--- zzzz-none-000/linux-3.10.107/drivers/xen/swiotlb-xen.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/drivers/xen/swiotlb-xen.c 2021-02-04 17:41:59.000000000 +0000 @@ -33,6 +33,8 @@ * */ +#define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt + #include #include #include @@ -40,12 +42,31 @@ #include #include #include + +#include +#include + +#include /* * Used to do a quick range check in swiotlb_tbl_unmap_single and * swiotlb_tbl_sync_single_*, to see if the memory was in fact allocated by this * API. */ +#ifndef CONFIG_X86 +static unsigned long dma_alloc_coherent_mask(struct device *dev, + gfp_t gfp) +{ + unsigned long dma_mask = 0; + + dma_mask = dev->coherent_dma_mask; + if (!dma_mask) + dma_mask = (gfp & GFP_DMA) ? DMA_BIT_MASK(24) : DMA_BIT_MASK(32); + + return dma_mask; +} +#endif + static char *xen_io_tlb_start, *xen_io_tlb_end; static unsigned long xen_io_tlb_nslabs; /* @@ -54,63 +75,78 @@ static u64 start_dma_addr; -static dma_addr_t xen_phys_to_bus(phys_addr_t paddr) +/* + * Both of these functions should avoid XEN_PFN_PHYS because phys_addr_t + * can be 32bit when dma_addr_t is 64bit leading to a loss in + * information if the shift is done before casting to 64bit. + */ +static inline dma_addr_t xen_phys_to_bus(phys_addr_t paddr) { - return phys_to_machine(XPADDR(paddr)).maddr; + unsigned long bfn = pfn_to_bfn(XEN_PFN_DOWN(paddr)); + dma_addr_t dma = (dma_addr_t)bfn << XEN_PAGE_SHIFT; + + dma |= paddr & ~XEN_PAGE_MASK; + + return dma; } -static phys_addr_t xen_bus_to_phys(dma_addr_t baddr) +static inline phys_addr_t xen_bus_to_phys(dma_addr_t baddr) { - return machine_to_phys(XMADDR(baddr)).paddr; + unsigned long xen_pfn = bfn_to_pfn(XEN_PFN_DOWN(baddr)); + dma_addr_t dma = (dma_addr_t)xen_pfn << XEN_PAGE_SHIFT; + phys_addr_t paddr = dma; + + paddr |= baddr & ~XEN_PAGE_MASK; + + return paddr; } -static dma_addr_t xen_virt_to_bus(void *address) +static inline dma_addr_t xen_virt_to_bus(void *address) { return xen_phys_to_bus(virt_to_phys(address)); } -static int check_pages_physically_contiguous(unsigned long pfn, +static int check_pages_physically_contiguous(unsigned long xen_pfn, unsigned int offset, size_t length) { - unsigned long next_mfn; + unsigned long next_bfn; int i; int nr_pages; - next_mfn = pfn_to_mfn(pfn); - nr_pages = (offset + length + PAGE_SIZE-1) >> PAGE_SHIFT; + next_bfn = pfn_to_bfn(xen_pfn); + nr_pages = (offset + length + XEN_PAGE_SIZE-1) >> XEN_PAGE_SHIFT; for (i = 1; i < nr_pages; i++) { - if (pfn_to_mfn(++pfn) != ++next_mfn) + if (pfn_to_bfn(++xen_pfn) != ++next_bfn) return 0; } return 1; } -static int range_straddles_page_boundary(phys_addr_t p, size_t size) +static inline int range_straddles_page_boundary(phys_addr_t p, size_t size) { - unsigned long pfn = PFN_DOWN(p); - unsigned int offset = p & ~PAGE_MASK; + unsigned long xen_pfn = XEN_PFN_DOWN(p); + unsigned int offset = p & ~XEN_PAGE_MASK; - if (offset + size <= PAGE_SIZE) + if (offset + size <= XEN_PAGE_SIZE) return 0; - if (check_pages_physically_contiguous(pfn, offset, size)) + if (check_pages_physically_contiguous(xen_pfn, offset, size)) return 0; return 1; } static int is_xen_swiotlb_buffer(dma_addr_t dma_addr) { - unsigned long mfn = PFN_DOWN(dma_addr); - unsigned long pfn = mfn_to_local_pfn(mfn); - phys_addr_t paddr; + unsigned long bfn = XEN_PFN_DOWN(dma_addr); + unsigned long xen_pfn = bfn_to_local_pfn(bfn); + phys_addr_t paddr = XEN_PFN_PHYS(xen_pfn); /* If the address is outside our domain, it CAN * have the same virtual address as another address * in our domain. Therefore _only_ check address within our domain. */ - if (pfn_valid(pfn)) { - paddr = PFN_PHYS(pfn); + if (pfn_valid(PFN_DOWN(paddr))) { return paddr >= virt_to_phys(xen_io_tlb_start) && paddr < virt_to_phys(xen_io_tlb_end); } @@ -124,6 +160,8 @@ { int i, rc; int dma_bits; + dma_addr_t dma_handle; + phys_addr_t p = virt_to_phys(buf); dma_bits = get_order(IO_TLB_SEGSIZE << IO_TLB_SHIFT) + PAGE_SHIFT; @@ -133,9 +171,9 @@ do { rc = xen_create_contiguous_region( - (unsigned long)buf + (i << IO_TLB_SHIFT), + p + (i << IO_TLB_SHIFT), get_order(slabs << IO_TLB_SHIFT), - dma_bits); + dma_bits, &dma_handle); } while (rc && dma_bits++ < max_dma_bits); if (rc) return rc; @@ -196,14 +234,14 @@ #define SLABS_PER_PAGE (1 << (PAGE_SHIFT - IO_TLB_SHIFT)) #define IO_TLB_MIN_SLABS ((1<<20) >> IO_TLB_SHIFT) while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) { - xen_io_tlb_start = (void *)__get_free_pages(__GFP_NOWARN, order); + xen_io_tlb_start = (void *)xen_get_swiotlb_free_pages(order); if (xen_io_tlb_start) break; order--; } if (order != get_order(bytes)) { - pr_warn("Warning: only able to allocate %ld MB " - "for software IO TLB\n", (PAGE_SIZE << order) >> 20); + pr_warn("Warning: only able to allocate %ld MB for software IO TLB\n", + (PAGE_SIZE << order) >> 20); xen_io_tlb_nslabs = SLABS_PER_PAGE << order; bytes = xen_io_tlb_nslabs << IO_TLB_SHIFT; } @@ -242,11 +280,11 @@ if (repeat--) { xen_io_tlb_nslabs = max(1024UL, /* Min is 2MB */ (xen_io_tlb_nslabs >> 1)); - printk(KERN_INFO "Xen-SWIOTLB: Lowering to %luMB\n", - (xen_io_tlb_nslabs << IO_TLB_SHIFT) >> 20); + pr_info("Lowering to %luMB\n", + (xen_io_tlb_nslabs << IO_TLB_SHIFT) >> 20); goto retry; } - pr_err("%s (rc:%d)", xen_swiotlb_error(m_ret), rc); + pr_err("%s (rc:%d)\n", xen_swiotlb_error(m_ret), rc); if (early) panic("%s (rc:%d)", xen_swiotlb_error(m_ret), rc); else @@ -261,7 +299,6 @@ void *ret; int order = get_order(size); u64 dma_mask = DMA_BIT_MASK(32); - unsigned long vstart; phys_addr_t phys; dma_addr_t dev_addr; @@ -273,11 +310,12 @@ */ flags &= ~(__GFP_DMA | __GFP_HIGHMEM); - if (dma_alloc_from_coherent(hwdev, size, dma_handle, &ret)) - return ret; - - vstart = __get_free_pages(flags, order); - ret = (void *)vstart; + /* On ARM this function returns an ioremap'ped virtual address for + * which virt_to_phys doesn't return the corresponding physical + * address. In fact on ARM virt_to_phys only works for kernel direct + * mapped RAM memory. Also see comment below. + */ + ret = xen_alloc_coherent_pages(hwdev, size, dma_handle, flags, attrs); if (!ret) return ret; @@ -285,18 +323,21 @@ if (hwdev && hwdev->coherent_dma_mask) dma_mask = dma_alloc_coherent_mask(hwdev, flags); - phys = virt_to_phys(ret); + /* At this point dma_handle is the physical address, next we are + * going to set it to the machine address. + * Do not use virt_to_phys(ret) because on ARM it doesn't correspond + * to *dma_handle. */ + phys = *dma_handle; dev_addr = xen_phys_to_bus(phys); if (((dev_addr + size - 1 <= dma_mask)) && !range_straddles_page_boundary(phys, size)) *dma_handle = dev_addr; else { - if (xen_create_contiguous_region(vstart, order, - fls64(dma_mask)) != 0) { - free_pages(vstart, order); + if (xen_create_contiguous_region(phys, order, + fls64(dma_mask), dma_handle) != 0) { + xen_free_coherent_pages(hwdev, size, ret, (dma_addr_t)phys, attrs); return NULL; } - *dma_handle = virt_to_machine(ret).maddr; } memset(ret, 0, size); return ret; @@ -311,19 +352,18 @@ phys_addr_t phys; u64 dma_mask = DMA_BIT_MASK(32); - if (dma_release_from_coherent(hwdev, order, vaddr)) - return; - if (hwdev && hwdev->coherent_dma_mask) dma_mask = hwdev->coherent_dma_mask; - phys = virt_to_phys(vaddr); + /* do not use virt_to_phys because on ARM it doesn't return you the + * physical address */ + phys = xen_bus_to_phys(dev_addr); if (((dev_addr + size - 1 > dma_mask)) || range_straddles_page_boundary(phys, size)) - xen_destroy_contiguous_region((unsigned long)vaddr, order); + xen_destroy_contiguous_region(phys, order); - free_pages((unsigned long)vaddr, order); + xen_free_coherent_pages(hwdev, size, vaddr, (dma_addr_t)phys, attrs); } EXPORT_SYMBOL_GPL(xen_swiotlb_free_coherent); @@ -350,16 +390,27 @@ * buffering it. */ if (dma_capable(dev, dev_addr, size) && - !range_straddles_page_boundary(phys, size) && !swiotlb_force) + !range_straddles_page_boundary(phys, size) && + !xen_arch_need_swiotlb(dev, phys, dev_addr) && + !swiotlb_force) { + /* we are not interested in the dma_addr returned by + * xen_dma_map_page, only in the potential cache flushes executed + * by the function. */ + xen_dma_map_page(dev, page, dev_addr, offset, size, dir, attrs); return dev_addr; + } /* * Oh well, have to allocate and map a bounce buffer. */ + trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force); + map = swiotlb_tbl_map_single(dev, start_dma_addr, phys, size, dir); if (map == SWIOTLB_MAP_ERROR) return DMA_ERROR_CODE; + xen_dma_map_page(dev, pfn_to_page(map >> PAGE_SHIFT), + dev_addr, map & ~PAGE_MASK, size, dir, attrs); dev_addr = xen_phys_to_bus(map); /* @@ -382,12 +433,15 @@ * whatever the device wrote there. */ static void xen_unmap_single(struct device *hwdev, dma_addr_t dev_addr, - size_t size, enum dma_data_direction dir) + size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) { phys_addr_t paddr = xen_bus_to_phys(dev_addr); BUG_ON(dir == DMA_NONE); + xen_dma_unmap_page(hwdev, dev_addr, size, dir, attrs); + /* NOTE: We use dev_addr here, not paddr! */ if (is_xen_swiotlb_buffer(dev_addr)) { swiotlb_tbl_unmap_single(hwdev, paddr, size, dir); @@ -410,7 +464,7 @@ size_t size, enum dma_data_direction dir, struct dma_attrs *attrs) { - xen_unmap_single(hwdev, dev_addr, size, dir); + xen_unmap_single(hwdev, dev_addr, size, dir, attrs); } EXPORT_SYMBOL_GPL(xen_swiotlb_unmap_page); @@ -433,11 +487,15 @@ BUG_ON(dir == DMA_NONE); + if (target == SYNC_FOR_CPU) + xen_dma_sync_single_for_cpu(hwdev, dev_addr, size, dir); + /* NOTE: We use dev_addr here, not paddr! */ - if (is_xen_swiotlb_buffer(dev_addr)) { + if (is_xen_swiotlb_buffer(dev_addr)) swiotlb_tbl_sync_single(hwdev, paddr, size, dir, target); - return; - } + + if (target == SYNC_FOR_DEVICE) + xen_dma_sync_single_for_device(hwdev, dev_addr, size, dir); if (dir != DMA_FROM_DEVICE) return; @@ -492,6 +550,7 @@ dma_addr_t dev_addr = xen_phys_to_bus(paddr); if (swiotlb_force || + xen_arch_need_swiotlb(hwdev, paddr, dev_addr) || !dma_capable(hwdev, dev_addr, sg->length) || range_straddles_page_boundary(paddr, sg->length)) { phys_addr_t map = swiotlb_tbl_map_single(hwdev, @@ -500,17 +559,34 @@ sg->length, dir); if (map == SWIOTLB_MAP_ERROR) { + dev_warn(hwdev, "swiotlb buffer is full\n"); /* Don't panic here, we expect map_sg users to do proper error handling. */ xen_swiotlb_unmap_sg_attrs(hwdev, sgl, i, dir, attrs); - sgl[0].dma_length = 0; - return DMA_ERROR_CODE; + sg_dma_len(sgl) = 0; + return 0; } + xen_dma_map_page(hwdev, pfn_to_page(map >> PAGE_SHIFT), + dev_addr, + map & ~PAGE_MASK, + sg->length, + dir, + attrs); sg->dma_address = xen_phys_to_bus(map); - } else + } else { + /* we are not interested in the dma_addr returned by + * xen_dma_map_page, only in the potential cache flushes executed + * by the function. */ + xen_dma_map_page(hwdev, pfn_to_page(paddr >> PAGE_SHIFT), + dev_addr, + paddr & ~PAGE_MASK, + sg->length, + dir, + attrs); sg->dma_address = dev_addr; - sg->dma_length = sg->length; + } + sg_dma_len(sg) = sg->length; } return nelems; } @@ -531,7 +607,7 @@ BUG_ON(dir == DMA_NONE); for_each_sg(sgl, sg, nelems, i) - xen_unmap_single(hwdev, sg->dma_address, sg->dma_length, dir); + xen_unmap_single(hwdev, sg->dma_address, sg_dma_len(sg), dir, attrs); } EXPORT_SYMBOL_GPL(xen_swiotlb_unmap_sg_attrs); @@ -553,7 +629,7 @@ for_each_sg(sgl, sg, nelems, i) xen_swiotlb_sync_single(hwdev, sg->dma_address, - sg->dma_length, dir, target); + sg_dma_len(sg), dir, target); } void @@ -591,3 +667,15 @@ return xen_virt_to_bus(xen_io_tlb_end - 1) <= mask; } EXPORT_SYMBOL_GPL(xen_swiotlb_dma_supported); + +int +xen_swiotlb_set_dma_mask(struct device *dev, u64 dma_mask) +{ + if (!dev->dma_mask || !xen_swiotlb_dma_supported(dev, dma_mask)) + return -EIO; + + *dev->dma_mask = dma_mask; + + return 0; +} +EXPORT_SYMBOL_GPL(xen_swiotlb_set_dma_mask);