The patch titled
Subject: mm: introduce find_dev_pagemap()
has been added to the -mm tree. Its filename is
mm-introduce-find_dev_pagemap.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-introduce-find_dev_pagemap.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-introduce-find_dev_pagemap.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Dan Williams <dan.j.williams@xxxxxxxxx>
Subject: mm: introduce find_dev_pagemap()
There are several scenarios where we need to retrieve and update metadata
associated with a given devm_memremap_pages() mapping, and the only lookup
key available is a pfn in the range:
1/ We want to augment vmemmap_populate() (called via arch_add_memory())
to allocate memmap storage from pre-allocated pages reserved by the
device driver. At vmemmap_alloc_block_buf() time it grabs device pages
rather than page allocator pages. This is in support of
devm_memremap_pages() mappings where the memmap is too large to fit in
main memory (i.e. large persistent memory devices).
2/ Taking a reference against the mapping when inserting device pages
into the address_space radix of a given inode. This facilitates
unmap_mapping_range() and truncate_inode_pages() operations when the
driver is tearing down the mapping.
3/ get_user_pages() operations on ZONE_DEVICE memory require taking a
reference against the mapping so that the driver teardown path can
revoke and drain usage of device pages.
Signed-off-by: Dan Williams <dan.j.williams@xxxxxxxxx>
Tested-by: Logan Gunthorpe <logang@xxxxxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: Dave Chinner <david@xxxxxxxxxxxxx>
Cc: Ross Zwisler <ross.zwisler@xxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/io.h | 15 -------
include/linux/mm.h | 33 ++++++++++++++++
kernel/memremap.c | 84 ++++++++++++++++++++++++++++++++++++++-----
3 files changed, 109 insertions(+), 23 deletions(-)
diff -puN include/linux/io.h~mm-introduce-find_dev_pagemap include/linux/io.h
--- a/include/linux/io.h~mm-introduce-find_dev_pagemap
+++ a/include/linux/io.h
@@ -89,21 +89,6 @@ void devm_memunmap(struct device *dev, v
void *__devm_memremap_pages(struct device *dev, struct resource *res);
-#ifdef CONFIG_ZONE_DEVICE
-void *devm_memremap_pages(struct device *dev, struct resource *res);
-#else
-static inline void *devm_memremap_pages(struct device *dev, struct resource *res)
-{
- /*
- * Fail attempts to call devm_memremap_pages() without
- * ZONE_DEVICE support enabled, this requires callers to fall
- * back to plain devm_memremap() based on config
- */
- WARN_ON_ONCE(1);
- return ERR_PTR(-ENXIO);
-}
-#endif
-
/*
* Some systems do not have legacy ISA devices.
* /dev/port is not a valid interface on these systems.
diff -puN include/linux/mm.h~mm-introduce-find_dev_pagemap include/linux/mm.h
--- a/include/linux/mm.h~mm-introduce-find_dev_pagemap
+++ a/include/linux/mm.h
@@ -686,6 +686,39 @@ static inline enum zone_type page_zonenu
return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK;
}
+struct resource;
+struct device;
+/**
+ * struct dev_pagemap - metadata for ZONE_DEVICE mappings
+ * @dev: host device of the mapping for debug
+ */
+struct dev_pagemap {
+ /* TODO: vmem_altmap and percpu_ref count */
+ struct device *dev;
+};
+
+#ifdef CONFIG_ZONE_DEVICE
+void *devm_memremap_pages(struct device *dev, struct resource *res);
+struct dev_pagemap *find_dev_pagemap(resource_size_t phys);
+#else
+static inline void *devm_memremap_pages(struct device *dev,
+ struct resource *res)
+{
+ /*
+ * Fail attempts to call devm_memremap_pages() without
+ * ZONE_DEVICE support enabled, this requires callers to fall
+ * back to plain devm_memremap() based on config
+ */
+ WARN_ON_ONCE(1);
+ return ERR_PTR(-ENXIO);
+}
+
+static inline struct dev_pagemap *find_dev_pagemap(resource_size_t phys)
+{
+ return NULL;
+}
+#endif
+
#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
#define SECTION_IN_PAGE_FLAGS
#endif
diff -puN kernel/memremap.c~mm-introduce-find_dev_pagemap kernel/memremap.c
--- a/kernel/memremap.c~mm-introduce-find_dev_pagemap
+++ a/kernel/memremap.c
@@ -10,6 +10,7 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*/
+#include <linux/radix-tree.h>
#include <linux/device.h>
#include <linux/types.h>
#include <linux/io.h>
@@ -154,22 +155,57 @@ pfn_t phys_to_pfn_t(dma_addr_t addr, uns
EXPORT_SYMBOL(phys_to_pfn_t);
#ifdef CONFIG_ZONE_DEVICE
+static DEFINE_MUTEX(pgmap_lock);
+static RADIX_TREE(pgmap_radix, GFP_KERNEL);
+#define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1)
+#define SECTION_SIZE (1UL << PA_SECTION_SHIFT)
+
struct page_map {
struct resource res;
+ struct percpu_ref *ref;
+ struct dev_pagemap pgmap;
};
-static void devm_memremap_pages_release(struct device *dev, void *res)
+static void pgmap_radix_release(struct resource *res)
+{
+ resource_size_t key;
+
+ mutex_lock(&pgmap_lock);
+ for (key = res->start; key <= res->end; key += SECTION_SIZE)
+ radix_tree_delete(&pgmap_radix, key >> PA_SECTION_SHIFT);
+ mutex_unlock(&pgmap_lock);
+}
+
+static void devm_memremap_pages_release(struct device *dev, void *data)
{
- struct page_map *page_map = res;
+ struct page_map *page_map = data;
+ struct resource *res = &page_map->res;
+ resource_size_t align_start, align_size;
+
+ pgmap_radix_release(res);
/* pages are dead and unused, undo the arch mapping */
- arch_remove_memory(page_map->res.start, resource_size(&page_map->res));
+ align_start = res->start & ~(SECTION_SIZE - 1);
+ align_size = ALIGN(resource_size(res), SECTION_SIZE);
+ arch_remove_memory(align_start, align_size);
+}
+
+/* assumes rcu_read_lock() held at entry */
+struct dev_pagemap *find_dev_pagemap(resource_size_t phys)
+{
+ struct page_map *page_map;
+
+ WARN_ON_ONCE(!rcu_read_lock_held());
+
+ page_map = radix_tree_lookup(&pgmap_radix, phys >> PA_SECTION_SHIFT);
+ return page_map ? &page_map->pgmap : NULL;
}
void *devm_memremap_pages(struct device *dev, struct resource *res)
{
int is_ram = region_intersects(res->start, resource_size(res),
"System RAM");
+ resource_size_t key, align_start, align_size;
struct page_map *page_map;
int error, nid;
@@ -189,18 +225,50 @@ void *devm_memremap_pages(struct device
memcpy(&page_map->res, res, sizeof(*res));
+ page_map->pgmap.dev = dev;
+ mutex_lock(&pgmap_lock);
+ error = 0;
+ for (key = res->start; key <= res->end; key += SECTION_SIZE) {
+ struct dev_pagemap *dup;
+
+ rcu_read_lock();
+ dup = find_dev_pagemap(key);
+ rcu_read_unlock();
+ if (dup) {
+ dev_err(dev, "%s: %pr collides with mapping for %s\n",
+ __func__, res, dev_name(dup->dev));
+ error = -EBUSY;
+ break;
+ }
+ error = radix_tree_insert(&pgmap_radix, key >> PA_SECTION_SHIFT,
+ page_map);
+ if (error) {
+ dev_err(dev, "%s: failed: %d\n", __func__, error);
+ break;
+ }
+ }
+ mutex_unlock(&pgmap_lock);
+ if (error)
+ goto err_radix;
+
nid = dev_to_node(dev);
if (nid < 0)
nid = numa_mem_id();
- error = arch_add_memory(nid, res->start, resource_size(res), true);
- if (error) {
- devres_free(page_map);
- return ERR_PTR(error);
- }
+ align_start = res->start & ~(SECTION_SIZE - 1);
+ align_size = ALIGN(resource_size(res), SECTION_SIZE);
+ error = arch_add_memory(nid, align_start, align_size, true);
+ if (error)
+ goto err_add_memory;
devres_add(dev, page_map);
return __va(res->start);
+
+ err_add_memory:
+ err_radix:
+ pgmap_radix_release(res);
+ devres_free(page_map);
+ return ERR_PTR(error);
}
EXPORT_SYMBOL(devm_memremap_pages);
#endif /* CONFIG_ZONE_DEVICE */
_
Patches currently in -mm which might be from dan.j.williams@xxxxxxxxx are
scatterlist-fix-sg_phys-masking.patch
pmem-dax-clean-up-clear_pmem.patch
dax-increase-granularity-of-dax_clear_blocks-operations.patch
dax-guarantee-page-aligned-results-from-bdev_direct_access.patch
dax-fix-lifetime-of-in-kernel-dax-mappings-with-dax_map_atomic.patch
dax-fix-lifetime-of-in-kernel-dax-mappings-with-dax_map_atomic-v3.patch
um-kill-pfn_t.patch
kvm-rename-pfn_t-to-kvm_pfn_t.patch
mm-dax-pmem-introduce-pfn_t.patch
mm-dax-pmem-introduce-pfn_t-v3.patch
mm-introduce-find_dev_pagemap.patch
x86-mm-introduce-vmem_altmap-to-augment-vmemmap_populate.patch
libnvdimm-pfn-pmem-allocate-memmap-array-in-persistent-memory.patch
avr32-convert-to-asm-generic-memory_modelh.patch
hugetlb-fix-compile-error-on-tile.patch
frv-fix-compiler-warning-from-definition-of-__pmd.patch
x86-mm-introduce-_page_devmap.patch
mm-dax-gpu-convert-vm_insert_mixed-to-pfn_t.patch
mm-dax-convert-vmf_insert_pfn_pmd-to-pfn_t.patch
list-introduce-list_del_poison.patch
libnvdimm-pmem-move-request_queue-allocation-earlier-in-probe.patch
mm-dax-pmem-introduce-getput_dev_pagemap-for-dax-gup.patch
mm-dax-dax-pmd-vs-thp-pmd-vs-hugetlbfs-pmd.patch
mm-x86-get_user_pages-for-dax-mappings.patch
dax-provide-diagnostics-for-pmd-mapping-failures.patch
dax-re-enable-dax-pmd-mappings.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
