summaryrefslogtreecommitdiff
path: root/drivers
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2023-11-03 08:38:47 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2023-11-03 08:38:47 +0300
commitecae0bd5173b1014f95a14a8dfbe40ec10367dcf (patch)
treef571213ef1a35354ea79f0240a180fdb4111b290 /drivers
parentbc3012f4e3a9765de81f454cb8f9bb16aafc6ff5 (diff)
parent9732336006764e2ee61225387e3c70eae9139035 (diff)
downloadlinux-ecae0bd5173b1014f95a14a8dfbe40ec10367dcf.tar.xz
Merge tag 'mm-stable-2023-11-01-14-33' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull MM updates from Andrew Morton: "Many singleton patches against the MM code. The patch series which are included in this merge do the following: - Kemeng Shi has contributed some compation maintenance work in the series 'Fixes and cleanups to compaction' - Joel Fernandes has a patchset ('Optimize mremap during mutual alignment within PMD') which fixes an obscure issue with mremap()'s pagetable handling during a subsequent exec(), based upon an implementation which Linus suggested - More DAMON/DAMOS maintenance and feature work from SeongJae Park i the following patch series: mm/damon: misc fixups for documents, comments and its tracepoint mm/damon: add a tracepoint for damos apply target regions mm/damon: provide pseudo-moving sum based access rate mm/damon: implement DAMOS apply intervals mm/damon/core-test: Fix memory leaks in core-test mm/damon/sysfs-schemes: Do DAMOS tried regions update for only one apply interval - In the series 'Do not try to access unaccepted memory' Adrian Hunter provides some fixups for the recently-added 'unaccepted memory' feature. To increase the feature's checking coverage. 'Plug a few gaps where RAM is exposed without checking if it is unaccepted memory' - In the series 'cleanups for lockless slab shrink' Qi Zheng has done some maintenance work which is preparation for the lockless slab shrinking code - Qi Zheng has redone the earlier (and reverted) attempt to make slab shrinking lockless in the series 'use refcount+RCU method to implement lockless slab shrink' - David Hildenbrand contributes some maintenance work for the rmap code in the series 'Anon rmap cleanups' - Kefeng Wang does more folio conversions and some maintenance work in the migration code. Series 'mm: migrate: more folio conversion and unification' - Matthew Wilcox has fixed an issue in the buffer_head code which was causing long stalls under some heavy memory/IO loads. Some cleanups were added on the way. Series 'Add and use bdev_getblk()' - In the series 'Use nth_page() in place of direct struct page manipulation' Zi Yan has fixed a potential issue with the direct manipulation of hugetlb page frames - In the series 'mm: hugetlb: Skip initialization of gigantic tail struct pages if freed by HVO' has improved our handling of gigantic pages in the hugetlb vmmemmep optimizaton code. This provides significant boot time improvements when significant amounts of gigantic pages are in use - Matthew Wilcox has sent the series 'Small hugetlb cleanups' - code rationalization and folio conversions in the hugetlb code - Yin Fengwei has improved mlock()'s handling of large folios in the series 'support large folio for mlock' - In the series 'Expose swapcache stat for memcg v1' Liu Shixin has added statistics for memcg v1 users which are available (and useful) under memcg v2 - Florent Revest has enhanced the MDWE (Memory-Deny-Write-Executable) prctl so that userspace may direct the kernel to not automatically propagate the denial to child processes. The series is named 'MDWE without inheritance' - Kefeng Wang has provided the series 'mm: convert numa balancing functions to use a folio' which does what it says - In the series 'mm/ksm: add fork-exec support for prctl' Stefan Roesch makes is possible for a process to propagate KSM treatment across exec() - Huang Ying has enhanced memory tiering's calculation of memory distances. This is used to permit the dax/kmem driver to use 'high bandwidth memory' in addition to Optane Data Center Persistent Memory Modules (DCPMM). The series is named 'memory tiering: calculate abstract distance based on ACPI HMAT' - In the series 'Smart scanning mode for KSM' Stefan Roesch has optimized KSM by teaching it to retain and use some historical information from previous scans - Yosry Ahmed has fixed some inconsistencies in memcg statistics in the series 'mm: memcg: fix tracking of pending stats updates values' - In the series 'Implement IOCTL to get and optionally clear info about PTEs' Peter Xu has added an ioctl to /proc/<pid>/pagemap which permits us to atomically read-then-clear page softdirty state. This is mainly used by CRIU - Hugh Dickins contributed the series 'shmem,tmpfs: general maintenance', a bunch of relatively minor maintenance tweaks to this code - Matthew Wilcox has increased the use of the VMA lock over file-backed page faults in the series 'Handle more faults under the VMA lock'. Some rationalizations of the fault path became possible as a result - In the series 'mm/rmap: convert page_move_anon_rmap() to folio_move_anon_rmap()' David Hildenbrand has implemented some cleanups and folio conversions - In the series 'various improvements to the GUP interface' Lorenzo Stoakes has simplified and improved the GUP interface with an eye to providing groundwork for future improvements - Andrey Konovalov has sent along the series 'kasan: assorted fixes and improvements' which does those things - Some page allocator maintenance work from Kemeng Shi in the series 'Two minor cleanups to break_down_buddy_pages' - In thes series 'New selftest for mm' Breno Leitao has developed another MM self test which tickles a race we had between madvise() and page faults - In the series 'Add folio_end_read' Matthew Wilcox provides cleanups and an optimization to the core pagecache code - Nhat Pham has added memcg accounting for hugetlb memory in the series 'hugetlb memcg accounting' - Cleanups and rationalizations to the pagemap code from Lorenzo Stoakes, in the series 'Abstract vma_merge() and split_vma()' - Audra Mitchell has fixed issues in the procfs page_owner code's new timestamping feature which was causing some misbehaviours. In the series 'Fix page_owner's use of free timestamps' - Lorenzo Stoakes has fixed the handling of new mappings of sealed files in the series 'permit write-sealed memfd read-only shared mappings' - Mike Kravetz has optimized the hugetlb vmemmap optimization in the series 'Batch hugetlb vmemmap modification operations' - Some buffer_head folio conversions and cleanups from Matthew Wilcox in the series 'Finish the create_empty_buffers() transition' - As a page allocator performance optimization Huang Ying has added automatic tuning to the allocator's per-cpu-pages feature, in the series 'mm: PCP high auto-tuning' - Roman Gushchin has contributed the patchset 'mm: improve performance of accounted kernel memory allocations' which improves their performance by ~30% as measured by a micro-benchmark - folio conversions from Kefeng Wang in the series 'mm: convert page cpupid functions to folios' - Some kmemleak fixups in Liu Shixin's series 'Some bugfix about kmemleak' - Qi Zheng has improved our handling of memoryless nodes by keeping them off the allocation fallback list. This is done in the series 'handle memoryless nodes more appropriately' - khugepaged conversions from Vishal Moola in the series 'Some khugepaged folio conversions'" [ bcachefs conflicts with the dynamically allocated shrinkers have been resolved as per Stephen Rothwell in https://lore.kernel.org/all/20230913093553.4290421e@canb.auug.org.au/ with help from Qi Zheng. The clone3 test filtering conflict was half-arsed by yours truly ] * tag 'mm-stable-2023-11-01-14-33' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (406 commits) mm/damon/sysfs: update monitoring target regions for online input commit mm/damon/sysfs: remove requested targets when online-commit inputs selftests: add a sanity check for zswap Documentation: maple_tree: fix word spelling error mm/vmalloc: fix the unchecked dereference warning in vread_iter() zswap: export compression failure stats Documentation: ubsan: drop "the" from article title mempolicy: migration attempt to match interleave nodes mempolicy: mmap_lock is not needed while migrating folios mempolicy: alloc_pages_mpol() for NUMA policy without vma mm: add page_rmappable_folio() wrapper mempolicy: remove confusing MPOL_MF_LAZY dead code mempolicy: mpol_shared_policy_init() without pseudo-vma mempolicy trivia: use pgoff_t in shared mempolicy tree mempolicy trivia: slightly more consistent naming mempolicy trivia: delete those ancient pr_debug()s mempolicy: fix migrate_pages(2) syscall return nr_failed kernfs: drop shared NUMA mempolicy hooks hugetlbfs: drop shared NUMA mempolicy pretence mm/damon/sysfs-test: add a unit test for damon_sysfs_set_targets() ...
Diffstat (limited to 'drivers')
-rw-r--r--drivers/acpi/acpi_pad.c2
-rw-r--r--drivers/acpi/numa/hmat.c146
-rw-r--r--drivers/android/binder_alloc.c30
-rw-r--r--drivers/base/cacheinfo.c51
-rw-r--r--drivers/dax/kmem.c62
-rw-r--r--drivers/firmware/efi/unaccepted_memory.c20
-rw-r--r--drivers/gpu/drm/i915/gem/i915_gem_shrinker.c29
-rw-r--r--drivers/gpu/drm/i915/i915_drv.h2
-rw-r--r--drivers/gpu/drm/msm/msm_drv.c4
-rw-r--r--drivers/gpu/drm/msm/msm_drv.h4
-rw-r--r--drivers/gpu/drm/msm/msm_gem_shrinker.c33
-rw-r--r--drivers/gpu/drm/panfrost/panfrost_device.h2
-rw-r--r--drivers/gpu/drm/panfrost/panfrost_drv.c6
-rw-r--r--drivers/gpu/drm/panfrost/panfrost_gem.h2
-rw-r--r--drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c29
-rw-r--r--drivers/gpu/drm/ttm/ttm_pool.c40
-rw-r--r--drivers/md/bcache/bcache.h2
-rw-r--r--drivers/md/bcache/btree.c27
-rw-r--r--drivers/md/bcache/sysfs.c3
-rw-r--r--drivers/md/dm-bufio.c28
-rw-r--r--drivers/md/dm-cache-metadata.c2
-rw-r--r--drivers/md/dm-zoned-metadata.c28
-rw-r--r--drivers/md/raid5.c26
-rw-r--r--drivers/md/raid5.h2
-rw-r--r--drivers/misc/vmw_balloon.c38
-rw-r--r--drivers/virtio/virtio_balloon.c24
-rw-r--r--drivers/xen/xenbus/xenbus_probe_backend.c17
27 files changed, 433 insertions, 226 deletions
diff --git a/drivers/acpi/acpi_pad.c b/drivers/acpi/acpi_pad.c
index 32a2c006908b..bd1ad07f0290 100644
--- a/drivers/acpi/acpi_pad.c
+++ b/drivers/acpi/acpi_pad.c
@@ -101,7 +101,7 @@ static void round_robin_cpu(unsigned int tsk_index)
for_each_cpu(cpu, pad_busy_cpus)
cpumask_or(tmp, tmp, topology_sibling_cpumask(cpu));
cpumask_andnot(tmp, cpu_online_mask, tmp);
- /* avoid HT sibilings if possible */
+ /* avoid HT siblings if possible */
if (cpumask_empty(tmp))
cpumask_andnot(tmp, cpu_online_mask, pad_busy_cpus);
if (cpumask_empty(tmp)) {
diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c
index bba268ecd802..9ef5f1bdcfdb 100644
--- a/drivers/acpi/numa/hmat.c
+++ b/drivers/acpi/numa/hmat.c
@@ -24,6 +24,7 @@
#include <linux/node.h>
#include <linux/sysfs.h>
#include <linux/dax.h>
+#include <linux/memory-tiers.h>
static u8 hmat_revision;
static int hmat_disable __initdata;
@@ -582,28 +583,25 @@ static int initiators_to_nodemask(unsigned long *p_nodes)
return 0;
}
-static void hmat_register_target_initiators(struct memory_target *target)
+static void hmat_update_target_attrs(struct memory_target *target,
+ unsigned long *p_nodes, int access)
{
- static DECLARE_BITMAP(p_nodes, MAX_NUMNODES);
struct memory_initiator *initiator;
- unsigned int mem_nid, cpu_nid;
+ unsigned int cpu_nid;
struct memory_locality *loc = NULL;
u32 best = 0;
- bool access0done = false;
int i;
- mem_nid = pxm_to_node(target->memory_pxm);
+ bitmap_zero(p_nodes, MAX_NUMNODES);
/*
- * If the Address Range Structure provides a local processor pxm, link
+ * If the Address Range Structure provides a local processor pxm, set
* only that one. Otherwise, find the best performance attributes and
- * register all initiators that match.
+ * collect all initiators that match.
*/
if (target->processor_pxm != PXM_INVAL) {
cpu_nid = pxm_to_node(target->processor_pxm);
- register_memory_node_under_compute_node(mem_nid, cpu_nid, 0);
- access0done = true;
- if (node_state(cpu_nid, N_CPU)) {
- register_memory_node_under_compute_node(mem_nid, cpu_nid, 1);
+ if (access == 0 || node_state(cpu_nid, N_CPU)) {
+ set_bit(target->processor_pxm, p_nodes);
return;
}
}
@@ -617,47 +615,10 @@ static void hmat_register_target_initiators(struct memory_target *target)
* We'll also use the sorting to prime the candidate nodes with known
* initiators.
*/
- bitmap_zero(p_nodes, MAX_NUMNODES);
list_sort(NULL, &initiators, initiator_cmp);
if (initiators_to_nodemask(p_nodes) < 0)
return;
- if (!access0done) {
- for (i = WRITE_LATENCY; i <= READ_BANDWIDTH; i++) {
- loc = localities_types[i];
- if (!loc)
- continue;
-
- best = 0;
- list_for_each_entry(initiator, &initiators, node) {
- u32 value;
-
- if (!test_bit(initiator->processor_pxm, p_nodes))
- continue;
-
- value = hmat_initiator_perf(target, initiator,
- loc->hmat_loc);
- if (hmat_update_best(loc->hmat_loc->data_type, value, &best))
- bitmap_clear(p_nodes, 0, initiator->processor_pxm);
- if (value != best)
- clear_bit(initiator->processor_pxm, p_nodes);
- }
- if (best)
- hmat_update_target_access(target, loc->hmat_loc->data_type,
- best, 0);
- }
-
- for_each_set_bit(i, p_nodes, MAX_NUMNODES) {
- cpu_nid = pxm_to_node(i);
- register_memory_node_under_compute_node(mem_nid, cpu_nid, 0);
- }
- }
-
- /* Access 1 ignores Generic Initiators */
- bitmap_zero(p_nodes, MAX_NUMNODES);
- if (initiators_to_nodemask(p_nodes) < 0)
- return;
-
for (i = WRITE_LATENCY; i <= READ_BANDWIDTH; i++) {
loc = localities_types[i];
if (!loc)
@@ -667,7 +628,7 @@ static void hmat_register_target_initiators(struct memory_target *target)
list_for_each_entry(initiator, &initiators, node) {
u32 value;
- if (!initiator->has_cpu) {
+ if (access == 1 && !initiator->has_cpu) {
clear_bit(initiator->processor_pxm, p_nodes);
continue;
}
@@ -681,14 +642,33 @@ static void hmat_register_target_initiators(struct memory_target *target)
clear_bit(initiator->processor_pxm, p_nodes);
}
if (best)
- hmat_update_target_access(target, loc->hmat_loc->data_type, best, 1);
+ hmat_update_target_access(target, loc->hmat_loc->data_type, best, access);
}
+}
+
+static void __hmat_register_target_initiators(struct memory_target *target,
+ unsigned long *p_nodes,
+ int access)
+{
+ unsigned int mem_nid, cpu_nid;
+ int i;
+
+ mem_nid = pxm_to_node(target->memory_pxm);
+ hmat_update_target_attrs(target, p_nodes, access);
for_each_set_bit(i, p_nodes, MAX_NUMNODES) {
cpu_nid = pxm_to_node(i);
- register_memory_node_under_compute_node(mem_nid, cpu_nid, 1);
+ register_memory_node_under_compute_node(mem_nid, cpu_nid, access);
}
}
+static void hmat_register_target_initiators(struct memory_target *target)
+{
+ static DECLARE_BITMAP(p_nodes, MAX_NUMNODES);
+
+ __hmat_register_target_initiators(target, p_nodes, 0);
+ __hmat_register_target_initiators(target, p_nodes, 1);
+}
+
static void hmat_register_target_cache(struct memory_target *target)
{
unsigned mem_nid = pxm_to_node(target->memory_pxm);
@@ -780,6 +760,61 @@ static int hmat_callback(struct notifier_block *self,
return NOTIFY_OK;
}
+static int hmat_set_default_dram_perf(void)
+{
+ int rc;
+ int nid, pxm;
+ struct memory_target *target;
+ struct node_hmem_attrs *attrs;
+
+ if (!default_dram_type)
+ return -EIO;
+
+ for_each_node_mask(nid, default_dram_type->nodes) {
+ pxm = node_to_pxm(nid);
+ target = find_mem_target(pxm);
+ if (!target)
+ continue;
+ attrs = &target->hmem_attrs[1];
+ rc = mt_set_default_dram_perf(nid, attrs, "ACPI HMAT");
+ if (rc)
+ return rc;
+ }
+
+ return 0;
+}
+
+static int hmat_calculate_adistance(struct notifier_block *self,
+ unsigned long nid, void *data)
+{
+ static DECLARE_BITMAP(p_nodes, MAX_NUMNODES);
+ struct memory_target *target;
+ struct node_hmem_attrs *perf;
+ int *adist = data;
+ int pxm;
+
+ pxm = node_to_pxm(nid);
+ target = find_mem_target(pxm);
+ if (!target)
+ return NOTIFY_OK;
+
+ mutex_lock(&target_lock);
+ hmat_update_target_attrs(target, p_nodes, 1);
+ mutex_unlock(&target_lock);
+
+ perf = &target->hmem_attrs[1];
+
+ if (mt_perf_to_adistance(perf, adist))
+ return NOTIFY_OK;
+
+ return NOTIFY_STOP;
+}
+
+static struct notifier_block hmat_adist_nb __meminitdata = {
+ .notifier_call = hmat_calculate_adistance,
+ .priority = 100,
+};
+
static __init void hmat_free_structures(void)
{
struct memory_target *target, *tnext;
@@ -862,8 +897,13 @@ static __init int hmat_init(void)
hmat_register_targets();
/* Keep the table and structures if the notifier may use them */
- if (!hotplug_memory_notifier(hmat_callback, HMAT_CALLBACK_PRI))
- return 0;
+ if (hotplug_memory_notifier(hmat_callback, HMAT_CALLBACK_PRI))
+ goto out_put;
+
+ if (!hmat_set_default_dram_perf())
+ register_mt_adistance_algorithm(&hmat_adist_nb);
+
+ return 0;
out_put:
hmat_free_structures();
acpi_put_table(tbl);
diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index e3db8297095a..138f6d43d13b 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -1053,11 +1053,7 @@ binder_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
NULL, sc->nr_to_scan);
}
-static struct shrinker binder_shrinker = {
- .count_objects = binder_shrink_count,
- .scan_objects = binder_shrink_scan,
- .seeks = DEFAULT_SEEKS,
-};
+static struct shrinker *binder_shrinker;
/**
* binder_alloc_init() - called by binder_open() for per-proc initialization
@@ -1077,19 +1073,29 @@ void binder_alloc_init(struct binder_alloc *alloc)
int binder_alloc_shrinker_init(void)
{
- int ret = list_lru_init(&binder_alloc_lru);
+ int ret;
- if (ret == 0) {
- ret = register_shrinker(&binder_shrinker, "android-binder");
- if (ret)
- list_lru_destroy(&binder_alloc_lru);
+ ret = list_lru_init(&binder_alloc_lru);
+ if (ret)
+ return ret;
+
+ binder_shrinker = shrinker_alloc(0, "android-binder");
+ if (!binder_shrinker) {
+ list_lru_destroy(&binder_alloc_lru);
+ return -ENOMEM;
}
- return ret;
+
+ binder_shrinker->count_objects = binder_shrink_count;
+ binder_shrinker->scan_objects = binder_shrink_scan;
+
+ shrinker_register(binder_shrinker);
+
+ return 0;
}
void binder_alloc_shrinker_exit(void)
{
- unregister_shrinker(&binder_shrinker);
+ shrinker_free(binder_shrinker);
list_lru_destroy(&binder_alloc_lru);
}
diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c
index cbae8be1fe52..f1e79263fe61 100644
--- a/drivers/base/cacheinfo.c
+++ b/drivers/base/cacheinfo.c
@@ -898,6 +898,48 @@ err:
return rc;
}
+/*
+ * Calculate the size of the per-CPU data cache slice. This can be
+ * used to estimate the size of the data cache slice that can be used
+ * by one CPU under ideal circumstances. UNIFIED caches are counted
+ * in addition to DATA caches. So, please consider code cache usage
+ * when use the result.
+ *
+ * Because the cache inclusive/non-inclusive information isn't
+ * available, we just use the size of the per-CPU slice of LLC to make
+ * the result more predictable across architectures.
+ */
+static void update_per_cpu_data_slice_size_cpu(unsigned int cpu)
+{
+ struct cpu_cacheinfo *ci;
+ struct cacheinfo *llc;
+ unsigned int nr_shared;
+
+ if (!last_level_cache_is_valid(cpu))
+ return;
+
+ ci = ci_cacheinfo(cpu);
+ llc = per_cpu_cacheinfo_idx(cpu, cache_leaves(cpu) - 1);
+
+ if (llc->type != CACHE_TYPE_DATA && llc->type != CACHE_TYPE_UNIFIED)
+ return;
+
+ nr_shared = cpumask_weight(&llc->shared_cpu_map);
+ if (nr_shared)
+ ci->per_cpu_data_slice_size = llc->size / nr_shared;
+}
+
+static void update_per_cpu_data_slice_size(bool cpu_online, unsigned int cpu)
+{
+ unsigned int icpu;
+
+ for_each_online_cpu(icpu) {
+ if (!cpu_online && icpu == cpu)
+ continue;
+ update_per_cpu_data_slice_size_cpu(icpu);
+ }
+}
+
static int cacheinfo_cpu_online(unsigned int cpu)
{
int rc = detect_cache_attributes(cpu);
@@ -906,7 +948,12 @@ static int cacheinfo_cpu_online(unsigned int cpu)
return rc;
rc = cache_add_dev(cpu);
if (rc)
- free_cache_attributes(cpu);
+ goto err;
+ update_per_cpu_data_slice_size(true, cpu);
+ setup_pcp_cacheinfo();
+ return 0;
+err:
+ free_cache_attributes(cpu);
return rc;
}
@@ -916,6 +963,8 @@ static int cacheinfo_cpu_pre_down(unsigned int cpu)
cpu_cache_sysfs_exit(cpu);
free_cache_attributes(cpu);
+ update_per_cpu_data_slice_size(false, cpu);
+ setup_pcp_cacheinfo();
return 0;
}
diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c
index c57acb73e3db..369c698b7706 100644
--- a/drivers/dax/kmem.c
+++ b/drivers/dax/kmem.c
@@ -49,14 +49,52 @@ struct dax_kmem_data {
struct resource *res[];
};
-static struct memory_dev_type *dax_slowmem_type;
+static DEFINE_MUTEX(kmem_memory_type_lock);
+static LIST_HEAD(kmem_memory_types);
+
+static struct memory_dev_type *kmem_find_alloc_memory_type(int adist)
+{
+ bool found = false;
+ struct memory_dev_type *mtype;
+
+ mutex_lock(&kmem_memory_type_lock);
+ list_for_each_entry(mtype, &kmem_memory_types, list) {
+ if (mtype->adistance == adist) {
+ found = true;
+ break;
+ }
+ }
+ if (!found) {
+ mtype = alloc_memory_type(adist);
+ if (!IS_ERR(mtype))
+ list_add(&mtype->list, &kmem_memory_types);
+ }
+ mutex_unlock(&kmem_memory_type_lock);
+
+ return mtype;
+}
+
+static void kmem_put_memory_types(void)
+{
+ struct memory_dev_type *mtype, *mtn;
+
+ mutex_lock(&kmem_memory_type_lock);
+ list_for_each_entry_safe(mtype, mtn, &kmem_memory_types, list) {
+ list_del(&mtype->list);
+ put_memory_type(mtype);
+ }
+ mutex_unlock(&kmem_memory_type_lock);
+}
+
static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
{
struct device *dev = &dev_dax->dev;
unsigned long total_len = 0;
struct dax_kmem_data *data;
+ struct memory_dev_type *mtype;
int i, rc, mapped = 0;
int numa_node;
+ int adist = MEMTIER_DEFAULT_DAX_ADISTANCE;
/*
* Ensure good NUMA information for the persistent memory.
@@ -71,6 +109,11 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
return -EINVAL;
}
+ mt_calc_adistance(numa_node, &adist);
+ mtype = kmem_find_alloc_memory_type(adist);
+ if (IS_ERR(mtype))
+ return PTR_ERR(mtype);
+
for (i = 0; i < dev_dax->nr_range; i++) {
struct range range;
@@ -88,7 +131,7 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
return -EINVAL;
}
- init_node_memory_type(numa_node, dax_slowmem_type);
+ init_node_memory_type(numa_node, mtype);
rc = -ENOMEM;
data = kzalloc(struct_size(data, res, dev_dax->nr_range), GFP_KERNEL);
@@ -167,7 +210,7 @@ err_reg_mgid:
err_res_name:
kfree(data);
err_dax_kmem_data:
- clear_node_memory_type(numa_node, dax_slowmem_type);
+ clear_node_memory_type(numa_node, mtype);
return rc;
}
@@ -219,7 +262,7 @@ static void dev_dax_kmem_remove(struct dev_dax *dev_dax)
* for that. This implies this reference will be around
* till next reboot.
*/
- clear_node_memory_type(node, dax_slowmem_type);
+ clear_node_memory_type(node, NULL);
}
}
#else
@@ -251,12 +294,6 @@ static int __init dax_kmem_init(void)
if (!kmem_name)
return -ENOMEM;
- dax_slowmem_type = alloc_memory_type(MEMTIER_DEFAULT_DAX_ADISTANCE);
- if (IS_ERR(dax_slowmem_type)) {
- rc = PTR_ERR(dax_slowmem_type);
- goto err_dax_slowmem_type;
- }
-
rc = dax_driver_register(&device_dax_kmem_driver);
if (rc)
goto error_dax_driver;
@@ -264,8 +301,7 @@ static int __init dax_kmem_init(void)
return rc;
error_dax_driver:
- put_memory_type(dax_slowmem_type);
-err_dax_slowmem_type:
+ kmem_put_memory_types();
kfree_const(kmem_name);
return rc;
}
@@ -275,7 +311,7 @@ static void __exit dax_kmem_exit(void)
dax_driver_unregister(&device_dax_kmem_driver);
if (!any_hotremove_failed)
kfree_const(kmem_name);
- put_memory_type(dax_slowmem_type);
+ kmem_put_memory_types();
}
MODULE_AUTHOR("Intel Corporation");
diff --git a/drivers/firmware/efi/unaccepted_memory.c b/drivers/firmware/efi/unaccepted_memory.c
index 135278ddaf62..3f2f7bf6e335 100644
--- a/drivers/firmware/efi/unaccepted_memory.c
+++ b/drivers/firmware/efi/unaccepted_memory.c
@@ -3,6 +3,7 @@
#include <linux/efi.h>
#include <linux/memblock.h>
#include <linux/spinlock.h>
+#include <linux/crash_dump.h>
#include <asm/unaccepted_memory.h>
/* Protects unaccepted memory bitmap and accepting_list */
@@ -201,3 +202,22 @@ bool range_contains_unaccepted_memory(phys_addr_t start, phys_addr_t end)
return ret;
}
+
+#ifdef CONFIG_PROC_VMCORE
+static bool unaccepted_memory_vmcore_pfn_is_ram(struct vmcore_cb *cb,
+ unsigned long pfn)
+{
+ return !pfn_is_unaccepted_memory(pfn);
+}
+
+static struct vmcore_cb vmcore_cb = {
+ .pfn_is_ram = unaccepted_memory_vmcore_pfn_is_ram,
+};
+
+static int __init unaccepted_memory_init_kdump(void)
+{
+ register_vmcore_cb(&vmcore_cb);
+ return 0;
+}
+core_initcall(unaccepted_memory_init_kdump);
+#endif /* CONFIG_PROC_VMCORE */
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
index 9cb7bbfb4278..d166052eb2ce 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
@@ -288,8 +288,7 @@ unsigned long i915_gem_shrink_all(struct drm_i915_private *i915)
static unsigned long
i915_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc)
{
- struct drm_i915_private *i915 =
- container_of(shrinker, struct drm_i915_private, mm.shrinker);
+ struct drm_i915_private *i915 = shrinker->private_data;
unsigned long num_objects;
unsigned long count;
@@ -306,8 +305,8 @@ i915_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc)
if (num_objects) {
unsigned long avg = 2 * count / num_objects;
- i915->mm.shrinker.batch =
- max((i915->mm.shrinker.batch + avg) >> 1,
+ i915->mm.shrinker->batch =
+ max((i915->mm.shrinker->batch + avg) >> 1,
128ul /* default SHRINK_BATCH */);
}
@@ -317,8 +316,7 @@ i915_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc)
static unsigned long
i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
{
- struct drm_i915_private *i915 =
- container_of(shrinker, struct drm_i915_private, mm.shrinker);
+ struct drm_i915_private *i915 = shrinker->private_data;
unsigned long freed;
sc->nr_scanned = 0;
@@ -430,12 +428,17 @@ i915_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr
void i915_gem_driver_register__shrinker(struct drm_i915_private *i915)
{
- i915->mm.shrinker.scan_objects = i915_gem_shrinker_scan;
- i915->mm.shrinker.count_objects = i915_gem_shrinker_count;
- i915->mm.shrinker.seeks = DEFAULT_SEEKS;
- i915->mm.shrinker.batch = 4096;
- drm_WARN_ON(&i915->drm, register_shrinker(&i915->mm.shrinker,
- "drm-i915_gem"));
+ i915->mm.shrinker = shrinker_alloc(0, "drm-i915_gem");
+ if (!i915->mm.shrinker) {
+ drm_WARN_ON(&i915->drm, 1);
+ } else {
+ i915->mm.shrinker->scan_objects = i915_gem_shrinker_scan;
+ i915->mm.shrinker->count_objects = i915_gem_shrinker_count;
+ i915->mm.shrinker->batch = 4096;
+ i915->mm.shrinker->private_data = i915;
+
+ shrinker_register(i915->mm.shrinker);
+ }
i915->mm.oom_notifier.notifier_call = i915_gem_shrinker_oom;
drm_WARN_ON(&i915->drm, register_oom_notifier(&i915->mm.oom_notifier));
@@ -451,7 +454,7 @@ void i915_gem_driver_unregister__shrinker(struct drm_i915_private *i915)
unregister_vmap_purge_notifier(&i915->mm.vmap_notifier));
drm_WARN_ON(&i915->drm,
unregister_oom_notifier(&i915->mm.oom_notifier));
- unregister_shrinker(&i915->mm.shrinker);
+ shrinker_free(i915->mm.shrinker);
}
void i915_gem_shrinker_taints_mutex(struct drm_i915_private *i915,
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 6a2a78c61f21..dd452c220df7 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -163,7 +163,7 @@ struct i915_gem_mm {
struct notifier_block oom_notifier;
struct notifier_block vmap_notifier;
- struct shrinker shrinker;
+ struct shrinker *shrinker;
#ifdef CONFIG_MMU_NOTIFIER
/**
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 443bbc3ed750..2aae7d107f33 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -265,7 +265,9 @@ static int msm_drm_init(struct device *dev, const struct drm_driver *drv)
if (ret)
goto err_deinit_vram;
- msm_gem_shrinker_init(ddev);
+ ret = msm_gem_shrinker_init(ddev);
+ if (ret)
+ goto err_msm_uninit;
if (priv->kms_init) {
ret = msm_drm_kms_init(dev, drv);
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index 7dbd0f06898b..cd5bf658df66 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -218,7 +218,7 @@ struct msm_drm_private {
} vram;
struct notifier_block vmap_notifier;
- struct shrinker shrinker;
+ struct shrinker *shrinker;
struct drm_atomic_state *pm_state;
@@ -280,7 +280,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
unsigned long msm_gem_shrinker_shrink(struct drm_device *dev, unsigned long nr_to_scan);
#endif
-void msm_gem_shrinker_init(struct drm_device *dev);
+int msm_gem_shrinker_init(struct drm_device *dev);
void msm_gem_shrinker_cleanup(struct drm_device *dev);
struct sg_table *msm_gem_prime_get_sg_table(struct drm_gem_object *obj);
diff --git a/drivers/gpu/drm/msm/msm_gem_shrinker.c b/drivers/gpu/drm/msm/msm_gem_shrinker.c
index f38296ad8743..5a7d48c02c4b 100644
--- a/drivers/gpu/drm/msm/msm_gem_shrinker.c
+++ b/drivers/gpu/drm/msm/msm_gem_shrinker.c
@@ -34,8 +34,7 @@ static bool can_block(struct shrink_control *sc)
static unsigned long
msm_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc)
{
- struct msm_drm_private *priv =
- container_of(shrinker, struct msm_drm_private, shrinker);
+ struct msm_drm_private *priv = shrinker->private_data;
unsigned count = priv->lru.dontneed.count;
if (can_swap())
@@ -100,8 +99,7 @@ active_evict(struct drm_gem_object *obj)
static unsigned long
msm_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
{
- struct msm_drm_private *priv =
- container_of(shrinker, struct msm_drm_private, shrinker);
+ struct msm_drm_private *priv = shrinker->private_data;
struct {
struct drm_gem_lru *lru;
bool (*shrink)(struct drm_gem_object *obj);
@@ -148,10 +146,11 @@ msm_gem_shrinker_shrink(struct drm_device *dev, unsigned long nr_to_scan)
struct shrink_control sc = {
.nr_to_scan = nr_to_scan,
};
- int ret;
+ unsigned long ret = SHRINK_STOP;
fs_reclaim_acquire(GFP_KERNEL);
- ret = msm_gem_shrinker_scan(&priv->shrinker, &sc);
+ if (priv->shrinker)
+ ret = msm_gem_shrinker_scan(priv->shrinker, &sc);
fs_reclaim_release(GFP_KERNEL);
return ret;
@@ -210,16 +209,24 @@ msm_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr)
*
* This function registers and sets up the msm shrinker.
*/
-void msm_gem_shrinker_init(struct drm_device *dev)
+int msm_gem_shrinker_init(struct drm_device *dev)
{
struct msm_drm_private *priv = dev->dev_private;
- priv->shrinker.count_objects = msm_gem_shrinker_count;
- priv->shrinker.scan_objects = msm_gem_shrinker_scan;
- priv->shrinker.seeks = DEFAULT_SEEKS;
- WARN_ON(register_shrinker(&priv->shrinker, "drm-msm_gem"));
+
+ priv->shrinker = shrinker_alloc(0, "drm-msm_gem");
+ if (!priv->shrinker)
+ return -ENOMEM;
+
+ priv->shrinker->count_objects = msm_gem_shrinker_count;
+ priv->shrinker->scan_objects = msm_gem_shrinker_scan;
+ priv->shrinker->private_data = priv;
+
+ shrinker_register(priv->shrinker);
priv->vmap_notifier.notifier_call = msm_gem_shrinker_vmap;
WARN_ON(register_vmap_purge_notifier(&priv->vmap_notifier));
+
+ return 0;
}
/**
@@ -232,8 +239,8 @@ void msm_gem_shrinker_cleanup(struct drm_device *dev)
{
struct msm_drm_private *priv = dev->dev_private;
- if (priv->shrinker.nr_deferred) {
+ if (priv->shrinker) {
WARN_ON(unregister_vmap_purge_notifier(&priv->vmap_notifier));
- unregister_shrinker(&priv->shrinker);
+ shrinker_free(priv->shrinker);
}
}
diff --git a/drivers/gpu/drm/panfrost/panfrost_device.h b/drivers/gpu/drm/panfrost/panfrost_device.h
index 1e85656dc2f7..1ef38f60d5dc 100644
--- a/drivers/gpu/drm/panfrost/panfrost_device.h
+++ b/drivers/gpu/drm/panfrost/panfrost_device.h
@@ -119,7 +119,7 @@ struct panfrost_device {
struct mutex shrinker_lock;
struct list_head shrinker_list;
- struct shrinker shrinker;
+ struct shrinker *shrinker;
struct panfrost_devfreq pfdevfreq;
diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c
index b834777b409b..7cabf4e3d1f2 100644
--- a/drivers/gpu/drm/panfrost/panfrost_drv.c
+++ b/drivers/gpu/drm/panfrost/panfrost_drv.c
@@ -659,10 +659,14 @@ static int panfrost_probe(struct platform_device *pdev)
if (err < 0)
goto err_out1;
- panfrost_gem_shrinker_init(ddev);
+ err = panfrost_gem_shrinker_init(ddev);
+ if (err)
+ goto err_out2;
return 0;
+err_out2:
+ drm_dev_unregister(ddev);
err_out1:
pm_runtime_disable(pfdev->dev);
panfrost_device_fini(pfdev);
diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.h b/drivers/gpu/drm/panfrost/panfrost_gem.h
index 13c0a8149c3a..7516b7ecf7fe 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gem.h
+++ b/drivers/gpu/drm/panfrost/panfrost_gem.h
@@ -86,7 +86,7 @@ panfrost_gem_mapping_get(struct panfrost_gem_object *bo,
void panfrost_gem_mapping_put(struct panfrost_gem_mapping *mapping);
void panfrost_gem_teardown_mappings_locked(struct panfrost_gem_object *bo);
-void panfrost_gem_shrinker_init(struct drm_device *dev);
+int panfrost_gem_shrinker_init(struct drm_device *dev);
void panfrost_gem_shrinker_cleanup(struct drm_device *dev);
#endif /* __PANFROST_GEM_H__ */
diff --git a/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c b/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c
index 6a71a2555f85..3d9f51bd48b6 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c
@@ -18,8 +18,7 @@
static unsigned long
panfrost_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc)
{
- struct panfrost_device *pfdev =
- container_of(shrinker, struct panfrost_device, shrinker);
+ struct panfrost_device *pfdev = shrinker->private_data;
struct drm_gem_shmem_object *shmem;
unsigned long count = 0;
@@ -65,8 +64,7 @@ unlock_mappings:
static unsigned long
panfrost_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
{
- struct panfrost_device *pfdev =
- container_of(shrinker, struct panfrost_device, shrinker);
+ struct panfrost_device *pfdev = shrinker->private_data;
struct drm_gem_shmem_object *shmem, *tmp;
unsigned long freed = 0;
@@ -97,13 +95,21 @@ panfrost_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
*
* This function registers and sets up the panfrost shrinker.
*/
-void panfrost_gem_shrinker_init(struct drm_device *dev)
+int panfrost_gem_shrinker_init(struct drm_device *dev)
{
struct panfrost_device *pfdev = dev->dev_private;
- pfdev->shrinker.count_objects = panfrost_gem_shrinker_count;
- pfdev->shrinker.scan_objects = panfrost_gem_shrinker_scan;
- pfdev->shrinker.seeks = DEFAULT_SEEKS;
- WARN_ON(register_shrinker(&pfdev->shrinker, "drm-panfrost"));
+
+ pfdev->shrinker = shrinker_alloc(0, "drm-panfrost");
+ if (!pfdev->shrinker)
+ return -ENOMEM;
+
+ pfdev->shrinker->count_objects = panfrost_gem_shrinker_count;
+ pfdev->shrinker->scan_objects = panfrost_gem_shrinker_scan;
+ pfdev->shrinker->private_data = pfdev;
+
+ shrinker_register(pfdev->shrinker);
+
+ return 0;
}
/**
@@ -116,7 +122,6 @@ void panfrost_gem_shrinker_cleanup(struct drm_device *dev)
{
struct panfrost_device *pfdev = dev->dev_private;
- if (pfdev->shrinker.nr_deferred) {
- unregister_shrinker(&pfdev->shrinker);
- }
+ if (pfdev->shrinker)
+ shrinker_free(pfdev->shrinker);
}
diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c
index cddb9151d20f..fe610a3cace0 100644
--- a/drivers/gpu/drm/ttm/ttm_pool.c
+++ b/drivers/gpu/drm/ttm/ttm_pool.c
@@ -73,7 +73,8 @@ static struct ttm_pool_type global_dma32_uncached[MAX_ORDER + 1];
static spinlock_t shrinker_lock;
static struct list_head shrinker_list;
-static struct shrinker mm_shrinker;
+static struct shrinker *mm_shrinker;
+static DECLARE_RWSEM(pool_shrink_rwsem);
/* Allocate pages of size 1 << order with the given gfp_flags */
static struct page *ttm_pool_alloc_page(struct ttm_pool *pool, gfp_t gfp_flags,
@@ -317,6 +318,7 @@ static unsigned int ttm_pool_shrink(void)
unsigned int num_pages;
struct page *p;
+ down_read(&pool_shrink_rwsem);
spin_lock(&shrinker_lock);
pt = list_first_entry(&shrinker_list, typeof(*pt), shrinker_list);
list_move_tail(&pt->shrinker_list, &shrinker_list);
@@ -329,6 +331,7 @@ static unsigned int ttm_pool_shrink(void)
} else {
num_pages = 0;
}
+ up_read(&pool_shrink_rwsem);
return num_pages;
}
@@ -573,6 +576,18 @@ void ttm_pool_init(struct ttm_pool *pool, struct device *dev,
EXPORT_SYMBOL(ttm_pool_init);
/**
+ * ttm_pool_synchronize_shrinkers - Wait for all running shrinkers to complete.
+ *
+ * This is useful to guarantee that all shrinker invocations have seen an
+ * update, before freeing memory, similar to rcu.
+ */
+static void ttm_pool_synchronize_shrinkers(void)
+{
+ down_write(&pool_shrink_rwsem);
+ up_write(&pool_shrink_rwsem);
+}
+
+/**
* ttm_pool_fini - Cleanup a pool
*
* @pool: the pool to clean up
@@ -593,7 +608,7 @@ void ttm_pool_fini(struct ttm_pool *pool)
/* We removed the pool types from the LRU, but we need to also make sure
* that no shrinker is concurrently freeing pages from the pool.
*/
- synchronize_shrinkers();
+ ttm_pool_synchronize_shrinkers();
}
EXPORT_SYMBOL(ttm_pool_fini);
@@ -734,8 +749,8 @@ static int ttm_pool_debugfs_shrink_show(struct seq_file *m, void *data)
struct shrink_control sc = { .gfp_mask = GFP_NOFS };
fs_reclaim_acquire(GFP_KERNEL);
- seq_printf(m, "%lu/%lu\n", ttm_pool_shrinker_count(&mm_shrinker, &sc),
- ttm_pool_shrinker_scan(&mm_shrinker, &sc));
+ seq_printf(m, "%lu/%lu\n", ttm_pool_shrinker_count(mm_shrinker, &sc),
+ ttm_pool_shrinker_scan(mm_shrinker, &sc));
fs_reclaim_release(GFP_KERNEL);
return 0;
@@ -779,10 +794,17 @@ int ttm_pool_mgr_init(unsigned long num_pages)
&ttm_pool_debugfs_shrink_fops);
#endif
- mm_shrinker.count_objects = ttm_pool_shrinker_count;
- mm_shrinker.scan_objects = ttm_pool_shrinker_scan;
- mm_shrinker.seeks = 1;
- return register_shrinker(&mm_shrinker, "drm-ttm_pool");
+ mm_shrinker = shrinker_alloc(0, "drm-ttm_pool");
+ if (!mm_shrinker)
+ return -ENOMEM;
+
+ mm_shrinker->count_objects = ttm_pool_shrinker_count;
+ mm_shrinker->scan_objects = ttm_pool_shrinker_scan;
+ mm_shrinker->seeks = 1;
+
+ shrinker_register(mm_shrinker);
+
+ return 0;
}
/**
@@ -802,6 +824,6 @@ void ttm_pool_mgr_fini(void)
ttm_pool_type_fini(&global_dma32_uncached[i]);
}
- unregister_shrinker(&mm_shrinker);
+ shrinker_free(mm_shrinker);
WARN_ON(!list_empty(&shrinker_list));
}
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 313cee6ad009..05be59ae21b2 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -543,7 +543,7 @@ struct cache_set {
struct bio_set bio_split;
/* For the btree cache */
- struct shrinker shrink;
+ struct shrinker *shrink;
/* For the btree cache and anything allocation related */
struct mutex bucket_lock;
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index fd121a61f17c..ae5cbb55861f 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -667,7 +667,7 @@ out_unlock:
static unsigned long bch_mca_scan(struct shrinker *shrink,
struct shrink_control *sc)
{
- struct cache_set *c = container_of(shrink, struct cache_set, shrink);
+ struct cache_set *c = shrink->private_data;
struct btree *b, *t;
unsigned long i, nr = sc->nr_to_scan;
unsigned long freed = 0;
@@ -734,7 +734,7 @@ out:
static unsigned long bch_mca_count(struct shrinker *shrink,
struct shrink_control *sc)
{
- struct cache_set *c = container_of(shrink, struct cache_set, shrink);
+ struct cache_set *c = shrink->private_data;
if (c->shrinker_disabled)
return 0;
@@ -752,8 +752,8 @@ void bch_btree_cache_free(struct cache_set *c)
closure_init_stack(&cl);
- if (c->shrink.list.next)
- unregister_shrinker(&c->shrink);
+ if (c->shrink)
+ shrinker_free(c->shrink);
mutex_lock(&c->bucket_lock);
@@ -828,14 +828,19 @@ int bch_btree_cache_alloc(struct cache_set *c)
c->verify_data = NULL;
#endif
- c->shrink.count_objects = bch_mca_count;
- c->shrink.scan_objects = bch_mca_scan;
- c->shrink.seeks = 4;
- c->shrink.batch = c->btree_pages * 2;
+ c->shrink = shrinker_alloc(0, "md-bcache:%pU", c->set_uuid);
+ if (!c->shrink) {
+ pr_warn("bcache: %s: could not allocate shrinker\n", __func__);
+ return 0;
+ }
+
+ c->shrink->count_objects = bch_mca_count;
+ c->shrink->scan_objects = bch_mca_scan;
+ c->shrink->seeks = 4;
+ c->shrink->batch = c->btree_pages * 2;
+ c->shrink->private_data = c;
- if (register_shrinker(&c->shrink, "md-bcache:%pU", c->set_uuid))
- pr_warn("bcache: %s: could not register shrinker\n",
- __func__);
+ shrinker_register(c->shrink);
return 0;
}
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 0e2c1880f60b..45d8af755de6 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -866,7 +866,8 @@ STORE(__bch_cache_set)
sc.gfp_mask = GFP_KERNEL;
sc.nr_to_scan = strtoul_or_return(buf);
- c->shrink.scan_objects(&c->shrink, &sc);
+ if (c->shrink)
+ c->shrink->scan_objects(c->shrink, &sc);
}
sysfs_strtoul_clamp(congested_read_threshold_us,
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index bc309e41d074..62eb27639c9b 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -963,7 +963,7 @@ struct dm_bufio_client {
sector_t start;
- struct shrinker shrinker;
+ struct shrinker *shrinker;
struct work_struct shrink_work;
atomic_long_t need_shrink;
@@ -2368,7 +2368,7 @@ static unsigned long dm_bufio_shrink_scan(struct shrinker *shrink, struct shrink
{
struct dm_bufio_client *c;
- c = container_of(shrink, struct dm_bufio_client, shrinker);
+ c = shrink->private_data;
atomic_long_add(sc->nr_to_scan, &c->need_shrink);
queue_work(dm_bufio_wq, &c->shrink_work);
@@ -2377,7 +2377,7 @@ static unsigned long dm_bufio_shrink_scan(struct shrinker *shrink, struct shrink
static unsigned long dm_bufio_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
{
- struct dm_bufio_client *c = container_of(shrink, struct dm_bufio_client, shrinker);
+ struct dm_bufio_client *c = shrink->private_data;
unsigned long count = cache_total(&c->cache);
unsigned long retain_target = get_retain_buffers(c);
unsigned long queued_for_cleanup = atomic_long_read(&c->need_shrink);
@@ -2490,14 +2490,20 @@ struct dm_bufio_client *dm_bufio_client_create(struct block_device *bdev, unsign
INIT_WORK(&c->shrink_work, shrink_work);
atomic_long_set(&c->need_shrink, 0);
- c->shrinker.count_objects = dm_bufio_shrink_count;
- c->shrinker.scan_objects = dm_bufio_shrink_scan;
- c->shrinker.seeks = 1;
- c->shrinker.batch = 0;
- r = register_shrinker(&c->shrinker, "dm-bufio:(%u:%u)",
- MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev));
- if (r)
+ c->shrinker = shrinker_alloc(0, "dm-bufio:(%u:%u)",
+ MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev));
+ if (!c->shrinker) {
+ r = -ENOMEM;
goto bad;
+ }
+
+ c->shrinker->count_objects = dm_bufio_shrink_count;
+ c->shrinker->scan_objects = dm_bufio_shrink_scan;
+ c->shrinker->seeks = 1;
+ c->shrinker->batch = 0;
+ c->shrinker->private_data = c;
+
+ shrinker_register(c->shrinker);
mutex_lock(&dm_bufio_clients_lock);
dm_bufio_client_count++;
@@ -2537,7 +2543,7 @@ void dm_bufio_client_destroy(struct dm_bufio_client *c)
drop_buffers(c);
- unregister_shrinker(&c->shrinker);
+ shrinker_free(c->shrinker);
flush_work(&c->shrink_work);
mutex_lock(&dm_bufio_clients_lock);
diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c
index 5a18b80d3666..96751cd3d181 100644
--- a/drivers/md/dm-cache-metadata.c
+++ b/drivers/md/dm-cache-metadata.c
@@ -1828,7 +1828,7 @@ int dm_cache_metadata_abort(struct dm_cache_metadata *cmd)
* Replacement block manager (new_bm) is created and old_bm destroyed outside of
* cmd root_lock to avoid ABBA deadlock that would result (due to life-cycle of
* shrinker associated with the block manager's bufio client vs cmd root_lock).
- * - must take shrinker_rwsem without holding cmd->root_lock
+ * - must take shrinker_mutex without holding cmd->root_lock
*/
new_bm = dm_block_manager_create(cmd->bdev, DM_CACHE_METADATA_BLOCK_SIZE << SECTOR_SHIFT,
CACHE_MAX_CONCURRENT_LOCKS);
diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c
index 9d3cca8e3dc9..60a4dc01ea18 100644
--- a/drivers/md/dm-zoned-metadata.c
+++ b/drivers/md/dm-zoned-metadata.c
@@ -187,7 +187,7 @@ struct dmz_metadata {
struct rb_root mblk_rbtree;
struct list_head mblk_lru_list;
struct list_head mblk_dirty_list;
- struct shrinker mblk_shrinker;
+ struct shrinker *mblk_shrinker;
/* Zone allocation management */
struct mutex map_lock;
@@ -615,7 +615,7 @@ static unsigned long dmz_shrink_mblock_cache(struct dmz_metadata *zmd,
static unsigned long dmz_mblock_shrinker_count(struct shrinker *shrink,
struct shrink_control *sc)
{
- struct dmz_metadata *zmd = container_of(shrink, struct dmz_metadata, mblk_shrinker);
+ struct dmz_metadata *zmd = shrink->private_data;
return atomic_read(&zmd->nr_mblks);
}
@@ -626,7 +626,7 @@ static unsigned long dmz_mblock_shrinker_count(struct shrinker *shrink,
static unsigned long dmz_mblock_shrinker_scan(struct shrinker *shrink,
struct shrink_control *sc)
{
- struct dmz_metadata *zmd = container_of(shrink, struct dmz_metadata, mblk_shrinker);
+ struct dmz_metadata *zmd = shrink->private_data;
unsigned long count;
spin_lock(&zmd->mblk_lock);
@@ -2936,19 +2936,23 @@ int dmz_ctr_metadata(struct dmz_dev *dev, int num_dev,
*/
zmd->min_nr_mblks = 2 + zmd->nr_map_blocks + zmd->zone_nr_bitmap_blocks * 16;
zmd->max_nr_mblks = zmd->min_nr_mblks + 512;
- zmd->mblk_shrinker.count_objects = dmz_mblock_shrinker_count;
- zmd->mblk_shrinker.scan_objects = dmz_mblock_shrinker_scan;
- zmd->mblk_shrinker.seeks = DEFAULT_SEEKS;
/* Metadata cache shrinker */
- ret = register_shrinker(&zmd->mblk_shrinker, "dm-zoned-meta:(%u:%u)",
- MAJOR(dev->bdev->bd_dev),
- MINOR(dev->bdev->bd_dev));
- if (ret) {
- dmz_zmd_err(zmd, "Register metadata cache shrinker failed");
+ zmd->mblk_shrinker = shrinker_alloc(0, "dm-zoned-meta:(%u:%u)",
+ MAJOR(dev->bdev->bd_dev),
+ MINOR(dev->bdev->bd_dev));
+ if (!zmd->mblk_shrinker) {
+ ret = -ENOMEM;
+ dmz_zmd_err(zmd, "Allocate metadata cache shrinker failed");
goto err;
}
+ zmd->mblk_shrinker->count_objects = dmz_mblock_shrinker_count;
+ zmd->mblk_shrinker->scan_objects = dmz_mblock_shrinker_scan;
+ zmd->mblk_shrinker->private_data = zmd;
+
+ shrinker_register(zmd->mblk_shrinker);
+
dmz_zmd_info(zmd, "DM-Zoned metadata version %d", zmd->sb_version);
for (i = 0; i < zmd->nr_devs; i++)
dmz_print_dev(zmd, i);
@@ -2995,7 +2999,7 @@ err:
*/
void dmz_dtr_metadata(struct dmz_metadata *zmd)
{
- unregister_shrinker(&zmd->mblk_shrinker);
+ shrinker_free(zmd->mblk_shrinker);
dmz_cleanup_metadata(zmd);
kfree(zmd);
}
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index c84ccc97329b..dc031d42f53b 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -7378,7 +7378,7 @@ static void free_conf(struct r5conf *conf)
log_exit(conf);
- unregister_shrinker(&conf->shrinker);
+ shrinker_free(conf->shrinker);
free_thread_groups(conf);
shrink_stripes(conf);
raid5_free_percpu(conf);
@@ -7426,7 +7426,7 @@ static int raid5_alloc_percpu(struct r5conf *conf)
static unsigned long raid5_cache_scan(struct shrinker *shrink,
struct shrink_control *sc)
{
- struct r5conf *conf = container_of(shrink, struct r5conf, shrinker);
+ struct r5conf *conf = shrink->private_data;
unsigned long ret = SHRINK_STOP;
if (mutex_trylock(&conf->cache_size_mutex)) {
@@ -7447,7 +7447,7 @@ static unsigned long raid5_cache_scan(struct shrinker *shrink,
static unsigned long raid5_cache_count(struct shrinker *shrink,
struct shrink_control *sc)
{
- struct r5conf *conf = container_of(shrink, struct r5conf, shrinker);
+ struct r5conf *conf = shrink->private_data;
if (conf->max_nr_stripes < conf->min_nr_stripes)
/* unlikely, but not impossible */
@@ -7682,18 +7682,22 @@ static struct r5conf *setup_conf(struct mddev *mddev)
* it reduces the queue depth and so can hurt throughput.
* So set it rather large, scaled by number of devices.
*/
- conf->shrinker.seeks = DEFAULT_SEEKS * conf->raid_disks * 4;
- conf->shrinker.scan_objects = raid5_cache_scan;
- conf->shrinker.count_objects = raid5_cache_count;
- conf->shrinker.batch = 128;
- conf->shrinker.flags = 0;
- ret = register_shrinker(&conf->shrinker, "md-raid5:%s", mdname(mddev));
- if (ret) {
- pr_warn("md/raid:%s: couldn't register shrinker.\n",
+ conf->shrinker = shrinker_alloc(0, "md-raid5:%s", mdname(mddev));
+ if (!conf->shrinker) {
+ ret = -ENOMEM;
+ pr_warn("md/raid:%s: couldn't allocate shrinker.\n",
mdname(mddev));
goto abort;
}
+ conf->shrinker->seeks = DEFAULT_SEEKS * conf->raid_disks * 4;
+ conf->shrinker->scan_objects = raid5_cache_scan;
+ conf->shrinker->count_objects = raid5_cache_count;
+ conf->shrinker->batch = 128;
+ conf->shrinker->private_data = conf;
+
+ shrinker_register(conf->shrinker);
+
sprintf(pers_name, "raid%d", mddev->new_level);
rcu_assign_pointer(conf->thread,
md_register_thread(raid5d, mddev, pers_name));
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index 97a795979a35..22bea20eccbd 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -670,7 +670,7 @@ struct r5conf {
wait_queue_head_t wait_for_stripe;
wait_queue_head_t wait_for_overlap;
unsigned long cache_state;
- struct shrinker shrinker;
+ struct shrinker *shrinker;
int pool_size; /* number of disks in stripeheads in pool */
spinlock_t device_lock;
struct disk_info *disks;
diff --git a/drivers/misc/vmw_balloon.c b/drivers/misc/vmw_balloon.c
index 9ce9b9e0e9b6..c817d8c21641 100644
--- a/drivers/misc/vmw_balloon.c
+++ b/drivers/misc/vmw_balloon.c
@@ -380,16 +380,7 @@ struct vmballoon {
/**
* @shrinker: shrinker interface that is used to avoid over-inflation.
*/
- struct shrinker shrinker;
-
- /**
- * @shrinker_registered: whether the shrinker was registered.
- *
- * The shrinker interface does not handle gracefully the removal of
- * shrinker that was not registered before. This indication allows to
- * simplify the unregistration process.
- */
- bool shrinker_registered;
+ struct shrinker *shrinker;
};
static struct vmballoon balloon;
@@ -1568,29 +1559,27 @@ static unsigned long vmballoon_shrinker_count(struct shrinker *shrinker,
static void vmballoon_unregister_shrinker(struct vmballoon *b)
{
- if (b->shrinker_registered)
- unregister_shrinker(&b->shrinker);
- b->shrinker_registered = false;
+ shrinker_free(b->shrinker);
+ b->shrinker = NULL;
}
static int vmballoon_register_shrinker(struct vmballoon *b)
{
- int r;
-
/* Do nothing if the shrinker is not enabled */
if (!vmwballoon_shrinker_enable)
return 0;
- b->shrinker.scan_objects = vmballoon_shrinker_scan;
- b->shrinker.count_objects = vmballoon_shrinker_count;
- b->shrinker.seeks = DEFAULT_SEEKS;
+ b->shrinker = shrinker_alloc(0, "vmw-balloon");
+ if (!b->shrinker)
+ return -ENOMEM;
- r = register_shrinker(&b->shrinker, "vmw-balloon");
+ b->shrinker->scan_objects = vmballoon_shrinker_scan;
+ b->shrinker->count_objects = vmballoon_shrinker_count;
+ b->shrinker->private_data = b;
- if (r == 0)
- b->shrinker_registered = true;
+ shrinker_register(b->shrinker);
- return r;
+ return 0;
}
/*
@@ -1883,7 +1872,7 @@ static int __init vmballoon_init(void)
error = vmballoon_register_shrinker(&balloon);
if (error)
- goto fail;
+ return error;
/*
* Initialization of compaction must be done after the call to
@@ -1905,9 +1894,6 @@ static int __init vmballoon_init(void)
vmballoon_debugfs_init(&balloon);
return 0;
-fail:
- vmballoon_unregister_shrinker(&balloon);
- return error;
}
/*
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 2d5d252ef419..44dcb9e7b55e 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -111,7 +111,7 @@ struct virtio_balloon {
struct virtio_balloon_stat stats[VIRTIO_BALLOON_S_NR];
/* Shrinker to return free pages - VIRTIO_BALLOON_F_FREE_PAGE_HINT */
- struct shrinker shrinker;
+ struct shrinker *shrinker;
/* OOM notifier to deflate on OOM - VIRTIO_BALLOON_F_DEFLATE_ON_OOM */
struct notifier_block oom_nb;
@@ -820,8 +820,7 @@ static unsigned long shrink_free_pages(struct virtio_balloon *vb,
static unsigned long virtio_balloon_shrinker_scan(struct shrinker *shrinker,
struct shrink_control *sc)
{
- struct virtio_balloon *vb = container_of(shrinker,
- struct virtio_balloon, shrinker);
+ struct virtio_balloon *vb = shrinker->private_data;
return shrink_free_pages(vb, sc->nr_to_scan);
}
@@ -829,8 +828,7 @@ static unsigned long virtio_balloon_shrinker_scan(struct shrinker *shrinker,
static unsigned long virtio_balloon_shrinker_count(struct shrinker *shrinker,
struct shrink_control *sc)
{
- struct virtio_balloon *vb = container_of(shrinker,
- struct virtio_balloon, shrinker);
+ struct virtio_balloon *vb = shrinker->private_data;
return vb->num_free_page_blocks * VIRTIO_BALLOON_HINT_BLOCK_PAGES;
}
@@ -851,16 +849,22 @@ static int virtio_balloon_oom_notify(struct notifier_block *nb,
static void virtio_balloon_unregister_shrinker(struct virtio_balloon *vb)
{
- unregister_shrinker(&vb->shrinker);
+ shrinker_free(vb->shrinker);
}
static int virtio_balloon_register_shrinker(struct virtio_balloon *vb)
{
- vb->shrinker.scan_objects = virtio_balloon_shrinker_scan;
- vb->shrinker.count_objects = virtio_balloon_shrinker_count;
- vb->shrinker.seeks = DEFAULT_SEEKS;
+ vb->shrinker = shrinker_alloc(0, "virtio-balloon");
+ if (!vb->shrinker)
+ return -ENOMEM;
- return register_shrinker(&vb->shrinker, "virtio-balloon");
+ vb->shrinker->scan_objects = virtio_balloon_shrinker_scan;
+ vb->shrinker->count_objects = virtio_balloon_shrinker_count;
+ vb->shrinker->private_data = vb;
+
+ shrinker_register(vb->shrinker);
+
+ return 0;
}
static int virtballoon_probe(struct virtio_device *vdev)
diff --git a/drivers/xen/xenbus/xenbus_probe_backend.c b/drivers/xen/xenbus/xenbus_probe_backend.c
index da96c260e26b..5ebb7233076f 100644
--- a/drivers/xen/xenbus/xenbus_probe_backend.c
+++ b/drivers/xen/xenbus/xenbus_probe_backend.c
@@ -284,13 +284,9 @@ static unsigned long backend_shrink_memory_count(struct shrinker *shrinker,
return 0;
}
-static struct shrinker backend_memory_shrinker = {
- .count_objects = backend_shrink_memory_count,
- .seeks = DEFAULT_SEEKS,
-};
-
static int __init xenbus_probe_backend_init(void)
{
+ struct shrinker *backend_memory_shrinker;
static struct notifier_block xenstore_notifier = {
.notifier_call = backend_probe_and_watch
};
@@ -305,8 +301,15 @@ static int __init xenbus_probe_backend_init(void)
register_xenstore_notifier(&xenstore_notifier);
- if (register_shrinker(&backend_memory_shrinker, "xen-backend"))
- pr_warn("shrinker registration failed\n");
+ backend_memory_shrinker = shrinker_alloc(0, "xen-backend");
+ if (!backend_memory_shrinker) {
+ pr_warn("shrinker allocation failed\n");
+ return 0;
+ }
+
+ backend_memory_shrinker->count_objects = backend_shrink_memory_count;
+
+ shrinker_register(backend_memory_shrinker);
return 0;
}