From 69f58384791ac6da4165ce8e6defd6f408f4afdf Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Wed, 14 Dec 2016 15:04:16 -0800 Subject: Revert "kdump, vmcoreinfo: report memory sections virtual addresses" This reverts commit 0549a3c02efb ("kdump, vmcoreinfo: report memory sections virtual addresses"). Commit 0549a3c02efb tells the userspace utility makedumpfile the randomized base address of these memmory sections when mm kaslr is enabled. However the following patch "kexec: export the value of phys_base instead of symbol address" makes makedumpfile not need these addresses any more. Besides we should use VMCOREINFO_NUMBER to export the value of the variable so that we can use the existing number_table mechanism of Makedumpfile to fetch it. So revert it now. If needed we can add it later. http://lists.infradead.org/pipermail/kexec/2016-October/017540.html Link: http://lkml.kernel.org/r/1478568596-30060-1-git-send-email-bhe@redhat.com Signed-off-by: Baoquan He Cc: Thomas Garnier Cc: Baoquan He Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H . Peter Anvin" Cc: Eric Biederman Cc: Xunlei Pang Cc: HATAYAMA Daisuke Cc: Kees Cook Cc: Eugene Surovegin Cc: Dave Young Cc: AKASHI Takahiro Cc: Atsushi Kumagai Cc: Dave Anderson Cc: Pratyush Anand Cc: Vivek Goyal Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/kernel/machine_kexec_64.c | 3 --- 1 file changed, 3 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 8c1f218926d7..5a294e48b185 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -337,9 +337,6 @@ void arch_crash_save_vmcoreinfo(void) #endif vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset()); - VMCOREINFO_PAGE_OFFSET(PAGE_OFFSET); - VMCOREINFO_VMALLOC_START(VMALLOC_START); - VMCOREINFO_VMEMMAP_START(VMEMMAP_START); } /* arch-dependent functionality related to kexec file-based syscall */ -- cgit From 401721ecd1dcb0a428aa5d6832ee05ffbdbffbbe Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Wed, 14 Dec 2016 15:04:20 -0800 Subject: kexec: export the value of phys_base instead of symbol address Currently in x86_64, the symbol address of phys_base is exported to vmcoreinfo. Dave Anderson complained this is really useless for his Crash implementation. Because in user-space utility Crash and Makedumpfile which exported vmcore information is mainly used for, value of phys_base is needed to covert virtual address of exported kernel symbol to physical address. Especially init_level4_pgt, if we want to access and go over the page table to look up a PA corresponding to VA, firstly we need calculate page_dir = SYMBOL(init_level4_pgt) - __START_KERNEL_map + phys_base; Now in Crash and Makedumpfile, we have to analyze the vmcore elf program header to get value of phys_base. As Dave said, it would be preferable if it were readily availabl in vmcoreinfo rather than depending upon the PT_LOAD semantics. Hence in this patch change to export the value of phys_base instead of its virtual address. And people also complained that KERNEL_IMAGE_SIZE exporting is x86_64 only, should be moved into arch dependent function arch_crash_save_vmcoreinfo. Do the moving in this patch. Link: http://lkml.kernel.org/r/1478568596-30060-2-git-send-email-bhe@redhat.com Signed-off-by: Baoquan He Cc: Thomas Garnier Cc: Baoquan He Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H . Peter Anvin" Cc: Eric Biederman Cc: Xunlei Pang Cc: HATAYAMA Daisuke Cc: Kees Cook Cc: Eugene Surovegin Cc: Dave Young Cc: AKASHI Takahiro Cc: Atsushi Kumagai Cc: Dave Anderson Cc: Pratyush Anand Cc: Vivek Goyal Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/kernel/machine_kexec_64.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 5a294e48b185..307b1f4543de 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -328,7 +328,7 @@ void machine_kexec(struct kimage *image) void arch_crash_save_vmcoreinfo(void) { - VMCOREINFO_SYMBOL(phys_base); + VMCOREINFO_NUMBER(phys_base); VMCOREINFO_SYMBOL(init_level4_pgt); #ifdef CONFIG_NUMA @@ -337,6 +337,7 @@ void arch_crash_save_vmcoreinfo(void) #endif vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset()); + VMCOREINFO_NUMBER(KERNEL_IMAGE_SIZE); } /* arch-dependent functionality related to kexec file-based syscall */ -- cgit From 8a3385d2d47cd912f28d23bd2225ee37de518d86 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 14 Dec 2016 15:04:29 -0800 Subject: arch/arc: add option to skip sync on DMA mapping Patch series "Add support for DMA writable pages being writable by the network stack", v3. The first 19 patches in the set add support for the DMA attribute DMA_ATTR_SKIP_CPU_SYNC on multiple platforms/architectures. This is needed so that we can flag the calls to dma_map/unmap_page so that we do not invalidate cache lines that do not currently belong to the device. Instead we have to take care of this in the driver via a call to sync_single_range_for_cpu prior to freeing the Rx page. Patch 20 adds support for dma_map_page_attrs and dma_unmap_page_attrs so that we can unmap and map a page using the DMA_ATTR_SKIP_CPU_SYNC attribute. Patch 21 adds support for freeing a page that has multiple references being held by a single caller. This way we can free page fragments that were allocated by a given driver. The last 2 patches use these updates in the igb driver, and lay the groundwork to allow for us to reimplement the use of build_skb. This patch (of 23): This change allows us to pass DMA_ATTR_SKIP_CPU_SYNC which allows us to avoid invoking cache line invalidation if the driver will just handle it later via a sync_for_cpu or sync_for_device call. Link: http://lkml.kernel.org/r/20161110113419.76501.38491.stgit@ahduyck-blue-test.jf.intel.com Signed-off-by: Alexander Duyck Acked-by: Vineet Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arc/mm/dma.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c index cd8aad8226dd..08450a1a5b5f 100644 --- a/arch/arc/mm/dma.c +++ b/arch/arc/mm/dma.c @@ -158,7 +158,10 @@ static dma_addr_t arc_dma_map_page(struct device *dev, struct page *page, unsigned long attrs) { phys_addr_t paddr = page_to_phys(page) + offset; - _dma_cache_sync(paddr, size, dir); + + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + _dma_cache_sync(paddr, size, dir); + return plat_phys_to_dma(dev, paddr); } -- cgit From fc1b138de7917d8fda5995aeecdb10c8182d9f75 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 14 Dec 2016 15:04:32 -0800 Subject: arch/arm: add option to skip sync on DMA map and unmap The use of DMA_ATTR_SKIP_CPU_SYNC was not consistent across all of the DMA APIs in the arch/arm folder. This change is meant to correct that so that we get consistent behavior. Link: http://lkml.kernel.org/r/20161110113424.76501.2715.stgit@ahduyck-blue-test.jf.intel.com Signed-off-by: Alexander Duyck Cc: Russell King Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/common/dmabounce.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) (limited to 'arch') diff --git a/arch/arm/common/dmabounce.c b/arch/arm/common/dmabounce.c index 301281645d08..75055df1cda3 100644 --- a/arch/arm/common/dmabounce.c +++ b/arch/arm/common/dmabounce.c @@ -243,7 +243,8 @@ static int needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t size) } static inline dma_addr_t map_single(struct device *dev, void *ptr, size_t size, - enum dma_data_direction dir) + enum dma_data_direction dir, + unsigned long attrs) { struct dmabounce_device_info *device_info = dev->archdata.dmabounce; struct safe_buffer *buf; @@ -262,7 +263,8 @@ static inline dma_addr_t map_single(struct device *dev, void *ptr, size_t size, __func__, buf->ptr, virt_to_dma(dev, buf->ptr), buf->safe, buf->safe_dma_addr); - if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) { + if ((dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) && + !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) { dev_dbg(dev, "%s: copy unsafe %p to safe %p, size %d\n", __func__, ptr, buf->safe, size); memcpy(buf->safe, ptr, size); @@ -272,7 +274,8 @@ static inline dma_addr_t map_single(struct device *dev, void *ptr, size_t size, } static inline void unmap_single(struct device *dev, struct safe_buffer *buf, - size_t size, enum dma_data_direction dir) + size_t size, enum dma_data_direction dir, + unsigned long attrs) { BUG_ON(buf->size != size); BUG_ON(buf->direction != dir); @@ -283,7 +286,8 @@ static inline void unmap_single(struct device *dev, struct safe_buffer *buf, DO_STATS(dev->archdata.dmabounce->bounce_count++); - if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL) { + if ((dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL) && + !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) { void *ptr = buf->ptr; dev_dbg(dev, "%s: copy back safe %p to unsafe %p size %d\n", @@ -334,7 +338,7 @@ static dma_addr_t dmabounce_map_page(struct device *dev, struct page *page, return DMA_ERROR_CODE; } - return map_single(dev, page_address(page) + offset, size, dir); + return map_single(dev, page_address(page) + offset, size, dir, attrs); } /* @@ -357,7 +361,7 @@ static void dmabounce_unmap_page(struct device *dev, dma_addr_t dma_addr, size_t return; } - unmap_single(dev, buf, size, dir); + unmap_single(dev, buf, size, dir, attrs); } static int __dmabounce_sync_for_cpu(struct device *dev, dma_addr_t addr, -- cgit From e8b4762c22589a514add9bf9dda7a3050e4fa54c Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 14 Dec 2016 15:04:35 -0800 Subject: arch/avr32: add option to skip sync on DMA map The use of DMA_ATTR_SKIP_CPU_SYNC was not consistent across all of the DMA APIs in the arch/arm folder. This change is meant to correct that so that we get consistent behavior. Link: http://lkml.kernel.org/r/20161110113430.76501.79737.stgit@ahduyck-blue-test.jf.intel.com Signed-off-by: Alexander Duyck Acked-by: Hans-Christian Noren Egtvedt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/avr32/mm/dma-coherent.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/avr32/mm/dma-coherent.c b/arch/avr32/mm/dma-coherent.c index 58610d0df7ed..54534e5d0781 100644 --- a/arch/avr32/mm/dma-coherent.c +++ b/arch/avr32/mm/dma-coherent.c @@ -146,7 +146,8 @@ static dma_addr_t avr32_dma_map_page(struct device *dev, struct page *page, { void *cpu_addr = page_address(page) + offset; - dma_cache_sync(dev, cpu_addr, size, direction); + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + dma_cache_sync(dev, cpu_addr, size, direction); return virt_to_bus(cpu_addr); } @@ -162,6 +163,10 @@ static int avr32_dma_map_sg(struct device *dev, struct scatterlist *sglist, sg->dma_address = page_to_bus(sg_page(sg)) + sg->offset; virt = sg_virt(sg); + + if (attrs & DMA_ATTR_SKIP_CPU_SYNC) + continue; + dma_cache_sync(dev, virt, sg->length, direction); } -- cgit From 8c16a2e209d563a1909451c769417a6f953e5b2c Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 14 Dec 2016 15:04:38 -0800 Subject: arch/blackfin: add option to skip sync on DMA map The use of DMA_ATTR_SKIP_CPU_SYNC was not consistent across all of the DMA APIs in the arch/arm folder. This change is meant to correct that so that we get consistent behavior. Link: http://lkml.kernel.org/r/20161110113436.76501.13386.stgit@ahduyck-blue-test.jf.intel.com Signed-off-by: Alexander Duyck Cc: Steven Miao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/blackfin/kernel/dma-mapping.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/blackfin/kernel/dma-mapping.c b/arch/blackfin/kernel/dma-mapping.c index 53fbbb61aa86..a27a74a18fb0 100644 --- a/arch/blackfin/kernel/dma-mapping.c +++ b/arch/blackfin/kernel/dma-mapping.c @@ -118,6 +118,10 @@ static int bfin_dma_map_sg(struct device *dev, struct scatterlist *sg_list, for_each_sg(sg_list, sg, nents, i) { sg->dma_address = (dma_addr_t) sg_virt(sg); + + if (attrs & DMA_ATTR_SKIP_CPU_SYNC) + continue; + __dma_sync(sg_dma_address(sg), sg_dma_len(sg), direction); } @@ -143,7 +147,9 @@ static dma_addr_t bfin_dma_map_page(struct device *dev, struct page *page, { dma_addr_t handle = (dma_addr_t)(page_address(page) + offset); - _dma_sync(handle, size, dir); + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + _dma_sync(handle, size, dir); + return handle; } -- cgit From 64c596b59c726514f548e15f13a87010efbff40d Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 14 Dec 2016 15:04:41 -0800 Subject: arch/c6x: add option to skip sync on DMA map and unmap This change allows us to pass DMA_ATTR_SKIP_CPU_SYNC which allows us to avoid invoking cache line invalidation if the driver will just handle it later via a sync_for_cpu or sync_for_device call. Link: http://lkml.kernel.org/r/20161110113442.76501.7673.stgit@ahduyck-blue-test.jf.intel.com Signed-off-by: Alexander Duyck Acked-by: Mark Salter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/c6x/kernel/dma.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/c6x/kernel/dma.c b/arch/c6x/kernel/dma.c index db4a6a301f5e..6752df32ef06 100644 --- a/arch/c6x/kernel/dma.c +++ b/arch/c6x/kernel/dma.c @@ -42,14 +42,17 @@ static dma_addr_t c6x_dma_map_page(struct device *dev, struct page *page, { dma_addr_t handle = virt_to_phys(page_address(page) + offset); - c6x_dma_sync(handle, size, dir); + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + c6x_dma_sync(handle, size, dir); + return handle; } static void c6x_dma_unmap_page(struct device *dev, dma_addr_t handle, size_t size, enum dma_data_direction dir, unsigned long attrs) { - c6x_dma_sync(handle, size, dir); + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + c6x_dma_sync(handle, size, dir); } static int c6x_dma_map_sg(struct device *dev, struct scatterlist *sglist, @@ -60,7 +63,8 @@ static int c6x_dma_map_sg(struct device *dev, struct scatterlist *sglist, for_each_sg(sglist, sg, nents, i) { sg->dma_address = sg_phys(sg); - c6x_dma_sync(sg->dma_address, sg->length, dir); + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + c6x_dma_sync(sg->dma_address, sg->length, dir); } return nents; @@ -72,9 +76,11 @@ static void c6x_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, struct scatterlist *sg; int i; + if (attrs & DMA_ATTR_SKIP_CPU_SYNC) + return; + for_each_sg(sglist, sg, nents, i) c6x_dma_sync(sg_dma_address(sg), sg->length, dir); - } static void c6x_dma_sync_single_for_cpu(struct device *dev, dma_addr_t handle, -- cgit From 34f8be79a772094a96da83f52f247cff2bc13978 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 14 Dec 2016 15:04:43 -0800 Subject: arch/frv: add option to skip sync on DMA map The use of DMA_ATTR_SKIP_CPU_SYNC was not consistent across all of the DMA APIs in the arch/arm folder. This change is meant to correct that so that we get consistent behavior. Link: http://lkml.kernel.org/r/20161110113447.76501.93160.stgit@ahduyck-blue-test.jf.intel.com Signed-off-by: Alexander Duyck Cc: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/frv/mb93090-mb00/pci-dma-nommu.c | 14 ++++++++++---- arch/frv/mb93090-mb00/pci-dma.c | 9 +++++++-- 2 files changed, 17 insertions(+), 6 deletions(-) (limited to 'arch') diff --git a/arch/frv/mb93090-mb00/pci-dma-nommu.c b/arch/frv/mb93090-mb00/pci-dma-nommu.c index 90f2e4cb33d6..187688128c65 100644 --- a/arch/frv/mb93090-mb00/pci-dma-nommu.c +++ b/arch/frv/mb93090-mb00/pci-dma-nommu.c @@ -109,16 +109,19 @@ static int frv_dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction, unsigned long attrs) { - int i; struct scatterlist *sg; + int i; + + BUG_ON(direction == DMA_NONE); + + if (attrs & DMA_ATTR_SKIP_CPU_SYNC) + return nents; for_each_sg(sglist, sg, nents, i) { frv_cache_wback_inv(sg_dma_address(sg), sg_dma_address(sg) + sg_dma_len(sg)); } - BUG_ON(direction == DMA_NONE); - return nents; } @@ -127,7 +130,10 @@ static dma_addr_t frv_dma_map_page(struct device *dev, struct page *page, enum dma_data_direction direction, unsigned long attrs) { BUG_ON(direction == DMA_NONE); - flush_dcache_page(page); + + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + flush_dcache_page(page); + return (dma_addr_t) page_to_phys(page) + offset; } diff --git a/arch/frv/mb93090-mb00/pci-dma.c b/arch/frv/mb93090-mb00/pci-dma.c index f585745b1abc..dba7df918144 100644 --- a/arch/frv/mb93090-mb00/pci-dma.c +++ b/arch/frv/mb93090-mb00/pci-dma.c @@ -40,13 +40,16 @@ static int frv_dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction, unsigned long attrs) { + struct scatterlist *sg; unsigned long dampr2; void *vaddr; int i; - struct scatterlist *sg; BUG_ON(direction == DMA_NONE); + if (attrs & DMA_ATTR_SKIP_CPU_SYNC) + return nents; + dampr2 = __get_DAMPR(2); for_each_sg(sglist, sg, nents, i) { @@ -70,7 +73,9 @@ static dma_addr_t frv_dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction direction, unsigned long attrs) { - flush_dcache_page(page); + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + flush_dcache_page(page); + return (dma_addr_t) page_to_phys(page) + offset; } -- cgit From b8a346dd472af45e1ee8cbc77101dad0b836210b Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 14 Dec 2016 15:04:46 -0800 Subject: arch/hexagon: Add option to skip DMA sync as a part of mapping This change allows us to pass DMA_ATTR_SKIP_CPU_SYNC which allows us to avoid invoking cache line invalidation if the driver will just handle it later via a sync_for_cpu or sync_for_device call. Link: http://lkml.kernel.org/r/20161110113452.76501.45864.stgit@ahduyck-blue-test.jf.intel.com Signed-off-by: Alexander Duyck Cc: Richard Kuo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/hexagon/kernel/dma.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/hexagon/kernel/dma.c b/arch/hexagon/kernel/dma.c index b9017785fb71..dbc4f1003da4 100644 --- a/arch/hexagon/kernel/dma.c +++ b/arch/hexagon/kernel/dma.c @@ -119,6 +119,9 @@ static int hexagon_map_sg(struct device *hwdev, struct scatterlist *sg, s->dma_length = s->length; + if (attrs & DMA_ATTR_SKIP_CPU_SYNC) + continue; + flush_dcache_range(dma_addr_to_virt(s->dma_address), dma_addr_to_virt(s->dma_address + s->length)); } @@ -180,7 +183,8 @@ static dma_addr_t hexagon_map_page(struct device *dev, struct page *page, if (!check_addr("map_single", dev, bus, size)) return bad_dma_address; - dma_sync(dma_addr_to_virt(bus), size, dir); + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + dma_sync(dma_addr_to_virt(bus), size, dir); return bus; } -- cgit From 5140d2344f1036dadffbb949a60af971b6dde0d3 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 14 Dec 2016 15:04:49 -0800 Subject: arch/m68k: add option to skip DMA sync as a part of mapping This change allows us to pass DMA_ATTR_SKIP_CPU_SYNC which allows us to avoid invoking cache line invalidation if the driver will just handle it later via a sync_for_cpu or sync_for_device call. Link: http://lkml.kernel.org/r/20161110113457.76501.77603.stgit@ahduyck-blue-test.jf.intel.com Signed-off-by: Alexander Duyck Cc: Geert Uytterhoeven Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/m68k/kernel/dma.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/m68k/kernel/dma.c b/arch/m68k/kernel/dma.c index 8cf97cbadc91..07070065a425 100644 --- a/arch/m68k/kernel/dma.c +++ b/arch/m68k/kernel/dma.c @@ -134,7 +134,9 @@ static dma_addr_t m68k_dma_map_page(struct device *dev, struct page *page, { dma_addr_t handle = page_to_phys(page) + offset; - dma_sync_single_for_device(dev, handle, size, dir); + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + dma_sync_single_for_device(dev, handle, size, dir); + return handle; } @@ -146,6 +148,10 @@ static int m68k_dma_map_sg(struct device *dev, struct scatterlist *sglist, for_each_sg(sglist, sg, nents, i) { sg->dma_address = sg_phys(sg); + + if (attrs & DMA_ATTR_SKIP_CPU_SYNC) + continue; + dma_sync_single_for_device(dev, sg->dma_address, sg->length, dir); } -- cgit From 38bdbdc7e391f5326a9f27f0bc8be0c175a73567 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 14 Dec 2016 15:04:52 -0800 Subject: arch/metag: add option to skip DMA sync as a part of map and unmap This change allows us to pass DMA_ATTR_SKIP_CPU_SYNC which allows us to avoid invoking cache line invalidation if the driver will just handle it via a sync_for_cpu or sync_for_device call. Link: http://lkml.kernel.org/r/20161110113503.76501.80809.stgit@ahduyck-blue-test.jf.intel.com Signed-off-by: Alexander Duyck Cc: James Hogan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/metag/kernel/dma.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/metag/kernel/dma.c b/arch/metag/kernel/dma.c index 0db31e24c541..91968d92652b 100644 --- a/arch/metag/kernel/dma.c +++ b/arch/metag/kernel/dma.c @@ -484,8 +484,9 @@ static dma_addr_t metag_dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction direction, unsigned long attrs) { - dma_sync_for_device((void *)(page_to_phys(page) + offset), size, - direction); + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + dma_sync_for_device((void *)(page_to_phys(page) + offset), + size, direction); return page_to_phys(page) + offset; } @@ -493,7 +494,8 @@ static void metag_dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size, enum dma_data_direction direction, unsigned long attrs) { - dma_sync_for_cpu(phys_to_virt(dma_address), size, direction); + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + dma_sync_for_cpu(phys_to_virt(dma_address), size, direction); } static int metag_dma_map_sg(struct device *dev, struct scatterlist *sglist, @@ -507,6 +509,10 @@ static int metag_dma_map_sg(struct device *dev, struct scatterlist *sglist, BUG_ON(!sg_page(sg)); sg->dma_address = sg_phys(sg); + + if (attrs & DMA_ATTR_SKIP_CPU_SYNC) + continue; + dma_sync_for_device(sg_virt(sg), sg->length, direction); } @@ -525,6 +531,10 @@ static void metag_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, BUG_ON(!sg_page(sg)); sg->dma_address = sg_phys(sg); + + if (attrs & DMA_ATTR_SKIP_CPU_SYNC) + continue; + dma_sync_for_cpu(sg_virt(sg), sg->length, direction); } } -- cgit From 98ac2fc274e07a22bea43682cf8998f47ffea9d0 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 14 Dec 2016 15:04:55 -0800 Subject: arch/microblaze: add option to skip DMA sync as a part of map and unmap This change allows us to pass DMA_ATTR_SKIP_CPU_SYNC which allows us to avoid invoking cache line invalidation if the driver will just handle it via a sync_for_cpu or sync_for_device call. Link: http://lkml.kernel.org/r/20161110113508.76501.77583.stgit@ahduyck-blue-test.jf.intel.com Signed-off-by: Alexander Duyck Cc: Michal Simek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/microblaze/kernel/dma.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c index ec04dc1e2527..818daf230eb4 100644 --- a/arch/microblaze/kernel/dma.c +++ b/arch/microblaze/kernel/dma.c @@ -61,6 +61,10 @@ static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, /* FIXME this part of code is untested */ for_each_sg(sgl, sg, nents, i) { sg->dma_address = sg_phys(sg); + + if (attrs & DMA_ATTR_SKIP_CPU_SYNC) + continue; + __dma_sync(page_to_phys(sg_page(sg)) + sg->offset, sg->length, direction); } @@ -80,7 +84,8 @@ static inline dma_addr_t dma_direct_map_page(struct device *dev, enum dma_data_direction direction, unsigned long attrs) { - __dma_sync(page_to_phys(page) + offset, size, direction); + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + __dma_sync(page_to_phys(page) + offset, size, direction); return page_to_phys(page) + offset; } @@ -95,7 +100,8 @@ static inline void dma_direct_unmap_page(struct device *dev, * phys_to_virt is here because in __dma_sync_page is __virt_to_phys and * dma_address is physical address */ - __dma_sync(dma_address, size, direction); + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + __dma_sync(dma_address, size, direction); } static inline void -- cgit From 9f318d470e37a470d65449f94a06165ea72dbce1 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 14 Dec 2016 15:04:58 -0800 Subject: arch/mips: add option to skip DMA sync as a part of map and unmap This change allows us to pass DMA_ATTR_SKIP_CPU_SYNC which allows us to avoid invoking cache line invalidation if the driver will just handle it via a sync_for_cpu or sync_for_device call. Link: http://lkml.kernel.org/r/20161110113513.76501.32321.stgit@ahduyck-blue-test.jf.intel.com Signed-off-by: Alexander Duyck Cc: Ralf Baechle Cc: Keguang Zhang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/mips/loongson64/common/dma-swiotlb.c | 2 +- arch/mips/mm/dma-default.c | 8 +++++--- 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/mips/loongson64/common/dma-swiotlb.c b/arch/mips/loongson64/common/dma-swiotlb.c index 1a80b6f73ab2..aab4fd681e1f 100644 --- a/arch/mips/loongson64/common/dma-swiotlb.c +++ b/arch/mips/loongson64/common/dma-swiotlb.c @@ -61,7 +61,7 @@ static int loongson_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir, unsigned long attrs) { - int r = swiotlb_map_sg_attrs(dev, sg, nents, dir, 0); + int r = swiotlb_map_sg_attrs(dev, sg, nents, dir, attrs); mb(); return r; diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c index 46d5696c4f27..a39c36af97ad 100644 --- a/arch/mips/mm/dma-default.c +++ b/arch/mips/mm/dma-default.c @@ -293,7 +293,7 @@ static inline void __dma_sync(struct page *page, static void mips_dma_unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size, enum dma_data_direction direction, unsigned long attrs) { - if (cpu_needs_post_dma_flush(dev)) + if (cpu_needs_post_dma_flush(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) __dma_sync(dma_addr_to_page(dev, dma_addr), dma_addr & ~PAGE_MASK, size, direction); plat_post_dma_flush(dev); @@ -307,7 +307,8 @@ static int mips_dma_map_sg(struct device *dev, struct scatterlist *sglist, struct scatterlist *sg; for_each_sg(sglist, sg, nents, i) { - if (!plat_device_is_coherent(dev)) + if (!plat_device_is_coherent(dev) && + !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) __dma_sync(sg_page(sg), sg->offset, sg->length, direction); #ifdef CONFIG_NEED_SG_DMA_LENGTH @@ -324,7 +325,7 @@ static dma_addr_t mips_dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction direction, unsigned long attrs) { - if (!plat_device_is_coherent(dev)) + if (!plat_device_is_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) __dma_sync(page, offset, size, direction); return plat_map_dma_mem_page(dev, page) + offset; @@ -339,6 +340,7 @@ static void mips_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, for_each_sg(sglist, sg, nhwentries, i) { if (!plat_device_is_coherent(dev) && + !(attrs & DMA_ATTR_SKIP_CPU_SYNC) && direction != DMA_TO_DEVICE) __dma_sync(sg_page(sg), sg->offset, sg->length, direction); -- cgit From abdf4799dac6210e3d09d368c4ed19e984c45dce Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 14 Dec 2016 15:05:00 -0800 Subject: arch/nios2: add option to skip DMA sync as a part of map and unmap This change allows us to pass DMA_ATTR_SKIP_CPU_SYNC which allows us to avoid invoking cache line invalidation if the driver will just handle it via a sync_for_cpu or sync_for_device call. Link: http://lkml.kernel.org/r/20161110113518.76501.52225.stgit@ahduyck-blue-test.jf.intel.com Signed-off-by: Alexander Duyck Reviewed-by: Tobias Klauser Cc: Ley Foon Tan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/nios2/mm/dma-mapping.c | 26 ++++++++++++++++++-------- 1 file changed, 18 insertions(+), 8 deletions(-) (limited to 'arch') diff --git a/arch/nios2/mm/dma-mapping.c b/arch/nios2/mm/dma-mapping.c index d800fad87896..f6a5dcf9d682 100644 --- a/arch/nios2/mm/dma-mapping.c +++ b/arch/nios2/mm/dma-mapping.c @@ -98,13 +98,17 @@ static int nios2_dma_map_sg(struct device *dev, struct scatterlist *sg, int i; for_each_sg(sg, sg, nents, i) { - void *addr; + void *addr = sg_virt(sg); - addr = sg_virt(sg); - if (addr) { - __dma_sync_for_device(addr, sg->length, direction); - sg->dma_address = sg_phys(sg); - } + if (!addr) + continue; + + sg->dma_address = sg_phys(sg); + + if (attrs & DMA_ATTR_SKIP_CPU_SYNC) + continue; + + __dma_sync_for_device(addr, sg->length, direction); } return nents; @@ -117,7 +121,9 @@ static dma_addr_t nios2_dma_map_page(struct device *dev, struct page *page, { void *addr = page_address(page) + offset; - __dma_sync_for_device(addr, size, direction); + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + __dma_sync_for_device(addr, size, direction); + return page_to_phys(page) + offset; } @@ -125,7 +131,8 @@ static void nios2_dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size, enum dma_data_direction direction, unsigned long attrs) { - __dma_sync_for_cpu(phys_to_virt(dma_address), size, direction); + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + __dma_sync_for_cpu(phys_to_virt(dma_address), size, direction); } static void nios2_dma_unmap_sg(struct device *dev, struct scatterlist *sg, @@ -138,6 +145,9 @@ static void nios2_dma_unmap_sg(struct device *dev, struct scatterlist *sg, if (direction == DMA_TO_DEVICE) return; + if (attrs & DMA_ATTR_SKIP_CPU_SYNC) + return; + for_each_sg(sg, sg, nhwentries, i) { addr = sg_virt(sg); if (addr) -- cgit From 043b42bcbbc6bc87c457b156041d74d51f6cebc2 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 14 Dec 2016 15:05:03 -0800 Subject: arch/openrisc: add option to skip DMA sync as a part of mapping This change allows us to pass DMA_ATTR_SKIP_CPU_SYNC which allows us to avoid invoking cache line invalidation if the driver will just handle it via a sync_for_cpu or sync_for_device call. Link: http://lkml.kernel.org/r/20161110113524.76501.87966.stgit@ahduyck-blue-test.jf.intel.com Signed-off-by: Alexander Duyck Cc: Jonas Bonn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/openrisc/kernel/dma.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch') diff --git a/arch/openrisc/kernel/dma.c b/arch/openrisc/kernel/dma.c index 140c99140649..906998bac957 100644 --- a/arch/openrisc/kernel/dma.c +++ b/arch/openrisc/kernel/dma.c @@ -141,6 +141,9 @@ or1k_map_page(struct device *dev, struct page *page, unsigned long cl; dma_addr_t addr = page_to_phys(page) + offset; + if (attrs & DMA_ATTR_SKIP_CPU_SYNC) + return addr; + switch (dir) { case DMA_TO_DEVICE: /* Flush the dcache for the requested range */ -- cgit From f50a2bd298b47e1957f67f794aed90f2c3bd9a10 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 14 Dec 2016 15:05:06 -0800 Subject: arch/parisc: add option to skip DMA sync as a part of map and unmap This change allows us to pass DMA_ATTR_SKIP_CPU_SYNC which allows us to avoid invoking cache line invalidation if the driver will just handle it via a sync_for_cpu or sync_for_device call. Link: http://lkml.kernel.org/r/20161110113529.76501.44762.stgit@ahduyck-blue-test.jf.intel.com Signed-off-by: Alexander Duyck Cc: "James E.J. Bottomley" Cc: Helge Deller Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/parisc/kernel/pci-dma.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) (limited to 'arch') diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c index 494ff6e8c88a..b6298a85e8ae 100644 --- a/arch/parisc/kernel/pci-dma.c +++ b/arch/parisc/kernel/pci-dma.c @@ -459,7 +459,9 @@ static dma_addr_t pa11_dma_map_page(struct device *dev, struct page *page, void *addr = page_address(page) + offset; BUG_ON(direction == DMA_NONE); - flush_kernel_dcache_range((unsigned long) addr, size); + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + flush_kernel_dcache_range((unsigned long) addr, size); + return virt_to_phys(addr); } @@ -469,8 +471,11 @@ static void pa11_dma_unmap_page(struct device *dev, dma_addr_t dma_handle, { BUG_ON(direction == DMA_NONE); + if (attrs & DMA_ATTR_SKIP_CPU_SYNC) + return; + if (direction == DMA_TO_DEVICE) - return; + return; /* * For PCI_DMA_FROMDEVICE this flush is not necessary for the @@ -479,7 +484,6 @@ static void pa11_dma_unmap_page(struct device *dev, dma_addr_t dma_handle, */ flush_kernel_dcache_range((unsigned long) phys_to_virt(dma_handle), size); - return; } static int pa11_dma_map_sg(struct device *dev, struct scatterlist *sglist, @@ -496,6 +500,10 @@ static int pa11_dma_map_sg(struct device *dev, struct scatterlist *sglist, sg_dma_address(sg) = (dma_addr_t) virt_to_phys(vaddr); sg_dma_len(sg) = sg->length; + + if (attrs & DMA_ATTR_SKIP_CPU_SYNC) + continue; + flush_kernel_dcache_range(vaddr, sg->length); } return nents; @@ -510,14 +518,16 @@ static void pa11_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, BUG_ON(direction == DMA_NONE); + if (attrs & DMA_ATTR_SKIP_CPU_SYNC) + return; + if (direction == DMA_TO_DEVICE) - return; + return; /* once we do combining we'll need to use phys_to_virt(sg_dma_address(sglist)) */ for_each_sg(sglist, sg, nents, i) flush_kernel_vmap_range(sg_virt(sg), sg->length); - return; } static void pa11_dma_sync_single_for_cpu(struct device *dev, -- cgit From 6f774809612d1f1fc800b452ee1ef447a277ec9d Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 14 Dec 2016 15:05:09 -0800 Subject: arch/powerpc: add option to skip DMA sync as a part of mapping This change allows us to pass DMA_ATTR_SKIP_CPU_SYNC which allows us to avoid invoking cache line invalidation if the driver will just handle it via a sync_for_cpu or sync_for_device call. Link: http://lkml.kernel.org/r/20161110113534.76501.86492.stgit@ahduyck-blue-test.jf.intel.com Signed-off-by: Alexander Duyck Acked-by: Michael Ellerman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/kernel/dma.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c index e64a6016fba7..6877e3fa95bb 100644 --- a/arch/powerpc/kernel/dma.c +++ b/arch/powerpc/kernel/dma.c @@ -203,6 +203,10 @@ static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, for_each_sg(sgl, sg, nents, i) { sg->dma_address = sg_phys(sg) + get_dma_offset(dev); sg->dma_length = sg->length; + + if (attrs & DMA_ATTR_SKIP_CPU_SYNC) + continue; + __dma_sync_page(sg_page(sg), sg->offset, sg->length, direction); } @@ -235,7 +239,10 @@ static inline dma_addr_t dma_direct_map_page(struct device *dev, unsigned long attrs) { BUG_ON(dir == DMA_NONE); - __dma_sync_page(page, offset, size, dir); + + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + __dma_sync_page(page, offset, size, dir); + return page_to_phys(page) + offset + get_dma_offset(dev); } -- cgit From a08120017d7d659719d446fb036d500fa9b1e6f9 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 14 Dec 2016 15:05:12 -0800 Subject: arch/sh: add option to skip DMA sync as a part of mapping This change allows us to pass DMA_ATTR_SKIP_CPU_SYNC which allows us to avoid invoking cache line invalidation if the driver will just handle it via a sync_for_cpu or sync_for_device call. Link: http://lkml.kernel.org/r/20161110113539.76501.6539.stgit@ahduyck-blue-test.jf.intel.com Signed-off-by: Alexander Duyck Cc: Yoshinori Sato Cc: Rich Felker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/sh/kernel/dma-nommu.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/sh/kernel/dma-nommu.c b/arch/sh/kernel/dma-nommu.c index eadb669a7329..47fee3b6e29c 100644 --- a/arch/sh/kernel/dma-nommu.c +++ b/arch/sh/kernel/dma-nommu.c @@ -18,7 +18,9 @@ static dma_addr_t nommu_map_page(struct device *dev, struct page *page, dma_addr_t addr = page_to_phys(page) + offset; WARN_ON(size == 0); - dma_cache_sync(dev, page_address(page) + offset, size, dir); + + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + dma_cache_sync(dev, page_address(page) + offset, size, dir); return addr; } @@ -35,7 +37,8 @@ static int nommu_map_sg(struct device *dev, struct scatterlist *sg, for_each_sg(sg, s, nents, i) { BUG_ON(!sg_page(s)); - dma_cache_sync(dev, sg_virt(s), s->length, dir); + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + dma_cache_sync(dev, sg_virt(s), s->length, dir); s->dma_address = sg_phys(s); s->dma_length = s->length; -- cgit From 68bbc28f616c18b695a13e59adefb9a1fc0c46a0 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 14 Dec 2016 15:05:15 -0800 Subject: arch/sparc: add option to skip DMA sync as a part of map and unmap This change allows us to pass DMA_ATTR_SKIP_CPU_SYNC which allows us to avoid invoking cache line invalidation if the driver will just handle it via a sync_for_cpu or sync_for_device call. Link: http://lkml.kernel.org/r/20161110113544.76501.40008.stgit@ahduyck-blue-test.jf.intel.com Signed-off-by: Alexander Duyck Cc: "David S. Miller" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/sparc/kernel/iommu.c | 4 ++-- arch/sparc/kernel/ioport.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c index 852a3291db96..9df997995f6b 100644 --- a/arch/sparc/kernel/iommu.c +++ b/arch/sparc/kernel/iommu.c @@ -415,7 +415,7 @@ static void dma_4u_unmap_page(struct device *dev, dma_addr_t bus_addr, ctx = (iopte_val(*base) & IOPTE_CONTEXT) >> 47UL; /* Step 1: Kick data out of streaming buffers if necessary. */ - if (strbuf->strbuf_enabled) + if (strbuf->strbuf_enabled && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) strbuf_flush(strbuf, iommu, bus_addr, ctx, npages, direction); @@ -640,7 +640,7 @@ static void dma_4u_unmap_sg(struct device *dev, struct scatterlist *sglist, base = iommu->page_table + entry; dma_handle &= IO_PAGE_MASK; - if (strbuf->strbuf_enabled) + if (strbuf->strbuf_enabled && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) strbuf_flush(strbuf, iommu, dma_handle, ctx, npages, direction); diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c index 2344103414d1..6ffaec44931a 100644 --- a/arch/sparc/kernel/ioport.c +++ b/arch/sparc/kernel/ioport.c @@ -527,7 +527,7 @@ static dma_addr_t pci32_map_page(struct device *dev, struct page *page, static void pci32_unmap_page(struct device *dev, dma_addr_t ba, size_t size, enum dma_data_direction dir, unsigned long attrs) { - if (dir != PCI_DMA_TODEVICE) + if (dir != PCI_DMA_TODEVICE && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) dma_make_coherent(ba, PAGE_ALIGN(size)); } @@ -572,7 +572,7 @@ static void pci32_unmap_sg(struct device *dev, struct scatterlist *sgl, struct scatterlist *sg; int n; - if (dir != PCI_DMA_TODEVICE) { + if (dir != PCI_DMA_TODEVICE && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) { for_each_sg(sgl, sg, nents, n) { dma_make_coherent(sg_phys(sg), PAGE_ALIGN(sg->length)); } -- cgit From 33c77e53d838dc27e9d2edec5b6ab6a11861fb32 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 14 Dec 2016 15:05:18 -0800 Subject: arch/tile: add option to skip DMA sync as a part of map and unmap This change allows us to pass DMA_ATTR_SKIP_CPU_SYNC which allows us to avoid invoking cache line invalidation if the driver will just handle it via a sync_for_cpu or sync_for_device call. Link: http://lkml.kernel.org/r/20161110113550.76501.73060.stgit@ahduyck-blue-test.jf.intel.com Signed-off-by: Alexander Duyck Cc: Chris Metcalf Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/tile/kernel/pci-dma.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/tile/kernel/pci-dma.c b/arch/tile/kernel/pci-dma.c index 09bb774b39cd..24e0f8c21f2f 100644 --- a/arch/tile/kernel/pci-dma.c +++ b/arch/tile/kernel/pci-dma.c @@ -213,10 +213,12 @@ static int tile_dma_map_sg(struct device *dev, struct scatterlist *sglist, for_each_sg(sglist, sg, nents, i) { sg->dma_address = sg_phys(sg); - __dma_prep_pa_range(sg->dma_address, sg->length, direction); #ifdef CONFIG_NEED_SG_DMA_LENGTH sg->dma_length = sg->length; #endif + if (attrs & DMA_ATTR_SKIP_CPU_SYNC) + continue; + __dma_prep_pa_range(sg->dma_address, sg->length, direction); } return nents; @@ -232,6 +234,8 @@ static void tile_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, BUG_ON(!valid_dma_direction(direction)); for_each_sg(sglist, sg, nents, i) { sg->dma_address = sg_phys(sg); + if (attrs & DMA_ATTR_SKIP_CPU_SYNC) + continue; __dma_complete_pa_range(sg->dma_address, sg->length, direction); } @@ -245,7 +249,8 @@ static dma_addr_t tile_dma_map_page(struct device *dev, struct page *page, BUG_ON(!valid_dma_direction(direction)); BUG_ON(offset + size > PAGE_SIZE); - __dma_prep_page(page, offset, size, direction); + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + __dma_prep_page(page, offset, size, direction); return page_to_pa(page) + offset; } @@ -256,6 +261,9 @@ static void tile_dma_unmap_page(struct device *dev, dma_addr_t dma_address, { BUG_ON(!valid_dma_direction(direction)); + if (attrs & DMA_ATTR_SKIP_CPU_SYNC) + return; + __dma_complete_page(pfn_to_page(PFN_DOWN(dma_address)), dma_address & (PAGE_SIZE - 1), size, direction); } -- cgit From 4bfa135abec99f4b35b5636f56a6db75ce3c64d7 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 14 Dec 2016 15:05:21 -0800 Subject: arch/xtensa: add option to skip DMA sync as a part of mapping This change allows us to pass DMA_ATTR_SKIP_CPU_SYNC which allows us to avoid invoking cache line invalidation if the driver will just handle it via a sync_for_cpu or sync_for_device call. Link: http://lkml.kernel.org/r/20161110113555.76501.52536.stgit@ahduyck-blue-test.jf.intel.com Signed-off-by: Alexander Duyck Cc: Max Filippov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/xtensa/kernel/pci-dma.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/xtensa/kernel/pci-dma.c b/arch/xtensa/kernel/pci-dma.c index 1e68806d6695..6a16decf278f 100644 --- a/arch/xtensa/kernel/pci-dma.c +++ b/arch/xtensa/kernel/pci-dma.c @@ -189,7 +189,9 @@ static dma_addr_t xtensa_map_page(struct device *dev, struct page *page, { dma_addr_t dma_handle = page_to_phys(page) + offset; - xtensa_sync_single_for_device(dev, dma_handle, size, dir); + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + xtensa_sync_single_for_device(dev, dma_handle, size, dir); + return dma_handle; } @@ -197,7 +199,8 @@ static void xtensa_unmap_page(struct device *dev, dma_addr_t dma_handle, size_t size, enum dma_data_direction dir, unsigned long attrs) { - xtensa_sync_single_for_cpu(dev, dma_handle, size, dir); + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + xtensa_sync_single_for_cpu(dev, dma_handle, size, dir); } static int xtensa_map_sg(struct device *dev, struct scatterlist *sg, -- cgit From 7a5c8b57cec93196b3e84e3cad2ff81ae0faed78 Mon Sep 17 00:00:00 2001 From: Babu Moger Date: Wed, 14 Dec 2016 15:06:28 -0800 Subject: sparc: implement watchdog_nmi_enable and watchdog_nmi_disable Implement functions watchdog_nmi_enable and watchdog_nmi_disable to enable/disable nmi watchdog. Sparc uses arch specific nmi watchdog handler. Currently, we do not have a way to enable/disable nmi watchdog dynamically. With these patches we can enable or disable arch specific nmi watchdogs using proc or sysctl interface. Example commands. To enable: echo 1 > /proc/sys/kernel/nmi_watchdog To disable: echo 0 > /proc/sys/kernel/nmi_watchdog It can also achieved using the sysctl parameter kernel.nmi_watchdog Link: http://lkml.kernel.org/r/1478034826-43888-4-git-send-email-babu.moger@oracle.com Signed-off-by: Babu Moger Acked-by: Don Zickus Cc: Ingo Molnar Cc: Jiri Kosina Cc: Andi Kleen Cc: Yaowei Bai Cc: Aaron Tomlin Cc: Ulrich Obergfell Cc: Tejun Heo Cc: Hidehiro Kawai Cc: Josh Hunt Cc: "David S. Miller" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/sparc/kernel/nmi.c | 44 +++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 43 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c index a9973bb4a1b2..95e73c63c99d 100644 --- a/arch/sparc/kernel/nmi.c +++ b/arch/sparc/kernel/nmi.c @@ -42,7 +42,7 @@ static int panic_on_timeout; */ atomic_t nmi_active = ATOMIC_INIT(0); /* oprofile uses this */ EXPORT_SYMBOL(nmi_active); - +static int nmi_init_done; static unsigned int nmi_hz = HZ; static DEFINE_PER_CPU(short, wd_enabled); static int endflag __initdata; @@ -153,6 +153,8 @@ static void report_broken_nmi(int cpu, int *prev_nmi_count) void stop_nmi_watchdog(void *unused) { + if (!__this_cpu_read(wd_enabled)) + return; pcr_ops->write_pcr(0, pcr_ops->pcr_nmi_disable); __this_cpu_write(wd_enabled, 0); atomic_dec(&nmi_active); @@ -207,6 +209,9 @@ error: void start_nmi_watchdog(void *unused) { + if (__this_cpu_read(wd_enabled)) + return; + __this_cpu_write(wd_enabled, 1); atomic_inc(&nmi_active); @@ -259,6 +264,8 @@ int __init nmi_init(void) } } + nmi_init_done = 1; + return err; } @@ -270,3 +277,38 @@ static int __init setup_nmi_watchdog(char *str) return 0; } __setup("nmi_watchdog=", setup_nmi_watchdog); + +/* + * sparc specific NMI watchdog enable function. + * Enables watchdog if it is not enabled already. + */ +int watchdog_nmi_enable(unsigned int cpu) +{ + if (atomic_read(&nmi_active) == -1) { + pr_warn("NMI watchdog cannot be enabled or disabled\n"); + return -1; + } + + /* + * watchdog thread could start even before nmi_init is called. + * Just Return in that case. Let nmi_init finish the init + * process first. + */ + if (!nmi_init_done) + return 0; + + smp_call_function_single(cpu, start_nmi_watchdog, NULL, 1); + + return 0; +} +/* + * sparc specific NMI watchdog disable function. + * Disables watchdog if it is not disabled already. + */ +void watchdog_nmi_disable(unsigned int cpu) +{ + if (atomic_read(&nmi_active) == -1) + pr_warn_once("NMI watchdog cannot be enabled or disabled\n"); + else + smp_call_function_single(cpu, stop_nmi_watchdog, NULL, 1); +} -- cgit From 1a29d85eb0f19b7d8271923d8917d7b4f5540b3e Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 14 Dec 2016 15:07:01 -0800 Subject: mm: use vmf->address instead of of vmf->virtual_address Every single user of vmf->virtual_address typed that entry to unsigned long before doing anything with it so the type of virtual_address does not really provide us any additional safety. Just use masked vmf->address which already has the appropriate type. Link: http://lkml.kernel.org/r/1479460644-25076-3-git-send-email-jack@suse.cz Signed-off-by: Jan Kara Acked-by: Kirill A. Shutemov Cc: Dan Williams Cc: Ross Zwisler Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/platforms/cell/spufs/file.c | 8 +++----- arch/x86/entry/vdso/vma.c | 4 ++-- 2 files changed, 5 insertions(+), 7 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c index 06254467e4dd..3a147122bc98 100644 --- a/arch/powerpc/platforms/cell/spufs/file.c +++ b/arch/powerpc/platforms/cell/spufs/file.c @@ -236,7 +236,6 @@ static int spufs_mem_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { struct spu_context *ctx = vma->vm_file->private_data; - unsigned long address = (unsigned long)vmf->virtual_address; unsigned long pfn, offset; offset = vmf->pgoff << PAGE_SHIFT; @@ -244,7 +243,7 @@ spufs_mem_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) return VM_FAULT_SIGBUS; pr_debug("spufs_mem_mmap_fault address=0x%lx, offset=0x%lx\n", - address, offset); + vmf->address, offset); if (spu_acquire(ctx)) return VM_FAULT_NOPAGE; @@ -256,7 +255,7 @@ spufs_mem_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) vma->vm_page_prot = pgprot_noncached_wc(vma->vm_page_prot); pfn = (ctx->spu->local_store_phys + offset) >> PAGE_SHIFT; } - vm_insert_pfn(vma, address, pfn); + vm_insert_pfn(vma, vmf->address, pfn); spu_release(ctx); @@ -355,8 +354,7 @@ static int spufs_ps_fault(struct vm_area_struct *vma, down_read(¤t->mm->mmap_sem); } else { area = ctx->spu->problem_phys + ps_offs; - vm_insert_pfn(vma, (unsigned long)vmf->virtual_address, - (area + offset) >> PAGE_SHIFT); + vm_insert_pfn(vma, vmf->address, (area + offset) >> PAGE_SHIFT); spu_context_trace(spufs_ps_fault__insert, ctx, ctx->spu); } diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index e739002427ed..40121d14d34d 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -109,7 +109,7 @@ static int vvar_fault(const struct vm_special_mapping *sm, return VM_FAULT_SIGBUS; if (sym_offset == image->sym_vvar_page) { - ret = vm_insert_pfn(vma, (unsigned long)vmf->virtual_address, + ret = vm_insert_pfn(vma, vmf->address, __pa_symbol(&__vvar_page) >> PAGE_SHIFT); } else if (sym_offset == image->sym_pvclock_page) { struct pvclock_vsyscall_time_info *pvti = @@ -117,7 +117,7 @@ static int vvar_fault(const struct vm_special_mapping *sm, if (pvti && vclock_was_used(VCLOCK_PVCLOCK)) { ret = vm_insert_pfn( vma, - (unsigned long)vmf->virtual_address, + vmf->address, __pa(pvti) >> PAGE_SHIFT); } } -- cgit