5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ricardo Ribalda ribalda@chromium.org

[ Upstream commit 309422d280748c74f57f471559980268ac27732a ]

This structure is embedded in multiple other structures that are packed, which conflicts with it being aligned.

drivers/media/usb/as102/as10x_cmd.h:379:30: warning: field reg_addr within 'struct as10x_dump_memory::(unnamed at drivers/media/usb/as102/as10x_cmd.h:373:2)' is less aligned than 'struct as10x_register_addr' and is usually due to 'struct as10x_dump_memory::(unnamed at drivers/media/usb/as102/as10x_cmd.h:373:2)' being packed, which can lead to unaligned accesses [-Wunaligned-access]

Mark it as being packed.

Marking the inner struct as 'packed' does not change the layout, since the whole struct is already packed, it just silences the clang warning. See also this llvm discussion:

https://github.com/llvm/llvm-project/issues/55520

Signed-off-by: Ricardo Ribalda ribalda@chromium.org Signed-off-by: Hans Verkuil hverkuil-cisco@xs4all.nl Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/media/dvb-frontends/as102_fe_types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/dvb-frontends/as102_fe_types.h b/drivers/media/dvb-frontends/as102_fe_types.h index 297f9520ebf9d..8a4e392c88965 100644 --- a/drivers/media/dvb-frontends/as102_fe_types.h +++ b/drivers/media/dvb-frontends/as102_fe_types.h @@ -174,6 +174,6 @@ struct as10x_register_addr { uint32_t addr; /* register mode access */ uint8_t mode; -}; +} __packed;

#endif

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Michael Guralnik michaelgur@nvidia.com

[ Upstream commit ca0b44e20a6f3032224599f02e7c8fb49525c894 ]

The existing behavior of ib_umad, which maintains received MAD packets in an unbounded list, poses a risk of uncontrolled growth. As user-space applications extract packets from this list, the rate of extraction may not match the rate of incoming packets, leading to potential list overflow.

To address this, we introduce a limit to the size of the list. After considering typical scenarios, such as OpenSM processing, which can handle approximately 100k packets per second, and the 1-second retry timeout for most packets, we set the list size limit to 200k. Packets received beyond this limit are dropped, assuming they are likely timed out by the time they are handled by user-space.

Notably, packets queued on the receive list due to reasons like timed-out sends are preserved even when the list is full.

Signed-off-by: Michael Guralnik michaelgur@nvidia.com Reviewed-by: Mark Zhang markzhang@nvidia.com Link: https://lore.kernel.org/r/7197cb58a7d9e78399008f25036205ceab07fbd5.171326881... Signed-off-by: Leon Romanovsky leon@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/core/user_mad.c | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-)

diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c index 390123f87658b..51ce5b7be0718 100644 --- a/drivers/infiniband/core/user_mad.c +++ b/drivers/infiniband/core/user_mad.c @@ -63,6 +63,8 @@ MODULE_AUTHOR("Roland Dreier"); MODULE_DESCRIPTION("InfiniBand userspace MAD packet access"); MODULE_LICENSE("Dual BSD/GPL");

+#define MAX_UMAD_RECV_LIST_SIZE 200000 + enum { IB_UMAD_MAX_PORTS = RDMA_MAX_PORTS, IB_UMAD_MAX_AGENTS = 32, @@ -113,6 +115,7 @@ struct ib_umad_file { struct mutex mutex; struct ib_umad_port *port; struct list_head recv_list; + atomic_t recv_list_size; struct list_head send_list; struct list_head port_list; spinlock_t send_lock; @@ -180,24 +183,28 @@ static struct ib_mad_agent *__get_agent(struct ib_umad_file *file, int id) return file->agents_dead ? NULL : file->agent[id]; }

-static int queue_packet(struct ib_umad_file *file, - struct ib_mad_agent *agent, - struct ib_umad_packet *packet) +static int queue_packet(struct ib_umad_file *file, struct ib_mad_agent *agent, + struct ib_umad_packet *packet, bool is_recv_mad) { int ret = 1;

mutex_lock(&file->mutex);

+ if (is_recv_mad && + atomic_read(&file->recv_list_size) > MAX_UMAD_RECV_LIST_SIZE) + goto unlock; + for (packet->mad.hdr.id = 0; packet->mad.hdr.id < IB_UMAD_MAX_AGENTS; packet->mad.hdr.id++) if (agent == __get_agent(file, packet->mad.hdr.id)) { list_add_tail(&packet->list, &file->recv_list); + atomic_inc(&file->recv_list_size); wake_up_interruptible(&file->recv_wait); ret = 0; break; } - +unlock: mutex_unlock(&file->mutex);

return ret; @@ -224,7 +231,7 @@ static void send_handler(struct ib_mad_agent *agent, if (send_wc->status == IB_WC_RESP_TIMEOUT_ERR) { packet->length = IB_MGMT_MAD_HDR; packet->mad.hdr.status = ETIMEDOUT; - if (!queue_packet(file, agent, packet)) + if (!queue_packet(file, agent, packet, false)) return; } kfree(packet); @@ -284,7 +291,7 @@ static void recv_handler(struct ib_mad_agent *agent, rdma_destroy_ah_attr(&ah_attr); }

- if (queue_packet(file, agent, packet)) + if (queue_packet(file, agent, packet, true)) goto err2; return;

@@ -409,6 +416,7 @@ static ssize_t ib_umad_read(struct file *filp, char __user *buf,

packet = list_entry(file->recv_list.next, struct ib_umad_packet, list); list_del(&packet->list); + atomic_dec(&file->recv_list_size);

mutex_unlock(&file->mutex);

@@ -421,6 +429,7 @@ static ssize_t ib_umad_read(struct file *filp, char __user *buf, /* Requeue packet */ mutex_lock(&file->mutex); list_add(&packet->list, &file->recv_list); + atomic_inc(&file->recv_list_size); mutex_unlock(&file->mutex); } else { if (packet->recv_wc)

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ma Jun Jun.Ma2@amd.com

[ Upstream commit 2e55bcf3d742a4946d862b86e39e75a95cc6f1c0 ]

Initialize the interrupt timestamp for some legacy SOCs to fix the coverity issue "Uninitialized scalar variable"

Signed-off-by: Ma Jun Jun.Ma2@amd.com Suggested-by: Christian König christian.koenig@amd.com Reviewed-by: Christian König christian.koenig@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c | 8 ++++++++ 1 file changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c index 76429932035e1..a803e6a4e3473 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c @@ -384,6 +384,14 @@ void amdgpu_irq_dispatch(struct amdgpu_device *adev, int r;

entry.iv_entry = (const uint32_t *)&ih->ring[ring_index]; + + /* + * timestamp is not supported on some legacy SOCs (cik, cz, iceland, + * si and tonga), so initialize timestamp and timestamp_src to 0 + */ + entry.timestamp = 0; + entry.timestamp_src = 0; + amdgpu_ih_decode_iv(adev, &entry);

trace_amdgpu_iv(ih - &adev->irq.ih, &entry);

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Michael Bunk micha@freedict.org

[ Upstream commit 0e148a522b8453115038193e19ec7bea71403e4a ]

The code ignored the I2C_M_RD flag on I2C messages. Instead it assumed an i2c transaction with a single message must be a write operation and a transaction with two messages would be a read operation.

Though this works for the driver code, it leads to problems once the i2c device is exposed to code not knowing this convention. For example, I did "insmod i2c-dev" and issued read requests from userspace, which were translated into write requests and destroyed the EEPROM of my device.

So, just check and respect the I2C_M_READ flag, which indicates a read when set on a message. If it is absent, it is a write message.

Incidentally, changing from the case statement to a while loop allows the code to lift the limitation to two i2c messages per transaction.

There are 4 more *_i2c_transfer functions affected by the same behaviour and limitation that should be fixed in the same way.

Link: https://lore.kernel.org/linux-media/20220116112238.74171-2-micha@freedict.or... Signed-off-by: Michael Bunk micha@freedict.org Signed-off-by: Mauro Carvalho Chehab mchehab@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/media/usb/dvb-usb/dw2102.c | 120 ++++++++++++++++++----------- 1 file changed, 73 insertions(+), 47 deletions(-)

diff --git a/drivers/media/usb/dvb-usb/dw2102.c b/drivers/media/usb/dvb-usb/dw2102.c index 924a6478007a8..ff5b007e2d99d 100644 --- a/drivers/media/usb/dvb-usb/dw2102.c +++ b/drivers/media/usb/dvb-usb/dw2102.c @@ -716,6 +716,7 @@ static int su3000_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[], { struct dvb_usb_device *d = i2c_get_adapdata(adap); struct dw2102_state *state; + int j;

if (!d) return -ENODEV; @@ -729,11 +730,11 @@ static int su3000_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[], return -EAGAIN; }

- switch (num) { - case 1: - switch (msg[0].addr) { + j = 0; + while (j < num) { + switch (msg[j].addr) { case SU3000_STREAM_CTRL: - state->data[0] = msg[0].buf[0] + 0x36; + state->data[0] = msg[j].buf[0] + 0x36; state->data[1] = 3; state->data[2] = 0; if (dvb_usb_generic_rw(d, state->data, 3, @@ -745,61 +746,86 @@ static int su3000_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[], if (dvb_usb_generic_rw(d, state->data, 1, state->data, 2, 0) < 0) err("i2c transfer failed."); - msg[0].buf[1] = state->data[0]; - msg[0].buf[0] = state->data[1]; + msg[j].buf[1] = state->data[0]; + msg[j].buf[0] = state->data[1]; break; default: - if (3 + msg[0].len > sizeof(state->data)) { - warn("i2c wr: len=%d is too big!\n", - msg[0].len); + /* if the current write msg is followed by a another + * read msg to/from the same address + */ + if ((j+1 < num) && (msg[j+1].flags & I2C_M_RD) && + (msg[j].addr == msg[j+1].addr)) { + /* join both i2c msgs to one usb read command */ + if (4 + msg[j].len > sizeof(state->data)) { + warn("i2c combined wr/rd: write len=%d is too big!\n", + msg[j].len); + num = -EOPNOTSUPP; + break; + } + if (1 + msg[j+1].len > sizeof(state->data)) { + warn("i2c combined wr/rd: read len=%d is too big!\n", + msg[j+1].len); + num = -EOPNOTSUPP; + break; + } + + state->data[0] = 0x09; + state->data[1] = msg[j].len; + state->data[2] = msg[j+1].len; + state->data[3] = msg[j].addr; + memcpy(&state->data[4], msg[j].buf, msg[j].len); + + if (dvb_usb_generic_rw(d, state->data, msg[j].len + 4, + state->data, msg[j+1].len + 1, 0) < 0) + err("i2c transfer failed."); + + memcpy(msg[j+1].buf, &state->data[1], msg[j+1].len); + j++; + break; + } + + if (msg[j].flags & I2C_M_RD) { + /* single read */ + if (1 + msg[j].len > sizeof(state->data)) { + warn("i2c rd: len=%d is too big!\n", msg[j].len); + num = -EOPNOTSUPP; + break; + } + + state->data[0] = 0x09; + state->data[1] = 0; + state->data[2] = msg[j].len; + state->data[3] = msg[j].addr; + memcpy(&state->data[4], msg[j].buf, msg[j].len); + + if (dvb_usb_generic_rw(d, state->data, 4, + state->data, msg[j].len + 1, 0) < 0) + err("i2c transfer failed."); + + memcpy(msg[j].buf, &state->data[1], msg[j].len); + break; + } + + /* single write */ + if (3 + msg[j].len > sizeof(state->data)) { + warn("i2c wr: len=%d is too big!\n", msg[j].len); num = -EOPNOTSUPP; break; }

- /* always i2c write*/ state->data[0] = 0x08; - state->data[1] = msg[0].addr; - state->data[2] = msg[0].len; + state->data[1] = msg[j].addr; + state->data[2] = msg[j].len;

- memcpy(&state->data[3], msg[0].buf, msg[0].len); + memcpy(&state->data[3], msg[j].buf, msg[j].len);

- if (dvb_usb_generic_rw(d, state->data, msg[0].len + 3, + if (dvb_usb_generic_rw(d, state->data, msg[j].len + 3, state->data, 1, 0) < 0) err("i2c transfer failed."); + } // switch + j++;

- } - break; - case 2: - /* always i2c read */ - if (4 + msg[0].len > sizeof(state->data)) { - warn("i2c rd: len=%d is too big!\n", - msg[0].len); - num = -EOPNOTSUPP; - break; - } - if (1 + msg[1].len > sizeof(state->data)) { - warn("i2c rd: len=%d is too big!\n", - msg[1].len); - num = -EOPNOTSUPP; - break; - } - - state->data[0] = 0x09; - state->data[1] = msg[0].len; - state->data[2] = msg[1].len; - state->data[3] = msg[0].addr; - memcpy(&state->data[4], msg[0].buf, msg[0].len); - - if (dvb_usb_generic_rw(d, state->data, msg[0].len + 4, - state->data, msg[1].len + 1, 0) < 0) - err("i2c transfer failed."); - - memcpy(msg[1].buf, &state->data[1], msg[1].len); - break; - default: - warn("more than 2 i2c messages at a time is not handled yet."); - break; - } + } // while mutex_unlock(&d->data_mutex); mutex_unlock(&d->i2c_mutex); return num;

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jean Delvare jdelvare@suse.de

[ Upstream commit 0ef11f604503b1862a21597436283f158114d77e ]

If a DMI table entry is shorter than 4 bytes, it is invalid. Due to how DMI table parsing works, it is impossible to safely recover from such an error, so we have to stop decoding the table.

Signed-off-by: Jean Delvare jdelvare@suse.de Link: https://lore.kernel.org/linux-kernel/Zh2K3-HLXOesT_vZ@liuwe-devbox-debian-v2... Reviewed-by: Michael Kelley mhklinux@outlook.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/firmware/dmi_scan.c | 11 +++++++++++ 1 file changed, 11 insertions(+)

diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c index 1e21fc3e9851a..537c104652f71 100644 --- a/drivers/firmware/dmi_scan.c +++ b/drivers/firmware/dmi_scan.c @@ -96,6 +96,17 @@ static void dmi_decode_table(u8 *buf, (data - buf + sizeof(struct dmi_header)) <= dmi_len) { const struct dmi_header *dm = (const struct dmi_header *)data;

+ /* + * If a short entry is found (less than 4 bytes), not only it + * is invalid, but we cannot reliably locate the next entry. + */ + if (dm->length < sizeof(struct dmi_header)) { + pr_warn(FW_BUG + "Corrupted DMI table, offset %zd (only %d entries processed)\n", + data - buf, i); + break; + } + /* * We want to know the total length (formatted area and * strings) before decoding to make sure we won't run off the

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Simon Horman horms@kernel.org

[ Upstream commit 4c7f3950a9fd53a62b156c0fe7c3a2c43b0ba19b ]

Since commit a3c53be55c95 ("net: dsa: mv88e6xxx: Support multiple MDIO busses") mv88e6xxx_default_mdio_bus() has checked that the return value of list_first_entry() is non-NULL.

This appears to be intended to guard against the list chip->mdios being empty. However, it is not the correct check as the implementation of list_first_entry is not designed to return NULL for empty lists.

Instead, use list_first_entry_or_null() which does return NULL if the list is empty.

Flagged by Smatch. Compile tested only.

Reviewed-by: Andrew Lunn andrew@lunn.ch Signed-off-by: Simon Horman horms@kernel.org Link: https://lore.kernel.org/r/20240430-mv88e6xx-list_empty-v3-1-c35c69d88d2e@ker... Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/dsa/mv88e6xxx/chip.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 81e6227cc8758..cf3d574374376 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -115,8 +115,8 @@ struct mii_bus *mv88e6xxx_default_mdio_bus(struct mv88e6xxx_chip *chip) { struct mv88e6xxx_mdio_bus *mdio_bus;

- mdio_bus = list_first_entry(&chip->mdios, struct mv88e6xxx_mdio_bus, - list); + mdio_bus = list_first_entry_or_null(&chip->mdios, + struct mv88e6xxx_mdio_bus, list); if (!mdio_bus) return NULL;

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ricardo Ribalda ribalda@chromium.org

[ Upstream commit 6cff72f6bcee89228a662435b7c47e21a391c8d0 ]

Use an API that resembles more the actual use of num_channels.

Found by cocci: drivers/media/usb/s2255/s2255drv.c:2362:5-24: WARNING: atomic_dec_and_test variation before object free at line 2363. drivers/media/usb/s2255/s2255drv.c:1557:5-24: WARNING: atomic_dec_and_test variation before object free at line 1558.

Link: https://lore.kernel.org/linux-media/20240429-fix-cocci-v3-11-3c4865f5a4b0@ch... Signed-off-by: Ricardo Ribalda ribalda@chromium.org Signed-off-by: Mauro Carvalho Chehab mchehab@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/media/usb/s2255/s2255drv.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/media/usb/s2255/s2255drv.c b/drivers/media/usb/s2255/s2255drv.c index 7ed526306816a..845869240abee 100644 --- a/drivers/media/usb/s2255/s2255drv.c +++ b/drivers/media/usb/s2255/s2255drv.c @@ -247,7 +247,7 @@ struct s2255_vc { struct s2255_dev { struct s2255_vc vc[MAX_CHANNELS]; struct v4l2_device v4l2_dev; - atomic_t num_channels; + refcount_t num_channels; int frames; struct mutex lock; /* channels[].vdev.lock */ struct mutex cmdlock; /* protects cmdbuf */ @@ -1552,11 +1552,11 @@ static void s2255_video_device_release(struct video_device *vdev) container_of(vdev, struct s2255_vc, vdev);

dprintk(dev, 4, "%s, chnls: %d\n", __func__, - atomic_read(&dev->num_channels)); + refcount_read(&dev->num_channels));

v4l2_ctrl_handler_free(&vc->hdl);

- if (atomic_dec_and_test(&dev->num_channels)) + if (refcount_dec_and_test(&dev->num_channels)) s2255_destroy(dev); return; } @@ -1661,7 +1661,7 @@ static int s2255_probe_v4l(struct s2255_dev *dev) "failed to register video device!\n"); break; } - atomic_inc(&dev->num_channels); + refcount_inc(&dev->num_channels); v4l2_info(&dev->v4l2_dev, "V4L2 device registered as %s\n", video_device_node_name(&vc->vdev));

@@ -1669,11 +1669,11 @@ static int s2255_probe_v4l(struct s2255_dev *dev) pr_info("Sensoray 2255 V4L driver Revision: %s\n", S2255_VERSION); /* if no channels registered, return error and probe will fail*/ - if (atomic_read(&dev->num_channels) == 0) { + if (refcount_read(&dev->num_channels) == 0) { v4l2_device_unregister(&dev->v4l2_dev); return ret; } - if (atomic_read(&dev->num_channels) != MAX_CHANNELS) + if (refcount_read(&dev->num_channels) != MAX_CHANNELS) pr_warn("s2255: Not all channels available.\n"); return 0; } @@ -2222,7 +2222,7 @@ static int s2255_probe(struct usb_interface *interface, goto errorFWDATA1; }

- atomic_set(&dev->num_channels, 0); + refcount_set(&dev->num_channels, 0); dev->pid = id->idProduct; dev->fw_data = kzalloc(sizeof(struct s2255_fw), GFP_KERNEL); if (!dev->fw_data) @@ -2342,12 +2342,12 @@ static void s2255_disconnect(struct usb_interface *interface) { struct s2255_dev *dev = to_s2255_dev(usb_get_intfdata(interface)); int i; - int channels = atomic_read(&dev->num_channels); + int channels = refcount_read(&dev->num_channels); mutex_lock(&dev->lock); v4l2_device_disconnect(&dev->v4l2_dev); mutex_unlock(&dev->lock); /*see comments in the uvc_driver.c usb disconnect function */ - atomic_inc(&dev->num_channels); + refcount_inc(&dev->num_channels); /* unregister each video device. */ for (i = 0; i < channels; i++) video_unregister_device(&dev->vc[i].vdev); @@ -2360,7 +2360,7 @@ static void s2255_disconnect(struct usb_interface *interface) dev->vc[i].vidstatus_ready = 1; wake_up(&dev->vc[i].wait_vidstatus); } - if (atomic_dec_and_test(&dev->num_channels)) + if (refcount_dec_and_test(&dev->num_channels)) s2255_destroy(dev); dev_info(&interface->dev, "%s\n", __func__); }

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Heiner Kallweit hkallweit1@gmail.com

[ Upstream commit 355b1513b1e97b6cef84b786c6480325dfd3753d ]

Annotate this variable as __ro_after_init to protect it from being overwritten later.

Signed-off-by: Heiner Kallweit hkallweit1@gmail.com Signed-off-by: Andi Shyti andi.shyti@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/i2c/busses/i2c-i801.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index 18489940a947b..2c077ffcee607 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -1057,7 +1057,7 @@ static const struct pci_device_id i801_ids[] = { MODULE_DEVICE_TABLE(pci, i801_ids);

#if defined CONFIG_X86 && defined CONFIG_DMI -static unsigned char apanel_addr; +static unsigned char apanel_addr __ro_after_init;

/* Scan the system ROM for the signature "FJKEYINF" */ static __init const void __iomem *bios_signature(const void __iomem *bios)

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Mike Marshall hubcap@omnibond.com

[ Upstream commit 53e4efa470d5fc6a96662d2d3322cfc925818517 ]

Arnd Bergmann sent a patch to fsdevel, he says:

"orangefs_statfs() copies two consecutive fields of the superblock into the statfs structure, which triggers a warning from the string fortification helpers"

Jan Kara suggested an alternate way to do the patch to make it more readable.

I ran both ideas through xfstests and both seem fine. This patch is based on Jan Kara's suggestion.

Signed-off-by: Mike Marshall hubcap@omnibond.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/orangefs/super.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/orangefs/super.c b/fs/orangefs/super.c index 2f2e430461b21..b48aef43b51d5 100644 --- a/fs/orangefs/super.c +++ b/fs/orangefs/super.c @@ -200,7 +200,8 @@ static int orangefs_statfs(struct dentry *dentry, struct kstatfs *buf) (long)new_op->downcall.resp.statfs.files_avail);

buf->f_type = sb->s_magic; - memcpy(&buf->f_fsid, &ORANGEFS_SB(sb)->fs_id, sizeof(buf->f_fsid)); + buf->f_fsid.val[0] = ORANGEFS_SB(sb)->fs_id; + buf->f_fsid.val[1] = ORANGEFS_SB(sb)->id; buf->f_bsize = new_op->downcall.resp.statfs.block_size; buf->f_namelen = ORANGEFS_NAME_MAX;

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Wang Yong wang.yong12@zte.com.cn

[ Upstream commit af9a8730ddb6a4b2edd779ccc0aceb994d616830 ]

During the stress testing of the jffs2 file system,the following abnormal printouts were found: [ 2430.649000] Unable to handle kernel paging request at virtual address 0069696969696948 [ 2430.649622] Mem abort info: [ 2430.649829] ESR = 0x96000004 [ 2430.650115] EC = 0x25: DABT (current EL), IL = 32 bits [ 2430.650564] SET = 0, FnV = 0 [ 2430.650795] EA = 0, S1PTW = 0 [ 2430.651032] FSC = 0x04: level 0 translation fault [ 2430.651446] Data abort info: [ 2430.651683] ISV = 0, ISS = 0x00000004 [ 2430.652001] CM = 0, WnR = 0 [ 2430.652558] [0069696969696948] address between user and kernel address ranges [ 2430.653265] Internal error: Oops: 96000004 [#1] PREEMPT SMP [ 2430.654512] CPU: 2 PID: 20919 Comm: cat Not tainted 5.15.25-g512f31242bf6 #33 [ 2430.655008] Hardware name: linux,dummy-virt (DT) [ 2430.655517] pstate: 20000005 (nzCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 2430.656142] pc : kfree+0x78/0x348 [ 2430.656630] lr : jffs2_free_inode+0x24/0x48 [ 2430.657051] sp : ffff800009eebd10 [ 2430.657355] x29: ffff800009eebd10 x28: 0000000000000001 x27: 0000000000000000 [ 2430.658327] x26: ffff000038f09d80 x25: 0080000000000000 x24: ffff800009d38000 [ 2430.658919] x23: 5a5a5a5a5a5a5a5a x22: ffff000038f09d80 x21: ffff8000084f0d14 [ 2430.659434] x20: ffff0000bf9a6ac0 x19: 0169696969696940 x18: 0000000000000000 [ 2430.659969] x17: ffff8000b6506000 x16: ffff800009eec000 x15: 0000000000004000 [ 2430.660637] x14: 0000000000000000 x13: 00000001000820a1 x12: 00000000000d1b19 [ 2430.661345] x11: 0004000800000000 x10: 0000000000000001 x9 : ffff8000084f0d14 [ 2430.662025] x8 : ffff0000bf9a6b40 x7 : ffff0000bf9a6b48 x6 : 0000000003470302 [ 2430.662695] x5 : ffff00002e41dcc0 x4 : ffff0000bf9aa3b0 x3 : 0000000003470342 [ 2430.663486] x2 : 0000000000000000 x1 : ffff8000084f0d14 x0 : fffffc0000000000 [ 2430.664217] Call trace: [ 2430.664528] kfree+0x78/0x348 [ 2430.664855] jffs2_free_inode+0x24/0x48 [ 2430.665233] i_callback+0x24/0x50 [ 2430.665528] rcu_do_batch+0x1ac/0x448 [ 2430.665892] rcu_core+0x28c/0x3c8 [ 2430.666151] rcu_core_si+0x18/0x28 [ 2430.666473] __do_softirq+0x138/0x3cc [ 2430.666781] irq_exit+0xf0/0x110 [ 2430.667065] handle_domain_irq+0x6c/0x98 [ 2430.667447] gic_handle_irq+0xac/0xe8 [ 2430.667739] call_on_irq_stack+0x28/0x54 The parameter passed to kfree was 5a5a5a5a, which corresponds to the target field of the jffs_inode_info structure. It was found that all variables in the jffs_inode_info structure were 5a5a5a5a, except for the first member sem. It is suspected that these variables are not initialized because they were set to 5a5a5a5a during memory testing, which is meant to detect uninitialized memory.The sem variable is initialized in the function jffs2_i_init_once, while other members are initialized in the function jffs2_init_inode_info.

The function jffs2_init_inode_info is called after iget_locked, but in the iget_locked function, the destroy_inode process is triggered, which releases the inode and consequently, the target member of the inode is not initialized.In concurrent high pressure scenarios, iget_locked may enter the destroy_inode branch as described in the code.

Since the destroy_inode functionality of jffs2 only releases the target, the fix method is to set target to NULL in jffs2_i_init_once.

Signed-off-by: Wang Yong wang.yong12@zte.com.cn Reviewed-by: Lu Zhongjun lu.zhongjun@zte.com.cn Reviewed-by: Yang Tao yang.tao172@zte.com.cn Cc: Xu Xin xu.xin16@zte.com.cn Cc: Yang Yang yang.yang29@zte.com.cn Signed-off-by: Richard Weinberger richard@nod.at Signed-off-by: Sasha Levin sashal@kernel.org --- fs/jffs2/super.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c index 6839a61e8ff1e..3602e368cee07 100644 --- a/fs/jffs2/super.c +++ b/fs/jffs2/super.c @@ -58,6 +58,7 @@ static void jffs2_i_init_once(void *foo) struct jffs2_inode_info *f = foo;

mutex_init(&f->sem); + f->target = NULL; inode_init_once(&f->vfs_inode); }

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: zhang kai zhangkaiheb@126.com

[ Upstream commit 636ef28d6e4d174e424102466caf572b0406fb0e ]

so tcp_is_sack/reno checks are removed from tcp_mark_head_lost.

Signed-off-by: zhang kai zhangkaiheb@126.com Acked-by: Neal Cardwell ncardwell@google.com Signed-off-by: David S. Miller davem@davemloft.net Stable-dep-of: a6458ab7fd4f ("UPSTREAM: tcp: fix DSACK undo in fast recovery to call tcp_try_to_open()") Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/tcp_input.c | 32 +++++++------------------------- 1 file changed, 7 insertions(+), 25 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 87a10bb11eb0b..dc446d7c9e0f2 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2202,8 +2202,7 @@ static bool tcp_time_to_recover(struct sock *sk, int flag) }

/* Detect loss in event "A" above by marking head of queue up as lost. - * For non-SACK(Reno) senders, the first "packets" number of segments - * are considered lost. For RFC3517 SACK, a segment is considered lost if it + * For RFC3517 SACK, a segment is considered lost if it * has at least tp->reordering SACKed seqments above it; "packets" refers to * the maximum SACKed segments to pass before reaching this limit. */ @@ -2211,10 +2210,9 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; - int cnt, oldcnt, lost; - unsigned int mss; + int cnt; /* Use SACK to deduce losses of new sequences sent during recovery */ - const u32 loss_high = tcp_is_sack(tp) ? tp->snd_nxt : tp->high_seq; + const u32 loss_high = tp->snd_nxt;

WARN_ON(packets > tp->packets_out); skb = tp->lost_skb_hint; @@ -2237,26 +2235,11 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) if (after(TCP_SKB_CB(skb)->end_seq, loss_high)) break;

- oldcnt = cnt; - if (tcp_is_reno(tp) || - (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) + if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) cnt += tcp_skb_pcount(skb);

- if (cnt > packets) { - if (tcp_is_sack(tp) || - (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) || - (oldcnt >= packets)) - break; - - mss = tcp_skb_mss(skb); - /* If needed, chop off the prefix to mark as lost. */ - lost = (packets - oldcnt) * mss; - if (lost < skb->len && - tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, - lost, mss, GFP_ATOMIC) < 0) - break; - cnt = packets; - } + if (cnt > packets) + break;

tcp_skb_mark_lost(tp, skb);

@@ -2883,8 +2866,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una, if (tcp_try_undo_partial(sk, prior_snd_una)) return; /* Partial ACK arrived. Force fast retransmit. */ - do_lost = tcp_is_reno(tp) || - tcp_force_fast_retransmit(sk); + do_lost = tcp_force_fast_retransmit(sk); } if (tcp_try_undo_dsack(sk)) { tcp_try_keep_open(sk);

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Yuchung Cheng ycheng@google.com

[ Upstream commit a29cb6914681a55667436a9eb7a42e28da8cf387 ]

This patch aims to improve the situation when reordering and loss are ocurring in the same flight of packets.

Previously the reordering would first induce a spurious recovery, then the subsequent ACK may undo the cwnd (based on the timestamps e.g.). However the current loss recovery does not proceed to invoke RACK to install a reordering timer. If some packets are also lost, this may lead to a long RTO-based recovery. An example is https://groups.google.com/g/bbr-dev/c/OFHADvJbTEI

The solution is to after reverting the recovery, always invoke RACK to either mount the RACK timer to fast retransmit after the reordering window, or restarts the recovery if new loss is identified. Hence it is possible the sender may go from Recovery to Disorder/Open to Recovery again in one ACK.

Reported-by: mingkun bian bianmingkun@gmail.com Signed-off-by: Yuchung Cheng ycheng@google.com Signed-off-by: Neal Cardwell ncardwell@google.com Signed-off-by: Eric Dumazet edumazet@google.com Signed-off-by: David S. Miller davem@davemloft.net Stable-dep-of: a6458ab7fd4f ("UPSTREAM: tcp: fix DSACK undo in fast recovery to call tcp_try_to_open()") Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/tcp_input.c | 45 +++++++++++++++++++++++++------------------- 1 file changed, 26 insertions(+), 19 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 0451249c61e27..1097bca0f24fb 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2736,8 +2736,17 @@ static void tcp_process_loss(struct sock *sk, int flag, int num_dupack, *rexmit = REXMIT_LOST; }

+static bool tcp_force_fast_retransmit(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + + return after(tcp_highest_sack_seq(tp), + tp->snd_una + tp->reordering * tp->mss_cache); +} + /* Undo during fast recovery after partial ACK. */ -static bool tcp_try_undo_partial(struct sock *sk, u32 prior_snd_una) +static bool tcp_try_undo_partial(struct sock *sk, u32 prior_snd_una, + bool *do_lost) { struct tcp_sock *tp = tcp_sk(sk);

@@ -2762,7 +2771,9 @@ static bool tcp_try_undo_partial(struct sock *sk, u32 prior_snd_una) tcp_undo_cwnd_reduction(sk, true); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPPARTIALUNDO); tcp_try_keep_open(sk); - return true; + } else { + /* Partial ACK arrived. Force fast retransmit. */ + *do_lost = tcp_force_fast_retransmit(sk); } return false; } @@ -2786,14 +2797,6 @@ static void tcp_identify_packet_loss(struct sock *sk, int *ack_flag) } }

-static bool tcp_force_fast_retransmit(struct sock *sk) -{ - struct tcp_sock *tp = tcp_sk(sk); - - return after(tcp_highest_sack_seq(tp), - tp->snd_una + tp->reordering * tp->mss_cache); -} - /* Process an event, which can update packets-in-flight not trivially. * Main goal of this function is to calculate new estimate for left_out, * taking into account both packets sitting in receiver's buffer and @@ -2863,17 +2866,21 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una, if (!(flag & FLAG_SND_UNA_ADVANCED)) { if (tcp_is_reno(tp)) tcp_add_reno_sack(sk, num_dupack, ece_ack); - } else { - if (tcp_try_undo_partial(sk, prior_snd_una)) - return; - /* Partial ACK arrived. Force fast retransmit. */ - do_lost = tcp_force_fast_retransmit(sk); - } - if (tcp_try_undo_dsack(sk)) { - tcp_try_keep_open(sk); + } else if (tcp_try_undo_partial(sk, prior_snd_una, &do_lost)) return; - } + + if (tcp_try_undo_dsack(sk)) + tcp_try_keep_open(sk); + tcp_identify_packet_loss(sk, ack_flag); + if (icsk->icsk_ca_state != TCP_CA_Recovery) { + if (!tcp_time_to_recover(sk, flag)) + return; + /* Undo reverts the recovery state. If loss is evident, + * starts a new recovery (e.g. reordering then loss); + */ + tcp_enter_recovery(sk, ece_ack); + } break; case TCP_CA_Loss: tcp_process_loss(sk, flag, num_dupack, rexmit);

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jakub Kicinski kuba@kernel.org

[ Upstream commit 66be40e622e177316ae81717aa30057ba9e61dff ]

I don't see anything checking that TCP_METRICS_ATTR_SADDR_IPV4 is at least 4 bytes long, and the policy doesn't have an entry for this attribute at all (neither does it for IPv6 but v6 is manually validated).

Reviewed-by: Eric Dumazet edumazet@google.com Fixes: 3e7013ddf55a ("tcp: metrics: Allow selective get/del of tcp-metrics based on src IP") Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/tcp_metrics.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 627e3be0f754b..f6483d6401fb4 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -614,6 +614,7 @@ static const struct nla_policy tcp_metrics_nl_policy[TCP_METRICS_ATTR_MAX + 1] = [TCP_METRICS_ATTR_ADDR_IPV4] = { .type = NLA_U32, }, [TCP_METRICS_ATTR_ADDR_IPV6] = { .type = NLA_BINARY, .len = sizeof(struct in6_addr), }, + [TCP_METRICS_ATTR_SADDR_IPV4] = { .type = NLA_U32, }, /* Following attributes are not received for GET/DEL, * we keep them for reference */

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sam Sun samsun1006219@gmail.com

[ Upstream commit e271ff53807e8f2c628758290f0e499dbe51cb3d ]

In function bond_option_arp_ip_targets_set(), if newval->string is an empty string, newval->string+1 will point to the byte after the string, causing an out-of-bound read.

BUG: KASAN: slab-out-of-bounds in strlen+0x7d/0xa0 lib/string.c:418 Read of size 1 at addr ffff8881119c4781 by task syz-executor665/8107 CPU: 1 PID: 8107 Comm: syz-executor665 Not tainted 6.7.0-rc7 #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xd9/0x150 lib/dump_stack.c:106 print_address_description mm/kasan/report.c:364 [inline] print_report+0xc1/0x5e0 mm/kasan/report.c:475 kasan_report+0xbe/0xf0 mm/kasan/report.c:588 strlen+0x7d/0xa0 lib/string.c:418 __fortify_strlen include/linux/fortify-string.h:210 [inline] in4_pton+0xa3/0x3f0 net/core/utils.c:130 bond_option_arp_ip_targets_set+0xc2/0x910 drivers/net/bonding/bond_options.c:1201 __bond_opt_set+0x2a4/0x1030 drivers/net/bonding/bond_options.c:767 __bond_opt_set_notify+0x48/0x150 drivers/net/bonding/bond_options.c:792 bond_opt_tryset_rtnl+0xda/0x160 drivers/net/bonding/bond_options.c:817 bonding_sysfs_store_option+0xa1/0x120 drivers/net/bonding/bond_sysfs.c:156 dev_attr_store+0x54/0x80 drivers/base/core.c:2366 sysfs_kf_write+0x114/0x170 fs/sysfs/file.c:136 kernfs_fop_write_iter+0x337/0x500 fs/kernfs/file.c:334 call_write_iter include/linux/fs.h:2020 [inline] new_sync_write fs/read_write.c:491 [inline] vfs_write+0x96a/0xd80 fs/read_write.c:584 ksys_write+0x122/0x250 fs/read_write.c:637 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0x40/0x110 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x63/0x6b ---[ end trace ]---

Fix it by adding a check of string length before using it.

Fixes: f9de11a16594 ("bonding: add ip checks when store ip target") Signed-off-by: Yue Sun samsun1006219@gmail.com Signed-off-by: Simon Horman horms@kernel.org Acked-by: Jay Vosburgh jay.vosburgh@canonical.com Reviewed-by: Hangbin Liu liuhangbin@gmail.com Link: https://patch.msgid.link/20240702-bond-oob-v6-1-2dfdba195c19@kernel.org Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/bonding/bond_options.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 933087d85549a..68fa3e891e6f2 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -1084,9 +1084,9 @@ static int bond_option_arp_ip_targets_set(struct bonding *bond, __be32 target;

if (newval->string) { - if (!in4_pton(newval->string+1, -1, (u8 *)&target, -1, NULL)) { - netdev_err(bond->dev, "invalid ARP target %pI4 specified\n", - &target); + if (strlen(newval->string) < 1 || + !in4_pton(newval->string + 1, -1, (u8 *)&target, -1, NULL)) { + netdev_err(bond->dev, "invalid ARP target specified\n"); return ret; } if (newval->string[0] == '+')

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Zijian Zhang zijianzhang@bytedance.com

[ Upstream commit 7d6d8f0c8b700c9493f2839abccb6d29028b4219 ]

We find that when lock debugging is on, notifications may not come in order. Thus, we have order checking outputs managed by cfg_verbose, to avoid too many outputs in this case.

Fixes: 07b65c5b31ce ("test: add msg_zerocopy test") Signed-off-by: Zijian Zhang zijianzhang@bytedance.com Signed-off-by: Xiaochun Lu xiaochun.lu@bytedance.com Reviewed-by: Willem de Bruijn willemb@google.com Link: https://patch.msgid.link/20240701225349.3395580-3-zijianzhang@bytedance.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/selftests/net/msg_zerocopy.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/msg_zerocopy.c b/tools/testing/selftests/net/msg_zerocopy.c index 926556febc83c..7ea5fb28c93db 100644 --- a/tools/testing/selftests/net/msg_zerocopy.c +++ b/tools/testing/selftests/net/msg_zerocopy.c @@ -438,7 +438,7 @@ static bool do_recv_completion(int fd, int domain) /* Detect notification gaps. These should not happen often, if at all. * Gaps can occur due to drops, reordering and retransmissions. */ - if (lo != next_completion) + if (cfg_verbose && lo != next_completion) fprintf(stderr, "gap: %u..%u does not append to %u\n", lo, hi, next_completion); next_completion = hi + 1;

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ryusuke Konishi konishi.ryusuke@gmail.com

commit e2fec219a36e0993642844be0f345513507031f4 upstream.

Patch series "nilfs2: fix potential issues related to reserved inodes".

This series fixes one use-after-free issue reported by syzbot, caused by nilfs2's internal inode being exposed in the namespace on a corrupted filesystem, and a couple of flaws that cause problems if the starting number of non-reserved inodes written in the on-disk super block is intentionally (or corruptly) changed from its default value.

This patch (of 3):

In the current implementation of nilfs2, "nilfs->ns_first_ino", which gives the first non-reserved inode number, is read from the superblock, but its lower limit is not checked.

As a result, if a number that overlaps with the inode number range of reserved inodes such as the root directory or metadata files is set in the super block parameter, the inode number test macros (NILFS_MDT_INODE and NILFS_VALID_INODE) will not function properly.

In addition, these test macros use left bit-shift calculations using with the inode number as the shift count via the BIT macro, but the result of a shift calculation that exceeds the bit width of an integer is undefined in the C specification, so if "ns_first_ino" is set to a large value other than the default value NILFS_USER_INO (=11), the macros may potentially malfunction depending on the environment.

Fix these issues by checking the lower bound of "nilfs->ns_first_ino" and by preventing bit shifts equal to or greater than the NILFS_USER_INO constant in the inode number test macros.

Also, change the type of "ns_first_ino" from signed integer to unsigned integer to avoid the need for type casting in comparisons such as the lower bound check introduced this time.

Link: https://lkml.kernel.org/r/20240623051135.4180-1-konishi.ryusuke@gmail.com Link: https://lkml.kernel.org/r/20240623051135.4180-2-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi konishi.ryusuke@gmail.com Cc: Hillf Danton hdanton@sina.com Cc: Jan Kara jack@suse.cz Cc: Matthew Wilcox (Oracle) willy@infradead.org Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/nilfs2/nilfs.h | 5 +++-- fs/nilfs2/the_nilfs.c | 6 ++++++ fs/nilfs2/the_nilfs.h | 2 +- 3 files changed, 10 insertions(+), 3 deletions(-)

--- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -116,9 +116,10 @@ enum { #define NILFS_FIRST_INO(sb) (((struct the_nilfs *)sb->s_fs_info)->ns_first_ino)

#define NILFS_MDT_INODE(sb, ino) \ - ((ino) < NILFS_FIRST_INO(sb) && (NILFS_MDT_INO_BITS & BIT(ino))) + ((ino) < NILFS_USER_INO && (NILFS_MDT_INO_BITS & BIT(ino))) #define NILFS_VALID_INODE(sb, ino) \ - ((ino) >= NILFS_FIRST_INO(sb) || (NILFS_SYS_INO_BITS & BIT(ino))) + ((ino) >= NILFS_FIRST_INO(sb) || \ + ((ino) < NILFS_USER_INO && (NILFS_SYS_INO_BITS & BIT(ino))))

/** * struct nilfs_transaction_info: context information for synchronization --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -420,6 +420,12 @@ static int nilfs_store_disk_layout(struc }

nilfs->ns_first_ino = le32_to_cpu(sbp->s_first_ino); + if (nilfs->ns_first_ino < NILFS_USER_INO) { + nilfs_err(nilfs->ns_sb, + "too small lower limit for non-reserved inode numbers: %u", + nilfs->ns_first_ino); + return -EINVAL; + }

nilfs->ns_blocks_per_segment = le32_to_cpu(sbp->s_blocks_per_segment); if (nilfs->ns_blocks_per_segment < NILFS_SEG_MIN_BLOCKS) { --- a/fs/nilfs2/the_nilfs.h +++ b/fs/nilfs2/the_nilfs.h @@ -182,7 +182,7 @@ struct the_nilfs { unsigned long ns_nrsvsegs; unsigned long ns_first_data_block; int ns_inode_size; - int ns_first_ino; + unsigned int ns_first_ino; u32 ns_crc_seed;

/* /sys/fs/<nilfs>/<device> */

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jinliang Zheng alexjlzheng@tencent.com

commit cf3f9a593dab87a032d2b6a6fb205e7f3de4f0a1 upstream.

When mm_update_owner_next() is racing with swapoff (try_to_unuse()) or /proc or ptrace or page migration (get_task_mm()), it is impossible to find an appropriate task_struct in the loop whose mm_struct is the same as the target mm_struct.

If the above race condition is combined with the stress-ng-zombie and stress-ng-dup tests, such a long loop can easily cause a Hard Lockup in write_lock_irq() for tasklist_lock.

Recognize this situation in advance and exit early.

Link: https://lkml.kernel.org/r/20240620122123.3877432-1-alexjlzheng@tencent.com Signed-off-by: Jinliang Zheng alexjlzheng@tencent.com Acked-by: Michal Hocko mhocko@suse.com Cc: Christian Brauner brauner@kernel.org Cc: Jens Axboe axboe@kernel.dk Cc: Mateusz Guzik mjguzik@gmail.com Cc: Matthew Wilcox (Oracle) willy@infradead.org Cc: Oleg Nesterov oleg@redhat.com Cc: Tycho Andersen tandersen@netflix.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/exit.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/kernel/exit.c +++ b/kernel/exit.c @@ -433,6 +433,8 @@ retry: * Search through everything else, we should not get here often. */ for_each_process(g) { + if (atomic_read(&mm->mm_users) <= 1) + break; if (g->flags & PF_KTHREAD) continue; for_each_thread(g, c) {

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jan Kara jack@suse.cz

commit 702eb71fd6501b3566283f8c96d7ccc6ddd662e9 upstream.

Currently we will not generate FS_OPEN events for O_PATH file descriptors but we will generate FS_CLOSE events for them. This is asymmetry is confusing. Arguably no fsnotify events should be generated for O_PATH file descriptors as they cannot be used to access or modify file content, they are just convenient handles to file objects like paths. So fix the asymmetry by stopping to generate FS_CLOSE for O_PATH file descriptors.

Cc: stable@vger.kernel.org Signed-off-by: Jan Kara jack@suse.cz Link: https://lore.kernel.org/r/20240617162303.1596-1-jack@suse.cz Reviewed-by: Amir Goldstein amir73il@gmail.com Signed-off-by: Christian Brauner brauner@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/fsnotify.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)

--- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -62,7 +62,13 @@ static inline int fsnotify_perm(struct f struct inode *inode = file_inode(file); __u32 fsnotify_mask = 0;

- if (file->f_mode & FMODE_NONOTIFY) + /* + * FMODE_NONOTIFY are fds generated by fanotify itself which should not + * generate new events. We also don't want to generate events for + * FMODE_PATH fds (involves open & close events) as they are just + * handle creation / destruction events and not "real" file events. + */ + if (file->f_mode & (FMODE_NONOTIFY | FMODE_PATH)) return 0; if (!(mask & (MAY_READ | MAY_OPEN))) return 0;

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ma Ke make24@iscas.ac.cn

commit 80bec6825b19d95ccdfd3393cf8ec15ff2a749b4 upstream.

In nouveau_connector_get_modes(), the return value of drm_mode_duplicate() is assigned to mode, which will lead to a possible NULL pointer dereference on failure of drm_mode_duplicate(). Add a check to avoid npd.

Cc: stable@vger.kernel.org Fixes: 6ee738610f41 ("drm/nouveau: Add DRM driver for NVIDIA GPUs") Signed-off-by: Ma Ke make24@iscas.ac.cn Signed-off-by: Lyude Paul lyude@redhat.com Link: https://patchwork.freedesktop.org/patch/msgid/20240627074204.3023776-1-make2... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/nouveau/nouveau_connector.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/drivers/gpu/drm/nouveau/nouveau_connector.c +++ b/drivers/gpu/drm/nouveau/nouveau_connector.c @@ -968,6 +968,9 @@ nouveau_connector_get_modes(struct drm_c struct drm_display_mode *mode;

mode = drm_mode_duplicate(dev, nv_connector->native_mode); + if (!mode) + return 0; + drm_mode_probed_add(connector, mode); ret = 1; }

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ghadi Elie Rahme ghadi.rahme@canonical.com

commit 134061163ee5ca4759de5c24ca3bd71608891ba7 upstream.

Fix UBSAN warnings that occur when using a system with 32 physical cpu cores or more, or when the user defines a number of Ethernet queues greater than or equal to FP_SB_MAX_E1x using the num_queues module parameter.

Currently there is a read/write out of bounds that occurs on the array "struct stats_query_entry query" present inside the "bnx2x_fw_stats_req" struct in "drivers/net/ethernet/broadcom/bnx2x/bnx2x.h". Looking at the definition of the "struct stats_query_entry query" array:

struct stats_query_entry query[FP_SB_MAX_E1x+ BNX2X_FIRST_QUEUE_QUERY_IDX];

FP_SB_MAX_E1x is defined as the maximum number of fast path interrupts and has a value of 16, while BNX2X_FIRST_QUEUE_QUERY_IDX has a value of 3 meaning the array has a total size of 19. Since accesses to "struct stats_query_entry query" are offset-ted by BNX2X_FIRST_QUEUE_QUERY_IDX, that means that the total number of Ethernet queues should not exceed FP_SB_MAX_E1x (16). However one of these queues is reserved for FCOE and thus the number of Ethernet queues should be set to [FP_SB_MAX_E1x -1] (15) if FCOE is enabled or [FP_SB_MAX_E1x] (16) if it is not.

This is also described in a comment in the source code in drivers/net/ethernet/broadcom/bnx2x/bnx2x.h just above the Macro definition of FP_SB_MAX_E1x. Below is the part of this explanation that it important for this patch

/* * The total number of L2 queues, MSIX vectors and HW contexts (CIDs) is * control by the number of fast-path status blocks supported by the * device (HW/FW). Each fast-path status block (FP-SB) aka non-default * status block represents an independent interrupts context that can * serve a regular L2 networking queue. However special L2 queues such * as the FCoE queue do not require a FP-SB and other components like * the CNIC may consume FP-SB reducing the number of possible L2 queues * * If the maximum number of FP-SB available is X then: * a. If CNIC is supported it consumes 1 FP-SB thus the max number of * regular L2 queues is Y=X-1 * b. In MF mode the actual number of L2 queues is Y= (X-1/MF_factor) * c. If the FCoE L2 queue is supported the actual number of L2 queues * is Y+1 * d. The number of irqs (MSIX vectors) is either Y+1 (one extra for * slow-path interrupts) or Y+2 if CNIC is supported (one additional * FP interrupt context for the CNIC). * e. The number of HW context (CID count) is always X or X+1 if FCoE * L2 queue is supported. The cid for the FCoE L2 queue is always X. */

However this driver also supports NICs that use the E2 controller which can handle more queues due to having more FP-SB represented by FP_SB_MAX_E2. Looking at the commits when the E2 support was added, it was originally using the E1x parameters: commit f2e0899f0f27 ("bnx2x: Add 57712 support"). Back then FP_SB_MAX_E2 was set to 16 the same as E1x. However the driver was later updated to take full advantage of the E2 instead of having it be limited to the capabilities of the E1x. But as far as we can tell, the array "stats_query_entry query" was still limited to using the FP-SB available to the E1x cards as part of an oversignt when the driver was updated to take full advantage of the E2, and now with the driver being aware of the greater queue size supported by E2 NICs, it causes the UBSAN warnings seen in the stack traces below.

This patch increases the size of the "stats_query_entry query" array by replacing FP_SB_MAX_E1x with FP_SB_MAX_E2 to be large enough to handle both types of NICs.

Stack traces:

UBSAN: array-index-out-of-bounds in drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c:1529:11 index 20 is out of range for type 'stats_query_entry [19]' CPU: 12 PID: 858 Comm: systemd-network Not tainted 6.9.0-060900rc7-generic #202405052133 Hardware name: HP ProLiant DL360 Gen9/ProLiant DL360 Gen9, BIOS P89 10/21/2019 Call Trace: <TASK> dump_stack_lvl+0x76/0xa0 dump_stack+0x10/0x20 __ubsan_handle_out_of_bounds+0xcb/0x110 bnx2x_prep_fw_stats_req+0x2e1/0x310 [bnx2x] bnx2x_stats_init+0x156/0x320 [bnx2x] bnx2x_post_irq_nic_init+0x81/0x1a0 [bnx2x] bnx2x_nic_load+0x8e8/0x19e0 [bnx2x] bnx2x_open+0x16b/0x290 [bnx2x] __dev_open+0x10e/0x1d0 RIP: 0033:0x736223927a0a Code: d8 64 89 02 48 c7 c0 ff ff ff ff eb b8 0f 1f 00 f3 0f 1e fa 41 89 ca 64 8b 04 25 18 00 00 00 85 c0 75 15 b8 2c 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 7e c3 0f 1f 44 00 00 41 54 48 83 ec 30 44 89 RSP: 002b:00007ffc0bb2ada8 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 0000583df50f9c78 RCX: 0000736223927a0a RDX: 0000000000000020 RSI: 0000583df50ee510 RDI: 0000000000000003 RBP: 0000583df50d4940 R08: 00007ffc0bb2adb0 R09: 0000000000000080 R10: 0000000000000000 R11: 0000000000000246 R12: 0000583df5103ae0 R13: 000000000000035a R14: 0000583df50f9c30 R15: 0000583ddddddf00 </TASK> ---[ end trace ]--- ------------[ cut here ]------------ UBSAN: array-index-out-of-bounds in drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c:1546:11 index 28 is out of range for type 'stats_query_entry [19]' CPU: 12 PID: 858 Comm: systemd-network Not tainted 6.9.0-060900rc7-generic #202405052133 Hardware name: HP ProLiant DL360 Gen9/ProLiant DL360 Gen9, BIOS P89 10/21/2019 Call Trace: <TASK> dump_stack_lvl+0x76/0xa0 dump_stack+0x10/0x20 __ubsan_handle_out_of_bounds+0xcb/0x110 bnx2x_prep_fw_stats_req+0x2fd/0x310 [bnx2x] bnx2x_stats_init+0x156/0x320 [bnx2x] bnx2x_post_irq_nic_init+0x81/0x1a0 [bnx2x] bnx2x_nic_load+0x8e8/0x19e0 [bnx2x] bnx2x_open+0x16b/0x290 [bnx2x] __dev_open+0x10e/0x1d0 RIP: 0033:0x736223927a0a Code: d8 64 89 02 48 c7 c0 ff ff ff ff eb b8 0f 1f 00 f3 0f 1e fa 41 89 ca 64 8b 04 25 18 00 00 00 85 c0 75 15 b8 2c 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 7e c3 0f 1f 44 00 00 41 54 48 83 ec 30 44 89 RSP: 002b:00007ffc0bb2ada8 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 0000583df50f9c78 RCX: 0000736223927a0a RDX: 0000000000000020 RSI: 0000583df50ee510 RDI: 0000000000000003 RBP: 0000583df50d4940 R08: 00007ffc0bb2adb0 R09: 0000000000000080 R10: 0000000000000000 R11: 0000000000000246 R12: 0000583df5103ae0 R13: 000000000000035a R14: 0000583df50f9c30 R15: 0000583ddddddf00 </TASK> ---[ end trace ]--- ------------[ cut here ]------------ UBSAN: array-index-out-of-bounds in drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c:1895:8 index 29 is out of range for type 'stats_query_entry [19]' CPU: 13 PID: 163 Comm: kworker/u96:1 Not tainted 6.9.0-060900rc7-generic #202405052133 Hardware name: HP ProLiant DL360 Gen9/ProLiant DL360 Gen9, BIOS P89 10/21/2019 Workqueue: bnx2x bnx2x_sp_task [bnx2x] Call Trace: <TASK> dump_stack_lvl+0x76/0xa0 dump_stack+0x10/0x20 __ubsan_handle_out_of_bounds+0xcb/0x110 bnx2x_iov_adjust_stats_req+0x3c4/0x3d0 [bnx2x] bnx2x_storm_stats_post.part.0+0x4a/0x330 [bnx2x] ? bnx2x_hw_stats_post+0x231/0x250 [bnx2x] bnx2x_stats_start+0x44/0x70 [bnx2x] bnx2x_stats_handle+0x149/0x350 [bnx2x] bnx2x_attn_int_asserted+0x998/0x9b0 [bnx2x] bnx2x_sp_task+0x491/0x5c0 [bnx2x] process_one_work+0x18d/0x3f0 </TASK> ---[ end trace ]---

Fixes: 50f0a562f8cc ("bnx2x: add fcoe statistics") Signed-off-by: Ghadi Elie Rahme ghadi.rahme@canonical.com Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20240627111405.1037812-1-ghadi.rahme@canonical.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/broadcom/bnx2x/bnx2x.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h @@ -1256,7 +1256,7 @@ enum {

struct bnx2x_fw_stats_req { struct stats_query_header hdr; - struct stats_query_entry query[FP_SB_MAX_E1x+ + struct stats_query_entry query[FP_SB_MAX_E2 + BNX2X_FIRST_QUEUE_QUERY_IDX]; };

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Piotr Wojtaszczyk piotr.wojtaszczyk@timesys.com

[ Upstream commit f63b94be6942ba82c55343e196bd09b53227618e ]

When del_timer_sync() is called in an interrupt context it throws a warning because of potential deadlock. The timer is used only to exit from wait_for_completion() after a timeout so replacing the call with wait_for_completion_timeout() allows to remove the problematic timer and its related functions altogether.

Fixes: 41561f28e76a ("i2c: New Philips PNX bus driver") Signed-off-by: Piotr Wojtaszczyk piotr.wojtaszczyk@timesys.com Signed-off-by: Andi Shyti andi.shyti@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/i2c/busses/i2c-pnx.c | 48 ++++++++---------------------------- 1 file changed, 10 insertions(+), 38 deletions(-)

diff --git a/drivers/i2c/busses/i2c-pnx.c b/drivers/i2c/busses/i2c-pnx.c index 6e0e546ef83fc..4d09665a72e59 100644 --- a/drivers/i2c/busses/i2c-pnx.c +++ b/drivers/i2c/busses/i2c-pnx.c @@ -15,7 +15,6 @@ #include <linux/ioport.h> #include <linux/delay.h> #include <linux/i2c.h> -#include <linux/timer.h> #include <linux/completion.h> #include <linux/platform_device.h> #include <linux/io.h> @@ -32,7 +31,6 @@ struct i2c_pnx_mif { int ret; /* Return value */ int mode; /* Interface mode */ struct completion complete; /* I/O completion */ - struct timer_list timer; /* Timeout */ u8 * buf; /* Data buffer */ int len; /* Length of data buffer */ int order; /* RX Bytes to order via TX */ @@ -117,24 +115,6 @@ static inline int wait_reset(struct i2c_pnx_algo_data *data) return (timeout <= 0); }

-static inline void i2c_pnx_arm_timer(struct i2c_pnx_algo_data *alg_data) -{ - struct timer_list *timer = &alg_data->mif.timer; - unsigned long expires = msecs_to_jiffies(alg_data->timeout); - - if (expires <= 1) - expires = 2; - - del_timer_sync(timer); - - dev_dbg(&alg_data->adapter.dev, "Timer armed at %lu plus %lu jiffies.\n", - jiffies, expires); - - timer->expires = jiffies + expires; - - add_timer(timer); -} - /** * i2c_pnx_start - start a device * @slave_addr: slave address @@ -259,8 +239,6 @@ static int i2c_pnx_master_xmit(struct i2c_pnx_algo_data *alg_data) ~(mcntrl_afie | mcntrl_naie | mcntrl_drmie), I2C_REG_CTL(alg_data));

- del_timer_sync(&alg_data->mif.timer); - dev_dbg(&alg_data->adapter.dev, "%s(): Waking up xfer routine.\n", __func__); @@ -276,8 +254,6 @@ static int i2c_pnx_master_xmit(struct i2c_pnx_algo_data *alg_data) ~(mcntrl_afie | mcntrl_naie | mcntrl_drmie), I2C_REG_CTL(alg_data));

- /* Stop timer. */ - del_timer_sync(&alg_data->mif.timer); dev_dbg(&alg_data->adapter.dev, "%s(): Waking up xfer routine after zero-xfer.\n", __func__); @@ -364,8 +340,6 @@ static int i2c_pnx_master_rcv(struct i2c_pnx_algo_data *alg_data) mcntrl_drmie | mcntrl_daie); iowrite32(ctl, I2C_REG_CTL(alg_data));

- /* Kill timer. */ - del_timer_sync(&alg_data->mif.timer); complete(&alg_data->mif.complete); } } @@ -400,8 +374,6 @@ static irqreturn_t i2c_pnx_interrupt(int irq, void *dev_id) mcntrl_drmie); iowrite32(ctl, I2C_REG_CTL(alg_data));

- /* Stop timer, to prevent timeout. */ - del_timer_sync(&alg_data->mif.timer); complete(&alg_data->mif.complete); } else if (stat & mstatus_nai) { /* Slave did not acknowledge, generate a STOP */ @@ -419,8 +391,6 @@ static irqreturn_t i2c_pnx_interrupt(int irq, void *dev_id) /* Our return value. */ alg_data->mif.ret = -EIO;

- /* Stop timer, to prevent timeout. */ - del_timer_sync(&alg_data->mif.timer); complete(&alg_data->mif.complete); } else { /* @@ -453,9 +423,8 @@ static irqreturn_t i2c_pnx_interrupt(int irq, void *dev_id) return IRQ_HANDLED; }

-static void i2c_pnx_timeout(struct timer_list *t) +static void i2c_pnx_timeout(struct i2c_pnx_algo_data *alg_data) { - struct i2c_pnx_algo_data *alg_data = from_timer(alg_data, t, mif.timer); u32 ctl;

dev_err(&alg_data->adapter.dev, @@ -472,7 +441,6 @@ static void i2c_pnx_timeout(struct timer_list *t) iowrite32(ctl, I2C_REG_CTL(alg_data)); wait_reset(alg_data); alg_data->mif.ret = -EIO; - complete(&alg_data->mif.complete); }

static inline void bus_reset_if_active(struct i2c_pnx_algo_data *alg_data) @@ -514,6 +482,7 @@ i2c_pnx_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) struct i2c_msg *pmsg; int rc = 0, completed = 0, i; struct i2c_pnx_algo_data *alg_data = adap->algo_data; + unsigned long time_left; u32 stat;

dev_dbg(&alg_data->adapter.dev, @@ -548,7 +517,6 @@ i2c_pnx_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) dev_dbg(&alg_data->adapter.dev, "%s(): mode %d, %d bytes\n", __func__, alg_data->mif.mode, alg_data->mif.len);

- i2c_pnx_arm_timer(alg_data);

/* initialize the completion var */ init_completion(&alg_data->mif.complete); @@ -564,7 +532,10 @@ i2c_pnx_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) break;

/* Wait for completion */ - wait_for_completion(&alg_data->mif.complete); + time_left = wait_for_completion_timeout(&alg_data->mif.complete, + alg_data->timeout); + if (time_left == 0) + i2c_pnx_timeout(alg_data);

if (!(rc = alg_data->mif.ret)) completed++; @@ -657,7 +628,10 @@ static int i2c_pnx_probe(struct platform_device *pdev) alg_data->adapter.algo_data = alg_data; alg_data->adapter.nr = pdev->id;

- alg_data->timeout = I2C_PNX_TIMEOUT_DEFAULT; + alg_data->timeout = msecs_to_jiffies(I2C_PNX_TIMEOUT_DEFAULT); + if (alg_data->timeout <= 1) + alg_data->timeout = 2; + #ifdef CONFIG_OF alg_data->adapter.dev.of_node = of_node_get(pdev->dev.of_node); if (pdev->dev.of_node) { @@ -677,8 +651,6 @@ static int i2c_pnx_probe(struct platform_device *pdev) if (IS_ERR(alg_data->clk)) return PTR_ERR(alg_data->clk);

- timer_setup(&alg_data->mif.timer, i2c_pnx_timeout, 0); - snprintf(alg_data->adapter.name, sizeof(alg_data->adapter.name), "%s", pdev->name);

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Nilay Shroff nilay@linux.ibm.com

[ Upstream commit d3a043733f25d743f3aa617c7f82dbcb5ee2211a ]

In current native multipath design when a shared namespace is created, we loop through each possible numa-node, calculate the NUMA distance of that node from each nvme controller and then cache the optimal IO path for future reference while sending IO. The issue with this design is that we may refer to the NUMA distance table for an offline node which may not be populated at the time and so we may inadvertently end up finding and caching a non-optimal path for IO. Then latter when the corresponding numa-node becomes online and hence the NUMA distance table entry for that node is created, ideally we should re-calculate the multipath node distance for the newly added node however that doesn't happen unless we rescan/reset the controller. So essentially, we may keep using non-optimal IO path for a node which is made online after namespace is created. This patch helps fix this issue ensuring that when a shared namespace is created, we calculate the multipath node distance for each online numa-node instead of each possible numa-node. Then latter when a node becomes online and we receive any IO on that newly added node, we would calculate the multipath node distance for newly added node but this time NUMA distance table would have been already populated for newly added node. Hence we would be able to correctly calculate the multipath node distance and choose the optimal path for the IO.

Signed-off-by: Nilay Shroff nilay@linux.ibm.com Reviewed-by: Christoph Hellwig hch@lst.de Signed-off-by: Keith Busch kbusch@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/host/multipath.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 4f3220aef7c47..36d63da71b2f9 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -437,7 +437,7 @@ static void nvme_mpath_set_live(struct nvme_ns *ns) int node, srcu_idx;

srcu_idx = srcu_read_lock(&head->srcu); - for_each_node(node) + for_each_online_node(node) __nvme_find_path(head, node); srcu_read_unlock(&head->srcu, srcu_idx); }

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jeff Layton jlayton@kernel.org

[ Upstream commit 1b3ec4f7c03d4b07bad70697d7e2f4088d2cfe92 ]

Light Hsieh reported a KASAN UAF warning in trace_posix_lock_inode(). The request pointer had been changed earlier to point to a lock entry that was added to the inode's list. However, before the tracepoint could fire, another task raced in and freed that lock.

Fix this by moving the tracepoint inside the spinlock, which should ensure that this doesn't happen.

Fixes: 74f6f5912693 ("locks: fix KASAN: use-after-free in trace_event_raw_event_filelock_lock") Link: https://lore.kernel.org/linux-fsdevel/724ffb0a2962e912ea62bb0515deadf39c3251... Reported-by: Light Hsieh (謝明燈) Light.Hsieh@mediatek.com Signed-off-by: Jeff Layton jlayton@kernel.org Link: https://lore.kernel.org/r/20240702-filelock-6-10-v1-1-96e766aadc98@kernel.or... Reviewed-by: Alexander Aring aahringo@redhat.com Signed-off-by: Christian Brauner brauner@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/locks.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/locks.c b/fs/locks.c index 90f92784aa554..bafe11deea56b 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1336,9 +1336,9 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, locks_wake_up_blocks(left); } out: + trace_posix_lock_inode(inode, request, error); spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); - trace_posix_lock_inode(inode, request, error); /* * Free any unused locks. */

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Brian Foster bfoster@redhat.com

[ Upstream commit aabfe57ebaa75841db47ea59091ec3c5a06d2f52 ]

The nr_dentry_negative counter is intended to only account negative dentries that are present on the superblock LRU. Therefore, the LRU add, remove and isolate helpers modify the counter based on whether the dentry is negative, but the shrinker list related helpers do not modify the counter, and the paths that change a dentry between positive and negative only do so if DCACHE_LRU_LIST is set.

The problem with this is that a dentry on a shrinker list still has DCACHE_LRU_LIST set to indicate ->d_lru is in use. The additional DCACHE_SHRINK_LIST flag denotes whether the dentry is on LRU or a shrink related list. Therefore if a relevant operation (i.e. unlink) occurs while a dentry is present on a shrinker list, and the associated codepath only checks for DCACHE_LRU_LIST, then it is technically possible to modify the negative dentry count for a dentry that is off the LRU. Since the shrinker list related helpers do not modify the negative dentry count (because non-LRU dentries should not be included in the count) when the dentry is ultimately removed from the shrinker list, this can cause the negative dentry count to become permanently inaccurate.

This problem can be reproduced via a heavy file create/unlink vs. drop_caches workload. On an 80xcpu system, I start 80 tasks each running a 1k file create/delete loop, and one task spinning on drop_caches. After 10 minutes or so of runtime, the idle/clean cache negative dentry count increases from somewhere in the range of 5-10 entries to several hundred (and increasingly grows beyond nr_dentry_unused).

Tweak the logic in the paths that turn a dentry negative or positive to filter out the case where the dentry is present on a shrink related list. This allows the above workload to maintain an accurate negative dentry count.

Fixes: af0c9af1b3f6 ("fs/dcache: Track & report number of negative dentries") Signed-off-by: Brian Foster bfoster@redhat.com Link: https://lore.kernel.org/r/20240703121301.247680-1-bfoster@redhat.com Acked-by: Ian Kent ikent@redhat.com Reviewed-by: Josef Bacik josef@toxicpanda.com Reviewed-by: Waiman Long longman@redhat.com Signed-off-by: Christian Brauner brauner@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/dcache.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/fs/dcache.c b/fs/dcache.c index 9505e5df30b74..c58b5e5cb045d 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -329,7 +329,11 @@ static inline void __d_clear_type_and_inode(struct dentry *dentry) flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU); WRITE_ONCE(dentry->d_flags, flags); dentry->d_inode = NULL; - if (flags & DCACHE_LRU_LIST) + /* + * The negative counter only tracks dentries on the LRU. Don't inc if + * d_lru is on another list. + */ + if ((flags & (DCACHE_LRU_LIST|DCACHE_SHRINK_LIST)) == DCACHE_LRU_LIST) this_cpu_inc(nr_dentry_negative); }

@@ -1921,9 +1925,11 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode)

spin_lock(&dentry->d_lock); /* - * Decrement negative dentry count if it was in the LRU list. + * The negative counter only tracks dentries on the LRU. Don't dec if + * d_lru is on another list. */ - if (dentry->d_flags & DCACHE_LRU_LIST) + if ((dentry->d_flags & + (DCACHE_LRU_LIST|DCACHE_SHRINK_LIST)) == DCACHE_LRU_LIST) this_cpu_dec(nr_dentry_negative); hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); raw_write_seqcount_begin(&dentry->d_seq);

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Neal Cardwell ncardwell@google.com

[ Upstream commit 0ec986ed7bab6801faed1440e8839dcc710331ff ]

Loss recovery undo_retrans bookkeeping had a long-standing bug where a DSACK from a spurious TLP retransmit packet could cause an erroneous undo of a fast recovery or RTO recovery that repaired a single really-lost packet (in a sequence range outside that of the TLP retransmit). Basically, because the loss recovery state machine didn't account for the fact that it sent a TLP retransmit, the DSACK for the TLP retransmit could erroneously be implicitly be interpreted as corresponding to the normal fast recovery or RTO recovery retransmit that plugged a real hole, thus resulting in an improper undo.

For example, consider the following buggy scenario where there is a real packet loss but the congestion control response is improperly undone because of this bug:

+ send packets P1, P2, P3, P4 + P1 is really lost + send TLP retransmit of P4 + receive SACK for original P2, P3, P4 + enter fast recovery, fast-retransmit P1, increment undo_retrans to 1 + receive DSACK for TLP P4, decrement undo_retrans to 0, undo (bug!) + receive cumulative ACK for P1-P4 (fast retransmit plugged real hole)

The fix: when we initialize undo machinery in tcp_init_undo(), if there is a TLP retransmit in flight, then increment tp->undo_retrans so that we make sure that we receive a DSACK corresponding to the TLP retransmit, as well as DSACKs for all later normal retransmits, before triggering a loss recovery undo. Note that we also have to move the line that clears tp->tlp_high_seq for RTO recovery, so that upon RTO we remember the tp->tlp_high_seq value until tcp_init_undo() and clear it only afterward.

Also note that the bug dates back to the original 2013 TLP implementation, commit 6ba8a3b19e76 ("tcp: Tail loss probe (TLP)").

However, this patch will only compile and work correctly with kernels that have tp->tlp_retrans, which was added only in v5.8 in 2020 in commit 76be93fc0702 ("tcp: allow at most one TLP probe per flight"). So we associate this fix with that later commit.

Fixes: 76be93fc0702 ("tcp: allow at most one TLP probe per flight") Signed-off-by: Neal Cardwell ncardwell@google.com Reviewed-by: Eric Dumazet edumazet@google.com Cc: Yuchung Cheng ycheng@google.com Cc: Kevin Yang yyd@google.com Link: https://patch.msgid.link/20240703171246.1739561-1-ncardwell.sw@gmail.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/tcp_input.c | 11 ++++++++++- net/ipv4/tcp_timer.c | 2 -- 2 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 57907fe94b238..cf6221e9fda50 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1956,8 +1956,16 @@ void tcp_clear_retrans(struct tcp_sock *tp) static inline void tcp_init_undo(struct tcp_sock *tp) { tp->undo_marker = tp->snd_una; + /* Retransmission still in flight may cause DSACKs later. */ - tp->undo_retrans = tp->retrans_out ? : -1; + /* First, account for regular retransmits in flight: */ + tp->undo_retrans = tp->retrans_out; + /* Next, account for TLP retransmits in flight: */ + if (tp->tlp_high_seq && tp->tlp_retrans) + tp->undo_retrans++; + /* Finally, avoid 0, because undo_retrans==0 means "can undo now": */ + if (!tp->undo_retrans) + tp->undo_retrans = -1; }

static bool tcp_is_rack(const struct sock *sk) @@ -2036,6 +2044,7 @@ void tcp_enter_loss(struct sock *sk)

tcp_set_ca_state(sk, TCP_CA_Loss); tp->high_seq = tp->snd_nxt; + tp->tlp_high_seq = 0; tcp_ecn_queue_cwr(tp);

/* F-RTO RFC5682 sec 3.1 step 1: retransmit SND.UNA if no previous diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 551c4a78f68d4..e20fced3c9cf6 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -467,8 +467,6 @@ void tcp_retransmit_timer(struct sock *sk) if (!tp->packets_out || WARN_ON_ONCE(tcp_rtx_queue_empty(sk))) return;

- tp->tlp_high_seq = 0; - if (!tp->snd_wnd && !sock_flag(sk, SOCK_DEAD) && !((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))) { /* Receiver dastardly shrinks window. Our retransmits

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Aleksander Jan Bajkowski olek2@wp.pl

[ Upstream commit 4c46625bb586a741b8d0e6bdbddbcb2549fa1d36 ]

This patch adds a missing line after the declaration and fixes the checkpatch warning:

WARNING: Missing a blank line after declarations + int desc; + for (desc = 0; desc < LTQ_DESC_NUM; desc++)

Signed-off-by: Aleksander Jan Bajkowski olek2@wp.pl Link: https://lore.kernel.org/r/20211228220031.71576-1-olek2@wp.pl Signed-off-by: Jakub Kicinski kuba@kernel.org Stable-dep-of: e1533b6319ab ("net: ethernet: lantiq_etop: fix double free in detach") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/lantiq_etop.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c index 12e8b0f957d3d..98aa172da051f 100644 --- a/drivers/net/ethernet/lantiq_etop.c +++ b/drivers/net/ethernet/lantiq_etop.c @@ -214,6 +214,7 @@ ltq_etop_free_channel(struct net_device *dev, struct ltq_etop_chan *ch) free_irq(ch->dma.irq, priv); if (IS_RX(ch->idx)) { int desc; + for (desc = 0; desc < LTQ_DESC_NUM; desc++) dev_kfree_skb_any(ch->skb[ch->dma.desc]); }

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Dmitry Antipov dmantipov@yandex.ru

[ Upstream commit f2aeb7306a898e1cbd03963d376f4b6656ca2b55 ]

Since 'ppp_async_encode()' assumes valid LCP packets (with code from 1 to 7 inclusive), add 'ppp_check_packet()' to ensure that LCP packet has an actual body beyond PPP_LCP header bytes, and reject claimed-as-LCP but actually malformed data otherwise.

Reported-by: syzbot+ec0723ba9605678b14bf@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=ec0723ba9605678b14bf Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Dmitry Antipov dmantipov@yandex.ru Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ppp/ppp_generic.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+)

diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 078c0f474f966..3cd4196b36b21 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -70,6 +70,7 @@ #define MPHDRLEN_SSN 4 /* ditto with short sequence numbers */

#define PPP_PROTO_LEN 2 +#define PPP_LCP_HDRLEN 4

/* * An instance of /dev/ppp can be associated with either a ppp @@ -491,6 +492,15 @@ static ssize_t ppp_read(struct file *file, char __user *buf, return ret; }

+static bool ppp_check_packet(struct sk_buff *skb, size_t count) +{ + /* LCP packets must include LCP header which 4 bytes long: + * 1-byte code, 1-byte identifier, and 2-byte length. + */ + return get_unaligned_be16(skb->data) != PPP_LCP || + count >= PPP_PROTO_LEN + PPP_LCP_HDRLEN; +} + static ssize_t ppp_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { @@ -513,6 +523,11 @@ static ssize_t ppp_write(struct file *file, const char __user *buf, kfree_skb(skb); goto out; } + ret = -EINVAL; + if (unlikely(!ppp_check_packet(skb, count))) { + kfree_skb(skb); + goto out; + }

switch (pf->kind) { case INTERFACE:

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sven Schnelle svens@linux.ibm.com

[ Upstream commit 7278a8fb8d032dfdc03d9b5d17e0bc451cdc1492 ]

Without __unitialized, the following code is generated when INIT_STACK_ALL_ZERO is enabled:

86: d7 0f f0 a0 f0 a0 xc 160(16,%r15), 160(%r15) 8c: e3 40 f0 a0 00 24 stg %r4, 160(%r15) 92: c0 10 00 00 00 08 larl %r1, 0xa2 98: e3 10 f0 a8 00 24 stg %r1, 168(%r15) 9e: b2 b2 f0 a0 lpswe 160(%r15)

The xc is not adding any security because psw is fully initialized with the following instructions. Add __unitialized to the psw definitiation to avoid the superfluous clearing of psw.

Reviewed-by: Heiko Carstens hca@linux.ibm.com Signed-off-by: Sven Schnelle svens@linux.ibm.com Signed-off-by: Alexander Gordeev agordeev@linux.ibm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/s390/include/asm/processor.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 48d6ccdef5f77..00bb2d287f740 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -256,8 +256,8 @@ static inline void __load_psw(psw_t psw) */ static __always_inline void __load_psw_mask(unsigned long mask) { + psw_t psw __uninitialized; unsigned long addr; - psw_t psw;

psw.mask = mask;

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Michal Mazur mmazur2@marvell.com

[ Upstream commit 404dc0fd6fb0bb942b18008c6f8c0320b80aca20 ]

Checksum and length checks are not enabled for IPv4 header with options and IPv6 with extension headers. To fix this a change in enum npc_kpu_lc_ltype is required which will allow adjustment of LTYPE_MASK to detect all types of IP headers.

Fixes: 21e6699e5cd6 ("octeontx2-af: Add NPC KPU profile") Signed-off-by: Michal Mazur mmazur2@marvell.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/marvell/octeontx2/af/npc.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc.h b/drivers/net/ethernet/marvell/octeontx2/af/npc.h index 5d4df315a0e19..86d5bda2c0bff 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/npc.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/npc.h @@ -38,14 +38,18 @@ enum npc_kpu_lb_ltype { NPC_LT_LB_ITAG, };

+/* Don't modify ltypes up to IP6_EXT, otherwise length and checksum of IP + * headers may not be checked correctly. IPv4 ltypes and IPv6 ltypes must + * differ only at bit 0 so mask 0xE can be used to detect extended headers. + */ enum npc_kpu_lc_ltype { - NPC_LT_LC_IP = 1, + NPC_LT_LC_PTP = 1, + NPC_LT_LC_IP, NPC_LT_LC_IP6, NPC_LT_LC_ARP, NPC_LT_LC_RARP, NPC_LT_LC_MPLS, NPC_LT_LC_NSH, - NPC_LT_LC_PTP, NPC_LT_LC_FCOE, };

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Daniele Palmas dnlplm@gmail.com

commit 9a590ff283421b71560deded2110dbdcbe1f7d1d upstream.

Add the following Telit FN912 compositions:

0x3000: rmnet + tty (AT/NMEA) + tty (AT) + tty (diag) T: Bus=03 Lev=01 Prnt=03 Port=07 Cnt=01 Dev#= 8 Spd=480 MxCh= 0 D: Ver= 2.01 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1 P: Vendor=1bc7 ProdID=3000 Rev=05.15 S: Manufacturer=Telit Cinterion S: Product=FN912 S: SerialNumber=92c4c4d8 C: #Ifs= 4 Cfg#= 1 Atr=e0 MxPwr=500mA I: If#= 0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=50 Driver=qmi_wwan E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=82(I) Atr=03(Int.) MxPS= 8 Ivl=32ms I: If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=60 Driver=option E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=84(I) Atr=03(Int.) MxPS= 10 Ivl=32ms I: If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=86(I) Atr=03(Int.) MxPS= 10 Ivl=32ms I: If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=87(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms

0x3001: rmnet + tty (AT) + tty (diag) + DPL (data packet logging) + adb T: Bus=03 Lev=01 Prnt=03 Port=07 Cnt=01 Dev#= 7 Spd=480 MxCh= 0 D: Ver= 2.01 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1 P: Vendor=1bc7 ProdID=3001 Rev=05.15 S: Manufacturer=Telit Cinterion S: Product=FN912 S: SerialNumber=92c4c4d8 C: #Ifs= 5 Cfg#= 1 Atr=e0 MxPwr=500mA I: If#= 0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=50 Driver=qmi_wwan E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=82(I) Atr=03(Int.) MxPS= 8 Ivl=32ms I: If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=84(I) Atr=03(Int.) MxPS= 10 Ivl=32ms I: If#= 2 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms I: If#= 3 Alt= 0 #EPs= 1 Cls=ff(vend.) Sub=ff Prot=80 Driver=(none) E: Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms I: If#= 4 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=usbfs E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=87(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms

Signed-off-by: Daniele Palmas dnlplm@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold johan@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/serial/option.c | 4 ++++ 1 file changed, 4 insertions(+)

--- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1425,6 +1425,10 @@ static const struct usb_device_id option .driver_info = NCTRL(0) | RSVD(1) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1901, 0xff), /* Telit LN940 (MBIM) */ .driver_info = NCTRL(0) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x3000, 0xff), /* Telit FN912 */ + .driver_info = RSVD(0) | NCTRL(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x3001, 0xff), /* Telit FN912 */ + .driver_info = RSVD(0) | NCTRL(2) | RSVD(3) | RSVD(4) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x7010, 0xff), /* Telit LE910-S1 (RNDIS) */ .driver_info = NCTRL(2) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x7011, 0xff), /* Telit LE910-S1 (ECM) */

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Slark Xiao slark_xiao@163.com

commit 3c841d54b63e4446383de3238399a3910e47d8e2 upstream.

T99W651 is a RNDIS based modem device. There are 3 serial ports need to be enumerated: Diag, NMEA and AT.

Test evidence as below: T: Bus=01 Lev=02 Prnt=02 Port=00 Cnt=01 Dev#= 6 Spd=480 MxCh= 0 D: Ver= 2.10 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=0489 ProdID=e145 Rev=05.15 S: Manufacturer=QCOM S: Product=SDXPINN-IDP _SN:93B562B2 S: SerialNumber=82e6fe26 C: #Ifs= 7 Cfg#= 1 Atr=a0 MxPwr=500mA I: If#=0x0 Alt= 0 #EPs= 1 Cls=ef(misc ) Sub=04 Prot=01 Driver=rndis_host I: If#=0x1 Alt= 0 #EPs= 2 Cls=0a(data ) Sub=00 Prot=00 Driver=rndis_host I: If#=0x2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option I: If#=0x3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option I: If#=0x4 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option I: If#=0x5 Alt= 0 #EPs= 1 Cls=ff(vend.) Sub=ff Prot=70 Driver=(none) I: If#=0x6 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=(none)

0&1: RNDIS, 2:AT, 3:NMEA, 4:DIAG, 5:QDSS, 6:ADB QDSS is not a serial port.

Signed-off-by: Slark Xiao slark_xiao@163.com Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold johan@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/serial/option.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -2294,6 +2294,8 @@ static const struct usb_device_id option .driver_info = RSVD(3) }, { USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe0f0, 0xff), /* Foxconn T99W373 MBIM */ .driver_info = RSVD(3) }, + { USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe145, 0xff), /* Foxconn T99W651 RNDIS */ + .driver_info = RSVD(5) | RSVD(6) }, { USB_DEVICE(0x1508, 0x1001), /* Fibocom NL668 (IOT version) */ .driver_info = RSVD(4) | RSVD(5) | RSVD(6) }, { USB_DEVICE(0x1782, 0x4d10) }, /* Fibocom L610 (AT mode) */

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Vanillan Wang vanillanwang@163.com

commit ae420771551bd9f04347c59744dd062332bdec3e upstream.

Update the USB serial option driver support for the Rolling RW350-GL - VID:PID 33f8:0802, RW350-GL are laptop M.2 cards (with MBIM interfaces for /Linux/Chrome OS)

Here are the outputs of usb-devices:

usbmode=63: mbim, pipe

T: Bus=02 Lev=01 Prnt=01 Port=02 Cnt=01 Dev#= 2 Spd=5000 MxCh= 0 D: Ver= 3.00 Cls=ef(misc ) Sub=02 Prot=01 MxPS= 9 #Cfgs= 1 P: Vendor=33f8 ProdID=0802 Rev=00.01 S: Manufacturer=Rolling Wireless S.a.r.l. S: Product=USB DATA CARD C: #Ifs= 3 Cfg#= 1 Atr=a0 MxPwr=896mA I: If#= 0 Alt= 0 #EPs= 1 Cls=02(commc) Sub=0e Prot=00 Driver=cdc_mbim E: Ad=82(I) Atr=03(Int.) MxPS= 64 Ivl=32ms I: If#= 1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim E: Ad=01(O) Atr=02(Bulk) MxPS=1024 Ivl=0ms E: Ad=81(I) Atr=02(Bulk) MxPS=1024 Ivl=0ms I: If#= 2 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=02(O) Atr=02(Bulk) MxPS=1024 Ivl=0ms E: Ad=83(I) Atr=02(Bulk) MxPS=1024 Ivl=0ms

usbmode=64: mbim, others at (If#= 5 adb)

MBIM(MI0) + GNSS(MI2) + AP log(MI3) + AP META(MI4) + ADB(MI5) + MD AT(MI6) + MD META(MI7) + NPT(MI8) + Debug(MI9)

T: Bus=02 Lev=01 Prnt=01 Port=02 Cnt=01 Dev#= 5 Spd=5000 MxCh= 0 D: Ver= 3.00 Cls=ef(misc ) Sub=02 Prot=01 MxPS= 9 #Cfgs= 1 P: Vendor=33f8 ProdID=0802 Rev=00.01 S: Manufacturer=Rolling Wireless S.a.r.l. S: Product=USB DATA CARD C: #Ifs=10 Cfg#= 1 Atr=a0 MxPwr=896mA I: If#= 0 Alt= 0 #EPs= 1 Cls=02(commc) Sub=0e Prot=00 Driver=cdc_mbim E: Ad=82(I) Atr=03(Int.) MxPS= 64 Ivl=32ms I: If#= 1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim E: Ad=01(O) Atr=02(Bulk) MxPS=1024 Ivl=0ms E: Ad=81(I) Atr=02(Bulk) MxPS=1024 Ivl=0ms I: If#= 2 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=02(O) Atr=02(Bulk) MxPS=1024 Ivl=0ms E: Ad=83(I) Atr=02(Bulk) MxPS=1024 Ivl=0ms I: If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=03(O) Atr=02(Bulk) MxPS=1024 Ivl=0ms E: Ad=84(I) Atr=02(Bulk) MxPS=1024 Ivl=0ms I: If#= 4 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=04(O) Atr=02(Bulk) MxPS=1024 Ivl=0ms E: Ad=85(I) Atr=02(Bulk) MxPS=1024 Ivl=0ms I: If#= 5 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=usbfs E: Ad=05(O) Atr=02(Bulk) MxPS=1024 Ivl=0ms E: Ad=86(I) Atr=02(Bulk) MxPS=1024 Ivl=0ms I: If#= 6 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=06(O) Atr=02(Bulk) MxPS=1024 Ivl=0ms E: Ad=87(I) Atr=02(Bulk) MxPS=1024 Ivl=0ms I: If#= 7 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=07(O) Atr=02(Bulk) MxPS=1024 Ivl=0ms E: Ad=88(I) Atr=02(Bulk) MxPS=1024 Ivl=0ms I: If#= 8 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=08(O) Atr=02(Bulk) MxPS=1024 Ivl=0ms E: Ad=89(I) Atr=02(Bulk) MxPS=1024 Ivl=0ms I: If#= 9 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=09(O) Atr=02(Bulk) MxPS=1024 Ivl=0ms E: Ad=8a(I) Atr=02(Bulk) MxPS=1024 Ivl=0ms

Signed-off-by: Vanillan Wang vanillanwang@163.com Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold johan@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/serial/option.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -2333,6 +2333,8 @@ static const struct usb_device_id option .driver_info = RSVD(4) }, { USB_DEVICE_INTERFACE_CLASS(0x33f8, 0x0115, 0xff), /* Rolling RW135-GL (laptop MBIM) */ .driver_info = RSVD(5) }, + { USB_DEVICE_INTERFACE_CLASS(0x33f8, 0x0802, 0xff), /* Rolling RW350-GL (laptop MBIM) */ + .driver_info = RSVD(5) }, { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x0100, 0xff, 0xff, 0x30) }, /* NetPrisma LCUK54-WWD for Global */ { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x0100, 0xff, 0x00, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x0100, 0xff, 0xff, 0x40) },

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Lee Jones lee@kernel.org

commit 6d3c721e686ea6c59e18289b400cc95c76e927e0 upstream.

Userspace provided string 's' could trivially have the length zero. Left unchecked this will firstly result in an OOB read in the form `if (str[0 - 1] == '\n') followed closely by an OOB write in the form `str[0 - 1] = '\0'`.

There is already a validating check to catch strings that are too long. Let's supply an additional check for invalid strings that are too short.

Signed-off-by: Lee Jones lee@kernel.org Cc: stable stable@kernel.org Link: https://lore.kernel.org/r/20240705074339.633717-1-lee@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/gadget/configfs.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/drivers/usb/gadget/configfs.c +++ b/drivers/usb/gadget/configfs.c @@ -116,9 +116,12 @@ static int usb_string_copy(const char *s int ret; char *str; char *copy = *s_copy; + ret = strlen(s); if (ret > USB_MAX_STRING_LEN) return -EOVERFLOW; + if (ret < 1) + return -EINVAL;

if (copy) { str = copy;

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: He Zhe zhe.he@windriver.com

commit 4e60131d0d36af65ab9c9144f4f163fe97ae36e8 upstream.

hpet_compat_ioctl and read file operations failed to handle parameters from 32-bit userspace and thus samples/timers/hpet_example.c fails as below.

root@intel-x86-64:~# ./hpet_example-32.out poll /dev/hpet 1 2 -hpet: executing poll hpet_poll: HPET_IRQFREQ failed

This patch fixes cmd and arg handling in hpet_compat_ioctl and adds compat handling for 32-bit userspace in hpet_read.

hpet_example now shows that it works for both 64-bit and 32-bit.

root@intel-x86-64:~# ./hpet_example-32.out poll /dev/hpet 1 2 -hpet: executing poll hpet_poll: info.hi_flags 0x0 hpet_poll: expired time = 0xf4298 hpet_poll: revents = 0x1 hpet_poll: data 0x1 hpet_poll: expired time = 0xf4235 hpet_poll: revents = 0x1 hpet_poll: data 0x1 root@intel-x86-64:~# ./hpet_example-64.out poll /dev/hpet 1 2 -hpet: executing poll hpet_poll: info.hi_flags 0x0 hpet_poll: expired time = 0xf42a1 hpet_poll: revents = 0x1 hpet_poll: data 0x1 hpet_poll: expired time = 0xf4232 hpet_poll: revents = 0x1 hpet_poll: data 0x1

Cc: stable@vger.kernel.org Signed-off-by: He Zhe zhe.he@windriver.com Fixes: 54066a57c584 ("hpet: kill BKL, add compat_ioctl") Reviewed-by: Arnd Bergmann arnd@arndb.de Link: https://lore.kernel.org/r/20240606123908.738733-1-zhe.he@windriver.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/char/hpet.c | 34 +++++++++++++++++++++++++++++----- 1 file changed, 29 insertions(+), 5 deletions(-)

--- a/drivers/char/hpet.c +++ b/drivers/char/hpet.c @@ -304,8 +304,13 @@ hpet_read(struct file *file, char __user if (!devp->hd_ireqfreq) return -EIO;

- if (count < sizeof(unsigned long)) - return -EINVAL; + if (in_compat_syscall()) { + if (count < sizeof(compat_ulong_t)) + return -EINVAL; + } else { + if (count < sizeof(unsigned long)) + return -EINVAL; + }

add_wait_queue(&devp->hd_waitqueue, &wait);

@@ -329,9 +334,16 @@ hpet_read(struct file *file, char __user schedule(); }

- retval = put_user(data, (unsigned long __user *)buf); - if (!retval) - retval = sizeof(unsigned long); + if (in_compat_syscall()) { + retval = put_user(data, (compat_ulong_t __user *)buf); + if (!retval) + retval = sizeof(compat_ulong_t); + } else { + retval = put_user(data, (unsigned long __user *)buf); + if (!retval) + retval = sizeof(unsigned long); + } + out: __set_current_state(TASK_RUNNING); remove_wait_queue(&devp->hd_waitqueue, &wait); @@ -686,12 +698,24 @@ struct compat_hpet_info { unsigned short hi_timer; };

+/* 32-bit types would lead to different command codes which should be + * translated into 64-bit ones before passed to hpet_ioctl_common + */ +#define COMPAT_HPET_INFO _IOR('h', 0x03, struct compat_hpet_info) +#define COMPAT_HPET_IRQFREQ _IOW('h', 0x6, compat_ulong_t) + static long hpet_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct hpet_info info; int err;

+ if (cmd == COMPAT_HPET_INFO) + cmd = HPET_INFO; + + if (cmd == COMPAT_HPET_IRQFREQ) + cmd = HPET_IRQFREQ; + mutex_lock(&hpet_mutex); err = hpet_ioctl_common(file->private_data, cmd, arg, &info); mutex_unlock(&hpet_mutex);

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Edson Juliano Drosdeck edson.drosdeck@gmail.com

commit 6db03b1929e207d2c6e84e75a9cd78124b3d6c6d upstream.

The internal mic boost on the VAIO models VJFE-CL and VJFE-IL is too high. Fix this by applying the ALC269_FIXUP_LIMIT_INT_MIC_BOOST fixup to the machine to limit the gain.

Signed-off-by: Edson Juliano Drosdeck edson.drosdeck@gmail.com Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20240705141012.5368-1-edson.drosdeck@gmail.com Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/pci/hda/patch_realtek.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -8331,6 +8331,7 @@ static const struct snd_pci_quirk alc269 SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC), SND_PCI_QUIRK(0x10ec, 0x10f2, "Intel Reference board", ALC700_FIXUP_INTEL_REFERENCE), SND_PCI_QUIRK(0x10ec, 0x118c, "Medion EE4254 MD62100", ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE), + SND_PCI_QUIRK(0x10ec, 0x11bc, "VAIO VJFE-IL", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x10ec, 0x1230, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0x10ec, 0x124c, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0x10ec, 0x1252, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), @@ -8494,6 +8495,7 @@ static const struct snd_pci_quirk alc269 SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1945, "Redmi G", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1947, "RedmiBook Air", ALC255_FIXUP_XIAOMI_HEADSET_MIC), + SND_PCI_QUIRK(0x2782, 0x0214, "VAIO VJFE-CL", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x2782, 0x0232, "CHUWI CoreBook XPro", ALC269VB_FIXUP_CHUWI_COREBOOK_XPRO), SND_PCI_QUIRK(0x2782, 0x1707, "Vaio VJFE-ADL", ALC298_FIXUP_SPK_VOLUME), SND_PCI_QUIRK(0x8086, 0x2074, "Intel NUC 8", ALC233_FIXUP_INTEL_NUC8_DMIC),

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: felix fuzhen5@huawei.com

commit bfca5fb4e97c46503ddfc582335917b0cc228264 upstream.

RPC client pipefs dentries cleanup is in separated rpc_remove_pipedir() workqueue,which takes care about pipefs superblock locking. In some special scenarios, when kernel frees the pipefs sb of the current client and immediately alloctes a new pipefs sb, rpc_remove_pipedir function would misjudge the existence of pipefs sb which is not the one it used to hold. As a result, the rpc_remove_pipedir would clean the released freed pipefs dentries.

To fix this issue, rpc_remove_pipedir should check whether the current pipefs sb is consistent with the original pipefs sb.

This error can be catched by KASAN: ========================================================= [ 250.497700] BUG: KASAN: slab-use-after-free in dget_parent+0x195/0x200 [ 250.498315] Read of size 4 at addr ffff88800a2ab804 by task kworker/0:18/106503 [ 250.500549] Workqueue: events rpc_free_client_work [ 250.501001] Call Trace: [ 250.502880] kasan_report+0xb6/0xf0 [ 250.503209] ? dget_parent+0x195/0x200 [ 250.503561] dget_parent+0x195/0x200 [ 250.503897] ? __pfx_rpc_clntdir_depopulate+0x10/0x10 [ 250.504384] rpc_rmdir_depopulate+0x1b/0x90 [ 250.504781] rpc_remove_client_dir+0xf5/0x150 [ 250.505195] rpc_free_client_work+0xe4/0x230 [ 250.505598] process_one_work+0x8ee/0x13b0 ... [ 22.039056] Allocated by task 244: [ 22.039390] kasan_save_stack+0x22/0x50 [ 22.039758] kasan_set_track+0x25/0x30 [ 22.040109] __kasan_slab_alloc+0x59/0x70 [ 22.040487] kmem_cache_alloc_lru+0xf0/0x240 [ 22.040889] __d_alloc+0x31/0x8e0 [ 22.041207] d_alloc+0x44/0x1f0 [ 22.041514] __rpc_lookup_create_exclusive+0x11c/0x140 [ 22.041987] rpc_mkdir_populate.constprop.0+0x5f/0x110 [ 22.042459] rpc_create_client_dir+0x34/0x150 [ 22.042874] rpc_setup_pipedir_sb+0x102/0x1c0 [ 22.043284] rpc_client_register+0x136/0x4e0 [ 22.043689] rpc_new_client+0x911/0x1020 [ 22.044057] rpc_create_xprt+0xcb/0x370 [ 22.044417] rpc_create+0x36b/0x6c0 ... [ 22.049524] Freed by task 0: [ 22.049803] kasan_save_stack+0x22/0x50 [ 22.050165] kasan_set_track+0x25/0x30 [ 22.050520] kasan_save_free_info+0x2b/0x50 [ 22.050921] __kasan_slab_free+0x10e/0x1a0 [ 22.051306] kmem_cache_free+0xa5/0x390 [ 22.051667] rcu_core+0x62c/0x1930 [ 22.051995] __do_softirq+0x165/0x52a [ 22.052347] [ 22.052503] Last potentially related work creation: [ 22.052952] kasan_save_stack+0x22/0x50 [ 22.053313] __kasan_record_aux_stack+0x8e/0xa0 [ 22.053739] __call_rcu_common.constprop.0+0x6b/0x8b0 [ 22.054209] dentry_free+0xb2/0x140 [ 22.054540] __dentry_kill+0x3be/0x540 [ 22.054900] shrink_dentry_list+0x199/0x510 [ 22.055293] shrink_dcache_parent+0x190/0x240 [ 22.055703] do_one_tree+0x11/0x40 [ 22.056028] shrink_dcache_for_umount+0x61/0x140 [ 22.056461] generic_shutdown_super+0x70/0x590 [ 22.056879] kill_anon_super+0x3a/0x60 [ 22.057234] rpc_kill_sb+0x121/0x200

Fixes: 0157d021d23a ("SUNRPC: handle RPC client pipefs dentries by network namespace aware routines") Signed-off-by: felix fuzhen5@huawei.com Signed-off-by: Trond Myklebust trond.myklebust@hammerspace.com Signed-off-by: Hagar Hemdan hagarhem@amazon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/sunrpc/clnt.h | 1 + net/sunrpc/clnt.c | 5 ++++- 2 files changed, 5 insertions(+), 1 deletion(-)

--- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -73,6 +73,7 @@ struct rpc_clnt { #endif struct rpc_xprt_iter cl_xpi; const struct cred *cl_cred; + struct super_block *pipefs_sb; };

/* --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -113,7 +113,8 @@ static void rpc_clnt_remove_pipedir(stru

pipefs_sb = rpc_get_sb_net(net); if (pipefs_sb) { - __rpc_clnt_remove_pipedir(clnt); + if (pipefs_sb == clnt->pipefs_sb) + __rpc_clnt_remove_pipedir(clnt); rpc_put_sb_net(net); } } @@ -153,6 +154,8 @@ rpc_setup_pipedir(struct super_block *pi { struct dentry *dentry;

+ clnt->pipefs_sb = pipefs_sb; + if (clnt->cl_program->pipe_dir_name != NULL) { dentry = rpc_setup_pipedir_sb(pipefs_sb, clnt); if (IS_ERR(dentry))

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Menglong Dong imagedong@tencent.com

commit e89688e3e97868451a5d05b38a9d2633d6785cd4 upstream.

In tcp_retransmit_timer(), a window shrunk connection will be regarded as timeout if 'tcp_jiffies32 - tp->rcv_tstamp > TCP_RTO_MAX'. This is not right all the time.

The retransmits will become zero-window probes in tcp_retransmit_timer() if the 'snd_wnd==0'. Therefore, the icsk->icsk_rto will come up to TCP_RTO_MAX sooner or later.

However, the timer can be delayed and be triggered after 122877ms, not TCP_RTO_MAX, as I tested.

Therefore, 'tcp_jiffies32 - tp->rcv_tstamp > TCP_RTO_MAX' is always true once the RTO come up to TCP_RTO_MAX, and the socket will die.

Fix this by replacing the 'tcp_jiffies32' with '(u32)icsk->icsk_timeout', which is exact the timestamp of the timeout.

However, "tp->rcv_tstamp" can restart from idle, then tp->rcv_tstamp could already be a long time (minutes or hours) in the past even on the first RTO. So we double check the timeout with the duration of the retransmission.

Meanwhile, making "2 * TCP_RTO_MAX" as the timeout to avoid the socket dying too soon.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Link: https://lore.kernel.org/netdev/CADxym3YyMiO+zMD4zj03YPM3FBi-1LHi6gSD2XT8pyAM... Signed-off-by: Menglong Dong imagedong@tencent.com Reviewed-by: Eric Dumazet edumazet@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv4/tcp_timer.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-)

--- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -434,6 +434,22 @@ static void tcp_fastopen_synack_timer(st TCP_TIMEOUT_INIT << req->num_timeout, TCP_RTO_MAX); }

+static bool tcp_rtx_probe0_timed_out(const struct sock *sk, + const struct sk_buff *skb) +{ + const struct tcp_sock *tp = tcp_sk(sk); + const int timeout = TCP_RTO_MAX * 2; + u32 rcv_delta, rtx_delta; + + rcv_delta = inet_csk(sk)->icsk_timeout - tp->rcv_tstamp; + if (rcv_delta <= timeout) + return false; + + rtx_delta = (u32)msecs_to_jiffies(tcp_time_stamp(tp) - + (tp->retrans_stamp ?: tcp_skb_timestamp(skb))); + + return rtx_delta > timeout; +}

/** * tcp_retransmit_timer() - The TCP retransmit timeout handler @@ -497,7 +513,7 @@ void tcp_retransmit_timer(struct sock *s tp->snd_una, tp->snd_nxt); } #endif - if (tcp_jiffies32 - tp->rcv_tstamp > TCP_RTO_MAX) { + if (tcp_rtx_probe0_timed_out(sk, skb)) { tcp_write_err(sk); goto out; }

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet edumazet@google.com

commit 97a9063518f198ec0adb2ecb89789de342bb8283 upstream.

If a TCP socket is using TCP_USER_TIMEOUT, and the other peer retracted its window to zero, tcp_retransmit_timer() can retransmit a packet every two jiffies (2 ms for HZ=1000), for about 4 minutes after TCP_USER_TIMEOUT has 'expired'.

The fix is to make sure tcp_rtx_probe0_timed_out() takes icsk->icsk_user_timeout into account.

Before blamed commit, the socket would not timeout after icsk->icsk_user_timeout, but would use standard exponential backoff for the retransmits.

Also worth noting that before commit e89688e3e978 ("net: tcp: fix unexcepted socket die when snd_wnd is 0"), the issue would last 2 minutes instead of 4.

Fixes: b701a99e431d ("tcp: Add tcp_clamp_rto_to_user_timeout() helper to improve accuracy") Signed-off-by: Eric Dumazet edumazet@google.com Cc: Neal Cardwell ncardwell@google.com Reviewed-by: Jason Xing kerneljasonxing@gmail.com Reviewed-by: Jon Maxwell jmaxwell37@gmail.com Reviewed-by: Kuniyuki Iwashima kuniyu@amazon.com Link: https://patch.msgid.link/20240710001402.2758273-1-edumazet@google.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv4/tcp_timer.c | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-)

--- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -437,22 +437,34 @@ static void tcp_fastopen_synack_timer(st static bool tcp_rtx_probe0_timed_out(const struct sock *sk, const struct sk_buff *skb) { + const struct inet_connection_sock *icsk = inet_csk(sk); + u32 user_timeout = READ_ONCE(icsk->icsk_user_timeout); const struct tcp_sock *tp = tcp_sk(sk); - const int timeout = TCP_RTO_MAX * 2; + int timeout = TCP_RTO_MAX * 2; u32 rtx_delta; s32 rcv_delta;

+ rtx_delta = (u32)msecs_to_jiffies(tcp_time_stamp(tp) - + (tp->retrans_stamp ?: tcp_skb_timestamp(skb))); + + if (user_timeout) { + /* If user application specified a TCP_USER_TIMEOUT, + * it does not want win 0 packets to 'reset the timer' + * while retransmits are not making progress. + */ + if (rtx_delta > user_timeout) + return true; + timeout = min_t(u32, timeout, msecs_to_jiffies(user_timeout)); + } + /* Note: timer interrupt might have been delayed by at least one jiffy, * and tp->rcv_tstamp might very well have been written recently. * rcv_delta can thus be negative. */ - rcv_delta = inet_csk(sk)->icsk_timeout - tp->rcv_tstamp; + rcv_delta = icsk->icsk_timeout - tp->rcv_tstamp; if (rcv_delta <= timeout) return false;

- rtx_delta = (u32)msecs_to_jiffies(tcp_time_stamp(tp) - - (tp->retrans_stamp ?: tcp_skb_timestamp(skb))); - return rtx_delta > timeout; }

5.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Wolfram Sang wsa+renesas@sang-engineering.com

[ Upstream commit 4e36c0f20cb1c74c7bd7ea31ba432c1c4a989031 ]

When probing, the hardware is not brought into a known state. This may be a problem when a hypervisor restarts Linux without resetting the hardware, leaving an old state running. Make sure the hardware gets initialized, especially interrupts should be cleared and disabled.

Reported-by: Dirk Behme dirk.behme@de.bosch.com Reported-by: Geert Uytterhoeven geert+renesas@glider.be Closes: https://lore.kernel.org/r/20240702045535.2000393-1-dirk.behme@de.bosch.com Fixes: 6ccbe607132b ("i2c: add Renesas R-Car I2C driver") Signed-off-by: Wolfram Sang wsa+renesas@sang-engineering.com Signed-off-by: Andi Shyti andi.shyti@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/i2c/busses/i2c-rcar.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-)

diff --git a/drivers/i2c/busses/i2c-rcar.c b/drivers/i2c/busses/i2c-rcar.c index d0c4b3019e41e..1327f29f1e93b 100644 --- a/drivers/i2c/busses/i2c-rcar.c +++ b/drivers/i2c/busses/i2c-rcar.c @@ -218,6 +218,14 @@ static void rcar_i2c_init(struct rcar_i2c_priv *priv)

}

+static void rcar_i2c_reset_slave(struct rcar_i2c_priv *priv) +{ + rcar_i2c_write(priv, ICSIER, 0); + rcar_i2c_write(priv, ICSSR, 0); + rcar_i2c_write(priv, ICSCR, SDBS); + rcar_i2c_write(priv, ICSAR, 0); /* Gen2: must be 0 if not using slave */ +} + static int rcar_i2c_bus_barrier(struct rcar_i2c_priv *priv) { int i; @@ -863,11 +871,8 @@ static int rcar_unreg_slave(struct i2c_client *slave)

/* ensure no irq is running before clearing ptr */ disable_irq(priv->irq); - rcar_i2c_write(priv, ICSIER, 0); - rcar_i2c_write(priv, ICSSR, 0); + rcar_i2c_reset_slave(priv); enable_irq(priv->irq); - rcar_i2c_write(priv, ICSCR, SDBS); - rcar_i2c_write(priv, ICSAR, 0); /* Gen2: must be 0 if not using slave */

priv->slave = NULL;

@@ -973,7 +978,9 @@ static int rcar_i2c_probe(struct platform_device *pdev) if (ret < 0) goto out_pm_put;

- rcar_i2c_write(priv, ICSAR, 0); /* Gen2: must be 0 if not using slave */ + /* Bring hardware to known state */ + rcar_i2c_init(priv); + rcar_i2c_reset_slave(priv);

if (priv->devtype == I2C_RCAR_GEN3) { priv->rstc = devm_reset_control_get_exclusive(&pdev->dev, NULL);