From 7ff6ad1075885fdc71f6fea94b95109a582dec29 Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Tue, 18 Apr 2023 10:39:06 -0700 Subject: cxl/memdev: Add trigger_poison_list sysfs attribute When a boolean 'true' is written to this attribute the memdev driver retrieves the poison list from the device. The list consists of addresses that are poisoned, or would result in poison if accessed, and the source of the poison. This attribute is only visible for devices supporting the capability. The retrieved errors are logged as kernel events when cxl_poison event tracing is enabled. Signed-off-by: Alison Schofield Reviewed-by: Jonathan Cameron Reviewed-by: Ira Weiny Link: https://lore.kernel.org/r/1081cfdc8a349dc754779642d584707e56db26ba.1681838291.git.alison.schofield@intel.com Tested-by: Jonathan Cameron Signed-off-by: Dan Williams --- drivers/cxl/core/memdev.c | 43 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) (limited to 'drivers/cxl/core/memdev.c') diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c index 28a05f2fe32d..8be01479d40b 100644 --- a/drivers/cxl/core/memdev.c +++ b/drivers/cxl/core/memdev.c @@ -106,6 +106,49 @@ static ssize_t numa_node_show(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR_RO(numa_node); +static int cxl_get_poison_by_memdev(struct cxl_memdev *cxlmd) +{ + struct cxl_dev_state *cxlds = cxlmd->cxlds; + u64 offset, length; + int rc = 0; + + /* CXL 3.0 Spec 8.2.9.8.4.1 Separate pmem and ram poison requests */ + if (resource_size(&cxlds->pmem_res)) { + offset = cxlds->pmem_res.start; + length = resource_size(&cxlds->pmem_res); + rc = cxl_mem_get_poison(cxlmd, offset, length, NULL); + if (rc) + return rc; + } + if (resource_size(&cxlds->ram_res)) { + offset = cxlds->ram_res.start; + length = resource_size(&cxlds->ram_res); + rc = cxl_mem_get_poison(cxlmd, offset, length, NULL); + /* + * Invalid Physical Address is not an error for + * volatile addresses. Device support is optional. + */ + if (rc == -EFAULT) + rc = 0; + } + return rc; +} + +int cxl_trigger_poison_list(struct cxl_memdev *cxlmd) +{ + int rc; + + rc = down_read_interruptible(&cxl_dpa_rwsem); + if (rc) + return rc; + + rc = cxl_get_poison_by_memdev(cxlmd); + up_read(&cxl_dpa_rwsem); + + return rc; +} +EXPORT_SYMBOL_NS_GPL(cxl_trigger_poison_list, CXL); + static struct attribute *cxl_memdev_attributes[] = { &dev_attr_serial.attr, &dev_attr_firmware_version.attr, -- cgit v1.2.3 From f0832a58639691af575fa28ffaeb657c51f3ca06 Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Tue, 18 Apr 2023 10:39:07 -0700 Subject: cxl/region: Provide region info to the cxl_poison trace event User space may need to know which region, if any, maps the poison address(es) logged in a cxl_poison trace event. Since the mapping of DPAs (device physical addresses) to a region can change, the kernel must provide this information at the time the poison list is read. The event informs user space that at event this mapped to this , which is poisoned. The cxl_poison trace event is already wired up to log the region name and uuid if it receives param 'struct cxl_region'. In order to provide that cxl_region, add another method for gathering poison - by committed endpoint decoder mappings. This method is only available with CONFIG_CXL_REGION and is only used if a region actually maps the memdev where poison is being read. After the region driver reads the poison list for all the mapped resources, poison is read for any remaining unmapped resources. The default method remains: read the poison by memdev resource. Signed-off-by: Alison Schofield Tested-by: Jonathan Cameron Reviewed-by: Jonathan Cameron Reviewed-by: Ira Weiny Reviewed-by: Dave Jiang Link: https://lore.kernel.org/r/438b01ccaa70592539e8eda4eb2b1d617ba03160.1681838292.git.alison.schofield@intel.com Tested-by: Jonathan Cameron Signed-off-by: Dan Williams --- drivers/cxl/core/core.h | 5 ++ drivers/cxl/core/memdev.c | 13 ++++- drivers/cxl/core/region.c | 124 ++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 141 insertions(+), 1 deletion(-) (limited to 'drivers/cxl/core/memdev.c') diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h index e888e293943e..deb5f87d6d0a 100644 --- a/drivers/cxl/core/core.h +++ b/drivers/cxl/core/core.h @@ -25,7 +25,12 @@ void cxl_decoder_kill_region(struct cxl_endpoint_decoder *cxled); #define CXL_DAX_REGION_TYPE(x) (&cxl_dax_region_type) int cxl_region_init(void); void cxl_region_exit(void); +int cxl_get_poison_by_endpoint(struct cxl_port *port); #else +static inline int cxl_get_poison_by_endpoint(struct cxl_port *port) +{ + return 0; +} static inline void cxl_decoder_kill_region(struct cxl_endpoint_decoder *cxled) { } diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c index 8be01479d40b..185b6d27b698 100644 --- a/drivers/cxl/core/memdev.c +++ b/drivers/cxl/core/memdev.c @@ -136,13 +136,24 @@ static int cxl_get_poison_by_memdev(struct cxl_memdev *cxlmd) int cxl_trigger_poison_list(struct cxl_memdev *cxlmd) { + struct cxl_port *port; int rc; + port = dev_get_drvdata(&cxlmd->dev); + if (!port || !is_cxl_endpoint(port)) + return -EINVAL; + rc = down_read_interruptible(&cxl_dpa_rwsem); if (rc) return rc; - rc = cxl_get_poison_by_memdev(cxlmd); + if (port->commit_end == -1) { + /* No regions mapped to this memdev */ + rc = cxl_get_poison_by_memdev(cxlmd); + } else { + /* Regions mapped, collect poison by endpoint */ + rc = cxl_get_poison_by_endpoint(port); + } up_read(&cxl_dpa_rwsem); return rc; diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index b2fd67fcebfb..f822de44bee0 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -2238,6 +2238,130 @@ struct cxl_pmem_region *to_cxl_pmem_region(struct device *dev) } EXPORT_SYMBOL_NS_GPL(to_cxl_pmem_region, CXL); +struct cxl_poison_context { + struct cxl_port *port; + enum cxl_decoder_mode mode; + u64 offset; +}; + +static int cxl_get_poison_unmapped(struct cxl_memdev *cxlmd, + struct cxl_poison_context *ctx) +{ + struct cxl_dev_state *cxlds = cxlmd->cxlds; + u64 offset, length; + int rc = 0; + + /* + * Collect poison for the remaining unmapped resources + * after poison is collected by committed endpoints. + * + * Knowing that PMEM must always follow RAM, get poison + * for unmapped resources based on the last decoder's mode: + * ram: scan remains of ram range, then any pmem range + * pmem: scan remains of pmem range + */ + + if (ctx->mode == CXL_DECODER_RAM) { + offset = ctx->offset; + length = resource_size(&cxlds->ram_res) - offset; + rc = cxl_mem_get_poison(cxlmd, offset, length, NULL); + if (rc == -EFAULT) + rc = 0; + if (rc) + return rc; + } + if (ctx->mode == CXL_DECODER_PMEM) { + offset = ctx->offset; + length = resource_size(&cxlds->dpa_res) - offset; + if (!length) + return 0; + } else if (resource_size(&cxlds->pmem_res)) { + offset = cxlds->pmem_res.start; + length = resource_size(&cxlds->pmem_res); + } else { + return 0; + } + + return cxl_mem_get_poison(cxlmd, offset, length, NULL); +} + +static int poison_by_decoder(struct device *dev, void *arg) +{ + struct cxl_poison_context *ctx = arg; + struct cxl_endpoint_decoder *cxled; + struct cxl_memdev *cxlmd; + u64 offset, length; + int rc = 0; + + if (!is_endpoint_decoder(dev)) + return rc; + + cxled = to_cxl_endpoint_decoder(dev); + if (!cxled->dpa_res || !resource_size(cxled->dpa_res)) + return rc; + + /* + * Regions are only created with single mode decoders: pmem or ram. + * Linux does not support mixed mode decoders. This means that + * reading poison per endpoint decoder adheres to the requirement + * that poison reads of pmem and ram must be separated. + * CXL 3.0 Spec 8.2.9.8.4.1 + */ + if (cxled->mode == CXL_DECODER_MIXED) { + dev_dbg(dev, "poison list read unsupported in mixed mode\n"); + return rc; + } + + cxlmd = cxled_to_memdev(cxled); + if (cxled->skip) { + offset = cxled->dpa_res->start - cxled->skip; + length = cxled->skip; + rc = cxl_mem_get_poison(cxlmd, offset, length, NULL); + if (rc == -EFAULT && cxled->mode == CXL_DECODER_RAM) + rc = 0; + if (rc) + return rc; + } + + offset = cxled->dpa_res->start; + length = cxled->dpa_res->end - offset + 1; + rc = cxl_mem_get_poison(cxlmd, offset, length, cxled->cxld.region); + if (rc == -EFAULT && cxled->mode == CXL_DECODER_RAM) + rc = 0; + if (rc) + return rc; + + /* Iterate until commit_end is reached */ + if (cxled->cxld.id == ctx->port->commit_end) { + ctx->offset = cxled->dpa_res->end + 1; + ctx->mode = cxled->mode; + return 1; + } + + return 0; +} + +int cxl_get_poison_by_endpoint(struct cxl_port *port) +{ + struct cxl_poison_context ctx; + int rc = 0; + + rc = down_read_interruptible(&cxl_region_rwsem); + if (rc) + return rc; + + ctx = (struct cxl_poison_context) { + .port = port + }; + + rc = device_for_each_child(&port->dev, &ctx, poison_by_decoder); + if (rc == 1) + rc = cxl_get_poison_unmapped(to_cxl_memdev(port->uport), &ctx); + + up_read(&cxl_region_rwsem); + return rc; +} + static struct lock_class_key cxl_pmem_region_key; static struct cxl_pmem_region *cxl_pmem_region_alloc(struct cxl_region *cxlr) -- cgit v1.2.3 From d2fbc48658022f48625064ae192baff52057987d Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Tue, 18 Apr 2023 20:26:25 -0700 Subject: cxl/memdev: Add support for the Inject Poison mailbox command CXL devices optionally support the INJECT POISON mailbox command. Add memdev driver support for the mailbox command. Per the CXL Specification (3.0 8.2.9.8.4.2), after receiving a valid inject poison request, the device will return poison when the address is accessed through the CXL.mem driver. Injecting poison adds the address to the device's Poison List and the error source is set to Injected. In addition, the device adds a poison creation event to its internal Informational Event log, updates the Event Status register, and if configured, interrupts the host. Also, per the CXL Specification, it is not an error to inject poison into an address that already has poison present and no error is returned from the device. If the address is not contained in the device's dpa resource, or is not 64 byte aligned, return -EINVAL without issuing the mbox command. Poison injection is intended for debug only and will be exposed to userspace through debugfs. Restrict compilation to CONFIG_DEBUG_FS. Signed-off-by: Alison Schofield Reviewed-by: Jonathan Cameron Reviewed-by: Dave Jiang Link: https://lore.kernel.org/r/241c64115e6bd2effed9c7a20b08b3908dd7be8f.1681874357.git.alison.schofield@intel.com Tested-by: Jonathan Cameron Signed-off-by: Dan Williams --- drivers/cxl/core/memdev.c | 56 +++++++++++++++++++++++++++++++++++++++++++++++ drivers/cxl/cxlmem.h | 6 +++++ 2 files changed, 62 insertions(+) (limited to 'drivers/cxl/core/memdev.c') diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c index 185b6d27b698..8a3b7d7505fe 100644 --- a/drivers/cxl/core/memdev.c +++ b/drivers/cxl/core/memdev.c @@ -160,6 +160,62 @@ int cxl_trigger_poison_list(struct cxl_memdev *cxlmd) } EXPORT_SYMBOL_NS_GPL(cxl_trigger_poison_list, CXL); +static int cxl_validate_poison_dpa(struct cxl_memdev *cxlmd, u64 dpa) +{ + struct cxl_dev_state *cxlds = cxlmd->cxlds; + + if (!IS_ENABLED(CONFIG_DEBUG_FS)) + return 0; + + if (!resource_size(&cxlds->dpa_res)) { + dev_dbg(cxlds->dev, "device has no dpa resource\n"); + return -EINVAL; + } + if (dpa < cxlds->dpa_res.start || dpa > cxlds->dpa_res.end) { + dev_dbg(cxlds->dev, "dpa:0x%llx not in resource:%pR\n", + dpa, &cxlds->dpa_res); + return -EINVAL; + } + if (!IS_ALIGNED(dpa, 64)) { + dev_dbg(cxlds->dev, "dpa:0x%llx is not 64-byte aligned\n", dpa); + return -EINVAL; + } + + return 0; +} + +int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa) +{ + struct cxl_dev_state *cxlds = cxlmd->cxlds; + struct cxl_mbox_inject_poison inject; + struct cxl_mbox_cmd mbox_cmd; + int rc; + + if (!IS_ENABLED(CONFIG_DEBUG_FS)) + return 0; + + rc = down_read_interruptible(&cxl_dpa_rwsem); + if (rc) + return rc; + + rc = cxl_validate_poison_dpa(cxlmd, dpa); + if (rc) + goto out; + + inject.address = cpu_to_le64(dpa); + mbox_cmd = (struct cxl_mbox_cmd) { + .opcode = CXL_MBOX_OP_INJECT_POISON, + .size_in = sizeof(inject), + .payload_in = &inject, + }; + rc = cxl_internal_send_cmd(cxlds, &mbox_cmd); +out: + up_read(&cxl_dpa_rwsem); + + return rc; +} +EXPORT_SYMBOL_NS_GPL(cxl_inject_poison, CXL); + static struct attribute *cxl_memdev_attributes[] = { &dev_attr_serial.attr, &dev_attr_firmware_version.attr, diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index bfb75bf0182e..2a0625e1d3aa 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -615,6 +615,11 @@ struct cxl_mbox_poison_out { #define CXL_POISON_SOURCE_INJECTED 3 #define CXL_POISON_SOURCE_VENDOR 7 +/* Inject & Clear Poison CXL 3.0 Spec 8.2.9.8.4.2/3 */ +struct cxl_mbox_inject_poison { + __le64 address; +}; + /** * struct cxl_mem_command - Driver representation of a memory device command * @info: Command information as it exists for the UAPI @@ -689,6 +694,7 @@ int cxl_poison_state_init(struct cxl_dev_state *cxlds); int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len, struct cxl_region *cxlr); int cxl_trigger_poison_list(struct cxl_memdev *cxlmd); +int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa); #ifdef CONFIG_CXL_SUSPEND void cxl_mem_active_inc(void); -- cgit v1.2.3 From 9690b07748d18ac667036a68442081c4aea33ba7 Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Tue, 18 Apr 2023 20:26:26 -0700 Subject: cxl/memdev: Add support for the Clear Poison mailbox command CXL devices optionally support the CLEAR POISON mailbox command. Add memdev driver support for clearing poison. Per the CXL Specification (3.0 8.2.9.8.4.3), after receiving a valid clear poison request, the device removes the address from the device's Poison List and writes 0 (zero) for 64 bytes starting at address. If the device cannot clear poison from the address, it returns a permanent media error and -ENXIO is returned to the user. Additionally, and per the spec also, it is not an error to clear poison of an address that is not poisoned. If the address is not contained in the device's dpa resource, or is not 64 byte aligned, the driver returns -EINVAL without sending the command to the device. Poison clearing is intended for debug only and will be exposed to userspace through debugfs. Restrict compilation to CONFIG_DEBUG_FS. Implementation note: Although the CXL specification defines the clear command to accept 64 bytes of 'write-data', this implementation always uses zeroes as write-data. Signed-off-by: Alison Schofield Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/8682c30ec24bd9c45af5feccb04b02be51e58c0a.1681874357.git.alison.schofield@intel.com Tested-by: Jonathan Cameron Signed-off-by: Dan Williams --- drivers/cxl/core/memdev.c | 43 +++++++++++++++++++++++++++++++++++++++++++ drivers/cxl/cxlmem.h | 7 +++++++ 2 files changed, 50 insertions(+) (limited to 'drivers/cxl/core/memdev.c') diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c index 8a3b7d7505fe..813fd1eeba3d 100644 --- a/drivers/cxl/core/memdev.c +++ b/drivers/cxl/core/memdev.c @@ -216,6 +216,49 @@ out: } EXPORT_SYMBOL_NS_GPL(cxl_inject_poison, CXL); +int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa) +{ + struct cxl_dev_state *cxlds = cxlmd->cxlds; + struct cxl_mbox_clear_poison clear; + struct cxl_mbox_cmd mbox_cmd; + int rc; + + if (!IS_ENABLED(CONFIG_DEBUG_FS)) + return 0; + + rc = down_read_interruptible(&cxl_dpa_rwsem); + if (rc) + return rc; + + rc = cxl_validate_poison_dpa(cxlmd, dpa); + if (rc) + goto out; + + /* + * In CXL 3.0 Spec 8.2.9.8.4.3, the Clear Poison mailbox command + * is defined to accept 64 bytes of write-data, along with the + * address to clear. This driver uses zeroes as write-data. + */ + clear = (struct cxl_mbox_clear_poison) { + .address = cpu_to_le64(dpa) + }; + + mbox_cmd = (struct cxl_mbox_cmd) { + .opcode = CXL_MBOX_OP_CLEAR_POISON, + .size_in = sizeof(clear), + .payload_in = &clear, + }; + + rc = cxl_internal_send_cmd(cxlds, &mbox_cmd); + if (rc) + goto out; +out: + up_read(&cxl_dpa_rwsem); + + return rc; +} +EXPORT_SYMBOL_NS_GPL(cxl_clear_poison, CXL); + static struct attribute *cxl_memdev_attributes[] = { &dev_attr_serial.attr, &dev_attr_firmware_version.attr, diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index 2a0625e1d3aa..80276f37b78f 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -620,6 +620,12 @@ struct cxl_mbox_inject_poison { __le64 address; }; +/* Clear Poison CXL 3.0 Spec 8.2.9.8.4.3 */ +struct cxl_mbox_clear_poison { + __le64 address; + u8 write_data[CXL_POISON_LEN_MULT]; +} __packed; + /** * struct cxl_mem_command - Driver representation of a memory device command * @info: Command information as it exists for the UAPI @@ -695,6 +701,7 @@ int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len, struct cxl_region *cxlr); int cxl_trigger_poison_list(struct cxl_memdev *cxlmd); int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa); +int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa); #ifdef CONFIG_CXL_SUSPEND void cxl_mem_active_inc(void); -- cgit v1.2.3 From 0a105ab28a4de44eb738ce64e9ac74946aa5133b Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Tue, 18 Apr 2023 20:26:27 -0700 Subject: cxl/memdev: Warn of poison inject or clear to a mapped region Inject and clear poison capabilities and intended for debug usage only. In order to be useful in debug environments, the driver needs to allow inject and clear operations on DPAs mapped in regions. dev_warn_once() when either operation occurs. Signed-off-by: Alison Schofield Link: https://lore.kernel.org/r/f911ca5277c9d0f9757b72d7e6842871bfff4fa2.1681874357.git.alison.schofield@intel.com Tested-by: Jonathan Cameron Reviewed-by: Jonathan Cameron Signed-off-by: Dan Williams --- drivers/cxl/core/memdev.c | 59 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 59 insertions(+) (limited to 'drivers/cxl/core/memdev.c') diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c index 813fd1eeba3d..40ce74f5500a 100644 --- a/drivers/cxl/core/memdev.c +++ b/drivers/cxl/core/memdev.c @@ -160,6 +160,50 @@ int cxl_trigger_poison_list(struct cxl_memdev *cxlmd) } EXPORT_SYMBOL_NS_GPL(cxl_trigger_poison_list, CXL); +struct cxl_dpa_to_region_context { + struct cxl_region *cxlr; + u64 dpa; +}; + +static int __cxl_dpa_to_region(struct device *dev, void *arg) +{ + struct cxl_dpa_to_region_context *ctx = arg; + struct cxl_endpoint_decoder *cxled; + u64 dpa = ctx->dpa; + + if (!is_endpoint_decoder(dev)) + return 0; + + cxled = to_cxl_endpoint_decoder(dev); + if (!cxled->dpa_res || !resource_size(cxled->dpa_res)) + return 0; + + if (dpa > cxled->dpa_res->end || dpa < cxled->dpa_res->start) + return 0; + + dev_dbg(dev, "dpa:0x%llx mapped in region:%s\n", dpa, + dev_name(&cxled->cxld.region->dev)); + + ctx->cxlr = cxled->cxld.region; + + return 1; +} + +static struct cxl_region *cxl_dpa_to_region(struct cxl_memdev *cxlmd, u64 dpa) +{ + struct cxl_dpa_to_region_context ctx; + struct cxl_port *port; + + ctx = (struct cxl_dpa_to_region_context) { + .dpa = dpa, + }; + port = dev_get_drvdata(&cxlmd->dev); + if (port && is_cxl_endpoint(port) && port->commit_end != -1) + device_for_each_child(&port->dev, &ctx, __cxl_dpa_to_region); + + return ctx.cxlr; +} + static int cxl_validate_poison_dpa(struct cxl_memdev *cxlmd, u64 dpa) { struct cxl_dev_state *cxlds = cxlmd->cxlds; @@ -189,6 +233,7 @@ int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa) struct cxl_dev_state *cxlds = cxlmd->cxlds; struct cxl_mbox_inject_poison inject; struct cxl_mbox_cmd mbox_cmd; + struct cxl_region *cxlr; int rc; if (!IS_ENABLED(CONFIG_DEBUG_FS)) @@ -209,6 +254,14 @@ int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa) .payload_in = &inject, }; rc = cxl_internal_send_cmd(cxlds, &mbox_cmd); + if (rc) + goto out; + + cxlr = cxl_dpa_to_region(cxlmd, dpa); + if (cxlr) + dev_warn_once(cxlds->dev, + "poison inject dpa:%#llx region: %s\n", dpa, + dev_name(&cxlr->dev)); out: up_read(&cxl_dpa_rwsem); @@ -221,6 +274,7 @@ int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa) struct cxl_dev_state *cxlds = cxlmd->cxlds; struct cxl_mbox_clear_poison clear; struct cxl_mbox_cmd mbox_cmd; + struct cxl_region *cxlr; int rc; if (!IS_ENABLED(CONFIG_DEBUG_FS)) @@ -252,6 +306,11 @@ int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa) rc = cxl_internal_send_cmd(cxlds, &mbox_cmd); if (rc) goto out; + + cxlr = cxl_dpa_to_region(cxlmd, dpa); + if (cxlr) + dev_warn_once(cxlds->dev, "poison clear dpa:%#llx region: %s\n", + dpa, dev_name(&cxlr->dev)); out: up_read(&cxl_dpa_rwsem); -- cgit v1.2.3 From 98b6926562d9ccdbca69de9a0e0bf4f90d7f1326 Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Tue, 18 Apr 2023 20:26:28 -0700 Subject: cxl/memdev: Trace inject and clear poison as cxl_poison events The cxl_poison trace event allows users to view the history of poison list reads. With the addition of inject and clear poison capabilities, users will expect similar tracing. Add trace types 'Inject' and 'Clear' to the cxl_poison trace_event and trace successful operations only. If the driver finds that the DPA being injected or cleared of poison is mapped in a region, that region info is included in the cxl_poison trace event. Region reconfigurations can make this extra info useless if the debug operations are not carefully managed. Signed-off-by: Alison Schofield Reviewed-by: Jonathan Cameron Reviewed-by: Dave Jiang Link: https://lore.kernel.org/r/e20eb7c3029137b480ece671998c183da0477e2e.1681874357.git.alison.schofield@intel.com Tested-by: Jonathan Cameron Signed-off-by: Dan Williams --- drivers/cxl/core/core.h | 2 ++ drivers/cxl/core/memdev.c | 15 +++++++++++++++ drivers/cxl/core/trace.h | 8 +++++--- 3 files changed, 22 insertions(+), 3 deletions(-) (limited to 'drivers/cxl/core/memdev.c') diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h index deb5f87d6d0a..27f0968449de 100644 --- a/drivers/cxl/core/core.h +++ b/drivers/cxl/core/core.h @@ -71,6 +71,8 @@ void cxl_mbox_init(void); enum cxl_poison_trace_type { CXL_POISON_TRACE_LIST, + CXL_POISON_TRACE_INJECT, + CXL_POISON_TRACE_CLEAR, }; #endif /* __CXL_CORE_H__ */ diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c index 40ce74f5500a..057a43267290 100644 --- a/drivers/cxl/core/memdev.c +++ b/drivers/cxl/core/memdev.c @@ -6,6 +6,7 @@ #include #include #include +#include "trace.h" #include "core.h" static DECLARE_RWSEM(cxl_memdev_rwsem); @@ -232,6 +233,7 @@ int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa) { struct cxl_dev_state *cxlds = cxlmd->cxlds; struct cxl_mbox_inject_poison inject; + struct cxl_poison_record record; struct cxl_mbox_cmd mbox_cmd; struct cxl_region *cxlr; int rc; @@ -262,6 +264,12 @@ int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa) dev_warn_once(cxlds->dev, "poison inject dpa:%#llx region: %s\n", dpa, dev_name(&cxlr->dev)); + + record = (struct cxl_poison_record) { + .address = cpu_to_le64(dpa), + .length = cpu_to_le32(1), + }; + trace_cxl_poison(cxlmd, cxlr, &record, 0, 0, CXL_POISON_TRACE_INJECT); out: up_read(&cxl_dpa_rwsem); @@ -273,6 +281,7 @@ int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa) { struct cxl_dev_state *cxlds = cxlmd->cxlds; struct cxl_mbox_clear_poison clear; + struct cxl_poison_record record; struct cxl_mbox_cmd mbox_cmd; struct cxl_region *cxlr; int rc; @@ -311,6 +320,12 @@ int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa) if (cxlr) dev_warn_once(cxlds->dev, "poison clear dpa:%#llx region: %s\n", dpa, dev_name(&cxlr->dev)); + + record = (struct cxl_poison_record) { + .address = cpu_to_le64(dpa), + .length = cpu_to_le32(1), + }; + trace_cxl_poison(cxlmd, cxlr, &record, 0, 0, CXL_POISON_TRACE_CLEAR); out: up_read(&cxl_dpa_rwsem); diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h index 220cc7e721b8..a0b5819bc70b 100644 --- a/drivers/cxl/core/trace.h +++ b/drivers/cxl/core/trace.h @@ -602,9 +602,11 @@ TRACE_EVENT(cxl_memory_module, ) ); -#define show_poison_trace_type(type) \ - __print_symbolic(type, \ - { CXL_POISON_TRACE_LIST, "List" }) +#define show_poison_trace_type(type) \ + __print_symbolic(type, \ + { CXL_POISON_TRACE_LIST, "List" }, \ + { CXL_POISON_TRACE_INJECT, "Inject" }, \ + { CXL_POISON_TRACE_CLEAR, "Clear" }) #define __show_poison_source(source) \ __print_symbolic(source, \ -- cgit v1.2.3