The maximum of SW-IOMMU is limited to 2^11*128 = 256K. And the size of IO_TLB_DEFAULT_SIZE is limited to (64UL<<20) 64M now. While in different platform and different requirement this seems improper. So modifing the IO_TLB_SEGSIZE to io_tlb_segsize and IO_TLB_DEFAULT_SIZE to io_tlb_default_size which can configure by kernel cmdline. This can meet different requirement. Signed-off-by: Chuansheng Liu <chuansheng.liu@xxxxxxxxx> Signed-off-by: Zhang Dongxing <dongxing.zhang@xxxxxxxxx> Signed-off-by: Wang Xiaoming <xiaoming.wang@xxxxxxxxx> --- patch v1 make this change at Kconfig which needs to edit the .config manually. https://lkml.org/lkml/2015/1/25/571 patch v2 only change IO_TLB_SEGSIZE configurable. https://lkml.org/lkml/2015/2/5/812 patch v3 parsing io_tlb_segsize and io_tlb_default_size independently. https://lkml.org/lkml/2015/2/15/217 patch v4 hasn't validated the data from command line. https://lkml.org/lkml/2015/2/17/114 patch v5 fix the postion of 'force'. https://lkml.org/lkml/2015/3/3/84 Documentation/kernel-parameters.txt | 5 +- arch/mips/cavium-octeon/dma-octeon.c | 2 +- arch/mips/netlogic/common/nlm-dma.c | 2 +- drivers/xen/swiotlb-xen.c | 6 +-- include/linux/swiotlb.h | 8 +-- lib/swiotlb.c | 99 ++++++++++++++++++++++++++-------- 6 files changed, 87 insertions(+), 35 deletions(-) diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 4df73da..8463ef4 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -3438,10 +3438,13 @@ bytes respectively. Such letter suffixes can also be entirely omitted. it if 0 is given (See Documentation/cgroups/memory.txt) swiotlb= [ARM,IA-64,PPC,MIPS,X86] - Format: { <int> | force } + Format: { <int>,force,<int>,<int>} <int> -- Number of I/O TLB slabs force -- force using of bounce buffers even if they wouldn't be automatically used by the kernel + <int> -- Maximum allowable number of contiguous slabs to map + <int> -- The size of SW-MMU mapped. + "Use ',' to seperate them." switches= [HW,M68k] diff --git a/arch/mips/cavium-octeon/dma-octeon.c b/arch/mips/cavium-octeon/dma-octeon.c index 3778655..a521af6 100644 --- a/arch/mips/cavium-octeon/dma-octeon.c +++ b/arch/mips/cavium-octeon/dma-octeon.c @@ -312,7 +312,7 @@ void __init plat_swiotlb_setup(void) swiotlbsize = 64 * (1<<20); #endif swiotlb_nslabs = swiotlbsize >> IO_TLB_SHIFT; - swiotlb_nslabs = ALIGN(swiotlb_nslabs, IO_TLB_SEGSIZE); + swiotlb_nslabs = ALIGN(swiotlb_nslabs, io_tlb_segsize); swiotlbsize = swiotlb_nslabs << IO_TLB_SHIFT; octeon_swiotlb = alloc_bootmem_low_pages(swiotlbsize); diff --git a/arch/mips/netlogic/common/nlm-dma.c b/arch/mips/netlogic/common/nlm-dma.c index f3d4ae8..eeffa8f 100644 --- a/arch/mips/netlogic/common/nlm-dma.c +++ b/arch/mips/netlogic/common/nlm-dma.c @@ -99,7 +99,7 @@ void __init plat_swiotlb_setup(void) swiotlbsize = 1 << 20; /* 1 MB for now */ swiotlb_nslabs = swiotlbsize >> IO_TLB_SHIFT; - swiotlb_nslabs = ALIGN(swiotlb_nslabs, IO_TLB_SEGSIZE); + swiotlb_nslabs = ALIGN(swiotlb_nslabs, io_tlb_segsize); swiotlbsize = swiotlb_nslabs << IO_TLB_SHIFT; nlm_swiotlb = alloc_bootmem_low_pages(swiotlbsize); diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 810ad41..3b3e9fe 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -164,11 +164,11 @@ xen_swiotlb_fixup(void *buf, size_t size, unsigned long nslabs) 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; + dma_bits = get_order(io_tlb_segsize << IO_TLB_SHIFT) + PAGE_SHIFT; i = 0; do { - int slabs = min(nslabs - i, (unsigned long)IO_TLB_SEGSIZE); + int slabs = min(nslabs - i, (unsigned long)io_tlb_segsize); do { rc = xen_create_contiguous_region( @@ -187,7 +187,7 @@ static unsigned long xen_set_nslabs(unsigned long nr_tbl) { if (!nr_tbl) { xen_io_tlb_nslabs = (64 * 1024 * 1024 >> IO_TLB_SHIFT); - xen_io_tlb_nslabs = ALIGN(xen_io_tlb_nslabs, IO_TLB_SEGSIZE); + xen_io_tlb_nslabs = ALIGN(xen_io_tlb_nslabs, io_tlb_segsize); } else xen_io_tlb_nslabs = nr_tbl; diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index e7a018e..13506db 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -8,13 +8,7 @@ struct dma_attrs; struct scatterlist; extern int swiotlb_force; - -/* - * Maximum allowable number of contiguous slabs to map, - * must be a power of 2. What is the appropriate value ? - * The complexity of {map,unmap}_single is linearly dependent on this value. - */ -#define IO_TLB_SEGSIZE 128 +extern int io_tlb_segsize; /* * log of the size of each IO TLB slab. The number of slabs is command line diff --git a/lib/swiotlb.c b/lib/swiotlb.c index 4abda07..223a45b 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -56,6 +56,25 @@ int swiotlb_force; /* + * default to 128 + * Maximum allowable number of contiguous slabs to map, + * must be a power of 2. What is the appropriate value ? + * define io_tlb_segsize as a parameter + * which can be changed dynamically in config file + * or as a parameter during bootup for special usage. + * The complexity of {map,unmap}_single is linearly dependent on this value. + */ +#define IO_TLB_SEGSIZE 128 +int io_tlb_segsize = IO_TLB_SEGSIZE; + +/* default to 64MB + * define io_tlb_default_size as a parameter + * which can be changed dynamically in config file for special usage. + */ +#define IO_TLB_DEFAULT_SIZE (64UL<<20) +static unsigned long io_tlb_default_size = IO_TLB_DEFAULT_SIZE; + +/* * 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. @@ -96,18 +115,57 @@ static DEFINE_SPINLOCK(io_tlb_lock); static int late_alloc; +/* + * Example: + * BOARD_KERNEL_CMDLINE += swiotlb=32768,force,512,268435456 + * io_tlb_nslabs=32768, swiotlb_force=1, + * io_tlb_segsize=512, io_tlb_default_size=268435456 + */ static int __init setup_io_tlb_npages(char *str) { - if (isdigit(*str)) { - io_tlb_nslabs = simple_strtoul(str, &str, 0); - /* avoid tail segment of size < IO_TLB_SEGSIZE */ - io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE); - } - if (*str == ',') + unsigned long swiotlb_param[3] ={0,0,0}; + int num_param = 3; + + while (*str) { + if (!strncmp(str, "force", 5)) { + swiotlb_force = 1; + str += 5; + if (*str != ',') + break; + ++str; + continue; + } + if (!num_param) + break; + if (isdigit(*str)) { + swiotlb_param[3 - num_param] = simple_strtoul(str, &str, 0); + num_param--; + } + if (*str != ',') + break; ++str; - if (!strcmp(str, "force")) - swiotlb_force = 1; + } + + if (swiotlb_param[1]) { + int n = 0; + io_tlb_segsize = (int)swiotlb_param[1]; + io_tlb_segsize = ALIGN(io_tlb_segsize, IO_TLB_SEGSIZE); + while ((io_tlb_segsize - 1) >> n) + n++; + io_tlb_segsize = (1 << n); + } + + if (swiotlb_param[0]) { + io_tlb_nslabs = swiotlb_param[0]; + /* avoid tail segment of size < io_tlb_segsize */ + io_tlb_nslabs = ALIGN(io_tlb_nslabs, io_tlb_segsize); + } + + if (swiotlb_param[2]) { + io_tlb_default_size = swiotlb_param[2]; + io_tlb_default_size = ALIGN(io_tlb_default_size, IO_TLB_DEFAULT_SIZE); + } return 0; } @@ -120,15 +178,13 @@ unsigned long swiotlb_nr_tbl(void) } EXPORT_SYMBOL_GPL(swiotlb_nr_tbl); -/* default to 64MB */ -#define IO_TLB_DEFAULT_SIZE (64UL<<20) unsigned long swiotlb_size_or_default(void) { unsigned long size; size = io_tlb_nslabs << IO_TLB_SHIFT; - return size ? size : (IO_TLB_DEFAULT_SIZE); + return size ? size : (io_tlb_default_size); } /* Note that this doesn't work with highmem page */ @@ -183,7 +239,7 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) /* * Allocate and initialize the free list array. This array is used - * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE + * to find contiguous free memory regions of size up to io_tlb_segsize * between io_tlb_start and io_tlb_end. */ io_tlb_list = memblock_virt_alloc( @@ -193,7 +249,7 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t)), PAGE_SIZE); for (i = 0; i < io_tlb_nslabs; i++) { - io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE); + io_tlb_list[i] = io_tlb_segsize - OFFSET(i, io_tlb_segsize); io_tlb_orig_addr[i] = INVALID_PHYS_ADDR; } io_tlb_index = 0; @@ -211,13 +267,12 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) void __init swiotlb_init(int verbose) { - size_t default_size = IO_TLB_DEFAULT_SIZE; unsigned char *vstart; unsigned long bytes; if (!io_tlb_nslabs) { - io_tlb_nslabs = (default_size >> IO_TLB_SHIFT); - io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE); + io_tlb_nslabs = (io_tlb_default_size >> IO_TLB_SHIFT); + io_tlb_nslabs = ALIGN(io_tlb_nslabs, io_tlb_segsize); } bytes = io_tlb_nslabs << IO_TLB_SHIFT; @@ -249,7 +304,7 @@ swiotlb_late_init_with_default_size(size_t default_size) if (!io_tlb_nslabs) { io_tlb_nslabs = (default_size >> IO_TLB_SHIFT); - io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE); + io_tlb_nslabs = ALIGN(io_tlb_nslabs, io_tlb_segsize); } /* @@ -308,7 +363,7 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) /* * Allocate and initialize the free list array. This array is used - * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE + * to find contiguous free memory regions of size up to io_tlb_segsize * between io_tlb_start and io_tlb_end. */ io_tlb_list = (unsigned int *)__get_free_pages(GFP_KERNEL, @@ -324,7 +379,7 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) goto cleanup4; for (i = 0; i < io_tlb_nslabs; i++) { - io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE); + io_tlb_list[i] = io_tlb_segsize - OFFSET(i, io_tlb_segsize); io_tlb_orig_addr[i] = INVALID_PHYS_ADDR; } io_tlb_index = 0; @@ -493,7 +548,7 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, for (i = index; i < (int) (index + nslots); i++) io_tlb_list[i] = 0; - for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE - 1) && io_tlb_list[i]; i--) + for (i = index - 1; (OFFSET(i, io_tlb_segsize) != io_tlb_segsize - 1) && io_tlb_list[i]; i--) io_tlb_list[i] = ++count; tlb_addr = io_tlb_start + (index << IO_TLB_SHIFT); @@ -571,7 +626,7 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, */ spin_lock_irqsave(&io_tlb_lock, flags); { - count = ((index + nslots) < ALIGN(index + 1, IO_TLB_SEGSIZE) ? + count = ((index + nslots) < ALIGN(index + 1, io_tlb_segsize) ? io_tlb_list[index + nslots] : 0); /* * Step 1: return the slots to the free list, merging the @@ -585,7 +640,7 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, * Step 2: merge the returned slots with the preceding slots, * if available (non zero) */ - for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE -1) && io_tlb_list[i]; i--) + for (i = index - 1; (OFFSET(i, io_tlb_segsize) != io_tlb_segsize -1) && io_tlb_list[i]; i--) io_tlb_list[i] = ++count; } spin_unlock_irqrestore(&io_tlb_lock, flags); -- 1.7.9.5
