diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-05-05 18:49:20 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-05-05 18:49:20 -0700 |
commit | 53ef7d0e208fa38c3f63d287e0c3ab174f1e1235 (patch) | |
tree | 7d437edf73ef6deb0d77ce291aa25f041837d056 | |
parent | c6a677c6f37bb7abc85ba7e3465e82b9f7eb1d91 (diff) | |
parent | 736163671bcb163fc82600b46c83dfa89d532d95 (diff) |
Merge tag 'libnvdimm-for-4.12' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm
Pull libnvdimm updates from Dan Williams:
"The bulk of this has been in multiple -next releases. There were a few
late breaking fixes and small features that got added in the last
couple days, but the whole set has received a build success
notification from the kbuild robot.
Change summary:
- Region media error reporting: A libnvdimm region device is the
parent to one or more namespaces. To date, media errors have been
reported via the "badblocks" attribute attached to pmem block
devices for namespaces in "raw" or "memory" mode. Given that
namespaces can be in "device-dax" or "btt-sector" mode this new
interface reports media errors generically, i.e. independent of
namespace modes or state.
This subsequently allows userspace tooling to craft "ACPI 6.1
Section 9.20.7.6 Function Index 4 - Clear Uncorrectable Error"
requests and submit them via the ioctl path for NVDIMM root bus
devices.
- Introduce 'struct dax_device' and 'struct dax_operations': Prompted
by a request from Linus and feedback from Christoph this allows for
dax capable drivers to publish their own custom dax operations.
This fixes the broken assumption that all dax operations are
related to a persistent memory device, and makes it easier for
other architectures and platforms to add customized persistent
memory support.
- 'libnvdimm' core updates: A new "deep_flush" sysfs attribute is
available for storage appliance applications to manually trigger
memory controllers to drain write-pending buffers that would
otherwise be flushed automatically by the platform ADR
(asynchronous-DRAM-refresh) mechanism at a power loss event.
Support for "locked" DIMMs is included to prevent namespaces from
surfacing when the namespace label data area is locked. Finally,
fixes for various reported deadlocks and crashes, also tagged for
-stable.
- ACPI / nfit driver updates: General updates of the nfit driver to
add DSM command overrides, ACPI 6.1 health state flags support, DSM
payload debug available by default, and various fixes.
Acknowledgements that came after the branch was pushed:
- commmit 565851c972b5 "device-dax: fix sysfs attribute deadlock":
Tested-by: Yi Zhang <yizhan@redhat.com>
- commit 23f498448362 "libnvdimm: rework region badblocks clearing"
Tested-by: Toshi Kani <toshi.kani@hpe.com>"
* tag 'libnvdimm-for-4.12' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (52 commits)
libnvdimm, pfn: fix 'npfns' vs section alignment
libnvdimm: handle locked label storage areas
libnvdimm: convert NDD_ flags to use bitops, introduce NDD_LOCKED
brd: fix uninitialized use of brd->dax_dev
block, dax: use correct format string in bdev_dax_supported
device-dax: fix sysfs attribute deadlock
libnvdimm: restore "libnvdimm: band aid btt vs clear poison locking"
libnvdimm: fix nvdimm_bus_lock() vs device_lock() ordering
libnvdimm: rework region badblocks clearing
acpi, nfit: kill ACPI_NFIT_DEBUG
libnvdimm: fix clear length of nvdimm_forget_poison()
libnvdimm, pmem: fix a NULL pointer BUG in nd_pmem_notify
libnvdimm, region: sysfs trigger for nvdimm_flush()
libnvdimm: fix phys_addr for nvdimm_clear_poison
x86, dax, pmem: remove indirection around memcpy_from_pmem()
block: remove block_device_operations ->direct_access()
block, dax: convert bdev_dax_supported() to dax_direct_access()
filesystem-dax: convert to dax_direct_access()
Revert "block: use DAX for partition table reads"
ext2, ext4, xfs: retrieve dax_device for iomap operations
...
63 files changed, 1807 insertions, 944 deletions
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index 7e3a2ebba29b..33244e3d9375 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -284,6 +284,7 @@ config CPM2 config AXON_RAM tristate "Axon DDR2 memory device driver" depends on PPC_IBM_CELL_BLADE && BLOCK + select DAX default m help It registers one block device per Axon's DDR2 memory bank found diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c index f523ac883150..a7fe5fee744f 100644 --- a/arch/powerpc/sysdev/axonram.c +++ b/arch/powerpc/sysdev/axonram.c @@ -25,6 +25,7 @@ #include <linux/bio.h> #include <linux/blkdev.h> +#include <linux/dax.h> #include <linux/device.h> #include <linux/errno.h> #include <linux/fs.h> @@ -62,6 +63,7 @@ static int azfs_major, azfs_minor; struct axon_ram_bank { struct platform_device *device; struct gendisk *disk; + struct dax_device *dax_dev; unsigned int irq_id; unsigned long ph_addr; unsigned long io_addr; @@ -137,25 +139,32 @@ axon_ram_make_request(struct request_queue *queue, struct bio *bio) return BLK_QC_T_NONE; } -/** - * axon_ram_direct_access - direct_access() method for block device - * @device, @sector, @data: see block_device_operations method - */ +static const struct block_device_operations axon_ram_devops = { + .owner = THIS_MODULE, +}; + static long -axon_ram_direct_access(struct block_device *device, sector_t sector, - void **kaddr, pfn_t *pfn, long size) +__axon_ram_direct_access(struct axon_ram_bank *bank, pgoff_t pgoff, long nr_pages, + void **kaddr, pfn_t *pfn) { - struct axon_ram_bank *bank = device->bd_disk->private_data; - loff_t offset = (loff_t)sector << AXON_RAM_SECTOR_SHIFT; + resource_size_t offset = pgoff * PAGE_SIZE; *kaddr = (void *) bank->io_addr + offset; *pfn = phys_to_pfn_t(bank->ph_addr + offset, PFN_DEV); - return bank->size - offset; + return (bank->size - offset) / PAGE_SIZE; } -static const struct block_device_operations axon_ram_devops = { - .owner = THIS_MODULE, - .direct_access = axon_ram_direct_access +static long +axon_ram_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, + void **kaddr, pfn_t *pfn) +{ + struct axon_ram_bank *bank = dax_get_private(dax_dev); + + return __axon_ram_direct_access(bank, pgoff, nr_pages, kaddr, pfn); +} + +static const struct dax_operations axon_ram_dax_ops = { + .direct_access = axon_ram_dax_direct_access, }; /** @@ -219,6 +228,7 @@ static int axon_ram_probe(struct platform_device *device) goto failed; } + bank->disk->major = azfs_major; bank->disk->first_minor = azfs_minor; bank->disk->fops = &axon_ram_devops; @@ -227,6 +237,13 @@ static int axon_ram_probe(struct platform_device *device) sprintf(bank->disk->disk_name, "%s%d", AXON_RAM_DEVICE_NAME, axon_ram_bank_id); + bank->dax_dev = alloc_dax(bank, bank->disk->disk_name, + &axon_ram_dax_ops); + if (!bank->dax_dev) { + rc = -ENOMEM; + goto failed; + } + bank->disk->queue = blk_alloc_queue(GFP_KERNEL); if (bank->disk->queue == NULL) { dev_err(&device->dev, "Cannot register disk queue\n"); @@ -278,6 +295,8 @@ failed: del_gendisk(bank->disk); put_disk(bank->disk); } + kill_dax(bank->dax_dev); + put_dax(bank->dax_dev); device->dev.platform_data = NULL; if (bank->io_addr != 0) iounmap((void __iomem *) bank->io_addr); @@ -300,6 +319,8 @@ axon_ram_remove(struct platform_device *device) device_remove_file(&device->dev, &dev_attr_ecc); free_irq(bank->irq_id, device); + kill_dax(bank->dax_dev); + put_dax(bank->dax_dev); del_gendisk(bank->disk); put_disk(bank->disk); iounmap((void __iomem *) bank->io_addr); diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h index 529bb4a6487a..d5a22bac9988 100644 --- a/arch/x86/include/asm/pmem.h +++ b/arch/x86/include/asm/pmem.h @@ -44,11 +44,6 @@ static inline void arch_memcpy_to_pmem(void *dst, const void *src, size_t n) BUG(); } -static inline int arch_memcpy_from_pmem(void *dst, const void *src, size_t n) -{ - return memcpy_mcsafe(dst, src, n); -} - /** * arch_wb_cache_pmem - write back a cache range with CLWB * @vaddr: virtual start address diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h index a164862d77e3..733bae07fb29 100644 --- a/arch/x86/include/asm/string_64.h +++ b/arch/x86/include/asm/string_64.h @@ -79,6 +79,7 @@ int strcmp(const char *cs, const char *ct); #define memset(s, c, n) __memset(s, c, n) #endif +#define __HAVE_ARCH_MEMCPY_MCSAFE 1 __must_check int memcpy_mcsafe_unrolled(void *dst, const void *src, size_t cnt); DECLARE_STATIC_KEY_FALSE(mcsafe_key); diff --git a/block/Kconfig b/block/Kconfig index 89cd28f8d051..a8ad7e77db28 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -6,6 +6,7 @@ menuconfig BLOCK default y select SBITMAP select SRCU + select DAX help Provide block layer support for the kernel. diff --git a/block/partition-generic.c b/block/partition-generic.c index 0171a2faad68..ff07b9143ca4 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -16,7 +16,6 @@ #include <linux/kmod.h> #include <linux/ctype.h> #include <linux/genhd.h> -#include <linux/dax.h> #include <linux/blktrace_api.h> #include "partitions/check.h" @@ -630,24 +629,12 @@ int invalidate_partitions(struct gendisk *disk, struct block_device *bdev) return 0; } -static struct page *read_pagecache_sector(struct block_device *bdev, sector_t n) -{ - struct address_space *mapping = bdev->bd_inode->i_mapping; - - return read_mapping_page(mapping, (pgoff_t)(n >> (PAGE_SHIFT-9)), - NULL); -} - unsigned char *read_dev_sector(struct block_device *bdev, sector_t n, Sector *p) { + struct address_space *mapping = bdev->bd_inode->i_mapping; struct page *page; - /* don't populate page cache for dax capable devices */ - if (IS_DAX(bdev->bd_inode)) - page = read_dax_sector(bdev, n); - else - page = read_pagecache_sector(bdev, n); - + page = read_mapping_page(mapping, (pgoff_t)(n >> (PAGE_SHIFT-9)), NULL); if (!IS_ERR(page)) { if (PageError(page)) goto fail; diff --git a/drivers/Makefile b/drivers/Makefile index 8f8bdc9e3d29..903b19199b69 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -71,7 +71,7 @@ obj-$(CONFIG_PARPORT) += parport/ obj-$(CONFIG_NVM) += lightnvm/ obj-y += base/ block/ misc/ mfd/ nfc/ obj-$(CONFIG_LIBNVDIMM) += nvdimm/ -obj-$(CONFIG_DEV_DAX) += dax/ +obj-$(CONFIG_DAX) += dax/ obj-$(CONFIG_DMA_SHARED_BUFFER) += dma-buf/ obj-$(CONFIG_NUBUS) += nubus/ obj-y += macintosh/ diff --git a/drivers/acpi/nfit/Kconfig b/drivers/acpi/nfit/Kconfig index dd0d53c52552..6d3351452ea2 100644 --- a/drivers/acpi/nfit/Kconfig +++ b/drivers/acpi/nfit/Kconfig @@ -12,15 +12,3 @@ config ACPI_NFIT To compile this driver as a module, choose M here: the module will be called nfit. - -config ACPI_NFIT_DEBUG - bool "NFIT DSM debug" - depends on ACPI_NFIT - depends on DYNAMIC_DEBUG - default n - help - Enabling this option causes the nfit driver to dump the - input and output buffers of _DSM operations on the ACPI0012 - device and its children. This can be very verbose, so leave - it disabled unless you are debugging a hardware / firmware - issue. diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index c8ea9d698cd0..656acb5d7166 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -49,7 +49,16 @@ MODULE_PARM_DESC(scrub_overflow_abort, static bool disable_vendor_specific; module_param(disable_vendor_specific, bool, S_IRUGO); MODULE_PARM_DESC(disable_vendor_specific, - "Limit commands to the publicly specified set\n"); + "Limit commands to the publicly specified set"); + +static unsigned long override_dsm_mask; +module_param(override_dsm_mask, ulong, S_IRUGO); +MODULE_PARM_DESC(override_dsm_mask, "Bitmask of allowed NVDIMM DSM functions"); + +static int default_dsm_family = -1; +module_param(default_dsm_family, int, S_IRUGO); +MODULE_PARM_DESC(default_dsm_family, + "Try this DSM type first when identifying NVDIMM family"); LIST_HEAD(acpi_descs); DEFINE_MUTEX(acpi_desc_lock); @@ -175,14 +184,29 @@ static int xlat_bus_status(void *buf, unsigned int cmd, u32 status) return 0; } +static int xlat_nvdimm_status(void *buf, unsigned int cmd, u32 status) +{ + switch (cmd) { + case ND_CMD_GET_CONFIG_SIZE: + if (status >> 16 & ND_CONFIG_LOCKED) + return -EACCES; + break; + default: + break; + } + + /* all other non-zero status results in an error */ + if (status) + return -EIO; + return 0; +} + static int xlat_status(struct nvdimm *nvdimm, void *buf, unsigned int cmd, u32 status) { if (!nvdimm) return xlat_bus_status(buf, cmd, status); - if (status) - return -EIO; - return 0; + return xlat_nvdimm_status(buf, cmd, status); } int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, @@ -259,14 +283,11 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, in_buf.buffer.length = call_pkg->nd_size_in; } - if (IS_ENABLED(CONFIG_ACPI_NFIT_DEBUG)) { - dev_dbg(dev, "%s:%s cmd: %d: func: %d input length: %d\n", - __func__, dimm_name, cmd, func, - in_buf.buffer.length); - print_hex_dump_debug("nvdimm in ", DUMP_PREFIX_OFFSET, 4, 4, + dev_dbg(dev, "%s:%s cmd: %d: func: %d input length: %d\n", + __func__, 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); - } out_obj = acpi_evaluate_dsm(handle, uuid, 1, func, &in_obj); if (!out_obj) { @@ -298,13 +319,11 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, goto out; } - if (IS_ENABLED(CONFIG_ACPI_NFIT_DEBUG)) { - dev_dbg(dev, "%s:%s cmd: %s output length: %d\n", __func__, - dimm_name, cmd_name, out_obj->buffer.length); - print_hex_dump_debug(cmd_name, DUMP_PREFIX_OFFSET, 4, - 4, out_obj->buffer.pointer, min_t(u32, 128, - out_obj->buffer.length), true); - } + dev_dbg(dev, "%s:%s cmd: %s output length: %d\n", __func__, dimm_name, + cmd_name, out_obj->buffer.length); + print_hex_dump_debug(cmd_name, DUMP_PREFIX_OFFSET, 4, 4, + out_obj->buffer.pointer, + min_t(u32, 128, out_obj->buffer.length), true); for (i = 0, offset = 0; i < desc->out_num; i++) { u32 out_size = nd_cmd_out_size(nvdimm, cmd, desc, i, buf, @@ -448,9 +467,9 @@ 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\n", + dev_dbg(dev, "%s: memdev handle: %#x spa: %d dcr: %d flags: %#x\n", __func__, memdev->device_handle, memdev->range_index, - memdev->region_index); + memdev->region_index, memdev->flags); return true; } @@ -729,28 +748,38 @@ static void nfit_mem_init_bdw(struct acpi_nfit_desc *acpi_desc, } } -static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc, +static int __nfit_mem_init(struct acpi_nfit_desc *acpi_desc, struct acpi_nfit_system_address *spa) { struct nfit_mem *nfit_mem, *found; struct nfit_memdev *nfit_memdev; - int type = nfit_spa_type(spa); + int type = spa ? nfit_spa_type(spa) : 0; switch (type) { case NFIT_SPA_DCR: case NFIT_SPA_PM: break; default: - return 0; + if (spa) + return 0; } + /* + * This loop runs in two modes, when a dimm is mapped the loop + * adds memdev associations to an existing dimm, or creates a + * dimm. In the unmapped dimm case this loop sweeps for memdev + * instances with an invalid / zero range_index and adds those + * dimms without spa associations. + */ list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) { struct nfit_flush *nfit_flush; struct nfit_dcr *nfit_dcr; u32 device_handle; u16 dcr; - if (nfit_memdev->memdev->range_index != spa->range_index) + if (spa && nfit_memdev->memdev->range_index != spa->range_index) + continue; + if (!spa && nfit_memdev->memdev->range_index) continue; found = NULL; dcr = nfit_memdev->memdev->region_index; @@ -835,14 +864,15 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc, break; } nfit_mem_init_bdw(acpi_desc, nfit_mem, spa); - } else { + } else if (type == NFIT_SPA_PM) { /* * A single dimm may belong to multiple SPA-PM * ranges, record at least one in addition to * any SPA-DCR range. */ nfit_mem->memdev_pmem = nfit_memdev->memdev; - } + } else + nfit_mem->memdev_dcr = nfit_memdev->memdev; } return 0; @@ -866,6 +896,8 @@ static int nfit_mem_cmp(void *priv, struct list_head *_a, struct list_head *_b) static int nfit_mem_init(struct acpi_nfit_desc *acpi_desc) { struct nfit_spa *nfit_spa; + int rc; + /* * For each SPA-DCR or SPA-PMEM address range find its @@ -876,13 +908,20 @@ static int nfit_mem_init(struct acpi_nfit_desc *acpi_desc) * BDWs are optional. */ list_for_each_entry(nfit_spa, &acpi_desc->spas, list) { - int rc; - - rc = nfit_mem_dcr_init(acpi_desc, nfit_spa->spa); + rc = __nfit_mem_init(acpi_desc, nfit_spa->spa); if (rc) return rc; } + /* + * If a DIMM has failed to be mapped into SPA there will be no + * SPA entries above. Find and register all the unmapped DIMMs + * for reporting and recovery purposes. + */ + rc = __nfit_mem_init(acpi_desc, NULL); + if (rc) + return rc; + list_sort(NULL, &acpi_desc->dimms, nfit_mem_cmp); return 0; @@ -1237,12 +1276,14 @@ static ssize_t flags_show(struct device *dev, { u16 flags = to_nfit_memdev(dev)->flags; - return sprintf(buf, "%s%s%s%s%s\n", + return sprintf(buf, "%s%s%s%s%s%s%s\n", flags & ACPI_NFIT_MEM_SAVE_FAILED ? "save_fail " : "", flags & ACPI_NFIT_MEM_RESTORE_FAILED ? "restore_fail " : "", flags & ACPI_NFIT_MEM_FLUSH_FAILED ? "flush_fail " : "", flags & ACPI_NFIT_MEM_NOT_ARMED ? "not_armed " : "", - flags & ACPI_NFIT_MEM_HEALTH_OBSERVED ? "smart_event " : ""); + flags & ACPI_NFIT_MEM_HEALTH_OBSERVED ? "smart_event " : "", + flags & ACPI_NFIT_MEM_MAP_FAILED ? "map_fail " : "", + flags & ACPI_NFIT_MEM_HEALTH_ENABLED ? "smart_notify " : ""); } static DEVICE_ATTR_RO(flags); @@ -1290,8 +1331,16 @@ static umode_t acpi_nfit_dimm_attr_visible(struct kobject *kobj, struct device *dev = container_of(kobj, struct device, kobj); struct nvdimm *nvdimm = to_nvdimm(dev); - if (!to_nfit_dcr(dev)) + if (!to_nfit_dcr(dev)) { + /* Without a dcr only the memdev attributes can be surfaced */ + if (a == &dev_attr_handle.attr || a == &dev_attr_phys_id.attr + || a == &dev_attr_flags.attr + || a == &dev_attr_family.attr + || a == &dev_attr_dsm_mask.attr) + return a->mode; return 0; + } + if (a == &dev_attr_format1.attr && num_nvdimm_formats(nvdimm) <= 1) return 0; return a->mode; @@ -1368,6 +1417,7 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc, unsigned long dsm_mask; const u8 *uuid; int i; + int family = -1; /* nfit test assumes 1:1 relationship between commands and dsms */ nfit_mem->dsm_mask = acpi_desc->dimm_cmd_force_en; @@ -1398,11 +1448,14 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc, */ for (i = NVDIMM_FAMILY_INTEL; i <= NVDIMM_FAMILY_MSFT; i++) if (acpi_check_dsm(adev_dimm->handle, to_nfit_uuid(i), 1, 1)) - break; + if (family < 0 || i == default_dsm_family) + family = i; /* limit the supported commands to those that are publicly documented */ - nfit_mem->family = i; - if (nfit_mem->family == NVDIMM_FAMILY_INTEL) { + nfit_mem->family = family; + if (override_dsm_mask && !disable_vendor_specific) + dsm_mask = override_dsm_mask; + else if (nfit_mem->family == NVDIMM_FAMILY_INTEL) { dsm_mask = 0x3fe; if (disable_vendor_specific) dsm_mask &= ~(1 << ND_CMD |