From: Ira Weiny <[email protected]> DC DAX regions must allow memory to be added or removed dynamically. In addition to the quantity of memory available the, location of the memory within a DC partition is dynamic, based on the extents offered by a device. CXL DAX regions must accommodate the dynamic movement of this memory in the management of DAX regions and devices.
Introduce the concept of a dynamic DAX region. Introduce create_dynamic_ram_a_region() sysfs entry to create such regions. Special case DC-capable regions to create a 0 sized seed DAX device to maintain compatibility which requires a default DAX device to hold a region reference. Indicate 0 byte available capacity until such time that capacity is added. Dynamic regions complicate the range mapping of dax devices. There is no known use case for range mapping on dynamic regions. Avoid the complication by preventing range mapping of dax devices on dynamic regions. Interleaving is deferred for now. Add checks. Based on an original patch by Navneet Singh. Signed-off-by: Ira Weiny <[email protected]> --- Changes: [anisa: rebase] [anisa: change "sparse" naming conventions and to "dynamic"] --- Documentation/ABI/testing/sysfs-bus-cxl | 22 ++++++++--------- drivers/cxl/core/core.h | 11 +++++++++ drivers/cxl/core/port.c | 1 + drivers/cxl/core/region.c | 33 +++++++++++++++++++++++-- drivers/cxl/core/region_dax.c | 6 +++++ drivers/dax/bus.c | 10 ++++++++ drivers/dax/bus.h | 1 + drivers/dax/cxl.c | 17 +++++++++++-- 8 files changed, 86 insertions(+), 15 deletions(-) diff --git a/Documentation/ABI/testing/sysfs-bus-cxl b/Documentation/ABI/testing/sysfs-bus-cxl index c604c7ca6432..3080aef9ad67 100644 --- a/Documentation/ABI/testing/sysfs-bus-cxl +++ b/Documentation/ABI/testing/sysfs-bus-cxl @@ -434,20 +434,20 @@ Description: interleave_granularity). -What: /sys/bus/cxl/devices/decoderX.Y/create_{pmem,ram}_region -Date: May, 2022, January, 2023 -KernelVersion: v6.0 (pmem), v6.3 (ram) +What: /sys/bus/cxl/devices/decoderX.Y/create_{pmem,ram,dynamic_ram_a}_region +Date: May, 2022, January, 2023, May 2025 +KernelVersion: v6.0 (pmem), v6.3 (ram), v6.16 (dynamic_ram_a) Contact: [email protected] Description: (RW) Write a string in the form 'regionZ' to start the process - of defining a new persistent, or volatile memory region - (interleave-set) within the decode range bounded by root decoder - 'decoderX.Y'. The value written must match the current value - returned from reading this attribute. An atomic compare exchange - operation is done on write to assign the requested id to a - region and allocate the region-id for the next creation attempt. - EBUSY is returned if the region name written does not match the - current cached value. + of defining a new persistent, volatile, or dynamic RAM memory + region (interleave-set) within the decode range bounded by root + decoder 'decoderX.Y'. The value written must match the current + value returned from reading this attribute. An atomic compare + exchange operation is done on write to assign the requested id + to a region and allocate the region-id for the next creation + attempt. EBUSY is returned if the region name written does not + match the current cached value. What: /sys/bus/cxl/devices/decoderX.Y/delete_region diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h index 82ca3a476708..8881cc9323e0 100644 --- a/drivers/cxl/core/core.h +++ b/drivers/cxl/core/core.h @@ -6,6 +6,7 @@ #include <cxl/mailbox.h> #include <linux/rwsem.h> +#include <cxlmem.h> extern const struct device_type cxl_nvdimm_bridge_type; extern const struct device_type cxl_nvdimm_type; @@ -18,6 +19,15 @@ enum cxl_detach_mode { DETACH_INVALIDATE, }; +static inline struct cxl_memdev_state * +cxled_to_mds(struct cxl_endpoint_decoder *cxled) +{ + struct cxl_memdev *cxlmd = cxled_to_memdev(cxled); + struct cxl_dev_state *cxlds = cxlmd->cxlds; + + return container_of(cxlds, struct cxl_memdev_state, cxlds); +} + #ifdef CONFIG_CXL_REGION struct cxl_region_context { @@ -29,6 +39,7 @@ struct cxl_region_context { extern struct device_attribute dev_attr_create_pmem_region; extern struct device_attribute dev_attr_create_ram_region; +extern struct device_attribute dev_attr_create_dynamic_ram_a_region; extern struct device_attribute dev_attr_delete_region; extern struct device_attribute dev_attr_region; extern const struct device_type cxl_pmem_region_type; diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index a7f71f36531f..2d33001dac26 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -337,6 +337,7 @@ static struct attribute *cxl_decoder_root_attrs[] = { &dev_attr_qos_class.attr, SET_CXL_REGION_ATTR(create_pmem_region) SET_CXL_REGION_ATTR(create_ram_region) + SET_CXL_REGION_ATTR(create_dynamic_ram_a_region) SET_CXL_REGION_ATTR(delete_region) NULL, }; diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index edc267c6cf77..7561bf3d8af8 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -493,6 +493,11 @@ static int set_interleave_ways(struct cxl_region *cxlr, int val) int save, rc; u8 iw; + if (cxlr->mode == CXL_PARTMODE_DYNAMIC_RAM_A && val != 1) { + dev_err(&cxlr->dev, "Interleaving and DCD not supported\n"); + return -EINVAL; + } + rc = ways_to_eiw(val, &iw); if (rc) return rc; @@ -2389,6 +2394,7 @@ static size_t store_targetN(struct cxl_region *cxlr, const char *buf, int pos, if (sysfs_streq(buf, "\n")) rc = detach_target(cxlr, pos); else { + struct cxl_endpoint_decoder *cxled; struct device *dev; dev = bus_find_device_by_name(&cxl_bus_type, NULL, buf); @@ -2400,8 +2406,14 @@ static size_t store_targetN(struct cxl_region *cxlr, const char *buf, int pos, goto out; } - rc = attach_target(cxlr, to_cxl_endpoint_decoder(dev), pos, - TASK_INTERRUPTIBLE); + cxled = to_cxl_endpoint_decoder(dev); + if (cxlr->mode == CXL_PARTMODE_DYNAMIC_RAM_A && + !cxl_dcd_supported(cxled_to_mds(cxled))) { + dev_dbg(dev, "DCD unsupported\n"); + rc = -EINVAL; + goto out; + } + rc = attach_target(cxlr, cxled, pos, TASK_INTERRUPTIBLE); out: put_device(dev); } @@ -2750,6 +2762,7 @@ static struct cxl_region *__create_region(struct cxl_root_decoder *cxlrd, switch (mode) { case CXL_PARTMODE_RAM: case CXL_PARTMODE_PMEM: + case CXL_PARTMODE_DYNAMIC_RAM_A: break; default: dev_err(&cxlrd->cxlsd.cxld.dev, "unsupported mode %d\n", mode); @@ -2802,6 +2815,21 @@ static ssize_t create_ram_region_store(struct device *dev, } DEVICE_ATTR_RW(create_ram_region); +static ssize_t create_dynamic_ram_a_region_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + return __create_region_show(to_cxl_root_decoder(dev), buf); +} + +static ssize_t create_dynamic_ram_a_region_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + return create_region_store(dev, buf, len, CXL_PARTMODE_DYNAMIC_RAM_A); +} +DEVICE_ATTR_RW(create_dynamic_ram_a_region); + static ssize_t region_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -4081,6 +4109,7 @@ static int cxl_region_probe(struct device *dev) return devm_cxl_add_pmem_region(cxlr); case CXL_PARTMODE_RAM: + case CXL_PARTMODE_DYNAMIC_RAM_A: rc = devm_cxl_region_edac_register(cxlr); if (rc) dev_dbg(&cxlr->dev, "CXL EDAC registration for region_id=%d failed\n", diff --git a/drivers/cxl/core/region_dax.c b/drivers/cxl/core/region_dax.c index de04f78f6ad8..d6bf69155827 100644 --- a/drivers/cxl/core/region_dax.c +++ b/drivers/cxl/core/region_dax.c @@ -84,6 +84,12 @@ int devm_cxl_add_dax_region(struct cxl_region *cxlr) struct device *dev; int rc; + if (cxlr->mode == CXL_PARTMODE_DYNAMIC_RAM_A && + cxlr->params.interleave_ways != 1) { + dev_err(&cxlr->dev, "Interleaving DC not supported\n"); + return -EINVAL; + } + struct cxl_dax_region *cxlr_dax __free(put_cxl_dax_region) = cxl_dax_region_alloc(cxlr); if (IS_ERR(cxlr_dax)) diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c index 95aee2a037fb..b0c2162b5e37 100644 --- a/drivers/dax/bus.c +++ b/drivers/dax/bus.c @@ -181,6 +181,11 @@ static bool is_static(struct dax_region *dax_region) return (dax_region->res.flags & IORESOURCE_DAX_STATIC) != 0; } +static bool is_dynamic(struct dax_region *dax_region) +{ + return (dax_region->res.flags & IORESOURCE_DAX_DCD) != 0; +} + bool static_dev_dax(struct dev_dax *dev_dax) { return is_static(dev_dax->region); @@ -304,6 +309,9 @@ static unsigned long long dax_region_avail_size(struct dax_region *dax_region) lockdep_assert_held(&dax_region_rwsem); + if (is_dynamic(dax_region)) + return 0; + for_each_dax_region_resource(dax_region, res) size -= resource_size(res); return size; @@ -1389,6 +1397,8 @@ static umode_t dev_dax_visible(struct kobject *kobj, struct attribute *a, int n) return 0; if (a == &dev_attr_mapping.attr && is_static(dax_region)) return 0; + if (a == &dev_attr_mapping.attr && is_dynamic(dax_region)) + return 0; if ((a == &dev_attr_align.attr || a == &dev_attr_size.attr) && is_static(dax_region)) return 0444; diff --git a/drivers/dax/bus.h b/drivers/dax/bus.h index 5909171a4428..6e739bfab932 100644 --- a/drivers/dax/bus.h +++ b/drivers/dax/bus.h @@ -15,6 +15,7 @@ struct dax_region; /* dax bus specific ioresource flags */ #define IORESOURCE_DAX_STATIC BIT(0) #define IORESOURCE_DAX_KMEM BIT(1) +#define IORESOURCE_DAX_DCD BIT(2) struct dax_region *alloc_dax_region(struct device *parent, int region_id, struct range *range, int target_node, unsigned int align, diff --git a/drivers/dax/cxl.c b/drivers/dax/cxl.c index 3ab39b77843d..f58fe992aa8d 100644 --- a/drivers/dax/cxl.c +++ b/drivers/dax/cxl.c @@ -13,19 +13,32 @@ static int cxl_dax_region_probe(struct device *dev) struct cxl_region *cxlr = cxlr_dax->cxlr; struct dax_region *dax_region; struct dev_dax_data data; + resource_size_t dev_size; + unsigned long flags; if (nid == NUMA_NO_NODE) nid = memory_add_physaddr_to_nid(cxlr_dax->hpa_range.start); + if (cxlr->mode == CXL_PARTMODE_DYNAMIC_RAM_A) + flags = IORESOURCE_DAX_DCD; + else + flags = IORESOURCE_DAX_KMEM; + dax_region = alloc_dax_region(dev, cxlr->id, &cxlr_dax->hpa_range, nid, - PMD_SIZE, IORESOURCE_DAX_KMEM); + PMD_SIZE, flags); if (!dax_region) return -ENOMEM; + if (cxlr->mode == CXL_PARTMODE_DYNAMIC_RAM_A) + /* Add empty seed dax device */ + dev_size = 0; + else + dev_size = range_len(&cxlr_dax->hpa_range); + data = (struct dev_dax_data) { .dax_region = dax_region, .id = -1, - .size = range_len(&cxlr_dax->hpa_range), + .size = dev_size, .memmap_on_memory = true, }; -- 2.43.0
