Also note the kernel might malfunction if you disable
some critical bits.
+ cma=nn[MG] [ARM,KNL]
+ Sets the size of kernel global memory area for contiguous
+ memory allocations. For more information, see
+ include/linux/dma-contiguous.h
+
cmo_free_hint= [PPC] Format: { yes | no }
Specify whether pages are marked as being inactive
when they are freed. This is used in CMO environments
a hypervisor.
Default: yes
+ coherent_pool=nn[KMG] [ARM,KNL]
+ Sets the size of memory pool for coherent, atomic dma
+ allocations, by default set to 256K.
+
code_bytes [X86] How many bytes of object code to print
in an oops report.
Range: 0 - 8192
no_debug_objects
[KNL] Disable object debugging
+ debug_guardpage_minorder=
+ [KNL] When CONFIG_DEBUG_PAGEALLOC is set, this
+ parameter allows control of the order of pages that will
+ be intentionally kept free (and hence protected) by the
+ buddy allocator. Bigger value increase the probability
+ of catching random memory corruption, but reduce the
+ amount of memory for normal system use. The maximum
+ possible value is MAX_ORDER/2. Setting this parameter
+ to 1 or 2 should be enough to identify most random
+ memory corruption problems caused by bugs in kernel or
+ driver code when a CPU writes to (or reads from) a
+ random memory location. Note that there exists a class
+ of memory corruptions problems caused by buggy H/W or
+ F/W or by drivers badly programing DMA (basically when
+ memory is written at bus level and the CPU MMU is
+ bypassed) which are not detectable by
+ CONFIG_DEBUG_PAGEALLOC, hence this option will not help
+ tracking down these problems.
+
debugpat [X86] Enable PAT debugging
decnet.addr= [HW,NET]
spia_pedr=
spia_peddr=
+ stack_guard_gap= [MM]
+ override the default stack gap protection. The value
+ is in page units and it defines how many pages prior
+ to (for stacks growing down) resp. after (for stacks
+ growing up) the main stack are reserved for no other
+ mapping. Default value is 256 pages.
+
stacktrace [FTRACE]
Enabled the stack tracer on boot up.
return 0;
}
+ /*
+ * Scorpion CPUs (at least those in APQ8060) seem to set DBGPRSR.SPD
+ * whenever a WFI is issued, even if the core is not powered down, in
+ * violation of the architecture. When DBGPRSR.SPD is set, accesses to
+ * breakpoint and watchpoint registers are treated as undefined, so
+ * this results in boot time and runtime failures when these are
+ * accessed and we unexpectedly take a trap.
+ *
+ * It's not clear if/how this can be worked around, so we blacklist
+ * Scorpion CPUs to avoid these issues.
+ */
+ if ((read_cpuid_id() & 0xff00fff0) == ARM_CPU_PART_SCORPION) {
+ pr_info("Scorpion CPU detected. Hardware breakpoints and watchpoints disabled\n");
+ return 0;
+ }
+
/* Determine how many BRPs/WRPs are available. */
core_num_brps = get_num_brps();
core_num_wrps = get_num_wrps();
}
/* Register debug fault handler. */
- hook_fault_code(2, hw_breakpoint_pending, SIGTRAP, TRAP_HWBKPT,
- "watchpoint debug exception");
- hook_ifault_code(2, hw_breakpoint_pending, SIGTRAP, TRAP_HWBKPT,
- "breakpoint debug exception");
+ hook_fault_code(FAULT_CODE_DEBUG, hw_breakpoint_pending, SIGTRAP,
+ TRAP_HWBKPT, "watchpoint debug exception");
+ hook_ifault_code(FAULT_CODE_DEBUG, hw_breakpoint_pending, SIGTRAP,
+ TRAP_HWBKPT, "breakpoint debug exception");
/* Register hotplug notifier. */
register_cpu_notifier(&dbg_reset_nb);
const void *kbuf, const void __user *ubuf)
{
int ret;
- struct pt_regs newregs;
+ struct pt_regs newregs = *task_pt_regs(target);
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
&newregs,
#endif
case PTRACE_GET_THREAD_AREA:
- ret = put_user(task_thread_info(child)->tp_value,
+ ret = put_user(task_thread_info(child)->tp_value[0],
datap);
break;
#include <linux/init.h>
#include <linux/device.h>
#include <linux/dma-mapping.h>
+#include <linux/dma-contiguous.h>
#include <linux/highmem.h>
+#include <linux/memblock.h>
#include <linux/slab.h>
+#include <linux/iommu.h>
+#include <linux/io.h>
+#include <linux/vmalloc.h>
#include <asm/memory.h>
#include <asm/highmem.h>
#include <asm/tlbflush.h>
#include <asm/sizes.h>
#include <asm/mach/arch.h>
+#include <asm/dma-iommu.h>
+#include <asm/mach/map.h>
+#include <asm/system.h>
+#include <asm/dma-contiguous.h>
#include "mm.h"
+/*
+ * The DMA API is built upon the notion of "buffer ownership". A buffer
+ * is either exclusively owned by the CPU (and therefore may be accessed
+ * by it) or exclusively owned by the DMA device. These helper functions
+ * represent the transitions between these two ownership states.
+ *
+ * Note, however, that on later ARMs, this notion does not work due to
+ * speculative prefetches. We model our approach on the assumption that
+ * the CPU does do speculative prefetches, which means we clean caches
+ * before transfers and delay cache invalidation until transfer completion.
+ *
+ */
+static void __dma_page_cpu_to_dev(struct page *, unsigned long,
+ size_t, enum dma_data_direction);
+static void __dma_page_dev_to_cpu(struct page *, unsigned long,
+ size_t, enum dma_data_direction);
+
+/**
+ * arm_dma_map_page - map a portion of a page for streaming DMA
+ * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
+ * @page: page that buffer resides in
+ * @offset: offset into page for start of buffer
+ * @size: size of buffer to map
+ * @dir: DMA transfer direction
+ *
+ * Ensure that any data held in the cache is appropriately discarded
+ * or written back.
+ *
+ * The device owns this memory once this call has completed. The CPU
+ * can regain ownership by calling dma_unmap_page().
+ */
+static dma_addr_t arm_dma_map_page(struct device *dev, struct page *page,
+ unsigned long offset, size_t size, enum dma_data_direction dir,
+ struct dma_attrs *attrs)
+{
+ if (!arch_is_coherent())
+ __dma_page_cpu_to_dev(page, offset, size, dir);
+ return pfn_to_dma(dev, page_to_pfn(page)) + offset;
+}
+
+/**
+ * arm_dma_unmap_page - unmap a buffer previously mapped through dma_map_page()
+ * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
+ * @handle: DMA address of buffer
+ * @size: size of buffer (same as passed to dma_map_page)
+ * @dir: DMA transfer direction (same as passed to dma_map_page)
+ *
+ * Unmap a page streaming mode DMA translation. The handle and size
+ * must match what was provided in the previous dma_map_page() call.
+ * All other usages are undefined.
+ *
+ * After this call, reads by the CPU to the buffer are guaranteed to see
+ * whatever the device wrote there.
+ */
+static void arm_dma_unmap_page(struct device *dev, dma_addr_t handle,
+ size_t size, enum dma_data_direction dir,
+ struct dma_attrs *attrs)
+{
+ if (!arch_is_coherent())
+ __dma_page_dev_to_cpu(pfn_to_page(dma_to_pfn(dev, handle)),
+ handle & ~PAGE_MASK, size, dir);
+}
+
+static void arm_dma_sync_single_for_cpu(struct device *dev,
+ dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+ unsigned int offset = handle & (PAGE_SIZE - 1);
+ struct page *page = pfn_to_page(dma_to_pfn(dev, handle-offset));
+ if (!arch_is_coherent())
+ __dma_page_dev_to_cpu(page, offset, size, dir);
+}
+
+static void arm_dma_sync_single_for_device(struct device *dev,
+ dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+ unsigned int offset = handle & (PAGE_SIZE - 1);
+ struct page *page = pfn_to_page(dma_to_pfn(dev, handle-offset));
+ if (!arch_is_coherent())
+ __dma_page_cpu_to_dev(page, offset, size, dir);
+}
+
+static int arm_dma_set_mask(struct device *dev, u64 dma_mask);
+
+struct dma_map_ops arm_dma_ops = {
+ .alloc = arm_dma_alloc,
+ .free = arm_dma_free,
+ .mmap = arm_dma_mmap,
+ .map_page = arm_dma_map_page,
+ .unmap_page = arm_dma_unmap_page,
+ .map_sg = arm_dma_map_sg,
+ .unmap_sg = arm_dma_unmap_sg,
+ .sync_single_for_cpu = arm_dma_sync_single_for_cpu,
+ .sync_single_for_device = arm_dma_sync_single_for_device,
+ .sync_sg_for_cpu = arm_dma_sync_sg_for_cpu,
+ .sync_sg_for_device = arm_dma_sync_sg_for_device,
+ .set_dma_mask = arm_dma_set_mask,
+};
+EXPORT_SYMBOL(arm_dma_ops);
+
static u64 get_coherent_dma_mask(struct device *dev)
{
u64 mask = (u64)arm_dma_limit;
return mask;
}
+static void __dma_clear_buffer(struct page *page, size_t size)
+{
+ void *ptr;
+ /*
+ * Ensure that the allocated pages are zeroed, and that any data
+ * lurking in the kernel direct-mapped region is invalidated.
+ */
+ ptr = page_address(page);
+ if (ptr) {
+ memset(ptr, 0, size);
+ dmac_flush_range(ptr, ptr + size);
+ outer_flush_range(__pa(ptr), __pa(ptr) + size);
+ }
+}
+
/*
* Allocate a DMA buffer for 'dev' of size 'size' using the
* specified gfp mask. Note that 'size' must be page aligned.
{
unsigned long order = get_order(size);
struct page *page, *p, *e;
- void *ptr;
- u64 mask = get_coherent_dma_mask(dev);
-
-#ifdef CONFIG_DMA_API_DEBUG
- u64 limit = (mask + 1) & ~mask;
- if (limit && size >= limit) {
- dev_warn(dev, "coherent allocation too big (requested %#x mask %#llx)\n",
- size, mask);
- return NULL;
- }
-#endif
-
- if (!mask)
- return NULL;
-
- if (mask < 0xffffffffULL)
- gfp |= GFP_DMA;
page = alloc_pages(gfp, order);
if (!page)
for (p = page + (size >> PAGE_SHIFT), e = page + (1 << order); p < e; p++)
__free_page(p);
- /*
- * Ensure that the allocated pages are zeroed, and that any data
- * lurking in the kernel direct-mapped region is invalidated.
- */
- ptr = page_address(page);
- memset(ptr, 0, size);
- dmac_flush_range(ptr, ptr + size);
- outer_flush_range(__pa(ptr), __pa(ptr) + size);
+ __dma_clear_buffer(page, size);
return page;
}
#ifdef CONFIG_MMU
-#define CONSISTENT_OFFSET(x) (((unsigned long)(x) - consistent_base) >> PAGE_SHIFT)
-#define CONSISTENT_PTE_INDEX(x) (((unsigned long)(x) - consistent_base) >> PMD_SHIFT)
-
-/*
- * These are the page tables (2MB each) covering uncached, DMA consistent allocations
- */
-static pte_t **consistent_pte;
-
-#define DEFAULT_CONSISTENT_DMA_SIZE SZ_2M
+static void *__alloc_from_contiguous(struct device *dev, size_t size,
+ pgprot_t prot, struct page **ret_page);
-unsigned long consistent_base = CONSISTENT_END - DEFAULT_CONSISTENT_DMA_SIZE;
+static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp,
+ pgprot_t prot, struct page **ret_page,
+ const void *caller);
-void __init init_consistent_dma_size(unsigned long size)
+static void *
+__dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot,
+ const void *caller)
{
- unsigned long base = CONSISTENT_END - ALIGN(size, SZ_2M);
+ struct vm_struct *area;
+ unsigned long addr;
- BUG_ON(consistent_pte); /* Check we're called before DMA region init */
- BUG_ON(base < VMALLOC_END);
+ /*
+ * DMA allocation can be mapped to user space, so lets
+ * set VM_USERMAP flags too.
+ */
+ area = get_vm_area_caller(size, VM_ARM_DMA_CONSISTENT | VM_USERMAP,
+ caller);
+ if (!area)
+ return NULL;
+ addr = (unsigned long)area->addr;
+ area->phys_addr = __pfn_to_phys(page_to_pfn(page));
+
+ if (ioremap_page_range(addr, addr + size, area->phys_addr, prot)) {
+ vunmap((void *)addr);
+ return NULL;
+ }
+ return (void *)addr;
+}
- /* Grow region to accommodate specified size */
- if (base < consistent_base)
- consistent_base = base;
+static void __dma_free_remap(void *cpu_addr, size_t size)
+{
+ unsigned int flags = VM_ARM_DMA_CONSISTENT | VM_USERMAP;
+ struct vm_struct *area = find_vm_area(cpu_addr);
+ if (!area || (area->flags & flags) != flags) {
+ WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr);
+ return;
+ }
+ unmap_kernel_range((unsigned long)cpu_addr, size);
+ vunmap(cpu_addr);
}
-#include "vmregion.h"
+struct dma_pool {
+ size_t size;
+ spinlock_t lock;
+ unsigned long *bitmap;
+ unsigned long nr_pages;
+ void *vaddr;
+ struct page *page;
+};
-static struct arm_vmregion_head consistent_head = {
- .vm_lock = __SPIN_LOCK_UNLOCKED(&consistent_head.vm_lock),
- .vm_list = LIST_HEAD_INIT(consistent_head.vm_list),
- .vm_end = CONSISTENT_END,
+static struct dma_pool atomic_pool = {
+ .size = SZ_256K,
};
-#ifdef CONFIG_HUGETLB_PAGE
-#error ARM Coherent DMA allocator does not (yet) support huge TLB
-#endif
+static int __init early_coherent_pool(char *p)
+{
+ atomic_pool.size = memparse(p, &p);
+ return 0;
+}
+early_param("coherent_pool", early_coherent_pool);
/*
- * Initialise the consistent memory allocation.
+ * Initialise the coherent pool for atomic allocations.
*/
-static int __init consistent_init(void)
+static int __init atomic_pool_init(void)
{
- int ret = 0;
- pgd_t *pgd;
- pud_t *pud;
- pmd_t *pmd;
- pte_t *pte;
- int i = 0;
- unsigned long base = consistent_base;
- unsigned long num_ptes = (CONSISTENT_END - base) >> PMD_SHIFT;
+ struct dma_pool *pool = &atomic_pool;
+ pgprot_t prot = pgprot_dmacoherent(pgprot_kernel);
+ unsigned long nr_pages = pool->size >> PAGE_SHIFT;
+ unsigned long *bitmap;
+ struct page *page;
+ void *ptr;
+ int bitmap_size = BITS_TO_LONGS(nr_pages) * sizeof(long);
- consistent_pte = kmalloc(num_ptes * sizeof(pte_t), GFP_KERNEL);
- if (!consistent_pte) {
- pr_err("%s: no memory\n", __func__);
- return -ENOMEM;
+ bitmap = kzalloc(bitmap_size, GFP_KERNEL);
+ if (!bitmap)
+ goto no_bitmap;
+
+ if (IS_ENABLED(CONFIG_CMA))
+ ptr = __alloc_from_contiguous(NULL, pool->size, prot, &page);
+ else
+ ptr = __alloc_remap_buffer(NULL, pool->size, GFP_KERNEL, prot,
+ &page, NULL);
+ if (ptr) {
+ spin_lock_init(&pool->lock);
+ pool->vaddr = ptr;
+ pool->page = page;
+ pool->bitmap = bitmap;
+ pool->nr_pages = nr_pages;
+ pr_info("DMA: preallocated %u KiB pool for atomic coherent allocations\n",
+ (unsigned)pool->size / 1024);
+ return 0;
}
+ kfree(bitmap);
+no_bitmap:
+ pr_err("DMA: failed to allocate %u KiB pool for atomic coherent allocation\n",
+ (unsigned)pool->size / 1024);
+ return -ENOMEM;
+}
+/*
+ * CMA is activated by core_initcall, so we must be called after it.
+ */
+postcore_initcall(atomic_pool_init);
- pr_debug("DMA memory: 0x%08lx - 0x%08lx:\n", base, CONSISTENT_END);
- consistent_head.vm_start = base;
+struct dma_contig_early_reserve {
+ phys_addr_t base;
+ unsigned long size;
+};
- do {
- pgd = pgd_offset(&init_mm, base);
+static struct dma_contig_early_reserve dma_mmu_remap[MAX_CMA_AREAS] __initdata;
- pud = pud_alloc(&init_mm, pgd, base);
- if (!pud) {
- printk(KERN_ERR "%s: no pud tables\n", __func__);
- ret = -ENOMEM;
- break;
- }
+static int dma_mmu_remap_num __initdata;
- pmd = pmd_alloc(&init_mm, pud, base);
- if (!pmd) {
- printk(KERN_ERR "%s: no pmd tables\n", __func__);
- ret = -ENOMEM;
- break;
- }
- WARN_ON(!pmd_none(*pmd));
+void __init dma_contiguous_early_fixup(phys_addr_t base, unsigned long size)
+{
+ dma_mmu_remap[dma_mmu_remap_num].base = base;
+ dma_mmu_remap[dma_mmu_remap_num].size = size;
+ dma_mmu_remap_num++;
+}
- pte = pte_alloc_kernel(pmd, base);
- if (!pte) {
- printk(KERN_ERR "%s: no pte tables\n", __func__);
- ret = -ENOMEM;
- break;
- }
+void __init dma_contiguous_remap(void)
+{
+ int i;
+ for (i = 0; i < dma_mmu_remap_num; i++) {
+ phys_addr_t start = dma_mmu_remap[i].base;
+ phys_addr_t end = start + dma_mmu_remap[i].size;
+ struct map_desc map;
+ unsigned long addr;
+
+ if (end > arm_lowmem_limit)
+ end = arm_lowmem_limit;
+ if (start >= end)
+ return;
+
+ map.pfn = __phys_to_pfn(start);
+ map.virtual = __phys_to_virt(start);
+ map.length = end - start;
+ map.type = MT_MEMORY_DMA_READY;
- consistent_pte[i++] = pte;
- base += PMD_SIZE;
- } while (base < CONSISTENT_END);
+ /*
+ * Clear previous low-memory mapping
+ */
+ for (addr = __phys_to_virt(start); addr < __phys_to_virt(end);
+ addr += PMD_SIZE)
+ pmd_clear(pmd_off_k(addr));
- return ret;
+ iotable_init(&map, 1);
+ }
}
-core_initcall(consistent_init);
+static int __dma_update_pte(pte_t *pte, pgtable_t token, unsigned long addr,
+ void *data)
+{
+ struct page *page = virt_to_page(addr);
+ pgprot_t prot = *(pgprot_t *)data;
-static void *
-__dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot)
+ set_pte_ext(pte, mk_pte(page, prot), 0);
+ return 0;
+}
+
+static void __dma_remap(struct page *page, size_t size, pgprot_t prot)
+{
+ unsigned long start = (unsigned long) page_address(page);
+ unsigned end = start + size;
+
+ apply_to_page_range(&init_mm, start, size, __dma_update_pte, &prot);
+ dsb();
+ flush_tlb_kernel_range(start, end);
+}
+
+static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp,
+ pgprot_t prot, struct page **ret_page,
+ const void *caller)
{
- struct arm_vmregion *c;
- size_t align;
- int bit;
+ struct page *page;
+ void *ptr;
+ page = __dma_alloc_buffer(dev, size, gfp);
+ if (!page)
+ return NULL;
+
+ ptr = __dma_alloc_remap(page, size, gfp, prot, caller);
+ if (!ptr) {
+ __dma_free_buffer(page, size);
+ return NULL;
+ }
+
+ *ret_page = page;
+ return ptr;
+}
- if (!consistent_pte) {
- printk(KERN_ERR "%s: not initialised\n", __func__);
- dump_stack();
+static void *__alloc_from_pool(size_t size, struct page **ret_page)
+{
+ struct dma_pool *pool = &atomic_pool;
+ unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+ unsigned int pageno;
+ unsigned long flags;
+ void *ptr = NULL;
+ unsigned long align_mask;
+
+ if (!pool->vaddr) {
+ WARN(1, "coherent pool not initialised!\n");
return NULL;
}
/*
- * Align the virtual region allocation - maximum alignment is
- * a section size, minimum is a page size. This helps reduce
- * fragmentation of the DMA space, and also prevents allocations
- * smaller than a section from crossing a section boundary.
+ * Align the region allocation - allocations from pool are rather
+ * small, so align them to their order in pages, minimum is a page
+ * size. This helps reduce fragmentation of the DMA space.
*/
- bit = fls(size - 1);
- if (bit > SECTION_SHIFT)
- bit = SECTION_SHIFT;
- align = 1 << bit;
+ align_mask = (1 << get_order(size)) - 1;
+
+ spin_lock_irqsave(&pool->lock, flags);
+ pageno = bitmap_find_next_zero_area(pool->bitmap, pool->nr_pages,
+ 0, count, align_mask);
+ if (pageno < pool->nr_pages) {
+ bitmap_set(pool->bitmap, pageno, count);
+ ptr = pool->vaddr + PAGE_SIZE * pageno;
+ *ret_page = pool->page + pageno;
+ } else {
+ pr_err_once("ERROR: %u KiB atomic DMA coherent pool is too small!\n"
+ "Please increase it with coherent_pool= kernel parameter!\n",
+ (unsigned)pool->size / 1024);
+ }
+ spin_unlock_irqrestore(&pool->lock, flags);
- /*
- * Allocate a virtual address in the consistent mapping region.
- */
- c = arm_vmregion_alloc(&consistent_head, align, size,
- gfp & ~(__GFP_DMA | __GFP_HIGHMEM));
- if (c) {
- pte_t *pte;
- int idx = CONSISTENT_PTE_INDEX(c->vm_start);
- u32 off = CONSISTENT_OFFSET(c->vm_start) & (PTRS_PER_PTE-1);
-
- pte = consistent_pte[idx] + off;
- c->vm_pages = page;
-
- do {
- BUG_ON(!pte_none(*pte));
-
- set_pte_ext(pte, mk_pte(page, prot), 0);
- page++;
- pte++;
- off++;
- if (off >= PTRS_PER_PTE) {
- off = 0;
- pte = consistent_pte[++idx];
- }
- } while (size -= PAGE_SIZE);
+ return ptr;
+}
- dsb();
+static int __free_from_pool(void *start, size_t size)
+{
+ struct dma_pool *pool = &atomic_pool;
+ unsigned long pageno, count;
+ unsigned long flags;
+
+ if (start < pool->vaddr || start > pool->vaddr + pool->size)
+ return 0;
- return (void *)c->vm_start;
+ if (start + size > pool->vaddr + pool->size) {
+ WARN(1, "freeing wrong coherent size from pool\n");
+ return 0;
}
- return NULL;
+
+ pageno = (start - pool->vaddr) >> PAGE_SHIFT;
+ count = size >> PAGE_SHIFT;
+
+ spin_lock_irqsave(&pool->lock, flags);
+ bitmap_clear(pool->bitmap, pageno, count);
+ spin_unlock_irqrestore(&pool->lock, flags);
+
+ return 1;
}
-static void __dma_free_remap(void *cpu_addr, size_t size)
+static void *__alloc_from_contiguous(struct device *dev, size_t size,
+ pgprot_t prot, struct page **ret_page)
{
- struct arm_vmregion *c;
- unsigned long addr;
- pte_t *ptep;
- int idx;
- u32 off;
-
- c = arm_vmregion_find_remove(&consistent_head, (unsigned long)cpu_addr);
- if (!c) {
- printk(KERN_ERR "%s: trying to free invalid coherent area: %p\n",
- __func__, cpu_addr);
- dump_stack();
- return;
- }
+ unsigned long order = get_order(size);
+ size_t count = size >> PAGE_SHIFT;
+ struct page *page;
- 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;
- }
+ page = dma_alloc_from_contiguous(dev, count, order);
+ if (!page)
+ return NULL;
- idx = CONSISTENT_PTE_INDEX(c->vm_start);
- off = CONSISTENT_OFFSET(c->vm_start) & (PTRS_PER_PTE-1);
- ptep = consistent_pte[idx] + off;
- addr = c->vm_start;
- do {
- pte_t pte = ptep_get_and_clear(&init_mm, addr, ptep);
-
- ptep++;
- addr += PAGE_SIZE;
- off++;
- if (off >= PTRS_PER_PTE) {
- off = 0;
- ptep = consistent_pte[++idx];
- }
+ __dma_clear_buffer(page, size);
+ __dma_remap(page, size, prot);
- if (pte_none(pte) || !pte_present(pte))
- printk(KERN_CRIT "%s: bad page in kernel page table\n",
- __func__);
- } while (size -= PAGE_SIZE);
+ *ret_page = page;
+ return page_address(page);
+}
- flush_tlb_kernel_range(c->vm_start, c->vm_end);
+static void __free_from_contiguous(struct device *dev, struct page *page,
+ size_t size)
+{
+ __dma_remap(page, size, pgprot_kernel);
+ dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT);
+}
- arm_vmregion_free(&consistent_head, c);
+static inline pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot)
+{
+ prot = dma_get_attr(DMA_ATTR_WRITE_COMBINE, attrs) ?
+ pgprot_writecombine(prot) :
+ pgprot_dmacoherent(prot);
+ return prot;
}
+#define nommu() 0
+
#else /* !CONFIG_MMU */
-#define __dma_alloc_remap(page, size, gfp, prot) page_address(page)
-#define __dma_free_remap(addr, size) do { } while (0)
+#define nommu() 1
+
+#define __get_dma_pgprot(attrs, prot) __pgprot(0)
+#define __alloc_remap_buffer(dev, size, gfp, prot, ret, c) NULL
+#define __alloc_from_pool(size, ret_page) NULL
+#define __alloc_from_contiguous(dev, size, prot, ret) NULL
+#define __free_from_pool(cpu_addr, size) 0
+#define __free_from_contiguous(dev, page, size) do { } while (0)
+#define __dma_free_remap(cpu_addr, size) do { } while (0)
#endif /* CONFIG_MMU */
-static void *
-__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp,
- pgprot_t prot)
+static void *__alloc_simple_buffer(struct device *dev, size_t size, gfp_t gfp,
+ struct page **ret_page)
+{
+ struct page *page;
+ page = __dma_alloc_buffer(dev, size, gfp);
+ if (!page)
+ return NULL;
+
+ *ret_page = page;
+ return page_address(page);
+}
+
+
+
+static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
+ gfp_t gfp, pgprot_t prot, const void *caller)
{
+ u64 mask = get_coherent_dma_mask(dev);
struct page *page;
void *addr;
+#ifdef CONFIG_DMA_API_DEBUG
+ u64 limit = (mask + 1) & ~mask;
+ if (limit && size >= limit) {
+ dev_warn(dev, "coherent allocation too big (requested %#x mask %#llx)\n",
+ size, mask);
+ return NULL;
+ }
+#endif
+
+ if (!mask)
+ return NULL;
+
+ if (mask < 0xffffffffULL)
+ gfp |= GFP_DMA;
+
/*
* Following is a work-around (a.k.a. hack) to prevent pages
* with __GFP_COMP being passed to split_page() which cannot
*/
gfp &= ~(__GFP_COMP);
- *handle = ~0;
+ *handle = DMA_ERROR_CODE;
size = PAGE_ALIGN(size);
- page = __dma_alloc_buffer(dev, size, gfp);
- if (!page)
- return NULL;
-
- if (!arch_is_coherent())
- addr = __dma_alloc_remap(page, size, gfp, prot);
+ if (arch_is_coherent() || nommu())
+ addr = __alloc_simple_buffer(dev, size, gfp, &page);
+ else if (gfp & GFP_ATOMIC)
+ addr = __alloc_from_pool(size, &page);
+ else if (!IS_ENABLED(CONFIG_CMA))
+ addr = __alloc_remap_buffer(dev, size, gfp, prot, &page, caller);
else
- addr = page_address(page);
+ addr = __alloc_from_contiguous(dev, size, prot, &page);
if (addr)
*handle = pfn_to_dma(dev, page_to_pfn(page));
- else
- __dma_free_buffer(page, size);
return addr;
}
* Allocate DMA-coherent memory space and return both the kernel remapped
* virtual and bus address for that space.
*/
-void *
-dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp)
+void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
+ gfp_t gfp, struct dma_attrs *attrs)
{
- pgprot_t prot = __get_dma_pgprot(attrs, pgprot_kernel);
++ pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL);
void *memory;
if (dma_alloc_from_coherent(dev, size, handle, &memory))
return memory;
- return __dma_alloc(dev, size, handle, gfp,
- pgprot_dmacoherent(PAGE_KERNEL));
+ return __dma_alloc(dev, size, handle, gfp, prot,
+ __builtin_return_address(0));
}
-EXPORT_SYMBOL(dma_alloc_coherent);
/*
- * Allocate a writecombining region, in much the same way as
- * dma_alloc_coherent above.
+ * Create userspace mapping for the DMA-coherent memory.
*/
-void *
-dma_alloc_writecombine(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp)
-{
- return __dma_alloc(dev, size, handle, gfp,
- pgprot_writecombine(PAGE_KERNEL));
-}
-EXPORT_SYMBOL(dma_alloc_writecombine);
-
-static int dma_mmap(struct device *dev, struct vm_area_struct *vma,
- void *cpu_addr, dma_addr_t dma_addr, size_t size)
+int arm_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+ void *cpu_addr, dma_addr_t dma_addr, size_t size,
+ struct dma_attrs *attrs)
{
int ret = -ENXIO;
#ifdef CONFIG_MMU
- unsigned long user_size, kern_size;
- struct arm_vmregion *c;
-
- user_size = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+ unsigned long nr_vma_pages = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+ unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
+ unsigned long pfn = dma_to_pfn(dev, dma_addr);
+ unsigned long off = vma->vm_pgoff;
- c = arm_vmregion_find(&consistent_head, (unsigned long)cpu_addr);
- if (c) {
- unsigned long off = vma->vm_pgoff;
+ vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot);
- kern_size = (c->vm_end - c->vm_start) >> PAGE_SHIFT;
+ if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret))
+ return ret;
- if (off < kern_size &&
- user_size <= (kern_size - off)) {
- ret = remap_pfn_range(vma, vma->vm_start,
- page_to_pfn(c->vm_pages) + off,
- user_size << PAGE_SHIFT,
- vma->vm_page_prot);
- }
+ if (off < nr_pages && nr_vma_pages <= (nr_pages - off)) {
+ ret = remap_pfn_range(vma, vma->vm_start,
+ pfn + off,
+ vma->vm_end - vma->vm_start,
+ vma->vm_page_prot);
}
#endif /* CONFIG_MMU */
return ret;
}
-int dma_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
- void *cpu_addr, dma_addr_t dma_addr, size_t size)
-{
- vma->vm_page_prot = pgprot_dmacoherent(vma->vm_page_prot);
- return dma_mmap(dev, vma, cpu_addr, dma_addr, size);
-}
-EXPORT_SYMBOL(dma_mmap_coherent);
-
-int dma_mmap_writecombine(struct device *dev, struct vm_area_struct *vma,
- void *cpu_addr, dma_addr_t dma_addr, size_t size)
-{
- vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
- return dma_mmap(dev, vma, cpu_addr, dma_addr, size);
-}
-EXPORT_SYMBOL(dma_mmap_writecombine);
-
/*
- * free a page as defined by the above mapping.
- * Must not be called with IRQs disabled.
+ * Free a buffer as defined by the above mapping.
*/
-void dma_free_coherent(struct device *dev, size_t size, void *cpu_addr, dma_addr_t handle)
+void arm_dma_free(struct device *dev, size_t size, void *cpu_addr,
+ dma_addr_t handle, struct dma_attrs *attrs)
{
- WARN_ON(irqs_disabled());
+ struct page *page = pfn_to_page(dma_to_pfn(dev, handle));
if (dma_release_from_coherent(dev, get_order(size), cpu_addr))
return;
size = PAGE_ALIGN(size);
- if (!arch_is_coherent())
+ if (arch_is_coherent() || nommu()) {
+ __dma_free_buffer(page, size);
+ } else if (__free_from_pool(cpu_addr, size)) {
+ return;
+ } else if (!IS_ENABLED(CONFIG_CMA)) {
__dma_free_remap(cpu_addr, size);
-
- __dma_free_buffer(pfn_to_page(dma_to_pfn(dev, handle)), size);
-}
-EXPORT_SYMBOL(dma_free_coherent);
-
-/*
- * Make an area consistent for devices.
- * Note: Drivers should NOT use this function directly, as it will break
- * platforms with CONFIG_DMABOUNCE.
- * Use the driver DMA support - see dma-mapping.h (dma_sync_*)
- */
-void ___dma_single_cpu_to_dev(const void *kaddr, size_t size,
- enum dma_data_direction dir)
-{
- unsigned long paddr;
-
- BUG_ON(!virt_addr_valid(kaddr) || !virt_addr_valid(kaddr + size - 1));
-
- dmac_map_area(kaddr, size, dir);
-
- paddr = __pa(kaddr);
- if (dir == DMA_FROM_DEVICE) {
- outer_inv_range(paddr, paddr + size);
+ __dma_free_buffer(page, size);
} else {
- outer_clean_range(paddr, paddr + size);
- }
- /* FIXME: non-speculating: flush on bidirectional mappings? */
-}
-EXPORT_SYMBOL(___dma_single_cpu_to_dev);
-
-void ___dma_single_dev_to_cpu(const void *kaddr, size_t size,
- enum dma_data_direction dir)
-{
- BUG_ON(!virt_addr_valid(kaddr) || !virt_addr_valid(kaddr + size - 1));
-
- /* FIXME: non-speculating: not required */
- /* don't bother invalidating if DMA to device */
- if (dir != DMA_TO_DEVICE) {
- unsigned long paddr = __pa(kaddr);
- outer_inv_range(paddr, paddr + size);
+ /*
+ * Non-atomic allocations cannot be freed with IRQs disabled
+ */
+ WARN_ON(irqs_disabled());
+ __free_from_contiguous(dev, page, size);
}
-
- dmac_unmap_area(kaddr, size, dir);
}
-EXPORT_SYMBOL(___dma_single_dev_to_cpu);
static void dma_cache_maint_page(struct page *page, unsigned long offset,
size_t size, enum dma_data_direction dir,
} while (left);
}
-void ___dma_page_cpu_to_dev(struct page *page, unsigned long off,
+/*
+ * Make an area consistent for devices.
+ * Note: Drivers should NOT use this function directly, as it will break
+ * platforms with CONFIG_DMABOUNCE.
+ * Use the driver DMA support - see dma-mapping.h (dma_sync_*)
+ */
+static void __dma_page_cpu_to_dev(struct page *page, unsigned long off,
size_t size, enum dma_data_direction dir)
{
unsigned long paddr;
}
/* FIXME: non-speculating: flush on bidirectional mappings? */
}
-EXPORT_SYMBOL(___dma_page_cpu_to_dev);
-void ___dma_page_dev_to_cpu(struct page *page, unsigned long off,
+static void __dma_page_dev_to_cpu(struct page *page, unsigned long off,
size_t size, enum dma_data_direction dir)
{
unsigned long paddr = page_to_phys(page) + off;
dma_cache_maint_page(page, off, size, dir, dmac_unmap_area);
/*
- * Mark the D-cache clean for this page to avoid extra flushing.
+ * Mark the D-cache clean for these pages to avoid extra flushing.
*/
- if (dir != DMA_TO_DEVICE && off == 0 && size >= PAGE_SIZE)
- set_bit(PG_dcache_clean, &page->flags);
+ if (dir != DMA_TO_DEVICE && size >= PAGE_SIZE) {
+ unsigned long pfn;
+ size_t left = size;
+
+ pfn = page_to_pfn(page) + off / PAGE_SIZE;
+ off %= PAGE_SIZE;
+ if (off) {
+ pfn++;
+ left -= PAGE_SIZE - off;
+ }
+ while (left >= PAGE_SIZE) {
+ page = pfn_to_page(pfn++);
+ set_bit(PG_dcache_clean, &page->flags);
+ left -= PAGE_SIZE;
+ }
+ }
}
-EXPORT_SYMBOL(___dma_page_dev_to_cpu);
/**
- * dma_map_sg - map a set of SG buffers for streaming mode DMA
+ * arm_dma_map_sg - map a set of SG buffers for streaming mode DMA
* @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
* @sg: list of buffers
* @nents: number of buffers to map
* Device ownership issues as mentioned for dma_map_single are the same
* here.
*/
-int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
- enum dma_data_direction dir)
+int arm_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
+ enum dma_data_direction dir, struct dma_attrs *attrs)
{
+ struct dma_map_ops *ops = get_dma_ops(dev);
struct scatterlist *s;
int i, j;
- BUG_ON(!valid_dma_direction(dir));
-
for_each_sg(sg, s, nents, i) {
- s->dma_address = __dma_map_page(dev, sg_page(s), s->offset,
- s->length, dir);
+#ifdef CONFIG_NEED_SG_DMA_LENGTH
+ s->dma_length = s->length;
+#endif
+ s->dma_address = ops->map_page(dev, sg_page(s), s->offset,
+ s->length, dir, attrs);
if (dma_mapping_error(dev, s->dma_address))
goto bad_mapping;
}
- debug_dma_map_sg(dev, sg, nents, nents, dir);
return nents;
bad_mapping:
for_each_sg(sg, s, i, j)
- __dma_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir);
+ ops->unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir, attrs);
return 0;
}
-EXPORT_SYMBOL(dma_map_sg);
/**
- * dma_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg
+ * arm_dma_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg
* @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
* @sg: list of buffers
* @nents: number of buffers to unmap (same as was passed to dma_map_sg)
* Unmap a set of streaming mode DMA translations. Again, CPU access
* rules concerning calls here are the same as for dma_unmap_single().
*/
-void dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
- enum dma_data_direction dir)
+void arm_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
+ enum dma_data_direction dir, struct dma_attrs *attrs)
{
+ struct dma_map_ops *ops = get_dma_ops(dev);
struct scatterlist *s;
- int i;
- debug_dma_unmap_sg(dev, sg, nents, dir);
+ int i;
for_each_sg(sg, s, nents, i)
- __dma_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir);
+ ops->unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir, attrs);
}
-EXPORT_SYMBOL(dma_unmap_sg);
/**
- * dma_sync_sg_for_cpu
+ * arm_dma_sync_sg_for_cpu
* @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
* @sg: list of buffers
* @nents: number of buffers to map (returned from dma_map_sg)
* @dir: DMA transfer direction (same as was passed to dma_map_sg)
*/
-void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
+void arm_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
int nents, enum dma_data_direction dir)
{
+ struct dma_map_ops *ops = get_dma_ops(dev);
struct scatterlist *s;
int i;
- for_each_sg(sg, s, nents, i) {
- if (!dmabounce_sync_for_cpu(dev, sg_dma_address(s), 0,
- sg_dma_len(s), dir))
- continue;
-
- __dma_page_dev_to_cpu(sg_page(s), s->offset,
- s->length, dir);
- }
-
- debug_dma_sync_sg_for_cpu(dev, sg, nents, dir);
+ for_each_sg(sg, s, nents, i)
+ ops->sync_single_for_cpu(dev, sg_dma_address(s), s->length,
+ dir);
}
-EXPORT_SYMBOL(dma_sync_sg_for_cpu);
/**
- * dma_sync_sg_for_device
+ * arm_dma_sync_sg_for_device
* @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
* @sg: list of buffers
* @nents: number of buffers to map (returned from dma_map_sg)
* @dir: DMA transfer direction (same as was passed to dma_map_sg)
*/
-void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
+void arm_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
int nents, enum dma_data_direction dir)
{
+ struct dma_map_ops *ops = get_dma_ops(dev);
struct scatterlist *s;
int i;
- for_each_sg(sg, s, nents, i) {
- if (!dmabounce_sync_for_device(dev, sg_dma_address(s), 0,
- sg_dma_len(s), dir))
- continue;
-
- __dma_page_cpu_to_dev(sg_page(s), s->offset,
- s->length, dir);
- }
-
- debug_dma_sync_sg_for_device(dev, sg, nents, dir);
+ for_each_sg(sg, s, nents, i)
+ ops->sync_single_for_device(dev, sg_dma_address(s), s->length,
+ dir);
}
-EXPORT_SYMBOL(dma_sync_sg_for_device);
/*
* Return whether the given device DMA address mask can be supported
}
EXPORT_SYMBOL(dma_supported);
-int dma_set_mask(struct device *dev, u64 dma_mask)
+static int arm_dma_set_mask(struct device *dev, u64 dma_mask)
{
if (!dev->dma_mask || !dma_supported(dev, dma_mask))
return -EIO;
-#ifndef CONFIG_DMABOUNCE
*dev->dma_mask = dma_mask;
-#endif
return 0;
}
-EXPORT_SYMBOL(dma_set_mask);
#define PREALLOC_DMA_DEBUG_ENTRIES 4096
return 0;
}
fs_initcall(dma_debug_do_init);
+
+#ifdef CONFIG_ARM_DMA_USE_IOMMU
+
+/* IOMMU */
+
+static inline dma_addr_t __alloc_iova(struct dma_iommu_mapping *mapping,
+ size_t size)
+{
+ unsigned int order = get_order(size);
+ unsigned int align = 0;
+ unsigned int count, start;
+ unsigned long flags;
+
+ count = ((PAGE_ALIGN(size) >> PAGE_SHIFT) +
+ (1 << mapping->order) - 1) >> mapping->order;
+
+ if (order > mapping->order)
+ align = (1 << (order - mapping->order)) - 1;
+
+ spin_lock_irqsave(&mapping->lock, flags);
+ start = bitmap_find_next_zero_area(mapping->bitmap, mapping->bits, 0,
+ count, align);
+ if (start > mapping->bits) {
+ spin_unlock_irqrestore(&mapping->lock, flags);
+ return DMA_ERROR_CODE;
+ }
+
+ bitmap_set(mapping->bitmap, start, count);
+ spin_unlock_irqrestore(&mapping->lock, flags);
+
+ return mapping->base + (start << (mapping->order + PAGE_SHIFT));
+}
+
+static inline void __free_iova(struct dma_iommu_mapping *mapping,
+ dma_addr_t addr, size_t size)
+{
+ unsigned int start = (addr - mapping->base) >>
+ (mapping->order + PAGE_SHIFT);
+ unsigned int count = ((size >> PAGE_SHIFT) +
+ (1 << mapping->order) - 1) >> mapping->order;
+ unsigned long flags;
+
+ spin_lock_irqsave(&mapping->lock, flags);
+ bitmap_clear(mapping->bitmap, start, count);
+ spin_unlock_irqrestore(&mapping->lock, flags);
+}
+
+static struct page **__iommu_alloc_buffer(struct device *dev, size_t size, gfp_t gfp)
+{
+ struct page **pages;
+ int count = size >> PAGE_SHIFT;
+ int array_size = count * sizeof(struct page *);
+ int i = 0;
+
+ if (array_size <= PAGE_SIZE)
+ pages = kzalloc(array_size, gfp);
+ else
+ pages = vzalloc(array_size);
+ if (!pages)
+ return NULL;
+
+ while (count) {
+ int j, order = __fls(count);
+
+ pages[i] = alloc_pages(gfp | __GFP_NOWARN, order);
+ while (!pages[i] && order)
+ pages[i] = alloc_pages(gfp | __GFP_NOWARN, --order);
+ if (!pages[i])
+ goto error;
+
+ if (order)
+ split_page(pages[i], order);
+ j = 1 << order;
+ while (--j)
+ pages[i + j] = pages[i] + j;
+
+ __dma_clear_buffer(pages[i], PAGE_SIZE << order);
+ i += 1 << order;
+ count -= 1 << order;
+ }
+
+ return pages;
+error:
+ while (i--)
+ if (pages[i])
+ __free_pages(pages[i], 0);
+ if (array_size <= PAGE_SIZE)
+ kfree(pages);
+ else
+ vfree(pages);
+ return NULL;
+}
+
+static int __iommu_free_buffer(struct device *dev, struct page **pages, size_t size)
+{
+ int count = size >> PAGE_SHIFT;
+ int array_size = count * sizeof(struct page *);
+ int i;
+ for (i = 0; i < count; i++)
+ if (pages[i])
+ __free_pages(pages[i], 0);
+ if (array_size <= PAGE_SIZE)
+ kfree(pages);
+ else
+ vfree(pages);
+ return 0;
+}
+
+/*
+ * Create a CPU mapping for a specified pages
+ */
+static void *
+__iommu_alloc_remap(struct page **pages, size_t size, gfp_t gfp, pgprot_t prot,
+ const void *caller)
+{
+ unsigned int i, nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
+ struct vm_struct *area;
+ unsigned long p;
+
+ area = get_vm_area_caller(size, VM_ARM_DMA_CONSISTENT | VM_USERMAP,
+ caller);
+ if (!area)
+ return NULL;
+
+ area->pages = pages;
+ area->nr_pages = nr_pages;
+ p = (unsigned long)area->addr;
+
+ for (i = 0; i < nr_pages; i++) {
+ phys_addr_t phys = __pfn_to_phys(page_to_pfn(pages[i]));
+ if (ioremap_page_range(p, p + PAGE_SIZE, phys, prot))
+ goto err;
+ p += PAGE_SIZE;
+ }
+ return area->addr;
+err:
+ unmap_kernel_range((unsigned long)area->addr, size);
+ vunmap(area->addr);
+ return NULL;
+}
+
+/*
+ * Create a mapping in device IO address space for specified pages
+ */
+static dma_addr_t
+__iommu_create_mapping(struct device *dev, struct page **pages, size_t size)
+{
+ struct dma_iommu_mapping *mapping = dev->archdata.mapping;
+ unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+ dma_addr_t dma_addr, iova;
+ int i, ret = DMA_ERROR_CODE;
+
+ dma_addr = __alloc_iova(mapping, size);
+ if (dma_addr == DMA_ERROR_CODE)
+ return dma_addr;
+
+ iova = dma_addr;
+ for (i = 0; i < count; ) {
+ unsigned int next_pfn = page_to_pfn(pages[i]) + 1;
+ phys_addr_t phys = page_to_phys(pages[i]);
+ unsigned int len, j;
+
+ for (j = i + 1; j < count; j++, next_pfn++)
+ if (page_to_pfn(pages[j]) != next_pfn)
+ break;
+
+ len = (j - i) << PAGE_SHIFT;
+ ret = iommu_map(mapping->domain, iova, phys, len, 0);
+ if (ret < 0)
+ goto fail;
+ iova += len;
+ i = j;
+ }
+ return dma_addr;
+fail:
+ iommu_unmap(mapping->domain, dma_addr, iova-dma_addr);
+ __free_iova(mapping, dma_addr, size);
+ return DMA_ERROR_CODE;
+}
+
+static int __iommu_remove_mapping(struct device *dev, dma_addr_t iova, size_t size)
+{
+ struct dma_iommu_mapping *mapping = dev->archdata.mapping;
+
+ /*
+ * add optional in-page offset from iova to size and align
+ * result to page size
+ */
+ size = PAGE_ALIGN((iova & ~PAGE_MASK) + size);
+ iova &= PAGE_MASK;
+
+ iommu_unmap(mapping->domain, iova, size);
+ __free_iova(mapping, iova, size);
+ return 0;
+}
+
+static struct page **__iommu_get_pages(void *cpu_addr, struct dma_attrs *attrs)
+{
+ struct vm_struct *area;
+
+ if (dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs))
+ return cpu_addr;
+
+ area = find_vm_area(cpu_addr);
+ if (area && (area->flags & VM_ARM_DMA_CONSISTENT))
+ return area->pages;
+ return NULL;
+}
+
+static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
+ dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs)
+{
+ pgprot_t prot = __get_dma_pgprot(attrs, pgprot_kernel);
+ struct page **pages;
+ void *addr = NULL;
+
+ *handle = DMA_ERROR_CODE;
+ size = PAGE_ALIGN(size);
+
+ pages = __iommu_alloc_buffer(dev, size, gfp);
+ if (!pages)
+ return NULL;
+
+ *handle = __iommu_create_mapping(dev, pages, size);
+ if (*handle == DMA_ERROR_CODE)
+ goto err_buffer;
+
+ if (dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs))
+ return pages;
+
+ addr = __iommu_alloc_remap(pages, size, gfp, prot,
+ __builtin_return_address(0));
+ if (!addr)
+ goto err_mapping;
+
+ return addr;
+
+err_mapping:
+ __iommu_remove_mapping(dev, *handle, size);
+err_buffer:
+ __iommu_free_buffer(dev, pages, size);
+ return NULL;
+}
+
+static int arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
+ void *cpu_addr, dma_addr_t dma_addr, size_t size,
+ struct dma_attrs *attrs)
+{
+ unsigned long uaddr = vma->vm_start;
+ unsigned long usize = vma->vm_end - vma->vm_start;
+ struct page **pages = __iommu_get_pages(cpu_addr, attrs);
+
+ vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot);
+
+ if (!pages)
+ return -ENXIO;
+
+ do {
+ int ret = vm_insert_page(vma, uaddr, *pages++);
+ if (ret) {
+ pr_err("Remapping memory failed: %d\n", ret);
+ return ret;
+ }
+ uaddr += PAGE_SIZE;
+ usize -= PAGE_SIZE;
+ } while (usize > 0);
+
+ return 0;
+}
+
+/*
+ * free a page as defined by the above mapping.
+ * Must not be called with IRQs disabled.
+ */
+void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
+ dma_addr_t handle, struct dma_attrs *attrs)
+{
+ struct page **pages = __iommu_get_pages(cpu_addr, attrs);
+ size = PAGE_ALIGN(size);
+
+ if (!pages) {
+ WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr);
+ return;
+ }
+
+ if (!dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs)) {
+ unmap_kernel_range((unsigned long)cpu_addr, size);
+ vunmap(cpu_addr);
+ }
+
+ __iommu_remove_mapping(dev, handle, size);
+ __iommu_free_buffer(dev, pages, size);
+}
+
+/*
+ * Map a part of the scatter-gather list into contiguous io address space
+ */
+static int __map_sg_chunk(struct device *dev, struct scatterlist *sg,
+ size_t size, dma_addr_t *handle,
+ enum dma_data_direction dir)
+{
+ struct dma_iommu_mapping *mapping = dev->archdata.mapping;
+ dma_addr_t iova, iova_base;
+ int ret = 0;
+ unsigned int count;
+ struct scatterlist *s;
+
+ size = PAGE_ALIGN(size);
+ *handle = DMA_ERROR_CODE;
+
+ iova_base = iova = __alloc_iova(mapping, size);
+ if (iova == DMA_ERROR_CODE)
+ return -ENOMEM;
+
+ for (count = 0, s = sg; count < (size >> PAGE_SHIFT); s = sg_next(s)) {
+ phys_addr_t phys = page_to_phys(sg_page(s));
+ unsigned int len = PAGE_ALIGN(s->offset + s->length);
+
+ if (!arch_is_coherent())
+ __dma_page_cpu_to_dev(sg_page(s), s->offset, s->length, dir);
+
+ ret = iommu_map(mapping->domain, iova, phys, len, 0);
+ if (ret < 0)
+ goto fail;
+ count += len >> PAGE_SHIFT;
+ iova += len;
+ }
+ *handle = iova_base;
+
+ return 0;
+fail:
+ iommu_unmap(mapping->domain, iova_base, count * PAGE_SIZE);
+ __free_iova(mapping, iova_base, size);
+ return ret;
+}
+
+/**
+ * arm_iommu_map_sg - map a set of SG buffers for streaming mode DMA
+ * @dev: valid struct device pointer
+ * @sg: list of buffers
+ * @nents: number of buffers to map
+ * @dir: DMA transfer direction
+ *
+ * Map a set of buffers described by scatterlist in streaming mode for DMA.
+ * The scatter gather list elements are merged together (if possible) and
+ * tagged with the appropriate dma address and length. They are obtained via
+ * sg_dma_{address,length}.
+ */
+int arm_iommu_map_sg(struct device *dev, struct scatterlist *sg, int nents,
+ enum dma_data_direction dir, struct dma_attrs *attrs)
+{
+ struct scatterlist *s = sg, *dma = sg, *start = sg;
+ int i, count = 0;
+ unsigned int offset = s->offset;
+ unsigned int size = s->offset + s->length;
+ unsigned int max = dma_get_max_seg_size(dev);
+
+ for (i = 1; i < nents; i++) {
+ s = sg_next(s);
+
+ s->dma_address = DMA_ERROR_CODE;
+ s->dma_length = 0;
+
+ if (s->offset || (size & ~PAGE_MASK) || size + s->length > max) {
+ if (__map_sg_chunk(dev, start, size, &dma->dma_address,
+ dir) < 0)
+ goto bad_mapping;
+
+ dma->dma_address += offset;
+ dma->dma_length = size - offset;
+
+ size = offset = s->offset;
+ start = s;
+ dma = sg_next(dma);
+ count += 1;
+ }
+ size += s->length;
+ }
+ if (__map_sg_chunk(dev, start, size, &dma->dma_address, dir) < 0)
+ goto bad_mapping;
+
+ dma->dma_address += offset;
+ dma->dma_length = size - offset;
+
+ return count+1;
+
+bad_mapping:
+ for_each_sg(sg, s, count, i)
+ __iommu_remove_mapping(dev, sg_dma_address(s), sg_dma_len(s));
+ return 0;
+}
+
+/**
+ * arm_iommu_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg
+ * @dev: valid struct device pointer
+ * @sg: list of buffers
+ * @nents: number of buffers to unmap (same as was passed to dma_map_sg)
+ * @dir: DMA transfer direction (same as was passed to dma_map_sg)
+ *
+ * Unmap a set of streaming mode DMA translations. Again, CPU access
+ * rules concerning calls here are the same as for dma_unmap_single().
+ */
+void arm_iommu_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
+ enum dma_data_direction dir, struct dma_attrs *attrs)
+{
+ struct scatterlist *s;
+ int i;
+
+ for_each_sg(sg, s, nents, i) {
+ if (sg_dma_len(s))
+ __iommu_remove_mapping(dev, sg_dma_address(s),
+ sg_dma_len(s));
+ if (!arch_is_coherent())
+ __dma_page_dev_to_cpu(sg_page(s), s->offset,
+ s->length, dir);
+ }
+}
+
+/**
+ * arm_iommu_sync_sg_for_cpu
+ * @dev: valid struct device pointer
+ * @sg: list of buffers
+ * @nents: number of buffers to map (returned from dma_map_sg)
+ * @dir: DMA transfer direction (same as was passed to dma_map_sg)
+ */
+void arm_iommu_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
+ int nents, enum dma_data_direction dir)
+{
+ struct scatterlist *s;
+ int i;
+
+ for_each_sg(sg, s, nents, i)
+ if (!arch_is_coherent())
+ __dma_page_dev_to_cpu(sg_page(s), s->offset, s->length, dir);
+
+}
+
+/**
+ * arm_iommu_sync_sg_for_device
+ * @dev: valid struct device pointer
+ * @sg: list of buffers
+ * @nents: number of buffers to map (returned from dma_map_sg)
+ * @dir: DMA transfer direction (same as was passed to dma_map_sg)
+ */
+void arm_iommu_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
+ int nents, enum dma_data_direction dir)
+{
+ struct scatterlist *s;
+ int i;
+
+ for_each_sg(sg, s, nents, i)
+ if (!arch_is_coherent())
+ __dma_page_cpu_to_dev(sg_page(s), s->offset, s->length, dir);
+}
+
+
+/**
+ * arm_iommu_map_page
+ * @dev: valid struct device pointer
+ * @page: page that buffer resides in
+ * @offset: offset into page for start of buffer
+ * @size: size of buffer to map
+ * @dir: DMA transfer direction
+ *
+ * IOMMU aware version of arm_dma_map_page()
+ */
+static dma_addr_t arm_iommu_map_page(struct device *dev, struct page *page,
+ unsigned long offset, size_t size, enum dma_data_direction dir,
+ struct dma_attrs *attrs)
+{
+ struct dma_iommu_mapping *mapping = dev->archdata.mapping;
+ dma_addr_t dma_addr;
+ int ret, len = PAGE_ALIGN(size + offset);
+
+ if (!arch_is_coherent())
+ __dma_page_cpu_to_dev(page, offset, size, dir);
+
+ dma_addr = __alloc_iova(mapping, len);
+ if (dma_addr == DMA_ERROR_CODE)
+ return dma_addr;
+
+ ret = iommu_map(mapping->domain, dma_addr, page_to_phys(page), len, 0);
+ if (ret < 0)
+ goto fail;
+
+ return dma_addr + offset;
+fail:
+ __free_iova(mapping, dma_addr, len);
+ return DMA_ERROR_CODE;
+}
+
+/**
+ * arm_iommu_unmap_page
+ * @dev: valid struct device pointer
+ * @handle: DMA address of buffer
+ * @size: size of buffer (same as passed to dma_map_page)
+ * @dir: DMA transfer direction (same as passed to dma_map_page)
+ *
+ * IOMMU aware version of arm_dma_unmap_page()
+ */
+static void arm_iommu_unmap_page(struct device *dev, dma_addr_t handle,
+ size_t size, enum dma_data_direction dir,
+ struct dma_attrs *attrs)
+{
+ struct dma_iommu_mapping *mapping = dev->archdata.mapping;
+ dma_addr_t iova = handle & PAGE_MASK;
+ struct page *page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova));
+ int offset = handle & ~PAGE_MASK;
+ int len = PAGE_ALIGN(size + offset);
+
+ if (!iova)
+ return;
+
+ if (!arch_is_coherent())
+ __dma_page_dev_to_cpu(page, offset, size, dir);
+
+ iommu_unmap(mapping->domain, iova, len);
+ __free_iova(mapping, iova, len);
+}
+
+static void arm_iommu_sync_single_for_cpu(struct device *dev,
+ dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+ struct dma_iommu_mapping *mapping = dev->archdata.mapping;
+ dma_addr_t iova = handle & PAGE_MASK;
+ struct page *page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova));
+ unsigned int offset = handle & ~PAGE_MASK;
+
+ if (!iova)
+ return;
+
+ if (!arch_is_coherent())
+ __dma_page_dev_to_cpu(page, offset, size, dir);
+}
+
+static void arm_iommu_sync_single_for_device(struct device *dev,
+ dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+ struct dma_iommu_mapping *mapping = dev->archdata.mapping;
+ dma_addr_t iova = handle & PAGE_MASK;
+ struct page *page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova));
+ unsigned int offset = handle & ~PAGE_MASK;
+
+ if (!iova)
+ return;
+
+ __dma_page_cpu_to_dev(page, offset, size, dir);
+}
+
+struct dma_map_ops iommu_ops = {
+ .alloc = arm_iommu_alloc_attrs,
+ .free = arm_iommu_free_attrs,
+ .mmap = arm_iommu_mmap_attrs,
+
+ .map_page = arm_iommu_map_page,
+ .unmap_page = arm_iommu_unmap_page,
+ .sync_single_for_cpu = arm_iommu_sync_single_for_cpu,
+ .sync_single_for_device = arm_iommu_sync_single_for_device,
+
+ .map_sg = arm_iommu_map_sg,
+ .unmap_sg = arm_iommu_unmap_sg,
+ .sync_sg_for_cpu = arm_iommu_sync_sg_for_cpu,
+ .sync_sg_for_device = arm_iommu_sync_sg_for_device,
+};
+
+/**
+ * arm_iommu_create_mapping
+ * @bus: pointer to the bus holding the client device (for IOMMU calls)
+ * @base: start address of the valid IO address space
+ * @size: size of the valid IO address space
+ * @order: accuracy of the IO addresses allocations
+ *
+ * Creates a mapping structure which holds information about used/unused
+ * IO address ranges, which is required to perform memory allocation and
+ * mapping with IOMMU aware functions.
+ *
+ * The client device need to be attached to the mapping with
+ * arm_iommu_attach_device function.
+ */
+struct dma_iommu_mapping *
+arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, size_t size,
+ int order)
+{
+ unsigned int count = size >> (PAGE_SHIFT + order);
+ unsigned int bitmap_size = BITS_TO_LONGS(count) * sizeof(long);
+ struct dma_iommu_mapping *mapping;
+ int err = -ENOMEM;
+
+ if (!count)
+ return ERR_PTR(-EINVAL);
+
+ mapping = kzalloc(sizeof(struct dma_iommu_mapping), GFP_KERNEL);
+ if (!mapping)
+ goto err;
+
+ mapping->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
+ if (!mapping->bitmap)
+ goto err2;
+
+ mapping->base = base;
+ mapping->bits = BITS_PER_BYTE * bitmap_size;
+ mapping->order = order;
+ spin_lock_init(&mapping->lock);
+
+ mapping->domain = iommu_domain_alloc(bus);
+ if (!mapping->domain)
+ goto err3;
+
+ kref_init(&mapping->kref);
+ return mapping;
+err3:
+ kfree(mapping->bitmap);
+err2:
+ kfree(mapping);
+err:
+ return ERR_PTR(err);
+}
+
+static void release_iommu_mapping(struct kref *kref)
+{
+ struct dma_iommu_mapping *mapping =
+ container_of(kref, struct dma_iommu_mapping, kref);
+
+ iommu_domain_free(mapping->domain);
+ kfree(mapping->bitmap);
+ kfree(mapping);
+}
+
+void arm_iommu_release_mapping(struct dma_iommu_mapping *mapping)
+{
+ if (mapping)
+ kref_put(&mapping->kref, release_iommu_mapping);
+}
+
+/**
+ * arm_iommu_attach_device
+ * @dev: valid struct device pointer
+ * @mapping: io address space mapping structure (returned from
+ * arm_iommu_create_mapping)
+ *
+ * Attaches specified io address space mapping to the provided device,
+ * this replaces the dma operations (dma_map_ops pointer) with the
+ * IOMMU aware version. More than one client might be attached to
+ * the same io address space mapping.
+ */
+int arm_iommu_attach_device(struct device *dev,
+ struct dma_iommu_mapping *mapping)
+{
+ int err;
+
+ err = iommu_attach_device(mapping->domain, dev);
+ if (err)
+ return err;
+
+ kref_get(&mapping->kref);
+ dev->archdata.mapping = mapping;
+ set_dma_ops(dev, &iommu_ops);
+
+ pr_info("Attached IOMMU controller to %s device.\n", dev_name(dev));
+ return 0;
+}
+
+#endif
/* Ignore report if ErrorRollOver */
if (!(field->flags & HID_MAIN_ITEM_VARIABLE) &&
value[n] >= min && value[n] <= max &&
+ value[n] - min < field->maxusage &&
field->usage[value[n] - min].hid == HID_UP_KEYBOARD + 1)
goto exit;
}
}
if (field->value[n] >= min && field->value[n] <= max
+ && field->value[n] - min < field->maxusage
&& field->usage[field->value[n] - min].hid
&& search(value, field->value[n], count))
hid_process_event(hid, field, &field->usage[field->value[n] - min], 0, interrupt);
if (value[n] >= min && value[n] <= max
+ && value[n] - min < field->maxusage
&& field->usage[value[n] - min].hid
&& search(field->value, value[n], count))
hid_process_event(hid, field, &field->usage[value[n] - min], 1, interrupt);
{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_ELITE_KBD) },
{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_CORDLESS_DESKTOP_LX500) },
{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_EXTREME_3D) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_DUAL_ACTION) },
{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_WHEEL) },
{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_RUMBLEPAD_CORD) },
{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_RUMBLEPAD) },
#define USB_DEVICE_ID_ATEN_2PORTKVM 0x2204
#define USB_DEVICE_ID_ATEN_4PORTKVM 0x2205
#define USB_DEVICE_ID_ATEN_4PORTKVMC 0x2208
+ #define USB_DEVICE_ID_ATEN_CS682 0x2213
+ #define USB_DEVICE_ID_ATEN_CS692 0x8021
#define USB_VENDOR_ID_ATMEL 0x03eb
#define USB_DEVICE_ID_ATMEL_MULTITOUCH 0x211c
#define USB_DEVICE_ID_LOGITECH_RUMBLEPAD_CORD 0xc20a
#define USB_DEVICE_ID_LOGITECH_RUMBLEPAD 0xc211
#define USB_DEVICE_ID_LOGITECH_EXTREME_3D 0xc215
+#define USB_DEVICE_ID_LOGITECH_DUAL_ACTION 0xc216
#define USB_DEVICE_ID_LOGITECH_RUMBLEPAD2 0xc218
#define USB_DEVICE_ID_LOGITECH_RUMBLEPAD2_2 0xc219
#define USB_DEVICE_ID_LOGITECH_WINGMAN_F3D 0xc283
MMC_BLK_ABORT,
MMC_BLK_DATA_ERR,
MMC_BLK_ECC_ERR,
+ MMC_BLK_NOMEDIUM,
};
module_param(perdev_minors, int, 0444);
md = mmc_blk_get(bdev->bd_disk);
if (!md) {
err = -EINVAL;
- goto cmd_done;
+ goto cmd_err;
}
card = md->queue.card;
cmd_done:
mmc_blk_put(md);
+cmd_err:
kfree(idata->buf);
kfree(idata);
return err;
struct mmc_request mrq = {NULL};
struct mmc_command cmd = {0};
struct mmc_data data = {0};
- unsigned int timeout_us;
struct scatterlist sg;
cmd.arg = 0;
cmd.flags = MMC_RSP_SPI_R1 | MMC_RSP_R1 | MMC_CMD_ADTC;
- data.timeout_ns = card->csd.tacc_ns * 100;
- data.timeout_clks = card->csd.tacc_clks * 100;
-
- timeout_us = data.timeout_ns / 1000;
- timeout_us += data.timeout_clks * 1000 /
- (card->host->ios.clock / 1000);
-
- if (timeout_us > 100000) {
- data.timeout_ns = 100000000;
- data.timeout_clks = 0;
- }
-
data.blksz = 4;
data.blocks = 1;
data.flags = MMC_DATA_READ;
data.sg = &sg;
data.sg_len = 1;
+ mmc_set_data_timeout(&data, card);
mrq.cmd = &cmd;
mrq.data = &data;
return err;
}
+#define ERR_NOMEDIUM 3
#define ERR_RETRY 2
#define ERR_ABORT 1
#define ERR_CONTINUE 0
u32 status, stop_status = 0;
int err, retry;
+ if (mmc_card_removed(card))
+ return ERR_NOMEDIUM;
+
/*
* Try to get card status which indicates both the card state
* and why there was no response. If the first attempt fails,
}
/* We couldn't get a response from the card. Give up. */
- if (err)
+ if (err) {
+ /* Check if the card is removed */
+ if (mmc_detect_card_removed(card->host))
+ return ERR_NOMEDIUM;
return ERR_ABORT;
+ }
/* Flag ECC errors */
if ((status & R1_CARD_ECC_FAILED) ||
goto retry;
if (!err)
mmc_blk_reset_success(md, type);
- spin_lock_irq(&md->lock);
- __blk_end_request(req, err, blk_rq_bytes(req));
- spin_unlock_irq(&md->lock);
+ blk_end_request(req, err, blk_rq_bytes(req));
return err ? 0 : 1;
}
if (!err)
mmc_blk_reset_success(md, type);
out:
- spin_lock_irq(&md->lock);
- __blk_end_request(req, err, blk_rq_bytes(req));
- spin_unlock_irq(&md->lock);
+ blk_end_request(req, err, blk_rq_bytes(req));
return err ? 0 : 1;
}
if (ret)
ret = -EIO;
- spin_lock_irq(&md->lock);
- __blk_end_request_all(req, ret);
- spin_unlock_irq(&md->lock);
+ blk_end_request_all(req, ret);
return ret ? 0 : 1;
}
return MMC_BLK_RETRY;
case ERR_ABORT:
return MMC_BLK_ABORT;
+ case ERR_NOMEDIUM:
+ return MMC_BLK_NOMEDIUM;
case ERR_CONTINUE:
break;
}
blocks = mmc_sd_num_wr_blocks(card);
if (blocks != (u32)-1) {
- spin_lock_irq(&md->lock);
- ret = __blk_end_request(req, 0, blocks << 9);
- spin_unlock_irq(&md->lock);
+ ret = blk_end_request(req, 0, blocks << 9);
}
} else {
- spin_lock_irq(&md->lock);
- ret = __blk_end_request(req, 0, brq->data.bytes_xfered);
- spin_unlock_irq(&md->lock);
+ ret = blk_end_request(req, 0, brq->data.bytes_xfered);
}
return ret;
}
* A block was successfully transferred.
*/
mmc_blk_reset_success(md, type);
- spin_lock_irq(&md->lock);
- ret = __blk_end_request(req, 0,
+ ret = blk_end_request(req, 0,
brq->data.bytes_xfered);
- spin_unlock_irq(&md->lock);
/*
* If the blk_end_request function returns non-zero even
* though all data has been transferred and no errors
* time, so we only reach here after trying to
* read a single sector.
*/
- spin_lock_irq(&md->lock);
- ret = __blk_end_request(req, -EIO,
+ ret = blk_end_request(req, -EIO,
brq->data.blksz);
- spin_unlock_irq(&md->lock);
if (!ret)
goto start_new_req;
break;
+ case MMC_BLK_NOMEDIUM:
+ goto cmd_abort;
}
if (ret) {
return 1;
cmd_abort:
- spin_lock_irq(&md->lock);
+ if (mmc_card_removed(card))
+ req->cmd_flags |= REQ_QUIET;
while (ret)
- ret = __blk_end_request(req, -EIO, blk_rq_cur_bytes(req));
- spin_unlock_irq(&md->lock);
+ ret = blk_end_request(req, -EIO, blk_rq_cur_bytes(req));
start_new_req:
if (rqc) {
- mmc_blk_rw_rq_prep(mq->mqrq_cur, card, 0, mq);
- mmc_start_req(card->host, &mq->mqrq_cur->mmc_active, NULL);
+ if (mmc_card_removed(card)) {
+ rqc->cmd_flags |= REQ_QUIET;
+ blk_end_request_all(rqc, -EIO);
+ } else {
+ mmc_blk_rw_rq_prep(mq->mqrq_cur, card, 0, mq);
+ mmc_start_req(card->host,
+ &mq->mqrq_cur->mmc_active, NULL);
+ }
}
return 0;
ret = mmc_blk_part_switch(card, md);
if (ret) {
if (req) {
- spin_lock_irq(&md->lock);
- __blk_end_request_all(req, -EIO);
- spin_unlock_irq(&md->lock);
+ blk_end_request_all(req, -EIO);
}
ret = 0;
goto out;
set_capacity(md->disk, size);
if (mmc_host_cmd23(card->host)) {
- if (mmc_card_mmc(card) ||
+ if ((mmc_card_mmc(card) &&
+ card->csd.mmca_vsn >= CSD_SPEC_VER_3) ||
(mmc_card_sd(card) &&
card->scr.cmds & SD_SCR_CMD23_SUPPORT))
md->flags |= MMC_BLK_CMD23;
}
#ifdef CONFIG_PM
-static int mmc_blk_suspend(struct mmc_card *card, pm_message_t state)
+static int mmc_blk_suspend(struct mmc_card *card)
{
struct mmc_blk_data *part_md;
struct mmc_blk_data *md = mmc_get_drvdata(card);
return err;
}
- if (bytes == 0) {
- err = ubi_wl_flush(ubi, UBI_ALL, UBI_ALL);
- if (err)
- return err;
- err = ubi_wl_flush(ubi);
++ err = ubi_wl_flush(ubi, UBI_ALL, UBI_ALL);
+ if (err)
+ return err;
+ if (bytes == 0) {
err = clear_update_marker(ubi, vol, 0);
if (err)
return err;
dbg_gen("start changing LEB %d:%d, %u bytes",
vol->vol_id, req->lnum, req->bytes);
if (req->bytes == 0)
- return ubi_eba_atomic_leb_change(ubi, vol, req->lnum, NULL, 0,
- req->dtype);
+ return ubi_eba_atomic_leb_change(ubi, vol, req->lnum, NULL, 0);
vol->upd_bytes = req->bytes;
vol->upd_received = 0;
vol->changing_leb = 1;
vol->ch_lnum = req->lnum;
- vol->ch_dtype = req->dtype;
vol->upd_buf = vmalloc(ALIGN((int)req->bytes, ubi->min_io_size));
if (!vol->upd_buf)
return 0;
}
- err = ubi_eba_write_leb(ubi, vol, lnum, buf, 0, len,
- UBI_UNKNOWN);
+ err = ubi_eba_write_leb(ubi, vol, lnum, buf, 0, len);
} else {
/*
* When writing static volume, and this is the last logical
* contain zeros, not random trash.
*/
memset(buf + len, 0, vol->usable_leb_size - len);
- err = ubi_eba_write_leb_st(ubi, vol, lnum, buf, len,
- UBI_UNKNOWN, used_ebs);
+ err = ubi_eba_write_leb_st(ubi, vol, lnum, buf, len, used_ebs);
}
return err;
ubi_assert(vol->upd_received <= vol->upd_bytes);
if (vol->upd_received == vol->upd_bytes) {
- err = ubi_wl_flush(ubi);
+ err = ubi_wl_flush(ubi, UBI_ALL, UBI_ALL);
if (err)
return err;
/* The update is finished, clear the update marker */
len - vol->upd_bytes);
len = ubi_calc_data_len(ubi, vol->upd_buf, len);
err = ubi_eba_atomic_leb_change(ubi, vol, vol->ch_lnum,
- vol->upd_buf, len, UBI_UNKNOWN);
+ vol->upd_buf, len);
if (err)
return err;
}
priv->iv = kmemdup(iv, nr_segs * sizeof(struct iovec),
GFP_KERNEL);
if (!priv->iv) {
+ value = -ENOMEM;
kfree(priv);
goto fail;
}
/* data and/or status stage for control request */
} else if (dev->state == STATE_DEV_SETUP) {
- /* IN DATA+STATUS caller makes len <= wLength */
+ len = min_t(size_t, len, dev->setup_wLength);
if (dev->setup_in) {
retval = setup_req (dev->gadget->ep0, dev->req, len);
if (retval == 0) {
* such as configuration notifications.
*/
- static int is_valid_config (struct usb_config_descriptor *config)
+ static int is_valid_config(struct usb_config_descriptor *config,
+ unsigned int total)
{
return config->bDescriptorType == USB_DT_CONFIG
&& config->bLength == USB_DT_CONFIG_SIZE
+ && total >= USB_DT_CONFIG_SIZE
&& config->bConfigurationValue != 0
&& (config->bmAttributes & USB_CONFIG_ATT_ONE) != 0
&& (config->bmAttributes & USB_CONFIG_ATT_WAKEUP) == 0;
u32 tag;
char *kbuf;
- if (len < (USB_DT_CONFIG_SIZE + USB_DT_DEVICE_SIZE + 4))
+ if ((len < (USB_DT_CONFIG_SIZE + USB_DT_DEVICE_SIZE + 4)) ||
+ (len > PAGE_SIZE * 4))
return -EINVAL;
/* we might need to change message format someday */
/* full or low speed config */
dev->config = (void *) kbuf;
total = le16_to_cpu(dev->config->wTotalLength);
- if (!is_valid_config (dev->config) || total >= length)
+ if (!is_valid_config(dev->config, total) ||
+ total > length - USB_DT_DEVICE_SIZE)
goto fail;
kbuf += total;
length -= total;
if (kbuf [1] == USB_DT_CONFIG) {
dev->hs_config = (void *) kbuf;
total = le16_to_cpu(dev->hs_config->wTotalLength);
- if (!is_valid_config (dev->hs_config) || total >= length)
+ if (!is_valid_config(dev->hs_config, total) ||
+ total > length - USB_DT_DEVICE_SIZE)
goto fail;
kbuf += total;
length -= total;
+ } else {
+ dev->hs_config = NULL;
}
/* could support multiple configs, using another encoding! */
#include <linux/slab.h>
#include <linux/file.h>
#include <linux/fdtable.h>
+ #include <linux/freezer.h>
#include <linux/mm.h>
#include <linux/stat.h>
#include <linux/fcntl.h>
if (write) {
unsigned long size = bprm->vma->vm_end - bprm->vma->vm_start;
+ unsigned long ptr_size;
struct rlimit *rlim;
+ /*
+ * Since the stack will hold pointers to the strings, we
+ * must account for them as well.
+ *
+ * The size calculation is the entire vma while each arg page is
+ * built, so each time we get here it's calculating how far it
+ * is currently (rather than each call being just the newly
+ * added size from the arg page). As a result, we need to
+ * always add the entire size of the pointers, so that on the
+ * last call to get_arg_page() we'll actually have the entire
+ * correct size.
+ */
+ ptr_size = (bprm->argc + bprm->envc) * sizeof(void *);
+ if (ptr_size > ULONG_MAX - size)
+ goto fail;
+ size += ptr_size;
+
acct_arg_size(bprm, size / PAGE_SIZE);
/*
* to work from.
*/
rlim = current->signal->rlim;
- if (size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur) / 4) {
- put_page(page);
- return NULL;
- }
+ if (size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur) / 4)
+ goto fail;
}
return page;
+
+ fail:
+ put_page(page);
+ return NULL;
}
static void put_arg_page(struct page *page)
complete(vfork_done);
}
- if (core_waiters)
+ if (core_waiters > 0) {
+ freezer_do_not_count();
wait_for_completion(&core_state->startup);
+ freezer_count();
+ }
fail:
return core_waiters;
}
fd_install(0, rp);
spin_lock(&cf->file_lock);
fdt = files_fdtable(cf);
- FD_SET(0, fdt->open_fds);
- FD_CLR(0, fdt->close_on_exec);
+ __set_open_fd(0, fdt);
+ __clear_close_on_exec(0, fdt);
spin_unlock(&cf->file_lock);
/* and disallow core files too */
return ret;
}
+#ifdef __arm__
+static void show_arm_map_vma(struct seq_file *m, struct vm_area_struct *vma)
+{
+ static const char *cache_attrs4[4] = { "noC", "WB-WA", "WT-noWA", "WB-noWA" };
+ struct mm_struct *mm = vma->vm_mm;
+ struct file *file = vma->vm_file;
+ vm_flags_t flags = vma->vm_flags;
+ unsigned long start, end, end_b;
+ const char *name = NULL;
+ u32 *arm_pgd;
+ u32 *cpt, *cpt_e;
+ u32 desc1, desc2;
+ u32 tex_cb = 0;
+ u32 prrr, nmrr = 0;
+ u32 control = 0;
+ u32 xn = 1, ap = 0;
+ int desc_type;
+ int type;
+ char buf[64];
+ char rw[4];
+ int len;
+ int s;
+
+ if (mm == NULL)
+ return;
+
+ if (!file) {
+ name = arch_vma_name(vma);
+ if (!name) {
+ if (vma->vm_start <= mm->brk &&
+ vma->vm_end >= mm->start_brk) {
+ name = "[heap]";
+ } else if (vma->vm_start <= mm->start_stack &&
+ vma->vm_end >= mm->start_stack) {
+ name = "[stack]";
+ }
+ }
+ }
+
+ arm_pgd = (u32 *)mm->pgd;
+
+ asm ("mrc p15, 0, %0, c1, c0, 0" : "=r"(control));
+ asm ("mrc p15, 0, %0, c10, c2, 0" : "=r"(prrr)); // primary region RR
+ asm ("mrc p15, 0, %0, c10, c2, 1" : "=r"(nmrr)); // normal memory RR
+
+ start = vma->vm_start;
+ end = vma->vm_end;
+
+ while (start < end) {
+ desc_type = '-';
+
+ desc1 = arm_pgd[start >> 20];
+
+ end_b = (start & ~0xfffff) + 0x100000;
+ for (; end_b < end; end_b += 0x100000)
+ if ((arm_pgd[end_b >> 20] ^ desc1) & 0xfffff)
+ break;
+
+ switch (desc1 & 3) {
+ case 0:
+ sprintf(buf, "l1_fault");
+ goto do_output;
+ case 1:
+ break;
+ case 2:
+ tex_cb = ((desc1 >> 2) & 0x03) | ((desc1 >> 10) & 0x1c);
+ s = (desc1 >> 16) & 1;
+ xn = (desc1 >> 4) & 1;
+ ap = ((desc1 >> 10) & 3) | ((desc1 >> 13) & 4);
+ desc_type = (desc1 & (1 << 18)) ? 's' : 'h';
+ goto do_tex_cb;
+ case 3:
+ sprintf(buf, "reserved");
+ goto do_output;
+ }
+
+ cpt = __va(desc1 & 0xfffffc00);
+ desc2 = cpt[(start >> 12) & 0xff];
+
+ // find end
+ cpt_e = cpt;
+ for (end_b = start + 0x1000; end_b < end; end_b += 0x1000) {
+ if ((end_b & 0x000ff000) == 0) {
+ cpt_e = __va(arm_pgd[end_b >> 20] & 0xfffffc00);
+ if ((arm_pgd[end_b >> 20] ^ desc1) & 0x3ff)
+ break;
+ }
+
+ // assume small pages
+ if ((cpt_e[(end_b >> 12) & 0xff] ^ desc2) & 0xfff)
+ break;
+ }
+
+ switch (desc2 & 3) {
+ case 0:
+ sprintf(buf, "l2_fault");
+ goto do_output;
+ case 1:
+ tex_cb = ((desc2 >> 2) & 0x03) | ((desc2 >> 10) & 0x1c);
+ s = (desc2 >> 10) & 1;
+ xn = (desc2 >> 15) & 1;
+ ap = ((desc2 >> 4) & 3) | ((desc2 >> 7) & 4);
+ break;
+ case 2:
+ case 3:
+ tex_cb = ((desc2 >> 2) & 0x03) | ((desc2 >> 4) & 0x1c);
+ s = (desc2 >> 10) & 1;
+ xn = desc2 & 1;
+ ap = ((desc2 >> 4) & 3) | ((desc2 >> 7) & 4);
+ break;
+ }
+
+do_tex_cb:
+ if (control & (1 << 28)) { // TEX remap
+ // S (shareable) bit remapping
+ char s_normal[2] = { (prrr >> 18) & 1, (prrr >> 19) & 1 };
+ char s_device[2] = { (prrr >> 16) & 1, (prrr >> 17) & 1 };
+
+ buf[0] = 0;
+ tex_cb &= 7;
+ type = (prrr >> tex_cb * 2) & 3;
+ switch (type) {
+ case 0:
+ sprintf(buf, "strongly-ordered");
+ break;
+ case 1:
+ sprintf(buf, "device");
+ s = s_device[s];
+ break;
+ case 3:
+ sprintf(buf, "reserved/normal");
+ case 2:
+ s = s_normal[s];
+ sprintf(buf + strlen(buf), "inner-%s-outer-%s",
+ cache_attrs4[(nmrr >> tex_cb * 2) & 3],
+ cache_attrs4[(nmrr >> (tex_cb * 2 + 16)) & 3]);
+ }
+ }
+ else if (tex_cb & 0x10) { // TEX[2] set
+ sprintf(buf, "inner-%s-outer-%s",
+ cache_attrs4[tex_cb & 3], cache_attrs4[(tex_cb >> 2) & 3]);
+ }
+ else {
+ switch (tex_cb) {
+ case 0x00: sprintf(buf, "strongly-ordered"); s = 1; break;
+ case 0x01: sprintf(buf, "shareable-device"); s = 1; break;
+ case 0x02: sprintf(buf, "inner-outer-WT-noWA"); break;
+ case 0x03: sprintf(buf, "inner-outer-WB-noWA"); break;
+ case 0x04: sprintf(buf, "inner-outer-non-cacheable"); break;
+ case 0x06: sprintf(buf, "implementation-defined"); break;
+ case 0x07: sprintf(buf, "inner-outer-WB-WA"); break;
+ case 0x08: sprintf(buf, "non-shareable-device"); s = 0; break;
+ default: sprintf(buf, "reserved"); break;
+ }
+ }
+
+ if (s)
+ sprintf(buf + strlen(buf), "-shareable");
+
+do_output:
+ // use user permissions here
+ if (control & (1 << 29)) // AFE
+ sprintf(rw, "%c%c", (ap & 2) ? 'r' : '-',
+ ((ap & 2) && !(ap & 4)) ? 'w' : '-');
+ else
+ sprintf(rw, "%c%c", (ap & 2) ? 'r' : '-',
+ (ap == 3) ? 'w' : '-');
+
+ seq_printf(m, "%08lx-%08lx %s%c%c%c %-28s %n",
+ start, end_b,
+ rw,
+ xn ? '-' : 'x',
+ flags & VM_MAYSHARE ? 's' : 'p',
+ desc_type,
+ buf, &len);
+
+ if (file) {
+ pad_len_spaces(m, len);
+ seq_path(m, &file->f_path, "\n");
+ } else if (name) {
+ pad_len_spaces(m, len);
+ seq_puts(m, name);
+ }
+ seq_putc(m, '\n');
+
+ start = end_b;
+ }
+}
+#endif
+
static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
{
struct mm_struct *mm = vma->vm_mm;
/* We don't show the stack guard page in /proc/maps */
start = vma->vm_start;
- if (stack_guard_page_start(vma, start))
- start += PAGE_SIZE;
end = vma->vm_end;
- if (stack_guard_page_end(vma, end))
- end -= PAGE_SIZE;
seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu %n",
start,
.release = seq_release_private,
};
+#ifdef __arm__
+static int show_armv7_map(struct seq_file *m, void *v)
+{
+ struct vm_area_struct *vma = v;
+ struct proc_maps_private *priv = m->private;
+ struct task_struct *task = priv->task;
+
+ show_arm_map_vma(m, vma);
+
+ if (m->count < m->size) /* vma is copied successfully */
+ m->version = (vma != get_gate_vma(task->mm))
+ ? vma->vm_start : 0;
+ return 0;
+}
+
+static const struct seq_operations proc_pid_armv7_maps_op = {
+ .start = m_start,
+ .next = m_next,
+ .stop = m_stop,
+ .show = show_armv7_map
+};
+#endif
+
+static int armv7_maps_open(struct inode *inode, struct file *file)
+{
+ return do_maps_open(inode, file, &proc_pid_armv7_maps_op);
+}
+
+const struct file_operations proc_armv7_maps_operations = {
+ .open = armv7_maps_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_private,
+};
+
/*
* Proportional Set Size(PSS): my share of RSS.
*
buf->len = spd->partial[page_nr].len;
buf->private = spd->partial[page_nr].private;
buf->ops = spd->ops;
+ buf->flags = 0;
if (spd->flags & SPLICE_F_GIFT)
buf->flags |= PIPE_BUF_FLAG_GIFT;
/*
* Attempt to initiate a splice from pipe to file.
*/
-static long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
- loff_t *ppos, size_t len, unsigned int flags)
+long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
+ loff_t *ppos, size_t len, unsigned int flags)
{
ssize_t (*splice_write)(struct pipe_inode_info *, struct file *,
loff_t *, size_t, unsigned int);
return splice_write(pipe, out, ppos, len, flags);
}
+EXPORT_SYMBOL(do_splice_from);
/*
* Attempt to initiate a splice from a file to a pipe.
*/
-static long do_splice_to(struct file *in, loff_t *ppos,
- struct pipe_inode_info *pipe, size_t len,
- unsigned int flags)
+long do_splice_to(struct file *in, loff_t *ppos,
+ struct pipe_inode_info *pipe, size_t len,
+ unsigned int flags)
{
ssize_t (*splice_read)(struct file *, loff_t *,
struct pipe_inode_info *, size_t, unsigned int);
return splice_read(in, ppos, pipe, len, flags);
}
+EXPORT_SYMBOL(do_splice_to);
/**
* splice_direct_to_actor - splices data directly between two non-pipes
return inode;
}
-#ifdef CONFIG_UBIFS_FS_DEBUG
-
static int dbg_check_name(const struct ubifs_info *c,
const struct ubifs_dent_node *dent,
const struct qstr *nm)
return 0;
}
-#else
-
-#define dbg_check_name(c, dent, nm) 0
-
-#endif
-
static struct dentry *ubifs_lookup(struct inode *dir, struct dentry *dentry,
struct nameidata *nd)
{
*/
static int ubifs_readdir(struct file *file, void *dirent, filldir_t filldir)
{
- int err, over = 0;
+ int err = 0, over = 0;
loff_t pos = file->f_pos;
struct qstr nm;
union ubifs_key key;
}
out:
- if (err != -ENOENT) {
+ if (err != -ENOENT)
ubifs_err("cannot find next direntry, error %d", err);
- return err;
- }
+ else
+ /*
+ * -ENOENT is a non-fatal error in this context, the TNC uses
+ * it to indicate that the cursor moved past the current directory
+ * and readdir() has to stop.
+ */
+ err = 0;
+
kfree(file->private_data);
file->private_data = NULL;
/* 2 is a special value indicating that there are no more direntries */
file->f_pos = 2;
- return 0;
+ return err;
}
static loff_t ubifs_dir_llseek(struct file *file, loff_t offset, int origin)
int sz_change = CALC_DENT_SIZE(dentry->d_name.len);
int err, budgeted = 1;
struct ubifs_budget_req req = { .mod_dent = 1, .dirtied_ino = 2 };
+ unsigned int saved_nlink = inode->i_nlink;
/*
* Budget request settings: deletion direntry, deletion inode (+1 for
out_cancel:
dir->i_size += sz_change;
dir_ui->ui_size = dir->i_size;
- inc_nlink(inode);
+ set_nlink(inode, saved_nlink);
unlock_2_inodes(dir, inode);
if (budgeted)
ubifs_release_budget(c, &req);
dir->i_size += sz_change;
dir_ui->ui_size = dir->i_size;
inc_nlink(dir);
- inc_nlink(inode);
- inc_nlink(inode);
+ set_nlink(inode, 2);
unlock_2_inodes(dir, inode);
if (budgeted)
ubifs_release_budget(c, &req);
struct ubifs_budget_req ino_req = { .dirtied_ino = 1,
.dirtied_ino_d = ALIGN(old_inode_ui->data_len, 8) };
struct timespec time;
+ unsigned int uninitialized_var(saved_nlink);
/*
* Budget request settings: deletion direntry, new direntry, removing
* separately.
*/
- dbg_gen("dent '%.*s' ino %lu in dir ino %lu to dent '%.*s' in "
- "dir ino %lu", old_dentry->d_name.len, old_dentry->d_name.name,
+ dbg_gen("dent '%.*s' ino %lu in dir ino %lu to dent '%.*s' in dir ino %lu",
+ old_dentry->d_name.len, old_dentry->d_name.name,
old_inode->i_ino, old_dir->i_ino, new_dentry->d_name.len,
new_dentry->d_name.name, new_dir->i_ino);
ubifs_assert(mutex_is_locked(&old_dir->i_mutex));
if (unlink) {
/*
* Directories cannot have hard-links, so if this is a
- * directory, decrement its @i_nlink twice because an empty
- * directory has @i_nlink 2.
+ * directory, just clear @i_nlink.
*/
+ saved_nlink = new_inode->i_nlink;
if (is_dir)
+ clear_nlink(new_inode);
+ else
drop_nlink(new_inode);
new_inode->i_ctime = time;
- drop_nlink(new_inode);
} else {
new_dir->i_size += new_sz;
ubifs_inode(new_dir)->ui_size = new_dir->i_size;
out_cancel:
if (unlink) {
- if (is_dir)
- inc_nlink(new_inode);
- inc_nlink(new_inode);
+ set_nlink(new_inode, saved_nlink);
} else {
new_dir->i_size -= new_sz;
ubifs_inode(new_dir)->ui_size = new_dir->i_size;
.rename = ubifs_rename,
.setattr = ubifs_setattr,
.getattr = ubifs_getattr,
-#ifdef CONFIG_UBIFS_FS_XATTR
.setxattr = ubifs_setxattr,
.getxattr = ubifs_getxattr,
.listxattr = ubifs_listxattr,
.removexattr = ubifs_removexattr,
-#endif
};
const struct file_operations ubifs_dir_operations = {
#include <linux/slab.h>
#include "ubifs.h"
+ static int try_read_node(const struct ubifs_info *c, void *buf, int type,
+ int len, int lnum, int offs);
+ static int fallible_read_node(struct ubifs_info *c, const union ubifs_key *key,
+ struct ubifs_zbranch *zbr, void *node);
+
/*
* Returned codes of 'matches_name()' and 'fallible_matches_name()' functions.
* @NAME_LESS: name corresponding to the first argument is less than second
err = ubifs_validate_entry(c, dent);
if (err) {
- dbg_dump_stack();
- dbg_dump_node(c, dent);
+ dump_stack();
+ ubifs_dump_node(c, dent);
return err;
}
- lnc_node = kmalloc(zbr->len, GFP_NOFS);
+ lnc_node = kmemdup(node, zbr->len, GFP_NOFS);
if (!lnc_node)
/* We don't have to have the cache, so no error */
return 0;
- memcpy(lnc_node, node, zbr->len);
zbr->leaf = lnc_node;
return 0;
}
err = ubifs_validate_entry(c, node);
if (err) {
- dbg_dump_stack();
- dbg_dump_node(c, node);
+ dump_stack();
+ ubifs_dump_node(c, node);
return err;
}
return 0;
}
- err = ubifs_tnc_read_node(c, zbr, node);
+ if (c->replaying) {
+ err = fallible_read_node(c, &zbr->key, zbr, node);
+ /*
+ * When the node was not found, return -ENOENT, 0 otherwise.
+ * Negative return codes stay as-is.
+ */
+ if (err == 0)
+ err = -ENOENT;
+ else if (err == 1)
+ err = 0;
+ } else {
+ err = ubifs_tnc_read_node(c, zbr, node);
+ }
if (err)
return err;
{
int ret;
- dbg_tnc("LEB %d:%d, key %s", zbr->lnum, zbr->offs, DBGKEY(key));
+ dbg_tnck(key, "LEB %d:%d, key ", zbr->lnum, zbr->offs);
ret = try_read_node(c, node, key_type(c, key), zbr->len, zbr->lnum,
zbr->offs);
ret = 0;
}
if (ret == 0 && c->replaying)
- dbg_mnt("dangling branch LEB %d:%d len %d, key %s",
- zbr->lnum, zbr->offs, zbr->len, DBGKEY(key));
+ dbg_mntk(key, "dangling branch LEB %d:%d len %d, key ",
+ zbr->lnum, zbr->offs, zbr->len);
return ret;
}
if (adding || !o_znode)
return 0;
- dbg_mnt("dangling match LEB %d:%d len %d %s",
+ dbg_mntk(key, "dangling match LEB %d:%d len %d key ",
o_znode->zbranch[o_n].lnum, o_znode->zbranch[o_n].offs,
- o_znode->zbranch[o_n].len, DBGKEY(key));
+ o_znode->zbranch[o_n].len);
*zn = o_znode;
*n = o_n;
return 1;
struct ubifs_znode *znode;
unsigned long time = get_seconds();
- dbg_tnc("search key %s", DBGKEY(key));
+ dbg_tnck(key, "search key ");
ubifs_assert(key_type(c, key) < UBIFS_INVALID_KEY);
znode = c->zroot.znode;
struct ubifs_znode *znode;
unsigned long time = get_seconds();
- dbg_tnc("search and dirty key %s", DBGKEY(key));
+ dbg_tnck(key, "search and dirty key ");
znode = c->zroot.znode;
if (unlikely(!znode)) {
if (!keys_eq(c, &zbr->key, &key1)) {
ubifs_err("bad key in node at LEB %d:%d",
zbr->lnum, zbr->offs);
- dbg_tnc("looked for key %s found node's key %s",
- DBGKEY(&zbr->key), DBGKEY1(&key1));
+ dbg_tnck(&zbr->key, "looked for key ");
+ dbg_tnck(&key1, "found node's key ");
goto out_err;
}
err = -EINVAL;
out:
ubifs_err("bad node at LEB %d:%d", zbr->lnum, zbr->offs);
- dbg_dump_node(c, buf);
- dbg_dump_stack();
+ ubifs_dump_node(c, buf);
+ dump_stack();
return err;
}
if (err && err != -EBADMSG) {
ubifs_err("failed to read from LEB %d:%d, error %d",
lnum, offs, err);
- dbg_dump_stack();
- dbg_tnc("key %s", DBGKEY(&bu->key));
+ dump_stack();
+ dbg_tnck(&bu->key, "key ");
return err;
}
int found, n, err;
struct ubifs_znode *znode;
- dbg_tnc("name '%.*s' key %s", nm->len, nm->name, DBGKEY(key));
+ dbg_tnck(key, "name '%.*s' key ", nm->len, nm->name);
mutex_lock(&c->tnc_mutex);
found = ubifs_lookup_level0(c, key, &znode, &n);
if (!found) {
zp = znode->parent;
if (znode->child_cnt < c->fanout) {
ubifs_assert(n != c->fanout);
- dbg_tnc("inserted at %d level %d, key %s", n, znode->level,
- DBGKEY(key));
+ dbg_tnck(key, "inserted at %d level %d, key ", n, znode->level);
insert_zbranch(znode, zbr, n);
* Unfortunately, @znode does not have more empty slots and we have to
* split it.
*/
- dbg_tnc("splitting level %d, key %s", znode->level, DBGKEY(key));
+ dbg_tnck(key, "splitting level %d, key ", znode->level);
if (znode->alt)
/*
}
/* Insert new key and branch */
- dbg_tnc("inserting at %d level %d, key %s", n, zn->level, DBGKEY(key));
+ dbg_tnck(key, "inserting at %d level %d, key ", n, zn->level);
insert_zbranch(zi, zbr, n);
struct ubifs_znode *znode;
mutex_lock(&c->tnc_mutex);
- dbg_tnc("%d:%d, len %d, key %s", lnum, offs, len, DBGKEY(key));
+ dbg_tnck(key, "%d:%d, len %d, key ", lnum, offs, len);
found = lookup_level0_dirty(c, key, &znode, &n);
if (!found) {
struct ubifs_zbranch zbr;
struct ubifs_znode *znode;
mutex_lock(&c->tnc_mutex);
- dbg_tnc("old LEB %d:%d, new LEB %d:%d, len %d, key %s", old_lnum,
- old_offs, lnum, offs, len, DBGKEY(key));
+ dbg_tnck(key, "old LEB %d:%d, new LEB %d:%d, len %d, key ", old_lnum,
+ old_offs, lnum, offs, len);
found = lookup_level0_dirty(c, key, &znode, &n);
if (found < 0) {
err = found;
struct ubifs_znode *znode;
mutex_lock(&c->tnc_mutex);
- dbg_tnc("LEB %d:%d, name '%.*s', key %s", lnum, offs, nm->len, nm->name,
- DBGKEY(key));
+ dbg_tnck(key, "LEB %d:%d, name '%.*s', key ",
+ lnum, offs, nm->len, nm->name);
found = lookup_level0_dirty(c, key, &znode, &n);
if (found < 0) {
err = found;
/* Delete without merge for now */
ubifs_assert(znode->level == 0);
ubifs_assert(n >= 0 && n < c->fanout);
- dbg_tnc("deleting %s", DBGKEY(&znode->zbranch[n].key));
+ dbg_tnck(&znode->zbranch[n].key, "deleting key ");
zbr = &znode->zbranch[n];
lnc_free(zbr);
err = ubifs_add_dirt(c, zbr->lnum, zbr->len);
if (err) {
- dbg_dump_znode(c, znode);
+ ubifs_dump_znode(c, znode);
return err;
}
struct ubifs_znode *znode;
mutex_lock(&c->tnc_mutex);
- dbg_tnc("key %s", DBGKEY(key));
+ dbg_tnck(key, "key ");
found = lookup_level0_dirty(c, key, &znode, &n);
if (found < 0) {
err = found;
struct ubifs_znode *znode;
mutex_lock(&c->tnc_mutex);
- dbg_tnc("%.*s, key %s", nm->len, nm->name, DBGKEY(key));
+ dbg_tnck(key, "%.*s, key ", nm->len, nm->name);
err = lookup_level0_dirty(c, key, &znode, &n);
if (err < 0)
goto out_unlock;
err = ubifs_add_dirt(c, znode->zbranch[i].lnum,
znode->zbranch[i].len);
if (err) {
- dbg_dump_znode(c, znode);
+ ubifs_dump_znode(c, znode);
goto out_unlock;
}
- dbg_tnc("removing %s", DBGKEY(key));
+ dbg_tnck(key, "removing key ");
}
if (k) {
for (i = n + 1 + k; i < znode->child_cnt; i++)
struct ubifs_zbranch *zbr;
union ubifs_key *dkey;
- dbg_tnc("%s %s", nm->name ? (char *)nm->name : "(lowest)", DBGKEY(key));
+ dbg_tnck(key, "%s ", nm->name ? (char *)nm->name : "(lowest)");
ubifs_assert(is_hash_key(c, key));
mutex_lock(&c->tnc_mutex);
if (nm->name) {
if (err) {
/* Handle collisions */
- err = resolve_collision(c, key, &znode, &n, nm);
+ if (c->replaying)
+ err = fallible_resolve_collision(c, key, &znode, &n,
+ nm, 0);
+ else
+ err = resolve_collision(c, key, &znode, &n, nm);
dbg_tnc("rc returned %d, znode %p, n %d",
err, znode, n);
if (unlikely(err < 0))
return err;
}
-#ifdef CONFIG_UBIFS_FS_DEBUG
-
/**
* dbg_check_inode_size - check if inode size is correct.
* @c: UBIFS file-system description object
out_dump:
block = key_block(c, key);
- ubifs_err("inode %lu has size %lld, but there are data at offset %lld "
- "(data key %s)", (unsigned long)inode->i_ino, size,
- ((loff_t)block) << UBIFS_BLOCK_SHIFT, DBGKEY(key));
+ ubifs_err("inode %lu has size %lld, but there are data at offset %lld",
+ (unsigned long)inode->i_ino, size,
+ ((loff_t)block) << UBIFS_BLOCK_SHIFT);
mutex_unlock(&c->tnc_mutex);
- dbg_dump_inode(c, inode);
- dbg_dump_stack();
+ ubifs_dump_inode(c, inode);
+ dump_stack();
return -EINVAL;
out_unlock:
mutex_unlock(&c->tnc_mutex);
return err;
}
-
-#endif /* CONFIG_UBIFS_FS_DEBUG */
ui = ubifs_inode(inode);
ui->xattr = 1;
ui->flags |= UBIFS_XATTR_FL;
- ui->data = kmalloc(size, GFP_NOFS);
+ ui->data = kmemdup(value, size, GFP_NOFS);
if (!ui->data) {
err = -ENOMEM;
goto out_free;
}
- memcpy(ui->data, value, size);
inode->i_size = ui->ui_size = size;
ui->data_len = size;
host_ui->xattr_cnt -= 1;
host_ui->xattr_size -= CALC_DENT_SIZE(nm->len);
host_ui->xattr_size -= CALC_XATTR_BYTES(size);
+ host_ui->xattr_names -= nm->len;
mutex_unlock(&host_ui->ui_mutex);
out_free:
make_bad_inode(inode);
return err;
kfree(ui->data);
- ui->data = kmalloc(size, GFP_NOFS);
+ ui->data = kmemdup(value, size, GFP_NOFS);
if (!ui->data) {
err = -ENOMEM;
goto out_free;
}
- memcpy(ui->data, value, size);
inode->i_size = ui->ui_size = size;
ui->data_len = size;
if (buf) {
/* If @buf is %NULL we are supposed to return the length */
if (ui->data_len > size) {
- dbg_err("buffer size %zd, xattr len %d",
- size, ui->data_len);
+ ubifs_err("buffer size %zd, xattr len %d",
+ size, ui->data_len);
err = -ERANGE;
goto out_iput;
}
host_ui->xattr_cnt += 1;
host_ui->xattr_size += CALC_DENT_SIZE(nm->len);
host_ui->xattr_size += CALC_XATTR_BYTES(ui->data_len);
+ host_ui->xattr_names += nm->len;
mutex_unlock(&host_ui->ui_mutex);
ubifs_release_budget(c, &req);
make_bad_inode(inode);
int set_page_dirty_lock(struct page *page);
int clear_page_dirty_for_io(struct page *page);
- /* Is the vma a continuation of the stack vma above it? */
- static inline int vma_growsdown(struct vm_area_struct *vma, unsigned long addr)
- {
- return vma && (vma->vm_end == addr) && (vma->vm_flags & VM_GROWSDOWN);
- }
-
- static inline int stack_guard_page_start(struct vm_area_struct *vma,
- unsigned long addr)
- {
- return (vma->vm_flags & VM_GROWSDOWN) &&
- (vma->vm_start == addr) &&
- !vma_growsdown(vma->vm_prev, addr);
- }
-
- /* Is the vma a continuation of the stack vma below it? */
- static inline int vma_growsup(struct vm_area_struct *vma, unsigned long addr)
- {
- return vma && (vma->vm_start == addr) && (vma->vm_flags & VM_GROWSUP);
- }
-
- static inline int stack_guard_page_end(struct vm_area_struct *vma,
- unsigned long addr)
- {
- return (vma->vm_flags & VM_GROWSUP) &&
- (vma->vm_end == addr) &&
- !vma_growsup(vma->vm_next, addr);
- }
-
extern unsigned long move_page_tables(struct vm_area_struct *vma,
unsigned long old_addr, struct vm_area_struct *new_vma,
unsigned long new_addr, unsigned long len);
struct address_space *mapping,
struct file *filp);
+ extern unsigned long stack_guard_gap;
/* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */
extern int expand_stack(struct vm_area_struct *vma, unsigned long address);
return vma;
}
+ static inline unsigned long vm_start_gap(struct vm_area_struct *vma)
+ {
+ unsigned long vm_start = vma->vm_start;
+
+ if (vma->vm_flags & VM_GROWSDOWN) {
+ vm_start -= stack_guard_gap;
+ if (vm_start > vma->vm_start)
+ vm_start = 0;
+ }
+ return vm_start;
+ }
+
+ static inline unsigned long vm_end_gap(struct vm_area_struct *vma)
+ {
+ unsigned long vm_end = vma->vm_end;
+
+ if (vma->vm_flags & VM_GROWSUP) {
+ vm_end += stack_guard_gap;
+ if (vm_end < vma->vm_end)
+ vm_end = -PAGE_SIZE;
+ }
+ return vm_end;
+ }
+
static inline unsigned long vma_pages(struct vm_area_struct *vma)
{
return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
unsigned int pages_per_huge_page);
#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */
+#ifdef CONFIG_DEBUG_PAGEALLOC
+extern unsigned int _debug_guardpage_minorder;
+
+static inline unsigned int debug_guardpage_minorder(void)
+{
+ return _debug_guardpage_minorder;
+}
+
+static inline bool page_is_guard(struct page *page)
+{
+ return test_bit(PAGE_DEBUG_FLAG_GUARD, &page->debug_flags);
+}
+#else
+static inline unsigned int debug_guardpage_minorder(void) { return 0; }
+static inline bool page_is_guard(struct page *page) { return false; }
+#endif /* CONFIG_DEBUG_PAGEALLOC */
+
#endif /* __KERNEL__ */
#endif /* _LINUX_MM_H */
struct rq *this_rq = this_rq();
/*
- * If we're still before the sample window, we're done.
+ * If we're still before the pending sample window, we're done.
*/
+ this_rq->calc_load_update = calc_load_update;
if (time_before(jiffies, this_rq->calc_load_update))
return;
* accounted through the nohz accounting, so skip the entire deal and
* sync up for the next window.
*/
- this_rq->calc_load_update = calc_load_update;
if (time_before(jiffies, this_rq->calc_load_update + 10))
this_rq->calc_load_update += LOAD_FREQ;
}
return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) ||
capable(CAP_SYS_NICE));
}
+EXPORT_SYMBOL_GPL(can_nice);
#ifdef __ARCH_WANT_SYS_NICE
#ifdef CONFIG_CGROUP_SCHED
list_add(&root_task_group.list, &task_groups);
INIT_LIST_HEAD(&root_task_group.children);
+ INIT_LIST_HEAD(&root_task_group.siblings);
autogroup_init(&init_task);
#endif /* CONFIG_CGROUP_SCHED */
arch_spin_lock(&trace_cmdline_lock);
map = map_pid_to_cmdline[pid];
if (map != NO_CMDLINE_MAP)
- strcpy(comm, saved_cmdlines[map]);
+ strlcpy(comm, saved_cmdlines[map], TASK_COMM_LEN);
else
strcpy(comm, "<...>");
};
struct dentry *trace_create_file(const char *name,
- mode_t mode,
+ umode_t mode,
struct dentry *parent,
void *data,
const struct file_operations *fops)
static struct hlist_head *mm_slots_hash __read_mostly;
static struct kmem_cache *mm_slot_cache __read_mostly;
+#ifdef CONFIG_FB
+extern const struct file_operations fb_fops;
+
+#define is_fb_vma(vma) \
+ (vma->vm_file && vma->vm_file->f_op == &fb_fops)
+#else
+#define is_fb_vma(vma) 0
+#endif
+
+static void split_fb_pmd(struct vm_area_struct *vma, pmd_t *pmd);
+
/**
* struct mm_slot - hash lookup from mm to mm_slot
* @hash: hash collision list
* where the extra memory used could hurt more than TLB overhead
* is likely to save. The admin can still enable it through /sys.
*/
- if (totalram_pages < (512 << (20 - PAGE_SHIFT)))
+ if (totalram_pages < (200 << (20 - PAGE_SHIFT)))
transparent_hugepage_flags = 0;
start_khugepaged();
return pgtable;
}
+void huge_pmd_set_accessed(struct mm_struct *mm,
+ struct vm_area_struct *vma,
+ unsigned long address,
+ pmd_t *pmd, pmd_t orig_pmd,
+ int dirty)
+{
+ pmd_t entry;
+ unsigned long haddr;
+
+ spin_lock(&mm->page_table_lock);
+ if (unlikely(!pmd_same(*pmd, orig_pmd)))
+ goto unlock;
+
+ entry = pmd_mkyoung(orig_pmd);
+ haddr = address & HPAGE_PMD_MASK;
+ if (pmdp_set_access_flags(vma, haddr, pmd, entry, dirty))
+ update_mmu_cache_pmd(vma, address, pmd);
+
+unlock:
+ spin_unlock(&mm->page_table_lock);
+}
+
static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
struct vm_area_struct *vma,
unsigned long address,
entry = pmd_mkyoung(orig_pmd);
entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
if (pmdp_set_access_flags(vma, haddr, pmd, entry, 1))
- update_mmu_cache(vma, address, entry);
+ update_mmu_cache(vma, address, pmd);
ret |= VM_FAULT_WRITE;
goto out_unlock;
}
pmdp_clear_flush_notify(vma, haddr, pmd);
page_add_new_anon_rmap(new_page, vma, haddr);
set_pmd_at(mm, haddr, pmd, entry);
- update_mmu_cache(vma, address, entry);
+ update_mmu_cache(vma, address, pmd);
page_remove_rmap(page);
put_page(page);
ret |= VM_FAULT_WRITE;
return ret;
}
+ /*
+ * FOLL_FORCE can write to even unwritable pmd's, but only
+ * after we've gone through a COW cycle and they are dirty.
+ */
+ static inline bool can_follow_write_pmd(pmd_t pmd, struct page *page,
+ unsigned int flags)
+ {
+ return pmd_write(pmd) ||
+ ((flags & FOLL_FORCE) && (flags & FOLL_COW) &&
+ page && PageAnon(page));
+ }
+
struct page *follow_trans_huge_pmd(struct mm_struct *mm,
unsigned long addr,
pmd_t *pmd,
assert_spin_locked(&mm->page_table_lock);
- if (flags & FOLL_WRITE && !pmd_write(*pmd))
- goto out;
-
page = pmd_page(*pmd);
VM_BUG_ON(!PageHead(page));
+
+ if (flags & FOLL_WRITE && !can_follow_write_pmd(*pmd, page, flags))
+ return NULL;
+
if (flags & FOLL_TOUCH) {
pmd_t _pmd;
/*
spin_lock(&tlb->mm->page_table_lock);
if (likely(pmd_trans_huge(*pmd))) {
+ if (is_fb_vma(vma)) {
+ split_fb_pmd(vma, pmd);
+ return 0;
+ }
+
if (unlikely(pmd_trans_splitting(*pmd))) {
spin_unlock(&tlb->mm->page_table_lock);
wait_split_huge_page(vma->anon_vma,
return ret;
}
+/* callers must hold mmap_sem (madvise() does) */
+static int collapse_fb_pmd(struct mm_struct *mm, pmd_t *pmd,
+ unsigned long addr, struct vm_area_struct *vma)
+{
+ unsigned long _addr;
+ struct page *page;
+ pgtable_t pgtable;
+ pte_t *pte, *_pte;
+ pmd_t _pmd;
+ u32 pa;
+
+ pte = pte_offset_map(pmd, addr);
+ page = pte_page(*pte);
+ pa = __pfn_to_phys(page_to_pfn(page));
+ _pmd = pmdp_clear_flush_notify(vma, addr, pmd);
+
+ if ((addr | pa) & ~HPAGE_PMD_MASK) {
+ printk(KERN_ERR "collapse_fb: bad alignment: %08lx->%08x\n",
+ addr, pa);
+ pte_unmap(pte);
+ return -EINVAL;
+ }
+
+ for (_pte = pte, _addr = addr; _pte < pte + HPAGE_PMD_NR; _pte++) {
+ pte_t pteval = *_pte;
+ struct page *src_page;
+
+ if (!pte_none(pteval)) {
+ src_page = pte_page(pteval);
+
+ pte_clear(vma->vm_mm, _addr, _pte);
+ if (pte_present(pteval))
+ page_remove_rmap(src_page);
+ }
+
+ _addr += PAGE_SIZE;
+ }
+
+ pte_unmap(pte);
+ pgtable = pmd_pgtable(_pmd);
+ VM_BUG_ON(page_count(pgtable) != 1);
+ VM_BUG_ON(page_mapcount(pgtable) != 0);
+
+ _pmd = mk_pmd(page, vma->vm_page_prot);
+ _pmd = maybe_pmd_mkwrite(pmd_mkdirty(_pmd), vma);
+ _pmd = pmd_mkhuge(_pmd);
+
+ smp_wmb();
+
+ spin_lock(&mm->page_table_lock);
+ BUG_ON(!pmd_none(*pmd));
+ set_pmd_at(mm, addr, pmd, _pmd);
+ update_mmu_cache(vma, addr, pmd);
+ prepare_pmd_huge_pte(pgtable, mm);
+ spin_unlock(&mm->page_table_lock);
+
+ return 0;
+}
+
+static int try_collapse_fb(struct vm_area_struct *vma)
+{
+ struct mm_struct *mm = vma->vm_mm;
+ unsigned long hstart, hend, addr;
+ int ret = 0;
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+
+ hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
+ hend = vma->vm_end & HPAGE_PMD_MASK;
+ if (hstart >= hend)
+ return -EINVAL;
+
+ for (addr = hstart; addr < hend; addr += HPAGE_PMD_SIZE) {
+ pgd = pgd_offset(mm, addr);
+ if (!pgd_present(*pgd))
+ return -EINVAL;
+
+ pud = pud_offset(pgd, addr);
+ if (!pud_present(*pud))
+ return -EINVAL;
+
+ pmd = pmd_offset(pud, addr);
+ if (!pmd_present(*pmd))
+ return -EINVAL;
+ if (pmd_trans_huge(*pmd))
+ continue;
+
+ ret = collapse_fb_pmd(mm, pmd, addr, vma);
+ if (ret)
+ break;
+ }
+
+ return ret;
+}
+
+/* undo collapse_fb_pmd(), restore pages so that mm subsys can release them
+ * page_table_lock() should be held */
+static void split_fb_pmd(struct vm_area_struct *vma, pmd_t *pmd)
+{
+ struct mm_struct *mm = vma->vm_mm;
+ unsigned long addr, haddr, pfn;
+ struct page *page;
+ pgtable_t pgtable;
+ pmd_t _pmd;
+ int i;
+
+ page = pmd_page(*pmd);
+ pgtable = get_pmd_huge_pte(mm);
+ pfn = page_to_pfn(page);
+ addr = pfn << PAGE_SHIFT;
+
+ pmd_populate(mm, &_pmd, pgtable);
+
+ for (i = 0, haddr = addr; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
+ pte_t *pte, entry;
+ BUG_ON(PageCompound(page + i));
+ entry = mk_pte(page + i, vma->vm_page_prot);
+ entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+ if (!pmd_young(*pmd))
+ entry = pte_mkold(entry);
+ atomic_set(&page[i]._mapcount, 0); // hack?
+ pte = pte_offset_map(&_pmd, haddr);
+ BUG_ON(!pte_none(*pte));
+ set_pte_at(mm, haddr, pte, entry);
+ pte_unmap(pte);
+ }
+
+ set_pmd_at(mm, addr, pmd, pmd_mknotpresent(*pmd));
+ flush_tlb_range(vma, addr, addr + HPAGE_PMD_SIZE);
+ pmd_populate(mm, pmd, pgtable);
+}
+
+#ifndef __arm__
+#error arm only..
+#endif
+static u32 pmd_to_va(struct mm_struct *mm, pmd_t *pmd)
+{
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd0;
+ u32 ret;
+
+ pgd = pgd_offset(mm, 0);
+ pud = pud_offset(pgd, 0);
+ pmd0 = pmd_offset(pud, 0);
+
+ ret = (pmd - pmd0) << SECTION_SHIFT;
+ return ret;
+}
+
#define VM_NO_THP (VM_SPECIAL|VM_INSERTPAGE|VM_MIXEDMAP|VM_SAO| \
VM_HUGETLB|VM_SHARED|VM_MAYSHARE)
{
switch (advice) {
case MADV_HUGEPAGE:
+ if (is_fb_vma(vma))
+ return try_collapse_fb(vma);
+
/*
* Be somewhat over-protective like KSM for now!
*/
BUG_ON(!pmd_none(*pmd));
page_add_new_anon_rmap(new_page, vma, address);
set_pmd_at(mm, address, pmd, _pmd);
- update_mmu_cache(vma, address, _pmd);
+ update_mmu_cache(vma, address, pmd);
prepare_pmd_huge_pte(pgtable, mm);
spin_unlock(&mm->page_table_lock);
void __split_huge_page_pmd(struct mm_struct *mm, pmd_t *pmd)
{
+ struct vm_area_struct *vma;
struct page *page;
spin_lock(&mm->page_table_lock);
spin_unlock(&mm->page_table_lock);
return;
}
+ vma = find_vma(mm, pmd_to_va(mm, pmd));
+ if (vma && is_fb_vma(vma)) {
+ split_fb_pmd(vma, pmd);
+ spin_unlock(&mm->page_table_lock);
+ return;
+ }
page = pmd_page(*pmd);
VM_BUG_ON(!page_count(page));
get_page(page);
tlb_finish_mmu(&tlb, address, end);
return end;
}
+EXPORT_SYMBOL_GPL(zap_page_range);
/**
* zap_vma_ptes - remove ptes mapping the vma
return page;
}
- static inline int stack_guard_page(struct vm_area_struct *vma, unsigned long addr)
- {
- return stack_guard_page_start(vma, addr) ||
- stack_guard_page_end(vma, addr+PAGE_SIZE);
- }
-
/**
* __get_user_pages() - pin user pages in memory
* @tsk: task_struct of target task
int ret;
unsigned int fault_flags = 0;
- /* For mlock, just skip the stack guard page. */
- if (foll_flags & FOLL_MLOCK) {
- if (stack_guard_page(vma, start))
- goto next_page;
- }
if (foll_flags & FOLL_WRITE)
fault_flags |= FAULT_FLAG_WRITE;
if (nonblocking)
return ret;
}
- /*
- * This is like a special single-page "expand_{down|up}wards()",
- * except we must first make sure that 'address{-|+}PAGE_SIZE'
- * doesn't hit another vma.
- */
- static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned long address)
- {
- address &= PAGE_MASK;
- if ((vma->vm_flags & VM_GROWSDOWN) && address == vma->vm_start) {
- struct vm_area_struct *prev = vma->vm_prev;
-
- /*
- * Is there a mapping abutting this one below?
- *
- * That's only ok if it's the same stack mapping
- * that has gotten split..
- */
- if (prev && prev->vm_end == address)
- return prev->vm_flags & VM_GROWSDOWN ? 0 : -ENOMEM;
-
- return expand_downwards(vma, address - PAGE_SIZE);
- }
- if ((vma->vm_flags & VM_GROWSUP) && address + PAGE_SIZE == vma->vm_end) {
- struct vm_area_struct *next = vma->vm_next;
-
- /* As VM_GROWSDOWN but s/below/above/ */
- if (next && next->vm_start == address + PAGE_SIZE)
- return next->vm_flags & VM_GROWSUP ? 0 : -ENOMEM;
-
- return expand_upwards(vma, address + PAGE_SIZE);
- }
- return 0;
- }
-
/*
* We enter with non-exclusive mmap_sem (to exclude vma changes,
* but allow concurrent faults), and pte mapped but not yet locked.
if (vma->vm_flags & VM_SHARED)
return VM_FAULT_SIGBUS;
- /* Check if we need to add a guard page to the stack */
- if (check_stack_guard_page(vma, address) < 0)
- return VM_FAULT_SIGSEGV;
-
/* Use the zero-page for reads */
if (!(flags & FAULT_FLAG_WRITE)) {
entry = pte_mkspecial(pfn_pte(my_zero_pfn(address),
barrier();
if (pmd_trans_huge(orig_pmd)) {
- if (flags & FAULT_FLAG_WRITE &&
- !pmd_write(orig_pmd) &&
+ unsigned int dirty = flags & FAULT_FLAG_WRITE;
+
+ if (dirty && !pmd_write(orig_pmd) &&
!pmd_trans_splitting(orig_pmd)) {
ret = do_huge_pmd_wp_page(mm, vma, address, pmd,
orig_pmd);
if (unlikely(ret & VM_FAULT_OOM))
goto retry;
return ret;
+ } else {
+ huge_pmd_set_accessed(mm, vma, address, pmd,
+ orig_pmd, dirty);
}
return 0;
}
vma = find_vma(mm, addr);
if (!vma || vma->vm_start > addr)
break;
- if (vma->vm_ops && vma->vm_ops->access)
+ if ((vma->vm_flags & VM_PFNMAP) &&
+ !(vma->vm_flags & VM_IO))
+ ret = generic_access_phys(vma, addr, buf,
+ len, write);
+ if (ret <= 0 && vma->vm_ops && vma->vm_ops->access)
ret = vma->vm_ops->access(vma, addr, buf,
len, write);
if (ret <= 0)
* original page might be freed under memory pressure, then
* later read back in from swap, now with the wrong data.
*
- * Hibernation clears bits from gfp_allowed_mask to prevent
- * memory reclaim from writing to disk, so check that here.
+ * Hibration suspends storage while it is writing the image
+ * to disk so check that here.
*/
- if (!(gfp_allowed_mask & __GFP_IO))
+ if (pm_suspended_storage())
return 0;
delete_from_swap_cache(page);
swab32s(&swap_header->info.version);
swab32s(&swap_header->info.last_page);
swab32s(&swap_header->info.nr_badpages);
+ if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES)
+ return 0;
for (i = 0; i < swap_header->info.nr_badpages; i++)
swab32s(&swap_header->info.badpages[i]);
}
git.openpandora.org / pandora-kernel.git / commitdiff