| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1 | /** | 
 | 2 |  * iommu_fill_pdir - Insert coalesced scatter/gather chunks into the I/O Pdir. | 
 | 3 |  * @ioc: The I/O Controller. | 
 | 4 |  * @startsg: The scatter/gather list of coalesced chunks. | 
 | 5 |  * @nents: The number of entries in the scatter/gather list. | 
 | 6 |  * @hint: The DMA Hint. | 
 | 7 |  * | 
 | 8 |  * This function inserts the coalesced scatter/gather list chunks into the | 
 | 9 |  * I/O Controller's I/O Pdir. | 
 | 10 |  */  | 
 | 11 | static inline unsigned int | 
 | 12 | iommu_fill_pdir(struct ioc *ioc, struct scatterlist *startsg, int nents,  | 
 | 13 | 		unsigned long hint, | 
 | 14 | 		void (*iommu_io_pdir_entry)(u64 *, space_t, unsigned long, | 
 | 15 | 					    unsigned long)) | 
 | 16 | { | 
 | 17 | 	struct scatterlist *dma_sg = startsg;	/* pointer to current DMA */ | 
 | 18 | 	unsigned int n_mappings = 0; | 
 | 19 | 	unsigned long dma_offset = 0, dma_len = 0; | 
 | 20 | 	u64 *pdirp = NULL; | 
 | 21 |  | 
 | 22 | 	/* Horrible hack.  For efficiency's sake, dma_sg starts one  | 
 | 23 | 	 * entry below the true start (it is immediately incremented | 
 | 24 | 	 * in the loop) */ | 
 | 25 | 	 dma_sg--; | 
 | 26 |  | 
 | 27 | 	while (nents-- > 0) { | 
 | 28 | 		unsigned long vaddr; | 
 | 29 | 		long size; | 
 | 30 |  | 
 | 31 | 		DBG_RUN_SG(" %d : %08lx/%05x %08lx/%05x\n", nents, | 
 | 32 | 			   (unsigned long)sg_dma_address(startsg), cnt, | 
 | 33 | 			   sg_virt_addr(startsg), startsg->length | 
 | 34 | 		); | 
 | 35 |  | 
 | 36 |  | 
 | 37 | 		/* | 
 | 38 | 		** Look for the start of a new DMA stream | 
 | 39 | 		*/ | 
 | 40 | 		 | 
 | 41 | 		if (sg_dma_address(startsg) & PIDE_FLAG) { | 
 | 42 | 			u32 pide = sg_dma_address(startsg) & ~PIDE_FLAG; | 
 | 43 |  | 
 | 44 | 			BUG_ON(pdirp && (dma_len != sg_dma_len(dma_sg))); | 
 | 45 |  | 
 | 46 | 			dma_sg++; | 
 | 47 |  | 
 | 48 | 			dma_len = sg_dma_len(startsg); | 
 | 49 | 			sg_dma_len(startsg) = 0; | 
 | 50 | 			dma_offset = (unsigned long) pide & ~IOVP_MASK; | 
 | 51 | 			n_mappings++; | 
 | 52 | #if defined(ZX1_SUPPORT) | 
 | 53 | 			/* Pluto IOMMU IO Virt Address is not zero based */ | 
 | 54 | 			sg_dma_address(dma_sg) = pide | ioc->ibase; | 
 | 55 | #else | 
 | 56 | 			/* SBA, ccio, and dino are zero based. | 
 | 57 | 			 * Trying to save a few CPU cycles for most users. | 
 | 58 | 			 */ | 
 | 59 | 			sg_dma_address(dma_sg) = pide; | 
 | 60 | #endif | 
 | 61 | 			pdirp = &(ioc->pdir_base[pide >> IOVP_SHIFT]); | 
 | 62 | 			prefetchw(pdirp); | 
 | 63 | 		} | 
 | 64 | 		 | 
 | 65 | 		BUG_ON(pdirp == NULL); | 
 | 66 | 		 | 
 | 67 | 		vaddr = sg_virt_addr(startsg); | 
 | 68 | 		sg_dma_len(dma_sg) += startsg->length; | 
 | 69 | 		size = startsg->length + dma_offset; | 
 | 70 | 		dma_offset = 0; | 
 | 71 | #ifdef IOMMU_MAP_STATS | 
 | 72 | 		ioc->msg_pages += startsg->length >> IOVP_SHIFT; | 
 | 73 | #endif | 
 | 74 | 		do { | 
 | 75 | 			iommu_io_pdir_entry(pdirp, KERNEL_SPACE,  | 
 | 76 | 					    vaddr, hint); | 
 | 77 | 			vaddr += IOVP_SIZE; | 
 | 78 | 			size -= IOVP_SIZE; | 
 | 79 | 			pdirp++; | 
 | 80 | 		} while(unlikely(size > 0)); | 
 | 81 | 		startsg++; | 
 | 82 | 	} | 
 | 83 | 	return(n_mappings); | 
 | 84 | } | 
 | 85 |  | 
 | 86 |  | 
 | 87 | /* | 
 | 88 | ** First pass is to walk the SG list and determine where the breaks are | 
 | 89 | ** in the DMA stream. Allocates PDIR entries but does not fill them. | 
 | 90 | ** Returns the number of DMA chunks. | 
 | 91 | ** | 
 | 92 | ** Doing the fill separate from the coalescing/allocation keeps the | 
 | 93 | ** code simpler. Future enhancement could make one pass through | 
 | 94 | ** the sglist do both. | 
 | 95 | */ | 
 | 96 |  | 
 | 97 | static inline unsigned int | 
 | 98 | iommu_coalesce_chunks(struct ioc *ioc, struct scatterlist *startsg, int nents, | 
 | 99 | 		      int (*iommu_alloc_range)(struct ioc *, size_t)) | 
 | 100 | { | 
 | 101 | 	struct scatterlist *contig_sg;	   /* contig chunk head */ | 
 | 102 | 	unsigned long dma_offset, dma_len; /* start/len of DMA stream */ | 
 | 103 | 	unsigned int n_mappings = 0; | 
 | 104 |  | 
 | 105 | 	while (nents > 0) { | 
 | 106 |  | 
 | 107 | 		/* | 
 | 108 | 		** Prepare for first/next DMA stream | 
 | 109 | 		*/ | 
 | 110 | 		contig_sg = startsg; | 
 | 111 | 		dma_len = startsg->length; | 
 | 112 | 		dma_offset = sg_virt_addr(startsg) & ~IOVP_MASK; | 
 | 113 |  | 
 | 114 | 		/* PARANOID: clear entries */ | 
 | 115 | 		sg_dma_address(startsg) = 0; | 
 | 116 | 		sg_dma_len(startsg) = 0; | 
 | 117 |  | 
 | 118 | 		/* | 
 | 119 | 		** This loop terminates one iteration "early" since | 
 | 120 | 		** it's always looking one "ahead". | 
 | 121 | 		*/ | 
 | 122 | 		while(--nents > 0) { | 
 | 123 | 			unsigned long prevstartsg_end, startsg_end; | 
 | 124 |  | 
 | 125 | 			prevstartsg_end = sg_virt_addr(startsg) + | 
 | 126 | 				startsg->length; | 
 | 127 |  | 
 | 128 | 			startsg++; | 
 | 129 | 			startsg_end = sg_virt_addr(startsg) +  | 
 | 130 | 				startsg->length; | 
 | 131 |  | 
 | 132 | 			/* PARANOID: clear entries */ | 
 | 133 | 			sg_dma_address(startsg) = 0; | 
 | 134 | 			sg_dma_len(startsg) = 0; | 
 | 135 |  | 
 | 136 | 			/* | 
 | 137 | 			** First make sure current dma stream won't | 
 | 138 | 			** exceed DMA_CHUNK_SIZE if we coalesce the | 
 | 139 | 			** next entry. | 
 | 140 | 			*/    | 
 | 141 | 			if(unlikely(ROUNDUP(dma_len + dma_offset + startsg->length, | 
 | 142 | 					    IOVP_SIZE) > DMA_CHUNK_SIZE)) | 
 | 143 | 				break; | 
 | 144 |  | 
 | 145 | 			/* | 
 | 146 | 			** Next see if we can append the next chunk (i.e. | 
 | 147 | 			** it must end on one page and begin on another | 
 | 148 | 			*/ | 
 | 149 | 			if (unlikely(((prevstartsg_end | sg_virt_addr(startsg)) & ~PAGE_MASK) != 0)) | 
 | 150 | 				break; | 
 | 151 | 			 | 
 | 152 | 			dma_len += startsg->length; | 
 | 153 | 		} | 
 | 154 |  | 
 | 155 | 		/* | 
 | 156 | 		** End of DMA Stream | 
 | 157 | 		** Terminate last VCONTIG block. | 
 | 158 | 		** Allocate space for DMA stream. | 
 | 159 | 		*/ | 
 | 160 | 		sg_dma_len(contig_sg) = dma_len; | 
 | 161 | 		dma_len = ROUNDUP(dma_len + dma_offset, IOVP_SIZE); | 
 | 162 | 		sg_dma_address(contig_sg) = | 
 | 163 | 			PIDE_FLAG  | 
 | 164 | 			| (iommu_alloc_range(ioc, dma_len) << IOVP_SHIFT) | 
 | 165 | 			| dma_offset; | 
 | 166 | 		n_mappings++; | 
 | 167 | 	} | 
 | 168 |  | 
 | 169 | 	return n_mappings; | 
 | 170 | } | 
 | 171 |  |