summaryrefslogtreecommitdiff
path: root/drivers
diff options
context:
space:
mode:
Diffstat (limited to 'drivers')
-rw-r--r--drivers/base/cacheinfo.c50
-rw-r--r--drivers/base/cpu.c6
-rw-r--r--drivers/base/memory.c23
-rw-r--r--drivers/block/zram/zcomp.c5
-rw-r--r--drivers/block/zram/zcomp.h1
-rw-r--r--drivers/block/zram/zram_drv.c2
-rw-r--r--drivers/cpuidle/cpuidle.c2
-rw-r--r--drivers/dax/bus.c293
-rw-r--r--drivers/dax/super.c14
-rw-r--r--drivers/firmware/qemu_fw_cfg.c14
-rw-r--r--drivers/md/dm.c17
-rw-r--r--drivers/misc/sgi-gru/grufault.c2
-rw-r--r--drivers/nvdimm/pmem.c23
-rw-r--r--drivers/of/kexec.c2
-rw-r--r--drivers/s390/block/dcssblk.c11
-rw-r--r--drivers/s390/char/sclp_cmd.c44
16 files changed, 375 insertions, 134 deletions
diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c
index f1e79263fe61..23b8cba4a2a3 100644
--- a/drivers/base/cacheinfo.c
+++ b/drivers/base/cacheinfo.c
@@ -898,6 +898,37 @@ err:
return rc;
}
+static unsigned int cpu_map_shared_cache(bool online, unsigned int cpu,
+ cpumask_t **map)
+{
+ struct cacheinfo *llc, *sib_llc;
+ unsigned int sibling;
+
+ if (!last_level_cache_is_valid(cpu))
+ return 0;
+
+ llc = per_cpu_cacheinfo_idx(cpu, cache_leaves(cpu) - 1);
+
+ if (llc->type != CACHE_TYPE_DATA && llc->type != CACHE_TYPE_UNIFIED)
+ return 0;
+
+ if (online) {
+ *map = &llc->shared_cpu_map;
+ return cpumask_weight(*map);
+ }
+
+ /* shared_cpu_map of offlined CPU will be cleared, so use sibling map */
+ for_each_cpu(sibling, &llc->shared_cpu_map) {
+ if (sibling == cpu || !last_level_cache_is_valid(sibling))
+ continue;
+ sib_llc = per_cpu_cacheinfo_idx(sibling, cache_leaves(sibling) - 1);
+ *map = &sib_llc->shared_cpu_map;
+ return cpumask_weight(*map);
+ }
+
+ return 0;
+}
+
/*
* 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
@@ -929,28 +960,31 @@ static void update_per_cpu_data_slice_size_cpu(unsigned int cpu)
ci->per_cpu_data_slice_size = llc->size / nr_shared;
}
-static void update_per_cpu_data_slice_size(bool cpu_online, unsigned int cpu)
+static void update_per_cpu_data_slice_size(bool cpu_online, unsigned int cpu,
+ cpumask_t *cpu_map)
{
unsigned int icpu;
- for_each_online_cpu(icpu) {
+ for_each_cpu(icpu, cpu_map) {
if (!cpu_online && icpu == cpu)
continue;
update_per_cpu_data_slice_size_cpu(icpu);
+ setup_pcp_cacheinfo(icpu);
}
}
static int cacheinfo_cpu_online(unsigned int cpu)
{
int rc = detect_cache_attributes(cpu);
+ cpumask_t *cpu_map;
if (rc)
return rc;
rc = cache_add_dev(cpu);
if (rc)
goto err;
- update_per_cpu_data_slice_size(true, cpu);
- setup_pcp_cacheinfo();
+ if (cpu_map_shared_cache(true, cpu, &cpu_map))
+ update_per_cpu_data_slice_size(true, cpu, cpu_map);
return 0;
err:
free_cache_attributes(cpu);
@@ -959,12 +993,16 @@ err:
static int cacheinfo_cpu_pre_down(unsigned int cpu)
{
+ cpumask_t *cpu_map;
+ unsigned int nr_shared;
+
+ nr_shared = cpu_map_shared_cache(false, cpu, &cpu_map);
if (cpumask_test_and_clear_cpu(cpu, &cache_dev_map))
cpu_cache_sysfs_exit(cpu);
free_cache_attributes(cpu);
- update_per_cpu_data_slice_size(false, cpu);
- setup_pcp_cacheinfo();
+ if (nr_shared > 1)
+ update_per_cpu_data_slice_size(false, cpu, cpu_map);
return 0;
}
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 0b33e81f9c9b..f5a6bffce518 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -144,7 +144,7 @@ static DEVICE_ATTR(release, S_IWUSR, NULL, cpu_release_store);
#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */
#endif /* CONFIG_HOTPLUG_CPU */
-#ifdef CONFIG_KEXEC_CORE
+#ifdef CONFIG_CRASH_DUMP
#include <linux/kexec.h>
static ssize_t crash_notes_show(struct device *dev,
@@ -189,14 +189,14 @@ static const struct attribute_group crash_note_cpu_attr_group = {
#endif
static const struct attribute_group *common_cpu_attr_groups[] = {
-#ifdef CONFIG_KEXEC_CORE
+#ifdef CONFIG_CRASH_DUMP
&crash_note_cpu_attr_group,
#endif
NULL
};
static const struct attribute_group *hotplugable_cpu_attr_groups[] = {
-#ifdef CONFIG_KEXEC_CORE
+#ifdef CONFIG_CRASH_DUMP
&crash_note_cpu_attr_group,
#endif
NULL
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 14f964a7719b..c0436f46cfb7 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -188,6 +188,7 @@ static int memory_block_online(struct memory_block *mem)
unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr);
unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
unsigned long nr_vmemmap_pages = 0;
+ struct memory_notify arg;
struct zone *zone;
int ret;
@@ -207,9 +208,19 @@ static int memory_block_online(struct memory_block *mem)
if (mem->altmap)
nr_vmemmap_pages = mem->altmap->free;
+ arg.altmap_start_pfn = start_pfn;
+ arg.altmap_nr_pages = nr_vmemmap_pages;
+ arg.start_pfn = start_pfn + nr_vmemmap_pages;
+ arg.nr_pages = nr_pages - nr_vmemmap_pages;
mem_hotplug_begin();
+ ret = memory_notify(MEM_PREPARE_ONLINE, &arg);
+ ret = notifier_to_errno(ret);
+ if (ret)
+ goto out_notifier;
+
if (nr_vmemmap_pages) {
- ret = mhp_init_memmap_on_memory(start_pfn, nr_vmemmap_pages, zone);
+ ret = mhp_init_memmap_on_memory(start_pfn, nr_vmemmap_pages,
+ zone, mem->altmap->inaccessible);
if (ret)
goto out;
}
@@ -231,7 +242,11 @@ static int memory_block_online(struct memory_block *mem)
nr_vmemmap_pages);
mem->zone = zone;
+ mem_hotplug_done();
+ return ret;
out:
+ memory_notify(MEM_FINISH_OFFLINE, &arg);
+out_notifier:
mem_hotplug_done();
return ret;
}
@@ -244,6 +259,7 @@ static int memory_block_offline(struct memory_block *mem)
unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr);
unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
unsigned long nr_vmemmap_pages = 0;
+ struct memory_notify arg;
int ret;
if (!mem->zone)
@@ -275,6 +291,11 @@ static int memory_block_offline(struct memory_block *mem)
mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages);
mem->zone = NULL;
+ arg.altmap_start_pfn = start_pfn;
+ arg.altmap_nr_pages = nr_vmemmap_pages;
+ arg.start_pfn = start_pfn + nr_vmemmap_pages;
+ arg.nr_pages = nr_pages - nr_vmemmap_pages;
+ memory_notify(MEM_FINISH_OFFLINE, &arg);
out:
mem_hotplug_done();
return ret;
diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c
index 55af4efd7983..8237b08c49d8 100644
--- a/drivers/block/zram/zcomp.c
+++ b/drivers/block/zram/zcomp.c
@@ -11,6 +11,7 @@
#include <linux/sched.h>
#include <linux/cpu.h>
#include <linux/crypto.h>
+#include <linux/vmalloc.h>
#include "zcomp.h"
@@ -37,7 +38,7 @@ static void zcomp_strm_free(struct zcomp_strm *zstrm)
{
if (!IS_ERR_OR_NULL(zstrm->tfm))
crypto_free_comp(zstrm->tfm);
- free_pages((unsigned long)zstrm->buffer, 1);
+ vfree(zstrm->buffer);
zstrm->tfm = NULL;
zstrm->buffer = NULL;
}
@@ -53,7 +54,7 @@ static int zcomp_strm_init(struct zcomp_strm *zstrm, struct zcomp *comp)
* allocate 2 pages. 1 for compressed data, plus 1 extra for the
* case when compressed size is larger than the original one
*/
- zstrm->buffer = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 1);
+ zstrm->buffer = vzalloc(2 * PAGE_SIZE);
if (IS_ERR_OR_NULL(zstrm->tfm) || !zstrm->buffer) {
zcomp_strm_free(zstrm);
return -ENOMEM;
diff --git a/drivers/block/zram/zcomp.h b/drivers/block/zram/zcomp.h
index cdefdef93da8..e9fe63da0e9b 100644
--- a/drivers/block/zram/zcomp.h
+++ b/drivers/block/zram/zcomp.h
@@ -39,5 +39,4 @@ int zcomp_compress(struct zcomp_strm *zstrm,
int zcomp_decompress(struct zcomp_strm *zstrm,
const void *src, unsigned int src_len, void *dst);
-bool zcomp_set_max_streams(struct zcomp *comp, int num_strm);
#endif /* _ZCOMP_H_ */
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index da7a20fa6152..f0639df6cd18 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -1337,7 +1337,7 @@ static int zram_read_from_zspool(struct zram *zram, struct page *page,
src = zs_map_object(zram->mem_pool, handle, ZS_MM_RO);
if (size == PAGE_SIZE) {
dst = kmap_local_page(page);
- memcpy(dst, src, PAGE_SIZE);
+ copy_page(dst, src);
kunmap_local(dst);
ret = 0;
} else {
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 737a026ef58a..02e40fd7d948 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -237,7 +237,7 @@ noinstr int cpuidle_enter_state(struct cpuidle_device *dev,
}
if (target_state->flags & CPUIDLE_FLAG_TLB_FLUSHED)
- leave_mm(dev->cpu);
+ leave_mm();
/* Take note of the planned idle state. */
sched_idle_set_state(target_state);
diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
index 1ff1ab5fa105..27c86d0ca711 100644
--- a/drivers/dax/bus.c
+++ b/drivers/dax/bus.c
@@ -12,6 +12,18 @@
static DEFINE_MUTEX(dax_bus_lock);
+/*
+ * All changes to the dax region configuration occur with this lock held
+ * for write.
+ */
+DECLARE_RWSEM(dax_region_rwsem);
+
+/*
+ * All changes to the dax device configuration occur with this lock held
+ * for write.
+ */
+DECLARE_RWSEM(dax_dev_rwsem);
+
#define DAX_NAME_LEN 30
struct dax_id {
struct list_head list;
@@ -180,7 +192,7 @@ static u64 dev_dax_size(struct dev_dax *dev_dax)
u64 size = 0;
int i;
- device_lock_assert(&dev_dax->dev);
+ WARN_ON_ONCE(!rwsem_is_locked(&dax_dev_rwsem));
for (i = 0; i < dev_dax->nr_range; i++)
size += range_len(&dev_dax->ranges[i].range);
@@ -194,8 +206,15 @@ static int dax_bus_probe(struct device *dev)
struct dev_dax *dev_dax = to_dev_dax(dev);
struct dax_region *dax_region = dev_dax->region;
int rc;
+ u64 size;
+
+ rc = down_read_interruptible(&dax_dev_rwsem);
+ if (rc)
+ return rc;
+ size = dev_dax_size(dev_dax);
+ up_read(&dax_dev_rwsem);
- if (dev_dax_size(dev_dax) == 0 || dev_dax->id < 0)
+ if (size == 0 || dev_dax->id < 0)
return -ENXIO;
rc = dax_drv->probe(dev_dax);
@@ -250,7 +269,7 @@ static ssize_t id_show(struct device *dev,
{
struct dax_region *dax_region = dev_get_drvdata(dev);
- return sprintf(buf, "%d\n", dax_region->id);
+ return sysfs_emit(buf, "%d\n", dax_region->id);
}
static DEVICE_ATTR_RO(id);
@@ -259,8 +278,8 @@ static ssize_t region_size_show(struct device *dev,
{
struct dax_region *dax_region = dev_get_drvdata(dev);
- return sprintf(buf, "%llu\n", (unsigned long long)
- resource_size(&dax_region->res));
+ return sysfs_emit(buf, "%llu\n",
+ (unsigned long long)resource_size(&dax_region->res));
}
static struct device_attribute dev_attr_region_size = __ATTR(size, 0444,
region_size_show, NULL);
@@ -270,7 +289,7 @@ static ssize_t region_align_show(struct device *dev,
{
struct dax_region *dax_region = dev_get_drvdata(dev);
- return sprintf(buf, "%u\n", dax_region->align);
+ return sysfs_emit(buf, "%u\n", dax_region->align);
}
static struct device_attribute dev_attr_region_align =
__ATTR(align, 0400, region_align_show, NULL);
@@ -283,7 +302,7 @@ static unsigned long long dax_region_avail_size(struct dax_region *dax_region)
resource_size_t size = resource_size(&dax_region->res);
struct resource *res;
- device_lock_assert(dax_region->dev);
+ WARN_ON_ONCE(!rwsem_is_locked(&dax_region_rwsem));
for_each_dax_region_resource(dax_region, res)
size -= resource_size(res);
@@ -295,12 +314,15 @@ static ssize_t available_size_show(struct device *dev,
{
struct dax_region *dax_region = dev_get_drvdata(dev);
unsigned long long size;
+ int rc;
- device_lock(dev);
+ rc = down_read_interruptible(&dax_region_rwsem);
+ if (rc)
+ return rc;
size = dax_region_avail_size(dax_region);
- device_unlock(dev);
+ up_read(&dax_region_rwsem);
- return sprintf(buf, "%llu\n", size);
+ return sysfs_emit(buf, "%llu\n", size);
}
static DEVICE_ATTR_RO(available_size);
@@ -314,10 +336,12 @@ static ssize_t seed_show(struct device *dev,
if (is_static(dax_region))
return -EINVAL;
- device_lock(dev);
+ rc = down_read_interruptible(&dax_region_rwsem);
+ if (rc)
+ return rc;
seed = dax_region->seed;
- rc = sprintf(buf, "%s\n", seed ? dev_name(seed) : "");
- device_unlock(dev);
+ rc = sysfs_emit(buf, "%s\n", seed ? dev_name(seed) : "");
+ up_read(&dax_region_rwsem);
return rc;
}
@@ -333,14 +357,18 @@ static ssize_t create_show(struct device *dev,
if (is_static(dax_region))
return -EINVAL;
- device_lock(dev);
+ rc = down_read_interruptible(&dax_region_rwsem);
+ if (rc)
+ return rc;
youngest = dax_region->youngest;
- rc = sprintf(buf, "%s\n", youngest ? dev_name(youngest) : "");
- device_unlock(dev);
+ rc = sysfs_emit(buf, "%s\n", youngest ? dev_name(youngest) : "");
+ up_read(&dax_region_rwsem);
return rc;
}
+static struct dev_dax *__devm_create_dev_dax(struct dev_dax_data *data);
+
static ssize_t create_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t len)
{
@@ -358,7 +386,9 @@ static ssize_t create_store(struct device *dev, struct device_attribute *attr,
if (val != 1)
return -EINVAL;
- device_lock(dev);
+ rc = down_write_killable(&dax_region_rwsem);
+ if (rc)
+ return rc;
avail = dax_region_avail_size(dax_region);
if (avail == 0)
rc = -ENOSPC;
@@ -369,7 +399,7 @@ static ssize_t create_store(struct device *dev, struct device_attribute *attr,
.id = -1,
.memmap_on_memory = false,
};
- struct dev_dax *dev_dax = devm_create_dev_dax(&data);
+ struct dev_dax *dev_dax = __devm_create_dev_dax(&data);
if (IS_ERR(dev_dax))
rc = PTR_ERR(dev_dax);
@@ -387,7 +417,7 @@ static ssize_t create_store(struct device *dev, struct device_attribute *attr,
rc = len;
}
}
- device_unlock(dev);
+ up_write(&dax_region_rwsem);
return rc;
}
@@ -417,7 +447,7 @@ static void trim_dev_dax_range(struct dev_dax *dev_dax)
struct range *range = &dev_dax->ranges[i].range;
struct dax_region *dax_region = dev_dax->region;
- device_lock_assert(dax_region->dev);
+ WARN_ON_ONCE(!rwsem_is_locked(&dax_region_rwsem));
dev_dbg(&dev_dax->dev, "delete range[%d]: %#llx:%#llx\n", i,
(unsigned long long)range->start,
(unsigned long long)range->end);
@@ -435,7 +465,7 @@ static void free_dev_dax_ranges(struct dev_dax *dev_dax)
trim_dev_dax_range(dev_dax);
}
-static void unregister_dev_dax(void *dev)
+static void __unregister_dev_dax(void *dev)
{
struct dev_dax *dev_dax = to_dev_dax(dev);
@@ -447,6 +477,17 @@ static void unregister_dev_dax(void *dev)
put_device(dev);
}
+static void unregister_dev_dax(void *dev)
+{
+ if (rwsem_is_locked(&dax_region_rwsem))
+ return __unregister_dev_dax(dev);
+
+ if (WARN_ON_ONCE(down_write_killable(&dax_region_rwsem) != 0))
+ return;
+ __unregister_dev_dax(dev);
+ up_write(&dax_region_rwsem);
+}
+
static void dax_region_free(struct kref *kref)
{
struct dax_region *dax_region;
@@ -463,11 +504,10 @@ static void dax_region_put(struct dax_region *dax_region)
/* a return value >= 0 indicates this invocation invalidated the id */
static int __free_dev_dax_id(struct dev_dax *dev_dax)
{
- struct device *dev = &dev_dax->dev;
struct dax_region *dax_region;
int rc = dev_dax->id;
- device_lock_assert(dev);
+ WARN_ON_ONCE(!rwsem_is_locked(&dax_dev_rwsem));
if (!dev_dax->dyn_id || dev_dax->id < 0)
return -1;
@@ -480,12 +520,13 @@ static int __free_dev_dax_id(struct dev_dax *dev_dax)
static int free_dev_dax_id(struct dev_dax *dev_dax)
{
- struct device *dev = &dev_dax->dev;
int rc;
- device_lock(dev);
+ rc = down_write_killable(&dax_dev_rwsem);
+ if (rc)
+ return rc;
rc = __free_dev_dax_id(dev_dax);
- device_unlock(dev);
+ up_write(&dax_dev_rwsem);
return rc;
}
@@ -519,8 +560,14 @@ static ssize_t delete_store(struct device *dev, struct device_attribute *attr,
if (!victim)
return -ENXIO;
- device_lock(dev);
- device_lock(victim);
+ rc = down_write_killable(&dax_region_rwsem);
+ if (rc)
+ return rc;
+ rc = down_write_killable(&dax_dev_rwsem);
+ if (rc) {
+ up_write(&dax_region_rwsem);
+ return rc;
+ }
dev_dax = to_dev_dax(victim);
if (victim->driver || dev_dax_size(dev_dax))
rc = -EBUSY;
@@ -541,12 +588,12 @@ static ssize_t delete_store(struct device *dev, struct device_attribute *attr,
} else
rc = -EBUSY;
}
- device_unlock(victim);
+ up_write(&dax_dev_rwsem);
/* won the race to invalidate the device, clean it up */
if (do_del)
devm_release_action(dev, unregister_dev_dax, victim);
- device_unlock(dev);
+ up_write(&dax_region_rwsem);
put_device(victim);
return rc;
@@ -658,16 +705,15 @@ static void dax_mapping_release(struct device *dev)
put_device(parent);
}
-static void unregister_dax_mapping(void *data)
+static void __unregister_dax_mapping(void *data)
{
struct device *dev = data;
struct dax_mapping *mapping = to_dax_mapping(dev);
struct dev_dax *dev_dax = to_dev_dax(dev->parent);
- struct dax_region *dax_region = dev_dax->region;
dev_dbg(dev, "%s\n", __func__);
- device_lock_assert(dax_region->dev);
+ WARN_ON_ONCE(!rwsem_is_locked(&dax_region_rwsem));
dev_dax->ranges[mapping->range_id].mapping = NULL;
mapping->range_id = -1;
@@ -675,28 +721,37 @@ static void unregister_dax_mapping(void *data)
device_unregister(dev);
}
+static void unregister_dax_mapping(void *data)
+{
+ if (rwsem_is_locked(&dax_region_rwsem))
+ return __unregister_dax_mapping(data);
+
+ if (WARN_ON_ONCE(down_write_killable(&dax_region_rwsem) != 0))
+ return;
+ __unregister_dax_mapping(data);
+ up_write(&dax_region_rwsem);
+}
+
static struct dev_dax_range *get_dax_range(struct device *dev)
{
struct dax_mapping *mapping = to_dax_mapping(dev);
struct dev_dax *dev_dax = to_dev_dax(dev->parent);
- struct dax_region *dax_region = dev_dax->region;
+ int rc;
- device_lock(dax_region->dev);
+ rc = down_write_killable(&dax_region_rwsem);
+ if (rc)
+ return NULL;
if (mapping->range_id < 0) {
- device_unlock(dax_region->dev);
+ up_write(&dax_region_rwsem);
return NULL;
}
return &dev_dax->ranges[mapping->range_id];
}
-static void put_dax_range(struct dev_dax_range *dax_range)
+static void put_dax_range(void)
{
- struct dax_mapping *mapping = dax_range->mapping;
- struct dev_dax *dev_dax = to_dev_dax(mapping->dev.parent);
- struct dax_region *dax_region = dev_dax->region;
-
- device_unlock(dax_region->dev);
+ up_write(&dax_region_rwsem);
}
static ssize_t start_show(struct device *dev,
@@ -708,8 +763,8 @@ static ssize_t start_show(struct device *dev,
dax_range = get_dax_range(dev);
if (!dax_range)
return -ENXIO;
- rc = sprintf(buf, "%#llx\n", dax_range->range.start);
- put_dax_range(dax_range);
+ rc = sysfs_emit(buf, "%#llx\n", dax_range->range.start);
+ put_dax_range();
return rc;
}
@@ -724,8 +779,8 @@ static ssize_t end_show(struct device *dev,
dax_range = get_dax_range(dev);
if (!dax_range)
return -ENXIO;
- rc = sprintf(buf, "%#llx\n", dax_range->range.end);
- put_dax_range(dax_range);
+ rc = sysfs_emit(buf, "%#llx\n", dax_range->range.end);
+ put_dax_range();
return rc;
}
@@ -740,8 +795,8 @@ static ssize_t pgoff_show(struct device *dev,
dax_range = get_dax_range(dev);
if (!dax_range)
return -ENXIO;
- rc = sprintf(buf, "%#lx\n", dax_range->pgoff);
- put_dax_range(dax_range);
+ rc = sysfs_emit(buf, "%#lx\n", dax_range->pgoff);
+ put_dax_range();
return rc;
}
@@ -775,7 +830,7 @@ static int devm_register_dax_mapping(struct dev_dax *dev_dax, int range_id)
struct device *dev;
int rc;
- device_lock_assert(dax_region->dev);
+ WARN_ON_ONCE(!rwsem_is_locked(&dax_region_rwsem));
if (dev_WARN_ONCE(&dev_dax->dev, !dax_region->dev->driver,
"region disabled\n"))
@@ -821,7 +876,7 @@ static int alloc_dev_dax_range(struct dev_dax *dev_dax, u64 start,
struct resource *alloc;
int i, rc;
- device_lock_assert(dax_region->dev);
+ WARN_ON_ONCE(!rwsem_is_locked(&dax_region_rwsem));
/* handle the seed alloc special case */
if (!size) {
@@ -875,13 +930,12 @@ static int adjust_dev_dax_range(struct dev_dax *dev_dax, struct resource *res, r
{
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;
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);
+ WARN_ON_ONCE(!rwsem_is_locked(&dax_region_rwsem));
if (dev_WARN_ONCE(dev, !size, "deletion is handled by dev_dax_shrink\n"))
return -EINVAL;
@@ -907,12 +961,15 @@ static ssize_t size_show(struct device *dev,
{
struct dev_dax *dev_dax = to_dev_dax(dev);
unsigned long long size;
+ int rc;
- device_lock(dev);
+ rc = down_write_killable(&dax_dev_rwsem);
+ if (rc)
+ return rc;
size = dev_dax_size(dev_dax);
- device_unlock(dev);
+ up_write(&dax_dev_rwsem);
- return sprintf(buf, "%llu\n", size);
+ return sysfs_emit(buf, "%llu\n", size);
}
static bool alloc_is_aligned(struct dev_dax *dev_dax, resource_size_t size)
@@ -1080,17 +1137,27 @@ static ssize_t size_store(struct device *dev, struct device_attribute *attr,
return -EINVAL;
}
- device_lock(dax_region->dev);
+ rc = down_write_killable(&dax_region_rwsem);
+ if (rc)
+ return rc;
if (!dax_region->dev->driver) {
- device_unlock(dax_region->dev);
- return -ENXIO;
+ rc = -ENXIO;
+ goto err_region;
}
- device_lock(dev);
+ rc = down_write_killable(&dax_dev_rwsem);
+ if (rc)
+ goto err_dev;
+
rc = dev_dax_resize(dax_region, dev_dax, val);
- device_unlock(dev);
- device_unlock(dax_region->dev);
- return rc == 0 ? len : rc;
+err_dev:
+ up_write(&dax_dev_rwsem);
+err_region:
+ up_write(&dax_region_rwsem);
+
+ if (rc == 0)
+ return len;
+ return rc;
}
static DEVICE_ATTR_RW(size);
@@ -1138,18 +1205,24 @@ static ssize_t mapping_store(struct device *dev, struct device_attribute *attr,
return rc;
rc = -ENXIO;
- device_lock(dax_region->dev);
+ rc = down_write_killable(&dax_region_rwsem);
+ if (rc)
+ return rc;
if (!dax_region->dev->driver) {
- device_unlock(dax_region->dev);
+ up_write(&dax_region_rwsem);
+ return rc;
+ }
+ rc = down_write_killable(&dax_dev_rwsem);
+ if (rc) {
+ up_write(&dax_region_rwsem);
return rc;
}
- device_lock(dev);
to_alloc = range_len(&r);
if (alloc_is_aligned(dev_dax, to_alloc))
rc = alloc_dev_dax_range(dev_dax, r.start, to_alloc);
- device_unlock(dev);
- device_unlock(dax_region->dev);
+ up_write(&dax_dev_rwsem);
+ up_write(&dax_region_rwsem);
return rc == 0 ? len : rc;
}
@@ -1160,7 +1233,7 @@ static ssize_t align_show(struct device *dev,
{
struct dev_dax *dev_dax = to_dev_dax(dev);
- return sprintf(buf, "%d\n", dev_dax->align);
+ return sysfs_emit(buf, "%d\n", dev_dax->align);
}
static ssize_t dev_dax_validate_align(struct dev_dax *dev_dax)
@@ -1196,13 +1269,19 @@ static ssize_t align_store(struct device *dev, struct device_attribute *attr,
if (!dax_align_valid(val))
return -EINVAL;
- device_lock(dax_region->dev);
+ rc = down_write_killable(&dax_region_rwsem);
+ if (rc)
+ return rc;
if (!dax_region->dev->driver) {
- device_unlock(dax_region->dev);
+ up_write(&dax_region_rwsem);
return -ENXIO;
}
- device_lock(dev);
+ rc = down_write_killable(&dax_dev_rwsem);
+ if (rc) {
+ up_write(&dax_region_rwsem);
+ return rc;
+ }
if (dev->driver) {
rc = -EBUSY;
goto out_unlock;
@@ -1214,8 +1293,8 @@ static ssize_t align_store(struct device *dev, struct device_attribute *attr,
if (rc)
dev_dax->align = align_save;
out_unlock:
- device_unlock(dev);
- device_unlock(dax_region->dev);
+ up_write(&dax_dev_rwsem);
+ up_write(&dax_region_rwsem);
return rc == 0 ? len : rc;
}
static DEVICE_ATTR_RW(align);
@@ -1232,7 +1311,7 @@ static ssize_t target_node_show(struct device *dev,
{
struct dev_dax *dev_dax = to_dev_dax(dev);
- return sprintf(buf, "%d\n", dev_dax_target_node(dev_dax));
+ return sysfs_emit(buf, "%d\n", dev_dax_target_node(dev_dax));
}
static DEVICE_ATTR_RO(target_node);
@@ -1248,7 +1327,7 @@ static ssize_t resource_show(struct device *dev,
else
start = dev_dax->ranges[0].range.start;
- return sprintf(buf, "%#llx\n", start);
+ return sysfs_emit(buf, "%#llx\n", start);
}
static DEVICE_ATTR(resource, 0400, resource_show, NULL);
@@ -1259,17 +1338,59 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
* We only ever expect to handle device-dax instances, i.e. the
* @type argument to MODULE_ALIAS_DAX_DEVICE() is always zero
*/
- return sprintf(buf, DAX_DEVICE_MODALIAS_FMT "\n", 0);
+ return sysfs_emit(buf, DAX_DEVICE_MODALIAS_FMT "\n", 0);
}
static DEVICE_ATTR_RO(modalias);
static ssize_t numa_node_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
- return sprintf(buf, "%d\n", dev_to_node(dev));
+ return sysfs_emit(buf, "%d\n", dev_to_node(dev));
}
static DEVICE_ATTR_RO(numa_node);
+static ssize_t memmap_on_memory_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct dev_dax *dev_dax = to_dev_dax(dev);
+
+ return sysfs_emit(buf, "%d\n", dev_dax->memmap_on_memory);
+}
+
+static ssize_t memmap_on_memory_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t len)
+{
+ struct dev_dax *dev_dax = to_dev_dax(dev);
+ bool val;
+ int rc;
+
+ rc = kstrtobool(buf, &val);
+ if (rc)
+ return rc;
+
+ if (val == true && !mhp_supports_memmap_on_memory()) {
+ dev_dbg(dev, "memmap_on_memory is not available\n");
+ return -EOPNOTSUPP;
+ }
+
+ rc = down_write_killable(&dax_dev_rwsem);
+ if (rc)
+ return rc;
+
+ if (dev_dax->memmap_on_memory != val && dev->driver &&
+ to_dax_drv(dev->driver)->type == DAXDRV_KMEM_TYPE) {
+ up_write(&dax_dev_rwsem);
+ return -EBUSY;
+ }
+
+ dev_dax->memmap_on_memory = val;
+ up_write(&dax_dev_rwsem);
+
+ return len;
+}
+static DEVICE_ATTR_RW(memmap_on_memory);
+
static umode_t dev_dax_visible(struct kobject *kobj, struct attribute *a, int n)
{
struct device *dev = container_of(kobj, struct device, kobj);
@@ -1296,6 +1417,7 @@ static struct attribute *dev_dax_attributes[] = {
&dev_attr_align.attr,
&dev_attr_resource.attr,
&dev_attr_numa_node.attr,
+ &dev_attr_memmap_on_memory.attr,
NULL,
};
@@ -1325,7 +1447,7 @@ static const struct device_type dev_dax_type = {
.groups = dax_attribute_groups,
};
-struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data)
+static struct dev_dax *__devm_create_dev_dax(struct dev_dax_data *data)
{
struct dax_region *dax_region = data->dax_region;
struct device *parent = dax_region->dev;
@@ -1440,6 +1562,21 @@ err_id:
return ERR_PTR(rc);
}
+
+struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data)
+{
+ struct dev_dax *dev_dax;
+ int rc;
+
+ rc = down_write_killable(&dax_region_rwsem);
+ if (rc)
+ return ERR_PTR(rc);
+
+ dev_dax = __devm_create_dev_dax(data);
+ up_write(&dax_region_rwsem);
+
+ return dev_dax;
+}
EXPORT_SYMBOL_GPL(devm_create_dev_dax);
int __dax_driver_register(struct dax_device_driver *dax_drv,
diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index a0244f6bb44b..aca71d7fccc1 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -13,6 +13,7 @@
#include <linux/uio.h>
#include <linux/dax.h>
#include <linux/fs.h>
+#include <linux/cacheinfo.h>
#include "dax-private.h"
/**
@@ -319,6 +320,11 @@ EXPORT_SYMBOL_GPL(dax_alive);
* that any fault handlers or operations that might have seen
* dax_alive(), have completed. Any operations that start after
* synchronize_srcu() has run will abort upon seeing !dax_alive().
+ *
+ * Note, because alloc_dax() returns an ERR_PTR() on error, callers
+ * typically store its result into a local variable in order to check
+ * the result. Therefore, care must be taken to populate the struct
+ * device dax_dev field make sure the dax_dev is not leaked.
*/
void kill_dax(struct dax_device *dax_dev)
{
@@ -446,6 +452,14 @@ struct dax_device *alloc_dax(void *private, const struct dax_operations *ops)
dev_t devt;
int minor;
+ /*
+ * Unavailable on architectures with virtually aliased data caches,
+ * except for device-dax (NULL operations pointer), which does
+ * not use aliased mappings from the kernel.
+ */
+ if (ops && cpu_dcache_is_aliasing())
+ return ERR_PTR(-EOPNOTSUPP);
+
if (WARN_ON_ONCE(ops && !ops->zero_page_range))
return ERR_PTR(-EINVAL);
diff --git a/drivers/firmware/qemu_fw_cfg.c b/drivers/firmware/qemu_fw_cfg.c
index 03da9a4354f8..5f43dfa22f79 100644
--- a/drivers/firmware/qemu_fw_cfg.c
+++ b/drivers/firmware/qemu_fw_cfg.c
@@ -37,7 +37,7 @@
#include <uapi/linux/qemu_fw_cfg.h>
#include <linux/delay.h>
#include <linux/crash_dump.h>
-#include <linux/crash_core.h>
+#include <linux/vmcore_info.h>
MODULE_AUTHOR("Gabriel L. Somlo <somlo@cmu.edu>");
MODULE_DESCRIPTION("QEMU fw_cfg sysfs support");
@@ -67,7 +67,7 @@ static void fw_cfg_sel_endianness(u16 key)
iowrite16(key, fw_cfg_reg_ctrl);
}
-#ifdef CONFIG_CRASH_CORE
+#ifdef CONFIG_VMCORE_INFO
static inline bool fw_cfg_dma_enabled(void)
{
return (fw_cfg_rev & FW_CFG_VERSION_DMA) && fw_cfg_reg_dma;
@@ -156,7 +156,7 @@ static ssize_t fw_cfg_read_blob(u16 key,
return count;
}
-#ifdef CONFIG_CRASH_CORE
+#ifdef CONFIG_VMCORE_INFO
/* write chunk of given fw_cfg blob (caller responsible for sanity-check) */
static ssize_t fw_cfg_write_blob(u16 key,
void *buf, loff_t pos, size_t count)
@@ -195,7 +195,7 @@ end:
return ret;
}
-#endif /* CONFIG_CRASH_CORE */
+#endif /* CONFIG_VMCORE_INFO */
/* clean up fw_cfg device i/o */
static void fw_cfg_io_cleanup(void)
@@ -319,7 +319,7 @@ struct fw_cfg_sysfs_entry {
struct list_head list;
};
-#ifdef CONFIG_CRASH_CORE
+#ifdef CONFIG_VMCORE_INFO
static ssize_t fw_cfg_write_vmcoreinfo(const struct fw_cfg_file *f)
{
static struct fw_cfg_vmcoreinfo *data;
@@ -343,7 +343,7 @@ static ssize_t fw_cfg_write_vmcoreinfo(const struct fw_cfg_file *f)
kfree(data);
return ret;
}
-#endif /* CONFIG_CRASH_CORE */
+#endif /* CONFIG_VMCORE_INFO */
/* get fw_cfg_sysfs_entry from kobject member */
static inline struct fw_cfg_sysfs_entry *to_entry(struct kobject *kobj)
@@ -583,7 +583,7 @@ static int fw_cfg_register_file(const struct fw_cfg_file *f)
int err;
struct fw_cfg_sysfs_entry *entry;
-#ifdef CONFIG_CRASH_CORE
+#ifdef CONFIG_VMCORE_INFO
if (fw_cfg_dma_enabled() &&
strcmp(f->name, FW_CFG_VMCOREINFO_FILENAME) == 0 &&
!is_kdump_kernel()) {
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 06263b0a7b58..56aa2a8b9d71 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -2057,6 +2057,7 @@ static void cleanup_mapped_device(struct mapped_device *md)
static struct mapped_device *alloc_dev(int minor)
{
int r, numa_node_id = dm_get_numa_node();
+ struct dax_device *dax_dev;
struct mapped_device *md;
void *old_md;
@@ -2125,15 +2126,15 @@ static struct mapped_device *alloc_dev(int minor)
md->disk->private_data = md;
sprintf(md->disk->disk_name, "dm-%d", minor);
- if (IS_ENABLED(CONFIG_FS_DAX)) {
- md->dax_dev = alloc_dax(md, &dm_dax_ops);
- if (IS_ERR(md->dax_dev)) {
- md->dax_dev = NULL;
+ dax_dev = alloc_dax(md, &dm_dax_ops);
+ if (IS_ERR(dax_dev)) {
+ if (PTR_ERR(dax_dev) != -EOPNOTSUPP)
goto bad;
- }
- set_dax_nocache(md->dax_dev);
- set_dax_nomc(md->dax_dev);
- if (dax_add_host(md->dax_dev, md->disk))
+ } else {
+ set_dax_nocache(dax_dev);
+ set_dax_nomc(dax_dev);
+ md->dax_dev = dax_dev;
+ if (dax_add_host(dax_dev, md->disk))
goto bad;
}
diff --git a/drivers/misc/sgi-gru/grufault.c b/drivers/misc/sgi-gru/grufault.c
index 629edb6486de..3557d78ee47a 100644
--- a/drivers/misc/sgi-gru/grufault.c
+++ b/drivers/misc/sgi-gru/grufault.c
@@ -227,7 +227,7 @@ static int atomic_pte_lookup(struct vm_area_struct *vma, unsigned long vaddr,
if (unlikely(pmd_none(*pmdp)))
goto err;
#ifdef CONFIG_X86_64
- if (unlikely(pmd_large(*pmdp)))
+ if (unlikely(pmd_leaf(*pmdp)))
pte = ptep_get((pte_t *)pmdp);
else
#endif
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 8dcc10b6db5b..598fe2e89bda 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -562,18 +562,19 @@ static int pmem_attach_disk(struct device *dev,
dax_dev = alloc_dax(pmem, &pmem_dax_ops);
if (IS_ERR(dax_dev)) {
rc = PTR_ERR(dax_dev);
- goto out;
+ if (rc != -EOPNOTSUPP)
+ goto out;
+ } else {
+ set_dax_nocache(dax_dev);
+ set_dax_nomc(dax_dev);
+ if (is_nvdimm_sync(nd_region))
+ set_dax_synchronous(dax_dev);
+ pmem->dax_dev = dax_dev;
+ rc = dax_add_host(dax_dev, disk);
+ if (rc)
+ goto out_cleanup_dax;
+ dax_write_cache(dax_dev, nvdimm_has_cache(nd_region));
}
- set_dax_nocache(dax_dev);
- set_dax_nomc(dax_dev);
- if (is_nvdimm_sync(nd_region))
- set_dax_synchronous(dax_dev);
- rc = dax_add_host(dax_dev, disk);
- if (rc)
- goto out_cleanup_dax;
- dax_write_cache(dax_dev, nvdimm_has_cache(nd_region));
- pmem->dax_dev = dax_dev;
-
rc = device_add_disk(dev, disk, pmem_attribute_groups);
if (rc)
goto out_remove_host;
diff --git a/drivers/of/kexec.c b/drivers/of/kexec.c
index 68278340cecf..9ccde2fd77cb 100644
--- a/drivers/of/kexec.c
+++ b/drivers/of/kexec.c
@@ -395,6 +395,7 @@ void *of_kexec_alloc_and_setup_fdt(const struct kimage *image,
if (ret)
goto out;
+#ifdef CONFIG_CRASH_DUMP
/* add linux,usable-memory-range */
ret = fdt_appendprop_addrrange(fdt, 0, chosen_node,
"linux,usable-memory-range", crashk_res.start,
@@ -410,6 +411,7 @@ void *of_kexec_alloc_and_setup_fdt(const struct kimage *image,
if (ret)
goto out;
}
+#endif
}
/* add bootargs */
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index 9c8f529b827c..ba66aa6a83c6 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -552,6 +552,7 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char
int rc, i, j, num_of_segments;
struct dcssblk_dev_info *dev_info;
struct segment_info *seg_info, *temp;
+ struct dax_device *dax_dev;
char *local_buf;
unsigned long seg_byte_size;
@@ -679,13 +680,13 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char
if (rc)
goto put_dev;
- dev_info->dax_dev = alloc_dax(dev_info, &dcssblk_dax_ops);
- if (IS_ERR(dev_info->dax_dev)) {
- rc = PTR_ERR(dev_info->dax_dev);
- dev_info->dax_dev = NULL;
+ dax_dev = alloc_dax(dev_info, &dcssblk_dax_ops);
+ if (IS_ERR(dax_dev)) {
+ rc = PTR_ERR(dax_dev);
goto put_dev;
}
- set_dax_synchronous(dev_info->dax_dev);
+ set_dax_synchronous(dax_dev);
+ dev_info->dax_dev = dax_dev;
rc = dax_add_host(dev_info->dax_dev, dev_info->gd);
if (rc)
goto out_dax;
diff --git a/drivers/s390/char/sclp_cmd.c b/drivers/s390/char/sclp_cmd.c
index 11c428f4c7cf..7815e9bea69a 100644
--- a/drivers/s390/char/sclp_cmd.c
+++ b/drivers/s390/char/sclp_cmd.c
@@ -18,6 +18,7 @@
#include <linux/mm.h>
#include <linux/mmzone.h>
#include <linux/memory.h>
+#include <linux/memory_hotplug.h>
#include <linux/module.h>
#include <asm/ctlreg.h>
#include <asm/chpid.h>
@@ -26,6 +27,7 @@
#include <asm/sclp.h>
#include <asm/numa.h>
#include <asm/facility.h>
+#include <asm/page-states.h>
#include "sclp.h"
@@ -340,16 +342,38 @@ static int sclp_mem_notifier(struct notifier_block *nb,
if (contains_standby_increment(start, start + size))
rc = -EPERM;
break;
- case MEM_ONLINE:
- case MEM_CANCEL_OFFLINE:
- break;
- case MEM_GOING_ONLINE:
+ case MEM_PREPARE_ONLINE:
+ /*
+ * Access the altmap_start_pfn and altmap_nr_pages fields
+ * within the struct memory_notify specifically when dealing
+ * with only MEM_PREPARE_ONLINE/MEM_FINISH_OFFLINE notifiers.
+ *
+ * When altmap is in use, take the specified memory range
+ * online, which includes the altmap.
+ */
+ if (arg->altmap_nr_pages) {
+ start = PFN_PHYS(arg->altmap_start_pfn);
+ size += PFN_PHYS(arg->altmap_nr_pages);
+ }
rc = sclp_mem_change_state(start, size, 1);
+ if (rc || !arg->altmap_nr_pages)
+ break;
+ /*
+ * Set CMMA state to nodat here, since the struct page memory
+ * at the beginning of the memory block will not go through the
+ * buddy allocator later.
+ */
+ __arch_set_page_nodat((void *)__va(start), arg->altmap_nr_pages);
break;
- case MEM_CANCEL_ONLINE:
- sclp_mem_change_state(start, size, 0);
- break;
- case MEM_OFFLINE:
+ case MEM_FINISH_OFFLINE:
+ /*
+ * When altmap is in use, take the specified memory range
+ * offline, which includes the altmap.
+ */
+ if (arg->altmap_nr_pages) {
+ start = PFN_PHYS(arg->altmap_start_pfn);
+ size += PFN_PHYS(arg->altmap_nr_pages);
+ }
sclp_mem_change_state(start, size, 0);
break;
default:
@@ -400,7 +424,9 @@ static void __init add_memory_merged(u16 rn)
if (!size)
goto skip_add;
for (addr = start; addr < start + size; addr += block_size)
- add_memory(0, addr, block_size, MHP_NONE);
+ add_memory(0, addr, block_size,
+ MACHINE_HAS_EDAT1 ?
+ MHP_MEMMAP_ON_MEMORY | MHP_OFFLINE_INACCESSIBLE : MHP_NONE);
skip_add:
first_rn = rn;
num = 1;