From af3e4aca47d2e05a545a5e10ba5c7193e0b665e0 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 30 Apr 2009 10:59:19 +0000 Subject: powerpc: Do not assert pte_locked for hugepage PTE entries With CONFIG_DEBUG_VM, an assertion is made when changing the protection flags of a PTE that the PTE is locked. Huge pages use a different pagetable format and the assertion is bogus and will always trigger with a bug looking something like Unable to handle kernel paging request for data at address 0xf1a00235800006f8 Faulting instruction address: 0xc000000000034a80 Oops: Kernel access of bad area, sig: 11 [#1] SMP NR_CPUS=32 NUMA Maple Modules linked in: dm_snapshot dm_mirror dm_region_hash dm_log dm_mod loop evdev ext3 jbd mbcache sg sd_mod ide_pci_generic pata_amd ata_generic ipr libata tg3 libphy scsi_mod windfarm_pid windfarm_smu_sat windfarm_max6690_sensor windfarm_lm75_sensor windfarm_cpufreq_clamp windfarm_core i2c_powermac NIP: c000000000034a80 LR: c000000000034b18 CTR: 0000000000000003 REGS: c000000003037600 TRAP: 0300 Not tainted (2.6.30-rc3-autokern1) MSR: 9000000000009032 CR: 28002484 XER: 200fffff DAR: f1a00235800006f8, DSISR: 0000000040010000 TASK = c0000002e54cc740[2960] 'map_high_trunca' THREAD: c000000003034000 CPU: 2 GPR00: 4000000000000000 c000000003037880 c000000000895d30 c0000002e5a2e500 GPR04: 00000000a0000000 c0000002edc40880 0000005700000393 0000000000000001 GPR08: f000000011ac0000 01a00235800006e8 00000000000000f5 f1a00235800006e8 GPR12: 0000000028000484 c0000000008dd780 0000000000001000 0000000000000000 GPR16: fffffffffffff000 0000000000000000 00000000a0000000 c000000003037a20 GPR20: c0000002e5f4ece8 0000000000001000 c0000002edc40880 0000000000000000 GPR24: c0000002e5f4ece8 0000000000000000 00000000a0000000 c0000002e5f4ece8 GPR28: 0000005700000393 c0000002e5a2e500 00000000a0000000 c000000003037880 NIP [c000000000034a80] .assert_pte_locked+0xa4/0xd0 LR [c000000000034b18] .ptep_set_access_flags+0x6c/0xb4 Call Trace: [c000000003037880] [c000000003037990] 0xc000000003037990 (unreliable) [c000000003037910] [c000000000034b18] .ptep_set_access_flags+0x6c/0xb4 [c0000000030379b0] [c00000000014bef8] .hugetlb_cow+0x124/0x674 [c000000003037b00] [c00000000014c930] .hugetlb_fault+0x4e8/0x6f8 [c000000003037c00] [c00000000013443c] .handle_mm_fault+0xac/0x828 [c000000003037cf0] [c0000000000340a8] .do_page_fault+0x39c/0x584 [c000000003037e30] [c0000000000057b0] handle_page_fault+0x20/0x5c Instruction dump: 7d29582a 7d200074 7800d182 0b000000 3c004000 3960ffff 780007c6 796b00c4 7d290214 7929a302 1d290068 7d6b4a14 <800b0010> 7c000074 7800d182 0b000000 This patch fixes the problem by not asseting the PTE is locked for VMAs backed by huge pages. Signed-off-by: Mel Gorman Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/mm/pgtable.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/mm') diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c index f5c6fd42265..ae1d67cc090 100644 --- a/arch/powerpc/mm/pgtable.c +++ b/arch/powerpc/mm/pgtable.c @@ -219,7 +219,8 @@ int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, entry = do_dcache_icache_coherency(entry); changed = !pte_same(*(ptep), entry); if (changed) { - assert_pte_locked(vma->vm_mm, address); + if (!(vma->vm_flags & VM_HUGETLB)) + assert_pte_locked(vma->vm_mm, address); __ptep_set_access_flags(ptep, entry); flush_tlb_page_nohash(vma, address); } -- cgit v1.2.3 From 8e35961b57da14cb64cb0e4e1b7e3aabda6396fe Mon Sep 17 00:00:00 2001 From: Hideo Saito Date: Sun, 24 May 2009 15:33:34 +0000 Subject: powerpc/mm: Fix broken MMU PID stealing on !SMP The recent rework of the MMU PID handling for non-hash CPUs has a subtle bug in the !SMP "optimized" variant of the PID stealing function. It clears the PID in the mm context before it calls local_flush_tlb_mm(). However, the later will not flush anything if the PID in the context is clear... Signed-off-by: Hideo Saito Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/mm/mmu_context_nohash.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'arch/powerpc/mm') diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c index a70e311bd45..030d0005b4d 100644 --- a/arch/powerpc/mm/mmu_context_nohash.c +++ b/arch/powerpc/mm/mmu_context_nohash.c @@ -127,12 +127,12 @@ static unsigned int steal_context_up(unsigned int id) pr_debug("[%d] steal context %d from mm @%p\n", cpu, id, mm); - /* Mark this mm has having no context anymore */ - mm->context.id = MMU_NO_CONTEXT; - /* Flush the TLB for that context */ local_flush_tlb_mm(mm); + /* Mark this mm has having no context anymore */ + mm->context.id = MMU_NO_CONTEXT; + /* XXX This clear should ultimately be part of local_flush_tlb_mm */ __clear_bit(id, stale_map[cpu]); -- cgit v1.2.3 From b16e7766d6436835f473ba823ad04fbdfe5e9cbd Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Wed, 27 May 2009 13:36:10 +1000 Subject: powerpc: Move dma-noncoherent.c from arch/powerpc/lib to arch/powerpc/mm (pre-requisite to make the next patches more palatable) Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/mm/Makefile | 1 + arch/powerpc/mm/dma-noncoherent.c | 426 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 427 insertions(+) create mode 100644 arch/powerpc/mm/dma-noncoherent.c (limited to 'arch/powerpc/mm') diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile index 17290bcedc5..b746f4ca420 100644 --- a/arch/powerpc/mm/Makefile +++ b/arch/powerpc/mm/Makefile @@ -26,3 +26,4 @@ obj-$(CONFIG_NEED_MULTIPLE_NODES) += numa.o obj-$(CONFIG_PPC_MM_SLICES) += slice.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o obj-$(CONFIG_PPC_SUBPAGE_PROT) += subpage-prot.o +obj-$(CONFIG_NOT_COHERENT_CACHE) += dma-noncoherent.o diff --git a/arch/powerpc/mm/dma-noncoherent.c b/arch/powerpc/mm/dma-noncoherent.c new file mode 100644 index 00000000000..b7dc4c19f58 --- /dev/null +++ b/arch/powerpc/mm/dma-noncoherent.c @@ -0,0 +1,426 @@ +/* + * PowerPC version derived from arch/arm/mm/consistent.c + * Copyright (C) 2001 Dan Malek (dmalek@jlc.net) + * + * Copyright (C) 2000 Russell King + * + * Consistent memory allocators. Used for DMA devices that want to + * share uncached memory with the processor core. The function return + * is the virtual address and 'dma_handle' is the physical address. + * Mostly stolen from the ARM port, with some changes for PowerPC. + * -- Dan + * + * Reorganized to get rid of the arch-specific consistent_* functions + * and provide non-coherent implementations for the DMA API. -Matt + * + * Added in_interrupt() safe dma_alloc_coherent()/dma_free_coherent() + * implementation. This is pulled straight from ARM and barely + * modified. -Matt + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include +#include +#include + +#include + +/* + * This address range defaults to a value that is safe for all + * platforms which currently set CONFIG_NOT_COHERENT_CACHE. It + * can be further configured for specific applications under + * the "Advanced Setup" menu. -Matt + */ +#define CONSISTENT_BASE (CONFIG_CONSISTENT_START) +#define CONSISTENT_END (CONFIG_CONSISTENT_START + CONFIG_CONSISTENT_SIZE) +#define CONSISTENT_OFFSET(x) (((unsigned long)(x) - CONSISTENT_BASE) >> PAGE_SHIFT) + +/* + * This is the page table (2MB) covering uncached, DMA consistent allocations + */ +static pte_t *consistent_pte; +static DEFINE_SPINLOCK(consistent_lock); + +/* + * VM region handling support. + * + * This should become something generic, handling VM region allocations for + * vmalloc and similar (ioremap, module space, etc). + * + * I envisage vmalloc()'s supporting vm_struct becoming: + * + * struct vm_struct { + * struct vm_region region; + * unsigned long flags; + * struct page **pages; + * unsigned int nr_pages; + * unsigned long phys_addr; + * }; + * + * get_vm_area() would then call vm_region_alloc with an appropriate + * struct vm_region head (eg): + * + * struct vm_region vmalloc_head = { + * .vm_list = LIST_HEAD_INIT(vmalloc_head.vm_list), + * .vm_start = VMALLOC_START, + * .vm_end = VMALLOC_END, + * }; + * + * However, vmalloc_head.vm_start is variable (typically, it is dependent on + * the amount of RAM found at boot time.) I would imagine that get_vm_area() + * would have to initialise this each time prior to calling vm_region_alloc(). + */ +struct ppc_vm_region { + struct list_head vm_list; + unsigned long vm_start; + unsigned long vm_end; +}; + +static struct ppc_vm_region consistent_head = { + .vm_list = LIST_HEAD_INIT(consistent_head.vm_list), + .vm_start = CONSISTENT_BASE, + .vm_end = CONSISTENT_END, +}; + +static struct ppc_vm_region * +ppc_vm_region_alloc(struct ppc_vm_region *head, size_t size, gfp_t gfp) +{ + unsigned long addr = head->vm_start, end = head->vm_end - size; + unsigned long flags; + struct ppc_vm_region *c, *new; + + new = kmalloc(sizeof(struct ppc_vm_region), gfp); + if (!new) + goto out; + + spin_lock_irqsave(&consistent_lock, flags); + + list_for_each_entry(c, &head->vm_list, vm_list) { + if ((addr + size) < addr) + goto nospc; + if ((addr + size) <= c->vm_start) + goto found; + addr = c->vm_end; + if (addr > end) + goto nospc; + } + + found: + /* + * Insert this entry _before_ the one we found. + */ + list_add_tail(&new->vm_list, &c->vm_list); + new->vm_start = addr; + new->vm_end = addr + size; + + spin_unlock_irqrestore(&consistent_lock, flags); + return new; + + nospc: + spin_unlock_irqrestore(&consistent_lock, flags); + kfree(new); + out: + return NULL; +} + +static struct ppc_vm_region *ppc_vm_region_find(struct ppc_vm_region *head, unsigned long addr) +{ + struct ppc_vm_region *c; + + list_for_each_entry(c, &head->vm_list, vm_list) { + if (c->vm_start == addr) + goto out; + } + c = NULL; + out: + return c; +} + +/* + * Allocate DMA-coherent memory space and return both the kernel remapped + * virtual and bus address for that space. + */ +void * +__dma_alloc_coherent(size_t size, dma_addr_t *handle, gfp_t gfp) +{ + struct page *page; + struct ppc_vm_region *c; + unsigned long order; + u64 mask = 0x00ffffff, limit; /* ISA default */ + + if (!consistent_pte) { + printk(KERN_ERR "%s: not initialised\n", __func__); + dump_stack(); + return NULL; + } + + size = PAGE_ALIGN(size); + limit = (mask + 1) & ~mask; + if ((limit && size >= limit) || size >= (CONSISTENT_END - CONSISTENT_BASE)) { + printk(KERN_WARNING "coherent allocation too big (requested %#x mask %#Lx)\n", + size, mask); + return NULL; + } + + order = get_order(size); + + if (mask != 0xffffffff) + gfp |= GFP_DMA; + + page = alloc_pages(gfp, order); + if (!page) + goto no_page; + + /* + * Invalidate any data that might be lurking in the + * kernel direct-mapped region for device DMA. + */ + { + unsigned long kaddr = (unsigned long)page_address(page); + memset(page_address(page), 0, size); + flush_dcache_range(kaddr, kaddr + size); + } + + /* + * Allocate a virtual address in the consistent mapping region. + */ + c = ppc_vm_region_alloc(&consistent_head, size, + gfp & ~(__GFP_DMA | __GFP_HIGHMEM)); + if (c) { + unsigned long vaddr = c->vm_start; + pte_t *pte = consistent_pte + CONSISTENT_OFFSET(vaddr); + struct page *end = page + (1 << order); + + split_page(page, order); + + /* + * Set the "dma handle" + */ + *handle = page_to_phys(page); + + do { + BUG_ON(!pte_none(*pte)); + + SetPageReserved(page); + set_pte_at(&init_mm, vaddr, + pte, mk_pte(page, pgprot_noncached(PAGE_KERNEL))); + page++; + pte++; + vaddr += PAGE_SIZE; + } while (size -= PAGE_SIZE); + + /* + * Free the otherwise unused pages. + */ + while (page < end) { + __free_page(page); + page++; + } + + return (void *)c->vm_start; + } + + if (page) + __free_pages(page, order); + no_page: + return NULL; +} +EXPORT_SYMBOL(__dma_alloc_coherent); + +/* + * free a page as defined by the above mapping. + */ +void __dma_free_coherent(size_t size, void *vaddr) +{ + struct ppc_vm_region *c; + unsigned long flags, addr; + pte_t *ptep; + + size = PAGE_ALIGN(size); + + spin_lock_irqsave(&consistent_lock, flags); + + c = ppc_vm_region_find(&consistent_head, (unsigned long)vaddr); + if (!c) + goto no_area; + + if ((c->vm_end - c->vm_start) != size) { + printk(KERN_ERR "%s: freeing wrong coherent size (%ld != %d)\n", + __func__, c->vm_end - c->vm_start, size); + dump_stack(); + size = c->vm_end - c->vm_start; + } + + ptep = consistent_pte + CONSISTENT_OFFSET(c->vm_start); + addr = c->vm_start; + do { + pte_t pte = ptep_get_and_clear(&init_mm, addr, ptep); + unsigned long pfn; + + ptep++; + addr += PAGE_SIZE; + + if (!pte_none(pte) && pte_present(pte)) { + pfn = pte_pfn(pte); + + if (pfn_valid(pfn)) { + struct page *page = pfn_to_page(pfn); + ClearPageReserved(page); + + __free_page(page); + continue; + } + } + + printk(KERN_CRIT "%s: bad page in kernel page table\n", + __func__); + } while (size -= PAGE_SIZE); + + flush_tlb_kernel_range(c->vm_start, c->vm_end); + + list_del(&c->vm_list); + + spin_unlock_irqrestore(&consistent_lock, flags); + + kfree(c); + return; + + no_area: + spin_unlock_irqrestore(&consistent_lock, flags); + printk(KERN_ERR "%s: trying to free invalid coherent area: %p\n", + __func__, vaddr); + dump_stack(); +} +EXPORT_SYMBOL(__dma_free_coherent); + +/* + * Initialise the consistent memory allocation. + */ +static int __init dma_alloc_init(void) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + int ret = 0; + + do { + pgd = pgd_offset(&init_mm, CONSISTENT_BASE); + pud = pud_alloc(&init_mm, pgd, CONSISTENT_BASE); + pmd = pmd_alloc(&init_mm, pud, CONSISTENT_BASE); + if (!pmd) { + printk(KERN_ERR "%s: no pmd tables\n", __func__); + ret = -ENOMEM; + break; + } + + pte = pte_alloc_kernel(pmd, CONSISTENT_BASE); + if (!pte) { + printk(KERN_ERR "%s: no pte tables\n", __func__); + ret = -ENOMEM; + break; + } + + consistent_pte = pte; + } while (0); + + return ret; +} + +core_initcall(dma_alloc_init); + +/* + * make an area consistent. + */ +void __dma_sync(void *vaddr, size_t size, int direction) +{ + unsigned long start = (unsigned long)vaddr; + unsigned long end = start + size; + + switch (direction) { + case DMA_NONE: + BUG(); + case DMA_FROM_DEVICE: + /* + * invalidate only when cache-line aligned otherwise there is + * the potential for discarding uncommitted data from the cache + */ + if ((start & (L1_CACHE_BYTES - 1)) || (size & (L1_CACHE_BYTES - 1))) + flush_dcache_range(start, end); + else + invalidate_dcache_range(start, end); + break; + case DMA_TO_DEVICE: /* writeback only */ + clean_dcache_range(start, end); + break; + case DMA_BIDIRECTIONAL: /* writeback and invalidate */ + flush_dcache_range(start, end); + break; + } +} +EXPORT_SYMBOL(__dma_sync); + +#ifdef CONFIG_HIGHMEM +/* + * __dma_sync_page() implementation for systems using highmem. + * In this case, each page of a buffer must be kmapped/kunmapped + * in order to have a virtual address for __dma_sync(). This must + * not sleep so kmap_atomic()/kunmap_atomic() are used. + * + * Note: yes, it is possible and correct to have a buffer extend + * beyond the first page. + */ +static inline void __dma_sync_page_highmem(struct page *page, + unsigned long offset, size_t size, int direction) +{ + size_t seg_size = min((size_t)(PAGE_SIZE - offset), size); + size_t cur_size = seg_size; + unsigned long flags, start, seg_offset = offset; + int nr_segs = 1 + ((size - seg_size) + PAGE_SIZE - 1)/PAGE_SIZE; + int seg_nr = 0; + + local_irq_save(flags); + + do { + start = (unsigned long)kmap_atomic(page + seg_nr, + KM_PPC_SYNC_PAGE) + seg_offset; + + /* Sync this buffer segment */ + __dma_sync((void *)start, seg_size, direction); + kunmap_atomic((void *)start, KM_PPC_SYNC_PAGE); + seg_nr++; + + /* Calculate next buffer segment size */ + seg_size = min((size_t)PAGE_SIZE, size - cur_size); + + /* Add the segment size to our running total */ + cur_size += seg_size; + seg_offset = 0; + } while (seg_nr < nr_segs); + + local_irq_restore(flags); +} +#endif /* CONFIG_HIGHMEM */ + +/* + * __dma_sync_page makes memory consistent. identical to __dma_sync, but + * takes a struct page instead of a virtual address + */ +void __dma_sync_page(struct page *page, unsigned long offset, + size_t size, int direction) +{ +#ifdef CONFIG_HIGHMEM + __dma_sync_page_highmem(page, offset, size, direction); +#else + unsigned long start = (unsigned long)page_address(page) + offset; + __dma_sync((void *)start, size, direction); +#endif +} +EXPORT_SYMBOL(__dma_sync_page); -- cgit v1.2.3 From f637a49e507c88354ab32b5d914e06acfb7ee00d Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Wed, 27 May 2009 13:44:50 +1000 Subject: powerpc: Minor cleanups of kernel virt address space definitions Make FIXADDR_TOP a compile time constant and cleanup a couple of definitions relative to the layout of the kernel address space on ppc32. We also print out that layout at boot time for debugging purposes. This is a pre-requisite for properly fixing non-coherent DMA allocactions. Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/mm/init_32.c | 8 ++------ arch/powerpc/mm/mem.c | 13 +++++++++++++ arch/powerpc/mm/pgtable_32.c | 2 -- 3 files changed, 15 insertions(+), 8 deletions(-) (limited to 'arch/powerpc/mm') diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c index 666a5e8a5be..3de6a0d9382 100644 --- a/arch/powerpc/mm/init_32.c +++ b/arch/powerpc/mm/init_32.c @@ -168,12 +168,8 @@ void __init MMU_init(void) ppc_md.progress("MMU:mapin", 0x301); mapin_ram(); -#ifdef CONFIG_HIGHMEM - ioremap_base = PKMAP_BASE; -#else - ioremap_base = 0xfe000000UL; /* for now, could be 0xfffff000 */ -#endif /* CONFIG_HIGHMEM */ - ioremap_bot = ioremap_base; + /* Initialize early top-down ioremap allocator */ + ioremap_bot = IOREMAP_TOP; /* Map in I/O resources */ if (ppc_md.progress) diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index d0602a76bf7..d3a4e67561f 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -380,6 +380,19 @@ void __init mem_init(void) bsssize >> 10, initsize >> 10); +#ifdef CONFIG_PPC32 + pr_info("Kernel virtual memory layout:\n"); + pr_info(" * 0x%08lx..0x%08lx : fixmap\n", FIXADDR_START, FIXADDR_TOP); +#ifdef CONFIG_HIGHMEM + pr_info(" * 0x%08lx..0x%08lx : highmem PTEs\n", + PKMAP_BASE, PKMAP_ADDR(LAST_PKMAP)); +#endif /* CONFIG_HIGHMEM */ + pr_info(" * 0x%08lx..0x%08lx : early ioremap\n", + ioremap_bot, IOREMAP_TOP); + pr_info(" * 0x%08lx..0x%08lx : vmalloc & ioremap\n", + VMALLOC_START, VMALLOC_END); +#endif /* CONFIG_PPC32 */ + mem_init_done = 1; } diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index 430d0908fa5..5422169626b 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -399,8 +399,6 @@ void kernel_map_pages(struct page *page, int numpages, int enable) #endif /* CONFIG_DEBUG_PAGEALLOC */ static int fixmaps; -unsigned long FIXADDR_TOP = (-PAGE_SIZE); -EXPORT_SYMBOL(FIXADDR_TOP); void __set_fixmap (enum fixed_addresses idx, phys_addr_t phys, pgprot_t flags) { -- cgit v1.2.3 From 8b31e49d1d75729c1da9009664ba52abd1adc628 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Wed, 27 May 2009 13:50:33 +1000 Subject: powerpc: Fix up dma_alloc_coherent() on platforms without cache coherency. The implementation we just revived has issues, such as using a Kconfig-defined virtual address area in kernel space that nothing actually carves out (and thus will overlap whatever is there), or having some dependencies on being self contained in a single PTE page which adds unnecessary constraints on the kernel virtual address space. This fixes it by using more classic PTE accessors and automatically locating the area for consistent memory, carving an appropriate hole in the kernel virtual address space, leaving only the size of that area as a Kconfig option. It also brings some dma-mask related fixes from the ARM implementation which was almost identical initially but grew its own fixes. Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/mm/dma-noncoherent.c | 108 +++++++++++++++----------------------- arch/powerpc/mm/mem.c | 4 ++ 2 files changed, 45 insertions(+), 67 deletions(-) (limited to 'arch/powerpc/mm') diff --git a/arch/powerpc/mm/dma-noncoherent.c b/arch/powerpc/mm/dma-noncoherent.c index b7dc4c19f58..36692f5c9a7 100644 --- a/arch/powerpc/mm/dma-noncoherent.c +++ b/arch/powerpc/mm/dma-noncoherent.c @@ -32,20 +32,21 @@ #include +#include "mmu_decl.h" + /* * This address range defaults to a value that is safe for all * platforms which currently set CONFIG_NOT_COHERENT_CACHE. It * can be further configured for specific applications under * the "Advanced Setup" menu. -Matt */ -#define CONSISTENT_BASE (CONFIG_CONSISTENT_START) -#define CONSISTENT_END (CONFIG_CONSISTENT_START + CONFIG_CONSISTENT_SIZE) +#define CONSISTENT_BASE (IOREMAP_TOP) +#define CONSISTENT_END (CONSISTENT_BASE + CONFIG_CONSISTENT_SIZE) #define CONSISTENT_OFFSET(x) (((unsigned long)(x) - CONSISTENT_BASE) >> PAGE_SHIFT) /* * This is the page table (2MB) covering uncached, DMA consistent allocations */ -static pte_t *consistent_pte; static DEFINE_SPINLOCK(consistent_lock); /* @@ -148,22 +149,38 @@ static struct ppc_vm_region *ppc_vm_region_find(struct ppc_vm_region *head, unsi * virtual and bus address for that space. */ void * -__dma_alloc_coherent(size_t size, dma_addr_t *handle, gfp_t gfp) +__dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp) { struct page *page; struct ppc_vm_region *c; unsigned long order; - u64 mask = 0x00ffffff, limit; /* ISA default */ + u64 mask = ISA_DMA_THRESHOLD, limit; - if (!consistent_pte) { - printk(KERN_ERR "%s: not initialised\n", __func__); - dump_stack(); - return NULL; + if (dev) { + mask = dev->coherent_dma_mask; + + /* + * Sanity check the DMA mask - it must be non-zero, and + * must be able to be satisfied by a DMA allocation. + */ + if (mask == 0) { + dev_warn(dev, "coherent DMA mask is unset\n"); + goto no_page; + } + + if ((~mask) & ISA_DMA_THRESHOLD) { + dev_warn(dev, "coherent DMA mask %#llx is smaller " + "than system GFP_DMA mask %#llx\n", + mask, (unsigned long long)ISA_DMA_THRESHOLD); + goto no_page; + } } + size = PAGE_ALIGN(size); limit = (mask + 1) & ~mask; - if ((limit && size >= limit) || size >= (CONSISTENT_END - CONSISTENT_BASE)) { + if ((limit && size >= limit) || + size >= (CONSISTENT_END - CONSISTENT_BASE)) { printk(KERN_WARNING "coherent allocation too big (requested %#x mask %#Lx)\n", size, mask); return NULL; @@ -171,6 +188,7 @@ __dma_alloc_coherent(size_t size, dma_addr_t *handle, gfp_t gfp) order = get_order(size); + /* Might be useful if we ever have a real legacy DMA zone... */ if (mask != 0xffffffff) gfp |= GFP_DMA; @@ -195,7 +213,6 @@ __dma_alloc_coherent(size_t size, dma_addr_t *handle, gfp_t gfp) gfp & ~(__GFP_DMA | __GFP_HIGHMEM)); if (c) { unsigned long vaddr = c->vm_start; - pte_t *pte = consistent_pte + CONSISTENT_OFFSET(vaddr); struct page *end = page + (1 << order); split_page(page, order); @@ -206,13 +223,10 @@ __dma_alloc_coherent(size_t size, dma_addr_t *handle, gfp_t gfp) *handle = page_to_phys(page); do { - BUG_ON(!pte_none(*pte)); - SetPageReserved(page); - set_pte_at(&init_mm, vaddr, - pte, mk_pte(page, pgprot_noncached(PAGE_KERNEL))); + map_page(vaddr, page_to_phys(page), + pgprot_noncached(PAGE_KERNEL)); page++; - pte++; vaddr += PAGE_SIZE; } while (size -= PAGE_SIZE); @@ -241,8 +255,7 @@ void __dma_free_coherent(size_t size, void *vaddr) { struct ppc_vm_region *c; unsigned long flags, addr; - pte_t *ptep; - + size = PAGE_ALIGN(size); spin_lock_irqsave(&consistent_lock, flags); @@ -258,29 +271,26 @@ void __dma_free_coherent(size_t size, void *vaddr) size = c->vm_end - c->vm_start; } - ptep = consistent_pte + CONSISTENT_OFFSET(c->vm_start); addr = c->vm_start; do { - pte_t pte = ptep_get_and_clear(&init_mm, addr, ptep); + pte_t *ptep; unsigned long pfn; - ptep++; - addr += PAGE_SIZE; - - if (!pte_none(pte) && pte_present(pte)) { - pfn = pte_pfn(pte); - + ptep = pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k(addr), + addr), + addr), + addr); + if (!pte_none(*ptep) && pte_present(*ptep)) { + pfn = pte_pfn(*ptep); + pte_clear(&init_mm, addr, ptep); if (pfn_valid(pfn)) { struct page *page = pfn_to_page(pfn); - ClearPageReserved(page); + ClearPageReserved(page); __free_page(page); - continue; } } - - printk(KERN_CRIT "%s: bad page in kernel page table\n", - __func__); + addr += PAGE_SIZE; } while (size -= PAGE_SIZE); flush_tlb_kernel_range(c->vm_start, c->vm_end); @@ -300,42 +310,6 @@ void __dma_free_coherent(size_t size, void *vaddr) } EXPORT_SYMBOL(__dma_free_coherent); -/* - * Initialise the consistent memory allocation. - */ -static int __init dma_alloc_init(void) -{ - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - int ret = 0; - - do { - pgd = pgd_offset(&init_mm, CONSISTENT_BASE); - pud = pud_alloc(&init_mm, pgd, CONSISTENT_BASE); - pmd = pmd_alloc(&init_mm, pud, CONSISTENT_BASE); - if (!pmd) { - printk(KERN_ERR "%s: no pmd tables\n", __func__); - ret = -ENOMEM; - break; - } - - pte = pte_alloc_kernel(pmd, CONSISTENT_BASE); - if (!pte) { - printk(KERN_ERR "%s: no pte tables\n", __func__); - ret = -ENOMEM; - break; - } - - consistent_pte = pte; - } while (0); - - return ret; -} - -core_initcall(dma_alloc_init); - /* * make an area consistent. */ diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index d3a4e67561f..579382c163a 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -387,6 +387,10 @@ void __init mem_init(void) pr_info(" * 0x%08lx..0x%08lx : highmem PTEs\n", PKMAP_BASE, PKMAP_ADDR(LAST_PKMAP)); #endif /* CONFIG_HIGHMEM */ +#ifdef CONFIG_NOT_COHERENT_CACHE + pr_info(" * 0x%08lx..0x%08lx : consistent mem\n", + IOREMAP_TOP, IOREMAP_TOP + CONFIG_CONSISTENT_SIZE); +#endif /* CONFIG_NOT_COHERENT_CACHE */ pr_info(" * 0x%08lx..0x%08lx : early ioremap\n", ioremap_bot, IOREMAP_TOP); pr_info(" * 0x%08lx..0x%08lx : vmalloc & ioremap\n", -- cgit v1.2.3