diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2018-04-10 10:25:57 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-04-10 10:25:57 -0700 |
commit | 9f3a0941fb5efaa4d27911e251dc595034d58baa (patch) | |
tree | 7212d9872b41b73a0b3c4f8c991039b639add212 /drivers | |
parent | fbe173e3ffbd897b5a859020d714c0eaf4af2a1a (diff) | |
parent | e13e75b86ef2f88e3a47d672dd4c52a293efb95b (diff) |
Merge tag 'libnvdimm-for-4.17' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm
Pull libnvdimm updates from Dan Williams:
"This cycle was was not something I ever want to repeat as there were
several late changes that have only now just settled.
Half of the branch up to commit d2c997c0f145 ("fs, dax: use
page->mapping to warn...") have been in -next for several releases.
The of_pmem driver and the address range scrub rework were late
arrivals, and the dax work was scaled back at the last moment.
The of_pmem driver missed a previous merge window due to an oversight.
A sense of obligation to rectify that miss is why it is included for
4.17. It has acks from PowerPC folks. Stephen reported a build failure
that only occurs when merging it with your latest tree, for now I have
fixed that up by disabling modular builds of of_pmem. A test merge
with your tree has received a build success report from the 0day robot
over 156 configs.
An initial version of the ARS rework was submitted before the merge
window. It is self contained to libnvdimm, a net code reduction, and
passing all unit tests.
The filesystem-dax changes are based on the wait_var_event()
functionality from tip/sched/core. However, late review feedback
showed that those changes regressed truncate performance to a large
degree. The branch was rewound to drop the truncate behavior change
and now only includes preparation patches and cleanups (with full acks
and reviews). The finalization of this dax-dma-vs-trnucate work will
need to wait for 4.18.
Summary:
- A rework of the filesytem-dax implementation provides for detection
of unmap operations (truncate / hole punch) colliding with
in-progress device-DMA. A fix for these collisions remains a
work-in-progress pending resolution of truncate latency and
starvation regressions.
- The of_pmem driver expands the users of libnvdimm outside of x86
and ACPI to describe an implementation of persistent memory on
PowerPC with Open Firmware / Device tree.
- Address Range Scrub (ARS) handling is completely rewritten to
account for the fact that ARS may run for 100s of seconds and there
is no platform defined way to cancel it. ARS will now no longer
block namespace initialization.
- The NVDIMM Namespace Label implementation is updated to handle
label areas as small as 1K, down from 128K.
- Miscellaneous cleanups and updates to unit test infrastructure"
* tag 'libnvdimm-for-4.17' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (39 commits)
libnvdimm, of_pmem: workaround OF_NUMA=n build error
nfit, address-range-scrub: add module option to skip initial ars
nfit, address-range-scrub: rework and simplify ARS state machine
nfit, address-range-scrub: determine one platform max_ars value
powerpc/powernv: Create platform devs for nvdimm buses
doc/devicetree: Persistent memory region bindings
libnvdimm: Add device-tree based driver
libnvdimm: Add of_node to region and bus descriptors
libnvdimm, region: quiet region probe
libnvdimm, namespace: use a safe lookup for dimm device name
libnvdimm, dimm: fix dpa reservation vs uninitialized label area
libnvdimm, testing: update the default smart ctrl_temperature
libnvdimm, testing: Add emulation for smart injection commands
nfit, address-range-scrub: introduce nfit_spa->ars_state
libnvdimm: add an api to cast a 'struct nd_region' to its 'struct device'
nfit, address-range-scrub: fix scrub in-progress reporting
dax, dm: allow device-mapper to operate without dax support
dax: introduce CONFIG_DAX_DRIVER
fs, dax: use page->mapping to warn if truncate collides with a busy page
ext2, dax: introduce ext2_dax_aops
...
Diffstat (limited to 'drivers')
31 files changed, 700 insertions, 581 deletions
diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 22a112b4f4d8..e2235ed3e4be 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -36,16 +36,6 @@ static bool force_enable_dimms; module_param(force_enable_dimms, bool, S_IRUGO|S_IWUSR); MODULE_PARM_DESC(force_enable_dimms, "Ignore _STA (ACPI DIMM device) status"); -static unsigned int scrub_timeout = NFIT_ARS_TIMEOUT; -module_param(scrub_timeout, uint, S_IRUGO|S_IWUSR); -MODULE_PARM_DESC(scrub_timeout, "Initial scrub timeout in seconds"); - -/* after three payloads of overflow, it's dead jim */ -static unsigned int scrub_overflow_abort = 3; -module_param(scrub_overflow_abort, uint, S_IRUGO|S_IWUSR); -MODULE_PARM_DESC(scrub_overflow_abort, - "Number of times we overflow ARS results before abort"); - static bool disable_vendor_specific; module_param(disable_vendor_specific, bool, S_IRUGO); MODULE_PARM_DESC(disable_vendor_specific, @@ -60,6 +50,10 @@ module_param(default_dsm_family, int, S_IRUGO); MODULE_PARM_DESC(default_dsm_family, "Try this DSM type first when identifying NVDIMM family"); +static bool no_init_ars; +module_param(no_init_ars, bool, 0644); +MODULE_PARM_DESC(no_init_ars, "Skip ARS run at nfit init time"); + LIST_HEAD(acpi_descs); DEFINE_MUTEX(acpi_desc_lock); @@ -197,7 +191,7 @@ static int xlat_nvdimm_status(struct nvdimm *nvdimm, void *buf, unsigned int cmd * In the _LSI, _LSR, _LSW case the locked status is * communicated via the read/write commands */ - if (nfit_mem->has_lsi) + if (nfit_mem->has_lsr) break; if (status >> 16 & ND_CONFIG_LOCKED) @@ -477,14 +471,14 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, in_buf.buffer.length = call_pkg->nd_size_in; } - dev_dbg(dev, "%s:%s cmd: %d: func: %d input length: %d\n", - __func__, dimm_name, cmd, func, in_buf.buffer.length); + dev_dbg(dev, "%s cmd: %d: func: %d input length: %d\n", + dimm_name, cmd, func, in_buf.buffer.length); print_hex_dump_debug("nvdimm in ", DUMP_PREFIX_OFFSET, 4, 4, in_buf.buffer.pointer, min_t(u32, 256, in_buf.buffer.length), true); /* call the BIOS, prefer the named methods over _DSM if available */ - if (nvdimm && cmd == ND_CMD_GET_CONFIG_SIZE && nfit_mem->has_lsi) + if (nvdimm && cmd == ND_CMD_GET_CONFIG_SIZE && nfit_mem->has_lsr) out_obj = acpi_label_info(handle); else if (nvdimm && cmd == ND_CMD_GET_CONFIG_DATA && nfit_mem->has_lsr) { struct nd_cmd_get_config_data_hdr *p = buf; @@ -507,8 +501,7 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, } if (!out_obj) { - dev_dbg(dev, "%s:%s _DSM failed cmd: %s\n", __func__, dimm_name, - cmd_name); + dev_dbg(dev, "%s _DSM failed cmd: %s\n", dimm_name, cmd_name); return -EINVAL; } @@ -529,13 +522,13 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, } if (out_obj->package.type != ACPI_TYPE_BUFFER) { - dev_dbg(dev, "%s:%s unexpected output object type cmd: %s type: %d\n", - __func__, dimm_name, cmd_name, out_obj->type); + dev_dbg(dev, "%s unexpected output object type cmd: %s type: %d\n", + dimm_name, cmd_name, out_obj->type); rc = -EINVAL; goto out; } - dev_dbg(dev, "%s:%s cmd: %s output length: %d\n", __func__, dimm_name, + dev_dbg(dev, "%s cmd: %s output length: %d\n", dimm_name, cmd_name, out_obj->buffer.length); print_hex_dump_debug(cmd_name, DUMP_PREFIX_OFFSET, 4, 4, out_obj->buffer.pointer, @@ -547,14 +540,14 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, out_obj->buffer.length - offset); if (offset + out_size > out_obj->buffer.length) { - dev_dbg(dev, "%s:%s output object underflow cmd: %s field: %d\n", - __func__, dimm_name, cmd_name, i); + dev_dbg(dev, "%s output object underflow cmd: %s field: %d\n", + dimm_name, cmd_name, i); break; } if (in_buf.buffer.length + offset + out_size > buf_len) { - dev_dbg(dev, "%s:%s output overrun cmd: %s field: %d\n", - __func__, dimm_name, cmd_name, i); + dev_dbg(dev, "%s output overrun cmd: %s field: %d\n", + dimm_name, cmd_name, i); rc = -ENXIO; goto out; } @@ -656,7 +649,7 @@ static bool add_spa(struct acpi_nfit_desc *acpi_desc, INIT_LIST_HEAD(&nfit_spa->list); memcpy(nfit_spa->spa, spa, sizeof(*spa)); list_add_tail(&nfit_spa->list, &acpi_desc->spas); - dev_dbg(dev, "%s: spa index: %d type: %s\n", __func__, + dev_dbg(dev, "spa index: %d type: %s\n", spa->range_index, spa_type_name(nfit_spa_type(spa))); return true; @@ -685,8 +678,8 @@ static bool add_memdev(struct acpi_nfit_desc *acpi_desc, INIT_LIST_HEAD(&nfit_memdev->list); memcpy(nfit_memdev->memdev, memdev, sizeof(*memdev)); list_add_tail(&nfit_memdev->list, &acpi_desc->memdevs); - dev_dbg(dev, "%s: memdev handle: %#x spa: %d dcr: %d flags: %#x\n", - __func__, memdev->device_handle, memdev->range_index, + dev_dbg(dev, "memdev handle: %#x spa: %d dcr: %d flags: %#x\n", + memdev->device_handle, memdev->range_index, memdev->region_index, memdev->flags); return true; } @@ -754,7 +747,7 @@ static bool add_dcr(struct acpi_nfit_desc *acpi_desc, INIT_LIST_HEAD(&nfit_dcr->list); memcpy(nfit_dcr->dcr, dcr, sizeof_dcr(dcr)); list_add_tail(&nfit_dcr->list, &acpi_desc->dcrs); - dev_dbg(dev, "%s: dcr index: %d windows: %d\n", __func__, + dev_dbg(dev, "dcr index: %d windows: %d\n", dcr->region_index, dcr->windows); return true; } @@ -781,7 +774,7 @@ static bool add_bdw(struct acpi_nfit_desc *acpi_desc, INIT_LIST_HEAD(&nfit_bdw->list); memcpy(nfit_bdw->bdw, bdw, sizeof(*bdw)); list_add_tail(&nfit_bdw->list, &acpi_desc->bdws); - dev_dbg(dev, "%s: bdw dcr: %d windows: %d\n", __func__, + dev_dbg(dev, "bdw dcr: %d windows: %d\n", bdw->region_index, bdw->windows); return true; } @@ -820,7 +813,7 @@ static bool add_idt(struct acpi_nfit_desc *acpi_desc, INIT_LIST_HEAD(&nfit_idt->list); memcpy(nfit_idt->idt, idt, sizeof_idt(idt)); list_add_tail(&nfit_idt->list, &acpi_desc->idts); - dev_dbg(dev, "%s: idt index: %d num_lines: %d\n", __func__, + dev_dbg(dev, "idt index: %d num_lines: %d\n", idt->interleave_index, idt->line_count); return true; } @@ -860,7 +853,7 @@ static bool add_flush(struct acpi_nfit_desc *acpi_desc, INIT_LIST_HEAD(&nfit_flush->list); memcpy(nfit_flush->flush, flush, sizeof_flush(flush)); list_add_tail(&nfit_flush->list, &acpi_desc->flushes); - dev_dbg(dev, "%s: nfit_flush handle: %d hint_count: %d\n", __func__, + dev_dbg(dev, "nfit_flush handle: %d hint_count: %d\n", flush->device_handle, flush->hint_count); return true; } @@ -873,7 +866,7 @@ static bool add_platform_cap(struct acpi_nfit_desc *acpi_desc, mask = (1 << (pcap->highest_capability + 1)) - 1; acpi_desc->platform_cap = pcap->capabilities & mask; - dev_dbg(dev, "%s: cap: %#x\n", __func__, acpi_desc->platform_cap); + dev_dbg(dev, "cap: %#x\n", acpi_desc->platform_cap); return true; } @@ -920,7 +913,7 @@ static void *add_table(struct acpi_nfit_desc *acpi_desc, return err; break; case ACPI_NFIT_TYPE_SMBIOS: - dev_dbg(dev, "%s: smbios\n", __func__); + dev_dbg(dev, "smbios\n"); break; case ACPI_NFIT_TYPE_CAPABILITIES: if (!add_platform_cap(acpi_desc, table)) @@ -1277,8 +1270,11 @@ static ssize_t scrub_show(struct device *dev, if (nd_desc) { struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc); + mutex_lock(&acpi_desc->init_mutex); rc = sprintf(buf, "%d%s", acpi_desc->scrub_count, - (work_busy(&acpi_desc->work)) ? "+\n" : "\n"); + work_busy(&acpi_desc->dwork.work) + && !acpi_desc->cancel ? "+\n" : "\n"); + mutex_unlock(&acpi_desc->init_mutex); } device_unlock(dev); return rc; @@ -1648,7 +1644,7 @@ void __acpi_nvdimm_notify(struct device *dev, u32 event) struct nfit_mem *nfit_mem; struct acpi_nfit_desc *acpi_desc; - dev_dbg(dev->parent, "%s: %s: event: %d\n", dev_name(dev), __func__, + dev_dbg(dev->parent, "%s: event: %d\n", dev_name(dev), event); if (event != NFIT_NOTIFY_DIMM_HEALTH) { @@ -1681,12 +1677,23 @@ static void acpi_nvdimm_notify(acpi_handle handle, u32 event, void *data) device_unlock(dev->parent); } +static bool acpi_nvdimm_has_method(struct acpi_device *adev, char *method) +{ + acpi_handle handle; + acpi_status status; + + status = acpi_get_handle(adev->handle, method, &handle); + + if (ACPI_SUCCESS(status)) + return true; + return false; +} + static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc, struct nfit_mem *nfit_mem, u32 device_handle) { struct acpi_device *adev, *adev_dimm; struct device *dev = acpi_desc->dev; - union acpi_object *obj; unsigned long dsm_mask; const guid_t *guid; int i; @@ -1759,25 +1766,15 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc, 1ULL << i)) set_bit(i, &nfit_mem->dsm_mask); - obj = acpi_label_info(adev_dimm->handle); - if (obj) { - ACPI_FREE(obj); - nfit_mem->has_lsi = 1; - dev_dbg(dev, "%s: has _LSI\n", dev_name(&adev_dimm->dev)); - } - - obj = acpi_label_read(adev_dimm->handle, 0, 0); - if (obj) { - ACPI_FREE(obj); - nfit_mem->has_lsr = 1; + if (acpi_nvdimm_has_method(adev_dimm, "_LSI") + && acpi_nvdimm_has_method(adev_dimm, "_LSR")) { dev_dbg(dev, "%s: has _LSR\n", dev_name(&adev_dimm->dev)); + nfit_mem->has_lsr = true; } - obj = acpi_label_write(adev_dimm->handle, 0, 0, NULL); - if (obj) { - ACPI_FREE(obj); - nfit_mem->has_lsw = 1; + if (nfit_mem->has_lsr && acpi_nvdimm_has_method(adev_dimm, "_LSW")) { dev_dbg(dev, "%s: has _LSW\n", dev_name(&adev_dimm->dev)); + nfit_mem->has_lsw = true; } return 0; @@ -1866,10 +1863,10 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc) cmd_mask |= nfit_mem->dsm_mask & NVDIMM_STANDARD_CMDMASK; } - if (nfit_mem->has_lsi) + if (nfit_mem->has_lsr) { set_bit(ND_CMD_GET_CONFIG_SIZE, &cmd_mask); - if (nfit_mem->has_lsr) set_bit(ND_CMD_GET_CONFIG_DATA, &cmd_mask); + } if (nfit_mem->has_lsw) set_bit(ND_CMD_SET_CONFIG_DATA, &cmd_mask); @@ -2365,7 +2362,7 @@ static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus, nvdimm = nd_blk_region_to_dimm(ndbr); nfit_mem = nvdimm_provider_data(nvdimm); if (!nfit_mem || !nfit_mem->dcr || !nfit_mem->bdw) { - dev_dbg(dev, "%s: missing%s%s%s\n", __func__, + dev_dbg(dev, "missing%s%s%s\n", nfit_mem ? "" : " nfit_mem", (nfit_mem && nfit_mem->dcr) ? "" : " dcr", (nfit_mem && nfit_mem->bdw) ? "" : " bdw"); @@ -2384,7 +2381,7 @@ static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus, mmio->addr.base = devm_nvdimm_memremap(dev, nfit_mem->spa_bdw->address, nfit_mem->spa_bdw->length, nd_blk_memremap_flags(ndbr)); if (!mmio->addr.base) { - dev_dbg(dev, "%s: %s failed to map bdw\n", __func__, + dev_dbg(dev, "%s failed to map bdw\n", nvdimm_name(nvdimm)); return -ENOMEM; } @@ -2395,8 +2392,8 @@ static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus, rc = nfit_blk_init_interleave(mmio, nfit_mem->idt_bdw, nfit_mem->memdev_bdw->interleave_ways); if (rc) { - dev_dbg(dev, "%s: %s failed to init bdw interleave\n", - __func__, nvdimm_name(nvdimm)); + dev_dbg(dev, "%s failed to init bdw interleave\n", + nvdimm_name(nvdimm)); return rc; } @@ -2407,7 +2404,7 @@ static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus, mmio->addr.base = devm_nvdimm_ioremap(dev, nfit_mem->spa_dcr->address, nfit_mem->spa_dcr->length); if (!mmio->addr.base) { - dev_dbg(dev, "%s: %s failed to map dcr\n", __func__, + dev_dbg(dev, "%s failed to map dcr\n", nvdimm_name(nvdimm)); return -ENOMEM; } @@ -2418,15 +2415,15 @@ static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus, rc = nfit_blk_init_interleave(mmio, nfit_mem->idt_dcr, nfit_mem->memdev_dcr->interleave_ways); if (rc) { - dev_dbg(dev, "%s: %s failed to init dcr interleave\n", - __func__, nvdimm_name(nvdimm)); + dev_dbg(dev, "%s failed to init dcr interleave\n", + nvdimm_name(nvdimm)); return rc; } rc = acpi_nfit_blk_get_flags(nd_desc, nvdimm, nfit_blk); if (rc < 0) { - dev_dbg(dev, "%s: %s failed get DIMM flags\n", - __func__, nvdimm_name(nvdimm)); + dev_dbg(dev, "%s failed get DIMM flags\n", + nvdimm_name(nvdimm)); return rc; } @@ -2476,7 +2473,8 @@ static int ars_start(struct acpi_nfit_desc *acpi_desc, struct nfit_spa *nfit_spa memset(&ars_start, 0, sizeof(ars_start)); ars_start.address = spa->address; ars_start.length = spa->length; - ars_start.flags = acpi_desc->ars_start_flags; + if (test_bit(ARS_SHORT, &nfit_spa->ars_state)) + ars_start.flags = ND_ARS_RETURN_PREV_DATA; if (nfit_spa_type(spa) == NFIT_SPA_PM) ars_start.type = ND_ARS_PERSISTENT; else if (nfit_spa_type(spa) == NFIT_SPA_VOLATILE) @@ -2518,16 +2516,62 @@ static int ars_get_status(struct acpi_nfit_desc *acpi_desc) int rc, cmd_rc; rc = nd_desc->ndctl(nd_desc, NULL, ND_CMD_ARS_STATUS, ars_status, - acpi_desc->ars_status_size, &cmd_rc); + acpi_desc->max_ars, &cmd_rc); if (rc < 0) return rc; return cmd_rc; } -static int ars_status_process_records(struct acpi_nfit_desc *acpi_desc, - struct nd_cmd_ars_status *ars_status) +static void ars_complete(struct acpi_nfit_desc *acpi_desc, + struct nfit_spa *nfit_spa) +{ + struct nd_cmd_ars_status *ars_status = acpi_desc->ars_status; + struct acpi_nfit_system_address *spa = nfit_spa->spa; + struct nd_region *nd_region = nfit_spa->nd_region; + struct device *dev; + + if ((ars_status->address >= spa->address && ars_status->address + < spa->address + spa->length) + || (ars_status->address < spa->address)) { + /* + * Assume that if a scrub starts at an offset from the + * start of nfit_spa that we are in the continuation + * case. + * + * Otherwise, if the scrub covers the spa range, mark + * any pending request complete. + */ + if (ars_status->address + ars_status->length + >= spa->address + spa->length) + /* complete */; + else + return; + } else + return; + + if (test_bit(ARS_DONE, &nfit_spa->ars_state)) + return; + + if (!test_and_clear_bit(ARS_REQ, &nfit_spa->ars_state)) + return; + + if (nd_region) { + dev = nd_region_dev(nd_region); + nvdimm_region_notify(nd_region, NVDIMM_REVALIDATE_POISON); + } else + dev = acpi_desc->dev; + + dev_dbg(dev, "ARS: range %d %s complete\n", spa->range_index, + test_bit(ARS_SHORT, &nfit_spa->ars_state) + ? "short" : "long"); + clear_bit(ARS_SHORT, &nfit_spa->ars_state); + set_bit(ARS_DONE, &nfit_spa->ars_state); +} + +static int ars_status_process_records(struct acpi_nfit_desc *acpi_desc) { struct nvdimm_bus *nvdimm_bus = acpi_desc->nvdimm_bus; + struct nd_cmd_ars_status *ars_status = acpi_desc->ars_status; int rc; u32 i; @@ -2606,7 +2650,7 @@ static int acpi_nfit_init_mapping(struct acpi_nfit_desc *acpi_desc, struct acpi_nfit_system_address *spa = nfit_spa->spa; struct nd_blk_region_desc *ndbr_desc; struct nfit_mem *nfit_mem; - int blk_valid = 0, rc; + int rc; if (!nvdimm) { dev_err(acpi_desc->dev, "spa%d dimm: %#x not found\n", @@ -2626,15 +2670,14 @@ static int acpi_nfit_init_mapping(struct acpi_nfit_desc *acpi_desc, if (!nfit_mem || !nfit_mem->bdw) { dev_dbg(acpi_desc->dev, "spa%d %s missing bdw\n", spa->range_index, nvdimm_name(nvdimm)); - } else { - mapping->size = nfit_mem->bdw->capacity; - mapping->start = nfit_mem->bdw->start_address; - ndr_desc->num_lanes = nfit_mem->bdw->windows; - blk_valid = 1; + break; } + mapping->size = nfit_mem->bdw->capacity; + mapping->start = nfit_mem->bdw->start_address; + ndr_desc->num_lanes = nfit_mem->bdw->windows; ndr_desc->mapping = mapping; - ndr_desc->num_mappings = blk_valid; + ndr_desc->num_mappings = 1; ndbr_desc = to_blk_region_desc(ndr_desc); ndbr_desc->enable = acpi_nfit_blk_region_enable; ndbr_desc->do_io = acpi_desc->blk_do_io; @@ -2682,8 +2725,7 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc, return 0; if (spa->range_index == 0 && !nfit_spa_is_virtual(spa)) { - dev_dbg(acpi_desc->dev, "%s: detected invalid spa index\n", - __func__); + dev_dbg(acpi_desc->dev, "detected invalid spa index\n"); return 0; } @@ -2769,301 +2811,243 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc, return rc; } -static int ars_status_alloc(struct acpi_nfit_desc *acpi_desc, - u32 max_ars) +static int ars_status_alloc(struct acpi_nfit_desc *acpi_desc) { struct device *dev = acpi_desc->dev; struct nd_cmd_ars_status *ars_status; - if (acpi_desc->ars_status && acpi_desc->ars_status_size >= max_ars) { - memset(acpi_desc->ars_status, 0, acpi_desc->ars_status_size); + if (acpi_desc->ars_status) { + memset(acpi_desc->ars_status, 0, acpi_desc->max_ars); return 0; } - if (acpi_desc->ars_status) - devm_kfree(dev, acpi_desc->ars_status); - acpi_desc->ars_status = NULL; - ars_status = devm_kzalloc(dev, max_ars, GFP_KERNEL); + ars_status = devm_kzalloc(dev, acpi_desc->max_ars, GFP_KERNEL); if (!ars_status) return -ENOMEM; acpi_desc->ars_status = ars_status; - acpi_desc->ars_status_size = max_ars; return 0; } -static int acpi_nfit_query_poison(struct acpi_nfit_desc *acpi_desc, - struct nfit_spa *nfit_spa) +static int acpi_nfit_query_poison(struct acpi_nfit_desc *acpi_desc) { - struct acpi_nfit_system_address *spa = nfit_spa->spa; int rc; - if (!nfit_spa->max_ars) { - struct nd_cmd_ars_cap ars_cap; - - memset(&ars_cap, 0, sizeof(ars_cap)); - rc = ars_get_cap(acpi_desc, &ars_cap, nfit_spa); - if (rc < 0) - return rc; - nfit_spa->max_ars = ars_cap.max_ars_out; - nfit_spa->clear_err_unit = ars_cap.clear_err_unit; - /* check that the supported scrub types match the spa type */ - if (nfit_spa_type(spa) == NFIT_SPA_VOLATILE && - ((ars_cap.status >> 16) & ND_ARS_VOLATILE) == 0) - return -ENOTTY; - else if (nfit_spa_type(spa) == NFIT_SPA_PM && - ((ars_cap.status >> 16) & ND_ARS_PERSISTENT) == 0) - return -ENOTTY; - } - - if (ars_status_alloc(acpi_desc, nfit_spa->max_ars)) + if (ars_status_alloc(acpi_desc)) return -ENOMEM; rc = ars_get_status(acpi_desc); + if (rc < 0 && rc != -ENOSPC) return rc; - if (ars_status_process_records(acpi_desc, acpi_desc->ars_status)) + if (ars_status_process_records(acpi_desc)) return -ENOMEM; return 0; } -static void acpi_nfit_async_scrub(struct acpi_nfit_desc *acpi_desc, - struct nfit_spa *nfit_spa) +static int ars_register(struct acpi_nfit_desc *acpi_desc, struct nfit_spa *nfit_spa, + int *query_rc) { - struct acpi_nfit_system_address *spa = nfit_spa->spa; - unsigned int overflow_retry = scrub_overflow_abort; - u64 init_ars_start = 0, init_ars_len = 0; - struct device *dev = acpi_desc->dev; - unsigned int tmo = scrub_timeout; - int rc; + int rc = *query_rc; - if (!nfit_spa->ars_required || !nfit_spa->nd_region) - return; + if (no_init_ars) + return acpi_nfit_register_region(acpi_desc, nfit_spa); - rc = ars_start(acpi_desc, nfit_spa); - /* - * If we timed out the initial scan we'll still be busy here, - * and will wait another timeout before giving up permanently. - */ - if (rc < 0 && rc != -EBUSY) - return; - - do { - u64 ars_start, ars_len; - - if (acpi_desc->cancel) - break; - rc = acpi_nfit_query_poison(acpi_desc, nfit_spa); - if (rc == -ENOTTY) - break; - if (rc == -EBUSY && !tmo) { - dev_warn(dev, "range %d ars timeout, aborting\n", - spa->range_index); - break; - } + set_bit(ARS_REQ, &nfit_spa->ars_state); + set_bit(ARS_SHORT, &nfit_spa->ars_state); + switch (rc) { + case 0: + case -EAGAIN: + rc = ars_start(acpi_desc, nfit_spa); if (rc == -EBUSY) { - /* - * Note, entries may be appended to the list - * while the lock is dropped, but the workqueue - * being active prevents entries being deleted / - * freed. - */ - mutex_unlock(&acpi_desc->init_mutex); - ssleep(1); - tmo--; - mutex_lock(&acpi_desc->init_mutex); - continue; - } - - /* we got some results, but there are more pending... */ - if (rc == -ENOSPC && overflow_retry--) { - if (!init_ars_len) { - init_ars_len = acpi_desc->ars_status->length; - init_ars_start = acpi_desc->ars_status->address; - } - rc = ars_continue(acpi_desc); - } - - if (rc < 0) { - dev_warn(dev, "range %d ars continuation failed\n", - spa->range_index); + *query_rc = rc; break; - } - - if (init_ars_len) { - ars_start = init_ars_start; - ars_len = init_ars_len; + } else if (rc == 0) { + rc = acpi_nfit_query_poison(acpi_desc); } else { - ars_start = acpi_desc->ars_status->address; - ars_len = acpi_desc->ars_status->length; + set_bit(ARS_FAILED, &nfit_spa->ars_state); + break; } - dev_dbg(dev, "spa range: %d ars from %#llx + %#llx complete\n", - spa->range_index, ars_start, ars_len); - /* notify the region about new poison entries */ - nvdimm_region_notify(nfit_spa->nd_region, - NVDIMM_REVALIDATE_POISON); + if (rc == -EAGAIN) + clear_bit(ARS_SHORT, &nfit_spa->ars_state); + else if (rc == 0) + ars_complete(acpi_desc, nfit_spa); break; - } while (1); + case -EBUSY: + case -ENOSPC: + break; + default: + set_bit(ARS_FAILED, &nfit_spa->ars_state); + break; + } + + if (test_and_clear_bit(ARS_DONE, &nfit_spa->ars_state)) + set_bit(ARS_REQ, &nfit_spa->ars_state); + + return acpi_nfit_register_region(acpi_desc, nfit_spa); } -static void acpi_nfit_scrub(struct work_struct *work) +static void ars_complete_all(struct acpi_nfit_desc *acpi_desc) { - struct device *dev; - u64 init_scrub_length = 0; struct nfit_spa *nfit_spa; - u64 init_scrub_address = 0; - bool init_ars_done = false; - struct acpi_nfit_desc *acpi_desc; - unsigned int tmo = scrub_timeout; - unsigned int overflow_retry = scrub_overflow_abort; - - acpi_desc = container_of(work, typeof(*acpi_desc), work); - dev = acpi_desc->dev; - - /* - * We scrub in 2 phases. The first phase waits for any platform - * firmware initiated scrubs to complete and then we go search for the - * affected spa regions to mark them scanned. In the second phase we - * initiate a directed scrub for every range that was not scrubbed in - * phase 1. If we're called for a 'rescan', we harmlessly pass through - * the first phase, but really only care about running phase 2, where - * regions can be notified of new poison. - */ - /* process platform firmware initiated scrubs */ - retry: - mutex_lock(&acpi_desc->init_mutex); list_for_each_entry(nfit_spa, &acpi_desc->spas, list) { - struct nd_cmd_ars_status *ars_status; - struct acpi_nfit_system_address *spa; - u64 ars_start, ars_len; - int rc; - - if (acpi_desc->cancel) - break; - - if (nfit_spa->nd_region) + if (test_bit(ARS_FAILED, &nfit_spa->ars_state)) continue; + ars_complete(acpi_desc, nfit_spa); + } +} - if (init_ars_done) { - /* - * No need to re-query, we're now just - * reconciling all the ranges covered by the - * initial scrub - */ - rc = 0; - } else - rc = acpi_nfit_query_poison(acpi_desc, nfit_spa); - - if (rc == -ENOTTY) { - /* no ars capability, just register spa and move on */ - acpi_nfit_register_region(acpi_desc, nfit_spa); - continue; - } - - if (rc == -EBUSY && !tmo) { - /* fallthrough to directed scrub in phase 2 */ - dev_warn(dev, "timeout awaiting ars results, continuing...\n"); - break; - } else if (rc == -EBUSY) { - mutex_unlock(&acpi_desc->init_mutex); - ssleep(1); - tmo--; - goto retry; - } - - /* we got some results, but there are more pending... */ - if (rc == -ENOSPC && overflow_retry--) { - ars_status = acpi_desc->ars_status; - /* - * Record the original scrub range, so that we - * can recall all the ranges impacted by the - * initial scrub. - */ - if (!init_scrub_length) { - init_scrub_length = ars_status->length; - init_scrub_address = ars_status->address; - } - rc = ars_continue(acpi_desc); - if (rc == 0) { - mutex_unlock(&acpi_desc->init_mutex); - goto retry; - } - } +static unsigned int __acpi_nfit_scrub(struct acpi_nfit_desc *acpi_desc, + int query_rc) +{ + unsigned int tmo = acpi_desc->scrub_tmo; + struct device *dev = acpi_desc->dev; + struct nfit_spa *nfit_spa; - if (rc < 0) { - /* - * Initial scrub failed, we'll give it one more - * try below... - */ - break; - } + if (acpi_desc->cancel) + return 0; - /* We got some final results, record completed ranges */ - ars_status = acpi_desc->ars_status; - if (init_scrub_length) { - ars_start = init_scrub_address; - ars_len = ars_start + init_scrub_length; - } else { - ars_start = ars_status->address; - ars_len = ars_status->length; - } - spa = nfit_spa->spa; + if (query_rc == -EBUSY) { + dev_dbg(dev, "ARS: ARS busy\n"); + return min(30U * 60U, tmo * 2); + } + if (query_rc == -ENOSPC) { + dev_dbg(dev, "ARS: ARS continue\n"); + ars_continue(acpi_desc); + return 1; + } + if (query_rc && query_rc != -EAGAIN) { + unsigned long long addr, end; - if (!init_ars_done) { - init_ars_done = true; - dev_dbg(dev, "init scrub %#llx |