select ARCH_HAS_FORTIFY_SOURCE
select ARCH_HAS_GCOV_PROFILE_ALL
select ARCH_HAS_KCOV if X86_64
- select ARCH_HAS_MMIO_FLUSH
select ARCH_HAS_PMEM_API if X86_64
+ # Causing hangs/crashes, see the commit that added this change for details.
+ select ARCH_HAS_REFCOUNT if BROKEN
select ARCH_HAS_UACCESS_FLUSHCACHE if X86_64
select ARCH_HAS_SET_MEMORY
select ARCH_HAS_SG_CHAIN
select ARCH_USE_QUEUED_RWLOCKS
select ARCH_USE_QUEUED_SPINLOCKS
select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
- select ARCH_WANT_FRAME_POINTERS
select ARCH_WANTS_DYNAMIC_TASK_STRUCT
select ARCH_WANTS_THP_SWAP if X86_64
select BUILDTIME_EXTABLE_SORT
select HAVE_MEMBLOCK
select HAVE_MEMBLOCK_NODE_MAP
select HAVE_MIXED_BREAKPOINTS_REGS
+ select HAVE_MOD_ARCH_SPECIFIC
select HAVE_NMI
select HAVE_OPROFILE
select HAVE_OPTPROBES
select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI
select HAVE_PERF_REGS
select HAVE_PERF_USER_STACK_DUMP
+ select HAVE_RCU_TABLE_FREE
select HAVE_REGS_AND_STACK_ACCESS_API
- select HAVE_RELIABLE_STACKTRACE if X86_64 && FRAME_POINTER && STACK_VALIDATION
+ select HAVE_RELIABLE_STACKTRACE if X86_64 && FRAME_POINTER_UNWINDER && STACK_VALIDATION
select HAVE_STACK_VALIDATION if X86_64
select HAVE_SYSCALL_TRACEPOINTS
select HAVE_UNSTABLE_SCHED_CLOCK
config PGTABLE_LEVELS
int
+ default 5 if X86_5LEVEL
default 4 if X86_64
default 3 if X86_PAE
default 2
def_bool y
depends on X86_GOLDFISH
-config INTEL_RDT_A
- bool "Intel Resource Director Technology Allocation support"
+config INTEL_RDT
+ bool "Intel Resource Director Technology support"
default n
depends on X86 && CPU_SUP_INTEL
select KERNFS
help
- Select to enable resource allocation which is a sub-feature of
- Intel Resource Director Technology(RDT). More information about
- RDT can be found in the Intel x86 Architecture Software
- Developer Manual.
+ Select to enable resource allocation and monitoring which are
+ sub-features of Intel Resource Director Technology(RDT). More
+ information about RDT can be found in the Intel x86
+ Architecture Software Developer Manual.
Say N if unsure.
Statistics are displayed in debugfs filesystem. Enabling this option
may incur significant overhead.
-source "arch/x86/lguest/Kconfig"
-
config PARAVIRT_TIME_ACCOUNTING
bool "Paravirtual steal time accounting"
depends on PARAVIRT
has the cost of more pagetable lookup overhead, and also
consumes more pagetable space per process.
+config X86_5LEVEL
+ bool "Enable 5-level page tables support"
+ depends on X86_64
+ ---help---
+ 5-level paging enables access to larger address space:
+ upto 128 PiB of virtual address space and 4 PiB of
+ physical address space.
+
+ It will be supported by future Intel CPUs.
+
+ Note: a kernel with this option enabled can only be booted
+ on machines that support the feature.
+
+ See Documentation/x86/x86_64/5level-paging.txt for more
+ information.
+
+ Say N if unsure.
+
config ARCH_PHYS_ADDR_T_64BIT
def_bool y
depends on X86_64 || X86_PAE
supports them), so don't confuse the user by printing
that we have them enabled.
+config ARCH_HAS_MEM_ENCRYPT
+ def_bool y
+
+config AMD_MEM_ENCRYPT
+ bool "AMD Secure Memory Encryption (SME) support"
+ depends on X86_64 && CPU_SUP_AMD
+ ---help---
+ Say yes to enable support for the encryption of system memory.
+ This requires an AMD processor that supports Secure Memory
+ Encryption (SME).
+
+config AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT
+ bool "Activate AMD Secure Memory Encryption (SME) by default"
+ default y
+ depends on AMD_MEM_ENCRYPT
+ ---help---
+ Say yes to have system memory encrypted by default if running on
+ an AMD processor that supports Secure Memory Encryption (SME).
+
+ If set to Y, then the encryption of system memory can be
+ deactivated with the mem_encrypt=off command line option.
+
+ If set to N, then the encryption of system memory can be
+ activated with the mem_encrypt=on command line option.
+
+config ARCH_USE_MEMREMAP_PROT
+ def_bool y
+ depends on AMD_MEM_ENCRYPT
+
# Common NUMA Features
config NUMA
bool "Numa Memory Allocation and Scheduler Support"
config X86_INTEL_MPX
prompt "Intel MPX (Memory Protection Extensions)"
def_bool n
- depends on CPU_SUP_INTEL
+ # Note: only available in 64-bit mode due to VMA flags shortage
+ depends on CPU_SUP_INTEL && X86_64
+ select ARCH_USES_HIGH_VMA_FLAGS
---help---
MPX provides hardware features that can be used in
conjunction with compiler-instrumented code to check
endmenu
+config ARCH_HAS_ADD_PAGES
+ def_bool y
+ depends on X86_64 && ARCH_ENABLE_MEMORY_HOTPLUG
+
config ARCH_ENABLE_MEMORY_HOTPLUG
def_bool y
depends on X86_64 || (X86_32 && HIGHMEM)
def_bool y
depends on X86_64 && HUGETLB_PAGE && MIGRATION
+config ARCH_ENABLE_THP_MIGRATION
+ def_bool y
+ depends on X86_64 && TRANSPARENT_HUGEPAGE
+
menu "Power management and ACPI options"
config ARCH_HIBERNATION_HEADER
if (cmd == ND_CMD_CALL) {
call_pkg = buf;
func = call_pkg->nd_command;
+
+ for (i = 0; i < ARRAY_SIZE(call_pkg->nd_reserved2); i++)
+ if (call_pkg->nd_reserved2[i])
+ return -EINVAL;
}
if (nvdimm) {
}
static DEVICE_ATTR_RO(range_index);
+ static ssize_t ecc_unit_size_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+ {
+ struct nd_region *nd_region = to_nd_region(dev);
+ struct nfit_spa *nfit_spa = nd_region_provider_data(nd_region);
+
+ return sprintf(buf, "%d\n", nfit_spa->clear_err_unit);
+ }
+ static DEVICE_ATTR_RO(ecc_unit_size);
+
static struct attribute *acpi_nfit_region_attributes[] = {
&dev_attr_range_index.attr,
+ &dev_attr_ecc_unit_size.attr,
NULL,
};
struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
struct acpi_nfit_memory_map *memdev = memdev_from_spa(acpi_desc,
spa->range_index, i);
+ struct acpi_nfit_control_region *dcr = nfit_mem->dcr;
if (!memdev || !nfit_mem->dcr) {
dev_err(dev, "%s: failed to find DCR\n", __func__);
}
map->region_offset = memdev->region_offset;
- map->serial_number = nfit_mem->dcr->serial_number;
+ map->serial_number = dcr->serial_number;
map2->region_offset = memdev->region_offset;
- map2->serial_number = nfit_mem->dcr->serial_number;
- map2->vendor_id = nfit_mem->dcr->vendor_id;
- map2->manufacturing_date = nfit_mem->dcr->manufacturing_date;
- map2->manufacturing_location = nfit_mem->dcr->manufacturing_location;
+ map2->serial_number = dcr->serial_number;
+ map2->vendor_id = dcr->vendor_id;
+ map2->manufacturing_date = dcr->manufacturing_date;
+ map2->manufacturing_location = dcr->manufacturing_location;
}
/* v1.1 namespaces */
cmp_map_compat, NULL);
nd_set->altcookie = nd_fletcher64(info, sizeof_nfit_set_info(nr), 0);
+ /* record the result of the sort for the mapping position */
+ for (i = 0; i < nr; i++) {
+ struct nfit_set_info_map2 *map2 = &info2->mapping[i];
+ int j;
+
+ for (j = 0; j < nr; j++) {
+ struct nd_mapping_desc *mapping = &ndr_desc->mapping[j];
+ struct nvdimm *nvdimm = mapping->nvdimm;
+ struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
+ struct acpi_nfit_control_region *dcr = nfit_mem->dcr;
+
+ if (map2->serial_number == dcr->serial_number &&
+ map2->vendor_id == dcr->vendor_id &&
+ map2->manufacturing_date == dcr->manufacturing_date &&
+ map2->manufacturing_location
+ == dcr->manufacturing_location) {
+ mapping->position = i;
+ break;
+ }
+ }
+ }
+
ndr_desc->nd_set = nd_set;
devm_kfree(dev, info);
devm_kfree(dev, info2);
memcpy_flushcache(mmio->addr.aperture + offset, iobuf + copied, c);
else {
if (nfit_blk->dimm_flags & NFIT_BLK_READ_FLUSH)
- mmio_flush_range((void __force *)
+ arch_invalidate_pmem((void __force *)
mmio->addr.aperture + offset, c);
memcpy(iobuf + copied, mmio->addr.aperture + offset, c);
* need to be interruptible while waiting.
*/
INIT_WORK_ONSTACK(&flush.work, flush_probe);
- COMPLETION_INITIALIZER_ONSTACK(flush.cmp);
+ init_completion(&flush.cmp);
queue_work(nfit_wq, &flush.work);
mutex_unlock(&acpi_desc->init_mutex);
LOG_OLD_ENT
};
+ static struct device *to_dev(struct arena_info *arena)
+ {
+ return &arena->nd_btt->dev;
+ }
+
+ static u64 adjust_initial_offset(struct nd_btt *nd_btt, u64 offset)
+ {
+ return offset + nd_btt->initial_offset;
+ }
+
static int arena_read_bytes(struct arena_info *arena, resource_size_t offset,
void *buf, size_t n, unsigned long flags)
{
struct nd_namespace_common *ndns = nd_btt->ndns;
/* arena offsets may be shifted from the base of the device */
- offset += arena->nd_btt->initial_offset;
+ offset = adjust_initial_offset(nd_btt, offset);
return nvdimm_read_bytes(ndns, offset, buf, n, flags);
}
struct nd_namespace_common *ndns = nd_btt->ndns;
/* arena offsets may be shifted from the base of the device */
- offset += arena->nd_btt->initial_offset;
+ offset = adjust_initial_offset(nd_btt, offset);
return nvdimm_write_bytes(ndns, offset, buf, n, flags);
}
* We rely on that to make sure rw_bytes does error clearing
* correctly, so make sure that is the case.
*/
- WARN_ON_ONCE(!IS_ALIGNED(arena->infooff, 512));
- WARN_ON_ONCE(!IS_ALIGNED(arena->info2off, 512));
+ dev_WARN_ONCE(to_dev(arena), !IS_ALIGNED(arena->infooff, 512),
+ "arena->infooff: %#llx is unaligned\n", arena->infooff);
+ dev_WARN_ONCE(to_dev(arena), !IS_ALIGNED(arena->info2off, 512),
+ "arena->info2off: %#llx is unaligned\n", arena->info2off);
ret = arena_write_bytes(arena, arena->info2off, super,
sizeof(struct btt_sb), 0);
static int btt_info_read(struct arena_info *arena, struct btt_sb *super)
{
- WARN_ON(!super);
return arena_read_bytes(arena, arena->infooff, super,
sizeof(struct btt_sb), 0);
}
{
u64 ns_off = arena->mapoff + (lba * MAP_ENT_SIZE);
- WARN_ON(lba >= arena->external_nlba);
+ if (unlikely(lba >= arena->external_nlba))
+ dev_err_ratelimited(to_dev(arena),
+ "%s: lba %#x out of range (max: %#x)\n",
+ __func__, lba, arena->external_nlba);
return arena_write_bytes(arena, ns_off, &mapping, MAP_ENT_SIZE, flags);
}
* This 'mapping' is supposed to be just the LBA mapping, without
* any flags set, so strip the flag bits.
*/
- mapping &= MAP_LBA_MASK;
+ mapping = ent_lba(mapping);
ze = (z_flag << 1) + e_flag;
switch (ze) {
* construed as a valid 'normal' case, but we decide not to,
* to avoid confusion
*/
- WARN_ONCE(1, "Invalid use of Z and E flags\n");
+ dev_err_ratelimited(to_dev(arena),
+ "Invalid use of Z and E flags\n");
return -EIO;
}
u32 raw_mapping, postmap, ze, z_flag, e_flag;
u64 ns_off = arena->mapoff + (lba * MAP_ENT_SIZE);
- WARN_ON(lba >= arena->external_nlba);
+ if (unlikely(lba >= arena->external_nlba))
+ dev_err_ratelimited(to_dev(arena),
+ "%s: lba %#x out of range (max: %#x)\n",
+ __func__, lba, arena->external_nlba);
ret = arena_read_bytes(arena, ns_off, &in, MAP_ENT_SIZE, rwb_flags);
if (ret)
raw_mapping = le32_to_cpu(in);
- z_flag = (raw_mapping & MAP_TRIM_MASK) >> MAP_TRIM_SHIFT;
- e_flag = (raw_mapping & MAP_ERR_MASK) >> MAP_ERR_SHIFT;
+ z_flag = ent_z_flag(raw_mapping);
+ e_flag = ent_e_flag(raw_mapping);
ze = (z_flag << 1) + e_flag;
- postmap = raw_mapping & MAP_LBA_MASK;
+ postmap = ent_lba(raw_mapping);
/* Reuse the {z,e}_flag variables for *trim and *error */
z_flag = 0;
static int btt_log_read_pair(struct arena_info *arena, u32 lane,
struct log_entry *ent)
{
- WARN_ON(!ent);
return arena_read_bytes(arena,
arena->logoff + (2 * lane * LOG_ENT_SIZE), ent,
2 * LOG_ENT_SIZE, 0);
return old;
}
- static struct device *to_dev(struct arena_info *arena)
- {
- return &arena->nd_btt->dev;
- }
-
/*
* This function copies the desired (old/new) log entry into ent if
* it is not NULL. It returns the sub-slot number (0 or 1)
arena->freelist[lane].sub = 1 - arena->freelist[lane].sub;
if (++(arena->freelist[lane].seq) == 4)
arena->freelist[lane].seq = 1;
- arena->freelist[lane].block = le32_to_cpu(ent->old_map);
+ if (ent_e_flag(ent->old_map))
+ arena->freelist[lane].has_err = 1;
+ arena->freelist[lane].block = le32_to_cpu(ent_lba(ent->old_map));
return ret;
}
* make sure rw_bytes does error clearing correctly, so make sure that
* is the case.
*/
- WARN_ON_ONCE(!IS_ALIGNED(arena->mapoff, 512));
+ dev_WARN_ONCE(to_dev(arena), !IS_ALIGNED(arena->mapoff, 512),
+ "arena->mapoff: %#llx is unaligned\n", arena->mapoff);
while (mapsize) {
size_t size = min(mapsize, chunk_size);
- WARN_ON_ONCE(size < 512);
+ dev_WARN_ONCE(to_dev(arena), size < 512,
+ "chunk size: %#zx is unaligned\n", size);
ret = arena_write_bytes(arena, arena->mapoff + offset, zerobuf,
size, 0);
if (ret)
* make sure rw_bytes does error clearing correctly, so make sure that
* is the case.
*/
- WARN_ON_ONCE(!IS_ALIGNED(arena->logoff, 512));
+ dev_WARN_ONCE(to_dev(arena), !IS_ALIGNED(arena->logoff, 512),
+ "arena->logoff: %#llx is unaligned\n", arena->logoff);
while (logsize) {
size_t size = min(logsize, chunk_size);
- WARN_ON_ONCE(size < 512);
+ dev_WARN_ONCE(to_dev(arena), size < 512,
+ "chunk size: %#zx is unaligned\n", size);
ret = arena_write_bytes(arena, arena->logoff + offset, zerobuf,
size, 0);
if (ret)
return ret;
}
+ static u64 to_namespace_offset(struct arena_info *arena, u64 lba)
+ {
+ return arena->dataoff + ((u64)lba * arena->internal_lbasize);
+ }
+
+ static int arena_clear_freelist_error(struct arena_info *arena, u32 lane)
+ {
+ int ret = 0;
+
+ if (arena->freelist[lane].has_err) {
+ void *zero_page = page_address(ZERO_PAGE(0));
+ u32 lba = arena->freelist[lane].block;
+ u64 nsoff = to_namespace_offset(arena, lba);
+ unsigned long len = arena->sector_size;
+
+ mutex_lock(&arena->err_lock);
+
+ while (len) {
+ unsigned long chunk = min(len, PAGE_SIZE);
+
+ ret = arena_write_bytes(arena, nsoff, zero_page,
+ chunk, 0);
+ if (ret)
+ break;
+ len -= chunk;
+ nsoff += chunk;
+ if (len == 0)
+ arena->freelist[lane].has_err = 0;
+ }
+ mutex_unlock(&arena->err_lock);
+ }
+ return ret;
+ }
+
static int btt_freelist_init(struct arena_info *arena)
{
int old, new, ret;
arena->freelist[i].seq = nd_inc_seq(le32_to_cpu(log_new.seq));
arena->freelist[i].block = le32_to_cpu(log_new.old_map);
+ /*
+ * FIXME: if error clearing fails during init, we want to make
+ * the BTT read-only
+ */
+ if (ent_e_flag(log_new.old_map)) {
+ ret = arena_clear_freelist_error(arena, i);
+ if (ret)
+ dev_err_ratelimited(to_dev(arena),
+ "Unable to clear known errors\n");
+ }
+
/* This implies a newly created or untouched flog entry */
if (log_new.old_map == log_new.new_map)
continue;
if (ret)
return ret;
}
-
}
return 0;
if (!arena)
return NULL;
arena->nd_btt = btt->nd_btt;
+ arena->sector_size = btt->sector_size;
if (!size)
return arena;
arena->external_lba_start = cur_nlba;
parse_arena_meta(arena, super, cur_off);
+ mutex_init(&arena->err_lock);
ret = btt_freelist_init(arena);
if (ret)
goto out;
spin_unlock(&arena->map_locks[idx].lock);
}
- static u64 to_namespace_offset(struct arena_info *arena, u64 lba)
- {
- return arena->dataoff + ((u64)lba * arena->internal_lbasize);
- }
-
static int btt_data_read(struct arena_info *arena, struct page *page,
unsigned int off, u32 lba, u32 len)
{
*/
while (1) {
u32 new_map;
+ int new_t, new_e;
if (t_flag) {
zero_fill_data(page, off, cur_len);
*/
barrier();
- ret = btt_map_read(arena, premap, &new_map, &t_flag,
- &e_flag, NVDIMM_IO_ATOMIC);
+ ret = btt_map_read(arena, premap, &new_map, &new_t,
+ &new_e, NVDIMM_IO_ATOMIC);
if (ret)
goto out_rtt;
- if (postmap == new_map)
+ if ((postmap == new_map) && (t_flag == new_t) &&
+ (e_flag == new_e))
break;
postmap = new_map;
+ t_flag = new_t;
+ e_flag = new_e;
}
ret = btt_data_read(arena, page, off, postmap, cur_len);
- if (ret)
+ if (ret) {
+ int rc;
+
+ /* Media error - set the e_flag */
+ rc = btt_map_write(arena, premap, postmap, 0, 1,
+ NVDIMM_IO_ATOMIC);
goto out_rtt;
+ }
if (bip) {
ret = btt_rw_integrity(btt, bip, arena, postmap, READ);
return ret;
}
+ /*
+ * Normally, arena_{read,write}_bytes will take care of the initial offset
+ * adjustment, but in the case of btt_is_badblock, where we query is_bad_pmem,
+ * we need the final, raw namespace offset here
+ */
+ static bool btt_is_badblock(struct btt *btt, struct arena_info *arena,
+ u32 postmap)
+ {
+ u64 nsoff = adjust_initial_offset(arena->nd_btt,
+ to_namespace_offset(arena, postmap));
+ sector_t phys_sector = nsoff >> 9;
+
+ return is_bad_pmem(btt->phys_bb, phys_sector, arena->internal_lbasize);
+ }
+
static int btt_write_pg(struct btt *btt, struct bio_integrity_payload *bip,
sector_t sector, struct page *page, unsigned int off,
unsigned int len)
while (len) {
u32 cur_len;
+ int e_flag;
+ retry:
lane = nd_region_acquire_lane(btt->nd_region);
ret = lba_to_arena(btt, sector, &premap, &arena);
goto out_lane;
}
+ if (btt_is_badblock(btt, arena, arena->freelist[lane].block))
+ arena->freelist[lane].has_err = 1;
+
+ if (mutex_is_locked(&arena->err_lock)
+ || arena->freelist[lane].has_err) {
+ nd_region_release_lane(btt->nd_region, lane);
+
+ ret = arena_clear_freelist_error(arena, lane);
+ if (ret)
+ return ret;
+
+ /* OK to acquire a different lane/free block */
+ goto retry;
+ }
+
new_postmap = arena->freelist[lane].block;
/* Wait if the new block is being read from */
}
lock_map(arena, premap);
- ret = btt_map_read(arena, premap, &old_postmap, NULL, NULL,
+ ret = btt_map_read(arena, premap, &old_postmap, NULL, &e_flag,
NVDIMM_IO_ATOMIC);
if (ret)
goto out_map;
ret = -EIO;
goto out_map;
}
+ if (e_flag)
+ set_e_flag(old_postmap);
log.lba = cpu_to_le32(premap);
log.old_map = cpu_to_le32(old_postmap);
if (ret)
goto out_map;
- ret = btt_map_write(arena, premap, new_postmap, 0, 0, 0);
+ ret = btt_map_write(arena, premap, new_postmap, 0, 0,
+ NVDIMM_IO_ATOMIC);
if (ret)
goto out_map;
unlock_map(arena, premap);
nd_region_release_lane(btt->nd_region, lane);
+ if (e_flag) {
+ ret = arena_clear_freelist_error(arena, lane);
+ if (ret)
+ return ret;
+ }
+
len -= cur_len;
off += cur_len;
sector += btt->sector_size >> SECTOR_SHIFT;
bio_for_each_segment(bvec, bio, iter) {
unsigned int len = bvec.bv_len;
- BUG_ON(len > PAGE_SIZE);
- /* Make sure len is in multiples of sector size. */
- /* XXX is this right? */
- BUG_ON(len < btt->sector_size);
- BUG_ON(len % btt->sector_size);
+ if (len > PAGE_SIZE || len < btt->sector_size ||
+ len % btt->sector_size) {
+ dev_err_ratelimited(&btt->nd_btt->dev,
+ "unaligned bio segment (len: %d)\n", len);
+ bio->bi_status = BLK_STS_IOERR;
+ break;
+ }
err = btt_do_bvec(btt, bip, bvec.bv_page, len, bvec.bv_offset,
op_is_write(bio_op(bio)), iter.bi_sector);
{
struct btt *btt = bdev->bd_disk->private_data;
int rc;
+ unsigned int len;
- rc = btt_do_bvec(btt, NULL, page, PAGE_SIZE, 0, is_write, sector);
+ len = hpage_nr_pages(page) * PAGE_SIZE;
+ rc = btt_do_bvec(btt, NULL, page, len, 0, is_write, sector);
if (rc == 0)
page_endio(page, is_write, 0);
{
int ret;
struct btt *btt;
+ struct nd_namespace_io *nsio;
struct device *dev = &nd_btt->dev;
btt = devm_kzalloc(dev, sizeof(struct btt), GFP_KERNEL);
INIT_LIST_HEAD(&btt->arena_list);
mutex_init(&btt->init_lock);
btt->nd_region = nd_region;
+ nsio = to_nd_namespace_io(&nd_btt->ndns->dev);
+ btt->phys_bb = &nsio->bb;
ret = discover_arenas(btt);
if (ret) {
}
btt_sb = devm_kzalloc(&nd_btt->dev, sizeof(*btt_sb), GFP_KERNEL);
+ if (!btt_sb)
+ return -ENOMEM;
/*
* If this returns < 0, that is ok as it just means there wasn't
struct nvdimm_drvdata {
struct device *dev;
- int nsindex_size, nslabel_size;
+ int nslabel_size;
struct nd_cmd_get_config_size nsarea;
void *data;
int ns_current, ns_next;
struct nvdimm *nvdimm;
u64 start;
u64 size;
+ int position;
struct list_head labels;
struct mutex lock;
/*
void nd_device_notify(struct device *dev, enum nvdimm_event event);
int nd_uuid_store(struct device *dev, u8 **uuid_out, const char *buf,
size_t len);
- ssize_t nd_sector_size_show(unsigned long current_lbasize,
+ ssize_t nd_size_select_show(unsigned long current_size,
const unsigned long *supported, char *buf);
- ssize_t nd_sector_size_store(struct device *dev, const char *buf,
- unsigned long *current_lbasize, const unsigned long *supported);
+ ssize_t nd_size_select_store(struct device *dev, const char *buf,
+ unsigned long *current_size, const unsigned long *supported);
int __init nvdimm_init(void);
int __init nd_region_init(void);
int __init nd_label_init(void);
struct nd_pfn *to_nd_pfn(struct device *dev);
#if IS_ENABLED(CONFIG_NVDIMM_PFN)
+
+ #ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ #define PFN_DEFAULT_ALIGNMENT HPAGE_PMD_SIZE
+ #else
+ #define PFN_DEFAULT_ALIGNMENT PAGE_SIZE
+ #endif
+
int nd_pfn_probe(struct device *dev, struct nd_namespace_common *ndns);
bool is_nd_pfn(struct device *dev);
struct device *nd_pfn_create(struct nd_region *nd_region);
void __nd_iostat_start(struct bio *bio, unsigned long *start);
static inline bool nd_iostat_start(struct bio *bio, unsigned long *start)
{
- struct gendisk *disk = bio->bi_bdev->bd_disk;
+ struct gendisk *disk = bio->bi_disk;
if (!blk_queue_io_stat(disk->queue))
return false;
*start = jiffies;
- generic_start_io_acct(bio_data_dir(bio),
+ generic_start_io_acct(disk->queue, bio_data_dir(bio),
bio_sectors(bio), &disk->part0);
return true;
}
static inline void nd_iostat_end(struct bio *bio, unsigned long start)
{
- struct gendisk *disk = bio->bi_bdev->bd_disk;
+ struct gendisk *disk = bio->bi_disk;
- generic_end_io_acct(bio_data_dir(bio), &disk->part0, start);
+ generic_end_io_acct(disk->queue, bio_data_dir(bio), &disk->part0,
+ start);
}
static inline bool is_bad_pmem(struct badblocks *bb, sector_t sector,
unsigned int len)
{
if (unlikely(sizeof(time->tv_sec) > 4 &&
(extra & cpu_to_le32(EXT4_EPOCH_MASK)))) {
-#if LINUX_VERSION_CODE < KERNEL_VERSION(4,20,0)
+
+#if 1
/* Handle legacy encoding of pre-1970 dates with epoch
- * bits 1,1. We assume that by kernel version 4.20,
- * everyone will have run fsck over the affected
- * filesystems to correct the problem. (This
- * backwards compatibility may be removed before this
- * time, at the discretion of the ext4 developers.)
+ * bits 1,1. (This backwards compatibility may be removed
+ * at the discretion of the ext4 developers.)
*/
u64 extra_bits = le32_to_cpu(extra) & EXT4_EPOCH_MASK;
if (extra_bits == 3 && ((time->tv_sec) & 0x80000000) != 0)
/* Barrier between changing inodes' journal flags and writepages ops. */
struct percpu_rw_semaphore s_journal_flag_rwsem;
+ struct dax_device *s_daxdev;
};
static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
nolocking */
EXT4_STATE_MAY_INLINE_DATA, /* may have in-inode data */
EXT4_STATE_EXT_PRECACHED, /* extents have been precached */
+ EXT4_STATE_LUSTRE_EA_INODE, /* Lustre-style ea_inode */
};
#define EXT4_INODE_BIT_FNS(name, field, offset) \
pagevec_init(&pvec, 0);
while (index <= end) {
- nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE);
+ nr_pages = pagevec_lookup_range(&pvec, mapping, &index, end);
if (nr_pages == 0)
break;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
- if (page->index > end)
- break;
+
BUG_ON(!PageLocked(page));
BUG_ON(PageWriteback(page));
if (invalidate) {
}
unlock_page(page);
}
- index = pvec.pages[nr_pages - 1]->index + 1;
pagevec_release(&pvec);
}
}
pagevec_init(&pvec, 0);
while (start <= end) {
- nr_pages = pagevec_lookup(&pvec, inode->i_mapping, start,
- PAGEVEC_SIZE);
+ nr_pages = pagevec_lookup_range(&pvec, inode->i_mapping,
+ &start, end);
if (nr_pages == 0)
break;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
- if (page->index > end)
- break;
- /* Up to 'end' pages must be contiguous */
- BUG_ON(page->index != start);
bh = head = page_buffers(page);
do {
if (lblk < mpd->map.m_lblk)
pagevec_release(&pvec);
return err;
}
- start++;
}
pagevec_release(&pvec);
}
static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
unsigned flags, struct iomap *iomap)
{
- struct block_device *bdev;
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
unsigned int blkbits = inode->i_blkbits;
unsigned long first_block = offset >> blkbits;
unsigned long last_block = (offset + length - 1) >> blkbits;
}
iomap->flags = 0;
- bdev = inode->i_sb->s_bdev;
- iomap->bdev = bdev;
- if (blk_queue_dax(bdev->bd_queue))
- iomap->dax_dev = fs_dax_get_by_host(bdev->bd_disk->disk_name);
- else
- iomap->dax_dev = NULL;
+ iomap->bdev = inode->i_sb->s_bdev;
+ iomap->dax_dev = sbi->s_daxdev;
iomap->offset = first_block << blkbits;
if (ret == 0) {
int blkbits = inode->i_blkbits;
bool truncate = false;
- fs_put_dax(iomap->dax_dev);
if (!(flags & IOMAP_WRITE) || (flags & IOMAP_FAULT))
return 0;
brelse(iloc.bh);
ext4_set_inode_flags(inode);
- if (ei->i_flags & EXT4_EA_INODE_FL) {
- ext4_xattr_inode_set_class(inode);
-
- inode_lock(inode);
- inode->i_flags |= S_NOQUOTA;
- inode_unlock(inode);
- }
-
unlock_new_inode(inode);
return inode;
if (sbi->s_chksum_driver)
crypto_free_shash(sbi->s_chksum_driver);
kfree(sbi->s_blockgroup_lock);
+ fs_put_dax(sbi->s_daxdev);
kfree(sbi);
}
unsigned int s_flags = sb->s_flags;
int ret, nr_orphans = 0, nr_truncates = 0;
#ifdef CONFIG_QUOTA
+ int quota_update = 0;
int i;
#endif
if (!es->s_last_orphan) {
#ifdef CONFIG_QUOTA
/* Needed for iput() to work correctly and not trash data */
sb->s_flags |= MS_ACTIVE;
- /* Turn on quotas so that they are updated correctly */
+
+ /*
+ * Turn on quotas which were not enabled for read-only mounts if
+ * filesystem has quota feature, so that they are updated correctly.
+ */
+ if (ext4_has_feature_quota(sb) && (s_flags & MS_RDONLY)) {
+ int ret = ext4_enable_quotas(sb);
+
+ if (!ret)
+ quota_update = 1;
+ else
+ ext4_msg(sb, KERN_ERR,
+ "Cannot turn on quotas: error %d", ret);
+ }
+
+ /* Turn on journaled quotas used for old sytle */
for (i = 0; i < EXT4_MAXQUOTAS; i++) {
if (EXT4_SB(sb)->s_qf_names[i]) {
int ret = ext4_quota_on_mount(sb, i);
- if (ret < 0)
+
+ if (!ret)
+ quota_update = 1;
+ else
ext4_msg(sb, KERN_ERR,
"Cannot turn on journaled "
- "quota: error %d", ret);
+ "quota: type %d: error %d", i, ret);
}
}
#endif
ext4_msg(sb, KERN_INFO, "%d truncate%s cleaned up",
PLURAL(nr_truncates));
#ifdef CONFIG_QUOTA
- /* Turn quotas off */
- for (i = 0; i < EXT4_MAXQUOTAS; i++) {
- if (sb_dqopt(sb)->files[i])
- dquot_quota_off(sb, i);
+ /* Turn off quotas if they were enabled for orphan cleanup */
+ if (quota_update) {
+ for (i = 0; i < EXT4_MAXQUOTAS; i++) {
+ if (sb_dqopt(sb)->files[i])
+ dquot_quota_off(sb, i);
+ }
}
#endif
sb->s_flags = s_flags; /* Restore MS_RDONLY status */
static int ext4_fill_super(struct super_block *sb, void *data, int silent)
{
+ struct dax_device *dax_dev = fs_dax_get_by_bdev(sb->s_bdev);
char *orig_data = kstrdup(data, GFP_KERNEL);
struct buffer_head *bh;
struct ext4_super_block *es = NULL;
if ((data && !orig_data) || !sbi)
goto out_free_base;
+ sbi->s_daxdev = dax_dev;
sbi->s_blockgroup_lock =
kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL);
if (!sbi->s_blockgroup_lock)
out_free_base:
kfree(sbi);
kfree(orig_data);
+ fs_put_dax(dax_dev);
return err ? err : ret;
}
dquot = dqget(sb, qid);
if (IS_ERR(dquot))
return PTR_ERR(dquot);
- spin_lock(&dq_data_lock);
+ spin_lock(&dquot->dq_dqb_lock);
limit = (dquot->dq_dqb.dqb_bsoftlimit ?
dquot->dq_dqb.dqb_bsoftlimit :
(buf->f_files - dquot->dq_dqb.dqb_curinodes) : 0;
}
- spin_unlock(&dq_data_lock);
+ spin_unlock(&dquot->dq_dqb_lock);
dqput(dquot);
return 0;
}
return 0;
}
-/* Helper function for writing quotas on sync - we need to start transaction
- * before quota file is locked for write. Otherwise the are possible deadlocks:
- * Process 1 Process 2
- * ext4_create() quota_sync()
- * jbd2_journal_start() write_dquot()
- * dquot_initialize() down(dqio_mutex)
- * down(dqio_mutex) jbd2_journal_start()
- *
- */
#ifdef CONFIG_QUOTA
+/*
+ * Helper functions so that transaction is started before we acquire dqio_sem
+ * to keep correct lock ordering of transaction > dqio_sem
+ */
static inline struct inode *dquot_to_inode(struct dquot *dquot)
{
return sb_dqopt(dquot->dq_sb)->files[dquot->dq_id.type];
ext4_msg(sb, KERN_WARNING,
"Quota file not on filesystem root. "
"Journaled quota will not work");
+ sb_dqopt(sb)->flags |= DQUOT_NOLIST_DIRTY;
+ } else {
+ /*
+ * Clear the flag just in case mount options changed since
+ * last time.
+ */
+ sb_dqopt(sb)->flags &= ~DQUOT_NOLIST_DIRTY;
}
/*
test_opt(sb, PRJQUOTA),
};
- sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE;
+ sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE | DQUOT_NOLIST_DIRTY;
for (type = 0; type < EXT4_MAXQUOTAS; type++) {
if (qf_inums[type]) {
err = ext4_quota_enable(sb, type, QFMT_VFS_V1,
DQUOT_USAGE_ENABLED |
(quota_mopt[type] ? DQUOT_LIMITS_ENABLED : 0));
if (err) {
+ for (type--; type >= 0; type--)
+ dquot_quota_off(sb, type);
+
ext4_warning(sb,
"Failed to enable quota tracking "
"(type=%d, err=%d). Please run "
return mp->m_ddev_targp->bt_bdev;
}
+ struct dax_device *
+ xfs_find_daxdev_for_inode(
+ struct inode *inode)
+ {
+ struct xfs_inode *ip = XFS_I(inode);
+ struct xfs_mount *mp = ip->i_mount;
+
+ if (XFS_IS_REALTIME_INODE(ip))
+ return mp->m_rtdev_targp->bt_daxdev;
+ else
+ return mp->m_ddev_targp->bt_daxdev;
+ }
+
/*
* We're now finished for good with this page. Update the page state via the
* associated buffer_heads, paying attention to the start and end offsets that
* we need to process on the page.
*
- * Landmine Warning: bh->b_end_io() will call end_page_writeback() on the last
- * buffer in the IO. Once it does this, it is unsafe to access the bufferhead or
- * the page at all, as we may be racing with memory reclaim and it can free both
- * the bufferhead chain and the page as it will see the page as clean and
- * unused.
+ * Note that we open code the action in end_buffer_async_write here so that we
+ * only have to iterate over the buffers attached to the page once. This is not
+ * only more efficient, but also ensures that we only calls end_page_writeback
+ * at the end of the iteration, and thus avoids the pitfall of having the page
+ * and buffers potentially freed after every call to end_buffer_async_write.
*/
static void
xfs_finish_page_writeback(
struct bio_vec *bvec,
int error)
{
- unsigned int end = bvec->bv_offset + bvec->bv_len - 1;
- struct buffer_head *head, *bh, *next;
+ struct buffer_head *head = page_buffers(bvec->bv_page), *bh = head;
+ bool busy = false;
unsigned int off = 0;
- unsigned int bsize;
+ unsigned long flags;
ASSERT(bvec->bv_offset < PAGE_SIZE);
ASSERT((bvec->bv_offset & (i_blocksize(inode) - 1)) == 0);
- ASSERT(end < PAGE_SIZE);
+ ASSERT(bvec->bv_offset + bvec->bv_len <= PAGE_SIZE);
ASSERT((bvec->bv_len & (i_blocksize(inode) - 1)) == 0);
- bh = head = page_buffers(bvec->bv_page);
-
- bsize = bh->b_size;
+ local_irq_save(flags);
+ bit_spin_lock(BH_Uptodate_Lock, &head->b_state);
do {
- if (off > end)
- break;
- next = bh->b_this_page;
- if (off < bvec->bv_offset)
- goto next_bh;
- bh->b_end_io(bh, !error);
-next_bh:
- off += bsize;
- } while ((bh = next) != head);
+ if (off >= bvec->bv_offset &&
+ off < bvec->bv_offset + bvec->bv_len) {
+ ASSERT(buffer_async_write(bh));
+ ASSERT(bh->b_end_io == NULL);
+
+ if (error) {
+ mark_buffer_write_io_error(bh);
+ clear_buffer_uptodate(bh);
+ SetPageError(bvec->bv_page);
+ } else {
+ set_buffer_uptodate(bh);
+ }
+ clear_buffer_async_write(bh);
+ unlock_buffer(bh);
+ } else if (buffer_async_write(bh)) {
+ ASSERT(buffer_locked(bh));
+ busy = true;
+ }
+ off += bh->b_size;
+ } while ((bh = bh->b_this_page) != head);
+ bit_spin_unlock(BH_Uptodate_Lock, &head->b_state);
+ local_irq_restore(flags);
+
+ if (!busy)
+ end_page_writeback(bvec->bv_page);
}
/*
int error)
{
struct inode *inode = ioend->io_inode;
- struct bio *last = ioend->io_bio;
- struct bio *bio, *next;
+ struct bio *bio = &ioend->io_inline_bio;
+ struct bio *last = ioend->io_bio, *next;
+ u64 start = bio->bi_iter.bi_sector;
+ bool quiet = bio_flagged(bio, BIO_QUIET);
for (bio = &ioend->io_inline_bio; bio; bio = next) {
struct bio_vec *bvec;
bio_put(bio);
}
+
+ if (unlikely(error && !quiet)) {
+ xfs_err_ratelimited(XFS_I(inode)->i_mount,
+ "writeback error on sector %llu", start);
+ }
}
/*
ASSERT(!buffer_delay(bh));
ASSERT(!buffer_unwritten(bh));
- mark_buffer_async_write(bh);
+ bh->b_end_io = NULL;
+ set_buffer_async_write(bh);
set_buffer_uptodate(bh);
clear_buffer_dirty(bh);
}
struct buffer_head *bh)
{
bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
- bio->bi_bdev = bh->b_bdev;
+ bio_set_dev(bio, bh->b_bdev);
}
static struct xfs_ioend *
nr_pages = min(total_nr_pages, BIO_MAX_PAGES);
bio = bio_alloc(GFP_NOIO, nr_pages);
- bio->bi_bdev = bp->b_target->bt_bdev;
+ bio_set_dev(bio, bp->b_target->bt_bdev);
bio->bi_iter.bi_sector = sector;
bio->bi_end_io = xfs_buf_bio_end_io;
bio->bi_private = bp;
xfs_buftarg_t *
xfs_alloc_buftarg(
struct xfs_mount *mp,
- struct block_device *bdev)
+ struct block_device *bdev,
+ struct dax_device *dax_dev)
{
xfs_buftarg_t *btp;
btp->bt_mount = mp;
btp->bt_dev = bdev->bd_dev;
btp->bt_bdev = bdev;
+ btp->bt_daxdev = dax_dev;
if (xfs_setsize_buftarg_early(btp, bdev))
goto error;
iomap->offset = XFS_FSB_TO_B(mp, imap->br_startoff);
iomap->length = XFS_FSB_TO_B(mp, imap->br_blockcount);
iomap->bdev = xfs_find_bdev_for_inode(VFS_I(ip));
+ iomap->dax_dev = xfs_find_daxdev_for_inode(VFS_I(ip));
}
xfs_extlen_t
/*
* Complete the transaction
*/
- error = xfs_defer_finish(&tp, &dfops, NULL);
+ error = xfs_defer_finish(&tp, &dfops);
if (error)
goto out_bmap_cancel;
struct inode *inode,
loff_t offset,
loff_t count,
- unsigned flags,
struct iomap *iomap)
{
struct xfs_inode *ip = XFS_I(inode);
if (error)
goto trans_cancel;
- error = xfs_defer_finish(&tp, &dfops, NULL);
+ error = xfs_defer_finish(&tp, &dfops);
if (error)
goto trans_cancel;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
}
- error = xfs_defer_finish(&tp, &dfops, NULL);
+ error = xfs_defer_finish(&tp, &dfops);
if (error)
goto error_on_bmapi_transaction;
int nimaps = 1, error = 0;
bool shared = false, trimmed = false;
unsigned lockmode;
- struct block_device *bdev;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
if (((flags & (IOMAP_WRITE | IOMAP_DIRECT)) == IOMAP_WRITE) &&
!IS_DAX(inode) && !xfs_get_extsz_hint(ip)) {
/* Reserve delalloc blocks for regular writeback. */
- return xfs_file_iomap_begin_delay(inode, offset, length, flags,
- iomap);
+ return xfs_file_iomap_begin_delay(inode, offset, length, iomap);
}
if (need_excl_ilock(ip, flags)) {
xfs_bmbt_to_iomap(ip, iomap, &imap);
- /* optionally associate a dax device with the iomap bdev */
- bdev = iomap->bdev;
- if (blk_queue_dax(bdev->bd_queue))
- iomap->dax_dev = fs_dax_get_by_host(bdev->bd_disk->disk_name);
- else
- iomap->dax_dev = NULL;
-
if (shared)
iomap->flags |= IOMAP_F_SHARED;
return 0;
unsigned flags,
struct iomap *iomap)
{
- fs_put_dax(iomap->dax_dev);
if ((flags & IOMAP_WRITE) && iomap->type == IOMAP_DELALLOC)
return xfs_file_iomap_end_delalloc(XFS_I(inode), offset,
length, written, iomap);
xfs_close_devices(
struct xfs_mount *mp)
{
+ struct dax_device *dax_ddev = mp->m_ddev_targp->bt_daxdev;
+
if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) {
struct block_device *logdev = mp->m_logdev_targp->bt_bdev;
+ struct dax_device *dax_logdev = mp->m_logdev_targp->bt_daxdev;
+
xfs_free_buftarg(mp, mp->m_logdev_targp);
xfs_blkdev_put(logdev);
+ fs_put_dax(dax_logdev);
}
if (mp->m_rtdev_targp) {
struct block_device *rtdev = mp->m_rtdev_targp->bt_bdev;
+ struct dax_device *dax_rtdev = mp->m_rtdev_targp->bt_daxdev;
+
xfs_free_buftarg(mp, mp->m_rtdev_targp);
xfs_blkdev_put(rtdev);
+ fs_put_dax(dax_rtdev);
}
xfs_free_buftarg(mp, mp->m_ddev_targp);
+ fs_put_dax(dax_ddev);
}
/*
struct xfs_mount *mp)
{
struct block_device *ddev = mp->m_super->s_bdev;
+ struct dax_device *dax_ddev = fs_dax_get_by_bdev(ddev);
+ struct dax_device *dax_logdev = NULL, *dax_rtdev = NULL;
struct block_device *logdev = NULL, *rtdev = NULL;
int error;
error = xfs_blkdev_get(mp, mp->m_logname, &logdev);
if (error)
goto out;
+ dax_logdev = fs_dax_get_by_bdev(logdev);
}
if (mp->m_rtname) {
error = -EINVAL;
goto out_close_rtdev;
}
+ dax_rtdev = fs_dax_get_by_bdev(rtdev);
}
/*
* Setup xfs_mount buffer target pointers
*/
error = -ENOMEM;
- mp->m_ddev_targp = xfs_alloc_buftarg(mp, ddev);
+ mp->m_ddev_targp = xfs_alloc_buftarg(mp, ddev, dax_ddev);
if (!mp->m_ddev_targp)
goto out_close_rtdev;
if (rtdev) {
- mp->m_rtdev_targp = xfs_alloc_buftarg(mp, rtdev);
+ mp->m_rtdev_targp = xfs_alloc_buftarg(mp, rtdev, dax_rtdev);
if (!mp->m_rtdev_targp)
goto out_free_ddev_targ;
}
if (logdev && logdev != ddev) {
- mp->m_logdev_targp = xfs_alloc_buftarg(mp, logdev);
+ mp->m_logdev_targp = xfs_alloc_buftarg(mp, logdev, dax_logdev);
if (!mp->m_logdev_targp)
goto out_free_rtdev_targ;
} else {
xfs_free_buftarg(mp, mp->m_ddev_targp);
out_close_rtdev:
xfs_blkdev_put(rtdev);
+ fs_put_dax(dax_rtdev);
out_close_logdev:
- if (logdev && logdev != ddev)
+ if (logdev && logdev != ddev) {
xfs_blkdev_put(logdev);
+ fs_put_dax(dax_logdev);
+ }
out:
+ fs_put_dax(dax_ddev);
return error;
}
tmp_mp->m_super = sb;
error = xfs_parseargs(tmp_mp, options);
xfs_free_fsname(tmp_mp);
- kfree(tmp_mp);
+ kmem_free(tmp_mp);
return error;
}
put_dax(dax_dev);
}
+ struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev);
#else
static inline int bdev_dax_supported(struct super_block *sb, int blocksize)
{
static inline void fs_put_dax(struct dax_device *dax_dev)
{
}
+
+ static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev)
+ {
+ return NULL;
+ }
#endif
int dax_read_lock(void);
void dax_write_cache(struct dax_device *dax_dev, bool wc);
bool dax_write_cache_enabled(struct dax_device *dax_dev);
-/*
- * We use lowest available bit in exceptional entry for locking, one bit for
- * the entry size (PMD) and two more to tell us if the entry is a huge zero
- * page (HZP) or an empty entry that is just used for locking. In total four
- * special bits.
- *
- * If the PMD bit isn't set the entry has size PAGE_SIZE, and if the HZP and
- * EMPTY bits aren't set the entry is a normal DAX entry with a filesystem
- * block allocation.
- */
-#define RADIX_DAX_SHIFT (RADIX_TREE_EXCEPTIONAL_SHIFT + 4)
-#define RADIX_DAX_ENTRY_LOCK (1 << RADIX_TREE_EXCEPTIONAL_SHIFT)
-#define RADIX_DAX_PMD (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 1))
-#define RADIX_DAX_HZP (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2))
-#define RADIX_DAX_EMPTY (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 3))
-
-static inline unsigned long dax_radix_sector(void *entry)
-{
- return (unsigned long)entry >> RADIX_DAX_SHIFT;
-}
-
-static inline void *dax_radix_locked_entry(sector_t sector, unsigned long flags)
-{
- return (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY | flags |
- ((unsigned long)sector << RADIX_DAX_SHIFT) |
- RADIX_DAX_ENTRY_LOCK);
-}
-
ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
const struct iomap_ops *ops);
int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
pgoff_t index);
-void dax_wake_mapping_entry_waiter(struct address_space *mapping,
- pgoff_t index, void *entry, bool wake_all);
#ifdef CONFIG_FS_DAX
int __dax_zero_page_range(struct block_device *bdev,
}
#endif
-#ifdef CONFIG_FS_DAX_PMD
-static inline unsigned int dax_radix_order(void *entry)
-{
- if ((unsigned long)entry & RADIX_DAX_PMD)
- return PMD_SHIFT - PAGE_SHIFT;
- return 0;
-}
-#else
-static inline unsigned int dax_radix_order(void *entry)
-{
- return 0;
-}
-#endif
-int dax_pfn_mkwrite(struct vm_fault *vmf);
-
static inline bool dax_mapping(struct address_space *mapping)
{
return mapping->host && IS_DAX(mapping->host);
config ARCH_HAS_UACCESS_FLUSHCACHE
bool
- config ARCH_HAS_MMIO_FLUSH
- bool
-
config STACKDEPOT
bool
select STACKTRACE
config PRIME_NUMBERS
tristate
+config STRING_SELFTEST
+ bool "Test string functions"
+
endmenu
projects / linux.git / commitdiff