From: Alex Deucher alexdeucher@gmail.com

This reverts commit a135a1b4c4db1f3b8cbed9676a40ede39feb3362.

This leads to blank screens on some boards after replugging a display. Revert until we understand the root cause and can fix both the leak and the blank screen after replug.

Cc: Stylon Wang stylon.wang@amd.com Cc: Harry Wentland harry.wentland@amd.com Cc: Nicholas Kazlauskas nicholas.kazlauskas@amd.com Cc: Andre Tomt andre@tomt.net Cc: Oleksandr Natalenko oleksandr@natalenko.name Signed-off-by: Alex Deucher alexander.deucher@amd.com Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2278,8 +2278,7 @@ void amdgpu_dm_update_connector_after_de

drm_connector_update_edid_property(connector, aconnector->edid); - aconnector->num_modes = drm_add_edid_modes(connector, aconnector->edid); - drm_connector_list_update(connector); + drm_add_edid_modes(connector, aconnector->edid);

if (aconnector->dc_link->aux_mode) drm_dp_cec_set_edid(&aconnector->dm_dp_aux.aux,

From: Uwe Kleine-König u.kleine-koenig@pengutronix.de

commit 5d78533a0c53af9659227c803df944ba27cd56e0 upstream.

The obvious advantages are:

- The linker can drop the watchdog functions if CONFIG_WATCHDOG is off. - All watchdog stuff grouped together with only a single function call left in generic code. - Watchdog register is only read when it is actually used. - Less #ifdefery

Signed-off-by: Uwe Kleine-König u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni alexandre.belloni@bootlin.com Link: https://lore.kernel.org/r/20200924105256.18162-2-u.kleine-koenig@pengutronix... Cc: Rasmus Villemoes rasmus.villemoes@prevas.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/rtc/rtc-pcf2127.c | 56 +++++++++++++++++++++++++--------------------- 1 file changed, 31 insertions(+), 25 deletions(-)

--- a/drivers/rtc/rtc-pcf2127.c +++ b/drivers/rtc/rtc-pcf2127.c @@ -331,6 +331,36 @@ static const struct watchdog_ops pcf2127 .set_timeout = pcf2127_wdt_set_timeout, };

+static int pcf2127_watchdog_init(struct device *dev, struct pcf2127 *pcf2127) +{ + u32 wdd_timeout; + int ret; + + if (!IS_ENABLED(CONFIG_WATCHDOG)) + return 0; + + pcf2127->wdd.parent = dev; + pcf2127->wdd.info = &pcf2127_wdt_info; + pcf2127->wdd.ops = &pcf2127_watchdog_ops; + pcf2127->wdd.min_timeout = PCF2127_WD_VAL_MIN; + pcf2127->wdd.max_timeout = PCF2127_WD_VAL_MAX; + pcf2127->wdd.timeout = PCF2127_WD_VAL_DEFAULT; + pcf2127->wdd.min_hw_heartbeat_ms = 500; + pcf2127->wdd.status = WATCHDOG_NOWAYOUT_INIT_STATUS; + + watchdog_set_drvdata(&pcf2127->wdd, pcf2127); + + /* Test if watchdog timer is started by bootloader */ + ret = regmap_read(pcf2127->regmap, PCF2127_REG_WD_VAL, &wdd_timeout); + if (ret) + return ret; + + if (wdd_timeout) + set_bit(WDOG_HW_RUNNING, &pcf2127->wdd.status); + + return devm_watchdog_register_device(dev, &pcf2127->wdd); +} + /* Alarm */ static int pcf2127_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm) { @@ -532,7 +562,6 @@ static int pcf2127_probe(struct device * int alarm_irq, const char *name, bool has_nvmem) { struct pcf2127 *pcf2127; - u32 wdd_timeout; int ret = 0;

dev_dbg(dev, "%s\n", __func__); @@ -571,17 +600,6 @@ static int pcf2127_probe(struct device * pcf2127->rtc->ops = &pcf2127_rtc_alrm_ops; }

- pcf2127->wdd.parent = dev; - pcf2127->wdd.info = &pcf2127_wdt_info; - pcf2127->wdd.ops = &pcf2127_watchdog_ops; - pcf2127->wdd.min_timeout = PCF2127_WD_VAL_MIN; - pcf2127->wdd.max_timeout = PCF2127_WD_VAL_MAX; - pcf2127->wdd.timeout = PCF2127_WD_VAL_DEFAULT; - pcf2127->wdd.min_hw_heartbeat_ms = 500; - pcf2127->wdd.status = WATCHDOG_NOWAYOUT_INIT_STATUS; - - watchdog_set_drvdata(&pcf2127->wdd, pcf2127); - if (has_nvmem) { struct nvmem_config nvmem_cfg = { .priv = pcf2127, @@ -611,19 +629,7 @@ static int pcf2127_probe(struct device * return ret; }

- /* Test if watchdog timer is started by bootloader */ - ret = regmap_read(pcf2127->regmap, PCF2127_REG_WD_VAL, &wdd_timeout); - if (ret) - return ret; - - if (wdd_timeout) - set_bit(WDOG_HW_RUNNING, &pcf2127->wdd.status); - -#ifdef CONFIG_WATCHDOG - ret = devm_watchdog_register_device(dev, &pcf2127->wdd); - if (ret) - return ret; -#endif /* CONFIG_WATCHDOG */ + pcf2127_watchdog_init(dev, pcf2127);

/* * Disable battery low/switch-over timestamp and interrupts.

From: Rasmus Villemoes rasmus.villemoes@prevas.dk

commit 320d159e2d63a97a40f24cd6dfda5a57eec65b91 upstream.

Some RTCs, e.g. the pcf2127, can be used as a hardware watchdog. But if the reset pin is not actually wired up, the driver exposes a watchdog device that doesn't actually work.

Provide a standard binding that can be used to indicate that a given RTC can perform a reset of the machine, similar to wakeup-source.

Suggested-by: Alexandre Belloni alexandre.belloni@bootlin.com Signed-off-by: Rasmus Villemoes rasmus.villemoes@prevas.dk Reviewed-by: Rob Herring robh@kernel.org Signed-off-by: Alexandre Belloni alexandre.belloni@bootlin.com Link: https://lore.kernel.org/r/20201218101054.25416-2-rasmus.villemoes@prevas.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- Documentation/devicetree/bindings/rtc/rtc.yaml | 5 +++++ 1 file changed, 5 insertions(+)

--- a/Documentation/devicetree/bindings/rtc/rtc.yaml +++ b/Documentation/devicetree/bindings/rtc/rtc.yaml @@ -63,6 +63,11 @@ properties: description: Enables wake up of host system on alarm.

+ reset-source: + $ref: /schemas/types.yaml#/definitions/flag + description: + The RTC is able to reset the machine. + additionalProperties: true

...

From: Edward Vear edwardvear@gmail.com

commit a31489d2a368d2f9225ed6a6f595c63bc7d10de8 upstream.

During controller initialization, an LE Set RPA Timeout command is sent to the controller if supported. However, the value checked to determine if the command is supported is incorrect. Page 1921 of the Bluetooth Core Spec v5.2 shows that bit 2 of octet 35 of the Supported_Commands field corresponds to the LE Set RPA Timeout command, but currently bit 6 of octet 35 is checked. This patch checks the correct value instead.

This issue led to the error seen in the following btmon output during initialization of an adapter (rtl8761b) and prevented initialization from completing.

< HCI Command: LE Set Resolvable Private Address Timeout (0x08|0x002e) plen 2 Timeout: 900 seconds

HCI Event: Command Complete (0x0e) plen 4

LE Set Resolvable Private Address Timeout (0x08|0x002e) ncmd 2 Status: Unsupported Remote Feature / Unsupported LMP Feature (0x1a) = Close Index: 00:E0:4C:6B:E5:03

The error did not appear when running with this patch.

Signed-off-by: Edward Vear edwardvear@gmail.com Signed-off-by: Marcel Holtmann marcel@holtmann.org Signed-off-by: Johan Hedberg johan.hedberg@intel.com Cc: Sudip Mukherjee sudipm.mukherjee@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- net/bluetooth/hci_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -763,7 +763,7 @@ static int hci_init3_req(struct hci_requ hci_req_add(req, HCI_OP_LE_CLEAR_RESOLV_LIST, 0, NULL); }

- if (hdev->commands[35] & 0x40) { + if (hdev->commands[35] & 0x04) { __le16 rpa_timeout = cpu_to_le16(hdev->rpa_timeout);

/* Set RPA timeout */

From: Takashi Iwai tiwai@suse.de

commit 3d5c5fdcee0f9a94deb0472e594706018b00aa31 upstream.

The silent_stream_disable() function introduced by the commit b1a5039759cb ("ALSA: hda/hdmi: fix silent stream for first playback to DP") takes the per_pin->lock mutex, but it unlocks the wrong one, spec->pcm_lock, which causes a deadlock. This patch corrects it.

Fixes: b1a5039759cb ("ALSA: hda/hdmi: fix silent stream for first playback to DP") Reported-by: Jan Alexander Steffens (heftig) heftig@archlinux.org Cc: stable@vger.kernel.org Acked-by: Kai Vehmanen kai.vehmanen@linux.intel.com Link: https://lore.kernel.org/r/20210101083852.12094-1-tiwai@suse.de Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- sound/pci/hda/patch_hdmi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -1736,7 +1736,7 @@ static void silent_stream_disable(struct per_pin->silent_stream = false;

unlock_out: - mutex_unlock(&spec->pcm_lock); + mutex_unlock(&per_pin->lock); }

/* update ELD and jack state via audio component */

From: Adrian Hunter adrian.hunter@intel.com

[ Upstream commit 151f1b664ffbb847c7fbbce5a5b8580f1b9b1d98 ]

It is simpler for drivers to provide a ->device_reset() callback irrespective of whether the GPIO, or firmware interface necessary to do the reset, is discovered during probe.

Change ->device_reset() to return an error code. Drivers that provide the callback, but do not do the reset operation should return -EOPNOTSUPP.

Link: https://lore.kernel.org/r/20201103141403.2142-3-adrian.hunter@intel.com Reviewed-by: Asutosh Das asutoshd@codeaurora.org Reviewed-by: Stanley Chu stanley.chu@mediatek.com Reviewed-by: Bean huo beanhuo@micron.com Reviewed-by: Can Guo cang@codeaurora.org Signed-off-by: Adrian Hunter adrian.hunter@intel.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/ufs/ufs-mediatek.c | 4 +++- drivers/scsi/ufs/ufs-qcom.c | 6 ++++-- drivers/scsi/ufs/ufshcd.h | 11 +++++++---- 3 files changed, 14 insertions(+), 7 deletions(-)

diff --git a/drivers/scsi/ufs/ufs-mediatek.c b/drivers/scsi/ufs/ufs-mediatek.c index 8df73bc2f8cb2..914a827a93ee8 100644 --- a/drivers/scsi/ufs/ufs-mediatek.c +++ b/drivers/scsi/ufs/ufs-mediatek.c @@ -743,7 +743,7 @@ static int ufs_mtk_link_startup_notify(struct ufs_hba *hba, return ret; }

-static void ufs_mtk_device_reset(struct ufs_hba *hba) +static int ufs_mtk_device_reset(struct ufs_hba *hba) { struct arm_smccc_res res;

@@ -764,6 +764,8 @@ static void ufs_mtk_device_reset(struct ufs_hba *hba) usleep_range(10000, 15000);

dev_info(hba->dev, "device reset done\n"); + + return 0; }

static int ufs_mtk_link_set_hpm(struct ufs_hba *hba) diff --git a/drivers/scsi/ufs/ufs-qcom.c b/drivers/scsi/ufs/ufs-qcom.c index f9d6ef3565407..a244c8ae1b4eb 100644 --- a/drivers/scsi/ufs/ufs-qcom.c +++ b/drivers/scsi/ufs/ufs-qcom.c @@ -1421,13 +1421,13 @@ static void ufs_qcom_dump_dbg_regs(struct ufs_hba *hba) * * Toggles the (optional) reset line to reset the attached device. */ -static void ufs_qcom_device_reset(struct ufs_hba *hba) +static int ufs_qcom_device_reset(struct ufs_hba *hba) { struct ufs_qcom_host *host = ufshcd_get_variant(hba);

/* reset gpio is optional */ if (!host->device_reset) - return; + return -EOPNOTSUPP;

/* * The UFS device shall detect reset pulses of 1us, sleep for 10us to @@ -1438,6 +1438,8 @@ static void ufs_qcom_device_reset(struct ufs_hba *hba)

gpiod_set_value_cansleep(host->device_reset, 0); usleep_range(10, 15); + + return 0; }

#if IS_ENABLED(CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND) diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h index e0f00a42371c5..de97971e2d865 100644 --- a/drivers/scsi/ufs/ufshcd.h +++ b/drivers/scsi/ufs/ufshcd.h @@ -318,7 +318,7 @@ struct ufs_hba_variant_ops { int (*resume)(struct ufs_hba *, enum ufs_pm_op); void (*dbg_register_dump)(struct ufs_hba *hba); int (*phy_initialization)(struct ufs_hba *); - void (*device_reset)(struct ufs_hba *hba); + int (*device_reset)(struct ufs_hba *hba); void (*config_scaling_param)(struct ufs_hba *hba, struct devfreq_dev_profile *profile, void *data); @@ -1181,9 +1181,12 @@ static inline void ufshcd_vops_dbg_register_dump(struct ufs_hba *hba) static inline void ufshcd_vops_device_reset(struct ufs_hba *hba) { if (hba->vops && hba->vops->device_reset) { - hba->vops->device_reset(hba); - ufshcd_set_ufs_dev_active(hba); - ufshcd_update_reg_hist(&hba->ufs_stats.dev_reset, 0); + int err = hba->vops->device_reset(hba); + + if (!err) + ufshcd_set_ufs_dev_active(hba); + if (err != -EOPNOTSUPP) + ufshcd_update_reg_hist(&hba->ufs_stats.dev_reset, err); } }

From: Christoph Hellwig hch@lst.de

[ Upstream commit 5a7a9e038b032137ae9c45d5429f18a2ffdf7d42 ]

Use the ib_dma_* helpers to skip the DMA translation instead. This removes the last user if dma_virt_ops and keeps the weird layering violation inside the RDMA core instead of burderning the DMA mapping subsystems with it. This also means the software RDMA drivers now don't have to mess with DMA parameters that are not relevant to them at all, and that in the future we can use PCI P2P transfers even for software RDMA, as there is no first fake layer of DMA mapping that the P2P DMA support.

Link: https://lore.kernel.org/r/20201106181941.1878556-8-hch@lst.de Signed-off-by: Christoph Hellwig hch@lst.de Tested-by: Mike Marciniszyn mike.marciniszyn@cornelisnetworks.com Signed-off-by: Jason Gunthorpe jgg@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/core/device.c | 43 ++++++++-------- drivers/infiniband/core/rw.c | 5 +- drivers/infiniband/sw/rdmavt/Kconfig | 1 - drivers/infiniband/sw/rdmavt/mr.c | 6 +-- drivers/infiniband/sw/rdmavt/vt.c | 8 --- drivers/infiniband/sw/rxe/Kconfig | 1 - drivers/infiniband/sw/rxe/rxe_verbs.c | 7 --- drivers/infiniband/sw/rxe/rxe_verbs.h | 1 - drivers/infiniband/sw/siw/Kconfig | 1 - drivers/infiniband/sw/siw/siw.h | 1 - drivers/infiniband/sw/siw/siw_main.c | 7 --- drivers/nvme/target/rdma.c | 3 +- include/rdma/ib_verbs.h | 73 ++++++++++++++++++--------- 13 files changed, 81 insertions(+), 76 deletions(-)

diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 4a041511b70ec..76b9c436edcd2 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -1177,25 +1177,6 @@ out: return ret; }

-static void setup_dma_device(struct ib_device *device, - struct device *dma_device) -{ - /* - * If the caller does not provide a DMA capable device then the IB - * device will be used. In this case the caller should fully setup the - * ibdev for DMA. This usually means using dma_virt_ops. - */ -#ifdef CONFIG_DMA_VIRT_OPS - if (!dma_device) { - device->dev.dma_ops = &dma_virt_ops; - dma_device = &device->dev; - } -#endif - WARN_ON(!dma_device); - device->dma_device = dma_device; - WARN_ON(!device->dma_device->dma_parms); -} - /* * setup_device() allocates memory and sets up data that requires calling the * device ops, this is the only reason these actions are not done during @@ -1341,7 +1322,14 @@ int ib_register_device(struct ib_device *device, const char *name, if (ret) return ret;

- setup_dma_device(device, dma_device); + /* + * If the caller does not provide a DMA capable device then the IB core + * will set up ib_sge and scatterlist structures that stash the kernel + * virtual address into the address field. + */ + WARN_ON(dma_device && !dma_device->dma_parms); + device->dma_device = dma_device; + ret = setup_device(device); if (ret) return ret; @@ -2676,6 +2664,21 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops) } EXPORT_SYMBOL(ib_set_device_ops);

+#ifdef CONFIG_INFINIBAND_VIRT_DMA +int ib_dma_virt_map_sg(struct ib_device *dev, struct scatterlist *sg, int nents) +{ + struct scatterlist *s; + int i; + + for_each_sg(sg, s, nents, i) { + sg_dma_address(s) = (uintptr_t)sg_virt(s); + sg_dma_len(s) = s->length; + } + return nents; +} +EXPORT_SYMBOL(ib_dma_virt_map_sg); +#endif /* CONFIG_INFINIBAND_VIRT_DMA */ + static const struct rdma_nl_cbs ibnl_ls_cb_table[RDMA_NL_LS_NUM_OPS] = { [RDMA_NL_LS_OP_RESOLVE] = { .doit = ib_nl_handle_resolve_resp, diff --git a/drivers/infiniband/core/rw.c b/drivers/infiniband/core/rw.c index 13f43ab7220b0..a96030b784eb2 100644 --- a/drivers/infiniband/core/rw.c +++ b/drivers/infiniband/core/rw.c @@ -285,8 +285,11 @@ static void rdma_rw_unmap_sg(struct ib_device *dev, struct scatterlist *sg, static int rdma_rw_map_sg(struct ib_device *dev, struct scatterlist *sg, u32 sg_cnt, enum dma_data_direction dir) { - if (is_pci_p2pdma_page(sg_page(sg))) + if (is_pci_p2pdma_page(sg_page(sg))) { + if (WARN_ON_ONCE(ib_uses_virt_dma(dev))) + return 0; return pci_p2pdma_map_sg(dev->dma_device, sg, sg_cnt, dir); + } return ib_dma_map_sg(dev, sg, sg_cnt, dir); }

diff --git a/drivers/infiniband/sw/rdmavt/Kconfig b/drivers/infiniband/sw/rdmavt/Kconfig index c8e268082952b..0df48b3a6b56c 100644 --- a/drivers/infiniband/sw/rdmavt/Kconfig +++ b/drivers/infiniband/sw/rdmavt/Kconfig @@ -4,6 +4,5 @@ config INFINIBAND_RDMAVT depends on INFINIBAND_VIRT_DMA depends on X86_64 depends on PCI - select DMA_VIRT_OPS help This is a common software verbs provider for RDMA networks. diff --git a/drivers/infiniband/sw/rdmavt/mr.c b/drivers/infiniband/sw/rdmavt/mr.c index 8490fdb9c91e5..90fc234f489ac 100644 --- a/drivers/infiniband/sw/rdmavt/mr.c +++ b/drivers/infiniband/sw/rdmavt/mr.c @@ -324,8 +324,6 @@ static void __rvt_free_mr(struct rvt_mr *mr) * @acc: access flags * * Return: the memory region on success, otherwise returns an errno. - * Note that all DMA addresses should be created via the functions in - * struct dma_virt_ops. */ struct ib_mr *rvt_get_dma_mr(struct ib_pd *pd, int acc) { @@ -766,7 +764,7 @@ int rvt_lkey_ok(struct rvt_lkey_table *rkt, struct rvt_pd *pd,

/* * We use LKEY == zero for kernel virtual addresses - * (see rvt_get_dma_mr() and dma_virt_ops). + * (see rvt_get_dma_mr()). */ if (sge->lkey == 0) { struct rvt_dev_info *dev = ib_to_rvt(pd->ibpd.device); @@ -877,7 +875,7 @@ int rvt_rkey_ok(struct rvt_qp *qp, struct rvt_sge *sge,

/* * We use RKEY == zero for kernel virtual addresses - * (see rvt_get_dma_mr() and dma_virt_ops). + * (see rvt_get_dma_mr()). */ rcu_read_lock(); if (rkey == 0) { diff --git a/drivers/infiniband/sw/rdmavt/vt.c b/drivers/infiniband/sw/rdmavt/vt.c index 670a9623b46e1..d1bbe66610cfe 100644 --- a/drivers/infiniband/sw/rdmavt/vt.c +++ b/drivers/infiniband/sw/rdmavt/vt.c @@ -524,7 +524,6 @@ static noinline int check_support(struct rvt_dev_info *rdi, int verb) int rvt_register_device(struct rvt_dev_info *rdi) { int ret = 0, i; - u64 dma_mask;

if (!rdi) return -EINVAL; @@ -579,13 +578,6 @@ int rvt_register_device(struct rvt_dev_info *rdi) /* Completion queues */ spin_lock_init(&rdi->n_cqs_lock);

- /* DMA Operations */ - rdi->ibdev.dev.dma_parms = rdi->ibdev.dev.parent->dma_parms; - dma_mask = IS_ENABLED(CONFIG_64BIT) ? DMA_BIT_MASK(64) : DMA_BIT_MASK(32); - ret = dma_coerce_mask_and_coherent(&rdi->ibdev.dev, dma_mask); - if (ret) - goto bail_wss; - /* Protection Domain */ spin_lock_init(&rdi->n_pds_lock); rdi->n_pds_allocated = 0; diff --git a/drivers/infiniband/sw/rxe/Kconfig b/drivers/infiniband/sw/rxe/Kconfig index 8810bfa680495..4521490667925 100644 --- a/drivers/infiniband/sw/rxe/Kconfig +++ b/drivers/infiniband/sw/rxe/Kconfig @@ -5,7 +5,6 @@ config RDMA_RXE depends on INFINIBAND_VIRT_DMA select NET_UDP_TUNNEL select CRYPTO_CRC32 - select DMA_VIRT_OPS help This driver implements the InfiniBand RDMA transport over the Linux network stack. It enables a system with a diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index f9c832e82552f..9c66f76545b3c 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -1118,7 +1118,6 @@ int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name) int err; struct ib_device *dev = &rxe->ib_dev; struct crypto_shash *tfm; - u64 dma_mask;

strlcpy(dev->node_desc, "rxe", sizeof(dev->node_desc));

@@ -1129,12 +1128,6 @@ int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name) dev->local_dma_lkey = 0; addrconf_addr_eui48((unsigned char *)&dev->node_guid, rxe->ndev->dev_addr); - dev->dev.dma_parms = &rxe->dma_parms; - dma_set_max_seg_size(&dev->dev, UINT_MAX); - dma_mask = IS_ENABLED(CONFIG_64BIT) ? DMA_BIT_MASK(64) : DMA_BIT_MASK(32); - err = dma_coerce_mask_and_coherent(&dev->dev, dma_mask); - if (err) - return err;

dev->uverbs_cmd_mask = BIT_ULL(IB_USER_VERBS_CMD_GET_CONTEXT) | BIT_ULL(IB_USER_VERBS_CMD_CREATE_COMP_CHANNEL) diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.h b/drivers/infiniband/sw/rxe/rxe_verbs.h index 3414b341b7091..4bf5d85a1ab3c 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.h +++ b/drivers/infiniband/sw/rxe/rxe_verbs.h @@ -352,7 +352,6 @@ struct rxe_port { struct rxe_dev { struct ib_device ib_dev; struct ib_device_attr attr; - struct device_dma_parameters dma_parms; int max_ucontext; int max_inline_data; struct mutex usdev_lock; diff --git a/drivers/infiniband/sw/siw/Kconfig b/drivers/infiniband/sw/siw/Kconfig index 3450ba5081df5..1b5105cbabaee 100644 --- a/drivers/infiniband/sw/siw/Kconfig +++ b/drivers/infiniband/sw/siw/Kconfig @@ -2,7 +2,6 @@ config RDMA_SIW tristate "Software RDMA over TCP/IP (iWARP) driver" depends on INET && INFINIBAND && LIBCRC32C depends on INFINIBAND_VIRT_DMA - select DMA_VIRT_OPS help This driver implements the iWARP RDMA transport over the Linux TCP/IP network stack. It enables a system with a diff --git a/drivers/infiniband/sw/siw/siw.h b/drivers/infiniband/sw/siw/siw.h index e9753831ac3f3..adda789962196 100644 --- a/drivers/infiniband/sw/siw/siw.h +++ b/drivers/infiniband/sw/siw/siw.h @@ -69,7 +69,6 @@ struct siw_pd {

struct siw_device { struct ib_device base_dev; - struct device_dma_parameters dma_parms; struct net_device *netdev; struct siw_dev_cap attrs;

diff --git a/drivers/infiniband/sw/siw/siw_main.c b/drivers/infiniband/sw/siw/siw_main.c index 181e06c1c43d7..c62a7a0d423c0 100644 --- a/drivers/infiniband/sw/siw/siw_main.c +++ b/drivers/infiniband/sw/siw/siw_main.c @@ -306,7 +306,6 @@ static struct siw_device *siw_device_create(struct net_device *netdev) struct siw_device *sdev = NULL; struct ib_device *base_dev; struct device *parent = netdev->dev.parent; - u64 dma_mask; int rv;

if (!parent) { @@ -383,12 +382,6 @@ static struct siw_device *siw_device_create(struct net_device *netdev) */ base_dev->phys_port_cnt = 1; base_dev->dev.parent = parent; - base_dev->dev.dma_parms = &sdev->dma_parms; - dma_set_max_seg_size(&base_dev->dev, UINT_MAX); - dma_mask = IS_ENABLED(CONFIG_64BIT) ? DMA_BIT_MASK(64) : DMA_BIT_MASK(32); - if (dma_coerce_mask_and_coherent(&base_dev->dev, dma_mask)) - goto error; - base_dev->num_comp_vectors = num_possible_cpus();

xa_init_flags(&sdev->qp_xa, XA_FLAGS_ALLOC1); diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index ae6620489457d..5c1e7cb7fe0de 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -414,7 +414,8 @@ static int nvmet_rdma_alloc_rsp(struct nvmet_rdma_device *ndev, if (ib_dma_mapping_error(ndev->device, r->send_sge.addr)) goto out_free_rsp;

- r->req.p2p_client = &ndev->device->dev; + if (!ib_uses_virt_dma(ndev->device)) + r->req.p2p_client = &ndev->device->dev; r->send_sge.length = sizeof(*r->req.cqe); r->send_sge.lkey = ndev->pd->local_dma_lkey;

diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 9bf6c319a670e..65771bef5e654 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -3943,6 +3943,16 @@ static inline int ib_req_ncomp_notif(struct ib_cq *cq, int wc_cnt) -ENOSYS; }

+/* + * Drivers that don't need a DMA mapping at the RDMA layer, set dma_device to + * NULL. This causes the ib_dma* helpers to just stash the kernel virtual + * address into the dma address. + */ +static inline bool ib_uses_virt_dma(struct ib_device *dev) +{ + return IS_ENABLED(CONFIG_INFINIBAND_VIRT_DMA) && !dev->dma_device; +} + /** * ib_dma_mapping_error - check a DMA addr for error * @dev: The device for which the dma_addr was created @@ -3950,6 +3960,8 @@ static inline int ib_req_ncomp_notif(struct ib_cq *cq, int wc_cnt) */ static inline int ib_dma_mapping_error(struct ib_device *dev, u64 dma_addr) { + if (ib_uses_virt_dma(dev)) + return 0; return dma_mapping_error(dev->dma_device, dma_addr); }

@@ -3964,6 +3976,8 @@ static inline u64 ib_dma_map_single(struct ib_device *dev, void *cpu_addr, size_t size, enum dma_data_direction direction) { + if (ib_uses_virt_dma(dev)) + return (uintptr_t)cpu_addr; return dma_map_single(dev->dma_device, cpu_addr, size, direction); }

@@ -3978,7 +3992,8 @@ static inline void ib_dma_unmap_single(struct ib_device *dev, u64 addr, size_t size, enum dma_data_direction direction) { - dma_unmap_single(dev->dma_device, addr, size, direction); + if (!ib_uses_virt_dma(dev)) + dma_unmap_single(dev->dma_device, addr, size, direction); }

/** @@ -3995,6 +4010,8 @@ static inline u64 ib_dma_map_page(struct ib_device *dev, size_t size, enum dma_data_direction direction) { + if (ib_uses_virt_dma(dev)) + return (uintptr_t)(page_address(page) + offset); return dma_map_page(dev->dma_device, page, offset, size, direction); }

@@ -4009,7 +4026,30 @@ static inline void ib_dma_unmap_page(struct ib_device *dev, u64 addr, size_t size, enum dma_data_direction direction) { - dma_unmap_page(dev->dma_device, addr, size, direction); + if (!ib_uses_virt_dma(dev)) + dma_unmap_page(dev->dma_device, addr, size, direction); +} + +int ib_dma_virt_map_sg(struct ib_device *dev, struct scatterlist *sg, int nents); +static inline int ib_dma_map_sg_attrs(struct ib_device *dev, + struct scatterlist *sg, int nents, + enum dma_data_direction direction, + unsigned long dma_attrs) +{ + if (ib_uses_virt_dma(dev)) + return ib_dma_virt_map_sg(dev, sg, nents); + return dma_map_sg_attrs(dev->dma_device, sg, nents, direction, + dma_attrs); +} + +static inline void ib_dma_unmap_sg_attrs(struct ib_device *dev, + struct scatterlist *sg, int nents, + enum dma_data_direction direction, + unsigned long dma_attrs) +{ + if (!ib_uses_virt_dma(dev)) + dma_unmap_sg_attrs(dev->dma_device, sg, nents, direction, + dma_attrs); }

/** @@ -4023,7 +4063,7 @@ static inline int ib_dma_map_sg(struct ib_device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction) { - return dma_map_sg(dev->dma_device, sg, nents, direction); + return ib_dma_map_sg_attrs(dev, sg, nents, direction, 0); }

/** @@ -4037,24 +4077,7 @@ static inline void ib_dma_unmap_sg(struct ib_device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction) { - dma_unmap_sg(dev->dma_device, sg, nents, direction); -} - -static inline int ib_dma_map_sg_attrs(struct ib_device *dev, - struct scatterlist *sg, int nents, - enum dma_data_direction direction, - unsigned long dma_attrs) -{ - return dma_map_sg_attrs(dev->dma_device, sg, nents, direction, - dma_attrs); -} - -static inline void ib_dma_unmap_sg_attrs(struct ib_device *dev, - struct scatterlist *sg, int nents, - enum dma_data_direction direction, - unsigned long dma_attrs) -{ - dma_unmap_sg_attrs(dev->dma_device, sg, nents, direction, dma_attrs); + ib_dma_unmap_sg_attrs(dev, sg, nents, direction, 0); }

/** @@ -4065,6 +4088,8 @@ static inline void ib_dma_unmap_sg_attrs(struct ib_device *dev, */ static inline unsigned int ib_dma_max_seg_size(struct ib_device *dev) { + if (ib_uses_virt_dma(dev)) + return UINT_MAX; return dma_get_max_seg_size(dev->dma_device); }

@@ -4080,7 +4105,8 @@ static inline void ib_dma_sync_single_for_cpu(struct ib_device *dev, size_t size, enum dma_data_direction dir) { - dma_sync_single_for_cpu(dev->dma_device, addr, size, dir); + if (!ib_uses_virt_dma(dev)) + dma_sync_single_for_cpu(dev->dma_device, addr, size, dir); }

/** @@ -4095,7 +4121,8 @@ static inline void ib_dma_sync_single_for_device(struct ib_device *dev, size_t size, enum dma_data_direction dir) { - dma_sync_single_for_device(dev->dma_device, addr, size, dir); + if (!ib_uses_virt_dma(dev)) + dma_sync_single_for_device(dev->dma_device, addr, size, dir); }

/**

From: Miklos Szeredi mszeredi@redhat.com

[ Upstream commit 5d069dbe8aaf2a197142558b6fb2978189ba3454 ]

Jan Kara's analysis of the syzbot report (edited):

The reproducer opens a directory on FUSE filesystem, it then attaches dnotify mark to the open directory. After that a fuse_do_getattr() call finds that attributes returned by the server are inconsistent, and calls make_bad_inode() which, among other things does:

inode->i_mode = S_IFREG;

This then confuses dnotify which doesn't tear down its structures properly and eventually crashes.

Avoid calling make_bad_inode() on a live inode: switch to a private flag on the fuse inode. Also add the test to ops which the bad_inode_ops would have caught.

This bug goes back to the initial merge of fuse in 2.6.14...

Reported-by: syzbot+f427adf9324b92652ccc@syzkaller.appspotmail.com Signed-off-by: Miklos Szeredi mszeredi@redhat.com Tested-by: Jan Kara jack@suse.cz Cc: stable@vger.kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/fuse/acl.c | 6 ++++++ fs/fuse/dir.c | 37 ++++++++++++++++++++++++++++++++----- fs/fuse/file.c | 19 +++++++++++-------- fs/fuse/fuse_i.h | 12 ++++++++++++ fs/fuse/inode.c | 4 ++-- fs/fuse/readdir.c | 4 ++-- fs/fuse/xattr.c | 9 +++++++++ 7 files changed, 74 insertions(+), 17 deletions(-)

diff --git a/fs/fuse/acl.c b/fs/fuse/acl.c index 5a48cee6d7d33..f529075a2ce87 100644 --- a/fs/fuse/acl.c +++ b/fs/fuse/acl.c @@ -19,6 +19,9 @@ struct posix_acl *fuse_get_acl(struct inode *inode, int type) void *value = NULL; struct posix_acl *acl;

+ if (fuse_is_bad(inode)) + return ERR_PTR(-EIO); + if (!fc->posix_acl || fc->no_getxattr) return NULL;

@@ -53,6 +56,9 @@ int fuse_set_acl(struct inode *inode, struct posix_acl *acl, int type) const char *name; int ret;

+ if (fuse_is_bad(inode)) + return -EIO; + if (!fc->posix_acl || fc->no_setxattr) return -EOPNOTSUPP;

diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index ff7dbeb16f88d..ffa031fe52933 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -202,7 +202,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags) int ret;

inode = d_inode_rcu(entry); - if (inode && is_bad_inode(inode)) + if (inode && fuse_is_bad(inode)) goto invalid; else if (time_before64(fuse_dentry_time(entry), get_jiffies_64()) || (flags & LOOKUP_REVAL)) { @@ -463,6 +463,9 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry, bool outarg_valid = true; bool locked;

+ if (fuse_is_bad(dir)) + return ERR_PTR(-EIO); + locked = fuse_lock_inode(dir); err = fuse_lookup_name(dir->i_sb, get_node_id(dir), &entry->d_name, &outarg, &inode); @@ -606,6 +609,9 @@ static int fuse_atomic_open(struct inode *dir, struct dentry *entry, struct fuse_conn *fc = get_fuse_conn(dir); struct dentry *res = NULL;

+ if (fuse_is_bad(dir)) + return -EIO; + if (d_in_lookup(entry)) { res = fuse_lookup(dir, entry, 0); if (IS_ERR(res)) @@ -654,6 +660,9 @@ static int create_new_entry(struct fuse_mount *fm, struct fuse_args *args, int err; struct fuse_forget_link *forget;

+ if (fuse_is_bad(dir)) + return -EIO; + forget = fuse_alloc_forget(); if (!forget) return -ENOMEM; @@ -781,6 +790,9 @@ static int fuse_unlink(struct inode *dir, struct dentry *entry) struct fuse_mount *fm = get_fuse_mount(dir); FUSE_ARGS(args);

+ if (fuse_is_bad(dir)) + return -EIO; + args.opcode = FUSE_UNLINK; args.nodeid = get_node_id(dir); args.in_numargs = 1; @@ -817,6 +829,9 @@ static int fuse_rmdir(struct inode *dir, struct dentry *entry) struct fuse_mount *fm = get_fuse_mount(dir); FUSE_ARGS(args);

+ if (fuse_is_bad(dir)) + return -EIO; + args.opcode = FUSE_RMDIR; args.nodeid = get_node_id(dir); args.in_numargs = 1; @@ -895,6 +910,9 @@ static int fuse_rename2(struct inode *olddir, struct dentry *oldent, struct fuse_conn *fc = get_fuse_conn(olddir); int err;

+ if (fuse_is_bad(olddir)) + return -EIO; + if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT)) return -EINVAL;

@@ -1030,7 +1048,7 @@ static int fuse_do_getattr(struct inode *inode, struct kstat *stat, if (!err) { if (fuse_invalid_attr(&outarg.attr) || (inode->i_mode ^ outarg.attr.mode) & S_IFMT) { - make_bad_inode(inode); + fuse_make_bad(inode); err = -EIO; } else { fuse_change_attributes(inode, &outarg.attr, @@ -1232,6 +1250,9 @@ static int fuse_permission(struct inode *inode, int mask) bool refreshed = false; int err = 0;

+ if (fuse_is_bad(inode)) + return -EIO; + if (!fuse_allow_current_process(fc)) return -EACCES;

@@ -1327,7 +1348,7 @@ static const char *fuse_get_link(struct dentry *dentry, struct inode *inode, int err;

err = -EIO; - if (is_bad_inode(inode)) + if (fuse_is_bad(inode)) goto out_err;

if (fc->cache_symlinks) @@ -1375,7 +1396,7 @@ static int fuse_dir_fsync(struct file *file, loff_t start, loff_t end, struct fuse_conn *fc = get_fuse_conn(inode); int err;

- if (is_bad_inode(inode)) + if (fuse_is_bad(inode)) return -EIO;

if (fc->no_fsyncdir) @@ -1664,7 +1685,7 @@ int fuse_do_setattr(struct dentry *dentry, struct iattr *attr,

if (fuse_invalid_attr(&outarg.attr) || (inode->i_mode ^ outarg.attr.mode) & S_IFMT) { - make_bad_inode(inode); + fuse_make_bad(inode); err = -EIO; goto error; } @@ -1727,6 +1748,9 @@ static int fuse_setattr(struct dentry *entry, struct iattr *attr) struct file *file = (attr->ia_valid & ATTR_FILE) ? attr->ia_file : NULL; int ret;

+ if (fuse_is_bad(inode)) + return -EIO; + if (!fuse_allow_current_process(get_fuse_conn(inode))) return -EACCES;

@@ -1785,6 +1809,9 @@ static int fuse_getattr(const struct path *path, struct kstat *stat, struct inode *inode = d_inode(path->dentry); struct fuse_conn *fc = get_fuse_conn(inode);

+ if (fuse_is_bad(inode)) + return -EIO; + if (!fuse_allow_current_process(fc)) { if (!request_mask) { /* diff --git a/fs/fuse/file.c b/fs/fuse/file.c index c03034e8c1529..8b306005453cc 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -226,6 +226,9 @@ int fuse_open_common(struct inode *inode, struct file *file, bool isdir) bool dax_truncate = (file->f_flags & O_TRUNC) && fc->atomic_o_trunc && FUSE_IS_DAX(inode);

+ if (fuse_is_bad(inode)) + return -EIO; + err = generic_file_open(inode, file); if (err) return err; @@ -463,7 +466,7 @@ static int fuse_flush(struct file *file, fl_owner_t id) FUSE_ARGS(args); int err;

- if (is_bad_inode(inode)) + if (fuse_is_bad(inode)) return -EIO;

err = write_inode_now(inode, 1); @@ -535,7 +538,7 @@ static int fuse_fsync(struct file *file, loff_t start, loff_t end, struct fuse_conn *fc = get_fuse_conn(inode); int err;

- if (is_bad_inode(inode)) + if (fuse_is_bad(inode)) return -EIO;

inode_lock(inode); @@ -859,7 +862,7 @@ static int fuse_readpage(struct file *file, struct page *page) int err;

err = -EIO; - if (is_bad_inode(inode)) + if (fuse_is_bad(inode)) goto out;

err = fuse_do_readpage(file, page); @@ -952,7 +955,7 @@ static void fuse_readahead(struct readahead_control *rac) struct fuse_conn *fc = get_fuse_conn(inode); unsigned int i, max_pages, nr_pages = 0;

- if (is_bad_inode(inode)) + if (fuse_is_bad(inode)) return;

max_pages = min_t(unsigned int, fc->max_pages, @@ -1555,7 +1558,7 @@ static ssize_t fuse_file_read_iter(struct kiocb *iocb, struct iov_iter *to) struct fuse_file *ff = file->private_data; struct inode *inode = file_inode(file);

- if (is_bad_inode(inode)) + if (fuse_is_bad(inode)) return -EIO;

if (FUSE_IS_DAX(inode)) @@ -1573,7 +1576,7 @@ static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from) struct fuse_file *ff = file->private_data; struct inode *inode = file_inode(file);

- if (is_bad_inode(inode)) + if (fuse_is_bad(inode)) return -EIO;

if (FUSE_IS_DAX(inode)) @@ -2172,7 +2175,7 @@ static int fuse_writepages(struct address_space *mapping, int err;

err = -EIO; - if (is_bad_inode(inode)) + if (fuse_is_bad(inode)) goto out;

data.inode = inode; @@ -2954,7 +2957,7 @@ long fuse_ioctl_common(struct file *file, unsigned int cmd, if (!fuse_allow_current_process(fc)) return -EACCES;

- if (is_bad_inode(inode)) + if (fuse_is_bad(inode)) return -EIO;

return fuse_do_ioctl(file, cmd, arg, flags); diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index d51598017d133..404d66f01e8d7 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -172,6 +172,8 @@ enum { FUSE_I_INIT_RDPLUS, /** An operation changing file size is in progress */ FUSE_I_SIZE_UNSTABLE, + /* Bad inode */ + FUSE_I_BAD, };

struct fuse_conn; @@ -858,6 +860,16 @@ static inline u64 fuse_get_attr_version(struct fuse_conn *fc) return atomic64_read(&fc->attr_version); }

+static inline void fuse_make_bad(struct inode *inode) +{ + set_bit(FUSE_I_BAD, &get_fuse_inode(inode)->state); +} + +static inline bool fuse_is_bad(struct inode *inode) +{ + return unlikely(test_bit(FUSE_I_BAD, &get_fuse_inode(inode)->state)); +} + /** Device operations */ extern const struct file_operations fuse_dev_operations;

diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 1a47afc95f800..f94b0bb57619c 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -132,7 +132,7 @@ static void fuse_evict_inode(struct inode *inode) fi->forget = NULL; } } - if (S_ISREG(inode->i_mode) && !is_bad_inode(inode)) { + if (S_ISREG(inode->i_mode) && !fuse_is_bad(inode)) { WARN_ON(!list_empty(&fi->write_files)); WARN_ON(!list_empty(&fi->queued_writes)); } @@ -342,7 +342,7 @@ retry: unlock_new_inode(inode); } else if ((inode->i_mode ^ attr->mode) & S_IFMT) { /* Inode has changed type, any I/O on the old should fail */ - make_bad_inode(inode); + fuse_make_bad(inode); iput(inode); goto retry; } diff --git a/fs/fuse/readdir.c b/fs/fuse/readdir.c index 3b5e91045871a..3441ffa740f3d 100644 --- a/fs/fuse/readdir.c +++ b/fs/fuse/readdir.c @@ -207,7 +207,7 @@ retry: dput(dentry); goto retry; } - if (is_bad_inode(inode)) { + if (fuse_is_bad(inode)) { dput(dentry); return -EIO; } @@ -568,7 +568,7 @@ int fuse_readdir(struct file *file, struct dir_context *ctx) struct inode *inode = file_inode(file); int err;

- if (is_bad_inode(inode)) + if (fuse_is_bad(inode)) return -EIO;

mutex_lock(&ff->readdir.lock); diff --git a/fs/fuse/xattr.c b/fs/fuse/xattr.c index 371bdcbc72337..cdea18de94f7e 100644 --- a/fs/fuse/xattr.c +++ b/fs/fuse/xattr.c @@ -113,6 +113,9 @@ ssize_t fuse_listxattr(struct dentry *entry, char *list, size_t size) struct fuse_getxattr_out outarg; ssize_t ret;

+ if (fuse_is_bad(inode)) + return -EIO; + if (!fuse_allow_current_process(fm->fc)) return -EACCES;

@@ -178,6 +181,9 @@ static int fuse_xattr_get(const struct xattr_handler *handler, struct dentry *dentry, struct inode *inode, const char *name, void *value, size_t size) { + if (fuse_is_bad(inode)) + return -EIO; + return fuse_getxattr(inode, name, value, size); }

@@ -186,6 +192,9 @@ static int fuse_xattr_set(const struct xattr_handler *handler, const char *name, const void *value, size_t size, int flags) { + if (fuse_is_bad(inode)) + return -EIO; + if (!value) return fuse_removexattr(inode, name);

From: Eric W. Biederman ebiederm@xmission.com

[ Upstream commit 0f9368b5bf6db0c04afc5454b1be79022a681615 ]

In preparation for converting exec_update_mutex to a rwsem so that multiple readers can execute in parallel and not deadlock, add down_read_killable_nested. This is needed so that kcmp_lock can be converted from working on a mutexes to working on rw_semaphores.

Signed-off-by: Eric W. Biederman ebiederm@xmission.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lkml.kernel.org/r/87o8jabqh3.fsf@x220.int.ebiederm.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/rwsem.h | 2 ++ kernel/locking/rwsem.c | 14 ++++++++++++++ 2 files changed, 16 insertions(+)

diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index 25e3fde856178..13021b08b2ed6 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -171,6 +171,7 @@ extern void downgrade_write(struct rw_semaphore *sem); * See Documentation/locking/lockdep-design.rst for more details.) */ extern void down_read_nested(struct rw_semaphore *sem, int subclass); +extern int __must_check down_read_killable_nested(struct rw_semaphore *sem, int subclass); extern void down_write_nested(struct rw_semaphore *sem, int subclass); extern int down_write_killable_nested(struct rw_semaphore *sem, int subclass); extern void _down_write_nest_lock(struct rw_semaphore *sem, struct lockdep_map *nest_lock); @@ -191,6 +192,7 @@ extern void down_read_non_owner(struct rw_semaphore *sem); extern void up_read_non_owner(struct rw_semaphore *sem); #else # define down_read_nested(sem, subclass) down_read(sem) +# define down_read_killable_nested(sem, subclass) down_read_killable(sem) # define down_write_nest_lock(sem, nest_lock) down_write(sem) # define down_write_nested(sem, subclass) down_write(sem) # define down_write_killable_nested(sem, subclass) down_write_killable(sem) diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index f11b9bd3431d2..54d11cb975510 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -1605,6 +1605,20 @@ void down_read_nested(struct rw_semaphore *sem, int subclass) } EXPORT_SYMBOL(down_read_nested);

+int down_read_killable_nested(struct rw_semaphore *sem, int subclass) +{ + might_sleep(); + rwsem_acquire_read(&sem->dep_map, subclass, 0, _RET_IP_); + + if (LOCK_CONTENDED_RETURN(sem, __down_read_trylock, __down_read_killable)) { + rwsem_release(&sem->dep_map, _RET_IP_); + return -EINTR; + } + + return 0; +} +EXPORT_SYMBOL(down_read_killable_nested); + void _down_write_nest_lock(struct rw_semaphore *sem, struct lockdep_map *nest) { might_sleep();

From: Eric W. Biederman ebiederm@xmission.com

[ Upstream commit f7cfd871ae0c5008d94b6f66834e7845caa93c15 ]

Recently syzbot reported[0] that there is a deadlock amongst the users of exec_update_mutex. The problematic lock ordering found by lockdep was:

perf_event_open (exec_update_mutex -> ovl_i_mutex) chown (ovl_i_mutex -> sb_writes) sendfile (sb_writes -> p->lock) by reading from a proc file and writing to overlayfs proc_pid_syscall (p->lock -> exec_update_mutex)

While looking at possible solutions it occured to me that all of the users and possible users involved only wanted to state of the given process to remain the same. They are all readers. The only writer is exec.

There is no reason for readers to block on each other. So fix this deadlock by transforming exec_update_mutex into a rw_semaphore named exec_update_lock that only exec takes for writing.

Cc: Jann Horn jannh@google.com Cc: Vasiliy Kulikov segoon@openwall.com Cc: Al Viro viro@zeniv.linux.org.uk Cc: Bernd Edlinger bernd.edlinger@hotmail.de Cc: Oleg Nesterov oleg@redhat.com Cc: Christopher Yeoh cyeoh@au1.ibm.com Cc: Cyrill Gorcunov gorcunov@gmail.com Cc: Sargun Dhillon sargun@sargun.me Cc: Christian Brauner christian.brauner@ubuntu.com Cc: Arnd Bergmann arnd@arndb.de Cc: Peter Zijlstra peterz@infradead.org Cc: Ingo Molnar mingo@redhat.com Cc: Arnaldo Carvalho de Melo acme@kernel.org Fixes: eea9673250db ("exec: Add exec_update_mutex to replace cred_guard_mutex") [0] https://lkml.kernel.org/r/00000000000063640c05ade8e3de@google.com Reported-by: syzbot+db9cdf3dd1f64252c6ef@syzkaller.appspotmail.com Link: https://lkml.kernel.org/r/87ft4mbqen.fsf@x220.int.ebiederm.org Signed-off-by: Eric W. Biederman ebiederm@xmission.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/exec.c | 12 ++++++------ fs/proc/base.c | 10 +++++----- include/linux/sched/signal.h | 11 ++++++----- init/init_task.c | 2 +- kernel/events/core.c | 12 ++++++------ kernel/fork.c | 6 +++--- kernel/kcmp.c | 30 +++++++++++++++--------------- kernel/pid.c | 4 ++-- 8 files changed, 44 insertions(+), 43 deletions(-)

diff --git a/fs/exec.c b/fs/exec.c index 547a2390baf54..ca89e0e3ef10f 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -965,8 +965,8 @@ EXPORT_SYMBOL(read_code);

/* * Maps the mm_struct mm into the current task struct. - * On success, this function returns with the mutex - * exec_update_mutex locked. + * On success, this function returns with exec_update_lock + * held for writing. */ static int exec_mmap(struct mm_struct *mm) { @@ -981,7 +981,7 @@ static int exec_mmap(struct mm_struct *mm) if (old_mm) sync_mm_rss(old_mm);

- ret = mutex_lock_killable(&tsk->signal->exec_update_mutex); + ret = down_write_killable(&tsk->signal->exec_update_lock); if (ret) return ret;

@@ -995,7 +995,7 @@ static int exec_mmap(struct mm_struct *mm) mmap_read_lock(old_mm); if (unlikely(old_mm->core_state)) { mmap_read_unlock(old_mm); - mutex_unlock(&tsk->signal->exec_update_mutex); + up_write(&tsk->signal->exec_update_lock); return -EINTR; } } @@ -1382,7 +1382,7 @@ int begin_new_exec(struct linux_binprm * bprm) return 0;

out_unlock: - mutex_unlock(&me->signal->exec_update_mutex); + up_write(&me->signal->exec_update_lock); out: return retval; } @@ -1423,7 +1423,7 @@ void setup_new_exec(struct linux_binprm * bprm) * some architectures like powerpc */ me->mm->task_size = TASK_SIZE; - mutex_unlock(&me->signal->exec_update_mutex); + up_write(&me->signal->exec_update_lock); mutex_unlock(&me->signal->cred_guard_mutex); } EXPORT_SYMBOL(setup_new_exec); diff --git a/fs/proc/base.c b/fs/proc/base.c index b362523a9829a..55ce0ee9c5c73 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -405,11 +405,11 @@ print0:

static int lock_trace(struct task_struct *task) { - int err = mutex_lock_killable(&task->signal->exec_update_mutex); + int err = down_read_killable(&task->signal->exec_update_lock); if (err) return err; if (!ptrace_may_access(task, PTRACE_MODE_ATTACH_FSCREDS)) { - mutex_unlock(&task->signal->exec_update_mutex); + up_read(&task->signal->exec_update_lock); return -EPERM; } return 0; @@ -417,7 +417,7 @@ static int lock_trace(struct task_struct *task)

static void unlock_trace(struct task_struct *task) { - mutex_unlock(&task->signal->exec_update_mutex); + up_read(&task->signal->exec_update_lock); }

#ifdef CONFIG_STACKTRACE @@ -2930,7 +2930,7 @@ static int do_io_accounting(struct task_struct *task, struct seq_file *m, int wh unsigned long flags; int result;

- result = mutex_lock_killable(&task->signal->exec_update_mutex); + result = down_read_killable(&task->signal->exec_update_lock); if (result) return result;

@@ -2966,7 +2966,7 @@ static int do_io_accounting(struct task_struct *task, struct seq_file *m, int wh result = 0;

out_unlock: - mutex_unlock(&task->signal->exec_update_mutex); + up_read(&task->signal->exec_update_lock); return result; }

diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 1bad18a1d8ba7..4b6a8234d7fc2 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -228,12 +228,13 @@ struct signal_struct { * credential calculations * (notably. ptrace) * Deprecated do not use in new code. - * Use exec_update_mutex instead. - */ - struct mutex exec_update_mutex; /* Held while task_struct is being - * updated during exec, and may have - * inconsistent permissions. + * Use exec_update_lock instead. */ + struct rw_semaphore exec_update_lock; /* Held while task_struct is + * being updated during exec, + * and may have inconsistent + * permissions. + */ } __randomize_layout;

/* diff --git a/init/init_task.c b/init/init_task.c index a56f0abb63e93..15f6eb93a04fa 100644 --- a/init/init_task.c +++ b/init/init_task.c @@ -26,7 +26,7 @@ static struct signal_struct init_signals = { .multiprocess = HLIST_HEAD_INIT, .rlim = INIT_RLIMITS, .cred_guard_mutex = __MUTEX_INITIALIZER(init_signals.cred_guard_mutex), - .exec_update_mutex = __MUTEX_INITIALIZER(init_signals.exec_update_mutex), + .exec_update_lock = __RWSEM_INITIALIZER(init_signals.exec_update_lock), #ifdef CONFIG_POSIX_TIMERS .posix_timers = LIST_HEAD_INIT(init_signals.posix_timers), .cputimer = { diff --git a/kernel/events/core.c b/kernel/events/core.c index 7e9a398fc3cb0..c3ba29d058b73 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1325,7 +1325,7 @@ static void put_ctx(struct perf_event_context *ctx) * function. * * Lock order: - * exec_update_mutex + * exec_update_lock * task_struct::perf_event_mutex * perf_event_context::mutex * perf_event::child_mutex; @@ -11847,14 +11847,14 @@ SYSCALL_DEFINE5(perf_event_open, }

if (task) { - err = mutex_lock_interruptible(&task->signal->exec_update_mutex); + err = down_read_interruptible(&task->signal->exec_update_lock); if (err) goto err_file;

/* * Preserve ptrace permission check for backwards compatibility. * - * We must hold exec_update_mutex across this and any potential + * We must hold exec_update_lock across this and any potential * perf_install_in_context() call for this new event to * serialize against exec() altering our credentials (and the * perf_event_exit_task() that could imply). @@ -12017,7 +12017,7 @@ SYSCALL_DEFINE5(perf_event_open, mutex_unlock(&ctx->mutex);

if (task) { - mutex_unlock(&task->signal->exec_update_mutex); + up_read(&task->signal->exec_update_lock); put_task_struct(task); }

@@ -12041,7 +12041,7 @@ err_locked: mutex_unlock(&ctx->mutex); err_cred: if (task) - mutex_unlock(&task->signal->exec_update_mutex); + up_read(&task->signal->exec_update_lock); err_file: fput(event_file); err_context: @@ -12358,7 +12358,7 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn) /* * When a child task exits, feed back event values to parent events. * - * Can be called with exec_update_mutex held when called from + * Can be called with exec_update_lock held when called from * setup_new_exec(). */ void perf_event_exit_task(struct task_struct *child) diff --git a/kernel/fork.c b/kernel/fork.c index dc55f68a6ee36..c675fdbd3dce1 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1222,7 +1222,7 @@ struct mm_struct *mm_access(struct task_struct *task, unsigned int mode) struct mm_struct *mm; int err;

- err = mutex_lock_killable(&task->signal->exec_update_mutex); + err = down_read_killable(&task->signal->exec_update_lock); if (err) return ERR_PTR(err);

@@ -1232,7 +1232,7 @@ struct mm_struct *mm_access(struct task_struct *task, unsigned int mode) mmput(mm); mm = ERR_PTR(-EACCES); } - mutex_unlock(&task->signal->exec_update_mutex); + up_read(&task->signal->exec_update_lock);

return mm; } @@ -1592,7 +1592,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) sig->oom_score_adj_min = current->signal->oom_score_adj_min;

mutex_init(&sig->cred_guard_mutex); - mutex_init(&sig->exec_update_mutex); + init_rwsem(&sig->exec_update_lock);

return 0; } diff --git a/kernel/kcmp.c b/kernel/kcmp.c index b3ff9288c6cc9..c0d2ad9b4705d 100644 --- a/kernel/kcmp.c +++ b/kernel/kcmp.c @@ -75,25 +75,25 @@ get_file_raw_ptr(struct task_struct *task, unsigned int idx) return file; }

-static void kcmp_unlock(struct mutex *m1, struct mutex *m2) +static void kcmp_unlock(struct rw_semaphore *l1, struct rw_semaphore *l2) { - if (likely(m2 != m1)) - mutex_unlock(m2); - mutex_unlock(m1); + if (likely(l2 != l1)) + up_read(l2); + up_read(l1); }

-static int kcmp_lock(struct mutex *m1, struct mutex *m2) +static int kcmp_lock(struct rw_semaphore *l1, struct rw_semaphore *l2) { int err;

- if (m2 > m1) - swap(m1, m2); + if (l2 > l1) + swap(l1, l2);

- err = mutex_lock_killable(m1); - if (!err && likely(m1 != m2)) { - err = mutex_lock_killable_nested(m2, SINGLE_DEPTH_NESTING); + err = down_read_killable(l1); + if (!err && likely(l1 != l2)) { + err = down_read_killable_nested(l2, SINGLE_DEPTH_NESTING); if (err) - mutex_unlock(m1); + up_read(l1); }

return err; @@ -173,8 +173,8 @@ SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type, /* * One should have enough rights to inspect task details. */ - ret = kcmp_lock(&task1->signal->exec_update_mutex, - &task2->signal->exec_update_mutex); + ret = kcmp_lock(&task1->signal->exec_update_lock, + &task2->signal->exec_update_lock); if (ret) goto err; if (!ptrace_may_access(task1, PTRACE_MODE_READ_REALCREDS) || @@ -229,8 +229,8 @@ SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type, }

err_unlock: - kcmp_unlock(&task1->signal->exec_update_mutex, - &task2->signal->exec_update_mutex); + kcmp_unlock(&task1->signal->exec_update_lock, + &task2->signal->exec_update_lock); err: put_task_struct(task1); put_task_struct(task2); diff --git a/kernel/pid.c b/kernel/pid.c index a96bc4bf4f869..4856818c9de1a 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -628,7 +628,7 @@ static struct file *__pidfd_fget(struct task_struct *task, int fd) struct file *file; int ret;

- ret = mutex_lock_killable(&task->signal->exec_update_mutex); + ret = down_read_killable(&task->signal->exec_update_lock); if (ret) return ERR_PTR(ret);

@@ -637,7 +637,7 @@ static struct file *__pidfd_fget(struct task_struct *task, int fd) else file = ERR_PTR(-EPERM);

- mutex_unlock(&task->signal->exec_update_mutex); + up_read(&task->signal->exec_update_lock);

return file ?: ERR_PTR(-EBADF); }