diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2023-04-30 11:51:51 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2023-04-30 11:51:51 -0700 |
commit | 7acc1372113083fa281ba426021801e2402caca1 (patch) | |
tree | f910476851f61f87ac5f740aa9ad17673aa8d56a /drivers/pci | |
parent | 10de638d8ea57ebab4231ea077bed01d9bade775 (diff) | |
parent | fd35fdcbf75b5f31dba6c284886b676bb2145fe6 (diff) |
Merge tag 'cxl-for-6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/cxl/cxl
Pull compute express link updates from Dan Williams:
"DOE support is promoted from drivers/cxl/ to drivers/pci/ with Bjorn's
blessing, and the CXL core continues to mature its media management
capabilities with support for listing and injecting media errors. Some
late fixes that missed v6.3-final are also included:
- Refactor the DOE infrastructure (Data Object Exchange
PCI-config-cycle mailbox) to be a facility of the PCI core rather
than the CXL core.
This is foundational for upcoming support for PCI
device-attestation and PCIe / CXL link encryption.
- Add support for retrieving and injecting poison for CXL memory
expanders.
This enabling uses trace-events to convey CXL media error records
to user tooling. It includes translation of device-local addresses
(DPA) to system physical addresses (SPA) and their corresponding
CXL region.
- Fixes for decoder enumeration that missed v6.3-final
- Miscellaneous fixups"
* tag 'cxl-for-6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/cxl/cxl: (38 commits)
cxl/test: Add mock test for set_timestamp
cxl/mbox: Update CMD_RC_TABLE
tools/testing/cxl: Require CONFIG_DEBUG_FS
tools/testing/cxl: Add a sysfs attr to test poison inject limits
tools/testing/cxl: Use injected poison for get poison list
tools/testing/cxl: Mock the Clear Poison mailbox command
tools/testing/cxl: Mock the Inject Poison mailbox command
cxl/mem: Add debugfs attributes for poison inject and clear
cxl/memdev: Trace inject and clear poison as cxl_poison events
cxl/memdev: Warn of poison inject or clear to a mapped region
cxl/memdev: Add support for the Clear Poison mailbox command
cxl/memdev: Add support for the Inject Poison mailbox command
tools/testing/cxl: Mock support for Get Poison List
cxl/trace: Add an HPA to cxl_poison trace events
cxl/region: Provide region info to the cxl_poison trace event
cxl/memdev: Add trigger_poison_list sysfs attribute
cxl/trace: Add TRACE support for CXL media-error records
cxl/mbox: Add GET_POISON_LIST mailbox command
cxl/mbox: Initialize the poison state
cxl/mbox: Restrict poison cmds to debugfs cxl_raw_allow_all
...
Diffstat (limited to 'drivers/pci')
-rw-r--r-- | drivers/pci/doe.c | 328 | ||||
-rw-r--r-- | drivers/pci/pci.h | 11 | ||||
-rw-r--r-- | drivers/pci/probe.c | 1 | ||||
-rw-r--r-- | drivers/pci/remove.c | 1 |
4 files changed, 262 insertions, 79 deletions
diff --git a/drivers/pci/doe.c b/drivers/pci/doe.c index e5e9b287b976..1b97a5ab71a9 100644 --- a/drivers/pci/doe.c +++ b/drivers/pci/doe.c @@ -20,6 +20,8 @@ #include <linux/pci-doe.h> #include <linux/workqueue.h> +#include "pci.h" + #define PCI_DOE_PROTOCOL_DISCOVERY 0 /* Timeout of 1 second from 6.30.2 Operation, PCI Spec r6.0 */ @@ -37,7 +39,7 @@ * * This state is used to manage a single DOE mailbox capability. All fields * should be considered opaque to the consumers and the structure passed into - * the helpers below after being created by devm_pci_doe_create() + * the helpers below after being created by pci_doe_create_mb(). * * @pdev: PCI device this mailbox belongs to * @cap_offset: Capability offset @@ -56,6 +58,40 @@ struct pci_doe_mb { unsigned long flags; }; +struct pci_doe_protocol { + u16 vid; + u8 type; +}; + +/** + * struct pci_doe_task - represents a single query/response + * + * @prot: DOE Protocol + * @request_pl: The request payload + * @request_pl_sz: Size of the request payload (bytes) + * @response_pl: The response payload + * @response_pl_sz: Size of the response payload (bytes) + * @rv: Return value. Length of received response or error (bytes) + * @complete: Called when task is complete + * @private: Private data for the consumer + * @work: Used internally by the mailbox + * @doe_mb: Used internally by the mailbox + */ +struct pci_doe_task { + struct pci_doe_protocol prot; + const __le32 *request_pl; + size_t request_pl_sz; + __le32 *response_pl; + size_t response_pl_sz; + int rv; + void (*complete)(struct pci_doe_task *task); + void *private; + + /* initialized by pci_doe_submit_task() */ + struct work_struct work; + struct pci_doe_mb *doe_mb; +}; + static int pci_doe_wait(struct pci_doe_mb *doe_mb, unsigned long timeout) { if (wait_event_timeout(doe_mb->wq, @@ -110,7 +146,7 @@ static int pci_doe_send_req(struct pci_doe_mb *doe_mb, { struct pci_dev *pdev = doe_mb->pdev; int offset = doe_mb->cap_offset; - size_t length; + size_t length, remainder; u32 val; int i; @@ -128,7 +164,7 @@ static int pci_doe_send_req(struct pci_doe_mb *doe_mb, return -EIO; /* Length is 2 DW of header + length of payload in DW */ - length = 2 + task->request_pl_sz / sizeof(__le32); + length = 2 + DIV_ROUND_UP(task->request_pl_sz, sizeof(__le32)); if (length > PCI_DOE_MAX_LENGTH) return -EIO; if (length == PCI_DOE_MAX_LENGTH) @@ -141,10 +177,21 @@ static int pci_doe_send_req(struct pci_doe_mb *doe_mb, pci_write_config_dword(pdev, offset + PCI_DOE_WRITE, FIELD_PREP(PCI_DOE_DATA_OBJECT_HEADER_2_LENGTH, length)); + + /* Write payload */ for (i = 0; i < task->request_pl_sz / sizeof(__le32); i++) pci_write_config_dword(pdev, offset + PCI_DOE_WRITE, le32_to_cpu(task->request_pl[i])); + /* Write last payload dword */ + remainder = task->request_pl_sz % sizeof(__le32); + if (remainder) { + val = 0; + memcpy(&val, &task->request_pl[i], remainder); + le32_to_cpus(&val); + pci_write_config_dword(pdev, offset + PCI_DOE_WRITE, val); + } + pci_doe_write_ctrl(doe_mb, PCI_DOE_CTRL_GO); return 0; @@ -164,11 +211,11 @@ static bool pci_doe_data_obj_ready(struct pci_doe_mb *doe_mb) static int pci_doe_recv_resp(struct pci_doe_mb *doe_mb, struct pci_doe_task *task) { + size_t length, payload_length, remainder, received; struct pci_dev *pdev = doe_mb->pdev; int offset = doe_mb->cap_offset; - size_t length, payload_length; + int i = 0; u32 val; - int i; /* Read the first dword to get the protocol */ pci_read_config_dword(pdev, offset + PCI_DOE_READ, &val); @@ -195,15 +242,38 @@ static int pci_doe_recv_resp(struct pci_doe_mb *doe_mb, struct pci_doe_task *tas /* First 2 dwords have already been read */ length -= 2; - payload_length = min(length, task->response_pl_sz / sizeof(__le32)); - /* Read the rest of the response payload */ - for (i = 0; i < payload_length; i++) { + received = task->response_pl_sz; + payload_length = DIV_ROUND_UP(task->response_pl_sz, sizeof(__le32)); + remainder = task->response_pl_sz % sizeof(__le32); + + /* remainder signifies number of data bytes in last payload dword */ + if (!remainder) + remainder = sizeof(__le32); + + if (length < payload_length) { + received = length * sizeof(__le32); + payload_length = length; + remainder = sizeof(__le32); + } + + if (payload_length) { + /* Read all payload dwords except the last */ + for (; i < payload_length - 1; i++) { + pci_read_config_dword(pdev, offset + PCI_DOE_READ, + &val); + task->response_pl[i] = cpu_to_le32(val); + pci_write_config_dword(pdev, offset + PCI_DOE_READ, 0); + } + + /* Read last payload dword */ pci_read_config_dword(pdev, offset + PCI_DOE_READ, &val); - task->response_pl[i] = cpu_to_le32(val); + cpu_to_le32s(&val); + memcpy(&task->response_pl[i], &val, remainder); /* Prior to the last ack, ensure Data Object Ready */ - if (i == (payload_length - 1) && !pci_doe_data_obj_ready(doe_mb)) + if (!pci_doe_data_obj_ready(doe_mb)) return -EIO; pci_write_config_dword(pdev, offset + PCI_DOE_READ, 0); + i++; } /* Flush excess length */ @@ -217,7 +287,7 @@ static int pci_doe_recv_resp(struct pci_doe_mb *doe_mb, struct pci_doe_task *tas if (FIELD_GET(PCI_DOE_STATUS_ERROR, val)) return -EIO; - return min(length, task->response_pl_sz / sizeof(__le32)) * sizeof(__le32); + return received; } static void signal_task_complete(struct pci_doe_task *task, int rv) @@ -321,26 +391,15 @@ static int pci_doe_discovery(struct pci_doe_mb *doe_mb, u8 *index, u16 *vid, __le32 request_pl_le = cpu_to_le32(request_pl); __le32 response_pl_le; u32 response_pl; - DECLARE_COMPLETION_ONSTACK(c); - struct pci_doe_task task = { - .prot.vid = PCI_VENDOR_ID_PCI_SIG, - .prot.type = PCI_DOE_PROTOCOL_DISCOVERY, - .request_pl = &request_pl_le, - .request_pl_sz = sizeof(request_pl), - .response_pl = &response_pl_le, - .response_pl_sz = sizeof(response_pl), - .complete = pci_doe_task_complete, - .private = &c, - }; int rc; - rc = pci_doe_submit_task(doe_mb, &task); + rc = pci_doe(doe_mb, PCI_VENDOR_ID_PCI_SIG, PCI_DOE_PROTOCOL_DISCOVERY, + &request_pl_le, sizeof(request_pl_le), + &response_pl_le, sizeof(response_pl_le)); if (rc < 0) return rc; - wait_for_completion(&c); - - if (task.rv != sizeof(response_pl)) + if (rc != sizeof(response_pl_le)) return -EIO; response_pl = le32_to_cpu(response_pl_le); @@ -385,37 +444,18 @@ static int pci_doe_cache_protocols(struct pci_doe_mb *doe_mb) return 0; } -static void pci_doe_xa_destroy(void *mb) -{ - struct pci_doe_mb *doe_mb = mb; - - xa_destroy(&doe_mb->prots); -} - -static void pci_doe_destroy_workqueue(void *mb) +static void pci_doe_cancel_tasks(struct pci_doe_mb *doe_mb) { - struct pci_doe_mb *doe_mb = mb; - - destroy_workqueue(doe_mb->work_queue); -} - -static void pci_doe_flush_mb(void *mb) -{ - struct pci_doe_mb *doe_mb = mb; - /* Stop all pending work items from starting */ set_bit(PCI_DOE_FLAG_DEAD, &doe_mb->flags); /* Cancel an in progress work item, if necessary */ set_bit(PCI_DOE_FLAG_CANCEL, &doe_mb->flags); wake_up(&doe_mb->wq); - - /* Flush all work items */ - flush_workqueue(doe_mb->work_queue); } /** - * pcim_doe_create_mb() - Create a DOE mailbox object + * pci_doe_create_mb() - Create a DOE mailbox object * * @pdev: PCI device to create the DOE mailbox for * @cap_offset: Offset of the DOE mailbox @@ -426,64 +466,77 @@ static void pci_doe_flush_mb(void *mb) * RETURNS: created mailbox object on success * ERR_PTR(-errno) on failure */ -struct pci_doe_mb *pcim_doe_create_mb(struct pci_dev *pdev, u16 cap_offset) +static struct pci_doe_mb *pci_doe_create_mb(struct pci_dev *pdev, + u16 cap_offset) { struct pci_doe_mb *doe_mb; - struct device *dev = &pdev->dev; int rc; - doe_mb = devm_kzalloc(dev, sizeof(*doe_mb), GFP_KERNEL); + doe_mb = kzalloc(sizeof(*doe_mb), GFP_KERNEL); if (!doe_mb) return ERR_PTR(-ENOMEM); doe_mb->pdev = pdev; doe_mb->cap_offset = cap_offset; init_waitqueue_head(&doe_mb->wq); - xa_init(&doe_mb->prots); - rc = devm_add_action(dev, pci_doe_xa_destroy, doe_mb); - if (rc) - return ERR_PTR(rc); doe_mb->work_queue = alloc_ordered_workqueue("%s %s DOE [%x]", 0, - dev_driver_string(&pdev->dev), + dev_bus_name(&pdev->dev), pci_name(pdev), doe_mb->cap_offset); if (!doe_mb->work_queue) { pci_err(pdev, "[%x] failed to allocate work queue\n", doe_mb->cap_offset); - return ERR_PTR(-ENOMEM); + rc = -ENOMEM; + goto err_free; } - rc = devm_add_action_or_reset(dev, pci_doe_destroy_workqueue, doe_mb); - if (rc) - return ERR_PTR(rc); /* Reset the mailbox by issuing an abort */ rc = pci_doe_abort(doe_mb); if (rc) { pci_err(pdev, "[%x] failed to reset mailbox with abort command : %d\n", doe_mb->cap_offset, rc); - return ERR_PTR(rc); + goto err_destroy_wq; } /* * The state machine and the mailbox should be in sync now; - * Set up mailbox flush prior to using the mailbox to query protocols. + * Use the mailbox to query protocols. */ - rc = devm_add_action_or_reset(dev, pci_doe_flush_mb, doe_mb); - if (rc) - return ERR_PTR(rc); - rc = pci_doe_cache_protocols(doe_mb); if (rc) { pci_err(pdev, "[%x] failed to cache protocols : %d\n", doe_mb->cap_offset, rc); - return ERR_PTR(rc); + goto err_cancel; } return doe_mb; + +err_cancel: + pci_doe_cancel_tasks(doe_mb); + xa_destroy(&doe_mb->prots); +err_destroy_wq: + destroy_workqueue(doe_mb->work_queue); +err_free: + kfree(doe_mb); + return ERR_PTR(rc); +} + +/** + * pci_doe_destroy_mb() - Destroy a DOE mailbox object + * + * @doe_mb: DOE mailbox + * + * Destroy all internal data structures created for the DOE mailbox. + */ +static void pci_doe_destroy_mb(struct pci_doe_mb *doe_mb) +{ + pci_doe_cancel_tasks(doe_mb); + xa_destroy(&doe_mb->prots); + destroy_workqueue(doe_mb->work_queue); + kfree(doe_mb); } -EXPORT_SYMBOL_GPL(pcim_doe_create_mb); /** * pci_doe_supports_prot() - Return if the DOE instance supports the given @@ -494,7 +547,7 @@ EXPORT_SYMBOL_GPL(pcim_doe_create_mb); * * RETURNS: True if the DOE mailbox supports the protocol specified */ -bool pci_doe_supports_prot(struct pci_doe_mb *doe_mb, u16 vid, u8 type) +static bool pci_doe_supports_prot(struct pci_doe_mb *doe_mb, u16 vid, u8 type) { unsigned long index; void *entry; @@ -509,7 +562,6 @@ bool pci_doe_supports_prot(struct pci_doe_mb *doe_mb, u16 vid, u8 type) return false; } -EXPORT_SYMBOL_GPL(pci_doe_supports_prot); /** * pci_doe_submit_task() - Submit a task to be processed by the state machine @@ -530,19 +582,12 @@ EXPORT_SYMBOL_GPL(pci_doe_supports_prot); * * RETURNS: 0 when task has been successfully queued, -ERRNO on error */ -int pci_doe_submit_task(struct pci_doe_mb *doe_mb, struct pci_doe_task *task) +static int pci_doe_submit_task(struct pci_doe_mb *doe_mb, + struct pci_doe_task *task) { if (!pci_doe_supports_prot(doe_mb, task->prot.vid, task->prot.type)) return -EINVAL; - /* - * DOE requests must be a whole number of DW and the response needs to - * be big enough for at least 1 DW - */ - if (task->request_pl_sz % sizeof(__le32) || - task->response_pl_sz < sizeof(__le32)) - return -EINVAL; - if (test_bit(PCI_DOE_FLAG_DEAD, &doe_mb->flags)) return -EIO; @@ -551,4 +596,129 @@ int pci_doe_submit_task(struct pci_doe_mb *doe_mb, struct pci_doe_task *task) queue_work(doe_mb->work_queue, &task->work); return 0; } -EXPORT_SYMBOL_GPL(pci_doe_submit_task); + +/** + * pci_doe() - Perform Data Object Exchange + * + * @doe_mb: DOE Mailbox + * @vendor: Vendor ID + * @type: Data Object Type + * @request: Request payload + * @request_sz: Size of request payload (bytes) + * @response: Response payload + * @response_sz: Size of response payload (bytes) + * + * Submit @request to @doe_mb and store the @response. + * The DOE exchange is performed synchronously and may therefore sleep. + * + * Payloads are treated as opaque byte streams which are transmitted verbatim, + * without byte-swapping. If payloads contain little-endian register values, + * the caller is responsible for conversion with cpu_to_le32() / le32_to_cpu(). + * + * For convenience, arbitrary payload sizes are allowed even though PCIe r6.0 + * sec 6.30.1 specifies the Data Object Header 2 "Length" in dwords. The last + * (partial) dword is copied with byte granularity and padded with zeroes if + * necessary. Callers are thus relieved of using dword-sized bounce buffers. + * + * RETURNS: Length of received response or negative errno. + * Received data in excess of @response_sz is discarded. + * The length may be smaller than @response_sz and the caller + * is responsible for checking that. + */ +int pci_doe(struct pci_doe_mb *doe_mb, u16 vendor, u8 type, + const void *request, size_t request_sz, + void *response, size_t response_sz) +{ + DECLARE_COMPLETION_ONSTACK(c); + struct pci_doe_task task = { + .prot.vid = vendor, + .prot.type = type, + .request_pl = request, + .request_pl_sz = request_sz, + .response_pl = response, + .response_pl_sz = response_sz, + .complete = pci_doe_task_complete, + .private = &c, + }; + int rc; + + rc = pci_doe_submit_task(doe_mb, &task); + if (rc) + return rc; + + wait_for_completion(&c); + + return task.rv; +} +EXPORT_SYMBOL_GPL(pci_doe); + +/** + * pci_find_doe_mailbox() - Find Data Object Exchange mailbox + * + * @pdev: PCI device + * @vendor: Vendor ID + * @type: Data Object Type + * + * Find first DOE mailbox of a PCI device which supports the given protocol. + * + * RETURNS: Pointer to the DOE mailbox or NULL if none was found. + */ +struct pci_doe_mb *pci_find_doe_mailbox(struct pci_dev *pdev, u16 vendor, + u8 type) +{ + struct pci_doe_mb *doe_mb; + unsigned long index; + + xa_for_each(&pdev->doe_mbs, index, doe_mb) + if (pci_doe_supports_prot(doe_mb, vendor, type)) + return doe_mb; + + return NULL; +} +EXPORT_SYMBOL_GPL(pci_find_doe_mailbox); + +void pci_doe_init(struct pci_dev *pdev) +{ + struct pci_doe_mb *doe_mb; + u16 offset = 0; + int rc; + + xa_init(&pdev->doe_mbs); + + while ((offset = pci_find_next_ext_capability(pdev, offset, + PCI_EXT_CAP_ID_DOE))) { + doe_mb = pci_doe_create_mb(pdev, offset); + if (IS_ERR(doe_mb)) { + pci_err(pdev, "[%x] failed to create mailbox: %ld\n", + offset, PTR_ERR(doe_mb)); + continue; + } + + rc = xa_insert(&pdev->doe_mbs, offset, doe_mb, GFP_KERNEL); + if (rc) { + pci_err(pdev, "[%x] failed to insert mailbox: %d\n", + offset, rc); + pci_doe_destroy_mb(doe_mb); + } + } +} + +void pci_doe_destroy(struct pci_dev *pdev) +{ + struct pci_doe_mb *doe_mb; + unsigned long index; + + xa_for_each(&pdev->doe_mbs, index, doe_mb) + pci_doe_destroy_mb(doe_mb); + + xa_destroy(&pdev->doe_mbs); +} + +void pci_doe_disconnected(struct pci_dev *pdev) +{ + struct pci_doe_mb *doe_mb; + unsigned long index; + + xa_for_each(&pdev->doe_mbs, index, doe_mb) + pci_doe_cancel_tasks(doe_mb); +} diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 67005a0ee381..2475098f6518 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -311,6 +311,16 @@ struct pci_sriov { bool drivers_autoprobe; /* Auto probing of VFs by driver */ }; +#ifdef CONFIG_PCI_DOE +void pci_doe_init(struct pci_dev *pdev); +void pci_doe_destroy(struct pci_dev *pdev); +void pci_doe_disconnected(struct pci_dev *pdev); +#else +static inline void pci_doe_init(struct pci_dev *pdev) { } +static inline void pci_doe_destroy(struct pci_dev *pdev) { } +static inline void pci_doe_disconnected(struct pci_dev *pdev) { } +#endif + /** * pci_dev_set_io_state - Set the new error state if possible. * @@ -347,6 +357,7 @@ static inline bool pci_dev_set_io_state(struct pci_dev *dev, static inline int pci_dev_set_disconnected(struct pci_dev *dev, void *unused) { pci_dev_set_io_state(dev, pci_channel_io_perm_failure); + pci_doe_disconnected(dev); return 0; } diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 9123bafab451..0b2826c4a832 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2479,6 +2479,7 @@ static void pci_init_capabilities(struct pci_dev *dev) pci_aer_init(dev); /* Advanced Error Reporting */ pci_dpc_init(dev); /* Downstream Port Containment */ pci_rcec_init(dev); /* Root Complex Event Collector */ + pci_doe_init(dev); /* Data Object Exchange */ pcie_report_downtraining(dev); pci_init_reset_methods(dev); diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c index 30a787d45d2e..d68aee29386b 100644 --- a/drivers/pci/remove.c +++ b/drivers/pci/remove.c @@ -38,6 +38,7 @@ static void pci_destroy_dev(struct pci_dev *dev) list_del(&dev->bus_list); up_write(&pci_bus_sem); + pci_doe_destroy(dev); pcie_aspm_exit_link_state(dev); pci_bridge_d3_update(dev); pci_free_resources(dev); |