diff options
Diffstat (limited to 'lib')
| -rw-r--r-- | lib/Makefile | 1 | ||||
| -rw-r--r-- | lib/iommu-helper.c | 80 | ||||
| -rw-r--r-- | lib/radix-tree.c | 15 | ||||
| -rw-r--r-- | lib/swiotlb.c | 41 |
4 files changed, 127 insertions, 10 deletions
diff --git a/lib/Makefile b/lib/Makefile index 543f2502..a18062e4 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -65,6 +65,7 @@ obj-$(CONFIG_SMP) += pcounter.o obj-$(CONFIG_AUDIT_GENERIC) += audit.o obj-$(CONFIG_SWIOTLB) += swiotlb.o +obj-$(CONFIG_IOMMU_HELPER) += iommu-helper.o obj-$(CONFIG_FAULT_INJECTION) += fault-inject.o lib-$(CONFIG_GENERIC_BUG) += bug.o diff --git a/lib/iommu-helper.c b/lib/iommu-helper.c new file mode 100644 index 0000000..495575a --- /dev/null +++ b/lib/iommu-helper.c @@ -0,0 +1,80 @@ +/* + * IOMMU helper functions for the free area management + */ + +#include <linux/module.h> +#include <linux/bitops.h> + +static unsigned long find_next_zero_area(unsigned long *map, + unsigned long size, + unsigned long start, + unsigned int nr, + unsigned long align_mask) +{ + unsigned long index, end, i; +again: + index = find_next_zero_bit(map, size, start); + + /* Align allocation */ + index = (index + align_mask) & ~align_mask; + + end = index + nr; + if (end >= size) + return -1; + for (i = index; i < end; i++) { + if (test_bit(i, map)) { + start = i+1; + goto again; + } + } + return index; +} + +static inline void set_bit_area(unsigned long *map, unsigned long i, + int len) +{ + unsigned long end = i + len; + while (i < end) { + __set_bit(i, map); + i++; + } +} + +static inline int is_span_boundary(unsigned int index, unsigned int nr, + unsigned long shift, + unsigned long boundary_size) +{ + shift = (shift + index) & (boundary_size - 1); + return shift + nr > boundary_size; +} + +unsigned long iommu_area_alloc(unsigned long *map, unsigned long size, + unsigned long start, unsigned int nr, + unsigned long shift, unsigned long boundary_size, + unsigned long align_mask) +{ + unsigned long index; +again: + index = find_next_zero_area(map, size, start, nr, align_mask); + if (index != -1) { + if (is_span_boundary(index, nr, shift, boundary_size)) { + /* we could do more effectively */ + start = index + 1; + goto again; + } + set_bit_area(map, index, nr); + } + return index; +} +EXPORT_SYMBOL(iommu_area_alloc); + +void iommu_area_free(unsigned long *map, unsigned long start, unsigned int nr) +{ + unsigned long end = start + nr; + + while (start < end) { + __clear_bit(start, map); + start++; + } +} +EXPORT_SYMBOL(iommu_area_free); diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 48c250f..65f0e75 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -95,14 +95,17 @@ static inline gfp_t root_gfp_mask(struct radix_tree_root *root) static struct radix_tree_node * radix_tree_node_alloc(struct radix_tree_root *root) { - struct radix_tree_node *ret; + struct radix_tree_node *ret = NULL; gfp_t gfp_mask = root_gfp_mask(root); - ret = kmem_cache_alloc(radix_tree_node_cachep, - set_migrateflags(gfp_mask, __GFP_RECLAIMABLE)); - if (ret == NULL && !(gfp_mask & __GFP_WAIT)) { + if (!(gfp_mask & __GFP_WAIT)) { struct radix_tree_preload *rtp; + /* + * Provided the caller has preloaded here, we will always + * succeed in getting a node here (and never reach + * kmem_cache_alloc) + */ rtp = &__get_cpu_var(radix_tree_preloads); if (rtp->nr) { ret = rtp->nodes[rtp->nr - 1]; @@ -110,6 +113,10 @@ radix_tree_node_alloc(struct radix_tree_root *root) rtp->nr--; } } + if (ret == NULL) + ret = kmem_cache_alloc(radix_tree_node_cachep, + set_migrateflags(gfp_mask, __GFP_RECLAIMABLE)); + BUG_ON(radix_tree_is_indirect_ptr(ret)); return ret; } diff --git a/lib/swiotlb.c b/lib/swiotlb.c index 1a8050a..4bb5a11 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -282,6 +282,15 @@ address_needs_mapping(struct device *hwdev, dma_addr_t addr) return (addr & ~mask) != 0; } +static inline unsigned int is_span_boundary(unsigned int index, + unsigned int nslots, + unsigned long offset_slots, + unsigned long max_slots) +{ + unsigned long offset = (offset_slots + index) & (max_slots - 1); + return offset + nslots > max_slots; +} + /* * Allocates bounce buffer and returns its kernel virtual address. */ @@ -292,6 +301,16 @@ map_single(struct device *hwdev, char *buffer, size_t size, int dir) char *dma_addr; unsigned int nslots, stride, index, wrap; int i; + unsigned long start_dma_addr; + unsigned long mask; + unsigned long offset_slots; + unsigned long max_slots; + + mask = dma_get_seg_boundary(hwdev); + start_dma_addr = virt_to_bus(io_tlb_start) & mask; + + offset_slots = ALIGN(start_dma_addr, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; + max_slots = ALIGN(mask + 1, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; /* * For mappings greater than a page, we limit the stride (and @@ -311,10 +330,17 @@ map_single(struct device *hwdev, char *buffer, size_t size, int dir) */ spin_lock_irqsave(&io_tlb_lock, flags); { - wrap = index = ALIGN(io_tlb_index, stride); - + index = ALIGN(io_tlb_index, stride); if (index >= io_tlb_nslabs) - wrap = index = 0; + index = 0; + + while (is_span_boundary(index, nslots, offset_slots, + max_slots)) { + index += stride; + if (index >= io_tlb_nslabs) + index = 0; + } + wrap = index; do { /* @@ -341,9 +367,12 @@ map_single(struct device *hwdev, char *buffer, size_t size, int dir) goto found; } - index += stride; - if (index >= io_tlb_nslabs) - index = 0; + do { + index += stride; + if (index >= io_tlb_nslabs) + index = 0; + } while (is_span_boundary(index, nslots, offset_slots, + max_slots)); } while (index != wrap); spin_unlock_irqrestore(&io_tlb_lock, flags); |
