return (dax_region->res.flags & IORESOURCE_DAX_STATIC) != 0;
}
+static u64 dev_dax_size(struct dev_dax *dev_dax)
+{
+ u64 size = 0;
+ int i;
+
+ device_lock_assert(&dev_dax->dev);
+
+ for (i = 0; i < dev_dax->nr_range; i++)
+ size += range_len(&dev_dax->ranges[i].range);
+
+ return size;
+}
+
static int dax_bus_probe(struct device *dev)
{
struct dax_device_driver *dax_drv = to_dax_drv(dev->driver);
struct dev_dax *dev_dax = to_dev_dax(dev);
struct dax_region *dax_region = dev_dax->region;
- struct range *range = &dev_dax->range;
int rc;
- if (range_len(range) == 0 || dev_dax->id < 0)
+ if (dev_dax_size(dev_dax) == 0 || dev_dax->id < 0)
return -ENXIO;
rc = dax_drv->probe(dev_dax);
}
EXPORT_SYMBOL_GPL(kill_dev_dax);
-static void free_dev_dax_range(struct dev_dax *dev_dax)
+static void free_dev_dax_ranges(struct dev_dax *dev_dax)
{
struct dax_region *dax_region = dev_dax->region;
- struct range *range = &dev_dax->range;
+ int i;
device_lock_assert(dax_region->dev);
- if (range_len(range))
+ for (i = 0; i < dev_dax->nr_range; i++) {
+ struct range *range = &dev_dax->ranges[i].range;
+
__release_region(&dax_region->res, range->start,
range_len(range));
+ }
+ dev_dax->nr_range = 0;
}
static void unregister_dev_dax(void *dev)
dev_dbg(dev, "%s\n", __func__);
kill_dev_dax(dev_dax);
- free_dev_dax_range(dev_dax);
+ free_dev_dax_ranges(dev_dax);
device_del(dev);
put_device(dev);
}
device_lock(dev);
device_lock(victim);
dev_dax = to_dev_dax(victim);
- if (victim->driver || range_len(&dev_dax->range))
+ if (victim->driver || dev_dax_size(dev_dax))
rc = -EBUSY;
else {
/*
struct dax_region *dax_region = dev_dax->region;
struct resource *res = &dax_region->res;
struct device *dev = &dev_dax->dev;
+ struct dev_dax_range *ranges;
+ unsigned long pgoff = 0;
struct resource *alloc;
+ int i;
device_lock_assert(dax_region->dev);
/* handle the seed alloc special case */
if (!size) {
- dev_dax->range = (struct range) {
- .start = res->start,
- .end = res->start - 1,
- };
+ if (dev_WARN_ONCE(dev, dev_dax->nr_range,
+ "0-size allocation must be first\n"))
+ return -EBUSY;
+ /* nr_range == 0 is elsewhere special cased as 0-size device */
return 0;
}
+ ranges = krealloc(dev_dax->ranges, sizeof(*ranges)
+ * (dev_dax->nr_range + 1), GFP_KERNEL);
+ if (!ranges)
+ return -ENOMEM;
+
alloc = __request_region(res, start, size, dev_name(dev), 0);
- if (!alloc)
+ if (!alloc) {
+ /*
+ * If this was an empty set of ranges nothing else
+ * will release @ranges, so do it now.
+ */
+ if (!dev_dax->nr_range) {
+ kfree(ranges);
+ ranges = NULL;
+ }
+ dev_dax->ranges = ranges;
return -ENOMEM;
+ }
- dev_dax->range = (struct range) {
- .start = alloc->start,
- .end = alloc->end,
+ for (i = 0; i < dev_dax->nr_range; i++)
+ pgoff += PHYS_PFN(range_len(&ranges[i].range));
+ dev_dax->ranges = ranges;
+ ranges[dev_dax->nr_range++] = (struct dev_dax_range) {
+ .pgoff = pgoff,
+ .range = {
+ .start = alloc->start,
+ .end = alloc->end,
+ },
};
+ dev_dbg(dev, "alloc range[%d]: %pa:%pa\n", dev_dax->nr_range - 1,
+ &alloc->start, &alloc->end);
+
return 0;
}
static int adjust_dev_dax_range(struct dev_dax *dev_dax, struct resource *res, resource_size_t size)
{
+ int last_range = dev_dax->nr_range - 1;
+ struct dev_dax_range *dax_range = &dev_dax->ranges[last_range];
struct dax_region *dax_region = dev_dax->region;
- struct range *range = &dev_dax->range;
- int rc = 0;
+ bool is_shrink = resource_size(res) > size;
+ struct range *range = &dax_range->range;
+ struct device *dev = &dev_dax->dev;
+ int rc;
device_lock_assert(dax_region->dev);
- if (size)
- rc = adjust_resource(res, range->start, size);
- else
- __release_region(&dax_region->res, range->start, range_len(range));
+ if (dev_WARN_ONCE(dev, !size, "deletion is handled by dev_dax_shrink\n"))
+ return -EINVAL;
+
+ rc = adjust_resource(res, range->start, size);
if (rc)
return rc;
- dev_dax->range = (struct range) {
+ *range = (struct range) {
.start = range->start,
.end = range->start + size - 1,
};
+ dev_dbg(dev, "%s range[%d]: %#llx:%#llx\n", is_shrink ? "shrink" : "extend",
+ last_range, (unsigned long long) range->start,
+ (unsigned long long) range->end);
+
return 0;
}
struct device_attribute *attr, char *buf)
{
struct dev_dax *dev_dax = to_dev_dax(dev);
- unsigned long long size = range_len(&dev_dax->range);
+ unsigned long long size;
+
+ device_lock(dev);
+ size = dev_dax_size(dev_dax);
+ device_unlock(dev);
return sprintf(buf, "%llu\n", size);
}
static int dev_dax_shrink(struct dev_dax *dev_dax, resource_size_t size)
{
+ resource_size_t to_shrink = dev_dax_size(dev_dax) - size;
struct dax_region *dax_region = dev_dax->region;
- struct range *range = &dev_dax->range;
- struct resource *res, *adjust = NULL;
struct device *dev = &dev_dax->dev;
-
- for_each_dax_region_resource(dax_region, res)
- if (strcmp(res->name, dev_name(dev)) == 0
- && res->start == range->start) {
- adjust = res;
- break;
+ int i;
+
+ for (i = dev_dax->nr_range - 1; i >= 0; i--) {
+ struct range *range = &dev_dax->ranges[i].range;
+ struct resource *adjust = NULL, *res;
+ resource_size_t shrink;
+
+ shrink = min_t(u64, to_shrink, range_len(range));
+ if (shrink >= range_len(range)) {
+ __release_region(&dax_region->res, range->start,
+ range_len(range));
+ dev_dax->nr_range--;
+ dev_dbg(dev, "delete range[%d]: %#llx:%#llx\n", i,
+ (unsigned long long) range->start,
+ (unsigned long long) range->end);
+ to_shrink -= shrink;
+ if (!to_shrink)
+ break;
+ continue;
}
- if (dev_WARN_ONCE(dev, !adjust, "failed to find matching resource\n"))
- return -ENXIO;
- return adjust_dev_dax_range(dev_dax, adjust, size);
+ for_each_dax_region_resource(dax_region, res)
+ if (strcmp(res->name, dev_name(dev)) == 0
+ && res->start == range->start) {
+ adjust = res;
+ break;
+ }
+
+ if (dev_WARN_ONCE(dev, !adjust || i != dev_dax->nr_range - 1,
+ "failed to find matching resource\n"))
+ return -ENXIO;
+ return adjust_dev_dax_range(dev_dax, adjust, range_len(range)
+ - shrink);
+ }
+ return 0;
+}
+
+/*
+ * Only allow adjustments that preserve the relative pgoff of existing
+ * allocations. I.e. the dev_dax->ranges array is ordered by increasing pgoff.
+ */
+static bool adjust_ok(struct dev_dax *dev_dax, struct resource *res)
+{
+ struct dev_dax_range *last;
+ int i;
+
+ if (dev_dax->nr_range == 0)
+ return false;
+ if (strcmp(res->name, dev_name(&dev_dax->dev)) != 0)
+ return false;
+ last = &dev_dax->ranges[dev_dax->nr_range - 1];
+ if (last->range.start != res->start || last->range.end != res->end)
+ return false;
+ for (i = 0; i < dev_dax->nr_range - 1; i++) {
+ struct dev_dax_range *dax_range = &dev_dax->ranges[i];
+
+ if (dax_range->pgoff > last->pgoff)
+ return false;
+ }
+
+ return true;
}
static ssize_t dev_dax_resize(struct dax_region *dax_region,
struct dev_dax *dev_dax, resource_size_t size)
{
resource_size_t avail = dax_region_avail_size(dax_region), to_alloc;
- resource_size_t dev_size = range_len(&dev_dax->range);
+ resource_size_t dev_size = dev_dax_size(dev_dax);
struct resource *region_res = &dax_region->res;
struct device *dev = &dev_dax->dev;
- const char *name = dev_name(dev);
struct resource *res, *first;
+ resource_size_t alloc = 0;
+ int rc;
if (dev->driver)
return -EBUSY;
* may involve adjusting the end of an existing resource, or
* allocating a new resource.
*/
+retry:
first = region_res->child;
if (!first)
return alloc_dev_dax_range(dev_dax, dax_region->res.start, to_alloc);
- for (res = first; to_alloc && res; res = res->sibling) {
+
+ rc = -ENOSPC;
+ for (res = first; res; res = res->sibling) {
struct resource *next = res->sibling;
- resource_size_t free;
/* space at the beginning of the region */
- free = 0;
- if (res == first && res->start > dax_region->res.start)
- free = res->start - dax_region->res.start;
- if (free >= to_alloc && dev_size == 0)
- return alloc_dev_dax_range(dev_dax, dax_region->res.start, to_alloc);
+ if (res == first && res->start > dax_region->res.start) {
+ alloc = min(res->start - dax_region->res.start, to_alloc);
+ rc = alloc_dev_dax_range(dev_dax, dax_region->res.start, alloc);
+ break;
+ }
- free = 0;
+ alloc = 0;
/* space between allocations */
if (next && next->start > res->end + 1)
- free = next->start - res->end + 1;
+ alloc = min(next->start - (res->end + 1), to_alloc);
/* space at the end of the region */
- if (free < to_alloc && !next && res->end < region_res->end)
- free = region_res->end - res->end;
+ if (!alloc && !next && res->end < region_res->end)
+ alloc = min(region_res->end - res->end, to_alloc);
- if (free >= to_alloc && strcmp(name, res->name) == 0)
- return adjust_dev_dax_range(dev_dax, res, resource_size(res) + to_alloc);
- else if (free >= to_alloc && dev_size == 0)
- return alloc_dev_dax_range(dev_dax, res->end + 1, to_alloc);
+ if (!alloc)
+ continue;
+
+ if (adjust_ok(dev_dax, res)) {
+ rc = adjust_dev_dax_range(dev_dax, res, resource_size(res) + alloc);
+ break;
+ }
+ rc = alloc_dev_dax_range(dev_dax, res->end + 1, alloc);
+ break;
}
- return -ENOSPC;
+ if (rc)
+ return rc;
+ to_alloc -= alloc;
+ if (to_alloc)
+ goto retry;
+ return 0;
}
static ssize_t size_store(struct device *dev, struct device_attribute *attr,
struct device_attribute *attr, char *buf)
{
struct dev_dax *dev_dax = to_dev_dax(dev);
+ struct dax_region *dax_region = dev_dax->region;
+ unsigned long long start;
+
+ if (dev_dax->nr_range < 1)
+ start = dax_region->res.start;
+ else
+ start = dev_dax->ranges[0].range.start;
- return sprintf(buf, "%#llx\n", dev_dax->range.start);
+ return sprintf(buf, "%#llx\n", start);
}
static DEVICE_ATTR(resource, 0400, resource_show, NULL);
put_dax(dax_dev);
free_dev_dax_id(dev_dax);
dax_region_put(dax_region);
+ kfree(dev_dax->ranges);
kfree(dev_dax->pgmap);
kfree(dev_dax);
}
err_alloc_dax:
kfree(dev_dax->pgmap);
err_pgmap:
- free_dev_dax_range(dev_dax);
+ free_dev_dax_ranges(dev_dax);
err_range:
free_dev_dax_id(dev_dax);
err_id:
__weak phys_addr_t dax_pgoff_to_phys(struct dev_dax *dev_dax, pgoff_t pgoff,
unsigned long size)
{
- struct range *range = &dev_dax->range;
- phys_addr_t phys;
-
- phys = pgoff * PAGE_SIZE + range->start;
- if (phys >= range->start && phys <= range->end) {
+ int i;
+
+ for (i = 0; i < dev_dax->nr_range; i++) {
+ struct dev_dax_range *dax_range = &dev_dax->ranges[i];
+ struct range *range = &dax_range->range;
+ unsigned long long pgoff_end;
+ phys_addr_t phys;
+
+ pgoff_end = dax_range->pgoff + PHYS_PFN(range_len(range)) - 1;
+ if (pgoff < dax_range->pgoff || pgoff > pgoff_end)
+ continue;
+ phys = PFN_PHYS(pgoff - dax_range->pgoff) + range->start;
if (phys + size - 1 <= range->end)
return phys;
+ break;
}
-
return -1;
}
int dev_dax_probe(struct dev_dax *dev_dax)
{
struct dax_device *dax_dev = dev_dax->dax_dev;
- struct range *range = &dev_dax->range;
struct device *dev = &dev_dax->dev;
struct dev_pagemap *pgmap;
struct inode *inode;
struct cdev *cdev;
void *addr;
- int rc;
-
- /* 1:1 map region resource range to device-dax instance range */
- if (!devm_request_mem_region(dev, range->start, range_len(range),
- dev_name(dev))) {
- dev_warn(dev, "could not reserve range: %#llx - %#llx\n",
- range->start, range->end);
- return -EBUSY;
- }
+ int rc, i;
pgmap = dev_dax->pgmap;
+ if (dev_WARN_ONCE(dev, pgmap && dev_dax->nr_range > 1,
+ "static pgmap / multi-range device conflict\n"))
+ return -EINVAL;
+
if (!pgmap) {
- pgmap = devm_kzalloc(dev, sizeof(*pgmap), GFP_KERNEL);
+ pgmap = devm_kzalloc(dev, sizeof(*pgmap) + sizeof(struct range)
+ * (dev_dax->nr_range - 1), GFP_KERNEL);
if (!pgmap)
return -ENOMEM;
- pgmap->range = *range;
- pgmap->nr_range = 1;
+ pgmap->nr_range = dev_dax->nr_range;
+ }
+
+ for (i = 0; i < dev_dax->nr_range; i++) {
+ struct range *range = &dev_dax->ranges[i].range;
+
+ if (!devm_request_mem_region(dev, range->start,
+ range_len(range), dev_name(dev))) {
+ dev_warn(dev, "mapping%d: %#llx-%#llx could not reserve range\n",
+ i, range->start, range->end);
+ return -EBUSY;
+ }
+ /* don't update the range for static pgmap */
+ if (!dev_dax->pgmap)
+ pgmap->ranges[i] = *range;
}
+
pgmap->type = MEMORY_DEVICE_GENERIC;
addr = devm_memremap_pages(dev, pgmap);
if (IS_ERR(addr))
/* Set if any memory will remain added when the driver will be unloaded. */
static bool any_hotremove_failed;
-static struct range dax_kmem_range(struct dev_dax *dev_dax)
+static int dax_kmem_range(struct dev_dax *dev_dax, int i, struct range *r)
{
- struct range range;
+ struct dev_dax_range *dax_range = &dev_dax->ranges[i];
+ struct range *range = &dax_range->range;
/* memory-block align the hotplug range */
- range.start = ALIGN(dev_dax->range.start, memory_block_size_bytes());
- range.end = ALIGN_DOWN(dev_dax->range.end + 1, memory_block_size_bytes()) - 1;
- return range;
+ r->start = ALIGN(range->start, memory_block_size_bytes());
+ r->end = ALIGN_DOWN(range->end + 1, memory_block_size_bytes()) - 1;
+ if (r->start >= r->end) {
+ r->start = range->start;
+ r->end = range->end;
+ return -ENOSPC;
+ }
+ return 0;
}
static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
{
- struct range range = dax_kmem_range(dev_dax);
struct device *dev = &dev_dax->dev;
- struct resource *res;
+ int i, mapped = 0;
char *res_name;
int numa_node;
- int rc;
/*
* Ensure good NUMA information for the persistent memory.
if (!res_name)
return -ENOMEM;
- /* Region is permanently reserved if hotremove fails. */
- res = request_mem_region(range.start, range_len(&range), res_name);
- if (!res) {
- dev_warn(dev, "could not reserve region [%#llx-%#llx]\n", range.start, range.end);
- kfree(res_name);
- return -EBUSY;
- }
-
- /*
- * Set flags appropriate for System RAM. Leave ..._BUSY clear
- * so that add_memory() can add a child resource. Do not
- * inherit flags from the parent since it may set new flags
- * unknown to us that will break add_memory() below.
- */
- res->flags = IORESOURCE_SYSTEM_RAM;
-
- /*
- * Ensure that future kexec'd kernels will not treat this as RAM
- * automatically.
- */
- rc = add_memory_driver_managed(numa_node, range.start, range_len(&range), kmem_name);
- if (rc) {
- release_mem_region(range.start, range_len(&range));
- kfree(res_name);
- return rc;
+ for (i = 0; i < dev_dax->nr_range; i++) {
+ struct resource *res;
+ struct range range;
+ int rc;
+
+ rc = dax_kmem_range(dev_dax, i, &range);
+ if (rc) {
+ dev_info(dev, "mapping%d: %#llx-%#llx too small after alignment\n",
+ i, range.start, range.end);
+ continue;
+ }
+
+ /* Region is permanently reserved if hotremove fails. */
+ res = request_mem_region(range.start, range_len(&range), res_name);
+ if (!res) {
+ dev_warn(dev, "mapping%d: %#llx-%#llx could not reserve region\n",
+ i, range.start, range.end);
+ /*
+ * Once some memory has been onlined we can't
+ * assume that it can be un-onlined safely.
+ */
+ if (mapped)
+ continue;
+ kfree(res_name);
+ return -EBUSY;
+ }
+
+ /*
+ * Set flags appropriate for System RAM. Leave ..._BUSY clear
+ * so that add_memory() can add a child resource. Do not
+ * inherit flags from the parent since it may set new flags
+ * unknown to us that will break add_memory() below.
+ */
+ res->flags = IORESOURCE_SYSTEM_RAM;
+
+ /*
+ * Ensure that future kexec'd kernels will not treat
+ * this as RAM automatically.
+ */
+ rc = add_memory_driver_managed(numa_node, range.start,
+ range_len(&range), kmem_name);
+
+ if (rc) {
+ dev_warn(dev, "mapping%d: %#llx-%#llx memory add failed\n",
+ i, range.start, range.end);
+ release_mem_region(range.start, range_len(&range));
+ if (mapped)
+ continue;
+ kfree(res_name);
+ return rc;
+ }
+ mapped++;
}
dev_set_drvdata(dev, res_name);
#ifdef CONFIG_MEMORY_HOTREMOVE
static int dev_dax_kmem_remove(struct dev_dax *dev_dax)
{
- int rc;
+ int i, success = 0;
struct device *dev = &dev_dax->dev;
- struct range range = dax_kmem_range(dev_dax);
const char *res_name = dev_get_drvdata(dev);
/*
* there is no way to hotremove this memory until reboot because device
* unbind will succeed even if we return failure.
*/
- rc = remove_memory(dev_dax->target_node, range.start, range_len(&range));
- if (rc) {
+ for (i = 0; i < dev_dax->nr_range; i++) {
+ struct range range;
+ int rc;
+
+ rc = dax_kmem_range(dev_dax, i, &range);
+ if (rc)
+ continue;
+
+ rc = remove_memory(dev_dax->target_node, range.start,
+ range_len(&range));
+ if (rc == 0) {
+ release_mem_region(range.start, range_len(&range));
+ success++;
+ continue;
+ }
any_hotremove_failed = true;
- dev_err(dev, "%#llx-%#llx cannot be hotremoved until the next reboot\n",
- range.start, range.end);
- return rc;
+ dev_err(dev,
+ "mapping%d: %#llx-%#llx cannot be hotremoved until the next reboot\n",
+ i, range.start, range.end);
}
- /* Release and free dax resources */
- release_mem_region(range.start, range_len(&range));
- kfree(res_name);
+ if (success >= dev_dax->nr_range) {
+ kfree(res_name);
+ dev_set_drvdata(dev, NULL);
+ }
return 0;
}
projects / kernel.git / commitdiff