[PATCH AUTOSEL 4.19 01/34] nvme_fc: add module to ops template to allow module references
From: James Smart jsmart2021@gmail.com
[ Upstream commit 863fbae929c7a5b64e96b8a3ffb34a29eefb9f8f ]
In nvme-fc: it's possible to have connected active controllers and as no references are taken on the LLDD, the LLDD can be unloaded. The controller would enter a reconnect state and as long as the LLDD resumed within the reconnect timeout, the controller would resume. But if a namespace on the controller is the root device, allowing the driver to unload can be problematic. To reload the driver, it may require new io to the boot device, and as it's no longer connected we get into a catch-22 that eventually fails, and the system locks up.
Fix this issue by taking a module reference for every connected controller (which is what the core layer did to the transport module). Reference is cleared when the controller is removed.
Acked-by: Himanshu Madhani hmadhani@marvell.com Reviewed-by: Christoph Hellwig hch@lst.de Signed-off-by: James Smart jsmart2021@gmail.com Signed-off-by: Keith Busch kbusch@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/host/fc.c | 14 ++++++++++++-- drivers/nvme/target/fcloop.c | 1 + drivers/scsi/lpfc/lpfc_nvme.c | 2 ++ drivers/scsi/qla2xxx/qla_nvme.c | 1 + include/linux/nvme-fc-driver.h | 4 ++++ 5 files changed, 20 insertions(+), 2 deletions(-)
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 565bddcfd130d..d567035571bf2 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -342,7 +342,8 @@ nvme_fc_register_localport(struct nvme_fc_port_info *pinfo, !template->ls_req || !template->fcp_io || !template->ls_abort || !template->fcp_abort || !template->max_hw_queues || !template->max_sgl_segments || - !template->max_dif_sgl_segments || !template->dma_boundary) { + !template->max_dif_sgl_segments || !template->dma_boundary || + !template->module) { ret = -EINVAL; goto out_reghost_failed; } @@ -1986,6 +1987,7 @@ nvme_fc_ctrl_free(struct kref *ref) { struct nvme_fc_ctrl *ctrl = container_of(ref, struct nvme_fc_ctrl, ref); + struct nvme_fc_lport *lport = ctrl->lport; unsigned long flags;
if (ctrl->ctrl.tagset) { @@ -2011,6 +2013,7 @@ nvme_fc_ctrl_free(struct kref *ref) if (ctrl->ctrl.opts) nvmf_free_options(ctrl->ctrl.opts); kfree(ctrl); + module_put(lport->ops->module); }
static void @@ -3040,10 +3043,15 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, goto out_fail; }
+ if (!try_module_get(lport->ops->module)) { + ret = -EUNATCH; + goto out_free_ctrl; + } + idx = ida_simple_get(&nvme_fc_ctrl_cnt, 0, 0, GFP_KERNEL); if (idx < 0) { ret = -ENOSPC; - goto out_free_ctrl; + goto out_mod_put; }
ctrl->ctrl.opts = opts; @@ -3185,6 +3193,8 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, out_free_ida: put_device(ctrl->dev); ida_simple_remove(&nvme_fc_ctrl_cnt, ctrl->cnum); +out_mod_put: + module_put(lport->ops->module); out_free_ctrl: kfree(ctrl); out_fail: diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c index 291f4121f516a..f0536d341f2f2 100644 --- a/drivers/nvme/target/fcloop.c +++ b/drivers/nvme/target/fcloop.c @@ -825,6 +825,7 @@ fcloop_targetport_delete(struct nvmet_fc_target_port *targetport) #define FCLOOP_DMABOUND_4G 0xFFFFFFFF
static struct nvme_fc_port_template fctemplate = { + .module = THIS_MODULE, .localport_delete = fcloop_localport_delete, .remoteport_delete = fcloop_remoteport_delete, .create_queue = fcloop_create_queue, diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c index f73726e55e44d..6c355d87c709d 100644 --- a/drivers/scsi/lpfc/lpfc_nvme.c +++ b/drivers/scsi/lpfc/lpfc_nvme.c @@ -1903,6 +1903,8 @@ lpfc_nvme_fcp_abort(struct nvme_fc_local_port *pnvme_lport,
/* Declare and initialization an instance of the FC NVME template. */ static struct nvme_fc_port_template lpfc_nvme_template = { + .module = THIS_MODULE, + /* initiator-based functions */ .localport_delete = lpfc_nvme_localport_delete, .remoteport_delete = lpfc_nvme_remoteport_delete, diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c index 5590d6e8b5762..db367e428095d 100644 --- a/drivers/scsi/qla2xxx/qla_nvme.c +++ b/drivers/scsi/qla2xxx/qla_nvme.c @@ -560,6 +560,7 @@ static void qla_nvme_remoteport_delete(struct nvme_fc_remote_port *rport) }
static struct nvme_fc_port_template qla_nvme_fc_transport = { + .module = THIS_MODULE, .localport_delete = qla_nvme_localport_delete, .remoteport_delete = qla_nvme_remoteport_delete, .create_queue = qla_nvme_alloc_queue, diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index 496ff759f84c6..2f3ae41c212dc 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -282,6 +282,8 @@ struct nvme_fc_remote_port { * * Host/Initiator Transport Entrypoints/Parameters: * + * @module: The LLDD module using the interface + * * @localport_delete: The LLDD initiates deletion of a localport via * nvme_fc_deregister_localport(). However, the teardown is * asynchronous. This routine is called upon the completion of the @@ -395,6 +397,8 @@ struct nvme_fc_remote_port { * Value is Mandatory. Allowed to be zero. */ struct nvme_fc_port_template { + struct module *module; + /* initiator-based functions */ void (*localport_delete)(struct nvme_fc_local_port *); void (*remoteport_delete)(struct nvme_fc_remote_port *);
From: James Smart jsmart2021@gmail.com
[ Upstream commit c869e494ef8b5846d9ba91f1e922c23cd444f0c1 ]
If an error occurs on one of the ios used for creating an association, the creating routine has error paths that are invoked by the command failure and the error paths will free up the controller resources created to that point.
But... the io was ultimately determined by an asynchronous completion routine that detected the error and which unconditionally invokes the error_recovery path which calls delete_association. Delete association deletes all outstanding io then tears down the controller resources. So the create_association thread can be running in parallel with the error_recovery thread. What was seen was the LLDD received a call to delete a queue, causing the LLDD to do a free of a resource, then the transport called the delete queue again causing the driver to repeat the free call. The second free routine corrupted the allocator. The transport shouldn't be making the duplicate call, and the delete queue is just one of the resources being freed.
To fix, it is realized that the create_association path is completely serialized with one command at a time. So the failed io completion will always be seen by the create_association path and as of the failure, there are no ios to terminate and there is no reason to be manipulating queue freeze states, etc. The serialized condition stays true until the controller is transitioned to the LIVE state. Thus the fix is to change the error recovery path to check the controller state and only invoke the teardown path if not already in the CONNECTING state.
Reviewed-by: Himanshu Madhani hmadhani@marvell.com Reviewed-by: Ewan D. Milne emilne@redhat.com Signed-off-by: James Smart jsmart2021@gmail.com Signed-off-by: Keith Busch kbusch@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/host/fc.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-)
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index d567035571bf2..1875f6b8a907b 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2894,10 +2894,22 @@ nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status) static void __nvme_fc_terminate_io(struct nvme_fc_ctrl *ctrl) { - nvme_stop_keep_alive(&ctrl->ctrl); + /* + * if state is connecting - the error occurred as part of a + * reconnect attempt. The create_association error paths will + * clean up any outstanding io. + * + * if it's a different state - ensure all pending io is + * terminated. Given this can delay while waiting for the + * aborted io to return, we recheck adapter state below + * before changing state. + */ + if (ctrl->ctrl.state != NVME_CTRL_CONNECTING) { + nvme_stop_keep_alive(&ctrl->ctrl);
- /* will block will waiting for io to terminate */ - nvme_fc_delete_association(ctrl); + /* will block will waiting for io to terminate */ + nvme_fc_delete_association(ctrl); + }
if (ctrl->ctrl.state != NVME_CTRL_CONNECTING && !nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING))
From: Guchun Chen guchun.chen@amd.com
[ Upstream commit 6e807535dae5dbbd53bcc5e81047a20bf5eb08ea ]
When security violation from new vbios happens, data fabric is risky to stop working. So prevent the direct access to DF mmFabricConfigAccessControl from the new vbios and onwards.
Signed-off-by: Guchun Chen guchun.chen@amd.com Reviewed-by: Hawking Zhang Hawking.Zhang@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/amdgpu/df_v3_6.c | 38 ++++++++++++++++------------ 1 file changed, 22 insertions(+), 16 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/df_v3_6.c b/drivers/gpu/drm/amd/amdgpu/df_v3_6.c index d5ebe566809b2..a1c941229f4b3 100644 --- a/drivers/gpu/drm/amd/amdgpu/df_v3_6.c +++ b/drivers/gpu/drm/amd/amdgpu/df_v3_6.c @@ -75,23 +75,29 @@ static void df_v3_6_update_medium_grain_clock_gating(struct amdgpu_device *adev, { u32 tmp;
- /* Put DF on broadcast mode */ - adev->df_funcs->enable_broadcast_mode(adev, true); - - if (enable && (adev->cg_flags & AMD_CG_SUPPORT_DF_MGCG)) { - tmp = RREG32_SOC15(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater); - tmp &= ~DF_PIE_AON0_DfGlobalClkGater__MGCGMode_MASK; - tmp |= DF_V3_6_MGCG_ENABLE_15_CYCLE_DELAY; - WREG32_SOC15(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater, tmp); - } else { - tmp = RREG32_SOC15(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater); - tmp &= ~DF_PIE_AON0_DfGlobalClkGater__MGCGMode_MASK; - tmp |= DF_V3_6_MGCG_DISABLE; - WREG32_SOC15(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater, tmp); + if (adev->cg_flags & AMD_CG_SUPPORT_DF_MGCG) { + /* Put DF on broadcast mode */ + adev->df_funcs->enable_broadcast_mode(adev, true); + + if (enable) { + tmp = RREG32_SOC15(DF, 0, + mmDF_PIE_AON0_DfGlobalClkGater); + tmp &= ~DF_PIE_AON0_DfGlobalClkGater__MGCGMode_MASK; + tmp |= DF_V3_6_MGCG_ENABLE_15_CYCLE_DELAY; + WREG32_SOC15(DF, 0, + mmDF_PIE_AON0_DfGlobalClkGater, tmp); + } else { + tmp = RREG32_SOC15(DF, 0, + mmDF_PIE_AON0_DfGlobalClkGater); + tmp &= ~DF_PIE_AON0_DfGlobalClkGater__MGCGMode_MASK; + tmp |= DF_V3_6_MGCG_DISABLE; + WREG32_SOC15(DF, 0, + mmDF_PIE_AON0_DfGlobalClkGater, tmp); + } + + /* Exit broadcast mode */ + adev->df_funcs->enable_broadcast_mode(adev, false); } - - /* Exit broadcast mode */ - adev->df_funcs->enable_broadcast_mode(adev, false); }
static void df_v3_6_get_clockgating_state(struct amdgpu_device *adev,
From: Pierre-Eric Pelloux-Prayer pierre-eric.pelloux-prayer@amd.com
[ Upstream commit bf26da927a1cd57c9deb2db29ae8cf276ba8b17b ]
The same workaround is used for gfx7. Both PAL and Mesa use it for gfx8 too, so port this commit to gfx_v8_0_ring_emit_fence_gfx.
Signed-off-by: Pierre-Eric Pelloux-Prayer pierre-eric.pelloux-prayer@amd.com Reviewed-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 22 +++++++++++++++++++--- 1 file changed, 19 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 5a9534a82d409..e1cb7fa89e4d6 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -6405,7 +6405,23 @@ static void gfx_v8_0_ring_emit_fence_gfx(struct amdgpu_ring *ring, u64 addr, bool write64bit = flags & AMDGPU_FENCE_FLAG_64BIT; bool int_sel = flags & AMDGPU_FENCE_FLAG_INT;
- /* EVENT_WRITE_EOP - flush caches, send int */ + /* Workaround for cache flush problems. First send a dummy EOP + * event down the pipe with seq one below. + */ + amdgpu_ring_write(ring, PACKET3(PACKET3_EVENT_WRITE_EOP, 4)); + amdgpu_ring_write(ring, (EOP_TCL1_ACTION_EN | + EOP_TC_ACTION_EN | + EOP_TC_WB_ACTION_EN | + EVENT_TYPE(CACHE_FLUSH_AND_INV_TS_EVENT) | + EVENT_INDEX(5))); + amdgpu_ring_write(ring, addr & 0xfffffffc); + amdgpu_ring_write(ring, (upper_32_bits(addr) & 0xffff) | + DATA_SEL(1) | INT_SEL(0)); + amdgpu_ring_write(ring, lower_32_bits(seq - 1)); + amdgpu_ring_write(ring, upper_32_bits(seq - 1)); + + /* Then send the real EOP event down the pipe: + * EVENT_WRITE_EOP - flush caches, send int */ amdgpu_ring_write(ring, PACKET3(PACKET3_EVENT_WRITE_EOP, 4)); amdgpu_ring_write(ring, (EOP_TCL1_ACTION_EN | EOP_TC_ACTION_EN | @@ -7154,7 +7170,7 @@ static const struct amdgpu_ring_funcs gfx_v8_0_ring_funcs_gfx = { 5 + /* COND_EXEC */ 7 + /* PIPELINE_SYNC */ VI_FLUSH_GPU_TLB_NUM_WREG * 5 + 9 + /* VM_FLUSH */ - 8 + /* FENCE for VM_FLUSH */ + 12 + /* FENCE for VM_FLUSH */ 20 + /* GDS switch */ 4 + /* double SWITCH_BUFFER, the first COND_EXEC jump to the place just @@ -7166,7 +7182,7 @@ static const struct amdgpu_ring_funcs gfx_v8_0_ring_funcs_gfx = { 31 + /* DE_META */ 3 + /* CNTX_CTRL */ 5 + /* HDP_INVL */ - 8 + 8 + /* FENCE x2 */ + 12 + 12 + /* FENCE x2 */ 2, /* SWITCH_BUFFER */ .emit_ib_size = 4, /* gfx_v8_0_ring_emit_ib_gfx */ .emit_ib = gfx_v8_0_ring_emit_ib_gfx,
From: David Galiffi David.Galiffi@amd.com
[ Upstream commit a51d9f8fe756beac51ce26ef54195da00a260d13 ]
[Why] In dc_link_is_dp_sink_present, if dal_ddc_open fails, then dal_gpio_destroy_ddc is called, destroying pin_data and pin_clock. They are created only on dc_construct, and next aux access will cause a panic.
[How] Instead of calling dal_gpio_destroy_ddc, call dal_ddc_close.
Signed-off-by: David Galiffi David.Galiffi@amd.com Reviewed-by: Tony Cheng Tony.Cheng@amd.com Acked-by: Leo Li sunpeng.li@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/display/dc/core/dc_link.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index 23a7ef97afdd2..33c8eda97457f 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -348,7 +348,7 @@ bool dc_link_is_dp_sink_present(struct dc_link *link)
if (GPIO_RESULT_OK != dal_ddc_open( ddc, GPIO_MODE_INPUT, GPIO_DDC_CONFIG_TYPE_MODE_I2C)) { - dal_gpio_destroy_ddc(&ddc); + dal_ddc_close(ddc);
return present; }
From: Geert Uytterhoeven geert+renesas@glider.be
[ Upstream commit 9fd229c478fbf77c41c8528aa757ef14210365f6 ]
As of commit b9ddd5091160793e ("iio: adc: max9611: Fix temperature reading in probe"), max9611 initialization sometimes fails on the Salvator-X(S) development board with:
max9611 4-007f: Invalid value received from ADC 0x8000: aborting max9611: probe of 4-007f failed with error -5
The max9611 driver tests communications with the chip by reading the die temperature during the probe function, which returns an invalid value.
According to the datasheet, the typical ADC conversion time is 2 ms, but no minimum or maximum values are provided. Maxim Technical Support confirmed this was tested with temperature Ta=25 degreeC, and promised to inform me if a maximum/minimum value is available (they didn't get back to me, so I assume it is not).
However, the driver assumes a 1 ms conversion time. Usually the usleep_range() call returns after more than 1.8 ms, hence it succeeds. When it returns earlier, the data register may be read too early, and the previous measurement value will be returned. After boot, this is the temperature POR (power-on reset) value, causing the failure above.
Fix this by increasing the delay from 1000-2000 µs to 3000-3300 µs.
Note that this issue has always been present, but it was exposed by the aformentioned commit.
Fixes: 69780a3bbc0b1e7e ("iio: adc: Add Maxim max9611 ADC driver") Signed-off-by: Geert Uytterhoeven geert+renesas@glider.be Reviewed-by: Jacopo Mondi jacopo+renesas@jmondi.org Reviewed-by: Wolfram Sang wsa+renesas@sang-engineering.com Signed-off-by: Jonathan Cameron Jonathan.Cameron@huawei.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/iio/adc/max9611.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-)
diff --git a/drivers/iio/adc/max9611.c b/drivers/iio/adc/max9611.c index 0884435eec68d..9f1a5ef0b444c 100644 --- a/drivers/iio/adc/max9611.c +++ b/drivers/iio/adc/max9611.c @@ -92,6 +92,12 @@ #define MAX9611_TEMP_SCALE_NUM 1000000 #define MAX9611_TEMP_SCALE_DIV 2083
+/* + * Conversion time is 2 ms (typically) at Ta=25 degreeC + * No maximum value is known, so play it safe. + */ +#define MAX9611_CONV_TIME_US_RANGE 3000, 3300 + struct max9611_dev { struct device *dev; struct i2c_client *i2c_client; @@ -239,11 +245,9 @@ static int max9611_read_single(struct max9611_dev *max9611, return ret; }
- /* - * need a delay here to make register configuration - * stabilize. 1 msec at least, from empirical testing. - */ - usleep_range(1000, 2000); + /* need a delay here to make register configuration stabilize. */ + + usleep_range(MAX9611_CONV_TIME_US_RANGE);
ret = i2c_smbus_read_word_swapped(max9611->i2c_client, reg_addr); if (ret < 0) { @@ -510,7 +514,7 @@ static int max9611_init(struct max9611_dev *max9611) MAX9611_REG_CTRL2, 0); return ret; } - usleep_range(1000, 2000); + usleep_range(MAX9611_CONV_TIME_US_RANGE);
return 0; }
From: Leonard Crestez leonard.crestez@nxp.com
[ Upstream commit e876e710ede23f670494331e062d643928e4142a ]
Notifier callbacks shouldn't return negative errno but one of the NOTIFY_OK/DONE/BAD values.
The OPP core will ignore return values from notifiers but returning a value that matches NOTIFY_STOP_MASK will stop the notification chain.
Fix by always returning NOTIFY_OK.
Signed-off-by: Leonard Crestez leonard.crestez@nxp.com Reviewed-by: Matthias Kaehlcke mka@chromium.org Reviewed-by: Chanwoo Choi cw00.choi@samsung.com Signed-off-by: Chanwoo Choi cw00.choi@samsung.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/devfreq/devfreq.c | 24 +++++++++++++----------- 1 file changed, 13 insertions(+), 11 deletions(-)
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index 61fbaa89d7b4f..34e297f28fc2a 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -538,26 +538,28 @@ static int devfreq_notifier_call(struct notifier_block *nb, unsigned long type, void *devp) { struct devfreq *devfreq = container_of(nb, struct devfreq, nb); - int ret; + int err = -EINVAL;
mutex_lock(&devfreq->lock);
devfreq->scaling_min_freq = find_available_min_freq(devfreq); - if (!devfreq->scaling_min_freq) { - mutex_unlock(&devfreq->lock); - return -EINVAL; - } + if (!devfreq->scaling_min_freq) + goto out;
devfreq->scaling_max_freq = find_available_max_freq(devfreq); - if (!devfreq->scaling_max_freq) { - mutex_unlock(&devfreq->lock); - return -EINVAL; - } + if (!devfreq->scaling_max_freq) + goto out; + + err = update_devfreq(devfreq);
- ret = update_devfreq(devfreq); +out: mutex_unlock(&devfreq->lock); + if (err) + dev_err(devfreq->dev.parent, + "failed to update frequency from OPP notifier (%d)\n", + err);
- return ret; + return NOTIFY_OK; }
/**
From: Leonard Crestez leonard.crestez@nxp.com
[ Upstream commit e7cc792d00049c874010b398a27c3cc7bc8fef34 ]
The devfreq_notifier_call functions will update scaling_min_freq and scaling_max_freq when the OPP table is updated.
If fetching the maximum frequency fails then scaling_max_freq remains set to zero which is confusing. Set to ULONG_MAX instead so we don't need special handling for this case in other places.
Signed-off-by: Leonard Crestez leonard.crestez@nxp.com Reviewed-by: Matthias Kaehlcke mka@chromium.org Reviewed-by: Chanwoo Choi cw00.choi@samsung.com Signed-off-by: Chanwoo Choi cw00.choi@samsung.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/devfreq/devfreq.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index 34e297f28fc2a..a47e76a62287f 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -547,8 +547,10 @@ static int devfreq_notifier_call(struct notifier_block *nb, unsigned long type, goto out;
devfreq->scaling_max_freq = find_available_max_freq(devfreq); - if (!devfreq->scaling_max_freq) + if (!devfreq->scaling_max_freq) { + devfreq->scaling_max_freq = ULONG_MAX; goto out; + }
err = update_devfreq(devfreq);
From: Leonard Crestez leonard.crestez@nxp.com
[ Upstream commit 42a6b25e67df6ee6675e8d1eaf18065bd73328ba ]
Right now devfreq_dev_release will print a warning and abort the rest of the cleanup if the devfreq instance is not part of the global devfreq_list. But this is a valid scenario, for example it can happen if the governor can't be found or on any other init error that happens after device_register.
Initialize devfreq->node to an empty list head in devfreq_add_device so that list_del becomes a safe noop inside devfreq_dev_release and we can continue the rest of the cleanup.
Signed-off-by: Leonard Crestez leonard.crestez@nxp.com Reviewed-by: Matthias Kaehlcke mka@chromium.org Reviewed-by: Chanwoo Choi cw00.choi@samsung.com Signed-off-by: Chanwoo Choi cw00.choi@samsung.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/devfreq/devfreq.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-)
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index a47e76a62287f..69bbb1e9ab23d 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -575,11 +575,6 @@ static void devfreq_dev_release(struct device *dev) struct devfreq *devfreq = to_devfreq(dev);
mutex_lock(&devfreq_list_lock); - if (IS_ERR(find_device_devfreq(devfreq->dev.parent))) { - mutex_unlock(&devfreq_list_lock); - dev_warn(&devfreq->dev, "releasing devfreq which doesn't exist\n"); - return; - } list_del(&devfreq->node); mutex_unlock(&devfreq_list_lock);
@@ -634,6 +629,7 @@ struct devfreq *devfreq_add_device(struct device *dev, devfreq->dev.parent = dev; devfreq->dev.class = devfreq_class; devfreq->dev.release = devfreq_dev_release; + INIT_LIST_HEAD(&devfreq->node); devfreq->profile = profile; strncpy(devfreq->governor_name, governor_name, DEVFREQ_NAME_LEN); devfreq->previous_freq = profile->initial_freq;
From: Marc Dionne marc.dionne@auristor.com
[ Upstream commit 9bd0160d12370a076e44f8d1320cde9c83f2c647 ]
afs_find_server tries to find a server that has an address that matches the transport address of an rxrpc peer. The code assumes that the transport address is always ipv6, with ipv4 represented as ipv4 mapped addresses, but that's not the case. If the transport family is AF_INET, srx->transport.sin6.sin6_addr.s6_addr32[] will be beyond the actual ipv4 address and will always be 0, and all ipv4 addresses will be seen as matching.
As a result, the first ipv4 address seen on any server will be considered a match, and the server returned may be the wrong one.
One of the consequences is that callbacks received over ipv4 will only be correctly applied for the server that happens to have the first ipv4 address on the fs_addresses4 list. Callbacks over ipv4 from all other servers are dropped, causing the client to serve stale data.
This is fixed by looking at the transport family, and comparing ipv4 addresses based on a sockaddr_in structure rather than a sockaddr_in6.
Fixes: d2ddc776a458 ("afs: Overhaul volume and server record caching and fileserver rotation") Signed-off-by: Marc Dionne marc.dionne@auristor.com Signed-off-by: David Howells dhowells@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/afs/server.c | 21 ++++++++------------- 1 file changed, 8 insertions(+), 13 deletions(-)
diff --git a/fs/afs/server.c b/fs/afs/server.c index 1d329e6981d51..2c7f6211c3601 100644 --- a/fs/afs/server.c +++ b/fs/afs/server.c @@ -34,18 +34,11 @@ static void afs_dec_servers_outstanding(struct afs_net *net) struct afs_server *afs_find_server(struct afs_net *net, const struct sockaddr_rxrpc *srx) { - const struct sockaddr_in6 *a = &srx->transport.sin6, *b; const struct afs_addr_list *alist; struct afs_server *server = NULL; unsigned int i; - bool ipv6 = true; int seq = 0, diff;
- if (srx->transport.sin6.sin6_addr.s6_addr32[0] == 0 || - srx->transport.sin6.sin6_addr.s6_addr32[1] == 0 || - srx->transport.sin6.sin6_addr.s6_addr32[2] == htonl(0xffff)) - ipv6 = false; - rcu_read_lock();
do { @@ -54,7 +47,8 @@ struct afs_server *afs_find_server(struct afs_net *net, server = NULL; read_seqbegin_or_lock(&net->fs_addr_lock, &seq);
- if (ipv6) { + if (srx->transport.family == AF_INET6) { + const struct sockaddr_in6 *a = &srx->transport.sin6, *b; hlist_for_each_entry_rcu(server, &net->fs_addresses6, addr6_link) { alist = rcu_dereference(server->addresses); for (i = alist->nr_ipv4; i < alist->nr_addrs; i++) { @@ -70,15 +64,16 @@ struct afs_server *afs_find_server(struct afs_net *net, } } } else { + const struct sockaddr_in *a = &srx->transport.sin, *b; hlist_for_each_entry_rcu(server, &net->fs_addresses4, addr4_link) { alist = rcu_dereference(server->addresses); for (i = 0; i < alist->nr_ipv4; i++) { - b = &alist->addrs[i].transport.sin6; - diff = ((u16 __force)a->sin6_port - - (u16 __force)b->sin6_port); + b = &alist->addrs[i].transport.sin; + diff = ((u16 __force)a->sin_port - + (u16 __force)b->sin_port); if (diff == 0) - diff = ((u32 __force)a->sin6_addr.s6_addr32[3] - - (u32 __force)b->sin6_addr.s6_addr32[3]); + diff = ((u32 __force)a->sin_addr.s_addr - + (u32 __force)b->sin_addr.s_addr); if (diff == 0) goto found; }
From: David Howells dhowells@redhat.com
[ Upstream commit bcbccaf2edcf1b76f73f890e968babef446151a4 ]
Make the AFS dynamic root superblock R/W so that SELinux can set the security label on it. Without this, upgrades to, say, the Fedora filesystem-afs RPM fail if afs is mounted on it because the SELinux label can't be (re-)applied.
It might be better to make it possible to bypass the R/O check for LSM label application through setxattr.
Fixes: 4d673da14533 ("afs: Support the AFS dynamic root") Signed-off-by: David Howells dhowells@redhat.com Reviewed-by: Marc Dionne marc.dionne@auristor.com cc: selinux@vger.kernel.org cc: linux-security-module@vger.kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/afs/super.c | 1 - 1 file changed, 1 deletion(-)
diff --git a/fs/afs/super.c b/fs/afs/super.c index 4d3e274207fb7..bd26082974732 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -404,7 +404,6 @@ static int afs_fill_super(struct super_block *sb, /* allocate the root inode and dentry */ if (as->dyn_root) { inode = afs_iget_pseudo_dir(sb, true); - sb->s_flags |= SB_RDONLY; } else { sprintf(sb->s_id, "%u", as->volume->vid); afs_activate_volume(as->volume);
From: Chuhong Yuan hslester96@gmail.com
[ Upstream commit 44a7b6759000ac51b92715579a7bba9e3f9245c2 ]
The driver forgets to call unregister_pernet_subsys() in the error path of cma_init(). Add the missed call to fix it.
Fixes: 4be74b42a6d0 ("IB/cma: Separate port allocation to network namespaces") Signed-off-by: Chuhong Yuan hslester96@gmail.com Reviewed-by: Parav Pandit parav@mellanox.com Link: https://lore.kernel.org/r/20191206012426.12744-1-hslester96@gmail.com Signed-off-by: Doug Ledford dledford@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/core/cma.c | 1 + 1 file changed, 1 insertion(+)
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 1f373ba573b6d..319bfef00a4a8 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -4658,6 +4658,7 @@ static int __init cma_init(void) err: unregister_netdevice_notifier(&cma_nb); ib_sa_unregister_client(&sa_client); + unregister_pernet_subsys(&cma_pernet_operations); err_wq: destroy_workqueue(cma_wq); return ret;
From: Steve Wise larrystevenwise@gmail.com
[ Upstream commit 2030abddec6884aaf5892f5724c48fc340e6826f ]
If RoCE PDUs being sent or received contain pad bytes, then the iCRC is miscalculated, resulting in PDUs being emitted by RXE with an incorrect iCRC, as well as ingress PDUs being dropped due to erroneously detecting a bad iCRC in the PDU. The fix is to include the pad bytes, if any, in iCRC computations.
Note: This bug has caused broken on-the-wire compatibility with actual hardware RoCE devices since the soft-RoCE driver was first put into the mainstream kernel. Fixing it will create an incompatibility with the original soft-RoCE devices, but is necessary to be compatible with real hardware devices.
Fixes: 8700e3e7c485 ("Soft RoCE driver") Signed-off-by: Steve Wise larrystevenwise@gmail.com Link: https://lore.kernel.org/r/20191203020319.15036-2-larrystevenwise@gmail.com Signed-off-by: Doug Ledford dledford@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/sw/rxe/rxe_recv.c | 2 +- drivers/infiniband/sw/rxe/rxe_req.c | 6 ++++++ drivers/infiniband/sw/rxe/rxe_resp.c | 7 +++++++ 3 files changed, 14 insertions(+), 1 deletion(-)
diff --git a/drivers/infiniband/sw/rxe/rxe_recv.c b/drivers/infiniband/sw/rxe/rxe_recv.c index d30dbac24583a..695a607e2d14c 100644 --- a/drivers/infiniband/sw/rxe/rxe_recv.c +++ b/drivers/infiniband/sw/rxe/rxe_recv.c @@ -391,7 +391,7 @@ void rxe_rcv(struct sk_buff *skb)
calc_icrc = rxe_icrc_hdr(pkt, skb); calc_icrc = rxe_crc32(rxe, calc_icrc, (u8 *)payload_addr(pkt), - payload_size(pkt)); + payload_size(pkt) + bth_pad(pkt)); calc_icrc = (__force u32)cpu_to_be32(~calc_icrc); if (unlikely(calc_icrc != pack_icrc)) { if (skb->protocol == htons(ETH_P_IPV6)) diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c index f7dd8de799415..1c1eae0ef8c28 100644 --- a/drivers/infiniband/sw/rxe/rxe_req.c +++ b/drivers/infiniband/sw/rxe/rxe_req.c @@ -500,6 +500,12 @@ static int fill_packet(struct rxe_qp *qp, struct rxe_send_wqe *wqe, if (err) return err; } + if (bth_pad(pkt)) { + u8 *pad = payload_addr(pkt) + paylen; + + memset(pad, 0, bth_pad(pkt)); + crc = rxe_crc32(rxe, crc, pad, bth_pad(pkt)); + } } p = payload_addr(pkt) + paylen + bth_pad(pkt);
diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c index 681d8e0913d06..9078cfd3b8bdd 100644 --- a/drivers/infiniband/sw/rxe/rxe_resp.c +++ b/drivers/infiniband/sw/rxe/rxe_resp.c @@ -737,6 +737,13 @@ static enum resp_states read_reply(struct rxe_qp *qp, if (err) pr_err("Failed copying memory\n");
+ if (bth_pad(&ack_pkt)) { + struct rxe_dev *rxe = to_rdev(qp->ibqp.device); + u8 *pad = payload_addr(&ack_pkt) + payload; + + memset(pad, 0, bth_pad(&ack_pkt)); + icrc = rxe_crc32(rxe, icrc, pad, bth_pad(&ack_pkt)); + } p = payload_addr(&ack_pkt) + payload + bth_pad(&ack_pkt); *p = ~icrc;
From: Bo Wu wubo40@huawei.com
[ Upstream commit 9a1b0b9a6dab452fb0e39fe96880c4faf3878369 ]
When phba->mbox_ext_buf_ctx.seqNum != phba->mbox_ext_buf_ctx.numBuf, dd_data should be freed before return SLI_CONFIG_HANDLED.
When lpfc_sli_issue_mbox func return fails, pmboxq should be also freed in job_error tag.
Link: https://lore.kernel.org/r/EDBAAA0BBBA2AC4E9C8B6B81DEEE1D6915E7A966@DGGEML525... Signed-off-by: Bo Wu wubo40@huawei.com Reviewed-by: Zhiqiang Liu liuzhiqiang26@huawei.com Reviewed-by: James Smart james.smart@broadcom.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/lpfc/lpfc_bsg.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-)
diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c index 99aea52e584b0..21f104c5eab62 100644 --- a/drivers/scsi/lpfc/lpfc_bsg.c +++ b/drivers/scsi/lpfc/lpfc_bsg.c @@ -4419,12 +4419,6 @@ lpfc_bsg_write_ebuf_set(struct lpfc_hba *phba, struct bsg_job *job, phba->mbox_ext_buf_ctx.seqNum++; nemb_tp = phba->mbox_ext_buf_ctx.nembType;
- dd_data = kmalloc(sizeof(struct bsg_job_data), GFP_KERNEL); - if (!dd_data) { - rc = -ENOMEM; - goto job_error; - } - pbuf = (uint8_t *)dmabuf->virt; size = job->request_payload.payload_len; sg_copy_to_buffer(job->request_payload.sg_list, @@ -4461,6 +4455,13 @@ lpfc_bsg_write_ebuf_set(struct lpfc_hba *phba, struct bsg_job *job, "2968 SLI_CONFIG ext-buffer wr all %d " "ebuffers received\n", phba->mbox_ext_buf_ctx.numBuf); + + dd_data = kmalloc(sizeof(struct bsg_job_data), GFP_KERNEL); + if (!dd_data) { + rc = -ENOMEM; + goto job_error; + } + /* mailbox command structure for base driver */ pmboxq = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL); if (!pmboxq) { @@ -4509,6 +4510,8 @@ lpfc_bsg_write_ebuf_set(struct lpfc_hba *phba, struct bsg_job *job, return SLI_CONFIG_HANDLED;
job_error: + if (pmboxq) + mempool_free(pmboxq, phba->mbox_mem_pool); lpfc_bsg_dma_page_free(phba, dmabuf); kfree(dd_data);
From: Roman Bolshakov r.bolshakov@yadro.com
[ Upstream commit 600954e6f2df695434887dfc6a99a098859990cf ]
del_work is already initialized inside qla2x00_alloc_fcport, there's no need to overwrite it. Indeed, it might prevent complete traversal of workqueue list.
Fixes: a01c77d2cbc45 ("scsi: qla2xxx: Move session delete to driver work queue") Cc: Quinn Tran qutran@marvell.com Link: https://lore.kernel.org/r/20191125165702.1013-5-r.bolshakov@yadro.com Acked-by: Himanshu Madhani hmadhani@marvell.com Reviewed-by: Hannes Reinecke hare@suse.de Tested-by: Hannes Reinecke hare@suse.de Reviewed-by: Bart Van Assche bvanassche@acm.org Signed-off-by: Roman Bolshakov r.bolshakov@yadro.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/qla2xxx/qla_target.c | 1 - 1 file changed, 1 deletion(-)
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 210ce294038df..8eda55e917e04 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -1261,7 +1261,6 @@ void qlt_schedule_sess_for_deletion(struct fc_port *sess) "Scheduling sess %p for deletion %8phC\n", sess, sess->port_name);
- INIT_WORK(&sess->del_work, qla24xx_delete_sess_fn); WARN_ON(!queue_work(sess->vha->hw->wq, &sess->del_work)); }
From: Roman Bolshakov r.bolshakov@yadro.com
[ Upstream commit 2c2f4bed9b6299e6430a65a29b5d27b8763fdf25 ]
MBA_PORT_UPDATE generates duplicate log lines in target mode because qlt_async_event is called twice. Drop the calls within the case as the function will be called right after the switch statement.
Cc: Quinn Tran qutran@marvell.com Link: https://lore.kernel.org/r/20191125165702.1013-8-r.bolshakov@yadro.com Acked-by: Himanshu Madhani hmadhani@marvel.com Reviewed-by: Hannes Reinecke hare@suse.de Tested-by: Hannes Reinecke hare@suse.de Acked-by: Himanshu Madhani hmadhani@marvell.com Signed-off-by: Roman Bolshakov r.bolshakov@yadro.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/qla2xxx/qla_isr.c | 4 ---- 1 file changed, 4 deletions(-)
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index afe15b3e45fbf..e6d162945f5db 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -1049,8 +1049,6 @@ qla2x00_async_event(scsi_qla_host_t *vha, struct rsp_que *rsp, uint16_t *mb) ql_dbg(ql_dbg_async, vha, 0x5011, "Asynchronous PORT UPDATE ignored %04x/%04x/%04x.\n", mb[1], mb[2], mb[3]); - - qlt_async_event(mb[0], vha, mb); break; }
@@ -1067,8 +1065,6 @@ qla2x00_async_event(scsi_qla_host_t *vha, struct rsp_que *rsp, uint16_t *mb) set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags); set_bit(LOCAL_LOOP_UPDATE, &vha->dpc_flags); set_bit(VP_CONFIG_OK, &vha->vp_flags); - - qlt_async_event(mb[0], vha, mb); break;
case MBA_RSCN_UPDATE: /* State Change Registration */
From: Roman Bolshakov r.bolshakov@yadro.com
[ Upstream commit 0334cdea1fba36fad8bdf9516f267ce01de625f7 ]
The size of the buffer is hardcoded as 0x70 or 112 bytes, while the size of ELS IOCB is 0x40 and the size of PLOGI payload returned by Get Parameters command is 0x74.
Cc: Quinn Tran qutran@marvell.com Link: https://lore.kernel.org/r/20191125165702.1013-9-r.bolshakov@yadro.com Acked-by: Himanshu Madhani hmadhani@marvell.com Reviewed-by: Hannes Reinecke hare@suse.de Tested-by: Hannes Reinecke hare@suse.de Signed-off-by: Roman Bolshakov r.bolshakov@yadro.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/qla2xxx/qla_iocb.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c index c699bbb8485bb..7e47321e003c8 100644 --- a/drivers/scsi/qla2xxx/qla_iocb.c +++ b/drivers/scsi/qla2xxx/qla_iocb.c @@ -2537,7 +2537,8 @@ qla24xx_els_logo_iocb(srb_t *sp, struct els_entry_24xx *els_iocb) ql_dbg(ql_dbg_io + ql_dbg_buffer, vha, 0x3073, "PLOGI ELS IOCB:\n"); ql_dump_buffer(ql_log_info, vha, 0x0109, - (uint8_t *)els_iocb, 0x70); + (uint8_t *)els_iocb, + sizeof(*els_iocb)); } else { els_iocb->tx_byte_count = sizeof(struct els_logo_payload); els_iocb->tx_address[0] = @@ -2703,7 +2704,8 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode,
ql_dbg(ql_dbg_disc + ql_dbg_buffer, vha, 0x3073, "PLOGI buffer:\n"); ql_dump_buffer(ql_dbg_disc + ql_dbg_buffer, vha, 0x0109, - (uint8_t *)elsio->u.els_plogi.els_plogi_pyld, 0x70); + (uint8_t *)elsio->u.els_plogi.els_plogi_pyld, + sizeof(*elsio->u.els_plogi.els_plogi_pyld));
rval = qla2x00_start_sp(sp); if (rval != QLA_SUCCESS) {
From: Roman Bolshakov r.bolshakov@yadro.com
[ Upstream commit fd1de5830a5abaf444cc4312871e02c41e24fdc1 ]
qla2x00_configure_local_loop initializes PLOGI payload for PLOGI ELS using Get Parameters mailbox command.
In the case when the driver is running in target mode, the topology is N2N and the target port has higher WWPN, LOCAL_LOOP_UPDATE bit is cleared too early and PLOGI payload is not initialized by the Get Parameters command. That causes a failure of ELS IOCB carrying the PLOGI with 0x15 aka Data Underrun error.
LOCAL_LOOP_UPDATE has to be set to initialize PLOGI payload.
Fixes: 48acad099074 ("scsi: qla2xxx: Fix N2N link re-connect") Link: https://lore.kernel.org/r/20191125165702.1013-10-r.bolshakov@yadro.com Acked-by: Quinn Tran qutran@marvell.com Acked-by: Himanshu Madhani hmadhani@marvell.com Reviewed-by: Hannes Reinecke hare@suse.de Tested-by: Hannes Reinecke hare@suse.de Signed-off-by: Roman Bolshakov r.bolshakov@yadro.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/qla2xxx/qla_init.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-)
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index d734dcf517b92..753338d5343b9 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -4814,14 +4814,8 @@ qla2x00_configure_loop(scsi_qla_host_t *vha) set_bit(RSCN_UPDATE, &flags); clear_bit(LOCAL_LOOP_UPDATE, &flags);
- } else if (ha->current_topology == ISP_CFG_N) { - clear_bit(RSCN_UPDATE, &flags); - if (qla_tgt_mode_enabled(vha)) { - /* allow the other side to start the login */ - clear_bit(LOCAL_LOOP_UPDATE, &flags); - set_bit(RELOGIN_NEEDED, &vha->dpc_flags); - } - } else if (ha->current_topology == ISP_CFG_NL) { + } else if (ha->current_topology == ISP_CFG_NL || + ha->current_topology == ISP_CFG_N) { clear_bit(RSCN_UPDATE, &flags); set_bit(LOCAL_LOOP_UPDATE, &flags); } else if (!vha->flags.online ||
From: Roman Bolshakov r.bolshakov@yadro.com
[ Upstream commit 5e6b01d84b9d20bcd77fc7c4733a2a4149bf220a ]
qlt_handle_login schedules session for deletion even if a login is in progress. That causes login bouncing, i.e. a few logins are made before it settles down.
Complete the first login by sending Notify Acknowledge IOCB via qlt_plogi_ack_unref if the session is pending login completion.
Fixes: 9cd883f07a54 ("scsi: qla2xxx: Fix session cleanup for N2N") Cc: Krishna Kant krishna.kant@purestorage.com Cc: Alexei Potashnik alexei@purestorage.com Link: https://lore.kernel.org/r/20191125165702.1013-11-r.bolshakov@yadro.com Acked-by: Quinn Tran qutran@marvell.com Acked-by: Himanshu Madhani hmadhani@marvell.com Reviewed-by: Hannes Reinecke hare@suse.de Tested-by: Hannes Reinecke hare@suse.de Signed-off-by: Roman Bolshakov r.bolshakov@yadro.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/qla2xxx/qla_target.c | 1 + 1 file changed, 1 insertion(+)
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 8eda55e917e04..e9545411ec5a9 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -4779,6 +4779,7 @@ static int qlt_handle_login(struct scsi_qla_host *vha,
switch (sess->disc_state) { case DSC_DELETED: + case DSC_LOGIN_PEND: qlt_plogi_ack_unref(vha, pla); break;
From: Roman Bolshakov r.bolshakov@yadro.com
[ Upstream commit af22f0c7b052c5c203207f1e5ebd6aa65f87c538 ]
PORT UPDATE asynchronous event is generated on the host that issues PLOGI ELS (in the case of higher WWPN). In that case, the event shouldn't be handled as it sets unwanted DPC flags (i.e. LOOP_RESYNC_NEEDED) that trigger link flap.
Ignore the event if the host has higher WWPN, but handle otherwise.
Cc: Quinn Tran qutran@marvell.com Link: https://lore.kernel.org/r/20191125165702.1013-13-r.bolshakov@yadro.com Acked-by: Himanshu Madhani hmadhani@marvell.com Reviewed-by: Hannes Reinecke hare@suse.de Tested-by: Hannes Reinecke hare@suse.de Signed-off-by: Roman Bolshakov r.bolshakov@yadro.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/qla2xxx/qla_mbx.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c index b01f69dd4b283..abef3b29fa101 100644 --- a/drivers/scsi/qla2xxx/qla_mbx.c +++ b/drivers/scsi/qla2xxx/qla_mbx.c @@ -3871,6 +3871,7 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha, vha->d_id.b24 = 0; vha->d_id.b.al_pa = 1; ha->flags.n2n_bigger = 1; + ha->flags.n2n_ae = 0;
id.b.al_pa = 2; ql_dbg(ql_dbg_async, vha, 0x5075, @@ -3881,6 +3882,7 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha, "Format 1: Remote login - Waiting for WWPN %8phC.\n", rptid_entry->u.f1.port_name); ha->flags.n2n_bigger = 0; + ha->flags.n2n_ae = 1; } qla24xx_post_newsess_work(vha, &id, rptid_entry->u.f1.port_name, @@ -3892,7 +3894,6 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha, /* if our portname is higher then initiate N2N login */
set_bit(N2N_LOGIN_NEEDED, &vha->dpc_flags); - ha->flags.n2n_ae = 1; return; break; case TOPO_FL:
From: Dan Carpenter dan.carpenter@oracle.com
[ Upstream commit fee92f25777789d73e1936b91472e9c4644457c8 ]
On this error path we call qla4xxx_mem_free() and then the caller also calls qla4xxx_free_adapter() which calls qla4xxx_mem_free(). It leads to a couple double frees:
drivers/scsi/qla4xxx/ql4_os.c:8856 qla4xxx_probe_adapter() warn: 'ha->chap_dma_pool' double freed drivers/scsi/qla4xxx/ql4_os.c:8856 qla4xxx_probe_adapter() warn: 'ha->fw_ddb_dma_pool' double freed
Fixes: afaf5a2d341d ("[SCSI] Initial Commit of qla4xxx") Link: https://lore.kernel.org/r/20191203094421.hw7ex7qr3j2rbsmx@kili.mountain Signed-off-by: Dan Carpenter dan.carpenter@oracle.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/qla4xxx/ql4_os.c | 1 - 1 file changed, 1 deletion(-)
diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c index 25c8ce54a976d..f8acf101af3d9 100644 --- a/drivers/scsi/qla4xxx/ql4_os.c +++ b/drivers/scsi/qla4xxx/ql4_os.c @@ -4280,7 +4280,6 @@ static int qla4xxx_mem_alloc(struct scsi_qla_host *ha) return QLA_SUCCESS;
mem_alloc_error_exit: - qla4xxx_mem_free(ha); return QLA_ERROR; }
From: Jason Yan yanaijie@huawei.com
[ Upstream commit f70267f379b5e5e11bdc5d72a56bf17e5feed01f ]
The discovering of sas port is driven by workqueue in libsas. When libsas is processing port events or phy events in workqueue, new events may rise up and change the state of some structures such as asd_sas_phy. This may cause some problems such as follows:
==>thread 1 ==>thread 2
==>phy up ==>phy_up_v3_hw() ==>oob_mode = SATA_OOB_MODE; ==>phy down quickly ==>hisi_sas_phy_down() ==>sas_ha->notify_phy_event() ==>sas_phy_disconnected() ==>oob_mode = OOB_NOT_CONNECTED ==>workqueue wakeup ==>sas_form_port() ==>sas_discover_domain() ==>sas_get_port_device() ==>oob_mode is OOB_NOT_CONNECTED and device is wrongly taken as expander
This at last lead to the panic when libsas trying to issue a command to discover the device.
[183047.614035] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000058 [183047.622896] Mem abort info: [183047.625762] ESR = 0x96000004 [183047.628893] Exception class = DABT (current EL), IL = 32 bits [183047.634888] SET = 0, FnV = 0 [183047.638015] EA = 0, S1PTW = 0 [183047.641232] Data abort info: [183047.644189] ISV = 0, ISS = 0x00000004 [183047.648100] CM = 0, WnR = 0 [183047.651145] user pgtable: 4k pages, 48-bit VAs, pgdp = 00000000b7df67be [183047.657834] [0000000000000058] pgd=0000000000000000 [183047.662789] Internal error: Oops: 96000004 [#1] SMP [183047.667740] Process kworker/u16:2 (pid: 31291, stack limit = 0x00000000417c4974) [183047.675208] CPU: 0 PID: 3291 Comm: kworker/u16:2 Tainted: G W OE 4.19.36-vhulk1907.1.0.h410.eulerosv2r8.aarch64 #1 [183047.687015] Hardware name: N/A N/A/Kunpeng Desktop Board D920S10, BIOS 0.15 10/22/2019 [183047.695007] Workqueue: 0000:74:02.0_disco_q sas_discover_domain [183047.700999] pstate: 20c00009 (nzCv daif +PAN +UAO) [183047.705864] pc : prep_ata_v3_hw+0xf8/0x230 [hisi_sas_v3_hw] [183047.711510] lr : prep_ata_v3_hw+0xb0/0x230 [hisi_sas_v3_hw] [183047.717153] sp : ffff00000f28ba60 [183047.720541] x29: ffff00000f28ba60 x28: ffff8026852d7228 [183047.725925] x27: ffff8027dba3e0a8 x26: ffff8027c05fc200 [183047.731310] x25: 0000000000000000 x24: ffff8026bafa8dc0 [183047.736695] x23: ffff8027c05fc218 x22: ffff8026852d7228 [183047.742079] x21: ffff80007c2f2940 x20: ffff8027c05fc200 [183047.747464] x19: 0000000000f80800 x18: 0000000000000010 [183047.752848] x17: 0000000000000000 x16: 0000000000000000 [183047.758232] x15: ffff000089a5a4ff x14: 0000000000000005 [183047.763617] x13: ffff000009a5a50e x12: ffff8026bafa1e20 [183047.769001] x11: ffff0000087453b8 x10: ffff00000f28b870 [183047.774385] x9 : 0000000000000000 x8 : ffff80007e58f9b0 [183047.779770] x7 : 0000000000000000 x6 : 000000000000003f [183047.785154] x5 : 0000000000000040 x4 : ffffffffffffffe0 [183047.790538] x3 : 00000000000000f8 x2 : 0000000002000007 [183047.795922] x1 : 0000000000000008 x0 : 0000000000000000 [183047.801307] Call trace: [183047.803827] prep_ata_v3_hw+0xf8/0x230 [hisi_sas_v3_hw] [183047.809127] hisi_sas_task_prep+0x750/0x888 [hisi_sas_main] [183047.814773] hisi_sas_task_exec.isra.7+0x88/0x1f0 [hisi_sas_main] [183047.820939] hisi_sas_queue_command+0x28/0x38 [hisi_sas_main] [183047.826757] smp_execute_task_sg+0xec/0x218 [183047.831013] smp_execute_task+0x74/0xa0 [183047.834921] sas_discover_expander.part.7+0x9c/0x5f8 [183047.839959] sas_discover_root_expander+0x90/0x160 [183047.844822] sas_discover_domain+0x1b8/0x1e8 [183047.849164] process_one_work+0x1b4/0x3f8 [183047.853246] worker_thread+0x54/0x470 [183047.856981] kthread+0x134/0x138 [183047.860283] ret_from_fork+0x10/0x18 [183047.863931] Code: f9407a80 528000e2 39409281 72a04002 (b9405800) [183047.870097] kernel fault(0x1) notification starting on CPU 0 [183047.875828] kernel fault(0x1) notification finished on CPU 0 [183047.881559] Modules linked in: unibsp(OE) hns3(OE) hclge(OE) hnae3(OE) mem_drv(OE) hisi_sas_v3_hw(OE) hisi_sas_main(OE) [183047.892418] ---[ end trace 4cc26083fc11b783 ]--- [183047.897107] Kernel panic - not syncing: Fatal exception [183047.902403] kernel fault(0x5) notification starting on CPU 0 [183047.908134] kernel fault(0x5) notification finished on CPU 0 [183047.913865] SMP: stopping secondary CPUs [183047.917861] Kernel Offset: disabled [183047.921422] CPU features: 0x2,a2a00a38 [183047.925243] Memory Limit: none [183047.928372] kernel reboot(0x2) notification starting on CPU 0 [183047.934190] kernel reboot(0x2) notification finished on CPU 0 [183047.940008] ---[ end Kernel panic - not syncing: Fatal exception ]---
Fixes: 2908d778ab3e ("[SCSI] aic94xx: new driver") Link: https://lore.kernel.org/r/20191206011118.46909-1-yanaijie@huawei.com Reported-by: Gao Chuan gaochuan4@huawei.com Reviewed-by: John Garry john.garry@huawei.com Signed-off-by: Jason Yan yanaijie@huawei.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/libsas/sas_discover.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-)
diff --git a/drivers/scsi/libsas/sas_discover.c b/drivers/scsi/libsas/sas_discover.c index 0148ae62a52a9..e320534310b1e 100644 --- a/drivers/scsi/libsas/sas_discover.c +++ b/drivers/scsi/libsas/sas_discover.c @@ -97,12 +97,21 @@ static int sas_get_port_device(struct asd_sas_port *port) else dev->dev_type = SAS_SATA_DEV; dev->tproto = SAS_PROTOCOL_SATA; - } else { + } else if (port->oob_mode == SAS_OOB_MODE) { struct sas_identify_frame *id = (struct sas_identify_frame *) dev->frame_rcvd; dev->dev_type = id->dev_type; dev->iproto = id->initiator_bits; dev->tproto = id->target_bits; + } else { + /* If the oob mode is OOB_NOT_CONNECTED, the port is + * disconnected due to race with PHY down. We cannot + * continue to discover this port + */ + sas_put_device(dev); + pr_warn("Port %016llx is disconnected when discovering\n", + SAS_ADDR(port->attached_sas_addr)); + return -ENODEV; }
sas_init_dev(dev);
From: Hans de Goede hdegoede@redhat.com
[ Upstream commit 37a68eab4cd92b507c9e8afd760fdc18e4fecac6 ]
Place the declaration of struct nouveau_conn_atom above that of struct nouveau_connector. This commit makes no changes to the moved block what so ever, it just moves it up a bit.
This is a preparation patch to fix some issues with connector handling on pre nv50 displays (which do not use atomic modesetting).
Signed-off-by: Hans de Goede hdegoede@redhat.com Reviewed-by: Lyude Paul lyude@redhat.com Signed-off-by: Ben Skeggs bskeggs@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/nouveau/nouveau_connector.h | 110 ++++++++++---------- 1 file changed, 55 insertions(+), 55 deletions(-)
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.h b/drivers/gpu/drm/nouveau/nouveau_connector.h index dc7454e7f19aa..b46e99f7641ed 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.h +++ b/drivers/gpu/drm/nouveau/nouveau_connector.h @@ -29,6 +29,7 @@
#include <nvif/notify.h>
+#include <drm/drm_crtc.h> #include <drm/drm_edid.h> #include <drm/drm_encoder.h> #include <drm/drm_dp_helper.h> @@ -37,6 +38,60 @@
struct nvkm_i2c_port;
+#define nouveau_conn_atom(p) \ + container_of((p), struct nouveau_conn_atom, state) + +struct nouveau_conn_atom { + struct drm_connector_state state; + + struct { + /* The enum values specifically defined here match nv50/gf119 + * hw values, and the code relies on this. + */ + enum { + DITHERING_MODE_OFF = 0x00, + DITHERING_MODE_ON = 0x01, + DITHERING_MODE_DYNAMIC2X2 = 0x10 | DITHERING_MODE_ON, + DITHERING_MODE_STATIC2X2 = 0x18 | DITHERING_MODE_ON, + DITHERING_MODE_TEMPORAL = 0x20 | DITHERING_MODE_ON, + DITHERING_MODE_AUTO + } mode; + enum { + DITHERING_DEPTH_6BPC = 0x00, + DITHERING_DEPTH_8BPC = 0x02, + DITHERING_DEPTH_AUTO + } depth; + } dither; + + struct { + int mode; /* DRM_MODE_SCALE_* */ + struct { + enum { + UNDERSCAN_OFF, + UNDERSCAN_ON, + UNDERSCAN_AUTO, + } mode; + u32 hborder; + u32 vborder; + } underscan; + bool full; + } scaler; + + struct { + int color_vibrance; + int vibrant_hue; + } procamp; + + union { + struct { + bool dither:1; + bool scaler:1; + bool procamp:1; + }; + u8 mask; + } set; +}; + struct nouveau_connector { struct drm_connector base; enum dcb_connector_type type; @@ -111,61 +166,6 @@ extern int nouveau_ignorelid; extern int nouveau_duallink; extern int nouveau_hdmimhz;
-#include <drm/drm_crtc.h> -#define nouveau_conn_atom(p) \ - container_of((p), struct nouveau_conn_atom, state) - -struct nouveau_conn_atom { - struct drm_connector_state state; - - struct { - /* The enum values specifically defined here match nv50/gf119 - * hw values, and the code relies on this. - */ - enum { - DITHERING_MODE_OFF = 0x00, - DITHERING_MODE_ON = 0x01, - DITHERING_MODE_DYNAMIC2X2 = 0x10 | DITHERING_MODE_ON, - DITHERING_MODE_STATIC2X2 = 0x18 | DITHERING_MODE_ON, - DITHERING_MODE_TEMPORAL = 0x20 | DITHERING_MODE_ON, - DITHERING_MODE_AUTO - } mode; - enum { - DITHERING_DEPTH_6BPC = 0x00, - DITHERING_DEPTH_8BPC = 0x02, - DITHERING_DEPTH_AUTO - } depth; - } dither; - - struct { - int mode; /* DRM_MODE_SCALE_* */ - struct { - enum { - UNDERSCAN_OFF, - UNDERSCAN_ON, - UNDERSCAN_AUTO, - } mode; - u32 hborder; - u32 vborder; - } underscan; - bool full; - } scaler; - - struct { - int color_vibrance; - int vibrant_hue; - } procamp; - - union { - struct { - bool dither:1; - bool scaler:1; - bool procamp:1; - }; - u8 mask; - } set; -}; - void nouveau_conn_attach_properties(struct drm_connector *); void nouveau_conn_reset(struct drm_connector *); struct drm_connector_state *
From: EJ Hsu ejh@nvidia.com
[ Upstream commit e5b5da96da50ef30abb39cb9f694e99366404d24 ]
Gadget driver should always use config_ep_by_speed() to initialize usb_ep struct according to usb device's operating speed. Otherwise, usb_ep struct may be wrong if usb devcie's operating speed is changed.
The key point in this patch is that we want to make sure the desc pointer in usb_ep struct will be set to NULL when gadget is disconnected. This will force it to call config_ep_by_speed() to correctly initialize usb_ep struct based on the new operating speed when gadget is re-connected later.
Reviewed-by: Peter Chen peter.chen@nxp.com Signed-off-by: EJ Hsu ejh@nvidia.com Signed-off-by: Felipe Balbi balbi@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/usb/gadget/function/f_ecm.c | 6 +++++- drivers/usb/gadget/function/f_rndis.c | 1 + 2 files changed, 6 insertions(+), 1 deletion(-)
diff --git a/drivers/usb/gadget/function/f_ecm.c b/drivers/usb/gadget/function/f_ecm.c index 6ce044008cf6c..460d5d7c984f5 100644 --- a/drivers/usb/gadget/function/f_ecm.c +++ b/drivers/usb/gadget/function/f_ecm.c @@ -621,8 +621,12 @@ static void ecm_disable(struct usb_function *f)
DBG(cdev, "ecm deactivated\n");
- if (ecm->port.in_ep->enabled) + if (ecm->port.in_ep->enabled) { gether_disconnect(&ecm->port); + } else { + ecm->port.in_ep->desc = NULL; + ecm->port.out_ep->desc = NULL; + }
usb_ep_disable(ecm->notify); ecm->notify->desc = NULL; diff --git a/drivers/usb/gadget/function/f_rndis.c b/drivers/usb/gadget/function/f_rndis.c index d48df36622b74..0d8e4a364ca6e 100644 --- a/drivers/usb/gadget/function/f_rndis.c +++ b/drivers/usb/gadget/function/f_rndis.c @@ -618,6 +618,7 @@ static void rndis_disable(struct usb_function *f) gether_disconnect(&rndis->port);
usb_ep_disable(rndis->notify); + rndis->notify->desc = NULL; }
/*-------------------------------------------------------------------------*/
From: Jens Axboe axboe@kernel.dk
[ Upstream commit ebfcd8955c0b52eb793bcbc9e71140e3d0cdb228 ]
The socket read/write helpers only look at the file O_NONBLOCK. not the iocb IOCB_NOWAIT flag. This breaks users like preadv2/pwritev2 and io_uring that rely on not having the file itself marked nonblocking, but rather the iocb itself.
Cc: netdev@vger.kernel.org Acked-by: David Miller davem@davemloft.net Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- net/socket.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/net/socket.c b/net/socket.c index 18d27b8c25116..1290aad5d1c35 100644 --- a/net/socket.c +++ b/net/socket.c @@ -867,7 +867,7 @@ static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to) .msg_iocb = iocb}; ssize_t res;
- if (file->f_flags & O_NONBLOCK) + if (file->f_flags & O_NONBLOCK || (iocb->ki_flags & IOCB_NOWAIT)) msg.msg_flags = MSG_DONTWAIT;
if (iocb->ki_pos != 0) @@ -892,7 +892,7 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from) if (iocb->ki_pos != 0) return -ESPIPE;
- if (file->f_flags & O_NONBLOCK) + if (file->f_flags & O_NONBLOCK || (iocb->ki_flags & IOCB_NOWAIT)) msg.msg_flags = MSG_DONTWAIT;
if (sock->type == SOCK_SEQPACKET)
From: David Howells dhowells@redhat.com
[ Upstream commit 1da4bd9f9d187f53618890d7b66b9628bbec3c70 ]
Fix the lookup method on the dynamic root directory such that creation calls, such as mkdir, open(O_CREAT), symlink, etc. fail with EOPNOTSUPP rather than failing with some odd error (such as EEXIST).
lookup() itself tries to create automount directories when it is invoked. These are cached locally in RAM and not committed to storage.
Signed-off-by: David Howells dhowells@redhat.com Reviewed-by: Marc Dionne marc.dionne@auristor.com Tested-by: Jonathan Billings jsbillings@jsbillings.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/afs/dynroot.c | 3 +++ 1 file changed, 3 insertions(+)
diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c index f29c6dade7f62..069273a2483f9 100644 --- a/fs/afs/dynroot.c +++ b/fs/afs/dynroot.c @@ -145,6 +145,9 @@ static struct dentry *afs_dynroot_lookup(struct inode *dir, struct dentry *dentr
ASSERTCMP(d_inode(dentry), ==, NULL);
+ if (flags & LOOKUP_CREATE) + return ERR_PTR(-EOPNOTSUPP); + if (dentry->d_name.len >= AFSNAMEMAX) { _leave(" = -ENAMETOOLONG"); return ERR_PTR(-ENAMETOOLONG);
From: Zhiqiang Liu liuzhiqiang26@huawei.com
[ Upstream commit 028288df635f5a9addd48ac4677b720192747944 ]
In raid1_sync_request func, rdev should be checked before reference.
Signed-off-by: Zhiqiang Liu liuzhiqiang26@huawei.com Signed-off-by: Song Liu songliubraving@fb.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/md/raid1.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 6800dcd50a11b..abcb4c3a76c18 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -2756,7 +2756,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr, write_targets++; } } - if (bio->bi_end_io) { + if (rdev && bio->bi_end_io) { atomic_inc(&rdev->nr_pending); bio->bi_iter.bi_sector = sector_nr + rdev->data_offset; bio_set_dev(bio, rdev->bdev);
From: Thomas Richter tmricht@linux.ibm.com
[ Upstream commit 39d4a501a9ef55c57b51e3ef07fc2aeed7f30b3b ]
Function perf_event_ever_overflow() and perf_event_account_interrupt() are called every time samples are processed by the interrupt handler. However function perf_event_account_interrupt() has checks to avoid being flooded with interrupts (more then 1000 samples are received per task_tick). Samples are then dropped and a PERF_RECORD_THROTTLED is added to the perf data. The perf subsystem limit calculation is:
maximum sample frequency := 100000 --> 1 samples per 10 us task_tick = 10ms = 10000us --> 1000 samples per task_tick
The work flow is
measurement_alert() uses SDBT head and each SBDT points to 511 SDB pages, each with 126 sample entries. After processing 8 SBDs and for each valid sample calling:
perf_event_overflow() perf_event_account_interrupts()
there is a considerable amount of samples being dropped, especially when the sample frequency is very high and near the 100000 limit.
To avoid the high amount of samples being dropped near the end of a task_tick time frame, increment the sampling interval in case of dropped events. The CPU Measurement sampling facility on the s390 supports only intervals, specifiing how many CPU cycles have to be executed before a sample is generated. Increase the interval when the samples being generated hit the task_tick limit.
Signed-off-by: Thomas Richter tmricht@linux.ibm.com Signed-off-by: Vasily Gorbik gor@linux.ibm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/s390/kernel/perf_cpum_sf.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+)
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index df92c2af99b69..0b09585305521 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -1260,6 +1260,22 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all) if (sampl_overflow) OVERFLOW_REG(hwc) = DIV_ROUND_UP(OVERFLOW_REG(hwc) + sampl_overflow, 1 + num_sdb); + + /* Perf_event_overflow() and perf_event_account_interrupt() limit + * the interrupt rate to an upper limit. Roughly 1000 samples per + * task tick. + * Hitting this limit results in a large number + * of throttled REF_REPORT_THROTTLE entries and the samples + * are dropped. + * Slightly increase the interval to avoid hitting this limit. + */ + if (event_overflow) { + SAMPL_RATE(hwc) += DIV_ROUND_UP(SAMPL_RATE(hwc), 10); + debug_sprintf_event(sfdbg, 1, "%s: rate adjustment %ld\n", + __func__, + DIV_ROUND_UP(SAMPL_RATE(hwc), 10)); + } + if (sampl_overflow || event_overflow) debug_sprintf_event(sfdbg, 4, "hw_perf_event_update: " "overflow stats: sample=%llu event=%llu\n",
From: Thomas Richter tmricht@linux.ibm.com
[ Upstream commit 0539ad0b22877225095d8adef0c376f52cc23834 ]
The s390 CPU Measurement sampling facility has an overflow condition which fires when all entries in a SBD are used. The measurement alert interrupt is triggered and reads out all samples in this SDB. It then tests the successor SDB, if this SBD is not full, the interrupt handler does not read any samples at all from this SDB The design waits for the hardware to fill this SBD and then trigger another meassurement alert interrupt.
This scheme works nicely until an perf_event_overflow() function call discards the sample due to a too high sampling rate. The interrupt handler has logic to read out a partially filled SDB when the perf event overflow condition in linux common code is met. This causes the CPUM sampling measurement hardware and the PMU device driver to operate on the same SBD's trailer entry. This should not happen.
This can be seen here using this trace: cpumsf_pmu_add: tear:0xb5286000 hw_perf_event_update: sdbt 0xb5286000 full 1 over 0 flush_all:0 hw_perf_event_update: sdbt 0xb5286008 full 0 over 0 flush_all:0 above shows 1. interrupt hw_perf_event_update: sdbt 0xb5286008 full 1 over 0 flush_all:0 hw_perf_event_update: sdbt 0xb5286008 full 0 over 0 flush_all:0 above shows 2. interrupt ... this goes on fine until... hw_perf_event_update: sdbt 0xb5286068 full 1 over 0 flush_all:0 perf_push_sample1: overflow one or more samples read from the IRQ handler are rejected by perf_event_overflow() and the IRQ handler advances to the next SDB and modifies the trailer entry of a partially filled SDB. hw_perf_event_update: sdbt 0xb5286070 full 0 over 0 flush_all:1 timestamp: 14:32:52.519953
Next time the IRQ handler is called for this SDB the trailer entry shows an overflow count of 19 missed entries. hw_perf_event_update: sdbt 0xb5286070 full 1 over 19 flush_all:1 timestamp: 14:32:52.970058
Remove access to a follow on SDB when event overflow happened.
Signed-off-by: Thomas Richter tmricht@linux.ibm.com Signed-off-by: Vasily Gorbik gor@linux.ibm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/s390/kernel/perf_cpum_sf.c | 6 ------ 1 file changed, 6 deletions(-)
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 0b09585305521..8ba440ba84624 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -1248,12 +1248,6 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all) */ if (flush_all && done) break; - - /* If an event overflow happened, discard samples by - * processing any remaining sample-data-blocks. - */ - if (event_overflow) - flush_all = 1; }
/* Account sample overflows in the event hardware structure */
From: Parav Pandit parav@mellanox.com
[ Upstream commit 89f988d93c62384758b19323c886db917a80c371 ]
Current code device add sequence is:
ib_register_device() ib_mad_init() init_sriov_init() register_netdev_notifier()
Therefore, the remove sequence should be,
unregister_netdev_notifier() close_sriov() mad_cleanup() ib_unregister_device()
However it is not above. Hence, make do above remove sequence.
Fixes: fa417f7b520ee ("IB/mlx4: Add support for IBoE") Signed-off-by: Parav Pandit parav@mellanox.com Reviewed-by: Maor Gottlieb maorg@mellanox.com Signed-off-by: Leon Romanovsky leonro@mellanox.com Link: https://lore.kernel.org/r/20191212091214.315005-3-leon@kernel.org Signed-off-by: Doug Ledford dledford@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/hw/mlx4/main.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 0bbeaaae47e07..9386bb57b3d71 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -3069,16 +3069,17 @@ static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr) ibdev->ib_active = false; flush_workqueue(wq);
- mlx4_ib_close_sriov(ibdev); - mlx4_ib_mad_cleanup(ibdev); - ib_unregister_device(&ibdev->ib_dev); - mlx4_ib_diag_cleanup(ibdev); if (ibdev->iboe.nb.notifier_call) { if (unregister_netdevice_notifier(&ibdev->iboe.nb)) pr_warn("failure unregistering notifier\n"); ibdev->iboe.nb.notifier_call = NULL; }
+ mlx4_ib_close_sriov(ibdev); + mlx4_ib_mad_cleanup(ibdev); + ib_unregister_device(&ibdev->ib_dev); + mlx4_ib_diag_cleanup(ibdev); + mlx4_qp_release_range(dev, ibdev->steer_qpn_base, ibdev->steer_qpn_count); kfree(ibdev->ib_uc_qpns_bitmap);
From: Maor Gottlieb maorg@mellanox.com
[ Upstream commit ed9085fed9d95d5921582e3c8474f3736c5d2782 ]
There are two flow rule destinations: QP and packet. While users are setting DROP packet rule, the QP should not be set as a destination.
Fixes: 3b3233fbf02e ("IB/mlx5: Add flow counters binding support") Signed-off-by: Maor Gottlieb maorg@mellanox.com Reviewed-by: Raed Salem raeds@mellanox.com Signed-off-by: Leon Romanovsky leonro@mellanox.com Link: https://lore.kernel.org/r/20191212091214.315005-4-leon@kernel.org Signed-off-by: Doug Ledford dledford@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/hw/mlx5/main.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-)
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index f4ffdc588ea07..df5be462dd281 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -3286,10 +3286,6 @@ static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev, }
INIT_LIST_HEAD(&handler->list); - if (dst) { - memcpy(&dest_arr[0], dst, sizeof(*dst)); - dest_num++; - }
for (spec_index = 0; spec_index < flow_attr->num_of_specs; spec_index++) { err = parse_flow_attr(dev->mdev, spec->match_criteria, @@ -3303,6 +3299,11 @@ static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev, ib_flow += ((union ib_flow_spec *)ib_flow)->size; }
+ if (dst && !(flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DROP)) { + memcpy(&dest_arr[0], dst, sizeof(*dst)); + dest_num++; + } + if (!flow_is_multicast_only(flow_attr)) set_underlay_qp(dev, spec, underlay_qpn);
@@ -3340,10 +3341,8 @@ static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev, }
if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DROP) { - if (!(flow_act.action & MLX5_FLOW_CONTEXT_ACTION_COUNT)) { + if (!dest_num) rule_dst = NULL; - dest_num = 0; - } } else { if (is_egress) flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_ALLOW;
From: Paul Durrant pdurrant@amazon.com
[ Upstream commit fa2ac657f9783f0891b2935490afe9a7fd29d3fa ]
Objects allocated by xen_blkif_alloc come from the 'blkif_cache' kmem cache. This cache is destoyed when xen-blkif is unloaded so it is necessary to wait for the deferred free routine used for such objects to complete. This necessity was missed in commit 14855954f636 "xen-blkback: allow module to be cleanly unloaded". This patch fixes the problem by taking/releasing extra module references in xen_blkif_alloc/free() respectively.
Signed-off-by: Paul Durrant pdurrant@amazon.com Reviewed-by: Roger Pau Monné roger.pau@citrix.com Signed-off-by: Juergen Gross jgross@suse.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/block/xen-blkback/xenbus.c | 10 ++++++++++ 1 file changed, 10 insertions(+)
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c index 55869b362fdfb..25c41ce070a7f 100644 --- a/drivers/block/xen-blkback/xenbus.c +++ b/drivers/block/xen-blkback/xenbus.c @@ -179,6 +179,15 @@ static struct xen_blkif *xen_blkif_alloc(domid_t domid) blkif->domid = domid; atomic_set(&blkif->refcnt, 1); init_completion(&blkif->drain_complete); + + /* + * Because freeing back to the cache may be deferred, it is not + * safe to unload the module (and hence destroy the cache) until + * this has completed. To prevent premature unloading, take an + * extra module reference here and release only when the object + * has been freed back to the cache. + */ + __module_get(THIS_MODULE); INIT_WORK(&blkif->free_work, xen_blkif_deferred_free);
return blkif; @@ -328,6 +337,7 @@ static void xen_blkif_free(struct xen_blkif *blkif)
/* Make sure everything is drained before shutting down */ kmem_cache_free(xen_blkif_cachep, blkif); + module_put(THIS_MODULE); }
int __init xen_blkif_interface_init(void)
From: Juergen Gross jgross@suse.com
[ Upstream commit c673ec61ade89bf2f417960f986bc25671762efb ]
When CONFIG_XEN_BALLOON_MEMORY_HOTPLUG is not defined reserve_additional_memory() will set balloon_stats.target_pages to a wrong value in case there are still some ballooned pages allocated via alloc_xenballooned_pages().
This will result in balloon_process() no longer be triggered when ballooned pages are freed in batches.
Reported-by: Nicholas Tsirakis niko.tsirakis@gmail.com Signed-off-by: Juergen Gross jgross@suse.com Reviewed-by: Boris Ostrovsky boris.ostrovsky@oracle.com Signed-off-by: Juergen Gross jgross@suse.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/xen/balloon.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index 747a15acbce37..6fa7209f24f43 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -395,7 +395,8 @@ static struct notifier_block xen_memory_nb = { #else static enum bp_state reserve_additional_memory(void) { - balloon_stats.target_pages = balloon_stats.current_pages; + balloon_stats.target_pages = balloon_stats.current_pages + + balloon_stats.target_unpopulated; return BP_ECANCELED; } #endif /* CONFIG_XEN_BALLOON_MEMORY_HOTPLUG */
From: Andy Whitcroft apw@canonical.com
[ Upstream commit da6043fe85eb5ec621e34a92540735dcebbea134 ]
When looking for a bit by number we make use of the cached result from the preceding lookup to speed up operation. Firstly we check if the requested pfn is within the cached zone and if not lookup the new zone. We then check if the offset for that pfn falls within the existing cached node. This happens regardless of whether the node is within the zone we are now scanning. With certain memory layouts it is possible for this to false trigger creating a temporary alias for the pfn to a different bit. This leads the hibernation code to free memory which it was never allocated with the expected fallout.
Ensure the zone we are scanning matches the cached zone before considering the cached node.
Deep thanks go to Andrea for many, many, many hours of hacking and testing that went into cornering this bug.
Reported-by: Andrea Righi andrea.righi@canonical.com Tested-by: Andrea Righi andrea.righi@canonical.com Signed-off-by: Andy Whitcroft apw@canonical.com Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/power/snapshot.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 3d37c279c0900..f2635fc751d93 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -736,8 +736,15 @@ static int memory_bm_find_bit(struct memory_bitmap *bm, unsigned long pfn, * We have found the zone. Now walk the radix tree to find the leaf node * for our PFN. */ + + /* + * If the zone we wish to scan is the the current zone and the + * pfn falls into the current node then we do not need to walk + * the tree. + */ node = bm->cur.node; - if (((pfn - zone->start_pfn) & ~BM_BLOCK_MASK) == bm->cur.node_pfn) + if (zone == bm->cur.zone && + ((pfn - zone->start_pfn) & ~BM_BLOCK_MASK) == bm->cur.node_pfn) goto node_found;
node = zone->rtree;
linux-stable-mirror@lists.linaro.org
-
Sasha Levin