 00000000 */ @@ -2569,8 +2569,7 @@ static const unsigned char fontdata_8x8[ 0x00, /* 00000000 */ 0x00, /* 00000000 */ 0x00, /* 00000000 */ - -}; +} };

const struct font_desc font_vga_8x8 = { @@ -2578,6 +2577,6 @@ const struct font_desc font_vga_8x8 = { .name = "VGA8x8", .width = 8, .height = 8, - .data = fontdata_8x8, + .data = fontdata_8x8.data, .pref = 0, }; --- a/lib/fonts/font_acorn_8x8.c +++ b/lib/fonts/font_acorn_8x8.c @@ -2,7 +2,10 @@

#include <linux/font.h>

-static const unsigned char acorndata_8x8[] = { +#define FONTDATAMAX 2048 + +static struct font_data acorndata_8x8 = { +{ 0, 0, FONTDATAMAX, 0 }, { /* 00 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* ^@ */ /* 01 */ 0x7e, 0x81, 0xa5, 0x81, 0xbd, 0x99, 0x81, 0x7e, /* ^A */ /* 02 */ 0x7e, 0xff, 0xbd, 0xff, 0xc3, 0xe7, 0xff, 0x7e, /* ^B */ @@ -259,14 +262,14 @@ static const unsigned char acorndata_8x8 /* FD */ 0x38, 0x04, 0x18, 0x20, 0x3c, 0x00, 0x00, 0x00, /* FE */ 0x00, 0x00, 0x3c, 0x3c, 0x3c, 0x3c, 0x00, 0x00, /* FF */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 -}; +} };

const struct font_desc font_acorn_8x8 = { .idx = ACORN8x8_IDX, .name = "Acorn8x8", .width = 8, .height = 8, - .data = acorndata_8x8, + .data = acorndata_8x8.data, #ifdef CONFIG_ARCH_ACORN .pref = 20, #else --- a/lib/fonts/font_mini_4x6.c +++ b/lib/fonts/font_mini_4x6.c @@ -43,8 +43,8 @@ __END__;

#define FONTDATAMAX 1536

-static const unsigned char fontdata_mini_4x6[FONTDATAMAX] = { - +static struct font_data fontdata_mini_4x6 = { + { 0, 0, FONTDATAMAX, 0 }, { /*{*/ /* Char 0: ' ' */ 0xee, /*= [*** ] */ @@ -2145,14 +2145,14 @@ static const unsigned char fontdata_mini 0xee, /*= [*** ] */ 0x00, /*= [ ] */ /*}*/ -}; +} };

const struct font_desc font_mini_4x6 = { .idx = MINI4x6_IDX, .name = "MINI4x6", .width = 4, .height = 6, - .data = fontdata_mini_4x6, + .data = fontdata_mini_4x6.data, .pref = 3, };

--- a/lib/fonts/font_pearl_8x8.c +++ b/lib/fonts/font_pearl_8x8.c @@ -13,8 +13,8 @@

#define FONTDATAMAX 2048

-static const unsigned char fontdata_pearl8x8[FONTDATAMAX] = { - +static struct font_data fontdata_pearl8x8 = { + { 0, 0, FONTDATAMAX, 0 }, { /* 0 0x00 '^@' */ 0x00, /* 00000000 */ 0x00, /* 00000000 */ @@ -2574,14 +2574,13 @@ static const unsigned char fontdata_pear 0x00, /* 00000000 */ 0x00, /* 00000000 */ 0x00, /* 00000000 */ - -}; +} };

const struct font_desc font_pearl_8x8 = { .idx = PEARL8x8_IDX, .name = "PEARL8x8", .width = 8, .height = 8, - .data = fontdata_pearl8x8, + .data = fontdata_pearl8x8.data, .pref = 2, }; --- a/lib/fonts/font_sun12x22.c +++ b/lib/fonts/font_sun12x22.c @@ -2,8 +2,8 @@

#define FONTDATAMAX 11264

-static const unsigned char fontdata_sun12x22[FONTDATAMAX] = { - +static struct font_data fontdata_sun12x22 = { + { 0, 0, FONTDATAMAX, 0 }, { /* 0 0x00 '^@' */ 0x00, 0x00, /* 000000000000 */ 0x00, 0x00, /* 000000000000 */ @@ -6147,8 +6147,7 @@ static const unsigned char fontdata_sun1 0x00, 0x00, /* 000000000000 */ 0x00, 0x00, /* 000000000000 */ 0x00, 0x00, /* 000000000000 */ - -}; +} };

const struct font_desc font_sun_12x22 = { @@ -6156,7 +6155,7 @@ const struct font_desc font_sun_12x22 = .name = "SUN12x22", .width = 12, .height = 22, - .data = fontdata_sun12x22, + .data = fontdata_sun12x22.data, #ifdef __sparc__ .pref = 5, #else --- a/lib/fonts/font_sun8x16.c +++ b/lib/fonts/font_sun8x16.c @@ -2,7 +2,8 @@

#define FONTDATAMAX 4096

-static const unsigned char fontdata_sun8x16[FONTDATAMAX] = { +static struct font_data fontdata_sun8x16 = { +{ 0, 0, FONTDATAMAX, 0 }, { /* */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* */ 0x00,0x00,0x7e,0x81,0xa5,0x81,0x81,0xbd,0x99,0x81,0x81,0x7e,0x00,0x00,0x00,0x00, /* */ 0x00,0x00,0x7e,0xff,0xdb,0xff,0xff,0xc3,0xe7,0xff,0xff,0x7e,0x00,0x00,0x00,0x00, @@ -259,14 +260,14 @@ static const unsigned char fontdata_sun8 /* */ 0x00,0x70,0xd8,0x30,0x60,0xc8,0xf8,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* */ 0x00,0x00,0x00,0x00,0x7c,0x7c,0x7c,0x7c,0x7c,0x7c,0x7c,0x00,0x00,0x00,0x00,0x00, /* */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, -}; +} };

const struct font_desc font_sun_8x16 = { .idx = SUN8x16_IDX, .name = "SUN8x16", .width = 8, .height = 16, - .data = fontdata_sun8x16, + .data = fontdata_sun8x16.data, #ifdef __sparc__ .pref = 10, #else

From: Peilin Ye yepeilin.cs@gmail.com

commit 5af08640795b2b9a940c9266c0260455377ae262 upstream.

fbcon_get_font() is reading out-of-bounds. A malicious user may resize `vc->vc_font.height` to a large value, causing fbcon_get_font() to read out of `fontdata`.

fbcon_get_font() handles both built-in and user-provided fonts. Fortunately, recently we have added FONT_EXTRA_WORDS support for built-in fonts, so fix it by adding range checks using FNTSIZE().

This patch depends on patch "fbdev, newport_con: Move FONT_EXTRA_WORDS macros into linux/font.h", and patch "Fonts: Support FONT_EXTRA_WORDS macros for built-in fonts".

Cc: stable@vger.kernel.org Reported-and-tested-by: syzbot+29d4ed7f3bdedf2aa2fd@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=08b8be45afea11888776f897895aef9ad1c3ecf... Signed-off-by: Peilin Ye yepeilin.cs@gmail.com Reviewed-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Daniel Vetter daniel.vetter@ffwll.ch Link: https://patchwork.freedesktop.org/patch/msgid/b34544687a1a09d6de630659eb7a77... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/video/console/fbcon.c | 12 ++++++++++++ 1 file changed, 12 insertions(+)

--- a/drivers/video/console/fbcon.c +++ b/drivers/video/console/fbcon.c @@ -2234,6 +2234,9 @@ static int fbcon_get_font(struct vc_data

if (font->width <= 8) { j = vc->vc_font.height; + if (font->charcount * j > FNTSIZE(fontdata)) + return -EINVAL; + for (i = 0; i < font->charcount; i++) { memcpy(data, fontdata, j); memset(data + j, 0, 32 - j); @@ -2242,6 +2245,9 @@ static int fbcon_get_font(struct vc_data } } else if (font->width <= 16) { j = vc->vc_font.height * 2; + if (font->charcount * j > FNTSIZE(fontdata)) + return -EINVAL; + for (i = 0; i < font->charcount; i++) { memcpy(data, fontdata, j); memset(data + j, 0, 64 - j); @@ -2249,6 +2255,9 @@ static int fbcon_get_font(struct vc_data fontdata += j; } } else if (font->width <= 24) { + if (font->charcount * (vc->vc_font.height * sizeof(u32)) > FNTSIZE(fontdata)) + return -EINVAL; + for (i = 0; i < font->charcount; i++) { for (j = 0; j < vc->vc_font.height; j++) { *data++ = fontdata[0]; @@ -2261,6 +2270,9 @@ static int fbcon_get_font(struct vc_data } } else { j = vc->vc_font.height * 4; + if (font->charcount * j > FNTSIZE(fontdata)) + return -EINVAL; + for (i = 0; i < font->charcount; i++) { memcpy(data, fontdata, j); memset(data + j, 0, 128 - j);

From: Linus Torvalds torvalds@linux-foundation.org

commit 4013c1496c49615d90d36b9d513eee8e369778e9 upstream.

Kernel threads intentionally do CLONE_FS in order to follow any changes that 'init' does to set up the root directory (or cwd).

It is admittedly a bit odd, but it avoids the situation where 'init' does some extensive setup to initialize the system environment, and then we execute a usermode helper program, and it uses the original FS setup from boot time that may be very limited and incomplete.

[ Both Al Viro and Eric Biederman point out that 'pivot_root()' will follow the root regardless, since it fixes up other users of root (see chroot_fs_refs() for details), but overmounting root and doing a chroot() would not. ]

However, Vegard Nossum noticed that the CLONE_FS not only means that we follow the root and current working directories, it also means we share umask with whatever init changed it to. That wasn't intentional.

Just reset umask to the original default (0022) before actually starting the usermode helper program.

Reported-by: Vegard Nossum vegard.nossum@oracle.com Cc: Al Viro viro@zeniv.linux.org.uk Acked-by: Eric W. Biederman ebiederm@xmission.com Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- kernel/kmod.c | 9 +++++++++ 1 file changed, 9 insertions(+)

--- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -28,6 +28,7 @@ #include <linux/cred.h> #include <linux/file.h> #include <linux/fdtable.h> +#include <linux/fs_struct.h> #include <linux/workqueue.h> #include <linux/security.h> #include <linux/mount.h> @@ -223,6 +224,14 @@ static int call_usermodehelper_exec_asyn spin_unlock_irq(&current->sighand->siglock);

/* + * Initial kernel threads share ther FS with init, in order to + * get the init root directory. But we've now created a new + * thread that is going to execve a user process and has its own + * 'struct fs_struct'. Reset umask to the default. + */ + current->fs->umask = 0022; + + /* * Our parent (unbound workqueue) runs with elevated scheduling * priority. Avoid propagating that into the userspace child. */

From: Aaron Ma aaron.ma@canonical.com

commit 720ef73d1a239e33c3ad8fac356b9b1348e68aaf upstream.

Evaluating ACPI _BCL could fail, then ACPI buffer size will be set to 0. When reuse this ACPI buffer, AE_BUFFER_OVERFLOW will be triggered.

Re-initialize buffer size will make ACPI evaluate successfully.

Fixes: 46445b6b896fd ("thinkpad-acpi: fix handle locate for video and query of _BCL") Signed-off-by: Aaron Ma aaron.ma@canonical.com Signed-off-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/platform/x86/thinkpad_acpi.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

--- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -6640,8 +6640,10 @@ static int __init tpacpi_query_bcl_level list_for_each_entry(child, &device->children, node) { acpi_status status = acpi_evaluate_object(child->handle, "_BCL", NULL, &buffer); - if (ACPI_FAILURE(status)) + if (ACPI_FAILURE(status)) { + buffer.length = ACPI_ALLOCATE_BUFFER; continue; + }

obj = (union acpi_object *)buffer.pointer; if (!obj || (obj->type != ACPI_TYPE_PACKAGE)) {

From: Tommi Rantala tommi.t.rantala@nokia.com

commit 29b4f5f188571c112713c35cc87eefb46efee612 upstream.

Since glibc 2.28 when running 'perf top --stdio', input handling no longer works, but hitting any key always just prints the "Mapped keys" help text.

To fix it, call clearerr() in the display_thread() loop to clear any EOF sticky errors, as instructed in the glibc NEWS file (https://sourceware.org/git/?p=glibc.git%3Ba=blob%3Bf=NEWS):

* All stdio functions now treat end-of-file as a sticky condition. If you read from a file until EOF, and then the file is enlarged by another process, you must call clearerr or another function with the same effect (e.g. fseek, rewind) before you can read the additional data. This corrects a longstanding C99 conformance bug. It is most likely to affect programs that use stdio to read interactive input from a terminal. (Bug #1190.)

Signed-off-by: Tommi Rantala tommi.t.rantala@nokia.com Tested-by: Arnaldo Carvalho de Melo acme@redhat.com Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Jiri Olsa jolsa@redhat.com Cc: Mark Rutland mark.rutland@arm.com Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Link: http://lore.kernel.org/lkml/20200305083714.9381-2-tommi.t.rantala@nokia.com Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- tools/perf/builtin-top.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

--- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -633,7 +633,9 @@ repeat: delay_msecs = top->delay_secs * MSEC_PER_SEC; set_term_quiet_input(&save); /* trash return*/ - getc(stdin); + clearerr(stdin); + if (poll(&stdin_poll, 1, 0) > 0) + getc(stdin);

while (!done) { perf_top__print_sym_table(top);

From: Steven Rostedt (VMware) rostedt@goodmis.org

commit b40341fad6cc2daa195f8090fd3348f18fff640a upstream.

The first thing that the ftrace function callback helper functions should do is to check for recursion. Peter Zijlstra found that when "rcu_is_watching()" had its notrace removed, it caused perf function tracing to crash. This is because the call of rcu_is_watching() is tested before function recursion is checked and and if it is traced, it will cause an infinite recursion loop.

rcu_is_watching() should still stay notrace, but to prevent this should never had crashed in the first place. The recursion prevention must be the first thing done in callback functions.

Link: https://lore.kernel.org/r/20200929112541.GM2628@hirez.programming.kicks-ass....

Cc: stable@vger.kernel.org Cc: Paul McKenney paulmck@kernel.org Fixes: c68c0fa293417 ("ftrace: Have ftrace_ops_get_func() handle RCU and PER_CPU flags too") Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Reported-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Steven Rostedt (VMware) rostedt@goodmis.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- kernel/trace/ftrace.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-)

--- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -5334,17 +5334,15 @@ static void ftrace_ops_assist_func(unsig { int bit;

- if ((op->flags & FTRACE_OPS_FL_RCU) && !rcu_is_watching()) - return; - bit = trace_test_and_set_recursion(TRACE_LIST_START, TRACE_LIST_MAX); if (bit < 0) return;

preempt_disable_notrace();

- if (!(op->flags & FTRACE_OPS_FL_PER_CPU) || - !ftrace_function_local_disabled(op)) { + if ((!(op->flags & FTRACE_OPS_FL_RCU) || rcu_is_watching()) && + (!(op->flags & FTRACE_OPS_FL_PER_CPU) || + !ftrace_function_local_disabled(op))) { op->func(ip, parent_ip, op, regs); }

From: Hugh Dickins hughd@google.com

commit 033b5d77551167f8c24ca862ce83d3e0745f9245 upstream.

There have been elusive reports of filemap_fault() hitting its VM_BUG_ON_PAGE(page_to_pgoff(page) != offset, page) on kernels built with CONFIG_READ_ONLY_THP_FOR_FS=y.

Suren has hit it on a kernel with CONFIG_READ_ONLY_THP_FOR_FS=y and CONFIG_NUMA is not set: and he has analyzed it down to how khugepaged without NUMA reuses the same huge page after collapse_file() failed (whereas NUMA targets its allocation to the respective node each time). And most of us were usually testing with CONFIG_NUMA=y kernels.

collapse_file(old start) new_page = khugepaged_alloc_page(hpage) __SetPageLocked(new_page) new_page->index = start // hpage->index=old offset new_page->mapping = mapping xas_store(&xas, new_page)

filemap_fault page = find_get_page(mapping, offset) // if offset falls inside hpage then // compound_head(page) == hpage lock_page_maybe_drop_mmap() __lock_page(page)

// collapse fails xas_store(&xas, old page) new_page->mapping = NULL unlock_page(new_page)

collapse_file(new start) new_page = khugepaged_alloc_page(hpage) __SetPageLocked(new_page) new_page->index = start // hpage->index=new offset new_page->mapping = mapping // mapping becomes valid again

// since compound_head(page) == hpage // page_to_pgoff(page) got changed VM_BUG_ON_PAGE(page_to_pgoff(page) != offset)

An initial patch replaced __SetPageLocked() by lock_page(), which did fix the race which Suren illustrates above. But testing showed that it's not good enough: if the racing task's __lock_page() gets delayed long after its find_get_page(), then it may follow collapse_file(new start)'s successful final unlock_page(), and crash on the same VM_BUG_ON_PAGE.

It could be fixed by relaxing filemap_fault()'s VM_BUG_ON_PAGE to a check and retry (as is done for mapping), with similar relaxations in find_lock_entry() and pagecache_get_page(): but it's not obvious what else might get caught out; and khugepaged non-NUMA appears to be unique in exposing a page to page cache, then revoking, without going through a full cycle of freeing before reuse.

Instead, non-NUMA khugepaged_prealloc_page() release the old page if anyone else has a reference to it (1% of cases when I tested).

Although never reported on huge tmpfs, I believe its find_lock_entry() has been at similar risk; but huge tmpfs does not rely on khugepaged for its normal working nearly so much as READ_ONLY_THP_FOR_FS does.

Reported-by: Denis Lisov dennis.lissov@gmail.com Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=206569 Link: https://lore.kernel.org/linux-mm/?q=20200219144635.3b7417145de19b65f258c943%... Reported-by: Qian Cai cai@lca.pw Link: https://lore.kernel.org/linux-xfs/?q=20200616013309.GB815%40lca.pw Reported-and-analyzed-by: Suren Baghdasaryan surenb@google.com Fixes: 87c460a0bded ("mm/khugepaged: collapse_shmem() without freezing new_page") Signed-off-by: Hugh Dickins hughd@google.com Cc: stable@vger.kernel.org # v4.9+ Reviewed-by: Matthew Wilcox (Oracle) willy@infradead.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- mm/khugepaged.c | 12 ++++++++++++ 1 file changed, 12 insertions(+)

--- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -802,6 +802,18 @@ static struct page *khugepaged_alloc_hug

static bool khugepaged_prealloc_page(struct page **hpage, bool *wait) { + /* + * If the hpage allocated earlier was briefly exposed in page cache + * before collapse_file() failed, it is possible that racing lookups + * have not yet completed, and would then be unpleasantly surprised by + * finding the hpage reused for the same mapping at a different offset. + * Just release the previous allocation if there is any danger of that. + */ + if (*hpage && page_count(*hpage) > 1) { + put_page(*hpage); + *hpage = NULL; + } + if (!*hpage) *hpage = khugepaged_alloc_hugepage(wait);

From: Eric Dumazet edumazet@google.com

commit 89d01748b2354e210b5d4ea47bc25a42a1b42c82 upstream.

Some devices set needed_headroom. If we ignore it, we might end up crashing in various skb_push() for example in ipgre_header() since some layers assume enough headroom has been reserved.

Fixes: 1d76efe1577b ("team: add support for non-ethernet devices") Signed-off-by: Eric Dumazet edumazet@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/net/team/team.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -2085,6 +2085,7 @@ static void team_setup_by_port(struct ne dev->header_ops = port_dev->header_ops; dev->type = port_dev->type; dev->hard_header_len = port_dev->hard_header_len; + dev->needed_headroom = port_dev->needed_headroom; dev->addr_len = port_dev->addr_len; dev->mtu = port_dev->mtu; memcpy(dev->broadcast, port_dev->broadcast, port_dev->addr_len);

From: Dumitru Ceara dceara@redhat.com

commit 8aa7b526dc0b5dbf40c1b834d76a667ad672a410 upstream.

With multiple DNAT rules it's possible that after destination translation the resulting tuples collide.

For example, two openvswitch flows: nw_dst=10.0.0.10,tp_dst=10, actions=ct(commit,table=2,nat(dst=20.0.0.1:20)) nw_dst=10.0.0.20,tp_dst=10, actions=ct(commit,table=2,nat(dst=20.0.0.1:20))

Assuming two TCP clients initiating the following connections: 10.0.0.10:5000->10.0.0.10:10 10.0.0.10:5000->10.0.0.20:10

Both tuples would translate to 10.0.0.10:5000->20.0.0.1:20 causing nf_conntrack_confirm() to fail because of tuple collision.

Netfilter handles this case by allocating a null binding for SNAT at egress by default. Perform the same operation in openvswitch for DNAT if no explicit SNAT is requested by the user and allocate a null binding for SNAT for packets in the "original" direction.

Reported-at: https://bugzilla.redhat.com/1877128 Suggested-by: Florian Westphal fw@strlen.de Fixes: 05752523e565 ("openvswitch: Interface with NAT.") Signed-off-by: Dumitru Ceara dceara@redhat.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- net/openvswitch/conntrack.c | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-)

--- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -709,15 +709,19 @@ static int ovs_ct_nat(struct net *net, s } err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, maniptype);

- if (err == NF_ACCEPT && - ct->status & IPS_SRC_NAT && ct->status & IPS_DST_NAT) { - if (maniptype == NF_NAT_MANIP_SRC) - maniptype = NF_NAT_MANIP_DST; - else - maniptype = NF_NAT_MANIP_SRC; + if (err == NF_ACCEPT && ct->status & IPS_DST_NAT) { + if (ct->status & IPS_SRC_NAT) { + if (maniptype == NF_NAT_MANIP_SRC) + maniptype = NF_NAT_MANIP_DST; + else + maniptype = NF_NAT_MANIP_SRC;

- err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, - maniptype); + err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, + maniptype); + } else if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) { + err = ovs_ct_nat_execute(skb, ct, ctinfo, NULL, + NF_NAT_MANIP_SRC); + } }

/* Mark NAT done if successful and update the flow key. */

From: Antony Antony antony.antony@secunet.com

[ Upstream commit 91a46c6d1b4fcbfa4773df9421b8ad3e58088101 ]

XFRMA_REPLAY_ESN_VAL was not cloned completely from the old to the new. Migrate this attribute during XFRMA_MSG_MIGRATE

v1->v2: - move curleft cloning to a separate patch

Fixes: af2f464e326e ("xfrm: Assign esn pointers when cloning a state") Signed-off-by: Antony Antony antony.antony@secunet.com Signed-off-by: Steffen Klassert steffen.klassert@secunet.com Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/xfrm.h | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-)

diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 9e2f260cbb518..b2a405c93a342 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1726,21 +1726,17 @@ static inline int xfrm_replay_state_esn_len(struct xfrm_replay_state_esn *replay static inline int xfrm_replay_clone(struct xfrm_state *x, struct xfrm_state *orig) { - x->replay_esn = kzalloc(xfrm_replay_state_esn_len(orig->replay_esn), + + x->replay_esn = kmemdup(orig->replay_esn, + xfrm_replay_state_esn_len(orig->replay_esn), GFP_KERNEL); if (!x->replay_esn) return -ENOMEM; - - x->replay_esn->bmp_len = orig->replay_esn->bmp_len; - x->replay_esn->replay_window = orig->replay_esn->replay_window; - - x->preplay_esn = kmemdup(x->replay_esn, - xfrm_replay_state_esn_len(x->replay_esn), + x->preplay_esn = kmemdup(orig->preplay_esn, + xfrm_replay_state_esn_len(orig->preplay_esn), GFP_KERNEL); - if (!x->preplay_esn) { - kfree(x->replay_esn); + if (!x->preplay_esn) return -ENOMEM; - }

return 0; }

From: Voon Weifeng weifeng.voon@intel.com

[ Upstream commit 7241c5a697479c7d0c5a96595822cdab750d41ae ]

EEE should be only be enabled during stmmac_mac_link_up() when the link are up and being set up properly. set_eee should only do settings configuration and disabling the eee.

Without this fix, turning on EEE using ethtool will return "Operation not supported". This is due to the driver is in a dead loop waiting for eee to be advertised in the for eee to be activated but the driver will only configure the EEE advertisement after the eee is activated.

Ethtool should only return "Operation not supported" if there is no EEE capbility in the MAC controller.

Fixes: 8a7493e58ad6 ("net: stmmac: Fix a race in EEE enable callback") Signed-off-by: Voon Weifeng weifeng.voon@intel.com Acked-by: Mark Gross mgross@linux.intel.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- .../net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 15 ++++----------- 1 file changed, 4 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 3519a8a589dda..c8673e231a880 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -678,23 +678,16 @@ static int stmmac_ethtool_op_set_eee(struct net_device *dev, struct stmmac_priv *priv = netdev_priv(dev); int ret;

- if (!edata->eee_enabled) { + if (!priv->dma_cap.eee) + return -EOPNOTSUPP; + + if (!edata->eee_enabled) stmmac_disable_eee_mode(priv); - } else { - /* We are asking for enabling the EEE but it is safe - * to verify all by invoking the eee_init function. - * In case of failure it will return an error. - */ - edata->eee_enabled = stmmac_eee_init(priv); - if (!edata->eee_enabled) - return -EOPNOTSUPP; - }

ret = phy_ethtool_set_eee(dev->phydev, edata); if (ret) return ret;

- priv->eee_enabled = edata->eee_enabled; priv->tx_lpi_timer = edata->tx_lpi_timer; return 0; }

From: Eric Dumazet edumazet@google.com

[ Upstream commit f32f19339596b214c208c0dba716f4b6cc4f6958 ]

syzbot managed to crash a host by creating a bond with a GRE device.

For non Ethernet device, bonding calls bond_setup_by_slave() instead of ether_setup(), and unfortunately dev->needed_headroom was not copied from the new added member.

[ 171.243095] skbuff: skb_under_panic: text:ffffffffa184b9ea len:116 put:20 head:ffff883f84012dc0 data:ffff883f84012dbc tail:0x70 end:0xd00 dev:bond0 [ 171.243111] ------------[ cut here ]------------ [ 171.243112] kernel BUG at net/core/skbuff.c:112! [ 171.243117] invalid opcode: 0000 [#1] SMP KASAN PTI [ 171.243469] gsmi: Log Shutdown Reason 0x03 [ 171.243505] Call Trace: [ 171.243506] <IRQ> [ 171.243512] [<ffffffffa171be59>] skb_push+0x49/0x50 [ 171.243516] [<ffffffffa184b9ea>] ipgre_header+0x2a/0xf0 [ 171.243520] [<ffffffffa17452d7>] neigh_connected_output+0xb7/0x100 [ 171.243524] [<ffffffffa186f1d3>] ip6_finish_output2+0x383/0x490 [ 171.243528] [<ffffffffa186ede2>] __ip6_finish_output+0xa2/0x110 [ 171.243531] [<ffffffffa186acbc>] ip6_finish_output+0x2c/0xa0 [ 171.243534] [<ffffffffa186abe9>] ip6_output+0x69/0x110 [ 171.243537] [<ffffffffa186ac90>] ? ip6_output+0x110/0x110 [ 171.243541] [<ffffffffa189d952>] mld_sendpack+0x1b2/0x2d0 [ 171.243544] [<ffffffffa189d290>] ? mld_send_report+0xf0/0xf0 [ 171.243548] [<ffffffffa189c797>] mld_ifc_timer_expire+0x2d7/0x3b0 [ 171.243551] [<ffffffffa189c4c0>] ? mld_gq_timer_expire+0x50/0x50 [ 171.243556] [<ffffffffa0fea270>] call_timer_fn+0x30/0x130 [ 171.243559] [<ffffffffa0fea17c>] expire_timers+0x4c/0x110 [ 171.243563] [<ffffffffa0fea0e3>] __run_timers+0x213/0x260 [ 171.243566] [<ffffffffa0fecb7d>] ? ktime_get+0x3d/0xa0 [ 171.243570] [<ffffffffa0ff9c4e>] ? clockevents_program_event+0x7e/0xe0 [ 171.243574] [<ffffffffa0f7e5d5>] ? sched_clock_cpu+0x15/0x190 [ 171.243577] [<ffffffffa0fe973d>] run_timer_softirq+0x1d/0x40 [ 171.243581] [<ffffffffa1c00152>] __do_softirq+0x152/0x2f0 [ 171.243585] [<ffffffffa0f44e1f>] irq_exit+0x9f/0xb0 [ 171.243588] [<ffffffffa1a02e1d>] smp_apic_timer_interrupt+0xfd/0x1a0 [ 171.243591] [<ffffffffa1a01ea6>] apic_timer_interrupt+0x86/0x90

Fixes: f5184d267c1a ("net: Allow netdevices to specify needed head/tailroom") Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: syzbot syzkaller@googlegroups.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/bonding/bond_main.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 8322129c3f987..240d7850c8252 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1129,6 +1129,7 @@ static void bond_setup_by_slave(struct net_device *bond_dev,

bond_dev->type = slave_dev->type; bond_dev->hard_header_len = slave_dev->hard_header_len; + bond_dev->needed_headroom = slave_dev->needed_headroom; bond_dev->addr_len = slave_dev->addr_len;

memcpy(bond_dev->broadcast, slave_dev->broadcast,

From: Marc Dionne marc.dionne@auristor.com

[ Upstream commit 56305118e05b2db8d0395bba640ac9a3aee92624 ]

The session key should be encoded with just the 8 data bytes and no length; ENCODE_DATA precedes it with a 4 byte length, which confuses some existing tools that try to parse this format.

Add an ENCODE_BYTES macro that does not include a length, and use it for the key. Also adjust the expected length.

Note that commit 774521f353e1d ("rxrpc: Fix an assertion in rxrpc_read()") had fixed a BUG by changing the length rather than fixing the encoding. The original length was correct.

Fixes: 99455153d067 ("RxRPC: Parse security index 5 keys (Kerberos 5)") Signed-off-by: Marc Dionne marc.dionne@auristor.com Signed-off-by: David Howells dhowells@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/rxrpc/key.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/net/rxrpc/key.c b/net/rxrpc/key.c index 7fc340726d034..fd9260620824e 100644 --- a/net/rxrpc/key.c +++ b/net/rxrpc/key.c @@ -1139,6 +1139,14 @@ static long rxrpc_read(const struct key *key, goto fault; \ xdr += (_l + 3) >> 2; \ } while(0) +#define ENCODE_BYTES(l, s) \ + do { \ + u32 _l = (l); \ + memcpy(xdr, (s), _l); \ + if (_l & 3) \ + memcpy((u8 *)xdr + _l, &zero, 4 - (_l & 3)); \ + xdr += (_l + 3) >> 2; \ + } while(0) #define ENCODE64(x) \ do { \ __be64 y = cpu_to_be64(x); \ @@ -1167,7 +1175,7 @@ static long rxrpc_read(const struct key *key, case RXRPC_SECURITY_RXKAD: ENCODE(token->kad->vice_id); ENCODE(token->kad->kvno); - ENCODE_DATA(8, token->kad->session_key); + ENCODE_BYTES(8, token->kad->session_key); ENCODE(token->kad->start); ENCODE(token->kad->expiry); ENCODE(token->kad->primary_flag);

From: David Howells dhowells@redhat.com

[ Upstream commit fa1d113a0f96f9ab7e4fe4f8825753ba1e34a9d3 ]

conn->state_lock may be taken in softirq mode, but a previous patch replaced an outer lock in the response-packet event handling code, and lost the _bh from that when doing so.

Fix this by applying the _bh annotation to the state_lock locking.

Fixes: a1399f8bb033 ("rxrpc: Call channels should have separate call number spaces") Signed-off-by: David Howells dhowells@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/rxrpc/conn_event.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index b099b64366f35..ec02dd7c12ef4 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -309,18 +309,18 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, return ret;

spin_lock(&conn->channel_lock); - spin_lock(&conn->state_lock); + spin_lock_bh(&conn->state_lock);

if (conn->state == RXRPC_CONN_SERVICE_CHALLENGING) { conn->state = RXRPC_CONN_SERVICE; - spin_unlock(&conn->state_lock); + spin_unlock_bh(&conn->state_lock); for (loop = 0; loop < RXRPC_MAXCALLS; loop++) rxrpc_call_is_secure( rcu_dereference_protected( conn->channels[loop].call, lockdep_is_held(&conn->channel_lock))); } else { - spin_unlock(&conn->state_lock); + spin_unlock_bh(&conn->state_lock); }

spin_unlock(&conn->channel_lock);

From: Kajol Jain kjain@linux.ibm.com

[ Upstream commit 6d6b8b9f4fceab7266ca03d194f60ec72bd4b654 ]

The error handling introduced by commit:

2ed6edd33a21 ("perf: Add cond_resched() to task_function_call()")

looses any return value from smp_call_function_single() that is not {0, -EINVAL}. This is a problem because it will return -EXNIO when the target CPU is offline. Worse, in that case it'll turn into an infinite loop.

Fixes: 2ed6edd33a21 ("perf: Add cond_resched() to task_function_call()") Reported-by: Srikar Dronamraju srikar@linux.vnet.ibm.com Signed-off-by: Kajol Jain kjain@linux.ibm.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Ingo Molnar mingo@kernel.org Reviewed-by: Barret Rhoden brho@google.com Tested-by: Srikar Dronamraju srikar@linux.vnet.ibm.com Link: https://lkml.kernel.org/r/20200827064732.20860-1-kjain@linux.ibm.com Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/events/core.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c index b562467d2d498..7aad4d22b4223 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -94,7 +94,7 @@ static void remote_function(void *data) * retry due to any failures in smp_call_function_single(), such as if the * task_cpu() goes offline concurrently. * - * returns @func return value or -ESRCH when the process isn't running + * returns @func return value or -ESRCH or -ENXIO when the process isn't running */ static int task_function_call(struct task_struct *p, remote_function_f func, void *info) @@ -110,7 +110,8 @@ task_function_call(struct task_struct *p, remote_function_f func, void *info) for (;;) { ret = smp_call_function_single(task_cpu(p), remote_function, &data, 1); - ret = !ret ? data.ret : -EAGAIN; + if (!ret) + ret = data.ret;

if (ret != -EAGAIN) break;

From: Anant Thazhemadam anant.thazhemadam@gmail.com

commit f45a4248ea4cc13ed50618ff066849f9587226b2 upstream.

When get_registers() fails in set_ethernet_addr(),the uninitialized value of node_id gets copied over as the address. So, check the return value of get_registers().

If get_registers() executed successfully (i.e., it returns sizeof(node_id)), copy over the MAC address using ether_addr_copy() (instead of using memcpy()).

Else, if get_registers() failed instead, a randomly generated MAC address is set as the MAC address instead.

Reported-by: syzbot+abbc768b560c84d92fd3@syzkaller.appspotmail.com Tested-by: syzbot+abbc768b560c84d92fd3@syzkaller.appspotmail.com Acked-by: Petko Manolov petkan@nucleusys.com Signed-off-by: Anant Thazhemadam anant.thazhemadam@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/net/usb/rtl8150.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-)

--- a/drivers/net/usb/rtl8150.c +++ b/drivers/net/usb/rtl8150.c @@ -277,12 +277,20 @@ static int write_mii_word(rtl8150_t * de return 1; }

-static inline void set_ethernet_addr(rtl8150_t * dev) +static void set_ethernet_addr(rtl8150_t *dev) { - u8 node_id[6]; + u8 node_id[ETH_ALEN]; + int ret;

- get_registers(dev, IDR, sizeof(node_id), node_id); - memcpy(dev->netdev->dev_addr, node_id, sizeof(node_id)); + ret = get_registers(dev, IDR, sizeof(node_id), node_id); + + if (ret == sizeof(node_id)) { + ether_addr_copy(dev->netdev->dev_addr, node_id); + } else { + eth_hw_addr_random(dev->netdev); + netdev_notice(dev->netdev, "Assigned a random MAC address: %pM\n", + dev->netdev->dev_addr); + } }

static int rtl8150_set_mac_address(struct net_device *netdev, void *p)