From d0abf5787adc0341a04667d3b4a23b4d0999af30 Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Tue, 18 Apr 2023 10:39:03 -0700 Subject: cxl/mbox: Initialize the poison state Driver reads of the poison list are synchronized to ensure that a reader does not get an incomplete list because their request overlapped (was interrupted or preceded by) another read request of the same DPA range. (CXL Spec 3.0 Section 8.2.9.8.4.1). The driver maintains state information to achieve this goal. To initialize the state, first recognize the poison commands in the CEL (Command Effects Log). If the device supports Get Poison List, allocate a single buffer for the poison list and protect it with a lock. Signed-off-by: Alison Schofield Link: https://lore.kernel.org/r/9078d180769be28a5087288b38cdfc827cae58bf.1681838291.git.alison.schofield@intel.com Reviewed-by: Jonathan Cameron Tested-by: Jonathan Cameron Signed-off-by: Dan Williams --- drivers/cxl/cxlmem.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'drivers/cxl/cxlmem.h') diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index 090acebba4fa..40de21fac128 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -215,6 +215,37 @@ struct cxl_event_state { struct mutex log_lock; }; +/* Device enabled poison commands */ +enum poison_cmd_enabled_bits { + CXL_POISON_ENABLED_LIST, + CXL_POISON_ENABLED_INJECT, + CXL_POISON_ENABLED_CLEAR, + CXL_POISON_ENABLED_SCAN_CAPS, + CXL_POISON_ENABLED_SCAN_MEDIA, + CXL_POISON_ENABLED_SCAN_RESULTS, + CXL_POISON_ENABLED_MAX +}; + +/** + * struct cxl_poison_state - Driver poison state info + * + * @max_errors: Maximum media error records held in device cache + * @enabled_cmds: All poison commands enabled in the CEL + * @list_out: The poison list payload returned by device + * @lock: Protect reads of the poison list + * + * Reads of the poison list are synchronized to ensure that a reader + * does not get an incomplete list because their request overlapped + * (was interrupted or preceded by) another read request of the same + * DPA range. CXL Spec 3.0 Section 8.2.9.8.4.1 + */ +struct cxl_poison_state { + u32 max_errors; + DECLARE_BITMAP(enabled_cmds, CXL_POISON_ENABLED_MAX); + struct cxl_mbox_poison_out *list_out; + struct mutex lock; /* Protect reads of poison list */ +}; + /** * struct cxl_dev_state - The driver device state * @@ -251,6 +282,7 @@ struct cxl_event_state { * @serial: PCIe Device Serial Number * @doe_mbs: PCI DOE mailbox array * @event: event log driver state + * @poison: poison driver state info * @mbox_send: @dev specific transport for transmitting mailbox commands * * See section 8.2.9.5.2 Capacity Configuration and Label Storage for @@ -290,6 +322,7 @@ struct cxl_dev_state { struct xarray doe_mbs; struct cxl_event_state event; + struct cxl_poison_state poison; int (*mbox_send)(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd *cmd); }; @@ -608,6 +641,7 @@ void set_exclusive_cxl_commands(struct cxl_dev_state *cxlds, unsigned long *cmds void clear_exclusive_cxl_commands(struct cxl_dev_state *cxlds, unsigned long *cmds); void cxl_mem_get_event_records(struct cxl_dev_state *cxlds, u32 status); int cxl_set_timestamp(struct cxl_dev_state *cxlds); +int cxl_poison_state_init(struct cxl_dev_state *cxlds); #ifdef CONFIG_CXL_SUSPEND void cxl_mem_active_inc(void); -- cgit v1.2.3 From ed83f7ca398b3798b82c1d5d1113011c0e5a2198 Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Tue, 18 Apr 2023 10:39:04 -0700 Subject: cxl/mbox: Add GET_POISON_LIST mailbox command CXL devices maintain a list of locations that are poisoned or result in poison if the addresses are accessed by the host. Per the spec, (CXL 3.0 8.2.9.8.4.1), the device returns this Poison list as a set of Media Error Records that include the source of the error, the starting device physical address, and length. The length is the number of adjacent DPAs in the record and is in units of 64 bytes. Retrieve the poison list. Signed-off-by: Alison Schofield Reviewed-by: Jonathan Cameron Reviewed-by: Ira Weiny Link: https://lore.kernel.org/r/a1f332e817834ef8e89c0ff32e760308fb903346.1681838291.git.alison.schofield@intel.com Tested-by: Jonathan Cameron Signed-off-by: Dan Williams --- drivers/cxl/core/mbox.c | 55 +++++++++++++++++++++++++++++++++++++++++++++++++ drivers/cxl/cxlmem.h | 46 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 101 insertions(+) (limited to 'drivers/cxl/cxlmem.h') diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index 17737386283a..05ff50ee8489 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -5,6 +5,7 @@ #include #include #include +#include #include #include #include @@ -1038,6 +1039,7 @@ int cxl_dev_state_identify(struct cxl_dev_state *cxlds) /* See CXL 2.0 Table 175 Identify Memory Device Output Payload */ struct cxl_mbox_identify id; struct cxl_mbox_cmd mbox_cmd; + u32 val; int rc; mbox_cmd = (struct cxl_mbox_cmd) { @@ -1061,6 +1063,11 @@ int cxl_dev_state_identify(struct cxl_dev_state *cxlds) cxlds->lsa_size = le32_to_cpu(id.lsa_size); memcpy(cxlds->firmware_version, id.fw_revision, sizeof(id.fw_revision)); + if (test_bit(CXL_POISON_ENABLED_LIST, cxlds->poison.enabled_cmds)) { + val = get_unaligned_le24(id.poison_list_max_mer); + cxlds->poison.max_errors = min_t(u32, val, CXL_POISON_LIST_MAX); + } + return 0; } EXPORT_SYMBOL_NS_GPL(cxl_dev_state_identify, CXL); @@ -1151,6 +1158,54 @@ int cxl_set_timestamp(struct cxl_dev_state *cxlds) } EXPORT_SYMBOL_NS_GPL(cxl_set_timestamp, CXL); +int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len, + struct cxl_region *cxlr) +{ + struct cxl_dev_state *cxlds = cxlmd->cxlds; + struct cxl_mbox_poison_out *po; + struct cxl_mbox_poison_in pi; + struct cxl_mbox_cmd mbox_cmd; + int nr_records = 0; + int rc; + + rc = mutex_lock_interruptible(&cxlds->poison.lock); + if (rc) + return rc; + + po = cxlds->poison.list_out; + pi.offset = cpu_to_le64(offset); + pi.length = cpu_to_le64(len / CXL_POISON_LEN_MULT); + + mbox_cmd = (struct cxl_mbox_cmd) { + .opcode = CXL_MBOX_OP_GET_POISON, + .size_in = sizeof(pi), + .payload_in = &pi, + .size_out = cxlds->payload_size, + .payload_out = po, + .min_out = struct_size(po, record, 0), + }; + + do { + rc = cxl_internal_send_cmd(cxlds, &mbox_cmd); + if (rc) + break; + + /* TODO TRACE the media error records */ + + /* Protect against an uncleared _FLAG_MORE */ + nr_records = nr_records + le16_to_cpu(po->count); + if (nr_records >= cxlds->poison.max_errors) { + dev_dbg(&cxlmd->dev, "Max Error Records reached: %d\n", + nr_records); + break; + } + } while (po->flags & CXL_POISON_FLAG_MORE); + + mutex_unlock(&cxlds->poison.lock); + return rc; +} +EXPORT_SYMBOL_NS_GPL(cxl_mem_get_poison, CXL); + static void free_poison_buf(void *buf) { kvfree(buf); diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index 40de21fac128..f2f0cdda5825 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -571,6 +571,50 @@ struct cxl_mbox_set_timestamp_in { } __packed; +/* Get Poison List CXL 3.0 Spec 8.2.9.8.4.1 */ +struct cxl_mbox_poison_in { + __le64 offset; + __le64 length; +} __packed; + +struct cxl_mbox_poison_out { + u8 flags; + u8 rsvd1; + __le64 overflow_ts; + __le16 count; + u8 rsvd2[20]; + struct cxl_poison_record { + __le64 address; + __le32 length; + __le32 rsvd; + } __packed record[]; +} __packed; + +/* + * Get Poison List address field encodes the starting + * address of poison, and the source of the poison. + */ +#define CXL_POISON_START_MASK GENMASK_ULL(63, 6) +#define CXL_POISON_SOURCE_MASK GENMASK(2, 0) + +/* Get Poison List record length is in units of 64 bytes */ +#define CXL_POISON_LEN_MULT 64 + +/* Kernel defined maximum for a list of poison errors */ +#define CXL_POISON_LIST_MAX 1024 + +/* Get Poison List: Payload out flags */ +#define CXL_POISON_FLAG_MORE BIT(0) +#define CXL_POISON_FLAG_OVERFLOW BIT(1) +#define CXL_POISON_FLAG_SCANNING BIT(2) + +/* Get Poison List: Poison Source */ +#define CXL_POISON_SOURCE_UNKNOWN 0 +#define CXL_POISON_SOURCE_EXTERNAL 1 +#define CXL_POISON_SOURCE_INTERNAL 2 +#define CXL_POISON_SOURCE_INJECTED 3 +#define CXL_POISON_SOURCE_VENDOR 7 + /** * struct cxl_mem_command - Driver representation of a memory device command * @info: Command information as it exists for the UAPI @@ -642,6 +686,8 @@ void clear_exclusive_cxl_commands(struct cxl_dev_state *cxlds, unsigned long *cm void cxl_mem_get_event_records(struct cxl_dev_state *cxlds, u32 status); int cxl_set_timestamp(struct cxl_dev_state *cxlds); 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); #ifdef CONFIG_CXL_SUSPEND void cxl_mem_active_inc(void); -- cgit v1.2.3 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 --- Documentation/ABI/testing/sysfs-bus-cxl | 14 +++++++++++ drivers/cxl/core/memdev.c | 43 +++++++++++++++++++++++++++++++++ drivers/cxl/cxlmem.h | 3 ++- drivers/cxl/mem.c | 43 +++++++++++++++++++++++++++++++++ 4 files changed, 102 insertions(+), 1 deletion(-) (limited to 'drivers/cxl/cxlmem.h') diff --git a/Documentation/ABI/testing/sysfs-bus-cxl b/Documentation/ABI/testing/sysfs-bus-cxl index 3acf2f17a73f..48ac0d911801 100644 --- a/Documentation/ABI/testing/sysfs-bus-cxl +++ b/Documentation/ABI/testing/sysfs-bus-cxl @@ -415,3 +415,17 @@ Description: 1), and checks that the hardware accepts the commit request. Reading this value indicates whether the region is committed or not. + + +What: /sys/bus/cxl/devices/memX/trigger_poison_list +Date: April, 2023 +KernelVersion: v6.4 +Contact: linux-cxl@vger.kernel.org +Description: + (WO) 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. 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, diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index f2f0cdda5825..bfb75bf0182e 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -145,7 +145,7 @@ struct cxl_mbox_cmd { C(FWROLLBACK, -ENXIO, "rolled back to the previous active FW"), \ C(FWRESET, -ENXIO, "FW failed to activate, needs cold reset"), \ C(HANDLE, -ENXIO, "one or more Event Record Handles were invalid"), \ - C(PADDR, -ENXIO, "physical address specified is invalid"), \ + C(PADDR, -EFAULT, "physical address specified is invalid"), \ C(POISONLMT, -ENXIO, "poison injection limit has been reached"), \ C(MEDIAFAILURE, -ENXIO, "permanent issue with the media"), \ C(ABORT, -ENXIO, "background cmd was aborted by device"), \ @@ -688,6 +688,7 @@ int cxl_set_timestamp(struct cxl_dev_state *cxlds); 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); #ifdef CONFIG_CXL_SUSPEND void cxl_mem_active_inc(void); diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c index 39c4b54f0715..b6a413facbd7 100644 --- a/drivers/cxl/mem.c +++ b/drivers/cxl/mem.c @@ -176,10 +176,53 @@ unlock: return devm_add_action_or_reset(dev, enable_suspend, NULL); } +static ssize_t trigger_poison_list_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + bool trigger; + int rc; + + if (kstrtobool(buf, &trigger) || !trigger) + return -EINVAL; + + rc = cxl_trigger_poison_list(to_cxl_memdev(dev)); + + return rc ? rc : len; +} +static DEVICE_ATTR_WO(trigger_poison_list); + +static umode_t cxl_mem_visible(struct kobject *kobj, struct attribute *a, int n) +{ + if (a == &dev_attr_trigger_poison_list.attr) { + struct device *dev = kobj_to_dev(kobj); + + if (!test_bit(CXL_POISON_ENABLED_LIST, + to_cxl_memdev(dev)->cxlds->poison.enabled_cmds)) + return 0; + } + return a->mode; +} + +static struct attribute *cxl_mem_attrs[] = { + &dev_attr_trigger_poison_list.attr, + NULL +}; + +static struct attribute_group cxl_mem_group = { + .attrs = cxl_mem_attrs, + .is_visible = cxl_mem_visible, +}; + +__ATTRIBUTE_GROUPS(cxl_mem); + static struct cxl_driver cxl_mem_driver = { .name = "cxl_mem", .probe = cxl_mem_probe, .id = CXL_DEVICE_MEMORY_EXPANDER, + .drv = { + .dev_groups = cxl_mem_groups, + }, }; module_cxl_driver(cxl_mem_driver); -- 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/cxlmem.h') 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/cxlmem.h') 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