cxl for 6.0

- Introduce a 'struct cxl_region' object with support for provisioning
   and assembling persistent memory regions.
 
 - Introduce alloc_free_mem_region() to accompany the existing
   request_free_mem_region() as a method to allocate physical memory
   capacity out of an existing resource.
 
 - Export insert_resource_expand_to_fit() for the CXL subsystem to
   late-publish CXL platform windows in iomem_resource.
 
 - Add a polled mode PCI DOE (Data Object Exchange) driver service and
   use it in cxl_pci to retrieve the CDAT (Coherent Device Attribute
   Table).
 -----BEGIN PGP SIGNATURE-----
 
 iHUEABYKAB0WIQSbo+XnGs+rwLz9XGXfioYZHlFsZwUCYvLYmAAKCRDfioYZHlFs
 Z0pbAQC/3j+WriWpU7CdhrnZI1Wqn+x5IIklF0Lc4/f6LwGZtAEAsSbLpItzvwqx
 M/rcLaeLpwYlgvS1JjdsuQ2VQ7KOtAs=
 =ehNT
 -----END PGP SIGNATURE-----

Merge tag 'cxl-for-6.0' of git://git.kernel.org/pub/scm/linux/kernel/git/cxl/cxl

Pull cxl updates from Dan Williams:
 "Compute Express Link (CXL) updates for 6.0:

   - Introduce a 'struct cxl_region' object with support for
     provisioning and assembling persistent memory regions.

   - Introduce alloc_free_mem_region() to accompany the existing
     request_free_mem_region() as a method to allocate physical memory
     capacity out of an existing resource.

   - Export insert_resource_expand_to_fit() for the CXL subsystem to
     late-publish CXL platform windows in iomem_resource.

   - Add a polled mode PCI DOE (Data Object Exchange) driver service and
     use it in cxl_pci to retrieve the CDAT (Coherent Device Attribute
     Table)"

* tag 'cxl-for-6.0' of git://git.kernel.org/pub/scm/linux/kernel/git/cxl/cxl: (74 commits)
  cxl/hdm: Fix skip allocations vs multiple pmem allocations
  cxl/region: Disallow region granularity != window granularity
  cxl/region: Fix x1 interleave to greater than x1 interleave routing
  cxl/region: Move HPA setup to cxl_region_attach()
  cxl/region: Fix decoder interleave programming
  Documentation: cxl: remove dangling kernel-doc reference
  cxl/region: describe targets and nr_targets members of cxl_region_params
  cxl/regions: add padding for cxl_rr_ep_add nested lists
  cxl/region: Fix IS_ERR() vs NULL check
  cxl/region: Fix region reference target accounting
  cxl/region: Fix region commit uninitialized variable warning
  cxl/region: Fix port setup uninitialized variable warnings
  cxl/region: Stop initializing interleave granularity
  cxl/hdm: Fix DPA reservation vs cxl_endpoint_decoder lifetime
  cxl/acpi: Minimize granularity for x1 interleaves
  cxl/region: Delete 'region' attribute from root decoders
  cxl/acpi: Autoload driver for 'cxl_acpi' test devices
  cxl/region: decrement ->nr_targets on error in cxl_region_attach()
  cxl/region: prevent underflow in ways_to_cxl()
  cxl/region: uninitialized variable in alloc_hpa()
  ...
This commit is contained in:
Linus Torvalds 2022-08-10 11:07:26 -07:00
commit c235698355
39 changed files with 5508 additions and 586 deletions

View file

@ -141,6 +141,7 @@ enum {
IORES_DESC_DEVICE_PRIVATE_MEMORY = 6,
IORES_DESC_RESERVED = 7,
IORES_DESC_SOFT_RESERVED = 8,
IORES_DESC_CXL = 9,
};
/*
@ -329,6 +330,8 @@ struct resource *devm_request_free_mem_region(struct device *dev,
struct resource *base, unsigned long size);
struct resource *request_free_mem_region(struct resource *base,
unsigned long size, const char *name);
struct resource *alloc_free_mem_region(struct resource *base,
unsigned long size, unsigned long align, const char *name);
static inline void irqresource_disabled(struct resource *res, u32 irq)
{

View file

@ -59,6 +59,9 @@ enum {
/* Platform provides asynchronous flush mechanism */
ND_REGION_ASYNC = 3,
/* Region was created by CXL subsystem */
ND_REGION_CXL = 4,
/* mark newly adjusted resources as requiring a label update */
DPA_RESOURCE_ADJUSTED = 1 << 0,
};
@ -122,6 +125,7 @@ struct nd_region_desc {
int numa_node;
int target_node;
unsigned long flags;
int memregion;
struct device_node *of_node;
int (*flush)(struct nd_region *nd_region, struct bio *bio);
};
@ -259,6 +263,7 @@ static inline struct nvdimm *nvdimm_create(struct nvdimm_bus *nvdimm_bus,
cmd_mask, num_flush, flush_wpq, NULL, NULL, NULL);
}
void nvdimm_delete(struct nvdimm *nvdimm);
void nvdimm_region_delete(struct nd_region *nd_region);
const struct nd_cmd_desc *nd_cmd_dimm_desc(int cmd);
const struct nd_cmd_desc *nd_cmd_bus_desc(int cmd);

77
include/linux/pci-doe.h Normal file
View file

@ -0,0 +1,77 @@
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Data Object Exchange
* PCIe r6.0, sec 6.30 DOE
*
* Copyright (C) 2021 Huawei
* Jonathan Cameron <Jonathan.Cameron@huawei.com>
*
* Copyright (C) 2022 Intel Corporation
* Ira Weiny <ira.weiny@intel.com>
*/
#ifndef LINUX_PCI_DOE_H
#define LINUX_PCI_DOE_H
struct pci_doe_protocol {
u16 vid;
u8 type;
};
struct pci_doe_mb;
/**
* 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
*
* The payload sizes and rv are specified in bytes with the following
* restrictions concerning the protocol.
*
* 1) The request_pl_sz must be a multiple of double words (4 bytes)
* 2) The response_pl_sz must be >= a single double word (4 bytes)
* 3) rv is returned as bytes but it will be a multiple of double words
*
* NOTE there is no need for the caller to initialize work or doe_mb.
*/
struct pci_doe_task {
struct pci_doe_protocol prot;
u32 *request_pl;
size_t request_pl_sz;
u32 *response_pl;
size_t response_pl_sz;
int rv;
void (*complete)(struct pci_doe_task *task);
void *private;
/* No need for the user to initialize these fields */
struct work_struct work;
struct pci_doe_mb *doe_mb;
};
/**
* pci_doe_for_each_off - Iterate each DOE capability
* @pdev: struct pci_dev to iterate
* @off: u16 of config space offset of each mailbox capability found
*/
#define pci_doe_for_each_off(pdev, off) \
for (off = pci_find_next_ext_capability(pdev, off, \
PCI_EXT_CAP_ID_DOE); \
off > 0; \
off = pci_find_next_ext_capability(pdev, off, \
PCI_EXT_CAP_ID_DOE))
struct pci_doe_mb *pcim_doe_create_mb(struct pci_dev *pdev, u16 cap_offset);
bool pci_doe_supports_prot(struct pci_doe_mb *doe_mb, u16 vid, u8 type);
int pci_doe_submit_task(struct pci_doe_mb *doe_mb, struct pci_doe_task *task);
#endif

View file

@ -151,6 +151,7 @@
#define PCI_CLASS_OTHERS 0xff
/* Vendors and devices. Sort key: vendor first, device next. */
#define PCI_VENDOR_ID_PCI_SIG 0x0001
#define PCI_VENDOR_ID_LOONGSON 0x0014

View file

@ -235,6 +235,22 @@ struct bin_attribute bin_attr_##_name = __BIN_ATTR_WO(_name, _size)
#define BIN_ATTR_RW(_name, _size) \
struct bin_attribute bin_attr_##_name = __BIN_ATTR_RW(_name, _size)
#define __BIN_ATTR_ADMIN_RO(_name, _size) { \
.attr = { .name = __stringify(_name), .mode = 0400 }, \
.read = _name##_read, \
.size = _size, \
}
#define __BIN_ATTR_ADMIN_RW(_name, _size) \
__BIN_ATTR(_name, 0600, _name##_read, _name##_write, _size)
#define BIN_ATTR_ADMIN_RO(_name, _size) \
struct bin_attribute bin_attr_##_name = __BIN_ATTR_ADMIN_RO(_name, _size)
#define BIN_ATTR_ADMIN_RW(_name, _size) \
struct bin_attribute bin_attr_##_name = __BIN_ATTR_ADMIN_RW(_name, _size)
struct sysfs_ops {
ssize_t (*show)(struct kobject *, struct attribute *, char *);
ssize_t (*store)(struct kobject *, struct attribute *, const char *, size_t);

View file

@ -737,7 +737,8 @@
#define PCI_EXT_CAP_ID_DVSEC 0x23 /* Designated Vendor-Specific */
#define PCI_EXT_CAP_ID_DLF 0x25 /* Data Link Feature */
#define PCI_EXT_CAP_ID_PL_16GT 0x26 /* Physical Layer 16.0 GT/s */
#define PCI_EXT_CAP_ID_MAX PCI_EXT_CAP_ID_PL_16GT
#define PCI_EXT_CAP_ID_DOE 0x2E /* Data Object Exchange */
#define PCI_EXT_CAP_ID_MAX PCI_EXT_CAP_ID_DOE
#define PCI_EXT_CAP_DSN_SIZEOF 12
#define PCI_EXT_CAP_MCAST_ENDPOINT_SIZEOF 40
@ -1103,4 +1104,30 @@
#define PCI_PL_16GT_LE_CTRL_USP_TX_PRESET_MASK 0x000000F0
#define PCI_PL_16GT_LE_CTRL_USP_TX_PRESET_SHIFT 4
/* Data Object Exchange */
#define PCI_DOE_CAP 0x04 /* DOE Capabilities Register */
#define PCI_DOE_CAP_INT_SUP 0x00000001 /* Interrupt Support */
#define PCI_DOE_CAP_INT_MSG_NUM 0x00000ffe /* Interrupt Message Number */
#define PCI_DOE_CTRL 0x08 /* DOE Control Register */
#define PCI_DOE_CTRL_ABORT 0x00000001 /* DOE Abort */
#define PCI_DOE_CTRL_INT_EN 0x00000002 /* DOE Interrupt Enable */
#define PCI_DOE_CTRL_GO 0x80000000 /* DOE Go */
#define PCI_DOE_STATUS 0x0c /* DOE Status Register */
#define PCI_DOE_STATUS_BUSY 0x00000001 /* DOE Busy */
#define PCI_DOE_STATUS_INT_STATUS 0x00000002 /* DOE Interrupt Status */
#define PCI_DOE_STATUS_ERROR 0x00000004 /* DOE Error */
#define PCI_DOE_STATUS_DATA_OBJECT_READY 0x80000000 /* Data Object Ready */
#define PCI_DOE_WRITE 0x10 /* DOE Write Data Mailbox Register */
#define PCI_DOE_READ 0x14 /* DOE Read Data Mailbox Register */
/* DOE Data Object - note not actually registers */
#define PCI_DOE_DATA_OBJECT_HEADER_1_VID 0x0000ffff
#define PCI_DOE_DATA_OBJECT_HEADER_1_TYPE 0x00ff0000
#define PCI_DOE_DATA_OBJECT_HEADER_2_LENGTH 0x0003ffff
#define PCI_DOE_DATA_OBJECT_DISC_REQ_3_INDEX 0x000000ff
#define PCI_DOE_DATA_OBJECT_DISC_RSP_3_VID 0x0000ffff
#define PCI_DOE_DATA_OBJECT_DISC_RSP_3_PROTOCOL 0x00ff0000
#define PCI_DOE_DATA_OBJECT_DISC_RSP_3_NEXT_INDEX 0xff000000
#endif /* LINUX_PCI_REGS_H */