Merge git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-2.…

…6-nommu

* git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-2.6-nommu:
  NOMMU: Support XIP on initramfs
  NOMMU: Teach kobjsize() about VMA regions.
  FLAT: Don't attempt to expand the userspace stack to fill the space allocated
  FDPIC: Don't attempt to expand the userspace stack to fill the space allocated
  NOMMU: Improve procfs output using per-MM VMAs
  NOMMU: Make mmap allocation page trimming behaviour configurable.
  NOMMU: Make VMAs per MM as for MMU-mode linux
  NOMMU: Delete askedalloc and realalloc variables
  NOMMU: Rename ARM's struct vm_region
  NOMMU: Fix cleanup handling in ramfs_nommu_get_umapped_area()

Documentation/nommu-mmap.txt

@@ -109,12 +109,18 @@ and it's also much more restricted in the latter case:
 FURTHER NOTES ON NO-MMU MMAP
 ============================
 
- (*) A request for a private mapping of less than a page in size may not return
-     a page-aligned buffer. This is because the kernel calls kmalloc() to
-     allocate the buffer, not get_free_page().
+ (*) A request for a private mapping of a file may return a buffer that is not
+     page-aligned.  This is because XIP may take place, and the data may not be
+     paged aligned in the backing store.
 
- (*) A list of all the mappings on the system is visible through /proc/maps in
-     no-MMU mode.
+ (*) A request for an anonymous mapping will always be page aligned.  If
+     possible the size of the request should be a power of two otherwise some
+     of the space may be wasted as the kernel must allocate a power-of-2
+     granule but will only discard the excess if appropriately configured as
+     this has an effect on fragmentation.
+
+ (*) A list of all the private copy and anonymous mappings on the system is
+     visible through /proc/maps in no-MMU mode.
 
  (*) A list of all the mappings in use by a process is visible through
      /proc/<pid>/maps in no-MMU mode.
@@ -242,3 +248,18 @@ PROVIDING SHAREABLE BLOCK DEVICE SUPPORT
 Provision of shared mappings on block device files is exactly the same as for
 character devices. If there isn't a real device underneath, then the driver
 should allocate sufficient contiguous memory to honour any supported mapping.
+
+
+=================================
+ADJUSTING PAGE TRIMMING BEHAVIOUR
+=================================
+
+NOMMU mmap automatically rounds up to the nearest power-of-2 number of pages
+when performing an allocation.  This can have adverse effects on memory
+fragmentation, and as such, is left configurable.  The default behaviour is to
+aggressively trim allocations and discard any excess pages back in to the page
+allocator.  In order to retain finer-grained control over fragmentation, this
+behaviour can either be disabled completely, or bumped up to a higher page
+watermark where trimming begins.
+
+Page trimming behaviour is configurable via the sysctl `vm.nr_trim_pages'.

Documentation/sysctl/vm.txt

@@ -38,6 +38,7 @@ Currently, these files are in /proc/sys/vm:
 - numa_zonelist_order
 - nr_hugepages
 - nr_overcommit_hugepages
+- nr_trim_pages		(only if CONFIG_MMU=n)
 
 ==============================================================
 
@@ -348,3 +349,20 @@ Change the maximum size of the hugepage pool. The maximum is
 nr_hugepages + nr_overcommit_hugepages.
 
 See Documentation/vm/hugetlbpage.txt
+
+==============================================================
+
+nr_trim_pages
+
+This is available only on NOMMU kernels.
+
+This value adjusts the excess page trimming behaviour of power-of-2 aligned
+NOMMU mmap allocations.
+
+A value of 0 disables trimming of allocations entirely, while a value of 1
+trims excess pages aggressively. Any value >= 1 acts as the watermark where
+trimming of allocations is initiated.
+
+The default value is 1.
+
+See Documentation/nommu-mmap.txt for more information.

arch/arm/include/asm/mmu.h

@@ -24,7 +24,6 @@ typedef struct {
  *  modified for 2.6 by Hyok S. Choi <hyok.choi@samsung.com>
  */
 typedef struct {
-	struct vm_list_struct	*vmlist;
 	unsigned long		end_brk;
 } mm_context_t;
 

arch/arm/mm/dma-mapping.c

@@ -71,28 +71,28 @@ static DEFINE_SPINLOCK(consistent_lock);
  * the amount of RAM found at boot time.)  I would imagine that get_vm_area()
  * would have to initialise this each time prior to calling vm_region_alloc().
  */
-struct vm_region {
+struct arm_vm_region {
 	struct list_head	vm_list;
 	unsigned long		vm_start;
 	unsigned long		vm_end;
 	struct page		*vm_pages;
 	int			vm_active;
 };
 
-static struct vm_region consistent_head = {
+static struct arm_vm_region consistent_head = {
 	.vm_list	= LIST_HEAD_INIT(consistent_head.vm_list),
 	.vm_start	= CONSISTENT_BASE,
 	.vm_end		= CONSISTENT_END,
 };
 
-static struct vm_region *
-vm_region_alloc(struct vm_region *head, size_t size, gfp_t gfp)
+static struct arm_vm_region *
+arm_vm_region_alloc(struct arm_vm_region *head, size_t size, gfp_t gfp)
 {
 	unsigned long addr = head->vm_start, end = head->vm_end - size;
 	unsigned long flags;
-	struct vm_region *c, *new;
+	struct arm_vm_region *c, *new;
 
-	new = kmalloc(sizeof(struct vm_region), gfp);
+	new = kmalloc(sizeof(struct arm_vm_region), gfp);
 	if (!new)
 		goto out;
 
@@ -127,9 +127,9 @@ vm_region_alloc(struct vm_region *head, size_t size, gfp_t gfp)
 	return NULL;
 }
 
-static struct vm_region *vm_region_find(struct vm_region *head, unsigned long addr)
+static struct arm_vm_region *arm_vm_region_find(struct arm_vm_region *head, unsigned long addr)
 {
-	struct vm_region *c;
+	struct arm_vm_region *c;
 
 	list_for_each_entry(c, &head->vm_list, vm_list) {
 		if (c->vm_active && c->vm_start == addr)
@@ -149,7 +149,7 @@ __dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp,
 	    pgprot_t prot)
 {
 	struct page *page;
-	struct vm_region *c;
+	struct arm_vm_region *c;
 	unsigned long order;
 	u64 mask = ISA_DMA_THRESHOLD, limit;
 
@@ -214,7 +214,7 @@ __dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp,
 	/*
 	 * Allocate a virtual address in the consistent mapping region.
 	 */
-	c = vm_region_alloc(&consistent_head, size,
+	c = arm_vm_region_alloc(&consistent_head, size,
 			    gfp & ~(__GFP_DMA | __GFP_HIGHMEM));
 	if (c) {
 		pte_t *pte;
@@ -311,13 +311,13 @@ static int dma_mmap(struct device *dev, struct vm_area_struct *vma,
 		    void *cpu_addr, dma_addr_t dma_addr, size_t size)
 {
 	unsigned long flags, user_size, kern_size;
-	struct vm_region *c;
+	struct arm_vm_region *c;
 	int ret = -ENXIO;
 
 	user_size = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
 
 	spin_lock_irqsave(&consistent_lock, flags);
-	c = vm_region_find(&consistent_head, (unsigned long)cpu_addr);
+	c = arm_vm_region_find(&consistent_head, (unsigned long)cpu_addr);
 	spin_unlock_irqrestore(&consistent_lock, flags);
 
 	if (c) {
@@ -359,7 +359,7 @@ EXPORT_SYMBOL(dma_mmap_writecombine);
  */
 void dma_free_coherent(struct device *dev, size_t size, void *cpu_addr, dma_addr_t handle)
 {
-	struct vm_region *c;
+	struct arm_vm_region *c;
 	unsigned long flags, addr;
 	pte_t *ptep;
 	int idx;
@@ -378,7 +378,7 @@ void dma_free_coherent(struct device *dev, size_t size, void *cpu_addr, dma_addr
 	size = PAGE_ALIGN(size);
 
 	spin_lock_irqsave(&consistent_lock, flags);
-	c = vm_region_find(&consistent_head, (unsigned long)cpu_addr);
+	c = arm_vm_region_find(&consistent_head, (unsigned long)cpu_addr);
 	if (!c)
 		goto no_area;
 

arch/blackfin/include/asm/mmu.h

@@ -10,7 +10,6 @@ struct sram_list_struct {
 };
 
 typedef struct {
-	struct vm_list_struct *vmlist;
 	unsigned long end_brk;
 	unsigned long stack_start;
 

arch/blackfin/kernel/ptrace.c

@@ -160,15 +160,15 @@ put_reg(struct task_struct *task, int regno, unsigned long data)
 static inline int is_user_addr_valid(struct task_struct *child,
 				     unsigned long start, unsigned long len)
 {
-	struct vm_list_struct *vml;
+	struct vm_area_struct *vma;
 	struct sram_list_struct *sraml;
 
 	/* overflow */
 	if (start + len < start)
 		return -EIO;
 
-	for (vml = child->mm->context.vmlist; vml; vml = vml->next)
-		if (start >= vml->vma->vm_start && start + len < vml->vma->vm_end)
+	vma = find_vma(child->mm, start);
+	if (vma && start >= vma->vm_start && start + len <= vma->vm_end)
 			return 0;
 
 	for (sraml = child->mm->context.sram_list; sraml; sraml = sraml->next)

arch/blackfin/kernel/traps.c

@@ -32,6 +32,7 @@
 #include <linux/module.h>
 #include <linux/kallsyms.h>
 #include <linux/fs.h>
+#include <linux/rbtree.h>
 #include <asm/traps.h>
 #include <asm/cacheflush.h>
 #include <asm/cplb.h>
@@ -83,6 +84,7 @@ static void decode_address(char *buf, unsigned long address)
 	struct mm_struct *mm;
 	unsigned long flags, offset;
 	unsigned char in_atomic = (bfin_read_IPEND() & 0x10) || in_atomic();
+	struct rb_node *n;
 
 #ifdef CONFIG_KALLSYMS
 	unsigned long symsize;
@@ -128,9 +130,10 @@ static void decode_address(char *buf, unsigned long address)
 		if (!mm)
 			continue;
 
-		vml = mm->context.vmlist;
-		while (vml) {
-			struct vm_area_struct *vma = vml->vma;
+		for (n = rb_first(&mm->mm_rb); n; n = rb_next(n)) {
+			struct vm_area_struct *vma;
+
+			vma = rb_entry(n, struct vm_area_struct, vm_rb);
 
 			if (address >= vma->vm_start && address < vma->vm_end) {
 				char _tmpbuf[256];
@@ -176,8 +179,6 @@ static void decode_address(char *buf, unsigned long address)
 
 				goto done;
 			}
-
-			vml = vml->next;
 		}
 		if (!in_atomic)
 			mmput(mm);

arch/frv/kernel/ptrace.c

@@ -69,7 +69,8 @@ static inline int put_reg(struct task_struct *task, int regno,
 }
 
 /*
- * check that an address falls within the bounds of the target process's memory mappings
+ * check that an address falls within the bounds of the target process's memory
+ * mappings
  */
 static inline int is_user_addr_valid(struct task_struct *child,
 				     unsigned long start, unsigned long len)
@@ -79,11 +80,11 @@ static inline int is_user_addr_valid(struct task_struct *child,
 		return -EIO;
 	return 0;
 #else
-	struct vm_list_struct *vml;
+	struct vm_area_struct *vma;
 
-	for (vml = child->mm->context.vmlist; vml; vml = vml->next)
-		if (start >= vml->vma->vm_start && start + len <= vml->vma->vm_end)
-			return 0;
+	vma = find_vma(child->mm, start);
+	if (vma && start >= vma->vm_start && start + len <= vma->vm_end)
+		return 0;
 
 	return -EIO;
 #endif

arch/h8300/include/asm/mmu.h

@@ -4,7 +4,6 @@
 /* Copyright (C) 2002, David McCullough <davidm@snapgear.com> */
 
 typedef struct {
-	struct vm_list_struct	*vmlist;
 	unsigned long		end_brk;
 } mm_context_t;
 

arch/m68knommu/include/asm/mmu.h

@@ -4,7 +4,6 @@
 /* Copyright (C) 2002, David McCullough <davidm@snapgear.com> */
 
 typedef struct {
-	struct vm_list_struct	*vmlist;
 	unsigned long		end_brk;
 } mm_context_t;
 

arch/sh/include/asm/mmu.h

@@ -9,7 +9,6 @@ typedef struct {
 	mm_context_id_t		id;
 	void			*vdso;
 #else
-	struct vm_list_struct	*vmlist;
 	unsigned long		end_brk;
 #endif
 #ifdef CONFIG_BINFMT_ELF_FDPIC

fs/binfmt_elf_fdpic.c

@@ -168,9 +168,6 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm,
 	struct elf_fdpic_params exec_params, interp_params;
 	struct elf_phdr *phdr;
 	unsigned long stack_size, entryaddr;
-#ifndef CONFIG_MMU
-	unsigned long fullsize;
-#endif
 #ifdef ELF_FDPIC_PLAT_INIT
 	unsigned long dynaddr;
 #endif
@@ -390,11 +387,6 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm,
 		goto error_kill;
 	}
 
-	/* expand the stack mapping to use up the entire allocation granule */
-	fullsize = kobjsize((char *) current->mm->start_brk);
-	if (!IS_ERR_VALUE(do_mremap(current->mm->start_brk, stack_size,
-				    fullsize, 0, 0)))
-		stack_size = fullsize;
 	up_write(&current->mm->mmap_sem);
 
 	current->mm->brk = current->mm->start_brk;
@@ -1567,11 +1559,9 @@ static int elf_fdpic_dump_segments(struct file *file, size_t *size,
 static int elf_fdpic_dump_segments(struct file *file, size_t *size,
 			   unsigned long *limit, unsigned long mm_flags)
 {
-	struct vm_list_struct *vml;
-
-	for (vml = current->mm->context.vmlist; vml; vml = vml->next) {
-	struct vm_area_struct *vma = vml->vma;
+	struct vm_area_struct *vma;
 
+	for (vma = current->mm->mmap; vma; vma = vma->vm_next) {
 		if (!maydump(vma, mm_flags))
 			continue;
 
@@ -1617,9 +1607,6 @@ static int elf_fdpic_core_dump(long signr, struct pt_regs *regs,
 	elf_fpxregset_t *xfpu = NULL;
 #endif
 	int thread_status_size = 0;
-#ifndef CONFIG_MMU
-	struct vm_list_struct *vml;
-#endif
 	elf_addr_t *auxv;
 	unsigned long mm_flags;
 
@@ -1685,13 +1672,7 @@ static int elf_fdpic_core_dump(long signr, struct pt_regs *regs,
 	fill_prstatus(prstatus, current, signr);
 	elf_core_copy_regs(&prstatus->pr_reg, regs);
 
-#ifdef CONFIG_MMU
 	segs = current->mm->map_count;
-#else
-	segs = 0;
-	for (vml = current->mm->context.vmlist; vml; vml = vml->next)
-	    segs++;
-#endif
 #ifdef ELF_CORE_EXTRA_PHDRS
 	segs += ELF_CORE_EXTRA_PHDRS;
 #endif
@@ -1766,20 +1747,10 @@ static int elf_fdpic_core_dump(long signr, struct pt_regs *regs,
 	mm_flags = current->mm->flags;
 
 	/* write program headers for segments dump */
-	for (
-#ifdef CONFIG_MMU
-		vma = current->mm->mmap; vma; vma = vma->vm_next
-#else
-			vml = current->mm->context.vmlist; vml; vml = vml->next
-#endif
-	     ) {
+	for (vma = current->mm->mmap; vma; vma = vma->vm_next) {
 		struct elf_phdr phdr;
 		size_t sz;
 
-#ifndef CONFIG_MMU
-		vma = vml->vma;
-#endif
-
 		sz = vma->vm_end - vma->vm_start;
 
 		phdr.p_type = PT_LOAD;