* [PATCH 1/1] cxl/events: Bound the event log drain loop [not found] <cover.1787768932.git.anisa.su@samsung.com> @ 2026-08-26 18:43 ` Anisa Su 2026-08-26 21:28 ` Cheatham, Benjamin 2026-08-27 3:01 ` Richard Cheng 0 siblings, 2 replies; 5+ messages in thread From: Anisa Su @ 2026-08-26 18:43 UTC (permalink / raw) To: linux-cxl Cc: Davidlohr Bueso, Jonathan Cameron, Gregory Price, Dave Jiang, Alison Schofield, Vishal Verma, Anisa Su, stable cxl_event_thread() drains every log named in the Event Status register and repeats until that register reads zero. CXL 8.2.9.3.1 Table 8-203 marks the register RO and leaves clearing it to the device, so a misbehaving device that leaves a status bit set spins the thread forever, resending Get Event Records as fast as the mailbox completes. Bound the loop on work completed instead. cxl_mem_get_records_log() and cxl_mem_get_event_records() report failures and which logs returned records; the thread stops on the first error and drops any log whose status bit was set while it returned nothing. Every pass either drains a record or clears a bit from the mask, so the loop terminates whatever the device reports. Logs are drained best effort, so a broken one does not suppress reporting from the rest. Fixes: a49aa8141b65 ("cxl/mem: Wire up event interrupts") Cc: <stable@vger.kernel.org> Signed-off-by: Anisa Su <anisa.su@samsung.com> --- drivers/cxl/core/mbox.c | 58 ++++++++++++++++++++++++++++-------- drivers/cxl/cxlmem.h | 3 +- drivers/cxl/pci.c | 39 +++++++++++++++++++----- tools/testing/cxl/test/mem.c | 4 +-- 4 files changed, 81 insertions(+), 23 deletions(-) diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index 7c6c5b7450a5..5954ba20f0be 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -1059,8 +1059,8 @@ static int cxl_clear_event_record(struct cxl_memdev_state *mds, return rc; } -static void cxl_mem_get_records_log(struct cxl_memdev_state *mds, - enum cxl_event_log_type type) +static int cxl_mem_get_records_log(struct cxl_memdev_state *mds, + enum cxl_event_log_type type, bool *drained) { struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; struct cxl_memdev *cxlmd = mds->cxlds.cxlmd; @@ -1068,12 +1068,15 @@ static void cxl_mem_get_records_log(struct cxl_memdev_state *mds, struct cxl_get_event_payload *payload; u8 log_type = type; u16 nr_rec; + int rc = 0; + + *drained = false; mutex_lock(&mds->event.log_lock); payload = mds->event.buf; do { - int rc, i; + int i; struct cxl_mbox_cmd mbox_cmd = (struct cxl_mbox_cmd) { .opcode = CXL_MBOX_OP_GET_EVENT_RECORD, .payload_in = &log_type, @@ -1094,6 +1097,7 @@ static void cxl_mem_get_records_log(struct cxl_memdev_state *mds, nr_rec = le16_to_cpu(payload->record_count); if (!nr_rec) break; + *drained = true; for (i = 0; i < nr_rec; i++) __cxl_event_trace_record(cxlmd, type, @@ -1112,31 +1116,59 @@ static void cxl_mem_get_records_log(struct cxl_memdev_state *mds, } while (nr_rec); mutex_unlock(&mds->event.log_lock); + + return rc; } /** * cxl_mem_get_event_records - Get Event Records from the device * @mds: The driver data for the operation * @status: Event Status register value identifying which events are available. + * @drained: Optional mask of the logs in @status that returned records. * * Retrieve all event records available on the device, report them as trace - * events, and clear them. + * events, and clear them. Every log named in @status is drained even if + * another one fails, so that a broken log does not suppress reporting from + * the rest. + * + * Return: 0, or the first error encountered. * * See CXL rev 3.0 @8.2.9.2.2 Get Event Records * See CXL rev 3.0 @8.2.9.2.3 Clear Event Records */ -void cxl_mem_get_event_records(struct cxl_memdev_state *mds, u32 status) +int cxl_mem_get_event_records(struct cxl_memdev_state *mds, u32 status, + u32 *drained) { + static const struct { + u32 status; + enum cxl_event_log_type type; + } logs[] = { + { CXLDEV_EVENT_STATUS_FATAL, CXL_EVENT_TYPE_FATAL }, + { CXLDEV_EVENT_STATUS_FAIL, CXL_EVENT_TYPE_FAIL }, + { CXLDEV_EVENT_STATUS_WARN, CXL_EVENT_TYPE_WARN }, + { CXLDEV_EVENT_STATUS_INFO, CXL_EVENT_TYPE_INFO }, + }; + int ret = 0; + dev_dbg(mds->cxlds.dev, "Reading event logs: %x\n", status); - if (status & CXLDEV_EVENT_STATUS_FATAL) - cxl_mem_get_records_log(mds, CXL_EVENT_TYPE_FATAL); - if (status & CXLDEV_EVENT_STATUS_FAIL) - cxl_mem_get_records_log(mds, CXL_EVENT_TYPE_FAIL); - if (status & CXLDEV_EVENT_STATUS_WARN) - cxl_mem_get_records_log(mds, CXL_EVENT_TYPE_WARN); - if (status & CXLDEV_EVENT_STATUS_INFO) - cxl_mem_get_records_log(mds, CXL_EVENT_TYPE_INFO); + if (drained) + *drained = 0; + + for (int i = 0; i < ARRAY_SIZE(logs); i++) { + bool got_records; + int rc; + + if (!(status & logs[i].status)) + continue; + + rc = cxl_mem_get_records_log(mds, logs[i].type, &got_records); + if (got_records && drained) + *drained |= logs[i].status; + ret = ret ?: rc; + } + + return ret; } EXPORT_SYMBOL_NS_GPL(cxl_mem_get_event_records, "CXL"); diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index ed419d0c59f2..cb5372eb2d85 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -803,7 +803,8 @@ void set_exclusive_cxl_commands(struct cxl_memdev_state *mds, unsigned long *cmds); void clear_exclusive_cxl_commands(struct cxl_memdev_state *mds, unsigned long *cmds); -void cxl_mem_get_event_records(struct cxl_memdev_state *mds, u32 status); +int cxl_mem_get_event_records(struct cxl_memdev_state *mds, u32 status, + u32 *drained); void cxl_event_trace_record(struct cxl_memdev *cxlmd, enum cxl_event_log_type type, enum cxl_event_type event_type, diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index 267c679b0b3c..3daf17835c06 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -514,21 +514,46 @@ static irqreturn_t cxl_event_thread(int irq, void *id) struct cxl_dev_id *dev_id = id; struct cxl_dev_state *cxlds = dev_id->cxlds; struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds); - u32 status; + u32 mask = CXLDEV_EVENT_STATUS_ALL; + + while (mask) { + u32 status, drained, stuck; + int rc; - do { /* * CXL 3.0 8.2.8.3.1: The lower 32 bits are the status; * ignore the reserved upper 32 bits */ status = readl(cxlds->regs.status + CXLDEV_DEV_EVENT_STATUS_OFFSET); - /* Ignore logs unknown to the driver */ - status &= CXLDEV_EVENT_STATUS_ALL; + /* Ignore logs unknown to the driver, and logs given up on */ + status &= mask; if (!status) break; - cxl_mem_get_event_records(mds, status); + + /* + * A failed drain leaves the log's status bit set, so another + * pass would resend the same query forever. + */ + rc = cxl_mem_get_event_records(mds, status, &drained); + if (rc) + break; + + /* + * The Event Status register is device owned and read only, so + * it cannot bound this loop; records read can. A device that + * leaves a bit set with an empty log makes no progress, and + * only the device can clear that state, so stop polling that + * log rather than spin on it. + */ + stuck = status & ~drained; + if (stuck) { + dev_warn_once(cxlds->dev, + "Event status %#x set with no records to read\n", + stuck); + mask &= ~stuck; + } cond_resched(); - } while (status); + } return IRQ_HANDLED; } @@ -682,7 +707,7 @@ static int cxl_event_config(struct pci_host_bridge *host_bridge, if (rc) return rc; - cxl_mem_get_event_records(mds, CXLDEV_EVENT_STATUS_ALL); + cxl_mem_get_event_records(mds, CXLDEV_EVENT_STATUS_ALL, NULL); return 0; } diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c index a7da279aa3ef..87e01612cea9 100644 --- a/tools/testing/cxl/test/mem.c +++ b/tools/testing/cxl/test/mem.c @@ -372,7 +372,7 @@ static void cxl_mock_event_trigger(struct device *dev) event_reset_log(log); } - cxl_mem_get_event_records(mdata->mds, mes->ev_status); + cxl_mem_get_event_records(mdata->mds, mes->ev_status, NULL); } struct cxl_event_record_raw maint_needed = { @@ -1805,7 +1805,7 @@ static int cxl_mock_mem_probe(struct platform_device *pdev) if (rc) dev_dbg(dev, "No CXL FWCTL setup\n"); - cxl_mem_get_event_records(mds, CXLDEV_EVENT_STATUS_ALL); + cxl_mem_get_event_records(mds, CXLDEV_EVENT_STATUS_ALL, NULL); cxl_mock_test_feat_init(mdata); return 0; -- 2.43.0 ^ permalink raw reply related [flat|nested] 5+ messages in thread
* Re: [PATCH 1/1] cxl/events: Bound the event log drain loop 2026-08-26 18:43 ` [PATCH 1/1] cxl/events: Bound the event log drain loop Anisa Su @ 2026-08-26 21:28 ` Cheatham, Benjamin 2026-08-27 18:05 ` Anisa Su 2026-08-27 3:01 ` Richard Cheng 1 sibling, 1 reply; 5+ messages in thread From: Cheatham, Benjamin @ 2026-08-26 21:28 UTC (permalink / raw) To: Anisa Su, linux-cxl Cc: Davidlohr Bueso, Jonathan Cameron, Gregory Price, Dave Jiang, Alison Schofield, Vishal Verma, Anisa Su, stable On 8/26/2026 1:43 PM, Anisa Su wrote: > cxl_event_thread() drains every log named in the Event Status register and > repeats until that register reads zero. CXL 8.2.9.3.1 Table 8-203 marks > the register RO and leaves clearing it to the device, so a misbehaving device > that leaves a status bit set spins the thread forever, resending > Get Event Records as fast as the mailbox completes. > > Bound the loop on work completed instead. cxl_mem_get_records_log() and > cxl_mem_get_event_records() report failures and which logs returned > records; the thread stops on the first error and drops any log whose status > bit was set while it returned nothing. Every pass either drains a record > or clears a bit from the mask, so the loop terminates whatever the device > reports. Logs are drained best effort, so a broken one does not suppress > reporting from the rest. > > Fixes: a49aa8141b65 ("cxl/mem: Wire up event interrupts") > Cc: <stable@vger.kernel.org> > Signed-off-by: Anisa Su <anisa.su@samsung.com> > --- One nit below, but looks good to me regardless so: Reviewed-by: Ben Cheatham <benjamin.cheatham@amd.com> > drivers/cxl/core/mbox.c | 58 ++++++++++++++++++++++++++++-------- > drivers/cxl/cxlmem.h | 3 +- > drivers/cxl/pci.c | 39 +++++++++++++++++++----- > tools/testing/cxl/test/mem.c | 4 +-- > 4 files changed, 81 insertions(+), 23 deletions(-) > > diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c > index 7c6c5b7450a5..5954ba20f0be 100644 > --- a/drivers/cxl/core/mbox.c > +++ b/drivers/cxl/core/mbox.c > @@ -1059,8 +1059,8 @@ static int cxl_clear_event_record(struct cxl_memdev_state *mds, > return rc; > } > > -static void cxl_mem_get_records_log(struct cxl_memdev_state *mds, > - enum cxl_event_log_type type) > +static int cxl_mem_get_records_log(struct cxl_memdev_state *mds, > + enum cxl_event_log_type type, bool *drained) Nit: Could this get renamed from "drained" to "got_records"? You use that name below when calling this function and there's a bit of overloading of the name drained in this call path that makes it a tad confusing. Thanks, Ben > { > struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; > struct cxl_memdev *cxlmd = mds->cxlds.cxlmd; > @@ -1068,12 +1068,15 @@ static void cxl_mem_get_records_log(struct cxl_memdev_state *mds, > struct cxl_get_event_payload *payload; > u8 log_type = type; > u16 nr_rec; > + int rc = 0; > + > + *drained = false; > > mutex_lock(&mds->event.log_lock); > payload = mds->event.buf; > > do { > - int rc, i; > + int i; > struct cxl_mbox_cmd mbox_cmd = (struct cxl_mbox_cmd) { > .opcode = CXL_MBOX_OP_GET_EVENT_RECORD, > .payload_in = &log_type, > @@ -1094,6 +1097,7 @@ static void cxl_mem_get_records_log(struct cxl_memdev_state *mds, > nr_rec = le16_to_cpu(payload->record_count); > if (!nr_rec) > break; > + *drained = true; > > for (i = 0; i < nr_rec; i++) > __cxl_event_trace_record(cxlmd, type, > @@ -1112,31 +1116,59 @@ static void cxl_mem_get_records_log(struct cxl_memdev_state *mds, > } while (nr_rec); > > mutex_unlock(&mds->event.log_lock); > + > + return rc; > } > > /** > * cxl_mem_get_event_records - Get Event Records from the device > * @mds: The driver data for the operation > * @status: Event Status register value identifying which events are available. > + * @drained: Optional mask of the logs in @status that returned records. > * > * Retrieve all event records available on the device, report them as trace > - * events, and clear them. > + * events, and clear them. Every log named in @status is drained even if > + * another one fails, so that a broken log does not suppress reporting from > + * the rest. > + * > + * Return: 0, or the first error encountered. > * > * See CXL rev 3.0 @8.2.9.2.2 Get Event Records > * See CXL rev 3.0 @8.2.9.2.3 Clear Event Records > */ > -void cxl_mem_get_event_records(struct cxl_memdev_state *mds, u32 status) > +int cxl_mem_get_event_records(struct cxl_memdev_state *mds, u32 status, > + u32 *drained) > { > + static const struct { > + u32 status; > + enum cxl_event_log_type type; > + } logs[] = { > + { CXLDEV_EVENT_STATUS_FATAL, CXL_EVENT_TYPE_FATAL }, > + { CXLDEV_EVENT_STATUS_FAIL, CXL_EVENT_TYPE_FAIL }, > + { CXLDEV_EVENT_STATUS_WARN, CXL_EVENT_TYPE_WARN }, > + { CXLDEV_EVENT_STATUS_INFO, CXL_EVENT_TYPE_INFO }, > + }; > + int ret = 0; > + > dev_dbg(mds->cxlds.dev, "Reading event logs: %x\n", status); > > - if (status & CXLDEV_EVENT_STATUS_FATAL) > - cxl_mem_get_records_log(mds, CXL_EVENT_TYPE_FATAL); > - if (status & CXLDEV_EVENT_STATUS_FAIL) > - cxl_mem_get_records_log(mds, CXL_EVENT_TYPE_FAIL); > - if (status & CXLDEV_EVENT_STATUS_WARN) > - cxl_mem_get_records_log(mds, CXL_EVENT_TYPE_WARN); > - if (status & CXLDEV_EVENT_STATUS_INFO) > - cxl_mem_get_records_log(mds, CXL_EVENT_TYPE_INFO); > + if (drained) > + *drained = 0; > + > + for (int i = 0; i < ARRAY_SIZE(logs); i++) { > + bool got_records; > + int rc; > + > + if (!(status & logs[i].status)) > + continue; > + > + rc = cxl_mem_get_records_log(mds, logs[i].type, &got_records); > + if (got_records && drained) > + *drained |= logs[i].status; > + ret = ret ?: rc; > + } > + > + return ret; > } > EXPORT_SYMBOL_NS_GPL(cxl_mem_get_event_records, "CXL"); > > diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h > index ed419d0c59f2..cb5372eb2d85 100644 > --- a/drivers/cxl/cxlmem.h > +++ b/drivers/cxl/cxlmem.h > @@ -803,7 +803,8 @@ void set_exclusive_cxl_commands(struct cxl_memdev_state *mds, > unsigned long *cmds); > void clear_exclusive_cxl_commands(struct cxl_memdev_state *mds, > unsigned long *cmds); > -void cxl_mem_get_event_records(struct cxl_memdev_state *mds, u32 status); > +int cxl_mem_get_event_records(struct cxl_memdev_state *mds, u32 status, > + u32 *drained); > void cxl_event_trace_record(struct cxl_memdev *cxlmd, > enum cxl_event_log_type type, > enum cxl_event_type event_type, > diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c > index 267c679b0b3c..3daf17835c06 100644 > --- a/drivers/cxl/pci.c > +++ b/drivers/cxl/pci.c > @@ -514,21 +514,46 @@ static irqreturn_t cxl_event_thread(int irq, void *id) > struct cxl_dev_id *dev_id = id; > struct cxl_dev_state *cxlds = dev_id->cxlds; > struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds); > - u32 status; > + u32 mask = CXLDEV_EVENT_STATUS_ALL; > + > + while (mask) { > + u32 status, drained, stuck; > + int rc; > > - do { > /* > * CXL 3.0 8.2.8.3.1: The lower 32 bits are the status; > * ignore the reserved upper 32 bits > */ > status = readl(cxlds->regs.status + CXLDEV_DEV_EVENT_STATUS_OFFSET); > - /* Ignore logs unknown to the driver */ > - status &= CXLDEV_EVENT_STATUS_ALL; > + /* Ignore logs unknown to the driver, and logs given up on */ > + status &= mask; > if (!status) > break; > - cxl_mem_get_event_records(mds, status); > + > + /* > + * A failed drain leaves the log's status bit set, so another > + * pass would resend the same query forever. > + */ > + rc = cxl_mem_get_event_records(mds, status, &drained); > + if (rc) > + break; > + > + /* > + * The Event Status register is device owned and read only, so > + * it cannot bound this loop; records read can. A device that > + * leaves a bit set with an empty log makes no progress, and > + * only the device can clear that state, so stop polling that > + * log rather than spin on it. > + */ > + stuck = status & ~drained; > + if (stuck) { > + dev_warn_once(cxlds->dev, > + "Event status %#x set with no records to read\n", > + stuck); > + mask &= ~stuck; > + } > cond_resched(); > - } while (status); > + } > > return IRQ_HANDLED; > } > @@ -682,7 +707,7 @@ static int cxl_event_config(struct pci_host_bridge *host_bridge, > if (rc) > return rc; > > - cxl_mem_get_event_records(mds, CXLDEV_EVENT_STATUS_ALL); > + cxl_mem_get_event_records(mds, CXLDEV_EVENT_STATUS_ALL, NULL); > > return 0; > } > diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c > index a7da279aa3ef..87e01612cea9 100644 > --- a/tools/testing/cxl/test/mem.c > +++ b/tools/testing/cxl/test/mem.c > @@ -372,7 +372,7 @@ static void cxl_mock_event_trigger(struct device *dev) > event_reset_log(log); > } > > - cxl_mem_get_event_records(mdata->mds, mes->ev_status); > + cxl_mem_get_event_records(mdata->mds, mes->ev_status, NULL); > } > > struct cxl_event_record_raw maint_needed = { > @@ -1805,7 +1805,7 @@ static int cxl_mock_mem_probe(struct platform_device *pdev) > if (rc) > dev_dbg(dev, "No CXL FWCTL setup\n"); > > - cxl_mem_get_event_records(mds, CXLDEV_EVENT_STATUS_ALL); > + cxl_mem_get_event_records(mds, CXLDEV_EVENT_STATUS_ALL, NULL); > cxl_mock_test_feat_init(mdata); > > return 0; ^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [PATCH 1/1] cxl/events: Bound the event log drain loop 2026-08-26 21:28 ` Cheatham, Benjamin @ 2026-08-27 18:05 ` Anisa Su 0 siblings, 0 replies; 5+ messages in thread From: Anisa Su @ 2026-08-27 18:05 UTC (permalink / raw) To: Cheatham, Benjamin Cc: Anisa Su, linux-cxl, Davidlohr Bueso, Jonathan Cameron, Gregory Price, Dave Jiang, Alison Schofield, Vishal Verma, stable On Wed, Aug 26, 2026 at 04:28:49PM -0500, Cheatham, Benjamin wrote: > On 8/26/2026 1:43 PM, Anisa Su wrote: > > cxl_event_thread() drains every log named in the Event Status register and > > repeats until that register reads zero. CXL 8.2.9.3.1 Table 8-203 marks > > the register RO and leaves clearing it to the device, so a misbehaving device > > that leaves a status bit set spins the thread forever, resending > > Get Event Records as fast as the mailbox completes. > > > > Bound the loop on work completed instead. cxl_mem_get_records_log() and > > cxl_mem_get_event_records() report failures and which logs returned > > records; the thread stops on the first error and drops any log whose status > > bit was set while it returned nothing. Every pass either drains a record > > or clears a bit from the mask, so the loop terminates whatever the device > > reports. Logs are drained best effort, so a broken one does not suppress > > reporting from the rest. > > > > Fixes: a49aa8141b65 ("cxl/mem: Wire up event interrupts") > > Cc: <stable@vger.kernel.org> > > Signed-off-by: Anisa Su <anisa.su@samsung.com> > > --- > > One nit below, but looks good to me regardless so: > Reviewed-by: Ben Cheatham <benjamin.cheatham@amd.com> > > drivers/cxl/core/mbox.c | 58 ++++++++++++++++++++++++++++-------- > > drivers/cxl/cxlmem.h | 3 +- > > drivers/cxl/pci.c | 39 +++++++++++++++++++----- > > tools/testing/cxl/test/mem.c | 4 +-- > > 4 files changed, 81 insertions(+), 23 deletions(-) > > > > diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c > > index 7c6c5b7450a5..5954ba20f0be 100644 > > --- a/drivers/cxl/core/mbox.c > > +++ b/drivers/cxl/core/mbox.c > > @@ -1059,8 +1059,8 @@ static int cxl_clear_event_record(struct cxl_memdev_state *mds, > > return rc; > > } > > > > -static void cxl_mem_get_records_log(struct cxl_memdev_state *mds, > > - enum cxl_event_log_type type) > > +static int cxl_mem_get_records_log(struct cxl_memdev_state *mds, > > + enum cxl_event_log_type type, bool *drained) > > Nit: Could this get renamed from "drained" to "got_records"? You use that name below when calling > this function and there's a bit of overloading of the name drained in this call path that makes > it a tad confusing. > Yeah sure! Sorry I'm terrible at naming vars... > Thanks, > Ben Thanks, Anisa > > { > > struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; > > struct cxl_memdev *cxlmd = mds->cxlds.cxlmd; > > @@ -1068,12 +1068,15 @@ static void cxl_mem_get_records_log(struct cxl_memdev_state *mds, > > struct cxl_get_event_payload *payload; > > u8 log_type = type; > > u16 nr_rec; > > + int rc = 0; > > + > > + *drained = false; > > > > mutex_lock(&mds->event.log_lock); > > payload = mds->event.buf; > > > > do { > > - int rc, i; > > + int i; > > struct cxl_mbox_cmd mbox_cmd = (struct cxl_mbox_cmd) { > > .opcode = CXL_MBOX_OP_GET_EVENT_RECORD, > > .payload_in = &log_type, > > @@ -1094,6 +1097,7 @@ static void cxl_mem_get_records_log(struct cxl_memdev_state *mds, > > nr_rec = le16_to_cpu(payload->record_count); > > if (!nr_rec) > > break; > > + *drained = true; > > > > for (i = 0; i < nr_rec; i++) > > __cxl_event_trace_record(cxlmd, type, > > @@ -1112,31 +1116,59 @@ static void cxl_mem_get_records_log(struct cxl_memdev_state *mds, > > } while (nr_rec); > > > > mutex_unlock(&mds->event.log_lock); > > + > > + return rc; > > } > > > > /** > > * cxl_mem_get_event_records - Get Event Records from the device > > * @mds: The driver data for the operation > > * @status: Event Status register value identifying which events are available. > > + * @drained: Optional mask of the logs in @status that returned records. > > * > > * Retrieve all event records available on the device, report them as trace > > - * events, and clear them. > > + * events, and clear them. Every log named in @status is drained even if > > + * another one fails, so that a broken log does not suppress reporting from > > + * the rest. > > + * > > + * Return: 0, or the first error encountered. > > * > > * See CXL rev 3.0 @8.2.9.2.2 Get Event Records > > * See CXL rev 3.0 @8.2.9.2.3 Clear Event Records > > */ > > -void cxl_mem_get_event_records(struct cxl_memdev_state *mds, u32 status) > > +int cxl_mem_get_event_records(struct cxl_memdev_state *mds, u32 status, > > + u32 *drained) > > { > > + static const struct { > > + u32 status; > > + enum cxl_event_log_type type; > > + } logs[] = { > > + { CXLDEV_EVENT_STATUS_FATAL, CXL_EVENT_TYPE_FATAL }, > > + { CXLDEV_EVENT_STATUS_FAIL, CXL_EVENT_TYPE_FAIL }, > > + { CXLDEV_EVENT_STATUS_WARN, CXL_EVENT_TYPE_WARN }, > > + { CXLDEV_EVENT_STATUS_INFO, CXL_EVENT_TYPE_INFO }, > > + }; > > + int ret = 0; > > + > > dev_dbg(mds->cxlds.dev, "Reading event logs: %x\n", status); > > > > - if (status & CXLDEV_EVENT_STATUS_FATAL) > > - cxl_mem_get_records_log(mds, CXL_EVENT_TYPE_FATAL); > > - if (status & CXLDEV_EVENT_STATUS_FAIL) > > - cxl_mem_get_records_log(mds, CXL_EVENT_TYPE_FAIL); > > - if (status & CXLDEV_EVENT_STATUS_WARN) > > - cxl_mem_get_records_log(mds, CXL_EVENT_TYPE_WARN); > > - if (status & CXLDEV_EVENT_STATUS_INFO) > > - cxl_mem_get_records_log(mds, CXL_EVENT_TYPE_INFO); > > + if (drained) > > + *drained = 0; > > + > > + for (int i = 0; i < ARRAY_SIZE(logs); i++) { > > + bool got_records; > > + int rc; > > + > > + if (!(status & logs[i].status)) > > + continue; > > + > > + rc = cxl_mem_get_records_log(mds, logs[i].type, &got_records); > > + if (got_records && drained) > > + *drained |= logs[i].status; > > + ret = ret ?: rc; > > + } > > + > > + return ret; > > } > > EXPORT_SYMBOL_NS_GPL(cxl_mem_get_event_records, "CXL"); > > > > diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h > > index ed419d0c59f2..cb5372eb2d85 100644 > > --- a/drivers/cxl/cxlmem.h > > +++ b/drivers/cxl/cxlmem.h > > @@ -803,7 +803,8 @@ void set_exclusive_cxl_commands(struct cxl_memdev_state *mds, > > unsigned long *cmds); > > void clear_exclusive_cxl_commands(struct cxl_memdev_state *mds, > > unsigned long *cmds); > > -void cxl_mem_get_event_records(struct cxl_memdev_state *mds, u32 status); > > +int cxl_mem_get_event_records(struct cxl_memdev_state *mds, u32 status, > > + u32 *drained); > > void cxl_event_trace_record(struct cxl_memdev *cxlmd, > > enum cxl_event_log_type type, > > enum cxl_event_type event_type, > > diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c > > index 267c679b0b3c..3daf17835c06 100644 > > --- a/drivers/cxl/pci.c > > +++ b/drivers/cxl/pci.c > > @@ -514,21 +514,46 @@ static irqreturn_t cxl_event_thread(int irq, void *id) > > struct cxl_dev_id *dev_id = id; > > struct cxl_dev_state *cxlds = dev_id->cxlds; > > struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds); > > - u32 status; > > + u32 mask = CXLDEV_EVENT_STATUS_ALL; > > + > > + while (mask) { > > + u32 status, drained, stuck; > > + int rc; > > > > - do { > > /* > > * CXL 3.0 8.2.8.3.1: The lower 32 bits are the status; > > * ignore the reserved upper 32 bits > > */ > > status = readl(cxlds->regs.status + CXLDEV_DEV_EVENT_STATUS_OFFSET); > > - /* Ignore logs unknown to the driver */ > > - status &= CXLDEV_EVENT_STATUS_ALL; > > + /* Ignore logs unknown to the driver, and logs given up on */ > > + status &= mask; > > if (!status) > > break; > > - cxl_mem_get_event_records(mds, status); > > + > > + /* > > + * A failed drain leaves the log's status bit set, so another > > + * pass would resend the same query forever. > > + */ > > + rc = cxl_mem_get_event_records(mds, status, &drained); > > + if (rc) > > + break; > > + > > + /* > > + * The Event Status register is device owned and read only, so > > + * it cannot bound this loop; records read can. A device that > > + * leaves a bit set with an empty log makes no progress, and > > + * only the device can clear that state, so stop polling that > > + * log rather than spin on it. > > + */ > > + stuck = status & ~drained; > > + if (stuck) { > > + dev_warn_once(cxlds->dev, > > + "Event status %#x set with no records to read\n", > > + stuck); > > + mask &= ~stuck; > > + } > > cond_resched(); > > - } while (status); > > + } > > > > return IRQ_HANDLED; > > } > > @@ -682,7 +707,7 @@ static int cxl_event_config(struct pci_host_bridge *host_bridge, > > if (rc) > > return rc; > > > > - cxl_mem_get_event_records(mds, CXLDEV_EVENT_STATUS_ALL); > > + cxl_mem_get_event_records(mds, CXLDEV_EVENT_STATUS_ALL, NULL); > > > > return 0; > > } > > diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c > > index a7da279aa3ef..87e01612cea9 100644 > > --- a/tools/testing/cxl/test/mem.c > > +++ b/tools/testing/cxl/test/mem.c > > @@ -372,7 +372,7 @@ static void cxl_mock_event_trigger(struct device *dev) > > event_reset_log(log); > > } > > > > - cxl_mem_get_event_records(mdata->mds, mes->ev_status); > > + cxl_mem_get_event_records(mdata->mds, mes->ev_status, NULL); > > } > > > > struct cxl_event_record_raw maint_needed = { > > @@ -1805,7 +1805,7 @@ static int cxl_mock_mem_probe(struct platform_device *pdev) > > if (rc) > > dev_dbg(dev, "No CXL FWCTL setup\n"); > > > > - cxl_mem_get_event_records(mds, CXLDEV_EVENT_STATUS_ALL); > > + cxl_mem_get_event_records(mds, CXLDEV_EVENT_STATUS_ALL, NULL); > > cxl_mock_test_feat_init(mdata); > > > > return 0; > ^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [PATCH 1/1] cxl/events: Bound the event log drain loop 2026-08-26 18:43 ` [PATCH 1/1] cxl/events: Bound the event log drain loop Anisa Su 2026-08-26 21:28 ` Cheatham, Benjamin @ 2026-08-27 3:01 ` Richard Cheng 2026-08-27 22:25 ` Anisa Su 1 sibling, 1 reply; 5+ messages in thread From: Richard Cheng @ 2026-08-27 3:01 UTC (permalink / raw) To: Anisa Su Cc: linux-cxl, Davidlohr Bueso, Jonathan Cameron, Gregory Price, Dave Jiang, Alison Schofield, Vishal Verma, Anisa Su, stable On Wed, Aug 26, 2026 at 11:43:08AM +0800, Anisa Su wrote: > cxl_event_thread() drains every log named in the Event Status register and > repeats until that register reads zero. CXL 8.2.9.3.1 Table 8-203 marks > the register RO and leaves clearing it to the device, so a misbehaving device > that leaves a status bit set spins the thread forever, resending > Get Event Records as fast as the mailbox completes. > > Bound the loop on work completed instead. cxl_mem_get_records_log() and > cxl_mem_get_event_records() report failures and which logs returned > records; the thread stops on the first error and drops any log whose status > bit was set while it returned nothing. Every pass either drains a record > or clears a bit from the mask, so the loop terminates whatever the device > reports. Logs are drained best effort, so a broken one does not suppress > reporting from the rest. > > Fixes: a49aa8141b65 ("cxl/mem: Wire up event interrupts") > Cc: <stable@vger.kernel.org> > Signed-off-by: Anisa Su <anisa.su@samsung.com> > --- > drivers/cxl/core/mbox.c | 58 ++++++++++++++++++++++++++++-------- > drivers/cxl/cxlmem.h | 3 +- > drivers/cxl/pci.c | 39 +++++++++++++++++++----- > tools/testing/cxl/test/mem.c | 4 +-- > 4 files changed, 81 insertions(+), 23 deletions(-) > > diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c > index 7c6c5b7450a5..5954ba20f0be 100644 > --- a/drivers/cxl/core/mbox.c > +++ b/drivers/cxl/core/mbox.c > @@ -1059,8 +1059,8 @@ static int cxl_clear_event_record(struct cxl_memdev_state *mds, > return rc; > } > > -static void cxl_mem_get_records_log(struct cxl_memdev_state *mds, > - enum cxl_event_log_type type) > +static int cxl_mem_get_records_log(struct cxl_memdev_state *mds, > + enum cxl_event_log_type type, bool *drained) > { > struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; > struct cxl_memdev *cxlmd = mds->cxlds.cxlmd; > @@ -1068,12 +1068,15 @@ static void cxl_mem_get_records_log(struct cxl_memdev_state *mds, > struct cxl_get_event_payload *payload; > u8 log_type = type; > u16 nr_rec; > + int rc = 0; > + > + *drained = false; > > mutex_lock(&mds->event.log_lock); > payload = mds->event.buf; > > do { > - int rc, i; > + int i; > struct cxl_mbox_cmd mbox_cmd = (struct cxl_mbox_cmd) { > .opcode = CXL_MBOX_OP_GET_EVENT_RECORD, > .payload_in = &log_type, > @@ -1094,6 +1097,7 @@ static void cxl_mem_get_records_log(struct cxl_memdev_state *mds, > nr_rec = le16_to_cpu(payload->record_count); > if (!nr_rec) > break; > + *drained = true; > > for (i = 0; i < nr_rec; i++) > __cxl_event_trace_record(cxlmd, type, > @@ -1112,31 +1116,59 @@ static void cxl_mem_get_records_log(struct cxl_memdev_state *mds, > } while (nr_rec); > > mutex_unlock(&mds->event.log_lock); > + > + return rc; > } > > /** > * cxl_mem_get_event_records - Get Event Records from the device > * @mds: The driver data for the operation > * @status: Event Status register value identifying which events are available. > + * @drained: Optional mask of the logs in @status that returned records. > * > * Retrieve all event records available on the device, report them as trace > - * events, and clear them. > + * events, and clear them. Every log named in @status is drained even if > + * another one fails, so that a broken log does not suppress reporting from > + * the rest. > + * > + * Return: 0, or the first error encountered. > * > * See CXL rev 3.0 @8.2.9.2.2 Get Event Records > * See CXL rev 3.0 @8.2.9.2.3 Clear Event Records > */ > -void cxl_mem_get_event_records(struct cxl_memdev_state *mds, u32 status) > +int cxl_mem_get_event_records(struct cxl_memdev_state *mds, u32 status, > + u32 *drained) > { > + static const struct { > + u32 status; > + enum cxl_event_log_type type; > + } logs[] = { > + { CXLDEV_EVENT_STATUS_FATAL, CXL_EVENT_TYPE_FATAL }, > + { CXLDEV_EVENT_STATUS_FAIL, CXL_EVENT_TYPE_FAIL }, > + { CXLDEV_EVENT_STATUS_WARN, CXL_EVENT_TYPE_WARN }, > + { CXLDEV_EVENT_STATUS_INFO, CXL_EVENT_TYPE_INFO }, > + }; > + int ret = 0; > + > dev_dbg(mds->cxlds.dev, "Reading event logs: %x\n", status); > > - if (status & CXLDEV_EVENT_STATUS_FATAL) > - cxl_mem_get_records_log(mds, CXL_EVENT_TYPE_FATAL); > - if (status & CXLDEV_EVENT_STATUS_FAIL) > - cxl_mem_get_records_log(mds, CXL_EVENT_TYPE_FAIL); > - if (status & CXLDEV_EVENT_STATUS_WARN) > - cxl_mem_get_records_log(mds, CXL_EVENT_TYPE_WARN); > - if (status & CXLDEV_EVENT_STATUS_INFO) > - cxl_mem_get_records_log(mds, CXL_EVENT_TYPE_INFO); > + if (drained) > + *drained = 0; > + > + for (int i = 0; i < ARRAY_SIZE(logs); i++) { > + bool got_records; > + int rc; > + > + if (!(status & logs[i].status)) > + continue; > + > + rc = cxl_mem_get_records_log(mds, logs[i].type, &got_records); > + if (got_records && drained) > + *drained |= logs[i].status; > + ret = ret ?: rc; > + } > + > + return ret; > } > EXPORT_SYMBOL_NS_GPL(cxl_mem_get_event_records, "CXL"); > > diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h > index ed419d0c59f2..cb5372eb2d85 100644 > --- a/drivers/cxl/cxlmem.h > +++ b/drivers/cxl/cxlmem.h > @@ -803,7 +803,8 @@ void set_exclusive_cxl_commands(struct cxl_memdev_state *mds, > unsigned long *cmds); > void clear_exclusive_cxl_commands(struct cxl_memdev_state *mds, > unsigned long *cmds); > -void cxl_mem_get_event_records(struct cxl_memdev_state *mds, u32 status); > +int cxl_mem_get_event_records(struct cxl_memdev_state *mds, u32 status, > + u32 *drained); > void cxl_event_trace_record(struct cxl_memdev *cxlmd, > enum cxl_event_log_type type, > enum cxl_event_type event_type, > diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c > index 267c679b0b3c..3daf17835c06 100644 > --- a/drivers/cxl/pci.c > +++ b/drivers/cxl/pci.c > @@ -514,21 +514,46 @@ static irqreturn_t cxl_event_thread(int irq, void *id) > struct cxl_dev_id *dev_id = id; > struct cxl_dev_state *cxlds = dev_id->cxlds; > struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds); > - u32 status; > + u32 mask = CXLDEV_EVENT_STATUS_ALL; > + > + while (mask) { > + u32 status, drained, stuck; > + int rc; > > - do { > /* > * CXL 3.0 8.2.8.3.1: The lower 32 bits are the status; > * ignore the reserved upper 32 bits > */ > status = readl(cxlds->regs.status + CXLDEV_DEV_EVENT_STATUS_OFFSET); > - /* Ignore logs unknown to the driver */ > - status &= CXLDEV_EVENT_STATUS_ALL; > + /* Ignore logs unknown to the driver, and logs given up on */ > + status &= mask; > if (!status) > break; > - cxl_mem_get_event_records(mds, status); > + > + /* > + * A failed drain leaves the log's status bit set, so another > + * pass would resend the same query forever. > + */ > + rc = cxl_mem_get_event_records(mds, status, &drained); > + if (rc) > + break; > + Hi Anisa, IMHO, this new error path might leave an event log permanently undrainted. Now cxl_event_thread() breaks on any error returned by cxl_mem_get_event_records(), which incldues a temporary failure e.g. "Retry Required" from Get Event Records or Clear Event Records. In that case the log ramain non-empty. CXL event interrupt are generated when a log transitions from empty to non-empty, so after returning from the handler there may be no subsequent interrupt to retry the drain. Maybe we can use a bounded retry for retryable failure ? or schedule deferred retry work before returning ? Best regards, Richard Cheng. > + /* > + * The Event Status register is device owned and read only, so > + * it cannot bound this loop; records read can. A device that > + * leaves a bit set with an empty log makes no progress, and > + * only the device can clear that state, so stop polling that > + * log rather than spin on it. > + */ > + stuck = status & ~drained; > + if (stuck) { > + dev_warn_once(cxlds->dev, > + "Event status %#x set with no records to read\n", > + stuck); > + mask &= ~stuck; > + } > cond_resched(); > - } while (status); > + } > > return IRQ_HANDLED; > } > @@ -682,7 +707,7 @@ static int cxl_event_config(struct pci_host_bridge *host_bridge, > if (rc) > return rc; > > - cxl_mem_get_event_records(mds, CXLDEV_EVENT_STATUS_ALL); > + cxl_mem_get_event_records(mds, CXLDEV_EVENT_STATUS_ALL, NULL); > > return 0; > } > diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c > index a7da279aa3ef..87e01612cea9 100644 > --- a/tools/testing/cxl/test/mem.c > +++ b/tools/testing/cxl/test/mem.c > @@ -372,7 +372,7 @@ static void cxl_mock_event_trigger(struct device *dev) > event_reset_log(log); > } > > - cxl_mem_get_event_records(mdata->mds, mes->ev_status); > + cxl_mem_get_event_records(mdata->mds, mes->ev_status, NULL); > } > > struct cxl_event_record_raw maint_needed = { > @@ -1805,7 +1805,7 @@ static int cxl_mock_mem_probe(struct platform_device *pdev) > if (rc) > dev_dbg(dev, "No CXL FWCTL setup\n"); > > - cxl_mem_get_event_records(mds, CXLDEV_EVENT_STATUS_ALL); > + cxl_mem_get_event_records(mds, CXLDEV_EVENT_STATUS_ALL, NULL); > cxl_mock_test_feat_init(mdata); > > return 0; > -- > 2.43.0 > > ^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [PATCH 1/1] cxl/events: Bound the event log drain loop 2026-08-27 3:01 ` Richard Cheng @ 2026-08-27 22:25 ` Anisa Su 0 siblings, 0 replies; 5+ messages in thread From: Anisa Su @ 2026-08-27 22:25 UTC (permalink / raw) To: Richard Cheng Cc: Anisa Su, linux-cxl, Davidlohr Bueso, Jonathan Cameron, Gregory Price, Dave Jiang, Alison Schofield, Vishal Verma, benjamin.cheatham, stable On Thu, Aug 27, 2026 at 11:01:15AM +0800, Richard Cheng wrote: > On Wed, Aug 26, 2026 at 11:43:08AM +0800, Anisa Su wrote: > > cxl_event_thread() drains every log named in the Event Status register and > > repeats until that register reads zero. CXL 8.2.9.3.1 Table 8-203 marks > > the register RO and leaves clearing it to the device, so a misbehaving device > > that leaves a status bit set spins the thread forever, resending > > Get Event Records as fast as the mailbox completes. > > > > Bound the loop on work completed instead. cxl_mem_get_records_log() and > > cxl_mem_get_event_records() report failures and which logs returned > > records; the thread stops on the first error and drops any log whose status > > bit was set while it returned nothing. Every pass either drains a record > > or clears a bit from the mask, so the loop terminates whatever the device > > reports. Logs are drained best effort, so a broken one does not suppress > > reporting from the rest. > > > > Fixes: a49aa8141b65 ("cxl/mem: Wire up event interrupts") > > Cc: <stable@vger.kernel.org> > > Signed-off-by: Anisa Su <anisa.su@samsung.com> > > --- > > drivers/cxl/core/mbox.c | 58 ++++++++++++++++++++++++++++-------- > > drivers/cxl/cxlmem.h | 3 +- > > drivers/cxl/pci.c | 39 +++++++++++++++++++----- > > tools/testing/cxl/test/mem.c | 4 +-- > > 4 files changed, 81 insertions(+), 23 deletions(-) > > > > diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c > > index 7c6c5b7450a5..5954ba20f0be 100644 > > --- a/drivers/cxl/core/mbox.c > > +++ b/drivers/cxl/core/mbox.c > > @@ -1059,8 +1059,8 @@ static int cxl_clear_event_record(struct cxl_memdev_state *mds, > > return rc; > > } > > > > -static void cxl_mem_get_records_log(struct cxl_memdev_state *mds, > > - enum cxl_event_log_type type) > > +static int cxl_mem_get_records_log(struct cxl_memdev_state *mds, > > + enum cxl_event_log_type type, bool *drained) > > { > > struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; > > struct cxl_memdev *cxlmd = mds->cxlds.cxlmd; > > @@ -1068,12 +1068,15 @@ static void cxl_mem_get_records_log(struct cxl_memdev_state *mds, > > struct cxl_get_event_payload *payload; > > u8 log_type = type; > > u16 nr_rec; > > + int rc = 0; > > + > > + *drained = false; > > > > mutex_lock(&mds->event.log_lock); > > payload = mds->event.buf; > > > > do { > > - int rc, i; > > + int i; > > struct cxl_mbox_cmd mbox_cmd = (struct cxl_mbox_cmd) { > > .opcode = CXL_MBOX_OP_GET_EVENT_RECORD, > > .payload_in = &log_type, > > @@ -1094,6 +1097,7 @@ static void cxl_mem_get_records_log(struct cxl_memdev_state *mds, > > nr_rec = le16_to_cpu(payload->record_count); > > if (!nr_rec) > > break; > > + *drained = true; > > > > for (i = 0; i < nr_rec; i++) > > __cxl_event_trace_record(cxlmd, type, > > @@ -1112,31 +1116,59 @@ static void cxl_mem_get_records_log(struct cxl_memdev_state *mds, > > } while (nr_rec); > > > > mutex_unlock(&mds->event.log_lock); > > + > > + return rc; > > } > > > > /** > > * cxl_mem_get_event_records - Get Event Records from the device > > * @mds: The driver data for the operation > > * @status: Event Status register value identifying which events are available. > > + * @drained: Optional mask of the logs in @status that returned records. > > * > > * Retrieve all event records available on the device, report them as trace > > - * events, and clear them. > > + * events, and clear them. Every log named in @status is drained even if > > + * another one fails, so that a broken log does not suppress reporting from > > + * the rest. > > + * > > + * Return: 0, or the first error encountered. > > * > > * See CXL rev 3.0 @8.2.9.2.2 Get Event Records > > * See CXL rev 3.0 @8.2.9.2.3 Clear Event Records > > */ > > -void cxl_mem_get_event_records(struct cxl_memdev_state *mds, u32 status) > > +int cxl_mem_get_event_records(struct cxl_memdev_state *mds, u32 status, > > + u32 *drained) > > { > > + static const struct { > > + u32 status; > > + enum cxl_event_log_type type; > > + } logs[] = { > > + { CXLDEV_EVENT_STATUS_FATAL, CXL_EVENT_TYPE_FATAL }, > > + { CXLDEV_EVENT_STATUS_FAIL, CXL_EVENT_TYPE_FAIL }, > > + { CXLDEV_EVENT_STATUS_WARN, CXL_EVENT_TYPE_WARN }, > > + { CXLDEV_EVENT_STATUS_INFO, CXL_EVENT_TYPE_INFO }, > > + }; > > + int ret = 0; > > + > > dev_dbg(mds->cxlds.dev, "Reading event logs: %x\n", status); > > > > - if (status & CXLDEV_EVENT_STATUS_FATAL) > > - cxl_mem_get_records_log(mds, CXL_EVENT_TYPE_FATAL); > > - if (status & CXLDEV_EVENT_STATUS_FAIL) > > - cxl_mem_get_records_log(mds, CXL_EVENT_TYPE_FAIL); > > - if (status & CXLDEV_EVENT_STATUS_WARN) > > - cxl_mem_get_records_log(mds, CXL_EVENT_TYPE_WARN); > > - if (status & CXLDEV_EVENT_STATUS_INFO) > > - cxl_mem_get_records_log(mds, CXL_EVENT_TYPE_INFO); > > + if (drained) > > + *drained = 0; > > + > > + for (int i = 0; i < ARRAY_SIZE(logs); i++) { > > + bool got_records; > > + int rc; > > + > > + if (!(status & logs[i].status)) > > + continue; > > + > > + rc = cxl_mem_get_records_log(mds, logs[i].type, &got_records); > > + if (got_records && drained) > > + *drained |= logs[i].status; > > + ret = ret ?: rc; > > + } > > + > > + return ret; > > } > > EXPORT_SYMBOL_NS_GPL(cxl_mem_get_event_records, "CXL"); > > > > diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h > > index ed419d0c59f2..cb5372eb2d85 100644 > > --- a/drivers/cxl/cxlmem.h > > +++ b/drivers/cxl/cxlmem.h > > @@ -803,7 +803,8 @@ void set_exclusive_cxl_commands(struct cxl_memdev_state *mds, > > unsigned long *cmds); > > void clear_exclusive_cxl_commands(struct cxl_memdev_state *mds, > > unsigned long *cmds); > > -void cxl_mem_get_event_records(struct cxl_memdev_state *mds, u32 status); > > +int cxl_mem_get_event_records(struct cxl_memdev_state *mds, u32 status, > > + u32 *drained); > > void cxl_event_trace_record(struct cxl_memdev *cxlmd, > > enum cxl_event_log_type type, > > enum cxl_event_type event_type, > > diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c > > index 267c679b0b3c..3daf17835c06 100644 > > --- a/drivers/cxl/pci.c > > +++ b/drivers/cxl/pci.c > > @@ -514,21 +514,46 @@ static irqreturn_t cxl_event_thread(int irq, void *id) > > struct cxl_dev_id *dev_id = id; > > struct cxl_dev_state *cxlds = dev_id->cxlds; > > struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds); > > - u32 status; > > + u32 mask = CXLDEV_EVENT_STATUS_ALL; > > + > > + while (mask) { > > + u32 status, drained, stuck; > > + int rc; > > > > - do { > > /* > > * CXL 3.0 8.2.8.3.1: The lower 32 bits are the status; > > * ignore the reserved upper 32 bits > > */ > > status = readl(cxlds->regs.status + CXLDEV_DEV_EVENT_STATUS_OFFSET); > > - /* Ignore logs unknown to the driver */ > > - status &= CXLDEV_EVENT_STATUS_ALL; > > + /* Ignore logs unknown to the driver, and logs given up on */ > > + status &= mask; > > if (!status) > > break; > > - cxl_mem_get_event_records(mds, status); > > + > > + /* > > + * A failed drain leaves the log's status bit set, so another > > + * pass would resend the same query forever. > > + */ > > + rc = cxl_mem_get_event_records(mds, status, &drained); > > + if (rc) > > + break; > > + > > Hi Anisa, > > IMHO, this new error path might leave an event log permanently undrainted. > > Now cxl_event_thread() breaks on any error returned by cxl_mem_get_event_records(), which incldues a temporary failure e.g. "Retry Required" from Get Event > Records or Clear Event Records. In that case the log ramain non-empty. > > CXL event interrupt are generated when a log transitions from empty to non-empty, > so after returning from the handler there may be no subsequent interrupt > to retry the drain. > > Maybe we can use a bounded retry for retryable failure ? or schedule deferred > retry work before returning ? > > Best regards, > Richard Cheng. > Hmmm you're right... I think a bounded retry makes more sense since scheduling deferred work still needs a way to eventually give up if the error or status bit persists. Thanks, Anisa > > + /* > > + * The Event Status register is device owned and read only, so > > + * it cannot bound this loop; records read can. A device that > > + * leaves a bit set with an empty log makes no progress, and > > + * only the device can clear that state, so stop polling that > > + * log rather than spin on it. > > + */ > > + stuck = status & ~drained; > > + if (stuck) { > > + dev_warn_once(cxlds->dev, > > + "Event status %#x set with no records to read\n", > > + stuck); > > + mask &= ~stuck; > > + } > > cond_resched(); > > - } while (status); > > + } > > > > return IRQ_HANDLED; > > } > > @@ -682,7 +707,7 @@ static int cxl_event_config(struct pci_host_bridge *host_bridge, > > if (rc) > > return rc; > > > > - cxl_mem_get_event_records(mds, CXLDEV_EVENT_STATUS_ALL); > > + cxl_mem_get_event_records(mds, CXLDEV_EVENT_STATUS_ALL, NULL); > > > > return 0; > > } > > diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c > > index a7da279aa3ef..87e01612cea9 100644 > > --- a/tools/testing/cxl/test/mem.c > > +++ b/tools/testing/cxl/test/mem.c > > @@ -372,7 +372,7 @@ static void cxl_mock_event_trigger(struct device *dev) > > event_reset_log(log); > > } > > > > - cxl_mem_get_event_records(mdata->mds, mes->ev_status); > > + cxl_mem_get_event_records(mdata->mds, mes->ev_status, NULL); > > } > > > > struct cxl_event_record_raw maint_needed = { > > @@ -1805,7 +1805,7 @@ static int cxl_mock_mem_probe(struct platform_device *pdev) > > if (rc) > > dev_dbg(dev, "No CXL FWCTL setup\n"); > > > > - cxl_mem_get_event_records(mds, CXLDEV_EVENT_STATUS_ALL); > > + cxl_mem_get_event_records(mds, CXLDEV_EVENT_STATUS_ALL, NULL); > > cxl_mock_test_feat_init(mdata); > > > > return 0; > > -- > > 2.43.0 > > > > ^ permalink raw reply [flat|nested] 5+ messages in thread
end of thread, other threads:[~2026-08-27 22:24 UTC | newest]
Thread overview: 5+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
[not found] <cover.1787768932.git.anisa.su@samsung.com>
2026-08-26 18:43 ` [PATCH 1/1] cxl/events: Bound the event log drain loop Anisa Su
2026-08-26 21:28 ` Cheatham, Benjamin
2026-08-27 18:05 ` Anisa Su
2026-08-27 3:01 ` Richard Cheng
2026-08-27 22:25 ` Anisa Su
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox