From e836a256e8fd579c9d7a3685f22981225a1ca451 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 12 Aug 2015 18:42:56 -0400 Subject: pmem: convert to generic memremap Kill arch_memremap_pmem() and just let the architecture specify the flags to be passed to memremap(). Default to writethrough by default. Suggested-by: Christoph Hellwig Reviewed-by: Christoph Hellwig Reviewed-by: Ross Zwisler Signed-off-by: Dan Williams --- tools/testing/nvdimm/Kbuild | 4 ++-- tools/testing/nvdimm/test/iomap.c | 34 +++++++++++++++++++++++++--------- 2 files changed, 27 insertions(+), 11 deletions(-) (limited to 'tools') diff --git a/tools/testing/nvdimm/Kbuild b/tools/testing/nvdimm/Kbuild index f56914c..8032a49 100644 --- a/tools/testing/nvdimm/Kbuild +++ b/tools/testing/nvdimm/Kbuild @@ -1,7 +1,7 @@ -ldflags-y += --wrap=ioremap_wt ldflags-y += --wrap=ioremap_wc ldflags-y += --wrap=devm_ioremap_nocache -ldflags-y += --wrap=ioremap_cache +ldflags-y += --wrap=memremap +ldflags-y += --wrap=memunmap ldflags-y += --wrap=ioremap_nocache ldflags-y += --wrap=iounmap ldflags-y += --wrap=__request_region diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c index 64bfaa5..21288f3 100644 --- a/tools/testing/nvdimm/test/iomap.c +++ b/tools/testing/nvdimm/test/iomap.c @@ -80,11 +80,20 @@ void __iomem *__wrap_devm_ioremap_nocache(struct device *dev, } EXPORT_SYMBOL(__wrap_devm_ioremap_nocache); -void __iomem *__wrap_ioremap_cache(resource_size_t offset, unsigned long size) +void *__wrap_memremap(resource_size_t offset, size_t size, + unsigned long flags) { - return __nfit_test_ioremap(offset, size, ioremap_cache); + struct nfit_test_resource *nfit_res; + + rcu_read_lock(); + nfit_res = get_nfit_res(offset); + rcu_read_unlock(); + if (nfit_res) + return (void __iomem *) nfit_res->buf + offset + - nfit_res->res->start; + return memremap(offset, size, flags); } -EXPORT_SYMBOL(__wrap_ioremap_cache); +EXPORT_SYMBOL(__wrap_memremap); void __iomem *__wrap_ioremap_nocache(resource_size_t offset, unsigned long size) { @@ -92,12 +101,6 @@ void __iomem *__wrap_ioremap_nocache(resource_size_t offset, unsigned long size) } EXPORT_SYMBOL(__wrap_ioremap_nocache); -void __iomem *__wrap_ioremap_wt(resource_size_t offset, unsigned long size) -{ - return __nfit_test_ioremap(offset, size, ioremap_wt); -} -EXPORT_SYMBOL(__wrap_ioremap_wt); - void __iomem *__wrap_ioremap_wc(resource_size_t offset, unsigned long size) { return __nfit_test_ioremap(offset, size, ioremap_wc); @@ -117,6 +120,19 @@ void __wrap_iounmap(volatile void __iomem *addr) } EXPORT_SYMBOL(__wrap_iounmap); +void __wrap_memunmap(void *addr) +{ + struct nfit_test_resource *nfit_res; + + rcu_read_lock(); + nfit_res = get_nfit_res((unsigned long) addr); + rcu_read_unlock(); + if (nfit_res) + return; + return memunmap(addr); +} +EXPORT_SYMBOL(__wrap_memunmap); + struct resource *__wrap___request_region(struct resource *parent, resource_size_t start, resource_size_t n, const char *name, int flags) -- cgit v1.1 From 708ab62bef1ed3a3cf065a4138bd87f5d083cfeb Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 10 Aug 2015 23:07:08 -0400 Subject: pmem: switch to devm_ allocations Signed-off-by: Christoph Hellwig [djbw: tools/testing/nvdimm/ and memunmap_pmem support] Reviewed-by: Ross Zwisler Signed-off-by: Dan Williams --- tools/testing/nvdimm/Kbuild | 4 ++-- tools/testing/nvdimm/test/iomap.c | 46 ++++++++++++++++++++++----------------- 2 files changed, 28 insertions(+), 22 deletions(-) (limited to 'tools') diff --git a/tools/testing/nvdimm/Kbuild b/tools/testing/nvdimm/Kbuild index 8032a49..04c5fc0 100644 --- a/tools/testing/nvdimm/Kbuild +++ b/tools/testing/nvdimm/Kbuild @@ -1,9 +1,9 @@ ldflags-y += --wrap=ioremap_wc ldflags-y += --wrap=devm_ioremap_nocache -ldflags-y += --wrap=memremap -ldflags-y += --wrap=memunmap +ldflags-y += --wrap=devm_memremap ldflags-y += --wrap=ioremap_nocache ldflags-y += --wrap=iounmap +ldflags-y += --wrap=__devm_request_region ldflags-y += --wrap=__request_region ldflags-y += --wrap=__release_region diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c index 21288f3..ff1e004 100644 --- a/tools/testing/nvdimm/test/iomap.c +++ b/tools/testing/nvdimm/test/iomap.c @@ -80,8 +80,8 @@ void __iomem *__wrap_devm_ioremap_nocache(struct device *dev, } EXPORT_SYMBOL(__wrap_devm_ioremap_nocache); -void *__wrap_memremap(resource_size_t offset, size_t size, - unsigned long flags) +void *__wrap_devm_memremap(struct device *dev, resource_size_t offset, + size_t size, unsigned long flags) { struct nfit_test_resource *nfit_res; @@ -91,9 +91,9 @@ void *__wrap_memremap(resource_size_t offset, size_t size, if (nfit_res) return (void __iomem *) nfit_res->buf + offset - nfit_res->res->start; - return memremap(offset, size, flags); + return devm_memremap(dev, offset, size, flags); } -EXPORT_SYMBOL(__wrap_memremap); +EXPORT_SYMBOL(__wrap_devm_memremap); void __iomem *__wrap_ioremap_nocache(resource_size_t offset, unsigned long size) { @@ -120,22 +120,9 @@ void __wrap_iounmap(volatile void __iomem *addr) } EXPORT_SYMBOL(__wrap_iounmap); -void __wrap_memunmap(void *addr) -{ - struct nfit_test_resource *nfit_res; - - rcu_read_lock(); - nfit_res = get_nfit_res((unsigned long) addr); - rcu_read_unlock(); - if (nfit_res) - return; - return memunmap(addr); -} -EXPORT_SYMBOL(__wrap_memunmap); - -struct resource *__wrap___request_region(struct resource *parent, - resource_size_t start, resource_size_t n, const char *name, - int flags) +static struct resource *nfit_test_request_region(struct device *dev, + struct resource *parent, resource_size_t start, + resource_size_t n, const char *name, int flags) { struct nfit_test_resource *nfit_res; @@ -163,10 +150,29 @@ struct resource *__wrap___request_region(struct resource *parent, return res; } } + if (dev) + return __devm_request_region(dev, parent, start, n, name); return __request_region(parent, start, n, name, flags); } + +struct resource *__wrap___request_region(struct resource *parent, + resource_size_t start, resource_size_t n, const char *name, + int flags) +{ + return nfit_test_request_region(NULL, parent, start, n, name, flags); +} EXPORT_SYMBOL(__wrap___request_region); +struct resource *__wrap___devm_request_region(struct device *dev, + struct resource *parent, resource_size_t start, + resource_size_t n, const char *name) +{ + if (!dev) + return NULL; + return nfit_test_request_region(dev, parent, start, n, name, 0); +} +EXPORT_SYMBOL(__wrap___devm_request_region); + void __wrap___release_region(struct resource *parent, resource_size_t start, resource_size_t n) { -- cgit v1.1 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 --- tools/testing/nvdimm/Kbuild | 2 ++ tools/testing/nvdimm/test/iomap.c | 30 ++++++++++++++++++++++++++++-- tools/testing/nvdimm/test/nfit.c | 10 +++++++--- 3 files changed, 37 insertions(+), 5 deletions(-) (limited to 'tools') diff --git a/tools/testing/nvdimm/Kbuild b/tools/testing/nvdimm/Kbuild index 04c5fc0..94a5e0e 100644 --- a/tools/testing/nvdimm/Kbuild +++ b/tools/testing/nvdimm/Kbuild @@ -1,8 +1,10 @@ ldflags-y += --wrap=ioremap_wc +ldflags-y += --wrap=memremap ldflags-y += --wrap=devm_ioremap_nocache ldflags-y += --wrap=devm_memremap ldflags-y += --wrap=ioremap_nocache ldflags-y += --wrap=iounmap +ldflags-y += --wrap=memunmap ldflags-y += --wrap=__devm_request_region ldflags-y += --wrap=__request_region ldflags-y += --wrap=__release_region diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c index ff1e004..179d228 100644 --- a/tools/testing/nvdimm/test/iomap.c +++ b/tools/testing/nvdimm/test/iomap.c @@ -89,12 +89,25 @@ void *__wrap_devm_memremap(struct device *dev, resource_size_t offset, nfit_res = get_nfit_res(offset); rcu_read_unlock(); if (nfit_res) - return (void __iomem *) nfit_res->buf + offset - - nfit_res->res->start; + return nfit_res->buf + offset - nfit_res->res->start; return devm_memremap(dev, offset, size, flags); } EXPORT_SYMBOL(__wrap_devm_memremap); +void *__wrap_memremap(resource_size_t offset, size_t size, + unsigned long flags) +{ + struct nfit_test_resource *nfit_res; + + rcu_read_lock(); + nfit_res = get_nfit_res(offset); + rcu_read_unlock(); + if (nfit_res) + return nfit_res->buf + offset - nfit_res->res->start; + return memremap(offset, size, flags); +} +EXPORT_SYMBOL(__wrap_memremap); + void __iomem *__wrap_ioremap_nocache(resource_size_t offset, unsigned long size) { return __nfit_test_ioremap(offset, size, ioremap_nocache); @@ -120,6 +133,19 @@ void __wrap_iounmap(volatile void __iomem *addr) } EXPORT_SYMBOL(__wrap_iounmap); +void __wrap_memunmap(void *addr) +{ + struct nfit_test_resource *nfit_res; + + rcu_read_lock(); + nfit_res = get_nfit_res((unsigned long) addr); + rcu_read_unlock(); + if (nfit_res) + return; + return memunmap(addr); +} +EXPORT_SYMBOL(__wrap_memunmap); + static struct resource *nfit_test_request_region(struct device *dev, struct resource *parent, resource_size_t start, resource_size_t n, const char *name, int flags) diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index 28dba91..021e6f9 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -1029,9 +1029,13 @@ static int nfit_test_blk_do_io(struct nd_blk_region *ndbr, resource_size_t dpa, lane = nd_region_acquire_lane(nd_region); if (rw) - memcpy(mmio->base + dpa, iobuf, len); - else - memcpy(iobuf, mmio->base + dpa, len); + memcpy(mmio->addr.base + dpa, iobuf, len); + else { + memcpy(iobuf, mmio->addr.base + dpa, len); + + /* give us some some coverage of the mmio_flush_range() API */ + mmio_flush_range(mmio->addr.base + dpa, len); + } nd_region_release_lane(nd_region, lane); return 0; -- cgit v1.1