From 39c686b862cdb2049b90e095b6c6c727b2a7ab60 Mon Sep 17 00:00:00 2001 From: Vishal Verma Date: Thu, 9 Jul 2015 13:25:36 -0600 Subject: libnvdimm: Add DSM support for Address Range Scrub commands Add support for the three ARS DSM commands: - Query ARS Capabilities - Queries the firmware to check if a given range supports scrub, and if so, which type (persistent vs. volatile) - Start ARS - Starts a scrub for a given range/type - Query ARS Status - Checks status of a previously started scrub, and provides the error logs if any. The commands are described by the example DSM spec at: http://pmem.io/documents/NVDIMM_DSM_Interface_Example.pdf Also add these commands to the nfit_test test framework, and return canned data. Signed-off-by: Vishal Verma Signed-off-by: Dan Williams --- drivers/acpi/nfit.c | 1 + drivers/acpi/nfit.h | 1 + 2 files changed, 2 insertions(+) (limited to 'drivers/acpi') diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c index 628a42c41ab1..ef8a664db254 100644 --- a/drivers/acpi/nfit.c +++ b/drivers/acpi/nfit.c @@ -868,6 +868,7 @@ static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc) struct acpi_device *adev; int i; + nd_desc->dsm_mask = acpi_desc->bus_dsm_force_en; adev = to_acpi_dev(acpi_desc); if (!adev) return; diff --git a/drivers/acpi/nfit.h b/drivers/acpi/nfit.h index 79b6d83875c1..f2c2bb751882 100644 --- a/drivers/acpi/nfit.h +++ b/drivers/acpi/nfit.h @@ -107,6 +107,7 @@ struct acpi_nfit_desc { struct nvdimm_bus *nvdimm_bus; struct device *dev; unsigned long dimm_dsm_force_en; + unsigned long bus_dsm_force_en; int (*blk_do_io)(struct nd_blk_region *ndbr, resource_size_t dpa, void *iobuf, u64 len, int rw); }; -- cgit v1.2.3 From 60e95f43fc8573e81f54b0c1e0bc542c2260d956 Mon Sep 17 00:00:00 2001 From: Linda Knippers Date: Wed, 22 Jul 2015 16:17:22 -0400 Subject: nfit: Don't check _STA on NVDIMM devices The _STA only applies to the root device, not the individual NVDIMMS, so don't check here. NVDIMM device state flags are checked elsewhere. Signed-off-by: Linda Knippers Signed-off-by: Dan Williams --- drivers/acpi/nfit.c | 20 ++------------------ 1 file changed, 2 insertions(+), 18 deletions(-) (limited to 'drivers/acpi') diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c index ef8a664db254..7c2638f914a9 100644 --- a/drivers/acpi/nfit.c +++ b/drivers/acpi/nfit.c @@ -764,9 +764,7 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc, struct acpi_device *adev, *adev_dimm; struct device *dev = acpi_desc->dev; const u8 *uuid = to_nfit_uuid(NFIT_DEV_DIMM); - unsigned long long sta; - int i, rc = -ENODEV; - acpi_status status; + int i; nfit_mem->dsm_mask = acpi_desc->dimm_dsm_force_en; adev = to_acpi_dev(acpi_desc); @@ -781,25 +779,11 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc, return force_enable_dimms ? 0 : -ENODEV; } - status = acpi_evaluate_integer(adev_dimm->handle, "_STA", NULL, &sta); - if (status == AE_NOT_FOUND) { - dev_dbg(dev, "%s missing _STA, assuming enabled...\n", - dev_name(&adev_dimm->dev)); - rc = 0; - } else if (ACPI_FAILURE(status)) - dev_err(dev, "%s failed to retrieve_STA, disabling...\n", - dev_name(&adev_dimm->dev)); - else if ((sta & ACPI_STA_DEVICE_ENABLED) == 0) - dev_info(dev, "%s disabled by firmware\n", - dev_name(&adev_dimm->dev)); - else - rc = 0; - for (i = ND_CMD_SMART; i <= ND_CMD_VENDOR; i++) if (acpi_check_dsm(adev_dimm->handle, uuid, 1, 1ULL << i)) set_bit(i, &nfit_mem->dsm_mask); - return force_enable_dimms ? 0 : rc; + return 0; } static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc) -- cgit v1.2.3 From 67a3e8fe90156d41cd480d3dfbb40f3bc007c262 Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Thu, 27 Aug 2015 13:14:20 -0600 Subject: nd_blk: change aperture mapping from WC to WB This should result in a pretty sizeable performance gain for reads. For rough comparison I did some simple read testing using PMEM to compare reads of write combining (WC) mappings vs write-back (WB). This was done on a random lab machine. PMEM reads from a write combining mapping: # dd of=/dev/null if=/dev/pmem0 bs=4096 count=100000 100000+0 records in 100000+0 records out 409600000 bytes (410 MB) copied, 9.2855 s, 44.1 MB/s PMEM reads from a write-back mapping: # dd of=/dev/null if=/dev/pmem0 bs=4096 count=1000000 1000000+0 records in 1000000+0 records out 4096000000 bytes (4.1 GB) copied, 3.44034 s, 1.2 GB/s To be able to safely support a write-back aperture I needed to add support for the "read flush" _DSM flag, as outlined in the DSM spec: http://pmem.io/documents/NVDIMM_DSM_Interface_Example.pdf This flag tells the ND BLK driver that it needs to flush the cache lines associated with the aperture after the aperture is moved but before any new data is read. This ensures that any stale cache lines from the previous contents of the aperture will be discarded from the processor cache, and the new data will be read properly from the DIMM. We know that the cache lines are clean and will be discarded without any writeback because either a) the previous aperture operation was a read, and we never modified the contents of the aperture, or b) the previous aperture operation was a write and we must have written back the dirtied contents of the aperture to the DIMM before the I/O was completed. In order to add support for the "read flush" flag I needed to add a generic routine to invalidate cache lines, mmio_flush_range(). This is protected by the ARCH_HAS_MMIO_FLUSH Kconfig variable, and is currently only supported on x86. Signed-off-by: Ross Zwisler Signed-off-by: Dan Williams --- drivers/acpi/Kconfig | 1 + drivers/acpi/nfit.c | 55 +++++++++++++++++++++++++++++----------------------- drivers/acpi/nfit.h | 16 ++++++++++----- 3 files changed, 43 insertions(+), 29 deletions(-) (limited to 'drivers/acpi') diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index 114cf48085ab..4baeb853e0c3 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -410,6 +410,7 @@ config ACPI_NFIT tristate "ACPI NVDIMM Firmware Interface Table (NFIT)" depends on PHYS_ADDR_T_64BIT depends on BLK_DEV + depends on ARCH_HAS_MMIO_FLUSH select LIBNVDIMM help Infrastructure to probe ACPI 6 compliant platforms for diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c index 7c2638f914a9..56fff0141636 100644 --- a/drivers/acpi/nfit.c +++ b/drivers/acpi/nfit.c @@ -1017,7 +1017,7 @@ static u64 read_blk_stat(struct nfit_blk *nfit_blk, unsigned int bw) if (mmio->num_lines) offset = to_interleave_offset(offset, mmio); - return readq(mmio->base + offset); + return readq(mmio->addr.base + offset); } static void write_blk_ctl(struct nfit_blk *nfit_blk, unsigned int bw, @@ -1042,11 +1042,11 @@ static void write_blk_ctl(struct nfit_blk *nfit_blk, unsigned int bw, if (mmio->num_lines) offset = to_interleave_offset(offset, mmio); - writeq(cmd, mmio->base + offset); + writeq(cmd, mmio->addr.base + offset); wmb_blk(nfit_blk); if (nfit_blk->dimm_flags & ND_BLK_DCR_LATCH) - readq(mmio->base + offset); + readq(mmio->addr.base + offset); } static int acpi_nfit_blk_single_io(struct nfit_blk *nfit_blk, @@ -1078,11 +1078,16 @@ static int acpi_nfit_blk_single_io(struct nfit_blk *nfit_blk, } if (rw) - memcpy_to_pmem(mmio->aperture + offset, + memcpy_to_pmem(mmio->addr.aperture + offset, iobuf + copied, c); - else + else { + if (nfit_blk->dimm_flags & ND_BLK_READ_FLUSH) + mmio_flush_range((void __force *) + mmio->addr.aperture + offset, c); + memcpy_from_pmem(iobuf + copied, - mmio->aperture + offset, c); + mmio->addr.aperture + offset, c); + } copied += c; len -= c; @@ -1129,7 +1134,10 @@ static void nfit_spa_mapping_release(struct kref *kref) WARN_ON(!mutex_is_locked(&acpi_desc->spa_map_mutex)); dev_dbg(acpi_desc->dev, "%s: SPA%d\n", __func__, spa->range_index); - iounmap(spa_map->iomem); + if (spa_map->type == SPA_MAP_APERTURE) + memunmap((void __force *)spa_map->addr.aperture); + else + iounmap(spa_map->addr.base); release_mem_region(spa->address, spa->length); list_del(&spa_map->list); kfree(spa_map); @@ -1175,7 +1183,7 @@ static void __iomem *__nfit_spa_map(struct acpi_nfit_desc *acpi_desc, spa_map = find_spa_mapping(acpi_desc, spa); if (spa_map) { kref_get(&spa_map->kref); - return spa_map->iomem; + return spa_map->addr.base; } spa_map = kzalloc(sizeof(*spa_map), GFP_KERNEL); @@ -1191,20 +1199,19 @@ static void __iomem *__nfit_spa_map(struct acpi_nfit_desc *acpi_desc, if (!res) goto err_mem; - if (type == SPA_MAP_APERTURE) { - /* - * TODO: memremap_pmem() support, but that requires cache - * flushing when the aperture is moved. - */ - spa_map->iomem = ioremap_wc(start, n); - } else - spa_map->iomem = ioremap_nocache(start, n); + spa_map->type = type; + if (type == SPA_MAP_APERTURE) + spa_map->addr.aperture = (void __pmem *)memremap(start, n, + ARCH_MEMREMAP_PMEM); + else + spa_map->addr.base = ioremap_nocache(start, n); + - if (!spa_map->iomem) + if (!spa_map->addr.base) goto err_map; list_add_tail(&spa_map->list, &acpi_desc->spa_maps); - return spa_map->iomem; + return spa_map->addr.base; err_map: release_mem_region(start, n); @@ -1267,7 +1274,7 @@ static int acpi_nfit_blk_get_flags(struct nvdimm_bus_descriptor *nd_desc, nfit_blk->dimm_flags = flags.flags; else if (rc == -ENOTTY) { /* fall back to a conservative default */ - nfit_blk->dimm_flags = ND_BLK_DCR_LATCH; + nfit_blk->dimm_flags = ND_BLK_DCR_LATCH | ND_BLK_READ_FLUSH; rc = 0; } else rc = -ENXIO; @@ -1307,9 +1314,9 @@ static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus, /* map block aperture memory */ nfit_blk->bdw_offset = nfit_mem->bdw->offset; mmio = &nfit_blk->mmio[BDW]; - mmio->base = nfit_spa_map(acpi_desc, nfit_mem->spa_bdw, + mmio->addr.base = nfit_spa_map(acpi_desc, nfit_mem->spa_bdw, SPA_MAP_APERTURE); - if (!mmio->base) { + if (!mmio->addr.base) { dev_dbg(dev, "%s: %s failed to map bdw\n", __func__, nvdimm_name(nvdimm)); return -ENOMEM; @@ -1330,9 +1337,9 @@ static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus, nfit_blk->cmd_offset = nfit_mem->dcr->command_offset; nfit_blk->stat_offset = nfit_mem->dcr->status_offset; mmio = &nfit_blk->mmio[DCR]; - mmio->base = nfit_spa_map(acpi_desc, nfit_mem->spa_dcr, + mmio->addr.base = nfit_spa_map(acpi_desc, nfit_mem->spa_dcr, SPA_MAP_CONTROL); - if (!mmio->base) { + if (!mmio->addr.base) { dev_dbg(dev, "%s: %s failed to map dcr\n", __func__, nvdimm_name(nvdimm)); return -ENOMEM; @@ -1399,7 +1406,7 @@ static void acpi_nfit_blk_region_disable(struct nvdimm_bus *nvdimm_bus, for (i = 0; i < 2; i++) { struct nfit_blk_mmio *mmio = &nfit_blk->mmio[i]; - if (mmio->base) + if (mmio->addr.base) nfit_spa_unmap(acpi_desc, mmio->spa); } nd_blk_region_set_provider_data(ndbr, NULL); diff --git a/drivers/acpi/nfit.h b/drivers/acpi/nfit.h index f2c2bb751882..7e740156b9c2 100644 --- a/drivers/acpi/nfit.h +++ b/drivers/acpi/nfit.h @@ -41,6 +41,7 @@ enum nfit_uuids { }; enum { + ND_BLK_READ_FLUSH = 1, ND_BLK_DCR_LATCH = 2, }; @@ -117,12 +118,16 @@ enum nd_blk_mmio_selector { DCR, }; +struct nd_blk_addr { + union { + void __iomem *base; + void __pmem *aperture; + }; +}; + struct nfit_blk { struct nfit_blk_mmio { - union { - void __iomem *base; - void __pmem *aperture; - }; + struct nd_blk_addr addr; u64 size; u64 base_offset; u32 line_size; @@ -149,7 +154,8 @@ struct nfit_spa_mapping { struct acpi_nfit_system_address *spa; struct list_head list; struct kref kref; - void __iomem *iomem; + enum spa_map_type type; + struct nd_blk_addr addr; }; static inline struct nfit_spa_mapping *to_spa_map(struct kref *kref) -- cgit v1.2.3 From 96601adb745186ccbcf5b078d4756f13381ec2af Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 24 Aug 2015 18:29:38 -0400 Subject: x86, pmem: clarify that ARCH_HAS_PMEM_API implies PMEM mapped WB Given that a write-back (WB) mapping plus non-temporal stores is expected to be the most efficient way to access PMEM, update the definition of ARCH_HAS_PMEM_API to imply arch support for WB-mapped-PMEM. This is needed as a pre-requisite for adding PMEM to the direct map and mapping it with struct page. The above clarification for X86_64 means that memcpy_to_pmem() is permitted to use the non-temporal arch_memcpy_to_pmem() rather than needlessly fall back to default_memcpy_to_pmem() when the pcommit instruction is not available. When arch_memcpy_to_pmem() is not guaranteed to flush writes out of cache, i.e. on older X86_32 implementations where non-temporal stores may just dirty cache, ARCH_HAS_PMEM_API is simply disabled. The default fall back for persistent memory handling remains. Namely, map it with the WT (write-through) cache-type and hope for the best. arch_has_pmem_api() is updated to only indicate whether the arch provides the proper helpers to meet the minimum "writes are visible outside the cache hierarchy after memcpy_to_pmem() + wmb_pmem()". Code that cares whether wmb_pmem() actually flushes writes to pmem must now call arch_has_wmb_pmem() directly. Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Reviewed-by: Ross Zwisler [hch: set ARCH_HAS_PMEM_API=n on x86_32] Reviewed-by: Christoph Hellwig [toshi: x86_32 compile fixes] Signed-off-by: Toshi Kani Signed-off-by: Dan Williams --- drivers/acpi/nfit.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'drivers/acpi') diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c index 56fff0141636..f61e69fa2ad1 100644 --- a/drivers/acpi/nfit.c +++ b/drivers/acpi/nfit.c @@ -20,6 +20,7 @@ #include #include #include +#include #include "nfit.h" /* @@ -1371,7 +1372,7 @@ static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus, return -ENOMEM; } - if (!arch_has_pmem_api() && !nfit_blk->nvdimm_flush) + if (!arch_has_wmb_pmem() && !nfit_blk->nvdimm_flush) dev_warn(dev, "unable to guarantee persistence of writes\n"); if (mmio->line_size == 0) -- cgit v1.2.3