Update Linux to v5.10.109
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz
Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/mm/memremap.c b/mm/memremap.c
index c51c6bd..2455bac 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -7,6 +7,7 @@
#include <linux/mm.h>
#include <linux/pfn_t.h>
#include <linux/swap.h>
+#include <linux/mmzone.h>
#include <linux/swapops.h>
#include <linux/types.h>
#include <linux/wait_bit.h>
@@ -14,56 +15,91 @@
static DEFINE_XARRAY(pgmap_array);
+/*
+ * The memremap() and memremap_pages() interfaces are alternately used
+ * to map persistent memory namespaces. These interfaces place different
+ * constraints on the alignment and size of the mapping (namespace).
+ * memremap() can map individual PAGE_SIZE pages. memremap_pages() can
+ * only map subsections (2MB), and at least one architecture (PowerPC)
+ * the minimum mapping granularity of memremap_pages() is 16MB.
+ *
+ * The role of memremap_compat_align() is to communicate the minimum
+ * arch supported alignment of a namespace such that it can freely
+ * switch modes without violating the arch constraint. Namely, do not
+ * allow a namespace to be PAGE_SIZE aligned since that namespace may be
+ * reconfigured into a mode that requires SUBSECTION_SIZE alignment.
+ */
+#ifndef CONFIG_ARCH_HAS_MEMREMAP_COMPAT_ALIGN
+unsigned long memremap_compat_align(void)
+{
+ return SUBSECTION_SIZE;
+}
+EXPORT_SYMBOL_GPL(memremap_compat_align);
+#endif
+
#ifdef CONFIG_DEV_PAGEMAP_OPS
DEFINE_STATIC_KEY_FALSE(devmap_managed_key);
EXPORT_SYMBOL(devmap_managed_key);
-static atomic_t devmap_managed_enable;
-static void devmap_managed_enable_put(void)
+static void devmap_managed_enable_put(struct dev_pagemap *pgmap)
{
- if (atomic_dec_and_test(&devmap_managed_enable))
- static_branch_disable(&devmap_managed_key);
+ if (pgmap->type == MEMORY_DEVICE_PRIVATE ||
+ pgmap->type == MEMORY_DEVICE_FS_DAX)
+ static_branch_dec(&devmap_managed_key);
}
-static int devmap_managed_enable_get(struct dev_pagemap *pgmap)
+static void devmap_managed_enable_get(struct dev_pagemap *pgmap)
{
- if (!pgmap->ops || !pgmap->ops->page_free) {
- WARN(1, "Missing page_free method\n");
- return -EINVAL;
- }
-
- if (atomic_inc_return(&devmap_managed_enable) == 1)
- static_branch_enable(&devmap_managed_key);
- return 0;
+ if (pgmap->type == MEMORY_DEVICE_PRIVATE ||
+ pgmap->type == MEMORY_DEVICE_FS_DAX)
+ static_branch_inc(&devmap_managed_key);
}
#else
-static int devmap_managed_enable_get(struct dev_pagemap *pgmap)
+static void devmap_managed_enable_get(struct dev_pagemap *pgmap)
{
- return -EINVAL;
}
-static void devmap_managed_enable_put(void)
+static void devmap_managed_enable_put(struct dev_pagemap *pgmap)
{
}
#endif /* CONFIG_DEV_PAGEMAP_OPS */
-static void pgmap_array_delete(struct resource *res)
+static void pgmap_array_delete(struct range *range)
{
- xa_store_range(&pgmap_array, PHYS_PFN(res->start), PHYS_PFN(res->end),
+ xa_store_range(&pgmap_array, PHYS_PFN(range->start), PHYS_PFN(range->end),
NULL, GFP_KERNEL);
synchronize_rcu();
}
-static unsigned long pfn_first(struct dev_pagemap *pgmap)
+static unsigned long pfn_first(struct dev_pagemap *pgmap, int range_id)
{
- return PHYS_PFN(pgmap->res.start) +
- vmem_altmap_offset(pgmap_altmap(pgmap));
+ struct range *range = &pgmap->ranges[range_id];
+ unsigned long pfn = PHYS_PFN(range->start);
+
+ if (range_id)
+ return pfn;
+ return pfn + vmem_altmap_offset(pgmap_altmap(pgmap));
}
-static unsigned long pfn_end(struct dev_pagemap *pgmap)
+bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn)
{
- const struct resource *res = &pgmap->res;
+ int i;
- return (res->start + resource_size(res)) >> PAGE_SHIFT;
+ for (i = 0; i < pgmap->nr_range; i++) {
+ struct range *range = &pgmap->ranges[i];
+
+ if (pfn >= PHYS_PFN(range->start) &&
+ pfn <= PHYS_PFN(range->end))
+ return pfn >= pfn_first(pgmap, i);
+ }
+
+ return false;
+}
+
+static unsigned long pfn_end(struct dev_pagemap *pgmap, int range_id)
+{
+ const struct range *range = &pgmap->ranges[range_id];
+
+ return (range->start + range_len(range)) >> PAGE_SHIFT;
}
static unsigned long pfn_next(unsigned long pfn)
@@ -73,8 +109,8 @@
return pfn + 1;
}
-#define for_each_device_pfn(pfn, map) \
- for (pfn = pfn_first(map); pfn < pfn_end(map); pfn = pfn_next(pfn))
+#define for_each_device_pfn(pfn, map, i) \
+ for (pfn = pfn_first(map, i); pfn < pfn_end(map, i); pfn = pfn_next(pfn))
static void dev_pagemap_kill(struct dev_pagemap *pgmap)
{
@@ -100,39 +136,51 @@
pgmap->ref = NULL;
}
-void memunmap_pages(struct dev_pagemap *pgmap)
+static void pageunmap_range(struct dev_pagemap *pgmap, int range_id)
{
- struct resource *res = &pgmap->res;
+ struct range *range = &pgmap->ranges[range_id];
struct page *first_page;
- unsigned long pfn;
int nid;
- dev_pagemap_kill(pgmap);
- for_each_device_pfn(pfn, pgmap)
- put_page(pfn_to_page(pfn));
- dev_pagemap_cleanup(pgmap);
-
/* make sure to access a memmap that was actually initialized */
- first_page = pfn_to_page(pfn_first(pgmap));
+ first_page = pfn_to_page(pfn_first(pgmap, range_id));
/* pages are dead and unused, undo the arch mapping */
nid = page_to_nid(first_page);
mem_hotplug_begin();
+ remove_pfn_range_from_zone(page_zone(first_page), PHYS_PFN(range->start),
+ PHYS_PFN(range_len(range)));
if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
- __remove_pages(PHYS_PFN(res->start),
- PHYS_PFN(resource_size(res)), NULL);
+ __remove_pages(PHYS_PFN(range->start),
+ PHYS_PFN(range_len(range)), NULL);
} else {
- arch_remove_memory(nid, res->start, resource_size(res),
+ arch_remove_memory(nid, range->start, range_len(range),
pgmap_altmap(pgmap));
- kasan_remove_zero_shadow(__va(res->start), resource_size(res));
+ kasan_remove_zero_shadow(__va(range->start), range_len(range));
}
mem_hotplug_done();
- untrack_pfn(NULL, PHYS_PFN(res->start), resource_size(res));
- pgmap_array_delete(res);
+ untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range));
+ pgmap_array_delete(range);
+}
+
+void memunmap_pages(struct dev_pagemap *pgmap)
+{
+ unsigned long pfn;
+ int i;
+
+ dev_pagemap_kill(pgmap);
+ for (i = 0; i < pgmap->nr_range; i++)
+ for_each_device_pfn(pfn, pgmap, i)
+ put_page(pfn_to_page(pfn));
+ dev_pagemap_cleanup(pgmap);
+
+ for (i = 0; i < pgmap->nr_range; i++)
+ pageunmap_range(pgmap, i);
+
WARN_ONCE(pgmap->altmap.alloc, "failed to free all reserved pages\n");
- devmap_managed_enable_put();
+ devmap_managed_enable_put(pgmap);
}
EXPORT_SYMBOL_GPL(memunmap_pages);
@@ -149,6 +197,115 @@
complete(&pgmap->done);
}
+static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params,
+ int range_id, int nid)
+{
+ struct range *range = &pgmap->ranges[range_id];
+ struct dev_pagemap *conflict_pgmap;
+ int error, is_ram;
+
+ if (WARN_ONCE(pgmap_altmap(pgmap) && range_id > 0,
+ "altmap not supported for multiple ranges\n"))
+ return -EINVAL;
+
+ conflict_pgmap = get_dev_pagemap(PHYS_PFN(range->start), NULL);
+ if (conflict_pgmap) {
+ WARN(1, "Conflicting mapping in same section\n");
+ put_dev_pagemap(conflict_pgmap);
+ return -ENOMEM;
+ }
+
+ conflict_pgmap = get_dev_pagemap(PHYS_PFN(range->end), NULL);
+ if (conflict_pgmap) {
+ WARN(1, "Conflicting mapping in same section\n");
+ put_dev_pagemap(conflict_pgmap);
+ return -ENOMEM;
+ }
+
+ is_ram = region_intersects(range->start, range_len(range),
+ IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE);
+
+ if (is_ram != REGION_DISJOINT) {
+ WARN_ONCE(1, "attempted on %s region %#llx-%#llx\n",
+ is_ram == REGION_MIXED ? "mixed" : "ram",
+ range->start, range->end);
+ return -ENXIO;
+ }
+
+ error = xa_err(xa_store_range(&pgmap_array, PHYS_PFN(range->start),
+ PHYS_PFN(range->end), pgmap, GFP_KERNEL));
+ if (error)
+ return error;
+
+ if (nid < 0)
+ nid = numa_mem_id();
+
+ error = track_pfn_remap(NULL, ¶ms->pgprot, PHYS_PFN(range->start), 0,
+ range_len(range));
+ if (error)
+ goto err_pfn_remap;
+
+ mem_hotplug_begin();
+
+ /*
+ * For device private memory we call add_pages() as we only need to
+ * allocate and initialize struct page for the device memory. More-
+ * over the device memory is un-accessible thus we do not want to
+ * create a linear mapping for the memory like arch_add_memory()
+ * would do.
+ *
+ * For all other device memory types, which are accessible by
+ * the CPU, we do want the linear mapping and thus use
+ * arch_add_memory().
+ */
+ if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
+ error = add_pages(nid, PHYS_PFN(range->start),
+ PHYS_PFN(range_len(range)), params);
+ } else {
+ error = kasan_add_zero_shadow(__va(range->start), range_len(range));
+ if (error) {
+ mem_hotplug_done();
+ goto err_kasan;
+ }
+
+ error = arch_add_memory(nid, range->start, range_len(range),
+ params);
+ }
+
+ if (!error) {
+ struct zone *zone;
+
+ zone = &NODE_DATA(nid)->node_zones[ZONE_DEVICE];
+ move_pfn_range_to_zone(zone, PHYS_PFN(range->start),
+ PHYS_PFN(range_len(range)), params->altmap,
+ MIGRATE_MOVABLE);
+ }
+
+ mem_hotplug_done();
+ if (error)
+ goto err_add_memory;
+
+ /*
+ * Initialization of the pages has been deferred until now in order
+ * to allow us to do the work while not holding the hotplug lock.
+ */
+ memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
+ PHYS_PFN(range->start),
+ PHYS_PFN(range_len(range)), pgmap);
+ percpu_ref_get_many(pgmap->ref, pfn_end(pgmap, range_id)
+ - pfn_first(pgmap, range_id));
+ return 0;
+
+err_add_memory:
+ kasan_remove_zero_shadow(__va(range->start), range_len(range));
+err_kasan:
+ untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range));
+err_pfn_remap:
+ pgmap_array_delete(range);
+ return error;
+}
+
+
/*
* Not device managed version of dev_memremap_pages, undone by
* memunmap_pages(). Please use dev_memremap_pages if you have a struct
@@ -156,17 +313,15 @@
*/
void *memremap_pages(struct dev_pagemap *pgmap, int nid)
{
- struct resource *res = &pgmap->res;
- struct dev_pagemap *conflict_pgmap;
- struct mhp_restrictions restrictions = {
- /*
- * We do not want any optional features only our own memmap
- */
+ struct mhp_params params = {
.altmap = pgmap_altmap(pgmap),
+ .pgprot = PAGE_KERNEL,
};
- pgprot_t pgprot = PAGE_KERNEL;
- int error, is_ram;
- bool need_devmap_managed = true;
+ const int nr_range = pgmap->nr_range;
+ int error, i;
+
+ if (WARN_ONCE(!nr_range, "nr_range must be specified\n"))
+ return ERR_PTR(-EINVAL);
switch (pgmap->type) {
case MEMORY_DEVICE_PRIVATE:
@@ -178,6 +333,14 @@
WARN(1, "Missing migrate_to_ram method\n");
return ERR_PTR(-EINVAL);
}
+ if (!pgmap->ops->page_free) {
+ WARN(1, "Missing page_free method\n");
+ return ERR_PTR(-EINVAL);
+ }
+ if (!pgmap->owner) {
+ WARN(1, "Missing owner\n");
+ return ERR_PTR(-EINVAL);
+ }
break;
case MEMORY_DEVICE_FS_DAX:
if (!IS_ENABLED(CONFIG_ZONE_DEVICE) ||
@@ -186,9 +349,10 @@
return ERR_PTR(-EINVAL);
}
break;
- case MEMORY_DEVICE_DEVDAX:
+ case MEMORY_DEVICE_GENERIC:
+ break;
case MEMORY_DEVICE_PCI_P2PDMA:
- need_devmap_managed = false;
+ params.pgprot = pgprot_noncached(params.pgprot);
break;
default:
WARN(1, "Invalid pgmap type %d\n", pgmap->type);
@@ -212,111 +376,29 @@
}
}
- if (need_devmap_managed) {
- error = devmap_managed_enable_get(pgmap);
+ devmap_managed_enable_get(pgmap);
+
+ /*
+ * Clear the pgmap nr_range as it will be incremented for each
+ * successfully processed range. This communicates how many
+ * regions to unwind in the abort case.
+ */
+ pgmap->nr_range = 0;
+ error = 0;
+ for (i = 0; i < nr_range; i++) {
+ error = pagemap_range(pgmap, ¶ms, i, nid);
if (error)
- return ERR_PTR(error);
+ break;
+ pgmap->nr_range++;
}
- conflict_pgmap = get_dev_pagemap(PHYS_PFN(res->start), NULL);
- if (conflict_pgmap) {
- WARN(1, "Conflicting mapping in same section\n");
- put_dev_pagemap(conflict_pgmap);
- error = -ENOMEM;
- goto err_array;
+ if (i < nr_range) {
+ memunmap_pages(pgmap);
+ pgmap->nr_range = nr_range;
+ return ERR_PTR(error);
}
- conflict_pgmap = get_dev_pagemap(PHYS_PFN(res->end), NULL);
- if (conflict_pgmap) {
- WARN(1, "Conflicting mapping in same section\n");
- put_dev_pagemap(conflict_pgmap);
- error = -ENOMEM;
- goto err_array;
- }
-
- is_ram = region_intersects(res->start, resource_size(res),
- IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE);
-
- if (is_ram != REGION_DISJOINT) {
- WARN_ONCE(1, "%s attempted on %s region %pr\n", __func__,
- is_ram == REGION_MIXED ? "mixed" : "ram", res);
- error = -ENXIO;
- goto err_array;
- }
-
- error = xa_err(xa_store_range(&pgmap_array, PHYS_PFN(res->start),
- PHYS_PFN(res->end), pgmap, GFP_KERNEL));
- if (error)
- goto err_array;
-
- if (nid < 0)
- nid = numa_mem_id();
-
- error = track_pfn_remap(NULL, &pgprot, PHYS_PFN(res->start), 0,
- resource_size(res));
- if (error)
- goto err_pfn_remap;
-
- mem_hotplug_begin();
-
- /*
- * For device private memory we call add_pages() as we only need to
- * allocate and initialize struct page for the device memory. More-
- * over the device memory is un-accessible thus we do not want to
- * create a linear mapping for the memory like arch_add_memory()
- * would do.
- *
- * For all other device memory types, which are accessible by
- * the CPU, we do want the linear mapping and thus use
- * arch_add_memory().
- */
- if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
- error = add_pages(nid, PHYS_PFN(res->start),
- PHYS_PFN(resource_size(res)), &restrictions);
- } else {
- error = kasan_add_zero_shadow(__va(res->start), resource_size(res));
- if (error) {
- mem_hotplug_done();
- goto err_kasan;
- }
-
- error = arch_add_memory(nid, res->start, resource_size(res),
- &restrictions);
- }
-
- if (!error) {
- struct zone *zone;
-
- zone = &NODE_DATA(nid)->node_zones[ZONE_DEVICE];
- move_pfn_range_to_zone(zone, PHYS_PFN(res->start),
- PHYS_PFN(resource_size(res)), restrictions.altmap);
- }
-
- mem_hotplug_done();
- if (error)
- goto err_add_memory;
-
- /*
- * Initialization of the pages has been deferred until now in order
- * to allow us to do the work while not holding the hotplug lock.
- */
- memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
- PHYS_PFN(res->start),
- PHYS_PFN(resource_size(res)), pgmap);
- percpu_ref_get_many(pgmap->ref, pfn_end(pgmap) - pfn_first(pgmap));
- return __va(res->start);
-
- err_add_memory:
- kasan_remove_zero_shadow(__va(res->start), resource_size(res));
- err_kasan:
- untrack_pfn(NULL, PHYS_PFN(res->start), resource_size(res));
- err_pfn_remap:
- pgmap_array_delete(res);
- err_array:
- dev_pagemap_kill(pgmap);
- dev_pagemap_cleanup(pgmap);
- devmap_managed_enable_put();
- return ERR_PTR(error);
+ return __va(pgmap->ranges[0].start);
}
EXPORT_SYMBOL_GPL(memremap_pages);
@@ -336,7 +418,7 @@
* 'live' on entry and will be killed and reaped at
* devm_memremap_pages_release() time, or if this routine fails.
*
- * 4/ res is expected to be a host memory range that could feasibly be
+ * 4/ range is expected to be a host memory range that could feasibly be
* treated as a "System RAM" range, i.e. not a device mmio range, but
* this is not enforced.
*/
@@ -393,7 +475,7 @@
* In the cached case we're already holding a live reference.
*/
if (pgmap) {
- if (phys >= pgmap->res.start && phys <= pgmap->res.end)
+ if (phys >= pgmap->range.start && phys <= pgmap->range.end)
return pgmap;
put_dev_pagemap(pgmap);
}
@@ -410,48 +492,40 @@
EXPORT_SYMBOL_GPL(get_dev_pagemap);
#ifdef CONFIG_DEV_PAGEMAP_OPS
-void __put_devmap_managed_page(struct page *page)
+void free_devmap_managed_page(struct page *page)
{
- int count = page_ref_dec_return(page);
+ /* notify page idle for dax */
+ if (!is_device_private_page(page)) {
+ wake_up_var(&page->_refcount);
+ return;
+ }
+
+ __ClearPageWaiters(page);
+
+ mem_cgroup_uncharge(page);
/*
- * If refcount is 1 then page is freed and refcount is stable as nobody
- * holds a reference on the page.
+ * When a device_private page is freed, the page->mapping field
+ * may still contain a (stale) mapping value. For example, the
+ * lower bits of page->mapping may still identify the page as an
+ * anonymous page. Ultimately, this entire field is just stale
+ * and wrong, and it will cause errors if not cleared. One
+ * example is:
+ *
+ * migrate_vma_pages()
+ * migrate_vma_insert_page()
+ * page_add_new_anon_rmap()
+ * __page_set_anon_rmap()
+ * ...checks page->mapping, via PageAnon(page) call,
+ * and incorrectly concludes that the page is an
+ * anonymous page. Therefore, it incorrectly,
+ * silently fails to set up the new anon rmap.
+ *
+ * For other types of ZONE_DEVICE pages, migration is either
+ * handled differently or not done at all, so there is no need
+ * to clear page->mapping.
*/
- if (count == 1) {
- /* Clear Active bit in case of parallel mark_page_accessed */
- __ClearPageActive(page);
- __ClearPageWaiters(page);
-
- mem_cgroup_uncharge(page);
-
- /*
- * When a device_private page is freed, the page->mapping field
- * may still contain a (stale) mapping value. For example, the
- * lower bits of page->mapping may still identify the page as
- * an anonymous page. Ultimately, this entire field is just
- * stale and wrong, and it will cause errors if not cleared.
- * One example is:
- *
- * migrate_vma_pages()
- * migrate_vma_insert_page()
- * page_add_new_anon_rmap()
- * __page_set_anon_rmap()
- * ...checks page->mapping, via PageAnon(page) call,
- * and incorrectly concludes that the page is an
- * anonymous page. Therefore, it incorrectly,
- * silently fails to set up the new anon rmap.
- *
- * For other types of ZONE_DEVICE pages, migration is either
- * handled differently or not done at all, so there is no need
- * to clear page->mapping.
- */
- if (is_device_private_page(page))
- page->mapping = NULL;
-
- page->pgmap->ops->page_free(page);
- } else if (!count)
- __put_page(page);
+ page->mapping = NULL;
+ page->pgmap->ops->page_free(page);
}
-EXPORT_SYMBOL(__put_devmap_managed_page);
#endif /* CONFIG_DEV_PAGEMAP_OPS */