From: Oleksandr Tyshchenko oleksandr_tyshchenko@epam.com

[ Upstream commit a54bace095d00e9222161495649688bc43de4dde ]

The "vdev->dev.parent" should be used instead of "vdev->dev" as a device for which to perform the DMA operation in both virtio_gpu_cmd_transfer_to_host_2d(3d).

Because the virtio-gpu device "vdev->dev" doesn't really have DMA OPS assigned to it, but parent (virtio-pci or virtio-mmio) device "vdev->dev.parent" has. The more, the sgtable in question the code is trying to sync here was mapped for the parent device (by using its DMA OPS) previously at: virtio_gpu_object_shmem_init()->drm_gem_shmem_get_pages_sgt()-> dma_map_sgtable(), so should be synced here for the same parent device.

Fixes: b5c9ed70d1a9 ("drm/virtio: Improve DMA API usage for shmem BOs") Signed-off-by: Oleksandr Tyshchenko oleksandr_tyshchenko@epam.com Reviewed-by: Dmitry Osipenko dmitry.osipenko@collabora.com Signed-off-by: Dmitry Osipenko dmitry.osipenko@collabora.com Link: https://patchwork.freedesktop.org/patch/msgid/20230224153450.526222-1-olekst... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/virtio/virtgpu_vq.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c index 9ff8660b50ade..208e9434cb28d 100644 --- a/drivers/gpu/drm/virtio/virtgpu_vq.c +++ b/drivers/gpu/drm/virtio/virtgpu_vq.c @@ -597,7 +597,7 @@ void virtio_gpu_cmd_transfer_to_host_2d(struct virtio_gpu_device *vgdev, bool use_dma_api = !virtio_has_dma_quirk(vgdev->vdev);

if (virtio_gpu_is_shmem(bo) && use_dma_api) - dma_sync_sgtable_for_device(&vgdev->vdev->dev, + dma_sync_sgtable_for_device(vgdev->vdev->dev.parent, bo->base.sgt, DMA_TO_DEVICE);

cmd_p = virtio_gpu_alloc_cmd(vgdev, &vbuf, sizeof(*cmd_p)); @@ -1019,7 +1019,7 @@ void virtio_gpu_cmd_transfer_to_host_3d(struct virtio_gpu_device *vgdev, bool use_dma_api = !virtio_has_dma_quirk(vgdev->vdev);

if (virtio_gpu_is_shmem(bo) && use_dma_api) - dma_sync_sgtable_for_device(&vgdev->vdev->dev, + dma_sync_sgtable_for_device(vgdev->vdev->dev.parent, bo->base.sgt, DMA_TO_DEVICE);

cmd_p = virtio_gpu_alloc_cmd(vgdev, &vbuf, sizeof(*cmd_p));

From: Dmitry Osipenko dmitry.osipenko@collabora.com

[ Upstream commit ba3be66f11c3c49afaa9f49b99e21d88756229ef ]

Lockdep warns about potential circular locking dependency of devfreq with the fs_reclaim caused by immediate device suspension when mapping is released by shrinker. Fix it by doing the suspension asynchronously.

Reviewed-by: Steven Price steven.price@arm.com Fixes: ec7eba47da86 ("drm/panfrost: Rework page table flushing and runtime PM interaction") Signed-off-by: Dmitry Osipenko dmitry.osipenko@collabora.com Link: https://lore.kernel.org/all/20230108210445.3948344-3-dmitry.osipenko@collabo... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/panfrost/panfrost_mmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c index 4e83a1891f3ed..666a5e53fe193 100644 --- a/drivers/gpu/drm/panfrost/panfrost_mmu.c +++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c @@ -282,7 +282,7 @@ static void panfrost_mmu_flush_range(struct panfrost_device *pfdev, if (pm_runtime_active(pfdev->dev)) mmu_hw_do_operation(pfdev, mmu, iova, size, AS_COMMAND_FLUSH_PT);

- pm_runtime_put_sync_autosuspend(pfdev->dev); + pm_runtime_put_autosuspend(pfdev->dev); }

static int mmu_map_sg(struct panfrost_device *pfdev, struct panfrost_mmu *mmu,

From: Zhang Xiaoxu zhangxiaoxu5@huawei.com

[ Upstream commit d0dc41119905f740e8d5594adce277f7c0de8c92 ]

When send SMB_COM_NT_CANCEL and RFC1002_SESSION_REQUEST, the in_send statistic was lost.

Let's move the in_send statistic to the send function to avoid this scenario.

Fixes: 7ee1af765dfa ("[CIFS]") Signed-off-by: Zhang Xiaoxu zhangxiaoxu5@huawei.com Signed-off-by: Steve French stfrench@microsoft.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/cifs/transport.c | 21 +++++++++------------ 1 file changed, 9 insertions(+), 12 deletions(-)

diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 3851d0aaa2886..c961b90f92b9f 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -297,7 +297,7 @@ static int __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, struct smb_rqst *rqst) { - int rc = 0; + int rc; struct kvec *iov; int n_vec; unsigned int send_length = 0; @@ -308,6 +308,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, struct msghdr smb_msg = {}; __be32 rfc1002_marker;

+ cifs_in_send_inc(server); if (cifs_rdma_enabled(server)) { /* return -EAGAIN when connecting or reconnecting */ rc = -EAGAIN; @@ -316,14 +317,17 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, goto smbd_done; }

+ rc = -EAGAIN; if (ssocket == NULL) - return -EAGAIN; + goto out;

+ rc = -ERESTARTSYS; if (fatal_signal_pending(current)) { cifs_dbg(FYI, "signal pending before send request\n"); - return -ERESTARTSYS; + goto out; }

+ rc = 0; /* cork the socket */ tcp_sock_set_cork(ssocket->sk, true);

@@ -434,7 +438,8 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, rc); else if (rc > 0) rc = 0; - +out: + cifs_in_send_dec(server); return rc; }

@@ -853,9 +858,7 @@ cifs_call_async(struct TCP_Server_Info *server, struct smb_rqst *rqst, * I/O response may come back and free the mid entry on another thread. */ cifs_save_when_sent(mid); - cifs_in_send_inc(server); rc = smb_send_rqst(server, 1, rqst, flags); - cifs_in_send_dec(server);

if (rc < 0) { revert_current_mid(server, mid->credits); @@ -1146,9 +1149,7 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, else midQ[i]->callback = cifs_compound_last_callback; } - cifs_in_send_inc(server); rc = smb_send_rqst(server, num_rqst, rqst, flags); - cifs_in_send_dec(server);

for (i = 0; i < num_rqst; i++) cifs_save_when_sent(midQ[i]); @@ -1398,9 +1399,7 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses,

midQ->mid_state = MID_REQUEST_SUBMITTED;

- cifs_in_send_inc(server); rc = smb_send(server, in_buf, len); - cifs_in_send_dec(server); cifs_save_when_sent(midQ);

if (rc < 0) @@ -1541,9 +1540,7 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon, }

midQ->mid_state = MID_REQUEST_SUBMITTED; - cifs_in_send_inc(server); rc = smb_send(server, in_buf, len); - cifs_in_send_dec(server); cifs_save_when_sent(midQ);

if (rc < 0)

From: Randy Dunlap rdunlap@infradead.org

[ Upstream commit 0ffad67784a097beccf34d297ddd1b0773b3b8a3 ]

REGMAP is a hidden (not user visible) symbol. Users cannot set it directly thru "make *config", so drivers should select it instead of depending on it if they need it.

Consistently using "select" or "depends on" can also help reduce Kconfig circular dependency issues.

Therefore, change the use of "depends on REGMAP" to "select REGMAP".

Fixes: 3a49afb84ca0 ("clk: enable hi655x common clk automatically") Signed-off-by: Randy Dunlap rdunlap@infradead.org Cc: Riku Voipio riku.voipio@linaro.org Cc: Stephen Boyd sboyd@kernel.org Cc: Michael Turquette mturquette@baylibre.com Cc: linux-clk@vger.kernel.org Link: https://lore.kernel.org/r/20230226053953.4681-3-rdunlap@infradead.org Signed-off-by: Stephen Boyd sboyd@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/clk/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig index d79905f3e1744..5da82f2bdd211 100644 --- a/drivers/clk/Kconfig +++ b/drivers/clk/Kconfig @@ -92,7 +92,7 @@ config COMMON_CLK_RK808 config COMMON_CLK_HI655X tristate "Clock driver for Hi655x" if EXPERT depends on (MFD_HI655X_PMIC || COMPILE_TEST) - depends on REGMAP + select REGMAP default MFD_HI655X_PMIC help This driver supports the hi655x PMIC clock. This

From: Ranjani Sridharan ranjani.sridharan@linux.intel.com

[ Upstream commit a659e35ca0af2765f567bdfdccfa247eff0cdab8 ]

Add the missing ops_free callback.

Fixes: 064520e8aeaa ("ASoC: SOF: Intel: Add support for MeteorLake (MTL)")

Signed-off-by: Ranjani Sridharan ranjani.sridharan@linux.intel.com Reviewed-by: Pierre-Louis Bossart pierre-louis.bossart@linux.intel.com Reviewed-by: Bard Liao yung-chuan.liao@linux.intel.com Signed-off-by: Peter Ujfalusi peter.ujfalusi@linux.intel.com Link: https://lore.kernel.org/r/20230307093914.25409-2-peter.ujfalusi@linux.intel.... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/sof/intel/pci-mtl.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/sound/soc/sof/intel/pci-mtl.c b/sound/soc/sof/intel/pci-mtl.c index 6e4e6d4ef5a56..b183dc0014b4b 100644 --- a/sound/soc/sof/intel/pci-mtl.c +++ b/sound/soc/sof/intel/pci-mtl.c @@ -46,6 +46,7 @@ static const struct sof_dev_desc mtl_desc = { .nocodec_tplg_filename = "sof-mtl-nocodec.tplg", .ops = &sof_mtl_ops, .ops_init = sof_mtl_ops_init, + .ops_free = hda_ops_free, };

/* PCI IDs */

From: Ranjani Sridharan ranjani.sridharan@linux.intel.com

[ Upstream commit 1f320bdb29b644a2c9fb301a6fb2d6170e6417e9 ]

Add missing ops_free callback for SKL/KBL platforms.

Fixes: 52d7939d10f2 ("ASoC: SOF: Intel: add ops for SKL/KBL")

Signed-off-by: Ranjani Sridharan ranjani.sridharan@linux.intel.com Reviewed-by: Pierre-Louis Bossart pierre-louis.bossart@linux.intel.com Reviewed-by: Bard Liao yung-chuan.liao@linux.intel.com Signed-off-by: Peter Ujfalusi peter.ujfalusi@linux.intel.com Link: https://lore.kernel.org/r/20230307093914.25409-4-peter.ujfalusi@linux.intel.... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/sof/intel/pci-skl.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/sound/soc/sof/intel/pci-skl.c b/sound/soc/sof/intel/pci-skl.c index 3a99dc444f92e..5b4bccf819658 100644 --- a/sound/soc/sof/intel/pci-skl.c +++ b/sound/soc/sof/intel/pci-skl.c @@ -38,6 +38,7 @@ static struct sof_dev_desc skl_desc = { .nocodec_tplg_filename = "sof-skl-nocodec.tplg", .ops = &sof_skl_ops, .ops_init = sof_skl_ops_init, + .ops_free = hda_ops_free, };

static struct sof_dev_desc kbl_desc = { @@ -61,6 +62,7 @@ static struct sof_dev_desc kbl_desc = { .nocodec_tplg_filename = "sof-kbl-nocodec.tplg", .ops = &sof_skl_ops, .ops_init = sof_skl_ops_init, + .ops_free = hda_ops_free, };

/* PCI IDs */

From: Jaska Uimonen jaska.uimonen@linux.intel.com

[ Upstream commit c99e48f4ce9b986ab7992ec7283a06dae875f668 ]

Dmic dai index was set incorrectly to bits 5-7, when it is actually using just the lowest 3. Fix the macro for setting the bits.

Fixes: aa84ffb72158 ("ASoC: SOF: ipc4-topology: Add support for SSP/DMIC DAI's") Signed-off-by: Jaska Uimonen jaska.uimonen@linux.intel.com Reviewed-by: Adrian Bonislawski adrian.bonislawski@intel.com Reviewed-by: Péter Ujfalusi peter.ujfalusi@linux.intel.com Reviewed-by: Pierre-Louis Bossart pierre-louis.bossart@linux.intel.com Reviewed-by: Ranjani Sridharan ranjani.sridharan@linux.intel.com Signed-off-by: Peter Ujfalusi peter.ujfalusi@linux.intel.com Link: https://lore.kernel.org/r/20230307110730.1995-1-peter.ujfalusi@linux.intel.c... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/sof/ipc4-topology.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/sof/ipc4-topology.h b/sound/soc/sof/ipc4-topology.h index 0aa87a8add5d3..2363a7cc0b57d 100644 --- a/sound/soc/sof/ipc4-topology.h +++ b/sound/soc/sof/ipc4-topology.h @@ -46,7 +46,7 @@ #define SOF_IPC4_NODE_INDEX_INTEL_SSP(x) (((x) & 0xf) << 4)

/* Node ID for DMIC type DAI copiers */ -#define SOF_IPC4_NODE_INDEX_INTEL_DMIC(x) (((x) & 0x7) << 5) +#define SOF_IPC4_NODE_INDEX_INTEL_DMIC(x) ((x) & 0x7)

#define SOF_IPC4_GAIN_ALL_CHANNELS_MASK 0xffffffff #define SOF_IPC4_VOL_ZERO_DB 0x7fffffff

From: Wenchao Hao haowenchao2@huawei.com

[ Upstream commit d3c57724f1569311e4b81e98fad0931028b9bdcd ]

Port is allocated by sas_port_alloc_num() and rphy is allocated by either sas_end_device_alloc() or sas_expander_alloc(), all of which may return NULL. So we need to check the rphy to avoid possible NULL pointer access.

If sas_rphy_add() returned with failure, rphy is set to NULL. We would access the rphy in the following lines which would also result NULL pointer access.

Fixes: 78316e9dfc24 ("scsi: mpt3sas: Fix possible resource leaks in mpt3sas_transport_port_add()") Signed-off-by: Wenchao Hao haowenchao2@huawei.com Link: https://lore.kernel.org/r/20230225100135.2109330-1-haowenchao2@huawei.com Acked-by: Sathya Prakash Veerichetty sathya.prakash@broadcom.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/mpt3sas/mpt3sas_transport.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/mpt3sas/mpt3sas_transport.c b/drivers/scsi/mpt3sas/mpt3sas_transport.c index e5ecd6ada6cdd..e8a4750f6ec47 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_transport.c +++ b/drivers/scsi/mpt3sas/mpt3sas_transport.c @@ -785,7 +785,7 @@ mpt3sas_transport_port_add(struct MPT3SAS_ADAPTER *ioc, u16 handle, goto out_fail; } port = sas_port_alloc_num(sas_node->parent_dev); - if ((sas_port_add(port))) { + if (!port || (sas_port_add(port))) { ioc_err(ioc, "failure at %s:%d/%s()!\n", __FILE__, __LINE__, __func__); goto out_fail; @@ -824,6 +824,12 @@ mpt3sas_transport_port_add(struct MPT3SAS_ADAPTER *ioc, u16 handle, mpt3sas_port->remote_identify.sas_address; }

+ if (!rphy) { + ioc_err(ioc, "failure at %s:%d/%s()!\n", + __FILE__, __LINE__, __func__); + goto out_delete_port; + } + rphy->identify = mpt3sas_port->remote_identify;

if ((sas_rphy_add(rphy))) { @@ -831,6 +837,7 @@ mpt3sas_transport_port_add(struct MPT3SAS_ADAPTER *ioc, u16 handle, __FILE__, __LINE__, __func__); sas_rphy_free(rphy); rphy = NULL; + goto out_delete_port; }

if (mpt3sas_port->remote_identify.device_type == SAS_END_DEVICE) { @@ -857,7 +864,10 @@ mpt3sas_transport_port_add(struct MPT3SAS_ADAPTER *ioc, u16 handle, rphy_to_expander_device(rphy), hba_port->port_id); return mpt3sas_port;

- out_fail: +out_delete_port: + sas_port_delete(port); + +out_fail: list_for_each_entry_safe(mpt3sas_phy, next, &mpt3sas_port->phy_list, port_siblings) list_del(&mpt3sas_phy->port_siblings);

From: Tomas Henzl thenzl@redhat.com

[ Upstream commit 7d2b02172b6a2ae6aecd7ef6480b9c4bf3dc59f4 ]

A fix for:

DMA-API: pci 0000:83:00.0: device driver has pending DMA allocations while released from device [count=1]

Fixes: 32d457d5a2af ("scsi: mpi3mr: Add framework to issue config requests") Signed-off-by: Tomas Henzl thenzl@redhat.com Link: https://lore.kernel.org/r/20230302234336.25456-3-thenzl@redhat.com Acked-by: Sathya Prakash Veerichetty sathya.prakash@broadcom.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/mpi3mr/mpi3mr_fw.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/mpi3mr/mpi3mr_fw.c b/drivers/scsi/mpi3mr/mpi3mr_fw.c index 9c716d92c2564..77282ad5688da 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_fw.c +++ b/drivers/scsi/mpi3mr/mpi3mr_fw.c @@ -4350,7 +4350,11 @@ void mpi3mr_free_mem(struct mpi3mr_ioc *mrioc) mrioc->admin_req_base, mrioc->admin_req_dma); mrioc->admin_req_base = NULL; } - + if (mrioc->cfg_page) { + dma_free_coherent(&mrioc->pdev->dev, mrioc->cfg_page_sz, + mrioc->cfg_page, mrioc->cfg_page_dma); + mrioc->cfg_page = NULL; + } if (mrioc->pel_seqnum_virt) { dma_free_coherent(&mrioc->pdev->dev, mrioc->pel_seqnum_sz, mrioc->pel_seqnum_virt, mrioc->pel_seqnum_dma);

From: Tomas Henzl thenzl@redhat.com

[ Upstream commit d4caa1a4255cc44be56bcab3db2c97c632e6cc10 ]

Free mrioc->sas_hba.phy at .remove.

Fixes: 42fc9fee116f ("scsi: mpi3mr: Add helper functions to manage device's port") Signed-off-by: Tomas Henzl thenzl@redhat.com Link: https://lore.kernel.org/r/20230302234336.25456-5-thenzl@redhat.com Acked-by: Sathya Prakash Veerichetty sathya.prakash@broadcom.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/mpi3mr/mpi3mr_os.c | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/drivers/scsi/mpi3mr/mpi3mr_os.c b/drivers/scsi/mpi3mr/mpi3mr_os.c index 5032b0b5186d4..5698e7b90f852 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_os.c +++ b/drivers/scsi/mpi3mr/mpi3mr_os.c @@ -5127,6 +5127,12 @@ static void mpi3mr_remove(struct pci_dev *pdev) } spin_unlock_irqrestore(&mrioc->sas_node_lock, flags);

+ if (mrioc->sas_hba.num_phys) { + kfree(mrioc->sas_hba.phy); + mrioc->sas_hba.phy = NULL; + mrioc->sas_hba.num_phys = 0; + } + spin_lock(&mrioc_list_lock); list_del(&mrioc->list); spin_unlock(&mrioc_list_lock);

From: Tomas Henzl thenzl@redhat.com

[ Upstream commit c798304470cab88723d895726d17fcb96472e0e9 ]

Don't allocate memory again when IOC is being reinitialized.

Fixes: fe6db6151565 ("scsi: mpi3mr: Handle offline FW activation in graceful manner") Signed-off-by: Tomas Henzl thenzl@redhat.com Link: https://lore.kernel.org/r/20230302234336.25456-6-thenzl@redhat.com Acked-by: Sathya Prakash Veerichetty sathya.prakash@broadcom.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/mpi3mr/mpi3mr_fw.c | 41 ++++++++++++++++++--------------- 1 file changed, 23 insertions(+), 18 deletions(-)

diff --git a/drivers/scsi/mpi3mr/mpi3mr_fw.c b/drivers/scsi/mpi3mr/mpi3mr_fw.c index e702911e8e934..4147920afbaee 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_fw.c +++ b/drivers/scsi/mpi3mr/mpi3mr_fw.c @@ -3813,29 +3813,34 @@ int mpi3mr_init_ioc(struct mpi3mr_ioc *mrioc)

mpi3mr_print_ioc_info(mrioc);

- dprint_init(mrioc, "allocating config page buffers\n"); - mrioc->cfg_page = dma_alloc_coherent(&mrioc->pdev->dev, - MPI3MR_DEFAULT_CFG_PAGE_SZ, &mrioc->cfg_page_dma, GFP_KERNEL); if (!mrioc->cfg_page) { - retval = -1; - goto out_failed_noretry; + dprint_init(mrioc, "allocating config page buffers\n"); + mrioc->cfg_page_sz = MPI3MR_DEFAULT_CFG_PAGE_SZ; + mrioc->cfg_page = dma_alloc_coherent(&mrioc->pdev->dev, + mrioc->cfg_page_sz, &mrioc->cfg_page_dma, GFP_KERNEL); + if (!mrioc->cfg_page) { + retval = -1; + goto out_failed_noretry; + } }

- mrioc->cfg_page_sz = MPI3MR_DEFAULT_CFG_PAGE_SZ; - - retval = mpi3mr_alloc_reply_sense_bufs(mrioc); - if (retval) { - ioc_err(mrioc, - "%s :Failed to allocated reply sense buffers %d\n", - __func__, retval); - goto out_failed_noretry; + if (!mrioc->init_cmds.reply) { + retval = mpi3mr_alloc_reply_sense_bufs(mrioc); + if (retval) { + ioc_err(mrioc, + "%s :Failed to allocated reply sense buffers %d\n", + __func__, retval); + goto out_failed_noretry; + } }

- retval = mpi3mr_alloc_chain_bufs(mrioc); - if (retval) { - ioc_err(mrioc, "Failed to allocated chain buffers %d\n", - retval); - goto out_failed_noretry; + if (!mrioc->chain_sgl_list) { + retval = mpi3mr_alloc_chain_bufs(mrioc); + if (retval) { + ioc_err(mrioc, "Failed to allocated chain buffers %d\n", + retval); + goto out_failed_noretry; + } }

retval = mpi3mr_issue_iocinit(mrioc);

From: Tomas Henzl thenzl@redhat.com

[ Upstream commit ce756daa36e1ba271bb3334267295e447aa57a5c ]

Add a missing resource clean up in .remove.

Fixes: e22bae30667a ("scsi: mpi3mr: Add expander devices to STL") Signed-off-by: Tomas Henzl thenzl@redhat.com Link: https://lore.kernel.org/r/20230302234336.25456-7-thenzl@redhat.com Acked-by: Sathya Prakash Veerichetty sathya.prakash@broadcom.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/mpi3mr/mpi3mr.h | 2 ++ drivers/scsi/mpi3mr/mpi3mr_os.c | 7 +++++++ drivers/scsi/mpi3mr/mpi3mr_transport.c | 5 +---- 3 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/scsi/mpi3mr/mpi3mr.h b/drivers/scsi/mpi3mr/mpi3mr.h index 68f29ffb05b82..de6914d57402c 100644 --- a/drivers/scsi/mpi3mr/mpi3mr.h +++ b/drivers/scsi/mpi3mr/mpi3mr.h @@ -1394,4 +1394,6 @@ void mpi3mr_flush_drv_cmds(struct mpi3mr_ioc *mrioc); void mpi3mr_flush_cmds_for_unrecovered_controller(struct mpi3mr_ioc *mrioc); void mpi3mr_free_enclosure_list(struct mpi3mr_ioc *mrioc); int mpi3mr_process_admin_reply_q(struct mpi3mr_ioc *mrioc); +void mpi3mr_expander_node_remove(struct mpi3mr_ioc *mrioc, + struct mpi3mr_sas_node *sas_expander); #endif /*MPI3MR_H_INCLUDED*/ diff --git a/drivers/scsi/mpi3mr/mpi3mr_os.c b/drivers/scsi/mpi3mr/mpi3mr_os.c index 2e546c80d98ce..6d55698ea4d16 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_os.c +++ b/drivers/scsi/mpi3mr/mpi3mr_os.c @@ -5079,6 +5079,7 @@ static void mpi3mr_remove(struct pci_dev *pdev) unsigned long flags; struct mpi3mr_tgt_dev *tgtdev, *tgtdev_next; struct mpi3mr_hba_port *port, *hba_port_next; + struct mpi3mr_sas_node *sas_expander, *sas_expander_next;

if (!shost) return; @@ -5119,6 +5120,12 @@ static void mpi3mr_remove(struct pci_dev *pdev) mpi3mr_cleanup_resources(mrioc);

spin_lock_irqsave(&mrioc->sas_node_lock, flags); + list_for_each_entry_safe_reverse(sas_expander, sas_expander_next, + &mrioc->sas_expander_list, list) { + spin_unlock_irqrestore(&mrioc->sas_node_lock, flags); + mpi3mr_expander_node_remove(mrioc, sas_expander); + spin_lock_irqsave(&mrioc->sas_node_lock, flags); + } list_for_each_entry_safe(port, hba_port_next, &mrioc->hba_port_table_list, list) { ioc_info(mrioc, "removing hba_port entry: %p port: %d from hba_port list\n", diff --git a/drivers/scsi/mpi3mr/mpi3mr_transport.c b/drivers/scsi/mpi3mr/mpi3mr_transport.c index 3b61815979dab..50263ba4f8428 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_transport.c +++ b/drivers/scsi/mpi3mr/mpi3mr_transport.c @@ -9,9 +9,6 @@

#include "mpi3mr.h"

-static void mpi3mr_expander_node_remove(struct mpi3mr_ioc *mrioc, - struct mpi3mr_sas_node *sas_expander); - /** * mpi3mr_post_transport_req - Issue transport requests and wait * @mrioc: Adapter instance reference @@ -2163,7 +2160,7 @@ int mpi3mr_expander_add(struct mpi3mr_ioc *mrioc, u16 handle) * * Return nothing. */ -static void mpi3mr_expander_node_remove(struct mpi3mr_ioc *mrioc, +void mpi3mr_expander_node_remove(struct mpi3mr_ioc *mrioc, struct mpi3mr_sas_node *sas_expander) { struct mpi3mr_sas_port *mr_sas_port, *next;

From: Jeremy Sowden jeremy@azazel.net

[ Upstream commit 068d82e75d537b444303b8c449a11e51ea659565 ]

The values in the protocol registers are two bytes wide. However, when parsing the register loads, the code currently uses the larger 16-byte size of a `union nf_inet_addr`. Change it to use the (correct) size of a `union nf_conntrack_man_proto` instead.

Fixes: d07db9884a5f ("netfilter: nf_tables: introduce nft_validate_register_load()") Signed-off-by: Jeremy Sowden jeremy@azazel.net Reviewed-by: Florian Westphal fw@strlen.de Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/nft_nat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index 0479991503900..5c29915ab0289 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -226,7 +226,7 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, priv->flags |= NF_NAT_RANGE_MAP_IPS; }

- plen = sizeof_field(struct nf_nat_range, min_addr.all); + plen = sizeof_field(struct nf_nat_range, min_proto.all); if (tb[NFTA_NAT_REG_PROTO_MIN]) { err = nft_parse_register_load(tb[NFTA_NAT_REG_PROTO_MIN], &priv->sreg_proto_min, plen);

From: Jeremy Sowden jeremy@azazel.net

[ Upstream commit 1f617b6b4c7a3d5ea7a56abb83a4c27733b60c2f ]

The values in the protocol registers are two bytes wide. However, when parsing the register loads, the code currently uses the larger 16-byte size of a `union nf_inet_addr`. Change it to use the (correct) size of a `union nf_conntrack_man_proto` instead.

Fixes: d07db9884a5f ("netfilter: nf_tables: introduce nft_validate_register_load()") Signed-off-by: Jeremy Sowden jeremy@azazel.net Reviewed-by: Florian Westphal fw@strlen.de Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/nft_redir.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c index 5f77399875593..dbc642f5d32a3 100644 --- a/net/netfilter/nft_redir.c +++ b/net/netfilter/nft_redir.c @@ -48,7 +48,7 @@ static int nft_redir_init(const struct nft_ctx *ctx, unsigned int plen; int err;

- plen = sizeof_field(struct nf_nat_range, min_addr.all); + plen = sizeof_field(struct nf_nat_range, min_proto.all); if (tb[NFTA_REDIR_REG_PROTO_MIN]) { err = nft_parse_register_load(tb[NFTA_REDIR_REG_PROTO_MIN], &priv->sreg_proto_min, plen);

From: Lee Duncan lduncan@suse.com

[ Upstream commit 4b1a2c2a8e0ddcb89c5f6c5003bd9b53142f69e3 ]

Some storage, such as AIX VDASD (virtual storage) and IBM 2076 (front end), fail as a result of commit c92a6b5d6335 ("scsi: core: Query VPD size before getting full page").

That commit changed getting SCSI VPD pages so that we now read just enough of the page to get the actual page size, then read the whole page in a second read. The problem is that the above mentioned hardware returns zero for the page size, because of a firmware error. In such cases, until the firmware is fixed, this new blacklist flag says to revert to the original method of reading the VPD pages, i.e. try to read a whole buffer's worth on the first try.

[mkp: reworked somewhat]

Fixes: c92a6b5d6335 ("scsi: core: Query VPD size before getting full page") Reported-by: Martin Wilck mwilck@suse.com Suggested-by: Hannes Reinecke hare@suse.de Signed-off-by: Lee Duncan lduncan@suse.com Link: https://lore.kernel.org/r/20220928181350.9948-1-leeman.duncan@gmail.com Tested-by: Srikar Dronamraju srikar@linux.vnet.ibm.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/scsi.c | 3 +++ drivers/scsi/scsi_devinfo.c | 3 ++- drivers/scsi/scsi_scan.c | 3 +++ include/scsi/scsi_device.h | 2 ++ include/scsi/scsi_devinfo.h | 6 +++--- 5 files changed, 13 insertions(+), 4 deletions(-)

diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c index 9feb0323bc44a..dff1d692e756a 100644 --- a/drivers/scsi/scsi.c +++ b/drivers/scsi/scsi.c @@ -326,6 +326,9 @@ static int scsi_get_vpd_size(struct scsi_device *sdev, u8 page) unsigned char vpd_header[SCSI_VPD_HEADER_SIZE] __aligned(4); int result;

+ if (sdev->no_vpd_size) + return SCSI_DEFAULT_VPD_LEN; + /* * Fetch the VPD page header to find out how big the page * is. This is done to prevent problems on legacy devices diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c index c7080454aea99..bc9d280417f6a 100644 --- a/drivers/scsi/scsi_devinfo.c +++ b/drivers/scsi/scsi_devinfo.c @@ -134,7 +134,7 @@ static struct { {"3PARdata", "VV", NULL, BLIST_REPORTLUN2}, {"ADAPTEC", "AACRAID", NULL, BLIST_FORCELUN}, {"ADAPTEC", "Adaptec 5400S", NULL, BLIST_FORCELUN}, - {"AIX", "VDASD", NULL, BLIST_TRY_VPD_PAGES}, + {"AIX", "VDASD", NULL, BLIST_TRY_VPD_PAGES | BLIST_NO_VPD_SIZE}, {"AFT PRO", "-IX CF", "0.0>", BLIST_FORCELUN}, {"BELKIN", "USB 2 HS-CF", "1.95", BLIST_FORCELUN | BLIST_INQUIRY_36}, {"BROWNIE", "1200U3P", NULL, BLIST_NOREPORTLUN}, @@ -188,6 +188,7 @@ static struct { {"HPE", "OPEN-", "*", BLIST_REPORTLUN2 | BLIST_TRY_VPD_PAGES}, {"IBM", "AuSaV1S2", NULL, BLIST_FORCELUN}, {"IBM", "ProFibre 4000R", "*", BLIST_SPARSELUN | BLIST_LARGELUN}, + {"IBM", "2076", NULL, BLIST_NO_VPD_SIZE}, {"IBM", "2105", NULL, BLIST_RETRY_HWERROR}, {"iomega", "jaz 1GB", "J.86", BLIST_NOTQ | BLIST_NOLUN}, {"IOMEGA", "ZIP", NULL, BLIST_NOTQ | BLIST_NOLUN}, diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index f9b18fdc7b3c8..6042a5587bc37 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -1055,6 +1055,9 @@ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result, else if (*bflags & BLIST_SKIP_VPD_PAGES) sdev->skip_vpd_pages = 1;

+ if (*bflags & BLIST_NO_VPD_SIZE) + sdev->no_vpd_size = 1; + transport_configure_device(&sdev->sdev_gendev);

if (sdev->host->hostt->slave_configure) { diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 3642b8e3928b7..15169d75c251e 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -145,6 +145,7 @@ struct scsi_device { const char * model; /* ... after scan; point to static string */ const char * rev; /* ... "nullnullnullnull" before scan */

+#define SCSI_DEFAULT_VPD_LEN 255 /* default SCSI VPD page size (max) */ struct scsi_vpd __rcu *vpd_pg0; struct scsi_vpd __rcu *vpd_pg83; struct scsi_vpd __rcu *vpd_pg80; @@ -215,6 +216,7 @@ struct scsi_device { * creation time */ unsigned ignore_media_change:1; /* Ignore MEDIA CHANGE on resume */ unsigned silence_suspend:1; /* Do not print runtime PM related messages */ + unsigned no_vpd_size:1; /* No VPD size reported in header */

unsigned int queue_stopped; /* request queue is quiesced */ bool offline_already; /* Device offline message logged */ diff --git a/include/scsi/scsi_devinfo.h b/include/scsi/scsi_devinfo.h index 5d14adae21c78..6b548dc2c4965 100644 --- a/include/scsi/scsi_devinfo.h +++ b/include/scsi/scsi_devinfo.h @@ -32,7 +32,8 @@ #define BLIST_IGN_MEDIA_CHANGE ((__force blist_flags_t)(1ULL << 11)) /* do not do automatic start on add */ #define BLIST_NOSTARTONADD ((__force blist_flags_t)(1ULL << 12)) -#define __BLIST_UNUSED_13 ((__force blist_flags_t)(1ULL << 13)) +/* do not ask for VPD page size first on some broken targets */ +#define BLIST_NO_VPD_SIZE ((__force blist_flags_t)(1ULL << 13)) #define __BLIST_UNUSED_14 ((__force blist_flags_t)(1ULL << 14)) #define __BLIST_UNUSED_15 ((__force blist_flags_t)(1ULL << 15)) #define __BLIST_UNUSED_16 ((__force blist_flags_t)(1ULL << 16)) @@ -74,8 +75,7 @@ #define __BLIST_HIGH_UNUSED (~(__BLIST_LAST_USED | \ (__force blist_flags_t) \ ((__force __u64)__BLIST_LAST_USED - 1ULL))) -#define __BLIST_UNUSED_MASK (__BLIST_UNUSED_13 | \ - __BLIST_UNUSED_14 | \ +#define __BLIST_UNUSED_MASK (__BLIST_UNUSED_14 | \ __BLIST_UNUSED_15 | \ __BLIST_UNUSED_16 | \ __BLIST_UNUSED_24 | \

From: Arnd Bergmann arnd@arndb.de

[ Upstream commit aa69f814920d85a2d4cfd5c294757c3d59d2fba6 ]

When CONFIG_FUNCTION_GRAPH_TRACER is disabled, __kcfi_typeid_ftrace_stub_graph is missing, causing a link failure:

ld.lld: error: undefined symbol: __kcfi_typeid_ftrace_stub_graph referenced by arch/x86/kernel/ftrace_64.o:(__cfi_ftrace_stub_graph) in archive vmlinux.a

Mark the reference to it as conditional on the same symbol, as is done on arm64.

Link: https://lore.kernel.org/linux-trace-kernel/20230131093643.3850272-1-arnd@ker...

Cc: Peter Zijlstra peterz@infradead.org Cc: Masami Hiramatsu mhiramat@kernel.org Cc: Mark Rutland mark.rutland@arm.com Cc: Thomas Gleixner tglx@linutronix.de Cc: Ingo Molnar mingo@redhat.com Cc: Borislav Petkov bp@alien8.de Cc: Dave Hansen dave.hansen@linux.intel.com Cc: "H. Peter Anvin" hpa@zytor.com Cc: Josh Poimboeuf jpoimboe@kernel.org Fixes: 883bbbffa5a4 ("ftrace,kcfi: Separate ftrace_stub() and ftrace_stub_graph()") See-also: 2598ac6ec493 ("arm64: ftrace: Define ftrace_stub_graph only with FUNCTION_GRAPH_TRACER") Signed-off-by: Arnd Bergmann arnd@arndb.de Signed-off-by: Steven Rostedt (Google) rostedt@goodmis.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kernel/ftrace_64.S | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index 1265ad519249c..fb4f1e01b64a2 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -136,10 +136,12 @@ SYM_TYPED_FUNC_START(ftrace_stub) RET SYM_FUNC_END(ftrace_stub)

+#ifdef CONFIG_FUNCTION_GRAPH_TRACER SYM_TYPED_FUNC_START(ftrace_stub_graph) CALL_DEPTH_ACCOUNT RET SYM_FUNC_END(ftrace_stub_graph) +#endif

#ifdef CONFIG_DYNAMIC_FTRACE

From: Si-Wei Liu si-wei.liu@oracle.com

[ Upstream commit 09e65ee9059d76b89cb713795748805efd3f50c6 ]

Otherwise the virtqueue object to instate could point to invalid address that was unmapped from the MTT:

mlx5_core 0000:41:04.2: mlx5_cmd_out_err:782:(pid 8321): CREATE_GENERAL_OBJECT(0xa00) op_mod(0xd) failed, status bad parameter(0x3), syndrome (0x5fa1c), err(-22)

Fixes: cae15c2ed8e6 ("vdpa/mlx5: Implement susupend virtqueue callback") Cc: Eli Cohen elic@nvidia.com Signed-off-by: Si-Wei Liu si-wei.liu@oracle.com Reviewed-by: Eli Cohen elic@nvidia.com

Message-Id: 1676424640-11673-1-git-send-email-si-wei.liu@oracle.com Signed-off-by: Michael S. Tsirkin mst@redhat.com Acked-by: Jason Wang jasowang@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/vdpa/mlx5/core/mlx5_vdpa.h | 1 + drivers/vdpa/mlx5/net/mlx5_vnet.c | 6 +++++- 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h index 058fbe28107e9..25fc4120b618d 100644 --- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h +++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h @@ -96,6 +96,7 @@ struct mlx5_vdpa_dev { struct mlx5_control_vq cvq; struct workqueue_struct *wq; unsigned int group2asid[MLX5_VDPA_NUMVQ_GROUPS]; + bool suspended; };

int mlx5_vdpa_alloc_pd(struct mlx5_vdpa_dev *dev, u32 *pdn, u16 uid); diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 3a6dbbc6440d4..daac3ab314785 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -2411,7 +2411,7 @@ static int mlx5_vdpa_change_map(struct mlx5_vdpa_dev *mvdev, if (err) goto err_mr;

- if (!(mvdev->status & VIRTIO_CONFIG_S_DRIVER_OK)) + if (!(mvdev->status & VIRTIO_CONFIG_S_DRIVER_OK) || mvdev->suspended) goto err_mr;

restore_channels_info(ndev); @@ -2579,6 +2579,7 @@ static int mlx5_vdpa_reset(struct vdpa_device *vdev) clear_vqs_ready(ndev); mlx5_vdpa_destroy_mr(&ndev->mvdev); ndev->mvdev.status = 0; + ndev->mvdev.suspended = false; ndev->cur_num_vqs = 0; ndev->mvdev.cvq.received_desc = 0; ndev->mvdev.cvq.completed_desc = 0; @@ -2815,6 +2816,8 @@ static int mlx5_vdpa_suspend(struct vdpa_device *vdev) struct mlx5_vdpa_virtqueue *mvq; int i;

+ mlx5_vdpa_info(mvdev, "suspending device\n"); + down_write(&ndev->reslock); ndev->nb_registered = false; mlx5_notifier_unregister(mvdev->mdev, &ndev->nb); @@ -2824,6 +2827,7 @@ static int mlx5_vdpa_suspend(struct vdpa_device *vdev) suspend_vq(ndev, mvq); } mlx5_vdpa_cvq_suspend(mvdev); + mvdev->suspended = true; up_write(&ndev->reslock); return 0; }

From: Johannes Berg johannes.berg@intel.com

[ Upstream commit 96c069508377547f913e7265a80fffe9355de592 ]

When disconnecting from an MLO connection we need the AP MLD address, not an arbitrary BSSID. Fix the code to do that.

Fixes: 9ecff10e82a5 ("wifi: nl80211: refactor BSS lookup in nl80211_associate()") Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Gregory Greenman gregory.greenman@intel.com Link: https://lore.kernel.org/r/20230301115906.4c1b3b18980e.I008f070c7f3b8e8bde927... Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/wireless/nl80211.c | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-)

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 326c6e50e9db5..e34491e63133d 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -10700,8 +10700,7 @@ static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev,

static struct cfg80211_bss *nl80211_assoc_bss(struct cfg80211_registered_device *rdev, const u8 *ssid, int ssid_len, - struct nlattr **attrs, - const u8 **bssid_out) + struct nlattr **attrs) { struct ieee80211_channel *chan; struct cfg80211_bss *bss; @@ -10728,7 +10727,6 @@ static struct cfg80211_bss *nl80211_assoc_bss(struct cfg80211_registered_device if (!bss) return ERR_PTR(-ENOENT);

- *bssid_out = bssid; return bss; }

@@ -10738,7 +10736,7 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) struct net_device *dev = info->user_ptr[1]; struct cfg80211_assoc_request req = {}; struct nlattr **attrs = NULL; - const u8 *bssid, *ssid; + const u8 *ap_addr, *ssid; unsigned int link_id; int err, ssid_len;

@@ -10875,6 +10873,7 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) return -EINVAL;

req.ap_mld_addr = nla_data(info->attrs[NL80211_ATTR_MLD_ADDR]); + ap_addr = req.ap_mld_addr;

attrs = kzalloc(attrsize, GFP_KERNEL); if (!attrs) @@ -10900,8 +10899,7 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) goto free; } req.links[link_id].bss = - nl80211_assoc_bss(rdev, ssid, ssid_len, attrs, - &bssid); + nl80211_assoc_bss(rdev, ssid, ssid_len, attrs); if (IS_ERR(req.links[link_id].bss)) { err = PTR_ERR(req.links[link_id].bss); req.links[link_id].bss = NULL; @@ -10952,10 +10950,10 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) if (req.link_id >= 0) return -EINVAL;

- req.bss = nl80211_assoc_bss(rdev, ssid, ssid_len, info->attrs, - &bssid); + req.bss = nl80211_assoc_bss(rdev, ssid, ssid_len, info->attrs); if (IS_ERR(req.bss)) return PTR_ERR(req.bss); + ap_addr = req.bss->bssid; }

err = nl80211_crypto_settings(rdev, info, &req.crypto, 1); @@ -10968,7 +10966,7 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) dev->ieee80211_ptr->conn_owner_nlportid = info->snd_portid; memcpy(dev->ieee80211_ptr->disconnect_bssid, - bssid, ETH_ALEN); + ap_addr, ETH_ALEN); }

wdev_unlock(dev->ieee80211_ptr);

From: Fedor Pchelkin pchelkin@ispras.ru

[ Upstream commit 484b7059796e3bc1cb527caa61dfc60da649b4f6 ]

struct pn533_out_arg used as a temporary context for out_urb is not initialized properly. Its uninitialized 'phy' field can be dereferenced in error cases inside pn533_out_complete() callback function. It causes the following failure:

general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] CPU: 1 PID: 0 Comm: swapper/1 Not tainted 6.2.0-rc3-next-20230110-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022 RIP: 0010:pn533_out_complete.cold+0x15/0x44 drivers/nfc/pn533/usb.c:441 Call Trace: <IRQ> __usb_hcd_giveback_urb+0x2b6/0x5c0 drivers/usb/core/hcd.c:1671 usb_hcd_giveback_urb+0x384/0x430 drivers/usb/core/hcd.c:1754 dummy_timer+0x1203/0x32d0 drivers/usb/gadget/udc/dummy_hcd.c:1988 call_timer_fn+0x1da/0x800 kernel/time/timer.c:1700 expire_timers+0x234/0x330 kernel/time/timer.c:1751 __run_timers kernel/time/timer.c:2022 [inline] __run_timers kernel/time/timer.c:1995 [inline] run_timer_softirq+0x326/0x910 kernel/time/timer.c:2035 __do_softirq+0x1fb/0xaf6 kernel/softirq.c:571 invoke_softirq kernel/softirq.c:445 [inline] __irq_exit_rcu+0x123/0x180 kernel/softirq.c:650 irq_exit_rcu+0x9/0x20 kernel/softirq.c:662 sysvec_apic_timer_interrupt+0x97/0xc0 arch/x86/kernel/apic/apic.c:1107

Initialize the field with the pn533_usb_phy currently used.

Found by Linux Verification Center (linuxtesting.org) with Syzkaller.

Fixes: 9dab880d675b ("nfc: pn533: Wait for out_urb's completion in pn533_usb_send_frame()") Reported-by: syzbot+1e608ba4217c96d1952f@syzkaller.appspotmail.com Signed-off-by: Fedor Pchelkin pchelkin@ispras.ru Reviewed-by: Simon Horman simon.horman@corigine.com Link: https://lore.kernel.org/r/20230309165050.207390-1-pchelkin@ispras.ru Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nfc/pn533/usb.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/nfc/pn533/usb.c b/drivers/nfc/pn533/usb.c index ed9c5e2cf3ad4..a187f0e0b0f7d 100644 --- a/drivers/nfc/pn533/usb.c +++ b/drivers/nfc/pn533/usb.c @@ -175,6 +175,7 @@ static int pn533_usb_send_frame(struct pn533 *dev, print_hex_dump_debug("PN533 TX: ", DUMP_PREFIX_NONE, 16, 1, out->data, out->len, false);

+ arg.phy = phy; init_completion(&arg.done); cntx = phy->out_urb->context; phy->out_urb->context = &arg;

From: Ivan Vecera ivecera@redhat.com

[ Upstream commit 7e4f8a0c495413a50413e8c9f1032ce1bc633bae ]

If the driver detects during probe that firmware is in recovery mode then i40e_init_recovery_mode() is called and the rest of probe function is skipped including pci_set_drvdata(). Subsequent i40e_shutdown() called during shutdown/reboot dereferences NULL pointer as pci_get_drvdata() returns NULL.

To fix call pci_set_drvdata() also during entering to recovery mode.

Reproducer: 1) Lets have i40e NIC with firmware in recovery mode 2) Run reboot

Result: [ 139.084698] i40e: Intel(R) Ethernet Connection XL710 Network Driver [ 139.090959] i40e: Copyright (c) 2013 - 2019 Intel Corporation. [ 139.108438] i40e 0000:02:00.0: Firmware recovery mode detected. Limiting functionality. [ 139.116439] i40e 0000:02:00.0: Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware recovery mode. [ 139.129499] i40e 0000:02:00.0: fw 8.3.64775 api 1.13 nvm 8.30 0x8000b78d 1.3106.0 [8086:1583] [15d9:084a] [ 139.215932] i40e 0000:02:00.0 enp2s0f0: renamed from eth0 [ 139.223292] i40e 0000:02:00.1: Firmware recovery mode detected. Limiting functionality. [ 139.231292] i40e 0000:02:00.1: Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware recovery mode. [ 139.244406] i40e 0000:02:00.1: fw 8.3.64775 api 1.13 nvm 8.30 0x8000b78d 1.3106.0 [8086:1583] [15d9:084a] [ 139.329209] i40e 0000:02:00.1 enp2s0f1: renamed from eth0 ... [ 156.311376] BUG: kernel NULL pointer dereference, address: 00000000000006c2 [ 156.318330] #PF: supervisor write access in kernel mode [ 156.323546] #PF: error_code(0x0002) - not-present page [ 156.328679] PGD 0 P4D 0 [ 156.331210] Oops: 0002 [#1] PREEMPT SMP NOPTI [ 156.335567] CPU: 26 PID: 15119 Comm: reboot Tainted: G E 6.2.0+ #1 [ 156.343126] Hardware name: Abacus electric, s.r.o. - servis@abacus.cz Super Server/H12SSW-iN, BIOS 2.4 04/13/2022 [ 156.353369] RIP: 0010:i40e_shutdown+0x15/0x130 [i40e] [ 156.358430] Code: c1 fc ff ff 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa 0f 1f 44 00 00 55 48 89 fd 53 48 8b 9f 48 01 00 00 <f0> 80 8b c2 06 00 00 04 f0 80 8b c0 06 00 00 08 48 8d bb 08 08 00 [ 156.377168] RSP: 0018:ffffb223c8447d90 EFLAGS: 00010282 [ 156.382384] RAX: ffffffffc073ee70 RBX: 0000000000000000 RCX: 0000000000000001 [ 156.389510] RDX: 0000000080000001 RSI: 0000000000000246 RDI: ffff95db49988000 [ 156.396634] RBP: ffff95db49988000 R08: ffffffffffffffff R09: ffffffff8bd17d40 [ 156.403759] R10: 0000000000000001 R11: ffffffff8a5e3d28 R12: ffff95db49988000 [ 156.410882] R13: ffffffff89a6fe17 R14: ffff95db49988150 R15: 0000000000000000 [ 156.418007] FS: 00007fe7c0cc3980(0000) GS:ffff95ea8ee80000(0000) knlGS:0000000000000000 [ 156.426083] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 156.431819] CR2: 00000000000006c2 CR3: 00000003092fc005 CR4: 0000000000770ee0 [ 156.438944] PKRU: 55555554 [ 156.441647] Call Trace: [ 156.444096] <TASK> [ 156.446199] pci_device_shutdown+0x38/0x60 [ 156.450297] device_shutdown+0x163/0x210 [ 156.454215] kernel_restart+0x12/0x70 [ 156.457872] __do_sys_reboot+0x1ab/0x230 [ 156.461789] ? vfs_writev+0xa6/0x1a0 [ 156.465362] ? __pfx_file_free_rcu+0x10/0x10 [ 156.469635] ? __call_rcu_common.constprop.85+0x109/0x5a0 [ 156.475034] do_syscall_64+0x3e/0x90 [ 156.478611] entry_SYSCALL_64_after_hwframe+0x72/0xdc [ 156.483658] RIP: 0033:0x7fe7bff37ab7

Fixes: 4ff0ee1af016 ("i40e: Introduce recovery mode support") Signed-off-by: Ivan Vecera ivecera@redhat.com Tested-by: Arpana Arland arpanax.arland@intel.com (A Contingent worker at Intel) Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Link: https://lore.kernel.org/r/20230309184509.984639-1-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/i40e/i40e_main.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 52eec0a50492b..8328139db3795 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -15518,6 +15518,7 @@ static int i40e_init_recovery_mode(struct i40e_pf *pf, struct i40e_hw *hw) int err; int v_idx;

+ pci_set_drvdata(pf->pdev, pf); pci_save_state(pf->pdev);

/* set up periodic task facility */

From: Eugenio Pérez eperezma@redhat.com

[ Upstream commit 0e84f918fac8ae61dcb790534fad5e3555ca2930 ]

vdpasim_queue_ready calls vringh_init_iotlb, which resets split indexes. But it can be called after setting a ring base with vdpasim_set_vq_state.

Fix it by stashing them. They're still resetted in vdpasim_vq_reset.

This was discovered and tested live migrating the vdpa_sim_net device.

Fixes: 2c53d0f64c06 ("vdpasim: vDPA device simulator") Signed-off-by: Eugenio Pérez eperezma@redhat.com Message-Id: 20230118164359.1523760-2-eperezma@redhat.com Signed-off-by: Michael S. Tsirkin mst@redhat.com Acked-by: Jason Wang jasowang@redhat.com Tested-by: Lei Yang leiyang@redhat.com Stable-dep-of: b4cca6d48eb3 ("vdpa_sim: set last_used_idx as last_avail_idx in vdpasim_queue_ready") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/vdpa/vdpa_sim/vdpa_sim.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index cb88891b44a8c..8839232a3fcbc 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -66,6 +66,7 @@ static void vdpasim_vq_notify(struct vringh *vring) static void vdpasim_queue_ready(struct vdpasim *vdpasim, unsigned int idx) { struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx]; + uint16_t last_avail_idx = vq->vring.last_avail_idx;

vringh_init_iotlb(&vq->vring, vdpasim->features, vq->num, false, (struct vring_desc *)(uintptr_t)vq->desc_addr, @@ -74,6 +75,7 @@ static void vdpasim_queue_ready(struct vdpasim *vdpasim, unsigned int idx) (struct vring_used *) (uintptr_t)vq->device_addr);

+ vq->vring.last_avail_idx = last_avail_idx; vq->vring.notify = vdpasim_vq_notify; }

From: Niklas Schnelle schnelle@linux.ibm.com

[ Upstream commit ab909509850b27fd39b8ba99e44cda39dbc3858c ]

On s390 PCI functions may be hotplugged individually even when they belong to a multi-function device. In particular on an SR-IOV device VFs may be removed and later re-added.

In commit a50297cf8235 ("s390/pci: separate zbus creation from scanning") it was missed however that struct pci_bus and struct zpci_bus's resource list retained a reference to the PCI functions MMIO resources even though those resources are released and freed on hot-unplug. These stale resources may subsequently be claimed when the PCI function re-appears resulting in use-after-free.

One idea of fixing this use-after-free in s390 specific code that was investigated was to simply keep resources around from the moment a PCI function first appeared until the whole virtual PCI bus created for a multi-function device disappears. The problem with this however is that due to the requirement of artificial MMIO addreesses (address cookies) extra logic is then needed to keep the address cookies compatible on re-plug. At the same time the MMIO resources semantically belong to the PCI function so tying their lifecycle to the function seems more logical.

Instead a simpler approach is to remove the resources of an individually hot-unplugged PCI function from the PCI bus's resource list while keeping the resources of other PCI functions on the PCI bus untouched.

This is done by introducing pci_bus_remove_resource() to remove an individual resource. Similarly the resource also needs to be removed from the struct zpci_bus's resource list. It turns out however, that there is really no need to add the MMIO resources to the struct zpci_bus's resource list at all and instead we can simply use the zpci_bar_struct's resource pointer directly.

Fixes: a50297cf8235 ("s390/pci: separate zbus creation from scanning") Signed-off-by: Niklas Schnelle schnelle@linux.ibm.com Reviewed-by: Matthew Rosato mjrosato@linux.ibm.com Acked-by: Bjorn Helgaas bhelgaas@google.com Link: https://lore.kernel.org/r/20230306151014.60913-2-schnelle@linux.ibm.com Signed-off-by: Vasily Gorbik gor@linux.ibm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/s390/pci/pci.c | 16 ++++++++++------ arch/s390/pci/pci_bus.c | 12 +++++------- arch/s390/pci/pci_bus.h | 3 +-- drivers/pci/bus.c | 21 +++++++++++++++++++++ include/linux/pci.h | 1 + 5 files changed, 38 insertions(+), 15 deletions(-)

diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index ef38b1514c77a..e16afacc8fd1b 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -544,8 +544,7 @@ static struct resource *__alloc_res(struct zpci_dev *zdev, unsigned long start, return r; }

-int zpci_setup_bus_resources(struct zpci_dev *zdev, - struct list_head *resources) +int zpci_setup_bus_resources(struct zpci_dev *zdev) { unsigned long addr, size, flags; struct resource *res; @@ -581,7 +580,6 @@ int zpci_setup_bus_resources(struct zpci_dev *zdev, return -ENOMEM; } zdev->bars[i].res = res; - pci_add_resource(resources, res); } zdev->has_resources = 1;

@@ -590,17 +588,23 @@ int zpci_setup_bus_resources(struct zpci_dev *zdev,

static void zpci_cleanup_bus_resources(struct zpci_dev *zdev) { + struct resource *res; int i;

+ pci_lock_rescan_remove(); for (i = 0; i < PCI_STD_NUM_BARS; i++) { - if (!zdev->bars[i].size || !zdev->bars[i].res) + res = zdev->bars[i].res; + if (!res) continue;

+ release_resource(res); + pci_bus_remove_resource(zdev->zbus->bus, res); zpci_free_iomap(zdev, zdev->bars[i].map_idx); - release_resource(zdev->bars[i].res); - kfree(zdev->bars[i].res); + zdev->bars[i].res = NULL; + kfree(res); } zdev->has_resources = 0; + pci_unlock_rescan_remove(); }

int pcibios_device_add(struct pci_dev *pdev) diff --git a/arch/s390/pci/pci_bus.c b/arch/s390/pci/pci_bus.c index 6a8da1b742ae5..a99926af2b69a 100644 --- a/arch/s390/pci/pci_bus.c +++ b/arch/s390/pci/pci_bus.c @@ -41,9 +41,7 @@ static int zpci_nb_devices; */ static int zpci_bus_prepare_device(struct zpci_dev *zdev) { - struct resource_entry *window, *n; - struct resource *res; - int rc; + int rc, i;

if (!zdev_enabled(zdev)) { rc = zpci_enable_device(zdev); @@ -57,10 +55,10 @@ static int zpci_bus_prepare_device(struct zpci_dev *zdev) }

if (!zdev->has_resources) { - zpci_setup_bus_resources(zdev, &zdev->zbus->resources); - resource_list_for_each_entry_safe(window, n, &zdev->zbus->resources) { - res = window->res; - pci_bus_add_resource(zdev->zbus->bus, res, 0); + zpci_setup_bus_resources(zdev); + for (i = 0; i < PCI_STD_NUM_BARS; i++) { + if (zdev->bars[i].res) + pci_bus_add_resource(zdev->zbus->bus, zdev->bars[i].res, 0); } }

diff --git a/arch/s390/pci/pci_bus.h b/arch/s390/pci/pci_bus.h index e96c9860e0644..af9f0ac79a1b1 100644 --- a/arch/s390/pci/pci_bus.h +++ b/arch/s390/pci/pci_bus.h @@ -30,8 +30,7 @@ static inline void zpci_zdev_get(struct zpci_dev *zdev)

int zpci_alloc_domain(int domain); void zpci_free_domain(int domain); -int zpci_setup_bus_resources(struct zpci_dev *zdev, - struct list_head *resources); +int zpci_setup_bus_resources(struct zpci_dev *zdev);

static inline struct zpci_dev *zdev_from_bus(struct pci_bus *bus, unsigned int devfn) diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c index 83ae838ceb5f0..549c4bd5caeca 100644 --- a/drivers/pci/bus.c +++ b/drivers/pci/bus.c @@ -76,6 +76,27 @@ struct resource *pci_bus_resource_n(const struct pci_bus *bus, int n) } EXPORT_SYMBOL_GPL(pci_bus_resource_n);

+void pci_bus_remove_resource(struct pci_bus *bus, struct resource *res) +{ + struct pci_bus_resource *bus_res, *tmp; + int i; + + for (i = 0; i < PCI_BRIDGE_RESOURCE_NUM; i++) { + if (bus->resource[i] == res) { + bus->resource[i] = NULL; + return; + } + } + + list_for_each_entry_safe(bus_res, tmp, &bus->resources, list) { + if (bus_res->res == res) { + list_del(&bus_res->list); + kfree(bus_res); + return; + } + } +} + void pci_bus_remove_resources(struct pci_bus *bus) { int i; diff --git a/include/linux/pci.h b/include/linux/pci.h index 50042ea8e0083..db6ec828aa4b2 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1437,6 +1437,7 @@ void pci_bus_add_resource(struct pci_bus *bus, struct resource *res, unsigned int flags); struct resource *pci_bus_resource_n(const struct pci_bus *bus, int n); void pci_bus_remove_resources(struct pci_bus *bus); +void pci_bus_remove_resource(struct pci_bus *bus, struct resource *res); int devm_request_pci_bus_resources(struct device *dev, struct list_head *resources);

From: Andrea Righi andrea.righi@canonical.com

[ Upstream commit 193c41926d152761764894f46e23b53c00186a82 ]

It seems that commit bc3c5e0809ae ("drm/i915/sseu: Don't try to store EU mask internally in UAPI format") exposed a potential out-of-bounds access, reported by UBSAN as following on a laptop with a gen 11 i915 card:

UBSAN: array-index-out-of-bounds in drivers/gpu/drm/i915/gt/intel_sseu.c:65:27 index 6 is out of range for type 'u16 [6]' CPU: 2 PID: 165 Comm: systemd-udevd Not tainted 6.2.0-9-generic #9-Ubuntu Hardware name: Dell Inc. XPS 13 9300/077Y9N, BIOS 1.11.0 03/22/2022 Call Trace: <TASK> show_stack+0x4e/0x61 dump_stack_lvl+0x4a/0x6f dump_stack+0x10/0x18 ubsan_epilogue+0x9/0x3a __ubsan_handle_out_of_bounds.cold+0x42/0x47 gen11_compute_sseu_info+0x121/0x130 [i915] intel_sseu_info_init+0x15d/0x2b0 [i915] intel_gt_init_mmio+0x23/0x40 [i915] i915_driver_mmio_probe+0x129/0x400 [i915] ? intel_gt_probe_all+0x91/0x2e0 [i915] i915_driver_probe+0xe1/0x3f0 [i915] ? drm_privacy_screen_get+0x16d/0x190 [drm] ? acpi_dev_found+0x64/0x80 i915_pci_probe+0xac/0x1b0 [i915] ...

According to the definition of sseu_dev_info, eu_mask->hsw is limited to a maximum of GEN_MAX_SS_PER_HSW_SLICE (6) sub-slices, but gen11_sseu_info_init() can potentially set 8 sub-slices, in the !IS_JSL_EHL(gt->i915) case.

Fix this by reserving up to 8 slots for max_subslices in the eu_mask struct.

Reported-by: Emil Renner Berthing emil.renner.berthing@canonical.com Signed-off-by: Andrea Righi andrea.righi@canonical.com Fixes: bc3c5e0809ae ("drm/i915/sseu: Don't try to store EU mask internally in UAPI format") Reviewed-by: Matt Roper matthew.d.roper@intel.com Signed-off-by: Matt Roper matthew.d.roper@intel.com Link: https://patchwork.freedesktop.org/patch/msgid/20230220171858.131416-1-andrea... (cherry picked from commit 3cba09a6ac86ea1d456909626eb2685596c07822) Signed-off-by: Jani Nikula jani.nikula@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/i915/gt/intel_sseu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.h b/drivers/gpu/drm/i915/gt/intel_sseu.h index aa87d3832d60d..d7e8c374f153e 100644 --- a/drivers/gpu/drm/i915/gt/intel_sseu.h +++ b/drivers/gpu/drm/i915/gt/intel_sseu.h @@ -27,7 +27,7 @@ struct drm_printer; * is only relevant to pre-Xe_HP platforms (Xe_HP and beyond use the * I915_MAX_SS_FUSE_BITS value below). */ -#define GEN_MAX_SS_PER_HSW_SLICE 6 +#define GEN_MAX_SS_PER_HSW_SLICE 8

/* * Maximum number of 32-bit registers used by hardware to express the

From: D. Wythe alibuda@linux.alibaba.com

[ Upstream commit 22a825c541d775c1dbe7b2402786025acad6727b ]

When performing a stress test on SMC-R by rmmod mlx5_ib driver during the wrk/nginx test, we found that there is a probability of triggering a panic while terminating all link groups.

This issue dues to the race between smc_smcr_terminate_all() and smc_buf_create().

smc_smcr_terminate_all

smc_buf_create /* init */ conn->sndbuf_desc = NULL; ...

__smc_lgr_terminate smc_conn_kill smc_close_abort smc_cdc_get_slot_and_msg_send

__softirqentry_text_start smc_wr_tx_process_cqe smc_cdc_tx_handler READ(conn->sndbuf_desc->len); /* panic dues to NULL sndbuf_desc */

conn->sndbuf_desc = xxx;

This patch tries to fix the issue by always to check the sndbuf_desc before send any cdc msg, to make sure that no null pointer is seen during cqe processing.

Fixes: 0b29ec643613 ("net/smc: immediate termination for SMCR link groups") Signed-off-by: D. Wythe alibuda@linux.alibaba.com Reviewed-by: Tony Lu tonylu@linux.alibaba.com Reviewed-by: Wenjia Zhang wenjia@linux.ibm.com Link: https://lore.kernel.org/r/1678263432-17329-1-git-send-email-alibuda@linux.al... Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/smc/smc_cdc.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index 53f63bfbaf5f9..89105e95b4523 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -114,6 +114,9 @@ int smc_cdc_msg_send(struct smc_connection *conn, union smc_host_cursor cfed; int rc;

+ if (unlikely(!READ_ONCE(conn->sndbuf_desc))) + return -ENOBUFS; + smc_cdc_add_pending_send(conn, pend);

conn->tx_cdc_seq++;

From: Arınç ÜNAL arinc.unal@arinc9.com

[ Upstream commit feb03fd11c5616f3a47e4714d2f9917d0f1a2edd ]

Remove now incorrect comment regarding port 5 as GMAC5. This is supposed to be supported since commit 38f790a80560 ("net: dsa: mt7530: Add support for port 5") under mt7530_setup_port5().

Fixes: 38f790a80560 ("net: dsa: mt7530: Add support for port 5") Signed-off-by: Arınç ÜNAL arinc.unal@arinc9.com Link: https://lore.kernel.org/r/20230310073338.5836-1-arinc.unal@arinc9.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/dsa/mt7530.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 003672d71a3bf..9876aedc0f360 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -2206,7 +2206,7 @@ mt7530_setup(struct dsa_switch *ds)

mt7530_pll_setup(priv);

- /* Enable Port 6 only; P5 as GMAC5 which currently is not supported */ + /* Enable port 6 */ val = mt7530_read(priv, MT7530_MHWTRAP); val &= ~MHWTRAP_P6_DIS & ~MHWTRAP_PHY_ACCESS; val |= MHWTRAP_MANUAL;

From: Jan Kara jack@suse.cz

[ Upstream commit 34e0a279a993debaff03158fc2fbf6a00c093643 ]

Commit 26fed4ac4eab ("block: flush plug based on hardware and software queue order") changed flushing of plug list to submit requests one device at a time. However while doing that it also started using list_add_tail() instead of list_add() used previously thus effectively submitting requests in reverse order. Also when forming a rq_list with remaining requests (in case two or more devices are used), we effectively reverse the ordering of the plug list for each device we process. Submitting requests in reverse order has negative impact on performance for rotational disks (when BFQ is not in use). We observe 10-25% regression in random 4k write throughput, as well as ~20% regression in MariaDB OLTP benchmark on rotational storage on btrfs filesystem.

Fix the problem by preserving ordering of the plug list when inserting requests into the queuelist as well as by appending to requeue_list instead of prepending to it.

Fixes: 26fed4ac4eab ("block: flush plug based on hardware and software queue order") Signed-off-by: Jan Kara jack@suse.cz Reviewed-by: Christoph Hellwig hch@lst.de Link: https://lore.kernel.org/r/20230313093002.11756-1-jack@suse.cz Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- block/blk-mq.c | 5 +++-- include/linux/blk-mq.h | 6 ++++++ 2 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c index b9e3b558367f1..c021fb05161b9 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2743,6 +2743,7 @@ static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched) struct blk_mq_hw_ctx *this_hctx = NULL; struct blk_mq_ctx *this_ctx = NULL; struct request *requeue_list = NULL; + struct request **requeue_lastp = &requeue_list; unsigned int depth = 0; LIST_HEAD(list);

@@ -2753,10 +2754,10 @@ static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched) this_hctx = rq->mq_hctx; this_ctx = rq->mq_ctx; } else if (this_hctx != rq->mq_hctx || this_ctx != rq->mq_ctx) { - rq_list_add(&requeue_list, rq); + rq_list_add_tail(&requeue_lastp, rq); continue; } - list_add_tail(&rq->queuelist, &list); + list_add(&rq->queuelist, &list); depth++; } while (!rq_list_empty(plug->mq_list));

diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 779fba613bd09..19ae71f3fb97d 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -228,6 +228,12 @@ static inline unsigned short req_get_ioprio(struct request *req) *(listptr) = rq; \ } while (0)

+#define rq_list_add_tail(lastpptr, rq) do { \ + (rq)->rq_next = NULL; \ + **(lastpptr) = rq; \ + *(lastpptr) = &rq->rq_next; \ +} while (0) + #define rq_list_pop(listptr) \ ({ \ struct request *__req = NULL; \

From: Chris Leech cleech@redhat.com

[ Upstream commit 00e885efcfbb8712d3e1bfc1ae30639c15ca1d3b ]

The 'q' parameter of the macro __blk_mq_run_dispatch_ops may not be one local variable, such as, it is rq->q, then request queue pointed by this variable could be changed to another queue in case of BLK_MQ_F_TAG_QUEUE_SHARED after 'dispatch_ops' returns, then 'bad unlock balance' is triggered.

Fixes the issue by adding one local variable for doing srcu lock/unlock.

Fixes: 2a904d00855f ("blk-mq: remove hctx_lock and hctx_unlock") Cc: Marco Patalano mpatalan@redhat.com Signed-off-by: Chris Leech cleech@redhat.com Signed-off-by: Ming Lei ming.lei@redhat.com Link: https://lore.kernel.org/r/20230310010913.1014789-1-ming.lei@redhat.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- block/blk-mq.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/block/blk-mq.h b/block/blk-mq.h index ef59fee62780d..a7482d2cc82e7 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -378,12 +378,13 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx, #define __blk_mq_run_dispatch_ops(q, check_sleep, dispatch_ops) \ do { \ if ((q)->tag_set->flags & BLK_MQ_F_BLOCKING) { \ + struct blk_mq_tag_set *__tag_set = (q)->tag_set; \ int srcu_idx; \ \ might_sleep_if(check_sleep); \ - srcu_idx = srcu_read_lock((q)->tag_set->srcu); \ + srcu_idx = srcu_read_lock(__tag_set->srcu); \ (dispatch_ops); \ - srcu_read_unlock((q)->tag_set->srcu, srcu_idx); \ + srcu_read_unlock(__tag_set->srcu, srcu_idx); \ } else { \ rcu_read_lock(); \ (dispatch_ops); \

From: Heiner Kallweit hkallweit1@gmail.com

[ Upstream commit c22c3bbf351e4ce905f082649cffa1ff893ea8c1 ]

If genphy_read_status fails then further access to the PHY may result in unpredictable behavior. To prevent this bail out immediately if genphy_read_status fails.

Fixes: 4223dbffed9f ("net: phy: smsc: Re-enable EDPD mode for LAN87xx") Signed-off-by: Heiner Kallweit hkallweit1@gmail.com Reviewed-by: Simon Horman simon.horman@corigine.com Link: https://lore.kernel.org/r/026aa4f2-36f5-1c10-ab9f-cdb17dda6ac4@gmail.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/phy/smsc.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c index 00d9eff91dcfa..df2c5435c5c49 100644 --- a/drivers/net/phy/smsc.c +++ b/drivers/net/phy/smsc.c @@ -199,8 +199,11 @@ static int lan95xx_config_aneg_ext(struct phy_device *phydev) static int lan87xx_read_status(struct phy_device *phydev) { struct smsc_phy_priv *priv = phydev->priv; + int err;

- int err = genphy_read_status(phydev); + err = genphy_read_status(phydev); + if (err) + return err;

if (!phydev->link && priv->energy_enable && phydev->irq == PHY_POLL) { /* Disable EDPD to wake up PHY */

From: Zheng Wang zyytlz.wz@163.com

[ Upstream commit 5000fe6c27827a61d8250a7e4a1d26c3298ef4f6 ]

This bug influences both st_nci_i2c_remove and st_nci_spi_remove. Take st_nci_i2c_remove as an example.

In st_nci_i2c_probe, it called ndlc_probe and bound &ndlc->sm_work with llt_ndlc_sm_work.

When it calls ndlc_recv or timeout handler, it will finally call schedule_work to start the work.

When we call st_nci_i2c_remove to remove the driver, there may be a sequence as follows:

Fix it by finishing the work before cleanup in ndlc_remove

CPU0 CPU1

|llt_ndlc_sm_work st_nci_i2c_remove | ndlc_remove | st_nci_remove | nci_free_device| kfree(ndev) | //free ndlc->ndev | |llt_ndlc_rcv_queue |nci_recv_frame |//use ndlc->ndev

Fixes: 35630df68d60 ("NFC: st21nfcb: Add driver for STMicroelectronics ST21NFCB NFC chip") Signed-off-by: Zheng Wang zyytlz.wz@163.com Reviewed-by: Krzysztof Kozlowski krzysztof.kozlowski@linaro.org Link: https://lore.kernel.org/r/20230312160837.2040857-1-zyytlz.wz@163.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nfc/st-nci/ndlc.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/nfc/st-nci/ndlc.c b/drivers/nfc/st-nci/ndlc.c index 755460a73c0dc..d2aa9f766738e 100644 --- a/drivers/nfc/st-nci/ndlc.c +++ b/drivers/nfc/st-nci/ndlc.c @@ -282,13 +282,15 @@ EXPORT_SYMBOL(ndlc_probe);

void ndlc_remove(struct llt_ndlc *ndlc) { - st_nci_remove(ndlc->ndev); - /* cancel timers */ del_timer_sync(&ndlc->t1_timer); del_timer_sync(&ndlc->t2_timer); ndlc->t2_active = false; ndlc->t1_active = false; + /* cancel work */ + cancel_work_sync(&ndlc->sm_work); + + st_nci_remove(ndlc->ndev);

skb_queue_purge(&ndlc->rcv_q); skb_queue_purge(&ndlc->send_q);

From: Wenjia Zhang wenjia@linux.ibm.com

[ Upstream commit 13085e1b5cab8ad802904d72e6a6dae85ae0cd20 ]

The following LOCKDEP was detected: Workqueue: events smc_lgr_free_work [smc] WARNING: possible circular locking dependency detected 6.1.0-20221027.rc2.git8.56bc5b569087.300.fc36.s390x+debug #1 Not tainted ------------------------------------------------------ kworker/3:0/176251 is trying to acquire lock: 00000000f1467148 ((wq_completion)smc_tx_wq-00000000#2){+.+.}-{0:0}, at: __flush_workqueue+0x7a/0x4f0 but task is already holding lock: 0000037fffe97dc8 ((work_completion)(&(&lgr->free_work)->work)){+.+.}-{0:0}, at: process_one_work+0x232/0x730 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #4 ((work_completion)(&(&lgr->free_work)->work)){+.+.}-{0:0}: __lock_acquire+0x58e/0xbd8 lock_acquire.part.0+0xe2/0x248 lock_acquire+0xac/0x1c8 __flush_work+0x76/0xf0 __cancel_work_timer+0x170/0x220 __smc_lgr_terminate.part.0+0x34/0x1c0 [smc] smc_connect_rdma+0x15e/0x418 [smc] __smc_connect+0x234/0x480 [smc] smc_connect+0x1d6/0x230 [smc] __sys_connect+0x90/0xc0 __do_sys_socketcall+0x186/0x370 __do_syscall+0x1da/0x208 system_call+0x82/0xb0 -> #3 (smc_client_lgr_pending){+.+.}-{3:3}: __lock_acquire+0x58e/0xbd8 lock_acquire.part.0+0xe2/0x248 lock_acquire+0xac/0x1c8 __mutex_lock+0x96/0x8e8 mutex_lock_nested+0x32/0x40 smc_connect_rdma+0xa4/0x418 [smc] __smc_connect+0x234/0x480 [smc] smc_connect+0x1d6/0x230 [smc] __sys_connect+0x90/0xc0 __do_sys_socketcall+0x186/0x370 __do_syscall+0x1da/0x208 system_call+0x82/0xb0 -> #2 (sk_lock-AF_SMC){+.+.}-{0:0}: __lock_acquire+0x58e/0xbd8 lock_acquire.part.0+0xe2/0x248 lock_acquire+0xac/0x1c8 lock_sock_nested+0x46/0xa8 smc_tx_work+0x34/0x50 [smc] process_one_work+0x30c/0x730 worker_thread+0x62/0x420 kthread+0x138/0x150 __ret_from_fork+0x3c/0x58 ret_from_fork+0xa/0x40 -> #1 ((work_completion)(&(&smc->conn.tx_work)->work)){+.+.}-{0:0}: __lock_acquire+0x58e/0xbd8 lock_acquire.part.0+0xe2/0x248 lock_acquire+0xac/0x1c8 process_one_work+0x2bc/0x730 worker_thread+0x62/0x420 kthread+0x138/0x150 __ret_from_fork+0x3c/0x58 ret_from_fork+0xa/0x40 -> #0 ((wq_completion)smc_tx_wq-00000000#2){+.+.}-{0:0}: check_prev_add+0xd8/0xe88 validate_chain+0x70c/0xb20 __lock_acquire+0x58e/0xbd8 lock_acquire.part.0+0xe2/0x248 lock_acquire+0xac/0x1c8 __flush_workqueue+0xaa/0x4f0 drain_workqueue+0xaa/0x158 destroy_workqueue+0x44/0x2d8 smc_lgr_free+0x9e/0xf8 [smc] process_one_work+0x30c/0x730 worker_thread+0x62/0x420 kthread+0x138/0x150 __ret_from_fork+0x3c/0x58 ret_from_fork+0xa/0x40 other info that might help us debug this: Chain exists of: (wq_completion)smc_tx_wq-00000000#2 --> smc_client_lgr_pending --> (work_completion)(&(&lgr->free_work)->work) Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock((work_completion)(&(&lgr->free_work)->work)); lock(smc_client_lgr_pending); lock((work_completion) (&(&lgr->free_work)->work)); lock((wq_completion)smc_tx_wq-00000000#2); *** DEADLOCK *** 2 locks held by kworker/3:0/176251: #0: 0000000080183548 ((wq_completion)events){+.+.}-{0:0}, at: process_one_work+0x232/0x730 #1: 0000037fffe97dc8 ((work_completion) (&(&lgr->free_work)->work)){+.+.}-{0:0}, at: process_one_work+0x232/0x730 stack backtrace: CPU: 3 PID: 176251 Comm: kworker/3:0 Not tainted Hardware name: IBM 8561 T01 701 (z/VM 7.2.0) Call Trace: [<000000002983c3e4>] dump_stack_lvl+0xac/0x100 [<0000000028b477ae>] check_noncircular+0x13e/0x160 [<0000000028b48808>] check_prev_add+0xd8/0xe88 [<0000000028b49cc4>] validate_chain+0x70c/0xb20 [<0000000028b4bd26>] __lock_acquire+0x58e/0xbd8 [<0000000028b4cf6a>] lock_acquire.part.0+0xe2/0x248 [<0000000028b4d17c>] lock_acquire+0xac/0x1c8 [<0000000028addaaa>] __flush_workqueue+0xaa/0x4f0 [<0000000028addf9a>] drain_workqueue+0xaa/0x158 [<0000000028ae303c>] destroy_workqueue+0x44/0x2d8 [<000003ff8029af26>] smc_lgr_free+0x9e/0xf8 [smc] [<0000000028adf3d4>] process_one_work+0x30c/0x730 [<0000000028adf85a>] worker_thread+0x62/0x420 [<0000000028aeac50>] kthread+0x138/0x150 [<0000000028a63914>] __ret_from_fork+0x3c/0x58 [<00000000298503da>] ret_from_fork+0xa/0x40 INFO: lockdep is turned off. ===================================================================

This deadlock occurs because cancel_delayed_work_sync() waits for the work(&lgr->free_work) to finish, while the &lgr->free_work waits for the work(lgr->tx_wq), which needs the sk_lock-AF_SMC, that is already used under the mutex_lock.

The solution is to use cancel_delayed_work() instead, which kills off a pending work.

Fixes: a52bcc919b14 ("net/smc: improve termination processing") Signed-off-by: Wenjia Zhang wenjia@linux.ibm.com Reviewed-by: Jan Karcher jaka@linux.ibm.com Reviewed-by: Karsten Graul kgraul@linux.ibm.com Reviewed-by: Tony Lu tonylu@linux.alibaba.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/smc/smc_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index c19d4b7c1f28a..0208dfb353456 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -1459,7 +1459,7 @@ static void __smc_lgr_terminate(struct smc_link_group *lgr, bool soft) if (lgr->terminating) return; /* lgr already terminating */ /* cancel free_work sync, will terminate when lgr->freeing is set */ - cancel_delayed_work_sync(&lgr->free_work); + cancel_delayed_work(&lgr->free_work); lgr->terminating = 1;

/* kill remaining link group connections */

From: Daniel Golle daniel@makrotopia.org

[ Upstream commit 611e2dabb4b3243d176739fd6a5a34d007fa3f86 ]

Reset the internal PCS state machine when changing interface mode. This prevents confusing the state machine when changing interface modes, e.g. from SGMII to 2500Base-X or vice-versa.

Fixes: 7e538372694b ("net: ethernet: mediatek: Re-add support SGMII") Reviewed-by: Russell King (Oracle) rmk+kernel@armlinux.org.uk Tested-by: Bjørn Mork bjorn@mork.no Signed-off-by: Daniel Golle daniel@makrotopia.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mediatek/mtk_eth_soc.h | 4 ++++ drivers/net/ethernet/mediatek/mtk_sgmii.c | 4 ++++ 2 files changed, 8 insertions(+)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index b481d0d46bb16..d4b4f9eaa4419 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -528,6 +528,10 @@ #define SGMII_SEND_AN_ERROR_EN BIT(11) #define SGMII_IF_MODE_MASK GENMASK(5, 1)

+/* Register to reset SGMII design */ +#define SGMII_RESERVED_0 0x34 +#define SGMII_SW_RESET BIT(0) + /* Register to set SGMII speed, ANA RG_ Control Signals III*/ #define SGMSYS_ANA_RG_CS3 0x2028 #define RG_PHY_SPEED_MASK (BIT(2) | BIT(3)) diff --git a/drivers/net/ethernet/mediatek/mtk_sgmii.c b/drivers/net/ethernet/mediatek/mtk_sgmii.c index bb00de1003ac4..612f65bb03454 100644 --- a/drivers/net/ethernet/mediatek/mtk_sgmii.c +++ b/drivers/net/ethernet/mediatek/mtk_sgmii.c @@ -88,6 +88,10 @@ static int mtk_pcs_config(struct phylink_pcs *pcs, unsigned int mode, regmap_update_bits(mpcs->regmap, SGMSYS_QPHY_PWR_STATE_CTRL, SGMII_PHYA_PWD, SGMII_PHYA_PWD);

+ /* Reset SGMII PCS state */ + regmap_update_bits(mpcs->regmap, SGMII_RESERVED_0, + SGMII_SW_RESET, SGMII_SW_RESET); + if (interface == PHY_INTERFACE_MODE_2500BASEX) rgc3 = RG_PHY_SPEED_3_125G; else

From: Liu Ying victor.liu@nxp.com

[ Upstream commit 0d3c9333d976af41d7dbc6bf4d9d2e95fbdf9c89 ]

The returned array size for input formats is set through atomic_get_input_bus_fmts()'s 'num_input_fmts' argument, so use 'num_input_fmts' to represent the array size in the function's kdoc, not 'num_output_fmts'.

Fixes: 91ea83306bfa ("drm/bridge: Fix the bridge kernel doc") Fixes: f32df58acc68 ("drm/bridge: Add the necessary bits to support bus format negotiation") Signed-off-by: Liu Ying victor.liu@nxp.com Reviewed-by: Robert Foss rfoss@kernel.org Signed-off-by: Neil Armstrong neil.armstrong@linaro.org Link: https://patchwork.freedesktop.org/patch/msgid/20230314055035.3731179-1-victo... Signed-off-by: Sasha Levin sashal@kernel.org --- include/drm/drm_bridge.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/drm/drm_bridge.h b/include/drm/drm_bridge.h index 6b65b0dfb4fb4..288c6feda5de2 100644 --- a/include/drm/drm_bridge.h +++ b/include/drm/drm_bridge.h @@ -447,11 +447,11 @@ struct drm_bridge_funcs { * * The returned array must be allocated with kmalloc() and will be * freed by the caller. If the allocation fails, NULL should be - * returned. num_output_fmts must be set to the returned array size. + * returned. num_input_fmts must be set to the returned array size. * Formats listed in the returned array should be listed in decreasing * preference order (the core will try all formats until it finds one * that works). When the format is not supported NULL should be - * returned and num_output_fmts should be set to 0. + * returned and num_input_fmts should be set to 0. * * This method is called on all elements of the bridge chain as part of * the bus format negotiation process that happens in

From: Damien Le Moal damien.lemoal@opensource.wdc.com

[ Upstream commit 63f886597085f346276e3b3c8974de0100d65f32 ]

When injecting a fake timeout into the null_blk driver using fail_io_timeout, the request timeout handler does not execute blk_mq_complete_request(), so the complete callback is never executed for a timedout request.

The null_blk driver also has a driver-specific fake timeout mechanism which does not have this problem. Fix the problem with fail_io_timeout by using the same meachanism as null_blk internal timeout feature, using the fake_timeout field of null_blk commands.

Reported-by: Akinobu Mita akinobu.mita@gmail.com Fixes: de3510e52b0a ("null_blk: fix command timeout completion handling") Signed-off-by: Damien Le Moal damien.lemoal@opensource.wdc.com Reviewed-by: Johannes Thumshirn johannes.thumshirn@wdc.com Link: https://lore.kernel.org/r/20230314041106.19173-2-damien.lemoal@opensource.wd... Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/block/null_blk/main.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index 7d28e3aa406c2..a200aba02e436 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -1413,8 +1413,7 @@ static inline void nullb_complete_cmd(struct nullb_cmd *cmd) case NULL_IRQ_SOFTIRQ: switch (cmd->nq->dev->queue_mode) { case NULL_Q_MQ: - if (likely(!blk_should_fake_timeout(cmd->rq->q))) - blk_mq_complete_request(cmd->rq); + blk_mq_complete_request(cmd->rq); break; case NULL_Q_BIO: /* @@ -1675,7 +1674,8 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx, cmd->rq = bd->rq; cmd->error = BLK_STS_OK; cmd->nq = nq; - cmd->fake_timeout = should_timeout_request(bd->rq); + cmd->fake_timeout = should_timeout_request(bd->rq) || + blk_should_fake_timeout(bd->rq->q);

blk_mq_start_request(bd->rq);

From: Damien Le Moal damien.lemoal@opensource.wdc.com

[ Upstream commit 6173a77b7e9d3e202bdb9897b23f2a8afe7bf286 ]

An nvme target ->queue_response() operation implementation may free the request passed as argument. Such implementation potentially could result in a use after free of the request pointer when percpu_ref_put() is called in nvmet_req_complete().

Avoid such problem by using a local variable to save the sq pointer before calling __nvmet_req_complete(), thus avoiding dereferencing the req pointer after that function call.

Fixes: a07b4970f464 ("nvmet: add a generic NVMe target") Signed-off-by: Damien Le Moal damien.lemoal@opensource.wdc.com Reviewed-by: Chaitanya Kulkarni kch@nvidia.com Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/target/core.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index f66ed13d7c11d..3935165048e74 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -756,8 +756,10 @@ static void __nvmet_req_complete(struct nvmet_req *req, u16 status)

void nvmet_req_complete(struct nvmet_req *req, u16 status) { + struct nvmet_sq *sq = req->sq; + __nvmet_req_complete(req, status); - percpu_ref_put(&req->sq->ref); + percpu_ref_put(&sq->ref); } EXPORT_SYMBOL_GPL(nvmet_req_complete);

From: Yu Kuai yukuai3@huawei.com

[ Upstream commit 5f27571382ca42daa3e3d40d1b252bf18c2b61d2 ]

While using iostat for raid, I observed very strange 'await' occasionally, and turns out it's due to that 'ios' and 'sectors' is counted in bdev_start_io_acct(), while 'nsecs' is counted in bdev_end_io_acct(). I'm not sure why they are ccounted like that but I think this behaviour is obviously wrong because user will get wrong disk stats.

Fix the problem by counting 'ios' and 'sectors' when io is done, like what rq-based device does.

Fixes: 394ffa503bc4 ("blk: introduce generic io stat accounting help function") Signed-off-by: Yu Kuai yukuai3@huawei.com Reviewed-by: Christoph Hellwig hch@lst.de Link: https://lore.kernel.org/r/20230223091226.1135678-1-yukuai1@huaweicloud.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- block/blk-core.c | 16 ++++++---------- drivers/block/zram/zram_drv.c | 4 ++-- drivers/md/dm.c | 6 +++--- drivers/nvme/host/multipath.c | 8 ++++---- include/linux/blkdev.h | 5 ++--- 5 files changed, 17 insertions(+), 22 deletions(-)

diff --git a/block/blk-core.c b/block/blk-core.c index 5a0049215ee72..597293151cd11 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -946,16 +946,11 @@ void update_io_ticks(struct block_device *part, unsigned long now, bool end) } }

-unsigned long bdev_start_io_acct(struct block_device *bdev, - unsigned int sectors, enum req_op op, +unsigned long bdev_start_io_acct(struct block_device *bdev, enum req_op op, unsigned long start_time) { - const int sgrp = op_stat_group(op); - part_stat_lock(); update_io_ticks(bdev, start_time, false); - part_stat_inc(bdev, ios[sgrp]); - part_stat_add(bdev, sectors[sgrp], sectors); part_stat_local_inc(bdev, in_flight[op_is_write(op)]); part_stat_unlock();

@@ -971,13 +966,12 @@ EXPORT_SYMBOL(bdev_start_io_acct); */ unsigned long bio_start_io_acct(struct bio *bio) { - return bdev_start_io_acct(bio->bi_bdev, bio_sectors(bio), - bio_op(bio), jiffies); + return bdev_start_io_acct(bio->bi_bdev, bio_op(bio), jiffies); } EXPORT_SYMBOL_GPL(bio_start_io_acct);

void bdev_end_io_acct(struct block_device *bdev, enum req_op op, - unsigned long start_time) + unsigned int sectors, unsigned long start_time) { const int sgrp = op_stat_group(op); unsigned long now = READ_ONCE(jiffies); @@ -985,6 +979,8 @@ void bdev_end_io_acct(struct block_device *bdev, enum req_op op,

part_stat_lock(); update_io_ticks(bdev, now, true); + part_stat_inc(bdev, ios[sgrp]); + part_stat_add(bdev, sectors[sgrp], sectors); part_stat_add(bdev, nsecs[sgrp], jiffies_to_nsecs(duration)); part_stat_local_dec(bdev, in_flight[op_is_write(op)]); part_stat_unlock(); @@ -994,7 +990,7 @@ EXPORT_SYMBOL(bdev_end_io_acct); void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time, struct block_device *orig_bdev) { - bdev_end_io_acct(orig_bdev, bio_op(bio), start_time); + bdev_end_io_acct(orig_bdev, bio_op(bio), bio_sectors(bio), start_time); } EXPORT_SYMBOL_GPL(bio_end_io_acct_remapped);

diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index e290d6d970474..03ef03e10618d 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -2108,9 +2108,9 @@ static int zram_rw_page(struct block_device *bdev, sector_t sector, bv.bv_offset = 0;

start_time = bdev_start_io_acct(bdev->bd_disk->part0, - SECTORS_PER_PAGE, op, jiffies); + op, jiffies); ret = zram_bvec_rw(zram, &bv, index, offset, op, NULL); - bdev_end_io_acct(bdev->bd_disk->part0, op, start_time); + bdev_end_io_acct(bdev->bd_disk->part0, op, SECTORS_PER_PAGE, start_time); out: /* * If I/O fails, just return error(ie, non-zero) without diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 605662935ce91..fdcf42554e2a9 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -510,10 +510,10 @@ static void dm_io_acct(struct dm_io *io, bool end) sectors = io->sectors;

if (!end) - bdev_start_io_acct(bio->bi_bdev, sectors, bio_op(bio), - start_time); + bdev_start_io_acct(bio->bi_bdev, bio_op(bio), start_time); else - bdev_end_io_acct(bio->bi_bdev, bio_op(bio), start_time); + bdev_end_io_acct(bio->bi_bdev, bio_op(bio), sectors, + start_time);

if (static_branch_unlikely(&stats_enabled) && unlikely(dm_stats_used(&md->stats))) { diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index fc39d01e7b63b..9171452e2f6d4 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -123,9 +123,8 @@ void nvme_mpath_start_request(struct request *rq) return;

nvme_req(rq)->flags |= NVME_MPATH_IO_STATS; - nvme_req(rq)->start_time = bdev_start_io_acct(disk->part0, - blk_rq_bytes(rq) >> SECTOR_SHIFT, - req_op(rq), jiffies); + nvme_req(rq)->start_time = bdev_start_io_acct(disk->part0, req_op(rq), + jiffies); } EXPORT_SYMBOL_GPL(nvme_mpath_start_request);

@@ -136,7 +135,8 @@ void nvme_mpath_end_request(struct request *rq) if (!(nvme_req(rq)->flags & NVME_MPATH_IO_STATS)) return; bdev_end_io_acct(ns->head->disk->part0, req_op(rq), - nvme_req(rq)->start_time); + blk_rq_bytes(rq) >> SECTOR_SHIFT, + nvme_req(rq)->start_time); }

void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 43d4e073b1115..c3e066242941d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1434,11 +1434,10 @@ static inline void blk_wake_io_task(struct task_struct *waiter) wake_up_process(waiter); }

-unsigned long bdev_start_io_acct(struct block_device *bdev, - unsigned int sectors, enum req_op op, +unsigned long bdev_start_io_acct(struct block_device *bdev, enum req_op op, unsigned long start_time); void bdev_end_io_acct(struct block_device *bdev, enum req_op op, - unsigned long start_time); + unsigned int sectors, unsigned long start_time);

unsigned long bio_start_io_acct(struct bio *bio); void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time,

From: Parav Pandit parav@nvidia.com

[ Upstream commit 9a92fe1db9e57ea94388a1d768e8ee42af858377 ]

When mlx5e attaches again after device health recovery, the device capabilities might have changed by the eswitch manager.

For example in one flow when ECPF changes the eswitch mode between legacy and switchdev, it updates the flow table tunnel capability.

The cached value is only used in one place, so just check the capability there instead.

Fixes: 5bef709d76a2 ("net/mlx5: Enable host PF HCA after eswitch is initialized") Signed-off-by: Parav Pandit parav@nvidia.com Signed-off-by: Daniel Jurgens danielj@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 1 - drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 4 +--- drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 1 - drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 1 - 4 files changed, 1 insertion(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 2d77fb8a8a015..ae73c9af8f251 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -313,7 +313,6 @@ struct mlx5e_params { } channel; } mqprio; bool rx_cqe_compress_def; - bool tunneled_offload_en; struct dim_cq_moder rx_cq_moderation; struct dim_cq_moder tx_cq_moderation; struct mlx5e_packet_merge_param packet_merge; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 6c24f33a5ea5c..d6bcbc17151d7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -4923,8 +4923,6 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16 /* TX inline */ mlx5_query_min_inline(mdev, &params->tx_min_inline_mode);

- params->tunneled_offload_en = mlx5_tunnel_inner_ft_supported(mdev); - /* AF_XDP */ params->xsk = xsk;

@@ -5223,7 +5221,7 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv) }

features = MLX5E_RX_RES_FEATURE_PTP; - if (priv->channels.params.tunneled_offload_en) + if (mlx5_tunnel_inner_ft_supported(mdev)) features |= MLX5E_RX_RES_FEATURE_INNER_FT; err = mlx5e_rx_res_init(priv->rx_res, priv->mdev, features, priv->max_nch, priv->drop_rq.rqn, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 7d90e5b728548..301a734b7c6a7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -752,7 +752,6 @@ static void mlx5e_build_rep_params(struct net_device *netdev) mlx5e_set_rx_cq_mode_params(params, cq_period_mode);

params->mqprio.num_tc = 1; - params->tunneled_offload_en = false; if (rep->vport != MLX5_VPORT_UPLINK) params->vlan_strip_disable = true;

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 911cf4d239645..4285b31fee6c4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -70,7 +70,6 @@ static void mlx5i_build_nic_params(struct mlx5_core_dev *mdev,

params->packet_merge.type = MLX5E_PACKET_MERGE_NONE; params->hard_mtu = MLX5_IB_GRH_BYTES + MLX5_IPOIB_HARD_LEN; - params->tunneled_offload_en = false;

/* CQE compression is not supported for IPoIB */ params->rx_cqe_compress_def = false;

From: Daniel Jurgens danielj@nvidia.com

[ Upstream commit 7ba930fc25def6fd736abcdfa224272948a65cf7 ]

The offending commit changed the ordering of moving to legacy mode and waiting for the VF pages. Moving to legacy mode is important in bluefield, because it sends the host driver into error state, and frees its pages. Without this transition we end up waiting 2 minutes for pages that aren't coming before carrying on with the unload process.

Fixes: f019679ea5f2 ("net/mlx5: E-switch, Remove dependency between sriov and eswitch mode") Signed-off-by: Daniel Jurgens danielj@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 4e1b5757528a0..bb718003d6f49 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1346,8 +1346,8 @@ static void mlx5_unload(struct mlx5_core_dev *dev) { mlx5_devlink_traps_unregister(priv_to_devlink(dev)); mlx5_sf_dev_table_destroy(dev); - mlx5_sriov_detach(dev); mlx5_eswitch_disable(dev->priv.eswitch); + mlx5_sriov_detach(dev); mlx5_lag_remove_mdev(dev); mlx5_ec_cleanup(dev); mlx5_sf_hw_table_destroy(dev);

From: Maor Dickman maord@nvidia.com

[ Upstream commit 28d3815a629cbdee660dd1c9de28d77cb3d77917 ]

Rules with mirror actions are split to two FTEs when the actions after the mirror action contains pedit, vlan push/pop or ct. Forward to ovs internal port adds implicit header rewrite (pedit) but missing trigger to do split.

Fix by setting split_count when forwarding to ovs internal port which will trigger split in mirror rules.

Fixes: 27484f7170ed ("net/mlx5e: Offload tc rules that redirect to ovs internal port") Signed-off-by: Maor Dickman maord@nvidia.com Reviewed-by: Roi Dayan roid@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 243d5d7750beb..6a07242b5d5ef 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -4240,6 +4240,7 @@ int mlx5e_set_fwd_to_int_port_actions(struct mlx5e_priv *priv,

esw_attr->dest_int_port = dest_int_port; esw_attr->dests[out_index].flags |= MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE; + esw_attr->split_count = out_index;

/* Forward to root fdb for matching against the new source vport */ attr->dest_chain = 0;

From: Shay Drory shayd@nvidia.com

[ Upstream commit 031a163f2c476adcb2c01e27a7d323e66174ac11 ]

Currently, BREAK_FW_WAIT flag is set after syncing with fw_reset. However, fw_reset can call mlx5_load_one() which is waiting for fw init bit and BREAK_FW_WAIT flag is intended to stop. e.g.: the driver might wait on a loop it should exit. Fix it by setting the flag before syncing with fw_reset.

Fixes: 8324a02c342a ("net/mlx5: Add exit route when waiting for FW") Signed-off-by: Shay Drory shayd@nvidia.com Reviewed-by: Moshe Shemesh moshe@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index bb718003d6f49..f4e0431da55b4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1768,11 +1768,11 @@ static void remove_one(struct pci_dev *pdev) struct mlx5_core_dev *dev = pci_get_drvdata(pdev); struct devlink *devlink = priv_to_devlink(dev);

+ set_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state); /* mlx5_drain_fw_reset() is using devlink APIs. Hence, we must drain * fw_reset before unregistering the devlink. */ mlx5_drain_fw_reset(dev); - set_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state); devlink_unregister(devlink); mlx5_sriov_disable(pdev); mlx5_crdump_disable(dev);

From: Maciej Fijalkowski maciej.fijalkowski@intel.com

[ Upstream commit b830c9642386867863ac64295185f896ff2928ac ]

ice_qp_dis() intends to stop a given queue pair that is a target of xsk pool attach/detach. One of the steps is to disable interrupts on these queues. It currently is broken in a way that txq irq is turned off *after* HW flush which in turn takes no effect.

ice_qp_dis(): -> ice_qvec_dis_irq() --> disable rxq irq --> flush hw -> ice_vsi_stop_tx_ring() -->disable txq irq

Below splat can be triggered by following steps: - start xdpsock WITHOUT loading xdp prog - run xdp_rxq_info with XDP_TX action on this interface - start traffic - terminate xdpsock

[ 256.312485] BUG: kernel NULL pointer dereference, address: 0000000000000018 [ 256.319560] #PF: supervisor read access in kernel mode [ 256.324775] #PF: error_code(0x0000) - not-present page [ 256.329994] PGD 0 P4D 0 [ 256.332574] Oops: 0000 [#1] PREEMPT SMP NOPTI [ 256.337006] CPU: 3 PID: 32 Comm: ksoftirqd/3 Tainted: G OE 6.2.0-rc5+ #51 [ 256.345218] Hardware name: Intel Corporation S2600WFT/S2600WFT, BIOS SE5C620.86B.02.01.0008.031920191559 03/19/2019 [ 256.355807] RIP: 0010:ice_clean_rx_irq_zc+0x9c/0x7d0 [ice] [ 256.361423] Code: b7 8f 8a 00 00 00 66 39 ca 0f 84 f1 04 00 00 49 8b 47 40 4c 8b 24 d0 41 0f b7 45 04 66 25 ff 3f 66 89 04 24 0f 84 85 02 00 00 <49> 8b 44 24 18 0f b7 14 24 48 05 00 01 00 00 49 89 04 24 49 89 44 [ 256.380463] RSP: 0018:ffffc900088bfd20 EFLAGS: 00010206 [ 256.385765] RAX: 000000000000003c RBX: 0000000000000035 RCX: 000000000000067f [ 256.393012] RDX: 0000000000000775 RSI: 0000000000000000 RDI: ffff8881deb3ac80 [ 256.400256] RBP: 000000000000003c R08: ffff889847982710 R09: 0000000000010000 [ 256.407500] R10: ffffffff82c060c0 R11: 0000000000000004 R12: 0000000000000000 [ 256.414746] R13: ffff88811165eea0 R14: ffffc9000d255000 R15: ffff888119b37600 [ 256.421990] FS: 0000000000000000(0000) GS:ffff8897e0cc0000(0000) knlGS:0000000000000000 [ 256.430207] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 256.436036] CR2: 0000000000000018 CR3: 0000000005c0a006 CR4: 00000000007706e0 [ 256.443283] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 256.450527] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 256.457770] PKRU: 55555554 [ 256.460529] Call Trace: [ 256.463015] <TASK> [ 256.465157] ? ice_xmit_zc+0x6e/0x150 [ice] [ 256.469437] ice_napi_poll+0x46d/0x680 [ice] [ 256.473815] ? _raw_spin_unlock_irqrestore+0x1b/0x40 [ 256.478863] __napi_poll+0x29/0x160 [ 256.482409] net_rx_action+0x136/0x260 [ 256.486222] __do_softirq+0xe8/0x2e5 [ 256.489853] ? smpboot_thread_fn+0x2c/0x270 [ 256.494108] run_ksoftirqd+0x2a/0x50 [ 256.497747] smpboot_thread_fn+0x1c1/0x270 [ 256.501907] ? __pfx_smpboot_thread_fn+0x10/0x10 [ 256.506594] kthread+0xea/0x120 [ 256.509785] ? __pfx_kthread+0x10/0x10 [ 256.513597] ret_from_fork+0x29/0x50 [ 256.517238] </TASK>

In fact, irqs were not disabled and napi managed to be scheduled and run while xsk_pool pointer was still valid, but SW ring of xdp_buff pointers was already freed.

To fix this, call ice_qvec_dis_irq() after ice_vsi_stop_tx_ring(). Also while at it, remove redundant ice_clean_rx_ring() call - this is handled in ice_qp_clean_rings().

Fixes: 2d4238f55697 ("ice: Add support for AF_XDP") Signed-off-by: Maciej Fijalkowski maciej.fijalkowski@intel.com Reviewed-by: Larysa Zaremba larysa.zaremba@intel.com Tested-by: Chandan Kumar Rout chandanx.rout@intel.com (A Contingent Worker at Intel) Acked-by: John Fastabend john.fastabend@gmail.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Reviewed-by: Leon Romanovsky leonro@nvidia.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/ice/ice_xsk.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 374b7f10b549b..76b8ac3462266 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -184,8 +184,6 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) } netif_tx_stop_queue(netdev_get_tx_queue(vsi->netdev, q_idx));

- ice_qvec_dis_irq(vsi, rx_ring, q_vector); - ice_fill_txq_meta(vsi, tx_ring, &txq_meta); err = ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, 0, tx_ring, &txq_meta); if (err) @@ -200,10 +198,11 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) if (err) return err; } + ice_qvec_dis_irq(vsi, rx_ring, q_vector); + err = ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, true); if (err) return err; - ice_clean_rx_ring(rx_ring);

ice_qvec_toggle_napi(vsi, q_vector, false); ice_qp_clean_rings(vsi, q_idx);

From: Vladimir Oltean vladimir.oltean@nxp.com

[ Upstream commit 7e9517375a14f44ee830ca1c3278076dd65fcc8f ]

There are 3 classes of switch families that the driver is aware of, as far as mv88e6xxx_change_mtu() is concerned:

- MTU configuration is available per port. Here, the chip->info->ops->port_set_jumbo_size() method will be present.

- MTU configuration is global to the switch. Here, the chip->info->ops->set_max_frame_size() method will be present.

- We don't know how to change the MTU. Here, none of the above methods will be present.

Switch families MV88E6165, MV88E6191, MV88E6220, MV88E6250 and MV88E6290 fall in category 3.

The blamed commit has adjusted the MTU for all 3 categories by EDSA_HLEN (8 bytes), resulting in a new maximum MTU of 1492 being reported by the driver for these switches.

I don't have the hardware to test, but I do have a MV88E6390 switch on which I can simulate this by commenting out its .port_set_jumbo_size definition from mv88e6390_ops. The result is this set of messages at probe time:

mv88e6085 d0032004.mdio-mii:10: nonfatal error -34 setting MTU to 1500 on port 1 mv88e6085 d0032004.mdio-mii:10: nonfatal error -34 setting MTU to 1500 on port 2 mv88e6085 d0032004.mdio-mii:10: nonfatal error -34 setting MTU to 1500 on port 3 mv88e6085 d0032004.mdio-mii:10: nonfatal error -34 setting MTU to 1500 on port 4 mv88e6085 d0032004.mdio-mii:10: nonfatal error -34 setting MTU to 1500 on port 5 mv88e6085 d0032004.mdio-mii:10: nonfatal error -34 setting MTU to 1500 on port 6 mv88e6085 d0032004.mdio-mii:10: nonfatal error -34 setting MTU to 1500 on port 7 mv88e6085 d0032004.mdio-mii:10: nonfatal error -34 setting MTU to 1500 on port 8

It is highly implausible that there exist Ethernet switches which don't support the standard MTU of 1500 octets, and this is what the DSA framework says as well - the error comes from dsa_slave_create() -> dsa_slave_change_mtu(slave_dev, ETH_DATA_LEN).

But the error messages are alarming, and it would be good to suppress them.

As a consequence of this unlikeliness, we reimplement mv88e6xxx_get_max_mtu() and mv88e6xxx_change_mtu() on switches from the 3rd category as follows: the maximum supported MTU is 1500, and any request to set the MTU to a value larger than that fails in dev_validate_mtu().

Fixes: b9c587fed61c ("dsa: mv88e6xxx: Include tagger overhead when setting MTU for DSA and CPU ports") Signed-off-by: Vladimir Oltean vladimir.oltean@nxp.com Reviewed-by: Simon Horman simon.horman@corigine.com Reviewed-by: Florian Fainelli f.fainelli@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/dsa/mv88e6xxx/chip.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 242b8b325504a..89829e0ca8e8f 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3549,7 +3549,7 @@ static int mv88e6xxx_get_max_mtu(struct dsa_switch *ds, int port) return 10240 - VLAN_ETH_HLEN - EDSA_HLEN - ETH_FCS_LEN; else if (chip->info->ops->set_max_frame_size) return 1632 - VLAN_ETH_HLEN - EDSA_HLEN - ETH_FCS_LEN; - return 1522 - VLAN_ETH_HLEN - EDSA_HLEN - ETH_FCS_LEN; + return ETH_DATA_LEN; }

static int mv88e6xxx_change_mtu(struct dsa_switch *ds, int port, int new_mtu) @@ -3557,6 +3557,17 @@ static int mv88e6xxx_change_mtu(struct dsa_switch *ds, int port, int new_mtu) struct mv88e6xxx_chip *chip = ds->priv; int ret = 0;

+ /* For families where we don't know how to alter the MTU, + * just accept any value up to ETH_DATA_LEN + */ + if (!chip->info->ops->port_set_jumbo_size && + !chip->info->ops->set_max_frame_size) { + if (new_mtu > ETH_DATA_LEN) + return -EINVAL; + + return 0; + } + if (dsa_is_dsa_port(ds, port) || dsa_is_cpu_port(ds, port)) new_mtu += EDSA_HLEN;

@@ -3565,9 +3576,6 @@ static int mv88e6xxx_change_mtu(struct dsa_switch *ds, int port, int new_mtu) ret = chip->info->ops->port_set_jumbo_size(chip, port, new_mtu); else if (chip->info->ops->set_max_frame_size) ret = chip->info->ops->set_max_frame_size(chip, new_mtu); - else - if (new_mtu > 1522) - ret = -EINVAL; mv88e6xxx_reg_unlock(chip);

return ret;

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

[ Upstream commit c6be7136afb224a01d4cde2983ddebac8da98693 ]

SH_ETH doesn't need mdiobus suspend/resume, that's why it sets 'mac_managed_pm'. However, setting it needs to be moved from init to probe, so mdiobus PM functions will really never be called (e.g. when the interface is not up yet during suspend/resume).

Fixes: 6a1dbfefdae4 ("net: sh_eth: Fix PHY state warning splat during system resume") Suggested-by: Heiner Kallweit hkallweit1@gmail.com Signed-off-by: Wolfram Sang wsa+renesas@sang-engineering.com Reviewed-by: Michal Kubiak michal.kubiak@intel.com Reviewed-by: Sergey Shtylyov s.shtylyov@omp.ru Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/renesas/sh_eth.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 71a4991133080..14dc5833c465c 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -2029,8 +2029,6 @@ static int sh_eth_phy_init(struct net_device *ndev) if (mdp->cd->register_type != SH_ETH_REG_GIGABIT) phy_set_max_speed(phydev, SPEED_100);

- /* Indicate that the MAC is responsible for managing PHY PM */ - phydev->mac_managed_pm = true; phy_attached_info(phydev);

return 0; @@ -3074,6 +3072,8 @@ static int sh_mdio_init(struct sh_eth_private *mdp, struct bb_info *bitbang; struct platform_device *pdev = mdp->pdev; struct device *dev = &mdp->pdev->dev; + struct phy_device *phydev; + struct device_node *pn;

/* create bit control struct for PHY */ bitbang = devm_kzalloc(dev, sizeof(struct bb_info), GFP_KERNEL); @@ -3108,6 +3108,14 @@ static int sh_mdio_init(struct sh_eth_private *mdp, if (ret) goto out_free_bus;

+ pn = of_parse_phandle(dev->of_node, "phy-handle", 0); + phydev = of_phy_find_device(pn); + if (phydev) { + phydev->mac_managed_pm = true; + put_device(&phydev->mdio.dev); + } + of_node_put(pn); + return 0;

out_free_bus:

From: Szymon Heidrich szymon.heidrich@gmail.com

[ Upstream commit 43ffe6caccc7a1bb9d7442fbab521efbf6c1378c ]

Packet length check needs to be located after size and align_count calculation to prevent kernel panic in skb_pull() in case rx_cmd_a & RX_CMD_A_RED evaluates to true.

Fixes: d8b228318935 ("net: usb: smsc75xx: Limit packet length to skb->len") Signed-off-by: Szymon Heidrich szymon.heidrich@gmail.com Link: https://lore.kernel.org/r/20230316110540.77531-1-szymon.heidrich@gmail.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/usb/smsc75xx.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c index db34f8d1d6051..5d6454fedb3f1 100644 --- a/drivers/net/usb/smsc75xx.c +++ b/drivers/net/usb/smsc75xx.c @@ -2200,6 +2200,13 @@ static int smsc75xx_rx_fixup(struct usbnet *dev, struct sk_buff *skb) size = (rx_cmd_a & RX_CMD_A_LEN) - RXW_PADDING; align_count = (4 - ((size + RXW_PADDING) % 4)) % 4;

+ if (unlikely(size > skb->len)) { + netif_dbg(dev, rx_err, dev->net, + "size err rx_cmd_a=0x%08x\n", + rx_cmd_a); + return 0; + } + if (unlikely(rx_cmd_a & RX_CMD_A_RED)) { netif_dbg(dev, rx_err, dev->net, "Error rx_cmd_a=0x%08x\n", rx_cmd_a); @@ -2212,8 +2219,7 @@ static int smsc75xx_rx_fixup(struct usbnet *dev, struct sk_buff *skb) dev->net->stats.rx_frame_errors++; } else { /* MAX_SINGLE_PACKET_SIZE + 4(CRC) + 2(COE) + 4(Vlan) */ - if (unlikely(size > (MAX_SINGLE_PACKET_SIZE + ETH_HLEN + 12) || - size > skb->len)) { + if (unlikely(size > (MAX_SINGLE_PACKET_SIZE + ETH_HLEN + 12))) { netif_dbg(dev, rx_err, dev->net, "size err rx_cmd_a=0x%08x\n", rx_cmd_a);

From: Alexandra Winter wintera@linux.ibm.com

[ Upstream commit 3d87debb8ed2649608ff432699e7c961c0c6f03b ]

iucv_irq_data needs to be 4 bytes larger. These bytes are not used by the iucv module, but written by the z/VM hypervisor in case a CPU is deconfigured.

Reported as: BUG dma-kmalloc-64 (Not tainted): kmalloc Redzone overwritten ----------------------------------------------------------------------------- 0x0000000000400564-0x0000000000400567 @offset=1380. First byte 0x80 instead of 0xcc Allocated in iucv_cpu_prepare+0x44/0xd0 age=167839 cpu=2 pid=1 __kmem_cache_alloc_node+0x166/0x450 kmalloc_node_trace+0x3a/0x70 iucv_cpu_prepare+0x44/0xd0 cpuhp_invoke_callback+0x156/0x2f0 cpuhp_issue_call+0xf0/0x298 __cpuhp_setup_state_cpuslocked+0x136/0x338 __cpuhp_setup_state+0xf4/0x288 iucv_init+0xf4/0x280 do_one_initcall+0x78/0x390 do_initcalls+0x11a/0x140 kernel_init_freeable+0x25e/0x2a0 kernel_init+0x2e/0x170 __ret_from_fork+0x3c/0x58 ret_from_fork+0xa/0x40 Freed in iucv_init+0x92/0x280 age=167839 cpu=2 pid=1 __kmem_cache_free+0x308/0x358 iucv_init+0x92/0x280 do_one_initcall+0x78/0x390 do_initcalls+0x11a/0x140 kernel_init_freeable+0x25e/0x2a0 kernel_init+0x2e/0x170 __ret_from_fork+0x3c/0x58 ret_from_fork+0xa/0x40 Slab 0x0000037200010000 objects=32 used=30 fp=0x0000000000400640 flags=0x1ffff00000010200(slab|head|node=0|zone=0| Object 0x0000000000400540 @offset=1344 fp=0x0000000000000000 Redzone 0000000000400500: cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc ................ Redzone 0000000000400510: cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc ................ Redzone 0000000000400520: cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc ................ Redzone 0000000000400530: cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc ................ Object 0000000000400540: 00 01 00 03 00 00 00 00 00 00 00 00 00 00 00 00 ................ Object 0000000000400550: f3 86 81 f2 f4 82 f8 82 f0 f0 f0 f0 f0 f0 f0 f2 ................ Object 0000000000400560: 00 00 00 00 80 00 00 00 cc cc cc cc cc cc cc cc ................ Object 0000000000400570: cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc ................ Redzone 0000000000400580: cc cc cc cc cc cc cc cc ........ Padding 00000000004005d4: 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a ZZZZZZZZZZZZZZZZ Padding 00000000004005e4: 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a ZZZZZZZZZZZZZZZZ Padding 00000000004005f4: 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a ZZZZZZZZZZZZ CPU: 6 PID: 121030 Comm: 116-pai-crypto. Not tainted 6.3.0-20230221.rc0.git4.99b8246b2d71.300.fc37.s390x+debug #1 Hardware name: IBM 3931 A01 704 (z/VM 7.3.0) Call Trace: [<000000032aa034ec>] dump_stack_lvl+0xac/0x100 [<0000000329f5a6cc>] check_bytes_and_report+0x104/0x140 [<0000000329f5aa78>] check_object+0x370/0x3c0 [<0000000329f5ede6>] free_debug_processing+0x15e/0x348 [<0000000329f5f06a>] free_to_partial_list+0x9a/0x2f0 [<0000000329f5f4a4>] __slab_free+0x1e4/0x3a8 [<0000000329f61768>] __kmem_cache_free+0x308/0x358 [<000000032a91465c>] iucv_cpu_dead+0x6c/0x88 [<0000000329c2fc66>] cpuhp_invoke_callback+0x156/0x2f0 [<000000032aa062da>] _cpu_down.constprop.0+0x22a/0x5e0 [<0000000329c3243e>] cpu_device_down+0x4e/0x78 [<000000032a61dee0>] device_offline+0xc8/0x118 [<000000032a61e048>] online_store+0x60/0xe0 [<000000032a08b6b0>] kernfs_fop_write_iter+0x150/0x1e8 [<0000000329fab65c>] vfs_write+0x174/0x360 [<0000000329fab9fc>] ksys_write+0x74/0x100 [<000000032aa03a5a>] __do_syscall+0x1da/0x208 [<000000032aa177b2>] system_call+0x82/0xb0 INFO: lockdep is turned off. FIX dma-kmalloc-64: Restoring kmalloc Redzone 0x0000000000400564-0x0000000000400567=0xcc FIX dma-kmalloc-64: Object at 0x0000000000400540 not freed

Fixes: 2356f4cb1911 ("[S390]: Rewrite of the IUCV base code, part 2") Signed-off-by: Alexandra Winter wintera@linux.ibm.com Link: https://lore.kernel.org/r/20230315131435.4113889-1-wintera@linux.ibm.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/iucv/iucv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index eb0295d900395..fc3fddeb6f36d 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -83,7 +83,7 @@ struct iucv_irq_data { u16 ippathid; u8 ipflags1; u8 iptype; - u32 res2[8]; + u32 res2[9]; };

struct iucv_irq_list {

From: Po-Hsu Lin po-hsu.lin@canonical.com

[ Upstream commit 24994513ad13ff2c47ba91d2b5df82c3d496c370 ]

The `devlink -j port show` command output may not contain the "flavour" key, an example from Ubuntu 22.10 s390x LPAR(5.19.0-37-generic), with mlx4 driver and iproute2-5.15.0: {"port":{"pci/0001:00:00.0/1":{"type":"eth","netdev":"ens301"}, "pci/0001:00:00.0/2":{"type":"eth","netdev":"ens301d1"}, "pci/0002:00:00.0/1":{"type":"eth","netdev":"ens317"}, "pci/0002:00:00.0/2":{"type":"eth","netdev":"ens317d1"}}}

This will cause a KeyError exception.

Create a validate_devlink_output() to check for this "flavour" from devlink command output to avoid this KeyError exception. Also let it handle the check for `devlink -j dev show` output in main().

Apart from this, if the test was not started because the max lanes of the designated device is 0. The script will still return 0 and thus causing a false-negative test result.

Use a found_max_lanes flag to determine if these tests were skipped due to this reason and return KSFT_SKIP to make it more clear.

Link: https://bugs.launchpad.net/bugs/1937133 Fixes: f3348a82e727 ("selftests: net: Add port split test") Signed-off-by: Po-Hsu Lin po-hsu.lin@canonical.com Link: https://lore.kernel.org/r/20230315165353.229590-1-po-hsu.lin@canonical.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- .../selftests/net/devlink_port_split.py | 36 ++++++++++++++++--- 1 file changed, 31 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/net/devlink_port_split.py b/tools/testing/selftests/net/devlink_port_split.py index 2b5d6ff873738..2d84c7a0be6b2 100755 --- a/tools/testing/selftests/net/devlink_port_split.py +++ b/tools/testing/selftests/net/devlink_port_split.py @@ -59,6 +59,8 @@ class devlink_ports(object): assert stderr == "" ports = json.loads(stdout)['port']

+ validate_devlink_output(ports, 'flavour') + for port in ports: if dev in port: if ports[port]['flavour'] == 'physical': @@ -220,6 +222,27 @@ def split_splittable_port(port, k, lanes, dev): unsplit(port.bus_info)

+def validate_devlink_output(devlink_data, target_property=None): + """ + Determine if test should be skipped by checking: + 1. devlink_data contains values + 2. The target_property exist in devlink_data + """ + skip_reason = None + if any(devlink_data.values()): + if target_property: + skip_reason = "{} not found in devlink output, test skipped".format(target_property) + for key in devlink_data: + if target_property in devlink_data[key]: + skip_reason = None + else: + skip_reason = 'devlink output is empty, test skipped' + + if skip_reason: + print(skip_reason) + sys.exit(KSFT_SKIP) + + def make_parser(): parser = argparse.ArgumentParser(description='A test for port splitting.') parser.add_argument('--dev', @@ -240,12 +263,9 @@ def main(cmdline=None): stdout, stderr = run_command(cmd) assert stderr == ""

+ validate_devlink_output(json.loads(stdout)) devs = json.loads(stdout)['dev'] - if devs: - dev = list(devs.keys())[0] - else: - print("no devlink device was found, test skipped") - sys.exit(KSFT_SKIP) + dev = list(devs.keys())[0]

cmd = "devlink dev show %s" % dev stdout, stderr = run_command(cmd) @@ -255,6 +275,7 @@ def main(cmdline=None):

ports = devlink_ports(dev)

+ found_max_lanes = False for port in ports.if_names: max_lanes = get_max_lanes(port.name)

@@ -277,6 +298,11 @@ def main(cmdline=None): split_splittable_port(port, lane, max_lanes, dev)

lane //= 2 + found_max_lanes = True + + if not found_max_lanes: + print(f"Test not started, no port of device {dev} reports max_lanes") + sys.exit(KSFT_SKIP)

if __name__ == "__main__":

From: Marek Vasut marex@denx.de

[ Upstream commit 5ae06327a3a5bad4ee246d81df203b1b00a7b390 ]

The blamed commit has replaced a ksz_write8() call to address REG_PORT_5_CTRL_6 (0x56) with a ksz_set_xmii() -> ksz_pwrite8() call to regs[P_XMII_CTRL_1], which is also defined as 0x56 for ksz8795_regs[].

The trouble is that, when compared to ksz_write8(), ksz_pwrite8() also adjusts the register offset with the port base address. So in reality, ksz_pwrite8(offset=0x56) accesses register 0x56 + 0x50 = 0xa6, which in this switch appears to be unmapped, and the RGMII delay configuration on the CPU port does nothing.

So if the switch wasn't fine with the RGMII delay configuration done through pin strapping and relied on Linux to apply a different one in order to pass traffic, this is now broken.

Using the offset translation logic imposed by ksz_pwrite8(), the correct value for regs[P_XMII_CTRL_1] should have been 0x6 on ksz8795_regs[], in order to really end up accessing register 0x56.

Static code analysis shows that, despite there being multiple other accesses to regs[P_XMII_CTRL_1] in this driver, the only code path that is applicable to ksz8795_regs[] and ksz8_dev_ops is ksz_set_xmii(). Therefore, the problem is isolated to RGMII delays.

In its current form, ksz8795_regs[] contains the same value for P_XMII_CTRL_0 and for P_XMII_CTRL_1, and this raises valid suspicions that writes made by the driver to regs[P_XMII_CTRL_0] might overwrite writes made to regs[P_XMII_CTRL_1] or vice versa.

Again, static analysis shows that the only accesses to P_XMII_CTRL_0 from the driver are made from code paths which are not reachable with ksz8_dev_ops. So the accesses made by ksz_set_xmii() are safe for this switch family.

[ vladimiroltean: rewrote commit message ]

Fixes: c476bede4b0f ("net: dsa: microchip: ksz8795: use common xmii function") Signed-off-by: Marek Vasut marex@denx.de Signed-off-by: Vladimir Oltean vladimir.oltean@nxp.com Acked-by: Arun Ramadoss arun.ramadoss@microchip.com Reviewed-by: Florian Fainelli f.fainelli@gmail.com Link: https://lore.kernel.org/r/20230315231916.2998480-1-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/dsa/microchip/ksz_common.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 9b20c2ee6d62a..19cd05762ab77 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -310,7 +310,7 @@ static const u16 ksz8795_regs[] = { [S_BROADCAST_CTRL] = 0x06, [S_MULTICAST_CTRL] = 0x04, [P_XMII_CTRL_0] = 0x06, - [P_XMII_CTRL_1] = 0x56, + [P_XMII_CTRL_1] = 0x06, };

static const u32 ksz8795_masks[] = {

From: Yoshihiro Shimoda yoshihiro.shimoda.uh@renesas.com

[ Upstream commit 251eadcc640a0b5fd2767aaeb22a6f1ebf9b3c96 ]

To add a new ring which is really related to timestamp (ts_ring) in the future, rename the following members to improve readability:

ring --> tx_ring ts_ring --> rx_ring

Signed-off-by: Yoshihiro Shimoda yoshihiro.shimoda.uh@renesas.com Reviewed-by: Alexander Duyck alexanderduyck@fb.com Signed-off-by: Jakub Kicinski kuba@kernel.org Stable-dep-of: e05bb97d9c9d ("net: renesas: rswitch: Fix the output value of quote from rswitch_rx()") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/renesas/rswitch.c | 64 +++++++++++++------------- drivers/net/ethernet/renesas/rswitch.h | 4 +- 2 files changed, 34 insertions(+), 34 deletions(-)

diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c index 2370c7797a0aa..847b1f161fc66 100644 --- a/drivers/net/ethernet/renesas/rswitch.c +++ b/drivers/net/ethernet/renesas/rswitch.c @@ -241,7 +241,7 @@ static int rswitch_get_num_cur_queues(struct rswitch_gwca_queue *gq)

static bool rswitch_is_queue_rxed(struct rswitch_gwca_queue *gq) { - struct rswitch_ext_ts_desc *desc = &gq->ts_ring[gq->dirty]; + struct rswitch_ext_ts_desc *desc = &gq->rx_ring[gq->dirty];

if ((desc->desc.die_dt & DT_MASK) != DT_FEMPTY) return true; @@ -284,13 +284,13 @@ static void rswitch_gwca_queue_free(struct net_device *ndev, if (gq->gptp) { dma_free_coherent(ndev->dev.parent, sizeof(struct rswitch_ext_ts_desc) * - (gq->ring_size + 1), gq->ts_ring, gq->ring_dma); - gq->ts_ring = NULL; + (gq->ring_size + 1), gq->rx_ring, gq->ring_dma); + gq->rx_ring = NULL; } else { dma_free_coherent(ndev->dev.parent, sizeof(struct rswitch_ext_desc) * - (gq->ring_size + 1), gq->ring, gq->ring_dma); - gq->ring = NULL; + (gq->ring_size + 1), gq->tx_ring, gq->ring_dma); + gq->tx_ring = NULL; }

if (!gq->dir_tx) { @@ -322,14 +322,14 @@ static int rswitch_gwca_queue_alloc(struct net_device *ndev, rswitch_gwca_queue_alloc_skb(gq, 0, gq->ring_size);

if (gptp) - gq->ts_ring = dma_alloc_coherent(ndev->dev.parent, + gq->rx_ring = dma_alloc_coherent(ndev->dev.parent, sizeof(struct rswitch_ext_ts_desc) * (gq->ring_size + 1), &gq->ring_dma, GFP_KERNEL); else - gq->ring = dma_alloc_coherent(ndev->dev.parent, - sizeof(struct rswitch_ext_desc) * - (gq->ring_size + 1), &gq->ring_dma, GFP_KERNEL); - if (!gq->ts_ring && !gq->ring) + gq->tx_ring = dma_alloc_coherent(ndev->dev.parent, + sizeof(struct rswitch_ext_desc) * + (gq->ring_size + 1), &gq->ring_dma, GFP_KERNEL); + if (!gq->rx_ring && !gq->tx_ring) goto out;

i = gq->index / 32; @@ -362,14 +362,14 @@ static int rswitch_gwca_queue_format(struct net_device *ndev, struct rswitch_private *priv, struct rswitch_gwca_queue *gq) { - int tx_ring_size = sizeof(struct rswitch_ext_desc) * gq->ring_size; + int ring_size = sizeof(struct rswitch_ext_desc) * gq->ring_size; struct rswitch_ext_desc *desc; struct rswitch_desc *linkfix; dma_addr_t dma_addr; int i;

- memset(gq->ring, 0, tx_ring_size); - for (i = 0, desc = gq->ring; i < gq->ring_size; i++, desc++) { + memset(gq->tx_ring, 0, ring_size); + for (i = 0, desc = gq->tx_ring; i < gq->ring_size; i++, desc++) { if (!gq->dir_tx) { dma_addr = dma_map_single(ndev->dev.parent, gq->skbs[i]->data, PKT_BUF_SZ, @@ -398,7 +398,7 @@ static int rswitch_gwca_queue_format(struct net_device *ndev,

err: if (!gq->dir_tx) { - for (i--, desc = gq->ring; i >= 0; i--, desc++) { + for (i--, desc = gq->tx_ring; i >= 0; i--, desc++) { dma_addr = rswitch_desc_get_dptr(&desc->desc); dma_unmap_single(ndev->dev.parent, dma_addr, PKT_BUF_SZ, DMA_FROM_DEVICE); @@ -408,9 +408,9 @@ static int rswitch_gwca_queue_format(struct net_device *ndev, return -ENOMEM; }

-static int rswitch_gwca_queue_ts_fill(struct net_device *ndev, - struct rswitch_gwca_queue *gq, - int start_index, int num) +static int rswitch_gwca_queue_ext_ts_fill(struct net_device *ndev, + struct rswitch_gwca_queue *gq, + int start_index, int num) { struct rswitch_device *rdev = netdev_priv(ndev); struct rswitch_ext_ts_desc *desc; @@ -419,7 +419,7 @@ static int rswitch_gwca_queue_ts_fill(struct net_device *ndev,

for (i = 0; i < num; i++) { index = (i + start_index) % gq->ring_size; - desc = &gq->ts_ring[index]; + desc = &gq->rx_ring[index]; if (!gq->dir_tx) { dma_addr = dma_map_single(ndev->dev.parent, gq->skbs[index]->data, PKT_BUF_SZ, @@ -443,7 +443,7 @@ static int rswitch_gwca_queue_ts_fill(struct net_device *ndev, if (!gq->dir_tx) { for (i--; i >= 0; i--) { index = (i + start_index) % gq->ring_size; - desc = &gq->ts_ring[index]; + desc = &gq->rx_ring[index]; dma_addr = rswitch_desc_get_dptr(&desc->desc); dma_unmap_single(ndev->dev.parent, dma_addr, PKT_BUF_SZ, DMA_FROM_DEVICE); @@ -453,21 +453,21 @@ static int rswitch_gwca_queue_ts_fill(struct net_device *ndev, return -ENOMEM; }

-static int rswitch_gwca_queue_ts_format(struct net_device *ndev, - struct rswitch_private *priv, - struct rswitch_gwca_queue *gq) +static int rswitch_gwca_queue_ext_ts_format(struct net_device *ndev, + struct rswitch_private *priv, + struct rswitch_gwca_queue *gq) { - int tx_ts_ring_size = sizeof(struct rswitch_ext_ts_desc) * gq->ring_size; + int ring_size = sizeof(struct rswitch_ext_ts_desc) * gq->ring_size; struct rswitch_ext_ts_desc *desc; struct rswitch_desc *linkfix; int err;

- memset(gq->ts_ring, 0, tx_ts_ring_size); - err = rswitch_gwca_queue_ts_fill(ndev, gq, 0, gq->ring_size); + memset(gq->rx_ring, 0, ring_size); + err = rswitch_gwca_queue_ext_ts_fill(ndev, gq, 0, gq->ring_size); if (err < 0) return err;

- desc = &gq->ts_ring[gq->ring_size]; /* Last */ + desc = &gq->rx_ring[gq->ring_size]; /* Last */ rswitch_desc_set_dptr(&desc->desc, gq->ring_dma); desc->desc.die_dt = DT_LINKFIX;

@@ -595,7 +595,7 @@ static int rswitch_rxdmac_init(struct rswitch_private *priv, int index) struct rswitch_device *rdev = priv->rdev[index]; struct net_device *ndev = rdev->ndev;

- return rswitch_gwca_queue_ts_format(ndev, priv, rdev->rx_queue); + return rswitch_gwca_queue_ext_ts_format(ndev, priv, rdev->rx_queue); }

static int rswitch_gwca_hw_init(struct rswitch_private *priv) @@ -676,7 +676,7 @@ static bool rswitch_rx(struct net_device *ndev, int *quota) boguscnt = min_t(int, gq->ring_size, *quota); limit = boguscnt;

- desc = &gq->ts_ring[gq->cur]; + desc = &gq->rx_ring[gq->cur]; while ((desc->desc.die_dt & DT_MASK) != DT_FEMPTY) { if (--boguscnt < 0) break; @@ -704,14 +704,14 @@ static bool rswitch_rx(struct net_device *ndev, int *quota) rdev->ndev->stats.rx_bytes += pkt_len;

gq->cur = rswitch_next_queue_index(gq, true, 1); - desc = &gq->ts_ring[gq->cur]; + desc = &gq->rx_ring[gq->cur]; }

num = rswitch_get_num_cur_queues(gq); ret = rswitch_gwca_queue_alloc_skb(gq, gq->dirty, num); if (ret < 0) goto err; - ret = rswitch_gwca_queue_ts_fill(ndev, gq, gq->dirty, num); + ret = rswitch_gwca_queue_ext_ts_fill(ndev, gq, gq->dirty, num); if (ret < 0) goto err; gq->dirty = rswitch_next_queue_index(gq, false, num); @@ -738,7 +738,7 @@ static int rswitch_tx_free(struct net_device *ndev, bool free_txed_only)

for (; rswitch_get_num_cur_queues(gq) > 0; gq->dirty = rswitch_next_queue_index(gq, false, 1)) { - desc = &gq->ring[gq->dirty]; + desc = &gq->tx_ring[gq->dirty]; if (free_txed_only && (desc->desc.die_dt & DT_MASK) != DT_FEMPTY) break;

@@ -1416,7 +1416,7 @@ static netdev_tx_t rswitch_start_xmit(struct sk_buff *skb, struct net_device *nd }

gq->skbs[gq->cur] = skb; - desc = &gq->ring[gq->cur]; + desc = &gq->tx_ring[gq->cur]; rswitch_desc_set_dptr(&desc->desc, dma_addr); desc->desc.info_ds = cpu_to_le16(skb->len);

diff --git a/drivers/net/ethernet/renesas/rswitch.h b/drivers/net/ethernet/renesas/rswitch.h index 49efb0f31c77a..0584670abead5 100644 --- a/drivers/net/ethernet/renesas/rswitch.h +++ b/drivers/net/ethernet/renesas/rswitch.h @@ -915,8 +915,8 @@ struct rswitch_gwca_queue { bool dir_tx; bool gptp; union { - struct rswitch_ext_desc *ring; - struct rswitch_ext_ts_desc *ts_ring; + struct rswitch_ext_desc *tx_ring; + struct rswitch_ext_ts_desc *rx_ring; }; dma_addr_t ring_dma; int ring_size;

From: Nikolay Aleksandrov razor@blackwall.org

[ Upstream commit 9ec7eb60dcbcb6c41076defbc5df7bbd95ceaba5 ]

Add bond_ether_setup helper which is used to fix ether_setup() calls in the bonding driver. It takes care of both IFF_MASTER and IFF_SLAVE flags, the former is always restored and the latter only if it was set. If the bond enslaves non-ARPHRD_ETHER device (changes its type), then releases it and enslaves ARPHRD_ETHER device (changes back) then we use ether_setup() to restore the bond device type but it also resets its flags and removes IFF_MASTER and IFF_SLAVE[1]. Use the bond_ether_setup helper to restore both after such transition.

[1] reproduce (nlmon is non-ARPHRD_ETHER): $ ip l add nlmon0 type nlmon $ ip l add bond2 type bond mode active-backup $ ip l set nlmon0 master bond2 $ ip l set nlmon0 nomaster $ ip l add bond1 type bond (we use bond1 as ARPHRD_ETHER device to restore bond2's mode) $ ip l set bond1 master bond2 $ ip l sh dev bond2 37: bond2: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN mode DEFAULT group default qlen 1000 link/ether be:d7:c5:40:5b:cc brd ff:ff:ff:ff:ff:ff promiscuity 0 minmtu 68 maxmtu 1500 (notice bond2's IFF_MASTER is missing)

Fixes: e36b9d16c6a6 ("bonding: clean muticast addresses when device changes type") Signed-off-by: Nikolay Aleksandrov razor@blackwall.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/bonding/bond_main.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 0363ce5976614..ef7ae8c99b452 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1773,6 +1773,19 @@ void bond_lower_state_changed(struct slave *slave) slave_err(bond_dev, slave_dev, "Error: %s\n", errmsg); \ } while (0)

+/* The bonding driver uses ether_setup() to convert a master bond device + * to ARPHRD_ETHER, that resets the target netdevice's flags so we always + * have to restore the IFF_MASTER flag, and only restore IFF_SLAVE if it was set + */ +static void bond_ether_setup(struct net_device *bond_dev) +{ + unsigned int slave_flag = bond_dev->flags & IFF_SLAVE; + + ether_setup(bond_dev); + bond_dev->flags |= IFF_MASTER | slave_flag; + bond_dev->priv_flags &= ~IFF_TX_SKB_SHARING; +} + /* enslave device <slave> to bond device <master> */ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, struct netlink_ext_ack *extack) @@ -1864,10 +1877,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,

if (slave_dev->type != ARPHRD_ETHER) bond_setup_by_slave(bond_dev, slave_dev); - else { - ether_setup(bond_dev); - bond_dev->priv_flags &= ~IFF_TX_SKB_SHARING; - } + else + bond_ether_setup(bond_dev);

call_netdevice_notifiers(NETDEV_POST_TYPE_CHANGE, bond_dev);

From: Tony O'Brien tony.obrien@alliedtelesis.co.nz

[ Upstream commit 5f8d1e3b6f9b5971f9c06d5846ce00c49e3a8d94 ]

Throughout the ADT7475 driver, attributes relating to the temperature sensors are displayed in the order Remote 1, Local, Remote 2. Make temp_st_show() conform to this expectation so that values set by temp_st_store() can be displayed using the correct attribute.

Fixes: 8f05bcc33e74 ("hwmon: (adt7475) temperature smoothing") Signed-off-by: Tony O'Brien tony.obrien@alliedtelesis.co.nz Link: https://lore.kernel.org/r/20230222005228.158661-2-tony.obrien@alliedtelesis.... Signed-off-by: Guenter Roeck linux@roeck-us.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hwmon/adt7475.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/hwmon/adt7475.c b/drivers/hwmon/adt7475.c index 51b3d16c32233..77222c35a38ec 100644 --- a/drivers/hwmon/adt7475.c +++ b/drivers/hwmon/adt7475.c @@ -556,11 +556,11 @@ static ssize_t temp_st_show(struct device *dev, struct device_attribute *attr, val = data->enh_acoustics[0] & 0xf; break; case 1: - val = (data->enh_acoustics[1] >> 4) & 0xf; + val = data->enh_acoustics[1] & 0xf; break; case 2: default: - val = data->enh_acoustics[1] & 0xf; + val = (data->enh_acoustics[1] >> 4) & 0xf; break; }

From: Zheng Wang zyytlz.wz@163.com

[ Upstream commit cb090e64cf25602b9adaf32d5dfc9c8bec493cd1 ]

In xgene_hwmon_probe, &ctx->workq is bound with xgene_hwmon_evt_work. Then it will be started.

If we remove the driver which will call xgene_hwmon_remove to clean up, there may be unfinished work.

The possible sequence is as follows:

Fix it by finishing the work before cleanup in xgene_hwmon_remove.

CPU0 CPU1

|xgene_hwmon_evt_work xgene_hwmon_remove | kfifo_free(&ctx->async_msg_fifo);| | |kfifo_out_spinlocked |//use &ctx->async_msg_fifo Fixes: 2ca492e22cb7 ("hwmon: (xgene) Fix crash when alarm occurs before driver probe") Signed-off-by: Zheng Wang zyytlz.wz@163.com Link: https://lore.kernel.org/r/20230310084007.1403388-1-zyytlz.wz@163.com Signed-off-by: Guenter Roeck linux@roeck-us.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hwmon/xgene-hwmon.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/hwmon/xgene-hwmon.c b/drivers/hwmon/xgene-hwmon.c index 5cde837bfd094..d1abea49f01be 100644 --- a/drivers/hwmon/xgene-hwmon.c +++ b/drivers/hwmon/xgene-hwmon.c @@ -761,6 +761,7 @@ static int xgene_hwmon_remove(struct platform_device *pdev) { struct xgene_hwmon_dev *ctx = platform_get_drvdata(pdev);

+ cancel_work_sync(&ctx->workq); hwmon_device_unregister(ctx->hwmon_dev); kfifo_free(&ctx->async_msg_fifo); if (acpi_disabled)

From: Lars-Peter Clausen lars@metafoo.de

[ Upstream commit 8d655e65237643c48ada2c131b83679bf1105373 ]

When probing the ucd90320 access to some of the registers randomly fails. Sometimes it NACKs a transfer, sometimes it returns just random data and the PEC check fails.

Experimentation shows that this seems to be triggered by a register access directly back to back with a previous register write. Experimentation also shows that inserting a small delay after register writes makes the issue go away.

Use a similar solution to what the max15301 driver does to solve the same problem. Create a custom set of bus read and write functions that make sure that the delay is added.

Fixes: a470f11c5ba2 ("hwmon: (pmbus/ucd9000) Add support for UCD90320 Power Sequencer") Signed-off-by: Lars-Peter Clausen lars@metafoo.de Link: https://lore.kernel.org/r/20230312160312.2227405-1-lars@metafoo.de Signed-off-by: Guenter Roeck linux@roeck-us.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hwmon/pmbus/ucd9000.c | 75 +++++++++++++++++++++++++++++++++++ 1 file changed, 75 insertions(+)

diff --git a/drivers/hwmon/pmbus/ucd9000.c b/drivers/hwmon/pmbus/ucd9000.c index 75fc770c9e403..3daaf22378322 100644 --- a/drivers/hwmon/pmbus/ucd9000.c +++ b/drivers/hwmon/pmbus/ucd9000.c @@ -7,6 +7,7 @@ */

#include <linux/debugfs.h> +#include <linux/delay.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/of_device.h> @@ -16,6 +17,7 @@ #include <linux/i2c.h> #include <linux/pmbus.h> #include <linux/gpio/driver.h> +#include <linux/timekeeping.h> #include "pmbus.h"

enum chips { ucd9000, ucd90120, ucd90124, ucd90160, ucd90320, ucd9090, @@ -65,6 +67,7 @@ struct ucd9000_data { struct gpio_chip gpio; #endif struct dentry *debugfs; + ktime_t write_time; }; #define to_ucd9000_data(_info) container_of(_info, struct ucd9000_data, info)

@@ -73,6 +76,73 @@ struct ucd9000_debugfs_entry { u8 index; };

+/* + * It has been observed that the UCD90320 randomly fails register access when + * doing another access right on the back of a register write. To mitigate this + * make sure that there is a minimum delay between a write access and the + * following access. The 250us is based on experimental data. At a delay of + * 200us the issue seems to go away. Add a bit of extra margin to allow for + * system to system differences. + */ +#define UCD90320_WAIT_DELAY_US 250 + +static inline void ucd90320_wait(const struct ucd9000_data *data) +{ + s64 delta = ktime_us_delta(ktime_get(), data->write_time); + + if (delta < UCD90320_WAIT_DELAY_US) + udelay(UCD90320_WAIT_DELAY_US - delta); +} + +static int ucd90320_read_word_data(struct i2c_client *client, int page, + int phase, int reg) +{ + const struct pmbus_driver_info *info = pmbus_get_driver_info(client); + struct ucd9000_data *data = to_ucd9000_data(info); + + if (reg >= PMBUS_VIRT_BASE) + return -ENXIO; + + ucd90320_wait(data); + return pmbus_read_word_data(client, page, phase, reg); +} + +static int ucd90320_read_byte_data(struct i2c_client *client, int page, int reg) +{ + const struct pmbus_driver_info *info = pmbus_get_driver_info(client); + struct ucd9000_data *data = to_ucd9000_data(info); + + ucd90320_wait(data); + return pmbus_read_byte_data(client, page, reg); +} + +static int ucd90320_write_word_data(struct i2c_client *client, int page, + int reg, u16 word) +{ + const struct pmbus_driver_info *info = pmbus_get_driver_info(client); + struct ucd9000_data *data = to_ucd9000_data(info); + int ret; + + ucd90320_wait(data); + ret = pmbus_write_word_data(client, page, reg, word); + data->write_time = ktime_get(); + + return ret; +} + +static int ucd90320_write_byte(struct i2c_client *client, int page, u8 value) +{ + const struct pmbus_driver_info *info = pmbus_get_driver_info(client); + struct ucd9000_data *data = to_ucd9000_data(info); + int ret; + + ucd90320_wait(data); + ret = pmbus_write_byte(client, page, value); + data->write_time = ktime_get(); + + return ret; +} + static int ucd9000_get_fan_config(struct i2c_client *client, int fan) { int fan_config = 0; @@ -598,6 +668,11 @@ static int ucd9000_probe(struct i2c_client *client) info->read_byte_data = ucd9000_read_byte_data; info->func[0] |= PMBUS_HAVE_FAN12 | PMBUS_HAVE_STATUS_FAN12 | PMBUS_HAVE_FAN34 | PMBUS_HAVE_STATUS_FAN34; + } else if (mid->driver_data == ucd90320) { + info->read_byte_data = ucd90320_read_byte_data; + info->read_word_data = ucd90320_read_word_data; + info->write_byte = ucd90320_write_byte; + info->write_word_data = ucd90320_write_word_data; }

ucd9000_probe_gpio(client, mid, data);

From: Jurica Vukadin jura@vukad.in

[ Upstream commit ee06a3ef7e3cddb62b90ac40aa661d3c12f7cabc ]

Prior to commit 5ee546594025 ("kconfig: change sym_change_count to a boolean flag"), the conf_updated flag was set to the new value *before* calling the callback. xconfig's save action depends on this behaviour, because xconfig calls conf_get_changed() directly from the callback and now sees the old value, thus never enabling the save button or the shortcut.

Restore the previous behaviour.

Fixes: 5ee546594025 ("kconfig: change sym_change_count to a boolean flag") Signed-off-by: Jurica Vukadin jura@vukad.in Acked-by: Randy Dunlap rdunlap@infradead.org Tested-by: Randy Dunlap rdunlap@infradead.org Signed-off-by: Masahiro Yamada masahiroy@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- scripts/kconfig/confdata.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c index b7c9f1dd5e422..992575f1e9769 100644 --- a/scripts/kconfig/confdata.c +++ b/scripts/kconfig/confdata.c @@ -1226,10 +1226,12 @@ static void (*conf_changed_callback)(void);

void conf_set_changed(bool val) { - if (conf_changed_callback && conf_changed != val) - conf_changed_callback(); + bool changed = conf_changed != val;

conf_changed = val; + + if (conf_changed_callback && changed) + conf_changed_callback(); }

bool conf_get_changed(void)

From: Lars-Peter Clausen lars@metafoo.de

[ Upstream commit ab00709310eedcd8dae0df1f66d332f9bc64c99e ]

The ltc2992 drivers uses a mutex and I2C bus access in its GPIO chip `set` and `get` implementation. This means these functions can sleep and the GPIO chip should set the `can_sleep` property to true.

This will ensure that a warning is printed when trying to set or get the GPIO value from a context that potentially can't sleep.

Fixes: 9ca26df1ba25 ("hwmon: (ltc2992) Add support for GPIOs.") Signed-off-by: Lars-Peter Clausen lars@metafoo.de Link: https://lore.kernel.org/r/20230314093146.2443845-2-lars@metafoo.de Signed-off-by: Guenter Roeck linux@roeck-us.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hwmon/ltc2992.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/hwmon/ltc2992.c b/drivers/hwmon/ltc2992.c index 88514152d9306..69341de397cb9 100644 --- a/drivers/hwmon/ltc2992.c +++ b/drivers/hwmon/ltc2992.c @@ -323,6 +323,7 @@ static int ltc2992_config_gpio(struct ltc2992_state *st) st->gc.label = name; st->gc.parent = &st->client->dev; st->gc.owner = THIS_MODULE; + st->gc.can_sleep = true; st->gc.base = -1; st->gc.names = st->gpio_names; st->gc.ngpio = ARRAY_SIZE(st->gpio_names);

From: Baokun Li libaokun1@huawei.com

[ Upstream commit 3039d8b8692408438a618fac2776b629852663c3 ]

When mounting a crafted ext4 image, s_journal_inum may change after journal replay, which is obviously unreasonable because we have successfully loaded and replayed the journal through the old s_journal_inum. And the new s_journal_inum bypasses some of the checks in ext4_get_journal(), which may trigger a null pointer dereference problem. So if s_journal_inum changes after the journal replay, we ignore the change, and rewrite the current journal_inum to the superblock.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=216541 Reported-by: Luís Henriques lhenriques@suse.de Signed-off-by: Baokun Li libaokun1@huawei.com Reviewed-by: Jan Kara jack@suse.cz Link: https://lore.kernel.org/r/20230107032126.4165860-3-libaokun1@huawei.com Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ext4/super.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/fs/ext4/super.c b/fs/ext4/super.c index c81fa0fa9901a..e79ca9ef98316 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5967,8 +5967,11 @@ static int ext4_load_journal(struct super_block *sb, if (!really_read_only && journal_devnum && journal_devnum != le32_to_cpu(es->s_journal_dev)) { es->s_journal_dev = cpu_to_le32(journal_devnum); - - /* Make sure we flush the recovery flag to disk. */ + ext4_commit_super(sb); + } + if (!really_read_only && journal_inum && + journal_inum != le32_to_cpu(es->s_journal_inum)) { + es->s_journal_inum = cpu_to_le32(journal_inum); ext4_commit_super(sb); }

From: Qu Huang qu.huang@linux.dev

[ Upstream commit 4fc8fff378b2f2039f2a666d9f8c570f4e58352c ]

In the kfd_wait_on_events() function, the kfd_event_waiter structure is allocated by alloc_event_waiters(), but the event field of the waiter structure is not initialized; When copy_from_user() fails in the kfd_wait_on_events() function, it will enter exception handling to release the previously allocated memory of the waiter structure; Due to the event field of the waiters structure being accessed in the free_waiters() function, this results in illegal memory access and system crash, here is the crash log:

localhost kernel: RIP: 0010:native_queued_spin_lock_slowpath+0x185/0x1e0 localhost kernel: RSP: 0018:ffffaa53c362bd60 EFLAGS: 00010082 localhost kernel: RAX: ff3d3d6bff4007cb RBX: 0000000000000282 RCX: 00000000002c0000 localhost kernel: RDX: ffff9e855eeacb80 RSI: 000000000000279c RDI: ffffe7088f6a21d0 localhost kernel: RBP: ffffe7088f6a21d0 R08: 00000000002c0000 R09: ffffaa53c362be64 localhost kernel: R10: ffffaa53c362bbd8 R11: 0000000000000001 R12: 0000000000000002 localhost kernel: R13: ffff9e7ead15d600 R14: 0000000000000000 R15: ffff9e7ead15d698 localhost kernel: FS: 0000152a3d111700(0000) GS:ffff9e855ee80000(0000) knlGS:0000000000000000 localhost kernel: CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 localhost kernel: CR2: 0000152938000010 CR3: 000000044d7a4000 CR4: 00000000003506e0 localhost kernel: Call Trace: localhost kernel: _raw_spin_lock_irqsave+0x30/0x40 localhost kernel: remove_wait_queue+0x12/0x50 localhost kernel: kfd_wait_on_events+0x1b6/0x490 [hydcu] localhost kernel: ? ftrace_graph_caller+0xa0/0xa0 localhost kernel: kfd_ioctl+0x38c/0x4a0 [hydcu] localhost kernel: ? kfd_ioctl_set_trap_handler+0x70/0x70 [hydcu] localhost kernel: ? kfd_ioctl_create_queue+0x5a0/0x5a0 [hydcu] localhost kernel: ? ftrace_graph_caller+0xa0/0xa0 localhost kernel: __x64_sys_ioctl+0x8e/0xd0 localhost kernel: ? syscall_trace_enter.isra.18+0x143/0x1b0 localhost kernel: do_syscall_64+0x33/0x80 localhost kernel: entry_SYSCALL_64_after_hwframe+0x44/0xa9 localhost kernel: RIP: 0033:0x152a4dff68d7

Allocate the structure with kcalloc, and remove redundant 0-initialization and a redundant loop condition check.

Signed-off-by: Qu Huang qu.huang@linux.dev Signed-off-by: Felix Kuehling Felix.Kuehling@amd.com Reviewed-by: Felix Kuehling Felix.Kuehling@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/amdkfd/kfd_events.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c index 729d26d648af3..2880ed96ac2e3 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c @@ -778,16 +778,13 @@ static struct kfd_event_waiter *alloc_event_waiters(uint32_t num_events) struct kfd_event_waiter *event_waiters; uint32_t i;

- event_waiters = kmalloc_array(num_events, - sizeof(struct kfd_event_waiter), - GFP_KERNEL); + event_waiters = kcalloc(num_events, sizeof(struct kfd_event_waiter), + GFP_KERNEL); if (!event_waiters) return NULL;

- for (i = 0; (event_waiters) && (i < num_events) ; i++) { + for (i = 0; i < num_events; i++) init_wait(&event_waiters[i].wait); - event_waiters[i].activated = false; - }

return event_waiters; }

From: Tiezhu Yang yangtiezhu@loongson.cn

[ Upstream commit bb7a78e343468873bf00b2b181fcfd3c02d8cb56 ]

Under CONFIG_DEBUG_ATOMIC_SLEEP=y and CONFIG_DEBUG_PREEMPT=y, we can see the following messages on LoongArch, this is because using might_sleep() in preemption disable context.

[ 0.001127] smp: Bringing up secondary CPUs ... [ 0.001222] Booting CPU#1... [ 0.001244] 64-bit Loongson Processor probed (LA464 Core) [ 0.001247] CPU1 revision is: 0014c012 (Loongson-64bit) [ 0.001250] FPU1 revision is: 00000000 [ 0.001252] BUG: sleeping function called from invalid context at kernel/locking/mutex.c:283 [ 0.001255] in_atomic(): 1, irqs_disabled(): 1, non_block: 0, pid: 0, name: swapper/1 [ 0.001257] preempt_count: 1, expected: 0 [ 0.001258] RCU nest depth: 0, expected: 0 [ 0.001259] Preemption disabled at: [ 0.001261] [<9000000000223800>] arch_dup_task_struct+0x20/0x110 [ 0.001272] CPU: 1 PID: 0 Comm: swapper/1 Not tainted 6.2.0-rc7+ #43 [ 0.001275] Hardware name: Loongson Loongson-3A5000-7A1000-1w-A2101/Loongson-LS3A5000-7A1000-1w-A2101, BIOS vUDK2018-LoongArch-V4.0.05132-beta10 12/13/202 [ 0.001277] Stack : 0072617764726148 0000000000000000 9000000000222f1c 90000001001e0000 [ 0.001286] 90000001001e3be0 90000001001e3be8 0000000000000000 0000000000000000 [ 0.001292] 90000001001e3be8 0000000000000040 90000001001e3cb8 90000001001e3a50 [ 0.001297] 9000000001642000 90000001001e3be8 be694d10ce4139dd 9000000100174500 [ 0.001303] 0000000000000001 0000000000000001 00000000ffffe0a2 0000000000000020 [ 0.001309] 000000000000002f 9000000001354116 00000000056b0000 ffffffffffffffff [ 0.001314] 0000000000000000 0000000000000000 90000000014f6e90 9000000001642000 [ 0.001320] 900000000022b69c 0000000000000001 0000000000000000 9000000001736a90 [ 0.001325] 9000000100038000 0000000000000000 9000000000222f34 0000000000000000 [ 0.001331] 00000000000000b0 0000000000000004 0000000000000000 0000000000070000 [ 0.001337] ... [ 0.001339] Call Trace: [ 0.001342] [<9000000000222f34>] show_stack+0x5c/0x180 [ 0.001346] [<90000000010bdd80>] dump_stack_lvl+0x60/0x88 [ 0.001352] [<9000000000266418>] __might_resched+0x180/0x1cc [ 0.001356] [<90000000010c742c>] mutex_lock+0x20/0x64 [ 0.001359] [<90000000002a8ccc>] irq_find_matching_fwspec+0x48/0x124 [ 0.001364] [<90000000002259c4>] constant_clockevent_init+0x68/0x204 [ 0.001368] [<900000000022acf4>] start_secondary+0x40/0xa8 [ 0.001371] [<90000000010c0124>] smpboot_entry+0x60/0x64

Here are the complete call chains:

smpboot_entry() start_secondary() constant_clockevent_init() get_timer_irq() irq_find_matching_fwnode() irq_find_matching_fwspec() mutex_lock() might_sleep() __might_sleep() __might_resched()

In order to avoid the above issue, we should break the call chains, using timer_irq_installed variable as check condition to only call get_timer_irq() once in constant_clockevent_init() is a simple and proper way.

Signed-off-by: Tiezhu Yang yangtiezhu@loongson.cn Signed-off-by: Huacai Chen chenhuacai@loongson.cn Signed-off-by: Sasha Levin sashal@kernel.org --- arch/loongarch/kernel/time.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/arch/loongarch/kernel/time.c b/arch/loongarch/kernel/time.c index a6576dea590c0..4351f69d99501 100644 --- a/arch/loongarch/kernel/time.c +++ b/arch/loongarch/kernel/time.c @@ -140,16 +140,17 @@ static int get_timer_irq(void)

int constant_clockevent_init(void) { - int irq; unsigned int cpu = smp_processor_id(); unsigned long min_delta = 0x600; unsigned long max_delta = (1UL << 48) - 1; struct clock_event_device *cd; - static int timer_irq_installed = 0; + static int irq = 0, timer_irq_installed = 0;

- irq = get_timer_irq(); - if (irq < 0) - pr_err("Failed to map irq %d (timer)\n", irq); + if (!timer_irq_installed) { + irq = get_timer_irq(); + if (irq < 0) + pr_err("Failed to map irq %d (timer)\n", irq); + }

cd = &per_cpu(constant_clockevent_device, cpu);

From: Horatio Zhang Hongkun.Zhang@amd.com

[ Upstream commit 23f4a2d29ba57bf88095f817de5809d427fcbe7e ]

The call trace occurs when the amdgpu is removed after the mode1 reset. During mode1 reset, from suspend to resume, there is no need to reinitialize the ta firmware buffer which caused the bo pin_count increase redundantly.

[ 489.885525] Call Trace: [ 489.885525] <TASK> [ 489.885526] amdttm_bo_put+0x34/0x50 [amdttm] [ 489.885529] amdgpu_bo_free_kernel+0xe8/0x130 [amdgpu] [ 489.885620] psp_free_shared_bufs+0xb7/0x150 [amdgpu] [ 489.885720] psp_hw_fini+0xce/0x170 [amdgpu] [ 489.885815] amdgpu_device_fini_hw+0x2ff/0x413 [amdgpu] [ 489.885960] ? blocking_notifier_chain_unregister+0x56/0xb0 [ 489.885962] amdgpu_driver_unload_kms+0x51/0x60 [amdgpu] [ 489.886049] amdgpu_pci_remove+0x5a/0x140 [amdgpu] [ 489.886132] ? __pm_runtime_resume+0x60/0x90 [ 489.886134] pci_device_remove+0x3e/0xb0 [ 489.886135] __device_release_driver+0x1ab/0x2a0 [ 489.886137] driver_detach+0xf3/0x140 [ 489.886138] bus_remove_driver+0x6c/0xf0 [ 489.886140] driver_unregister+0x31/0x60 [ 489.886141] pci_unregister_driver+0x40/0x90 [ 489.886142] amdgpu_exit+0x15/0x451 [amdgpu]

Signed-off-by: Horatio Zhang Hongkun.Zhang@amd.com Signed-off-by: longlyao Longlong.Yao@amd.com Reviewed-by: Guchun Chen guchun.chen@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_psp.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index ba092072308fa..1b4105110f398 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -1685,7 +1685,7 @@ static int psp_hdcp_initialize(struct psp_context *psp) psp->hdcp_context.context.mem_context.shared_mem_size = PSP_HDCP_SHARED_MEM_SIZE; psp->hdcp_context.context.ta_load_type = GFX_CMD_ID_LOAD_TA;

- if (!psp->hdcp_context.context.initialized) { + if (!psp->hdcp_context.context.mem_context.shared_buf) { ret = psp_ta_init_shared_buf(psp, &psp->hdcp_context.context.mem_context); if (ret) return ret; @@ -1752,7 +1752,7 @@ static int psp_dtm_initialize(struct psp_context *psp) psp->dtm_context.context.mem_context.shared_mem_size = PSP_DTM_SHARED_MEM_SIZE; psp->dtm_context.context.ta_load_type = GFX_CMD_ID_LOAD_TA;

- if (!psp->dtm_context.context.initialized) { + if (!psp->dtm_context.context.mem_context.shared_buf) { ret = psp_ta_init_shared_buf(psp, &psp->dtm_context.context.mem_context); if (ret) return ret; @@ -1820,7 +1820,7 @@ static int psp_rap_initialize(struct psp_context *psp) psp->rap_context.context.mem_context.shared_mem_size = PSP_RAP_SHARED_MEM_SIZE; psp->rap_context.context.ta_load_type = GFX_CMD_ID_LOAD_TA;

- if (!psp->rap_context.context.initialized) { + if (!psp->rap_context.context.mem_context.shared_buf) { ret = psp_ta_init_shared_buf(psp, &psp->rap_context.context.mem_context); if (ret) return ret;

From: Theodore Ts'o tytso@mit.edu

commit 70e42feab2e20618ddd0cbfc4ab4b08628236ecd upstream.

Fixes: 0813299c586b ("ext4: Fix possible corruption when moving a directory") Link: https://lore.kernel.org/r/5efbe1b9-ad8b-4a4f-b422-24824d2b775c@kili.mountain Reported-by: Dan Carpenter error27@gmail.com Reported-by: syzbot+0c73d1d8b952c5f3d714@syzkaller.appspotmail.com Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/ext4/namei.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)

--- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -3884,10 +3884,8 @@ static int ext4_rename(struct user_names goto end_rename; } retval = ext4_rename_dir_prepare(handle, &old); - if (retval) { - inode_unlock(old.inode); + if (retval) goto end_rename; - } } /* * If we're renaming a file within an inline_data dir and adding or

From: Alexander Sverdlin alexander.sverdlin@siemens.com

commit 1be6f2b15f902c02e055ae0b419ca789200473c9 upstream.

From time to time DMA completion can come in the middle of DMA shutdown:

<process ctx>: <IRQ>: lpuart32_shutdown() lpuart_dma_shutdown() del_timer_sync() lpuart_dma_rx_complete() lpuart_copy_rx_to_tty() mod_timer() lpuart_dma_rx_free()

When the timer fires a bit later, sport->dma_rx_desc is NULL:

Unable to handle kernel NULL pointer dereference at virtual address 0000000000000004 pc : lpuart_copy_rx_to_tty+0xcc/0x5bc lr : lpuart_timer_func+0x1c/0x2c Call trace: lpuart_copy_rx_to_tty lpuart_timer_func call_timer_fn __run_timers.part.0 run_timer_softirq __do_softirq __irq_exit_rcu irq_exit handle_domain_irq gic_handle_irq call_on_irq_stack do_interrupt_handler ...

To fix this fold del_timer_sync() into lpuart_dma_rx_free() after dmaengine_terminate_sync() to make sure timer will not be re-started in lpuart_copy_rx_to_tty() <= lpuart_dma_rx_complete().

Fixes: 4a8588a1cf86 ("serial: fsl_lpuart: delete timer on shutdown") Cc: stable stable@kernel.org Signed-off-by: Alexander Sverdlin alexander.sverdlin@siemens.com Link: https://lore.kernel.org/r/20230309134302.74940-2-alexander.sverdlin@siemens.... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/tty/serial/fsl_lpuart.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-)

--- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -1328,6 +1328,7 @@ static void lpuart_dma_rx_free(struct ua struct dma_chan *chan = sport->dma_rx_chan;

dmaengine_terminate_sync(chan); + del_timer_sync(&sport->lpuart_timer); dma_unmap_sg(chan->device->dev, &sport->rx_sgl, 1, DMA_FROM_DEVICE); kfree(sport->rx_ring.buf); sport->rx_ring.tail = 0; @@ -1762,7 +1763,6 @@ static int lpuart32_startup(struct uart_ static void lpuart_dma_shutdown(struct lpuart_port *sport) { if (sport->lpuart_dma_rx_use) { - del_timer_sync(&sport->lpuart_timer); lpuart_dma_rx_free(&sport->port); sport->lpuart_dma_rx_use = false; } @@ -1922,10 +1922,8 @@ lpuart_set_termios(struct uart_port *por * Since timer function acqures sport->port.lock, need to stop before * acquring same lock because otherwise del_timer_sync() can deadlock. */ - if (old && sport->lpuart_dma_rx_use) { - del_timer_sync(&sport->lpuart_timer); + if (old && sport->lpuart_dma_rx_use) lpuart_dma_rx_free(&sport->port); - }

spin_lock_irqsave(&sport->port.lock, flags);

@@ -2159,10 +2157,8 @@ lpuart32_set_termios(struct uart_port *p * Since timer function acqures sport->port.lock, need to stop before * acquring same lock because otherwise del_timer_sync() can deadlock. */ - if (old && sport->lpuart_dma_rx_use) { - del_timer_sync(&sport->lpuart_timer); + if (old && sport->lpuart_dma_rx_use) lpuart_dma_rx_free(&sport->port); - }

spin_lock_irqsave(&sport->port.lock, flags);

@@ -2962,7 +2958,6 @@ static int lpuart_suspend(struct device * cannot resume as expected, hence gracefully release the * Rx DMA path before suspend and start Rx DMA path on resume. */ - del_timer_sync(&sport->lpuart_timer); lpuart_dma_rx_free(&sport->port);

/* Disable Rx DMA to use UART port as wakeup source */

From: Biju Das biju.das.jz@bp.renesas.com

commit 32e293be736b853f168cd065d9cbc1b0c69f545d upstream.

As per HW manual for EMEV2 "R19UH0040EJ0400 Rev.4.00", the UART IP found on EMMA mobile SoC is Register-compatible with the general-purpose 16750 UART chip. Fix UART port type as 16750 and enable 64-bytes fifo support.

Fixes: 22886ee96895 ("serial8250-em: Emma Mobile UART driver V2") Cc: stable@vger.kernel.org Signed-off-by: Biju Das biju.das.jz@bp.renesas.com Link: https://lore.kernel.org/r/20230227114152.22265-2-biju.das.jz@bp.renesas.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/tty/serial/8250/8250_em.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/drivers/tty/serial/8250/8250_em.c +++ b/drivers/tty/serial/8250/8250_em.c @@ -106,8 +106,8 @@ static int serial8250_em_probe(struct pl memset(&up, 0, sizeof(up)); up.port.mapbase = regs->start; up.port.irq = irq; - up.port.type = PORT_UNKNOWN; - up.port.flags = UPF_BOOT_AUTOCONF | UPF_FIXED_PORT | UPF_IOREMAP; + up.port.type = PORT_16750; + up.port.flags = UPF_FIXED_PORT | UPF_IOREMAP | UPF_FIXED_TYPE; up.port.dev = &pdev->dev; up.port.private_data = priv;

From: Randy Dunlap rdunlap@infradead.org

commit f8086d1a65ac693e3fd863128352b4b11ee7324d upstream.

REGMAP is a hidden (not user visible) symbol. Users cannot set it directly thru "make *config", so drivers should select it instead of depending on it if they need it.

Consistently using "select" or "depends on" can also help reduce Kconfig circular dependency issues.

Therefore, change the use of "depends on REGMAP" to "select REGMAP".

Fixes: 8d310c9107a2 ("drivers/tty/serial/8250: Make Aspeed VUART SIRQ polarity configurable") Cc: stable stable@kernel.org Signed-off-by: Randy Dunlap rdunlap@infradead.org Cc: Greg Kroah-Hartman gregkh@linuxfoundation.org Cc: Oskar Senft osk@google.com Cc: linux-serial@vger.kernel.org Link: https://lore.kernel.org/r/20230226053953.4681-9-rdunlap@infradead.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/tty/serial/8250/Kconfig | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/drivers/tty/serial/8250/Kconfig +++ b/drivers/tty/serial/8250/Kconfig @@ -253,8 +253,9 @@ config SERIAL_8250_ASPEED_VUART tristate "Aspeed Virtual UART" depends on SERIAL_8250 depends on OF - depends on REGMAP && MFD_SYSCON + depends on MFD_SYSCON depends on ARCH_ASPEED || COMPILE_TEST + select REGMAP help If you want to use the virtual UART (VUART) device on Aspeed BMC platforms, enable this option. This enables the 16550A-

From: Johan Hovold johan+linaro@kernel.org

commit 5553055c62683ce339f9ef5fb2a26c8331485d68 upstream.

The current interconnect provider registration interface is inherently racy as nodes are not added until the after adding the provider. This can specifically cause racing DT lookups to fail.

Switch to using the new API where the provider is not registered until after it has been fully initialised.

Fixes: 06f079816d4c ("memory: tegra-mc: Add interconnect framework") Cc: stable@vger.kernel.org # 5.11 Cc: Dmitry Osipenko digetx@gmail.com Acked-by: Krzysztof Kozlowski krzysztof.kozlowski@linaro.org Signed-off-by: Johan Hovold johan+linaro@kernel.org Link: https://lore.kernel.org/r/20230306075651.2449-18-johan+linaro@kernel.org Signed-off-by: Georgi Djakov djakov@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/memory/tegra/mc.c | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-)

--- a/drivers/memory/tegra/mc.c +++ b/drivers/memory/tegra/mc.c @@ -794,16 +794,12 @@ static int tegra_mc_interconnect_setup(s mc->provider.aggregate = mc->soc->icc_ops->aggregate; mc->provider.xlate_extended = mc->soc->icc_ops->xlate_extended;

- err = icc_provider_add(&mc->provider); - if (err) - return err; + icc_provider_init(&mc->provider);

/* create Memory Controller node */ node = icc_node_create(TEGRA_ICC_MC); - if (IS_ERR(node)) { - err = PTR_ERR(node); - goto del_provider; - } + if (IS_ERR(node)) + return PTR_ERR(node);

node->name = "Memory Controller"; icc_node_add(node, &mc->provider); @@ -830,12 +826,14 @@ static int tegra_mc_interconnect_setup(s goto remove_nodes; }

+ err = icc_provider_register(&mc->provider); + if (err) + goto remove_nodes; + return 0;

remove_nodes: icc_nodes_remove(&mc->provider); -del_provider: - icc_provider_del(&mc->provider);

return err; }

From: Johan Hovold johan+linaro@kernel.org

commit abd9f1b49cf25eebeaba193c7707355be3f48dae upstream.

The current interconnect provider registration interface is inherently racy as nodes are not added until the after adding the provider. This can specifically cause racing DT lookups to fail.

Switch to using the new API where the provider is not registered until after it has been fully initialised.

Fixes: 380def2d4cf2 ("memory: tegra124: Support interconnect framework") Cc: stable@vger.kernel.org # 5.12 Cc: Dmitry Osipenko digetx@gmail.com Acked-by: Krzysztof Kozlowski krzysztof.kozlowski@linaro.org Signed-off-by: Johan Hovold johan+linaro@kernel.org Link: https://lore.kernel.org/r/20230306075651.2449-19-johan+linaro@kernel.org Signed-off-by: Georgi Djakov djakov@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/memory/tegra/tegra124-emc.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-)

--- a/drivers/memory/tegra/tegra124-emc.c +++ b/drivers/memory/tegra/tegra124-emc.c @@ -1351,15 +1351,13 @@ static int tegra_emc_interconnect_init(s emc->provider.aggregate = soc->icc_ops->aggregate; emc->provider.xlate_extended = emc_of_icc_xlate_extended;

- err = icc_provider_add(&emc->provider); - if (err) - goto err_msg; + icc_provider_init(&emc->provider);

/* create External Memory Controller node */ node = icc_node_create(TEGRA_ICC_EMC); if (IS_ERR(node)) { err = PTR_ERR(node); - goto del_provider; + goto err_msg; }

node->name = "External Memory Controller"; @@ -1380,12 +1378,14 @@ static int tegra_emc_interconnect_init(s node->name = "External Memory (DRAM)"; icc_node_add(node, &emc->provider);

+ err = icc_provider_register(&emc->provider); + if (err) + goto remove_nodes; + return 0;

remove_nodes: icc_nodes_remove(&emc->provider); -del_provider: - icc_provider_del(&emc->provider); err_msg: dev_err(emc->dev, "failed to initialize ICC: %d\n", err);

From: Thomas Hellström thomas.hellstrom@linux.intel.com

commit 9a9a8fe26751334b7739193a94eba741073b8a55 upstream.

The LRU mechanism may look up a resource in the process of being removed from an object. The locking rules here are a bit unclear but it looks currently like res->bo assignment is protected by the LRU lock, whereas bo->resource is protected by the object lock, while *clearing* of bo->resource is also protected by the LRU lock. This means that if we check that bo->resource points to the LRU resource under the LRU lock we should be safe. So perform that check before deciding to swap out a bo. That avoids dereferencing a NULL bo->resource in ttm_bo_swapout().

Fixes: 6a9b02899402 ("drm/ttm: move the LRU into resource handling v4") Cc: Christian König christian.koenig@amd.com Cc: Daniel Vetter daniel.vetter@ffwll.ch Cc: Christian Koenig christian.koenig@amd.com Cc: Huang Rui ray.huang@amd.com Cc: Alex Deucher alexander.deucher@amd.com Cc: Felix Kuehling Felix.Kuehling@amd.com Cc: Philip Yang Philip.Yang@amd.com Cc: Qiang Yu qiang.yu@amd.com Cc: Matthew Auld matthew.auld@intel.com Cc: Nirmoy Das nirmoy.das@intel.com Cc: Tvrtko Ursulin tvrtko.ursulin@intel.com Cc: "Thomas Hellström" thomas.hellstrom@linux.intel.com Cc: Anshuman Gupta anshuman.gupta@intel.com Cc: Arunpravin Paneer Selvam Arunpravin.PaneerSelvam@amd.com Cc: dri-devel@lists.freedesktop.org Cc: stable@vger.kernel.org # v5.19+ Signed-off-by: Thomas Hellström thomas.hellstrom@linux.intel.com Reviewed-by: Christian König christian.koenig@amd.com Link: https://patchwork.freedesktop.org/patch/msgid/20230307144621.10748-2-thomas.... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/ttm/ttm_device.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/gpu/drm/ttm/ttm_device.c +++ b/drivers/gpu/drm/ttm/ttm_device.c @@ -158,7 +158,7 @@ int ttm_device_swapout(struct ttm_device struct ttm_buffer_object *bo = res->bo; uint32_t num_pages;

- if (!bo) + if (!bo || bo->resource != res) continue;

num_pages = PFN_UP(bo->base.size);

From: Johan Hovold johan+linaro@kernel.org

commit e0e7089bf9a87bc5e3997422e4e24563424f9018 upstream.

The interconnect framework currently expects that providers are only removed when there are no users and after all nodes have been removed.

There is currently nothing that guarantees this to be the case and the framework does not do any reference counting, but refusing to remove the provider is never correct as that would leave a dangling pointer to a resource that is about to be released in the global provider list (e.g. accessible through debugfs).

Replace the current sanity checks with WARN_ON() so that the provider is always removed.

Fixes: 11f1ceca7031 ("interconnect: Add generic on-chip interconnect API") Cc: stable@vger.kernel.org # 5.1: 680f8666baf6: interconnect: Make icc_provider_del() return void Reviewed-by: Konrad Dybcio konrad.dybcio@linaro.org Signed-off-by: Johan Hovold johan+linaro@kernel.org Tested-by: Luca Ceresoli luca.ceresoli@bootlin.com # i.MX8MP MSC SM2-MB-EP1 Board Link: https://lore.kernel.org/r/20230306075651.2449-3-johan+linaro@kernel.org Signed-off-by: Georgi Djakov djakov@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/interconnect/core.c | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-)

--- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -1061,18 +1061,8 @@ EXPORT_SYMBOL_GPL(icc_provider_add); void icc_provider_del(struct icc_provider *provider) { mutex_lock(&icc_lock); - if (provider->users) { - pr_warn("interconnect provider still has %d users\n", - provider->users); - mutex_unlock(&icc_lock); - return; - } - - if (!list_empty(&provider->nodes)) { - pr_warn("interconnect provider still has nodes\n"); - mutex_unlock(&icc_lock); - return; - } + WARN_ON(provider->users); + WARN_ON(!list_empty(&provider->nodes));

list_del(&provider->provider_list); mutex_unlock(&icc_lock);

From: Johan Hovold johan+linaro@kernel.org

commit 9fbd35520f1f7f3cbe1873939a27ad9b009f21f9 upstream.

The current interconnect provider registration interface is inherently racy as nodes are not added until the after adding the provider. This can specifically cause racing DT lookups to fail.

Switch to using the new API where the provider is not registered until after it has been fully initialised.

Fixes: f0d8048525d7 ("interconnect: Add imx core driver") Cc: stable@vger.kernel.org # 5.8 Cc: Alexandre Bailon abailon@baylibre.com Reviewed-by: Konrad Dybcio konrad.dybcio@linaro.org Signed-off-by: Johan Hovold johan+linaro@kernel.org Tested-by: Luca Ceresoli luca.ceresoli@bootlin.com # i.MX8MP MSC SM2-MB-EP1 Board Link: https://lore.kernel.org/r/20230306075651.2449-5-johan+linaro@kernel.org Signed-off-by: Georgi Djakov djakov@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/interconnect/imx/imx.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-)

--- a/drivers/interconnect/imx/imx.c +++ b/drivers/interconnect/imx/imx.c @@ -295,6 +295,9 @@ int imx_icc_register(struct platform_dev provider->xlate = of_icc_xlate_onecell; provider->data = data; provider->dev = dev->parent; + + icc_provider_init(provider); + platform_set_drvdata(pdev, imx_provider);

if (settings) { @@ -306,20 +309,18 @@ int imx_icc_register(struct platform_dev } }

- ret = icc_provider_add(provider); - if (ret) { - dev_err(dev, "error adding interconnect provider: %d\n", ret); + ret = imx_icc_register_nodes(imx_provider, nodes, nodes_count, settings); + if (ret) return ret; - }

- ret = imx_icc_register_nodes(imx_provider, nodes, nodes_count, settings); + ret = icc_provider_register(provider); if (ret) - goto provider_del; + goto err_unregister_nodes;

return 0;

-provider_del: - icc_provider_del(provider); +err_unregister_nodes: + imx_icc_unregister_nodes(&imx_provider->provider); return ret; } EXPORT_SYMBOL_GPL(imx_icc_register); @@ -328,9 +329,8 @@ void imx_icc_unregister(struct platform_ { struct imx_icc_provider *imx_provider = platform_get_drvdata(pdev);

+ icc_provider_deregister(&imx_provider->provider); imx_icc_unregister_nodes(&imx_provider->provider); - - icc_provider_del(&imx_provider->provider); } EXPORT_SYMBOL_GPL(imx_icc_unregister);

From: Johan Hovold johan+linaro@kernel.org

commit 174941ed28a3573db075da46d95b4dcf9d4c49c2 upstream.

The current interconnect provider registration interface is inherently racy as nodes are not added until the after adding the provider. This can specifically cause racing DT lookups to fail:

of_icc_xlate_onecell: invalid index 0 cpu cpu0: error -EINVAL: error finding src node cpu cpu0: dev_pm_opp_of_find_icc_paths: Unable to get path0: -22 qcom-cpufreq-hw: probe of 18591000.cpufreq failed with error -22

Switch to using the new API where the provider is not registered until after it has been fully initialised.

Fixes: 5bc9900addaf ("interconnect: qcom: Add OSM L3 interconnect provider support") Cc: stable@vger.kernel.org # 5.7 Reviewed-by: Konrad Dybcio konrad.dybcio@linaro.org Signed-off-by: Johan Hovold johan+linaro@kernel.org Link: https://lore.kernel.org/r/20230306075651.2449-6-johan+linaro@kernel.org Signed-off-by: Georgi Djakov djakov@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/interconnect/qcom/osm-l3.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-)

--- a/drivers/interconnect/qcom/osm-l3.c +++ b/drivers/interconnect/qcom/osm-l3.c @@ -158,8 +158,8 @@ static int qcom_osm_l3_remove(struct pla { struct qcom_osm_l3_icc_provider *qp = platform_get_drvdata(pdev);

+ icc_provider_deregister(&qp->provider); icc_nodes_remove(&qp->provider); - icc_provider_del(&qp->provider);

return 0; } @@ -245,14 +245,9 @@ static int qcom_osm_l3_probe(struct plat provider->set = qcom_osm_l3_set; provider->aggregate = icc_std_aggregate; provider->xlate = of_icc_xlate_onecell; - INIT_LIST_HEAD(&provider->nodes); provider->data = data;

- ret = icc_provider_add(provider); - if (ret) { - dev_err(&pdev->dev, "error adding interconnect provider\n"); - return ret; - } + icc_provider_init(provider);

for (i = 0; i < num_nodes; i++) { size_t j; @@ -275,12 +270,15 @@ static int qcom_osm_l3_probe(struct plat } data->num_nodes = num_nodes;

+ ret = icc_provider_register(provider); + if (ret) + goto err; + platform_set_drvdata(pdev, qp);

return 0; err: icc_nodes_remove(provider); - icc_provider_del(provider);

return ret; }

From: Johan Hovold johan+linaro@kernel.org

commit 90ae93d8affc1061cd87ca8ddd9a838c7d31a158 upstream.

The current interconnect provider registration interface is inherently racy as nodes are not added until the after adding the provider. This can specifically cause racing DT lookups to fail.

Switch to using the new API where the provider is not registered until after it has been fully initialised.

Fixes: 62feb14ee8a3 ("interconnect: qcom: Consolidate interconnect RPM support") Fixes: 30c8fa3ec61a ("interconnect: qcom: Add MSM8916 interconnect provider driver") Cc: stable@vger.kernel.org # 5.7 Reviewed-by: Konrad Dybcio konrad.dybcio@linaro.org Reviewed-by: Jun Nie jun.nie@linaro.org Signed-off-by: Johan Hovold johan+linaro@kernel.org Link: https://lore.kernel.org/r/20230306075651.2449-9-johan+linaro@kernel.org Signed-off-by: Georgi Djakov djakov@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/interconnect/qcom/icc-rpm.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-)

--- a/drivers/interconnect/qcom/icc-rpm.c +++ b/drivers/interconnect/qcom/icc-rpm.c @@ -503,7 +503,6 @@ regmap_done: }

provider = &qp->provider; - INIT_LIST_HEAD(&provider->nodes); provider->dev = dev; provider->set = qcom_icc_set; provider->pre_aggregate = qcom_icc_pre_bw_aggregate; @@ -511,12 +510,7 @@ regmap_done: provider->xlate_extended = qcom_icc_xlate_extended; provider->data = data;

- ret = icc_provider_add(provider); - if (ret) { - dev_err(dev, "error adding interconnect provider: %d\n", ret); - clk_bulk_disable_unprepare(qp->num_clks, qp->bus_clks); - return ret; - } + icc_provider_init(provider);

for (i = 0; i < num_nodes; i++) { size_t j; @@ -524,7 +518,7 @@ regmap_done: node = icc_node_create(qnodes[i]->id); if (IS_ERR(node)) { ret = PTR_ERR(node); - goto err; + goto err_remove_nodes; }

node->name = qnodes[i]->name; @@ -538,20 +532,26 @@ regmap_done: } data->num_nodes = num_nodes;

+ ret = icc_provider_register(provider); + if (ret) + goto err_remove_nodes; + platform_set_drvdata(pdev, qp);

/* Populate child NoC devices if any */ if (of_get_child_count(dev->of_node) > 0) { ret = of_platform_populate(dev->of_node, NULL, NULL, dev); if (ret) - goto err; + goto err_deregister_provider; }

return 0; -err: + +err_deregister_provider: + icc_provider_deregister(provider); +err_remove_nodes: icc_nodes_remove(provider); clk_bulk_disable_unprepare(qp->num_clks, qp->bus_clks); - icc_provider_del(provider);

return ret; } @@ -561,9 +561,9 @@ int qnoc_remove(struct platform_device * { struct qcom_icc_provider *qp = platform_get_drvdata(pdev);

+ icc_provider_deregister(&qp->provider); icc_nodes_remove(&qp->provider); clk_bulk_disable_unprepare(qp->num_clks, qp->bus_clks); - icc_provider_del(&qp->provider);

return 0; }

From: Johan Hovold johan+linaro@kernel.org

commit 74240a5bebd48d8b843c6d0f1acfaa722a5abeb7 upstream.

The current interconnect provider registration interface is inherently racy as nodes are not added until the after adding the provider. This can specifically cause racing DT lookups to fail.

Switch to using the new API where the provider is not registered until after it has been fully initialised.

Fixes: 976daac4a1c5 ("interconnect: qcom: Consolidate interconnect RPMh support") Cc: stable@vger.kernel.org # 5.7 Reviewed-by: Konrad Dybcio konrad.dybcio@linaro.org Signed-off-by: Johan Hovold johan+linaro@kernel.org Link: https://lore.kernel.org/r/20230306075651.2449-11-johan+linaro@kernel.org Signed-off-by: Georgi Djakov djakov@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/interconnect/qcom/icc-rpmh.c | 25 +++++++++++++++---------- 1 file changed, 15 insertions(+), 10 deletions(-)

--- a/drivers/interconnect/qcom/icc-rpmh.c +++ b/drivers/interconnect/qcom/icc-rpmh.c @@ -192,9 +192,10 @@ int qcom_icc_rpmh_probe(struct platform_ provider->pre_aggregate = qcom_icc_pre_aggregate; provider->aggregate = qcom_icc_aggregate; provider->xlate_extended = qcom_icc_xlate_extended; - INIT_LIST_HEAD(&provider->nodes); provider->data = data;

+ icc_provider_init(provider); + qp->dev = dev; qp->bcms = desc->bcms; qp->num_bcms = desc->num_bcms; @@ -203,10 +204,6 @@ int qcom_icc_rpmh_probe(struct platform_ if (IS_ERR(qp->voter)) return PTR_ERR(qp->voter);

- ret = icc_provider_add(provider); - if (ret) - return ret; - for (i = 0; i < qp->num_bcms; i++) qcom_icc_bcm_init(qp->bcms[i], dev);

@@ -218,7 +215,7 @@ int qcom_icc_rpmh_probe(struct platform_ node = icc_node_create(qn->id); if (IS_ERR(node)) { ret = PTR_ERR(node); - goto err; + goto err_remove_nodes; }

node->name = qn->name; @@ -232,19 +229,27 @@ int qcom_icc_rpmh_probe(struct platform_ }

data->num_nodes = num_nodes; + + ret = icc_provider_register(provider); + if (ret) + goto err_remove_nodes; + platform_set_drvdata(pdev, qp);

/* Populate child NoC devices if any */ if (of_get_child_count(dev->of_node) > 0) { ret = of_platform_populate(dev->of_node, NULL, NULL, dev); if (ret) - goto err; + goto err_deregister_provider; }

return 0; -err: + +err_deregister_provider: + icc_provider_deregister(provider); +err_remove_nodes: icc_nodes_remove(provider); - icc_provider_del(provider); + return ret; } EXPORT_SYMBOL_GPL(qcom_icc_rpmh_probe); @@ -253,8 +258,8 @@ int qcom_icc_rpmh_remove(struct platform { struct qcom_icc_provider *qp = platform_get_drvdata(pdev);

+ icc_provider_deregister(&qp->provider); icc_nodes_remove(&qp->provider); - icc_provider_del(&qp->provider);

return 0; }

From: Johan Hovold johan+linaro@kernel.org

commit 3aab264875bf3c915ea2517fae1eec213e0b4987 upstream.

Make sure to add the newly allocated interconnect node to the provider before adding the PM QoS request so that the node is freed on errors.

Fixes: 2f95b9d5cf0b ("interconnect: Add generic interconnect driver for Exynos SoCs") Cc: stable@vger.kernel.org # 5.11 Cc: Sylwester Nawrocki s.nawrocki@samsung.com Reviewed-by: Krzysztof Kozlowski krzysztof.kozlowski@linaro.org Signed-off-by: Johan Hovold johan+linaro@kernel.org Link: https://lore.kernel.org/r/20230306075651.2449-15-johan+linaro@kernel.org Signed-off-by: Georgi Djakov djakov@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/interconnect/samsung/exynos.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

--- a/drivers/interconnect/samsung/exynos.c +++ b/drivers/interconnect/samsung/exynos.c @@ -149,6 +149,9 @@ static int exynos_generic_icc_probe(stru &priv->bus_clk_ratio)) priv->bus_clk_ratio = EXYNOS_ICC_DEFAULT_BUS_CLK_RATIO;

+ icc_node->data = priv; + icc_node_add(icc_node, provider); + /* * Register a PM QoS request for the parent (devfreq) device. */ @@ -157,9 +160,6 @@ static int exynos_generic_icc_probe(stru if (ret < 0) goto err_node_del;

- icc_node->data = priv; - icc_node_add(icc_node, provider); - icc_parent_node = exynos_icc_get_parent(bus_dev->of_node); if (IS_ERR(icc_parent_node)) { ret = PTR_ERR(icc_parent_node);

From: NeilBrown neilb@suse.de

commit 6c0f5898836c05c6d850a750ed7940ba29e4e6c5 upstream.

When BLOCK_LEGACY_AUTOLOAD is not enable, mdadm is not able to activate new arrays unless "CREATE names=yes" appears in mdadm.conf

As this is a regression we need to always enable BLOCK_LEGACY_AUTOLOAD for when MD is selected - at least until mdadm is updated and the updates widely available.

Cc: stable@vger.kernel.org # v5.18+ Fixes: fbdee71bb5d8 ("block: deprecate autoloading based on dev_t") Signed-off-by: NeilBrown neilb@suse.de Signed-off-by: Song Liu song@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/md/Kconfig | 4 ++++ 1 file changed, 4 insertions(+)

--- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -16,6 +16,10 @@ if MD config BLK_DEV_MD tristate "RAID support" select BLOCK_HOLDER_DEPRECATED if SYSFS + # BLOCK_LEGACY_AUTOLOAD requirement should be removed + # after relevant mdadm enhancements - to make "names=yes" + # the default - are widely available. + select BLOCK_LEGACY_AUTOLOAD help This driver lets you combine several hard disk partitions into one logical block device. This can be used to simply append one

From: Sung-hun Kim sfoon.kim@samsung.com

commit e400be674a1a40e9dcb2e95f84d6c1fd2d88f31d upstream.

Since the commit 36e2c7421f02 ("fs: don't allow splice read/write without explicit ops") is applied to the kernel, splice() and sendfile() calls on the trace file (/sys/kernel/debug/tracing /trace) return EINVAL.

This patch restores these system calls by initializing splice_read in file_operations of the trace file. This patch only enables such functionalities for the read case.

Link: https://lore.kernel.org/linux-trace-kernel/20230314013707.28814-1-sfoon.kim@...

Cc: stable@vger.kernel.org Fixes: 36e2c7421f02 ("fs: don't allow splice read/write without explicit ops") Signed-off-by: Sung-hun Kim sfoon.kim@samsung.com Signed-off-by: Steven Rostedt (Google) rostedt@goodmis.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/trace/trace.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -5119,6 +5119,8 @@ loff_t tracing_lseek(struct file *file, static const struct file_operations tracing_fops = { .open = tracing_open, .read = seq_read, + .read_iter = seq_read_iter, + .splice_read = generic_file_splice_read, .write = tracing_write_stub, .llseek = tracing_lseek, .release = tracing_release,

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

commit 9f116f76fa8c04c81aef33ad870dbf9a158e5b70 upstream.

The function hist_field_name() cannot handle being passed a NULL field parameter. It should never be NULL, but due to a previous bug, NULL was passed to the function and the kernel crashed due to a NULL dereference. Mark Rutland reported this to me on IRC.

The bug was fixed, but to prevent future bugs from crashing the kernel, check the field and add a WARN_ON() if it is NULL.

Link: https://lkml.kernel.org/r/20230302020810.762384440@goodmis.org

Cc: stable@vger.kernel.org Cc: Masami Hiramatsu mhiramat@kernel.org Cc: Andrew Morton akpm@linux-foundation.org Reported-by: Mark Rutland mark.rutland@arm.com Fixes: c6afad49d127f ("tracing: Add hist trigger 'sym' and 'sym-offset' modifiers") Tested-by: Mark Rutland mark.rutland@arm.com Signed-off-by: Steven Rostedt (Google) rostedt@goodmis.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/trace/trace_events_hist.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -1334,6 +1334,9 @@ static const char *hist_field_name(struc { const char *field_name = "";

+ if (WARN_ON_ONCE(!field)) + return field_name; + if (level > 1) return field_name;

From: Volker Lendecke vl@samba.org

commit 211baef0eabf4169ce4f73ebd917749d1a7edd74 upstream.

If cifs_get_writable_path() finds a writable file, smb2_compound_op() must use that file's FID and not the COMPOUND_FID.

Cc: stable@vger.kernel.org Signed-off-by: Volker Lendecke vl@samba.org Reviewed-by: Paulo Alcantara (SUSE) pc@manguebit.com Signed-off-by: Steve French stfrench@microsoft.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/cifs/smb2inode.c | 31 ++++++++++++++++++++++++------- 1 file changed, 24 insertions(+), 7 deletions(-)

--- a/fs/cifs/smb2inode.c +++ b/fs/cifs/smb2inode.c @@ -234,15 +234,32 @@ static int smb2_compound_op(const unsign size[0] = 8; /* sizeof __le64 */ data[0] = ptr;

- rc = SMB2_set_info_init(tcon, server, - &rqst[num_rqst], COMPOUND_FID, - COMPOUND_FID, current->tgid, - FILE_END_OF_FILE_INFORMATION, - SMB2_O_INFO_FILE, 0, data, size); + if (cfile) { + rc = SMB2_set_info_init(tcon, server, + &rqst[num_rqst], + cfile->fid.persistent_fid, + cfile->fid.volatile_fid, + current->tgid, + FILE_END_OF_FILE_INFORMATION, + SMB2_O_INFO_FILE, 0, + data, size); + } else { + rc = SMB2_set_info_init(tcon, server, + &rqst[num_rqst], + COMPOUND_FID, + COMPOUND_FID, + current->tgid, + FILE_END_OF_FILE_INFORMATION, + SMB2_O_INFO_FILE, 0, + data, size); + if (!rc) { + smb2_set_next_command(tcon, &rqst[num_rqst]); + smb2_set_related(&rqst[num_rqst]); + } + } if (rc) goto finished; - smb2_set_next_command(tcon, &rqst[num_rqst]); - smb2_set_related(&rqst[num_rqst++]); + num_rqst++; trace_smb3_set_eof_enter(xid, ses->Suid, tcon->tid, full_path); break; case SMB2_OP_SET_INFO:

From: Paulo Alcantara pc@manguebit.com

commit 396935de145589c8bfe552fa03a5e38604071829 upstream.

The UAF bug occurred because we were putting DFS root sessions in cifs_umount() while DFS cache refresher was being executed.

Make DFS root sessions have same lifetime as DFS tcons so we can avoid the use-after-free bug is DFS cache refresher and other places that require IPCs to get new DFS referrals on. Also, get rid of mount group handling in DFS cache as we no longer need it.

This fixes below use-after-free bug catched by KASAN

[ 379.946955] BUG: KASAN: use-after-free in __refresh_tcon.isra.0+0x10b/0xc10 [cifs] [ 379.947642] Read of size 8 at addr ffff888018f57030 by task kworker/u4:3/56 [ 379.948096] [ 379.948208] CPU: 0 PID: 56 Comm: kworker/u4:3 Not tainted 6.2.0-rc7-lku #23 [ 379.948661] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.0-0-gd239552-rebuilt.opensuse.org 04/01/2014 [ 379.949368] Workqueue: cifs-dfscache refresh_cache_worker [cifs] [ 379.949942] Call Trace: [ 379.950113] <TASK> [ 379.950260] dump_stack_lvl+0x50/0x67 [ 379.950510] print_report+0x16a/0x48e [ 379.950759] ? __virt_addr_valid+0xd8/0x160 [ 379.951040] ? __phys_addr+0x41/0x80 [ 379.951285] kasan_report+0xdb/0x110 [ 379.951533] ? __refresh_tcon.isra.0+0x10b/0xc10 [cifs] [ 379.952056] ? __refresh_tcon.isra.0+0x10b/0xc10 [cifs] [ 379.952585] __refresh_tcon.isra.0+0x10b/0xc10 [cifs] [ 379.953096] ? __pfx___refresh_tcon.isra.0+0x10/0x10 [cifs] [ 379.953637] ? __pfx___mutex_lock+0x10/0x10 [ 379.953915] ? lock_release+0xb6/0x720 [ 379.954167] ? __pfx_lock_acquire+0x10/0x10 [ 379.954443] ? refresh_cache_worker+0x34e/0x6d0 [cifs] [ 379.954960] ? __pfx_wb_workfn+0x10/0x10 [ 379.955239] refresh_cache_worker+0x4ad/0x6d0 [cifs] [ 379.955755] ? __pfx_refresh_cache_worker+0x10/0x10 [cifs] [ 379.956323] ? __pfx_lock_acquired+0x10/0x10 [ 379.956615] ? read_word_at_a_time+0xe/0x20 [ 379.956898] ? lockdep_hardirqs_on_prepare+0x12/0x220 [ 379.957235] process_one_work+0x535/0x990 [ 379.957509] ? __pfx_process_one_work+0x10/0x10 [ 379.957812] ? lock_acquired+0xb7/0x5f0 [ 379.958069] ? __list_add_valid+0x37/0xd0 [ 379.958341] ? __list_add_valid+0x37/0xd0 [ 379.958611] worker_thread+0x8e/0x630 [ 379.958861] ? __pfx_worker_thread+0x10/0x10 [ 379.959148] kthread+0x17d/0x1b0 [ 379.959369] ? __pfx_kthread+0x10/0x10 [ 379.959630] ret_from_fork+0x2c/0x50 [ 379.959879] </TASK>

Signed-off-by: Paulo Alcantara (SUSE) pc@manguebit.com Cc: stable@vger.kernel.org # 6.2 Signed-off-by: Steve French stfrench@microsoft.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/cifs/cifs_fs_sb.h | 2 fs/cifs/cifsglob.h | 3 - fs/cifs/connect.c | 9 +-- fs/cifs/dfs.c | 52 ++++++++++++++---- fs/cifs/dfs.h | 16 +++++ fs/cifs/dfs_cache.c | 140 --------------------------------------------------- fs/cifs/dfs_cache.h | 2 fs/cifs/misc.c | 7 ++ 8 files changed, 67 insertions(+), 164 deletions(-)

--- a/fs/cifs/cifs_fs_sb.h +++ b/fs/cifs/cifs_fs_sb.h @@ -61,8 +61,6 @@ struct cifs_sb_info { /* only used when CIFS_MOUNT_USE_PREFIX_PATH is set */ char *prepath;

- /* randomly generated 128-bit number for indexing dfs mount groups in referral cache */ - uuid_t dfs_mount_id; /* * Indicate whether serverino option was turned off later * (cifs_autodisable_serverino) in order to match new mounts. --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -1239,6 +1239,7 @@ struct cifs_tcon { /* BB add field for back pointer to sb struct(s)? */ #ifdef CONFIG_CIFS_DFS_UPCALL struct list_head ulist; /* cache update list */ + struct list_head dfs_ses_list; #endif struct delayed_work query_interfaces; /* query interfaces workqueue job */ }; @@ -1767,8 +1768,8 @@ struct cifs_mount_ctx { struct TCP_Server_Info *server; struct cifs_ses *ses; struct cifs_tcon *tcon; - uuid_t mount_id; char *origin_fullpath, *leaf_fullpath; + struct list_head dfs_ses_list; };

static inline void free_dfs_info_param(struct dfs_info3_param *param) --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -3457,7 +3457,8 @@ int cifs_mount(struct cifs_sb_info *cifs bool isdfs; int rc;

- uuid_gen(&mnt_ctx.mount_id); + INIT_LIST_HEAD(&mnt_ctx.dfs_ses_list); + rc = dfs_mount_share(&mnt_ctx, &isdfs); if (rc) goto error; @@ -3477,7 +3478,6 @@ int cifs_mount(struct cifs_sb_info *cifs kfree(cifs_sb->prepath); cifs_sb->prepath = ctx->prepath; ctx->prepath = NULL; - uuid_copy(&cifs_sb->dfs_mount_id, &mnt_ctx.mount_id);

out: cifs_try_adding_channels(cifs_sb, mnt_ctx.ses); @@ -3489,7 +3489,7 @@ out: return rc;

error: - dfs_cache_put_refsrv_sessions(&mnt_ctx.mount_id); + dfs_put_root_smb_sessions(&mnt_ctx.dfs_ses_list); kfree(mnt_ctx.origin_fullpath); kfree(mnt_ctx.leaf_fullpath); cifs_mount_put_conns(&mnt_ctx); @@ -3687,9 +3687,6 @@ cifs_umount(struct cifs_sb_info *cifs_sb spin_unlock(&cifs_sb->tlink_tree_lock);

kfree(cifs_sb->prepath); -#ifdef CONFIG_CIFS_DFS_UPCALL - dfs_cache_put_refsrv_sessions(&cifs_sb->dfs_mount_id); -#endif call_rcu(&cifs_sb->rcu, delayed_free); }

--- a/fs/cifs/dfs.c +++ b/fs/cifs/dfs.c @@ -99,18 +99,27 @@ static int get_session(struct cifs_mount return rc; }

-static void set_root_ses(struct cifs_mount_ctx *mnt_ctx) +static int get_root_smb_session(struct cifs_mount_ctx *mnt_ctx) { struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; + struct dfs_root_ses *root_ses; struct cifs_ses *ses = mnt_ctx->ses;

if (ses) { + root_ses = kmalloc(sizeof(*root_ses), GFP_KERNEL); + if (!root_ses) + return -ENOMEM; + + INIT_LIST_HEAD(&root_ses->list); + spin_lock(&cifs_tcp_ses_lock); ses->ses_count++; spin_unlock(&cifs_tcp_ses_lock); - dfs_cache_add_refsrv_session(&mnt_ctx->mount_id, ses); + root_ses->ses = ses; + list_add_tail(&root_ses->list, &mnt_ctx->dfs_ses_list); } - ctx->dfs_root_ses = mnt_ctx->ses; + ctx->dfs_root_ses = ses; + return 0; }

static int get_dfs_conn(struct cifs_mount_ctx *mnt_ctx, const char *ref_path, const char *full_path, @@ -118,7 +127,8 @@ static int get_dfs_conn(struct cifs_moun { struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; struct dfs_info3_param ref = {}; - int rc; + bool is_refsrv = false; + int rc, rc2;

rc = dfs_cache_get_tgt_referral(ref_path + 1, tit, &ref); if (rc) @@ -133,8 +143,7 @@ static int get_dfs_conn(struct cifs_moun if (rc) goto out;

- if (ref.flags & DFSREF_REFERRAL_SERVER) - set_root_ses(mnt_ctx); + is_refsrv = !!(ref.flags & DFSREF_REFERRAL_SERVER);

rc = -EREMOTE; if (ref.flags & DFSREF_STORAGE_SERVER) { @@ -143,13 +152,17 @@ static int get_dfs_conn(struct cifs_moun goto out;

/* some servers may not advertise referral capability under ref.flags */ - if (!(ref.flags & DFSREF_REFERRAL_SERVER) && - is_tcon_dfs(mnt_ctx->tcon)) - set_root_ses(mnt_ctx); + is_refsrv |= is_tcon_dfs(mnt_ctx->tcon);

rc = cifs_is_path_remote(mnt_ctx); }

+ if (rc == -EREMOTE && is_refsrv) { + rc2 = get_root_smb_session(mnt_ctx); + if (rc2) + rc = rc2; + } + out: free_dfs_info_param(&ref); return rc; @@ -162,6 +175,7 @@ static int __dfs_mount_share(struct cifs char *ref_path = NULL, *full_path = NULL; struct dfs_cache_tgt_iterator *tit; struct TCP_Server_Info *server; + struct cifs_tcon *tcon; char *origin_fullpath = NULL; int num_links = 0; int rc; @@ -231,12 +245,22 @@ static int __dfs_mount_share(struct cifs

if (!rc) { server = mnt_ctx->server; + tcon = mnt_ctx->tcon;

mutex_lock(&server->refpath_lock); - server->origin_fullpath = origin_fullpath; - server->current_fullpath = server->leaf_fullpath; + if (!server->origin_fullpath) { + server->origin_fullpath = origin_fullpath; + server->current_fullpath = server->leaf_fullpath; + origin_fullpath = NULL; + } mutex_unlock(&server->refpath_lock); - origin_fullpath = NULL; + + if (list_empty(&tcon->dfs_ses_list)) { + list_replace_init(&mnt_ctx->dfs_ses_list, + &tcon->dfs_ses_list); + } else { + dfs_put_root_smb_sessions(&mnt_ctx->dfs_ses_list); + } }

out: @@ -277,7 +301,9 @@ int dfs_mount_share(struct cifs_mount_ct }

*isdfs = true; - set_root_ses(mnt_ctx); + rc = get_root_smb_session(mnt_ctx); + if (rc) + return rc;

return __dfs_mount_share(mnt_ctx); } --- a/fs/cifs/dfs.h +++ b/fs/cifs/dfs.h @@ -10,6 +10,11 @@ #include "fs_context.h" #include "cifs_unicode.h"

+struct dfs_root_ses { + struct list_head list; + struct cifs_ses *ses; +}; + int dfs_parse_target_referral(const char *full_path, const struct dfs_info3_param *ref, struct smb3_fs_context *ctx); int dfs_mount_share(struct cifs_mount_ctx *mnt_ctx, bool *isdfs); @@ -44,4 +49,15 @@ static inline char *dfs_get_automount_de true); }

+static inline void dfs_put_root_smb_sessions(struct list_head *head) +{ + struct dfs_root_ses *root, *tmp; + + list_for_each_entry_safe(root, tmp, head, list) { + list_del_init(&root->list); + cifs_put_smb_ses(root->ses); + kfree(root); + } +} + #endif /* _CIFS_DFS_H */ --- a/fs/cifs/dfs_cache.c +++ b/fs/cifs/dfs_cache.c @@ -49,17 +49,6 @@ struct cache_entry { struct cache_dfs_tgt *tgthint; };

-/* List of referral server sessions per dfs mount */ -struct mount_group { - struct list_head list; - uuid_t id; - struct cifs_ses *sessions[CACHE_MAX_ENTRIES]; - int num_sessions; - spinlock_t lock; - struct list_head refresh_list; - struct kref refcount; -}; - static struct kmem_cache *cache_slab __read_mostly; static struct workqueue_struct *dfscache_wq __read_mostly;

@@ -76,85 +65,10 @@ static atomic_t cache_count; static struct hlist_head cache_htable[CACHE_HTABLE_SIZE]; static DECLARE_RWSEM(htable_rw_lock);

-static LIST_HEAD(mount_group_list); -static DEFINE_MUTEX(mount_group_list_lock); - static void refresh_cache_worker(struct work_struct *work);

static DECLARE_DELAYED_WORK(refresh_task, refresh_cache_worker);

-static void __mount_group_release(struct mount_group *mg) -{ - int i; - - for (i = 0; i < mg->num_sessions; i++) - cifs_put_smb_ses(mg->sessions[i]); - kfree(mg); -} - -static void mount_group_release(struct kref *kref) -{ - struct mount_group *mg = container_of(kref, struct mount_group, refcount); - - mutex_lock(&mount_group_list_lock); - list_del(&mg->list); - mutex_unlock(&mount_group_list_lock); - __mount_group_release(mg); -} - -static struct mount_group *find_mount_group_locked(const uuid_t *id) -{ - struct mount_group *mg; - - list_for_each_entry(mg, &mount_group_list, list) { - if (uuid_equal(&mg->id, id)) - return mg; - } - return ERR_PTR(-ENOENT); -} - -static struct mount_group *__get_mount_group_locked(const uuid_t *id) -{ - struct mount_group *mg; - - mg = find_mount_group_locked(id); - if (!IS_ERR(mg)) - return mg; - - mg = kmalloc(sizeof(*mg), GFP_KERNEL); - if (!mg) - return ERR_PTR(-ENOMEM); - kref_init(&mg->refcount); - uuid_copy(&mg->id, id); - mg->num_sessions = 0; - spin_lock_init(&mg->lock); - list_add(&mg->list, &mount_group_list); - return mg; -} - -static struct mount_group *get_mount_group(const uuid_t *id) -{ - struct mount_group *mg; - - mutex_lock(&mount_group_list_lock); - mg = __get_mount_group_locked(id); - if (!IS_ERR(mg)) - kref_get(&mg->refcount); - mutex_unlock(&mount_group_list_lock); - - return mg; -} - -static void free_mount_group_list(void) -{ - struct mount_group *mg, *tmp_mg; - - list_for_each_entry_safe(mg, tmp_mg, &mount_group_list, list) { - list_del_init(&mg->list); - __mount_group_release(mg); - } -} - /** * dfs_cache_canonical_path - get a canonical DFS path * @@ -704,7 +618,6 @@ void dfs_cache_destroy(void) { cancel_delayed_work_sync(&refresh_task); unload_nls(cache_cp); - free_mount_group_list(); flush_cache_ents(); kmem_cache_destroy(cache_slab); destroy_workqueue(dfscache_wq); @@ -1111,54 +1024,6 @@ out_unlock: return rc; }

-/** - * dfs_cache_add_refsrv_session - add SMB session of referral server - * - * @mount_id: mount group uuid to lookup. - * @ses: reference counted SMB session of referral server. - */ -void dfs_cache_add_refsrv_session(const uuid_t *mount_id, struct cifs_ses *ses) -{ - struct mount_group *mg; - - if (WARN_ON_ONCE(!mount_id || uuid_is_null(mount_id) || !ses)) - return; - - mg = get_mount_group(mount_id); - if (WARN_ON_ONCE(IS_ERR(mg))) - return; - - spin_lock(&mg->lock); - if (mg->num_sessions < ARRAY_SIZE(mg->sessions)) - mg->sessions[mg->num_sessions++] = ses; - spin_unlock(&mg->lock); - kref_put(&mg->refcount, mount_group_release); -} - -/** - * dfs_cache_put_refsrv_sessions - put all referral server sessions - * - * Put all SMB sessions from the given mount group id. - * - * @mount_id: mount group uuid to lookup. - */ -void dfs_cache_put_refsrv_sessions(const uuid_t *mount_id) -{ - struct mount_group *mg; - - if (!mount_id || uuid_is_null(mount_id)) - return; - - mutex_lock(&mount_group_list_lock); - mg = find_mount_group_locked(mount_id); - if (IS_ERR(mg)) { - mutex_unlock(&mount_group_list_lock); - return; - } - mutex_unlock(&mount_group_list_lock); - kref_put(&mg->refcount, mount_group_release); -} - /* Extract share from DFS target and return a pointer to prefix path or NULL */ static const char *parse_target_share(const char *target, char **share) { @@ -1384,11 +1249,6 @@ int dfs_cache_remount_fs(struct cifs_sb_ cifs_dbg(FYI, "%s: not a dfs mount\n", __func__); return 0; } - - if (uuid_is_null(&cifs_sb->dfs_mount_id)) { - cifs_dbg(FYI, "%s: no dfs mount group id\n", __func__); - return -EINVAL; - } /* * After reconnecting to a different server, unique ids won't match anymore, so we disable * serverino. This prevents dentry revalidation to think the dentry are stale (ESTALE). --- a/fs/cifs/dfs_cache.h +++ b/fs/cifs/dfs_cache.h @@ -40,8 +40,6 @@ int dfs_cache_get_tgt_referral(const cha struct dfs_info3_param *ref); int dfs_cache_get_tgt_share(char *path, const struct dfs_cache_tgt_iterator *it, char **share, char **prefix); -void dfs_cache_put_refsrv_sessions(const uuid_t *mount_id); -void dfs_cache_add_refsrv_session(const uuid_t *mount_id, struct cifs_ses *ses); char *dfs_cache_canonical_path(const char *path, const struct nls_table *cp, int remap); int dfs_cache_remount_fs(struct cifs_sb_info *cifs_sb);

--- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -22,6 +22,7 @@ #ifdef CONFIG_CIFS_DFS_UPCALL #include "dns_resolve.h" #include "dfs_cache.h" +#include "dfs.h" #endif #include "fs_context.h" #include "cached_dir.h" @@ -134,6 +135,9 @@ tconInfoAlloc(void) spin_lock_init(&ret_buf->stat_lock); atomic_set(&ret_buf->num_local_opens, 0); atomic_set(&ret_buf->num_remote_opens, 0); +#ifdef CONFIG_CIFS_DFS_UPCALL + INIT_LIST_HEAD(&ret_buf->dfs_ses_list); +#endif

return ret_buf; } @@ -149,6 +153,9 @@ tconInfoFree(struct cifs_tcon *tcon) atomic_dec(&tconInfoAllocCount); kfree(tcon->nativeFileSystem); kfree_sensitive(tcon->password); +#ifdef CONFIG_CIFS_DFS_UPCALL + dfs_put_root_smb_sessions(&tcon->dfs_ses_list); +#endif kfree(tcon); }

From: Paulo Alcantara pc@manguebit.com

commit 6284e46bdd47743a064fe6ac834a7ac05b1fd206 upstream.

Use DFS root session whenever possible to get new DFS referrals otherwise we might end up with an IPC tcon (tcon->ses->tcon_ipc) that doesn't respond to them. It should be safe accessing @ses->dfs_root_ses directly in cifs_inval_name_dfs_link_error() as it has same lifetime as of @tcon.

Signed-off-by: Paulo Alcantara (SUSE) pc@manguebit.com Cc: stable@vger.kernel.org # 6.2 Signed-off-by: Steve French stfrench@microsoft.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/cifs/misc.c | 1 + 1 file changed, 1 insertion(+)

--- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -1364,6 +1364,7 @@ int cifs_inval_name_dfs_link_error(const * removing cached DFS targets that the client would eventually * need during failover. */ + ses = CIFS_DFS_ROOT_SES(ses); if (ses->server->ops->get_dfs_refer && !ses->server->ops->get_dfs_refer(xid, ses, ref_path, &refs, &num_refs, cifs_sb->local_nls,

From: Suravee Suthikulpanit suravee.suthikulpanit@amd.com

commit 5999715922c5a3ede5d8fe2a6b17aba58a157d41 upstream.

Define AVIC_VCPU_ID_MASK based on AVIC_PHYSICAL_MAX_INDEX, i.e. the mask that effectively controls the largest guest physical APIC ID supported by x2AVIC, instead of hardcoding the number of bits to 8 (and the number of VM bits to 24).

The AVIC GATag is programmed into the AMD IOMMU IRTE to provide a reference back to KVM in case the IOMMU cannot inject an interrupt into a non-running vCPU. In such a case, the IOMMU notifies software by creating a GALog entry with the corresponded GATag, and KVM then uses the GATag to find the correct VM+vCPU to kick. Dropping bit 8 from the GATag results in kicking the wrong vCPU when targeting vCPUs with x2APIC ID > 255.

Fixes: 4d1d7942e36a ("KVM: SVM: Introduce logic to (de)activate x2AVIC mode") Cc: stable@vger.kernel.org Reported-by: Alejandro Jimenez alejandro.j.jimenez@oracle.com Signed-off-by: Suravee Suthikulpanit suravee.suthikulpanit@amd.com Co-developed-by: Sean Christopherson seanjc@google.com Signed-off-by: Sean Christopherson seanjc@google.com Reviewed-by: Suravee Suthikulpanit suravee.suthikulpanit@amd.com Tested-by: Suravee Suthikulpanit suravee.suthikulpanit@amd.com Message-Id: 20230207002156.521736-3-seanjc@google.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kvm/svm/avic.c | 26 ++++++++++++++++++-------- 1 file changed, 18 insertions(+), 8 deletions(-)

--- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -27,19 +27,29 @@ #include "irq.h" #include "svm.h"

-/* AVIC GATAG is encoded using VM and VCPU IDs */ -#define AVIC_VCPU_ID_BITS 8 -#define AVIC_VCPU_ID_MASK ((1 << AVIC_VCPU_ID_BITS) - 1) +/* + * Encode the arbitrary VM ID and the vCPU's default APIC ID, i.e the vCPU ID, + * into the GATag so that KVM can retrieve the correct vCPU from a GALog entry + * if an interrupt can't be delivered, e.g. because the vCPU isn't running. + * + * For the vCPU ID, use however many bits are currently allowed for the max + * guest physical APIC ID (limited by the size of the physical ID table), and + * use whatever bits remain to assign arbitrary AVIC IDs to VMs. Note, the + * size of the GATag is defined by hardware (32 bits), but is an opaque value + * as far as hardware is concerned. + */ +#define AVIC_VCPU_ID_MASK AVIC_PHYSICAL_MAX_INDEX_MASK

-#define AVIC_VM_ID_BITS 24 -#define AVIC_VM_ID_NR (1 << AVIC_VM_ID_BITS) -#define AVIC_VM_ID_MASK ((1 << AVIC_VM_ID_BITS) - 1) +#define AVIC_VM_ID_SHIFT HWEIGHT32(AVIC_PHYSICAL_MAX_INDEX_MASK) +#define AVIC_VM_ID_MASK (GENMASK(31, AVIC_VM_ID_SHIFT) >> AVIC_VM_ID_SHIFT)

-#define AVIC_GATAG(x, y) (((x & AVIC_VM_ID_MASK) << AVIC_VCPU_ID_BITS) | \ +#define AVIC_GATAG(x, y) (((x & AVIC_VM_ID_MASK) << AVIC_VM_ID_SHIFT) | \ (y & AVIC_VCPU_ID_MASK)) -#define AVIC_GATAG_TO_VMID(x) ((x >> AVIC_VCPU_ID_BITS) & AVIC_VM_ID_MASK) +#define AVIC_GATAG_TO_VMID(x) ((x >> AVIC_VM_ID_SHIFT) & AVIC_VM_ID_MASK) #define AVIC_GATAG_TO_VCPUID(x) (x & AVIC_VCPU_ID_MASK)

+static_assert(AVIC_GATAG(AVIC_VM_ID_MASK, AVIC_VCPU_ID_MASK) == -1u); + static bool force_avic; module_param_unsafe(force_avic, bool, 0444);

From: Bard Liao yung-chuan.liao@linux.intel.com

commit bbdf904b13a62bb8b1272d92a7dde082dff86fbb upstream.

Use SOF as default audio driver.

Signed-off-by: Bard Liao yung-chuan.liao@linux.intel.com Reviewed-by: Gongjun Song gongjun.song@intel.com Reviewed-by: Kai Vehmanen kai.vehmanen@linux.intel.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230306074101.3906707-1-yung-chuan.liao@linux.int... Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/hda/intel-dsp-config.c | 9 +++++++++ 1 file changed, 9 insertions(+)

--- a/sound/hda/intel-dsp-config.c +++ b/sound/hda/intel-dsp-config.c @@ -472,6 +472,15 @@ static const struct config_entry config_ }, #endif

+/* Meteor Lake */ +#if IS_ENABLED(CONFIG_SND_SOC_SOF_METEORLAKE) + /* Meteorlake-P */ + { + .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, + .device = 0x7e28, + }, +#endif + };

static const struct config_entry *snd_intel_dsp_find_config

From: Jeremy Szu jeremy.szu@canonical.com

commit 7bb62340951a9af20235a3bde8c98e2e292915df upstream.

There is a HP platform needs ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED quirk to make mic-mute/audio-mute/speaker working.

Signed-off-by: Jeremy Szu jeremy.szu@canonical.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230307135317.37621-1-jeremy.szu@canonical.com Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+)

--- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9446,6 +9446,7 @@ static const struct snd_pci_quirk alc269 SND_PCI_QUIRK(0x103c, 0x8b8a, "HP", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b8b, "HP", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b8d, "HP", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8b8f, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b92, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8bf0, "HP", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC),

From: Guo Ren guoren@linux.alibaba.com

commit 82dd33fde0268cc622d3d1ac64971f3f61634142 upstream.

After use_asid_allocator is enabled, the userspace application will crash by stale TLB entries. Because only using cpumask_clear_cpu without local_flush_tlb_all couldn't guarantee CPU's TLB entries were fresh. Then set_mm_asid would cause the user space application to get a stale value by stale TLB entry, but set_mm_noasid is okay.

Here is the symptom of the bug: unhandled signal 11 code 0x1 (coredump) 0x0000003fd6d22524 <+4>: auipc s0,0x70 0x0000003fd6d22528 <+8>: ld s0,-148(s0) # 0x3fd6d92490 => 0x0000003fd6d2252c <+12>: ld a5,0(s0) (gdb) i r s0 s0 0x8082ed1cc3198b21 0x8082ed1cc3198b21 (gdb) x /2x 0x3fd6d92490 0x3fd6d92490: 0xd80ac8a8 0x0000003f The core dump file shows that register s0 is wrong, but the value in memory is correct. Because 'ld s0, -148(s0)' used a stale mapping entry in TLB and got a wrong result from an incorrect physical address.

When the task ran on CPU0, which loaded/speculative-loaded the value of address(0x3fd6d92490), then the first version of the mapping entry was PTWed into CPU0's TLB. When the task switched from CPU0 to CPU1 (No local_tlb_flush_all here by asid), it happened to write a value on the address (0x3fd6d92490). It caused do_page_fault -> wp_page_copy -> ptep_clear_flush -> ptep_get_and_clear & flush_tlb_page. The flush_tlb_page used mm_cpumask(mm) to determine which CPUs need TLB flush, but CPU0 had cleared the CPU0's mm_cpumask in the previous switch_mm. So we only flushed the CPU1 TLB and set the second version mapping of the PTE. When the task switched from CPU1 to CPU0 again, CPU0 still used a stale TLB mapping entry which contained a wrong target physical address. It raised a bug when the task happened to read that value.

CPU0 CPU1 - switch 'task' in - read addr (Fill stale mapping entry into TLB) - switch 'task' out (no tlb_flush) - switch 'task' in (no tlb_flush) - write addr cause pagefault do_page_fault() (change to new addr mapping) wp_page_copy() ptep_clear_flush() ptep_get_and_clear() & flush_tlb_page() write new value into addr - switch 'task' out (no tlb_flush) - switch 'task' in (no tlb_flush) - read addr again (Use stale mapping entry in TLB) get wrong value from old phyical addr, BUG!

The solution is to keep all CPUs' footmarks of cpumask(mm) in switch_mm, which could guarantee to invalidate all stale TLB entries during TLB flush.

Fixes: 65d4b9c53017 ("RISC-V: Implement ASID allocator") Signed-off-by: Guo Ren guoren@linux.alibaba.com Signed-off-by: Guo Ren guoren@kernel.org Tested-by: Lad Prabhakar prabhakar.mahadev-lad.rj@bp.renesas.com Tested-by: Zong Li zong.li@sifive.com Tested-by: Sergey Matyukevich sergey.matyukevich@syntacore.com Cc: Anup Patel apatel@ventanamicro.com Cc: Palmer Dabbelt palmer@rivosinc.com Cc: stable@vger.kernel.org Reviewed-by: Andrew Jones ajones@ventanamicro.com Link: https://lore.kernel.org/r/20230226150137.1919750-3-geomatsi@gmail.com Signed-off-by: Palmer Dabbelt palmer@rivosinc.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/riscv/mm/context.c | 30 ++++++++++++++++++++---------- 1 file changed, 20 insertions(+), 10 deletions(-)

--- a/arch/riscv/mm/context.c +++ b/arch/riscv/mm/context.c @@ -205,12 +205,24 @@ static void set_mm_noasid(struct mm_stru local_flush_tlb_all(); }

-static inline void set_mm(struct mm_struct *mm, unsigned int cpu) +static inline void set_mm(struct mm_struct *prev, + struct mm_struct *next, unsigned int cpu) { - if (static_branch_unlikely(&use_asid_allocator)) - set_mm_asid(mm, cpu); - else - set_mm_noasid(mm); + /* + * The mm_cpumask indicates which harts' TLBs contain the virtual + * address mapping of the mm. Compared to noasid, using asid + * can't guarantee that stale TLB entries are invalidated because + * the asid mechanism wouldn't flush TLB for every switch_mm for + * performance. So when using asid, keep all CPUs footmarks in + * cpumask() until mm reset. + */ + cpumask_set_cpu(cpu, mm_cpumask(next)); + if (static_branch_unlikely(&use_asid_allocator)) { + set_mm_asid(next, cpu); + } else { + cpumask_clear_cpu(cpu, mm_cpumask(prev)); + set_mm_noasid(next); + } }

static int __init asids_init(void) @@ -264,7 +276,8 @@ static int __init asids_init(void) } early_initcall(asids_init); #else -static inline void set_mm(struct mm_struct *mm, unsigned int cpu) +static inline void set_mm(struct mm_struct *prev, + struct mm_struct *next, unsigned int cpu) { /* Nothing to do here when there is no MMU */ } @@ -317,10 +330,7 @@ void switch_mm(struct mm_struct *prev, s */ cpu = smp_processor_id();

- cpumask_clear_cpu(cpu, mm_cpumask(prev)); - cpumask_set_cpu(cpu, mm_cpumask(next)); - - set_mm(next, cpu); + set_mm(prev, next, cpu);

flush_icache_deferred(next, cpu); }

From: Dmitry Osipenko dmitry.osipenko@collabora.com

commit ee9adb7a45516cfa536ca92253d7ae59d56db9e4 upstream.

drm_gem_shmem_mmap() doesn't own reference in error code path, resulting in the dma-buf shmem GEM object getting prematurely freed leading to a later use-after-free.

Fixes: f49a51bfdc8e ("drm/shme-helpers: Fix dma_buf_mmap forwarding bug") Cc: stable@vger.kernel.org Signed-off-by: Dmitry Osipenko dmitry.osipenko@collabora.com Reviewed-by: Rob Clark robdclark@gmail.com Link: https://patchwork.freedesktop.org/patch/msgid/20230108211311.3950107-1-dmitr... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/drm_gem_shmem_helper.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)

--- a/drivers/gpu/drm/drm_gem_shmem_helper.c +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c @@ -622,11 +622,14 @@ int drm_gem_shmem_mmap(struct drm_gem_sh int ret;

if (obj->import_attach) { - /* Drop the reference drm_gem_mmap_obj() acquired.*/ - drm_gem_object_put(obj); vma->vm_private_data = NULL; + ret = dma_buf_mmap(obj->dma_buf, vma, 0); + + /* Drop the reference drm_gem_mmap_obj() acquired.*/ + if (!ret) + drm_gem_object_put(obj);

- return dma_buf_mmap(obj->dma_buf, vma, 0); + return ret; }