summaryrefslogtreecommitdiff
path: root/drivers
diff options
context:
space:
mode:
authorDan Williams <dan.j.williams@intel.com>2018-05-16 21:46:08 +0300
committerDan Williams <dan.j.williams@intel.com>2018-05-22 16:59:39 +0300
commite7638488434415aa478e78435cac8f0365737638 (patch)
tree7ce50f0ed69889aa44cb0124451cf7a56b34eba6 /drivers
parent5981690ddb8f72f9546a2d017a914cf56095fc1f (diff)
downloadlinux-e7638488434415aa478e78435cac8f0365737638.tar.xz
mm: introduce MEMORY_DEVICE_FS_DAX and CONFIG_DEV_PAGEMAP_OPS
In preparation for fixing dax-dma-vs-unmap issues, filesystems need to be able to rely on the fact that they will get wakeups on dev_pagemap page-idle events. Introduce MEMORY_DEVICE_FS_DAX and generic_dax_page_free() as common indicator / infrastructure for dax filesytems to require. With this change there are no users of the MEMORY_DEVICE_HOST designation, so remove it. The HMM sub-system extended dev_pagemap to arrange a callback when a dev_pagemap managed page is freed. Since a dev_pagemap page is free / idle when its reference count is 1 it requires an additional branch to check the page-type at put_page() time. Given put_page() is a hot-path we do not want to incur that check if HMM is not in use, so a static branch is used to avoid that overhead when not necessary. Now, the FS_DAX implementation wants to reuse this mechanism for receiving dev_pagemap ->page_free() callbacks. Rework the HMM-specific static-key into a generic mechanism that either HMM or FS_DAX code paths can enable. For ARCH=um builds, and any other arch that lacks ZONE_DEVICE support, care must be taken to compile out the DEV_PAGEMAP_OPS infrastructure. However, we still need to support FS_DAX in the FS_DAX_LIMITED case implemented by the s390/dcssblk driver. Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Michal Hocko <mhocko@suse.com> Reported-by: kbuild test robot <lkp@intel.com> Reported-by: Thomas Meyer <thomas@m3y3r.de> Reported-by: Dave Jiang <dave.jiang@intel.com> Cc: "Jérôme Glisse" <jglisse@redhat.com> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Diffstat (limited to 'drivers')
-rw-r--r--drivers/dax/super.c14
-rw-r--r--drivers/nvdimm/pfn_devs.c2
-rw-r--r--drivers/nvdimm/pmem.c25
3 files changed, 36 insertions, 5 deletions
diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 2b2332b605e4..bf8bfaf5596f 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -86,6 +86,7 @@ int __bdev_dax_supported(struct super_block *sb, int blocksize)
{
struct block_device *bdev = sb->s_bdev;
struct dax_device *dax_dev;
+ bool dax_enabled = false;
pgoff_t pgoff;
int err, id;
void *kaddr;
@@ -134,14 +135,21 @@ int __bdev_dax_supported(struct super_block *sb, int blocksize)
* on being able to do (page_address(pfn_to_page())).
*/
WARN_ON(IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API));
+ dax_enabled = true;
} else if (pfn_t_devmap(pfn)) {
- /* pass */;
- } else {
+ struct dev_pagemap *pgmap;
+
+ pgmap = get_dev_pagemap(pfn_t_to_pfn(pfn), NULL);
+ if (pgmap && pgmap->type == MEMORY_DEVICE_FS_DAX)
+ dax_enabled = true;
+ put_dev_pagemap(pgmap);
+ }
+
+ if (!dax_enabled) {
pr_debug("VFS (%s): error: dax support not enabled\n",
sb->s_id);
return -EOPNOTSUPP;
}
-
return 0;
}
EXPORT_SYMBOL_GPL(__bdev_dax_supported);
diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c
index 30b08791597d..3f7ad5bc443e 100644
--- a/drivers/nvdimm/pfn_devs.c
+++ b/drivers/nvdimm/pfn_devs.c
@@ -561,8 +561,6 @@ static int __nvdimm_setup_pfn(struct nd_pfn *nd_pfn, struct dev_pagemap *pgmap)
res->start += start_pad;
res->end -= end_trunc;
- pgmap->type = MEMORY_DEVICE_HOST;
-
if (nd_pfn->mode == PFN_MODE_RAM) {
if (offset < SZ_8K)
return -EINVAL;
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 9d714926ecf5..06b41ec9f1b3 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -294,6 +294,27 @@ static void pmem_release_disk(void *__pmem)
put_disk(pmem->disk);
}
+static void pmem_release_pgmap_ops(void *__pgmap)
+{
+ dev_pagemap_put_ops();
+}
+
+static void fsdax_pagefree(struct page *page, void *data)
+{
+ wake_up_var(&page->_refcount);
+}
+
+static int setup_pagemap_fsdax(struct device *dev, struct dev_pagemap *pgmap)
+{
+ dev_pagemap_get_ops();
+ if (devm_add_action_or_reset(dev, pmem_release_pgmap_ops, pgmap))
+ return -ENOMEM;
+ pgmap->type = MEMORY_DEVICE_FS_DAX;
+ pgmap->page_free = fsdax_pagefree;
+
+ return 0;
+}
+
static int pmem_attach_disk(struct device *dev,
struct nd_namespace_common *ndns)
{
@@ -353,6 +374,8 @@ static int pmem_attach_disk(struct device *dev,
pmem->pfn_flags = PFN_DEV;
pmem->pgmap.ref = &q->q_usage_counter;
if (is_nd_pfn(dev)) {
+ if (setup_pagemap_fsdax(dev, &pmem->pgmap))
+ return -ENOMEM;
addr = devm_memremap_pages(dev, &pmem->pgmap);
pfn_sb = nd_pfn->pfn_sb;
pmem->data_offset = le64_to_cpu(pfn_sb->dataoff);
@@ -364,6 +387,8 @@ static int pmem_attach_disk(struct device *dev,
} else if (pmem_should_map_pages(dev)) {
memcpy(&pmem->pgmap.res, &nsio->res, sizeof(pmem->pgmap.res));
pmem->pgmap.altmap_valid = false;
+ if (setup_pagemap_fsdax(dev, &pmem->pgmap))
+ return -ENOMEM;
addr = devm_memremap_pages(dev, &pmem->pgmap);
pmem->pfn_flags |= PFN_MAP;
memcpy(&bb_res, &pmem->pgmap.res, sizeof(bb_res));