diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2020-04-08 21:03:40 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-04-08 21:03:40 -0700 |
commit | 9b06860d7c1f1f4cb7d70f92e47dfa4a91bd5007 (patch) | |
tree | 120882e574394ce3b11bd491533613b4488fae45 /drivers | |
parent | 0906d8b975ff713cfb55328e4f3bf6de5967415e (diff) | |
parent | f6d2b802f80d0ca89ee1f51c1781b3f79cdb25d5 (diff) |
Merge tag 'libnvdimm-for-5.7' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm
Pull libnvdimm and dax updates from Dan Williams:
"There were multiple touches outside of drivers/nvdimm/ this round to
add cross arch compatibility to the devm_memremap_pages() interface,
enhance numa information for persistent memory ranges, and add a
zero_page_range() dax operation.
This cycle I switched from the patchwork api to Konstantin's b4 script
for collecting tags (from x86, PowerPC, filesystem, and device-mapper
folks), and everything looks to have gone ok there. This has all
appeared in -next with no reported issues.
Summary:
- Add support for region alignment configuration and enforcement to
fix compatibility across architectures and PowerPC page size
configurations.
- Introduce 'zero_page_range' as a dax operation. This facilitates
filesystem-dax operation without a block-device.
- Introduce phys_to_target_node() to facilitate drivers that want to
know resulting numa node if a given reserved address range was
onlined.
- Advertise a persistence-domain for of_pmem and papr_scm. The
persistence domain indicates where cpu-store cycles need to reach
in the platform-memory subsystem before the platform will consider
them power-fail protected.
- Promote numa_map_to_online_node() to a cross-kernel generic
facility.
- Save x86 numa information to allow for node-id lookups for reserved
memory ranges, deploy that capability for the e820-pmem driver.
- Pick up some miscellaneous minor fixes, that missed v5.6-final,
including a some smatch reports in the ioctl path and some unit
test compilation fixups.
- Fixup some flexible-array declarations"
* tag 'libnvdimm-for-5.7' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (29 commits)
dax: Move mandatory ->zero_page_range() check in alloc_dax()
dax,iomap: Add helper dax_iomap_zero() to zero a range
dax: Use new dax zero page method for zeroing a page
dm,dax: Add dax zero_page_range operation
s390,dcssblk,dax: Add dax zero_page_range operation to dcssblk driver
dax, pmem: Add a dax operation zero_page_range
pmem: Add functions for reading/writing page to/from pmem
libnvdimm: Update persistence domain value for of_pmem and papr_scm device
tools/test/nvdimm: Fix out of tree build
libnvdimm/region: Fix build error
libnvdimm/region: Replace zero-length array with flexible-array member
libnvdimm/label: Replace zero-length array with flexible-array member
ACPI: NFIT: Replace zero-length array with flexible-array member
libnvdimm/region: Introduce an 'align' attribute
libnvdimm/region: Introduce NDD_LABELING
libnvdimm/namespace: Enforce memremap_compat_align()
libnvdimm/pfn: Prevent raw mode fallback if pfn-infoblock valid
libnvdimm: Out of bounds read in __nd_ioctl()
acpi/nfit: improve bounds checking for 'func'
mm/memremap_pages: Introduce memremap_compat_align()
...
Diffstat (limited to 'drivers')
-rw-r--r-- | drivers/acpi/nfit/core.c | 14 | ||||
-rw-r--r-- | drivers/acpi/nfit/nfit.h | 13 | ||||
-rw-r--r-- | drivers/acpi/numa/srat.c | 41 | ||||
-rw-r--r-- | drivers/dax/bus.c | 4 | ||||
-rw-r--r-- | drivers/dax/super.c | 28 | ||||
-rw-r--r-- | drivers/md/dm-linear.c | 18 | ||||
-rw-r--r-- | drivers/md/dm-log-writes.c | 17 | ||||
-rw-r--r-- | drivers/md/dm-stripe.c | 23 | ||||
-rw-r--r-- | drivers/md/dm.c | 32 | ||||
-rw-r--r-- | drivers/nvdimm/bus.c | 6 | ||||
-rw-r--r-- | drivers/nvdimm/dimm.c | 2 | ||||
-rw-r--r-- | drivers/nvdimm/dimm_devs.c | 95 | ||||
-rw-r--r-- | drivers/nvdimm/e820.c | 18 | ||||
-rw-r--r-- | drivers/nvdimm/label.h | 2 | ||||
-rw-r--r-- | drivers/nvdimm/namespace_devs.c | 28 | ||||
-rw-r--r-- | drivers/nvdimm/nd.h | 7 | ||||
-rw-r--r-- | drivers/nvdimm/of_pmem.c | 4 | ||||
-rw-r--r-- | drivers/nvdimm/pfn.h | 12 | ||||
-rw-r--r-- | drivers/nvdimm/pfn_devs.c | 40 | ||||
-rw-r--r-- | drivers/nvdimm/pmem.c | 101 | ||||
-rw-r--r-- | drivers/nvdimm/region_devs.c | 130 | ||||
-rw-r--r-- | drivers/s390/block/dcssblk.c | 20 |
22 files changed, 494 insertions, 161 deletions
diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index a3320f93616d..fa4500f9cfd1 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -360,7 +360,7 @@ static union acpi_object *acpi_label_info(acpi_handle handle) static u8 nfit_dsm_revid(unsigned family, unsigned func) { - static const u8 revid_table[NVDIMM_FAMILY_MAX+1][32] = { + static const u8 revid_table[NVDIMM_FAMILY_MAX+1][NVDIMM_CMD_MAX+1] = { [NVDIMM_FAMILY_INTEL] = { [NVDIMM_INTEL_GET_MODES] = 2, [NVDIMM_INTEL_GET_FWINFO] = 2, @@ -386,7 +386,7 @@ static u8 nfit_dsm_revid(unsigned family, unsigned func) if (family > NVDIMM_FAMILY_MAX) return 0; - if (func > 31) + if (func > NVDIMM_CMD_MAX) return 0; id = revid_table[family][func]; if (id == 0) @@ -492,7 +492,8 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, * Check for a valid command. For ND_CMD_CALL, we also have to * make sure that the DSM function is supported. */ - if (cmd == ND_CMD_CALL && !test_bit(func, &dsm_mask)) + if (cmd == ND_CMD_CALL && + (func > NVDIMM_CMD_MAX || !test_bit(func, &dsm_mask))) return -ENOTTY; else if (!test_bit(cmd, &cmd_mask)) return -ENOTTY; @@ -2026,8 +2027,10 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc) continue; } - if (nfit_mem->bdw && nfit_mem->memdev_pmem) + if (nfit_mem->bdw && nfit_mem->memdev_pmem) { set_bit(NDD_ALIASING, &flags); + set_bit(NDD_LABELING, &flags); + } /* collate flags across all memdevs for this dimm */ list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) { @@ -3492,7 +3495,8 @@ static int acpi_nfit_clear_to_send(struct nvdimm_bus_descriptor *nd_desc, if (nvdimm && cmd == ND_CMD_CALL && call_pkg->nd_family == NVDIMM_FAMILY_INTEL) { func = call_pkg->nd_command; - if ((1 << func) & NVDIMM_INTEL_SECURITY_CMDMASK) + if (func > NVDIMM_CMD_MAX || + (1 << func) & NVDIMM_INTEL_SECURITY_CMDMASK) return -EOPNOTSUPP; } diff --git a/drivers/acpi/nfit/nfit.h b/drivers/acpi/nfit/nfit.h index 24241941181c..f5525f8bb770 100644 --- a/drivers/acpi/nfit/nfit.h +++ b/drivers/acpi/nfit/nfit.h @@ -34,6 +34,7 @@ | ACPI_NFIT_MEM_NOT_ARMED | ACPI_NFIT_MEM_MAP_FAILED) #define NVDIMM_FAMILY_MAX NVDIMM_FAMILY_HYPERV +#define NVDIMM_CMD_MAX 31 #define NVDIMM_STANDARD_CMDMASK \ (1 << ND_CMD_SMART | 1 << ND_CMD_SMART_THRESHOLD | 1 << ND_CMD_DIMM_FLAGS \ @@ -144,32 +145,32 @@ struct nfit_spa { unsigned long ars_state; u32 clear_err_unit; u32 max_ars; - struct acpi_nfit_system_address spa[0]; + struct acpi_nfit_system_address spa[]; }; struct nfit_dcr { struct list_head list; - struct acpi_nfit_control_region dcr[0]; + struct acpi_nfit_control_region dcr[]; }; struct nfit_bdw { struct list_head list; - struct acpi_nfit_data_region bdw[0]; + struct acpi_nfit_data_region bdw[]; }; struct nfit_idt { struct list_head list; - struct acpi_nfit_interleave idt[0]; + struct acpi_nfit_interleave idt[]; }; struct nfit_flush { struct list_head list; - struct acpi_nfit_flush_address flush[0]; + struct acpi_nfit_flush_address flush[]; }; struct nfit_memdev { struct list_head list; - struct acpi_nfit_memory_map memdev[0]; + struct acpi_nfit_memory_map memdev[]; }; enum nfit_mem_flags { diff --git a/drivers/acpi/numa/srat.c b/drivers/acpi/numa/srat.c index eadbf90e65d1..47b4969d9b93 100644 --- a/drivers/acpi/numa/srat.c +++ b/drivers/acpi/numa/srat.c @@ -72,47 +72,6 @@ int acpi_map_pxm_to_node(int pxm) } EXPORT_SYMBOL(acpi_map_pxm_to_node); -/** - * acpi_map_pxm_to_online_node - Map proximity ID to online node - * @pxm: ACPI proximity ID - * - * This is similar to acpi_map_pxm_to_node(), but always returns an online - * node. When the mapped node from a given proximity ID is offline, it - * looks up the node distance table and returns the nearest online node. - * - * ACPI device drivers, which are called after the NUMA initialization has - * completed in the kernel, can call this interface to obtain their device - * NUMA topology from ACPI tables. Such drivers do not have to deal with - * offline nodes. A node may be offline when a device proximity ID is - * unique, SRAT memory entry does not exist, or NUMA is disabled, ex. - * "numa=off" on x86. - */ -int acpi_map_pxm_to_online_node(int pxm) -{ - int node, min_node; - - node = acpi_map_pxm_to_node(pxm); - - if (node == NUMA_NO_NODE) - node = 0; - - min_node = node; - if (!node_online(node)) { - int min_dist = INT_MAX, dist, n; - - for_each_online_node(n) { - dist = node_distance(node, n); - if (dist < min_dist) { - min_dist = dist; - min_node = n; - } - } - } - - return min_node; -} -EXPORT_SYMBOL(acpi_map_pxm_to_online_node); - static void __init acpi_table_print_srat_entry(struct acpi_subtable_header *header) { diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c index 46e46047a1f7..df238c8b6ef2 100644 --- a/drivers/dax/bus.c +++ b/drivers/dax/bus.c @@ -421,8 +421,10 @@ struct dev_dax *__devm_create_dev_dax(struct dax_region *dax_region, int id, * device outside of mmap of the resulting character device. */ dax_dev = alloc_dax(dev_dax, NULL, NULL, DAXDEV_F_SYNC); - if (!dax_dev) + if (IS_ERR(dax_dev)) { + rc = PTR_ERR(dax_dev); goto err; + } /* a device_dax instance is dead while the driver is not attached */ kill_dax(dax_dev); diff --git a/drivers/dax/super.c b/drivers/dax/super.c index 0aa4b6bc5101..8e32345be0f7 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -344,6 +344,23 @@ size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, } EXPORT_SYMBOL_GPL(dax_copy_to_iter); +int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff, + size_t nr_pages) +{ + if (!dax_alive(dax_dev)) + return -ENXIO; + /* + * There are no callers that want to zero more than one page as of now. + * Once users are there, this check can be removed after the + * device mapper code has been updated to split ranges across targets. + */ + if (nr_pages != 1) + return -EIO; + + return dax_dev->ops->zero_page_range(dax_dev, pgoff, nr_pages); +} +EXPORT_SYMBOL_GPL(dax_zero_page_range); + #ifdef CONFIG_ARCH_HAS_PMEM_API void arch_wb_cache_pmem(void *addr, size_t size); void dax_flush(struct dax_device *dax_dev, void *addr, size_t size) @@ -551,9 +568,16 @@ struct dax_device *alloc_dax(void *private, const char *__host, dev_t devt; int minor; + if (ops && !ops->zero_page_range) { + pr_debug("%s: error: device does not provide dax" + " operation zero_page_range()\n", + __host ? __host : "Unknown"); + return ERR_PTR(-EINVAL); + } + host = kstrdup(__host, GFP_KERNEL); if (__host && !host) - return NULL; + return ERR_PTR(-ENOMEM); minor = ida_simple_get(&dax_minor_ida, 0, MINORMASK+1, GFP_KERNEL); if (minor < 0) @@ -576,7 +600,7 @@ struct dax_device *alloc_dax(void *private, const char *__host, ida_simple_remove(&dax_minor_ida, minor); err_minor: kfree(host); - return NULL; + return ERR_PTR(-ENOMEM); } EXPORT_SYMBOL_GPL(alloc_dax); diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index 8d07fdf63a47..e1db43446327 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -201,10 +201,27 @@ static size_t linear_dax_copy_to_iter(struct dm_target *ti, pgoff_t pgoff, return dax_copy_to_iter(dax_dev, pgoff, addr, bytes, i); } +static int linear_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff, + size_t nr_pages) +{ + int ret; + struct linear_c *lc = ti->private; + struct block_device *bdev = lc->dev->bdev; + struct dax_device *dax_dev = lc->dev->dax_dev; + sector_t dev_sector, sector = pgoff * PAGE_SECTORS; + + dev_sector = linear_map_sector(ti, sector); + ret = bdev_dax_pgoff(bdev, dev_sector, nr_pages << PAGE_SHIFT, &pgoff); + if (ret) + return ret; + return dax_zero_page_range(dax_dev, pgoff, nr_pages); +} + #else #define linear_dax_direct_access NULL #define linear_dax_copy_from_iter NULL #define linear_dax_copy_to_iter NULL +#define linear_dax_zero_page_range NULL #endif static struct target_type linear_target = { @@ -226,6 +243,7 @@ static struct target_type linear_target = { .direct_access = linear_dax_direct_access, .dax_copy_from_iter = linear_dax_copy_from_iter, .dax_copy_to_iter = linear_dax_copy_to_iter, + .dax_zero_page_range = linear_dax_zero_page_range, }; int __init dm_linear_init(void) diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c index 99721c76225d..8ea20b56b4d6 100644 --- a/drivers/md/dm-log-writes.c +++ b/drivers/md/dm-log-writes.c @@ -994,10 +994,26 @@ static size_t log_writes_dax_copy_to_iter(struct dm_target *ti, return dax_copy_to_iter(lc->dev->dax_dev, pgoff, addr, bytes, i); } +static int log_writes_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff, + size_t nr_pages) +{ + int ret; + struct log_writes_c *lc = ti->private; + sector_t sector = pgoff * PAGE_SECTORS; + + ret = bdev_dax_pgoff(lc->dev->bdev, sector, nr_pages << PAGE_SHIFT, + &pgoff); + if (ret) + return ret; + return dax_zero_page_range(lc->dev->dax_dev, pgoff, + nr_pages << PAGE_SHIFT); +} + #else #define log_writes_dax_direct_access NULL #define log_writes_dax_copy_from_iter NULL #define log_writes_dax_copy_to_iter NULL +#define log_writes_dax_zero_page_range NULL #endif static struct target_type log_writes_target = { @@ -1016,6 +1032,7 @@ static struct target_type log_writes_target = { .direct_access = log_writes_dax_direct_access, .dax_copy_from_iter = log_writes_dax_copy_from_iter, .dax_copy_to_iter = log_writes_dax_copy_to_iter, + .dax_zero_page_range = log_writes_dax_zero_page_range, }; static int __init dm_log_writes_init(void) diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index 63bbcc20f49a..fa813c0f993d 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -360,10 +360,32 @@ static size_t stripe_dax_copy_to_iter(struct dm_target *ti, pgoff_t pgoff, return dax_copy_to_iter(dax_dev, pgoff, addr, bytes, i); } +static int stripe_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff, + size_t nr_pages) +{ + int ret; + sector_t dev_sector, sector = pgoff * PAGE_SECTORS; + struct stripe_c *sc = ti->private; + struct dax_device *dax_dev; + struct block_device *bdev; + uint32_t stripe; + + stripe_map_sector(sc, sector, &stripe, &dev_sector); + dev_sector += sc->stripe[stripe].physical_start; + dax_dev = sc->stripe[stripe].dev->dax_dev; + bdev = sc->stripe[stripe].dev->bdev; + + ret = bdev_dax_pgoff(bdev, dev_sector, nr_pages << PAGE_SHIFT, &pgoff); + if (ret) + return ret; + return dax_zero_page_range(dax_dev, pgoff, nr_pages); +} + #else #define stripe_dax_direct_access NULL #define stripe_dax_copy_from_iter NULL #define stripe_dax_copy_to_iter NULL +#define stripe_dax_zero_page_range NULL #endif /* @@ -486,6 +508,7 @@ static struct target_type stripe_target = { .direct_access = stripe_dax_direct_access, .dax_copy_from_iter = stripe_dax_copy_from_iter, .dax_copy_to_iter = stripe_dax_copy_to_iter, + .dax_zero_page_range = stripe_dax_zero_page_range, }; int __init dm_stripe_init(void) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 21c0207e3207..db9e46114653 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1199,6 +1199,35 @@ static size_t dm_dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, return ret; } +static int dm_dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff, + size_t nr_pages) +{ + struct mapped_device *md = dax_get_private(dax_dev); + sector_t sector = pgoff * PAGE_SECTORS; + struct dm_target *ti; + int ret = -EIO; + int srcu_idx; + + ti = dm_dax_get_live_target(md, sector, &srcu_idx); + + if (!ti) + goto out; + if (WARN_ON(!ti->type->dax_zero_page_range)) { + /* + * ->zero_page_range() is mandatory dax operation. If we are + * here, something is wrong. + */ + dm_put_live_table(md, srcu_idx); + goto out; + } + ret = ti->type->dax_zero_page_range(ti, pgoff, nr_pages); + + out: + dm_put_live_table(md, srcu_idx); + + return ret; +} + /* * A target may call dm_accept_partial_bio only from the map routine. It is * allowed for all bio types except REQ_PREFLUSH, REQ_OP_ZONE_RESET, @@ -1969,7 +1998,7 @@ static struct mapped_device *alloc_dev(int minor) if (IS_ENABLED(CONFIG_DAX_DRIVER)) { md->dax_dev = alloc_dax(md, md->disk->disk_name, &dm_dax_ops, 0); - if (!md->dax_dev) + if (IS_ERR(md->dax_dev)) goto bad; } @@ -3200,6 +3229,7 @@ static const struct dax_operations dm_dax_ops = { .dax_supported = dm_dax_supported, .copy_from_iter = dm_dax_copy_from_iter, .copy_to_iter = dm_dax_copy_to_iter, + .zero_page_range = dm_dax_zero_page_range, }; /* diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index a8b515968569..09087c38fabd 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -1042,8 +1042,10 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, return -EFAULT; } - if (!desc || (desc->out_num + desc->in_num == 0) || - !test_bit(cmd, &cmd_mask)) + if (!desc || + (desc->out_num + desc->in_num == 0) || + cmd > ND_CMD_CALL || + !test_bit(cmd, &cmd_mask)) return -ENOTTY; /* fail write commands (when read-only) */ diff --git a/drivers/nvdimm/dimm.c b/drivers/nvdimm/dimm.c index 64776ed15bb3..7d4ddc4d9322 100644 --- a/drivers/nvdimm/dimm.c +++ b/drivers/nvdimm/dimm.c @@ -99,7 +99,7 @@ static int nvdimm_probe(struct device *dev) if (ndd->ns_current >= 0) { rc = nd_label_reserve_dpa(ndd); if (rc == 0) - nvdimm_set_aliasing(dev); + nvdimm_set_labeling(dev); } nvdimm_bus_unlock(dev); diff --git a/drivers/nvdimm/dimm_devs.c b/drivers/nvdimm/dimm_devs.c index 94ea6dba6b4f..b7b77e8d9027 100644 --- a/drivers/nvdimm/dimm_devs.c +++ b/drivers/nvdimm/dimm_devs.c @@ -32,7 +32,7 @@ int nvdimm_check_config_data(struct device *dev) if (!nvdimm->cmd_mask || !test_bit(ND_CMD_GET_CONFIG_DATA, &nvdimm->cmd_mask)) { - if (test_bit(NDD_ALIASING, &nvdimm->flags)) + if (test_bit(NDD_LABELING, &nvdimm->flags)) return -ENXIO; else return -ENOTTY; @@ -173,11 +173,11 @@ int nvdimm_set_config_data(struct nvdimm_drvdata *ndd, size_t offset, return rc; } -void nvdimm_set_aliasing(struct device *dev) +void nvdimm_set_labeling(struct device *dev) { struct nvdimm *nvdimm = to_nvdimm(dev); - set_bit(NDD_ALIASING, &nvdimm->flags); + set_bit(NDD_LABELING, &nvdimm->flags); } void nvdimm_set_locked(struct device *dev) @@ -312,8 +312,9 @@ static ssize_t flags_show(struct device *dev, { struct nvdimm *nvdimm = to_nvdimm(dev); - return sprintf(buf, "%s%s\n", + return sprintf(buf, "%s%s%s\n", test_bit(NDD_ALIASING, &nvdimm->flags) ? "alias " : "", + test_bit(NDD_LABELING, &nvdimm->flags) ? "label " : "", test_bit(NDD_LOCKED, &nvdimm->flags) ? "lock " : ""); } static DEVICE_ATTR_RO(flags); @@ -562,6 +563,21 @@ int nvdimm_security_freeze(struct nvdimm *nvdimm) return rc; } +static unsigned long dpa_align(struct nd_region *nd_region) +{ + struct device *dev = &nd_region->dev; + + if (dev_WARN_ONCE(dev, !is_nvdimm_bus_locked(dev), + "bus lock required for capacity provision\n")) + return 0; + if (dev_WARN_ONCE(dev, !nd_region->ndr_mappings || nd_region->align + % nd_region->ndr_mappings, + "invalid region align %#lx mappings: %d\n", + nd_region->align, nd_region->ndr_mappings)) + return 0; + return nd_region->align / nd_region->ndr_mappings; +} + int alias_dpa_busy(struct device *dev, void *data) { resource_size_t map_end, blk_start, new; @@ -570,6 +586,7 @@ int alias_dpa_busy(struct device *dev, void *data) struct nd_region *nd_region; struct nvdimm_drvdata *ndd; struct resource *res; + unsigned long align; int i; if (!is_memory(dev)) @@ -607,13 +624,21 @@ int alias_dpa_busy(struct device *dev, void *data) * Find the free dpa from the end of the last pmem allocation to * the end of the interleave-set mapping. */ + align = dpa_align(nd_region); + if (!align) + return 0; + for_each_dpa_resource(ndd, res) { + resource_size_t start, end; + if (strncmp(res->name, "pmem", 4) != 0) continue; - if ((res->start >= blk_start && res->start < map_end) - || (res->end >= blk_start - && res->end <= map_end)) { - new = max(blk_start, min(map_end + 1, res->end + 1)); + + start = ALIGN_DOWN(res->start, align); + end = ALIGN(res->end + 1, align) - 1; + if ((start >= blk_start && start < map_end) + || (end >= blk_start && end <= map_end)) { + new = max(blk_start, min(map_end, end) + 1); if (new != blk_start) { blk_start = new; goto retry; @@ -653,6 +678,7 @@ resource_size_t nd_blk_available_dpa(struct nd_region *nd_region) .res = NULL, }; struct resource *res; + unsigned long align; if (!ndd) return 0; @@ -660,10 +686,20 @@ resource_size_t nd_blk_available_dpa(struct nd_region *nd_region) device_for_each_child(&nvdimm_bus->dev, &info, alias_dpa_busy); /* now account for busy blk allocations in unaliased dpa */ + align = dpa_align(nd_region); + if (!align) + return 0; for_each_dpa_resource(ndd, res) { + resource_size_t start, end, size; + if (strncmp(res->name, "blk", 3) != 0) continue; - info.available -= resource_size(res); + start = ALIGN_DOWN(res->start, align); + end = ALIGN(res->end + 1, align) - 1; + size = end - start + 1; + if (size >= info.available) + return 0; + info.available -= size; } return info.available; @@ -682,19 +718,31 @@ resource_size_t nd_pmem_max_contiguous_dpa(struct nd_region *nd_region, struct nvdimm_bus *nvdimm_bus; resource_size_t max = 0; struct resource *res; + unsigned long align; /* if a dimm is disabled the available capacity is zero */ if (!ndd) return 0; + align = dpa_align(nd_region); + if (!align) + return 0; + nvdimm_bus = walk_to_nvdimm_bus(ndd->dev); if (__reserve_free_pmem(&nd_region->dev, nd_mapping->nvdimm)) return 0; for_each_dpa_resource(ndd, res) { + resource_size_t start, end; + if (strcmp(res->name, "pmem-reserve") != 0) continue; - if (resource_size(res) > max) - max = resource_size(res); + /* trim free space relative to current alignment setting */ + start = ALIGN(res->start, align); + end = ALIGN_DOWN(res->end + 1, align) - 1; + if (end < start) + continue; + if (end - start + 1 > max) + max = end - start + 1; } release_free_pmem(nvdimm_bus, nd_mapping); return max; @@ -722,24 +770,33 @@ resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region, struct nvdimm_drvdata *ndd = to_ndd(nd_mapping); struct resource *res; const char *reason; + unsigned long align; if (!ndd) return 0; + align = dpa_align(nd_region); + if (!align) + return 0; + map_start = nd_mapping->start; map_end = map_start + nd_mapping->size - 1; blk_start = max(map_start, map_end + 1 - *overlap); for_each_dpa_resource(ndd, res) { - if (res->start >= map_start && res->start < map_end) { + resource_size_t start, end; + + start = ALIGN_DOWN(res->start, align); + end = ALIGN(res->end + 1, align) - 1; + if (start >= map_start && start < map_end) { if (strncmp(res->name, "blk", 3) == 0) blk_start = min(blk_start, - max(map_start, res->start)); - else if (res->end > map_end) { + max(map_start, start)); + else if (end > map_end) { reason = "misaligned to iset"; goto err; } else - busy += resource_size(res); - } else if (res->end >= map_start && res->end <= map_end) { + busy += end - start + 1; + } else if (end >= map_start && end <= map_end) { if (strncmp(res->name, "blk", 3) == 0) { /* * If a BLK allocation overlaps the start of @@ -748,8 +805,8 @@ resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region, */ blk_start = map_start; } else - busy += resource_size(res); - } else if (map_start > res->start && map_start < res->end) { + busy += end - start + 1; + } else if (map_start > start && map_start < end) { /* total eclipse of the mapping */ busy += nd_mapping->size; blk_start = map_start; @@ -759,7 +816,7 @@ resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region, *overlap = map_end + 1 - blk_start; available = blk_start - map_start; if (busy < available) - return available - busy; + return ALIGN_DOWN(available - busy, align); return 0; err: diff --git a/drivers/nvdimm/e820.c b/drivers/nvdimm/e820.c index e02f60ad6c99..4cd18be9d0e9 100644 --- a/drivers/nvdimm/e820.c +++ b/drivers/nvdimm/e820.c @@ -7,6 +7,7 @@ #include <linux/memory_hotplug.h> #include <linux/libnvdimm.h> #include <linux/module.h> +#include <linux/numa.h> static int e820_pmem_remove(struct platform_device *pdev) { @@ -16,27 +17,16 @@ static int e820_pmem_remove(struct platform_device *pdev) return 0; } -#ifdef CONFIG_MEMORY_HOTPLUG -static int e820_range_to_nid(resource_size_t addr) -{ - return memory_add_physaddr_to_nid(addr); -} -#else -static int e820_range_to_nid(resource_size_t addr) -{ - return NUMA_NO_NODE; -} -#endif - static int e820_register_one(struct resource *res, void *data) { struct nd_region_desc ndr_desc; struct nvdimm_bus *nvdimm_bus = data; + int nid = phys_to_target_node(res->start); memset(&ndr_desc, 0, sizeof(ndr_desc)); ndr_desc.res = res; - ndr_desc.numa_node = e820_range_to_nid(res->start); - ndr_desc.target_node = ndr_desc.numa_node; + ndr_desc.numa_node = numa_map_to_online_node(nid); + ndr_desc.target_node = nid; set_bit(ND_REGION_PAGEMAP, &ndr_desc.flags); if (!nvdimm_pmem_region_create(nvdimm_bus, &ndr_desc)) return -ENXIO; diff --git a/drivers/nvdimm/label.h b/drivers/nvdimm/label.h index 4c7b775c2811..956b6d1bd8cc 100644 --- a/drivers/nvdimm/label.h +++ b/drivers/nvdimm/label.h @@ -62,7 +62,7 @@ struct nd_namespace_index { __le16 major; __le16 minor; __le64 checksum; - u8 free[0]; + u8 free[]; }; /** diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c index 032dc61725ff..ae155e860fdc 100644 --- a/drivers/nvdimm/namespace_devs.c +++ b/drivers/nvdimm/namespace_devs.c @@ -10,6 +10,7 @@ #include <linux/nd.h> #include "nd-core.h" #include "pmem.h" +#include "pfn.h" #include "nd.h" static void namespace_io_release(struct device *dev) @@ -541,6 +542,11 @@ static void space_valid(struct nd_region *nd_region, struct nvdimm_drvdata *ndd, { bool is_reserve = strcmp(label_id->id, "pmem-reserve") == 0; bool is_pmem = strncmp(label_id->id, "pmem", 4) == 0; + unsigned long align; + + align = nd_region->align / nd_region->ndr_mappings; + valid->start = ALIGN(valid->start, align); + valid->end = ALIGN_DOWN(valid->end + 1, align) - 1; if (valid->start >= valid->end) goto invalid; @@ -980,10 +986,10 @@ static ssize_t __size_store(struct device *dev, unsigned long long val) return -ENXIO; } - div_u64_rem(val, PAGE_SIZE * nd_region->ndr_mappings, &remainder); + div_u64_rem(val, nd_region->align, &remainder); if (remainder) { dev_dbg(dev, "%llu is not %ldK aligned\n", val, - (PAGE_SIZE * nd_region->ndr_mappings) / SZ_1K); + nd_region->align / SZ_1K); return -EINVAL; } @@ -1739,6 +1745,22 @@ struct nd_namespace_common *nvdimm_namespace_common_probe(struct device *dev) return ERR_PTR(-ENODEV); } + /* + * Note, alignment validation for fsdax and devdax mode + * namespaces happens in nd_pfn_validate() where infoblock + * padding parameters can be applied. + */ + if (pmem_should_map_pages(dev)) { + struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev); + struct resource *res = &nsio->res; + + if (!IS_ALIGNED(res->start | (res->end + 1), + memremap_compat_align())) { + dev_err(&ndns->dev, "%pr misaligned, unable to map\n", res); + return ERR_PTR(-EOPNOTSUPP); + } + } + if (is_namespace_pmem(&ndns->dev)) { struct nd_namespace_pmem *nspm; @@ -2521,7 +2543,7 @@ static int init_active_labels(struct nd_region *nd_region) if (!ndd) { if (test_bit(NDD_LOCKED, &nvdimm->flags)) /* fail, label data may be unreadable */; - else if (test_bit(NDD_ALIASING, &nvdimm->flags)) + else if (test_bit(NDD_LABELING, &nvdimm->flags)) /* fail, labels needed to disambiguate dpa */; else return 0; diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h index c9f6a5b5253a..85dbb2a322b9 100644 --- a/drivers/nvdimm/nd.h +++ b/drivers/nvdimm/nd.h @@ -39,7 +39,7 @@ struct nd_region_data { int ns_count; int ns_active; unsigned int hints_shift; - void __iomem *flush_wpq[0]; + void __iomem *flush_wpq[]; }; static inline void __iomem *ndrd_get_flush_wpq(struct nd_region_data *ndrd, @@ -146,6 +146,7 @@ struct nd_region { struct device *btt_seed; struct device *pfn_seed; struct device *dax_seed; + unsigned long align; u16 ndr_mappings; u64 ndr_size; u64 ndr_start; @@ -156,7 +157,7 @@ struct nd_region { struct nd_interleave_set *nd_set; struct nd_percpu_lane __percpu *lane; int (*flush)(struct nd_region *nd_region, struct bio *bio); - struct nd_mapping mapping[0]; + struct nd_mapping mapping[]; }; struct nd_blk_region { @@ -252,7 +253,7 @@ int nvdimm_set_config_data(struct nvdimm_drvdata *ndd, size_t offset, void *buf, size_t len); long nvdimm_clear_poison(struct device *dev, phys_addr_t phys, unsigned int len); -void nvdimm_set_aliasing(struct device *dev); +void nvdimm_set_labeling(struct device *dev); void nvdimm_set_locked(struct device *dev); void nvdimm_clear_locked(struct device *dev); int nvdimm_security_setup_events(struct device *dev); diff --git a/drivers/nvdimm/of_pmem.c b/drivers/nvdimm/of_pmem.c index 8224d1431ea9..6826a274a1f1 100644 --- a/drivers/nvdimm/of_pmem.c +++ b/drivers/nvdimm/of_pmem.c @@ -62,8 +62,10 @@ static int of_pmem_region_probe(struct platform_device *pdev) if (is_volatile) region = nvdimm_volatile_region_create(bus, &ndr_desc); - else + else { + set_bit(ND_REGION_PERSIST_MEMCTRL, &ndr_desc.flags); region = nvdimm_pmem_region_create(bus, &ndr_desc); + } |