| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1 | /* dma-alloc.c: consistent DMA memory allocation | 
 | 2 |  * | 
 | 3 |  * Derived from arch/ppc/mm/cachemap.c | 
 | 4 |  * | 
 | 5 |  *  PowerPC version derived from arch/arm/mm/consistent.c | 
 | 6 |  *    Copyright (C) 2001 Dan Malek (dmalek@jlc.net) | 
 | 7 |  * | 
 | 8 |  *  linux/arch/arm/mm/consistent.c | 
 | 9 |  * | 
 | 10 |  *  Copyright (C) 2000 Russell King | 
 | 11 |  * | 
 | 12 |  * Consistent memory allocators.  Used for DMA devices that want to | 
 | 13 |  * share uncached memory with the processor core.  The function return | 
 | 14 |  * is the virtual address and 'dma_handle' is the physical address. | 
 | 15 |  * Mostly stolen from the ARM port, with some changes for PowerPC. | 
 | 16 |  *						-- Dan | 
 | 17 |  * Modified for 36-bit support.  -Matt | 
 | 18 |  * | 
 | 19 |  * This program is free software; you can redistribute it and/or modify | 
 | 20 |  * it under the terms of the GNU General Public License version 2 as | 
 | 21 |  * published by the Free Software Foundation. | 
 | 22 |  */ | 
 | 23 |  | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 24 | #include <linux/module.h> | 
 | 25 | #include <linux/signal.h> | 
 | 26 | #include <linux/sched.h> | 
 | 27 | #include <linux/kernel.h> | 
 | 28 | #include <linux/errno.h> | 
 | 29 | #include <linux/string.h> | 
 | 30 | #include <linux/types.h> | 
 | 31 | #include <linux/ptrace.h> | 
 | 32 | #include <linux/mman.h> | 
 | 33 | #include <linux/mm.h> | 
 | 34 | #include <linux/swap.h> | 
 | 35 | #include <linux/stddef.h> | 
 | 36 | #include <linux/vmalloc.h> | 
 | 37 | #include <linux/init.h> | 
 | 38 | #include <linux/pci.h> | 
 | 39 |  | 
 | 40 | #include <asm/pgalloc.h> | 
 | 41 | #include <asm/io.h> | 
 | 42 | #include <asm/hardirq.h> | 
 | 43 | #include <asm/mmu_context.h> | 
 | 44 | #include <asm/pgtable.h> | 
 | 45 | #include <asm/mmu.h> | 
 | 46 | #include <asm/uaccess.h> | 
 | 47 | #include <asm/smp.h> | 
 | 48 |  | 
 | 49 | static int map_page(unsigned long va, unsigned long pa, pgprot_t prot) | 
 | 50 | { | 
 | 51 | 	pgd_t *pge; | 
 | 52 | 	pud_t *pue; | 
 | 53 | 	pmd_t *pme; | 
 | 54 | 	pte_t *pte; | 
 | 55 | 	int err = -ENOMEM; | 
 | 56 |  | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 57 | 	/* Use upper 10 bits of VA to index the first level map */ | 
 | 58 | 	pge = pgd_offset_k(va); | 
 | 59 | 	pue = pud_offset(pge, va); | 
 | 60 | 	pme = pmd_offset(pue, va); | 
 | 61 |  | 
 | 62 | 	/* Use middle 10 bits of VA to index the second-level map */ | 
| Hugh Dickins | 872fec1 | 2005-10-29 18:16:21 -0700 | [diff] [blame] | 63 | 	pte = pte_alloc_kernel(pme, va); | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 64 | 	if (pte != 0) { | 
 | 65 | 		err = 0; | 
 | 66 | 		set_pte(pte, mk_pte_phys(pa & PAGE_MASK, prot)); | 
 | 67 | 	} | 
 | 68 |  | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 69 | 	return err; | 
 | 70 | } | 
 | 71 |  | 
 | 72 | /* | 
 | 73 |  * This function will allocate the requested contiguous pages and | 
 | 74 |  * map them into the kernel's vmalloc() space.  This is done so we | 
 | 75 |  * get unique mapping for these pages, outside of the kernel's 1:1 | 
 | 76 |  * virtual:physical mapping.  This is necessary so we can cover large | 
 | 77 |  * portions of the kernel with single large page TLB entries, and | 
 | 78 |  * still get unique uncached pages for consistent DMA. | 
 | 79 |  */ | 
| Al Viro | a5da7d3 | 2005-10-21 03:21:18 -0400 | [diff] [blame] | 80 | void *consistent_alloc(gfp_t gfp, size_t size, dma_addr_t *dma_handle) | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 81 | { | 
 | 82 | 	struct vm_struct *area; | 
 | 83 | 	unsigned long page, va, pa; | 
 | 84 | 	void *ret; | 
 | 85 | 	int order, err, i; | 
 | 86 |  | 
 | 87 | 	if (in_interrupt()) | 
 | 88 | 		BUG(); | 
 | 89 |  | 
 | 90 | 	/* only allocate page size areas */ | 
 | 91 | 	size = PAGE_ALIGN(size); | 
 | 92 | 	order = get_order(size); | 
 | 93 |  | 
 | 94 | 	page = __get_free_pages(gfp, order); | 
 | 95 | 	if (!page) { | 
 | 96 | 		BUG(); | 
 | 97 | 		return NULL; | 
 | 98 | 	} | 
 | 99 |  | 
 | 100 | 	/* allocate some common virtual space to map the new pages */ | 
 | 101 | 	area = get_vm_area(size, VM_ALLOC); | 
 | 102 | 	if (area == 0) { | 
 | 103 | 		free_pages(page, order); | 
 | 104 | 		return NULL; | 
 | 105 | 	} | 
 | 106 | 	va = VMALLOC_VMADDR(area->addr); | 
 | 107 | 	ret = (void *) va; | 
 | 108 |  | 
 | 109 | 	/* this gives us the real physical address of the first page */ | 
 | 110 | 	*dma_handle = pa = virt_to_bus((void *) page); | 
 | 111 |  | 
 | 112 | 	/* set refcount=1 on all pages in an order>0 allocation so that vfree() will actually free | 
 | 113 | 	 * all pages that were allocated. | 
 | 114 | 	 */ | 
 | 115 | 	if (order > 0) { | 
 | 116 | 		struct page *rpage = virt_to_page(page); | 
| Nick Piggin | 8dfcc9b | 2006-03-22 00:08:05 -0800 | [diff] [blame] | 117 | 		split_page(rpage, order); | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 118 | 	} | 
 | 119 |  | 
 | 120 | 	err = 0; | 
 | 121 | 	for (i = 0; i < size && err == 0; i += PAGE_SIZE) | 
 | 122 | 		err = map_page(va + i, pa + i, PAGE_KERNEL_NOCACHE); | 
 | 123 |  | 
 | 124 | 	if (err) { | 
 | 125 | 		vfree((void *) va); | 
 | 126 | 		return NULL; | 
 | 127 | 	} | 
 | 128 |  | 
 | 129 | 	/* we need to ensure that there are no cachelines in use, or worse dirty in this area | 
 | 130 | 	 * - can't do until after virtual address mappings are created | 
 | 131 | 	 */ | 
 | 132 | 	frv_cache_invalidate(va, va + size); | 
 | 133 |  | 
 | 134 | 	return ret; | 
 | 135 | } | 
 | 136 |  | 
 | 137 | /* | 
 | 138 |  * free page(s) as defined by the above mapping. | 
 | 139 |  */ | 
 | 140 | void consistent_free(void *vaddr) | 
 | 141 | { | 
 | 142 | 	if (in_interrupt()) | 
 | 143 | 		BUG(); | 
 | 144 | 	vfree(vaddr); | 
 | 145 | } | 
 | 146 |  | 
 | 147 | /* | 
 | 148 |  * make an area consistent. | 
 | 149 |  */ | 
 | 150 | void consistent_sync(void *vaddr, size_t size, int direction) | 
 | 151 | { | 
 | 152 | 	unsigned long start = (unsigned long) vaddr; | 
 | 153 | 	unsigned long end   = start + size; | 
 | 154 |  | 
 | 155 | 	switch (direction) { | 
 | 156 | 	case PCI_DMA_NONE: | 
 | 157 | 		BUG(); | 
 | 158 | 	case PCI_DMA_FROMDEVICE:	/* invalidate only */ | 
 | 159 | 		frv_cache_invalidate(start, end); | 
 | 160 | 		break; | 
 | 161 | 	case PCI_DMA_TODEVICE:		/* writeback only */ | 
 | 162 | 		frv_dcache_writeback(start, end); | 
 | 163 | 		break; | 
 | 164 | 	case PCI_DMA_BIDIRECTIONAL:	/* writeback and invalidate */ | 
 | 165 | 		frv_dcache_writeback(start, end); | 
 | 166 | 		break; | 
 | 167 | 	} | 
 | 168 | } | 
 | 169 |  | 
 | 170 | /* | 
 | 171 |  * consistent_sync_page make a page are consistent. identical | 
 | 172 |  * to consistent_sync, but takes a struct page instead of a virtual address | 
 | 173 |  */ | 
 | 174 |  | 
 | 175 | void consistent_sync_page(struct page *page, unsigned long offset, | 
 | 176 | 			  size_t size, int direction) | 
 | 177 | { | 
 | 178 | 	void *start; | 
 | 179 |  | 
 | 180 | 	start = page_address(page) + offset; | 
 | 181 | 	consistent_sync(start, size, direction); | 
 | 182 | } |