From abe6602bf197167efb3b37161b9c11748fa076e1 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Mon, 5 Jan 2009 23:47:21 +0900 Subject: x86: add map_page and unmap_page to struct dma_mapping_ops This patch adds map_page and unmap_page to struct dma_mapping_ops. This is a preparation of struct dma_mapping_ops unification. We use map_page and unmap_page instead of map_single and unmap_single. We will remove map_single and unmap_single hooks in the last patch in this patchset. Signed-off-by: FUJITA Tomonori Signed-off-by: Ingo Molnar --- arch/x86/include/asm/dma-mapping.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index 4035357f5b9..3fe05046fb3 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -7,6 +7,7 @@ */ #include +#include #include #include #include @@ -50,6 +51,13 @@ struct dma_mapping_ops { void (*unmap_sg)(struct device *hwdev, struct scatterlist *sg, int nents, int direction); + dma_addr_t (*map_page)(struct device *dev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction dir, + struct dma_attrs *attrs); + void (*unmap_page)(struct device *dev, dma_addr_t dma_handle, + size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs); int (*dma_supported)(struct device *hwdev, u64 mask); int is_phys; }; -- cgit v1.2.3-70-g09d2 From d7dff84053524186b139342ac66a4160ce6bb517 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Mon, 5 Jan 2009 23:47:28 +0900 Subject: x86: remove map_single and unmap_single in struct dma_mapping_ops This patch converts dma_map_single and dma_unmap_single to use map_page and unmap_page respectively and removes unnecessary map_single and unmap_single in struct dma_mapping_ops. This leaves intel-iommu's dma_map_single and dma_unmap_single since IA64 uses them. They will be removed after the unification. Signed-off-by: FUJITA Tomonori Signed-off-by: Ingo Molnar --- arch/x86/include/asm/dma-mapping.h | 15 ++++++--------- arch/x86/kernel/amd_iommu.c | 15 --------------- arch/x86/kernel/pci-calgary_64.c | 16 ---------------- arch/x86/kernel/pci-gart_64.c | 19 ++----------------- arch/x86/kernel/pci-nommu.c | 8 -------- arch/x86/kernel/pci-swiotlb_64.c | 9 --------- drivers/pci/intel-iommu.c | 2 -- 7 files changed, 8 insertions(+), 76 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index 3fe05046fb3..b81f82268a1 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -24,10 +24,6 @@ struct dma_mapping_ops { dma_addr_t *dma_handle, gfp_t gfp); void (*free_coherent)(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle); - dma_addr_t (*map_single)(struct device *hwdev, phys_addr_t ptr, - size_t size, int direction); - void (*unmap_single)(struct device *dev, dma_addr_t addr, - size_t size, int direction); void (*sync_single_for_cpu)(struct device *hwdev, dma_addr_t dma_handle, size_t size, int direction); @@ -103,7 +99,9 @@ dma_map_single(struct device *hwdev, void *ptr, size_t size, struct dma_mapping_ops *ops = get_dma_ops(hwdev); BUG_ON(!valid_dma_direction(direction)); - return ops->map_single(hwdev, virt_to_phys(ptr), size, direction); + return ops->map_page(hwdev, virt_to_page(ptr), + (unsigned long)ptr & ~PAGE_MASK, size, + direction, NULL); } static inline void @@ -113,8 +111,8 @@ dma_unmap_single(struct device *dev, dma_addr_t addr, size_t size, struct dma_mapping_ops *ops = get_dma_ops(dev); BUG_ON(!valid_dma_direction(direction)); - if (ops->unmap_single) - ops->unmap_single(dev, addr, size, direction); + if (ops->unmap_page) + ops->unmap_page(dev, addr, size, direction, NULL); } static inline int @@ -221,8 +219,7 @@ static inline dma_addr_t dma_map_page(struct device *dev, struct page *page, struct dma_mapping_ops *ops = get_dma_ops(dev); BUG_ON(!valid_dma_direction(direction)); - return ops->map_single(dev, page_to_phys(page) + offset, - size, direction); + return ops->map_page(dev, page, offset, size, direction, NULL); } static inline void dma_unmap_page(struct device *dev, dma_addr_t addr, diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c index 85704418644..a5dedb690a9 100644 --- a/arch/x86/kernel/amd_iommu.c +++ b/arch/x86/kernel/amd_iommu.c @@ -1341,13 +1341,6 @@ out: return addr; } -static dma_addr_t map_single(struct device *dev, phys_addr_t paddr, - size_t size, int dir) -{ - return map_page(dev, pfn_to_page(paddr >> PAGE_SHIFT), - paddr & ~PAGE_MASK, size, dir, NULL); -} - /* * The exported unmap_single function for dma_ops. */ @@ -1378,12 +1371,6 @@ static void unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size, spin_unlock_irqrestore(&domain->lock, flags); } -static void unmap_single(struct device *dev, dma_addr_t dma_addr, - size_t size, int dir) -{ - return unmap_page(dev, dma_addr, size, dir, NULL); -} - /* * This is a special map_sg function which is used if we should map a * device which is not handled by an AMD IOMMU in the system. @@ -1664,8 +1651,6 @@ static void prealloc_protection_domains(void) static struct dma_mapping_ops amd_iommu_dma_ops = { .alloc_coherent = alloc_coherent, .free_coherent = free_coherent, - .map_single = map_single, - .unmap_single = unmap_single, .map_page = map_page, .unmap_page = unmap_page, .map_sg = map_sg, diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index e33cfcf1af5..756138b604e 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -461,14 +461,6 @@ static dma_addr_t calgary_map_page(struct device *dev, struct page *page, return iommu_alloc(dev, tbl, vaddr, npages, dir); } -static dma_addr_t calgary_map_single(struct device *dev, phys_addr_t paddr, - size_t size, int direction) -{ - return calgary_map_page(dev, pfn_to_page(paddr >> PAGE_SHIFT), - paddr & ~PAGE_MASK, size, - direction, NULL); -} - static void calgary_unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size, enum dma_data_direction dir, struct dma_attrs *attrs) @@ -480,12 +472,6 @@ static void calgary_unmap_page(struct device *dev, dma_addr_t dma_addr, iommu_free(tbl, dma_addr, npages); } -static void calgary_unmap_single(struct device *dev, dma_addr_t dma_handle, - size_t size, int direction) -{ - calgary_unmap_page(dev, dma_handle, size, direction, NULL); -} - static void* calgary_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag) { @@ -535,8 +521,6 @@ static void calgary_free_coherent(struct device *dev, size_t size, static struct dma_mapping_ops calgary_dma_ops = { .alloc_coherent = calgary_alloc_coherent, .free_coherent = calgary_free_coherent, - .map_single = calgary_map_single, - .unmap_single = calgary_unmap_single, .map_sg = calgary_map_sg, .unmap_sg = calgary_unmap_sg, .map_page = calgary_map_page, diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index e49c6dd0e8c..9c557c0c928 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -275,13 +275,6 @@ static dma_addr_t gart_map_page(struct device *dev, struct page *page, return bus; } -static dma_addr_t gart_map_single(struct device *dev, phys_addr_t paddr, - size_t size, int dir) -{ - return gart_map_page(dev, pfn_to_page(paddr >> PAGE_SHIFT), - paddr & ~PAGE_MASK, size, dir, NULL); -} - /* * Free a DMA mapping. */ @@ -306,12 +299,6 @@ static void gart_unmap_page(struct device *dev, dma_addr_t dma_addr, free_iommu(iommu_page, npages); } -static void gart_unmap_single(struct device *dev, dma_addr_t dma_addr, - size_t size, int direction) -{ - gart_unmap_page(dev, dma_addr, size, direction, NULL); -} - /* * Wrapper for pci_unmap_single working with scatterlists. */ @@ -324,7 +311,7 @@ gart_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, int dir) for_each_sg(sg, s, nents, i) { if (!s->dma_length || !s->length) break; - gart_unmap_single(dev, s->dma_address, s->dma_length, dir); + gart_unmap_page(dev, s->dma_address, s->dma_length, dir, NULL); } } @@ -538,7 +525,7 @@ static void gart_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_addr) { - gart_unmap_single(dev, dma_addr, size, DMA_BIDIRECTIONAL); + gart_unmap_page(dev, dma_addr, size, DMA_BIDIRECTIONAL, NULL); free_pages((unsigned long)vaddr, get_order(size)); } @@ -725,8 +712,6 @@ static __init int init_k8_gatt(struct agp_kern_info *info) } static struct dma_mapping_ops gart_dma_ops = { - .map_single = gart_map_single, - .unmap_single = gart_unmap_single, .map_sg = gart_map_sg, .unmap_sg = gart_unmap_sg, .map_page = gart_map_page, diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c index 5a73a824ac1..d42b69c90b4 100644 --- a/arch/x86/kernel/pci-nommu.c +++ b/arch/x86/kernel/pci-nommu.c @@ -38,13 +38,6 @@ static dma_addr_t nommu_map_page(struct device *dev, struct page *page, return bus; } -static dma_addr_t nommu_map_single(struct device *hwdev, phys_addr_t paddr, - size_t size, int direction) -{ - return nommu_map_page(hwdev, pfn_to_page(paddr >> PAGE_SHIFT), - paddr & ~PAGE_MASK, size, direction, NULL); -} - /* Map a set of buffers described by scatterlist in streaming * mode for DMA. This is the scatter-gather version of the * above pci_map_single interface. Here the scatter gather list @@ -88,7 +81,6 @@ static void nommu_free_coherent(struct device *dev, size_t size, void *vaddr, struct dma_mapping_ops nommu_dma_ops = { .alloc_coherent = dma_generic_alloc_coherent, .free_coherent = nommu_free_coherent, - .map_single = nommu_map_single, .map_sg = nommu_map_sg, .map_page = nommu_map_page, .is_phys = 1, diff --git a/arch/x86/kernel/pci-swiotlb_64.c b/arch/x86/kernel/pci-swiotlb_64.c index d1c0366886d..3ae354c0fde 100644 --- a/arch/x86/kernel/pci-swiotlb_64.c +++ b/arch/x86/kernel/pci-swiotlb_64.c @@ -38,13 +38,6 @@ int __weak swiotlb_arch_range_needs_mapping(void *ptr, size_t size) return 0; } -static dma_addr_t -swiotlb_map_single_phys(struct device *hwdev, phys_addr_t paddr, size_t size, - int direction) -{ - return swiotlb_map_single(hwdev, phys_to_virt(paddr), size, direction); -} - /* these will be moved to lib/swiotlb.c later on */ static dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, @@ -78,8 +71,6 @@ struct dma_mapping_ops swiotlb_dma_ops = { .mapping_error = swiotlb_dma_mapping_error, .alloc_coherent = x86_swiotlb_alloc_coherent, .free_coherent = swiotlb_free_coherent, - .map_single = swiotlb_map_single_phys, - .unmap_single = swiotlb_unmap_single, .sync_single_for_cpu = swiotlb_sync_single_for_cpu, .sync_single_for_device = swiotlb_sync_single_for_device, .sync_single_range_for_cpu = swiotlb_sync_single_range_for_cpu, diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c index 60258ecbcb4..da273e4ef66 100644 --- a/drivers/pci/intel-iommu.c +++ b/drivers/pci/intel-iommu.c @@ -2582,8 +2582,6 @@ int intel_map_sg(struct device *hwdev, struct scatterlist *sglist, int nelems, static struct dma_mapping_ops intel_dma_ops = { .alloc_coherent = intel_alloc_coherent, .free_coherent = intel_free_coherent, - .map_single = intel_map_single, - .unmap_single = intel_unmap_single, .map_sg = intel_map_sg, .unmap_sg = intel_unmap_sg, #ifdef CONFIG_X86_64 -- cgit v1.2.3-70-g09d2 From 160c1d8e40866edfeae7d68816b7005d70acf391 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Mon, 5 Jan 2009 23:59:02 +0900 Subject: x86, ia64: convert to use generic dma_map_ops struct This converts X86 and IA64 to use include/linux/dma-mapping.h. It's a bit large but pretty boring. The major change for X86 is converting 'int dir' to 'enum dma_data_direction dir' in DMA mapping operations. The major changes for IA64 is using map_page and unmap_page instead of map_single and unmap_single. Signed-off-by: FUJITA Tomonori Acked-by: Tony Luck Signed-off-by: Ingo Molnar --- arch/ia64/dig/Makefile | 4 +- arch/ia64/dig/dig_vtd_iommu.c | 77 ------------------- arch/ia64/hp/common/hwsw_iommu.c | 6 +- arch/ia64/hp/common/sba_iommu.c | 46 ++++++++---- arch/ia64/include/asm/dma-mapping.h | 107 ++++++++------------------ arch/ia64/include/asm/machvec.h | 12 +-- arch/ia64/kernel/dma-mapping.c | 4 +- arch/ia64/kernel/machvec.c | 8 +- arch/ia64/kernel/pci-dma.c | 49 +++++++----- arch/ia64/kernel/pci-swiotlb.c | 32 +++++--- arch/ia64/sn/pci/pci_dma.c | 58 +++++++------- arch/x86/include/asm/device.h | 2 +- arch/x86/include/asm/dma-mapping.h | 146 +++++++++++++----------------------- arch/x86/include/asm/iommu.h | 2 +- arch/x86/kernel/amd_iommu.c | 8 +- arch/x86/kernel/pci-calgary_64.c | 15 ++-- arch/x86/kernel/pci-dma.c | 4 +- arch/x86/kernel/pci-gart_64.c | 14 ++-- arch/x86/kernel/pci-nommu.c | 5 +- arch/x86/kernel/pci-swiotlb_64.c | 6 +- drivers/pci/intel-iommu.c | 9 +-- include/linux/intel-iommu.h | 6 +- include/linux/swiotlb.h | 18 +++-- lib/swiotlb.c | 18 +++-- 24 files changed, 278 insertions(+), 378 deletions(-) delete mode 100644 arch/ia64/dig/dig_vtd_iommu.c (limited to 'arch/x86/include') diff --git a/arch/ia64/dig/Makefile b/arch/ia64/dig/Makefile index 5c0283830bd..2f7caddf093 100644 --- a/arch/ia64/dig/Makefile +++ b/arch/ia64/dig/Makefile @@ -7,8 +7,8 @@ obj-y := setup.o ifeq ($(CONFIG_DMAR), y) -obj-$(CONFIG_IA64_GENERIC) += machvec.o machvec_vtd.o dig_vtd_iommu.o +obj-$(CONFIG_IA64_GENERIC) += machvec.o machvec_vtd.o else obj-$(CONFIG_IA64_GENERIC) += machvec.o endif -obj-$(CONFIG_IA64_DIG_VTD) += dig_vtd_iommu.o + diff --git a/arch/ia64/dig/dig_vtd_iommu.c b/arch/ia64/dig/dig_vtd_iommu.c deleted file mode 100644 index fdb8ba9f499..00000000000 --- a/arch/ia64/dig/dig_vtd_iommu.c +++ /dev/null @@ -1,77 +0,0 @@ -#include -#include -#include -#include -#include - -void * -vtd_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, - gfp_t flags) -{ - return intel_alloc_coherent(dev, size, dma_handle, flags); -} -EXPORT_SYMBOL_GPL(vtd_alloc_coherent); - -void -vtd_free_coherent(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle) -{ - intel_free_coherent(dev, size, vaddr, dma_handle); -} -EXPORT_SYMBOL_GPL(vtd_free_coherent); - -dma_addr_t -vtd_map_single_attrs(struct device *dev, void *addr, size_t size, - int dir, struct dma_attrs *attrs) -{ - return intel_map_single(dev, (phys_addr_t)addr, size, dir); -} -EXPORT_SYMBOL_GPL(vtd_map_single_attrs); - -void -vtd_unmap_single_attrs(struct device *dev, dma_addr_t iova, size_t size, - int dir, struct dma_attrs *attrs) -{ - intel_unmap_single(dev, iova, size, dir); -} -EXPORT_SYMBOL_GPL(vtd_unmap_single_attrs); - -int -vtd_map_sg_attrs(struct device *dev, struct scatterlist *sglist, int nents, - int dir, struct dma_attrs *attrs) -{ - return intel_map_sg(dev, sglist, nents, dir); -} -EXPORT_SYMBOL_GPL(vtd_map_sg_attrs); - -void -vtd_unmap_sg_attrs(struct device *dev, struct scatterlist *sglist, - int nents, int dir, struct dma_attrs *attrs) -{ - intel_unmap_sg(dev, sglist, nents, dir); -} -EXPORT_SYMBOL_GPL(vtd_unmap_sg_attrs); - -int -vtd_dma_mapping_error(struct device *dev, dma_addr_t dma_addr) -{ - return 0; -} -EXPORT_SYMBOL_GPL(vtd_dma_mapping_error); - -extern int iommu_dma_supported(struct device *dev, u64 mask); - -struct dma_mapping_ops vtd_dma_ops = { - .alloc_coherent = vtd_alloc_coherent, - .free_coherent = vtd_free_coherent, - .map_single_attrs = vtd_map_single_attrs, - .unmap_single_attrs = vtd_unmap_single_attrs, - .map_sg_attrs = vtd_map_sg_attrs, - .unmap_sg_attrs = vtd_unmap_sg_attrs, - .sync_single_for_cpu = machvec_dma_sync_single, - .sync_sg_for_cpu = machvec_dma_sync_sg, - .sync_single_for_device = machvec_dma_sync_single, - .sync_sg_for_device = machvec_dma_sync_sg, - .dma_supported_op = iommu_dma_supported, - .mapping_error = vtd_dma_mapping_error, -}; diff --git a/arch/ia64/hp/common/hwsw_iommu.c b/arch/ia64/hp/common/hwsw_iommu.c index e5bbeba7781..e4a80d82e3d 100644 --- a/arch/ia64/hp/common/hwsw_iommu.c +++ b/arch/ia64/hp/common/hwsw_iommu.c @@ -17,7 +17,7 @@ #include #include -extern struct dma_mapping_ops sba_dma_ops, swiotlb_dma_ops; +extern struct dma_map_ops sba_dma_ops, swiotlb_dma_ops; /* swiotlb declarations & definitions: */ extern int swiotlb_late_init_with_default_size (size_t size); @@ -30,10 +30,10 @@ extern int swiotlb_late_init_with_default_size (size_t size); static inline int use_swiotlb(struct device *dev) { return dev && dev->dma_mask && - !sba_dma_ops.dma_supported_op(dev, *dev->dma_mask); + !sba_dma_ops.dma_supported(dev, *dev->dma_mask); } -struct dma_mapping_ops *hwsw_dma_get_ops(struct device *dev) +struct dma_map_ops *hwsw_dma_get_ops(struct device *dev) { if (use_swiotlb(dev)) return &swiotlb_dma_ops; diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c index 29e7206f3dc..129b62eb39e 100644 --- a/arch/ia64/hp/common/sba_iommu.c +++ b/arch/ia64/hp/common/sba_iommu.c @@ -909,11 +909,13 @@ sba_mark_invalid(struct ioc *ioc, dma_addr_t iova, size_t byte_cnt) * * See Documentation/DMA-mapping.txt */ -static dma_addr_t -sba_map_single_attrs(struct device *dev, void *addr, size_t size, int dir, - struct dma_attrs *attrs) +static dma_addr_t sba_map_page(struct device *dev, struct page *page, + unsigned long poff, size_t size, + enum dma_data_direction dir, + struct dma_attrs *attrs) { struct ioc *ioc; + void *addr = page_address(page) + poff; dma_addr_t iovp; dma_addr_t offset; u64 *pdir_start; @@ -992,6 +994,14 @@ sba_map_single_attrs(struct device *dev, void *addr, size_t size, int dir, return SBA_IOVA(ioc, iovp, offset); } +static dma_addr_t sba_map_single_attrs(struct device *dev, void *addr, + size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + return sba_map_page(dev, virt_to_page(addr), + (unsigned long)addr & ~PAGE_MASK, size, dir, attrs); +} + #ifdef ENABLE_MARK_CLEAN static SBA_INLINE void sba_mark_clean(struct ioc *ioc, dma_addr_t iova, size_t size) @@ -1026,8 +1036,8 @@ sba_mark_clean(struct ioc *ioc, dma_addr_t iova, size_t size) * * See Documentation/DMA-mapping.txt */ -static void sba_unmap_single_attrs(struct device *dev, dma_addr_t iova, size_t size, - int dir, struct dma_attrs *attrs) +static void sba_unmap_page(struct device *dev, dma_addr_t iova, size_t size, + enum dma_data_direction dir, struct dma_attrs *attrs) { struct ioc *ioc; #if DELAYED_RESOURCE_CNT > 0 @@ -1095,6 +1105,12 @@ static void sba_unmap_single_attrs(struct device *dev, dma_addr_t iova, size_t s #endif /* DELAYED_RESOURCE_CNT == 0 */ } +void sba_unmap_single_attrs(struct device *dev, dma_addr_t iova, size_t size, + enum dma_data_direction dir, struct dma_attrs *attrs) +{ + sba_unmap_page(dev, iova, size, dir, attrs); +} + /** * sba_alloc_coherent - allocate/map shared mem for DMA * @dev: instance of PCI owned by the driver that's asking. @@ -1423,7 +1439,8 @@ sba_coalesce_chunks(struct ioc *ioc, struct device *dev, * See Documentation/DMA-mapping.txt */ static int sba_map_sg_attrs(struct device *dev, struct scatterlist *sglist, - int nents, int dir, struct dma_attrs *attrs) + int nents, enum dma_data_direction dir, + struct dma_attrs *attrs) { struct ioc *ioc; int coalesced, filled = 0; @@ -1514,7 +1531,8 @@ static int sba_map_sg_attrs(struct device *dev, struct scatterlist *sglist, * See Documentation/DMA-mapping.txt */ static void sba_unmap_sg_attrs(struct device *dev, struct scatterlist *sglist, - int nents, int dir, struct dma_attrs *attrs) + int nents, enum dma_data_direction dir, + struct dma_attrs *attrs) { #ifdef ASSERT_PDIR_SANITY struct ioc *ioc; @@ -2062,7 +2080,7 @@ static struct acpi_driver acpi_sba_ioc_driver = { }, }; -extern struct dma_mapping_ops swiotlb_dma_ops; +extern struct dma_map_ops swiotlb_dma_ops; static int __init sba_init(void) @@ -2176,18 +2194,18 @@ sba_page_override(char *str) __setup("sbapagesize=",sba_page_override); -struct dma_mapping_ops sba_dma_ops = { +struct dma_map_ops sba_dma_ops = { .alloc_coherent = sba_alloc_coherent, .free_coherent = sba_free_coherent, - .map_single_attrs = sba_map_single_attrs, - .unmap_single_attrs = sba_unmap_single_attrs, - .map_sg_attrs = sba_map_sg_attrs, - .unmap_sg_attrs = sba_unmap_sg_attrs, + .map_page = sba_map_page, + .unmap_page = sba_unmap_page, + .map_sg = sba_map_sg_attrs, + .unmap_sg = sba_unmap_sg_attrs, .sync_single_for_cpu = machvec_dma_sync_single, .sync_sg_for_cpu = machvec_dma_sync_sg, .sync_single_for_device = machvec_dma_sync_single, .sync_sg_for_device = machvec_dma_sync_sg, - .dma_supported_op = sba_dma_supported, + .dma_supported = sba_dma_supported, .mapping_error = sba_dma_mapping_error, }; diff --git a/arch/ia64/include/asm/dma-mapping.h b/arch/ia64/include/asm/dma-mapping.h index bac3159379f..d6230f51453 100644 --- a/arch/ia64/include/asm/dma-mapping.h +++ b/arch/ia64/include/asm/dma-mapping.h @@ -9,73 +9,21 @@ #include #include -struct dma_mapping_ops { - int (*mapping_error)(struct device *dev, - dma_addr_t dma_addr); - void* (*alloc_coherent)(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp); - void (*free_coherent)(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle); - dma_addr_t (*map_single)(struct device *hwdev, unsigned long ptr, - size_t size, int direction); - void (*unmap_single)(struct device *dev, dma_addr_t addr, - size_t size, int direction); - dma_addr_t (*map_single_attrs)(struct device *dev, void *cpu_addr, - size_t size, int direction, - struct dma_attrs *attrs); - void (*unmap_single_attrs)(struct device *dev, - dma_addr_t dma_addr, - size_t size, int direction, - struct dma_attrs *attrs); - void (*sync_single_for_cpu)(struct device *hwdev, - dma_addr_t dma_handle, size_t size, - int direction); - void (*sync_single_for_device)(struct device *hwdev, - dma_addr_t dma_handle, size_t size, - int direction); - void (*sync_single_range_for_cpu)(struct device *hwdev, - dma_addr_t dma_handle, unsigned long offset, - size_t size, int direction); - void (*sync_single_range_for_device)(struct device *hwdev, - dma_addr_t dma_handle, unsigned long offset, - size_t size, int direction); - void (*sync_sg_for_cpu)(struct device *hwdev, - struct scatterlist *sg, int nelems, - int direction); - void (*sync_sg_for_device)(struct device *hwdev, - struct scatterlist *sg, int nelems, - int direction); - int (*map_sg)(struct device *hwdev, struct scatterlist *sg, - int nents, int direction); - void (*unmap_sg)(struct device *hwdev, - struct scatterlist *sg, int nents, - int direction); - int (*map_sg_attrs)(struct device *dev, - struct scatterlist *sg, int nents, - int direction, struct dma_attrs *attrs); - void (*unmap_sg_attrs)(struct device *dev, - struct scatterlist *sg, int nents, - int direction, - struct dma_attrs *attrs); - int (*dma_supported_op)(struct device *hwdev, u64 mask); - int is_phys; -}; - -extern struct dma_mapping_ops *dma_ops; +extern struct dma_map_ops *dma_ops; extern struct ia64_machine_vector ia64_mv; extern void set_iommu_machvec(void); static inline void *dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *daddr, gfp_t gfp) { - struct dma_mapping_ops *ops = platform_dma_get_ops(dev); + struct dma_map_ops *ops = platform_dma_get_ops(dev); return ops->alloc_coherent(dev, size, daddr, gfp | GFP_DMA); } static inline void dma_free_coherent(struct device *dev, size_t size, void *caddr, dma_addr_t daddr) { - struct dma_mapping_ops *ops = platform_dma_get_ops(dev); + struct dma_map_ops *ops = platform_dma_get_ops(dev); ops->free_coherent(dev, size, caddr, daddr); } @@ -87,8 +35,10 @@ static inline dma_addr_t dma_map_single_attrs(struct device *dev, enum dma_data_direction dir, struct dma_attrs *attrs) { - struct dma_mapping_ops *ops = platform_dma_get_ops(dev); - return ops->map_single_attrs(dev, caddr, size, dir, attrs); + struct dma_map_ops *ops = platform_dma_get_ops(dev); + return ops->map_page(dev, virt_to_page(caddr), + (unsigned long)caddr & ~PAGE_MASK, size, + dir, attrs); } static inline void dma_unmap_single_attrs(struct device *dev, dma_addr_t daddr, @@ -96,8 +46,8 @@ static inline void dma_unmap_single_attrs(struct device *dev, dma_addr_t daddr, enum dma_data_direction dir, struct dma_attrs *attrs) { - struct dma_mapping_ops *ops = platform_dma_get_ops(dev); - ops->unmap_single_attrs(dev, daddr, size, dir, attrs); + struct dma_map_ops *ops = platform_dma_get_ops(dev); + ops->unmap_page(dev, daddr, size, dir, attrs); } #define dma_map_single(d, a, s, r) dma_map_single_attrs(d, a, s, r, NULL) @@ -107,8 +57,8 @@ static inline int dma_map_sg_attrs(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir, struct dma_attrs *attrs) { - struct dma_mapping_ops *ops = platform_dma_get_ops(dev); - return ops->map_sg_attrs(dev, sgl, nents, dir, attrs); + struct dma_map_ops *ops = platform_dma_get_ops(dev); + return ops->map_sg(dev, sgl, nents, dir, attrs); } static inline void dma_unmap_sg_attrs(struct device *dev, @@ -116,8 +66,8 @@ static inline void dma_unmap_sg_attrs(struct device *dev, enum dma_data_direction dir, struct dma_attrs *attrs) { - struct dma_mapping_ops *ops = platform_dma_get_ops(dev); - ops->unmap_sg_attrs(dev, sgl, nents, dir, attrs); + struct dma_map_ops *ops = platform_dma_get_ops(dev); + ops->unmap_sg(dev, sgl, nents, dir, attrs); } #define dma_map_sg(d, s, n, r) dma_map_sg_attrs(d, s, n, r, NULL) @@ -127,7 +77,7 @@ static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t daddr, size_t size, enum dma_data_direction dir) { - struct dma_mapping_ops *ops = platform_dma_get_ops(dev); + struct dma_map_ops *ops = platform_dma_get_ops(dev); ops->sync_single_for_cpu(dev, daddr, size, dir); } @@ -135,7 +85,7 @@ static inline void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir) { - struct dma_mapping_ops *ops = platform_dma_get_ops(dev); + struct dma_map_ops *ops = platform_dma_get_ops(dev); ops->sync_sg_for_cpu(dev, sgl, nents, dir); } @@ -144,7 +94,7 @@ static inline void dma_sync_single_for_device(struct device *dev, size_t size, enum dma_data_direction dir) { - struct dma_mapping_ops *ops = platform_dma_get_ops(dev); + struct dma_map_ops *ops = platform_dma_get_ops(dev); ops->sync_single_for_device(dev, daddr, size, dir); } @@ -153,20 +103,29 @@ static inline void dma_sync_sg_for_device(struct device *dev, int nents, enum dma_data_direction dir) { - struct dma_mapping_ops *ops = platform_dma_get_ops(dev); + struct dma_map_ops *ops = platform_dma_get_ops(dev); ops->sync_sg_for_device(dev, sgl, nents, dir); } static inline int dma_mapping_error(struct device *dev, dma_addr_t daddr) { - struct dma_mapping_ops *ops = platform_dma_get_ops(dev); + struct dma_map_ops *ops = platform_dma_get_ops(dev); return ops->mapping_error(dev, daddr); } -#define dma_map_page(dev, pg, off, size, dir) \ - dma_map_single(dev, page_address(pg) + (off), (size), (dir)) -#define dma_unmap_page(dev, dma_addr, size, dir) \ - dma_unmap_single(dev, dma_addr, size, dir) +static inline dma_addr_t dma_map_page(struct device *dev, struct page *page, + size_t offset, size_t size, + enum dma_data_direction dir) +{ + struct dma_map_ops *ops = platform_dma_get_ops(dev); + return ops->map_page(dev, page, offset, size, dir, NULL); +} + +static inline void dma_unmap_page(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir) +{ + dma_unmap_single(dev, addr, size, dir); +} /* * Rest of this file is part of the "Advanced DMA API". Use at your own risk. @@ -180,8 +139,8 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t daddr) static inline int dma_supported(struct device *dev, u64 mask) { - struct dma_mapping_ops *ops = platform_dma_get_ops(dev); - return ops->dma_supported_op(dev, mask); + struct dma_map_ops *ops = platform_dma_get_ops(dev); + return ops->dma_supported(dev, mask); } static inline int diff --git a/arch/ia64/include/asm/machvec.h b/arch/ia64/include/asm/machvec.h index 95e1708fa4e..e8442c7e4cc 100644 --- a/arch/ia64/include/asm/machvec.h +++ b/arch/ia64/include/asm/machvec.h @@ -11,7 +11,6 @@ #define _ASM_IA64_MACHVEC_H #include -#include /* forward declarations: */ struct device; @@ -24,6 +23,7 @@ struct task_struct; struct pci_dev; struct msi_desc; struct dma_attrs; +enum dma_data_direction; typedef void ia64_mv_setup_t (char **); typedef void ia64_mv_cpu_init_t (void); @@ -45,7 +45,7 @@ typedef void ia64_mv_kernel_launch_event_t(void); /* DMA-mapping interface: */ typedef void ia64_mv_dma_init (void); -typedef struct dma_mapping_ops *ia64_mv_dma_get_ops(struct device *); +typedef struct dma_map_ops *ia64_mv_dma_get_ops(struct device *); /* * WARNING: The legacy I/O space is _architected_. Platforms are @@ -97,8 +97,10 @@ machvec_noop_bus (struct pci_bus *bus) extern void machvec_setup (char **); extern void machvec_timer_interrupt (int, void *); -extern void machvec_dma_sync_single (struct device *, dma_addr_t, size_t, int); -extern void machvec_dma_sync_sg (struct device *, struct scatterlist *, int, int); +extern void machvec_dma_sync_single(struct device *, dma_addr_t, size_t, + enum dma_data_direction); +extern void machvec_dma_sync_sg(struct device *, struct scatterlist *, int, + enum dma_data_direction); extern void machvec_tlb_migrate_finish (struct mm_struct *); # if defined (CONFIG_IA64_HP_SIM) @@ -250,7 +252,7 @@ extern void machvec_init_from_cmdline(const char *cmdline); # endif /* CONFIG_IA64_GENERIC */ extern void swiotlb_dma_init(void); -extern struct dma_mapping_ops *dma_get_ops(struct device *); +extern struct dma_map_ops *dma_get_ops(struct device *); /* * Define default versions so we can extend machvec for new platforms without having diff --git a/arch/ia64/kernel/dma-mapping.c b/arch/ia64/kernel/dma-mapping.c index 427f6961722..7060e13fa42 100644 --- a/arch/ia64/kernel/dma-mapping.c +++ b/arch/ia64/kernel/dma-mapping.c @@ -1,9 +1,9 @@ #include -struct dma_mapping_ops *dma_ops; +struct dma_map_ops *dma_ops; EXPORT_SYMBOL(dma_ops); -struct dma_mapping_ops *dma_get_ops(struct device *dev) +struct dma_map_ops *dma_get_ops(struct device *dev) { return dma_ops; } diff --git a/arch/ia64/kernel/machvec.c b/arch/ia64/kernel/machvec.c index 7ccb228ceed..d41a40ef80c 100644 --- a/arch/ia64/kernel/machvec.c +++ b/arch/ia64/kernel/machvec.c @@ -1,5 +1,5 @@ #include - +#include #include #include @@ -75,14 +75,16 @@ machvec_timer_interrupt (int irq, void *dev_id) EXPORT_SYMBOL(machvec_timer_interrupt); void -machvec_dma_sync_single (struct device *hwdev, dma_addr_t dma_handle, size_t size, int dir) +machvec_dma_sync_single(struct device *hwdev, dma_addr_t dma_handle, size_t size, + enum dma_data_direction dir) { mb(); } EXPORT_SYMBOL(machvec_dma_sync_single); void -machvec_dma_sync_sg (struct device *hwdev, struct scatterlist *sg, int n, int dir) +machvec_dma_sync_sg(struct device *hwdev, struct scatterlist *sg, int n, + enum dma_data_direction dir) { mb(); } diff --git a/arch/ia64/kernel/pci-dma.c b/arch/ia64/kernel/pci-dma.c index 640669eba5d..b30209ec8c6 100644 --- a/arch/ia64/kernel/pci-dma.c +++ b/arch/ia64/kernel/pci-dma.c @@ -41,21 +41,7 @@ struct device fallback_dev = { .dma_mask = &fallback_dev.coherent_dma_mask, }; -extern struct dma_mapping_ops vtd_dma_ops; - -void __init pci_iommu_alloc(void) -{ - dma_ops = &vtd_dma_ops; - /* - * The order of these functions is important for - * fall-back/fail-over reasons - */ - detect_intel_iommu(); - -#ifdef CONFIG_SWIOTLB - pci_swiotlb_init(); -#endif -} +extern struct dma_map_ops intel_dma_ops; static int __init pci_iommu_init(void) { @@ -81,10 +67,10 @@ iommu_dma_init(void) int iommu_dma_supported(struct device *dev, u64 mask) { - struct dma_mapping_ops *ops = platform_dma_get_ops(dev); + struct dma_map_ops *ops = platform_dma_get_ops(dev); - if (ops->dma_supported_op) - return ops->dma_supported_op(dev, mask); + if (ops->dma_supported) + return ops->dma_supported(dev, mask); /* Copied from i386. Doesn't make much sense, because it will only work for pci_alloc_coherent. @@ -113,4 +99,31 @@ int iommu_dma_supported(struct device *dev, u64 mask) } EXPORT_SYMBOL(iommu_dma_supported); +static int vtd_dma_mapping_error(struct device *dev, dma_addr_t dma_addr) +{ + return 0; +} + +void __init pci_iommu_alloc(void) +{ + dma_ops = &intel_dma_ops; + + dma_ops->sync_single_for_cpu = machvec_dma_sync_single; + dma_ops->sync_sg_for_cpu = machvec_dma_sync_sg; + dma_ops->sync_single_for_device = machvec_dma_sync_single; + dma_ops->sync_sg_for_device = machvec_dma_sync_sg; + dma_ops->dma_supported = iommu_dma_supported; + dma_ops->mapping_error = vtd_dma_mapping_error; + + /* + * The order of these functions is important for + * fall-back/fail-over reasons + */ + detect_intel_iommu(); + +#ifdef CONFIG_SWIOTLB + pci_swiotlb_init(); +#endif +} + #endif diff --git a/arch/ia64/kernel/pci-swiotlb.c b/arch/ia64/kernel/pci-swiotlb.c index 9f172c86437..6bf8f66786b 100644 --- a/arch/ia64/kernel/pci-swiotlb.c +++ b/arch/ia64/kernel/pci-swiotlb.c @@ -16,24 +16,36 @@ EXPORT_SYMBOL(swiotlb); /* Set this to 1 if there is a HW IOMMU in the system */ int iommu_detected __read_mostly; -struct dma_mapping_ops swiotlb_dma_ops = { +static dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + return swiotlb_map_single_attrs(dev, page_address(page) + offset, size, + dir, attrs); +} + +static void swiotlb_unmap_page(struct device *dev, dma_addr_t dma_handle, + size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + swiotlb_unmap_single_attrs(dev, dma_handle, size, dir, attrs); +} + +struct dma_map_ops swiotlb_dma_ops = { .alloc_coherent = swiotlb_alloc_coherent, .free_coherent = swiotlb_free_coherent, - .map_single = swiotlb_map_single, - .unmap_single = swiotlb_unmap_single, - .map_single_attrs = swiotlb_map_single_attrs, - .unmap_single_attrs = swiotlb_unmap_single_attrs, - .map_sg_attrs = swiotlb_map_sg_attrs, - .unmap_sg_attrs = swiotlb_unmap_sg_attrs, + .map_page = swiotlb_map_page, + .unmap_page = swiotlb_unmap_page, + .map_sg = swiotlb_map_sg_attrs, + .unmap_sg = swiotlb_unmap_sg_attrs, .sync_single_for_cpu = swiotlb_sync_single_for_cpu, .sync_single_for_device = swiotlb_sync_single_for_device, .sync_single_range_for_cpu = swiotlb_sync_single_range_for_cpu, .sync_single_range_for_device = swiotlb_sync_single_range_for_device, .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu, .sync_sg_for_device = swiotlb_sync_sg_for_device, - .map_sg = swiotlb_map_sg, - .unmap_sg = swiotlb_unmap_sg, - .dma_supported_op = swiotlb_dma_supported, + .dma_supported = swiotlb_dma_supported, .mapping_error = swiotlb_dma_mapping_error, }; diff --git a/arch/ia64/sn/pci/pci_dma.c b/arch/ia64/sn/pci/pci_dma.c index efdd6949000..9c788f9cedf 100644 --- a/arch/ia64/sn/pci/pci_dma.c +++ b/arch/ia64/sn/pci/pci_dma.c @@ -10,7 +10,6 @@ */ #include -#include #include #include #include @@ -171,10 +170,12 @@ static void sn_dma_free_coherent(struct device *dev, size_t size, void *cpu_addr * TODO: simplify our interface; * figure out how to save dmamap handle so can use two step. */ -static dma_addr_t sn_dma_map_single_attrs(struct device *dev, void *cpu_addr, - size_t size, int direction, - struct dma_attrs *attrs) +static dma_addr_t sn_dma_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction dir, + struct dma_attrs *attrs) { + void *cpu_addr = page_address(page) + offset; dma_addr_t dma_addr; unsigned long phys_addr; struct pci_dev *pdev = to_pci_dev(dev); @@ -212,20 +213,20 @@ static dma_addr_t sn_dma_map_single_attrs(struct device *dev, void *cpu_addr, * by @dma_handle into the coherence domain. On SN, we're always cache * coherent, so we just need to free any ATEs associated with this mapping. */ -static void sn_dma_unmap_single_attrs(struct device *dev, dma_addr_t dma_addr, - size_t size, int direction, - struct dma_attrs *attrs) +static void sn_dma_unmap_page(struct device *dev, dma_addr_t dma_addr, + size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) { struct pci_dev *pdev = to_pci_dev(dev); struct sn_pcibus_provider *provider = SN_PCIDEV_BUSPROVIDER(pdev); BUG_ON(dev->bus != &pci_bus_type); - provider->dma_unmap(pdev, dma_addr, direction); + provider->dma_unmap(pdev, dma_addr, dir); } /** - * sn_dma_unmap_sg_attrs - unmap a DMA scatterlist + * sn_dma_unmap_sg - unmap a DMA scatterlist * @dev: device to unmap * @sg: scatterlist to unmap * @nhwentries: number of scatterlist entries @@ -234,9 +235,9 @@ static void sn_dma_unmap_single_attrs(struct device *dev, dma_addr_t dma_addr, * * Unmap a set of streaming mode DMA translations. */ -static void sn_dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sgl, - int nhwentries, int direction, - struct dma_attrs *attrs) +static void sn_dma_unmap_sg(struct device *dev, struct scatterlist *sgl, + int nhwentries, enum dma_data_direction dir, + struct dma_attrs *attrs) { int i; struct pci_dev *pdev = to_pci_dev(dev); @@ -246,14 +247,14 @@ static void sn_dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sgl, BUG_ON(dev->bus != &pci_bus_type); for_each_sg(sgl, sg, nhwentries, i) { - provider->dma_unmap(pdev, sg->dma_address, direction); + provider->dma_unmap(pdev, sg->dma_address, dir); sg->dma_address = (dma_addr_t) NULL; sg->dma_length = 0; } } /** - * sn_dma_map_sg_attrs - map a scatterlist for DMA + * sn_dma_map_sg - map a scatterlist for DMA * @dev: device to map for * @sg: scatterlist to map * @nhwentries: number of entries @@ -267,8 +268,9 @@ static void sn_dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sgl, * * Maps each entry of @sg for DMA. */ -static int sn_dma_map_sg_attrs(struct device *dev, struct scatterlist *sgl, - int nhwentries, int direction, struct dma_attrs *attrs) +static int sn_dma_map_sg(struct device *dev, struct scatterlist *sgl, + int nhwentries, enum dma_data_direction dir, + struct dma_attrs *attrs) { unsigned long phys_addr; struct scatterlist *saved_sg = sgl, *sg; @@ -305,8 +307,7 @@ static int sn_dma_map_sg_attrs(struct device *dev, struct scatterlist *sgl, * Free any successfully allocated entries. */ if (i > 0) - sn_dma_unmap_sg_attrs(dev, saved_sg, i, - direction, attrs); + sn_dma_unmap_sg(dev, saved_sg, i, dir, attrs); return 0; } @@ -317,25 +318,26 @@ static int sn_dma_map_sg_attrs(struct device *dev, struct scatterlist *sgl, } static void sn_dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, - size_t size, int direction) + size_t size, enum dma_data_direction dir) { BUG_ON(dev->bus != &pci_bus_type); } static void sn_dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle, - size_t size, int direction) + size_t size, + enum dma_data_direction dir) { BUG_ON(dev->bus != &pci_bus_type); } static void sn_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, - int nelems, int direction) + int nelems, enum dma_data_direction dir) { BUG_ON(dev->bus != &pci_bus_type); } static void sn_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, - int nelems, int direction) + int nelems, enum dma_data_direction dir) { BUG_ON(dev->bus != &pci_bus_type); } @@ -455,19 +457,19 @@ int sn_pci_legacy_write(struct pci_bus *bus, u16 port, u32 val, u8 size) return ret; } -static struct dma_mapping_ops sn_dma_ops = { +static struct dma_map_ops sn_dma_ops = { .alloc_coherent = sn_dma_alloc_coherent, .free_coherent = sn_dma_free_coherent, - .map_single_attrs = sn_dma_map_single_attrs, - .unmap_single_attrs = sn_dma_unmap_single_attrs, - .map_sg_attrs = sn_dma_map_sg_attrs, - .unmap_sg_attrs = sn_dma_unmap_sg_attrs, + .map_page = sn_dma_map_page, + .unmap_page = sn_dma_unmap_page, + .map_sg = sn_dma_map_sg, + .unmap_sg = sn_dma_unmap_sg, .sync_single_for_cpu = sn_dma_sync_single_for_cpu, .sync_sg_for_cpu = sn_dma_sync_sg_for_cpu, .sync_single_for_device = sn_dma_sync_single_for_device, .sync_sg_for_device = sn_dma_sync_sg_for_device, .mapping_error = sn_dma_mapping_error, - .dma_supported_op = sn_dma_supported, + .dma_supported = sn_dma_supported, }; void sn_dma_init(void) diff --git a/arch/x86/include/asm/device.h b/arch/x86/include/asm/device.h index 3c034f48fdb..4994a20acbc 100644 --- a/arch/x86/include/asm/device.h +++ b/arch/x86/include/asm/device.h @@ -6,7 +6,7 @@ struct dev_archdata { void *acpi_handle; #endif #ifdef CONFIG_X86_64 -struct dma_mapping_ops *dma_ops; +struct dma_map_ops *dma_ops; #endif #ifdef CONFIG_DMAR void *iommu; /* hook for IOMMU specific extension */ diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index b81f82268a1..5a347805a6c 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -17,50 +17,9 @@ extern int iommu_merge; extern struct device x86_dma_fallback_dev; extern int panic_on_overflow; -struct dma_mapping_ops { - int (*mapping_error)(struct device *dev, - dma_addr_t dma_addr); - void* (*alloc_coherent)(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp); - void (*free_coherent)(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle); - void (*sync_single_for_cpu)(struct device *hwdev, - dma_addr_t dma_handle, size_t size, - int direction); - void (*sync_single_for_device)(struct device *hwdev, - dma_addr_t dma_handle, size_t size, - int direction); - void (*sync_single_range_for_cpu)(struct device *hwdev, - dma_addr_t dma_handle, unsigned long offset, - size_t size, int direction); - void (*sync_single_range_for_device)(struct device *hwdev, - dma_addr_t dma_handle, unsigned long offset, - size_t size, int direction); - void (*sync_sg_for_cpu)(struct device *hwdev, - struct scatterlist *sg, int nelems, - int direction); - void (*sync_sg_for_device)(struct device *hwdev, - struct scatterlist *sg, int nelems, - int direction); - int (*map_sg)(struct device *hwdev, struct scatterlist *sg, - int nents, int direction); - void (*unmap_sg)(struct device *hwdev, - struct scatterlist *sg, int nents, - int direction); - dma_addr_t (*map_page)(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction dir, - struct dma_attrs *attrs); - void (*unmap_page)(struct device *dev, dma_addr_t dma_handle, - size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs); - int (*dma_supported)(struct device *hwdev, u64 mask); - int is_phys; -}; - -extern struct dma_mapping_ops *dma_ops; - -static inline struct dma_mapping_ops *get_dma_ops(struct device *dev) +extern struct dma_map_ops *dma_ops; + +static inline struct dma_map_ops *get_dma_ops(struct device *dev) { #ifdef CONFIG_X86_32 return dma_ops; @@ -75,7 +34,7 @@ static inline struct dma_mapping_ops *get_dma_ops(struct device *dev) /* Make sure we keep the same behaviour */ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { - struct dma_mapping_ops *ops = get_dma_ops(dev); + struct dma_map_ops *ops = get_dma_ops(dev); if (ops->mapping_error) return ops->mapping_error(dev, dma_addr); @@ -94,138 +53,139 @@ extern void *dma_generic_alloc_coherent(struct device *dev, size_t size, static inline dma_addr_t dma_map_single(struct device *hwdev, void *ptr, size_t size, - int direction) + enum dma_data_direction dir) { - struct dma_mapping_ops *ops = get_dma_ops(hwdev); + struct dma_map_ops *ops = get_dma_ops(hwdev); - BUG_ON(!valid_dma_direction(direction)); + BUG_ON(!valid_dma_direction(dir)); return ops->map_page(hwdev, virt_to_page(ptr), (unsigned long)ptr & ~PAGE_MASK, size, - direction, NULL); + dir, NULL); } static inline void dma_unmap_single(struct device *dev, dma_addr_t addr, size_t size, - int direction) + enum dma_data_direction dir) { - struct dma_mapping_ops *ops = get_dma_ops(dev); + struct dma_map_ops *ops = get_dma_ops(dev); - BUG_ON(!valid_dma_direction(direction)); + BUG_ON(!valid_dma_direction(dir)); if (ops->unmap_page) - ops->unmap_page(dev, addr, size, direction, NULL); + ops->unmap_page(dev, addr, size, dir, NULL); } static inline int dma_map_sg(struct device *hwdev, struct scatterlist *sg, - int nents, int direction) + int nents, enum dma_data_direction dir) { - struct dma_mapping_ops *ops = get_dma_ops(hwdev); + struct dma_map_ops *ops = get_dma_ops(hwdev); - BUG_ON(!valid_dma_direction(direction)); - return ops->map_sg(hwdev, sg, nents, direction); + BUG_ON(!valid_dma_direction(dir)); + return ops->map_sg(hwdev, sg, nents, dir, NULL); } static inline void dma_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nents, - int direction) + enum dma_data_direction dir) { - struct dma_mapping_ops *ops = get_dma_ops(hwdev); + struct dma_map_ops *ops = get_dma_ops(hwdev); - BUG_ON(!valid_dma_direction(direction)); + BUG_ON(!valid_dma_direction(dir)); if (ops->unmap_sg) - ops->unmap_sg(hwdev, sg, nents, direction); + ops->unmap_sg(hwdev, sg, nents, dir, NULL); } static inline void dma_sync_single_for_cpu(struct device *hwdev, dma_addr_t dma_handle, - size_t size, int direction) + size_t size, enum dma_data_direction dir) { - struct dma_mapping_ops *ops = get_dma_ops(hwdev); + struct dma_map_ops *ops = get_dma_ops(hwdev); - BUG_ON(!valid_dma_direction(direction)); + BUG_ON(!valid_dma_direction(dir)); if (ops->sync_single_for_cpu) - ops->sync_single_for_cpu(hwdev, dma_handle, size, direction); + ops->sync_single_for_cpu(hwdev, dma_handle, size, dir); flush_write_buffers(); } static inline void dma_sync_single_for_device(struct device *hwdev, dma_addr_t dma_handle, - size_t size, int direction) + size_t size, enum dma_data_direction dir) { - struct dma_mapping_ops *ops = get_dma_ops(hwdev); + struct dma_map_ops *ops = get_dma_ops(hwdev); - BUG_ON(!valid_dma_direction(direction)); + BUG_ON(!valid_dma_direction(dir)); if (ops->sync_single_for_device) - ops->sync_single_for_device(hwdev, dma_handle, size, direction); + ops->sync_single_for_device(hwdev, dma_handle, size, dir); flush_write_buffers(); } static inline void dma_sync_single_range_for_cpu(struct device *hwdev, dma_addr_t dma_handle, - unsigned long offset, size_t size, int direction) + unsigned long offset, size_t size, + enum dma_data_direction dir) { - struct dma_mapping_ops *ops = get_dma_ops(hwdev); + struct dma_map_ops *ops = get_dma_ops(hwdev); - BUG_ON(!valid_dma_direction(direction)); + BUG_ON(!valid_dma_direction(dir)); if (ops->sync_single_range_for_cpu) ops->sync_single_range_for_cpu(hwdev, dma_handle, offset, - size, direction); + size, dir); flush_write_buffers(); } static inline void dma_sync_single_range_for_device(struct device *hwdev, dma_addr_t dma_handle, unsigned long offset, size_t size, - int direction) + enum dma_data_direction dir) { - struct dma_mapping_ops *ops = get_dma_ops(hwdev); + struct dma_map_ops *ops = get_dma_ops(hwdev); - BUG_ON(!valid_dma_direction(direction)); + BUG_ON(!valid_dma_direction(dir)); if (ops->sync_single_range_for_device) ops->sync_single_range_for_device(hwdev, dma_handle, - offset, size, direction); + offset, size, dir); flush_write_buffers(); } static inline void dma_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg, - int nelems, int direction) + int nelems, enum dma_data_direction dir) { - struct dma_mapping_ops *ops = get_dma_ops(hwdev); + struct dma_map_ops *ops = get_dma_ops(hwdev); - BUG_ON(!valid_dma_direction(direction)); + BUG_ON(!valid_dma_direction(dir)); if (ops->sync_sg_for_cpu) - ops->sync_sg_for_cpu(hwdev, sg, nelems, direction); + ops->sync_sg_for_cpu(hwdev, sg, nelems, dir); flush_write_buffers(); } static inline void dma_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg, - int nelems, int direction) + int nelems, enum dma_data_direction dir) { - struct dma_mapping_ops *ops = get_dma_ops(hwdev); + struct dma_map_ops *ops = get_dma_ops(hwdev); - BUG_ON(!valid_dma_direction(direction)); + BUG_ON(!valid_dma_direction(dir)); if (ops->sync_sg_for_device) - ops->sync_sg_for_device(hwdev, sg, nelems, direction); + ops->sync_sg_for_device(hwdev, sg, nelems, dir); flush_write_buffers(); } static inline dma_addr_t dma_map_page(struct device *dev, struct page *page, size_t offset, size_t size, - int direction) + enum dma_data_direction dir) { - struct dma_mapping_ops *ops = get_dma_ops(dev); + struct dma_map_ops *ops = get_dma_ops(dev); - BUG_ON(!valid_dma_direction(direction)); - return ops->map_page(dev, page, offset, size, direction, NULL); + BUG_ON(!valid_dma_direction(dir)); + return ops->map_page(dev, page, offset, size, dir, NULL); } static inline void dma_unmap_page(struct device *dev, dma_addr_t addr, - size_t size, int direction) + size_t size, enum dma_data_direction dir) { - dma_unmap_single(dev, addr, size, direction); + dma_unmap_single(dev, addr, size, dir); } static inline void @@ -271,7 +231,7 @@ static inline void * dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp) { - struct dma_mapping_ops *ops = get_dma_ops(dev); + struct dma_map_ops *ops = get_dma_ops(dev); void *memory; gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32); @@ -297,7 +257,7 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, static inline void dma_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t bus) { - struct dma_mapping_ops *ops = get_dma_ops(dev); + struct dma_map_ops *ops = get_dma_ops(dev); WARN_ON(irqs_disabled()); /* for portability */ diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h index a6ee9e6f530..af326a2975b 100644 --- a/arch/x86/include/asm/iommu.h +++ b/arch/x86/include/asm/iommu.h @@ -3,7 +3,7 @@ extern void pci_iommu_shutdown(void); extern void no_iommu_init(void); -extern struct dma_mapping_ops nommu_dma_ops; +extern struct dma_map_ops nommu_dma_ops; extern int force_iommu, no_iommu; extern int iommu_detected; diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c index a5dedb690a9..008e522b953 100644 --- a/arch/x86/kernel/amd_iommu.c +++ b/arch/x86/kernel/amd_iommu.c @@ -1394,7 +1394,8 @@ static int map_sg_no_iommu(struct device *dev, struct scatterlist *sglist, * lists). */ static int map_sg(struct device *dev, struct scatterlist *sglist, - int nelems, int dir) + int nelems, enum dma_data_direction dir, + struct dma_attrs *attrs) { unsigned long flags; struct amd_iommu *iommu; @@ -1461,7 +1462,8 @@ unmap: * lists). */ static void unmap_sg(struct device *dev, struct scatterlist *sglist, - int nelems, int dir) + int nelems, enum dma_data_direction dir, + struct dma_attrs *attrs) { unsigned long flags; struct amd_iommu *iommu; @@ -1648,7 +1650,7 @@ static void prealloc_protection_domains(void) } } -static struct dma_mapping_ops amd_iommu_dma_ops = { +static struct dma_map_ops amd_iommu_dma_ops = { .alloc_coherent = alloc_coherent, .free_coherent = free_coherent, .map_page = map_page, diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index 756138b604e..755c21e906f 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -380,8 +380,9 @@ static inline struct iommu_table *find_iommu_table(struct device *dev) return tbl; } -static void calgary_unmap_sg(struct device *dev, - struct scatterlist *sglist, int nelems, int direction) +static void calgary_unmap_sg(struct device *dev, struct scatterlist *sglist, + int nelems,enum dma_data_direction dir, + struct dma_attrs *attrs) { struct iommu_table *tbl = find_iommu_table(dev); struct scatterlist *s; @@ -404,7 +405,8 @@ static void calgary_unmap_sg(struct device *dev, } static int calgary_map_sg(struct device *dev, struct scatterlist *sg, - int nelems, int direction) + int nelems, enum dma_data_direction dir, + struct dma_attrs *attrs) { struct iommu_table *tbl = find_iommu_table(dev); struct scatterlist *s; @@ -429,15 +431,14 @@ static int calgary_map_sg(struct device *dev, struct scatterlist *sg, s->dma_address = (entry << PAGE_SHIFT) | s->offset; /* insert into HW table */ - tce_build(tbl, entry, npages, vaddr & PAGE_MASK, - direction); + tce_build(tbl, entry, npages, vaddr & PAGE_MASK, dir); s->dma_length = s->length; } return nelems; error: - calgary_unmap_sg(dev, sg, nelems, direction); + calgary_unmap_sg(dev, sg, nelems, dir, NULL); for_each_sg(sg, s, nelems, i) { sg->dma_address = bad_dma_address; sg->dma_length = 0; @@ -518,7 +519,7 @@ static void calgary_free_coherent(struct device *dev, size_t size, free_pages((unsigned long)vaddr, get_order(size)); } -static struct dma_mapping_ops calgary_dma_ops = { +static struct dma_map_ops calgary_dma_ops = { .alloc_coherent = calgary_alloc_coherent, .free_coherent = calgary_free_coherent, .map_sg = calgary_map_sg, diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 19a1044a0cd..0d75c129b18 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -12,7 +12,7 @@ static int forbid_dac __read_mostly; -struct dma_mapping_ops *dma_ops; +struct dma_map_ops *dma_ops; EXPORT_SYMBOL(dma_ops); static int iommu_sac_force __read_mostly; @@ -224,7 +224,7 @@ early_param("iommu", iommu_setup); int dma_supported(struct device *dev, u64 mask) { - struct dma_mapping_ops *ops = get_dma_ops(dev); + struct dma_map_ops *ops = get_dma_ops(dev); #ifdef CONFIG_PCI if (mask > 0xffffffff && forbid_dac > 0) { diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index 9c557c0c928..8cb3e45439c 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -302,8 +302,8 @@ static void gart_unmap_page(struct device *dev, dma_addr_t dma_addr, /* * Wrapper for pci_unmap_single working with scatterlists. */ -static void -gart_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, int dir) +static void gart_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction dir, struct dma_attrs *attrs) { struct scatterlist *s; int i; @@ -333,7 +333,7 @@ static int dma_map_sg_nonforce(struct device *dev, struct scatterlist *sg, addr = dma_map_area(dev, addr, s->length, dir, 0); if (addr == bad_dma_address) { if (i > 0) - gart_unmap_sg(dev, sg, i, dir); + gart_unmap_sg(dev, sg, i, dir, NULL); nents = 0; sg[0].dma_length = 0; break; @@ -404,8 +404,8 @@ dma_map_cont(struct device *dev, struct scatterlist *start, int nelems, * DMA map all entries in a scatterlist. * Merge chunks that have page aligned sizes into a continuous mapping. */ -static int -gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir) +static int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction dir, struct dma_attrs *attrs) { struct scatterlist *s, *ps, *start_sg, *sgmap; int need = 0, nextneed, i, out, start; @@ -472,7 +472,7 @@ gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir) error: flush_gart(); - gart_unmap_sg(dev, sg, out, dir); + gart_unmap_sg(dev, sg, out, dir, NULL); /* When it was forced or merged try again in a dumb way */ if (force_iommu || iommu_merge) { @@ -711,7 +711,7 @@ static __init int init_k8_gatt(struct agp_kern_info *info) return -1; } -static struct dma_mapping_ops gart_dma_ops = { +static struct dma_map_ops gart_dma_ops = { .map_sg = gart_map_sg, .unmap_sg = gart_unmap_sg, .map_page = gart_map_page, diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c index d42b69c90b4..fe50214db87 100644 --- a/arch/x86/kernel/pci-nommu.c +++ b/arch/x86/kernel/pci-nommu.c @@ -54,7 +54,8 @@ static dma_addr_t nommu_map_page(struct device *dev, struct page *page, * the same here. */ static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg, - int nents, int direction) + int nents, enum dma_data_direction dir, + struct dma_attrs *attrs) { struct scatterlist *s; int i; @@ -78,7 +79,7 @@ static void nommu_free_coherent(struct device *dev, size_t size, void *vaddr, free_pages((unsigned long)vaddr, get_order(size)); } -struct dma_mapping_ops nommu_dma_ops = { +struct dma_map_ops nommu_dma_ops = { .alloc_coherent = dma_generic_alloc_coherent, .free_coherent = nommu_free_coherent, .map_sg = nommu_map_sg, diff --git a/arch/x86/kernel/pci-swiotlb_64.c b/arch/x86/kernel/pci-swiotlb_64.c index 3ae354c0fde..3f0d9924dd1 100644 --- a/arch/x86/kernel/pci-swiotlb_64.c +++ b/arch/x86/kernel/pci-swiotlb_64.c @@ -67,7 +67,7 @@ static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, return swiotlb_alloc_coherent(hwdev, size, dma_handle, flags); } -struct dma_mapping_ops swiotlb_dma_ops = { +struct dma_map_ops swiotlb_dma_ops = { .mapping_error = swiotlb_dma_mapping_error, .alloc_coherent = x86_swiotlb_alloc_coherent, .free_coherent = swiotlb_free_coherent, @@ -77,8 +77,8 @@ struct dma_mapping_ops swiotlb_dma_ops = { .sync_single_range_for_device = swiotlb_sync_single_range_for_device, .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu, .sync_sg_for_device = swiotlb_sync_sg_for_device, - .map_sg = swiotlb_map_sg, - .unmap_sg = swiotlb_unmap_sg, + .map_sg = swiotlb_map_sg_attrs, + .unmap_sg = swiotlb_unmap_sg_attrs, .map_page = swiotlb_map_page, .unmap_page = swiotlb_unmap_page, .dma_supported = NULL, diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c index da273e4ef66..b9a56293390 100644 --- a/drivers/pci/intel-iommu.c +++ b/drivers/pci/intel-iommu.c @@ -2441,7 +2441,8 @@ void intel_free_coherent(struct device *hwdev, size_t size, void *vaddr, #define SG_ENT_VIRT_ADDRESS(sg) (sg_virt((sg))) void intel_unmap_sg(struct device *hwdev, struct scatterlist *sglist, - int nelems, int dir) + int nelems, enum dma_data_direction dir, + struct dma_attrs *attrs) { int i; struct pci_dev *pdev = to_pci_dev(hwdev); @@ -2499,7 +2500,7 @@ static int intel_nontranslate_map_sg(struct device *hddev, } int intel_map_sg(struct device *hwdev, struct scatterlist *sglist, int nelems, - int dir) + enum dma_data_direction dir, struct dma_attrs *attrs) { void *addr; int i; @@ -2579,15 +2580,13 @@ int intel_map_sg(struct device *hwdev, struct scatterlist *sglist, int nelems, return nelems; } -static struct dma_mapping_ops intel_dma_ops = { +struct dma_map_ops intel_dma_ops = { .alloc_coherent = intel_alloc_coherent, .free_coherent = intel_free_coherent, .map_sg = intel_map_sg, .unmap_sg = intel_unmap_sg, -#ifdef CONFIG_X86_64 .map_page = intel_map_page, .unmap_page = intel_unmap_page, -#endif }; static inline int iommu_domain_cache_init(void) diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index c4f6c101dbc..a254db1decd 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -334,7 +334,9 @@ extern void *intel_alloc_coherent(struct device *, size_t, dma_addr_t *, gfp_t); extern void intel_free_coherent(struct device *, size_t, void *, dma_addr_t); extern dma_addr_t intel_map_single(struct device *, phys_addr_t, size_t, int); extern void intel_unmap_single(struct device *, dma_addr_t, size_t, int); -extern int intel_map_sg(struct device *, struct scatterlist *, int, int); -extern void intel_unmap_sg(struct device *, struct scatterlist *, int, int); +extern int intel_map_sg(struct device *, struct scatterlist *, int, + enum dma_data_direction, struct dma_attrs *); +extern void intel_unmap_sg(struct device *, struct scatterlist *, int, + enum dma_data_direction, struct dma_attrs *); #endif diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index dedd3c0cfe3..0567c3d8633 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -66,36 +66,38 @@ swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nents, extern int swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems, - int dir, struct dma_attrs *attrs); + enum dma_data_direction dir, struct dma_attrs *attrs); extern void swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl, - int nelems, int dir, struct dma_attrs *attrs); + int nelems, enum dma_data_direction dir, + struct dma_attrs *attrs); extern void swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr, - size_t size, int dir); + size_t size, enum dma_data_direction dir); extern void swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg, - int nelems, int dir); + int nelems, enum dma_data_direction dir); extern void swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr, - size_t size, int dir); + size_t size, enum dma_data_direction dir); extern void swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg, - int nelems, int dir); + int nelems, enum dma_data_direction dir); extern void swiotlb_sync_single_range_for_cpu(struct device *hwdev, dma_addr_t dev_addr, - unsigned long offset, size_t size, int dir); + unsigned long offset, size_t size, + enum dma_data_direction dir); extern void swiotlb_sync_single_range_for_device(struct device *hwdev, dma_addr_t dev_addr, unsigned long offset, size_t size, - int dir); + enum dma_data_direction dir); extern int swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr); diff --git a/lib/swiotlb.c b/lib/swiotlb.c index 48deef7e197..d047de990a3 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -736,7 +736,7 @@ swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr, void swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr, - size_t size, int dir) + size_t size, enum dma_data_direction dir) { swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_CPU); } @@ -744,7 +744,7 @@ EXPORT_SYMBOL(swiotlb_sync_single_for_cpu); void swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr, - size_t size, int dir) + size_t size, enum dma_data_direction dir) { swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_DEVICE); } @@ -769,7 +769,8 @@ swiotlb_sync_single_range(struct device *hwdev, dma_addr_t dev_addr, void swiotlb_sync_single_range_for_cpu(struct device *hwdev, dma_addr_t dev_addr, - unsigned long offset, size_t size, int dir) + unsigned long offset, size_t size, + enum dma_data_direction dir) { swiotlb_sync_single_range(hwdev, dev_addr, offset, size, dir, SYNC_FOR_CPU); @@ -778,7 +779,8 @@ EXPORT_SYMBOL_GPL(swiotlb_sync_single_range_for_cpu); void swiotlb_sync_single_range_for_device(struct device *hwdev, dma_addr_t dev_addr, - unsigned long offset, size_t size, int dir) + unsigned long offset, size_t size, + enum dma_data_direction dir) { swiotlb_sync_single_range(hwdev, dev_addr, offset, size, dir, SYNC_FOR_DEVICE); @@ -803,7 +805,7 @@ EXPORT_SYMBOL_GPL(swiotlb_sync_single_range_for_device); */ int swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems, - int dir, struct dma_attrs *attrs) + enum dma_data_direction dir, struct dma_attrs *attrs) { struct scatterlist *sg; int i; @@ -850,7 +852,7 @@ EXPORT_SYMBOL(swiotlb_map_sg); */ void swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl, - int nelems, int dir, struct dma_attrs *attrs) + int nelems, enum dma_data_direction dir, struct dma_attrs *attrs) { struct scatterlist *sg; int i; @@ -902,7 +904,7 @@ swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sgl, void swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg, - int nelems, int dir) + int nelems, enum dma_data_direction dir) { swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_CPU); } @@ -910,7 +912,7 @@ EXPORT_SYMBOL(swiotlb_sync_sg_for_cpu); void swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg, - int nelems, int dir) + int nelems, enum dma_data_direction dir) { swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_DEVICE); } -- cgit v1.2.3-70-g09d2 From cb9eff097831007afb30d64373f29d99825d0068 Mon Sep 17 00:00:00 2001 From: Patrick Ohly Date: Thu, 12 Feb 2009 05:03:36 +0000 Subject: net: new user space API for time stamping of incoming and outgoing packets User space can request hardware and/or software time stamping. Reporting of the result(s) via a new control message is enabled separately for each field in the message because some of the fields may require additional computation and thus cause overhead. User space can tell the different kinds of time stamps apart and choose what suits its needs. When a TX timestamp operation is requested, the TX skb will be cloned and the clone will be time stamped (in hardware or software) and added to the socket error queue of the skb, if the skb has a socket associated with it. The actual TX timestamp will reach userspace as a RX timestamp on the cloned packet. If timestamping is requested and no timestamping is done in the device driver (potentially this may use hardware timestamping), it will be done in software after the device's start_hard_xmit routine. Signed-off-by: Patrick Ohly Signed-off-by: David S. Miller --- Documentation/networking/timestamping.txt | 178 +++++++ Documentation/networking/timestamping/.gitignore | 1 + Documentation/networking/timestamping/Makefile | 6 + .../networking/timestamping/timestamping.c | 533 +++++++++++++++++++++ arch/alpha/include/asm/socket.h | 3 + arch/arm/include/asm/socket.h | 3 + arch/avr32/include/asm/socket.h | 3 + arch/blackfin/include/asm/socket.h | 3 + arch/cris/include/asm/socket.h | 3 + arch/h8300/include/asm/socket.h | 3 + arch/ia64/include/asm/socket.h | 3 + arch/m68k/include/asm/socket.h | 3 + arch/mips/include/asm/socket.h | 3 + arch/parisc/include/asm/socket.h | 3 + arch/powerpc/include/asm/socket.h | 3 + arch/s390/include/asm/socket.h | 3 + arch/sh/include/asm/socket.h | 3 + arch/sparc/include/asm/socket.h | 3 + arch/x86/include/asm/socket.h | 3 + arch/xtensa/include/asm/socket.h | 3 + include/asm-frv/socket.h | 3 + include/asm-m32r/socket.h | 3 + include/asm-mn10300/socket.h | 3 + include/linux/errqueue.h | 1 + include/linux/net_tstamp.h | 104 ++++ include/linux/sockios.h | 3 + 26 files changed, 883 insertions(+) create mode 100644 Documentation/networking/timestamping.txt create mode 100644 Documentation/networking/timestamping/.gitignore create mode 100644 Documentation/networking/timestamping/Makefile create mode 100644 Documentation/networking/timestamping/timestamping.c create mode 100644 include/linux/net_tstamp.h (limited to 'arch/x86/include') diff --git a/Documentation/networking/timestamping.txt b/Documentation/networking/timestamping.txt new file mode 100644 index 00000000000..a681a65b5bc --- /dev/null +++ b/Documentation/networking/timestamping.txt @@ -0,0 +1,178 @@ +The existing interfaces for getting network packages time stamped are: + +* SO_TIMESTAMP + Generate time stamp for each incoming packet using the (not necessarily + monotonous!) system time. Result is returned via recv_msg() in a + control message as timeval (usec resolution). + +* SO_TIMESTAMPNS + Same time stamping mechanism as SO_TIMESTAMP, but returns result as + timespec (nsec resolution). + +* IP_MULTICAST_LOOP + SO_TIMESTAMP[NS] + Only for multicasts: approximate send time stamp by receiving the looped + packet and using its receive time stamp. + +The following interface complements the existing ones: receive time +stamps can be generated and returned for arbitrary packets and much +closer to the point where the packet is really sent. Time stamps can +be generated in software (as before) or in hardware (if the hardware +has such a feature). + +SO_TIMESTAMPING: + +Instructs the socket layer which kind of information is wanted. The +parameter is an integer with some of the following bits set. Setting +other bits is an error and doesn't change the current state. + +SOF_TIMESTAMPING_TX_HARDWARE: try to obtain send time stamp in hardware +SOF_TIMESTAMPING_TX_SOFTWARE: if SOF_TIMESTAMPING_TX_HARDWARE is off or + fails, then do it in software +SOF_TIMESTAMPING_RX_HARDWARE: return the original, unmodified time stamp + as generated by the hardware +SOF_TIMESTAMPING_RX_SOFTWARE: if SOF_TIMESTAMPING_RX_HARDWARE is off or + fails, then do it in software +SOF_TIMESTAMPING_RAW_HARDWARE: return original raw hardware time stamp +SOF_TIMESTAMPING_SYS_HARDWARE: return hardware time stamp transformed to + the system time base +SOF_TIMESTAMPING_SOFTWARE: return system time stamp generated in + software + +SOF_TIMESTAMPING_TX/RX determine how time stamps are generated. +SOF_TIMESTAMPING_RAW/SYS determine how they are reported in the +following control message: + struct scm_timestamping { + struct timespec systime; + struct timespec hwtimetrans; + struct timespec hwtimeraw; + }; + +recvmsg() can be used to get this control message for regular incoming +packets. For send time stamps the outgoing packet is looped back to +the socket's error queue with the send time stamp(s) attached. It can +be received with recvmsg(flags=MSG_ERRQUEUE). The call returns the +original outgoing packet data including all headers preprended down to +and including the link layer, the scm_timestamping control message and +a sock_extended_err control message with ee_errno==ENOMSG and +ee_origin==SO_EE_ORIGIN_TIMESTAMPING. A socket with such a pending +bounced packet is ready for reading as far as select() is concerned. + +All three values correspond to the same event in time, but were +generated in different ways. Each of these values may be empty (= all +zero), in which case no such value was available. If the application +is not interested in some of these values, they can be left blank to +avoid the potential overhead of calculating them. + +systime is the value of the system time at that moment. This +corresponds to the value also returned via SO_TIMESTAMP[NS]. If the +time stamp was generated by hardware, then this field is +empty. Otherwise it is filled in if SOF_TIMESTAMPING_SOFTWARE is +set. + +hwtimeraw is the original hardware time stamp. Filled in if +SOF_TIMESTAMPING_RAW_HARDWARE is set. No assumptions about its +relation to system time should be made. + +hwtimetrans is the hardware time stamp transformed so that it +corresponds as good as possible to system time. This correlation is +not perfect; as a consequence, sorting packets received via different +NICs by their hwtimetrans may differ from the order in which they were +received. hwtimetrans may be non-monotonic even for the same NIC. +Filled in if SOF_TIMESTAMPING_SYS_HARDWARE is set. Requires support +by the network device and will be empty without that support. + + +SIOCSHWTSTAMP: + +Hardware time stamping must also be initialized for each device driver +that is expected to do hardware time stamping. The parameter is: + +struct hwtstamp_config { + int flags; /* no flags defined right now, must be zero */ + int tx_type; /* HWTSTAMP_TX_* */ + int rx_filter; /* HWTSTAMP_FILTER_* */ +}; + +Desired behavior is passed into the kernel and to a specific device by +calling ioctl(SIOCSHWTSTAMP) with a pointer to a struct ifreq whose +ifr_data points to a struct hwtstamp_config. The tx_type and +rx_filter are hints to the driver what it is expected to do. If +the requested fine-grained filtering for incoming packets is not +supported, the driver may time stamp more than just the requested types +of packets. + +A driver which supports hardware time stamping shall update the struct +with the actual, possibly more permissive configuration. If the +requested packets cannot be time stamped, then nothing should be +changed and ERANGE shall be returned (in contrast to EINVAL, which +indicates that SIOCSHWTSTAMP is not supported at all). + +Only a processes with admin rights may change the configuration. User +space is responsible to ensure that multiple processes don't interfere +with each other and that the settings are reset. + +/* possible values for hwtstamp_config->tx_type */ +enum { + /* + * no outgoing packet will need hardware time stamping; + * should a packet arrive which asks for it, no hardware + * time stamping will be done + */ + HWTSTAMP_TX_OFF, + + /* + * enables hardware time stamping for outgoing packets; + * the sender of the packet decides which are to be + * time stamped by setting SOF_TIMESTAMPING_TX_SOFTWARE + * before sending the packet + */ + HWTSTAMP_TX_ON, +}; + +/* possible values for hwtstamp_config->rx_filter */ +enum { + /* time stamp no incoming packet at all */ + HWTSTAMP_FILTER_NONE, + + /* time stamp any incoming packet */ + HWTSTAMP_FILTER_ALL, + + /* return value: time stamp all packets requested plus some others */ + HWTSTAMP_FILTER_SOME, + + /* PTP v1, UDP, any kind of event packet */ + HWTSTAMP_FILTER_PTP_V1_L4_EVENT, + + ... +}; + + +DEVICE IMPLEMENTATION + +A driver which supports hardware time stamping must support the +SIOCSHWTSTAMP ioctl. Time stamps for received packets must be stored +in the skb with skb_hwtstamp_set(). + +Time stamps for outgoing packets are to be generated as follows: +- In hard_start_xmit(), check if skb_hwtstamp_check_tx_hardware() + returns non-zero. If yes, then the driver is expected + to do hardware time stamping. +- If this is possible for the skb and requested, then declare + that the driver is doing the time stamping by calling + skb_hwtstamp_tx_in_progress(). A driver not supporting + hardware time stamping doesn't do that. A driver must never + touch sk_buff::tstamp! It is used to store how time stamping + for an outgoing packets is to be done. +- As soon as the driver has sent the packet and/or obtained a + hardware time stamp for it, it passes the time stamp back by + calling skb_hwtstamp_tx() with the original skb, the raw + hardware time stamp and a handle to the device (necessary + to convert the hardware time stamp to system time). If obtaining + the hardware time stamp somehow fails, then the driver should + not fall back to software time stamping. The rationale is that + this would occur at a later time in the processing pipeline + than other software time stamping and therefore could lead + to unexpected deltas between time stamps. +- If the driver did not call skb_hwtstamp_tx_in_progress(), then + dev_hard_start_xmit() checks whether software time stamping + is wanted as fallback and potentially generates the time stamp. diff --git a/Documentation/networking/timestamping/.gitignore b/Documentation/networking/timestamping/.gitignore new file mode 100644 index 00000000000..71e81eb2e22 --- /dev/null +++ b/Documentation/networking/timestamping/.gitignore @@ -0,0 +1 @@ +timestamping diff --git a/Documentation/networking/timestamping/Makefile b/Documentation/networking/timestamping/Makefile new file mode 100644 index 00000000000..2a1489fdc03 --- /dev/null +++ b/Documentation/networking/timestamping/Makefile @@ -0,0 +1,6 @@ +CPPFLAGS = -I../../../include + +timestamping: timestamping.c + +clean: + rm -f timestamping diff --git a/Documentation/networking/timestamping/timestamping.c b/Documentation/networking/timestamping/timestamping.c new file mode 100644 index 00000000000..43d14310421 --- /dev/null +++ b/Documentation/networking/timestamping/timestamping.c @@ -0,0 +1,533 @@ +/* + * This program demonstrates how the various time stamping features in + * the Linux kernel work. It emulates the behavior of a PTP + * implementation in stand-alone master mode by sending PTPv1 Sync + * multicasts once every second. It looks for similar packets, but + * beyond that doesn't actually implement PTP. + * + * Outgoing packets are time stamped with SO_TIMESTAMPING with or + * without hardware support. + * + * Incoming packets are time stamped with SO_TIMESTAMPING with or + * without hardware support, SIOCGSTAMP[NS] (per-socket time stamp) and + * SO_TIMESTAMP[NS]. + * + * Copyright (C) 2009 Intel Corporation. + * Author: Patrick Ohly + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. * See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + */ + +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include + +#include "asm/types.h" +#include "linux/net_tstamp.h" +#include "linux/errqueue.h" + +#ifndef SO_TIMESTAMPING +# define SO_TIMESTAMPING 37 +# define SCM_TIMESTAMPING SO_TIMESTAMPING +#endif + +#ifndef SO_TIMESTAMPNS +# define SO_TIMESTAMPNS 35 +#endif + +#ifndef SIOCGSTAMPNS +# define SIOCGSTAMPNS 0x8907 +#endif + +#ifndef SIOCSHWTSTAMP +# define SIOCSHWTSTAMP 0x89b0 +#endif + +static void usage(const char *error) +{ + if (error) + printf("invalid option: %s\n", error); + printf("timestamping interface option*\n\n" + "Options:\n" + " IP_MULTICAST_LOOP - looping outgoing multicasts\n" + " SO_TIMESTAMP - normal software time stamping, ms resolution\n" + " SO_TIMESTAMPNS - more accurate software time stamping\n" + " SOF_TIMESTAMPING_TX_HARDWARE - hardware time stamping of outgoing packets\n" + " SOF_TIMESTAMPING_TX_SOFTWARE - software fallback for outgoing packets\n" + " SOF_TIMESTAMPING_RX_HARDWARE - hardware time stamping of incoming packets\n" + " SOF_TIMESTAMPING_RX_SOFTWARE - software fallback for incoming packets\n" + " SOF_TIMESTAMPING_SOFTWARE - request reporting of software time stamps\n" + " SOF_TIMESTAMPING_SYS_HARDWARE - request reporting of transformed HW time stamps\n" + " SOF_TIMESTAMPING_RAW_HARDWARE - request reporting of raw HW time stamps\n" + " SIOCGSTAMP - check last socket time stamp\n" + " SIOCGSTAMPNS - more accurate socket time stamp\n"); + exit(1); +} + +static void bail(const char *error) +{ + printf("%s: %s\n", error, strerror(errno)); + exit(1); +} + +static const unsigned char sync[] = { + 0x00, 0x01, 0x00, 0x01, + 0x5f, 0x44, 0x46, 0x4c, + 0x54, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x01, 0x01, + + /* fake uuid */ + 0x00, 0x01, + 0x02, 0x03, 0x04, 0x05, + + 0x00, 0x01, 0x00, 0x37, + 0x00, 0x00, 0x00, 0x08, + 0x00, 0x00, 0x00, 0x00, + 0x49, 0x05, 0xcd, 0x01, + 0x29, 0xb1, 0x8d, 0xb0, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x01, + + /* fake uuid */ + 0x00, 0x01, + 0x02, 0x03, 0x04, 0x05, + + 0x00, 0x00, 0x00, 0x37, + 0x00, 0x00, 0x00, 0x04, + 0x44, 0x46, 0x4c, 0x54, + 0x00, 0x00, 0xf0, 0x60, + 0x00, 0x01, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x01, + 0x00, 0x00, 0xf0, 0x60, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x04, + 0x44, 0x46, 0x4c, 0x54, + 0x00, 0x01, + + /* fake uuid */ + 0x00, 0x01, + 0x02, 0x03, 0x04, 0x05, + + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00 +}; + +static void sendpacket(int sock, struct sockaddr *addr, socklen_t addr_len) +{ + struct timeval now; + int res; + + res = sendto(sock, sync, sizeof(sync), 0, + addr, addr_len); + gettimeofday(&now, 0); + if (res < 0) + printf("%s: %s\n", "send", strerror(errno)); + else + printf("%ld.%06ld: sent %d bytes\n", + (long)now.tv_sec, (long)now.tv_usec, + res); +} + +static void printpacket(struct msghdr *msg, int res, + char *data, + int sock, int recvmsg_flags, + int siocgstamp, int siocgstampns) +{ + struct sockaddr_in *from_addr = (struct sockaddr_in *)msg->msg_name; + struct cmsghdr *cmsg; + struct timeval tv; + struct timespec ts; + struct timeval now; + + gettimeofday(&now, 0); + + printf("%ld.%06ld: received %s data, %d bytes from %s, %d bytes control messages\n", + (long)now.tv_sec, (long)now.tv_usec, + (recvmsg_flags & MSG_ERRQUEUE) ? "error" : "regular", + res, + inet_ntoa(from_addr->sin_addr), + msg->msg_controllen); + for (cmsg = CMSG_FIRSTHDR(msg); + cmsg; + cmsg = CMSG_NXTHDR(msg, cmsg)) { + printf(" cmsg len %d: ", cmsg->cmsg_len); + switch (cmsg->cmsg_level) { + case SOL_SOCKET: + printf("SOL_SOCKET "); + switch (cmsg->cmsg_type) { + case SO_TIMESTAMP: { + struct timeval *stamp = + (struct timeval *)CMSG_DATA(cmsg); + printf("SO_TIMESTAMP %ld.%06ld", + (long)stamp->tv_sec, + (long)stamp->tv_usec); + break; + } + case SO_TIMESTAMPNS: { + struct timespec *stamp = + (struct timespec *)CMSG_DATA(cmsg); + printf("SO_TIMESTAMPNS %ld.%09ld", + (long)stamp->tv_sec, + (long)stamp->tv_nsec); + break; + } + case SO_TIMESTAMPING: { + struct timespec *stamp = + (struct timespec *)CMSG_DATA(cmsg); + printf("SO_TIMESTAMPING "); + printf("SW %ld.%09ld ", + (long)stamp->tv_sec, + (long)stamp->tv_nsec); + stamp++; + printf("HW transformed %ld.%09ld ", + (long)stamp->tv_sec, + (long)stamp->tv_nsec); + stamp++; + printf("HW raw %ld.%09ld", + (long)stamp->tv_sec, + (long)stamp->tv_nsec); + break; + } + default: + printf("type %d", cmsg->cmsg_type); + break; + } + break; + case IPPROTO_IP: + printf("IPPROTO_IP "); + switch (cmsg->cmsg_type) { + case IP_RECVERR: { + struct sock_extended_err *err = + (struct sock_extended_err *)CMSG_DATA(cmsg); + printf("IP_RECVERR ee_errno '%s' ee_origin %d => %s", + strerror(err->ee_errno), + err->ee_origin, +#ifdef SO_EE_ORIGIN_TIMESTAMPING + err->ee_origin == SO_EE_ORIGIN_TIMESTAMPING ? + "bounced packet" : "unexpected origin" +#else + "probably SO_EE_ORIGIN_TIMESTAMPING" +#endif + ); + if (res < sizeof(sync)) + printf(" => truncated data?!"); + else if (!memcmp(sync, data + res - sizeof(sync), + sizeof(sync))) + printf(" => GOT OUR DATA BACK (HURRAY!)"); + break; + } + case IP_PKTINFO: { + struct in_pktinfo *pktinfo = + (struct in_pktinfo *)CMSG_DATA(cmsg); + printf("IP_PKTINFO interface index %u", + pktinfo->ipi_ifindex); + break; + } + default: + printf("type %d", cmsg->cmsg_type); + break; + } + break; + default: + printf("level %d type %d", + cmsg->cmsg_level, + cmsg->cmsg_type); + break; + } + printf("\n"); + } + + if (siocgstamp) { + if (ioctl(sock, SIOCGSTAMP, &tv)) + printf(" %s: %s\n", "SIOCGSTAMP", strerror(errno)); + else + printf("SIOCGSTAMP %ld.%06ld\n", + (long)tv.tv_sec, + (long)tv.tv_usec); + } + if (siocgstampns) { + if (ioctl(sock, SIOCGSTAMPNS, &ts)) + printf(" %s: %s\n", "SIOCGSTAMPNS", strerror(errno)); + else + printf("SIOCGSTAMPNS %ld.%09ld\n", + (long)ts.tv_sec, + (long)ts.tv_nsec); + } +} + +static void recvpacket(int sock, int recvmsg_flags, + int siocgstamp, int siocgstampns) +{ + char data[256]; + struct msghdr msg; + struct iovec entry; + struct sockaddr_in from_addr; + struct { + struct cmsghdr cm; + char control[512]; + } control; + int res; + + memset(&msg, 0, sizeof(msg)); + msg.msg_iov = &entry; + msg.msg_iovlen = 1; + entry.iov_base = data; + entry.iov_len = sizeof(data); + msg.msg_name = (caddr_t)&from_addr; + msg.msg_namelen = sizeof(from_addr); + msg.msg_control = &control; + msg.msg_controllen = sizeof(control); + + res = recvmsg(sock, &msg, recvmsg_flags|MSG_DONTWAIT); + if (res < 0) { + printf("%s %s: %s\n", + "recvmsg", + (recvmsg_flags & MSG_ERRQUEUE) ? "error" : "regular", + strerror(errno)); + } else { + printpacket(&msg, res, data, + sock, recvmsg_flags, + siocgstamp, siocgstampns); + } +} + +int main(int argc, char **argv) +{ + int so_timestamping_flags = 0; + int so_timestamp = 0; + int so_timestampns = 0; + int siocgstamp = 0; + int siocgstampns = 0; + int ip_multicast_loop = 0; + char *interface; + int i; + int enabled = 1; + int sock; + struct ifreq device; + struct ifreq hwtstamp; + struct hwtstamp_config hwconfig, hwconfig_requested; + struct sockaddr_in addr; + struct ip_mreq imr; + struct in_addr iaddr; + int val; + socklen_t len; + struct timeval next; + + if (argc < 2) + usage(0); + interface = argv[1]; + + for (i = 2; i < argc; i++) { + if (!strcasecmp(argv[i], "SO_TIMESTAMP")) + so_timestamp = 1; + else if (!strcasecmp(argv[i], "SO_TIMESTAMPNS")) + so_timestampns = 1; + else if (!strcasecmp(argv[i], "SIOCGSTAMP")) + siocgstamp = 1; + else if (!strcasecmp(argv[i], "SIOCGSTAMPNS")) + siocgstampns = 1; + else if (!strcasecmp(argv[i], "IP_MULTICAST_LOOP")) + ip_multicast_loop = 1; + else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_TX_HARDWARE")) + so_timestamping_flags |= SOF_TIMESTAMPING_TX_HARDWARE; + else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_TX_SOFTWARE")) + so_timestamping_flags |= SOF_TIMESTAMPING_TX_SOFTWARE; + else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_RX_HARDWARE")) + so_timestamping_flags |= SOF_TIMESTAMPING_RX_HARDWARE; + else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_RX_SOFTWARE")) + so_timestamping_flags |= SOF_TIMESTAMPING_RX_SOFTWARE; + else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_SOFTWARE")) + so_timestamping_flags |= SOF_TIMESTAMPING_SOFTWARE; + else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_SYS_HARDWARE")) + so_timestamping_flags |= SOF_TIMESTAMPING_SYS_HARDWARE; + else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_RAW_HARDWARE")) + so_timestamping_flags |= SOF_TIMESTAMPING_RAW_HARDWARE; + else + usage(argv[i]); + } + + sock = socket(PF_INET, SOCK_DGRAM, IPPROTO_UDP); + if (socket < 0) + bail("socket"); + + memset(&device, 0, sizeof(device)); + strncpy(device.ifr_name, interface, sizeof(device.ifr_name)); + if (ioctl(sock, SIOCGIFADDR, &device) < 0) + bail("getting interface IP address"); + + memset(&hwtstamp, 0, sizeof(hwtstamp)); + strncpy(hwtstamp.ifr_name, interface, sizeof(hwtstamp.ifr_name)); + hwtstamp.ifr_data = (void *)&hwconfig; + memset(&hwconfig, 0, sizeof(&hwconfig)); + hwconfig.tx_type = + (so_timestamping_flags & SOF_TIMESTAMPING_TX_HARDWARE) ? + HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF; + hwconfig.rx_filter = + (so_timestamping_flags & SOF_TIMESTAMPING_RX_HARDWARE) ? + HWTSTAMP_FILTER_PTP_V1_L4_SYNC : HWTSTAMP_FILTER_NONE; + hwconfig_requested = hwconfig; + if (ioctl(sock, SIOCSHWTSTAMP, &hwtstamp) < 0) { + if ((errno == EINVAL || errno == ENOTSUP) && + hwconfig_requested.tx_type == HWTSTAMP_TX_OFF && + hwconfig_requested.rx_filter == HWTSTAMP_FILTER_NONE) + printf("SIOCSHWTSTAMP: disabling hardware time stamping not possible\n"); + else + bail("SIOCSHWTSTAMP"); + } + printf("SIOCSHWTSTAMP: tx_type %d requested, got %d; rx_filter %d requested, got %d\n", + hwconfig_requested.tx_type, hwconfig.tx_type, + hwconfig_requested.rx_filter, hwconfig.rx_filter); + + /* bind to PTP port */ + addr.sin_family = AF_INET; + addr.sin_addr.s_addr = htonl(INADDR_ANY); + addr.sin_port = htons(319 /* PTP event port */); + if (bind(sock, + (struct sockaddr *)&addr, + sizeof(struct sockaddr_in)) < 0) + bail("bind"); + + /* set multicast group for outgoing packets */ + inet_aton("224.0.1.130", &iaddr); /* alternate PTP domain 1 */ + addr.sin_addr = iaddr; + imr.imr_multiaddr.s_addr = iaddr.s_addr; + imr.imr_interface.s_addr = + ((struct sockaddr_in *)&device.ifr_addr)->sin_addr.s_addr; + if (setsockopt(sock, IPPROTO_IP, IP_MULTICAST_IF, + &imr.imr_interface.s_addr, sizeof(struct in_addr)) < 0) + bail("set multicast"); + + /* join multicast group, loop our own packet */ + if (setsockopt(sock, IPPROTO_IP, IP_ADD_MEMBERSHIP, + &imr, sizeof(struct ip_mreq)) < 0) + bail("join multicast group"); + + if (setsockopt(sock, IPPROTO_IP, IP_MULTICAST_LOOP, + &ip_multicast_loop, sizeof(enabled)) < 0) { + bail("loop multicast"); + } + + /* set socket options for time stamping */ + if (so_timestamp && + setsockopt(sock, SOL_SOCKET, SO_TIMESTAMP, + &enabled, sizeof(enabled)) < 0) + bail("setsockopt SO_TIMESTAMP"); + + if (so_timestampns && + setsockopt(sock, SOL_SOCKET, SO_TIMESTAMPNS, + &enabled, sizeof(enabled)) < 0) + bail("setsockopt SO_TIMESTAMPNS"); + + if (so_timestamping_flags && + setsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING, + &so_timestamping_flags, + sizeof(so_timestamping_flags)) < 0) + bail("setsockopt SO_TIMESTAMPING"); + + /* request IP_PKTINFO for debugging purposes */ + if (setsockopt(sock, SOL_IP, IP_PKTINFO, + &enabled, sizeof(enabled)) < 0) + printf("%s: %s\n", "setsockopt IP_PKTINFO", strerror(errno)); + + /* verify socket options */ + len = sizeof(val); + if (getsockopt(sock, SOL_SOCKET, SO_TIMESTAMP, &val, &len) < 0) + printf("%s: %s\n", "getsockopt SO_TIMESTAMP", strerror(errno)); + else + printf("SO_TIMESTAMP %d\n", val); + + if (getsockopt(sock, SOL_SOCKET, SO_TIMESTAMPNS, &val, &len) < 0) + printf("%s: %s\n", "getsockopt SO_TIMESTAMPNS", + strerror(errno)); + else + printf("SO_TIMESTAMPNS %d\n", val); + + if (getsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING, &val, &len) < 0) { + printf("%s: %s\n", "getsockopt SO_TIMESTAMPING", + strerror(errno)); + } else { + printf("SO_TIMESTAMPING %d\n", val); + if (val != so_timestamping_flags) + printf(" not the expected value %d\n", + so_timestamping_flags); + } + + /* send packets forever every five seconds */ + gettimeofday(&next, 0); + next.tv_sec = (next.tv_sec + 1) / 5 * 5; + next.tv_usec = 0; + while (1) { + struct timeval now; + struct timeval delta; + long delta_us; + int res; + fd_set readfs, errorfs; + + gettimeofday(&now, 0); + delta_us = (long)(next.tv_sec - now.tv_sec) * 1000000 + + (long)(next.tv_usec - now.tv_usec); + if (delta_us > 0) { + /* continue waiting for timeout or data */ + delta.tv_sec = delta_us / 1000000; + delta.tv_usec = delta_us % 1000000; + + FD_ZERO(&readfs); + FD_ZERO(&errorfs); + FD_SET(sock, &readfs); + FD_SET(sock, &errorfs); + printf("%ld.%06ld: select %ldus\n", + (long)now.tv_sec, (long)now.tv_usec, + delta_us); + res = select(sock + 1, &readfs, 0, &errorfs, &delta); + gettimeofday(&now, 0); + printf("%ld.%06ld: select returned: %d, %s\n", + (long)now.tv_sec, (long)now.tv_usec, + res, + res < 0 ? strerror(errno) : "success"); + if (res > 0) { + if (FD_ISSET(sock, &readfs)) + printf("ready for reading\n"); + if (FD_ISSET(sock, &errorfs)) + printf("has error\n"); + recvpacket(sock, 0, + siocgstamp, + siocgstampns); + recvpacket(sock, MSG_ERRQUEUE, + siocgstamp, + siocgstampns); + } + } else { + /* write one packet */ + sendpacket(sock, + (struct sockaddr *)&addr, + sizeof(addr)); + next.tv_sec += 5; + continue; + } + } + + return 0; +} diff --git a/arch/alpha/include/asm/socket.h b/arch/alpha/include/asm/socket.h index a1057c2d95e..3641ec1452f 100644 --- a/arch/alpha/include/asm/socket.h +++ b/arch/alpha/include/asm/socket.h @@ -62,6 +62,9 @@ #define SO_MARK 36 +#define SO_TIMESTAMPING 37 +#define SCM_TIMESTAMPING SO_TIMESTAMPING + /* O_NONBLOCK clashes with the bits used for socket types. Therefore we * have to define SOCK_NONBLOCK to a different value here. */ diff --git a/arch/arm/include/asm/socket.h b/arch/arm/include/asm/socket.h index 6817be9573a..537de4e0ef5 100644 --- a/arch/arm/include/asm/socket.h +++ b/arch/arm/include/asm/socket.h @@ -54,4 +54,7 @@ #define SO_MARK 36 +#define SO_TIMESTAMPING 37 +#define SCM_TIMESTAMPING SO_TIMESTAMPING + #endif /* _ASM_SOCKET_H */ diff --git a/arch/avr32/include/asm/socket.h b/arch/avr32/include/asm/socket.h index 35863f26092..04c86061970 100644 --- a/arch/avr32/include/asm/socket.h +++ b/arch/avr32/include/asm/socket.h @@ -54,4 +54,7 @@ #define SO_MARK 36 +#define SO_TIMESTAMPING 37 +#define SCM_TIMESTAMPING SO_TIMESTAMPING + #endif /* __ASM_AVR32_SOCKET_H */ diff --git a/arch/blackfin/include/asm/socket.h b/arch/blackfin/include/asm/socket.h index 2ca702e44d4..fac7fe9e1f8 100644 --- a/arch/blackfin/include/asm/socket.h +++ b/arch/blackfin/include/asm/socket.h @@ -53,4 +53,7 @@ #define SO_MARK 36 +#define SO_TIMESTAMPING 37 +#define SCM_TIMESTAMPING SO_TIMESTAMPING + #endif /* _ASM_SOCKET_H */ diff --git a/arch/cris/include/asm/socket.h b/arch/cris/include/asm/socket.h index 9df0ca82f5d..d5cf7400540 100644 --- a/arch/cris/include/asm/socket.h +++ b/arch/cris/include/asm/socket.h @@ -56,6 +56,9 @@ #define SO_MARK 36 +#define SO_TIMESTAMPING 37 +#define SCM_TIMESTAMPING SO_TIMESTAMPING + #endif /* _ASM_SOCKET_H */ diff --git a/arch/h8300/include/asm/socket.h b/arch/h8300/include/asm/socket.h index da2520dbf25..602518a70a1 100644 --- a/arch/h8300/include/asm/socket.h +++ b/arch/h8300/include/asm/socket.h @@ -54,4 +54,7 @@ #define SO_MARK 36 +#define SO_TIMESTAMPING 37 +#define SCM_TIMESTAMPING SO_TIMESTAMPING + #endif /* _ASM_SOCKET_H */ diff --git a/arch/ia64/include/asm/socket.h b/arch/ia64/include/asm/socket.h index d5ef0aa3e31..745421225ec 100644 --- a/arch/ia64/include/asm/socket.h +++ b/arch/ia64/include/asm/socket.h @@ -63,4 +63,7 @@ #define SO_MARK 36 +#define SO_TIMESTAMPING 37 +#define SCM_TIMESTAMPING SO_TIMESTAMPING + #endif /* _ASM_IA64_SOCKET_H */ diff --git a/arch/m68k/include/asm/socket.h b/arch/m68k/include/asm/socket.h index dbc64e92c41..ca87f938b03 100644 --- a/arch/m68k/include/asm/socket.h +++ b/arch/m68k/include/asm/socket.h @@ -54,4 +54,7 @@ #define SO_MARK 36 +#define SO_TIMESTAMPING 37 +#define SCM_TIMESTAMPING SO_TIMESTAMPING + #endif /* _ASM_SOCKET_H */ diff --git a/arch/mips/include/asm/socket.h b/arch/mips/include/asm/socket.h index facc2d7a87c..2abca178016 100644 --- a/arch/mips/include/asm/socket.h +++ b/arch/mips/include/asm/socket.h @@ -75,6 +75,9 @@ To add: #define SO_REUSEPORT 0x0200 /* Allow local address and port reuse. */ #define SO_MARK 36 +#define SO_TIMESTAMPING 37 +#define SCM_TIMESTAMPING SO_TIMESTAMPING + #ifdef __KERNEL__ /** sock_type - Socket types diff --git a/arch/parisc/include/asm/socket.h b/arch/parisc/include/asm/socket.h index fba402c95ac..885472bf7b7 100644 --- a/arch/parisc/include/asm/socket.h +++ b/arch/parisc/include/asm/socket.h @@ -54,6 +54,9 @@ #define SO_MARK 0x401f +#define SO_TIMESTAMPING 0x4020 +#define SCM_TIMESTAMPING SO_TIMESTAMPING + /* O_NONBLOCK clashes with the bits used for socket types. Therefore we * have to define SOCK_NONBLOCK to a different value here. */ diff --git a/arch/powerpc/include/asm/socket.h b/arch/powerpc/include/asm/socket.h index f5a4e168e49..1e5cfad0e3f 100644 --- a/arch/powerpc/include/asm/socket.h +++ b/arch/powerpc/include/asm/socket.h @@ -61,4 +61,7 @@ #define SO_MARK 36 +#define SO_TIMESTAMPING 37 +#define SCM_TIMESTAMPING SO_TIMESTAMPING + #endif /* _ASM_POWERPC_SOCKET_H */ diff --git a/arch/s390/include/asm/socket.h b/arch/s390/include/asm/socket.h index c786ab623b2..02330c50241 100644 --- a/arch/s390/include/asm/socket.h +++ b/arch/s390/include/asm/socket.h @@ -62,4 +62,7 @@ #define SO_MARK 36 +#define SO_TIMESTAMPING 37 +#define SCM_TIMESTAMPING SO_TIMESTAMPING + #endif /* _ASM_SOCKET_H */ diff --git a/arch/sh/include/asm/socket.h b/arch/sh/include/asm/socket.h index 6d4bf651295..345653b9682 100644 --- a/arch/sh/include/asm/socket.h +++ b/arch/sh/include/asm/socket.h @@ -54,4 +54,7 @@ #define SO_MARK 36 +#define SO_TIMESTAMPING 37 +#define SCM_TIMESTAMPING SO_TIMESTAMPING + #endif /* __ASM_SH_SOCKET_H */ diff --git a/arch/sparc/include/asm/socket.h b/arch/sparc/include/asm/socket.h index bf50d0c2d58..982a12f959f 100644 --- a/arch/sparc/include/asm/socket.h +++ b/arch/sparc/include/asm/socket.h @@ -50,6 +50,9 @@ #define SO_MARK 0x0022 +#define SO_TIMESTAMPING 0x0023 +#define SCM_TIMESTAMPING SO_TIMESTAMPING + /* Security levels - as per NRL IPv6 - don't actually do anything */ #define SO_SECURITY_AUTHENTICATION 0x5001 #define SO_SECURITY_ENCRYPTION_TRANSPORT 0x5002 diff --git a/arch/x86/include/asm/socket.h b/arch/x86/include/asm/socket.h index 8ab9cc8b2ec..ca8bf2cd0ba 100644 --- a/arch/x86/include/asm/socket.h +++ b/arch/x86/include/asm/socket.h @@ -54,4 +54,7 @@ #define SO_MARK 36 +#define SO_TIMESTAMPING 37 +#define SCM_TIMESTAMPING SO_TIMESTAMPING + #endif /* _ASM_X86_SOCKET_H */ diff --git a/arch/xtensa/include/asm/socket.h b/arch/xtensa/include/asm/socket.h index 6100682b1da..dd1a7a4a1ce 100644 --- a/arch/xtensa/include/asm/socket.h +++ b/arch/xtensa/include/asm/socket.h @@ -65,4 +65,7 @@ #define SO_MARK 36 +#define SO_TIMESTAMPING 37 +#define SCM_TIMESTAMPING SO_TIMESTAMPING + #endif /* _XTENSA_SOCKET_H */ diff --git a/include/asm-frv/socket.h b/include/asm-frv/socket.h index e51ca67b935..57c3d4054e8 100644 --- a/include/asm-frv/socket.h +++ b/include/asm-frv/socket.h @@ -54,5 +54,8 @@ #define SO_MARK 36 +#define SO_TIMESTAMPING 37 +#define SCM_TIMESTAMPING SO_TIMESTAMPING + #endif /* _ASM_SOCKET_H */ diff --git a/include/asm-m32r/socket.h b/include/asm-m32r/socket.h index 9a0e2001222..be7ed589af5 100644 --- a/include/asm-m32r/socket.h +++ b/include/asm-m32r/socket.h @@ -54,4 +54,7 @@ #define SO_MARK 36 +#define SO_TIMESTAMPING 37 +#define SCM_TIMESTAMPING SO_TIMESTAMPING + #endif /* _ASM_M32R_SOCKET_H */ diff --git a/include/asm-mn10300/socket.h b/include/asm-mn10300/socket.h index 80af9c4ccad..fb5daf438ec 100644 --- a/include/asm-mn10300/socket.h +++ b/include/asm-mn10300/socket.h @@ -54,4 +54,7 @@ #define SO_MARK 36 +#define SO_TIMESTAMPING 37 +#define SCM_TIMESTAMPING SO_TIMESTAMPING + #endif /* _ASM_SOCKET_H */ diff --git a/include/linux/errqueue.h b/include/linux/errqueue.h index ceb1454b697..ec12cc74366 100644 --- a/include/linux/errqueue.h +++ b/include/linux/errqueue.h @@ -18,6 +18,7 @@ struct sock_extended_err #define SO_EE_ORIGIN_LOCAL 1 #define SO_EE_ORIGIN_ICMP 2 #define SO_EE_ORIGIN_ICMP6 3 +#define SO_EE_ORIGIN_TIMESTAMPING 4 #define SO_EE_OFFENDER(ee) ((struct sockaddr*)((ee)+1)) diff --git a/include/linux/net_tstamp.h b/include/linux/net_tstamp.h new file mode 100644 index 00000000000..a3b8546354a --- /dev/null +++ b/include/linux/net_tstamp.h @@ -0,0 +1,104 @@ +/* + * Userspace API for hardware time stamping of network packets + * + * Copyright (C) 2008,2009 Intel Corporation + * Author: Patrick Ohly + * + */ + +#ifndef _NET_TIMESTAMPING_H +#define _NET_TIMESTAMPING_H + +#include /* for SO_TIMESTAMPING */ + +/* SO_TIMESTAMPING gets an integer bit field comprised of these values */ +enum { + SOF_TIMESTAMPING_TX_HARDWARE = (1<<0), + SOF_TIMESTAMPING_TX_SOFTWARE = (1<<1), + SOF_TIMESTAMPING_RX_HARDWARE = (1<<2), + SOF_TIMESTAMPING_RX_SOFTWARE = (1<<3), + SOF_TIMESTAMPING_SOFTWARE = (1<<4), + SOF_TIMESTAMPING_SYS_HARDWARE = (1<<5), + SOF_TIMESTAMPING_RAW_HARDWARE = (1<<6), + SOF_TIMESTAMPING_MASK = + (SOF_TIMESTAMPING_RAW_HARDWARE - 1) | + SOF_TIMESTAMPING_RAW_HARDWARE +}; + +/** + * struct hwtstamp_config - %SIOCSHWTSTAMP parameter + * + * @flags: no flags defined right now, must be zero + * @tx_type: one of HWTSTAMP_TX_* + * @rx_type: one of one of HWTSTAMP_FILTER_* + * + * %SIOCSHWTSTAMP expects a &struct ifreq with a ifr_data pointer to + * this structure. dev_ifsioc() in the kernel takes care of the + * translation between 32 bit userspace and 64 bit kernel. The + * structure is intentionally chosen so that it has the same layout on + * 32 and 64 bit systems, don't break this! + */ +struct hwtstamp_config { + int flags; + int tx_type; + int rx_filter; +}; + +/* possible values for hwtstamp_config->tx_type */ +enum { + /* + * No outgoing packet will need hardware time stamping; + * should a packet arrive which asks for it, no hardware + * time stamping will be done. + */ + HWTSTAMP_TX_OFF, + + /* + * Enables hardware time stamping for outgoing packets; + * the sender of the packet decides which are to be + * time stamped by setting %SOF_TIMESTAMPING_TX_SOFTWARE + * before sending the packet. + */ + HWTSTAMP_TX_ON, +}; + +/* possible values for hwtstamp_config->rx_filter */ +enum { + /* time stamp no incoming packet at all */ + HWTSTAMP_FILTER_NONE, + + /* time stamp any incoming packet */ + HWTSTAMP_FILTER_ALL, + + /* return value: time stamp all packets requested plus some others */ + HWTSTAMP_FILTER_SOME, + + /* PTP v1, UDP, any kind of event packet */ + HWTSTAMP_FILTER_PTP_V1_L4_EVENT, + /* PTP v1, UDP, Sync packet */ + HWTSTAMP_FILTER_PTP_V1_L4_SYNC, + /* PTP v1, UDP, Delay_req packet */ + HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ, + /* PTP v2, UDP, any kind of event packet */ + HWTSTAMP_FILTER_PTP_V2_L4_EVENT, + /* PTP v2, UDP, Sync packet */ + HWTSTAMP_FILTER_PTP_V2_L4_SYNC, + /* PTP v2, UDP, Delay_req packet */ + HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ, + + /* 802.AS1, Ethernet, any kind of event packet */ + HWTSTAMP_FILTER_PTP_V2_L2_EVENT, + /* 802.AS1, Ethernet, Sync packet */ + HWTSTAMP_FILTER_PTP_V2_L2_SYNC, + /* 802.AS1, Ethernet, Delay_req packet */ + HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ, + + /* PTP v2/802.AS1, any layer, any kind of event packet */ + HWTSTAMP_FILTER_PTP_V2_EVENT, + /* PTP v2/802.AS1, any layer, Sync packet */ + HWTSTAMP_FILTER_PTP_V2_SYNC, + /* PTP v2/802.AS1, any layer, Delay_req packet */ + HWTSTAMP_FILTER_PTP_V2_DELAY_REQ, +}; + +#endif /* _NET_TIMESTAMPING_H */ diff --git a/include/linux/sockios.h b/include/linux/sockios.h index abef7596655..241f179347d 100644 --- a/include/linux/sockios.h +++ b/include/linux/sockios.h @@ -122,6 +122,9 @@ #define SIOCBRADDIF 0x89a2 /* add interface to bridge */ #define SIOCBRDELIF 0x89a3 /* remove interface from bridge */ +/* hardware time stamping: parameters in linux/net_tstamp.h */ +#define SIOCSHWTSTAMP 0x89b0 + /* Device private ioctl calls */ /* -- cgit v1.2.3-70-g09d2 From 07bf44f86989f5ed866510374fe761d1903681fb Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Fri, 9 Jan 2009 17:25:50 +1100 Subject: crypto: aes - Export x86 AES encrypt/decrypt functions Intel AES-NI AES acceleration instructions touch XMM state, to use that in soft_irq context, general x86 AES implementation is used as fallback. The first parameter is changed from struct crypto_tfm * to struct crypto_aes_ctx * to make it easier to deal with 16 bytes alignment requirement of AES-NI implementation. Signed-off-by: Huang Ying Signed-off-by: Herbert Xu --- arch/x86/crypto/aes-i586-asm_32.S | 18 +++++++++--------- arch/x86/crypto/aes-x86_64-asm_64.S | 6 ++---- arch/x86/crypto/aes_glue.c | 20 ++++++++++++++++---- arch/x86/include/asm/aes.h | 11 +++++++++++ 4 files changed, 38 insertions(+), 17 deletions(-) create mode 100644 arch/x86/include/asm/aes.h (limited to 'arch/x86/include') diff --git a/arch/x86/crypto/aes-i586-asm_32.S b/arch/x86/crypto/aes-i586-asm_32.S index 5252c388017..b949ec2f9af 100644 --- a/arch/x86/crypto/aes-i586-asm_32.S +++ b/arch/x86/crypto/aes-i586-asm_32.S @@ -41,14 +41,14 @@ #define tlen 1024 // length of each of 4 'xor' arrays (256 32-bit words) /* offsets to parameters with one register pushed onto stack */ -#define tfm 8 +#define ctx 8 #define out_blk 12 #define in_blk 16 -/* offsets in crypto_tfm structure */ -#define klen (crypto_tfm_ctx_offset + 480) -#define ekey (crypto_tfm_ctx_offset + 0) -#define dkey (crypto_tfm_ctx_offset + 240) +/* offsets in crypto_aes_ctx structure */ +#define klen (480) +#define ekey (0) +#define dkey (240) // register mapping for encrypt and decrypt subroutines @@ -217,7 +217,7 @@ do_col (table, r5,r0,r1,r4, r2,r3); /* idx=r5 */ // AES (Rijndael) Encryption Subroutine -/* void aes_enc_blk(struct crypto_tfm *tfm, u8 *out_blk, const u8 *in_blk) */ +/* void aes_enc_blk(struct crypto_aes_ctx *ctx, u8 *out_blk, const u8 *in_blk) */ .global aes_enc_blk @@ -228,7 +228,7 @@ aes_enc_blk: push %ebp - mov tfm(%esp),%ebp + mov ctx(%esp),%ebp // CAUTION: the order and the values used in these assigns // rely on the register mappings @@ -292,7 +292,7 @@ aes_enc_blk: ret // AES (Rijndael) Decryption Subroutine -/* void aes_dec_blk(struct crypto_tfm *tfm, u8 *out_blk, const u8 *in_blk) */ +/* void aes_dec_blk(struct crypto_aes_ctx *ctx, u8 *out_blk, const u8 *in_blk) */ .global aes_dec_blk @@ -303,7 +303,7 @@ aes_enc_blk: aes_dec_blk: push %ebp - mov tfm(%esp),%ebp + mov ctx(%esp),%ebp // CAUTION: the order and the values used in these assigns // rely on the register mappings diff --git a/arch/x86/crypto/aes-x86_64-asm_64.S b/arch/x86/crypto/aes-x86_64-asm_64.S index 7f28f62737d..5b577d5a059 100644 --- a/arch/x86/crypto/aes-x86_64-asm_64.S +++ b/arch/x86/crypto/aes-x86_64-asm_64.S @@ -17,8 +17,6 @@ #include -#define BASE crypto_tfm_ctx_offset - #define R1 %rax #define R1E %eax #define R1X %ax @@ -56,13 +54,13 @@ .align 8; \ FUNC: movq r1,r2; \ movq r3,r4; \ - leaq BASE+KEY+48(r8),r9; \ + leaq KEY+48(r8),r9; \ movq r10,r11; \ movl (r7),r5 ## E; \ movl 4(r7),r1 ## E; \ movl 8(r7),r6 ## E; \ movl 12(r7),r7 ## E; \ - movl BASE+480(r8),r10 ## E; \ + movl 480(r8),r10 ## E; \ xorl -48(r9),r5 ## E; \ xorl -44(r9),r1 ## E; \ xorl -40(r9),r6 ## E; \ diff --git a/arch/x86/crypto/aes_glue.c b/arch/x86/crypto/aes_glue.c index 71f45782711..49ae9fe32b2 100644 --- a/arch/x86/crypto/aes_glue.c +++ b/arch/x86/crypto/aes_glue.c @@ -5,17 +5,29 @@ #include -asmlinkage void aes_enc_blk(struct crypto_tfm *tfm, u8 *out, const u8 *in); -asmlinkage void aes_dec_blk(struct crypto_tfm *tfm, u8 *out, const u8 *in); +asmlinkage void aes_enc_blk(struct crypto_aes_ctx *ctx, u8 *out, const u8 *in); +asmlinkage void aes_dec_blk(struct crypto_aes_ctx *ctx, u8 *out, const u8 *in); + +void crypto_aes_encrypt_x86(struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src) +{ + aes_enc_blk(ctx, dst, src); +} +EXPORT_SYMBOL_GPL(crypto_aes_encrypt_x86); + +void crypto_aes_decrypt_x86(struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src) +{ + aes_dec_blk(ctx, dst, src); +} +EXPORT_SYMBOL_GPL(crypto_aes_decrypt_x86); static void aes_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) { - aes_enc_blk(tfm, dst, src); + aes_enc_blk(crypto_tfm_ctx(tfm), dst, src); } static void aes_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) { - aes_dec_blk(tfm, dst, src); + aes_dec_blk(crypto_tfm_ctx(tfm), dst, src); } static struct crypto_alg aes_alg = { diff --git a/arch/x86/include/asm/aes.h b/arch/x86/include/asm/aes.h new file mode 100644 index 00000000000..80545a1cbe3 --- /dev/null +++ b/arch/x86/include/asm/aes.h @@ -0,0 +1,11 @@ +#ifndef ASM_X86_AES_H +#define ASM_X86_AES_H + +#include +#include + +void crypto_aes_encrypt_x86(struct crypto_aes_ctx *ctx, u8 *dst, + const u8 *src); +void crypto_aes_decrypt_x86(struct crypto_aes_ctx *ctx, u8 *dst, + const u8 *src); +#endif -- cgit v1.2.3-70-g09d2 From 54b6a1bd5364aca95cd6ffae00f2b64c6511122c Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Sun, 18 Jan 2009 16:28:34 +1100 Subject: crypto: aes-ni - Add support to Intel AES-NI instructions for x86_64 platform Intel AES-NI is a new set of Single Instruction Multiple Data (SIMD) instructions that are going to be introduced in the next generation of Intel processor, as of 2009. These instructions enable fast and secure data encryption and decryption, using the Advanced Encryption Standard (AES), defined by FIPS Publication number 197. The architecture introduces six instructions that offer full hardware support for AES. Four of them support high performance data encryption and decryption, and the other two instructions support the AES key expansion procedure. The white paper can be downloaded from: http://softwarecommunity.intel.com/isn/downloads/intelavx/AES-Instructions-Set_WP.pdf AES may be used in soft_irq context, but MMX/SSE context can not be touched safely in soft_irq context. So in_interrupt() is checked, if in IRQ or soft_irq context, the general x86_64 implementation are used instead. Signed-off-by: Huang Ying Signed-off-by: Herbert Xu --- arch/x86/crypto/Makefile | 3 + arch/x86/crypto/aesni-intel_asm.S | 896 +++++++++++++++++++++++++++++++++++++ arch/x86/crypto/aesni-intel_glue.c | 461 +++++++++++++++++++ arch/x86/include/asm/cpufeature.h | 1 + crypto/Kconfig | 25 ++ 5 files changed, 1386 insertions(+) create mode 100644 arch/x86/crypto/aesni-intel_asm.S create mode 100644 arch/x86/crypto/aesni-intel_glue.c (limited to 'arch/x86/include') diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile index 903de4aa509..ebe7deedd5b 100644 --- a/arch/x86/crypto/Makefile +++ b/arch/x86/crypto/Makefile @@ -9,6 +9,7 @@ obj-$(CONFIG_CRYPTO_SALSA20_586) += salsa20-i586.o obj-$(CONFIG_CRYPTO_AES_X86_64) += aes-x86_64.o obj-$(CONFIG_CRYPTO_TWOFISH_X86_64) += twofish-x86_64.o obj-$(CONFIG_CRYPTO_SALSA20_X86_64) += salsa20-x86_64.o +obj-$(CONFIG_CRYPTO_AES_NI_INTEL) += aesni-intel.o obj-$(CONFIG_CRYPTO_CRC32C_INTEL) += crc32c-intel.o @@ -19,3 +20,5 @@ salsa20-i586-y := salsa20-i586-asm_32.o salsa20_glue.o aes-x86_64-y := aes-x86_64-asm_64.o aes_glue.o twofish-x86_64-y := twofish-x86_64-asm_64.o twofish_glue.o salsa20-x86_64-y := salsa20-x86_64-asm_64.o salsa20_glue.o + +aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S new file mode 100644 index 00000000000..caba9960170 --- /dev/null +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -0,0 +1,896 @@ +/* + * Implement AES algorithm in Intel AES-NI instructions. + * + * The white paper of AES-NI instructions can be downloaded from: + * http://softwarecommunity.intel.com/isn/downloads/intelavx/AES-Instructions-Set_WP.pdf + * + * Copyright (C) 2008, Intel Corp. + * Author: Huang Ying + * Vinodh Gopal + * Kahraman Akdemir + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include + +.text + +#define STATE1 %xmm0 +#define STATE2 %xmm4 +#define STATE3 %xmm5 +#define STATE4 %xmm6 +#define STATE STATE1 +#define IN1 %xmm1 +#define IN2 %xmm7 +#define IN3 %xmm8 +#define IN4 %xmm9 +#define IN IN1 +#define KEY %xmm2 +#define IV %xmm3 + +#define KEYP %rdi +#define OUTP %rsi +#define INP %rdx +#define LEN %rcx +#define IVP %r8 +#define KLEN %r9d +#define T1 %r10 +#define TKEYP T1 +#define T2 %r11 + +_key_expansion_128: +_key_expansion_256a: + pshufd $0b11111111, %xmm1, %xmm1 + shufps $0b00010000, %xmm0, %xmm4 + pxor %xmm4, %xmm0 + shufps $0b10001100, %xmm0, %xmm4 + pxor %xmm4, %xmm0 + pxor %xmm1, %xmm0 + movaps %xmm0, (%rcx) + add $0x10, %rcx + ret + +_key_expansion_192a: + pshufd $0b01010101, %xmm1, %xmm1 + shufps $0b00010000, %xmm0, %xmm4 + pxor %xmm4, %xmm0 + shufps $0b10001100, %xmm0, %xmm4 + pxor %xmm4, %xmm0 + pxor %xmm1, %xmm0 + + movaps %xmm2, %xmm5 + movaps %xmm2, %xmm6 + pslldq $4, %xmm5 + pshufd $0b11111111, %xmm0, %xmm3 + pxor %xmm3, %xmm2 + pxor %xmm5, %xmm2 + + movaps %xmm0, %xmm1 + shufps $0b01000100, %xmm0, %xmm6 + movaps %xmm6, (%rcx) + shufps $0b01001110, %xmm2, %xmm1 + movaps %xmm1, 16(%rcx) + add $0x20, %rcx + ret + +_key_expansion_192b: + pshufd $0b01010101, %xmm1, %xmm1 + shufps $0b00010000, %xmm0, %xmm4 + pxor %xmm4, %xmm0 + shufps $0b10001100, %xmm0, %xmm4 + pxor %xmm4, %xmm0 + pxor %xmm1, %xmm0 + + movaps %xmm2, %xmm5 + pslldq $4, %xmm5 + pshufd $0b11111111, %xmm0, %xmm3 + pxor %xmm3, %xmm2 + pxor %xmm5, %xmm2 + + movaps %xmm0, (%rcx) + add $0x10, %rcx + ret + +_key_expansion_256b: + pshufd $0b10101010, %xmm1, %xmm1 + shufps $0b00010000, %xmm2, %xmm4 + pxor %xmm4, %xmm2 + shufps $0b10001100, %xmm2, %xmm4 + pxor %xmm4, %xmm2 + pxor %xmm1, %xmm2 + movaps %xmm2, (%rcx) + add $0x10, %rcx + ret + +/* + * int aesni_set_key(struct crypto_aes_ctx *ctx, const u8 *in_key, + * unsigned int key_len) + */ +ENTRY(aesni_set_key) + movups (%rsi), %xmm0 # user key (first 16 bytes) + movaps %xmm0, (%rdi) + lea 0x10(%rdi), %rcx # key addr + movl %edx, 480(%rdi) + pxor %xmm4, %xmm4 # xmm4 is assumed 0 in _key_expansion_x + cmp $24, %dl + jb .Lenc_key128 + je .Lenc_key192 + movups 0x10(%rsi), %xmm2 # other user key + movaps %xmm2, (%rcx) + add $0x10, %rcx + # aeskeygenassist $0x1, %xmm2, %xmm1 # round 1 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x01 + call _key_expansion_256a + # aeskeygenassist $0x1, %xmm0, %xmm1 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x01 + call _key_expansion_256b + # aeskeygenassist $0x2, %xmm2, %xmm1 # round 2 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x02 + call _key_expansion_256a + # aeskeygenassist $0x2, %xmm0, %xmm1 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x02 + call _key_expansion_256b + # aeskeygenassist $0x4, %xmm2, %xmm1 # round 3 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x04 + call _key_expansion_256a + # aeskeygenassist $0x4, %xmm0, %xmm1 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x04 + call _key_expansion_256b + # aeskeygenassist $0x8, %xmm2, %xmm1 # round 4 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x08 + call _key_expansion_256a + # aeskeygenassist $0x8, %xmm0, %xmm1 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x08 + call _key_expansion_256b + # aeskeygenassist $0x10, %xmm2, %xmm1 # round 5 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x10 + call _key_expansion_256a + # aeskeygenassist $0x10, %xmm0, %xmm1 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x10 + call _key_expansion_256b + # aeskeygenassist $0x20, %xmm2, %xmm1 # round 6 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x20 + call _key_expansion_256a + # aeskeygenassist $0x20, %xmm0, %xmm1 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x20 + call _key_expansion_256b + # aeskeygenassist $0x40, %xmm2, %xmm1 # round 7 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x40 + call _key_expansion_256a + jmp .Ldec_key +.Lenc_key192: + movq 0x10(%rsi), %xmm2 # other user key + # aeskeygenassist $0x1, %xmm2, %xmm1 # round 1 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x01 + call _key_expansion_192a + # aeskeygenassist $0x2, %xmm2, %xmm1 # round 2 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x02 + call _key_expansion_192b + # aeskeygenassist $0x4, %xmm2, %xmm1 # round 3 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x04 + call _key_expansion_192a + # aeskeygenassist $0x8, %xmm2, %xmm1 # round 4 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x08 + call _key_expansion_192b + # aeskeygenassist $0x10, %xmm2, %xmm1 # round 5 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x10 + call _key_expansion_192a + # aeskeygenassist $0x20, %xmm2, %xmm1 # round 6 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x20 + call _key_expansion_192b + # aeskeygenassist $0x40, %xmm2, %xmm1 # round 7 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x40 + call _key_expansion_192a + # aeskeygenassist $0x80, %xmm2, %xmm1 # round 8 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x80 + call _key_expansion_192b + jmp .Ldec_key +.Lenc_key128: + # aeskeygenassist $0x1, %xmm0, %xmm1 # round 1 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x01 + call _key_expansion_128 + # aeskeygenassist $0x2, %xmm0, %xmm1 # round 2 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x02 + call _key_expansion_128 + # aeskeygenassist $0x4, %xmm0, %xmm1 # round 3 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x04 + call _key_expansion_128 + # aeskeygenassist $0x8, %xmm0, %xmm1 # round 4 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x08 + call _key_expansion_128 + # aeskeygenassist $0x10, %xmm0, %xmm1 # round 5 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x10 + call _key_expansion_128 + # aeskeygenassist $0x20, %xmm0, %xmm1 # round 6 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x20 + call _key_expansion_128 + # aeskeygenassist $0x40, %xmm0, %xmm1 # round 7 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x40 + call _key_expansion_128 + # aeskeygenassist $0x80, %xmm0, %xmm1 # round 8 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x80 + call _key_expansion_128 + # aeskeygenassist $0x1b, %xmm0, %xmm1 # round 9 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x1b + call _key_expansion_128 + # aeskeygenassist $0x36, %xmm0, %xmm1 # round 10 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x36 + call _key_expansion_128 +.Ldec_key: + sub $0x10, %rcx + movaps (%rdi), %xmm0 + movaps (%rcx), %xmm1 + movaps %xmm0, 240(%rcx) + movaps %xmm1, 240(%rdi) + add $0x10, %rdi + lea 240-16(%rcx), %rsi +.align 4 +.Ldec_key_loop: + movaps (%rdi), %xmm0 + # aesimc %xmm0, %xmm1 + .byte 0x66, 0x0f, 0x38, 0xdb, 0xc8 + movaps %xmm1, (%rsi) + add $0x10, %rdi + sub $0x10, %rsi + cmp %rcx, %rdi + jb .Ldec_key_loop + xor %rax, %rax + ret + +/* + * void aesni_enc(struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src) + */ +ENTRY(aesni_enc) + movl 480(KEYP), KLEN # key length + movups (INP), STATE # input + call _aesni_enc1 + movups STATE, (OUTP) # output + ret + +/* + * _aesni_enc1: internal ABI + * input: + * KEYP: key struct pointer + * KLEN: round count + * STATE: initial state (input) + * output: + * STATE: finial state (output) + * changed: + * KEY + * TKEYP (T1) + */ +_aesni_enc1: + movaps (KEYP), KEY # key + mov KEYP, TKEYP + pxor KEY, STATE # round 0 + add $0x30, TKEYP + cmp $24, KLEN + jb .Lenc128 + lea 0x20(TKEYP), TKEYP + je .Lenc192 + add $0x20, TKEYP + movaps -0x60(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + movaps -0x50(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 +.align 4 +.Lenc192: + movaps -0x40(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + movaps -0x30(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 +.align 4 +.Lenc128: + movaps -0x20(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + movaps -0x10(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + movaps (TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + movaps 0x10(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + movaps 0x20(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + movaps 0x30(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + movaps 0x40(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + movaps 0x50(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + movaps 0x60(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + movaps 0x70(TKEYP), KEY + # aesenclast KEY, STATE # last round + .byte 0x66, 0x0f, 0x38, 0xdd, 0xc2 + ret + +/* + * _aesni_enc4: internal ABI + * input: + * KEYP: key struct pointer + * KLEN: round count + * STATE1: initial state (input) + * STATE2 + * STATE3 + * STATE4 + * output: + * STATE1: finial state (output) + * STATE2 + * STATE3 + * STATE4 + * changed: + * KEY + * TKEYP (T1) + */ +_aesni_enc4: + movaps (KEYP), KEY # key + mov KEYP, TKEYP + pxor KEY, STATE1 # round 0 + pxor KEY, STATE2 + pxor KEY, STATE3 + pxor KEY, STATE4 + add $0x30, TKEYP + cmp $24, KLEN + jb .L4enc128 + lea 0x20(TKEYP), TKEYP + je .L4enc192 + add $0x20, TKEYP + movaps -0x60(TKEYP), KEY + # aesenc KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + # aesenc KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 + # aesenc KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xea + # aesenc KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 + movaps -0x50(TKEYP), KEY + # aesenc KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + # aesenc KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 + # aesenc KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xea + # aesenc KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 +#.align 4 +.L4enc192: + movaps -0x40(TKEYP), KEY + # aesenc KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + # aesenc KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 + # aesenc KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xea + # aesenc KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 + movaps -0x30(TKEYP), KEY + # aesenc KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + # aesenc KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 + # aesenc KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xea + # aesenc KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 +#.align 4 +.L4enc128: + movaps -0x20(TKEYP), KEY + # aesenc KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + # aesenc KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 + # aesenc KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xea + # aesenc KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 + movaps -0x10(TKEYP), KEY + # aesenc KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + # aesenc KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 + # aesenc KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xea + # aesenc KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 + movaps (TKEYP), KEY + # aesenc KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + # aesenc KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 + # aesenc KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xea + # aesenc KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 + movaps 0x10(TKEYP), KEY + # aesenc KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + # aesenc KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 + # aesenc KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xea + # aesenc KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 + movaps 0x20(TKEYP), KEY + # aesenc KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + # aesenc KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 + # aesenc KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xea + # aesenc KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 + movaps 0x30(TKEYP), KEY + # aesenc KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + # aesenc KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 + # aesenc KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xea + # aesenc KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 + movaps 0x40(TKEYP), KEY + # aesenc KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + # aesenc KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 + # aesenc KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xea + # aesenc KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 + movaps 0x50(TKEYP), KEY + # aesenc KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + # aesenc KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 + # aesenc KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xea + # aesenc KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 + movaps 0x60(TKEYP), KEY + # aesenc KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + # aesenc KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 + # aesenc KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xea + # aesenc KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 + movaps 0x70(TKEYP), KEY + # aesenclast KEY, STATE1 # last round + .byte 0x66, 0x0f, 0x38, 0xdd, 0xc2 + # aesenclast KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xdd, 0xe2 + # aesenclast KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xdd, 0xea + # aesenclast KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xdd, 0xf2 + ret + +/* + * void aesni_dec (struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src) + */ +ENTRY(aesni_dec) + mov 480(KEYP), KLEN # key length + add $240, KEYP + movups (INP), STATE # input + call _aesni_dec1 + movups STATE, (OUTP) #output + ret + +/* + * _aesni_dec1: internal ABI + * input: + * KEYP: key struct pointer + * KLEN: key length + * STATE: initial state (input) + * output: + * STATE: finial state (output) + * changed: + * KEY + * TKEYP (T1) + */ +_aesni_dec1: + movaps (KEYP), KEY # key + mov KEYP, TKEYP + pxor KEY, STATE # round 0 + add $0x30, TKEYP + cmp $24, KLEN + jb .Ldec128 + lea 0x20(TKEYP), TKEYP + je .Ldec192 + add $0x20, TKEYP + movaps -0x60(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + movaps -0x50(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 +.align 4 +.Ldec192: + movaps -0x40(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + movaps -0x30(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 +.align 4 +.Ldec128: + movaps -0x20(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + movaps -0x10(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + movaps (TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + movaps 0x10(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + movaps 0x20(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + movaps 0x30(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + movaps 0x40(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + movaps 0x50(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + movaps 0x60(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + movaps 0x70(TKEYP), KEY + # aesdeclast KEY, STATE # last round + .byte 0x66, 0x0f, 0x38, 0xdf, 0xc2 + ret + +/* + * _aesni_dec4: internal ABI + * input: + * KEYP: key struct pointer + * KLEN: key length + * STATE1: initial state (input) + * STATE2 + * STATE3 + * STATE4 + * output: + * STATE1: finial state (output) + * STATE2 + * STATE3 + * STATE4 + * changed: + * KEY + * TKEYP (T1) + */ +_aesni_dec4: + movaps (KEYP), KEY # key + mov KEYP, TKEYP + pxor KEY, STATE1 # round 0 + pxor KEY, STATE2 + pxor KEY, STATE3 + pxor KEY, STATE4 + add $0x30, TKEYP + cmp $24, KLEN + jb .L4dec128 + lea 0x20(TKEYP), TKEYP + je .L4dec192 + add $0x20, TKEYP + movaps -0x60(TKEYP), KEY + # aesdec KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + # aesdec KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 + # aesdec KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xde, 0xea + # aesdec KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 + movaps -0x50(TKEYP), KEY + # aesdec KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + # aesdec KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 + # aesdec KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xde, 0xea + # aesdec KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 +.align 4 +.L4dec192: + movaps -0x40(TKEYP), KEY + # aesdec KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + # aesdec KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 + # aesdec KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xde, 0xea + # aesdec KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 + movaps -0x30(TKEYP), KEY + # aesdec KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + # aesdec KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 + # aesdec KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xde, 0xea + # aesdec KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 +.align 4 +.L4dec128: + movaps -0x20(TKEYP), KEY + # aesdec KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + # aesdec KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 + # aesdec KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xde, 0xea + # aesdec KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 + movaps -0x10(TKEYP), KEY + # aesdec KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + # aesdec KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 + # aesdec KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xde, 0xea + # aesdec KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 + movaps (TKEYP), KEY + # aesdec KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + # aesdec KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 + # aesdec KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xde, 0xea + # aesdec KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 + movaps 0x10(TKEYP), KEY + # aesdec KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + # aesdec KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 + # aesdec KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xde, 0xea + # aesdec KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 + movaps 0x20(TKEYP), KEY + # aesdec KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + # aesdec KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 + # aesdec KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xde, 0xea + # aesdec KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 + movaps 0x30(TKEYP), KEY + # aesdec KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + # aesdec KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 + # aesdec KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xde, 0xea + # aesdec KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 + movaps 0x40(TKEYP), KEY + # aesdec KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + # aesdec KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 + # aesdec KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xde, 0xea + # aesdec KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 + movaps 0x50(TKEYP), KEY + # aesdec KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + # aesdec KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 + # aesdec KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xde, 0xea + # aesdec KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 + movaps 0x60(TKEYP), KEY + # aesdec KEY, STATE1 + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + # aesdec KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 + # aesdec KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xde, 0xea + # aesdec KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 + movaps 0x70(TKEYP), KEY + # aesdeclast KEY, STATE1 # last round + .byte 0x66, 0x0f, 0x38, 0xdf, 0xc2 + # aesdeclast KEY, STATE2 + .byte 0x66, 0x0f, 0x38, 0xdf, 0xe2 + # aesdeclast KEY, STATE3 + .byte 0x66, 0x0f, 0x38, 0xdf, 0xea + # aesdeclast KEY, STATE4 + .byte 0x66, 0x0f, 0x38, 0xdf, 0xf2 + ret + +/* + * void aesni_ecb_enc(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src, + * size_t len) + */ +ENTRY(aesni_ecb_enc) + test LEN, LEN # check length + jz .Lecb_enc_ret + mov 480(KEYP), KLEN + cmp $16, LEN + jb .Lecb_enc_ret + cmp $64, LEN + jb .Lecb_enc_loop1 +.align 4 +.Lecb_enc_loop4: + movups (INP), STATE1 + movups 0x10(INP), STATE2 + movups 0x20(INP), STATE3 + movups 0x30(INP), STATE4 + call _aesni_enc4 + movups STATE1, (OUTP) + movups STATE2, 0x10(OUTP) + movups STATE3, 0x20(OUTP) + movups STATE4, 0x30(OUTP) + sub $64, LEN + add $64, INP + add $64, OUTP + cmp $64, LEN + jge .Lecb_enc_loop4 + cmp $16, LEN + jb .Lecb_enc_ret +.align 4 +.Lecb_enc_loop1: + movups (INP), STATE1 + call _aesni_enc1 + movups STATE1, (OUTP) + sub $16, LEN + add $16, INP + add $16, OUTP + cmp $16, LEN + jge .Lecb_enc_loop1 +.Lecb_enc_ret: + ret + +/* + * void aesni_ecb_dec(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src, + * size_t len); + */ +ENTRY(aesni_ecb_dec) + test LEN, LEN + jz .Lecb_dec_ret + mov 480(KEYP), KLEN + add $240, KEYP + cmp $16, LEN + jb .Lecb_dec_ret + cmp $64, LEN + jb .Lecb_dec_loop1 +.align 4 +.Lecb_dec_loop4: + movups (INP), STATE1 + movups 0x10(INP), STATE2 + movups 0x20(INP), STATE3 + movups 0x30(INP), STATE4 + call _aesni_dec4 + movups STATE1, (OUTP) + movups STATE2, 0x10(OUTP) + movups STATE3, 0x20(OUTP) + movups STATE4, 0x30(OUTP) + sub $64, LEN + add $64, INP + add $64, OUTP + cmp $64, LEN + jge .Lecb_dec_loop4 + cmp $16, LEN + jb .Lecb_dec_ret +.align 4 +.Lecb_dec_loop1: + movups (INP), STATE1 + call _aesni_dec1 + movups STATE1, (OUTP) + sub $16, LEN + add $16, INP + add $16, OUTP + cmp $16, LEN + jge .Lecb_dec_loop1 +.Lecb_dec_ret: + ret + +/* + * void aesni_cbc_enc(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src, + * size_t len, u8 *iv) + */ +ENTRY(aesni_cbc_enc) + cmp $16, LEN + jb .Lcbc_enc_ret + mov 480(KEYP), KLEN + movups (IVP), STATE # load iv as initial state +.align 4 +.Lcbc_enc_loop: + movups (INP), IN # load input + pxor IN, STATE + call _aesni_enc1 + movups STATE, (OUTP) # store output + sub $16, LEN + add $16, INP + add $16, OUTP + cmp $16, LEN + jge .Lcbc_enc_loop + movups STATE, (IVP) +.Lcbc_enc_ret: + ret + +/* + * void aesni_cbc_dec(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src, + * size_t len, u8 *iv) + */ +ENTRY(aesni_cbc_dec) + cmp $16, LEN + jb .Lcbc_dec_ret + mov 480(KEYP), KLEN + add $240, KEYP + movups (IVP), IV + cmp $64, LEN + jb .Lcbc_dec_loop1 +.align 4 +.Lcbc_dec_loop4: + movups (INP), IN1 + movaps IN1, STATE1 + movups 0x10(INP), IN2 + movaps IN2, STATE2 + movups 0x20(INP), IN3 + movaps IN3, STATE3 + movups 0x30(INP), IN4 + movaps IN4, STATE4 + call _aesni_dec4 + pxor IV, STATE1 + pxor IN1, STATE2 + pxor IN2, STATE3 + pxor IN3, STATE4 + movaps IN4, IV + movups STATE1, (OUTP) + movups STATE2, 0x10(OUTP) + movups STATE3, 0x20(OUTP) + movups STATE4, 0x30(OUTP) + sub $64, LEN + add $64, INP + add $64, OUTP + cmp $64, LEN + jge .Lcbc_dec_loop4 + cmp $16, LEN + jb .Lcbc_dec_ret +.align 4 +.Lcbc_dec_loop1: + movups (INP), IN + movaps IN, STATE + call _aesni_dec1 + pxor IV, STATE + movups STATE, (OUTP) + movaps IN, IV + sub $16, LEN + add $16, INP + add $16, OUTP + cmp $16, LEN + jge .Lcbc_dec_loop1 + movups IV, (IVP) +.Lcbc_dec_ret: + ret diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c new file mode 100644 index 00000000000..02af0af6549 --- /dev/null +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -0,0 +1,461 @@ +/* + * Support for Intel AES-NI instructions. This file contains glue + * code, the real AES implementation is in intel-aes_asm.S. + * + * Copyright (C) 2008, Intel Corp. + * Author: Huang Ying + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct async_aes_ctx { + struct cryptd_ablkcipher *cryptd_tfm; +}; + +#define AESNI_ALIGN 16 +#define AES_BLOCK_MASK (~(AES_BLOCK_SIZE-1)) + +asmlinkage int aesni_set_key(struct crypto_aes_ctx *ctx, const u8 *in_key, + unsigned int key_len); +asmlinkage void aesni_enc(struct crypto_aes_ctx *ctx, u8 *out, + const u8 *in); +asmlinkage void aesni_dec(struct crypto_aes_ctx *ctx, u8 *out, + const u8 *in); +asmlinkage void aesni_ecb_enc(struct crypto_aes_ctx *ctx, u8 *out, + const u8 *in, unsigned int len); +asmlinkage void aesni_ecb_dec(struct crypto_aes_ctx *ctx, u8 *out, + const u8 *in, unsigned int len); +asmlinkage void aesni_cbc_enc(struct crypto_aes_ctx *ctx, u8 *out, + const u8 *in, unsigned int len, u8 *iv); +asmlinkage void aesni_cbc_dec(struct crypto_aes_ctx *ctx, u8 *out, + const u8 *in, unsigned int len, u8 *iv); + +static inline int kernel_fpu_using(void) +{ + if (in_interrupt() && !(read_cr0() & X86_CR0_TS)) + return 1; + return 0; +} + +static inline struct crypto_aes_ctx *aes_ctx(void *raw_ctx) +{ + unsigned long addr = (unsigned long)raw_ctx; + unsigned long align = AESNI_ALIGN; + + if (align <= crypto_tfm_ctx_alignment()) + align = 1; + return (struct crypto_aes_ctx *)ALIGN(addr, align); +} + +static int aes_set_key_common(struct crypto_tfm *tfm, void *raw_ctx, + const u8 *in_key, unsigned int key_len) +{ + struct crypto_aes_ctx *ctx = aes_ctx(raw_ctx); + u32 *flags = &tfm->crt_flags; + int err; + + if (key_len != AES_KEYSIZE_128 && key_len != AES_KEYSIZE_192 && + key_len != AES_KEYSIZE_256) { + *flags |= CRYPTO_TFM_RES_BAD_KEY_LEN; + return -EINVAL; + } + + if (kernel_fpu_using()) + err = crypto_aes_expand_key(ctx, in_key, key_len); + else { + kernel_fpu_begin(); + err = aesni_set_key(ctx, in_key, key_len); + kernel_fpu_end(); + } + + return err; +} + +static int aes_set_key(struct crypto_tfm *tfm, const u8 *in_key, + unsigned int key_len) +{ + return aes_set_key_common(tfm, crypto_tfm_ctx(tfm), in_key, key_len); +} + +static void aes_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) +{ + struct crypto_aes_ctx *ctx = aes_ctx(crypto_tfm_ctx(tfm)); + + if (kernel_fpu_using()) + crypto_aes_encrypt_x86(ctx, dst, src); + else { + kernel_fpu_begin(); + aesni_enc(ctx, dst, src); + kernel_fpu_end(); + } +} + +static void aes_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) +{ + struct crypto_aes_ctx *ctx = aes_ctx(crypto_tfm_ctx(tfm)); + + if (kernel_fpu_using()) + crypto_aes_decrypt_x86(ctx, dst, src); + else { + kernel_fpu_begin(); + aesni_dec(ctx, dst, src); + kernel_fpu_end(); + } +} + +static struct crypto_alg aesni_alg = { + .cra_name = "aes", + .cra_driver_name = "aes-aesni", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_CIPHER, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct crypto_aes_ctx)+AESNI_ALIGN-1, + .cra_alignmask = 0, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(aesni_alg.cra_list), + .cra_u = { + .cipher = { + .cia_min_keysize = AES_MIN_KEY_SIZE, + .cia_max_keysize = AES_MAX_KEY_SIZE, + .cia_setkey = aes_set_key, + .cia_encrypt = aes_encrypt, + .cia_decrypt = aes_decrypt + } + } +}; + +static int ecb_encrypt(struct blkcipher_desc *desc, + struct scatterlist *dst, struct scatterlist *src, + unsigned int nbytes) +{ + struct crypto_aes_ctx *ctx = aes_ctx(crypto_blkcipher_ctx(desc->tfm)); + struct blkcipher_walk walk; + int err; + + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt(desc, &walk); + + kernel_fpu_begin(); + while ((nbytes = walk.nbytes)) { + aesni_ecb_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr, + nbytes & AES_BLOCK_MASK); + nbytes &= AES_BLOCK_SIZE - 1; + err = blkcipher_walk_done(desc, &walk, nbytes); + } + kernel_fpu_end(); + + return err; +} + +static int ecb_decrypt(struct blkcipher_desc *desc, + struct scatterlist *dst, struct scatterlist *src, + unsigned int nbytes) +{ + struct crypto_aes_ctx *ctx = aes_ctx(crypto_blkcipher_ctx(desc->tfm)); + struct blkcipher_walk walk; + int err; + + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt(desc, &walk); + + kernel_fpu_begin(); + while ((nbytes = walk.nbytes)) { + aesni_ecb_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr, + nbytes & AES_BLOCK_MASK); + nbytes &= AES_BLOCK_SIZE - 1; + err = blkcipher_walk_done(desc, &walk, nbytes); + } + kernel_fpu_end(); + + return err; +} + +static struct crypto_alg blk_ecb_alg = { + .cra_name = "__ecb-aes-aesni", + .cra_driver_name = "__driver-ecb-aes-aesni", + .cra_priority = 0, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct crypto_aes_ctx)+AESNI_ALIGN-1, + .cra_alignmask = 0, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(blk_ecb_alg.cra_list), + .cra_u = { + .blkcipher = { + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .setkey = aes_set_key, + .encrypt = ecb_encrypt, + .decrypt = ecb_decrypt, + }, + }, +}; + +static int cbc_encrypt(struct blkcipher_desc *desc, + struct scatterlist *dst, struct scatterlist *src, + unsigned int nbytes) +{ + struct crypto_aes_ctx *ctx = aes_ctx(crypto_blkcipher_ctx(desc->tfm)); + struct blkcipher_walk walk; + int err; + + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt(desc, &walk); + + kernel_fpu_begin(); + while ((nbytes = walk.nbytes)) { + aesni_cbc_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr, + nbytes & AES_BLOCK_MASK, walk.iv); + nbytes &= AES_BLOCK_SIZE - 1; + err = blkcipher_walk_done(desc, &walk, nbytes); + } + kernel_fpu_end(); + + return err; +} + +static int cbc_decrypt(struct blkcipher_desc *desc, + struct scatterlist *dst, struct scatterlist *src, + unsigned int nbytes) +{ + struct crypto_aes_ctx *ctx = aes_ctx(crypto_blkcipher_ctx(desc->tfm)); + struct blkcipher_walk walk; + int err; + + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt(desc, &walk); + + kernel_fpu_begin(); + while ((nbytes = walk.nbytes)) { + aesni_cbc_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr, + nbytes & AES_BLOCK_MASK, walk.iv); + nbytes &= AES_BLOCK_SIZE - 1; + err = blkcipher_walk_done(desc, &walk, nbytes); + } + kernel_fpu_end(); + + return err; +} + +static struct crypto_alg blk_cbc_alg = { + .cra_name = "__cbc-aes-aesni", + .cra_driver_name = "__driver-cbc-aes-aesni", + .cra_priority = 0, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct crypto_aes_ctx)+AESNI_ALIGN-1, + .cra_alignmask = 0, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(blk_cbc_alg.cra_list), + .cra_u = { + .blkcipher = { + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .setkey = aes_set_key, + .encrypt = cbc_encrypt, + .decrypt = cbc_decrypt, + }, + }, +}; + +static int ablk_set_key(struct crypto_ablkcipher *tfm, const u8 *key, + unsigned int key_len) +{ + struct async_aes_ctx *ctx = crypto_ablkcipher_ctx(tfm); + + return crypto_ablkcipher_setkey(&ctx->cryptd_tfm->base, key, key_len); +} + +static int ablk_encrypt(struct ablkcipher_request *req) +{ + struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req); + struct async_aes_ctx *ctx = crypto_ablkcipher_ctx(tfm); + + if (kernel_fpu_using()) { + struct ablkcipher_request *cryptd_req = + ablkcipher_request_ctx(req); + memcpy(cryptd_req, req, sizeof(*req)); + ablkcipher_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base); + return crypto_ablkcipher_encrypt(cryptd_req); + } else { + struct blkcipher_desc desc; + desc.tfm = cryptd_ablkcipher_child(ctx->cryptd_tfm); + desc.info = req->info; + desc.flags = 0; + return crypto_blkcipher_crt(desc.tfm)->encrypt( + &desc, req->dst, req->src, req->nbytes); + } +} + +static int ablk_decrypt(struct ablkcipher_request *req) +{ + struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req); + struct async_aes_ctx *ctx = crypto_ablkcipher_ctx(tfm); + + if (kernel_fpu_using()) { + struct ablkcipher_request *cryptd_req = + ablkcipher_request_ctx(req); + memcpy(cryptd_req, req, sizeof(*req)); + ablkcipher_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base); + return crypto_ablkcipher_decrypt(cryptd_req); + } else { + struct blkcipher_desc desc; + desc.tfm = cryptd_ablkcipher_child(ctx->cryptd_tfm); + desc.info = req->info; + desc.flags = 0; + return crypto_blkcipher_crt(desc.tfm)->decrypt( + &desc, req->dst, req->src, req->nbytes); + } +} + +static void ablk_exit(struct crypto_tfm *tfm) +{ + struct async_aes_ctx *ctx = crypto_tfm_ctx(tfm); + + cryptd_free_ablkcipher(ctx->cryptd_tfm); +} + +static void ablk_init_common(struct crypto_tfm *tfm, + struct cryptd_ablkcipher *cryptd_tfm) +{ + struct async_aes_ctx *ctx = crypto_tfm_ctx(tfm); + + ctx->cryptd_tfm = cryptd_tfm; + tfm->crt_ablkcipher.reqsize = sizeof(struct ablkcipher_request) + + crypto_ablkcipher_reqsize(&cryptd_tfm->base); +} + +static int ablk_ecb_init(struct crypto_tfm *tfm) +{ + struct cryptd_ablkcipher *cryptd_tfm; + + cryptd_tfm = cryptd_alloc_ablkcipher("__driver-ecb-aes-aesni", 0, 0); + if (IS_ERR(cryptd_tfm)) + return PTR_ERR(cryptd_tfm); + ablk_init_common(tfm, cryptd_tfm); + return 0; +} + +static struct crypto_alg ablk_ecb_alg = { + .cra_name = "ecb(aes)", + .cra_driver_name = "ecb-aes-aesni", + .cra_priority = 400, + .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct async_aes_ctx), + .cra_alignmask = 0, + .cra_type = &crypto_ablkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(ablk_ecb_alg.cra_list), + .cra_init = ablk_ecb_init, + .cra_exit = ablk_exit, + .cra_u = { + .ablkcipher = { + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .setkey = ablk_set_key, + .encrypt = ablk_encrypt, + .decrypt = ablk_decrypt, + }, + }, +}; + +static int ablk_cbc_init(struct crypto_tfm *tfm) +{ + struct cryptd_ablkcipher *cryptd_tfm; + + cryptd_tfm = cryptd_alloc_ablkcipher("__driver-cbc-aes-aesni", 0, 0); + if (IS_ERR(cryptd_tfm)) + return PTR_ERR(cryptd_tfm); + ablk_init_common(tfm, cryptd_tfm); + return 0; +} + +static struct crypto_alg ablk_cbc_alg = { + .cra_name = "cbc(aes)", + .cra_driver_name = "cbc-aes-aesni", + .cra_priority = 400, + .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct async_aes_ctx), + .cra_alignmask = 0, + .cra_type = &crypto_ablkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(ablk_cbc_alg.cra_list), + .cra_init = ablk_cbc_init, + .cra_exit = ablk_exit, + .cra_u = { + .ablkcipher = { + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .setkey = ablk_set_key, + .encrypt = ablk_encrypt, + .decrypt = ablk_decrypt, + }, + }, +}; + +static int __init aesni_init(void) +{ + int err; + + if (!cpu_has_aes) { + printk(KERN_ERR "Intel AES-NI instructions are not detected.\n"); + return -ENODEV; + } + if ((err = crypto_register_alg(&aesni_alg))) + goto aes_err; + if ((err = crypto_register_alg(&blk_ecb_alg))) + goto blk_ecb_err; + if ((err = crypto_register_alg(&blk_cbc_alg))) + goto blk_cbc_err; + if ((err = crypto_register_alg(&ablk_ecb_alg))) + goto ablk_ecb_err; + if ((err = crypto_register_alg(&ablk_cbc_alg))) + goto ablk_cbc_err; + + return err; + +ablk_cbc_err: + crypto_unregister_alg(&ablk_ecb_alg); +ablk_ecb_err: + crypto_unregister_alg(&blk_cbc_alg); +blk_cbc_err: + crypto_unregister_alg(&blk_ecb_alg); +blk_ecb_err: + crypto_unregister_alg(&aesni_alg); +aes_err: + return err; +} + +static void __exit aesni_exit(void) +{ + crypto_unregister_alg(&ablk_cbc_alg); + crypto_unregister_alg(&ablk_ecb_alg); + crypto_unregister_alg(&blk_cbc_alg); + crypto_unregister_alg(&blk_ecb_alg); + crypto_unregister_alg(&aesni_alg); +} + +module_init(aesni_init); +module_exit(aesni_exit); + +MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm, Intel AES-NI instructions optimized"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("aes"); diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 7301e60dc4a..0beba0d1468 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -213,6 +213,7 @@ extern const char * const x86_power_flags[32]; #define cpu_has_xmm boot_cpu_has(X86_FEATURE_XMM) #define cpu_has_xmm2 boot_cpu_has(X86_FEATURE_XMM2) #define cpu_has_xmm3 boot_cpu_has(X86_FEATURE_XMM3) +#define cpu_has_aes boot_cpu_has(X86_FEATURE_AES) #define cpu_has_ht boot_cpu_has(X86_FEATURE_HT) #define cpu_has_mp boot_cpu_has(X86_FEATURE_MP) #define cpu_has_nx boot_cpu_has(X86_FEATURE_NX) diff --git a/crypto/Kconfig b/crypto/Kconfig index 8dde4fcf99c..a83ce0462b6 100644 --- a/crypto/Kconfig +++ b/crypto/Kconfig @@ -470,6 +470,31 @@ config CRYPTO_AES_X86_64 See for more information. +config CRYPTO_AES_NI_INTEL + tristate "AES cipher algorithms (AES-NI)" + depends on (X86 || UML_X86) && 64BIT + select CRYPTO_AES_X86_64 + select CRYPTO_CRYPTD + select CRYPTO_ALGAPI + help + Use Intel AES-NI instructions for AES algorithm. + + AES cipher algorithms (FIPS-197). AES uses the Rijndael + algorithm. + + Rijndael appears to be consistently a very good performer in + both hardware and software across a wide range of computing + environments regardless of its use in feedback or non-feedback + modes. Its key setup time is excellent, and its key agility is + good. Rijndael's very low memory requirements make it very well + suited for restricted-space environments, in which it also + demonstrates excellent performance. Rijndael's operations are + among the easiest to defend against power and timing attacks. + + The AES specifies three key sizes: 128, 192 and 256 bits + + See for more information. + config CRYPTO_ANUBIS tristate "Anubis cipher algorithm" select CRYPTO_ALGAPI -- cgit v1.2.3-70-g09d2 From 712406a6bf59ebf4a00358bb59a4a2a1b2953d90 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 9 Feb 2009 10:54:03 -0800 Subject: tracing/function-graph-tracer: make arch generic push pop functions There is nothing really arch specific of the push and pop functions used by the function graph tracer. This patch moves them to generic code. Acked-by: Frederic Weisbecker Acked-by: Ingo Molnar Signed-off-by: Steven Rostedt --- arch/x86/include/asm/ftrace.h | 25 ------------ arch/x86/kernel/dumpstack.c | 1 + arch/x86/kernel/ftrace.c | 75 +----------------------------------- include/linux/ftrace.h | 24 ++++++++++++ kernel/trace/trace_functions_graph.c | 75 ++++++++++++++++++++++++++++++++++++ 5 files changed, 101 insertions(+), 99 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index b55b4a7fbef..db24c2278be 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -55,29 +55,4 @@ struct dyn_arch_ftrace { #endif /* __ASSEMBLY__ */ #endif /* CONFIG_FUNCTION_TRACER */ -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - -#ifndef __ASSEMBLY__ - -/* - * Stack of return addresses for functions - * of a thread. - * Used in struct thread_info - */ -struct ftrace_ret_stack { - unsigned long ret; - unsigned long func; - unsigned long long calltime; -}; - -/* - * Primary handler of a function return. - * It relays on ftrace_return_to_handler. - * Defined in entry_32/64.S - */ -extern void return_to_handler(void); - -#endif /* __ASSEMBLY__ */ -#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ - #endif /* _ASM_X86_FTRACE_H */ diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 6b1f6f6f866..c0852291b62 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 231bdd3c5b1..76f7141e0f9 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -389,79 +389,6 @@ void ftrace_nmi_exit(void) #endif /* !CONFIG_DYNAMIC_FTRACE */ -/* Add a function return address to the trace stack on thread info.*/ -static int push_return_trace(unsigned long ret, unsigned long long time, - unsigned long func, int *depth) -{ - int index; - - if (!current->ret_stack) - return -EBUSY; - - /* The return trace stack is full */ - if (current->curr_ret_stack == FTRACE_RETFUNC_DEPTH - 1) { - atomic_inc(¤t->trace_overrun); - return -EBUSY; - } - - index = ++current->curr_ret_stack; - barrier(); - current->ret_stack[index].ret = ret; - current->ret_stack[index].func = func; - current->ret_stack[index].calltime = time; - *depth = index; - - return 0; -} - -/* Retrieve a function return address to the trace stack on thread info.*/ -static void pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret) -{ - int index; - - index = current->curr_ret_stack; - - if (unlikely(index < 0)) { - ftrace_graph_stop(); - WARN_ON(1); - /* Might as well panic, otherwise we have no where to go */ - *ret = (unsigned long)panic; - return; - } - - *ret = current->ret_stack[index].ret; - trace->func = current->ret_stack[index].func; - trace->calltime = current->ret_stack[index].calltime; - trace->overrun = atomic_read(¤t->trace_overrun); - trace->depth = index; - barrier(); - current->curr_ret_stack--; - -} - -/* - * Send the trace to the ring-buffer. - * @return the original return address. - */ -unsigned long ftrace_return_to_handler(void) -{ - struct ftrace_graph_ret trace; - unsigned long ret; - - pop_return_trace(&trace, &ret); - trace.rettime = cpu_clock(raw_smp_processor_id()); - ftrace_graph_return(&trace); - - if (unlikely(!ret)) { - ftrace_graph_stop(); - WARN_ON(1); - /* Might as well panic. What else to do? */ - ret = (unsigned long)panic; - } - - return ret; -} - /* * Hook the return address and push it in the stack of return addrs * in current thread info. @@ -521,7 +448,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) calltime = cpu_clock(raw_smp_processor_id()); - if (push_return_trace(old, calltime, + if (ftrace_push_return_trace(old, calltime, self_addr, &trace.depth) == -EBUSY) { *parent = old; return; diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 677432b9cb7..a7f8134c594 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -379,6 +379,30 @@ struct ftrace_graph_ret { #ifdef CONFIG_FUNCTION_GRAPH_TRACER +/* + * Stack of return addresses for functions + * of a thread. + * Used in struct thread_info + */ +struct ftrace_ret_stack { + unsigned long ret; + unsigned long func; + unsigned long long calltime; +}; + +/* + * Primary handler of a function return. + * It relays on ftrace_return_to_handler. + * Defined in entry_32/64.S + */ +extern void return_to_handler(void); + +extern int +ftrace_push_return_trace(unsigned long ret, unsigned long long time, + unsigned long func, int *depth); +extern void +ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret); + /* * Sometimes we don't want to trace a function with the function * graph tracer but we want them to keep traced by the usual function diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 930c08e5b38..dce71a5b51b 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -42,6 +42,81 @@ static struct tracer_flags tracer_flags = { /* pid on the last trace processed */ static pid_t last_pid[NR_CPUS] = { [0 ... NR_CPUS-1] = -1 }; +/* Add a function return address to the trace stack on thread info.*/ +int +ftrace_push_return_trace(unsigned long ret, unsigned long long time, + unsigned long func, int *depth) +{ + int index; + + if (!current->ret_stack) + return -EBUSY; + + /* The return trace stack is full */ + if (current->curr_ret_stack == FTRACE_RETFUNC_DEPTH - 1) { + atomic_inc(¤t->trace_overrun); + return -EBUSY; + } + + index = ++current->curr_ret_stack; + barrier(); + current->ret_stack[index].ret = ret; + current->ret_stack[index].func = func; + current->ret_stack[index].calltime = time; + *depth = index; + + return 0; +} + +/* Retrieve a function return address to the trace stack on thread info.*/ +void +ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret) +{ + int index; + + index = current->curr_ret_stack; + + if (unlikely(index < 0)) { + ftrace_graph_stop(); + WARN_ON(1); + /* Might as well panic, otherwise we have no where to go */ + *ret = (unsigned long)panic; + return; + } + + *ret = current->ret_stack[index].ret; + trace->func = current->ret_stack[index].func; + trace->calltime = current->ret_stack[index].calltime; + trace->overrun = atomic_read(¤t->trace_overrun); + trace->depth = index; + barrier(); + current->curr_ret_stack--; + +} + +/* + * Send the trace to the ring-buffer. + * @return the original return address. + */ +unsigned long ftrace_return_to_handler(void) +{ + struct ftrace_graph_ret trace; + unsigned long ret; + + ftrace_pop_return_trace(&trace, &ret); + trace.rettime = cpu_clock(raw_smp_processor_id()); + ftrace_graph_return(&trace); + + if (unlikely(!ret)) { + ftrace_graph_stop(); + WARN_ON(1); + /* Might as well panic. What else to do? */ + ret = (unsigned long)panic; + } + + return ret; +} + static int graph_trace_init(struct trace_array *tr) { int cpu, ret; -- cgit v1.2.3-70-g09d2 From 16239630974516a8879a3695ee9b4dc661f79f96 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 17 Feb 2009 17:57:30 -0500 Subject: ftrace, x86: make kernel text writable only for conversions Impact: keep kernel text read only Because dynamic ftrace converts the calls to mcount into and out of nops at run time, we needed to always keep the kernel text writable. But this defeats the point of CONFIG_DEBUG_RODATA. This patch converts the kernel code to writable before ftrace modifies the text, and converts it back to read only afterward. The kernel text is converted to read/write, stop_machine is called to modify the code, then the kernel text is converted back to read only. The original version used SYSTEM_STATE to determine when it was OK or not to change the code to rw or ro. Andrew Morton pointed out that using SYSTEM_STATE is a bad idea since there is no guarantee to what its state will actually be. Instead, I moved the check into the set_kernel_text_* functions themselves, and use a local variable to determine when it is OK to change the kernel text RW permissions. [ Update: Ingo Molnar suggested moving the prototypes to cacheflush.h ] Reviewed-by: Andrew Morton Signed-off-by: Steven Rostedt --- arch/x86/include/asm/cacheflush.h | 5 +++++ arch/x86/kernel/ftrace.c | 13 +++++++++++++ arch/x86/mm/init_32.c | 35 ++++++++++++++++++++++++++++++++--- arch/x86/mm/init_64.c | 37 ++++++++++++++++++++++++++++++++----- 4 files changed, 82 insertions(+), 8 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h index 2f8466540fb..6145063cfe0 100644 --- a/arch/x86/include/asm/cacheflush.h +++ b/arch/x86/include/asm/cacheflush.h @@ -104,6 +104,11 @@ void clflush_cache_range(void *addr, unsigned int size); #ifdef CONFIG_DEBUG_RODATA void mark_rodata_ro(void); extern const int rodata_test_data; +void set_kernel_text_rw(void); +void set_kernel_text_ro(void); +#else +static inline void set_kernel_text_rw(void) { } +static inline void set_kernel_text_ro(void) { } #endif #ifdef CONFIG_DEBUG_RODATA_TEST diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 231bdd3c5b1..77857d4f7d0 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -18,6 +18,7 @@ #include #include +#include #include #include #include @@ -26,6 +27,18 @@ #ifdef CONFIG_DYNAMIC_FTRACE +int ftrace_arch_code_modify_prepare(void) +{ + set_kernel_text_rw(); + return 0; +} + +int ftrace_arch_code_modify_post_process(void) +{ + set_kernel_text_ro(); + return 0; +} + union ftrace_code_union { char code[MCOUNT_INSN_SIZE]; struct { diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 2cef0507441..3eb2ed188a4 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -1155,17 +1155,47 @@ static noinline int do_test_wp_bit(void) const int rodata_test_data = 0xC3; EXPORT_SYMBOL_GPL(rodata_test_data); +static int kernel_set_to_readonly; + +void set_kernel_text_rw(void) +{ + unsigned long start = PFN_ALIGN(_text); + unsigned long size = PFN_ALIGN(_etext) - start; + + if (!kernel_set_to_readonly) + return; + + pr_debug("Set kernel text: %lx - %lx for read write\n", + start, start+size); + + set_pages_rw(virt_to_page(start), size >> PAGE_SHIFT); +} + +void set_kernel_text_ro(void) +{ + unsigned long start = PFN_ALIGN(_text); + unsigned long size = PFN_ALIGN(_etext) - start; + + if (!kernel_set_to_readonly) + return; + + pr_debug("Set kernel text: %lx - %lx for read only\n", + start, start+size); + + set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT); +} + void mark_rodata_ro(void) { unsigned long start = PFN_ALIGN(_text); unsigned long size = PFN_ALIGN(_etext) - start; -#ifndef CONFIG_DYNAMIC_FTRACE - /* Dynamic tracing modifies the kernel text section */ set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT); printk(KERN_INFO "Write protecting the kernel text: %luk\n", size >> 10); + kernel_set_to_readonly = 1; + #ifdef CONFIG_CPA_DEBUG printk(KERN_INFO "Testing CPA: Reverting %lx-%lx\n", start, start+size); @@ -1174,7 +1204,6 @@ void mark_rodata_ro(void) printk(KERN_INFO "Testing CPA: write protecting again\n"); set_pages_ro(virt_to_page(start), size>>PAGE_SHIFT); #endif -#endif /* CONFIG_DYNAMIC_FTRACE */ start += size; size = (unsigned long)__end_rodata - start; diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index e6d36b49025..63fdc531601 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -986,21 +986,48 @@ void free_initmem(void) const int rodata_test_data = 0xC3; EXPORT_SYMBOL_GPL(rodata_test_data); +static int kernel_set_to_readonly; + +void set_kernel_text_rw(void) +{ + unsigned long start = PFN_ALIGN(_stext); + unsigned long end = PFN_ALIGN(__start_rodata); + + if (!kernel_set_to_readonly) + return; + + pr_debug("Set kernel text: %lx - %lx for read write\n", + start, end); + + set_memory_rw(start, (end - start) >> PAGE_SHIFT); +} + +void set_kernel_text_ro(void) +{ + unsigned long start = PFN_ALIGN(_stext); + unsigned long end = PFN_ALIGN(__start_rodata); + + if (!kernel_set_to_readonly) + return; + + pr_debug("Set kernel text: %lx - %lx for read only\n", + start, end); + + set_memory_ro(start, (end - start) >> PAGE_SHIFT); +} + void mark_rodata_ro(void) { unsigned long start = PFN_ALIGN(_stext), end = PFN_ALIGN(__end_rodata); unsigned long rodata_start = ((unsigned long)__start_rodata + PAGE_SIZE - 1) & PAGE_MASK; -#ifdef CONFIG_DYNAMIC_FTRACE - /* Dynamic tracing modifies the kernel text section */ - start = rodata_start; -#endif - printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n", (end - start) >> 10); set_memory_ro(start, (end - start) >> PAGE_SHIFT); + kernel_set_to_readonly = 1; + /* * The rodata section (but not the kernel text!) should also be * not-executable. -- cgit v1.2.3-70-g09d2 From 499aa86dcbc3c4daf7d2c59c5c30e1a78220fbc1 Mon Sep 17 00:00:00 2001 From: Markus Metzger Date: Tue, 24 Feb 2009 14:12:34 +0100 Subject: x86, ptrace: remove CONFIG guards around declarations Remove unnecessary CONFIG guards around type declarations and macro definitions. Reported-by: Cyrill Gorcunov Signed-off-by: Markus Metzger Cc: markus.t.metzger@gmail.com Cc: roland@redhat.com Cc: eranian@googlemail.com Cc: oleg@redhat.com Cc: juan.villacis@intel.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/ptrace-abi.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/ptrace-abi.h b/arch/x86/include/asm/ptrace-abi.h index 8e0f8d199e0..86723035a51 100644 --- a/arch/x86/include/asm/ptrace-abi.h +++ b/arch/x86/include/asm/ptrace-abi.h @@ -80,8 +80,6 @@ #define PTRACE_SINGLEBLOCK 33 /* resume execution until next branch */ -#ifdef CONFIG_X86_PTRACE_BTS - #ifndef __ASSEMBLY__ #include @@ -140,6 +138,5 @@ struct ptrace_bts_config { BTS records are read from oldest to newest. Returns number of BTS records drained. */ -#endif /* CONFIG_X86_PTRACE_BTS */ #endif /* _ASM_X86_PTRACE_ABI_H */ -- cgit v1.2.3-70-g09d2 From 199785eac892a1fa1b71cc22bec58e8b156d9311 Mon Sep 17 00:00:00 2001 From: Matthias-Christian Ott Date: Fri, 20 Feb 2009 20:52:17 -0500 Subject: [CPUFREQ] p4-clockmod reports wrong frequency. http://bugzilla.kernel.org/show_bug.cgi?id=10968 [ Updated for current tree, and fixed compile failure when p4-clockmod was built modular -- davej] From: Matthias-Christian Ott Signed-off-by: Dominik Brodowski Signed-off-by: Dave Jones --- arch/x86/include/asm/timer.h | 2 +- arch/x86/kernel/cpu/cpufreq/p4-clockmod.c | 7 ++++++ arch/x86/kernel/cpu/cpufreq/speedstep-lib.c | 34 +++++++++++++++++------------ arch/x86/kernel/tsc.c | 3 --- 4 files changed, 28 insertions(+), 18 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h index 2bb6a835c45..4f5c2472485 100644 --- a/arch/x86/include/asm/timer.h +++ b/arch/x86/include/asm/timer.h @@ -11,8 +11,8 @@ unsigned long native_calibrate_tsc(void); #ifdef CONFIG_X86_32 extern int timer_ack; +#endif extern int recalibrate_cpu_khz(void); -#endif /* CONFIG_X86_32 */ extern int no_timer_check; diff --git a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c index 46a2a7a5314..1778402305e 100644 --- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c +++ b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c @@ -31,6 +31,7 @@ #include #include +#include #include "speedstep-lib.h" @@ -224,6 +225,12 @@ static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy) dprintk("has errata -- disabling low frequencies\n"); } + if (speedstep_detect_processor() == SPEEDSTEP_CPU_P4D && + c->x86_model < 2) { + /* switch to maximum frequency and measure result */ + cpufreq_p4_setdc(policy->cpu, DC_DISABLE); + recalibrate_cpu_khz(); + } /* get max frequency */ stock_freq = cpufreq_p4_get_frequency(c); if (!stock_freq) diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c b/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c index 55c696daa05..2e3c6862657 100644 --- a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c +++ b/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c @@ -16,6 +16,7 @@ #include #include +#include #include "speedstep-lib.h" #define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ @@ -178,6 +179,15 @@ static unsigned int pentium4_get_frequency(void) u32 msr_lo, msr_hi, mult; unsigned int fsb = 0; unsigned int ret; + u8 fsb_code; + + /* Pentium 4 Model 0 and 1 do not have the Core Clock Frequency + * to System Bus Frequency Ratio Field in the Processor Frequency + * Configuration Register of the MSR. Therefore the current + * frequency cannot be calculated and has to be measured. + */ + if (c->x86_model < 2) + return cpu_khz; rdmsr(0x2c, msr_lo, msr_hi); @@ -188,21 +198,17 @@ static unsigned int pentium4_get_frequency(void) * revision #12 in Table B-1: MSRs in the Pentium 4 and * Intel Xeon Processors, on page B-4 and B-5. */ - if (c->x86_model < 2) + fsb_code = (msr_lo >> 16) & 0x7; + switch (fsb_code) { + case 0: fsb = 100 * 1000; - else { - u8 fsb_code = (msr_lo >> 16) & 0x7; - switch (fsb_code) { - case 0: - fsb = 100 * 1000; - break; - case 1: - fsb = 13333 * 10; - break; - case 2: - fsb = 200 * 1000; - break; - } + break; + case 1: + fsb = 13333 * 10; + break; + case 2: + fsb = 200 * 1000; + break; } if (!fsb) diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 599e5816863..5ad22f8f5f3 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -523,8 +523,6 @@ unsigned long native_calibrate_tsc(void) return tsc_pit_min; } -#ifdef CONFIG_X86_32 -/* Only called from the Powernow K7 cpu freq driver */ int recalibrate_cpu_khz(void) { #ifndef CONFIG_SMP @@ -546,7 +544,6 @@ int recalibrate_cpu_khz(void) EXPORT_SYMBOL(recalibrate_cpu_khz); -#endif /* CONFIG_X86_32 */ /* Accelerators for sched_clock() * convert from cycles(64bits) => nanoseconds (64bits) -- cgit v1.2.3-70-g09d2 From 78ff7fae04554b49d29226ed12536268c2500d1f Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 6 Mar 2009 10:37:54 -0500 Subject: x86: implement atomic text_poke() via fixmap Use fixmaps instead of vmap/vunmap in text_poke() for avoiding page allocation and delayed unmapping. At the result of above change, text_poke() becomes atomic and can be called from stop_machine() etc. Signed-off-by: Masami Hiramatsu Acked-by: Mathieu Desnoyers LKML-Reference: <49B14352.2040705@redhat.com> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/fixmap.h | 2 ++ arch/x86/kernel/alternative.c | 24 +++++++++++++++--------- 2 files changed, 17 insertions(+), 9 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 63a79c77d22..81937a5dc77 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -111,6 +111,8 @@ enum fixed_addresses { #ifdef CONFIG_PARAVIRT FIX_PARAVIRT_BOOTMAP, #endif + FIX_TEXT_POKE0, /* reserve 2 pages for text_poke() */ + FIX_TEXT_POKE1, __end_of_permanent_fixed_addresses, #ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT FIX_OHCI1394_BASE, diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 092a7b8be68..2d903b760dd 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -13,7 +13,9 @@ #include #include #include +#include #include +#include #define MAX_PATCH_LEN (255-1) @@ -505,15 +507,16 @@ void *text_poke_early(void *addr, const void *opcode, size_t len) * It means the size must be writable atomically and the address must be aligned * in a way that permits an atomic write. It also makes sure we fit on a single * page. + * + * Note: Must be called under text_mutex. */ void *__kprobes text_poke(void *addr, const void *opcode, size_t len) { + unsigned long flags; char *vaddr; - int nr_pages = 2; struct page *pages[2]; int i; - might_sleep(); if (!core_kernel_text((unsigned long)addr)) { pages[0] = vmalloc_to_page(addr); pages[1] = vmalloc_to_page(addr + PAGE_SIZE); @@ -523,14 +526,17 @@ void *__kprobes text_poke(void *addr, const void *opcode, size_t len) pages[1] = virt_to_page(addr + PAGE_SIZE); } BUG_ON(!pages[0]); - if (!pages[1]) - nr_pages = 1; - vaddr = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL); - BUG_ON(!vaddr); - local_irq_disable(); + set_fixmap(FIX_TEXT_POKE0, page_to_phys(pages[0])); + if (pages[1]) + set_fixmap(FIX_TEXT_POKE1, page_to_phys(pages[1])); + vaddr = (char *)fix_to_virt(FIX_TEXT_POKE0); + local_irq_save(flags); memcpy(&vaddr[(unsigned long)addr & ~PAGE_MASK], opcode, len); - local_irq_enable(); - vunmap(vaddr); + local_irq_restore(flags); + clear_fixmap(FIX_TEXT_POKE0); + if (pages[1]) + clear_fixmap(FIX_TEXT_POKE1); + local_flush_tlb(); sync_core(); /* Could also do a CLFLUSH here to speed up CPU recovery; but that causes hangs on some VIA CPUs. */ -- cgit v1.2.3-70-g09d2 From e01009833e22dc87075d770554b34d797843ed23 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 10 Mar 2009 16:27:48 +0900 Subject: percpu: make x86 addr <-> pcpu ptr conversion macros generic Impact: generic addr <-> pcpu ptr conversion macros There's nothing arch specific about x86 __addr_to_pcpu_ptr() and __pcpu_ptr_to_addr(). With proper __per_cpu_load and __per_cpu_start defined, they'll do the right thing regardless of actual layout. Move these macros from arch/x86/include/asm/percpu.h to mm/percpu.c and allow archs to override it as necessary. Signed-off-by: Tejun Heo --- arch/x86/include/asm/percpu.h | 8 -------- mm/percpu.c | 16 +++++++++++++++- 2 files changed, 15 insertions(+), 9 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index 8f1d2fbec1d..aee103b26d0 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -43,14 +43,6 @@ #else /* ...!ASSEMBLY */ #include -#include - -#define __addr_to_pcpu_ptr(addr) \ - (void *)((unsigned long)(addr) - (unsigned long)pcpu_base_addr \ - + (unsigned long)__per_cpu_start) -#define __pcpu_ptr_to_addr(ptr) \ - (void *)((unsigned long)(ptr) + (unsigned long)pcpu_base_addr \ - - (unsigned long)__per_cpu_start) #ifdef CONFIG_SMP #define __percpu_arg(x) "%%"__stringify(__percpu_seg)":%P" #x diff --git a/mm/percpu.c b/mm/percpu.c index bfe6a3afaf4..c6f38a2afac 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -46,7 +46,8 @@ * - define CONFIG_HAVE_DYNAMIC_PER_CPU_AREA * * - define __addr_to_pcpu_ptr() and __pcpu_ptr_to_addr() to translate - * regular address to percpu pointer and back + * regular address to percpu pointer and back if they need to be + * different from the default * * - use pcpu_setup_first_chunk() during percpu area initialization to * setup the first chunk containing the kernel static percpu area @@ -67,11 +68,24 @@ #include #include +#include #include #define PCPU_SLOT_BASE_SHIFT 5 /* 1-31 shares the same slot */ #define PCPU_DFL_MAP_ALLOC 16 /* start a map with 16 ents */ +/* default addr <-> pcpu_ptr mapping, override in asm/percpu.h if necessary */ +#ifndef __addr_to_pcpu_ptr +#define __addr_to_pcpu_ptr(addr) \ + (void *)((unsigned long)(addr) - (unsigned long)pcpu_base_addr \ + + (unsigned long)__per_cpu_start) +#endif +#ifndef __pcpu_ptr_to_addr +#define __pcpu_ptr_to_addr(ptr) \ + (void *)((unsigned long)(ptr) + (unsigned long)pcpu_base_addr \ + - (unsigned long)__per_cpu_start) +#endif + struct pcpu_chunk { struct list_head list; /* linked to pcpu_slot lists */ struct rb_node rb_node; /* key is chunk->vm->addr */ -- cgit v1.2.3-70-g09d2 From 9b779edf4b97798d037bb44fca2719ac184d0f14 Mon Sep 17 00:00:00 2001 From: Jaswinder Singh Rajput Date: Tue, 10 Mar 2009 15:37:51 +0530 Subject: x86: cpu architecture debug code Introduce: cat /sys/kernel/debug/x86/cpu/* for Intel and AMD processors to view / debug the state of each CPU. By using this we can debug whole range of registers and other cpu information for debugging purpose and monitor how things are changing. This can be useful for developers as well as for users. Signed-off-by: Jaswinder Singh Rajput LKML-Reference: <1236701373.3387.4.camel@localhost.localdomain> Signed-off-by: Ingo Molnar --- arch/x86/Kconfig | 6 + arch/x86/include/asm/cpu_debug.h | 193 ++++++++++ arch/x86/kernel/cpu/Makefile | 2 + arch/x86/kernel/cpu/cpu_debug.c | 784 +++++++++++++++++++++++++++++++++++++++ 4 files changed, 985 insertions(+) create mode 100755 arch/x86/include/asm/cpu_debug.h create mode 100755 arch/x86/kernel/cpu/cpu_debug.c (limited to 'arch/x86/include') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 31758378bcd..03f0a3aa43b 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -931,6 +931,12 @@ config X86_CPUID with major 203 and minors 0 to 31 for /dev/cpu/0/cpuid to /dev/cpu/31/cpuid. +config X86_CPU_DEBUG + tristate "/sys/kernel/debug/x86/cpu/* - CPU Debug support" + ---help--- + If you select this option, this will provide various x86 CPUs + information through debugfs. + choice prompt "High Memory Support" default HIGHMEM4G if !X86_NUMAQ diff --git a/arch/x86/include/asm/cpu_debug.h b/arch/x86/include/asm/cpu_debug.h new file mode 100755 index 00000000000..d24d64fcee0 --- /dev/null +++ b/arch/x86/include/asm/cpu_debug.h @@ -0,0 +1,193 @@ +#ifndef _ASM_X86_CPU_DEBUG_H +#define _ASM_X86_CPU_DEBUG_H + +/* + * CPU x86 architecture debug + * + * Copyright(C) 2009 Jaswinder Singh Rajput + */ + +/* Register flags */ +enum cpu_debug_bit { +/* Model Specific Registers (MSRs) */ + CPU_MC_BIT, /* Machine Check */ + CPU_MONITOR_BIT, /* Monitor */ + CPU_TIME_BIT, /* Time */ + CPU_PMC_BIT, /* Performance Monitor */ + CPU_PLATFORM_BIT, /* Platform */ + CPU_APIC_BIT, /* APIC */ + CPU_POWERON_BIT, /* Power-on */ + CPU_CONTROL_BIT, /* Control */ + CPU_FEATURES_BIT, /* Features control */ + CPU_LBRANCH_BIT, /* Last Branch */ + CPU_BIOS_BIT, /* BIOS */ + CPU_FREQ_BIT, /* Frequency */ + CPU_MTTR_BIT, /* MTRR */ + CPU_PERF_BIT, /* Performance */ + CPU_CACHE_BIT, /* Cache */ + CPU_SYSENTER_BIT, /* Sysenter */ + CPU_THERM_BIT, /* Thermal */ + CPU_MISC_BIT, /* Miscellaneous */ + CPU_DEBUG_BIT, /* Debug */ + CPU_PAT_BIT, /* PAT */ + CPU_VMX_BIT, /* VMX */ + CPU_CALL_BIT, /* System Call */ + CPU_BASE_BIT, /* BASE Address */ + CPU_SMM_BIT, /* System mgmt mode */ + CPU_SVM_BIT, /*Secure Virtual Machine*/ + CPU_OSVM_BIT, /* OS-Visible Workaround*/ +/* Standard Registers */ + CPU_TSS_BIT, /* Task Stack Segment */ + CPU_CR_BIT, /* Control Registers */ + CPU_DT_BIT, /* Descriptor Table */ +/* End of Registers flags */ + CPU_REG_ALL_BIT, /* Select all Registers */ +}; + +#define CPU_REG_ALL (~0) /* Select all Registers */ + +#define CPU_MC (1 << CPU_MC_BIT) +#define CPU_MONITOR (1 << CPU_MONITOR_BIT) +#define CPU_TIME (1 << CPU_TIME_BIT) +#define CPU_PMC (1 << CPU_PMC_BIT) +#define CPU_PLATFORM (1 << CPU_PLATFORM_BIT) +#define CPU_APIC (1 << CPU_APIC_BIT) +#define CPU_POWERON (1 << CPU_POWERON_BIT) +#define CPU_CONTROL (1 << CPU_CONTROL_BIT) +#define CPU_FEATURES (1 << CPU_FEATURES_BIT) +#define CPU_LBRANCH (1 << CPU_LBRANCH_BIT) +#define CPU_BIOS (1 << CPU_BIOS_BIT) +#define CPU_FREQ (1 << CPU_FREQ_BIT) +#define CPU_MTRR (1 << CPU_MTTR_BIT) +#define CPU_PERF (1 << CPU_PERF_BIT) +#define CPU_CACHE (1 << CPU_CACHE_BIT) +#define CPU_SYSENTER (1 << CPU_SYSENTER_BIT) +#define CPU_THERM (1 << CPU_THERM_BIT) +#define CPU_MISC (1 << CPU_MISC_BIT) +#define CPU_DEBUG (1 << CPU_DEBUG_BIT) +#define CPU_PAT (1 << CPU_PAT_BIT) +#define CPU_VMX (1 << CPU_VMX_BIT) +#define CPU_CALL (1 << CPU_CALL_BIT) +#define CPU_BASE (1 << CPU_BASE_BIT) +#define CPU_SMM (1 << CPU_SMM_BIT) +#define CPU_SVM (1 << CPU_SVM_BIT) +#define CPU_OSVM (1 << CPU_OSVM_BIT) +#define CPU_TSS (1 << CPU_TSS_BIT) +#define CPU_CR (1 << CPU_CR_BIT) +#define CPU_DT (1 << CPU_DT_BIT) + +/* Register file flags */ +enum cpu_file_bit { + CPU_INDEX_BIT, /* index */ + CPU_VALUE_BIT, /* value */ +}; + +#define CPU_FILE_VALUE (1 << CPU_VALUE_BIT) + +/* + * DisplayFamily_DisplayModel Processor Families/Processor Number Series + * -------------------------- ------------------------------------------ + * 05_01, 05_02, 05_04 Pentium, Pentium with MMX + * + * 06_01 Pentium Pro + * 06_03, 06_05 Pentium II Xeon, Pentium II + * 06_07, 06_08, 06_0A, 06_0B Pentium III Xeon, Pentum III + * + * 06_09, 060D Pentium M + * + * 06_0E Core Duo, Core Solo + * + * 06_0F Xeon 3000, 3200, 5100, 5300, 7300 series, + * Core 2 Quad, Core 2 Extreme, Core 2 Duo, + * Pentium dual-core + * 06_17 Xeon 5200, 5400 series, Core 2 Quad Q9650 + * + * 06_1C Atom + * + * 0F_00, 0F_01, 0F_02 Xeon, Xeon MP, Pentium 4 + * 0F_03, 0F_04 Xeon, Xeon MP, Pentium 4, Pentium D + * + * 0F_06 Xeon 7100, 5000 Series, Xeon MP, + * Pentium 4, Pentium D + */ + +/* Register processors bits */ +enum cpu_processor_bit { + CPU_NONE, +/* Intel */ + CPU_INTEL_PENTIUM_BIT, + CPU_INTEL_P6_BIT, + CPU_INTEL_PENTIUM_M_BIT, + CPU_INTEL_CORE_BIT, + CPU_INTEL_CORE2_BIT, + CPU_INTEL_ATOM_BIT, + CPU_INTEL_XEON_P4_BIT, + CPU_INTEL_XEON_MP_BIT, +}; + +#define CPU_ALL (~0) /* Select all CPUs */ + +#define CPU_INTEL_PENTIUM (1 << CPU_INTEL_PENTIUM_BIT) +#define CPU_INTEL_P6 (1 << CPU_INTEL_P6_BIT) +#define CPU_INTEL_PENTIUM_M (1 << CPU_INTEL_PENTIUM_M_BIT) +#define CPU_INTEL_CORE (1 << CPU_INTEL_CORE_BIT) +#define CPU_INTEL_CORE2 (1 << CPU_INTEL_CORE2_BIT) +#define CPU_INTEL_ATOM (1 << CPU_INTEL_ATOM_BIT) +#define CPU_INTEL_XEON_P4 (1 << CPU_INTEL_XEON_P4_BIT) +#define CPU_INTEL_XEON_MP (1 << CPU_INTEL_XEON_MP_BIT) + +#define CPU_INTEL_PX (CPU_INTEL_P6 | CPU_INTEL_PENTIUM_M) +#define CPU_INTEL_COREX (CPU_INTEL_CORE | CPU_INTEL_CORE2) +#define CPU_INTEL_XEON (CPU_INTEL_XEON_P4 | CPU_INTEL_XEON_MP) +#define CPU_CO_AT (CPU_INTEL_CORE | CPU_INTEL_ATOM) +#define CPU_C2_AT (CPU_INTEL_CORE2 | CPU_INTEL_ATOM) +#define CPU_CX_AT (CPU_INTEL_COREX | CPU_INTEL_ATOM) +#define CPU_CX_XE (CPU_INTEL_COREX | CPU_INTEL_XEON) +#define CPU_P6_XE (CPU_INTEL_P6 | CPU_INTEL_XEON) +#define CPU_PM_CO_AT (CPU_INTEL_PENTIUM_M | CPU_CO_AT) +#define CPU_C2_AT_XE (CPU_C2_AT | CPU_INTEL_XEON) +#define CPU_CX_AT_XE (CPU_CX_AT | CPU_INTEL_XEON) +#define CPU_P6_CX_AT (CPU_INTEL_P6 | CPU_CX_AT) +#define CPU_P6_CX_XE (CPU_P6_XE | CPU_INTEL_COREX) +#define CPU_P6_CX_AT_XE (CPU_INTEL_P6 | CPU_CX_AT_XE) +#define CPU_PM_CX_AT_XE (CPU_INTEL_PENTIUM_M | CPU_CX_AT_XE) +#define CPU_PM_CX_AT (CPU_INTEL_PENTIUM_M | CPU_CX_AT) +#define CPU_PM_CX_XE (CPU_INTEL_PENTIUM_M | CPU_CX_XE) +#define CPU_PX_CX_AT (CPU_INTEL_PX | CPU_CX_AT) +#define CPU_PX_CX_AT_XE (CPU_INTEL_PX | CPU_CX_AT_XE) + +/* Select all Intel CPUs*/ +#define CPU_INTEL_ALL (CPU_INTEL_PENTIUM | CPU_PX_CX_AT_XE) + +#define MAX_CPU_FILES 512 + +struct cpu_private { + unsigned cpu; + unsigned type; + unsigned reg; + unsigned file; +}; + +struct cpu_debug_base { + char *name; /* Register name */ + unsigned flag; /* Register flag */ +}; + +struct cpu_cpuX_base { + struct dentry *dentry; /* Register dentry */ + int init; /* Register index file */ +}; + +struct cpu_file_base { + char *name; /* Register file name */ + unsigned flag; /* Register file flag */ +}; + +struct cpu_debug_range { + unsigned min; /* Register range min */ + unsigned max; /* Register range max */ + unsigned flag; /* Supported flags */ + unsigned model; /* Supported models */ +}; + +#endif /* _ASM_X86_CPU_DEBUG_H */ diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 82db7f45e2d..d4356f8b752 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -14,6 +14,8 @@ obj-y += vmware.o hypervisor.o obj-$(CONFIG_X86_32) += bugs.o cmpxchg.o obj-$(CONFIG_X86_64) += bugs_64.o +obj-$(CONFIG_X86_CPU_DEBUG) += cpu_debug.o + obj-$(CONFIG_CPU_SUP_INTEL) += intel.o obj-$(CONFIG_CPU_SUP_AMD) += amd.o obj-$(CONFIG_CPU_SUP_CYRIX_32) += cyrix.o diff --git a/arch/x86/kernel/cpu/cpu_debug.c b/arch/x86/kernel/cpu/cpu_debug.c new file mode 100755 index 00000000000..0bdf4daba20 --- /dev/null +++ b/arch/x86/kernel/cpu/cpu_debug.c @@ -0,0 +1,784 @@ +/* + * CPU x86 architecture debug code + * + * Copyright(C) 2009 Jaswinder Singh Rajput + * + * For licencing details see kernel-base/COPYING + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +static DEFINE_PER_CPU(struct cpu_cpuX_base, cpu_arr[CPU_REG_ALL_BIT]); +static DEFINE_PER_CPU(struct cpu_private *, priv_arr[MAX_CPU_FILES]); +static DEFINE_PER_CPU(unsigned, cpu_modelflag); +static DEFINE_PER_CPU(int, cpu_priv_count); +static DEFINE_PER_CPU(unsigned, cpu_model); + +static DEFINE_MUTEX(cpu_debug_lock); + +static struct dentry *cpu_debugfs_dir; + +static struct cpu_debug_base cpu_base[] = { + { "mc", CPU_MC }, /* Machine Check */ + { "monitor", CPU_MONITOR }, /* Monitor */ + { "time", CPU_TIME }, /* Time */ + { "pmc", CPU_PMC }, /* Performance Monitor */ + { "platform", CPU_PLATFORM }, /* Platform */ + { "apic", CPU_APIC }, /* APIC */ + { "poweron", CPU_POWERON }, /* Power-on */ + { "control", CPU_CONTROL }, /* Control */ + { "features", CPU_FEATURES }, /* Features control */ + { "lastbranch", CPU_LBRANCH }, /* Last Branch */ + { "bios", CPU_BIOS }, /* BIOS */ + { "freq", CPU_FREQ }, /* Frequency */ + { "mtrr", CPU_MTRR }, /* MTRR */ + { "perf", CPU_PERF }, /* Performance */ + { "cache", CPU_CACHE }, /* Cache */ + { "sysenter", CPU_SYSENTER }, /* Sysenter */ + { "therm", CPU_THERM }, /* Thermal */ + { "misc", CPU_MISC }, /* Miscellaneous */ + { "debug", CPU_DEBUG }, /* Debug */ + { "pat", CPU_PAT }, /* PAT */ + { "vmx", CPU_VMX }, /* VMX */ + { "call", CPU_CALL }, /* System Call */ + { "base", CPU_BASE }, /* BASE Address */ + { "smm", CPU_SMM }, /* System mgmt mode */ + { "svm", CPU_SVM }, /*Secure Virtial Machine*/ + { "osvm", CPU_OSVM }, /* OS-Visible Workaround*/ + { "tss", CPU_TSS }, /* Task Stack Segment */ + { "cr", CPU_CR }, /* Control Registers */ + { "dt", CPU_DT }, /* Descriptor Table */ + { "registers", CPU_REG_ALL }, /* Select all Registers */ +}; + +static struct cpu_file_base cpu_file[] = { + { "index", CPU_REG_ALL }, /* index */ + { "value", CPU_REG_ALL }, /* value */ +}; + +/* Intel Registers Range */ +static struct cpu_debug_range cpu_intel_range[] = { + { 0x00000000, 0x00000001, CPU_MC, CPU_INTEL_ALL }, + { 0x00000006, 0x00000007, CPU_MONITOR, CPU_CX_AT_XE }, + { 0x00000010, 0x00000010, CPU_TIME, CPU_INTEL_ALL }, + { 0x00000011, 0x00000013, CPU_PMC, CPU_INTEL_PENTIUM }, + { 0x00000017, 0x00000017, CPU_PLATFORM, CPU_PX_CX_AT_XE }, + { 0x0000001B, 0x0000001B, CPU_APIC, CPU_P6_CX_AT_XE }, + + { 0x0000002A, 0x0000002A, CPU_POWERON, CPU_PX_CX_AT_XE }, + { 0x0000002B, 0x0000002B, CPU_POWERON, CPU_INTEL_XEON }, + { 0x0000002C, 0x0000002C, CPU_FREQ, CPU_INTEL_XEON }, + { 0x0000003A, 0x0000003A, CPU_CONTROL, CPU_CX_AT_XE }, + + { 0x00000040, 0x00000043, CPU_LBRANCH, CPU_PM_CX_AT_XE }, + { 0x00000044, 0x00000047, CPU_LBRANCH, CPU_PM_CO_AT }, + { 0x00000060, 0x00000063, CPU_LBRANCH, CPU_C2_AT }, + { 0x00000064, 0x00000067, CPU_LBRANCH, CPU_INTEL_ATOM }, + + { 0x00000079, 0x00000079, CPU_BIOS, CPU_P6_CX_AT_XE }, + { 0x00000088, 0x0000008A, CPU_CACHE, CPU_INTEL_P6 }, + { 0x0000008B, 0x0000008B, CPU_BIOS, CPU_P6_CX_AT_XE }, + { 0x0000009B, 0x0000009B, CPU_MONITOR, CPU_INTEL_XEON }, + + { 0x000000C1, 0x000000C2, CPU_PMC, CPU_P6_CX_AT }, + { 0x000000CD, 0x000000CD, CPU_FREQ, CPU_CX_AT }, + { 0x000000E7, 0x000000E8, CPU_PERF, CPU_CX_AT }, + { 0x000000FE, 0x000000FE, CPU_MTRR, CPU_P6_CX_XE }, + + { 0x00000116, 0x00000116, CPU_CACHE, CPU_INTEL_P6 }, + { 0x00000118, 0x00000118, CPU_CACHE, CPU_INTEL_P6 }, + { 0x00000119, 0x00000119, CPU_CACHE, CPU_INTEL_PX }, + { 0x0000011A, 0x0000011B, CPU_CACHE, CPU_INTEL_P6 }, + { 0x0000011E, 0x0000011E, CPU_CACHE, CPU_PX_CX_AT }, + + { 0x00000174, 0x00000176, CPU_SYSENTER, CPU_P6_CX_AT_XE }, + { 0x00000179, 0x0000017A, CPU_MC, CPU_PX_CX_AT_XE }, + { 0x0000017B, 0x0000017B, CPU_MC, CPU_P6_XE }, + { 0x00000186, 0x00000187, CPU_PMC, CPU_P6_CX_AT }, + { 0x00000198, 0x00000199, CPU_PERF, CPU_PM_CX_AT_XE }, + { 0x0000019A, 0x0000019A, CPU_TIME, CPU_PM_CX_AT_XE }, + { 0x0000019B, 0x0000019D, CPU_THERM, CPU_PM_CX_AT_XE }, + { 0x000001A0, 0x000001A0, CPU_MISC, CPU_PM_CX_AT_XE }, + + { 0x000001C9, 0x000001C9, CPU_LBRANCH, CPU_PM_CX_AT }, + { 0x000001D7, 0x000001D8, CPU_LBRANCH, CPU_INTEL_XEON }, + { 0x000001D9, 0x000001D9, CPU_DEBUG, CPU_CX_AT_XE }, + { 0x000001DA, 0x000001DA, CPU_LBRANCH, CPU_INTEL_XEON }, + { 0x000001DB, 0x000001DB, CPU_LBRANCH, CPU_P6_XE }, + { 0x000001DC, 0x000001DC, CPU_LBRANCH, CPU_INTEL_P6 }, + { 0x000001DD, 0x000001DE, CPU_LBRANCH, CPU_PX_CX_AT_XE }, + { 0x000001E0, 0x000001E0, CPU_LBRANCH, CPU_INTEL_P6 }, + + { 0x00000200, 0x0000020F, CPU_MTRR, CPU_P6_CX_XE }, + { 0x00000250, 0x00000250, CPU_MTRR, CPU_P6_CX_XE }, + { 0x00000258, 0x00000259, CPU_MTRR, CPU_P6_CX_XE }, + { 0x00000268, 0x0000026F, CPU_MTRR, CPU_P6_CX_XE }, + { 0x00000277, 0x00000277, CPU_PAT, CPU_C2_AT_XE }, + { 0x000002FF, 0x000002FF, CPU_MTRR, CPU_P6_CX_XE }, + + { 0x00000300, 0x00000308, CPU_PMC, CPU_INTEL_XEON }, + { 0x00000309, 0x0000030B, CPU_PMC, CPU_C2_AT_XE }, + { 0x0000030C, 0x00000311, CPU_PMC, CPU_INTEL_XEON }, + { 0x00000345, 0x00000345, CPU_PMC, CPU_C2_AT }, + { 0x00000360, 0x00000371, CPU_PMC, CPU_INTEL_XEON }, + { 0x0000038D, 0x00000390, CPU_PMC, CPU_C2_AT }, + { 0x000003A0, 0x000003BE, CPU_PMC, CPU_INTEL_XEON }, + { 0x000003C0, 0x000003CD, CPU_PMC, CPU_INTEL_XEON }, + { 0x000003E0, 0x000003E1, CPU_PMC, CPU_INTEL_XEON }, + { 0x000003F0, 0x000003F0, CPU_PMC, CPU_INTEL_XEON }, + { 0x000003F1, 0x000003F1, CPU_PMC, CPU_C2_AT_XE }, + { 0x000003F2, 0x000003F2, CPU_PMC, CPU_INTEL_XEON }, + + { 0x00000400, 0x00000402, CPU_MC, CPU_PM_CX_AT_XE }, + { 0x00000403, 0x00000403, CPU_MC, CPU_INTEL_XEON }, + { 0x00000404, 0x00000406, CPU_MC, CPU_PM_CX_AT_XE }, + { 0x00000407, 0x00000407, CPU_MC, CPU_INTEL_XEON }, + { 0x00000408, 0x0000040A, CPU_MC, CPU_PM_CX_AT_XE }, + { 0x0000040B, 0x0000040B, CPU_MC, CPU_INTEL_XEON }, + { 0x0000040C, 0x0000040E, CPU_MC, CPU_PM_CX_XE }, + { 0x0000040F, 0x0000040F, CPU_MC, CPU_INTEL_XEON }, + { 0x00000410, 0x00000412, CPU_MC, CPU_PM_CX_AT_XE }, + { 0x00000413, 0x00000417, CPU_MC, CPU_CX_AT_XE }, + { 0x00000480, 0x0000048B, CPU_VMX, CPU_CX_AT_XE }, + + { 0x00000600, 0x00000600, CPU_DEBUG, CPU_PM_CX_AT_XE }, + { 0x00000680, 0x0000068F, CPU_LBRANCH, CPU_INTEL_XEON }, + { 0x000006C0, 0x000006CF, CPU_LBRANCH, CPU_INTEL_XEON }, + + { 0x000107CC, 0x000107D3, CPU_PMC, CPU_INTEL_XEON_MP }, + + { 0xC0000080, 0xC0000080, CPU_FEATURES, CPU_INTEL_XEON }, + { 0xC0000081, 0xC0000082, CPU_CALL, CPU_INTEL_XEON }, + { 0xC0000084, 0xC0000084, CPU_CALL, CPU_INTEL_XEON }, + { 0xC0000100, 0xC0000102, CPU_BASE, CPU_INTEL_XEON }, +}; + +/* AMD Registers Range */ +static struct cpu_debug_range cpu_amd_range[] = { + { 0x00000010, 0x00000010, CPU_TIME, CPU_ALL, }, + { 0x0000001B, 0x0000001B, CPU_APIC, CPU_ALL, }, + { 0x000000FE, 0x000000FE, CPU_MTRR, CPU_ALL, }, + + { 0x00000174, 0x00000176, CPU_SYSENTER, CPU_ALL, }, + { 0x00000179, 0x0000017A, CPU_MC, CPU_ALL, }, + { 0x0000017B, 0x0000017B, CPU_MC, CPU_ALL, }, + { 0x000001D9, 0x000001D9, CPU_DEBUG, CPU_ALL, }, + { 0x000001DB, 0x000001DE, CPU_LBRANCH, CPU_ALL, }, + + { 0x00000200, 0x0000020F, CPU_MTRR, CPU_ALL, }, + { 0x00000250, 0x00000250, CPU_MTRR, CPU_ALL, }, + { 0x00000258, 0x00000259, CPU_MTRR, CPU_ALL, }, + { 0x00000268, 0x0000026F, CPU_MTRR, CPU_ALL, }, + { 0x00000277, 0x00000277, CPU_PAT, CPU_ALL, }, + { 0x000002FF, 0x000002FF, CPU_MTRR, CPU_ALL, }, + + { 0x00000400, 0x00000417, CPU_MC, CPU_ALL, }, + + { 0xC0000080, 0xC0000080, CPU_FEATURES, CPU_ALL, }, + { 0xC0000081, 0xC0000084, CPU_CALL, CPU_ALL, }, + { 0xC0000100, 0xC0000102, CPU_BASE, CPU_ALL, }, + { 0xC0000103, 0xC0000103, CPU_TIME, CPU_ALL, }, + + { 0xC0000408, 0xC000040A, CPU_MC, CPU_ALL, }, + + { 0xc0010000, 0xc0010007, CPU_PMC, CPU_ALL, }, + { 0xc0010010, 0xc0010010, CPU_MTRR, CPU_ALL, }, + { 0xc0010016, 0xc001001A, CPU_MTRR, CPU_ALL, }, + { 0xc001001D, 0xc001001D, CPU_MTRR, CPU_ALL, }, + { 0xc0010030, 0xc0010035, CPU_BIOS, CPU_ALL, }, + { 0xc0010056, 0xc0010056, CPU_SMM, CPU_ALL, }, + { 0xc0010061, 0xc0010063, CPU_SMM, CPU_ALL, }, + { 0xc0010074, 0xc0010074, CPU_MC, CPU_ALL, }, + { 0xc0010111, 0xc0010113, CPU_SMM, CPU_ALL, }, + { 0xc0010114, 0xc0010118, CPU_SVM, CPU_ALL, }, + { 0xc0010119, 0xc001011A, CPU_SMM, CPU_ALL, }, + { 0xc0010140, 0xc0010141, CPU_OSVM, CPU_ALL, }, + { 0xc0010156, 0xc0010156, CPU_SMM, CPU_ALL, }, +}; + + +static int get_cpu_modelflag(unsigned cpu) +{ + int flag; + + switch (per_cpu(cpu_model, cpu)) { + /* Intel */ + case 0x0501: + case 0x0502: + case 0x0504: + flag = CPU_INTEL_PENTIUM; + break; + case 0x0601: + case 0x0603: + case 0x0605: + case 0x0607: + case 0x0608: + case 0x060A: + case 0x060B: + flag = CPU_INTEL_P6; + break; + case 0x0609: + case 0x060D: + flag = CPU_INTEL_PENTIUM_M; + break; + case 0x060E: + flag = CPU_INTEL_CORE; + break; + case 0x060F: + case 0x0617: + flag = CPU_INTEL_CORE2; + break; + case 0x061C: + flag = CPU_INTEL_ATOM; + break; + case 0x0F00: + case 0x0F01: + case 0x0F02: + case 0x0F03: + case 0x0F04: + flag = CPU_INTEL_XEON_P4; + break; + case 0x0F06: + flag = CPU_INTEL_XEON_MP; + break; + default: + flag = CPU_NONE; + break; + } + + return flag; +} + +static int get_cpu_range_count(unsigned cpu) +{ + int index; + + switch (per_cpu(cpu_model, cpu) >> 16) { + case X86_VENDOR_INTEL: + index = ARRAY_SIZE(cpu_intel_range); + break; + case X86_VENDOR_AMD: + index = ARRAY_SIZE(cpu_amd_range); + break; + default: + index = 0; + break; + } + + return index; +} + +static int is_typeflag_valid(unsigned cpu, unsigned flag) +{ + unsigned vendor, modelflag; + int i, index; + + /* Standard Registers should be always valid */ + if (flag >= CPU_TSS) + return 1; + + modelflag = per_cpu(cpu_modelflag, cpu); + vendor = per_cpu(cpu_model, cpu) >> 16; + index = get_cpu_range_count(cpu); + + for (i = 0; i < index; i++) { + switch (vendor) { + case X86_VENDOR_INTEL: + if ((cpu_intel_range[i].model & modelflag) && + (cpu_intel_range[i].flag & flag)) + return 1; + break; + case X86_VENDOR_AMD: + if (cpu_amd_range[i].flag & flag) + return 1; + break; + } + } + + /* Invalid */ + return 0; +} + +static unsigned get_cpu_range(unsigned cpu, unsigned *min, unsigned *max, + int index, unsigned flag) +{ + unsigned modelflag; + + modelflag = per_cpu(cpu_modelflag, cpu); + *max = 0; + switch (per_cpu(cpu_model, cpu) >> 16) { + case X86_VENDOR_INTEL: + if ((cpu_intel_range[index].model & modelflag) && + (cpu_intel_range[index].flag & flag)) { + *min = cpu_intel_range[index].min; + *max = cpu_intel_range[index].max; + } + break; + case X86_VENDOR_AMD: + if (cpu_amd_range[index].flag & flag) { + *min = cpu_amd_range[index].min; + *max = cpu_amd_range[index].max; + } + break; + } + + return *max; +} + +/* This function can also be called with seq = NULL for printk */ +static void print_cpu_data(struct seq_file *seq, unsigned type, + u32 low, u32 high) +{ + struct cpu_private *priv; + u64 val = high; + + if (seq) { + priv = seq->private; + if (priv->file) { + val = (val << 32) | low; + seq_printf(seq, "0x%llx\n", val); + } else + seq_printf(seq, " %08x: %08x_%08x\n", + type, high, low); + } else + printk(KERN_INFO " %08x: %08x_%08x\n", type, high, low); +} + +/* This function can also be called with seq = NULL for printk */ +static void print_msr(struct seq_file *seq, unsigned cpu, unsigned flag) +{ + unsigned msr, msr_min, msr_max; + struct cpu_private *priv; + u32 low, high; + int i, range; + + if (seq) { + priv = seq->private; + if (priv->file) { + if (!rdmsr_safe_on_cpu(priv->cpu, priv->reg, + &low, &high)) + print_cpu_data(seq, priv->reg, low, high); + return; + } + } + + range = get_cpu_range_count(cpu); + + for (i = 0; i < range; i++) { + if (!get_cpu_range(cpu, &msr_min, &msr_max, i, flag)) + continue; + + for (msr = msr_min; msr <= msr_max; msr++) { + if (rdmsr_safe_on_cpu(cpu, msr, &low, &high)) + continue; + print_cpu_data(seq, msr, low, high); + } + } +} + +static void print_tss(void *arg) +{ + struct pt_regs *regs = task_pt_regs(current); + struct seq_file *seq = arg; + unsigned int seg; + + seq_printf(seq, " RAX\t: %016lx\n", regs->ax); + seq_printf(seq, " RBX\t: %016lx\n", regs->bx); + seq_printf(seq, " RCX\t: %016lx\n", regs->cx); + seq_printf(seq, " RDX\t: %016lx\n", regs->dx); + + seq_printf(seq, " RSI\t: %016lx\n", regs->si); + seq_printf(seq, " RDI\t: %016lx\n", regs->di); + seq_printf(seq, " RBP\t: %016lx\n", regs->bp); + seq_printf(seq, " ESP\t: %016lx\n", regs->sp); + +#ifdef CONFIG_X86_64 + seq_printf(seq, " R08\t: %016lx\n", regs->r8); + seq_printf(seq, " R09\t: %016lx\n", regs->r9); + seq_printf(seq, " R10\t: %016lx\n", regs->r10); + seq_printf(seq, " R11\t: %016lx\n", regs->r11); + seq_printf(seq, " R12\t: %016lx\n", regs->r12); + seq_printf(seq, " R13\t: %016lx\n", regs->r13); + seq_printf(seq, " R14\t: %016lx\n", regs->r14); + seq_printf(seq, " R15\t: %016lx\n", regs->r15); +#endif + + asm("movl %%cs,%0" : "=r" (seg)); + seq_printf(seq, " CS\t: %04x\n", seg); + asm("movl %%ds,%0" : "=r" (seg)); + seq_printf(seq, " DS\t: %04x\n", seg); + seq_printf(seq, " SS\t: %04lx\n", regs->ss); + asm("movl %%es,%0" : "=r" (seg)); + seq_printf(seq, " ES\t: %04x\n", seg); + asm("movl %%fs,%0" : "=r" (seg)); + seq_printf(seq, " FS\t: %04x\n", seg); + asm("movl %%gs,%0" : "=r" (seg)); + seq_printf(seq, " GS\t: %04x\n", seg); + + seq_printf(seq, " EFLAGS\t: %016lx\n", regs->flags); + + seq_printf(seq, " EIP\t: %016lx\n", regs->ip); +} + +static void print_cr(void *arg) +{ + struct seq_file *seq = arg; + + seq_printf(seq, " cr0\t: %016lx\n", read_cr0()); + seq_printf(seq, " cr2\t: %016lx\n", read_cr2()); + seq_printf(seq, " cr3\t: %016lx\n", read_cr3()); + seq_printf(seq, " cr4\t: %016lx\n", read_cr4_safe()); +#ifdef CONFIG_X86_64 + seq_printf(seq, " cr8\t: %016lx\n", read_cr8()); +#endif +} + +static void print_desc_ptr(char *str, struct seq_file *seq, struct desc_ptr dt) +{ + seq_printf(seq, " %s\t: %016llx\n", str, (u64)(dt.address | dt.size)); +} + +static void print_dt(void *seq) +{ + struct desc_ptr dt; + unsigned long ldt; + + /* IDT */ + store_idt((struct desc_ptr *)&dt); + print_desc_ptr("IDT", seq, dt); + + /* GDT */ + store_gdt((struct desc_ptr *)&dt); + print_desc_ptr("GDT", seq, dt); + + /* LDT */ + store_ldt(ldt); + seq_printf(seq, " LDT\t: %016lx\n", ldt); + + /* TR */ + store_tr(ldt); + seq_printf(seq, " TR\t: %016lx\n", ldt); +} + +static void print_dr(void *arg) +{ + struct seq_file *seq = arg; + unsigned long dr; + int i; + + for (i = 0; i < 8; i++) { + /* Ignore db4, db5 */ + if ((i == 4) || (i == 5)) + continue; + get_debugreg(dr, i); + seq_printf(seq, " dr%d\t: %016lx\n", i, dr); + } + + seq_printf(seq, "\n MSR\t:\n"); +} + +static void print_apic(void *arg) +{ + struct seq_file *seq = arg; + +#ifdef CONFIG_X86_LOCAL_APIC + seq_printf(seq, " LAPIC\t:\n"); + seq_printf(seq, " ID\t\t: %08x\n", apic_read(APIC_ID) >> 24); + seq_printf(seq, " LVR\t\t: %08x\n", apic_read(APIC_LVR)); + seq_printf(seq, " TASKPRI\t: %08x\n", apic_read(APIC_TASKPRI)); + seq_printf(seq, " ARBPRI\t\t: %08x\n", apic_read(APIC_ARBPRI)); + seq_printf(seq, " PROCPRI\t: %08x\n", apic_read(APIC_PROCPRI)); + seq_printf(seq, " LDR\t\t: %08x\n", apic_read(APIC_LDR)); + seq_printf(seq, " DFR\t\t: %08x\n", apic_read(APIC_DFR)); + seq_printf(seq, " SPIV\t\t: %08x\n", apic_read(APIC_SPIV)); + seq_printf(seq, " ISR\t\t: %08x\n", apic_read(APIC_ISR)); + seq_printf(seq, " ESR\t\t: %08x\n", apic_read(APIC_ESR)); + seq_printf(seq, " ICR\t\t: %08x\n", apic_read(APIC_ICR)); + seq_printf(seq, " ICR2\t\t: %08x\n", apic_read(APIC_ICR2)); + seq_printf(seq, " LVTT\t\t: %08x\n", apic_read(APIC_LVTT)); + seq_printf(seq, " LVTTHMR\t: %08x\n", apic_read(APIC_LVTTHMR)); + seq_printf(seq, " LVTPC\t\t: %08x\n", apic_read(APIC_LVTPC)); + seq_printf(seq, " LVT0\t\t: %08x\n", apic_read(APIC_LVT0)); + seq_printf(seq, " LVT1\t\t: %08x\n", apic_read(APIC_LVT1)); + seq_printf(seq, " LVTERR\t\t: %08x\n", apic_read(APIC_LVTERR)); + seq_printf(seq, " TMICT\t\t: %08x\n", apic_read(APIC_TMICT)); + seq_printf(seq, " TMCCT\t\t: %08x\n", apic_read(APIC_TMCCT)); + seq_printf(seq, " TDCR\t\t: %08x\n", apic_read(APIC_TDCR)); +#endif /* CONFIG_X86_LOCAL_APIC */ + + seq_printf(seq, "\n MSR\t:\n"); +} + +static int cpu_seq_show(struct seq_file *seq, void *v) +{ + struct cpu_private *priv = seq->private; + + if (priv == NULL) + return -EINVAL; + + switch (cpu_base[priv->type].flag) { + case CPU_TSS: + smp_call_function_single(priv->cpu, print_tss, seq, 1); + break; + case CPU_CR: + smp_call_function_single(priv->cpu, print_cr, seq, 1); + break; + case CPU_DT: + smp_call_function_single(priv->cpu, print_dt, seq, 1); + break; + case CPU_DEBUG: + if (priv->file == CPU_INDEX_BIT) + smp_call_function_single(priv->cpu, print_dr, seq, 1); + print_msr(seq, priv->cpu, cpu_base[priv->type].flag); + break; + case CPU_APIC: + if (priv->file == CPU_INDEX_BIT) + smp_call_function_single(priv->cpu, print_apic, seq, 1); + print_msr(seq, priv->cpu, cpu_base[priv->type].flag); + break; + + default: + print_msr(seq, priv->cpu, cpu_base[priv->type].flag); + break; + } + seq_printf(seq, "\n"); + + return 0; +} + +static void *cpu_seq_start(struct seq_file *seq, loff_t *pos) +{ + if (*pos == 0) /* One time is enough ;-) */ + return seq; + + return NULL; +} + +static void *cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + (*pos)++; + + return cpu_seq_start(seq, pos); +} + +static void cpu_seq_stop(struct seq_file *seq, void *v) +{ +} + +static const struct seq_operations cpu_seq_ops = { + .start = cpu_seq_start, + .next = cpu_seq_next, + .stop = cpu_seq_stop, + .show = cpu_seq_show, +}; + +static int cpu_seq_open(struct inode *inode, struct file *file) +{ + struct cpu_private *priv = inode->i_private; + struct seq_file *seq; + int err; + + err = seq_open(file, &cpu_seq_ops); + if (!err) { + seq = file->private_data; + seq->private = priv; + } + + return err; +} + +static const struct file_operations cpu_fops = { + .open = cpu_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static int cpu_create_file(unsigned cpu, unsigned type, unsigned reg, + unsigned file, struct dentry *dentry) +{ + struct cpu_private *priv = NULL; + + /* Already intialized */ + if (file == CPU_INDEX_BIT) + if (per_cpu(cpu_arr[type].init, cpu)) + return 0; + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (priv == NULL) + return -ENOMEM; + + priv->cpu = cpu; + priv->type = type; + priv->reg = reg; + priv->file = file; + mutex_lock(&cpu_debug_lock); + per_cpu(priv_arr[type], cpu) = priv; + per_cpu(cpu_priv_count, cpu)++; + mutex_unlock(&cpu_debug_lock); + + if (file) + debugfs_create_file(cpu_file[file].name, S_IRUGO, + dentry, (void *)priv, &cpu_fops); + else { + debugfs_create_file(cpu_base[type].name, S_IRUGO, + per_cpu(cpu_arr[type].dentry, cpu), + (void *)priv, &cpu_fops); + mutex_lock(&cpu_debug_lock); + per_cpu(cpu_arr[type].init, cpu) = 1; + mutex_unlock(&cpu_debug_lock); + } + + return 0; +} + +static int cpu_init_regfiles(unsigned cpu, unsigned int type, unsigned reg, + struct dentry *dentry) +{ + unsigned file; + int err = 0; + + for (file = 0; file < ARRAY_SIZE(cpu_file); file++) { + err = cpu_create_file(cpu, type, reg, file, dentry); + if (err) + return err; + } + + return err; +} + +static int cpu_init_msr(unsigned cpu, unsigned type, struct dentry *dentry) +{ + struct dentry *cpu_dentry = NULL; + unsigned reg, reg_min, reg_max; + int i, range, err = 0; + char reg_dir[12]; + u32 low, high; + + range = get_cpu_range_count(cpu); + + for (i = 0; i < range; i++) { + if (!get_cpu_range(cpu, ®_min, ®_max, i, + cpu_base[type].flag)) + continue; + + for (reg = reg_min; reg <= reg_max; reg++) { + if (rdmsr_safe_on_cpu(cpu, reg, &low, &high)) + continue; + + sprintf(reg_dir, "0x%x", reg); + cpu_dentry = debugfs_create_dir(reg_dir, dentry); + err = cpu_init_regfiles(cpu, type, reg, cpu_dentry); + if (err) + return err; + } + } + + return err; +} + +static int cpu_init_allreg(unsigned cpu, struct dentry *dentry) +{ + struct dentry *cpu_dentry = NULL; + unsigned type; + int err = 0; + + for (type = 0; type < ARRAY_SIZE(cpu_base) - 1; type++) { + if (!is_typeflag_valid(cpu, cpu_base[type].flag)) + continue; + cpu_dentry = debugfs_create_dir(cpu_base[type].name, dentry); + per_cpu(cpu_arr[type].dentry, cpu) = cpu_dentry; + + if (type < CPU_TSS_BIT) + err = cpu_init_msr(cpu, type, cpu_dentry); + else + err = cpu_create_file(cpu, type, 0, CPU_INDEX_BIT, + cpu_dentry); + if (err) + return err; + } + + return err; +} + +static int cpu_init_cpu(void) +{ + struct dentry *cpu_dentry = NULL; + struct cpuinfo_x86 *cpui; + char cpu_dir[12]; + unsigned cpu; + int err = 0; + + for (cpu = 0; cpu < nr_cpu_ids; cpu++) { + cpui = &cpu_data(cpu); + if (!cpu_has(cpui, X86_FEATURE_MSR)) + continue; + per_cpu(cpu_model, cpu) = ((cpui->x86_vendor << 16) | + (cpui->x86 << 8) | + (cpui->x86_model)); + per_cpu(cpu_modelflag, cpu) = get_cpu_modelflag(cpu); + + sprintf(cpu_dir, "cpu%d", cpu); + cpu_dentry = debugfs_create_dir(cpu_dir, cpu_debugfs_dir); + err = cpu_init_allreg(cpu, cpu_dentry); + + pr_info("cpu%d(%d) debug files %d\n", + cpu, nr_cpu_ids, per_cpu(cpu_priv_count, cpu)); + if (per_cpu(cpu_priv_count, cpu) > MAX_CPU_FILES) { + pr_err("Register files count %d exceeds limit %d\n", + per_cpu(cpu_priv_count, cpu), MAX_CPU_FILES); + per_cpu(cpu_priv_count, cpu) = MAX_CPU_FILES; + err = -ENFILE; + } + if (err) + return err; + } + + return err; +} + +static int __init cpu_debug_init(void) +{ + cpu_debugfs_dir = debugfs_create_dir("cpu", arch_debugfs_dir); + + return cpu_init_cpu(); +} + +static void __exit cpu_debug_exit(void) +{ + int i, cpu; + + if (cpu_debugfs_dir) + debugfs_remove_recursive(cpu_debugfs_dir); + + for (cpu = 0; cpu < nr_cpu_ids; cpu++) + for (i = 0; i < per_cpu(cpu_priv_count, cpu); i++) + kfree(per_cpu(priv_arr[i], cpu)); +} + +module_init(cpu_debug_init); +module_exit(cpu_debug_exit); + +MODULE_AUTHOR("Jaswinder Singh Rajput"); +MODULE_DESCRIPTION("CPU Debug module"); +MODULE_LICENSE("GPL"); -- cgit v1.2.3-70-g09d2 From bb7f5f6c26d0a304fb3af92591a1dddd39b6ac61 Mon Sep 17 00:00:00 2001 From: Cyrill Gorcunov Date: Mon, 9 Mar 2009 20:19:51 +0300 Subject: x86: shrink __ALIGN and __ALIGN_STR definitions Impact: cleanup 1) .p2align 4 and .align 16 are the same meaning (until a.out format for i386 is used which is not our case for CONFIG_X86_ALIGNMENT_16 anyway) 2) having 15 as max allowed bytes to be skipped does not make sense on modulo 16 Signed-off-by: Cyrill Gorcunov LKML-Reference: <20090309171951.GE9945@localhost> [ small cleanup, use __stringify(), etc. ] Signed-off-by: Ingo Molnar --- arch/x86/include/asm/linkage.h | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h index a0d70b46c27..12d55e773eb 100644 --- a/arch/x86/include/asm/linkage.h +++ b/arch/x86/include/asm/linkage.h @@ -1,6 +1,8 @@ #ifndef _ASM_X86_LINKAGE_H #define _ASM_X86_LINKAGE_H +#include + #undef notrace #define notrace __attribute__((no_instrument_function)) @@ -53,14 +55,9 @@ .globl name; \ name: -#ifdef CONFIG_X86_64 -#define __ALIGN .p2align 4,,15 -#define __ALIGN_STR ".p2align 4,,15" -#endif - -#ifdef CONFIG_X86_ALIGNMENT_16 -#define __ALIGN .align 16,0x90 -#define __ALIGN_STR ".align 16,0x90" +#if defined(CONFIG_X86_64) || defined(CONFIG_X86_ALIGNMENT_16) +#define __ALIGN .p2align 4, 0x90 +#define __ALIGN_STR __stringify(__ALIGN) #endif #endif /* __ASSEMBLY__ */ -- cgit v1.2.3-70-g09d2 From 8229d754383e8cd905c38b56bd7365c7fc10dfc1 Mon Sep 17 00:00:00 2001 From: Jaswinder Singh Rajput Date: Wed, 11 Mar 2009 19:13:49 +0530 Subject: x86: cpu architecture debug code, build fix, cleanup move store_ldt outside the CONFIG_PARAVIRT section and also clean up the code a bit. Signed-off-by: Jaswinder Singh Rajput Signed-off-by: Ingo Molnar --- arch/x86/include/asm/desc.h | 3 ++- arch/x86/kernel/cpu/cpu_debug.c | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index dc27705f544..5623c50d67b 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -91,7 +91,6 @@ static inline int desc_empty(const void *ptr) #define store_gdt(dtr) native_store_gdt(dtr) #define store_idt(dtr) native_store_idt(dtr) #define store_tr(tr) (tr = native_store_tr()) -#define store_ldt(ldt) asm("sldt %0":"=m" (ldt)) #define load_TLS(t, cpu) native_load_tls(t, cpu) #define set_ldt native_set_ldt @@ -112,6 +111,8 @@ static inline void paravirt_free_ldt(struct desc_struct *ldt, unsigned entries) } #endif /* CONFIG_PARAVIRT */ +#define store_ldt(ldt) asm("sldt %0" : "=m"(ldt)) + static inline void native_write_idt_entry(gate_desc *idt, int entry, const gate_desc *gate) { diff --git a/arch/x86/kernel/cpu/cpu_debug.c b/arch/x86/kernel/cpu/cpu_debug.c index 0bdf4daba20..9abbcbd933c 100755 --- a/arch/x86/kernel/cpu/cpu_debug.c +++ b/arch/x86/kernel/cpu/cpu_debug.c @@ -23,6 +23,7 @@ #include #include +#include #include #include #include @@ -427,7 +428,7 @@ static void print_tss(void *arg) seq_printf(seq, " CS\t: %04x\n", seg); asm("movl %%ds,%0" : "=r" (seg)); seq_printf(seq, " DS\t: %04x\n", seg); - seq_printf(seq, " SS\t: %04lx\n", regs->ss); + seq_printf(seq, " SS\t: %04lx\n", regs->ss & 0xffff); asm("movl %%es,%0" : "=r" (seg)); seq_printf(seq, " ES\t: %04x\n", seg); asm("movl %%fs,%0" : "=r" (seg)); -- cgit v1.2.3-70-g09d2 From bb6d59ca927d855ffac567b35c0a790c67016103 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Wed, 11 Mar 2009 23:33:18 +0900 Subject: x86: unify kmap_atomic_pfn() and iomap_atomic_prot_pfn() kmap_atomic_pfn() and iomap_atomic_prot_pfn() are almost same except pgprot. This patch removes the code duplication for these two functions. Signed-off-by: Akinobu Mita LKML-Reference: <20090311143317.GA22244@localhost.localdomain> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/highmem.h | 1 + arch/x86/mm/highmem_32.c | 17 +++++++++++------ arch/x86/mm/iomap_32.c | 13 ++----------- 3 files changed, 14 insertions(+), 17 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/highmem.h b/arch/x86/include/asm/highmem.h index bf9276bea66..014c2b85ae4 100644 --- a/arch/x86/include/asm/highmem.h +++ b/arch/x86/include/asm/highmem.h @@ -63,6 +63,7 @@ void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot); void *kmap_atomic(struct page *page, enum km_type type); void kunmap_atomic(void *kvaddr, enum km_type type); void *kmap_atomic_pfn(unsigned long pfn, enum km_type type); +void *kmap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot); struct page *kmap_atomic_to_page(void *ptr); #ifndef CONFIG_PARAVIRT diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c index d11745334a6..ae4c8dae266 100644 --- a/arch/x86/mm/highmem_32.c +++ b/arch/x86/mm/highmem_32.c @@ -121,23 +121,28 @@ void kunmap_atomic(void *kvaddr, enum km_type type) pagefault_enable(); } -/* This is the same as kmap_atomic() but can map memory that doesn't - * have a struct page associated with it. - */ -void *kmap_atomic_pfn(unsigned long pfn, enum km_type type) +void *kmap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot) { enum fixed_addresses idx; unsigned long vaddr; pagefault_disable(); - idx = type + KM_TYPE_NR*smp_processor_id(); + idx = type + KM_TYPE_NR * smp_processor_id(); vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); - set_pte(kmap_pte-idx, pfn_pte(pfn, kmap_prot)); + set_pte(kmap_pte - idx, pfn_pte(pfn, prot)); arch_flush_lazy_mmu_mode(); return (void*) vaddr; } + +/* This is the same as kmap_atomic() but can map memory that doesn't + * have a struct page associated with it. + */ +void *kmap_atomic_pfn(unsigned long pfn, enum km_type type) +{ + return kmap_atomic_prot_pfn(pfn, type, kmap_prot); +} EXPORT_SYMBOL_GPL(kmap_atomic_pfn); /* temporarily in use by i915 GEM until vmap */ struct page *kmap_atomic_to_page(void *ptr) diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c index 04102d42ff4..592984e5496 100644 --- a/arch/x86/mm/iomap_32.c +++ b/arch/x86/mm/iomap_32.c @@ -18,6 +18,7 @@ #include #include +#include #include int is_io_mapping_possible(resource_size_t base, unsigned long size) @@ -36,11 +37,6 @@ EXPORT_SYMBOL_GPL(is_io_mapping_possible); void * iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot) { - enum fixed_addresses idx; - unsigned long vaddr; - - pagefault_disable(); - /* * For non-PAT systems, promote PAGE_KERNEL_WC to PAGE_KERNEL_UC_MINUS. * PAGE_KERNEL_WC maps to PWT, which translates to uncached if the @@ -50,12 +46,7 @@ iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot) if (!pat_enabled && pgprot_val(prot) == pgprot_val(PAGE_KERNEL_WC)) prot = PAGE_KERNEL_UC_MINUS; - idx = type + KM_TYPE_NR*smp_processor_id(); - vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); - set_pte(kmap_pte-idx, pfn_pte(pfn, prot)); - arch_flush_lazy_mmu_mode(); - - return (void*) vaddr; + return kmap_atomic_prot_pfn(pfn, type, prot); } EXPORT_SYMBOL_GPL(iomap_atomic_prot_pfn); -- cgit v1.2.3-70-g09d2 From 5e47c478b0b69bc9bc3ba544e4b1ca3268f98fef Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Wed, 11 Mar 2009 10:55:33 -0700 Subject: x86: remove zImage support Impact: obsolete feature removal The zImage kernel format has been functionally unused for a very long time. It is just barely possible to build a modern kernel that still fits within the zImage size limit, but it is highly unlikely that anyone ever uses it. Furthermore, although it is still supported by most bootloaders, it has been at best poorly tested (or not tested at all); some bootloaders are even known to not support zImage at all and not having even noticed. Also remove some really obsolete constants that no longer have any meaning. LKML-Reference: <49B703D4.1000008@zytor.com> Signed-off-by: H. Peter Anvin --- arch/x86/boot/Makefile | 23 ++++++++--------------- arch/x86/boot/header.S | 29 +++++++++-------------------- arch/x86/boot/pm.c | 44 -------------------------------------------- arch/x86/boot/tools/build.c | 9 +-------- arch/x86/include/asm/boot.h | 4 ---- 5 files changed, 18 insertions(+), 91 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index c70eff69a1f..57a29fecf6b 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -6,26 +6,23 @@ # for more details. # # Copyright (C) 1994 by Linus Torvalds +# Changed by many, many contributors over the years. # # ROOT_DEV specifies the default root-device when making the image. # This can be either FLOPPY, CURRENT, /dev/xxxx or empty, in which case # the default of FLOPPY is used by 'build'. -ROOT_DEV := CURRENT +ROOT_DEV := CURRENT # If you want to preset the SVGA mode, uncomment the next line and # set SVGA_MODE to whatever number you want. # Set it to -DSVGA_MODE=NORMAL_VGA if you just want the EGA/VGA mode. # The number is the same as you would ordinarily press at bootup. -SVGA_MODE := -DSVGA_MODE=NORMAL_VGA +SVGA_MODE := -DSVGA_MODE=NORMAL_VGA -# If you want the RAM disk device, define this to be the size in blocks. - -#RAMDISK := -DRAMDISK=512 - -targets := vmlinux.bin setup.bin setup.elf zImage bzImage +targets := vmlinux.bin setup.bin setup.elf bzImage subdir- := compressed setup-y += a20.o cmdline.o copy.o cpu.o cpucheck.o edd.o @@ -71,17 +68,13 @@ KBUILD_CFLAGS := $(LINUXINCLUDE) -g -Os -D_SETUP -D__KERNEL__ \ KBUILD_CFLAGS += $(call cc-option,-m32) KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ -$(obj)/zImage: asflags-y := $(SVGA_MODE) $(RAMDISK) -$(obj)/bzImage: ccflags-y := -D__BIG_KERNEL__ -$(obj)/bzImage: asflags-y := $(SVGA_MODE) $(RAMDISK) -D__BIG_KERNEL__ -$(obj)/bzImage: BUILDFLAGS := -b +$(obj)/bzImage: asflags-y := $(SVGA_MODE) quiet_cmd_image = BUILD $@ -cmd_image = $(obj)/tools/build $(BUILDFLAGS) $(obj)/setup.bin \ - $(obj)/vmlinux.bin $(ROOT_DEV) > $@ +cmd_image = $(obj)/tools/build $(obj)/setup.bin $(obj)/vmlinux.bin \ + $(ROOT_DEV) > $@ -$(obj)/zImage $(obj)/bzImage: $(obj)/setup.bin \ - $(obj)/vmlinux.bin $(obj)/tools/build FORCE +$(obj)/bzImage: $(obj)/setup.bin $(obj)/vmlinux.bin $(obj)/tools/build FORCE $(call if_changed,image) @echo 'Kernel: $@ is ready' ' (#'`cat .version`')' diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index 7ccff4884a2..5d84d1c74e4 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -24,12 +24,8 @@ #include "boot.h" #include "offsets.h" -SETUPSECTS = 4 /* default nr of setup-sectors */ BOOTSEG = 0x07C0 /* original address of boot-sector */ -SYSSEG = DEF_SYSSEG /* system loaded at 0x10000 (65536) */ -SYSSIZE = DEF_SYSSIZE /* system size: # of 16-byte clicks */ - /* to be loaded */ -ROOT_DEV = 0 /* ROOT_DEV is now written by "build" */ +SYSSEG = 0x1000 /* historical load address >> 4 */ #ifndef SVGA_MODE #define SVGA_MODE ASK_VGA @@ -97,12 +93,12 @@ bugger_off_msg: .section ".header", "a" .globl hdr hdr: -setup_sects: .byte SETUPSECTS +setup_sects: .byte 0 /* Filled in by build.c */ root_flags: .word ROOT_RDONLY -syssize: .long SYSSIZE -ram_size: .word RAMDISK +syssize: .long 0 /* Filled in by build.c */ +ram_size: .word 0 /* Obsolete */ vid_mode: .word SVGA_MODE -root_dev: .word ROOT_DEV +root_dev: .word 0 /* Filled in by build.c */ boot_flag: .word 0xAA55 # offset 512, entry point @@ -123,14 +119,15 @@ _start: # or else old loadlin-1.5 will fail) .globl realmode_swtch realmode_swtch: .word 0, 0 # default_switch, SETUPSEG -start_sys_seg: .word SYSSEG +start_sys_seg: .word SYSSEG # obsolete and meaningless, but just + # in case something decided to "use" it .word kernel_version-512 # pointing to kernel version string # above section of header is compatible # with loadlin-1.5 (header v1.5). Don't # change it. -type_of_loader: .byte 0 # = 0, old one (LILO, Loadlin, - # Bootlin, SYSLX, bootsect...) +type_of_loader: .byte 0 # 0 means ancient bootloader, newer + # bootloaders know to change this. # See Documentation/i386/boot.txt for # assigned ids @@ -142,11 +139,7 @@ CAN_USE_HEAP = 0x80 # If set, the loader also has set # space behind setup.S can be used for # heap purposes. # Only the loader knows what is free -#ifndef __BIG_KERNEL__ - .byte 0 -#else .byte LOADED_HIGH -#endif setup_move_size: .word 0x8000 # size to move, when setup is not # loaded at 0x90000. We will move setup @@ -157,11 +150,7 @@ setup_move_size: .word 0x8000 # size to move, when setup is not code32_start: # here loaders can put a different # start address for 32-bit code. -#ifndef __BIG_KERNEL__ - .long 0x1000 # 0x1000 = default for zImage -#else .long 0x100000 # 0x100000 = default for big kernel -#endif ramdisk_image: .long 0 # address of loaded ramdisk image # Here the loader puts the 32-bit diff --git a/arch/x86/boot/pm.c b/arch/x86/boot/pm.c index 85a1cd8a8ff..8062f891525 100644 --- a/arch/x86/boot/pm.c +++ b/arch/x86/boot/pm.c @@ -32,47 +32,6 @@ static void realmode_switch_hook(void) } } -/* - * A zImage kernel is loaded at 0x10000 but wants to run at 0x1000. - * A bzImage kernel is loaded and runs at 0x100000. - */ -static void move_kernel_around(void) -{ - /* Note: rely on the compile-time option here rather than - the LOADED_HIGH flag. The Qemu kernel loader unconditionally - sets the loadflags to zero. */ -#ifndef __BIG_KERNEL__ - u16 dst_seg, src_seg; - u32 syssize; - - dst_seg = 0x1000 >> 4; - src_seg = 0x10000 >> 4; - syssize = boot_params.hdr.syssize; /* Size in 16-byte paragraphs */ - - while (syssize) { - int paras = (syssize >= 0x1000) ? 0x1000 : syssize; - int dwords = paras << 2; - - asm volatile("pushw %%es ; " - "pushw %%ds ; " - "movw %1,%%es ; " - "movw %2,%%ds ; " - "xorw %%di,%%di ; " - "xorw %%si,%%si ; " - "rep;movsl ; " - "popw %%ds ; " - "popw %%es" - : "+c" (dwords) - : "r" (dst_seg), "r" (src_seg) - : "esi", "edi"); - - syssize -= paras; - dst_seg += paras; - src_seg += paras; - } -#endif -} - /* * Disable all interrupts at the legacy PIC. */ @@ -147,9 +106,6 @@ void go_to_protected_mode(void) /* Hook before leaving real mode, also disables interrupts */ realmode_switch_hook(); - /* Move the kernel/setup to their final resting places */ - move_kernel_around(); - /* Enable the A20 gate */ if (enable_a20()) { puts("A20 gate not responding, unable to boot...\n"); diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index 44dc1923c0e..ee3a4ea923a 100644 --- a/arch/x86/boot/tools/build.c +++ b/arch/x86/boot/tools/build.c @@ -130,7 +130,7 @@ static void die(const char * str, ...) static void usage(void) { - die("Usage: build [-b] setup system [rootdev] [> image]"); + die("Usage: build setup system [rootdev] [> image]"); } int main(int argc, char ** argv) @@ -145,11 +145,6 @@ int main(int argc, char ** argv) void *kernel; u32 crc = 0xffffffffUL; - if (argc > 2 && !strcmp(argv[1], "-b")) - { - is_big_kernel = 1; - argc--, argv++; - } if ((argc < 3) || (argc > 4)) usage(); if (argc > 3) { @@ -216,8 +211,6 @@ int main(int argc, char ** argv) die("Unable to mmap '%s': %m", argv[2]); /* Number of 16-byte paragraphs, including space for a 4-byte CRC */ sys_size = (sz + 15 + 4) / 16; - if (!is_big_kernel && sys_size > DEF_SYSSIZE) - die("System is too big. Try using bzImage or modules."); /* Patch the setup code with the appropriate size parameters */ buf[0x1f1] = setup_sectors-1; diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h index 6526cf08b0e..6ba23dd9fc9 100644 --- a/arch/x86/include/asm/boot.h +++ b/arch/x86/include/asm/boot.h @@ -1,10 +1,6 @@ #ifndef _ASM_X86_BOOT_H #define _ASM_X86_BOOT_H -/* Don't touch these, unless you really know what you're doing. */ -#define DEF_SYSSEG 0x1000 -#define DEF_SYSSIZE 0x7F00 - /* Internal svga startup constants */ #define NORMAL_VGA 0xffff /* 80x25 mode */ #define EXTENDED_VGA 0xfffe /* 80x50 mode */ -- cgit v1.2.3-70-g09d2 From 6a5c05f002c3e4f24887a5fe8e7df757d339d368 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Thu, 12 Mar 2009 11:54:54 +0000 Subject: x86: fix HYPERVISOR_update_descriptor() Impact: fix potential oops during app-initiated LDT manipulation The underlying hypercall has differing argument requirements on 32- and 64-bit. Signed-off-by: Jan Beulich Acked-by: Jeremy Fitzhardinge LKML-Reference: <49B9061E.76E4.0078.0@novell.com> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/xen/hypercall.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 5e79ca69432..9c371e4a9fa 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -296,6 +296,8 @@ HYPERVISOR_get_debugreg(int reg) static inline int HYPERVISOR_update_descriptor(u64 ma, u64 desc) { + if (sizeof(u64) == sizeof(long)) + return _hypercall2(int, update_descriptor, ma, desc); return _hypercall4(int, update_descriptor, ma, ma>>32, desc, desc>>32); } -- cgit v1.2.3-70-g09d2 From 13c6c53282d99c82e79b02477efd2c1e30a991ef Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Thu, 12 Mar 2009 12:37:34 +0000 Subject: x86, 32-bit: also use cpuinfo_x86's x86_{phys,virt}_bits members Impact: 32/64-bit consolidation In a first step, this allows fixing phys_addr_valid() for PAE (which until now reported all addresses to be valid). Subsequently, this will also allow simplifying some MTRR handling code. Signed-off-by: Jan Beulich LKML-Reference: <49B9101E.76E4.0078.0@novell.com> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/processor.h | 2 +- arch/x86/kernel/cpu/common.c | 12 +++++++++++- arch/x86/kernel/cpu/intel.c | 5 +++++ arch/x86/mm/ioremap.c | 17 ++++++++--------- 4 files changed, 25 insertions(+), 11 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 76139506c3e..bd3406db1d6 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -75,9 +75,9 @@ struct cpuinfo_x86 { #else /* Number of 4K pages in DTLB/ITLB combined(in pages): */ int x86_tlbsize; +#endif __u8 x86_virt_bits; __u8 x86_phys_bits; -#endif /* CPUID returned core id bits: */ __u8 x86_coreid_bits; /* Max extended CPUID function supported: */ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 826d5c87627..a95e9480bb9 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -549,13 +549,15 @@ static void __cpuinit get_cpu_cap(struct cpuinfo_x86 *c) } } -#ifdef CONFIG_X86_64 if (c->extended_cpuid_level >= 0x80000008) { u32 eax = cpuid_eax(0x80000008); c->x86_virt_bits = (eax >> 8) & 0xff; c->x86_phys_bits = eax & 0xff; } +#ifdef CONFIG_X86_32 + else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36)) + c->x86_phys_bits = 36; #endif if (c->extended_cpuid_level >= 0x80000007) @@ -602,8 +604,12 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) { #ifdef CONFIG_X86_64 c->x86_clflush_size = 64; + c->x86_phys_bits = 36; + c->x86_virt_bits = 48; #else c->x86_clflush_size = 32; + c->x86_phys_bits = 32; + c->x86_virt_bits = 32; #endif c->x86_cache_alignment = c->x86_clflush_size; @@ -726,9 +732,13 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c) c->x86_coreid_bits = 0; #ifdef CONFIG_X86_64 c->x86_clflush_size = 64; + c->x86_phys_bits = 36; + c->x86_virt_bits = 48; #else c->cpuid_level = -1; /* CPUID not detected */ c->x86_clflush_size = 32; + c->x86_phys_bits = 32; + c->x86_virt_bits = 32; #endif c->x86_cache_alignment = c->x86_clflush_size; memset(&c->x86_capability, 0, sizeof c->x86_capability); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 191117f1ad5..ae769471042 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -54,6 +54,11 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c) c->x86_cache_alignment = 128; #endif + /* CPUID workaround for 0F33/0F34 CPU */ + if (c->x86 == 0xF && c->x86_model == 0x3 + && (c->x86_mask == 0x3 || c->x86_mask == 0x4)) + c->x86_phys_bits = 36; + /* * c->x86_power is 8000_0007 edx. Bit 8 is TSC runs at constant rate * with P/T states and does not stop in deep C-states diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index aca924a30ee..83ed74affba 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -22,13 +22,17 @@ #include #include -#ifdef CONFIG_X86_64 - -static inline int phys_addr_valid(unsigned long addr) +static inline int phys_addr_valid(resource_size_t addr) { - return addr < (1UL << boot_cpu_data.x86_phys_bits); +#ifdef CONFIG_PHYS_ADDR_T_64BIT + return !(addr >> boot_cpu_data.x86_phys_bits); +#else + return 1; +#endif } +#ifdef CONFIG_X86_64 + unsigned long __phys_addr(unsigned long x) { if (x >= __START_KERNEL_map) { @@ -65,11 +69,6 @@ EXPORT_SYMBOL(__virt_addr_valid); #else -static inline int phys_addr_valid(unsigned long addr) -{ - return 1; -} - #ifdef CONFIG_DEBUG_VIRTUAL unsigned long __phys_addr(unsigned long x) { -- cgit v1.2.3-70-g09d2 From 91219bcbdcccc1686b0ecce09e28825c93619c07 Mon Sep 17 00:00:00 2001 From: Jaswinder Singh Rajput Date: Thu, 12 Mar 2009 02:37:00 +0530 Subject: x86: cpu_debug add write support for MSRs Supported write flag for registers. currently write is enabled only for PMC MSR. [root@ht]# cat /sys/kernel/debug/x86/cpu/cpu1/pmc/0x300/value 0x0 [root@ht]# echo 1234 > /sys/kernel/debug/x86/cpu/cpu1/pmc/0x300/value [root@ht]# cat /sys/kernel/debug/x86/cpu/cpu1/pmc/0x300/value 0x4d2 [root@ht]# echo 0x1234 > /sys/kernel/debug/x86/cpu/cpu1/pmc/0x300/value [root@ht]# cat /sys/kernel/debug/x86/cpu/cpu1/pmc/0x300/value 0x1234 Signed-off-by: Jaswinder Singh Rajput Signed-off-by: Ingo Molnar --- arch/x86/include/asm/cpu_debug.h | 16 ++++-- arch/x86/kernel/cpu/cpu_debug.c | 118 ++++++++++++++++++++++++++++----------- 2 files changed, 97 insertions(+), 37 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/cpu_debug.h b/arch/x86/include/asm/cpu_debug.h index d24d64fcee0..56f1635e461 100755 --- a/arch/x86/include/asm/cpu_debug.h +++ b/arch/x86/include/asm/cpu_debug.h @@ -171,16 +171,22 @@ struct cpu_private { struct cpu_debug_base { char *name; /* Register name */ unsigned flag; /* Register flag */ + unsigned write; /* Register write flag */ }; -struct cpu_cpuX_base { - struct dentry *dentry; /* Register dentry */ - int init; /* Register index file */ -}; - +/* + * Currently it looks similar to cpu_debug_base but once we add more files + * cpu_file_base will go in different direction + */ struct cpu_file_base { char *name; /* Register file name */ unsigned flag; /* Register file flag */ + unsigned write; /* Register write flag */ +}; + +struct cpu_cpuX_base { + struct dentry *dentry; /* Register dentry */ + int init; /* Register index file */ }; struct cpu_debug_range { diff --git a/arch/x86/kernel/cpu/cpu_debug.c b/arch/x86/kernel/cpu/cpu_debug.c index 9abbcbd933c..21c0cf8ced1 100755 --- a/arch/x86/kernel/cpu/cpu_debug.c +++ b/arch/x86/kernel/cpu/cpu_debug.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -40,41 +41,41 @@ static DEFINE_MUTEX(cpu_debug_lock); static struct dentry *cpu_debugfs_dir; static struct cpu_debug_base cpu_base[] = { - { "mc", CPU_MC }, /* Machine Check */ - { "monitor", CPU_MONITOR }, /* Monitor */ - { "time", CPU_TIME }, /* Time */ - { "pmc", CPU_PMC }, /* Performance Monitor */ - { "platform", CPU_PLATFORM }, /* Platform */ - { "apic", CPU_APIC }, /* APIC */ - { "poweron", CPU_POWERON }, /* Power-on */ - { "control", CPU_CONTROL }, /* Control */ - { "features", CPU_FEATURES }, /* Features control */ - { "lastbranch", CPU_LBRANCH }, /* Last Branch */ - { "bios", CPU_BIOS }, /* BIOS */ - { "freq", CPU_FREQ }, /* Frequency */ - { "mtrr", CPU_MTRR }, /* MTRR */ - { "perf", CPU_PERF }, /* Performance */ - { "cache", CPU_CACHE }, /* Cache */ - { "sysenter", CPU_SYSENTER }, /* Sysenter */ - { "therm", CPU_THERM }, /* Thermal */ - { "misc", CPU_MISC }, /* Miscellaneous */ - { "debug", CPU_DEBUG }, /* Debug */ - { "pat", CPU_PAT }, /* PAT */ - { "vmx", CPU_VMX }, /* VMX */ - { "call", CPU_CALL }, /* System Call */ - { "base", CPU_BASE }, /* BASE Address */ - { "smm", CPU_SMM }, /* System mgmt mode */ - { "svm", CPU_SVM }, /*Secure Virtial Machine*/ - { "osvm", CPU_OSVM }, /* OS-Visible Workaround*/ - { "tss", CPU_TSS }, /* Task Stack Segment */ - { "cr", CPU_CR }, /* Control Registers */ - { "dt", CPU_DT }, /* Descriptor Table */ - { "registers", CPU_REG_ALL }, /* Select all Registers */ + { "mc", CPU_MC, 0 }, + { "monitor", CPU_MONITOR, 0 }, + { "time", CPU_TIME, 0 }, + { "pmc", CPU_PMC, 1 }, + { "platform", CPU_PLATFORM, 0 }, + { "apic", CPU_APIC, 0 }, + { "poweron", CPU_POWERON, 0 }, + { "control", CPU_CONTROL, 0 }, + { "features", CPU_FEATURES, 0 }, + { "lastbranch", CPU_LBRANCH, 0 }, + { "bios", CPU_BIOS, 0 }, + { "freq", CPU_FREQ, 0 }, + { "mtrr", CPU_MTRR, 0 }, + { "perf", CPU_PERF, 0 }, + { "cache", CPU_CACHE, 0 }, + { "sysenter", CPU_SYSENTER, 0 }, + { "therm", CPU_THERM, 0 }, + { "misc", CPU_MISC, 0 }, + { "debug", CPU_DEBUG, 0 }, + { "pat", CPU_PAT, 0 }, + { "vmx", CPU_VMX, 0 }, + { "call", CPU_CALL, 0 }, + { "base", CPU_BASE, 0 }, + { "smm", CPU_SMM, 0 }, + { "svm", CPU_SVM, 0 }, + { "osvm", CPU_OSVM, 0 }, + { "tss", CPU_TSS, 0 }, + { "cr", CPU_CR, 0 }, + { "dt", CPU_DT, 0 }, + { "registers", CPU_REG_ALL, 0 }, }; static struct cpu_file_base cpu_file[] = { - { "index", CPU_REG_ALL }, /* index */ - { "value", CPU_REG_ALL }, /* value */ + { "index", CPU_REG_ALL, 0 }, + { "value", CPU_REG_ALL, 1 }, }; /* Intel Registers Range */ @@ -608,9 +609,62 @@ static int cpu_seq_open(struct inode *inode, struct file *file) return err; } +static int write_msr(struct cpu_private *priv, u64 val) +{ + u32 low, high; + + high = (val >> 32) & 0xffffffff; + low = val & 0xffffffff; + + if (!wrmsr_safe_on_cpu(priv->cpu, priv->reg, low, high)) + return 0; + + return -EPERM; +} + +static int write_cpu_register(struct cpu_private *priv, const char *buf) +{ + int ret = -EPERM; + u64 val; + + ret = strict_strtoull(buf, 0, &val); + if (ret < 0) + return ret; + + /* Supporting only MSRs */ + if (priv->type < CPU_TSS_BIT) + return write_msr(priv, val); + + return ret; +} + +static ssize_t cpu_write(struct file *file, const char __user *ubuf, + size_t count, loff_t *off) +{ + struct seq_file *seq = file->private_data; + struct cpu_private *priv = seq->private; + char buf[19]; + + if ((priv == NULL) || (count >= sizeof(buf))) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, count)) + return -EFAULT; + + buf[count] = 0; + + if ((cpu_base[priv->type].write) && (cpu_file[priv->file].write)) + if (!write_cpu_register(priv, buf)) + return count; + + return -EACCES; +} + static const struct file_operations cpu_fops = { + .owner = THIS_MODULE, .open = cpu_seq_open, .read = seq_read, + .write = cpu_write, .llseek = seq_lseek, .release = seq_release, }; -- cgit v1.2.3-70-g09d2 From 1b3fa2ce64363c289b3b14723cca7290bf91cfce Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sat, 7 Mar 2009 05:53:00 +0100 Subject: tracing/x86: basic implementation of syscall tracing for x86 Provide the x86 trace callbacks to trace syscalls. Signed-off-by: Frederic Weisbecker Acked-by: Steven Rostedt Cc: Lai Jiangshan LKML-Reference: <1236401580-5758-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar --- arch/x86/Kconfig | 1 + arch/x86/include/asm/thread_info.h | 9 ++++++--- arch/x86/kernel/ptrace.c | 7 +++++++ 3 files changed, 14 insertions(+), 3 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index bdcee12c25a..b0a638b4199 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -35,6 +35,7 @@ config X86 select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACE_MCOUNT_TEST select HAVE_FTRACE_NMI_ENTER if DYNAMIC_FTRACE + select HAVE_FTRACE_SYSCALLS select HAVE_KVM select HAVE_ARCH_KGDB select HAVE_ARCH_TRACEHOOK diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index df9d5f78385..8820a73ae09 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -94,6 +94,7 @@ struct thread_info { #define TIF_FORCED_TF 24 /* true if TF in eflags artificially */ #define TIF_DEBUGCTLMSR 25 /* uses thread_struct.debugctlmsr */ #define TIF_DS_AREA_MSR 26 /* uses thread_struct.ds_area_msr */ +#define TIF_SYSCALL_FTRACE 27 /* for ftrace syscall instrumentation */ #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) @@ -115,15 +116,17 @@ struct thread_info { #define _TIF_FORCED_TF (1 << TIF_FORCED_TF) #define _TIF_DEBUGCTLMSR (1 << TIF_DEBUGCTLMSR) #define _TIF_DS_AREA_MSR (1 << TIF_DS_AREA_MSR) +#define _TIF_SYSCALL_FTRACE (1 << TIF_SYSCALL_FTRACE) /* work to do in syscall_trace_enter() */ #define _TIF_WORK_SYSCALL_ENTRY \ - (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | \ + (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | _TIF_SYSCALL_FTRACE | \ _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | _TIF_SINGLESTEP) /* work to do in syscall_trace_leave() */ #define _TIF_WORK_SYSCALL_EXIT \ - (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP) + (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP | \ + _TIF_SYSCALL_FTRACE) /* work to do on interrupt/exception return */ #define _TIF_WORK_MASK \ @@ -132,7 +135,7 @@ struct thread_info { _TIF_SINGLESTEP|_TIF_SECCOMP|_TIF_SYSCALL_EMU)) /* work to do on any return to user space */ -#define _TIF_ALLWORK_MASK (0x0000FFFF & ~_TIF_SECCOMP) +#define _TIF_ALLWORK_MASK ((0x0000FFFF & ~_TIF_SECCOMP) | _TIF_SYSCALL_FTRACE) /* Only used for 64 bit */ #define _TIF_DO_NOTIFY_MASK \ diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 3d9672e59c1..99749d6e87a 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include @@ -1416,6 +1417,9 @@ asmregparm long syscall_trace_enter(struct pt_regs *regs) tracehook_report_syscall_entry(regs)) ret = -1L; + if (unlikely(test_thread_flag(TIF_SYSCALL_FTRACE))) + ftrace_syscall_enter(regs); + if (unlikely(current->audit_context)) { if (IS_IA32) audit_syscall_entry(AUDIT_ARCH_I386, @@ -1439,6 +1443,9 @@ asmregparm void syscall_trace_leave(struct pt_regs *regs) if (unlikely(current->audit_context)) audit_syscall_exit(AUDITSC_RESULT(regs->ax), regs->ax); + if (unlikely(test_thread_flag(TIF_SYSCALL_FTRACE))) + ftrace_syscall_exit(regs); + if (test_thread_flag(TIF_SYSCALL_TRACE)) tracehook_report_syscall_exit(regs, 0); -- cgit v1.2.3-70-g09d2 From f58ba100678f421bdcb000a3c71793f432dfab93 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 13 Mar 2009 15:42:12 +0100 Subject: tracing/syscalls: support for syscalls tracing on x86 Extend x86 architecture syscall tracing support with syscall metadata table details. (The upcoming core syscall tracing modifications rely on this.) Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt LKML-Reference: <1236955332-10133-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/ftrace.h | 7 +++++ arch/x86/kernel/ftrace.c | 63 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 70 insertions(+) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index db24c2278be..bd2c6511c88 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -28,6 +28,13 @@ #endif +/* FIXME: I don't want to stay hardcoded */ +#ifdef CONFIG_X86_64 +# define FTRACE_SYSCALL_MAX 296 +#else +# define FTRACE_SYSCALL_MAX 333 +#endif + #ifdef CONFIG_FUNCTION_TRACER #define MCOUNT_ADDR ((long)(mcount)) #define MCOUNT_INSN_SIZE 5 /* sizeof mcount call */ diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index a85da1764b1..1d0d7f42efe 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -453,3 +453,66 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) } } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + +#ifdef CONFIG_FTRACE_SYSCALLS + +extern unsigned long __start_syscalls_metadata[]; +extern unsigned long __stop_syscalls_metadata[]; +extern unsigned long *sys_call_table; + +static struct syscall_metadata **syscalls_metadata; + +static struct syscall_metadata *find_syscall_meta(unsigned long *syscall) +{ + struct syscall_metadata *start; + struct syscall_metadata *stop; + char str[KSYM_SYMBOL_LEN]; + + + start = (struct syscall_metadata *)__start_syscalls_metadata; + stop = (struct syscall_metadata *)__stop_syscalls_metadata; + kallsyms_lookup((unsigned long) syscall, NULL, NULL, NULL, str); + + for ( ; start < stop; start++) { + if (start->name && !strcmp(start->name, str)) + return start; + } + return NULL; +} + +struct syscall_metadata *syscall_nr_to_meta(int nr) +{ + if (!syscalls_metadata || nr >= FTRACE_SYSCALL_MAX || nr < 0) + return NULL; + + return syscalls_metadata[nr]; +} + +void arch_init_ftrace_syscalls(void) +{ + int i; + struct syscall_metadata *meta; + unsigned long **psys_syscall_table = &sys_call_table; + static atomic_t refs; + + if (atomic_inc_return(&refs) != 1) + goto end; + + syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) * + FTRACE_SYSCALL_MAX, GFP_KERNEL); + if (!syscalls_metadata) { + WARN_ON(1); + return; + } + + for (i = 0; i < FTRACE_SYSCALL_MAX; i++) { + meta = find_syscall_meta(psys_syscall_table[i]); + syscalls_metadata[i] = meta; + } + return; + + /* Paranoid: avoid overflow */ +end: + atomic_dec(&refs); +} +#endif -- cgit v1.2.3-70-g09d2 From 9766cdbcb260389669e9679b2aa87c11832f479f Mon Sep 17 00:00:00 2001 From: Jaswinder Singh Rajput Date: Sat, 14 Mar 2009 11:19:49 +0530 Subject: x86: cpu/common.c cleanups - fix various style problems - declare varibles before they get used - introduced clear_all_debug_regs - fix header files issues LKML-Reference: <1237009789.4387.2.camel@localhost.localdomain> Signed-off-by: Jaswinder Singh Rajput Signed-off-by: Ingo Molnar --- arch/x86/include/asm/processor.h | 3 + arch/x86/kernel/cpu/common.c | 129 ++++++++++++++++++++------------------- 2 files changed, 68 insertions(+), 64 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 76139506c3e..dccef5be0fc 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -391,6 +391,9 @@ DECLARE_PER_CPU(union irq_stack_union, irq_stack_union); DECLARE_INIT_PER_CPU(irq_stack_union); DECLARE_PER_CPU(char *, irq_stack_ptr); +DECLARE_PER_CPU(unsigned int, irq_count); +extern unsigned long kernel_eflags; +extern asmlinkage void ignore_sysret(void); #else /* X86_64 */ #ifdef CONFIG_CC_STACKPROTECTOR DECLARE_PER_CPU(unsigned long, stack_canary); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 826d5c87627..cad6878c88d 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1,52 +1,52 @@ -#include -#include -#include -#include +#include #include +#include #include +#include #include -#include -#include +#include +#include #include +#include +#include +#include #include -#include -#include -#include -#include -#include +#include + +#include #include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include #include +#include +#include +#include #include +#include #include -#include -#include #include -#include -#include -#include #ifdef CONFIG_X86_LOCAL_APIC #include #endif -#include -#include -#include -#include -#include -#include -#include -#include -#include - #include "cpu.h" #ifdef CONFIG_X86_64 /* all of these masks are initialized in setup_cpu_local_masks() */ -cpumask_var_t cpu_callin_mask; -cpumask_var_t cpu_callout_mask; cpumask_var_t cpu_initialized_mask; +cpumask_var_t cpu_callout_mask; +cpumask_var_t cpu_callin_mask; /* representing cpus for which sibling maps can be computed */ cpumask_var_t cpu_sibling_setup_mask; @@ -62,10 +62,10 @@ void __init setup_cpu_local_masks(void) #else /* CONFIG_X86_32 */ -cpumask_t cpu_callin_map; +cpumask_t cpu_sibling_setup_map; cpumask_t cpu_callout_map; cpumask_t cpu_initialized; -cpumask_t cpu_sibling_setup_map; +cpumask_t cpu_callin_map; #endif /* CONFIG_X86_32 */ @@ -79,7 +79,7 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = { * IRET will check the segment types kkeil 2000/10/28 * Also sysret mandates a special GDT layout * - * The TLS descriptors are currently at a different place compared to i386. + * TLS descriptors are currently at a different place compared to i386. * Hopefully nobody expects them at a fixed place (Wine?) */ [GDT_ENTRY_KERNEL32_CS] = { { { 0x0000ffff, 0x00cf9b00 } } }, @@ -243,6 +243,7 @@ cpuid_dependent_features[] = { static void __cpuinit filter_cpuid_features(struct cpuinfo_x86 *c, bool warn) { const struct cpuid_dependent_feature *df; + for (df = cpuid_dependent_features; df->feature; df++) { /* * Note: cpuid_level is set to -1 if unavailable, but @@ -364,12 +365,12 @@ static void __cpuinit get_model_name(struct cpuinfo_x86 *c) undo that brain damage */ p = q = &c->x86_model_id[0]; while (*p == ' ') - p++; + p++; if (p != q) { - while (*p) - *q++ = *p++; - while (q <= &c->x86_model_id[48]) - *q++ = '\0'; /* Zero-pad the rest */ + while (*p) + *q++ = *p++; + while (q <= &c->x86_model_id[48]) + *q++ = '\0'; /* Zero-pad the rest */ } } @@ -441,14 +442,15 @@ void __cpuinit detect_ht(struct cpuinfo_x86 *c) } else if (smp_num_siblings > 1) { if (smp_num_siblings > nr_cpu_ids) { - printk(KERN_WARNING "CPU: Unsupported number of siblings %d", - smp_num_siblings); + pr_warning("CPU: Unsupported number of siblings %d", + smp_num_siblings); smp_num_siblings = 1; return; } index_msb = get_count_order(smp_num_siblings); - c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, index_msb); + c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, + index_msb); smp_num_siblings = smp_num_siblings / c->x86_max_cores; @@ -491,7 +493,8 @@ static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c) if (!printed) { printed++; - printk(KERN_ERR "CPU: vendor_id '%s' unknown, using generic init.\n", v); + printk(KERN_ERR "CPU: vendor_id '%s'" + "unknown, using generic init.\n", v); printk(KERN_ERR "CPU: Your system may be unstable.\n"); } @@ -637,7 +640,7 @@ void __init early_cpu_init(void) struct cpu_dev **cdev; int count = 0; - printk("KERNEL supported cpus:\n"); + printk(KERN_INFO "KERNEL supported cpus:\n"); for (cdev = __x86_cpu_dev_start; cdev < __x86_cpu_dev_end; cdev++) { struct cpu_dev *cpudev = *cdev; unsigned int j; @@ -650,7 +653,7 @@ void __init early_cpu_init(void) for (j = 0; j < 2; j++) { if (!cpudev->c_ident[j]) continue; - printk(" %s %s\n", cpudev->c_vendor, + printk(KERN_INFO " %s %s\n", cpudev->c_vendor, cpudev->c_ident[j]); } } @@ -952,8 +955,6 @@ static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks [(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]) __aligned(PAGE_SIZE); -extern asmlinkage void ignore_sysret(void); - /* May not be marked __init: used by software suspend */ void syscall_init(void) { @@ -999,6 +1000,22 @@ struct pt_regs * __cpuinit idle_regs(struct pt_regs *regs) } #endif /* x86_64 */ +/* + * Clear all 6 debug registers: + */ +static void clear_all_debug_regs(void) +{ + int i; + + for (i = 0; i < 8; i++) { + /* Ignore db4, db5 */ + if ((i == 4) || (i == 5)) + continue; + + set_debugreg(0, i); + } +} + /* * cpu_init() initializes state that is per-CPU. Some data is already * initialized (naturally) in the bootstrap process, such as the GDT @@ -1098,17 +1115,7 @@ void __cpuinit cpu_init(void) arch_kgdb_ops.correct_hw_break(); else #endif - { - /* - * Clear all 6 debug registers: - */ - set_debugreg(0UL, 0); - set_debugreg(0UL, 1); - set_debugreg(0UL, 2); - set_debugreg(0UL, 3); - set_debugreg(0UL, 6); - set_debugreg(0UL, 7); - } + clear_all_debug_regs(); fpu_init(); @@ -1129,7 +1136,8 @@ void __cpuinit cpu_init(void) if (cpumask_test_and_set_cpu(cpu, cpu_initialized_mask)) { printk(KERN_WARNING "CPU#%d already initialized!\n", cpu); - for (;;) local_irq_enable(); + for (;;) + local_irq_enable(); } printk(KERN_INFO "Initializing CPU#%d\n", cpu); @@ -1159,13 +1167,7 @@ void __cpuinit cpu_init(void) __set_tss_desc(cpu, GDT_ENTRY_DOUBLEFAULT_TSS, &doublefault_tss); #endif - /* Clear all 6 debug registers: */ - set_debugreg(0, 0); - set_debugreg(0, 1); - set_debugreg(0, 2); - set_debugreg(0, 3); - set_debugreg(0, 6); - set_debugreg(0, 7); + clear_all_debug_regs(); /* * Force FPU initialization: @@ -1186,5 +1188,4 @@ void __cpuinit cpu_init(void) xsave_init(); } - #endif -- cgit v1.2.3-70-g09d2 From f4c3c4cdb1de232ff37cf4339eb2f36c84e20da6 Mon Sep 17 00:00:00 2001 From: Jaswinder Singh Rajput Date: Fri, 13 Mar 2009 19:59:26 +0530 Subject: x86: cpu_debug add support for various AMD CPUs Impact: Added AMD CPUs support Added flags for various AMD CPUs. Signed-off-by: Jaswinder Singh Rajput Signed-off-by: Ingo Molnar --- arch/x86/include/asm/cpu_debug.h | 33 ++++++++- arch/x86/kernel/cpu/cpu_debug.c | 150 +++++++++++++++++++++++++++------------ 2 files changed, 136 insertions(+), 47 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/cpu_debug.h b/arch/x86/include/asm/cpu_debug.h index 56f1635e461..222802029fa 100755 --- a/arch/x86/include/asm/cpu_debug.h +++ b/arch/x86/include/asm/cpu_debug.h @@ -33,6 +33,8 @@ enum cpu_debug_bit { CPU_VMX_BIT, /* VMX */ CPU_CALL_BIT, /* System Call */ CPU_BASE_BIT, /* BASE Address */ + CPU_VER_BIT, /* Version ID */ + CPU_CONF_BIT, /* Configuration */ CPU_SMM_BIT, /* System mgmt mode */ CPU_SVM_BIT, /*Secure Virtual Machine*/ CPU_OSVM_BIT, /* OS-Visible Workaround*/ @@ -69,6 +71,8 @@ enum cpu_debug_bit { #define CPU_VMX (1 << CPU_VMX_BIT) #define CPU_CALL (1 << CPU_CALL_BIT) #define CPU_BASE (1 << CPU_BASE_BIT) +#define CPU_VER (1 << CPU_VER_BIT) +#define CPU_CONF (1 << CPU_CONF_BIT) #define CPU_SMM (1 << CPU_SMM_BIT) #define CPU_SVM (1 << CPU_SVM_BIT) #define CPU_OSVM (1 << CPU_OSVM_BIT) @@ -123,10 +127,15 @@ enum cpu_processor_bit { CPU_INTEL_ATOM_BIT, CPU_INTEL_XEON_P4_BIT, CPU_INTEL_XEON_MP_BIT, +/* AMD */ + CPU_AMD_K6_BIT, + CPU_AMD_K7_BIT, + CPU_AMD_K8_BIT, + CPU_AMD_0F_BIT, + CPU_AMD_10_BIT, + CPU_AMD_11_BIT, }; -#define CPU_ALL (~0) /* Select all CPUs */ - #define CPU_INTEL_PENTIUM (1 << CPU_INTEL_PENTIUM_BIT) #define CPU_INTEL_P6 (1 << CPU_INTEL_P6_BIT) #define CPU_INTEL_PENTIUM_M (1 << CPU_INTEL_PENTIUM_M_BIT) @@ -156,9 +165,27 @@ enum cpu_processor_bit { #define CPU_PX_CX_AT (CPU_INTEL_PX | CPU_CX_AT) #define CPU_PX_CX_AT_XE (CPU_INTEL_PX | CPU_CX_AT_XE) -/* Select all Intel CPUs*/ +/* Select all supported Intel CPUs */ #define CPU_INTEL_ALL (CPU_INTEL_PENTIUM | CPU_PX_CX_AT_XE) +#define CPU_AMD_K6 (1 << CPU_AMD_K6_BIT) +#define CPU_AMD_K7 (1 << CPU_AMD_K7_BIT) +#define CPU_AMD_K8 (1 << CPU_AMD_K8_BIT) +#define CPU_AMD_0F (1 << CPU_AMD_0F_BIT) +#define CPU_AMD_10 (1 << CPU_AMD_10_BIT) +#define CPU_AMD_11 (1 << CPU_AMD_11_BIT) + +#define CPU_K10_PLUS (CPU_AMD_10 | CPU_AMD_11) +#define CPU_K0F_PLUS (CPU_AMD_0F | CPU_K10_PLUS) +#define CPU_K8_PLUS (CPU_AMD_K8 | CPU_K0F_PLUS) +#define CPU_K7_PLUS (CPU_AMD_K7 | CPU_K8_PLUS) + +/* Select all supported AMD CPUs */ +#define CPU_AMD_ALL (CPU_AMD_K6 | CPU_K7_PLUS) + +/* Select all supported CPUs */ +#define CPU_ALL (CPU_INTEL_ALL | CPU_AMD_ALL) + #define MAX_CPU_FILES 512 struct cpu_private { diff --git a/arch/x86/kernel/cpu/cpu_debug.c b/arch/x86/kernel/cpu/cpu_debug.c index 21c0cf8ced1..46e29ab96c6 100755 --- a/arch/x86/kernel/cpu/cpu_debug.c +++ b/arch/x86/kernel/cpu/cpu_debug.c @@ -64,6 +64,8 @@ static struct cpu_debug_base cpu_base[] = { { "vmx", CPU_VMX, 0 }, { "call", CPU_CALL, 0 }, { "base", CPU_BASE, 0 }, + { "ver", CPU_VER, 0 }, + { "conf", CPU_CONF, 0 }, { "smm", CPU_SMM, 0 }, { "svm", CPU_SVM, 0 }, { "osvm", CPU_OSVM, 0 }, @@ -177,54 +179,59 @@ static struct cpu_debug_range cpu_intel_range[] = { /* AMD Registers Range */ static struct cpu_debug_range cpu_amd_range[] = { - { 0x00000010, 0x00000010, CPU_TIME, CPU_ALL, }, - { 0x0000001B, 0x0000001B, CPU_APIC, CPU_ALL, }, - { 0x000000FE, 0x000000FE, CPU_MTRR, CPU_ALL, }, - - { 0x00000174, 0x00000176, CPU_SYSENTER, CPU_ALL, }, - { 0x00000179, 0x0000017A, CPU_MC, CPU_ALL, }, - { 0x0000017B, 0x0000017B, CPU_MC, CPU_ALL, }, - { 0x000001D9, 0x000001D9, CPU_DEBUG, CPU_ALL, }, - { 0x000001DB, 0x000001DE, CPU_LBRANCH, CPU_ALL, }, - - { 0x00000200, 0x0000020F, CPU_MTRR, CPU_ALL, }, - { 0x00000250, 0x00000250, CPU_MTRR, CPU_ALL, }, - { 0x00000258, 0x00000259, CPU_MTRR, CPU_ALL, }, - { 0x00000268, 0x0000026F, CPU_MTRR, CPU_ALL, }, - { 0x00000277, 0x00000277, CPU_PAT, CPU_ALL, }, - { 0x000002FF, 0x000002FF, CPU_MTRR, CPU_ALL, }, - - { 0x00000400, 0x00000417, CPU_MC, CPU_ALL, }, - - { 0xC0000080, 0xC0000080, CPU_FEATURES, CPU_ALL, }, - { 0xC0000081, 0xC0000084, CPU_CALL, CPU_ALL, }, - { 0xC0000100, 0xC0000102, CPU_BASE, CPU_ALL, }, - { 0xC0000103, 0xC0000103, CPU_TIME, CPU_ALL, }, - - { 0xC0000408, 0xC000040A, CPU_MC, CPU_ALL, }, - - { 0xc0010000, 0xc0010007, CPU_PMC, CPU_ALL, }, - { 0xc0010010, 0xc0010010, CPU_MTRR, CPU_ALL, }, - { 0xc0010016, 0xc001001A, CPU_MTRR, CPU_ALL, }, - { 0xc001001D, 0xc001001D, CPU_MTRR, CPU_ALL, }, - { 0xc0010030, 0xc0010035, CPU_BIOS, CPU_ALL, }, - { 0xc0010056, 0xc0010056, CPU_SMM, CPU_ALL, }, - { 0xc0010061, 0xc0010063, CPU_SMM, CPU_ALL, }, - { 0xc0010074, 0xc0010074, CPU_MC, CPU_ALL, }, - { 0xc0010111, 0xc0010113, CPU_SMM, CPU_ALL, }, - { 0xc0010114, 0xc0010118, CPU_SVM, CPU_ALL, }, - { 0xc0010119, 0xc001011A, CPU_SMM, CPU_ALL, }, - { 0xc0010140, 0xc0010141, CPU_OSVM, CPU_ALL, }, - { 0xc0010156, 0xc0010156, CPU_SMM, CPU_ALL, }, + { 0x00000000, 0x00000001, CPU_MC, CPU_K10_PLUS, }, + { 0x00000010, 0x00000010, CPU_TIME, CPU_K8_PLUS, }, + { 0x0000001B, 0x0000001B, CPU_APIC, CPU_K8_PLUS, }, + { 0x0000002A, 0x0000002A, CPU_POWERON, CPU_K7_PLUS }, + { 0x0000008B, 0x0000008B, CPU_VER, CPU_K8_PLUS }, + { 0x000000FE, 0x000000FE, CPU_MTRR, CPU_K8_PLUS, }, + + { 0x00000174, 0x00000176, CPU_SYSENTER, CPU_K8_PLUS, }, + { 0x00000179, 0x0000017B, CPU_MC, CPU_K8_PLUS, }, + { 0x000001D9, 0x000001D9, CPU_DEBUG, CPU_K8_PLUS, }, + { 0x000001DB, 0x000001DE, CPU_LBRANCH, CPU_K8_PLUS, }, + + { 0x00000200, 0x0000020F, CPU_MTRR, CPU_K8_PLUS, }, + { 0x00000250, 0x00000250, CPU_MTRR, CPU_K8_PLUS, }, + { 0x00000258, 0x00000259, CPU_MTRR, CPU_K8_PLUS, }, + { 0x00000268, 0x0000026F, CPU_MTRR, CPU_K8_PLUS, }, + { 0x00000277, 0x00000277, CPU_PAT, CPU_K8_PLUS, }, + { 0x000002FF, 0x000002FF, CPU_MTRR, CPU_K8_PLUS, }, + + { 0x00000400, 0x00000413, CPU_MC, CPU_K8_PLUS, }, + + { 0xC0000080, 0xC0000080, CPU_FEATURES, CPU_AMD_ALL, }, + { 0xC0000081, 0xC0000084, CPU_CALL, CPU_K8_PLUS, }, + { 0xC0000100, 0xC0000102, CPU_BASE, CPU_K8_PLUS, }, + { 0xC0000103, 0xC0000103, CPU_TIME, CPU_K10_PLUS, }, + + { 0xC0010000, 0xC0010007, CPU_PMC, CPU_K8_PLUS, }, + { 0xC0010010, 0xC0010010, CPU_CONF, CPU_K7_PLUS, }, + { 0xC0010015, 0xC0010015, CPU_CONF, CPU_K7_PLUS, }, + { 0xC0010016, 0xC001001A, CPU_MTRR, CPU_K8_PLUS, }, + { 0xC001001D, 0xC001001D, CPU_MTRR, CPU_K8_PLUS, }, + { 0xC001001F, 0xC001001F, CPU_CONF, CPU_K8_PLUS, }, + { 0xC0010030, 0xC0010035, CPU_BIOS, CPU_K8_PLUS, }, + { 0xC0010044, 0xC0010048, CPU_MC, CPU_K8_PLUS, }, + { 0xC0010050, 0xC0010056, CPU_SMM, CPU_K0F_PLUS, }, + { 0xC0010058, 0xC0010058, CPU_CONF, CPU_K10_PLUS, }, + { 0xC0010060, 0xC0010060, CPU_CACHE, CPU_AMD_11, }, + { 0xC0010061, 0xC0010068, CPU_SMM, CPU_K10_PLUS, }, + { 0xC0010069, 0xC001006B, CPU_SMM, CPU_AMD_11, }, + { 0xC0010070, 0xC0010071, CPU_SMM, CPU_K10_PLUS, }, + { 0xC0010111, 0xC0010113, CPU_SMM, CPU_K8_PLUS, }, + { 0xC0010114, 0xC0010118, CPU_SVM, CPU_K10_PLUS, }, + { 0xC0010140, 0xC0010141, CPU_OSVM, CPU_K10_PLUS, }, + { 0xC0011022, 0xC0011023, CPU_CONF, CPU_K10_PLUS, }, }; -static int get_cpu_modelflag(unsigned cpu) +/* Intel */ +static int get_intel_modelflag(unsigned model) { int flag; - switch (per_cpu(cpu_model, cpu)) { - /* Intel */ + switch (model) { case 0x0501: case 0x0502: case 0x0504: @@ -271,6 +278,59 @@ static int get_cpu_modelflag(unsigned cpu) return flag; } +/* AMD */ +static int get_amd_modelflag(unsigned model) +{ + int flag; + + switch (model >> 8) { + case 0x6: + flag = CPU_AMD_K6; + break; + case 0x7: + flag = CPU_AMD_K7; + break; + case 0x8: + flag = CPU_AMD_K8; + break; + case 0xf: + flag = CPU_AMD_0F; + break; + case 0x10: + flag = CPU_AMD_10; + break; + case 0x11: + flag = CPU_AMD_11; + break; + default: + flag = CPU_NONE; + break; + } + + return flag; +} + +static int get_cpu_modelflag(unsigned cpu) +{ + int flag; + + flag = per_cpu(cpu_model, cpu); + + switch (flag >> 16) { + case X86_VENDOR_INTEL: + flag = get_intel_modelflag(flag); + break; + case X86_VENDOR_AMD: + flag = get_amd_modelflag(flag & 0xffff); + break; + default: + flag = CPU_NONE; + break; + } + + return flag; +} + static int get_cpu_range_count(unsigned cpu) { int index; @@ -311,7 +371,8 @@ static int is_typeflag_valid(unsigned cpu, unsigned flag) return 1; break; case X86_VENDOR_AMD: - if (cpu_amd_range[i].flag & flag) + if ((cpu_amd_range[i].model & modelflag) && + (cpu_amd_range[i].flag & flag)) return 1; break; } @@ -337,7 +398,8 @@ static unsigned get_cpu_range(unsigned cpu, unsigned *min, unsigned *max, } break; case X86_VENDOR_AMD: - if (cpu_amd_range[index].flag & flag) { + if ((cpu_amd_range[index].model & modelflag) && + (cpu_amd_range[index].flag & flag)) { *min = cpu_amd_range[index].min; *max = cpu_amd_range[index].max; } -- cgit v1.2.3-70-g09d2 From 93dbda7cbcd70a0bd1a99f39f44a9ccde8ab9040 Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Thu, 26 Feb 2009 17:35:44 -0800 Subject: x86: add brk allocation for very, very early allocations Impact: new interface Add a brk()-like allocator which effectively extends the bss in order to allow very early code to do dynamic allocations. This is better than using statically allocated arrays for data in subsystems which may never get used. The space for brk allocations is in the bss ELF segment, so that the space is mapped properly by the code which maps the kernel, and so that bootloaders keep the space free rather than putting a ramdisk or something into it. The bss itself, delimited by __bss_stop, ends before the brk area (__brk_base to __brk_limit). The kernel text, data and bss is reserved up to __bss_stop. Any brk-allocated data is reserved separately just before the kernel pagetable is built, as that code allocates from unreserved spaces in the e820 map, potentially allocating from any unused brk memory. Ultimately any unused memory in the brk area is used in the general kernel memory pool. Initially the brk space is set to 1MB, which is probably much larger than any user needs (the largest current user is i386 head_32.S's code to build the pagetables to map the kernel, which can get fairly large with a big kernel image and no PSE support). So long as the system has sufficient memory for the bootloader to reserve the kernel+1MB brk, there are no bad effects resulting from an over-large brk. Signed-off-by: Jeremy Fitzhardinge Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/sections.h | 7 +++++++ arch/x86/include/asm/setup.h | 4 ++++ arch/x86/kernel/head32.c | 2 +- arch/x86/kernel/head64.c | 2 +- arch/x86/kernel/setup.c | 39 ++++++++++++++++++++++++++++++++++----- arch/x86/kernel/vmlinux_32.lds.S | 7 +++++++ arch/x86/kernel/vmlinux_64.lds.S | 5 +++++ arch/x86/mm/pageattr.c | 5 +++-- arch/x86/xen/mmu.c | 6 +++--- 9 files changed, 65 insertions(+), 12 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h index 2b8c5160388..1b7ee5d673c 100644 --- a/arch/x86/include/asm/sections.h +++ b/arch/x86/include/asm/sections.h @@ -1 +1,8 @@ +#ifndef _ASM_X86_SECTIONS_H +#define _ASM_X86_SECTIONS_H + #include + +extern char __brk_base[], __brk_limit[]; + +#endif /* _ASM_X86_SECTIONS_H */ diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 05c6f6b11fd..45454f3fa12 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -100,6 +100,10 @@ extern struct boot_params boot_params; */ #define LOWMEMSIZE() (0x9f000) +/* exceedingly early brk-like allocator */ +extern unsigned long _brk_end; +void *extend_brk(size_t size, size_t align); + #ifdef __i386__ void __init i386_start_kernel(void); diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index ac108d1fe18..29f1095b084 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -18,7 +18,7 @@ void __init i386_start_kernel(void) { reserve_trampoline_memory(); - reserve_early(__pa_symbol(&_text), __pa_symbol(&_end), "TEXT DATA BSS"); + reserve_early(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS"); #ifdef CONFIG_BLK_DEV_INITRD /* Reserve INITRD */ diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index f5b27224769..70eaa852c73 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -100,7 +100,7 @@ void __init x86_64_start_reservations(char *real_mode_data) reserve_trampoline_memory(); - reserve_early(__pa_symbol(&_text), __pa_symbol(&_end), "TEXT DATA BSS"); + reserve_early(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS"); #ifdef CONFIG_BLK_DEV_INITRD /* Reserve INITRD */ diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index f28c56e6bf9..e6b742d2a3f 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -114,6 +114,9 @@ unsigned int boot_cpu_id __read_mostly; +static __initdata unsigned long _brk_start = (unsigned long)__brk_base; +unsigned long _brk_end = (unsigned long)__brk_base; + #ifdef CONFIG_X86_64 int default_cpu_present_to_apicid(int mps_cpu) { @@ -337,6 +340,34 @@ static void __init relocate_initrd(void) } #endif +void * __init extend_brk(size_t size, size_t align) +{ + size_t mask = align - 1; + void *ret; + + BUG_ON(_brk_start == 0); + BUG_ON(align & mask); + + _brk_end = (_brk_end + mask) & ~mask; + BUG_ON((char *)(_brk_end + size) > __brk_limit); + + ret = (void *)_brk_end; + _brk_end += size; + + memset(ret, 0, size); + + return ret; +} + +static void __init reserve_brk(void) +{ + if (_brk_end > _brk_start) + reserve_early(__pa(_brk_start), __pa(_brk_end), "BRK"); + + /* Mark brk area as locked down and no longer taking any new allocations */ + _brk_start = 0; +} + static void __init reserve_initrd(void) { u64 ramdisk_image = boot_params.hdr.ramdisk_image; @@ -717,11 +748,7 @@ void __init setup_arch(char **cmdline_p) init_mm.start_code = (unsigned long) _text; init_mm.end_code = (unsigned long) _etext; init_mm.end_data = (unsigned long) _edata; -#ifdef CONFIG_X86_32 - init_mm.brk = init_pg_tables_end + PAGE_OFFSET; -#else - init_mm.brk = (unsigned long) &_end; -#endif + init_mm.brk = _brk_end; code_resource.start = virt_to_phys(_text); code_resource.end = virt_to_phys(_etext)-1; @@ -842,6 +869,8 @@ void __init setup_arch(char **cmdline_p) setup_bios_corruption_check(); #endif + reserve_brk(); + /* max_pfn_mapped is updated here */ max_low_pfn_mapped = init_memory_mapping(0, max_low_pfn< #include #include +#include #include #include #include @@ -95,7 +96,7 @@ static inline unsigned long highmap_start_pfn(void) static inline unsigned long highmap_end_pfn(void) { - return __pa(roundup((unsigned long)_end, PMD_SIZE)) >> PAGE_SHIFT; + return __pa(roundup(_brk_end, PMD_SIZE)) >> PAGE_SHIFT; } #endif @@ -711,7 +712,7 @@ static int cpa_process_alias(struct cpa_data *cpa) * No need to redo, when the primary call touched the high * mapping already: */ - if (within(vaddr, (unsigned long) _text, (unsigned long) _end)) + if (within(vaddr, (unsigned long) _text, _brk_end)) return 0; /* diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index cb6afa4ec95..72f6a76dbfb 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1723,9 +1723,9 @@ __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, { pmd_t *kernel_pmd; - init_pg_tables_start = __pa(pgd); - init_pg_tables_end = __pa(pgd) + xen_start_info->nr_pt_frames*PAGE_SIZE; - max_pfn_mapped = PFN_DOWN(init_pg_tables_end + 512*1024); + max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->pt_base) + + xen_start_info->nr_pt_frames * PAGE_SIZE + + 512*1024); kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd); memcpy(level2_kernel_pgt, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD); -- cgit v1.2.3-70-g09d2 From ccf3fe02e35f4abca2589f99022cc25084bbd8ae Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Fri, 27 Feb 2009 13:27:38 -0800 Subject: x86-32: use brk segment for allocating initial kernel pagetable Impact: use new interface instead of previous ad hoc implementation Rather than having special purpose init_pg_table_start/end variables to delimit the kernel pagetable built by head_32.S, just use the brk mechanism to extend the bss for the new pagetable. This patch removes init_pg_table_start/end and pg0, defines __brk_base (which is page-aligned and immediately follows _end), initializes the brk region to start there, and uses it for the 32-bit pagetable. Signed-off-by: Jeremy Fitzhardinge Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/pgtable_32.h | 3 --- arch/x86/include/asm/setup.h | 3 --- arch/x86/kernel/head32.c | 3 --- arch/x86/kernel/head_32.S | 14 +++++++------- arch/x86/kernel/setup.c | 6 ------ arch/x86/kernel/vmlinux_32.lds.S | 4 ---- arch/x86/lguest/boot.c | 8 -------- 7 files changed, 7 insertions(+), 34 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h index 97612fc7632..31bd120cf2a 100644 --- a/arch/x86/include/asm/pgtable_32.h +++ b/arch/x86/include/asm/pgtable_32.h @@ -42,9 +42,6 @@ extern void set_pmd_pfn(unsigned long, unsigned long, pgprot_t); */ #undef TEST_ACCESS_OK -/* The boot page tables (all created as a single array) */ -extern unsigned long pg0[]; - #ifdef CONFIG_X86_PAE # include #else diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 45454f3fa12..366d3663994 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -109,9 +109,6 @@ void *extend_brk(size_t size, size_t align); void __init i386_start_kernel(void); extern void probe_roms(void); -extern unsigned long init_pg_tables_start; -extern unsigned long init_pg_tables_end; - #else void __init x86_64_start_kernel(char *real_mode); void __init x86_64_start_reservations(char *real_mode_data); diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index 29f1095b084..3f8579f8d42 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -29,9 +29,6 @@ void __init i386_start_kernel(void) reserve_early(ramdisk_image, ramdisk_end, "RAMDISK"); } #endif - reserve_early(init_pg_tables_start, init_pg_tables_end, - "INIT_PG_TABLE"); - reserve_ebda_region(); /* diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index c32ca19d591..db6652710e9 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -167,7 +167,7 @@ num_subarch_entries = (. - subarch_entries) / 4 /* * Initialize page tables. This creates a PDE and a set of page * tables, which are located immediately beyond _end. The variable - * init_pg_tables_end is set up to point to the first "safe" location. + * _brk_end is set up to point to the first "safe" location. * Mappings are created both at virtual address 0 (identity mapping) * and PAGE_OFFSET for up to _end+sizeof(page tables)+INIT_MAP_BEYOND_END. * @@ -190,8 +190,7 @@ default_entry: xorl %ebx,%ebx /* %ebx is kept at zero */ - movl $pa(pg0), %edi - movl %edi, pa(init_pg_tables_start) + movl $pa(__brk_base), %edi movl $pa(swapper_pg_pmd), %edx movl $PTE_IDENT_ATTR, %eax 10: @@ -216,7 +215,8 @@ default_entry: cmpl %ebp,%eax jb 10b 1: - movl %edi,pa(init_pg_tables_end) + addl $__PAGE_OFFSET, %edi + movl %edi, pa(_brk_end) shrl $12, %eax movl %eax, pa(max_pfn_mapped) @@ -227,8 +227,7 @@ default_entry: page_pde_offset = (__PAGE_OFFSET >> 20); - movl $pa(pg0), %edi - movl %edi, pa(init_pg_tables_start) + movl $pa(__brk_base), %edi movl $pa(swapper_pg_dir), %edx movl $PTE_IDENT_ATTR, %eax 10: @@ -249,7 +248,8 @@ page_pde_offset = (__PAGE_OFFSET >> 20); leal (INIT_MAP_BEYOND_END+PTE_IDENT_ATTR)(%edi),%ebp cmpl %ebp,%eax jb 10b - movl %edi,pa(init_pg_tables_end) + addl $__PAGE_OFFSET, %edi + movl %edi, pa(_brk_end) shrl $12, %eax movl %eax, pa(max_pfn_mapped) diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index b8329029c15..3ac2aa7b9ea 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -161,12 +161,6 @@ static struct resource bss_resource = { #ifdef CONFIG_X86_32 -/* This value is set up by the early boot code to point to the value - immediately after the boot time page tables. It contains a *physical* - address, and must not be in the .bss segment! */ -unsigned long init_pg_tables_start __initdata = ~0UL; -unsigned long init_pg_tables_end __initdata = ~0UL; - static struct resource video_ram_resource = { .name = "Video RAM area", .start = 0xa0000, diff --git a/arch/x86/kernel/vmlinux_32.lds.S b/arch/x86/kernel/vmlinux_32.lds.S index 27e44aa2158..1063fbe93c7 100644 --- a/arch/x86/kernel/vmlinux_32.lds.S +++ b/arch/x86/kernel/vmlinux_32.lds.S @@ -196,10 +196,6 @@ SECTIONS __brk_limit = . ; _end = . ; - - /* This is where the kernel creates the early boot page tables */ - . = ALIGN(PAGE_SIZE); - pg0 = . ; } /* Sections to be discarded */ diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 9fe4ddaa8f6..90e44a10e68 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -1058,14 +1058,6 @@ __init void lguest_init(void) * lguest_init() where the rest of the fairly chaotic boot setup * occurs. */ - /* The native boot code sets up initial page tables immediately after - * the kernel itself, and sets init_pg_tables_end so they're not - * clobbered. The Launcher places our initial pagetables somewhere at - * the top of our physical memory, so we don't need extra space: set - * init_pg_tables_end to the end of the kernel. */ - init_pg_tables_start = __pa(pg0); - init_pg_tables_end = __pa(pg0); - /* As described in head_32.S, we map the first 128M of memory. */ max_pfn_mapped = (128*1024*1024) >> PAGE_SHIFT; -- cgit v1.2.3-70-g09d2 From 6de6cb442e76bbaf2e685150be8ddac0f237a59c Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Fri, 27 Feb 2009 13:35:45 -0800 Subject: x86: use brk allocation for DMI Impact: use new interface instead of previous ad hoc implementation Use extend_brk() to allocate memory for DMI rather than having an ad-hoc allocator. Signed-off-by: Jeremy Fitzhardinge Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/dmi.h | 14 ++------------ arch/x86/kernel/setup.c | 6 ------ 2 files changed, 2 insertions(+), 18 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/dmi.h b/arch/x86/include/asm/dmi.h index bc68212c6bc..aa32f7e6c19 100644 --- a/arch/x86/include/asm/dmi.h +++ b/arch/x86/include/asm/dmi.h @@ -2,21 +2,11 @@ #define _ASM_X86_DMI_H #include +#include -#define DMI_MAX_DATA 2048 - -extern int dmi_alloc_index; -extern char dmi_alloc_data[DMI_MAX_DATA]; - -/* This is so early that there is no good way to allocate dynamic memory. - Allocate data in an BSS array. */ static inline void *dmi_alloc(unsigned len) { - int idx = dmi_alloc_index; - if ((dmi_alloc_index + len) > DMI_MAX_DATA) - return NULL; - dmi_alloc_index += len; - return dmi_alloc_data + idx; + return extend_brk(len, sizeof(int)); } /* Use early IO mappings for DMI because it's initialized early */ diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 3ac2aa7b9ea..e894f36335f 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -215,12 +215,6 @@ unsigned long mmu_cr4_features = X86_CR4_PAE; /* Boot loader ID as an integer, for the benefit of proc_dointvec */ int bootloader_type; -/* - * Early DMI memory - */ -int dmi_alloc_index; -char dmi_alloc_data[DMI_MAX_DATA]; - /* * Setup options */ -- cgit v1.2.3-70-g09d2 From 7543c1de84ed93c6769c9f20dced08a522af8912 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 12 Mar 2009 16:04:42 -0700 Subject: x86-32: compute initial mapping size more accurately Impact: simplification We only need to map the kernel in head_32.S, not the whole of lowmem. We use 512MB as a reasonable (but arbitrary) limit on the maximum size of the kernel image. Signed-off-by: Yinghai Lu Signed-off-by: Jeremy Fitzhardinge Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/page_32_types.h | 5 +++++ arch/x86/kernel/head_32.S | 2 +- 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h index f1e4a79a6e4..0f915ae649a 100644 --- a/arch/x86/include/asm/page_32_types.h +++ b/arch/x86/include/asm/page_32_types.h @@ -39,6 +39,11 @@ #define __VIRTUAL_MASK_SHIFT 32 #endif /* CONFIG_X86_PAE */ +/* + * Kernel image size is limited to 512 MB (see in arch/x86/kernel/head_32.S) + */ +#define KERNEL_IMAGE_SIZE (512 * 1024 * 1024) + #ifndef __ASSEMBLY__ /* diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index db6652710e9..3ce5456dfbe 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -54,7 +54,7 @@ * * This should be a multiple of a page. */ -LOW_PAGES = 1<<(32-PAGE_SHIFT_asm) +LOW_PAGES = (KERNEL_IMAGE_SIZE + PAGE_SIZE_asm - 1)>>PAGE_SHIFT /* * To preserve the DMA pool in PAGEALLOC kernels, we'll allocate -- cgit v1.2.3-70-g09d2 From 796216a57fe45c04adc35bda1f0782efec78a713 Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Thu, 12 Mar 2009 16:09:49 -0700 Subject: x86: allow extend_brk users to reserve brk space Impact: new interface; remove hard-coded limit Add RESERVE_BRK(name, size) macro to reserve space in the brk area. This should be a conservative (ie, larger) estimate of how much space might possibly be required from the brk area. Any unused space will be freed, so there's no real downside on making the reservation too large (within limits). The name should be unique within a given file, and somewhat descriptive. The C definition of RESERVE_BRK() ends up being more complex than one would expect to work around a cluster of gcc infelicities: The first attempt was to simply try putting __section(.brk_reservation) on a variable. This doesn't work because it ends up making it a @progbits section, which gets actual space allocated in the vmlinux executable. The second attempt was to emit the space into a section using asm, but gcc doesn't allow arguments to be passed to file-level asm() statements, making it hard to pass in the size. The final attempt is to wrap the asm() in a function to allow it to have arguments, and put the function itself into the .discard section, which vmlinux*.lds drops entirely from the emitted vmlinux. Signed-off-by: Jeremy Fitzhardinge Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/setup.h | 30 ++++++++++++++++++++++++++++++ arch/x86/kernel/head_32.S | 2 ++ arch/x86/kernel/setup.c | 2 ++ arch/x86/kernel/vmlinux_32.lds.S | 4 +++- arch/x86/kernel/vmlinux_64.lds.S | 4 +++- 5 files changed, 40 insertions(+), 2 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 366d3663994..61b126b9788 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -104,6 +104,29 @@ extern struct boot_params boot_params; extern unsigned long _brk_end; void *extend_brk(size_t size, size_t align); +/* + * Reserve space in the brk section. The name must be unique within + * the file, and somewhat descriptive. The size is in bytes. Must be + * used at file scope. + * + * (This uses a temp function to wrap the asm so we can pass it the + * size parameter; otherwise we wouldn't be able to. We can't use a + * "section" attribute on a normal variable because it always ends up + * being @progbits, which ends up allocating space in the vmlinux + * executable.) + */ +#define RESERVE_BRK(name,sz) \ + static void __section(.discard) __used \ + __brk_reservation_fn_##name##__(void) { \ + asm volatile ( \ + ".pushsection .brk_reservation,\"aw\",@nobits;" \ + "__brk_reservation_" #name "__:" \ + " 1:.skip %c0;" \ + " .size __brk_reservation_" #name "__, . - 1b;" \ + " .popsection" \ + : : "i" (sz)); \ + } + #ifdef __i386__ void __init i386_start_kernel(void); @@ -115,6 +138,13 @@ void __init x86_64_start_reservations(char *real_mode_data); #endif /* __i386__ */ #endif /* _SETUP */ +#else +#define RESERVE_BRK(name,sz) \ + .pushsection .brk_reservation,"aw",@nobits; \ +__brk_reservation_##name##__: \ +1: .skip sz; \ + .size __brk_reservation_##name##__,.-1b; \ + .popsection #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 3ce5456dfbe..9e89f2a14b9 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -75,6 +75,8 @@ ALLOCATOR_SLOP = 4 INIT_MAP_BEYOND_END = BOOTBITMAP_SIZE + (PAGE_TABLE_SIZE + ALLOCATOR_SLOP)*PAGE_SIZE_asm +RESERVE_BRK(pagetables, PAGE_TABLE_SIZE * PAGE_SIZE) + /* * 32-bit kernel entrypoint; only used by the boot CPU. On entry, * %esi points to the real-mode code as a 32-bit pointer. diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index e894f36335f..a0d26237d7c 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -112,6 +112,8 @@ #define ARCH_SETUP #endif +RESERVE_BRK(dmi_alloc, 65536); + unsigned int boot_cpu_id __read_mostly; static __initdata unsigned long _brk_start = (unsigned long)__brk_base; diff --git a/arch/x86/kernel/vmlinux_32.lds.S b/arch/x86/kernel/vmlinux_32.lds.S index 1063fbe93c7..a1f28b85fb3 100644 --- a/arch/x86/kernel/vmlinux_32.lds.S +++ b/arch/x86/kernel/vmlinux_32.lds.S @@ -192,7 +192,8 @@ SECTIONS . = ALIGN(PAGE_SIZE); __brk_base = . ; - . += 1024 * 1024 ; + . += 64 * 1024 ; /* 64k slop space */ + *(.brk_reservation) /* areas brk users have reserved */ __brk_limit = . ; _end = . ; @@ -201,6 +202,7 @@ SECTIONS /* Sections to be discarded */ /DISCARD/ : { *(.exitcall.exit) + *(.discard) } STABS_DEBUG diff --git a/arch/x86/kernel/vmlinux_64.lds.S b/arch/x86/kernel/vmlinux_64.lds.S index ff373423138..7996687663a 100644 --- a/arch/x86/kernel/vmlinux_64.lds.S +++ b/arch/x86/kernel/vmlinux_64.lds.S @@ -250,7 +250,8 @@ SECTIONS . = ALIGN(PAGE_SIZE); __brk_base = . ; - . += 1024 * 1024 ; + . += 64 * 1024; /* 64k slop space */ + *(.brk_reservation) /* areas brk users have reserved */ __brk_limit = . ; } @@ -260,6 +261,7 @@ SECTIONS /DISCARD/ : { *(.exitcall.exit) *(.eh_frame) + *(.discard) } STABS_DEBUG -- cgit v1.2.3-70-g09d2 From 42854dc0a6320ff36722749acafa0697522d9556 Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Mon, 16 Mar 2009 17:24:34 -0700 Subject: x86, paravirt: prevent gcc from generating the wrong addressing mode Impact: fix crash on VMI (VMware) When we generate a call sequence for calling a paravirtualized function, we presume that the generated code is "call *0xXXXXX", which is a 6 byte opcode; this is larger than a normal direct call, and so we can patch a direct call over it. At the moment, however we give gcc enough rope to hang us by putting the address in a register and generating a two byte indirect-via-register call. Prevent this by explicitly dereferencing the function pointer and passing it into the asm as a constant. This prevents crashes in VMI, as it cannot handle unpatchable callsites. Signed-off-by: Jeremy Fitzhardinge Cc: Alok Kataria LKML-Reference: <49BEEDC2.2070809@goop.org> Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/paravirt.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index e299287e8e3..0c212d528c0 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -360,7 +360,7 @@ extern struct pv_lock_ops pv_lock_ops; #define paravirt_type(op) \ [paravirt_typenum] "i" (PARAVIRT_PATCH(op)), \ - [paravirt_opptr] "m" (op) + [paravirt_opptr] "i" (&(op)) #define paravirt_clobber(clobber) \ [paravirt_clobber] "i" (clobber) @@ -412,7 +412,7 @@ int paravirt_disable_iospace(void); * offset into the paravirt_patch_template structure, and can therefore be * freely converted back into a structure offset. */ -#define PARAVIRT_CALL "call *%[paravirt_opptr];" +#define PARAVIRT_CALL "call *%c[paravirt_opptr];" /* * These macros are intended to wrap calls through one of the paravirt -- cgit v1.2.3-70-g09d2 From 2118d0c548e8a2205e1a29eb5b89e5f2e9ae2c8b Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Fri, 9 Jan 2009 15:13:15 +0100 Subject: dma-debug: x86 architecture bindings Impact: make use of DMA-API debugging code in x86 Signed-off-by: Joerg Roedel --- arch/x86/Kconfig | 1 + arch/x86/include/asm/dma-mapping.h | 45 +++++++++++++++++++++++++++++++++----- arch/x86/kernel/pci-dma.c | 6 +++++ 3 files changed, 46 insertions(+), 6 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index bc2fbadff9f..f2cb677b263 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -40,6 +40,7 @@ config X86 select HAVE_GENERIC_DMA_COHERENT if X86_32 select HAVE_EFFICIENT_UNALIGNED_ACCESS select USER_STACKTRACE_SUPPORT + select HAVE_DMA_API_DEBUG config ARCH_DEFCONFIG string diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index 9c78bd40ebe..cea7b74963e 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -7,6 +7,7 @@ */ #include +#include #include #include #include @@ -56,11 +57,16 @@ dma_map_single(struct device *hwdev, void *ptr, size_t size, enum dma_data_direction dir) { struct dma_map_ops *ops = get_dma_ops(hwdev); + dma_addr_t addr; BUG_ON(!valid_dma_direction(dir)); - return ops->map_page(hwdev, virt_to_page(ptr), + addr = ops->map_page(hwdev, virt_to_page(ptr), (unsigned long)ptr & ~PAGE_MASK, size, dir, NULL); + debug_dma_map_page(hwdev, virt_to_page(ptr), + (unsigned long)ptr & ~PAGE_MASK, size, + dir, addr, true); + return addr; } static inline void @@ -72,6 +78,7 @@ dma_unmap_single(struct device *dev, dma_addr_t addr, size_t size, BUG_ON(!valid_dma_direction(dir)); if (ops->unmap_page) ops->unmap_page(dev, addr, size, dir, NULL); + debug_dma_unmap_page(dev, addr, size, dir, true); } static inline int @@ -79,9 +86,13 @@ dma_map_sg(struct device *hwdev, struct scatterlist *sg, int nents, enum dma_data_direction dir) { struct dma_map_ops *ops = get_dma_ops(hwdev); + int ents; BUG_ON(!valid_dma_direction(dir)); - return ops->map_sg(hwdev, sg, nents, dir, NULL); + ents = ops->map_sg(hwdev, sg, nents, dir, NULL); + debug_dma_map_sg(hwdev, sg, nents, ents, dir); + + return ents; } static inline void @@ -91,6 +102,7 @@ dma_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nents, struct dma_map_ops *ops = get_dma_ops(hwdev); BUG_ON(!valid_dma_direction(dir)); + debug_dma_unmap_sg(hwdev, sg, nents, dir); if (ops->unmap_sg) ops->unmap_sg(hwdev, sg, nents, dir, NULL); } @@ -104,6 +116,7 @@ dma_sync_single_for_cpu(struct device *hwdev, dma_addr_t dma_handle, BUG_ON(!valid_dma_direction(dir)); if (ops->sync_single_for_cpu) ops->sync_single_for_cpu(hwdev, dma_handle, size, dir); + debug_dma_sync_single_for_cpu(hwdev, dma_handle, size, dir); flush_write_buffers(); } @@ -116,6 +129,7 @@ dma_sync_single_for_device(struct device *hwdev, dma_addr_t dma_handle, BUG_ON(!valid_dma_direction(dir)); if (ops->sync_single_for_device) ops->sync_single_for_device(hwdev, dma_handle, size, dir); + debug_dma_sync_single_for_device(hwdev, dma_handle, size, dir); flush_write_buffers(); } @@ -130,6 +144,8 @@ dma_sync_single_range_for_cpu(struct device *hwdev, dma_addr_t dma_handle, if (ops->sync_single_range_for_cpu) ops->sync_single_range_for_cpu(hwdev, dma_handle, offset, size, dir); + debug_dma_sync_single_range_for_cpu(hwdev, dma_handle, + offset, size, dir); flush_write_buffers(); } @@ -144,6 +160,8 @@ dma_sync_single_range_for_device(struct device *hwdev, dma_addr_t dma_handle, if (ops->sync_single_range_for_device) ops->sync_single_range_for_device(hwdev, dma_handle, offset, size, dir); + debug_dma_sync_single_range_for_device(hwdev, dma_handle, + offset, size, dir); flush_write_buffers(); } @@ -156,6 +174,7 @@ dma_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg, BUG_ON(!valid_dma_direction(dir)); if (ops->sync_sg_for_cpu) ops->sync_sg_for_cpu(hwdev, sg, nelems, dir); + debug_dma_sync_sg_for_cpu(hwdev, sg, nelems, dir); flush_write_buffers(); } @@ -168,6 +187,7 @@ dma_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg, BUG_ON(!valid_dma_direction(dir)); if (ops->sync_sg_for_device) ops->sync_sg_for_device(hwdev, sg, nelems, dir); + debug_dma_sync_sg_for_device(hwdev, sg, nelems, dir); flush_write_buffers(); } @@ -177,15 +197,24 @@ static inline dma_addr_t dma_map_page(struct device *dev, struct page *page, enum dma_data_direction dir) { struct dma_map_ops *ops = get_dma_ops(dev); + dma_addr_t addr; BUG_ON(!valid_dma_direction(dir)); - return ops->map_page(dev, page, offset, size, dir, NULL); + addr = ops->map_page(dev, page, offset, size, dir, NULL); + debug_dma_map_page(dev, page, offset, size, dir, addr, false); + + return addr; } static inline void dma_unmap_page(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir) { - dma_unmap_single(dev, addr, size, dir); + struct dma_map_ops *ops = get_dma_ops(dev); + + BUG_ON(!valid_dma_direction(dir)); + if (ops->unmap_page) + ops->unmap_page(dev, addr, size, dir, NULL); + debug_dma_unmap_page(dev, addr, size, dir, false); } static inline void @@ -250,8 +279,11 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, if (!ops->alloc_coherent) return NULL; - return ops->alloc_coherent(dev, size, dma_handle, - dma_alloc_coherent_gfp_flags(dev, gfp)); + memory = ops->alloc_coherent(dev, size, dma_handle, + dma_alloc_coherent_gfp_flags(dev, gfp)); + debug_dma_alloc_coherent(dev, size, *dma_handle, memory); + + return memory; } static inline void dma_free_coherent(struct device *dev, size_t size, @@ -264,6 +296,7 @@ static inline void dma_free_coherent(struct device *dev, size_t size, if (dma_release_from_coherent(dev, get_order(size), vaddr)) return; + debug_dma_free_coherent(dev, size, vaddr, bus); if (ops->free_coherent) ops->free_coherent(dev, size, vaddr, bus); } diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index f293a8df682..ebf7d454f21 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -1,4 +1,5 @@ #include +#include #include #include #include @@ -44,6 +45,9 @@ struct device x86_dma_fallback_dev = { }; EXPORT_SYMBOL(x86_dma_fallback_dev); +/* Number of entries preallocated for DMA-API debugging */ +#define PREALLOC_DMA_DEBUG_ENTRIES 32768 + int dma_set_mask(struct device *dev, u64 mask) { if (!dev->dma_mask || !dma_supported(dev, mask)) @@ -265,6 +269,8 @@ EXPORT_SYMBOL(dma_supported); static int __init pci_iommu_init(void) { + dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES); + calgary_iommu_init(); intel_iommu_init(); -- cgit v1.2.3-70-g09d2 From 0b1c723d0bd199300a1a2de57a46000d17577498 Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Sat, 14 Mar 2009 23:19:38 -0700 Subject: x86/brk: make the brk reservation symbols inaccessible from C Impact: bulletproofing, clarification The brk reservation symbols are just there to document the amount of space reserved by brk users in the final vmlinux file. Their addresses are irrelevent, and using their addresses will cause certain havok. Name them ".brk.NAME", which is a valid asm symbol but C can't reference it; it also highlights their special role in the symbol table. Signed-off-by: Jeremy Fitzhardinge --- arch/x86/include/asm/setup.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 61b126b9788..fbf0521eeed 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -116,13 +116,13 @@ void *extend_brk(size_t size, size_t align); * executable.) */ #define RESERVE_BRK(name,sz) \ - static void __section(.discard) __used \ + static void __section(.discard) __used \ __brk_reservation_fn_##name##__(void) { \ asm volatile ( \ ".pushsection .brk_reservation,\"aw\",@nobits;" \ - "__brk_reservation_" #name "__:" \ + ".brk." #name ":" \ " 1:.skip %c0;" \ - " .size __brk_reservation_" #name "__, . - 1b;" \ + " .size .brk." #name ", . - 1b;" \ " .popsection" \ : : "i" (sz)); \ } @@ -141,9 +141,9 @@ void __init x86_64_start_reservations(char *real_mode_data); #else #define RESERVE_BRK(name,sz) \ .pushsection .brk_reservation,"aw",@nobits; \ -__brk_reservation_##name##__: \ +.brk.name: \ 1: .skip sz; \ - .size __brk_reservation_##name##__,.-1b; \ + .size .brk.name,.-1b; \ .popsection #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ -- cgit v1.2.3-70-g09d2 From 9d783ba042771284fb4ee5013c3d94220755ae7f Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Mon, 16 Mar 2009 17:04:55 -0700 Subject: x86, x2apic: enable fault handling for intr-remapping Impact: interface augmentation (not yet used) Enable fault handling flow for intr-remapping aswell. Fault handling code now shared by both dma-remapping and intr-remapping. Signed-off-by: Suresh Siddha Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/msidef.h | 1 + arch/x86/kernel/apic/io_apic.c | 9 +++- arch/x86/kernel/apic/probe_64.c | 9 ++++ drivers/pci/dmar.c | 102 +++++++++++++++++++++++++++++++++------- drivers/pci/intel-iommu.c | 3 +- drivers/pci/intr_remapping.c | 2 +- include/linux/dmar.h | 5 +- include/linux/intel-iommu.h | 4 +- 8 files changed, 107 insertions(+), 28 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/msidef.h b/arch/x86/include/asm/msidef.h index 6706b3006f1..4cc48af23fe 100644 --- a/arch/x86/include/asm/msidef.h +++ b/arch/x86/include/asm/msidef.h @@ -47,6 +47,7 @@ #define MSI_ADDR_DEST_ID_MASK 0x00ffff0 #define MSI_ADDR_DEST_ID(dest) (((dest) << MSI_ADDR_DEST_ID_SHIFT) & \ MSI_ADDR_DEST_ID_MASK) +#define MSI_ADDR_EXT_DEST_ID(dest) ((dest) & 0xffffff00) #define MSI_ADDR_IR_EXT_INT (1 << 4) #define MSI_ADDR_IR_SHV (1 << 3) diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 00e6071cefc..b18a7734d68 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -3294,7 +3294,12 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms } else #endif { - msg->address_hi = MSI_ADDR_BASE_HI; + if (x2apic_enabled()) + msg->address_hi = MSI_ADDR_BASE_HI | + MSI_ADDR_EXT_DEST_ID(dest); + else + msg->address_hi = MSI_ADDR_BASE_HI; + msg->address_lo = MSI_ADDR_BASE_LO | ((apic->irq_dest_mode == 0) ? @@ -3528,7 +3533,7 @@ void arch_teardown_msi_irq(unsigned int irq) destroy_irq(irq); } -#ifdef CONFIG_DMAR +#if defined (CONFIG_DMAR) || defined (CONFIG_INTR_REMAP) #ifdef CONFIG_SMP static void dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask) { diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c index 8d7748efe6a..8297c2b8ed2 100644 --- a/arch/x86/kernel/apic/probe_64.c +++ b/arch/x86/kernel/apic/probe_64.c @@ -68,6 +68,15 @@ void __init default_setup_apic_routing(void) apic = &apic_physflat; printk(KERN_INFO "Setting APIC routing to %s\n", apic->name); } + +#ifdef CONFIG_X86_X2APIC + /* + * Now that apic routing model is selected, configure the + * fault handling for intr remapping. + */ + if (intr_remapping_enabled) + enable_drhd_fault_handling(); +#endif } /* Same for both flat and physical. */ diff --git a/drivers/pci/dmar.c b/drivers/pci/dmar.c index 75d34bf2db5..bb4ed985f9c 100644 --- a/drivers/pci/dmar.c +++ b/drivers/pci/dmar.c @@ -511,6 +511,7 @@ int alloc_iommu(struct dmar_drhd_unit *drhd) return -ENOMEM; iommu->seq_id = iommu_allocated++; + sprintf (iommu->name, "dmar%d", iommu->seq_id); iommu->reg = ioremap(drhd->reg_base_addr, VTD_PAGE_SIZE); if (!iommu->reg) { @@ -817,7 +818,13 @@ int dmar_enable_qi(struct intel_iommu *iommu) /* iommu interrupt handling. Most stuff are MSI-like. */ -static const char *fault_reason_strings[] = +enum faulttype { + DMA_REMAP, + INTR_REMAP, + UNKNOWN, +}; + +static const char *dma_remap_fault_reasons[] = { "Software", "Present bit in root entry is clear", @@ -833,14 +840,33 @@ static const char *fault_reason_strings[] = "non-zero reserved fields in CTP", "non-zero reserved fields in PTE", }; + +static const char *intr_remap_fault_reasons[] = +{ + "Detected reserved fields in the decoded interrupt-remapped request", + "Interrupt index exceeded the interrupt-remapping table size", + "Present field in the IRTE entry is clear", + "Error accessing interrupt-remapping table pointed by IRTA_REG", + "Detected reserved fields in the IRTE entry", + "Blocked a compatibility format interrupt request", + "Blocked an interrupt request due to source-id verification failure", +}; + #define MAX_FAULT_REASON_IDX (ARRAY_SIZE(fault_reason_strings) - 1) -const char *dmar_get_fault_reason(u8 fault_reason) +const char *dmar_get_fault_reason(u8 fault_reason, int *fault_type) { - if (fault_reason > MAX_FAULT_REASON_IDX) + if (fault_reason >= 0x20 && (fault_reason <= 0x20 + + ARRAY_SIZE(intr_remap_fault_reasons))) { + *fault_type = INTR_REMAP; + return intr_remap_fault_reasons[fault_reason - 0x20]; + } else if (fault_reason < ARRAY_SIZE(dma_remap_fault_reasons)) { + *fault_type = DMA_REMAP; + return dma_remap_fault_reasons[fault_reason]; + } else { + *fault_type = UNKNOWN; return "Unknown"; - else - return fault_reason_strings[fault_reason]; + } } void dmar_msi_unmask(unsigned int irq) @@ -897,16 +923,25 @@ static int dmar_fault_do_one(struct intel_iommu *iommu, int type, u8 fault_reason, u16 source_id, unsigned long long addr) { const char *reason; + int fault_type; - reason = dmar_get_fault_reason(fault_reason); + reason = dmar_get_fault_reason(fault_reason, &fault_type); - printk(KERN_ERR - "DMAR:[%s] Request device [%02x:%02x.%d] " - "fault addr %llx \n" - "DMAR:[fault reason %02d] %s\n", - (type ? "DMA Read" : "DMA Write"), - (source_id >> 8), PCI_SLOT(source_id & 0xFF), - PCI_FUNC(source_id & 0xFF), addr, fault_reason, reason); + if (fault_type == INTR_REMAP) + printk(KERN_ERR "INTR-REMAP: Request device [[%02x:%02x.%d] " + "fault index %llx\n" + "INTR-REMAP:[fault reason %02d] %s\n", + (source_id >> 8), PCI_SLOT(source_id & 0xFF), + PCI_FUNC(source_id & 0xFF), addr >> 48, + fault_reason, reason); + else + printk(KERN_ERR + "DMAR:[%s] Request device [%02x:%02x.%d] " + "fault addr %llx \n" + "DMAR:[fault reason %02d] %s\n", + (type ? "DMA Read" : "DMA Write"), + (source_id >> 8), PCI_SLOT(source_id & 0xFF), + PCI_FUNC(source_id & 0xFF), addr, fault_reason, reason); return 0; } @@ -920,10 +955,13 @@ static irqreturn_t dmar_fault(int irq, void *dev_id) spin_lock_irqsave(&iommu->register_lock, flag); fault_status = readl(iommu->reg + DMAR_FSTS_REG); + if (fault_status) + printk(KERN_ERR "DRHD: handling fault status reg %x\n", + fault_status); /* TBD: ignore advanced fault log currently */ if (!(fault_status & DMA_FSTS_PPF)) - goto clear_overflow; + goto clear_rest; fault_index = dma_fsts_fault_record_index(fault_status); reg = cap_fault_reg_offset(iommu->cap); @@ -964,11 +1002,10 @@ static irqreturn_t dmar_fault(int irq, void *dev_id) fault_index = 0; spin_lock_irqsave(&iommu->register_lock, flag); } -clear_overflow: - /* clear primary fault overflow */ +clear_rest: + /* clear all the other faults */ fault_status = readl(iommu->reg + DMAR_FSTS_REG); - if (fault_status & DMA_FSTS_PFO) - writel(DMA_FSTS_PFO, iommu->reg + DMAR_FSTS_REG); + writel(fault_status, iommu->reg + DMAR_FSTS_REG); spin_unlock_irqrestore(&iommu->register_lock, flag); return IRQ_HANDLED; @@ -978,6 +1015,12 @@ int dmar_set_interrupt(struct intel_iommu *iommu) { int irq, ret; + /* + * Check if the fault interrupt is already initialized. + */ + if (iommu->irq) + return 0; + irq = create_irq(); if (!irq) { printk(KERN_ERR "IOMMU: no free vectors\n"); @@ -1003,3 +1046,26 @@ int dmar_set_interrupt(struct intel_iommu *iommu) printk(KERN_ERR "IOMMU: can't request irq\n"); return ret; } + +int __init enable_drhd_fault_handling(void) +{ + struct dmar_drhd_unit *drhd; + + /* + * Enable fault control interrupt. + */ + for_each_drhd_unit(drhd) { + int ret; + struct intel_iommu *iommu = drhd->iommu; + ret = dmar_set_interrupt(iommu); + + if (ret) { + printk(KERN_ERR "DRHD %Lx: failed to enable fault, " + " interrupt, ret %d\n", + (unsigned long long)drhd->reg_base_addr, ret); + return -1; + } + } + + return 0; +} diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c index 4a4ab651b70..25fc1df486b 100644 --- a/drivers/pci/intel-iommu.c +++ b/drivers/pci/intel-iommu.c @@ -1799,7 +1799,7 @@ static int __init init_dmars(void) struct dmar_rmrr_unit *rmrr; struct pci_dev *pdev; struct intel_iommu *iommu; - int i, ret, unit = 0; + int i, ret; /* * for each drhd @@ -1921,7 +1921,6 @@ static int __init init_dmars(void) if (drhd->ignored) continue; iommu = drhd->iommu; - sprintf (iommu->name, "dmar%d", unit++); iommu_flush_write_buffer(iommu); diff --git a/drivers/pci/intr_remapping.c b/drivers/pci/intr_remapping.c index 5ffa65fffb6..c38e3f437a8 100644 --- a/drivers/pci/intr_remapping.c +++ b/drivers/pci/intr_remapping.c @@ -308,7 +308,7 @@ int modify_irte(int irq, struct irte *irte_modified) index = irq_iommu->irte_index + irq_iommu->sub_handle; irte = &iommu->ir_table->base[index]; - set_64bit((unsigned long *)irte, irte_modified->low | (1 << 1)); + set_64bit((unsigned long *)irte, irte_modified->low); __iommu_flush_cache(iommu, irte, sizeof(*irte)); rc = qi_flush_iec(iommu, index, 0); diff --git a/include/linux/dmar.h b/include/linux/dmar.h index f28440784cf..c7768330c11 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -49,6 +49,7 @@ extern int dmar_dev_scope_init(void); /* Intel IOMMU detection */ extern void detect_intel_iommu(void); +extern int enable_drhd_fault_handling(void); extern int parse_ioapics_under_ir(void); @@ -116,9 +117,6 @@ extern struct intel_iommu *map_ioapic_to_ir(int apic); #define intr_remapping_enabled (0) #endif -#ifdef CONFIG_DMAR -extern const char *dmar_get_fault_reason(u8 fault_reason); - /* Can't use the common MSI interrupt functions * since DMAR is not a pci device */ @@ -129,6 +127,7 @@ extern void dmar_msi_write(int irq, struct msi_msg *msg); extern int dmar_set_interrupt(struct intel_iommu *iommu); extern int arch_setup_dmar_msi(unsigned int irq); +#ifdef CONFIG_DMAR extern int iommu_detected, no_iommu; extern struct list_head dmar_rmrr_units; struct dmar_rmrr_unit { diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index d2e3cbfba14..a9563840644 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -292,6 +292,8 @@ struct intel_iommu { spinlock_t register_lock; /* protect register handling */ int seq_id; /* sequence id of the iommu */ int agaw; /* agaw of this iommu */ + unsigned int irq; + unsigned char name[13]; /* Device Name */ #ifdef CONFIG_DMAR unsigned long *domain_ids; /* bitmap of domains */ @@ -299,8 +301,6 @@ struct intel_iommu { spinlock_t lock; /* protect context, domain ids */ struct root_entry *root_entry; /* virtual address */ - unsigned int irq; - unsigned char name[7]; /* Device Name */ struct iommu_flush flush; #endif struct q_inval *qi; /* Queued invalidation info */ -- cgit v1.2.3-70-g09d2 From cf6567fe40c55e9cffca7355cd34e50fb2871e4e Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Mon, 16 Mar 2009 17:05:00 -0700 Subject: x86, x2apic: fix clear_local_APIC() in the presence of x2apic Impact: cleanup, paranoia We were not clearing the local APIC in clear_local_APIC() in the presence of x2apic. Fix it. Signed-off-by: Suresh Siddha Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/apic.h | 3 +++ arch/x86/include/asm/irq_remapping.h | 2 -- arch/x86/kernel/apic/apic.c | 9 ++------- 3 files changed, 5 insertions(+), 9 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 394d177d721..6d5b6f0900e 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -184,6 +184,9 @@ static inline int x2apic_enabled(void) { return 0; } + +#define x2apic 0 + #endif extern int get_physical_broadcast(void); diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h index 20e1fd588db..0396760fccb 100644 --- a/arch/x86/include/asm/irq_remapping.h +++ b/arch/x86/include/asm/irq_remapping.h @@ -1,8 +1,6 @@ #ifndef _ASM_X86_IRQ_REMAPPING_H #define _ASM_X86_IRQ_REMAPPING_H -extern int x2apic; - #define IRTE_DEST(dest) ((x2apic) ? dest : dest << 8) #endif /* _ASM_X86_IRQ_REMAPPING_H */ diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 30909a258d0..699f8cf76bb 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -809,7 +809,7 @@ void clear_local_APIC(void) u32 v; /* APIC hasn't been mapped yet */ - if (!apic_phys) + if (!x2apic && !apic_phys) return; maxlvt = lapic_get_maxlvt(); @@ -1523,12 +1523,10 @@ void __init early_init_lapic_mapping(void) */ void __init init_apic_mappings(void) { -#ifdef CONFIG_X86_X2APIC if (x2apic) { boot_cpu_physical_apicid = read_apic_id(); return; } -#endif /* * If no local APIC can be found then set up a fake all @@ -1972,12 +1970,9 @@ static int lapic_resume(struct sys_device *dev) local_irq_save(flags); -#ifdef CONFIG_X86_X2APIC if (x2apic) enable_x2apic(); - else -#endif - { + else { /* * Make sure the APICBASE points to the right address * -- cgit v1.2.3-70-g09d2 From 0280f7c416c652a2fd95d166f52b199ae61122c0 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Mon, 16 Mar 2009 17:05:01 -0700 Subject: x86, x2apic: cleanup the IO-APIC level migration with interrupt-remapping Impact: simplification In the current code, for level triggered migration, we need to modify the io-apic RTE with the update vector information, along with modifying interrupt remapping table entry(IRTE) with vector and destination. This is to ensure that remote IRR bit inthe IOAPIC RTE gets cleared when the cpu does EOI. With this patch, for level triggered, we eliminate the io-apic RTE modification (with the updated vector information), by using a virtual vector (io-apic pin number). Real vector that is used for interrupting cpu will be coming from the interrupt-remapping table entry. Trigger mode in the IRTE will always be edge, and the actual level or edge trigger will be setup in the IO-APIC RTE. So a level triggered interrupt will appear as an edge to the local apic cpu but still as level to the IO-APIC. With this change, level irq migration can be done by simply modifying the interrupt-remapping table entry with out changing the io-apic RTE. And as the interrupt appears as edge at the cpu, in addition to do the local apic EOI, we need to do IO-APIC directed EOI to clear the remote IRR bit in the IO-APIC RTE. This simplies the irq migration in the presence of interrupt-remapping. Idea-by: Rajesh Sankaran Signed-off-by: Suresh Siddha Cc: Eric W. Biederman Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/io_apic.h | 2 +- arch/x86/kernel/apic/io_apic.c | 156 +++++++++++++++++------------------------ 2 files changed, 66 insertions(+), 92 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h index 59cb4a1317b..ffcd08f96e4 100644 --- a/arch/x86/include/asm/io_apic.h +++ b/arch/x86/include/asm/io_apic.h @@ -172,7 +172,7 @@ extern void probe_nr_irqs_gsi(void); extern int setup_ioapic_entry(int apic, int irq, struct IO_APIC_route_entry *entry, unsigned int destination, int trigger, - int polarity, int vector); + int polarity, int vector, int pin); extern void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e); #else /* !CONFIG_X86_IO_APIC */ diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 4d975d0e358..e074eac5bd3 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -389,6 +389,8 @@ struct io_apic { unsigned int index; unsigned int unused[3]; unsigned int data; + unsigned int unused2[11]; + unsigned int eoi; }; static __attribute_const__ struct io_apic __iomem *io_apic_base(int idx) @@ -397,6 +399,12 @@ static __attribute_const__ struct io_apic __iomem *io_apic_base(int idx) + (mp_ioapics[idx].apicaddr & ~PAGE_MASK); } +static inline void io_apic_eoi(unsigned int apic, unsigned int vector) +{ + struct io_apic __iomem *io_apic = io_apic_base(apic); + writel(vector, &io_apic->eoi); +} + static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg) { struct io_apic __iomem *io_apic = io_apic_base(apic); @@ -1478,7 +1486,7 @@ static void ioapic_register_intr(int irq, struct irq_desc *desc, unsigned long t int setup_ioapic_entry(int apic_id, int irq, struct IO_APIC_route_entry *entry, unsigned int destination, int trigger, - int polarity, int vector) + int polarity, int vector, int pin) { /* * add it to the IO-APIC irq-routing table: @@ -1504,7 +1512,14 @@ int setup_ioapic_entry(int apic_id, int irq, irte.present = 1; irte.dst_mode = apic->irq_dest_mode; - irte.trigger_mode = trigger; + /* + * Trigger mode in the IRTE will always be edge, and the + * actual level or edge trigger will be setup in the IO-APIC + * RTE. This will help simplify level triggered irq migration. + * For more details, see the comments above explainig IO-APIC + * irq migration in the presence of interrupt-remapping. + */ + irte.trigger_mode = 0; irte.dlvry_mode = apic->irq_delivery_mode; irte.vector = vector; irte.dest_id = IRTE_DEST(destination); @@ -1515,18 +1530,23 @@ int setup_ioapic_entry(int apic_id, int irq, ir_entry->zero = 0; ir_entry->format = 1; ir_entry->index = (index & 0x7fff); + /* + * IO-APIC RTE will be configured with virtual vector. + * irq handler will do the explicit EOI to the io-apic. + */ + ir_entry->vector = pin; } else #endif { entry->delivery_mode = apic->irq_delivery_mode; entry->dest_mode = apic->irq_dest_mode; entry->dest = destination; + entry->vector = vector; } entry->mask = 0; /* enable IRQ */ entry->trigger = trigger; entry->polarity = polarity; - entry->vector = vector; /* Mask level triggered irqs. * Use IRQ_DELAYED_DISABLE for edge triggered irqs. @@ -1561,7 +1581,7 @@ static void setup_IO_APIC_irq(int apic_id, int pin, unsigned int irq, struct irq if (setup_ioapic_entry(mp_ioapics[apic_id].apicid, irq, &entry, - dest, trigger, polarity, cfg->vector)) { + dest, trigger, polarity, cfg->vector, pin)) { printk("Failed to setup ioapic entry for ioapic %d, pin %d\n", mp_ioapics[apic_id].apicid, pin); __clear_irq_vector(irq, cfg); @@ -2311,37 +2331,24 @@ static int ioapic_retrigger_irq(unsigned int irq) #ifdef CONFIG_SMP #ifdef CONFIG_INTR_REMAP -static void ir_irq_migration(struct work_struct *work); - -static DECLARE_DELAYED_WORK(ir_migration_work, ir_irq_migration); /* * Migrate the IO-APIC irq in the presence of intr-remapping. * - * For edge triggered, irq migration is a simple atomic update(of vector - * and cpu destination) of IRTE and flush the hardware cache. - * - * For level triggered, we need to modify the io-apic RTE aswell with the update - * vector information, along with modifying IRTE with vector and destination. - * So irq migration for level triggered is little bit more complex compared to - * edge triggered migration. But the good news is, we use the same algorithm - * for level triggered migration as we have today, only difference being, - * we now initiate the irq migration from process context instead of the - * interrupt context. + * For both level and edge triggered, irq migration is a simple atomic + * update(of vector and cpu destination) of IRTE and flush the hardware cache. * - * In future, when we do a directed EOI (combined with cpu EOI broadcast - * suppression) to the IO-APIC, level triggered irq migration will also be - * as simple as edge triggered migration and we can do the irq migration - * with a simple atomic update to IO-APIC RTE. + * For level triggered, we eliminate the io-apic RTE modification (with the + * updated vector information), by using a virtual vector (io-apic pin number). + * Real vector that is used for interrupting cpu will be coming from + * the interrupt-remapping table entry. */ static void migrate_ioapic_irq_desc(struct irq_desc *desc, const struct cpumask *mask) { struct irq_cfg *cfg; struct irte irte; - int modify_ioapic_rte; unsigned int dest; - unsigned long flags; unsigned int irq; if (!cpumask_intersects(mask, cpu_online_mask)) @@ -2359,13 +2366,6 @@ migrate_ioapic_irq_desc(struct irq_desc *desc, const struct cpumask *mask) dest = apic->cpu_mask_to_apicid_and(cfg->domain, mask); - modify_ioapic_rte = desc->status & IRQ_LEVEL; - if (modify_ioapic_rte) { - spin_lock_irqsave(&ioapic_lock, flags); - __target_IO_APIC_irq(irq, dest, cfg); - spin_unlock_irqrestore(&ioapic_lock, flags); - } - irte.vector = cfg->vector; irte.dest_id = IRTE_DEST(dest); @@ -2380,73 +2380,12 @@ migrate_ioapic_irq_desc(struct irq_desc *desc, const struct cpumask *mask) cpumask_copy(desc->affinity, mask); } -static int migrate_irq_remapped_level_desc(struct irq_desc *desc) -{ - int ret = -1; - struct irq_cfg *cfg = desc->chip_data; - - mask_IO_APIC_irq_desc(desc); - - if (io_apic_level_ack_pending(cfg)) { - /* - * Interrupt in progress. Migrating irq now will change the - * vector information in the IO-APIC RTE and that will confuse - * the EOI broadcast performed by cpu. - * So, delay the irq migration to the next instance. - */ - schedule_delayed_work(&ir_migration_work, 1); - goto unmask; - } - - /* everthing is clear. we have right of way */ - migrate_ioapic_irq_desc(desc, desc->pending_mask); - - ret = 0; - desc->status &= ~IRQ_MOVE_PENDING; - cpumask_clear(desc->pending_mask); - -unmask: - unmask_IO_APIC_irq_desc(desc); - - return ret; -} - -static void ir_irq_migration(struct work_struct *work) -{ - unsigned int irq; - struct irq_desc *desc; - - for_each_irq_desc(irq, desc) { - if (desc->status & IRQ_MOVE_PENDING) { - unsigned long flags; - - spin_lock_irqsave(&desc->lock, flags); - if (!desc->chip->set_affinity || - !(desc->status & IRQ_MOVE_PENDING)) { - desc->status &= ~IRQ_MOVE_PENDING; - spin_unlock_irqrestore(&desc->lock, flags); - continue; - } - - desc->chip->set_affinity(irq, desc->pending_mask); - spin_unlock_irqrestore(&desc->lock, flags); - } - } -} - /* * Migrates the IRQ destination in the process context. */ static void set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc, const struct cpumask *mask) { - if (desc->status & IRQ_LEVEL) { - desc->status |= IRQ_MOVE_PENDING; - cpumask_copy(desc->pending_mask, mask); - migrate_irq_remapped_level_desc(desc); - return; - } - migrate_ioapic_irq_desc(desc, mask); } static void set_ir_ioapic_affinity_irq(unsigned int irq, @@ -2537,9 +2476,44 @@ static inline void irq_complete_move(struct irq_desc **descp) {} #endif #ifdef CONFIG_INTR_REMAP +static void __eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg) +{ + int apic, pin; + struct irq_pin_list *entry; + + entry = cfg->irq_2_pin; + for (;;) { + + if (!entry) + break; + + apic = entry->apic; + pin = entry->pin; + io_apic_eoi(apic, pin); + entry = entry->next; + } +} + +static void +eoi_ioapic_irq(struct irq_desc *desc) +{ + struct irq_cfg *cfg; + unsigned long flags; + unsigned int irq; + + irq = desc->irq; + cfg = desc->chip_data; + + spin_lock_irqsave(&ioapic_lock, flags); + __eoi_ioapic_irq(irq, cfg); + spin_unlock_irqrestore(&ioapic_lock, flags); +} + static void ack_x2apic_level(unsigned int irq) { + struct irq_desc *desc = irq_to_desc(irq); ack_x2APIC_irq(); + eoi_ioapic_irq(desc); } static void ack_x2apic_edge(unsigned int irq) -- cgit v1.2.3-70-g09d2 From 05c3dc2c4b60387769cbe73174347de4cf85f0c9 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Mon, 16 Mar 2009 17:05:03 -0700 Subject: x86, ioapic: Fix non atomic allocation with interrupts disabled Impact: fix possible race save_mask_IO_APIC_setup() was using non atomic memory allocation while getting called with interrupts disabled. Fix this by splitting this into two different function. Allocation part save_IO_APIC_setup() now happens before disabling interrupts. Signed-off-by: Suresh Siddha Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/io_apic.h | 3 ++- arch/x86/kernel/apic/apic.c | 11 ++++++----- arch/x86/kernel/apic/io_apic.c | 34 +++++++++++++++++++++++----------- 3 files changed, 31 insertions(+), 17 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h index ffcd08f96e4..373cc2bbcad 100644 --- a/arch/x86/include/asm/io_apic.h +++ b/arch/x86/include/asm/io_apic.h @@ -162,7 +162,8 @@ extern int (*ioapic_renumber_irq)(int ioapic, int irq); extern void ioapic_init_mappings(void); #ifdef CONFIG_X86_64 -extern int save_mask_IO_APIC_setup(void); +extern int save_IO_APIC_setup(void); +extern void mask_IO_APIC_setup(void); extern void restore_IO_APIC_setup(void); extern void reinit_intr_remapped_IO_APIC(int); #endif diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 699f8cf76bb..85eb8e10081 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1334,15 +1334,16 @@ void __init enable_IR_x2apic(void) return; } - local_irq_save(flags); - mask_8259A(); - - ret = save_mask_IO_APIC_setup(); + ret = save_IO_APIC_setup(); if (ret) { pr_info("Saving IO-APIC state failed: %d\n", ret); goto end; } + local_irq_save(flags); + mask_IO_APIC_setup(); + mask_8259A(); + ret = enable_intr_remapping(1); if (ret && x2apic_preenabled) { @@ -1367,10 +1368,10 @@ end_restore: else reinit_intr_remapped_IO_APIC(x2apic_preenabled); -end: unmask_8259A(); local_irq_restore(flags); +end: if (!ret) { if (!x2apic_preenabled) pr_info("Enabled x2apic and interrupt-remapping\n"); diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index cf27795c641..ff1759a1128 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -853,9 +853,9 @@ __setup("pirq=", ioapic_pirq_setup); static struct IO_APIC_route_entry *early_ioapic_entries[MAX_IO_APICS]; /* - * Saves and masks all the unmasked IO-APIC RTE's + * Saves all the IO-APIC RTE's */ -int save_mask_IO_APIC_setup(void) +int save_IO_APIC_setup(void) { union IO_APIC_reg_01 reg_01; unsigned long flags; @@ -880,16 +880,9 @@ int save_mask_IO_APIC_setup(void) } for (apic = 0; apic < nr_ioapics; apic++) - for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) { - struct IO_APIC_route_entry entry; - - entry = early_ioapic_entries[apic][pin] = + for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) + early_ioapic_entries[apic][pin] = ioapic_read_entry(apic, pin); - if (!entry.mask) { - entry.mask = 1; - ioapic_write_entry(apic, pin, entry); - } - } return 0; @@ -902,6 +895,25 @@ nomem: return -ENOMEM; } +void mask_IO_APIC_setup(void) +{ + int apic, pin; + + for (apic = 0; apic < nr_ioapics; apic++) { + if (!early_ioapic_entries[apic]) + break; + for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) { + struct IO_APIC_route_entry entry; + + entry = early_ioapic_entries[apic][pin]; + if (!entry.mask) { + entry.mask = 1; + ioapic_write_entry(apic, pin, entry); + } + } + } +} + void restore_IO_APIC_setup(void) { int apic, pin; -- cgit v1.2.3-70-g09d2 From ce4e240c279a31096f74afa6584a62d64a1ba8c8 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Tue, 17 Mar 2009 10:16:54 -0800 Subject: x86: add x2apic_wrmsr_fence() to x2apic flush tlb paths Impact: optimize APIC IPI related barriers Uncached MMIO accesses for xapic are inherently serializing and hence we don't need explicit barriers for xapic IPI paths. x2apic MSR writes/reads don't have serializing semantics and hence need a serializing instruction or mfence, to make all the previous memory stores globally visisble before the x2apic msr write for IPI. Add x2apic_wrmsr_fence() in flush tlb path to x2apic specific paths. Signed-off-by: Suresh Siddha Cc: Peter Zijlstra Cc: Oleg Nesterov Cc: Jens Axboe Cc: Linus Torvalds Cc: "Paul E. McKenney" Cc: Rusty Russell Cc: Steven Rostedt Cc: "steiner@sgi.com" Cc: Nick Piggin LKML-Reference: <1237313814.27006.203.camel@localhost.localdomain> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/apic.h | 10 ++++++++++ arch/x86/kernel/apic/x2apic_cluster.c | 6 ++++++ arch/x86/kernel/apic/x2apic_phys.c | 6 ++++++ arch/x86/mm/tlb.c | 5 ----- 4 files changed, 22 insertions(+), 5 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 6d5b6f0900e..00f5962d82d 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -108,6 +108,16 @@ extern void native_apic_icr_write(u32 low, u32 id); extern u64 native_apic_icr_read(void); #ifdef CONFIG_X86_X2APIC +/* + * Make previous memory operations globally visible before + * sending the IPI through x2apic wrmsr. We need a serializing instruction or + * mfence for this. + */ +static inline void x2apic_wrmsr_fence(void) +{ + asm volatile("mfence" : : : "memory"); +} + static inline void native_apic_msr_write(u32 reg, u32 v) { if (reg == APIC_DFR || reg == APIC_ID || reg == APIC_LDR || diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index 8fb87b6dd63..4a903e2f0d1 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -57,6 +57,8 @@ static void x2apic_send_IPI_mask(const struct cpumask *mask, int vector) unsigned long query_cpu; unsigned long flags; + x2apic_wrmsr_fence(); + local_irq_save(flags); for_each_cpu(query_cpu, mask) { __x2apic_send_IPI_dest( @@ -73,6 +75,8 @@ static void unsigned long query_cpu; unsigned long flags; + x2apic_wrmsr_fence(); + local_irq_save(flags); for_each_cpu(query_cpu, mask) { if (query_cpu == this_cpu) @@ -90,6 +94,8 @@ static void x2apic_send_IPI_allbutself(int vector) unsigned long query_cpu; unsigned long flags; + x2apic_wrmsr_fence(); + local_irq_save(flags); for_each_online_cpu(query_cpu) { if (query_cpu == this_cpu) diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index 23625b9f98b..a284359627e 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -58,6 +58,8 @@ static void x2apic_send_IPI_mask(const struct cpumask *mask, int vector) unsigned long query_cpu; unsigned long flags; + x2apic_wrmsr_fence(); + local_irq_save(flags); for_each_cpu(query_cpu, mask) { __x2apic_send_IPI_dest(per_cpu(x86_cpu_to_apicid, query_cpu), @@ -73,6 +75,8 @@ static void unsigned long query_cpu; unsigned long flags; + x2apic_wrmsr_fence(); + local_irq_save(flags); for_each_cpu(query_cpu, mask) { if (query_cpu != this_cpu) @@ -89,6 +93,8 @@ static void x2apic_send_IPI_allbutself(int vector) unsigned long query_cpu; unsigned long flags; + x2apic_wrmsr_fence(); + local_irq_save(flags); for_each_online_cpu(query_cpu) { if (query_cpu == this_cpu) diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index a654d59e448..821e97017e9 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -186,11 +186,6 @@ static void flush_tlb_others_ipi(const struct cpumask *cpumask, cpumask_andnot(to_cpumask(f->flush_cpumask), cpumask, cpumask_of(smp_processor_id())); - /* - * Make the above memory operations globally visible before - * sending the IPI. - */ - smp_mb(); /* * We have to send the IPI only to * CPUs affected. -- cgit v1.2.3-70-g09d2 From 71ff49d71bb5cfcd2689b54cb433c0e6990a1d86 Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Wed, 18 Mar 2009 13:03:33 -0700 Subject: x86: with the last user gone, remove set_pte_present Impact: cleanup set_pte_present() is no longer used, directly or indirectly, so remove it. Signed-off-by: Jeremy Fitzhardinge Cc: Xen-devel Cc: Jeremy Fitzhardinge Cc: Alok Kataria Cc: Marcelo Tosatti Cc: Avi Kivity LKML-Reference: <1237406613-2929-2-git-send-email-jeremy@goop.org> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/paravirt.h | 15 --------------- arch/x86/include/asm/pgtable-2level.h | 7 ------- arch/x86/include/asm/pgtable-3level.h | 17 ----------------- arch/x86/include/asm/pgtable.h | 2 -- arch/x86/kernel/kvm.c | 7 ------- arch/x86/kernel/paravirt.c | 1 - arch/x86/kernel/vmi_32.c | 6 ------ arch/x86/xen/mmu.c | 1 - 8 files changed, 56 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 31fe83b10a4..7727aa8b7dd 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -317,8 +317,6 @@ struct pv_mmu_ops { #if PAGETABLE_LEVELS >= 3 #ifdef CONFIG_X86_PAE void (*set_pte_atomic)(pte_t *ptep, pte_t pteval); - void (*set_pte_present)(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte); void (*pte_clear)(struct mm_struct *mm, unsigned long addr, pte_t *ptep); void (*pmd_clear)(pmd_t *pmdp); @@ -1365,13 +1363,6 @@ static inline void set_pte_atomic(pte_t *ptep, pte_t pte) pte.pte, pte.pte >> 32); } -static inline void set_pte_present(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte) -{ - /* 5 arg words */ - pv_mmu_ops.set_pte_present(mm, addr, ptep, pte); -} - static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { @@ -1388,12 +1379,6 @@ static inline void set_pte_atomic(pte_t *ptep, pte_t pte) set_pte(ptep, pte); } -static inline void set_pte_present(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte) -{ - set_pte(ptep, pte); -} - static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h index c1774ac9da7..2334982b339 100644 --- a/arch/x86/include/asm/pgtable-2level.h +++ b/arch/x86/include/asm/pgtable-2level.h @@ -26,13 +26,6 @@ static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte) native_set_pte(ptep, pte); } -static inline void native_set_pte_present(struct mm_struct *mm, - unsigned long addr, - pte_t *ptep, pte_t pte) -{ - native_set_pte(ptep, pte); -} - static inline void native_pmd_clear(pmd_t *pmdp) { native_set_pmd(pmdp, __pmd(0)); diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h index 3f13cdf6115..177b0165ea0 100644 --- a/arch/x86/include/asm/pgtable-3level.h +++ b/arch/x86/include/asm/pgtable-3level.h @@ -31,23 +31,6 @@ static inline void native_set_pte(pte_t *ptep, pte_t pte) ptep->pte_low = pte.pte_low; } -/* - * Since this is only called on user PTEs, and the page fault handler - * must handle the already racy situation of simultaneous page faults, - * we are justified in merely clearing the PTE present bit, followed - * by a set. The ordering here is important. - */ -static inline void native_set_pte_present(struct mm_struct *mm, - unsigned long addr, - pte_t *ptep, pte_t pte) -{ - ptep->pte_low = 0; - smp_wmb(); - ptep->pte_high = pte.pte_high; - smp_wmb(); - ptep->pte_low = pte.pte_low; -} - static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte) { set_64bit((unsigned long long *)(ptep), native_pte_val(pte)); diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index d0812e155f1..29d96d168bc 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -31,8 +31,6 @@ extern struct list_head pgd_list; #define set_pte(ptep, pte) native_set_pte(ptep, pte) #define set_pte_at(mm, addr, ptep, pte) native_set_pte_at(mm, addr, ptep, pte) -#define set_pte_present(mm, addr, ptep, pte) \ - native_set_pte_present(mm, addr, ptep, pte) #define set_pte_atomic(ptep, pte) \ native_set_pte_atomic(ptep, pte) diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 478bca986ec..33019ddb56b 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -138,12 +138,6 @@ static void kvm_set_pte_atomic(pte_t *ptep, pte_t pte) kvm_mmu_write(ptep, pte_val(pte)); } -static void kvm_set_pte_present(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte) -{ - kvm_mmu_write(ptep, pte_val(pte)); -} - static void kvm_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { @@ -220,7 +214,6 @@ static void paravirt_ops_setup(void) #if PAGETABLE_LEVELS >= 3 #ifdef CONFIG_X86_PAE pv_mmu_ops.set_pte_atomic = kvm_set_pte_atomic; - pv_mmu_ops.set_pte_present = kvm_set_pte_present; pv_mmu_ops.pte_clear = kvm_pte_clear; pv_mmu_ops.pmd_clear = kvm_pmd_clear; #endif diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 63dd358d8ee..8e45f446488 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -470,7 +470,6 @@ struct pv_mmu_ops pv_mmu_ops = { #if PAGETABLE_LEVELS >= 3 #ifdef CONFIG_X86_PAE .set_pte_atomic = native_set_pte_atomic, - .set_pte_present = native_set_pte_present, .pte_clear = native_pte_clear, .pmd_clear = native_pmd_clear, #endif diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c index 2cc4a90e2cb..95deb9f2211 100644 --- a/arch/x86/kernel/vmi_32.c +++ b/arch/x86/kernel/vmi_32.c @@ -395,11 +395,6 @@ static void vmi_set_pte_atomic(pte_t *ptep, pte_t pteval) vmi_ops.update_pte(ptep, VMI_PAGE_PT); } -static void vmi_set_pte_present(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) -{ - vmi_ops.set_pte(pte, ptep, vmi_flags_addr_defer(mm, addr, VMI_PAGE_PT, 1)); -} - static void vmi_set_pud(pud_t *pudp, pud_t pudval) { /* Um, eww */ @@ -750,7 +745,6 @@ static inline int __init activate_vmi(void) pv_mmu_ops.set_pmd = vmi_set_pmd; #ifdef CONFIG_X86_PAE pv_mmu_ops.set_pte_atomic = vmi_set_pte_atomic; - pv_mmu_ops.set_pte_present = vmi_set_pte_present; pv_mmu_ops.set_pud = vmi_set_pud; pv_mmu_ops.pte_clear = vmi_pte_clear; pv_mmu_ops.pmd_clear = vmi_pmd_clear; diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 72f6a76dbfb..db3802fb7b8 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1870,7 +1870,6 @@ const struct pv_mmu_ops xen_mmu_ops __initdata = { #ifdef CONFIG_X86_PAE .set_pte_atomic = xen_set_pte_atomic, - .set_pte_present = xen_set_pte_at, .pte_clear = xen_pte_clear, .pmd_clear = xen_pmd_clear, #endif /* CONFIG_X86_PAE */ -- cgit v1.2.3-70-g09d2 From 11df1f05514beaf0269484191007dbc8d47e0e6f Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Mon, 19 Jan 2009 11:31:00 +1100 Subject: PCI/MSI: Use #ifdefs instead of weak functions Weak functions aren't all they're cracked up to be. They lead to incorrect binaries with some toolchains, they require us to have empty functions we otherwise wouldn't, and the unused code is not elided (as of gcc 4.3.2 anyway). So replace the weak MSI arch hooks with the #define foo foo idiom. We no longer need empty versions of arch_setup/teardown_msi_irq(). This is less source (by 1 line!), and results in smaller binaries too: text data bss dec hex filename 9354300 1693916 678424 11726640 b2ef30 build/powerpc/vmlinux-before 9354052 1693852 678424 11726328 b2edf8 build/powerpc/vmlinux-after Also smaller on x86_64 and arm (iop13xx). Signed-off-by: Michael Ellerman Signed-off-by: Jesse Barnes --- arch/powerpc/include/asm/pci.h | 4 ++++ arch/x86/include/asm/pci.h | 3 +++ drivers/pci/msi.c | 26 +++++++++----------------- 3 files changed, 16 insertions(+), 17 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h index 3548159a1be..ba17d5d90a4 100644 --- a/arch/powerpc/include/asm/pci.h +++ b/arch/powerpc/include/asm/pci.h @@ -114,6 +114,10 @@ extern int pci_domain_nr(struct pci_bus *bus); /* Decide whether to display the domain number in /proc */ extern int pci_proc_domain(struct pci_bus *bus); +/* MSI arch hooks */ +#define arch_setup_msi_irqs arch_setup_msi_irqs +#define arch_teardown_msi_irqs arch_teardown_msi_irqs +#define arch_msi_check_device arch_msi_check_device struct vm_area_struct; /* Map a range of PCI memory or I/O space for a device into user space */ diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index a977de23cb4..a0301bfeb95 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -86,6 +86,9 @@ static inline void early_quirks(void) { } extern void pci_iommu_alloc(void); +/* MSI arch hook */ +#define arch_setup_msi_irqs arch_setup_msi_irqs + #endif /* __KERNEL__ */ #ifdef CONFIG_X86_32 diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 08aedd5875b..33adf323f06 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -27,20 +27,15 @@ static int pci_msi_enable = 1; /* Arch hooks */ -int __attribute__ ((weak)) -arch_msi_check_device(struct pci_dev *dev, int nvec, int type) +#ifndef arch_msi_check_device +int arch_msi_check_device(struct pci_dev *dev, int nvec, int type) { return 0; } +#endif -int __attribute__ ((weak)) -arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *entry) -{ - return 0; -} - -int __attribute__ ((weak)) -arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) +#ifndef arch_setup_msi_irqs +int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) { struct msi_desc *entry; int ret; @@ -53,14 +48,10 @@ arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) return 0; } +#endif -void __attribute__ ((weak)) arch_teardown_msi_irq(unsigned int irq) -{ - return; -} - -void __attribute__ ((weak)) -arch_teardown_msi_irqs(struct pci_dev *dev) +#ifndef arch_teardown_msi_irqs +void arch_teardown_msi_irqs(struct pci_dev *dev) { struct msi_desc *entry; @@ -69,6 +60,7 @@ arch_teardown_msi_irqs(struct pci_dev *dev) arch_teardown_msi_irq(entry->irq); } } +#endif static void __msi_set_enable(struct pci_dev *dev, int pos, int enable) { -- cgit v1.2.3-70-g09d2 From 0f3507555f6fa4acbc85a646d6e8766230db38fc Mon Sep 17 00:00:00 2001 From: "venkatesh.pallipadi@intel.com" Date: Thu, 19 Mar 2009 14:51:15 -0700 Subject: x86, CPA: Add set_pages_arrayuc and set_pages_array_wb Add new interfaces: set_pages_array_uc() set_pages_array_wb() that can be used change the page attribute for a bunch of pages with flush etc done once at the end of all the changes. These interfaces are similar to existing set_memory_array_uc() and set_memory_array_wc(). Signed-off-by: Venkatesh Pallipadi Cc: arjan@infradead.org Cc: eric@anholt.net Cc: airlied@redhat.com LKML-Reference: <20090319215358.901545000@intel.com> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/cacheflush.h | 3 ++ arch/x86/mm/pageattr.c | 63 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 66 insertions(+) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h index 5b301b7ff5f..b3894bf52fc 100644 --- a/arch/x86/include/asm/cacheflush.h +++ b/arch/x86/include/asm/cacheflush.h @@ -90,6 +90,9 @@ int set_memory_4k(unsigned long addr, int numpages); int set_memory_array_uc(unsigned long *addr, int addrinarray); int set_memory_array_wb(unsigned long *addr, int addrinarray); +int set_pages_array_uc(struct page **pages, int addrinarray); +int set_pages_array_wb(struct page **pages, int addrinarray); + /* * For legacy compatibility with the old APIs, a few functions * are provided that work on a "struct page". diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index e5c257fb41e..d71e1b636ce 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -920,6 +920,20 @@ static inline int change_page_attr_clear(unsigned long *addr, int numpages, (array ? CPA_ARRAY : 0), NULL); } +static inline int cpa_set_pages_array(struct page **pages, int numpages, + pgprot_t mask) +{ + return change_page_attr_set_clr(NULL, numpages, mask, __pgprot(0), 0, + CPA_PAGES_ARRAY, pages); +} + +static inline int cpa_clear_pages_array(struct page **pages, int numpages, + pgprot_t mask) +{ + return change_page_attr_set_clr(NULL, numpages, __pgprot(0), mask, 0, + CPA_PAGES_ARRAY, pages); +} + int _set_memory_uc(unsigned long addr, int numpages) { /* @@ -1076,6 +1090,35 @@ int set_pages_uc(struct page *page, int numpages) } EXPORT_SYMBOL(set_pages_uc); +int set_pages_array_uc(struct page **pages, int addrinarray) +{ + unsigned long start; + unsigned long end; + int i; + int free_idx; + + for (i = 0; i < addrinarray; i++) { + start = (unsigned long)page_address(pages[i]); + end = start + PAGE_SIZE; + if (reserve_memtype(start, end, _PAGE_CACHE_UC_MINUS, NULL)) + goto err_out; + } + + if (cpa_set_pages_array(pages, addrinarray, + __pgprot(_PAGE_CACHE_UC_MINUS)) == 0) { + return 0; /* Success */ + } +err_out: + free_idx = i; + for (i = 0; i < free_idx; i++) { + start = (unsigned long)page_address(pages[i]); + end = start + PAGE_SIZE; + free_memtype(start, end); + } + return -EINVAL; +} +EXPORT_SYMBOL(set_pages_array_uc); + int set_pages_wb(struct page *page, int numpages) { unsigned long addr = (unsigned long)page_address(page); @@ -1084,6 +1127,26 @@ int set_pages_wb(struct page *page, int numpages) } EXPORT_SYMBOL(set_pages_wb); +int set_pages_array_wb(struct page **pages, int addrinarray) +{ + int retval; + unsigned long start; + unsigned long end; + int i; + + retval = cpa_clear_pages_array(pages, addrinarray, + __pgprot(_PAGE_CACHE_MASK)); + + for (i = 0; i < addrinarray; i++) { + start = (unsigned long)page_address(pages[i]); + end = start + PAGE_SIZE; + free_memtype(start, end); + } + + return retval; +} +EXPORT_SYMBOL(set_pages_array_wb); + int set_pages_x(struct page *page, int numpages) { unsigned long addr = (unsigned long)page_address(page); -- cgit v1.2.3-70-g09d2 From ba639039d68cd978f4fa900a6533fe930609ed35 Mon Sep 17 00:00:00 2001 From: Jaswinder Singh Rajput Date: Mon, 23 Mar 2009 02:13:01 +0530 Subject: x86: e820 fix various signedness issues in setup.c and e820.c Impact: cleanup This fixed various signedness issues in setup.c and e820.c: arch/x86/kernel/setup.c:455:53: warning: incorrect type in argument 3 (different signedness) arch/x86/kernel/setup.c:455:53: expected int *pnr_map arch/x86/kernel/setup.c:455:53: got unsigned int extern [toplevel] * arch/x86/kernel/setup.c:639:53: warning: incorrect type in argument 3 (different signedness) arch/x86/kernel/setup.c:639:53: expected int *pnr_map arch/x86/kernel/setup.c:639:53: got unsigned int extern [toplevel] * arch/x86/kernel/setup.c:820:54: warning: incorrect type in argument 3 (different signedness) arch/x86/kernel/setup.c:820:54: expected int *pnr_map arch/x86/kernel/setup.c:820:54: got unsigned int extern [toplevel] * arch/x86/kernel/e820.c:670:53: warning: incorrect type in argument 3 (different signedness) arch/x86/kernel/e820.c:670:53: expected int *pnr_map arch/x86/kernel/e820.c:670:53: got unsigned int [toplevel] * Signed-off-by: Jaswinder Singh Rajput --- arch/x86/include/asm/e820.h | 2 +- arch/x86/kernel/e820.c | 10 +++++----- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h index 00d41ce4c84..7ecba4d8508 100644 --- a/arch/x86/include/asm/e820.h +++ b/arch/x86/include/asm/e820.h @@ -72,7 +72,7 @@ extern int e820_all_mapped(u64 start, u64 end, unsigned type); extern void e820_add_region(u64 start, u64 size, int type); extern void e820_print_map(char *who); extern int -sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, int *pnr_map); +sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, u32 *pnr_map); extern u64 e820_update_range(u64 start, u64 size, unsigned old_type, unsigned new_type); extern u64 e820_remove_range(u64 start, u64 size, unsigned old_type, diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index fb638d9ce6d..ef2c3563357 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -233,7 +233,7 @@ void __init e820_print_map(char *who) */ int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, - int *pnr_map) + u32 *pnr_map) { struct change_member { struct e820entry *pbios; /* pointer to original bios entry */ @@ -552,7 +552,7 @@ u64 __init e820_remove_range(u64 start, u64 size, unsigned old_type, void __init update_e820(void) { - int nr_map; + u32 nr_map; nr_map = e820.nr_map; if (sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &nr_map)) @@ -563,7 +563,7 @@ void __init update_e820(void) } static void __init update_e820_saved(void) { - int nr_map; + u32 nr_map; nr_map = e820_saved.nr_map; if (sanitize_e820_map(e820_saved.map, ARRAY_SIZE(e820_saved.map), &nr_map)) @@ -1303,7 +1303,7 @@ early_param("memmap", parse_memmap_opt); void __init finish_e820_parsing(void) { if (userdef) { - int nr = e820.nr_map; + u32 nr = e820.nr_map; if (sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &nr) < 0) early_panic("Invalid user supplied memory map"); @@ -1386,7 +1386,7 @@ void __init e820_reserve_resources_late(void) char *__init default_machine_specific_memory_setup(void) { char *who = "BIOS-e820"; - int new_nr; + u32 new_nr; /* * Try to copy the BIOS-supplied E820-map. * -- cgit v1.2.3-70-g09d2 From c8608d6b58981a58ca4aee8308576666c5f7ab0c Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Sun, 22 Mar 2009 14:48:44 -0700 Subject: x86/dmi: fix dmi_alloc() section mismatches Impact: section mismatch fix Ingo reports these warnings: > WARNING: vmlinux.o(.text+0x6a288e): Section mismatch in reference from > the function dmi_alloc() to the function .init.text:extend_brk() > The function dmi_alloc() references > the function __init extend_brk(). > This is often because dmi_alloc lacks a __init annotation or the > annotation of extend_brk is wrong. dmi_alloc() is a static inline, and so should be immune to this kind of error. But force it to be inlined and make it __init anyway, just to be extra sure. All of dmi_alloc()'s callers are already __init. Signed-off-by: Jeremy Fitzhardinge Cc: Yinghai Lu LKML-Reference: <49C6B23C.2040308@goop.org> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/dmi.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/dmi.h b/arch/x86/include/asm/dmi.h index aa32f7e6c19..fd8f9e2ca35 100644 --- a/arch/x86/include/asm/dmi.h +++ b/arch/x86/include/asm/dmi.h @@ -1,10 +1,13 @@ #ifndef _ASM_X86_DMI_H #define _ASM_X86_DMI_H +#include +#include + #include #include -static inline void *dmi_alloc(unsigned len) +static __always_inline __init void *dmi_alloc(unsigned len) { return extend_brk(len, sizeof(int)); } -- cgit v1.2.3-70-g09d2 From 9962d032bbff0268f22068787831405f8468c8b4 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Tue, 25 Nov 2008 20:17:02 +0100 Subject: KVM: SVM: Move EFER and MSR constants to generic x86 code MSR_EFER_SVME_MASK, MSR_VM_CR and MSR_VM_HSAVE_PA are set in KVM specific headers. Linux does have nice header files to collect EFER bits and MSR IDs, so IMHO we should put them there. While at it, I also changed the naming scheme to match that of the other defines. (introduced in v6) Acked-by: Joerg Roedel Signed-off-by: Alexander Graf Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/include/asm/msr-index.h | 7 +++++++ arch/x86/include/asm/svm.h | 4 ---- arch/x86/include/asm/virtext.h | 2 +- arch/x86/kvm/svm.c | 6 +++--- 5 files changed, 12 insertions(+), 8 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 730843d1d2f..2998efe8927 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -22,6 +22,7 @@ #include #include #include +#include #define KVM_MAX_VCPUS 16 #define KVM_MEMORY_SLOTS 32 diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 358acc59ae0..46e9646e7a6 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -18,11 +18,13 @@ #define _EFER_LME 8 /* Long mode enable */ #define _EFER_LMA 10 /* Long mode active (read-only) */ #define _EFER_NX 11 /* No execute enable */ +#define _EFER_SVME 12 /* Enable virtualization */ #define EFER_SCE (1<<_EFER_SCE) #define EFER_LME (1<<_EFER_LME) #define EFER_LMA (1<<_EFER_LMA) #define EFER_NX (1<<_EFER_NX) +#define EFER_SVME (1<<_EFER_SVME) /* Intel MSRs. Some also available on other CPUs */ #define MSR_IA32_PERFCTR0 0x000000c1 @@ -360,4 +362,9 @@ #define MSR_IA32_VMX_PROCBASED_CTLS2 0x0000048b #define MSR_IA32_VMX_EPT_VPID_CAP 0x0000048c +/* AMD-V MSRs */ + +#define MSR_VM_CR 0xc0010114 +#define MSR_VM_HSAVE_PA 0xc0010117 + #endif /* _ASM_X86_MSR_INDEX_H */ diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 1b8afa78e86..82ada75f3eb 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -174,10 +174,6 @@ struct __attribute__ ((__packed__)) vmcb { #define SVM_CPUID_FEATURE_SHIFT 2 #define SVM_CPUID_FUNC 0x8000000a -#define MSR_EFER_SVME_MASK (1ULL << 12) -#define MSR_VM_CR 0xc0010114 -#define MSR_VM_HSAVE_PA 0xc0010117ULL - #define SVM_VM_CR_SVM_DISABLE 4 #define SVM_SELECTOR_S_SHIFT 4 diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h index 59363627523..e0f9aa16358 100644 --- a/arch/x86/include/asm/virtext.h +++ b/arch/x86/include/asm/virtext.h @@ -118,7 +118,7 @@ static inline void cpu_svm_disable(void) wrmsrl(MSR_VM_HSAVE_PA, 0); rdmsrl(MSR_EFER, efer); - wrmsrl(MSR_EFER, efer & ~MSR_EFER_SVME_MASK); + wrmsrl(MSR_EFER, efer & ~EFER_SVME); } /** Makes sure SVM is disabled, if it is supported on the CPU diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 33407d95761..e4eb3fd91b9 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -198,7 +198,7 @@ static void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) if (!npt_enabled && !(efer & EFER_LMA)) efer &= ~EFER_LME; - to_svm(vcpu)->vmcb->save.efer = efer | MSR_EFER_SVME_MASK; + to_svm(vcpu)->vmcb->save.efer = efer | EFER_SVME; vcpu->arch.shadow_efer = efer; } @@ -292,7 +292,7 @@ static void svm_hardware_enable(void *garbage) svm_data->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS); rdmsrl(MSR_EFER, efer); - wrmsrl(MSR_EFER, efer | MSR_EFER_SVME_MASK); + wrmsrl(MSR_EFER, efer | EFER_SVME); wrmsrl(MSR_VM_HSAVE_PA, page_to_pfn(svm_data->save_area) << PAGE_SHIFT); @@ -559,7 +559,7 @@ static void init_vmcb(struct vcpu_svm *svm) init_sys_seg(&save->ldtr, SEG_TYPE_LDT); init_sys_seg(&save->tr, SEG_TYPE_BUSY_TSS16); - save->efer = MSR_EFER_SVME_MASK; + save->efer = EFER_SVME; save->dr6 = 0xffff0ff0; save->dr7 = 0x400; save->rflags = 2; -- cgit v1.2.3-70-g09d2 From 1371d90460189d02bf1bcca19dbfe6bd10dc6031 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Tue, 25 Nov 2008 20:17:04 +0100 Subject: KVM: SVM: Implement GIF, clgi and stgi This patch implements the GIF flag and the clgi and stgi instructions that set this flag. Only if the flag is set (default), interrupts can be received by the CPU. To keep the information about that somewhere, this patch adds a new hidden flags vector. that is used to store information that does not go into the vmcb, but is SVM specific. I tried to write some code to make -no-kvm-irqchip work too, but the first level guest won't even boot with that atm, so I ditched it. v2 moves the hflags to x86 generic code v3 makes use of the new permission helper v6 only enables interrupt_window if GIF=1 Acked-by: Joerg Roedel Signed-off-by: Alexander Graf Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm_host.h | 3 +++ arch/x86/kvm/svm.c | 47 ++++++++++++++++++++++++++++++++++++----- 2 files changed, 45 insertions(+), 5 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 2998efe8927..29e4157732d 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -259,6 +259,7 @@ struct kvm_vcpu_arch { unsigned long cr3; unsigned long cr4; unsigned long cr8; + u32 hflags; u64 pdptrs[4]; /* pae */ u64 shadow_efer; u64 apic_base; @@ -738,6 +739,8 @@ enum { TASK_SWITCH_GATE = 3, }; +#define HF_GIF_MASK (1 << 0) + /* * Hardware virtualization extension instructions may fault if a * reboot turns off virtualization while processes are running. diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 87debdcd1b9..79cc06bfe57 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -251,7 +251,7 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) kvm_rip_write(vcpu, svm->next_rip); svm->vmcb->control.int_state &= ~SVM_INTERRUPT_SHADOW_MASK; - vcpu->arch.interrupt_window_open = 1; + vcpu->arch.interrupt_window_open = (svm->vcpu.arch.hflags & HF_GIF_MASK); } static int has_svm(void) @@ -600,6 +600,8 @@ static void init_vmcb(struct vcpu_svm *svm) save->cr4 = 0; } force_new_asid(&svm->vcpu); + + svm->vcpu.arch.hflags = HF_GIF_MASK; } static int svm_vcpu_reset(struct kvm_vcpu *vcpu) @@ -1234,6 +1236,36 @@ static int nested_svm_do(struct vcpu_svm *svm, return retval; } +static int stgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + if (nested_svm_check_permissions(svm)) + return 1; + + svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; + skip_emulated_instruction(&svm->vcpu); + + svm->vcpu.arch.hflags |= HF_GIF_MASK; + + return 1; +} + +static int clgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + if (nested_svm_check_permissions(svm)) + return 1; + + svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; + skip_emulated_instruction(&svm->vcpu); + + svm->vcpu.arch.hflags &= ~HF_GIF_MASK; + + /* After a CLGI no interrupts should come */ + svm_clear_vintr(svm); + svm->vmcb->control.int_ctl &= ~V_IRQ_MASK; + + return 1; +} + static int invalid_op_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) { @@ -1535,8 +1567,8 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm, [SVM_EXIT_VMMCALL] = vmmcall_interception, [SVM_EXIT_VMLOAD] = invalid_op_interception, [SVM_EXIT_VMSAVE] = invalid_op_interception, - [SVM_EXIT_STGI] = invalid_op_interception, - [SVM_EXIT_CLGI] = invalid_op_interception, + [SVM_EXIT_STGI] = stgi_interception, + [SVM_EXIT_CLGI] = clgi_interception, [SVM_EXIT_SKINIT] = invalid_op_interception, [SVM_EXIT_WBINVD] = emulate_on_interception, [SVM_EXIT_MONITOR] = invalid_op_interception, @@ -1684,6 +1716,9 @@ static void svm_intr_assist(struct kvm_vcpu *vcpu) if (!kvm_cpu_has_interrupt(vcpu)) goto out; + if (!(svm->vcpu.arch.hflags & HF_GIF_MASK)) + goto out; + if (!(vmcb->save.rflags & X86_EFLAGS_IF) || (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) || (vmcb->control.event_inj & SVM_EVTINJ_VALID)) { @@ -1710,7 +1745,8 @@ static void kvm_reput_irq(struct vcpu_svm *svm) } svm->vcpu.arch.interrupt_window_open = - !(control->int_state & SVM_INTERRUPT_SHADOW_MASK); + !(control->int_state & SVM_INTERRUPT_SHADOW_MASK) && + (svm->vcpu.arch.hflags & HF_GIF_MASK); } static void svm_do_inject_vector(struct vcpu_svm *svm) @@ -1734,7 +1770,8 @@ static void do_interrupt_requests(struct kvm_vcpu *vcpu, svm->vcpu.arch.interrupt_window_open = (!(control->int_state & SVM_INTERRUPT_SHADOW_MASK) && - (svm->vmcb->save.rflags & X86_EFLAGS_IF)); + (svm->vmcb->save.rflags & X86_EFLAGS_IF) && + (svm->vcpu.arch.hflags & HF_GIF_MASK)); if (svm->vcpu.arch.interrupt_window_open && svm->vcpu.arch.irq_summary) /* -- cgit v1.2.3-70-g09d2 From 3d6368ef580a4dff012960834bba4e28d3c1430c Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Tue, 25 Nov 2008 20:17:07 +0100 Subject: KVM: SVM: Add VMRUN handler This patch implements VMRUN. VMRUN enters a virtual CPU and runs that in the same context as the normal guest CPU would run. So basically it is implemented the same way, a normal CPU would do it. We also prepare all intercepts that get OR'ed with the original intercepts, as we do not allow a level 2 guest to be intercepted less than the first level guest. v2 implements the following improvements: - fixes the CPL check - does not allocate iopm when not used - remembers the host's IF in the HIF bit in the hflags v3: - make use of the new permission checking - add support for V_INTR_MASKING_MASK v4: - use host page backed hsave v5: - remove IOPM merging code v6: - save cr4 so PAE l1 guests work v7: - return 0 on vmrun so we check the MSRs too - fix MSR check to use the correct variable Acked-by: Joerg Roedel Signed-off-by: Alexander Graf Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm_host.h | 2 + arch/x86/kvm/kvm_svm.h | 8 ++ arch/x86/kvm/svm.c | 157 +++++++++++++++++++++++++++++++++++++++- 3 files changed, 165 insertions(+), 2 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 29e4157732d..53779309514 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -740,6 +740,8 @@ enum { }; #define HF_GIF_MASK (1 << 0) +#define HF_HIF_MASK (1 << 1) +#define HF_VINTR_MASK (1 << 2) /* * Hardware virtualization extension instructions may fault if a diff --git a/arch/x86/kvm/kvm_svm.h b/arch/x86/kvm/kvm_svm.h index a0877cac7b9..91673413d8f 100644 --- a/arch/x86/kvm/kvm_svm.h +++ b/arch/x86/kvm/kvm_svm.h @@ -43,6 +43,14 @@ struct vcpu_svm { u32 *msrpm; struct vmcb *hsave; u64 hsave_msr; + + u64 nested_vmcb; + + /* These are the merged vectors */ + u32 *nested_msrpm; + + /* gpa pointers to the real vectors */ + u64 nested_vmcb_msrpm; }; #endif diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index a83c94eb577..fad187cbfab 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -77,6 +77,11 @@ static inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu) return container_of(vcpu, struct vcpu_svm, vcpu); } +static inline bool is_nested(struct vcpu_svm *svm) +{ + return svm->nested_vmcb; +} + static unsigned long iopm_base; struct kvm_ldttss_desc { @@ -601,6 +606,7 @@ static void init_vmcb(struct vcpu_svm *svm) } force_new_asid(&svm->vcpu); + svm->nested_vmcb = 0; svm->vcpu.arch.hflags = HF_GIF_MASK; } @@ -627,6 +633,7 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) struct page *page; struct page *msrpm_pages; struct page *hsave_page; + struct page *nested_msrpm_pages; int err; svm = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); @@ -649,6 +656,11 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER); if (!msrpm_pages) goto uninit; + + nested_msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER); + if (!nested_msrpm_pages) + goto uninit; + svm->msrpm = page_address(msrpm_pages); svm_vcpu_init_msrpm(svm->msrpm); @@ -657,6 +669,8 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) goto uninit; svm->hsave = page_address(hsave_page); + svm->nested_msrpm = page_address(nested_msrpm_pages); + svm->vmcb = page_address(page); clear_page(svm->vmcb); svm->vmcb_pa = page_to_pfn(page) << PAGE_SHIFT; @@ -687,6 +701,7 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu) __free_page(pfn_to_page(svm->vmcb_pa >> PAGE_SHIFT)); __free_pages(virt_to_page(svm->msrpm), MSRPM_ALLOC_ORDER); __free_page(virt_to_page(svm->hsave)); + __free_pages(virt_to_page(svm->nested_msrpm), MSRPM_ALLOC_ORDER); kvm_vcpu_uninit(vcpu); kmem_cache_free(kvm_vcpu_cache, svm); } @@ -1243,6 +1258,123 @@ static int nested_svm_do(struct vcpu_svm *svm, return retval; } + +static int nested_svm_vmrun_msrpm(struct vcpu_svm *svm, void *arg1, + void *arg2, void *opaque) +{ + int i; + u32 *nested_msrpm = (u32*)arg1; + for (i=0; i< PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER) / 4; i++) + svm->nested_msrpm[i] = svm->msrpm[i] | nested_msrpm[i]; + svm->vmcb->control.msrpm_base_pa = __pa(svm->nested_msrpm); + + return 0; +} + +static int nested_svm_vmrun(struct vcpu_svm *svm, void *arg1, + void *arg2, void *opaque) +{ + struct vmcb *nested_vmcb = (struct vmcb *)arg1; + struct vmcb *hsave = svm->hsave; + + /* nested_vmcb is our indicator if nested SVM is activated */ + svm->nested_vmcb = svm->vmcb->save.rax; + + /* Clear internal status */ + svm->vcpu.arch.exception.pending = false; + + /* Save the old vmcb, so we don't need to pick what we save, but + can restore everything when a VMEXIT occurs */ + memcpy(hsave, svm->vmcb, sizeof(struct vmcb)); + /* We need to remember the original CR3 in the SPT case */ + if (!npt_enabled) + hsave->save.cr3 = svm->vcpu.arch.cr3; + hsave->save.cr4 = svm->vcpu.arch.cr4; + hsave->save.rip = svm->next_rip; + + if (svm->vmcb->save.rflags & X86_EFLAGS_IF) + svm->vcpu.arch.hflags |= HF_HIF_MASK; + else + svm->vcpu.arch.hflags &= ~HF_HIF_MASK; + + /* Load the nested guest state */ + svm->vmcb->save.es = nested_vmcb->save.es; + svm->vmcb->save.cs = nested_vmcb->save.cs; + svm->vmcb->save.ss = nested_vmcb->save.ss; + svm->vmcb->save.ds = nested_vmcb->save.ds; + svm->vmcb->save.gdtr = nested_vmcb->save.gdtr; + svm->vmcb->save.idtr = nested_vmcb->save.idtr; + svm->vmcb->save.rflags = nested_vmcb->save.rflags; + svm_set_efer(&svm->vcpu, nested_vmcb->save.efer); + svm_set_cr0(&svm->vcpu, nested_vmcb->save.cr0); + svm_set_cr4(&svm->vcpu, nested_vmcb->save.cr4); + if (npt_enabled) { + svm->vmcb->save.cr3 = nested_vmcb->save.cr3; + svm->vcpu.arch.cr3 = nested_vmcb->save.cr3; + } else { + kvm_set_cr3(&svm->vcpu, nested_vmcb->save.cr3); + kvm_mmu_reset_context(&svm->vcpu); + } + svm->vmcb->save.cr2 = nested_vmcb->save.cr2; + kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, nested_vmcb->save.rax); + kvm_register_write(&svm->vcpu, VCPU_REGS_RSP, nested_vmcb->save.rsp); + kvm_register_write(&svm->vcpu, VCPU_REGS_RIP, nested_vmcb->save.rip); + /* In case we don't even reach vcpu_run, the fields are not updated */ + svm->vmcb->save.rax = nested_vmcb->save.rax; + svm->vmcb->save.rsp = nested_vmcb->save.rsp; + svm->vmcb->save.rip = nested_vmcb->save.rip; + svm->vmcb->save.dr7 = nested_vmcb->save.dr7; + svm->vmcb->save.dr6 = nested_vmcb->save.dr6; + svm->vmcb->save.cpl = nested_vmcb->save.cpl; + + /* We don't want a nested guest to be more powerful than the guest, + so all intercepts are ORed */ + svm->vmcb->control.intercept_cr_read |= + nested_vmcb->control.intercept_cr_read; + svm->vmcb->control.intercept_cr_write |= + nested_vmcb->control.intercept_cr_write; + svm->vmcb->control.intercept_dr_read |= + nested_vmcb->control.intercept_dr_read; + svm->vmcb->control.intercept_dr_write |= + nested_vmcb->control.intercept_dr_write; + svm->vmcb->control.intercept_exceptions |= + nested_vmcb->control.intercept_exceptions; + + svm->vmcb->control.intercept |= nested_vmcb->control.intercept; + + svm->nested_vmcb_msrpm = nested_vmcb->control.msrpm_base_pa; + + force_new_asid(&svm->vcpu); + svm->vmcb->control.exit_int_info = nested_vmcb->control.exit_int_info; + svm->vmcb->control.exit_int_info_err = nested_vmcb->control.exit_int_info_err; + svm->vmcb->control.int_ctl = nested_vmcb->control.int_ctl | V_INTR_MASKING_MASK; + if (nested_vmcb->control.int_ctl & V_IRQ_MASK) { + nsvm_printk("nSVM Injecting Interrupt: 0x%x\n", + nested_vmcb->control.int_ctl); + } + if (nested_vmcb->control.int_ctl & V_INTR_MASKING_MASK) + svm->vcpu.arch.hflags |= HF_VINTR_MASK; + else + svm->vcpu.arch.hflags &= ~HF_VINTR_MASK; + + nsvm_printk("nSVM exit_int_info: 0x%x | int_state: 0x%x\n", + nested_vmcb->control.exit_int_info, + nested_vmcb->control.int_state); + + svm->vmcb->control.int_vector = nested_vmcb->control.int_vector; + svm->vmcb->control.int_state = nested_vmcb->control.int_state; + svm->vmcb->control.tsc_offset += nested_vmcb->control.tsc_offset; + if (nested_vmcb->control.event_inj & SVM_EVTINJ_VALID) + nsvm_printk("Injecting Event: 0x%x\n", + nested_vmcb->control.event_inj); + svm->vmcb->control.event_inj = nested_vmcb->control.event_inj; + svm->vmcb->control.event_inj_err = nested_vmcb->control.event_inj_err; + + svm->vcpu.arch.hflags |= HF_GIF_MASK; + + return 0; +} + static int nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb) { to_vmcb->save.fs = from_vmcb->save.fs; @@ -1299,6 +1431,26 @@ static int vmsave_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 1; } +static int vmrun_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + nsvm_printk("VMrun\n"); + if (nested_svm_check_permissions(svm)) + return 1; + + svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; + skip_emulated_instruction(&svm->vcpu); + + if (nested_svm_do(svm, svm->vmcb->save.rax, 0, + NULL, nested_svm_vmrun)) + return 1; + + if (nested_svm_do(svm, svm->nested_vmcb_msrpm, 0, + NULL, nested_svm_vmrun_msrpm)) + return 1; + + return 1; +} + static int stgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) { if (nested_svm_check_permissions(svm)) @@ -1632,7 +1784,7 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm, [SVM_EXIT_MSR] = msr_interception, [SVM_EXIT_TASK_SWITCH] = task_switch_interception, [SVM_EXIT_SHUTDOWN] = shutdown_interception, - [SVM_EXIT_VMRUN] = invalid_op_interception, + [SVM_EXIT_VMRUN] = vmrun_interception, [SVM_EXIT_VMMCALL] = vmmcall_interception, [SVM_EXIT_VMLOAD] = vmload_interception, [SVM_EXIT_VMSAVE] = vmsave_interception, @@ -1939,7 +2091,8 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) svm->host_cr2 = kvm_read_cr2(); svm->host_dr6 = read_dr6(); svm->host_dr7 = read_dr7(); - svm->vmcb->save.cr2 = vcpu->arch.cr2; + if (!is_nested(svm)) + svm->vmcb->save.cr2 = vcpu->arch.cr2; /* required for live migration with NPT */ if (npt_enabled) svm->vmcb->save.cr3 = vcpu->arch.cr3; -- cgit v1.2.3-70-g09d2 From 8ab2d2e231062814bd89bba2d6d92563190aa2bb Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Mon, 15 Dec 2008 13:52:10 +0100 Subject: KVM: VMX: Support for injecting software exceptions VMX differentiates between processor and software generated exceptions when injecting them into the guest. Extend vmx_queue_exception accordingly (and refactor related constants) so that we can use this service reliably for the new guest debugging framework. Signed-off-by: Jan Kiszka Signed-off-by: Avi Kivity --- arch/x86/include/asm/vmx.h | 3 ++- arch/x86/kvm/vmx.c | 35 ++++++++++++++++++++--------------- 2 files changed, 22 insertions(+), 16 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index d0238e6151d..32159f034ef 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -270,8 +270,9 @@ enum vmcs_field { #define INTR_TYPE_EXT_INTR (0 << 8) /* external interrupt */ #define INTR_TYPE_NMI_INTR (2 << 8) /* NMI */ -#define INTR_TYPE_EXCEPTION (3 << 8) /* processor exception */ +#define INTR_TYPE_HARD_EXCEPTION (3 << 8) /* processor exception */ #define INTR_TYPE_SOFT_INTR (4 << 8) /* software interrupt */ +#define INTR_TYPE_SOFT_EXCEPTION (6 << 8) /* software exception */ /* GUEST_INTERRUPTIBILITY_INFO flags. */ #define GUEST_INTR_STATE_STI 0x00000001 diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 7611af57682..1d974c1eaa7 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -189,21 +189,21 @@ static inline int is_page_fault(u32 intr_info) { return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | INTR_INFO_VALID_MASK)) == - (INTR_TYPE_EXCEPTION | PF_VECTOR | INTR_INFO_VALID_MASK); + (INTR_TYPE_HARD_EXCEPTION | PF_VECTOR | INTR_INFO_VALID_MASK); } static inline int is_no_device(u32 intr_info) { return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | INTR_INFO_VALID_MASK)) == - (INTR_TYPE_EXCEPTION | NM_VECTOR | INTR_INFO_VALID_MASK); + (INTR_TYPE_HARD_EXCEPTION | NM_VECTOR | INTR_INFO_VALID_MASK); } static inline int is_invalid_opcode(u32 intr_info) { return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | INTR_INFO_VALID_MASK)) == - (INTR_TYPE_EXCEPTION | UD_VECTOR | INTR_INFO_VALID_MASK); + (INTR_TYPE_HARD_EXCEPTION | UD_VECTOR | INTR_INFO_VALID_MASK); } static inline int is_external_interrupt(u32 intr_info) @@ -747,29 +747,33 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, bool has_error_code, u32 error_code) { struct vcpu_vmx *vmx = to_vmx(vcpu); + u32 intr_info = nr | INTR_INFO_VALID_MASK; - if (has_error_code) + if (has_error_code) { vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code); + intr_info |= INTR_INFO_DELIVER_CODE_MASK; + } if (vcpu->arch.rmode.active) { vmx->rmode.irq.pending = true; vmx->rmode.irq.vector = nr; vmx->rmode.irq.rip = kvm_rip_read(vcpu); - if (nr == BP_VECTOR) + if (nr == BP_VECTOR || nr == OF_VECTOR) vmx->rmode.irq.rip++; - vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, - nr | INTR_TYPE_SOFT_INTR - | (has_error_code ? INTR_INFO_DELIVER_CODE_MASK : 0) - | INTR_INFO_VALID_MASK); + intr_info |= INTR_TYPE_SOFT_INTR; + vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr_info); vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, 1); kvm_rip_write(vcpu, vmx->rmode.irq.rip - 1); return; } - vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, - nr | INTR_TYPE_EXCEPTION - | (has_error_code ? INTR_INFO_DELIVER_CODE_MASK : 0) - | INTR_INFO_VALID_MASK); + if (nr == BP_VECTOR || nr == OF_VECTOR) { + vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, 1); + intr_info |= INTR_TYPE_SOFT_EXCEPTION; + } else + intr_info |= INTR_TYPE_HARD_EXCEPTION; + + vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr_info); } static bool vmx_exception_injected(struct kvm_vcpu *vcpu) @@ -2650,7 +2654,7 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } if ((intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK)) == - (INTR_TYPE_EXCEPTION | 1)) { + (INTR_TYPE_HARD_EXCEPTION | 1)) { kvm_run->exit_reason = KVM_EXIT_DEBUG; return 0; } @@ -3238,7 +3242,8 @@ static void vmx_complete_interrupts(struct vcpu_vmx *vmx) vmx->vcpu.arch.nmi_injected = false; } kvm_clear_exception_queue(&vmx->vcpu); - if (idtv_info_valid && type == INTR_TYPE_EXCEPTION) { + if (idtv_info_valid && (type == INTR_TYPE_HARD_EXCEPTION || + type == INTR_TYPE_SOFT_EXCEPTION)) { if (idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK) { error = vmcs_read32(IDT_VECTORING_ERROR_CODE); kvm_queue_exception_e(&vmx->vcpu, vector, error); -- cgit v1.2.3-70-g09d2 From d0bfb940ecabf0b44fb1fd80d8d60594e569e5ec Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Mon, 15 Dec 2008 13:52:10 +0100 Subject: KVM: New guest debug interface This rips out the support for KVM_DEBUG_GUEST and introduces a new IOCTL instead: KVM_SET_GUEST_DEBUG. The IOCTL payload consists of a generic part, controlling the "main switch" and the single-step feature. The arch specific part adds an x86 interface for intercepting both types of debug exceptions separately and re-injecting them when the host was not interested. Moveover, the foundation for guest debugging via debug registers is layed. To signal breakpoint events properly back to userland, an arch-specific data block is now returned along KVM_EXIT_DEBUG. For x86, the arch block contains the PC, the debug exception, and relevant debug registers to tell debug events properly apart. The availability of this new interface is signaled by KVM_CAP_SET_GUEST_DEBUG. Empty stubs for not yet supported archs are provided. Note that both SVM and VTX are supported, but only the latter was tested yet. Based on the experience with all those VTX corner case, I would be fairly surprised if SVM will work out of the box. Signed-off-by: Jan Kiszka Signed-off-by: Avi Kivity --- arch/ia64/include/asm/kvm.h | 7 ++++ arch/ia64/kvm/kvm-ia64.c | 4 +- arch/powerpc/include/asm/kvm.h | 7 ++++ arch/powerpc/kvm/powerpc.c | 4 +- arch/s390/include/asm/kvm.h | 7 ++++ arch/s390/kvm/kvm-s390.c | 4 +- arch/x86/include/asm/kvm.h | 18 ++++++++ arch/x86/include/asm/kvm_host.h | 9 +--- arch/x86/kvm/svm.c | 50 +++++++++++++++++++++- arch/x86/kvm/vmx.c | 93 ++++++++++++++++------------------------- arch/x86/kvm/x86.c | 14 ++++--- include/linux/kvm.h | 51 +++++++++++++++------- include/linux/kvm_host.h | 6 +-- virt/kvm/kvm_main.c | 6 +-- 14 files changed, 179 insertions(+), 101 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/ia64/include/asm/kvm.h b/arch/ia64/include/asm/kvm.h index bfa86b6af7c..be3fdb89121 100644 --- a/arch/ia64/include/asm/kvm.h +++ b/arch/ia64/include/asm/kvm.h @@ -214,4 +214,11 @@ struct kvm_sregs { struct kvm_fpu { }; +struct kvm_debug_exit_arch { +}; + +/* for KVM_SET_GUEST_DEBUG */ +struct kvm_guest_debug_arch { +}; + #endif diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index 28f982045f2..de47467a0e6 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -1303,8 +1303,8 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) return -EINVAL; } -int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu, - struct kvm_debug_guest *dbg) +int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, + struct kvm_guest_debug *dbg) { return -EINVAL; } diff --git a/arch/powerpc/include/asm/kvm.h b/arch/powerpc/include/asm/kvm.h index f993e4198d5..755f1b1948c 100644 --- a/arch/powerpc/include/asm/kvm.h +++ b/arch/powerpc/include/asm/kvm.h @@ -52,4 +52,11 @@ struct kvm_fpu { __u64 fpr[32]; }; +struct kvm_debug_exit_arch { +}; + +/* for KVM_SET_GUEST_DEBUG */ +struct kvm_guest_debug_arch { +}; + #endif /* __LINUX_KVM_POWERPC_H */ diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 5f81256287f..7c2ad4017d6 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -240,8 +240,8 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) kvmppc_core_vcpu_put(vcpu); } -int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu, - struct kvm_debug_guest *dbg) +int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, + struct kvm_guest_debug *dbg) { int i; diff --git a/arch/s390/include/asm/kvm.h b/arch/s390/include/asm/kvm.h index e1f54654e3a..0b2f829f6d5 100644 --- a/arch/s390/include/asm/kvm.h +++ b/arch/s390/include/asm/kvm.h @@ -42,4 +42,11 @@ struct kvm_fpu { __u64 fprs[16]; }; +struct kvm_debug_exit_arch { +}; + +/* for KVM_SET_GUEST_DEBUG */ +struct kvm_guest_debug_arch { +}; + #endif diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 0d33893e1e8..cbfe91e1012 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -422,8 +422,8 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, return -EINVAL; /* not implemented yet */ } -int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu, - struct kvm_debug_guest *dbg) +int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, + struct kvm_guest_debug *dbg) { return -EINVAL; /* not implemented yet */ } diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h index 886c9402ec4..32eb96c7ca2 100644 --- a/arch/x86/include/asm/kvm.h +++ b/arch/x86/include/asm/kvm.h @@ -212,6 +212,24 @@ struct kvm_pit_channel_state { __s64 count_load_time; }; +struct kvm_debug_exit_arch { + __u32 exception; + __u32 pad; + __u64 pc; + __u64 dr6; + __u64 dr7; +}; + +#define KVM_GUESTDBG_USE_SW_BP 0x00010000 +#define KVM_GUESTDBG_USE_HW_BP 0x00020000 +#define KVM_GUESTDBG_INJECT_DB 0x00040000 +#define KVM_GUESTDBG_INJECT_BP 0x00080000 + +/* for KVM_SET_GUEST_DEBUG */ +struct kvm_guest_debug_arch { + __u64 debugreg[8]; +}; + struct kvm_pit_state { struct kvm_pit_channel_state channels[3]; }; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 53779309514..c430cd580ee 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -135,12 +135,6 @@ enum { #define KVM_NR_MEM_OBJS 40 -struct kvm_guest_debug { - int enabled; - unsigned long bp[4]; - int singlestep; -}; - /* * We don't want allocation failures within the mmu code, so we preallocate * enough memory for a single page fault in a cache. @@ -448,8 +442,7 @@ struct kvm_x86_ops { void (*vcpu_put)(struct kvm_vcpu *vcpu); int (*set_guest_debug)(struct kvm_vcpu *vcpu, - struct kvm_debug_guest *dbg); - void (*guest_debug_pre)(struct kvm_vcpu *vcpu); + struct kvm_guest_debug *dbg); int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata); int (*set_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 data); u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 0fbbde54eca..88d9062f454 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -968,9 +968,32 @@ static void svm_set_segment(struct kvm_vcpu *vcpu, } -static int svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_debug_guest *dbg) +static int svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) { - return -EOPNOTSUPP; + int old_debug = vcpu->guest_debug; + struct vcpu_svm *svm = to_svm(vcpu); + + vcpu->guest_debug = dbg->control; + + svm->vmcb->control.intercept_exceptions &= + ~((1 << DB_VECTOR) | (1 << BP_VECTOR)); + if (vcpu->guest_debug & KVM_GUESTDBG_ENABLE) { + if (vcpu->guest_debug & + (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) + svm->vmcb->control.intercept_exceptions |= + 1 << DB_VECTOR; + if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) + svm->vmcb->control.intercept_exceptions |= + 1 << BP_VECTOR; + } else + vcpu->guest_debug = 0; + + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) + svm->vmcb->save.rflags |= X86_EFLAGS_TF | X86_EFLAGS_RF; + else if (old_debug & KVM_GUESTDBG_SINGLESTEP) + svm->vmcb->save.rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); + + return 0; } static int svm_get_irq(struct kvm_vcpu *vcpu) @@ -1094,6 +1117,27 @@ static int pf_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return kvm_mmu_page_fault(&svm->vcpu, fault_address, error_code); } +static int db_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + if (!(svm->vcpu.guest_debug & + (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) { + kvm_queue_exception(&svm->vcpu, DB_VECTOR); + return 1; + } + kvm_run->exit_reason = KVM_EXIT_DEBUG; + kvm_run->debug.arch.pc = svm->vmcb->save.cs.base + svm->vmcb->save.rip; + kvm_run->debug.arch.exception = DB_VECTOR; + return 0; +} + +static int bp_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + kvm_run->exit_reason = KVM_EXIT_DEBUG; + kvm_run->debug.arch.pc = svm->vmcb->save.cs.base + svm->vmcb->save.rip; + kvm_run->debug.arch.exception = BP_VECTOR; + return 0; +} + static int ud_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) { int er; @@ -2050,6 +2094,8 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm, [SVM_EXIT_WRITE_DR3] = emulate_on_interception, [SVM_EXIT_WRITE_DR5] = emulate_on_interception, [SVM_EXIT_WRITE_DR7] = emulate_on_interception, + [SVM_EXIT_EXCP_BASE + DB_VECTOR] = db_interception, + [SVM_EXIT_EXCP_BASE + BP_VECTOR] = bp_interception, [SVM_EXIT_EXCP_BASE + UD_VECTOR] = ud_interception, [SVM_EXIT_EXCP_BASE + PF_VECTOR] = pf_interception, [SVM_EXIT_EXCP_BASE + NM_VECTOR] = nm_interception, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 1d974c1eaa7..f55690ddb3a 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -480,8 +480,13 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) eb = (1u << PF_VECTOR) | (1u << UD_VECTOR); if (!vcpu->fpu_active) eb |= 1u << NM_VECTOR; - if (vcpu->guest_debug.enabled) - eb |= 1u << DB_VECTOR; + if (vcpu->guest_debug & KVM_GUESTDBG_ENABLE) { + if (vcpu->guest_debug & + (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) + eb |= 1u << DB_VECTOR; + if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) + eb |= 1u << BP_VECTOR; + } if (vcpu->arch.rmode.active) eb = ~0; if (vm_need_ept()) @@ -1003,40 +1008,23 @@ static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) } } -static int set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_debug_guest *dbg) +static int set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) { - unsigned long dr7 = 0x400; - int old_singlestep; - - old_singlestep = vcpu->guest_debug.singlestep; - - vcpu->guest_debug.enabled = dbg->enabled; - if (vcpu->guest_debug.enabled) { - int i; - - dr7 |= 0x200; /* exact */ - for (i = 0; i < 4; ++i) { - if (!dbg->breakpoints[i].enabled) - continue; - vcpu->guest_debug.bp[i] = dbg->breakpoints[i].address; - dr7 |= 2 << (i*2); /* global enable */ - dr7 |= 0 << (i*4+16); /* execution breakpoint */ - } - - vcpu->guest_debug.singlestep = dbg->singlestep; - } else - vcpu->guest_debug.singlestep = 0; + int old_debug = vcpu->guest_debug; + unsigned long flags; - if (old_singlestep && !vcpu->guest_debug.singlestep) { - unsigned long flags; + vcpu->guest_debug = dbg->control; + if (!(vcpu->guest_debug & KVM_GUESTDBG_ENABLE)) + vcpu->guest_debug = 0; - flags = vmcs_readl(GUEST_RFLAGS); + flags = vmcs_readl(GUEST_RFLAGS); + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) + flags |= X86_EFLAGS_TF | X86_EFLAGS_RF; + else if (old_debug & KVM_GUESTDBG_SINGLESTEP) flags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); - vmcs_writel(GUEST_RFLAGS, flags); - } + vmcs_writel(GUEST_RFLAGS, flags); update_exception_bitmap(vcpu); - vmcs_writel(GUEST_DR7, dr7); return 0; } @@ -2540,24 +2528,6 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) return 0; } -static void kvm_guest_debug_pre(struct kvm_vcpu *vcpu) -{ - struct kvm_guest_debug *dbg = &vcpu->guest_debug; - - set_debugreg(dbg->bp[0], 0); - set_debugreg(dbg->bp[1], 1); - set_debugreg(dbg->bp[2], 2); - set_debugreg(dbg->bp[3], 3); - - if (dbg->singlestep) { - unsigned long flags; - - flags = vmcs_readl(GUEST_RFLAGS); - flags |= X86_EFLAGS_TF | X86_EFLAGS_RF; - vmcs_writel(GUEST_RFLAGS, flags); - } -} - static int handle_rmode_exception(struct kvm_vcpu *vcpu, int vec, u32 err_code) { @@ -2574,9 +2544,17 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu, * the required debugging infrastructure rework. */ switch (vec) { - case DE_VECTOR: case DB_VECTOR: + if (vcpu->guest_debug & + (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) + return 0; + kvm_queue_exception(vcpu, vec); + return 1; case BP_VECTOR: + if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) + return 0; + /* fall through */ + case DE_VECTOR: case OF_VECTOR: case BR_VECTOR: case UD_VECTOR: @@ -2593,7 +2571,7 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu, static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { struct vcpu_vmx *vmx = to_vmx(vcpu); - u32 intr_info, error_code; + u32 intr_info, ex_no, error_code; unsigned long cr2, rip; u32 vect_info; enum emulation_result er; @@ -2653,14 +2631,16 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; } - if ((intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK)) == - (INTR_TYPE_HARD_EXCEPTION | 1)) { + ex_no = intr_info & INTR_INFO_VECTOR_MASK; + if (ex_no == DB_VECTOR || ex_no == BP_VECTOR) { kvm_run->exit_reason = KVM_EXIT_DEBUG; - return 0; + kvm_run->debug.arch.pc = vmcs_readl(GUEST_CS_BASE) + rip; + kvm_run->debug.arch.exception = ex_no; + } else { + kvm_run->exit_reason = KVM_EXIT_EXCEPTION; + kvm_run->ex.exception = ex_no; + kvm_run->ex.error_code = error_code; } - kvm_run->exit_reason = KVM_EXIT_EXCEPTION; - kvm_run->ex.exception = intr_info & INTR_INFO_VECTOR_MASK; - kvm_run->ex.error_code = error_code; return 0; } @@ -3600,7 +3580,6 @@ static struct kvm_x86_ops vmx_x86_ops = { .vcpu_put = vmx_vcpu_put, .set_guest_debug = set_guest_debug, - .guest_debug_pre = kvm_guest_debug_pre, .get_msr = vmx_get_msr, .set_msr = vmx_set_msr, .get_segment_base = vmx_get_segment_base, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index b5e9932e0f6..e990d164b56 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3005,9 +3005,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) goto out; } - if (vcpu->guest_debug.enabled) - kvm_x86_ops->guest_debug_pre(vcpu); - vcpu->guest_mode = 1; /* * Make sure that guest_mode assignment won't happen after @@ -3218,7 +3215,7 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) /* * Don't leak debug flags in case they were set for guest debugging */ - if (vcpu->guest_debug.enabled && vcpu->guest_debug.singlestep) + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) regs->rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); vcpu_put(vcpu); @@ -3837,8 +3834,8 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, return 0; } -int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu, - struct kvm_debug_guest *dbg) +int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, + struct kvm_guest_debug *dbg) { int r; @@ -3846,6 +3843,11 @@ int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu, r = kvm_x86_ops->set_guest_debug(vcpu, dbg); + if (dbg->control & KVM_GUESTDBG_INJECT_DB) + kvm_queue_exception(vcpu, DB_VECTOR); + else if (dbg->control & KVM_GUESTDBG_INJECT_BP) + kvm_queue_exception(vcpu, BP_VECTOR); + vcpu_put(vcpu); return r; diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 0424326f167..429a2ce202f 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -126,6 +126,7 @@ struct kvm_run { __u64 data_offset; /* relative to kvm_run start */ } io; struct { + struct kvm_debug_exit_arch arch; } debug; /* KVM_EXIT_MMIO */ struct { @@ -217,21 +218,6 @@ struct kvm_interrupt { __u32 irq; }; -struct kvm_breakpoint { - __u32 enabled; - __u32 padding; - __u64 address; -}; - -/* for KVM_DEBUG_GUEST */ -struct kvm_debug_guest { - /* int */ - __u32 enabled; - __u32 pad; - struct kvm_breakpoint breakpoints[4]; - __u32 singlestep; -}; - /* for KVM_GET_DIRTY_LOG */ struct kvm_dirty_log { __u32 slot; @@ -292,6 +278,17 @@ struct kvm_s390_interrupt { __u64 parm64; }; +/* for KVM_SET_GUEST_DEBUG */ + +#define KVM_GUESTDBG_ENABLE 0x00000001 +#define KVM_GUESTDBG_SINGLESTEP 0x00000002 + +struct kvm_guest_debug { + __u32 control; + __u32 pad; + struct kvm_guest_debug_arch arch; +}; + #define KVM_TRC_SHIFT 16 /* * kvm trace categories @@ -396,6 +393,7 @@ struct kvm_trace_rec { #ifdef __KVM_HAVE_USER_NMI #define KVM_CAP_USER_NMI 22 #endif +#define KVM_CAP_SET_GUEST_DEBUG 23 /* * ioctls for VM fds @@ -440,7 +438,8 @@ struct kvm_trace_rec { #define KVM_SET_SREGS _IOW(KVMIO, 0x84, struct kvm_sregs) #define KVM_TRANSLATE _IOWR(KVMIO, 0x85, struct kvm_translation) #define KVM_INTERRUPT _IOW(KVMIO, 0x86, struct kvm_interrupt) -#define KVM_DEBUG_GUEST _IOW(KVMIO, 0x87, struct kvm_debug_guest) +/* KVM_DEBUG_GUEST is no longer supported, use KVM_SET_GUEST_DEBUG instead */ +#define KVM_DEBUG_GUEST __KVM_DEPRECATED_DEBUG_GUEST #define KVM_GET_MSRS _IOWR(KVMIO, 0x88, struct kvm_msrs) #define KVM_SET_MSRS _IOW(KVMIO, 0x89, struct kvm_msrs) #define KVM_SET_CPUID _IOW(KVMIO, 0x8a, struct kvm_cpuid) @@ -469,6 +468,26 @@ struct kvm_trace_rec { #define KVM_SET_MP_STATE _IOW(KVMIO, 0x99, struct kvm_mp_state) /* Available with KVM_CAP_NMI */ #define KVM_NMI _IO(KVMIO, 0x9a) +/* Available with KVM_CAP_SET_GUEST_DEBUG */ +#define KVM_SET_GUEST_DEBUG _IOW(KVMIO, 0x9b, struct kvm_guest_debug) + +/* + * Deprecated interfaces + */ +struct kvm_breakpoint { + __u32 enabled; + __u32 padding; + __u64 address; +}; + +struct kvm_debug_guest { + __u32 enabled; + __u32 pad; + struct kvm_breakpoint breakpoints[4]; + __u32 singlestep; +}; + +#define __KVM_DEPRECATED_DEBUG_GUEST _IOW(KVMIO, 0x87, struct kvm_debug_guest) #define KVM_TRC_INJ_VIRQ (KVM_TRC_HANDLER + 0x02) #define KVM_TRC_REDELIVER_EVT (KVM_TRC_HANDLER + 0x03) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index bf6f703642f..e92212f970d 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -73,7 +73,7 @@ struct kvm_vcpu { struct kvm_run *run; int guest_mode; unsigned long requests; - struct kvm_guest_debug guest_debug; + unsigned long guest_debug; int fpu_active; int guest_fpu_loaded; wait_queue_head_t wq; @@ -255,8 +255,8 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state); int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state); -int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu, - struct kvm_debug_guest *dbg); +int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, + struct kvm_guest_debug *dbg); int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run); int kvm_arch_init(void *opaque); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 29a667ce35b..f83ef9c7e89 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1755,13 +1755,13 @@ out_free2: r = 0; break; } - case KVM_DEBUG_GUEST: { - struct kvm_debug_guest dbg; + case KVM_SET_GUEST_DEBUG: { + struct kvm_guest_debug dbg; r = -EFAULT; if (copy_from_user(&dbg, argp, sizeof dbg)) goto out; - r = kvm_arch_vcpu_ioctl_debug_guest(vcpu, &dbg); + r = kvm_arch_vcpu_ioctl_set_guest_debug(vcpu, &dbg); if (r) goto out; r = 0; -- cgit v1.2.3-70-g09d2 From 42dbaa5a057736bf8b5c22aa42dbe975bf1080e5 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Mon, 15 Dec 2008 13:52:10 +0100 Subject: KVM: x86: Virtualize debug registers So far KVM only had basic x86 debug register support, once introduced to realize guest debugging that way. The guest itself was not able to use those registers. This patch now adds (almost) full support for guest self-debugging via hardware registers. It refactors the code, moving generic parts out of SVM (VMX was already cleaned up by the KVM_SET_GUEST_DEBUG patches), and it ensures that the registers are properly switched between host and guest. This patch also prepares debug register usage by the host. The latter will (once wired-up by the following patch) allow for hardware breakpoints/watchpoints in guest code. If this is enabled, the guest will only see faked debug registers without functionality, but with content reflecting the guest's modifications. Tested on Intel only, but SVM /should/ work as well, but who knows... Known limitations: Trapping on tss switch won't work - most probably on Intel. Credits also go to Joerg Roedel - I used his once posted debugging series as platform for this patch. Signed-off-by: Jan Kiszka Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm_host.h | 22 ++++++++ arch/x86/include/asm/vmx.h | 2 +- arch/x86/kvm/kvm_svm.h | 6 --- arch/x86/kvm/svm.c | 116 +++++++++++++++------------------------- arch/x86/kvm/vmx.c | 114 +++++++++++++++++++++++++++++++++------ arch/x86/kvm/x86.c | 29 ++++++++++ 6 files changed, 193 insertions(+), 96 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index c430cd580ee..0a4dab25a91 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -135,6 +135,19 @@ enum { #define KVM_NR_MEM_OBJS 40 +#define KVM_NR_DB_REGS 4 + +#define DR6_BD (1 << 13) +#define DR6_BS (1 << 14) +#define DR6_FIXED_1 0xffff0ff0 +#define DR6_VOLATILE 0x0000e00f + +#define DR7_BP_EN_MASK 0x000000ff +#define DR7_GE (1 << 9) +#define DR7_GD (1 << 13) +#define DR7_FIXED_1 0x00000400 +#define DR7_VOLATILE 0xffff23ff + /* * We don't want allocation failures within the mmu code, so we preallocate * enough memory for a single page fault in a cache. @@ -334,6 +347,15 @@ struct kvm_vcpu_arch { struct mtrr_state_type mtrr_state; u32 pat; + + int switch_db_regs; + unsigned long host_db[KVM_NR_DB_REGS]; + unsigned long host_dr6; + unsigned long host_dr7; + unsigned long db[KVM_NR_DB_REGS]; + unsigned long dr6; + unsigned long dr7; + unsigned long eff_db[KVM_NR_DB_REGS]; }; struct kvm_mem_alias { diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 32159f034ef..498f944010b 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -312,7 +312,7 @@ enum vmcs_field { #define DEBUG_REG_ACCESS_TYPE 0x10 /* 4, direction of access */ #define TYPE_MOV_TO_DR (0 << 4) #define TYPE_MOV_FROM_DR (1 << 4) -#define DEBUG_REG_ACCESS_REG 0xf00 /* 11:8, general purpose reg. */ +#define DEBUG_REG_ACCESS_REG(eq) (((eq) >> 8) & 0xf) /* 11:8, general purpose reg. */ /* segment AR */ diff --git a/arch/x86/kvm/kvm_svm.h b/arch/x86/kvm/kvm_svm.h index 91673413d8f..ed66e4c078d 100644 --- a/arch/x86/kvm/kvm_svm.h +++ b/arch/x86/kvm/kvm_svm.h @@ -18,7 +18,6 @@ static const u32 host_save_user_msrs[] = { }; #define NR_HOST_SAVE_USER_MSRS ARRAY_SIZE(host_save_user_msrs) -#define NUM_DB_REGS 4 struct kvm_vcpu; @@ -29,16 +28,11 @@ struct vcpu_svm { struct svm_cpu_data *svm_data; uint64_t asid_generation; - unsigned long db_regs[NUM_DB_REGS]; - u64 next_rip; u64 host_user_msrs[NR_HOST_SAVE_USER_MSRS]; u64 host_gs_base; unsigned long host_cr2; - unsigned long host_db_regs[NUM_DB_REGS]; - unsigned long host_dr6; - unsigned long host_dr7; u32 *msrpm; struct vmcb *hsave; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 88d9062f454..815f50e425a 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -38,9 +38,6 @@ MODULE_LICENSE("GPL"); #define IOPM_ALLOC_ORDER 2 #define MSRPM_ALLOC_ORDER 1 -#define DR7_GD_MASK (1 << 13) -#define DR6_BD_MASK (1 << 13) - #define SEG_TYPE_LDT 2 #define SEG_TYPE_BUSY_TSS16 3 @@ -181,32 +178,6 @@ static inline void kvm_write_cr2(unsigned long val) asm volatile ("mov %0, %%cr2" :: "r" (val)); } -static inline unsigned long read_dr6(void) -{ - unsigned long dr6; - - asm volatile ("mov %%dr6, %0" : "=r" (dr6)); - return dr6; -} - -static inline void write_dr6(unsigned long val) -{ - asm volatile ("mov %0, %%dr6" :: "r" (val)); -} - -static inline unsigned long read_dr7(void) -{ - unsigned long dr7; - - asm volatile ("mov %%dr7, %0" : "=r" (dr7)); - return dr7; -} - -static inline void write_dr7(unsigned long val) -{ - asm volatile ("mov %0, %%dr7" :: "r" (val)); -} - static inline void force_new_asid(struct kvm_vcpu *vcpu) { to_svm(vcpu)->asid_generation--; @@ -695,7 +666,6 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) clear_page(svm->vmcb); svm->vmcb_pa = page_to_pfn(page) << PAGE_SHIFT; svm->asid_generation = 0; - memset(svm->db_regs, 0, sizeof(svm->db_regs)); init_vmcb(svm); fx_init(&svm->vcpu); @@ -1035,7 +1005,29 @@ static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *svm_data) static unsigned long svm_get_dr(struct kvm_vcpu *vcpu, int dr) { - unsigned long val = to_svm(vcpu)->db_regs[dr]; + struct vcpu_svm *svm = to_svm(vcpu); + unsigned long val; + + switch (dr) { + case 0 ... 3: + val = vcpu->arch.db[dr]; + break; + case 6: + if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) + val = vcpu->arch.dr6; + else + val = svm->vmcb->save.dr6; + break; + case 7: + if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) + val = vcpu->arch.dr7; + else + val = svm->vmcb->save.dr7; + break; + default: + val = 0; + } + KVMTRACE_2D(DR_READ, vcpu, (u32)dr, (u32)val, handler); return val; } @@ -1045,33 +1037,40 @@ static void svm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long value, { struct vcpu_svm *svm = to_svm(vcpu); - *exception = 0; + KVMTRACE_2D(DR_WRITE, vcpu, (u32)dr, (u32)value, handler); - if (svm->vmcb->save.dr7 & DR7_GD_MASK) { - svm->vmcb->save.dr7 &= ~DR7_GD_MASK; - svm->vmcb->save.dr6 |= DR6_BD_MASK; - *exception = DB_VECTOR; - return; - } + *exception = 0; switch (dr) { case 0 ... 3: - svm->db_regs[dr] = value; + vcpu->arch.db[dr] = value; + if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) + vcpu->arch.eff_db[dr] = value; return; case 4 ... 5: - if (vcpu->arch.cr4 & X86_CR4_DE) { + if (vcpu->arch.cr4 & X86_CR4_DE) *exception = UD_VECTOR; + return; + case 6: + if (value & 0xffffffff00000000ULL) { + *exception = GP_VECTOR; return; } - case 7: { - if (value & ~((1ULL << 32) - 1)) { + vcpu->arch.dr6 = (value & DR6_VOLATILE) | DR6_FIXED_1; + return; + case 7: + if (value & 0xffffffff00000000ULL) { *exception = GP_VECTOR; return; } - svm->vmcb->save.dr7 = value; + vcpu->arch.dr7 = (value & DR7_VOLATILE) | DR7_FIXED_1; + if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) { + svm->vmcb->save.dr7 = vcpu->arch.dr7; + vcpu->arch.switch_db_regs = (value & DR7_BP_EN_MASK); + } return; - } default: + /* FIXME: Possible case? */ printk(KERN_DEBUG "%s: unexpected dr %u\n", __func__, dr); *exception = UD_VECTOR; @@ -2365,22 +2364,6 @@ static int svm_set_tss_addr(struct kvm *kvm, unsigned int addr) return 0; } -static void save_db_regs(unsigned long *db_regs) -{ - asm volatile ("mov %%dr0, %0" : "=r"(db_regs[0])); - asm volatile ("mov %%dr1, %0" : "=r"(db_regs[1])); - asm volatile ("mov %%dr2, %0" : "=r"(db_regs[2])); - asm volatile ("mov %%dr3, %0" : "=r"(db_regs[3])); -} - -static void load_db_regs(unsigned long *db_regs) -{ - asm volatile ("mov %0, %%dr0" : : "r"(db_regs[0])); - asm volatile ("mov %0, %%dr1" : : "r"(db_regs[1])); - asm volatile ("mov %0, %%dr2" : : "r"(db_regs[2])); - asm volatile ("mov %0, %%dr3" : : "r"(db_regs[3])); -} - static void svm_flush_tlb(struct kvm_vcpu *vcpu) { force_new_asid(vcpu); @@ -2439,20 +2422,12 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) gs_selector = kvm_read_gs(); ldt_selector = kvm_read_ldt(); svm->host_cr2 = kvm_read_cr2(); - svm->host_dr6 = read_dr6(); - svm->host_dr7 = read_dr7(); if (!is_nested(svm)) svm->vmcb->save.cr2 = vcpu->arch.cr2; /* required for live migration with NPT */ if (npt_enabled) svm->vmcb->save.cr3 = vcpu->arch.cr3; - if (svm->vmcb->save.dr7 & 0xff) { - write_dr7(0); - save_db_regs(svm->host_db_regs); - load_db_regs(svm->db_regs); - } - clgi(); local_irq_enable(); @@ -2528,16 +2503,11 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) #endif ); - if ((svm->vmcb->save.dr7 & 0xff)) - load_db_regs(svm->host_db_regs); - vcpu->arch.cr2 = svm->vmcb->save.cr2; vcpu->arch.regs[VCPU_REGS_RAX] = svm->vmcb->save.rax; vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp; vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip; - write_dr6(svm->host_dr6); - write_dr7(svm->host_dr7); kvm_write_cr2(svm->host_cr2); kvm_load_fs(fs_selector); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index c776868ffe4..0989776ee7b 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2311,7 +2311,6 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) kvm_rip_write(vcpu, 0); kvm_register_write(vcpu, VCPU_REGS_RSP, 0); - /* todo: dr0 = dr1 = dr2 = dr3 = 0; dr6 = 0xffff0ff0 */ vmcs_writel(GUEST_DR7, 0x400); vmcs_writel(GUEST_GDTR_BASE, 0); @@ -2577,7 +2576,7 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 intr_info, ex_no, error_code; - unsigned long cr2, rip; + unsigned long cr2, rip, dr6; u32 vect_info; enum emulation_result er; @@ -2637,14 +2636,28 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } ex_no = intr_info & INTR_INFO_VECTOR_MASK; - if (ex_no == DB_VECTOR || ex_no == BP_VECTOR) { + switch (ex_no) { + case DB_VECTOR: + dr6 = vmcs_readl(EXIT_QUALIFICATION); + if (!(vcpu->guest_debug & + (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) { + vcpu->arch.dr6 = dr6 | DR6_FIXED_1; + kvm_queue_exception(vcpu, DB_VECTOR); + return 1; + } + kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1; + kvm_run->debug.arch.dr7 = vmcs_readl(GUEST_DR7); + /* fall through */ + case BP_VECTOR: kvm_run->exit_reason = KVM_EXIT_DEBUG; kvm_run->debug.arch.pc = vmcs_readl(GUEST_CS_BASE) + rip; kvm_run->debug.arch.exception = ex_no; - } else { + break; + default: kvm_run->exit_reason = KVM_EXIT_EXCEPTION; kvm_run->ex.exception = ex_no; kvm_run->ex.error_code = error_code; + break; } return 0; } @@ -2784,21 +2797,44 @@ static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) unsigned long val; int dr, reg; - /* - * FIXME: this code assumes the host is debugging the guest. - * need to deal with guest debugging itself too. - */ + dr = vmcs_readl(GUEST_DR7); + if (dr & DR7_GD) { + /* + * As the vm-exit takes precedence over the debug trap, we + * need to emulate the latter, either for the host or the + * guest debugging itself. + */ + if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) { + kvm_run->debug.arch.dr6 = vcpu->arch.dr6; + kvm_run->debug.arch.dr7 = dr; + kvm_run->debug.arch.pc = + vmcs_readl(GUEST_CS_BASE) + + vmcs_readl(GUEST_RIP); + kvm_run->debug.arch.exception = DB_VECTOR; + kvm_run->exit_reason = KVM_EXIT_DEBUG; + return 0; + } else { + vcpu->arch.dr7 &= ~DR7_GD; + vcpu->arch.dr6 |= DR6_BD; + vmcs_writel(GUEST_DR7, vcpu->arch.dr7); + kvm_queue_exception(vcpu, DB_VECTOR); + return 1; + } + } + exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - dr = exit_qualification & 7; - reg = (exit_qualification >> 8) & 15; - if (exit_qualification & 16) { - /* mov from dr */ + dr = exit_qualification & DEBUG_REG_ACCESS_NUM; + reg = DEBUG_REG_ACCESS_REG(exit_qualification); + if (exit_qualification & TYPE_MOV_FROM_DR) { switch (dr) { + case 0 ... 3: + val = vcpu->arch.db[dr]; + break; case 6: - val = 0xffff0ff0; + val = vcpu->arch.dr6; break; case 7: - val = 0x400; + val = vcpu->arch.dr7; break; default: val = 0; @@ -2806,7 +2842,38 @@ static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) kvm_register_write(vcpu, reg, val); KVMTRACE_2D(DR_READ, vcpu, (u32)dr, (u32)val, handler); } else { - /* mov to dr */ + val = vcpu->arch.regs[reg]; + switch (dr) { + case 0 ... 3: + vcpu->arch.db[dr] = val; + if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) + vcpu->arch.eff_db[dr] = val; + break; + case 4 ... 5: + if (vcpu->arch.cr4 & X86_CR4_DE) + kvm_queue_exception(vcpu, UD_VECTOR); + break; + case 6: + if (val & 0xffffffff00000000ULL) { + kvm_queue_exception(vcpu, GP_VECTOR); + break; + } + vcpu->arch.dr6 = (val & DR6_VOLATILE) | DR6_FIXED_1; + break; + case 7: + if (val & 0xffffffff00000000ULL) { + kvm_queue_exception(vcpu, GP_VECTOR); + break; + } + vcpu->arch.dr7 = (val & DR7_VOLATILE) | DR7_FIXED_1; + if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) { + vmcs_writel(GUEST_DR7, vcpu->arch.dr7); + vcpu->arch.switch_db_regs = + (val & DR7_BP_EN_MASK); + } + break; + } + KVMTRACE_2D(DR_WRITE, vcpu, (u32)dr, (u32)val, handler); } skip_emulated_instruction(vcpu); return 1; @@ -2957,7 +3024,18 @@ static int handle_task_switch(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } tss_selector = exit_qualification; - return kvm_task_switch(vcpu, tss_selector, reason); + if (!kvm_task_switch(vcpu, tss_selector, reason)) + return 0; + + /* clear all local breakpoint enable flags */ + vmcs_writel(GUEST_DR7, vmcs_readl(GUEST_DR7) & ~55); + + /* + * TODO: What about debug traps on tss switch? + * Are we supposed to inject them and update dr6? + */ + + return 1; } static int handle_ept_violation(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) @@ -3342,6 +3420,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) */ vmcs_writel(HOST_CR0, read_cr0()); + set_debugreg(vcpu->arch.dr6, 6); + asm( /* Store host registers */ "push %%"R"dx; push %%"R"bp;" @@ -3436,6 +3516,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP)); vcpu->arch.regs_dirty = 0; + get_debugreg(vcpu->arch.dr6, 6); + vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD); if (vmx->rmode.irq.pending) fixup_rmode_irq(vmx); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index e990d164b56..300bc4d42ab 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3025,10 +3025,34 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) kvm_guest_enter(); + get_debugreg(vcpu->arch.host_dr6, 6); + get_debugreg(vcpu->arch.host_dr7, 7); + if (unlikely(vcpu->arch.switch_db_regs)) { + get_debugreg(vcpu->arch.host_db[0], 0); + get_debugreg(vcpu->arch.host_db[1], 1); + get_debugreg(vcpu->arch.host_db[2], 2); + get_debugreg(vcpu->arch.host_db[3], 3); + + set_debugreg(0, 7); + set_debugreg(vcpu->arch.eff_db[0], 0); + set_debugreg(vcpu->arch.eff_db[1], 1); + set_debugreg(vcpu->arch.eff_db[2], 2); + set_debugreg(vcpu->arch.eff_db[3], 3); + } KVMTRACE_0D(VMENTRY, vcpu, entryexit); kvm_x86_ops->run(vcpu, kvm_run); + if (unlikely(vcpu->arch.switch_db_regs)) { + set_debugreg(0, 7); + set_debugreg(vcpu->arch.host_db[0], 0); + set_debugreg(vcpu->arch.host_db[1], 1); + set_debugreg(vcpu->arch.host_db[2], 2); + set_debugreg(vcpu->arch.host_db[3], 3); + } + set_debugreg(vcpu->arch.host_dr6, 6); + set_debugreg(vcpu->arch.host_dr7, 7); + vcpu->guest_mode = 0; local_irq_enable(); @@ -4035,6 +4059,11 @@ int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu) vcpu->arch.nmi_pending = false; vcpu->arch.nmi_injected = false; + vcpu->arch.switch_db_regs = 0; + memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db)); + vcpu->arch.dr6 = DR6_FIXED_1; + vcpu->arch.dr7 = DR7_FIXED_1; + return kvm_x86_ops->vcpu_reset(vcpu); } -- cgit v1.2.3-70-g09d2 From a770f6f28b1a9287189f3dc8333eb694d9a2f0ab Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Sun, 21 Dec 2008 19:20:09 +0200 Subject: KVM: MMU: Inherit a shadow page's guest level count from vcpu setup Instead of "calculating" it on every shadow page allocation, set it once when switching modes, and copy it when allocating pages. This doesn't buy us much, but sets up the stage for inheriting more information related to the mmu setup. Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/mmu.c | 17 +++++++++++------ 2 files changed, 12 insertions(+), 6 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 0a4dab25a91..28f875f28f5 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -244,6 +244,7 @@ struct kvm_mmu { hpa_t root_hpa; int root_level; int shadow_root_level; + union kvm_mmu_page_role base_role; u64 *pae_root; }; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 2d4477c7147..f15023c11fe 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -1204,8 +1204,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp; struct hlist_node *node, *tmp; - role.word = 0; - role.glevels = vcpu->arch.mmu.root_level; + role = vcpu->arch.mmu.base_role; role.level = level; role.metaphysical = metaphysical; role.access = access; @@ -2251,17 +2250,23 @@ static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) static int init_kvm_softmmu(struct kvm_vcpu *vcpu) { + int r; + ASSERT(vcpu); ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa)); if (!is_paging(vcpu)) - return nonpaging_init_context(vcpu); + r = nonpaging_init_context(vcpu); else if (is_long_mode(vcpu)) - return paging64_init_context(vcpu); + r = paging64_init_context(vcpu); else if (is_pae(vcpu)) - return paging32E_init_context(vcpu); + r = paging32E_init_context(vcpu); else - return paging32_init_context(vcpu); + r = paging32_init_context(vcpu); + + vcpu->arch.mmu.base_role.glevels = vcpu->arch.mmu.root_level; + + return r; } static int init_kvm_mmu(struct kvm_vcpu *vcpu) -- cgit v1.2.3-70-g09d2 From 2f0b3d60b2c43aef7cd10169c425c052169c622a Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Sun, 21 Dec 2008 19:27:36 +0200 Subject: KVM: MMU: Segregate mmu pages created with different cr4.pge settings Don't allow a vcpu with cr4.pge cleared to use a shadow page created with cr4.pge set; this might cause a cr3 switch not to sync ptes that have the global bit set (the global bit has no effect if !cr4.pge). This can only occur on smp with different cr4.pge settings for different vcpus (since a cr4 change will resync the shadow ptes), but there's no cost to being correct here. Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/x86.c | 1 + 2 files changed, 2 insertions(+) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 28f875f28f5..c2a01d0513f 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -183,6 +183,7 @@ union kvm_mmu_page_role { unsigned metaphysical:1; unsigned access:3; unsigned invalid:1; + unsigned cr4_pge:1; }; }; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 2477e87b2f8..873602b5edf 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -364,6 +364,7 @@ void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) } kvm_x86_ops->set_cr4(vcpu, cr4); vcpu->arch.cr4 = cr4; + vcpu->arch.mmu.base_role.cr4_pge = !!(cr4 & X86_CR4_PGE); kvm_mmu_sync_global(vcpu); kvm_mmu_reset_context(vcpu); } -- cgit v1.2.3-70-g09d2 From 53f658b3c33616a4997ee254311b335e59063289 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Thu, 11 Dec 2008 20:45:05 +0100 Subject: KVM: VMX: initialize TSC offset relative to vm creation time VMX initializes the TSC offset for each vcpu at different times, and also reinitializes it for vcpus other than 0 on APIC SIPI message. This bug causes the TSC's to appear unsynchronized in the guest, even if the host is good. Older Linux kernels don't handle the situation very well, so gettimeofday is likely to go backwards in time: http://www.mail-archive.com/kvm@vger.kernel.org/msg02955.html http://sourceforge.net/tracker/index.php?func=detail&aid=2025534&group_id=180599&atid=893831 Fix it by initializating the offset of each vcpu relative to vm creation time, and moving it from vmx_vcpu_reset to vmx_vcpu_setup, out of the APIC MP init path. Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/vmx.c | 19 +++++++++++-------- arch/x86/kvm/x86.c | 2 ++ 3 files changed, 14 insertions(+), 8 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index c2a01d0513f..9efc446b5ac 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -398,6 +398,7 @@ struct kvm_arch{ unsigned long irq_sources_bitmap; unsigned long irq_states[KVM_IOAPIC_NUM_PINS]; + u64 vm_init_tsc; }; struct kvm_vm_stat { diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index cee81c9a665..3312047664a 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -865,11 +865,8 @@ static u64 guest_read_tsc(void) * writes 'guest_tsc' into guest's timestamp counter "register" * guest_tsc = host_tsc + tsc_offset ==> tsc_offset = guest_tsc - host_tsc */ -static void guest_write_tsc(u64 guest_tsc) +static void guest_write_tsc(u64 guest_tsc, u64 host_tsc) { - u64 host_tsc; - - rdtscll(host_tsc); vmcs_write64(TSC_OFFSET, guest_tsc - host_tsc); } @@ -934,6 +931,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct kvm_msr_entry *msr; + u64 host_tsc; int ret = 0; switch (msr_index) { @@ -959,7 +957,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) vmcs_writel(GUEST_SYSENTER_ESP, data); break; case MSR_IA32_TIME_STAMP_COUNTER: - guest_write_tsc(data); + rdtscll(host_tsc); + guest_write_tsc(data, host_tsc); break; case MSR_P6_PERFCTR0: case MSR_P6_PERFCTR1: @@ -2109,7 +2108,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) { u32 host_sysenter_cs, msr_low, msr_high; u32 junk; - u64 host_pat; + u64 host_pat, tsc_this, tsc_base; unsigned long a; struct descriptor_table dt; int i; @@ -2237,6 +2236,12 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmcs_writel(CR0_GUEST_HOST_MASK, ~0UL); vmcs_writel(CR4_GUEST_HOST_MASK, KVM_GUEST_CR4_MASK); + tsc_base = vmx->vcpu.kvm->arch.vm_init_tsc; + rdtscll(tsc_this); + if (tsc_this < vmx->vcpu.kvm->arch.vm_init_tsc) + tsc_base = tsc_this; + + guest_write_tsc(0, tsc_base); return 0; } @@ -2328,8 +2333,6 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0); vmcs_write32(GUEST_PENDING_DBG_EXCEPTIONS, 0); - guest_write_tsc(0); - /* Special registers */ vmcs_write64(GUEST_IA32_DEBUGCTL, 0); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 873602b5edf..3b2acfd72d7 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4170,6 +4170,8 @@ struct kvm *kvm_arch_create_vm(void) /* Reserve bit 0 of irq_sources_bitmap for userspace irq source */ set_bit(KVM_USERSPACE_IRQ_SOURCE_ID, &kvm->arch.irq_sources_bitmap); + rdtscll(kvm->arch.vm_init_tsc); + return kvm; } -- cgit v1.2.3-70-g09d2 From 77c2002e7c6f019f59a6f3cc5f8b16b41748dbe1 Mon Sep 17 00:00:00 2001 From: Izik Eidus Date: Mon, 29 Dec 2008 01:42:19 +0200 Subject: KVM: introduce kvm_read_guest_virt, kvm_write_guest_virt This commit change the name of emulator_read_std into kvm_read_guest_virt, and add new function name kvm_write_guest_virt that allow writing into a guest virtual address. Signed-off-by: Izik Eidus Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm_host.h | 4 --- arch/x86/kvm/x86.c | 56 ++++++++++++++++++++++++++++++----------- 2 files changed, 42 insertions(+), 18 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 9efc446b5ac..b74576aec19 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -609,10 +609,6 @@ void kvm_inject_nmi(struct kvm_vcpu *vcpu); void fx_init(struct kvm_vcpu *vcpu); -int emulator_read_std(unsigned long addr, - void *val, - unsigned int bytes, - struct kvm_vcpu *vcpu); int emulator_write_emulated(unsigned long addr, const void *val, unsigned int bytes, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 3b2acfd72d7..67f91764e99 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1976,10 +1976,8 @@ static struct kvm_io_device *vcpu_find_mmio_dev(struct kvm_vcpu *vcpu, return dev; } -int emulator_read_std(unsigned long addr, - void *val, - unsigned int bytes, - struct kvm_vcpu *vcpu) +int kvm_read_guest_virt(gva_t addr, void *val, unsigned int bytes, + struct kvm_vcpu *vcpu) { void *data = val; int r = X86EMUL_CONTINUE; @@ -1987,27 +1985,57 @@ int emulator_read_std(unsigned long addr, while (bytes) { gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr); unsigned offset = addr & (PAGE_SIZE-1); - unsigned tocopy = min(bytes, (unsigned)PAGE_SIZE - offset); + unsigned toread = min(bytes, (unsigned)PAGE_SIZE - offset); int ret; if (gpa == UNMAPPED_GVA) { r = X86EMUL_PROPAGATE_FAULT; goto out; } - ret = kvm_read_guest(vcpu->kvm, gpa, data, tocopy); + ret = kvm_read_guest(vcpu->kvm, gpa, data, toread); if (ret < 0) { r = X86EMUL_UNHANDLEABLE; goto out; } - bytes -= tocopy; - data += tocopy; - addr += tocopy; + bytes -= toread; + data += toread; + addr += toread; } out: return r; } -EXPORT_SYMBOL_GPL(emulator_read_std); + +int kvm_write_guest_virt(gva_t addr, void *val, unsigned int bytes, + struct kvm_vcpu *vcpu) +{ + void *data = val; + int r = X86EMUL_CONTINUE; + + while (bytes) { + gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr); + unsigned offset = addr & (PAGE_SIZE-1); + unsigned towrite = min(bytes, (unsigned)PAGE_SIZE - offset); + int ret; + + if (gpa == UNMAPPED_GVA) { + r = X86EMUL_PROPAGATE_FAULT; + goto out; + } + ret = kvm_write_guest(vcpu->kvm, gpa, data, towrite); + if (ret < 0) { + r = X86EMUL_UNHANDLEABLE; + goto out; + } + + bytes -= towrite; + data += towrite; + addr += towrite; + } +out: + return r; +} + static int emulator_read_emulated(unsigned long addr, void *val, @@ -2029,8 +2057,8 @@ static int emulator_read_emulated(unsigned long addr, if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) goto mmio; - if (emulator_read_std(addr, val, bytes, vcpu) - == X86EMUL_CONTINUE) + if (kvm_read_guest_virt(addr, val, bytes, vcpu) + == X86EMUL_CONTINUE) return X86EMUL_CONTINUE; if (gpa == UNMAPPED_GVA) return X86EMUL_PROPAGATE_FAULT; @@ -2233,7 +2261,7 @@ void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context) rip_linear = rip + get_segment_base(vcpu, VCPU_SREG_CS); - emulator_read_std(rip_linear, (void *)opcodes, 4, vcpu); + kvm_read_guest_virt(rip_linear, (void *)opcodes, 4, vcpu); printk(KERN_ERR "emulation failed (%s) rip %lx %02x %02x %02x %02x\n", context, rip, opcodes[0], opcodes[1], opcodes[2], opcodes[3]); @@ -2241,7 +2269,7 @@ void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context) EXPORT_SYMBOL_GPL(kvm_report_emulation_failure); static struct x86_emulate_ops emulate_ops = { - .read_std = emulator_read_std, + .read_std = kvm_read_guest_virt, .read_emulated = emulator_read_emulated, .write_emulated = emulator_write_emulated, .cmpxchg_emulated = emulator_cmpxchg_emulated, -- cgit v1.2.3-70-g09d2 From 52d939a0bf44081bc9f69b4fbdc9e7f416df27c7 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Tue, 30 Dec 2008 15:55:06 -0200 Subject: KVM: PIT: provide an option to disable interrupt reinjection Certain clocks (such as TSC) in older 2.6 guests overaccount for lost ticks, causing severe time drift. Interrupt reinjection magnifies the problem. Provide an option to disable it. [avi: allow room for expansion in case we want to disable reinjection of other timers] Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm.h | 5 +++++ arch/x86/kvm/i8254.c | 4 ++++ arch/x86/kvm/i8254.h | 1 + arch/x86/kvm/x86.c | 21 +++++++++++++++++++++ include/linux/kvm.h | 4 ++++ 5 files changed, 35 insertions(+) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h index 32eb96c7ca2..54bcf228152 100644 --- a/arch/x86/include/asm/kvm.h +++ b/arch/x86/include/asm/kvm.h @@ -233,4 +233,9 @@ struct kvm_guest_debug_arch { struct kvm_pit_state { struct kvm_pit_channel_state channels[3]; }; + +struct kvm_reinject_control { + __u8 pit_reinject; + __u8 reserved[31]; +}; #endif /* _ASM_X86_KVM_H */ diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 72bd275a9b5..528daadeba4 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -201,6 +201,9 @@ static int __pit_timer_fn(struct kvm_kpit_state *ps) if (!atomic_inc_and_test(&pt->pending)) set_bit(KVM_REQ_PENDING_TIMER, &vcpu0->requests); + if (!pt->reinject) + atomic_set(&pt->pending, 1); + if (vcpu0 && waitqueue_active(&vcpu0->wq)) wake_up_interruptible(&vcpu0->wq); @@ -580,6 +583,7 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm) pit_state->irq_ack_notifier.gsi = 0; pit_state->irq_ack_notifier.irq_acked = kvm_pit_ack_irq; kvm_register_irq_ack_notifier(kvm, &pit_state->irq_ack_notifier); + pit_state->pit_timer.reinject = true; mutex_unlock(&pit->pit_state.lock); kvm_pit_reset(pit); diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h index 4178022b97a..76959c4b500 100644 --- a/arch/x86/kvm/i8254.h +++ b/arch/x86/kvm/i8254.h @@ -9,6 +9,7 @@ struct kvm_kpit_timer { s64 period; /* unit: ns */ s64 scheduled; atomic_t pending; + bool reinject; }; struct kvm_kpit_channel_state { diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c3fbe8c55c1..a1f14611f4b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -993,6 +993,7 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_NOP_IO_DELAY: case KVM_CAP_MP_STATE: case KVM_CAP_SYNC_MMU: + case KVM_CAP_REINJECT_CONTROL: r = 1; break; case KVM_CAP_COALESCED_MMIO: @@ -1728,6 +1729,15 @@ static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps) return r; } +static int kvm_vm_ioctl_reinject(struct kvm *kvm, + struct kvm_reinject_control *control) +{ + if (!kvm->arch.vpit) + return -ENXIO; + kvm->arch.vpit->pit_state.pit_timer.reinject = control->pit_reinject; + return 0; +} + /* * Get (and clear) the dirty memory log for a memory slot. */ @@ -1925,6 +1935,17 @@ long kvm_arch_vm_ioctl(struct file *filp, r = 0; break; } + case KVM_REINJECT_CONTROL: { + struct kvm_reinject_control control; + r = -EFAULT; + if (copy_from_user(&control, argp, sizeof(control))) + goto out; + r = kvm_vm_ioctl_reinject(kvm, &control); + if (r) + goto out; + r = 0; + break; + } default: ; } diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 11e3e6197c8..ae7a12c7742 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -396,6 +396,9 @@ struct kvm_trace_rec { #if defined(CONFIG_X86) #define KVM_CAP_SET_GUEST_DEBUG 23 #endif +#if defined(CONFIG_X86) +#define KVM_CAP_REINJECT_CONTROL 24 +#endif /* * ioctls for VM fds @@ -429,6 +432,7 @@ struct kvm_trace_rec { struct kvm_assigned_pci_dev) #define KVM_ASSIGN_IRQ _IOR(KVMIO, 0x70, \ struct kvm_assigned_irq) +#define KVM_REINJECT_CONTROL _IO(KVMIO, 0x71) /* * ioctls for vcpu fds -- cgit v1.2.3-70-g09d2 From 1c08364c3565242f1e1bd585bc2ce458967941af Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Sun, 4 Jan 2009 12:39:07 +0200 Subject: KVM: Move struct kvm_pio_request into x86 kvm_host.h This is an x86 specific stucture and has no business living in common code. Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm_host.h | 12 ++++++++++++ include/linux/kvm_types.h | 12 ------------ 2 files changed, 12 insertions(+), 12 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index b74576aec19..863ea73431a 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -227,6 +227,18 @@ struct kvm_pv_mmu_op_buffer { char buf[512] __aligned(sizeof(long)); }; +struct kvm_pio_request { + unsigned long count; + int cur_count; + gva_t guest_gva; + int in; + int port; + int size; + int string; + int down; + int rep; +}; + /* * x86 supports 3 paging modes (4-level 64-bit, 3-level 64-bit, and 2-level * 32-bit). The kvm_mmu structure abstracts the details of the current mmu diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 5f4a18cae26..2b8318c83e5 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -40,16 +40,4 @@ typedef unsigned long hfn_t; typedef hfn_t pfn_t; -struct kvm_pio_request { - unsigned long count; - int cur_count; - gva_t guest_gva; - int in; - int port; - int size; - int string; - int down; - int rep; -}; - #endif /* __KVM_TYPES_H__ */ -- cgit v1.2.3-70-g09d2 From f6e2c02b6d28ddabe99377c5640a833407a62632 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Sun, 11 Jan 2009 13:02:10 +0200 Subject: KVM: MMU: Rename "metaphysical" attribute to "direct" This actually describes what is going on, rather than alerting the reader that something strange is going on. Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm_host.h | 5 +++-- arch/x86/kvm/mmu.c | 32 ++++++++++++++++---------------- arch/x86/kvm/paging_tmpl.h | 12 ++++++------ 3 files changed, 25 insertions(+), 24 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 863ea73431a..55fd4c5fd38 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -170,7 +170,8 @@ struct kvm_pte_chain { * bits 0:3 - total guest paging levels (2-4, or zero for real mode) * bits 4:7 - page table level for this shadow (1-4) * bits 8:9 - page table quadrant for 2-level guests - * bit 16 - "metaphysical" - gfn is not a real page (huge page/real mode) + * bit 16 - direct mapping of virtual to physical mapping at gfn + * used for real mode and two-dimensional paging * bits 17:19 - common access permissions for all ptes in this shadow page */ union kvm_mmu_page_role { @@ -180,7 +181,7 @@ union kvm_mmu_page_role { unsigned level:4; unsigned quadrant:2; unsigned pad_for_nice_hex_output:6; - unsigned metaphysical:1; + unsigned direct:1; unsigned access:3; unsigned invalid:1; unsigned cr4_pge:1; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index de9a9fbc16e..ef060ec444a 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -1066,7 +1066,7 @@ static struct kvm_mmu_page *kvm_mmu_lookup_page(struct kvm *kvm, gfn_t gfn) index = kvm_page_table_hashfn(gfn); bucket = &kvm->arch.mmu_page_hash[index]; hlist_for_each_entry(sp, node, bucket, hash_link) - if (sp->gfn == gfn && !sp->role.metaphysical + if (sp->gfn == gfn && !sp->role.direct && !sp->role.invalid) { pgprintk("%s: found role %x\n", __func__, sp->role.word); @@ -1200,7 +1200,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, gfn_t gfn, gva_t gaddr, unsigned level, - int metaphysical, + int direct, unsigned access, u64 *parent_pte) { @@ -1213,7 +1213,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, role = vcpu->arch.mmu.base_role; role.level = level; - role.metaphysical = metaphysical; + role.direct = direct; role.access = access; if (vcpu->arch.mmu.root_level <= PT32_ROOT_LEVEL) { quadrant = gaddr >> (PAGE_SHIFT + (PT64_PT_BITS * level)); @@ -1250,7 +1250,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, sp->role = role; sp->global = role.cr4_pge; hlist_add_head(&sp->hash_link, bucket); - if (!metaphysical) { + if (!direct) { if (rmap_write_protect(vcpu->kvm, gfn)) kvm_flush_remote_tlbs(vcpu->kvm); account_shadowed(vcpu->kvm, gfn); @@ -1395,7 +1395,7 @@ static int kvm_mmu_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp) kvm_mmu_page_unlink_children(kvm, sp); kvm_mmu_unlink_parents(kvm, sp); kvm_flush_remote_tlbs(kvm); - if (!sp->role.invalid && !sp->role.metaphysical) + if (!sp->role.invalid && !sp->role.direct) unaccount_shadowed(kvm, sp->gfn); if (sp->unsync) kvm_unlink_unsync_page(kvm, sp); @@ -1458,7 +1458,7 @@ static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) index = kvm_page_table_hashfn(gfn); bucket = &kvm->arch.mmu_page_hash[index]; hlist_for_each_entry_safe(sp, node, n, bucket, hash_link) - if (sp->gfn == gfn && !sp->role.metaphysical) { + if (sp->gfn == gfn && !sp->role.direct) { pgprintk("%s: gfn %lx role %x\n", __func__, gfn, sp->role.word); r = 1; @@ -1478,7 +1478,7 @@ static void mmu_unshadow(struct kvm *kvm, gfn_t gfn) index = kvm_page_table_hashfn(gfn); bucket = &kvm->arch.mmu_page_hash[index]; hlist_for_each_entry_safe(sp, node, nn, bucket, hash_link) { - if (sp->gfn == gfn && !sp->role.metaphysical + if (sp->gfn == gfn && !sp->role.direct && !sp->role.invalid) { pgprintk("%s: zap %lx %x\n", __func__, gfn, sp->role.word); @@ -1638,7 +1638,7 @@ static int kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) bucket = &vcpu->kvm->arch.mmu_page_hash[index]; /* don't unsync if pagetable is shadowed with multiple roles */ hlist_for_each_entry_safe(s, node, n, bucket, hash_link) { - if (s->gfn != sp->gfn || s->role.metaphysical) + if (s->gfn != sp->gfn || s->role.direct) continue; if (s->role.word != sp->role.word) return 1; @@ -1951,7 +1951,7 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu) int i; gfn_t root_gfn; struct kvm_mmu_page *sp; - int metaphysical = 0; + int direct = 0; root_gfn = vcpu->arch.cr3 >> PAGE_SHIFT; @@ -1960,18 +1960,18 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu) ASSERT(!VALID_PAGE(root)); if (tdp_enabled) - metaphysical = 1; + direct = 1; sp = kvm_mmu_get_page(vcpu, root_gfn, 0, - PT64_ROOT_LEVEL, metaphysical, + PT64_ROOT_LEVEL, direct, ACC_ALL, NULL); root = __pa(sp->spt); ++sp->root_count; vcpu->arch.mmu.root_hpa = root; return; } - metaphysical = !is_paging(vcpu); + direct = !is_paging(vcpu); if (tdp_enabled) - metaphysical = 1; + direct = 1; for (i = 0; i < 4; ++i) { hpa_t root = vcpu->arch.mmu.pae_root[i]; @@ -1985,7 +1985,7 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu) } else if (vcpu->arch.mmu.root_level == 0) root_gfn = 0; sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30, - PT32_ROOT_LEVEL, metaphysical, + PT32_ROOT_LEVEL, direct, ACC_ALL, NULL); root = __pa(sp->spt); ++sp->root_count; @@ -2487,7 +2487,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, index = kvm_page_table_hashfn(gfn); bucket = &vcpu->kvm->arch.mmu_page_hash[index]; hlist_for_each_entry_safe(sp, node, n, bucket, hash_link) { - if (sp->gfn != gfn || sp->role.metaphysical || sp->role.invalid) + if (sp->gfn != gfn || sp->role.direct || sp->role.invalid) continue; pte_size = sp->role.glevels == PT32_ROOT_LEVEL ? 4 : 8; misaligned = (offset ^ (offset + bytes - 1)) & ~(pte_size - 1); @@ -3125,7 +3125,7 @@ static void audit_write_protection(struct kvm_vcpu *vcpu) gfn_t gfn; list_for_each_entry(sp, &vcpu->kvm->arch.active_mmu_pages, link) { - if (sp->role.metaphysical) + if (sp->role.direct) continue; gfn = unalias_gfn(vcpu->kvm, sp->gfn); diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 46b68f941f6..7314c0944c5 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -277,7 +277,7 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, unsigned access = gw->pt_access; struct kvm_mmu_page *shadow_page; u64 spte, *sptep; - int metaphysical; + int direct; gfn_t table_gfn; int r; int level; @@ -313,17 +313,17 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, if (level == PT_DIRECTORY_LEVEL && gw->level == PT_DIRECTORY_LEVEL) { - metaphysical = 1; + direct = 1; if (!is_dirty_pte(gw->ptes[level - 1])) access &= ~ACC_WRITE_MASK; table_gfn = gpte_to_gfn(gw->ptes[level - 1]); } else { - metaphysical = 0; + direct = 0; table_gfn = gw->table_gfn[level - 2]; } shadow_page = kvm_mmu_get_page(vcpu, table_gfn, addr, level-1, - metaphysical, access, sptep); - if (!metaphysical) { + direct, access, sptep); + if (!direct) { r = kvm_read_guest_atomic(vcpu->kvm, gw->pte_gpa[level - 2], &curr_pte, sizeof(curr_pte)); @@ -512,7 +512,7 @@ static void FNAME(prefetch_page)(struct kvm_vcpu *vcpu, pt_element_t pt[256 / sizeof(pt_element_t)]; gpa_t pte_gpa; - if (sp->role.metaphysical + if (sp->role.direct || (PTTYPE == 32 && sp->role.level > PT_PAGE_TABLE_LEVEL)) { nonpaging_prefetch_page(vcpu, sp); return; -- cgit v1.2.3-70-g09d2 From 91b2ae773d3b168b763237fac33f75b13d891f20 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Mon, 19 Jan 2009 14:57:52 +0200 Subject: KVM: Avoid using CONFIG_ in userspace visible headers Kconfig symbols are not available in userspace, and are not stripped by headers-install. Avoid their use by adding #defines in to suit each architecture. Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm.h | 1 + include/linux/kvm.h | 6 +++--- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h index 54bcf228152..dc3f6cf1170 100644 --- a/arch/x86/include/asm/kvm.h +++ b/arch/x86/include/asm/kvm.h @@ -15,6 +15,7 @@ #define __KVM_HAVE_DEVICE_ASSIGNMENT #define __KVM_HAVE_MSI #define __KVM_HAVE_USER_NMI +#define __KVM_HAVE_GUEST_DEBUG /* Architectural interrupt line count. */ #define KVM_NR_INTERRUPTS 256 diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 7a5d73a8d4f..869462ca762 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -393,13 +393,13 @@ struct kvm_trace_rec { #ifdef __KVM_HAVE_USER_NMI #define KVM_CAP_USER_NMI 22 #endif -#if defined(CONFIG_X86) +#ifdef __KVM_HAVE_GUEST_DEBUG #define KVM_CAP_SET_GUEST_DEBUG 23 #endif -#if defined(CONFIG_X86) +#ifdef __KVM_HAVE_PIT #define KVM_CAP_REINJECT_CONTROL 24 #endif -#if defined(CONFIG_X86)||defined(CONFIG_IA64) +#ifdef __KVM_HAVE_IOAPIC #define KVM_CAP_IRQ_ROUTING 25 #endif -- cgit v1.2.3-70-g09d2 From d20626936dd6aa783760e780dae5abb127564316 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Mon, 2 Feb 2009 16:23:50 +0100 Subject: x86: Add EFER descriptions for FFXSR AMD k10 includes support for the FFXSR feature, which leaves out XMM registers on FXSAVE/FXSAVE when the EFER_FFXSR bit is set in EFER. The CPUID feature bit exists already, but the EFER bit is missing currently, so this patch adds it to the list of known EFER bits. Signed-off-by: Alexander Graf CC: Joerg Roedel Signed-off-by: Avi Kivity --- arch/x86/include/asm/msr-index.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 46e9646e7a6..f4e505f286b 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -19,12 +19,14 @@ #define _EFER_LMA 10 /* Long mode active (read-only) */ #define _EFER_NX 11 /* No execute enable */ #define _EFER_SVME 12 /* Enable virtualization */ +#define _EFER_FFXSR 14 /* Enable Fast FXSAVE/FXRSTOR */ #define EFER_SCE (1<<_EFER_SCE) #define EFER_LME (1<<_EFER_LME) #define EFER_LMA (1<<_EFER_LMA) #define EFER_NX (1<<_EFER_NX) #define EFER_SVME (1<<_EFER_SVME) +#define EFER_FFXSR (1<<_EFER_FFXSR) /* Intel MSRs. Some also available on other CPUs */ #define MSR_IA32_PERFCTR0 0x000000c1 -- cgit v1.2.3-70-g09d2 From 4925663a079c77d95d8685228ad6675fc5639c8e Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Wed, 4 Feb 2009 17:28:14 +0200 Subject: KVM: Report IRQ injection status to userspace. IRQ injection status is either -1 (if there was no CPU found that should except the interrupt because IRQ was masked or ioapic was misconfigured or ...) or >= 0 in that case the number indicates to how many CPUs interrupt was injected. If the value is 0 it means that the interrupt was coalesced and probably should be reinjected. Signed-off-by: Gleb Natapov Signed-off-by: Avi Kivity --- arch/ia64/kvm/kvm-ia64.c | 12 ++++++++++-- arch/x86/include/asm/kvm_host.h | 2 +- arch/x86/kvm/i8259.c | 18 +++++++++++++----- arch/x86/kvm/x86.c | 13 +++++++++++-- include/linux/kvm.h | 7 ++++++- include/linux/kvm_host.h | 4 ++-- virt/kvm/ioapic.c | 23 ++++++++++++++++------- virt/kvm/ioapic.h | 2 +- virt/kvm/irq_comm.c | 41 ++++++++++++++++++++++++++++------------- 9 files changed, 88 insertions(+), 34 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index 9c77e3939e9..076b00d1dbf 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -182,7 +182,7 @@ int kvm_dev_ioctl_check_extension(long ext) switch (ext) { case KVM_CAP_IRQCHIP: case KVM_CAP_MP_STATE: - + case KVM_CAP_IRQ_INJECT_STATUS: r = 1; break; case KVM_CAP_COALESCED_MMIO: @@ -927,6 +927,7 @@ long kvm_arch_vm_ioctl(struct file *filp, goto out; } break; + case KVM_IRQ_LINE_STATUS: case KVM_IRQ_LINE: { struct kvm_irq_level irq_event; @@ -934,10 +935,17 @@ long kvm_arch_vm_ioctl(struct file *filp, if (copy_from_user(&irq_event, argp, sizeof irq_event)) goto out; if (irqchip_in_kernel(kvm)) { + __s32 status; mutex_lock(&kvm->lock); - kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, + status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irq_event.irq, irq_event.level); mutex_unlock(&kvm->lock); + if (ioctl == KVM_IRQ_LINE_STATUS) { + irq_event.status = status; + if (copy_to_user(argp, &irq_event, + sizeof irq_event)) + goto out; + } r = 0; } break; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 55fd4c5fd38..f0faf58044f 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -616,7 +616,7 @@ void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code); void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long cr2, u32 error_code); -void kvm_pic_set_irq(void *opaque, int irq, int level); +int kvm_pic_set_irq(void *opaque, int irq, int level); void kvm_inject_nmi(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 93160375c84..b4e662e94dd 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -77,12 +77,13 @@ void kvm_pic_clear_isr_ack(struct kvm *kvm) /* * set irq level. If an edge is detected, then the IRR is set to 1 */ -static inline void pic_set_irq1(struct kvm_kpic_state *s, int irq, int level) +static inline int pic_set_irq1(struct kvm_kpic_state *s, int irq, int level) { - int mask; + int mask, ret = 1; mask = 1 << irq; if (s->elcr & mask) /* level triggered */ if (level) { + ret = !(s->irr & mask); s->irr |= mask; s->last_irr |= mask; } else { @@ -91,11 +92,15 @@ static inline void pic_set_irq1(struct kvm_kpic_state *s, int irq, int level) } else /* edge triggered */ if (level) { - if ((s->last_irr & mask) == 0) + if ((s->last_irr & mask) == 0) { + ret = !(s->irr & mask); s->irr |= mask; + } s->last_irr |= mask; } else s->last_irr &= ~mask; + + return (s->imr & mask) ? -1 : ret; } /* @@ -172,16 +177,19 @@ void kvm_pic_update_irq(struct kvm_pic *s) pic_unlock(s); } -void kvm_pic_set_irq(void *opaque, int irq, int level) +int kvm_pic_set_irq(void *opaque, int irq, int level) { struct kvm_pic *s = opaque; + int ret = -1; pic_lock(s); if (irq >= 0 && irq < PIC_NUM_PINS) { - pic_set_irq1(&s->pics[irq >> 3], irq & 7, level); + ret = pic_set_irq1(&s->pics[irq >> 3], irq & 7, level); pic_update_irq(s); } pic_unlock(s); + + return ret; } /* diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 05d7be89b5e..e4db5be7c95 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1019,6 +1019,7 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_MP_STATE: case KVM_CAP_SYNC_MMU: case KVM_CAP_REINJECT_CONTROL: + case KVM_CAP_IRQ_INJECT_STATUS: r = 1; break; case KVM_CAP_COALESCED_MMIO: @@ -1877,6 +1878,7 @@ long kvm_arch_vm_ioctl(struct file *filp, create_pit_unlock: mutex_unlock(&kvm->lock); break; + case KVM_IRQ_LINE_STATUS: case KVM_IRQ_LINE: { struct kvm_irq_level irq_event; @@ -1884,10 +1886,17 @@ long kvm_arch_vm_ioctl(struct file *filp, if (copy_from_user(&irq_event, argp, sizeof irq_event)) goto out; if (irqchip_in_kernel(kvm)) { + __s32 status; mutex_lock(&kvm->lock); - kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, - irq_event.irq, irq_event.level); + status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, + irq_event.irq, irq_event.level); mutex_unlock(&kvm->lock); + if (ioctl == KVM_IRQ_LINE_STATUS) { + irq_event.status = status; + if (copy_to_user(argp, &irq_event, + sizeof irq_event)) + goto out; + } r = 0; } break; diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 2163b3dd36e..dd48225d182 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -48,7 +48,10 @@ struct kvm_irq_level { * For IA-64 (APIC model) IOAPIC0: irq 0-23; IOAPIC1: irq 24-47.. * For X86 (standard AT mode) PIC0/1: irq 0-15. IOAPIC0: 0-23.. */ - __u32 irq; + union { + __u32 irq; + __s32 status; + }; __u32 level; }; @@ -402,6 +405,7 @@ struct kvm_trace_rec { #ifdef __KVM_HAVE_IOAPIC #define KVM_CAP_IRQ_ROUTING 25 #endif +#define KVM_CAP_IRQ_INJECT_STATUS 26 #ifdef KVM_CAP_IRQ_ROUTING @@ -465,6 +469,7 @@ struct kvm_irq_routing { #define KVM_CREATE_PIT _IO(KVMIO, 0x64) #define KVM_GET_PIT _IOWR(KVMIO, 0x65, struct kvm_pit_state) #define KVM_SET_PIT _IOR(KVMIO, 0x66, struct kvm_pit_state) +#define KVM_IRQ_LINE_STATUS _IOWR(KVMIO, 0x67, struct kvm_irq_level) #define KVM_REGISTER_COALESCED_MMIO \ _IOW(KVMIO, 0x67, struct kvm_coalesced_mmio_zone) #define KVM_UNREGISTER_COALESCED_MMIO \ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 18b4df8264c..894a56e365e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -110,7 +110,7 @@ struct kvm_memory_slot { struct kvm_kernel_irq_routing_entry { u32 gsi; - void (*set)(struct kvm_kernel_irq_routing_entry *e, + int (*set)(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int level); union { struct { @@ -352,7 +352,7 @@ void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq, struct kvm_irq_mask_notifier *kimn); void kvm_fire_mask_notifiers(struct kvm *kvm, int irq, bool mask); -void kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level); +int kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level); void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin); void kvm_register_irq_ack_notifier(struct kvm *kvm, struct kvm_irq_ack_notifier *kian); diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c index 1c986ac59ad..c3b99def9cb 100644 --- a/virt/kvm/ioapic.c +++ b/virt/kvm/ioapic.c @@ -83,19 +83,22 @@ static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic, return result; } -static void ioapic_service(struct kvm_ioapic *ioapic, unsigned int idx) +static int ioapic_service(struct kvm_ioapic *ioapic, unsigned int idx) { union ioapic_redir_entry *pent; + int injected = -1; pent = &ioapic->redirtbl[idx]; if (!pent->fields.mask) { - int injected = ioapic_deliver(ioapic, idx); + injected = ioapic_deliver(ioapic, idx); if (injected && pent->fields.trig_mode == IOAPIC_LEVEL_TRIG) pent->fields.remote_irr = 1; } if (!pent->fields.trig_mode) ioapic->irr &= ~(1 << idx); + + return injected; } static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) @@ -207,7 +210,7 @@ static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq) u8 trig_mode = ioapic->redirtbl[irq].fields.trig_mode; u32 deliver_bitmask; struct kvm_vcpu *vcpu; - int vcpu_id, r = 0; + int vcpu_id, r = -1; ioapic_debug("dest=%x dest_mode=%x delivery_mode=%x " "vector=%x trig_mode=%x\n", @@ -247,7 +250,9 @@ static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq) deliver_bitmask &= ~(1 << vcpu_id); vcpu = ioapic->kvm->vcpus[vcpu_id]; if (vcpu) { - r = ioapic_inj_irq(ioapic, vcpu, vector, + if (r < 0) + r = 0; + r += ioapic_inj_irq(ioapic, vcpu, vector, trig_mode, delivery_mode); } } @@ -258,8 +263,10 @@ static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq) continue; deliver_bitmask &= ~(1 << vcpu_id); vcpu = ioapic->kvm->vcpus[vcpu_id]; - if (vcpu) + if (vcpu) { ioapic_inj_nmi(vcpu); + r = 1; + } else ioapic_debug("NMI to vcpu %d failed\n", vcpu->vcpu_id); @@ -273,11 +280,12 @@ static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq) return r; } -void kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level) +int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level) { u32 old_irr = ioapic->irr; u32 mask = 1 << irq; union ioapic_redir_entry entry; + int ret = 1; if (irq >= 0 && irq < IOAPIC_NUM_PINS) { entry = ioapic->redirtbl[irq]; @@ -288,9 +296,10 @@ void kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level) ioapic->irr |= mask; if ((!entry.fields.trig_mode && old_irr != ioapic->irr) || !entry.fields.remote_irr) - ioapic_service(ioapic, irq); + ret = ioapic_service(ioapic, irq); } } + return ret; } static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int pin, diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h index 49c9581d258..a34bd5e6436 100644 --- a/virt/kvm/ioapic.h +++ b/virt/kvm/ioapic.h @@ -83,7 +83,7 @@ struct kvm_vcpu *kvm_get_lowest_prio_vcpu(struct kvm *kvm, u8 vector, unsigned long bitmap); void kvm_ioapic_update_eoi(struct kvm *kvm, int vector, int trigger_mode); int kvm_ioapic_init(struct kvm *kvm); -void kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level); +int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level); void kvm_ioapic_reset(struct kvm_ioapic *ioapic); u32 kvm_ioapic_get_delivery_bitmask(struct kvm_ioapic *ioapic, u8 dest, u8 dest_mode); diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index 6bc7439eff6..be8aba79155 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -29,22 +29,24 @@ #include "ioapic.h" -static void kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm, int level) +static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e, + struct kvm *kvm, int level) { #ifdef CONFIG_X86 - kvm_pic_set_irq(pic_irqchip(kvm), e->irqchip.pin, level); + return kvm_pic_set_irq(pic_irqchip(kvm), e->irqchip.pin, level); +#else + return -1; #endif } -static void kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm, int level) +static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e, + struct kvm *kvm, int level) { - kvm_ioapic_set_irq(kvm->arch.vioapic, e->irqchip.pin, level); + return kvm_ioapic_set_irq(kvm->arch.vioapic, e->irqchip.pin, level); } -static void kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm, int level) +static int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, + struct kvm *kvm, int level) { int vcpu_id; struct kvm_vcpu *vcpu; @@ -88,13 +90,20 @@ static void kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, default: break; } + return 1; } -/* This should be called with the kvm->lock mutex held */ -void kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level) +/* This should be called with the kvm->lock mutex held + * Return value: + * < 0 Interrupt was ignored (masked or not delivered for other reasons) + * = 0 Interrupt was coalesced (previous irq is still pending) + * > 0 Number of CPUs interrupt was delivered to + */ +int kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level) { struct kvm_kernel_irq_routing_entry *e; unsigned long *irq_state, sig_level; + int ret = -1; if (irq < KVM_IOAPIC_NUM_PINS) { irq_state = (unsigned long *)&kvm->arch.irq_states[irq]; @@ -113,8 +122,14 @@ void kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level) * writes to the unused one. */ list_for_each_entry(e, &kvm->irq_routing, link) - if (e->gsi == irq) - e->set(e, kvm, sig_level); + if (e->gsi == irq) { + int r = e->set(e, kvm, sig_level); + if (r < 0) + continue; + + ret = r + ((ret < 0) ? 0 : ret); + } + return ret; } void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin) @@ -232,7 +247,7 @@ int setup_routing_entry(struct kvm_kernel_irq_routing_entry *e, e->set = kvm_set_pic_irq; break; case KVM_IRQCHIP_PIC_SLAVE: - e->set = kvm_set_pic_irq; + e->set = kvm_set_pic_irq; delta = 8; break; case KVM_IRQCHIP_IOAPIC: -- cgit v1.2.3-70-g09d2 From f56e5034121c4911a155ba907076ab920754626d Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Tue, 24 Mar 2009 14:16:30 -0700 Subject: x86: use default_cpu_mask_to_apicid for 64bit Impact: cleanup Use online_mask directly on 64bit too. Signed-off-by: Yinghai Lu Cc: Andrew Morton Cc: "Eric W. Biederman" Cc: Rusty Russell LKML-Reference: <49C94DAE.9070300@kernel.org> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/apic.h | 20 ++++++++++---------- arch/x86/kernel/apic/apic_flat_64.c | 18 ++---------------- 2 files changed, 12 insertions(+), 26 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 00f5962d82d..130a9e2b458 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -489,10 +489,19 @@ static inline int default_apic_id_registered(void) return physid_isset(read_apic_id(), phys_cpu_present_map); } +static inline int default_phys_pkg_id(int cpuid_apic, int index_msb) +{ + return cpuid_apic >> index_msb; +} + +extern int default_apicid_to_node(int logical_apicid); + +#endif + static inline unsigned int default_cpu_mask_to_apicid(const struct cpumask *cpumask) { - return cpumask_bits(cpumask)[0]; + return cpumask_bits(cpumask)[0] & APIC_ALL_CPUS; } static inline unsigned int @@ -506,15 +515,6 @@ default_cpu_mask_to_apicid_and(const struct cpumask *cpumask, return (unsigned int)(mask1 & mask2 & mask3); } -static inline int default_phys_pkg_id(int cpuid_apic, int index_msb) -{ - return cpuid_apic >> index_msb; -} - -extern int default_apicid_to_node(int logical_apicid); - -#endif - static inline unsigned long default_check_apicid_used(physid_mask_t bitmap, int apicid) { return physid_isset(apicid, bitmap); diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index f933822dba1..0014714ea97 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -159,20 +159,6 @@ static int flat_apic_id_registered(void) return physid_isset(read_xapic_id(), phys_cpu_present_map); } -static unsigned int flat_cpu_mask_to_apicid(const struct cpumask *cpumask) -{ - return cpumask_bits(cpumask)[0] & APIC_ALL_CPUS; -} - -static unsigned int flat_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask) -{ - unsigned long mask1 = cpumask_bits(cpumask)[0] & APIC_ALL_CPUS; - unsigned long mask2 = cpumask_bits(andmask)[0] & APIC_ALL_CPUS; - - return mask1 & mask2; -} - static int flat_phys_pkg_id(int initial_apic_id, int index_msb) { return hard_smp_processor_id() >> index_msb; @@ -213,8 +199,8 @@ struct apic apic_flat = { .set_apic_id = set_apic_id, .apic_id_mask = 0xFFu << 24, - .cpu_mask_to_apicid = flat_cpu_mask_to_apicid, - .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid = default_cpu_mask_to_apicid, + .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, .send_IPI_mask = flat_send_IPI_mask, .send_IPI_mask_allbutself = flat_send_IPI_mask_allbutself, -- cgit v1.2.3-70-g09d2 From 70511134f61bd6e5eed19f767381f9fb3e762d49 Mon Sep 17 00:00:00 2001 From: Ravikiran G Thirumalai Date: Mon, 23 Mar 2009 23:14:29 -0700 Subject: Revert "x86: don't compile vsmp_64 for 32bit" Partial revert of commit 129d8bc828e011bda0b7110a097bf3a0167f966e titled 'x86: don't compile vsmp_64 for 32bit' Commit reverted to compile vsmp_64.c if CONFIG_X86_64 is defined, since is_vsmp_box() needs to indicate that TSCs are not synchronized, and hence, not a valid time source, even when CONFIG_X86_VSMP is not defined. Signed-off-by: Ravikiran Thirumalai Cc: Yinghai Lu Cc: Andrew Morton Cc: shai@scalex86.org LKML-Reference: <20090324061429.GH7278@localdomain> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/apic.h | 2 +- arch/x86/include/asm/setup.h | 2 +- arch/x86/kernel/Makefile | 2 +- arch/x86/kernel/vsmp_64.c | 12 +++++++++++- 4 files changed, 14 insertions(+), 4 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 130a9e2b458..df8a300dfe6 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -75,7 +75,7 @@ static inline void default_inquire_remote_apic(int apicid) #define setup_secondary_clock setup_secondary_APIC_clock #endif -#ifdef CONFIG_X86_VSMP +#ifdef CONFIG_X86_64 extern int is_vsmp_box(void); #else static inline int is_vsmp_box(void) diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index fbf0521eeed..bdc2ada05ae 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -64,7 +64,7 @@ extern void x86_quirk_time_init(void); #include /* Interrupt control for vSMPowered x86_64 systems */ -#ifdef CONFIG_X86_VSMP +#ifdef CONFIG_X86_64 void vsmp_init(void); #else static inline void vsmp_init(void) { } diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 339ce35648e..6e9c1f320ac 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -70,7 +70,6 @@ obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o obj-$(CONFIG_KEXEC) += machine_kexec_$(BITS).o obj-$(CONFIG_KEXEC) += relocate_kernel_$(BITS).o crash.o obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o -obj-$(CONFIG_X86_VSMP) += vsmp_64.o obj-$(CONFIG_KPROBES) += kprobes.o obj-$(CONFIG_MODULES) += module_$(BITS).o obj-$(CONFIG_EFI) += efi.o efi_$(BITS).o efi_stub_$(BITS).o @@ -120,4 +119,5 @@ ifeq ($(CONFIG_X86_64),y) obj-$(CONFIG_AMD_IOMMU) += amd_iommu_init.o amd_iommu.o obj-$(CONFIG_PCI_MMCONFIG) += mmconf-fam10h_64.o + obj-y += vsmp_64.o endif diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c index 74de562812c..a1d804bcd48 100644 --- a/arch/x86/kernel/vsmp_64.c +++ b/arch/x86/kernel/vsmp_64.c @@ -22,7 +22,7 @@ #include #include -#ifdef CONFIG_PARAVIRT +#if defined CONFIG_PCI && defined CONFIG_PARAVIRT /* * Interrupt control on vSMPowered systems: * ~AC is a shadow of IF. If IF is 'on' AC should be 'off' @@ -114,6 +114,7 @@ static void __init set_vsmp_pv_ops(void) } #endif +#ifdef CONFIG_PCI static int is_vsmp = -1; static void __init detect_vsmp_box(void) @@ -139,6 +140,15 @@ int is_vsmp_box(void) } } +#else +static void __init detect_vsmp_box(void) +{ +} +int is_vsmp_box(void) +{ + return 0; +} +#endif void __init vsmp_init(void) { detect_vsmp_box(); -- cgit v1.2.3-70-g09d2 From 17d140402e6f0fd5dde2fdf8d045e3f95f865663 Mon Sep 17 00:00:00 2001 From: Cyrill Gorcunov Date: Wed, 14 Jan 2009 23:37:50 +0300 Subject: x86: headers cleanup - setup.h Impact: cleanup 'make headers_check' warn us about leaking of kernel private (mostly compile time vars) data to userspace in headers. Fix it. Guard this one by __KERNEL__. Signed-off-by: Cyrill Gorcunov Signed-off-by: H. Peter Anvin Signed-off-by: Ingo Molnar --- arch/x86/include/asm/setup.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 5a3a1371575..c2308f5250f 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -1,6 +1,8 @@ #ifndef _ASM_X86_SETUP_H #define _ASM_X86_SETUP_H +#ifdef __KERNEL__ + #define COMMAND_LINE_SIZE 2048 #ifndef __ASSEMBLY__ @@ -33,8 +35,6 @@ struct x86_quirks { #endif /* __ASSEMBLY__ */ -#ifdef __KERNEL__ - #ifdef __i386__ #include -- cgit v1.2.3-70-g09d2 From 2b1c6bd77d4e6a727ffac8630cd154b2144b751a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 28 Nov 2008 10:09:09 +0100 Subject: generic compat_sys_ustat Due to a different size of ino_t ustat needs a compat handler, but currently only x86 and mips provide one. Add a generic compat_sys_ustat and switch all architectures over to it. Instead of doing various user copy hacks compat_sys_ustat just reimplements sys_ustat as it's trivial. This was suggested by Arnd Bergmann. Found by Eric Sandeen when running xfstests/017 on ppc64, which causes stack smashing warnings on RHEL/Fedora due to the too large amount of data writen by the syscall. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- arch/ia64/ia32/ia32_entry.S | 2 +- arch/mips/kernel/linux32.c | 34 ---------------------------------- arch/mips/kernel/scall64-n32.S | 2 +- arch/mips/kernel/scall64-o32.S | 2 +- arch/parisc/kernel/syscall_table.S | 2 +- arch/powerpc/include/asm/systbl.h | 2 +- arch/s390/kernel/compat_wrapper.S | 2 +- arch/x86/ia32/ia32entry.S | 2 +- arch/x86/ia32/sys_ia32.c | 22 ---------------------- arch/x86/include/asm/ia32.h | 7 ------- arch/x86/include/asm/sys_ia32.h | 2 -- fs/compat.c | 28 ++++++++++++++++++++++++++++ include/linux/compat.h | 8 ++++++++ 13 files changed, 43 insertions(+), 72 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/ia64/ia32/ia32_entry.S b/arch/ia64/ia32/ia32_entry.S index a46f8395e9a..af9405cd70e 100644 --- a/arch/ia64/ia32/ia32_entry.S +++ b/arch/ia64/ia32/ia32_entry.S @@ -240,7 +240,7 @@ ia32_syscall_table: data8 sys_ni_syscall data8 sys_umask /* 60 */ data8 sys_chroot - data8 sys_ustat + data8 compat_sys_ustat data8 sys_dup2 data8 sys_getppid data8 sys_getpgrp /* 65 */ diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c index 1a86f84fa94..784859cedef 100644 --- a/arch/mips/kernel/linux32.c +++ b/arch/mips/kernel/linux32.c @@ -356,40 +356,6 @@ SYSCALL_DEFINE1(32_personality, unsigned long, personality) return ret; } -/* ustat compatibility */ -struct ustat32 { - compat_daddr_t f_tfree; - compat_ino_t f_tinode; - char f_fname[6]; - char f_fpack[6]; -}; - -extern asmlinkage long sys_ustat(dev_t dev, struct ustat __user * ubuf); - -SYSCALL_DEFINE2(32_ustat, dev_t, dev, struct ustat32 __user *, ubuf32) -{ - int err; - struct ustat tmp; - struct ustat32 tmp32; - mm_segment_t old_fs = get_fs(); - - set_fs(KERNEL_DS); - err = sys_ustat(dev, (struct ustat __user *)&tmp); - set_fs(old_fs); - - if (err) - goto out; - - memset(&tmp32, 0, sizeof(struct ustat32)); - tmp32.f_tfree = tmp.f_tfree; - tmp32.f_tinode = tmp.f_tinode; - - err = copy_to_user(ubuf32, &tmp32, sizeof(struct ustat32)) ? -EFAULT : 0; - -out: - return err; -} - SYSCALL_DEFINE4(32_sendfile, long, out_fd, long, in_fd, compat_off_t __user *, offset, s32, count) { diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index 7438e92f8a0..f61d6b0e573 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -253,7 +253,7 @@ EXPORT(sysn32_call_table) PTR compat_sys_utime /* 6130 */ PTR sys_mknod PTR sys_32_personality - PTR sys_32_ustat + PTR compat_sys_ustat PTR compat_sys_statfs PTR compat_sys_fstatfs /* 6135 */ PTR sys_sysfs diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index b0fef4ff982..60997f1f69d 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -265,7 +265,7 @@ sys_call_table: PTR sys_olduname PTR sys_umask /* 4060 */ PTR sys_chroot - PTR sys_32_ustat + PTR compat_sys_ustat PTR sys_dup2 PTR sys_getppid PTR sys_getpgrp /* 4065 */ diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S index 303d2b647e4..03b9a01bc16 100644 --- a/arch/parisc/kernel/syscall_table.S +++ b/arch/parisc/kernel/syscall_table.S @@ -130,7 +130,7 @@ ENTRY_OURS(newuname) ENTRY_SAME(umask) /* 60 */ ENTRY_SAME(chroot) - ENTRY_SAME(ustat) + ENTRY_COMP(ustat) ENTRY_SAME(dup2) ENTRY_SAME(getppid) ENTRY_SAME(getpgrp) /* 65 */ diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h index 72353f6070a..fe166491e9d 100644 --- a/arch/powerpc/include/asm/systbl.h +++ b/arch/powerpc/include/asm/systbl.h @@ -65,7 +65,7 @@ SYSCALL(ni_syscall) SYSX(sys_ni_syscall,sys_olduname, sys_olduname) COMPAT_SYS_SPU(umask) SYSCALL_SPU(chroot) -SYSCALL(ustat) +COMPAT_SYS(ustat) SYSCALL_SPU(dup2) SYSCALL_SPU(getppid) SYSCALL_SPU(getpgrp) diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S index 62c706eb0de..87cf5a79a35 100644 --- a/arch/s390/kernel/compat_wrapper.S +++ b/arch/s390/kernel/compat_wrapper.S @@ -252,7 +252,7 @@ sys32_chroot_wrapper: sys32_ustat_wrapper: llgfr %r2,%r2 # dev_t llgtr %r3,%r3 # struct ustat * - jg sys_ustat + jg compat_sys_ustat .globl sys32_dup2_wrapper sys32_dup2_wrapper: diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 5a0d76dc56a..8ef8876666b 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -557,7 +557,7 @@ ia32_sys_call_table: .quad sys32_olduname .quad sys_umask /* 60 */ .quad sys_chroot - .quad sys32_ustat + .quad compat_sys_ustat .quad sys_dup2 .quad sys_getppid .quad sys_getpgrp /* 65 */ diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index 6c0d7f6231a..efac92fd1ef 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -638,28 +638,6 @@ long sys32_uname(struct old_utsname __user *name) return err ? -EFAULT : 0; } -long sys32_ustat(unsigned dev, struct ustat32 __user *u32p) -{ - struct ustat u; - mm_segment_t seg; - int ret; - - seg = get_fs(); - set_fs(KERNEL_DS); - ret = sys_ustat(dev, (struct ustat __user *)&u); - set_fs(seg); - if (ret < 0) - return ret; - - if (!access_ok(VERIFY_WRITE, u32p, sizeof(struct ustat32)) || - __put_user((__u32) u.f_tfree, &u32p->f_tfree) || - __put_user((__u32) u.f_tinode, &u32p->f_tfree) || - __copy_to_user(&u32p->f_fname, u.f_fname, sizeof(u.f_fname)) || - __copy_to_user(&u32p->f_fpack, u.f_fpack, sizeof(u.f_fpack))) - ret = -EFAULT; - return ret; -} - asmlinkage long sys32_execve(char __user *name, compat_uptr_t __user *argv, compat_uptr_t __user *envp, struct pt_regs *regs) { diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h index 50ca486fd88..1f7e6251728 100644 --- a/arch/x86/include/asm/ia32.h +++ b/arch/x86/include/asm/ia32.h @@ -129,13 +129,6 @@ typedef struct compat_siginfo { } _sifields; } compat_siginfo_t; -struct ustat32 { - __u32 f_tfree; - compat_ino_t f_tinode; - char f_fname[6]; - char f_fpack[6]; -}; - #define IA32_STACK_TOP IA32_PAGE_OFFSET #ifdef __KERNEL__ diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h index ffb08be2a53..72a6dcd1299 100644 --- a/arch/x86/include/asm/sys_ia32.h +++ b/arch/x86/include/asm/sys_ia32.h @@ -70,8 +70,6 @@ struct old_utsname; asmlinkage long sys32_olduname(struct oldold_utsname __user *); long sys32_uname(struct old_utsname __user *); -long sys32_ustat(unsigned, struct ustat32 __user *); - asmlinkage long sys32_execve(char __user *, compat_uptr_t __user *, compat_uptr_t __user *, struct pt_regs *); asmlinkage long sys32_clone(unsigned int, unsigned int, struct pt_regs *); diff --git a/fs/compat.c b/fs/compat.c index d0145ca2757..4e0db94b535 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -378,6 +378,34 @@ out: return error; } +/* + * This is a copy of sys_ustat, just dealing with a structure layout. + * Given how simple this syscall is that apporach is more maintainable + * than the various conversion hacks. + */ +asmlinkage long compat_sys_ustat(unsigned dev, struct compat_ustat __user *u) +{ + struct super_block *sb; + struct compat_ustat tmp; + struct kstatfs sbuf; + int err; + + sb = user_get_super(new_decode_dev(dev)); + if (!sb) + return -EINVAL; + err = vfs_statfs(sb->s_root, &sbuf); + drop_super(sb); + if (err) + return err; + + memset(&tmp, 0, sizeof(struct compat_ustat)); + tmp.f_tfree = sbuf.f_bfree; + tmp.f_tinode = sbuf.f_ffree; + if (copy_to_user(u, &tmp, sizeof(struct compat_ustat))) + return -EFAULT; + return 0; +} + static int get_compat_flock(struct flock *kfl, struct compat_flock __user *ufl) { if (!access_ok(VERIFY_READ, ufl, sizeof(*ufl)) || diff --git a/include/linux/compat.h b/include/linux/compat.h index 3fd2194ff57..b880864672d 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -125,6 +125,13 @@ struct compat_dirent { char d_name[256]; }; +struct compat_ustat { + compat_daddr_t f_tfree; + compat_ino_t f_tinode; + char f_fname[6]; + char f_fpack[6]; +}; + typedef union compat_sigval { compat_int_t sival_int; compat_uptr_t sival_ptr; @@ -178,6 +185,7 @@ long compat_sys_semtimedop(int semid, struct sembuf __user *tsems, unsigned nsems, const struct compat_timespec __user *timeout); asmlinkage long compat_sys_keyctl(u32 option, u32 arg2, u32 arg3, u32 arg4, u32 arg5); +asmlinkage long compat_sys_ustat(unsigned dev, struct compat_ustat __user *u32); asmlinkage ssize_t compat_sys_readv(unsigned long fd, const struct compat_iovec __user *vec, unsigned long vlen); -- cgit v1.2.3-70-g09d2 From 4cd8b5e2a159f18a1507f1187b44a1acbfa6341b Mon Sep 17 00:00:00 2001 From: Matias Zabaljauregui Date: Sat, 14 Mar 2009 13:37:52 -0200 Subject: lguest: use KVM hypercalls Impact: cleanup This patch allow us to use KVM hypercalls Signed-off-by: Matias Zabaljauregui Signed-off-by: Rusty Russell --- arch/x86/include/asm/lguest_hcall.h | 24 ++--------- arch/x86/lguest/boot.c | 78 ++++++++++++++++++++++------------- arch/x86/lguest/i386_head.S | 4 +- drivers/lguest/interrupts_and_traps.c | 7 ++-- drivers/lguest/lguest_device.c | 4 +- drivers/lguest/x86/core.c | 62 +++++++++++++++++++++++++++- 6 files changed, 122 insertions(+), 57 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/lguest_hcall.h b/arch/x86/include/asm/lguest_hcall.h index 43894428c3c..0f4ee7148af 100644 --- a/arch/x86/include/asm/lguest_hcall.h +++ b/arch/x86/include/asm/lguest_hcall.h @@ -26,36 +26,20 @@ #ifndef __ASSEMBLY__ #include +#include /*G:031 But first, how does our Guest contact the Host to ask for privileged * operations? There are two ways: the direct way is to make a "hypercall", * to make requests of the Host Itself. * - * Our hypercall mechanism uses the highest unused trap code (traps 32 and - * above are used by real hardware interrupts). Fifteen hypercalls are + * We use the KVM hypercall mechanism. Eighteen hypercalls are * available: the hypercall number is put in the %eax register, and the - * arguments (when required) are placed in %edx, %ebx and %ecx. If a return + * arguments (when required) are placed in %ebx, %ecx and %edx. If a return * value makes sense, it's returned in %eax. * * Grossly invalid calls result in Sudden Death at the hands of the vengeful * Host, rather than returning failure. This reflects Winston Churchill's * definition of a gentleman: "someone who is only rude intentionally". */ -static inline unsigned long -hcall(unsigned long call, - unsigned long arg1, unsigned long arg2, unsigned long arg3) -{ - /* "int" is the Intel instruction to trigger a trap. */ - asm volatile("int $" __stringify(LGUEST_TRAP_ENTRY) - /* The call in %eax (aka "a") might be overwritten */ - : "=a"(call) - /* The arguments are in %eax, %edx, %ebx & %ecx */ - : "a"(call), "d"(arg1), "b"(arg2), "c"(arg3) - /* "memory" means this might write somewhere in memory. - * This isn't true for all calls, but it's safe to tell - * gcc that it might happen so it doesn't get clever. */ - : "memory"); - return call; -} /*:*/ /* Can't use our min() macro here: needs to be a constant */ @@ -64,7 +48,7 @@ hcall(unsigned long call, #define LHCALL_RING_SIZE 64 struct hcall_args { /* These map directly onto eax, ebx, ecx, edx in struct lguest_regs */ - unsigned long arg0, arg2, arg3, arg1; + unsigned long arg0, arg1, arg2, arg3; }; #endif /* !__ASSEMBLY__ */ diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 7822d29b02c..5be9293961b 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -107,7 +107,7 @@ static void async_hcall(unsigned long call, unsigned long arg1, local_irq_save(flags); if (lguest_data.hcall_status[next_call] != 0xFF) { /* Table full, so do normal hcall which will flush table. */ - hcall(call, arg1, arg2, arg3); + kvm_hypercall3(call, arg1, arg2, arg3); } else { lguest_data.hcalls[next_call].arg0 = call; lguest_data.hcalls[next_call].arg1 = arg1; @@ -134,13 +134,32 @@ static void async_hcall(unsigned long call, unsigned long arg1, * * So, when we're in lazy mode, we call async_hcall() to store the call for * future processing: */ -static void lazy_hcall(unsigned long call, +static void lazy_hcall1(unsigned long call, + unsigned long arg1) +{ + if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) + kvm_hypercall1(call, arg1); + else + async_hcall(call, arg1, 0, 0); +} + +static void lazy_hcall2(unsigned long call, + unsigned long arg1, + unsigned long arg2) +{ + if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) + kvm_hypercall2(call, arg1, arg2); + else + async_hcall(call, arg1, arg2, 0); +} + +static void lazy_hcall3(unsigned long call, unsigned long arg1, unsigned long arg2, unsigned long arg3) { if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) - hcall(call, arg1, arg2, arg3); + kvm_hypercall3(call, arg1, arg2, arg3); else async_hcall(call, arg1, arg2, arg3); } @@ -150,7 +169,7 @@ static void lazy_hcall(unsigned long call, static void lguest_leave_lazy_mode(void) { paravirt_leave_lazy(paravirt_get_lazy_mode()); - hcall(LHCALL_FLUSH_ASYNC, 0, 0, 0); + kvm_hypercall0(LHCALL_FLUSH_ASYNC); } /*G:033 @@ -229,7 +248,7 @@ static void lguest_write_idt_entry(gate_desc *dt, /* Keep the local copy up to date. */ native_write_idt_entry(dt, entrynum, g); /* Tell Host about this new entry. */ - hcall(LHCALL_LOAD_IDT_ENTRY, entrynum, desc[0], desc[1]); + kvm_hypercall3(LHCALL_LOAD_IDT_ENTRY, entrynum, desc[0], desc[1]); } /* Changing to a different IDT is very rare: we keep the IDT up-to-date every @@ -241,7 +260,7 @@ static void lguest_load_idt(const struct desc_ptr *desc) struct desc_struct *idt = (void *)desc->address; for (i = 0; i < (desc->size+1)/8; i++) - hcall(LHCALL_LOAD_IDT_ENTRY, i, idt[i].a, idt[i].b); + kvm_hypercall3(LHCALL_LOAD_IDT_ENTRY, i, idt[i].a, idt[i].b); } /* @@ -261,8 +280,8 @@ static void lguest_load_idt(const struct desc_ptr *desc) */ static void lguest_load_gdt(const struct desc_ptr *desc) { - BUG_ON((desc->size+1)/8 != GDT_ENTRIES); - hcall(LHCALL_LOAD_GDT, __pa(desc->address), GDT_ENTRIES, 0); + BUG_ON((desc->size + 1) / 8 != GDT_ENTRIES); + kvm_hypercall2(LHCALL_LOAD_GDT, __pa(desc->address), GDT_ENTRIES); } /* For a single GDT entry which changes, we do the lazy thing: alter our GDT, @@ -272,7 +291,7 @@ static void lguest_write_gdt_entry(struct desc_struct *dt, int entrynum, const void *desc, int type) { native_write_gdt_entry(dt, entrynum, desc, type); - hcall(LHCALL_LOAD_GDT, __pa(dt), GDT_ENTRIES, 0); + kvm_hypercall2(LHCALL_LOAD_GDT, __pa(dt), GDT_ENTRIES); } /* OK, I lied. There are three "thread local storage" GDT entries which change @@ -284,7 +303,7 @@ static void lguest_load_tls(struct thread_struct *t, unsigned int cpu) * can't handle us removing entries we're currently using. So we clear * the GS register here: if it's needed it'll be reloaded anyway. */ lazy_load_gs(0); - lazy_hcall(LHCALL_LOAD_TLS, __pa(&t->tls_array), cpu, 0); + lazy_hcall2(LHCALL_LOAD_TLS, __pa(&t->tls_array), cpu); } /*G:038 That's enough excitement for now, back to ploughing through each of @@ -382,7 +401,7 @@ static void lguest_cpuid(unsigned int *ax, unsigned int *bx, static unsigned long current_cr0; static void lguest_write_cr0(unsigned long val) { - lazy_hcall(LHCALL_TS, val & X86_CR0_TS, 0, 0); + lazy_hcall1(LHCALL_TS, val & X86_CR0_TS); current_cr0 = val; } @@ -396,7 +415,7 @@ static unsigned long lguest_read_cr0(void) * the vowels have been optimized out. */ static void lguest_clts(void) { - lazy_hcall(LHCALL_TS, 0, 0, 0); + lazy_hcall1(LHCALL_TS, 0); current_cr0 &= ~X86_CR0_TS; } @@ -418,7 +437,7 @@ static bool cr3_changed = false; static void lguest_write_cr3(unsigned long cr3) { lguest_data.pgdir = cr3; - lazy_hcall(LHCALL_NEW_PGTABLE, cr3, 0, 0); + lazy_hcall1(LHCALL_NEW_PGTABLE, cr3); cr3_changed = true; } @@ -493,7 +512,7 @@ static void lguest_write_cr4(unsigned long val) static void lguest_pte_update(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - lazy_hcall(LHCALL_SET_PTE, __pa(mm->pgd), addr, ptep->pte_low); + lazy_hcall3(LHCALL_SET_PTE, __pa(mm->pgd), addr, ptep->pte_low); } static void lguest_set_pte_at(struct mm_struct *mm, unsigned long addr, @@ -509,8 +528,8 @@ static void lguest_set_pte_at(struct mm_struct *mm, unsigned long addr, static void lguest_set_pmd(pmd_t *pmdp, pmd_t pmdval) { *pmdp = pmdval; - lazy_hcall(LHCALL_SET_PMD, __pa(pmdp)&PAGE_MASK, - (__pa(pmdp)&(PAGE_SIZE-1))/4, 0); + lazy_hcall2(LHCALL_SET_PMD, __pa(pmdp) & PAGE_MASK, + (__pa(pmdp) & (PAGE_SIZE - 1)) / 4); } /* There are a couple of legacy places where the kernel sets a PTE, but we @@ -526,7 +545,7 @@ static void lguest_set_pte(pte_t *ptep, pte_t pteval) { *ptep = pteval; if (cr3_changed) - lazy_hcall(LHCALL_FLUSH_TLB, 1, 0, 0); + lazy_hcall1(LHCALL_FLUSH_TLB, 1); } /* Unfortunately for Lguest, the pv_mmu_ops for page tables were based on @@ -542,7 +561,7 @@ static void lguest_set_pte(pte_t *ptep, pte_t pteval) static void lguest_flush_tlb_single(unsigned long addr) { /* Simply set it to zero: if it was not, it will fault back in. */ - lazy_hcall(LHCALL_SET_PTE, lguest_data.pgdir, addr, 0); + lazy_hcall3(LHCALL_SET_PTE, lguest_data.pgdir, addr, 0); } /* This is what happens after the Guest has removed a large number of entries. @@ -550,7 +569,7 @@ static void lguest_flush_tlb_single(unsigned long addr) * have changed, ie. virtual addresses below PAGE_OFFSET. */ static void lguest_flush_tlb_user(void) { - lazy_hcall(LHCALL_FLUSH_TLB, 0, 0, 0); + lazy_hcall1(LHCALL_FLUSH_TLB, 0); } /* This is called when the kernel page tables have changed. That's not very @@ -558,7 +577,7 @@ static void lguest_flush_tlb_user(void) * slow), so it's worth separating this from the user flushing above. */ static void lguest_flush_tlb_kernel(void) { - lazy_hcall(LHCALL_FLUSH_TLB, 1, 0, 0); + lazy_hcall1(LHCALL_FLUSH_TLB, 1); } /* @@ -695,7 +714,7 @@ static int lguest_clockevent_set_next_event(unsigned long delta, } /* Please wake us this far in the future. */ - hcall(LHCALL_SET_CLOCKEVENT, delta, 0, 0); + kvm_hypercall1(LHCALL_SET_CLOCKEVENT, delta); return 0; } @@ -706,7 +725,7 @@ static void lguest_clockevent_set_mode(enum clock_event_mode mode, case CLOCK_EVT_MODE_UNUSED: case CLOCK_EVT_MODE_SHUTDOWN: /* A 0 argument shuts the clock down. */ - hcall(LHCALL_SET_CLOCKEVENT, 0, 0, 0); + kvm_hypercall0(LHCALL_SET_CLOCKEVENT); break; case CLOCK_EVT_MODE_ONESHOT: /* This is what we expect. */ @@ -781,8 +800,8 @@ static void lguest_time_init(void) static void lguest_load_sp0(struct tss_struct *tss, struct thread_struct *thread) { - lazy_hcall(LHCALL_SET_STACK, __KERNEL_DS|0x1, thread->sp0, - THREAD_SIZE/PAGE_SIZE); + lazy_hcall3(LHCALL_SET_STACK, __KERNEL_DS | 0x1, thread->sp0, + THREAD_SIZE / PAGE_SIZE); } /* Let's just say, I wouldn't do debugging under a Guest. */ @@ -855,7 +874,7 @@ static void set_lguest_basic_apic_ops(void) /* STOP! Until an interrupt comes in. */ static void lguest_safe_halt(void) { - hcall(LHCALL_HALT, 0, 0, 0); + kvm_hypercall0(LHCALL_HALT); } /* The SHUTDOWN hypercall takes a string to describe what's happening, and @@ -865,7 +884,8 @@ static void lguest_safe_halt(void) * rather than virtual addresses, so we use __pa() here. */ static void lguest_power_off(void) { - hcall(LHCALL_SHUTDOWN, __pa("Power down"), LGUEST_SHUTDOWN_POWEROFF, 0); + kvm_hypercall2(LHCALL_SHUTDOWN, __pa("Power down"), + LGUEST_SHUTDOWN_POWEROFF); } /* @@ -875,7 +895,7 @@ static void lguest_power_off(void) */ static int lguest_panic(struct notifier_block *nb, unsigned long l, void *p) { - hcall(LHCALL_SHUTDOWN, __pa(p), LGUEST_SHUTDOWN_POWEROFF, 0); + kvm_hypercall2(LHCALL_SHUTDOWN, __pa(p), LGUEST_SHUTDOWN_POWEROFF); /* The hcall won't return, but to keep gcc happy, we're "done". */ return NOTIFY_DONE; } @@ -916,7 +936,7 @@ static __init int early_put_chars(u32 vtermno, const char *buf, int count) len = sizeof(scratch) - 1; scratch[len] = '\0'; memcpy(scratch, buf, len); - hcall(LHCALL_NOTIFY, __pa(scratch), 0, 0); + kvm_hypercall1(LHCALL_NOTIFY, __pa(scratch)); /* This routine returns the number of bytes actually written. */ return len; @@ -926,7 +946,7 @@ static __init int early_put_chars(u32 vtermno, const char *buf, int count) * Launcher to reboot us. */ static void lguest_restart(char *reason) { - hcall(LHCALL_SHUTDOWN, __pa(reason), LGUEST_SHUTDOWN_RESTART, 0); + kvm_hypercall2(LHCALL_SHUTDOWN, __pa(reason), LGUEST_SHUTDOWN_RESTART); } /*G:050 diff --git a/arch/x86/lguest/i386_head.S b/arch/x86/lguest/i386_head.S index 10b9bd35a8f..f7954198947 100644 --- a/arch/x86/lguest/i386_head.S +++ b/arch/x86/lguest/i386_head.S @@ -27,8 +27,8 @@ ENTRY(lguest_entry) /* We make the "initialization" hypercall now to tell the Host about * us, and also find out where it put our page tables. */ movl $LHCALL_LGUEST_INIT, %eax - movl $lguest_data - __PAGE_OFFSET, %edx - int $LGUEST_TRAP_ENTRY + movl $lguest_data - __PAGE_OFFSET, %ebx + .byte 0x0f,0x01,0xc1 /* KVM_HYPERCALL */ /* Set up the initial stack so we can run C code. */ movl $(init_thread_union+THREAD_SIZE),%esp diff --git a/drivers/lguest/interrupts_and_traps.c b/drivers/lguest/interrupts_and_traps.c index 415fab0125a..504091da173 100644 --- a/drivers/lguest/interrupts_and_traps.c +++ b/drivers/lguest/interrupts_and_traps.c @@ -288,9 +288,10 @@ static int direct_trap(unsigned int num) /* The Host needs to see page faults (for shadow paging and to save the * fault address), general protection faults (in/out emulation) and - * device not available (TS handling), and of course, the hypercall - * trap. */ - return num != 14 && num != 13 && num != 7 && num != LGUEST_TRAP_ENTRY; + * device not available (TS handling), invalid opcode fault (kvm hcall), + * and of course, the hypercall trap. */ + return num != 14 && num != 13 && num != 7 && + num != 6 && num != LGUEST_TRAP_ENTRY; } /*:*/ diff --git a/drivers/lguest/lguest_device.c b/drivers/lguest/lguest_device.c index 8132533d71f..df44d962626 100644 --- a/drivers/lguest/lguest_device.c +++ b/drivers/lguest/lguest_device.c @@ -161,7 +161,7 @@ static void set_status(struct virtio_device *vdev, u8 status) /* We set the status. */ to_lgdev(vdev)->desc->status = status; - hcall(LHCALL_NOTIFY, (max_pfn<priv; - hcall(LHCALL_NOTIFY, lvq->config.pfn << PAGE_SHIFT, 0, 0); + kvm_hypercall1(LHCALL_NOTIFY, lvq->config.pfn << PAGE_SHIFT); } /* An extern declaration inside a C file is bad form. Don't do it. */ diff --git a/drivers/lguest/x86/core.c b/drivers/lguest/x86/core.c index bf7942327bd..a6b717644be 100644 --- a/drivers/lguest/x86/core.c +++ b/drivers/lguest/x86/core.c @@ -290,6 +290,57 @@ static int emulate_insn(struct lg_cpu *cpu) return 1; } +/* Our hypercalls mechanism used to be based on direct software interrupts. + * After Anthony's "Refactor hypercall infrastructure" kvm patch, we decided to + * change over to using kvm hypercalls. + * + * KVM_HYPERCALL is actually a "vmcall" instruction, which generates an invalid + * opcode fault (fault 6) on non-VT cpus, so the easiest solution seemed to be + * an *emulation approach*: if the fault was really produced by an hypercall + * (is_hypercall() does exactly this check), we can just call the corresponding + * hypercall host implementation function. + * + * But these invalid opcode faults are notably slower than software interrupts. + * So we implemented the *patching (or rewriting) approach*: every time we hit + * the KVM_HYPERCALL opcode in Guest code, we patch it to the old "int 0x1f" + * opcode, so next time the Guest calls this hypercall it will use the + * faster trap mechanism. + * + * Matias even benchmarked it to convince you: this shows the average cycle + * cost of a hypercall. For each alternative solution mentioned above we've + * made 5 runs of the benchmark: + * + * 1) direct software interrupt: 2915, 2789, 2764, 2721, 2898 + * 2) emulation technique: 3410, 3681, 3466, 3392, 3780 + * 3) patching (rewrite) technique: 2977, 2975, 2891, 2637, 2884 + * + * One two-line function is worth a 20% hypercall speed boost! + */ +static void rewrite_hypercall(struct lg_cpu *cpu) +{ + /* This are the opcodes we use to patch the Guest. The opcode for "int + * $0x1f" is "0xcd 0x1f" but vmcall instruction is 3 bytes long, so we + * complete the sequence with a NOP (0x90). */ + u8 insn[3] = {0xcd, 0x1f, 0x90}; + + __lgwrite(cpu, guest_pa(cpu, cpu->regs->eip), insn, sizeof(insn)); +} + +static bool is_hypercall(struct lg_cpu *cpu) +{ + u8 insn[3]; + + /* This must be the Guest kernel trying to do something. + * The bottom two bits of the CS segment register are the privilege + * level. */ + if ((cpu->regs->cs & 3) != GUEST_PL) + return false; + + /* Is it a vmcall? */ + __lgread(cpu, insn, guest_pa(cpu, cpu->regs->eip), sizeof(insn)); + return insn[0] == 0x0f && insn[1] == 0x01 && insn[2] == 0xc1; +} + /*H:050 Once we've re-enabled interrupts, we look at why the Guest exited. */ void lguest_arch_handle_trap(struct lg_cpu *cpu) { @@ -337,7 +388,7 @@ void lguest_arch_handle_trap(struct lg_cpu *cpu) break; case 32 ... 255: /* These values mean a real interrupt occurred, in which case - * the Host handler has already been run. We just do a + * the Host handler has already been run. We just do a * friendly check if another process should now be run, then * return to run the Guest again */ cond_resched(); @@ -347,6 +398,15 @@ void lguest_arch_handle_trap(struct lg_cpu *cpu) * up the pointer now to indicate a hypercall is pending. */ cpu->hcall = (struct hcall_args *)cpu->regs; return; + case 6: + /* kvm hypercalls trigger an invalid opcode fault (6). + * We need to check if ring == GUEST_PL and + * faulting instruction == vmcall. */ + if (is_hypercall(cpu)) { + rewrite_hypercall(cpu); + return; + } + break; } /* We didn't handle the trap, so it needs to go to the Guest. */ -- cgit v1.2.3-70-g09d2 From 0451fb2ebc4f65c265bb51d71a2fc986ebf20218 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Mon, 30 Mar 2009 22:05:11 -0600 Subject: cpumask: remove node_to_first_cpu Everyone defines it, and only one person uses it (arch/mips/sgi-ip27/ip27-nmi.c). So just open code it there. Signed-off-by: Rusty Russell Cc: linux-mips@linux-mips.org --- arch/ia64/include/asm/topology.h | 5 ----- arch/mips/include/asm/mach-ip27/topology.h | 1 - arch/mips/sgi-ip27/ip27-nmi.c | 2 +- arch/powerpc/include/asm/topology.h | 5 ----- arch/sh/include/asm/topology.h | 1 - arch/sparc/include/asm/topology_64.h | 5 ----- arch/x86/include/asm/topology.h | 12 ------------ include/asm-generic/topology.h | 3 --- 8 files changed, 1 insertion(+), 33 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h index 3193f4417e1..f260dcf2151 100644 --- a/arch/ia64/include/asm/topology.h +++ b/arch/ia64/include/asm/topology.h @@ -43,11 +43,6 @@ */ #define parent_node(nid) (nid) -/* - * Returns the number of the first CPU on Node 'node'. - */ -#define node_to_first_cpu(node) (cpumask_first(cpumask_of_node(node))) - /* * Determines the node for a given pci bus */ diff --git a/arch/mips/include/asm/mach-ip27/topology.h b/arch/mips/include/asm/mach-ip27/topology.h index 55d481569a1..07547231e07 100644 --- a/arch/mips/include/asm/mach-ip27/topology.h +++ b/arch/mips/include/asm/mach-ip27/topology.h @@ -26,7 +26,6 @@ extern struct cpuinfo_ip27 sn_cpu_info[NR_CPUS]; #define parent_node(node) (node) #define node_to_cpumask(node) (hub_data(node)->h_cpus) #define cpumask_of_node(node) (&hub_data(node)->h_cpus) -#define node_to_first_cpu(node) (cpumask_first(cpumask_of_node(node))) struct pci_bus; extern int pcibus_to_node(struct pci_bus *); diff --git a/arch/mips/sgi-ip27/ip27-nmi.c b/arch/mips/sgi-ip27/ip27-nmi.c index 64459e7d891..b174a51a162 100644 --- a/arch/mips/sgi-ip27/ip27-nmi.c +++ b/arch/mips/sgi-ip27/ip27-nmi.c @@ -219,7 +219,7 @@ cont_nmi_dump(void) if (i == 1000) { for_each_online_node(node) if (NODEPDA(node)->dump_count == 0) { - cpu = node_to_first_cpu(node); + cpu = cpumask_first(cpumask_of_node(node)); for (n=0; n < CNODE_NUM_CPUS(node); cpu++, n++) { CPUMASK_SETB(nmied_cpus, cpu); /* diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index 375258559ae..054a16d6808 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -24,11 +24,6 @@ static inline cpumask_t node_to_cpumask(int node) #define cpumask_of_node(node) (&numa_cpumask_lookup_table[node]) -static inline int node_to_first_cpu(int node) -{ - return cpumask_first(cpumask_of_node(node)); -} - int of_node_to_nid(struct device_node *device); struct pci_bus; diff --git a/arch/sh/include/asm/topology.h b/arch/sh/include/asm/topology.h index 066f0fba590..a3f23954589 100644 --- a/arch/sh/include/asm/topology.h +++ b/arch/sh/include/asm/topology.h @@ -33,7 +33,6 @@ #define node_to_cpumask(node) ((void)node, cpu_online_map) #define cpumask_of_node(node) ((void)node, cpu_online_mask) -#define node_to_first_cpu(node) ((void)(node),0) #define pcibus_to_node(bus) ((void)(bus), -1) #define pcibus_to_cpumask(bus) (pcibus_to_node(bus) == -1 ? \ diff --git a/arch/sparc/include/asm/topology_64.h b/arch/sparc/include/asm/topology_64.h index 5bc0b8fd637..2770f64fdc3 100644 --- a/arch/sparc/include/asm/topology_64.h +++ b/arch/sparc/include/asm/topology_64.h @@ -28,11 +28,6 @@ static inline cpumask_t node_to_cpumask(int node) #define node_to_cpumask_ptr_next(v, node) \ v = &(numa_cpumask_lookup_table[node]) -static inline int node_to_first_cpu(int node) -{ - return cpumask_first(cpumask_of_node(node)); -} - struct pci_bus; #ifdef CONFIG_PCI extern int pcibus_to_node(struct pci_bus *pbus); diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 77cfb2cfb38..744299c0b77 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -217,10 +217,6 @@ static inline cpumask_t node_to_cpumask(int node) { return cpu_online_map; } -static inline int node_to_first_cpu(int node) -{ - return first_cpu(cpu_online_map); -} static inline void setup_node_to_cpumask_map(void) { } @@ -237,14 +233,6 @@ static inline void setup_node_to_cpumask_map(void) { } #include -#ifdef CONFIG_NUMA -/* Returns the number of the first CPU on Node 'node'. */ -static inline int node_to_first_cpu(int node) -{ - return cpumask_first(cpumask_of_node(node)); -} -#endif - extern cpumask_t cpu_coregroup_map(int cpu); extern const struct cpumask *cpu_coregroup_mask(int cpu); diff --git a/include/asm-generic/topology.h b/include/asm-generic/topology.h index 0e9e2bc0ee9..47766b30061 100644 --- a/include/asm-generic/topology.h +++ b/include/asm-generic/topology.h @@ -43,9 +43,6 @@ #ifndef cpumask_of_node #define cpumask_of_node(node) ((void)node, cpu_online_mask) #endif -#ifndef node_to_first_cpu -#define node_to_first_cpu(node) ((void)(node),0) -#endif #ifndef pcibus_to_node #define pcibus_to_node(bus) ((void)(bus), -1) #endif -- cgit v1.2.3-70-g09d2 From 25c1a411e8a0a709abe3449866125dc290711ea8 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Mon, 30 Mar 2009 11:10:27 +1100 Subject: x86: fix mismerge in arch/x86/include/asm/timer.h Signed-off-by: Stephen Rothwell Signed-off-by: Linus Torvalds --- arch/x86/include/asm/timer.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h index a81195eaa2b..bd37ed444a2 100644 --- a/arch/x86/include/asm/timer.h +++ b/arch/x86/include/asm/timer.h @@ -12,9 +12,9 @@ unsigned long native_calibrate_tsc(void); #ifdef CONFIG_X86_32 extern int timer_ack; -extern int recalibrate_cpu_khz(void); extern irqreturn_t timer_interrupt(int irq, void *dev_id); #endif /* CONFIG_X86_32 */ +extern int recalibrate_cpu_khz(void); extern int no_timer_check; -- cgit v1.2.3-70-g09d2 From bf9ed57d35d64dac5d5651478b5530a89b20ea1e Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Tue, 31 Mar 2009 15:23:38 -0700 Subject: pm: cleanup includes Remove unused/duplicate cruft from asm/suspend.h: - x86_32: remove unused acpi code - powerpc: remove duplicate prototypes, see linux/suspend.h Signed-off-by: Magnus Damm Cc: Paul Mundt Acked-by: "Rafael J. Wysocki" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/include/asm/suspend.h | 3 --- arch/x86/include/asm/suspend_32.h | 24 ------------------------ 2 files changed, 27 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/powerpc/include/asm/suspend.h b/arch/powerpc/include/asm/suspend.h index cbf2c9404c3..c6efc3466aa 100644 --- a/arch/powerpc/include/asm/suspend.h +++ b/arch/powerpc/include/asm/suspend.h @@ -3,7 +3,4 @@ static inline int arch_prepare_suspend(void) { return 0; } -void save_processor_state(void); -void restore_processor_state(void); - #endif /* __ASM_POWERPC_SUSPEND_H */ diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h index a5074bd0f8b..48dcfa62ea0 100644 --- a/arch/x86/include/asm/suspend_32.h +++ b/arch/x86/include/asm/suspend_32.h @@ -24,28 +24,4 @@ struct saved_context { unsigned long return_address; } __attribute__((packed)); -#ifdef CONFIG_ACPI -extern unsigned long saved_eip; -extern unsigned long saved_esp; -extern unsigned long saved_ebp; -extern unsigned long saved_ebx; -extern unsigned long saved_esi; -extern unsigned long saved_edi; - -static inline void acpi_save_register_state(unsigned long return_point) -{ - saved_eip = return_point; - asm volatile("movl %%esp,%0" : "=m" (saved_esp)); - asm volatile("movl %%ebp,%0" : "=m" (saved_ebp)); - asm volatile("movl %%ebx,%0" : "=m" (saved_ebx)); - asm volatile("movl %%edi,%0" : "=m" (saved_edi)); - asm volatile("movl %%esi,%0" : "=m" (saved_esi)); -} - -#define acpi_restore_register_state() do {} while (0) - -/* routines for saving/restoring kernel state */ -extern int acpi_save_state_mem(void); -#endif - #endif /* _ASM_X86_SUSPEND_32_H */ -- cgit v1.2.3-70-g09d2 From bc5d9940e8b07c7df13b60af2dd66ffbeb40e845 Mon Sep 17 00:00:00 2001 From: Jack Steiner Date: Thu, 2 Apr 2009 16:59:00 -0700 Subject: sgi-gru: exclude UV definitions on 32-bit x86 Eliminate compile errors on 32-bit X86 caused by UV. Signed-off-by: Jack Steiner Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/include/asm/uv/uv_hub.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h index 9f4dfba33b2..466ac8d09b1 100644 --- a/arch/x86/include/asm/uv/uv_hub.h +++ b/arch/x86/include/asm/uv/uv_hub.h @@ -11,6 +11,7 @@ #ifndef _ASM_X86_UV_UV_HUB_H #define _ASM_X86_UV_UV_HUB_H +#ifdef CONFIG_X86_64 #include #include #include @@ -405,4 +406,5 @@ static inline void uv_set_cpu_scir_bits(int cpu, unsigned char value) } } +#endif /* CONFIG_X86_64 */ #endif /* _ASM_X86_UV_UV_HUB_H */ -- cgit v1.2.3-70-g09d2 From a4c3155719c2a68b6293bc69ce3521018550dd40 Mon Sep 17 00:00:00 2001 From: Jack Steiner Date: Thu, 2 Apr 2009 16:59:01 -0700 Subject: sgi-gru: add definitions of x86_64 GRU MMRs Add definitions for x86_64 GRU MMRs. Signed-off-by: Jack Steiner Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/include/asm/uv/uv_mmrs.h | 153 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 153 insertions(+) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h index dd627793a23..db68ac8a5ac 100644 --- a/arch/x86/include/asm/uv/uv_mmrs.h +++ b/arch/x86/include/asm/uv/uv_mmrs.h @@ -1,3 +1,4 @@ + /* * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive @@ -242,6 +243,158 @@ union uvh_event_occurred0_u { #define UVH_EVENT_OCCURRED0_ALIAS 0x0000000000070008UL #define UVH_EVENT_OCCURRED0_ALIAS_32 0x005f0 +/* ========================================================================= */ +/* UVH_GR0_TLB_INT0_CONFIG */ +/* ========================================================================= */ +#define UVH_GR0_TLB_INT0_CONFIG 0x61b00UL + +#define UVH_GR0_TLB_INT0_CONFIG_VECTOR_SHFT 0 +#define UVH_GR0_TLB_INT0_CONFIG_VECTOR_MASK 0x00000000000000ffUL +#define UVH_GR0_TLB_INT0_CONFIG_DM_SHFT 8 +#define UVH_GR0_TLB_INT0_CONFIG_DM_MASK 0x0000000000000700UL +#define UVH_GR0_TLB_INT0_CONFIG_DESTMODE_SHFT 11 +#define UVH_GR0_TLB_INT0_CONFIG_DESTMODE_MASK 0x0000000000000800UL +#define UVH_GR0_TLB_INT0_CONFIG_STATUS_SHFT 12 +#define UVH_GR0_TLB_INT0_CONFIG_STATUS_MASK 0x0000000000001000UL +#define UVH_GR0_TLB_INT0_CONFIG_P_SHFT 13 +#define UVH_GR0_TLB_INT0_CONFIG_P_MASK 0x0000000000002000UL +#define UVH_GR0_TLB_INT0_CONFIG_T_SHFT 15 +#define UVH_GR0_TLB_INT0_CONFIG_T_MASK 0x0000000000008000UL +#define UVH_GR0_TLB_INT0_CONFIG_M_SHFT 16 +#define UVH_GR0_TLB_INT0_CONFIG_M_MASK 0x0000000000010000UL +#define UVH_GR0_TLB_INT0_CONFIG_APIC_ID_SHFT 32 +#define UVH_GR0_TLB_INT0_CONFIG_APIC_ID_MASK 0xffffffff00000000UL + +union uvh_gr0_tlb_int0_config_u { + unsigned long v; + struct uvh_gr0_tlb_int0_config_s { + unsigned long vector_ : 8; /* RW */ + unsigned long dm : 3; /* RW */ + unsigned long destmode : 1; /* RW */ + unsigned long status : 1; /* RO */ + unsigned long p : 1; /* RO */ + unsigned long rsvd_14 : 1; /* */ + unsigned long t : 1; /* RO */ + unsigned long m : 1; /* RW */ + unsigned long rsvd_17_31: 15; /* */ + unsigned long apic_id : 32; /* RW */ + } s; +}; + +/* ========================================================================= */ +/* UVH_GR0_TLB_INT1_CONFIG */ +/* ========================================================================= */ +#define UVH_GR0_TLB_INT1_CONFIG 0x61b40UL + +#define UVH_GR0_TLB_INT1_CONFIG_VECTOR_SHFT 0 +#define UVH_GR0_TLB_INT1_CONFIG_VECTOR_MASK 0x00000000000000ffUL +#define UVH_GR0_TLB_INT1_CONFIG_DM_SHFT 8 +#define UVH_GR0_TLB_INT1_CONFIG_DM_MASK 0x0000000000000700UL +#define UVH_GR0_TLB_INT1_CONFIG_DESTMODE_SHFT 11 +#define UVH_GR0_TLB_INT1_CONFIG_DESTMODE_MASK 0x0000000000000800UL +#define UVH_GR0_TLB_INT1_CONFIG_STATUS_SHFT 12 +#define UVH_GR0_TLB_INT1_CONFIG_STATUS_MASK 0x0000000000001000UL +#define UVH_GR0_TLB_INT1_CONFIG_P_SHFT 13 +#define UVH_GR0_TLB_INT1_CONFIG_P_MASK 0x0000000000002000UL +#define UVH_GR0_TLB_INT1_CONFIG_T_SHFT 15 +#define UVH_GR0_TLB_INT1_CONFIG_T_MASK 0x0000000000008000UL +#define UVH_GR0_TLB_INT1_CONFIG_M_SHFT 16 +#define UVH_GR0_TLB_INT1_CONFIG_M_MASK 0x0000000000010000UL +#define UVH_GR0_TLB_INT1_CONFIG_APIC_ID_SHFT 32 +#define UVH_GR0_TLB_INT1_CONFIG_APIC_ID_MASK 0xffffffff00000000UL + +union uvh_gr0_tlb_int1_config_u { + unsigned long v; + struct uvh_gr0_tlb_int1_config_s { + unsigned long vector_ : 8; /* RW */ + unsigned long dm : 3; /* RW */ + unsigned long destmode : 1; /* RW */ + unsigned long status : 1; /* RO */ + unsigned long p : 1; /* RO */ + unsigned long rsvd_14 : 1; /* */ + unsigned long t : 1; /* RO */ + unsigned long m : 1; /* RW */ + unsigned long rsvd_17_31: 15; /* */ + unsigned long apic_id : 32; /* RW */ + } s; +}; + +/* ========================================================================= */ +/* UVH_GR1_TLB_INT0_CONFIG */ +/* ========================================================================= */ +#define UVH_GR1_TLB_INT0_CONFIG 0x61f00UL + +#define UVH_GR1_TLB_INT0_CONFIG_VECTOR_SHFT 0 +#define UVH_GR1_TLB_INT0_CONFIG_VECTOR_MASK 0x00000000000000ffUL +#define UVH_GR1_TLB_INT0_CONFIG_DM_SHFT 8 +#define UVH_GR1_TLB_INT0_CONFIG_DM_MASK 0x0000000000000700UL +#define UVH_GR1_TLB_INT0_CONFIG_DESTMODE_SHFT 11 +#define UVH_GR1_TLB_INT0_CONFIG_DESTMODE_MASK 0x0000000000000800UL +#define UVH_GR1_TLB_INT0_CONFIG_STATUS_SHFT 12 +#define UVH_GR1_TLB_INT0_CONFIG_STATUS_MASK 0x0000000000001000UL +#define UVH_GR1_TLB_INT0_CONFIG_P_SHFT 13 +#define UVH_GR1_TLB_INT0_CONFIG_P_MASK 0x0000000000002000UL +#define UVH_GR1_TLB_INT0_CONFIG_T_SHFT 15 +#define UVH_GR1_TLB_INT0_CONFIG_T_MASK 0x0000000000008000UL +#define UVH_GR1_TLB_INT0_CONFIG_M_SHFT 16 +#define UVH_GR1_TLB_INT0_CONFIG_M_MASK 0x0000000000010000UL +#define UVH_GR1_TLB_INT0_CONFIG_APIC_ID_SHFT 32 +#define UVH_GR1_TLB_INT0_CONFIG_APIC_ID_MASK 0xffffffff00000000UL + +union uvh_gr1_tlb_int0_config_u { + unsigned long v; + struct uvh_gr1_tlb_int0_config_s { + unsigned long vector_ : 8; /* RW */ + unsigned long dm : 3; /* RW */ + unsigned long destmode : 1; /* RW */ + unsigned long status : 1; /* RO */ + unsigned long p : 1; /* RO */ + unsigned long rsvd_14 : 1; /* */ + unsigned long t : 1; /* RO */ + unsigned long m : 1; /* RW */ + unsigned long rsvd_17_31: 15; /* */ + unsigned long apic_id : 32; /* RW */ + } s; +}; + +/* ========================================================================= */ +/* UVH_GR1_TLB_INT1_CONFIG */ +/* ========================================================================= */ +#define UVH_GR1_TLB_INT1_CONFIG 0x61f40UL + +#define UVH_GR1_TLB_INT1_CONFIG_VECTOR_SHFT 0 +#define UVH_GR1_TLB_INT1_CONFIG_VECTOR_MASK 0x00000000000000ffUL +#define UVH_GR1_TLB_INT1_CONFIG_DM_SHFT 8 +#define UVH_GR1_TLB_INT1_CONFIG_DM_MASK 0x0000000000000700UL +#define UVH_GR1_TLB_INT1_CONFIG_DESTMODE_SHFT 11 +#define UVH_GR1_TLB_INT1_CONFIG_DESTMODE_MASK 0x0000000000000800UL +#define UVH_GR1_TLB_INT1_CONFIG_STATUS_SHFT 12 +#define UVH_GR1_TLB_INT1_CONFIG_STATUS_MASK 0x0000000000001000UL +#define UVH_GR1_TLB_INT1_CONFIG_P_SHFT 13 +#define UVH_GR1_TLB_INT1_CONFIG_P_MASK 0x0000000000002000UL +#define UVH_GR1_TLB_INT1_CONFIG_T_SHFT 15 +#define UVH_GR1_TLB_INT1_CONFIG_T_MASK 0x0000000000008000UL +#define UVH_GR1_TLB_INT1_CONFIG_M_SHFT 16 +#define UVH_GR1_TLB_INT1_CONFIG_M_MASK 0x0000000000010000UL +#define UVH_GR1_TLB_INT1_CONFIG_APIC_ID_SHFT 32 +#define UVH_GR1_TLB_INT1_CONFIG_APIC_ID_MASK 0xffffffff00000000UL + +union uvh_gr1_tlb_int1_config_u { + unsigned long v; + struct uvh_gr1_tlb_int1_config_s { + unsigned long vector_ : 8; /* RW */ + unsigned long dm : 3; /* RW */ + unsigned long destmode : 1; /* RW */ + unsigned long status : 1; /* RO */ + unsigned long p : 1; /* RO */ + unsigned long rsvd_14 : 1; /* */ + unsigned long t : 1; /* RO */ + unsigned long m : 1; /* RW */ + unsigned long rsvd_17_31: 15; /* */ + unsigned long apic_id : 32; /* RW */ + } s; +}; + /* ========================================================================= */ /* UVH_INT_CMPB */ /* ========================================================================= */ -- cgit v1.2.3-70-g09d2 From 66666e50fcd69d80117d7d243ce02e1f774cbaf5 Mon Sep 17 00:00:00 2001 From: Jack Steiner Date: Thu, 2 Apr 2009 16:59:03 -0700 Subject: sgi-gru: add macros for using the UV hub to send interrupts Add macros for using the UV hub to send interrupts. Change the IPI code to use these macros. These macros will also be used in additional patches that will follow. Signed-off-by: Jack Steiner Cc: "Luck, Tony" Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/include/asm/uv/uv_hub.h | 6 ++++++ arch/x86/include/asm/uv/uv_hub.h | 12 ++++++++++++ arch/x86/kernel/apic/x2apic_uv_x.c | 9 ++------- 3 files changed, 20 insertions(+), 7 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/ia64/include/asm/uv/uv_hub.h b/arch/ia64/include/asm/uv/uv_hub.h index f607018af4a..53e9dfacd07 100644 --- a/arch/ia64/include/asm/uv/uv_hub.h +++ b/arch/ia64/include/asm/uv/uv_hub.h @@ -305,5 +305,11 @@ static inline int uv_num_possible_blades(void) return 1; } +static inline void uv_hub_send_ipi(int pnode, int apicid, int vector) +{ + /* not currently needed on ia64 */ +} + + #endif /* __ASM_IA64_UV_HUB__ */ diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h index 466ac8d09b1..d3a98ea1062 100644 --- a/arch/x86/include/asm/uv/uv_hub.h +++ b/arch/x86/include/asm/uv/uv_hub.h @@ -17,6 +17,7 @@ #include #include #include +#include /* @@ -398,6 +399,7 @@ static inline void uv_set_scir_bits(unsigned char value) uv_write_local_mmr8(uv_hub_info->scir.offset, value); } } + static inline void uv_set_cpu_scir_bits(int cpu, unsigned char value) { if (uv_cpu_hub_info(cpu)->scir.state != value) { @@ -406,5 +408,15 @@ static inline void uv_set_cpu_scir_bits(int cpu, unsigned char value) } } +static inline void uv_hub_send_ipi(int pnode, int apicid, int vector) +{ + unsigned long val; + + val = (1UL << UVH_IPI_INT_SEND_SHFT) | + ((apicid & 0x3f) << UVH_IPI_INT_APIC_ID_SHFT) | + (vector << UVH_IPI_INT_VECTOR_SHFT); + uv_write_global_mmr64(pnode, UVH_IPI_INT, val); +} + #endif /* CONFIG_X86_64 */ #endif /* _ASM_X86_UV_UV_HUB_H */ diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 1bd6da1f8fa..1248318436e 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -118,17 +118,12 @@ static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip) static void uv_send_IPI_one(int cpu, int vector) { - unsigned long val, apicid; + unsigned long apicid; int pnode; apicid = per_cpu(x86_cpu_to_apicid, cpu); pnode = uv_apicid_to_pnode(apicid); - - val = (1UL << UVH_IPI_INT_SEND_SHFT) | - (apicid << UVH_IPI_INT_APIC_ID_SHFT) | - (vector << UVH_IPI_INT_VECTOR_SHFT); - - uv_write_global_mmr64(pnode, UVH_IPI_INT, val); + uv_hub_send_ipi(pnode, apicid, vector); } static void uv_send_IPI_mask(const struct cpumask *mask, int vector) -- cgit v1.2.3-70-g09d2 From f3554f4bc69803ac2baaf7cf2aa4339e1f4b693e Mon Sep 17 00:00:00 2001 From: Gerd Hoffmann Date: Thu, 2 Apr 2009 16:59:23 -0700 Subject: preadv/pwritev: Add preadv and pwritev system calls. This patch adds preadv and pwritev system calls. These syscalls are a pretty straightforward combination of pread and readv (same for write). They are quite useful for doing vectored I/O in threaded applications. Using lseek+readv instead opens race windows you'll have to plug with locking. Other systems have such system calls too, for example NetBSD, check here: http://www.daemon-systems.org/man/preadv.2.html The application-visible interface provided by glibc should look like this to be compatible to the existing implementations in the *BSD family: ssize_t preadv(int d, const struct iovec *iov, int iovcnt, off_t offset); ssize_t pwritev(int d, const struct iovec *iov, int iovcnt, off_t offset); This prototype has one problem though: On 32bit archs is the (64bit) offset argument unaligned, which the syscall ABI of several archs doesn't allow to do. At least s390 needs a wrapper in glibc to handle this. As we'll need a wrappers in glibc anyway I've decided to push problem to glibc entriely and use a syscall prototype which works without arch-specific wrappers inside the kernel: The offset argument is explicitly splitted into two 32bit values. The patch sports the actual system call implementation and the windup in the x86 system call tables. Other archs follow as separate patches. Signed-off-by: Gerd Hoffmann Cc: Arnd Bergmann Cc: Al Viro Cc: Cc: Cc: Ralf Baechle Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/ia32/ia32entry.S | 2 ++ arch/x86/include/asm/unistd_32.h | 2 ++ arch/x86/include/asm/unistd_64.h | 4 +++ arch/x86/kernel/syscall_table_32.S | 2 ++ fs/compat.c | 36 +++++++++++++++++++++++++++ fs/read_write.c | 50 ++++++++++++++++++++++++++++++++++++++ include/linux/compat.h | 6 +++++ include/linux/syscalls.h | 4 +++ 8 files changed, 106 insertions(+) (limited to 'arch/x86/include') diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index db0c803170a..a505202086e 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -828,4 +828,6 @@ ia32_sys_call_table: .quad sys_dup3 /* 330 */ .quad sys_pipe2 .quad sys_inotify_init1 + .quad compat_sys_preadv + .quad compat_sys_pwritev ia32_syscall_end: diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h index f2bba78430a..6e72d74cf8d 100644 --- a/arch/x86/include/asm/unistd_32.h +++ b/arch/x86/include/asm/unistd_32.h @@ -338,6 +338,8 @@ #define __NR_dup3 330 #define __NR_pipe2 331 #define __NR_inotify_init1 332 +#define __NR_preadv 333 +#define __NR_pwritev 334 #ifdef __KERNEL__ diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h index d2e415e6666..f8182946232 100644 --- a/arch/x86/include/asm/unistd_64.h +++ b/arch/x86/include/asm/unistd_64.h @@ -653,6 +653,10 @@ __SYSCALL(__NR_dup3, sys_dup3) __SYSCALL(__NR_pipe2, sys_pipe2) #define __NR_inotify_init1 294 __SYSCALL(__NR_inotify_init1, sys_inotify_init1) +#define __NR_preadv 295 +__SYSCALL(__NR_preadv, sys_preadv) +#define __NR_pwritev 296 +__SYSCALL(__NR_pwritev, sys_pwritev) #ifndef __NO_STUBS diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S index 3bdb64829b8..ff5c8736b49 100644 --- a/arch/x86/kernel/syscall_table_32.S +++ b/arch/x86/kernel/syscall_table_32.S @@ -332,3 +332,5 @@ ENTRY(sys_call_table) .long sys_dup3 /* 330 */ .long sys_pipe2 .long sys_inotify_init1 + .long sys_preadv + .long sys_pwritev diff --git a/fs/compat.c b/fs/compat.c index e04b4660db8..7c1615183d1 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -1232,6 +1232,24 @@ compat_sys_readv(unsigned long fd, const struct compat_iovec __user *vec, return ret; } +asmlinkage ssize_t +compat_sys_preadv(unsigned long fd, const struct compat_iovec __user *vec, + unsigned long vlen, u32 pos_high, u32 pos_low) +{ + loff_t pos = ((loff_t)pos_high << 32) | pos_low; + struct file *file; + ssize_t ret; + + if (pos < 0) + return -EINVAL; + file = fget(fd); + if (!file) + return -EBADF; + ret = compat_readv(file, vec, vlen, &pos); + fput(file); + return ret; +} + static size_t compat_writev(struct file *file, const struct compat_iovec __user *vec, unsigned long vlen, loff_t *pos) @@ -1269,6 +1287,24 @@ compat_sys_writev(unsigned long fd, const struct compat_iovec __user *vec, return ret; } +asmlinkage ssize_t +compat_sys_pwritev(unsigned long fd, const struct compat_iovec __user *vec, + unsigned long vlen, u32 pos_high, u32 pos_low) +{ + loff_t pos = ((loff_t)pos_high << 32) | pos_low; + struct file *file; + ssize_t ret; + + if (pos < 0) + return -EINVAL; + file = fget(fd); + if (!file) + return -EBADF; + ret = compat_writev(file, vec, vlen, &pos); + fput(file); + return ret; +} + asmlinkage long compat_sys_vmsplice(int fd, const struct compat_iovec __user *iov32, unsigned int nr_segs, unsigned int flags) diff --git a/fs/read_write.c b/fs/read_write.c index 400fe81c973..6d5d8ff238a 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -731,6 +731,56 @@ SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec, return ret; } +SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec, + unsigned long, vlen, u32, pos_high, u32, pos_low) +{ + loff_t pos = ((loff_t)pos_high << 32) | pos_low; + struct file *file; + ssize_t ret = -EBADF; + int fput_needed; + + if (pos < 0) + return -EINVAL; + + file = fget_light(fd, &fput_needed); + if (file) { + ret = -ESPIPE; + if (file->f_mode & FMODE_PREAD) + ret = vfs_readv(file, vec, vlen, &pos); + fput_light(file, fput_needed); + } + + if (ret > 0) + add_rchar(current, ret); + inc_syscr(current); + return ret; +} + +SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec, + unsigned long, vlen, u32, pos_high, u32, pos_low) +{ + loff_t pos = ((loff_t)pos_high << 32) | pos_low; + struct file *file; + ssize_t ret = -EBADF; + int fput_needed; + + if (pos < 0) + return -EINVAL; + + file = fget_light(fd, &fput_needed); + if (file) { + ret = -ESPIPE; + if (file->f_mode & FMODE_PWRITE) + ret = vfs_writev(file, vec, vlen, &pos); + fput_light(file, fput_needed); + } + + if (ret > 0) + add_wchar(current, ret); + inc_syscw(current); + return ret; +} + static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, size_t count, loff_t max) { diff --git a/include/linux/compat.h b/include/linux/compat.h index b880864672d..9723edd6455 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -191,6 +191,12 @@ asmlinkage ssize_t compat_sys_readv(unsigned long fd, const struct compat_iovec __user *vec, unsigned long vlen); asmlinkage ssize_t compat_sys_writev(unsigned long fd, const struct compat_iovec __user *vec, unsigned long vlen); +asmlinkage ssize_t compat_sys_preadv(unsigned long fd, + const struct compat_iovec __user *vec, + unsigned long vlen, u32 pos_high, u32 pos_low); +asmlinkage ssize_t compat_sys_pwritev(unsigned long fd, + const struct compat_iovec __user *vec, + unsigned long vlen, u32 pos_high, u32 pos_low); int compat_do_execve(char * filename, compat_uptr_t __user *argv, compat_uptr_t __user *envp, struct pt_regs * regs); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index f9f900cfd06..b299a82a05e 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -461,6 +461,10 @@ asmlinkage long sys_pread64(unsigned int fd, char __user *buf, size_t count, loff_t pos); asmlinkage long sys_pwrite64(unsigned int fd, const char __user *buf, size_t count, loff_t pos); +asmlinkage long sys_preadv(unsigned long fd, const struct iovec __user *vec, + unsigned long vlen, u32 pos_high, u32 pos_low); +asmlinkage long sys_pwritev(unsigned long fd, const struct iovec __user *vec, + unsigned long vlen, u32 pos_high, u32 pos_low); asmlinkage long sys_getcwd(char __user *buf, unsigned long size); asmlinkage long sys_mkdir(const char __user *pathname, int mode); asmlinkage long sys_chdir(const char __user *filename); -- cgit v1.2.3-70-g09d2 From f5f7eac41db827a47b2163330eecd7bb55ae9f12 Mon Sep 17 00:00:00 2001 From: Robin Holt Date: Thu, 2 Apr 2009 16:59:46 -0700 Subject: Allow rwlocks to re-enable interrupts Pass the original flags to rwlock arch-code, so that it can re-enable interrupts if implemented for that architecture. Initially, make __raw_read_lock_flags and __raw_write_lock_flags stubs which just do the same thing as non-flags variants. Signed-off-by: Petr Tesarik Signed-off-by: Robin Holt Acked-by: Peter Zijlstra Cc: Acked-by: Ingo Molnar Cc: "Luck, Tony" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/include/asm/spinlock.h | 3 +++ arch/arm/include/asm/spinlock.h | 3 +++ arch/cris/include/arch-v32/arch/spinlock.h | 2 ++ arch/ia64/include/asm/spinlock.h | 3 +++ arch/mips/include/asm/spinlock.h | 2 ++ arch/parisc/include/asm/spinlock.h | 3 +++ arch/powerpc/include/asm/spinlock.h | 3 +++ arch/s390/include/asm/spinlock.h | 3 +++ arch/sh/include/asm/spinlock.h | 3 +++ arch/sparc/include/asm/spinlock_32.h | 2 ++ arch/sparc/include/asm/spinlock_64.h | 2 ++ arch/x86/include/asm/spinlock.h | 3 +++ include/asm-m32r/spinlock.h | 3 +++ include/linux/spinlock.h | 6 ++++++ kernel/spinlock.c | 6 ++++-- 15 files changed, 45 insertions(+), 2 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/alpha/include/asm/spinlock.h b/arch/alpha/include/asm/spinlock.h index aeeb125f685..e38fb95cb33 100644 --- a/arch/alpha/include/asm/spinlock.h +++ b/arch/alpha/include/asm/spinlock.h @@ -166,6 +166,9 @@ static inline void __raw_write_unlock(raw_rwlock_t * lock) lock->lock = 0; } +#define __raw_read_lock_flags(lock, flags) __raw_read_lock(lock) +#define __raw_write_lock_flags(lock, flags) __raw_write_lock(lock) + #define _raw_spin_relax(lock) cpu_relax() #define _raw_read_relax(lock) cpu_relax() #define _raw_write_relax(lock) cpu_relax() diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h index 2b41ebbfa7f..c13681ac1ed 100644 --- a/arch/arm/include/asm/spinlock.h +++ b/arch/arm/include/asm/spinlock.h @@ -217,6 +217,9 @@ static inline int __raw_read_trylock(raw_rwlock_t *rw) /* read_can_lock - would read_trylock() succeed? */ #define __raw_read_can_lock(x) ((x)->lock < 0x80000000) +#define __raw_read_lock_flags(lock, flags) __raw_read_lock(lock) +#define __raw_write_lock_flags(lock, flags) __raw_write_lock(lock) + #define _raw_spin_relax(lock) cpu_relax() #define _raw_read_relax(lock) cpu_relax() #define _raw_write_relax(lock) cpu_relax() diff --git a/arch/cris/include/arch-v32/arch/spinlock.h b/arch/cris/include/arch-v32/arch/spinlock.h index 0d5709b983a..129756b9666 100644 --- a/arch/cris/include/arch-v32/arch/spinlock.h +++ b/arch/cris/include/arch-v32/arch/spinlock.h @@ -121,6 +121,8 @@ static inline int __raw_write_trylock(raw_rwlock_t *rw) return 1; } +#define _raw_read_lock_flags(lock, flags) _raw_read_lock(lock) +#define _raw_write_lock_flags(lock, flags) _raw_write_lock(lock) #define _raw_spin_relax(lock) cpu_relax() #define _raw_read_relax(lock) cpu_relax() diff --git a/arch/ia64/include/asm/spinlock.h b/arch/ia64/include/asm/spinlock.h index 0229fb95fb3..0a619618b2f 100644 --- a/arch/ia64/include/asm/spinlock.h +++ b/arch/ia64/include/asm/spinlock.h @@ -213,6 +213,9 @@ static inline int __raw_read_trylock(raw_rwlock_t *x) return (u32)ia64_cmpxchg4_acq((__u32 *)(x), new.word, old.word) == old.word; } +#define __raw_read_lock_flags(lock, flags) __raw_read_lock(lock) +#define __raw_write_lock_flags(lock, flags) __raw_write_lock(lock) + #define _raw_spin_relax(lock) cpu_relax() #define _raw_read_relax(lock) cpu_relax() #define _raw_write_relax(lock) cpu_relax() diff --git a/arch/mips/include/asm/spinlock.h b/arch/mips/include/asm/spinlock.h index 10e82441b49..5b60a09a0f0 100644 --- a/arch/mips/include/asm/spinlock.h +++ b/arch/mips/include/asm/spinlock.h @@ -480,6 +480,8 @@ static inline int __raw_write_trylock(raw_rwlock_t *rw) return ret; } +#define __raw_read_lock_flags(lock, flags) __raw_read_lock(lock) +#define __raw_write_lock_flags(lock, flags) __raw_write_lock(lock) #define _raw_spin_relax(lock) cpu_relax() #define _raw_read_relax(lock) cpu_relax() diff --git a/arch/parisc/include/asm/spinlock.h b/arch/parisc/include/asm/spinlock.h index f3d2090a18d..fae03e136fa 100644 --- a/arch/parisc/include/asm/spinlock.h +++ b/arch/parisc/include/asm/spinlock.h @@ -187,6 +187,9 @@ static __inline__ int __raw_write_can_lock(raw_rwlock_t *rw) return !rw->counter; } +#define __raw_read_lock_flags(lock, flags) __raw_read_lock(lock) +#define __raw_write_lock_flags(lock, flags) __raw_write_lock(lock) + #define _raw_spin_relax(lock) cpu_relax() #define _raw_read_relax(lock) cpu_relax() #define _raw_write_relax(lock) cpu_relax() diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h index 36864364e60..c3b193121f8 100644 --- a/arch/powerpc/include/asm/spinlock.h +++ b/arch/powerpc/include/asm/spinlock.h @@ -287,6 +287,9 @@ static inline void __raw_write_unlock(raw_rwlock_t *rw) rw->lock = 0; } +#define __raw_read_lock_flags(lock, flags) __raw_read_lock(lock) +#define __raw_write_lock_flags(lock, flags) __raw_write_lock(lock) + #define _raw_spin_relax(lock) __spin_yield(lock) #define _raw_read_relax(lock) __rw_yield(lock) #define _raw_write_relax(lock) __rw_yield(lock) diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h index df84ae96915..f3861b09ebb 100644 --- a/arch/s390/include/asm/spinlock.h +++ b/arch/s390/include/asm/spinlock.h @@ -172,6 +172,9 @@ static inline int __raw_write_trylock(raw_rwlock_t *rw) return _raw_write_trylock_retry(rw); } +#define __raw_read_lock_flags(lock, flags) __raw_read_lock(lock) +#define __raw_write_lock_flags(lock, flags) __raw_write_lock(lock) + #define _raw_read_relax(lock) cpu_relax() #define _raw_write_relax(lock) cpu_relax() diff --git a/arch/sh/include/asm/spinlock.h b/arch/sh/include/asm/spinlock.h index e793181d64d..60283565f89 100644 --- a/arch/sh/include/asm/spinlock.h +++ b/arch/sh/include/asm/spinlock.h @@ -216,6 +216,9 @@ static inline int __raw_write_trylock(raw_rwlock_t *rw) return (oldval > (RW_LOCK_BIAS - 1)); } +#define __raw_read_lock_flags(lock, flags) __raw_read_lock(lock) +#define __raw_write_lock_flags(lock, flags) __raw_write_lock(lock) + #define _raw_spin_relax(lock) cpu_relax() #define _raw_read_relax(lock) cpu_relax() #define _raw_write_relax(lock) cpu_relax() diff --git a/arch/sparc/include/asm/spinlock_32.h b/arch/sparc/include/asm/spinlock_32.h index bf2d532593e..46f91ab66a5 100644 --- a/arch/sparc/include/asm/spinlock_32.h +++ b/arch/sparc/include/asm/spinlock_32.h @@ -177,6 +177,8 @@ static inline int __read_trylock(raw_rwlock_t *rw) #define __raw_write_unlock(rw) do { (rw)->lock = 0; } while(0) #define __raw_spin_lock_flags(lock, flags) __raw_spin_lock(lock) +#define __raw_read_lock_flags(rw, flags) __raw_read_lock(rw) +#define __raw_write_lock_flags(rw, flags) __raw_write_lock(rw) #define _raw_spin_relax(lock) cpu_relax() #define _raw_read_relax(lock) cpu_relax() diff --git a/arch/sparc/include/asm/spinlock_64.h b/arch/sparc/include/asm/spinlock_64.h index c4d274d330e..f6b2b92ad8d 100644 --- a/arch/sparc/include/asm/spinlock_64.h +++ b/arch/sparc/include/asm/spinlock_64.h @@ -211,9 +211,11 @@ static int inline __write_trylock(raw_rwlock_t *lock) } #define __raw_read_lock(p) __read_lock(p) +#define __raw_read_lock_flags(p, f) __read_lock(p) #define __raw_read_trylock(p) __read_trylock(p) #define __raw_read_unlock(p) __read_unlock(p) #define __raw_write_lock(p) __write_lock(p) +#define __raw_write_lock_flags(p, f) __write_lock(p) #define __raw_write_unlock(p) __write_unlock(p) #define __raw_write_trylock(p) __write_trylock(p) diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index 3a569665668..e5e6caffec8 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -295,6 +295,9 @@ static inline void __raw_write_unlock(raw_rwlock_t *rw) : "+m" (rw->lock) : "i" (RW_LOCK_BIAS) : "memory"); } +#define __raw_read_lock_flags(lock, flags) __raw_read_lock(lock) +#define __raw_write_lock_flags(lock, flags) __raw_write_lock(lock) + #define _raw_spin_relax(lock) cpu_relax() #define _raw_read_relax(lock) cpu_relax() #define _raw_write_relax(lock) cpu_relax() diff --git a/include/asm-m32r/spinlock.h b/include/asm-m32r/spinlock.h index f5cfba81ee1..dded923883b 100644 --- a/include/asm-m32r/spinlock.h +++ b/include/asm-m32r/spinlock.h @@ -316,6 +316,9 @@ static inline int __raw_write_trylock(raw_rwlock_t *lock) return 0; } +#define __raw_read_lock_flags(lock, flags) __raw_read_lock(lock) +#define __raw_write_lock_flags(lock, flags) __raw_write_lock(lock) + #define _raw_spin_relax(lock) cpu_relax() #define _raw_read_relax(lock) cpu_relax() #define _raw_write_relax(lock) cpu_relax() diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index a0c66a2e00a..252b245cfcf 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -153,9 +153,11 @@ do { \ extern int _raw_spin_trylock(spinlock_t *lock); extern void _raw_spin_unlock(spinlock_t *lock); extern void _raw_read_lock(rwlock_t *lock); +#define _raw_read_lock_flags(lock, flags) _raw_read_lock(lock) extern int _raw_read_trylock(rwlock_t *lock); extern void _raw_read_unlock(rwlock_t *lock); extern void _raw_write_lock(rwlock_t *lock); +#define _raw_write_lock_flags(lock, flags) _raw_write_lock(lock) extern int _raw_write_trylock(rwlock_t *lock); extern void _raw_write_unlock(rwlock_t *lock); #else @@ -165,9 +167,13 @@ do { \ # define _raw_spin_trylock(lock) __raw_spin_trylock(&(lock)->raw_lock) # define _raw_spin_unlock(lock) __raw_spin_unlock(&(lock)->raw_lock) # define _raw_read_lock(rwlock) __raw_read_lock(&(rwlock)->raw_lock) +# define _raw_read_lock_flags(lock, flags) \ + __raw_read_lock_flags(&(lock)->raw_lock, *(flags)) # define _raw_read_trylock(rwlock) __raw_read_trylock(&(rwlock)->raw_lock) # define _raw_read_unlock(rwlock) __raw_read_unlock(&(rwlock)->raw_lock) # define _raw_write_lock(rwlock) __raw_write_lock(&(rwlock)->raw_lock) +# define _raw_write_lock_flags(lock, flags) \ + __raw_write_lock_flags(&(lock)->raw_lock, *(flags)) # define _raw_write_trylock(rwlock) __raw_write_trylock(&(rwlock)->raw_lock) # define _raw_write_unlock(rwlock) __raw_write_unlock(&(rwlock)->raw_lock) #endif diff --git a/kernel/spinlock.c b/kernel/spinlock.c index 7283c6dc2d5..7932653c4eb 100644 --- a/kernel/spinlock.c +++ b/kernel/spinlock.c @@ -121,7 +121,8 @@ unsigned long __lockfunc _read_lock_irqsave(rwlock_t *lock) local_irq_save(flags); preempt_disable(); rwlock_acquire_read(&lock->dep_map, 0, 0, _RET_IP_); - LOCK_CONTENDED(lock, _raw_read_trylock, _raw_read_lock); + LOCK_CONTENDED_FLAGS(lock, _raw_read_trylock, _raw_read_lock, + _raw_read_lock_flags, &flags); return flags; } EXPORT_SYMBOL(_read_lock_irqsave); @@ -151,7 +152,8 @@ unsigned long __lockfunc _write_lock_irqsave(rwlock_t *lock) local_irq_save(flags); preempt_disable(); rwlock_acquire(&lock->dep_map, 0, 0, _RET_IP_); - LOCK_CONTENDED(lock, _raw_write_trylock, _raw_write_lock); + LOCK_CONTENDED_FLAGS(lock, _raw_write_trylock, _raw_write_lock, + _raw_write_lock_flags, &flags); return flags; } EXPORT_SYMBOL(_write_lock_irqsave); -- cgit v1.2.3-70-g09d2 From 67796bf7dc54c035fd97f2681a72e5d2bf2a234a Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 2 Apr 2009 15:55:55 +0200 Subject: x86/dma: unify definition of pci_unmap_addr* and pci_unmap_len macros Impact: unification of pci-dma macros and pci_32.h removal This patch unifies the definition of the pci_unmap_addr*, pci_unmap_len* and DECLARE_PCI_UNMAP* macros. This makes sense because the pci_unmap functions are no longer no-ops anymore when the kernel runs with CONFIG_DMA_API_DEBUG. Without an iommu or DMA_API_DEBUG it is a no-op on 32 bit because the dma mapping path returns a physical address and therefore the dma-api implementation has no internal state which needs to be destroyed with an unmap call. This unification also simplifies the port of x86_64 iommu drivers to 32 bit x86 and let us get rid of pci_32.h. Signed-off-by: Joerg Roedel Acked-by: Stephen Hemminger --- arch/x86/include/asm/pci.h | 36 ++++++++++++++++++++++++++++++++---- arch/x86/include/asm/pci_32.h | 34 ---------------------------------- arch/x86/include/asm/pci_64.h | 22 ---------------------- 3 files changed, 32 insertions(+), 60 deletions(-) delete mode 100644 arch/x86/include/asm/pci_32.h (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index a0301bfeb95..e545ea01abc 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -89,12 +89,40 @@ extern void pci_iommu_alloc(void); /* MSI arch hook */ #define arch_setup_msi_irqs arch_setup_msi_irqs -#endif /* __KERNEL__ */ +#define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys) + +#if defined(CONFIG_X86_64) || defined(CONFIG_DMA_API_DEBUG) + +#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) \ + dma_addr_t ADDR_NAME; +#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) \ + __u32 LEN_NAME; +#define pci_unmap_addr(PTR, ADDR_NAME) \ + ((PTR)->ADDR_NAME) +#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \ + (((PTR)->ADDR_NAME) = (VAL)) +#define pci_unmap_len(PTR, LEN_NAME) \ + ((PTR)->LEN_NAME) +#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \ + (((PTR)->LEN_NAME) = (VAL)) -#ifdef CONFIG_X86_32 -# include "pci_32.h" #else -# include "pci_64.h" + +#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) dma_addr_t ADDR_NAME[0]; +#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) unsigned LEN_NAME[0]; +#define pci_unmap_addr(PTR, ADDR_NAME) sizeof((PTR)->ADDR_NAME) +#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \ + do { break; } while (pci_unmap_addr(PTR, ADDR_NAME)) +#define pci_unmap_len(PTR, LEN_NAME) sizeof((PTR)->LEN_NAME) +#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \ + do { break; } while (pci_unmap_len(PTR, LEN_NAME)) + +#endif + +#endif /* __KERNEL__ */ + +#ifdef CONFIG_X86_64 +#include "pci_64.h" #endif /* implement the pci_ DMA API in terms of the generic device dma_ one */ diff --git a/arch/x86/include/asm/pci_32.h b/arch/x86/include/asm/pci_32.h deleted file mode 100644 index 6f1213a6ef4..00000000000 --- a/arch/x86/include/asm/pci_32.h +++ /dev/null @@ -1,34 +0,0 @@ -#ifndef _ASM_X86_PCI_32_H -#define _ASM_X86_PCI_32_H - - -#ifdef __KERNEL__ - - -/* Dynamic DMA mapping stuff. - * i386 has everything mapped statically. - */ - -struct pci_dev; - -/* The PCI address space does equal the physical memory - * address space. The networking and block device layers use - * this boolean for bounce buffer decisions. - */ -#define PCI_DMA_BUS_IS_PHYS (1) - -/* pci_unmap_{page,single} is a nop so... */ -#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) dma_addr_t ADDR_NAME[0]; -#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) unsigned LEN_NAME[0]; -#define pci_unmap_addr(PTR, ADDR_NAME) sizeof((PTR)->ADDR_NAME) -#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \ - do { break; } while (pci_unmap_addr(PTR, ADDR_NAME)) -#define pci_unmap_len(PTR, LEN_NAME) sizeof((PTR)->LEN_NAME) -#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \ - do { break; } while (pci_unmap_len(PTR, LEN_NAME)) - - -#endif /* __KERNEL__ */ - - -#endif /* _ASM_X86_PCI_32_H */ diff --git a/arch/x86/include/asm/pci_64.h b/arch/x86/include/asm/pci_64.h index 4da20798277..ae5e40f67da 100644 --- a/arch/x86/include/asm/pci_64.h +++ b/arch/x86/include/asm/pci_64.h @@ -24,28 +24,6 @@ extern int (*pci_config_write)(int seg, int bus, int dev, int fn, extern void dma32_reserve_bootmem(void); -/* The PCI address space does equal the physical memory - * address space. The networking and block device layers use - * this boolean for bounce buffer decisions - * - * On AMD64 it mostly equals, but we set it to zero if a hardware - * IOMMU (gart) of sotware IOMMU (swiotlb) is available. - */ -#define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys) - -#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) \ - dma_addr_t ADDR_NAME; -#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) \ - __u32 LEN_NAME; -#define pci_unmap_addr(PTR, ADDR_NAME) \ - ((PTR)->ADDR_NAME) -#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \ - (((PTR)->ADDR_NAME) = (VAL)) -#define pci_unmap_len(PTR, LEN_NAME) \ - ((PTR)->LEN_NAME) -#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \ - (((PTR)->LEN_NAME) = (VAL)) - #endif /* __KERNEL__ */ #endif /* _ASM_X86_PCI_64_H */ -- cgit v1.2.3-70-g09d2