mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-06 00:16:39 +07:00
e020d5bd8a
mm could be removed from current task struct, using previous vma->vm_mm It will crash on blackfin after updated to Linux 3.15. The commit "mm: per-thread vma caching" caused the crash. mm could be removed from current task struct before mmput()-> exit_mmap()-> delete_vma_from_mm() the detailed fault information: NULL pointer access Kernel OOPS in progress Deferred Exception context CURRENT PROCESS: COMM=modprobe PID=278 CPU=0 invalid mm return address: [0x000531de]; contents of: 0x000531b0: c727 acea 0c42 181d 0000 0000 0000 a0a8 0x000531c0: b090 acaa 0c42 1806 0000 0000 0000 a0e8 0x000531d0: b0d0 e801 0000 05b3 0010 e522 0046 [a090] 0x000531e0: 6408 b090 0c00 17cc 3042 e3ff f37b 2fc8 CPU: 0 PID: 278 Comm: modprobe Not tainted 3.15.0-ADI-2014R1-pre-00345-gea9f446 #25 task: 0572b720 ti: 0569e000 task.ti: 0569e000 Compiled for cpu family 0x27fe (Rev 0), but running on:0x0000 (Rev 0) ADSP-BF609-0.0 500(MHz CCLK) 125(MHz SCLK) (mpu off) Linux version 3.15.0-ADI-2014R1-pre-00345-gea9f446 (steven@steven-OptiPlex-390) (gcc version 4.3.5 (ADI-trunk/svn-5962) ) #25 Tue Jun 10 17:47:46 CST 2014 SEQUENCER STATUS: Not tainted SEQSTAT: 00000027 IPEND: 8008 IMASK: ffff SYSCFG: 2806 EXCAUSE : 0x27 physical IVG3 asserted : <0xffa00744> { _trap + 0x0 } physical IVG15 asserted : <0xffa00d68> { _evt_system_call + 0x0 } logical irq 6 mapped : <0xffa003bc> { _bfin_coretmr_interrupt + 0x0 } logical irq 7 mapped : <0x00008828> { _bfin_fault_routine + 0x0 } logical irq 11 mapped : <0x00007724> { _l2_ecc_err + 0x0 } logical irq 13 mapped : <0x00008828> { _bfin_fault_routine + 0x0 } logical irq 39 mapped : <0x00150788> { _bfin_twi_interrupt_entry + 0x0 } logical irq 40 mapped : <0x00150788> { _bfin_twi_interrupt_entry + 0x0 } RETE: <0x00000000> /* Maybe null pointer? */ RETN: <0x0569fe50> /* kernel dynamic memory (maybe user-space) */ RETX: <0x00000480> /* Maybe fixed code section */ RETS: <0x00053384> { _exit_mmap + 0x28 } PC : <0x000531de> { _delete_vma_from_mm + 0x92 } DCPLB_FAULT_ADDR: <0x00000008> /* Maybe null pointer? */ ICPLB_FAULT_ADDR: <0x000531de> { _delete_vma_from_mm + 0x92 } PROCESSOR STATE: R0 : 00000004 R1 : 0569e000 R2 : 00bf3db4 R3 : 00000000 R4 : 057f9800 R5 : 00000001 R6 : 0569ddd0 R7 : 0572b720 P0 : 0572b854 P1 : 00000004 P2 : 00000000 P3 : 0569dda0 P4 : 0572b720 P5 : 0566c368 FP : 0569fe5c SP : 0569fd74 LB0: 057f523f LT0: 057f523e LC0: 00000000 LB1: 0005317c LT1: 00053172 LC1: 00000002 B0 : 00000000 L0 : 00000000 M0 : 0566f5bc I0 : 00000000 B1 : 00000000 L1 : 00000000 M1 : 00000000 I1 : ffffffff B2 : 00000001 L2 : 00000000 M2 : 00000000 I2 : 00000000 B3 : 00000000 L3 : 00000000 M3 : 00000000 I3 : 057f8000 A0.w: 00000000 A0.x: 00000000 A1.w: 00000000 A1.x: 00000000 USP : 056ffcf8 ASTAT: 02003024 Hardware Trace: 0 Target : <0x00003fb8> { _trap_c + 0x0 } Source : <0xffa006d8> { _exception_to_level5 + 0xa0 } JUMP.L 1 Target : <0xffa00638> { _exception_to_level5 + 0x0 } Source : <0xffa004f2> { _bfin_return_from_exception + 0x6 } RTX 2 Target : <0xffa004ec> { _bfin_return_from_exception + 0x0 } Source : <0xffa00590> { _ex_trap_c + 0x70 } JUMP.S 3 Target : <0xffa00520> { _ex_trap_c + 0x0 } Source : <0xffa0076e> { _trap + 0x2a } JUMP (P4) 4 Target : <0xffa00744> { _trap + 0x0 } FAULT : <0x000531de> { _delete_vma_from_mm + 0x92 } P0 = W[P2 + 2] Source : <0x000531da> { _delete_vma_from_mm + 0x8e } P2 = [P4 + 0x18] 5 Target : <0x000531da> { _delete_vma_from_mm + 0x8e } Source : <0x00053176> { _delete_vma_from_mm + 0x2a } IF CC JUMP pcrel 6 Target : <0x0005314c> { _delete_vma_from_mm + 0x0 } Source : <0x00053380> { _exit_mmap + 0x24 } JUMP.L 7 Target : <0x00053378> { _exit_mmap + 0x1c } Source : <0x00053394> { _exit_mmap + 0x38 } IF !CC JUMP pcrel (BP) 8 Target : <0x00053390> { _exit_mmap + 0x34 } Source : <0xffa020e0> { __cond_resched + 0x20 } RTS 9 Target : <0xffa020c0> { __cond_resched + 0x0 } Source : <0x0005338c> { _exit_mmap + 0x30 } JUMP.L 10 Target : <0x0005338c> { _exit_mmap + 0x30 } Source : <0x0005333a> { _delete_vma + 0xb2 } RTS 11 Target : <0x00053334> { _delete_vma + 0xac } Source : <0x0005507a> { _kmem_cache_free + 0xba } RTS 12 Target : <0x00055068> { _kmem_cache_free + 0xa8 } Source : <0x0005505e> { _kmem_cache_free + 0x9e } IF !CC JUMP pcrel (BP) 13 Target : <0x00055052> { _kmem_cache_free + 0x92 } Source : <0x0005501a> { _kmem_cache_free + 0x5a } IF CC JUMP pcrel 14 Target : <0x00054ff4> { _kmem_cache_free + 0x34 } Source : <0x00054fce> { _kmem_cache_free + 0xe } IF CC JUMP pcrel (BP) 15 Target : <0x00054fc0> { _kmem_cache_free + 0x0 } Source : <0x00053330> { _delete_vma + 0xa8 } JUMP.L Kernel Stack Stack info: SP: [0x0569ff24] <0x0569ff24> /* kernel dynamic memory (maybe user-space) */ Memory from 0x0569ff20 to 056a0000 0569ff20: 00000001 [04e8da5a] 00008000 00000000 00000000 056a0000 04e8da5a 04e8da5a 0569ff40: 04eb9eea ffa00dce 02003025 04ea09c5 057f523f 04ea09c4 057f523e 00000000 0569ff60: 00000000 00000000 00000000 00000000 00000000 00000000 00000001 00000000 0569ff80: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 0569ffa0: 0566f5bc 057f8000 057f8000 00000001 04ec0170 056ffcf8 056ffd04 057f9800 0569ffc0: 04d1d498 057f9800 057f8fe4 057f8ef0 00000001 057f928c 00000001 00000001 0569ffe0: 057f9800 00000000 00000008 00000007 00000001 00000001 00000001 <00002806> Return addresses in stack: address : <0x00002806> { _show_cpuinfo + 0x2d2 } Modules linked in: Kernel panic - not syncing: Kernel exception [ end Kernel panic - not syncing: Kernel exception Signed-off-by: Steven Miao <realmz6@gmail.com> Acked-by: Davidlohr Bueso <davidlohr@hp.com> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: David Rientjes <rientjes@google.com> Cc: <stable@vger.kernel.org> [3.15.x] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2183 lines
54 KiB
C
2183 lines
54 KiB
C
/*
|
|
* linux/mm/nommu.c
|
|
*
|
|
* Replacement code for mm functions to support CPU's that don't
|
|
* have any form of memory management unit (thus no virtual memory).
|
|
*
|
|
* See Documentation/nommu-mmap.txt
|
|
*
|
|
* Copyright (c) 2004-2008 David Howells <dhowells@redhat.com>
|
|
* Copyright (c) 2000-2003 David McCullough <davidm@snapgear.com>
|
|
* Copyright (c) 2000-2001 D Jeff Dionne <jeff@uClinux.org>
|
|
* Copyright (c) 2002 Greg Ungerer <gerg@snapgear.com>
|
|
* Copyright (c) 2007-2010 Paul Mundt <lethal@linux-sh.org>
|
|
*/
|
|
|
|
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
|
|
|
|
#include <linux/export.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/vmacache.h>
|
|
#include <linux/mman.h>
|
|
#include <linux/swap.h>
|
|
#include <linux/file.h>
|
|
#include <linux/highmem.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/vmalloc.h>
|
|
#include <linux/blkdev.h>
|
|
#include <linux/backing-dev.h>
|
|
#include <linux/compiler.h>
|
|
#include <linux/mount.h>
|
|
#include <linux/personality.h>
|
|
#include <linux/security.h>
|
|
#include <linux/syscalls.h>
|
|
#include <linux/audit.h>
|
|
#include <linux/sched/sysctl.h>
|
|
#include <linux/printk.h>
|
|
|
|
#include <asm/uaccess.h>
|
|
#include <asm/tlb.h>
|
|
#include <asm/tlbflush.h>
|
|
#include <asm/mmu_context.h>
|
|
#include "internal.h"
|
|
|
|
#if 0
|
|
#define kenter(FMT, ...) \
|
|
printk(KERN_DEBUG "==> %s("FMT")\n", __func__, ##__VA_ARGS__)
|
|
#define kleave(FMT, ...) \
|
|
printk(KERN_DEBUG "<== %s()"FMT"\n", __func__, ##__VA_ARGS__)
|
|
#define kdebug(FMT, ...) \
|
|
printk(KERN_DEBUG "xxx" FMT"yyy\n", ##__VA_ARGS__)
|
|
#else
|
|
#define kenter(FMT, ...) \
|
|
no_printk(KERN_DEBUG "==> %s("FMT")\n", __func__, ##__VA_ARGS__)
|
|
#define kleave(FMT, ...) \
|
|
no_printk(KERN_DEBUG "<== %s()"FMT"\n", __func__, ##__VA_ARGS__)
|
|
#define kdebug(FMT, ...) \
|
|
no_printk(KERN_DEBUG FMT"\n", ##__VA_ARGS__)
|
|
#endif
|
|
|
|
void *high_memory;
|
|
struct page *mem_map;
|
|
unsigned long max_mapnr;
|
|
unsigned long highest_memmap_pfn;
|
|
struct percpu_counter vm_committed_as;
|
|
int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */
|
|
int sysctl_overcommit_ratio = 50; /* default is 50% */
|
|
unsigned long sysctl_overcommit_kbytes __read_mostly;
|
|
int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT;
|
|
int sysctl_nr_trim_pages = CONFIG_NOMMU_INITIAL_TRIM_EXCESS;
|
|
unsigned long sysctl_user_reserve_kbytes __read_mostly = 1UL << 17; /* 128MB */
|
|
unsigned long sysctl_admin_reserve_kbytes __read_mostly = 1UL << 13; /* 8MB */
|
|
int heap_stack_gap = 0;
|
|
|
|
atomic_long_t mmap_pages_allocated;
|
|
|
|
/*
|
|
* The global memory commitment made in the system can be a metric
|
|
* that can be used to drive ballooning decisions when Linux is hosted
|
|
* as a guest. On Hyper-V, the host implements a policy engine for dynamically
|
|
* balancing memory across competing virtual machines that are hosted.
|
|
* Several metrics drive this policy engine including the guest reported
|
|
* memory commitment.
|
|
*/
|
|
unsigned long vm_memory_committed(void)
|
|
{
|
|
return percpu_counter_read_positive(&vm_committed_as);
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(vm_memory_committed);
|
|
|
|
EXPORT_SYMBOL(mem_map);
|
|
|
|
/* list of mapped, potentially shareable regions */
|
|
static struct kmem_cache *vm_region_jar;
|
|
struct rb_root nommu_region_tree = RB_ROOT;
|
|
DECLARE_RWSEM(nommu_region_sem);
|
|
|
|
const struct vm_operations_struct generic_file_vm_ops = {
|
|
};
|
|
|
|
/*
|
|
* Return the total memory allocated for this pointer, not
|
|
* just what the caller asked for.
|
|
*
|
|
* Doesn't have to be accurate, i.e. may have races.
|
|
*/
|
|
unsigned int kobjsize(const void *objp)
|
|
{
|
|
struct page *page;
|
|
|
|
/*
|
|
* If the object we have should not have ksize performed on it,
|
|
* return size of 0
|
|
*/
|
|
if (!objp || !virt_addr_valid(objp))
|
|
return 0;
|
|
|
|
page = virt_to_head_page(objp);
|
|
|
|
/*
|
|
* If the allocator sets PageSlab, we know the pointer came from
|
|
* kmalloc().
|
|
*/
|
|
if (PageSlab(page))
|
|
return ksize(objp);
|
|
|
|
/*
|
|
* If it's not a compound page, see if we have a matching VMA
|
|
* region. This test is intentionally done in reverse order,
|
|
* so if there's no VMA, we still fall through and hand back
|
|
* PAGE_SIZE for 0-order pages.
|
|
*/
|
|
if (!PageCompound(page)) {
|
|
struct vm_area_struct *vma;
|
|
|
|
vma = find_vma(current->mm, (unsigned long)objp);
|
|
if (vma)
|
|
return vma->vm_end - vma->vm_start;
|
|
}
|
|
|
|
/*
|
|
* The ksize() function is only guaranteed to work for pointers
|
|
* returned by kmalloc(). So handle arbitrary pointers here.
|
|
*/
|
|
return PAGE_SIZE << compound_order(page);
|
|
}
|
|
|
|
long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
|
|
unsigned long start, unsigned long nr_pages,
|
|
unsigned int foll_flags, struct page **pages,
|
|
struct vm_area_struct **vmas, int *nonblocking)
|
|
{
|
|
struct vm_area_struct *vma;
|
|
unsigned long vm_flags;
|
|
int i;
|
|
|
|
/* calculate required read or write permissions.
|
|
* If FOLL_FORCE is set, we only require the "MAY" flags.
|
|
*/
|
|
vm_flags = (foll_flags & FOLL_WRITE) ?
|
|
(VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
|
|
vm_flags &= (foll_flags & FOLL_FORCE) ?
|
|
(VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
|
|
|
|
for (i = 0; i < nr_pages; i++) {
|
|
vma = find_vma(mm, start);
|
|
if (!vma)
|
|
goto finish_or_fault;
|
|
|
|
/* protect what we can, including chardevs */
|
|
if ((vma->vm_flags & (VM_IO | VM_PFNMAP)) ||
|
|
!(vm_flags & vma->vm_flags))
|
|
goto finish_or_fault;
|
|
|
|
if (pages) {
|
|
pages[i] = virt_to_page(start);
|
|
if (pages[i])
|
|
page_cache_get(pages[i]);
|
|
}
|
|
if (vmas)
|
|
vmas[i] = vma;
|
|
start = (start + PAGE_SIZE) & PAGE_MASK;
|
|
}
|
|
|
|
return i;
|
|
|
|
finish_or_fault:
|
|
return i ? : -EFAULT;
|
|
}
|
|
|
|
/*
|
|
* get a list of pages in an address range belonging to the specified process
|
|
* and indicate the VMA that covers each page
|
|
* - this is potentially dodgy as we may end incrementing the page count of a
|
|
* slab page or a secondary page from a compound page
|
|
* - don't permit access to VMAs that don't support it, such as I/O mappings
|
|
*/
|
|
long get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
|
|
unsigned long start, unsigned long nr_pages,
|
|
int write, int force, struct page **pages,
|
|
struct vm_area_struct **vmas)
|
|
{
|
|
int flags = 0;
|
|
|
|
if (write)
|
|
flags |= FOLL_WRITE;
|
|
if (force)
|
|
flags |= FOLL_FORCE;
|
|
|
|
return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas,
|
|
NULL);
|
|
}
|
|
EXPORT_SYMBOL(get_user_pages);
|
|
|
|
/**
|
|
* follow_pfn - look up PFN at a user virtual address
|
|
* @vma: memory mapping
|
|
* @address: user virtual address
|
|
* @pfn: location to store found PFN
|
|
*
|
|
* Only IO mappings and raw PFN mappings are allowed.
|
|
*
|
|
* Returns zero and the pfn at @pfn on success, -ve otherwise.
|
|
*/
|
|
int follow_pfn(struct vm_area_struct *vma, unsigned long address,
|
|
unsigned long *pfn)
|
|
{
|
|
if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
|
|
return -EINVAL;
|
|
|
|
*pfn = address >> PAGE_SHIFT;
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL(follow_pfn);
|
|
|
|
LIST_HEAD(vmap_area_list);
|
|
|
|
void vfree(const void *addr)
|
|
{
|
|
kfree(addr);
|
|
}
|
|
EXPORT_SYMBOL(vfree);
|
|
|
|
void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot)
|
|
{
|
|
/*
|
|
* You can't specify __GFP_HIGHMEM with kmalloc() since kmalloc()
|
|
* returns only a logical address.
|
|
*/
|
|
return kmalloc(size, (gfp_mask | __GFP_COMP) & ~__GFP_HIGHMEM);
|
|
}
|
|
EXPORT_SYMBOL(__vmalloc);
|
|
|
|
void *vmalloc_user(unsigned long size)
|
|
{
|
|
void *ret;
|
|
|
|
ret = __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO,
|
|
PAGE_KERNEL);
|
|
if (ret) {
|
|
struct vm_area_struct *vma;
|
|
|
|
down_write(¤t->mm->mmap_sem);
|
|
vma = find_vma(current->mm, (unsigned long)ret);
|
|
if (vma)
|
|
vma->vm_flags |= VM_USERMAP;
|
|
up_write(¤t->mm->mmap_sem);
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL(vmalloc_user);
|
|
|
|
struct page *vmalloc_to_page(const void *addr)
|
|
{
|
|
return virt_to_page(addr);
|
|
}
|
|
EXPORT_SYMBOL(vmalloc_to_page);
|
|
|
|
unsigned long vmalloc_to_pfn(const void *addr)
|
|
{
|
|
return page_to_pfn(virt_to_page(addr));
|
|
}
|
|
EXPORT_SYMBOL(vmalloc_to_pfn);
|
|
|
|
long vread(char *buf, char *addr, unsigned long count)
|
|
{
|
|
/* Don't allow overflow */
|
|
if ((unsigned long) buf + count < count)
|
|
count = -(unsigned long) buf;
|
|
|
|
memcpy(buf, addr, count);
|
|
return count;
|
|
}
|
|
|
|
long vwrite(char *buf, char *addr, unsigned long count)
|
|
{
|
|
/* Don't allow overflow */
|
|
if ((unsigned long) addr + count < count)
|
|
count = -(unsigned long) addr;
|
|
|
|
memcpy(addr, buf, count);
|
|
return count;
|
|
}
|
|
|
|
/*
|
|
* vmalloc - allocate virtually continguos memory
|
|
*
|
|
* @size: allocation size
|
|
*
|
|
* Allocate enough pages to cover @size from the page level
|
|
* allocator and map them into continguos kernel virtual space.
|
|
*
|
|
* For tight control over page level allocator and protection flags
|
|
* use __vmalloc() instead.
|
|
*/
|
|
void *vmalloc(unsigned long size)
|
|
{
|
|
return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL);
|
|
}
|
|
EXPORT_SYMBOL(vmalloc);
|
|
|
|
/*
|
|
* vzalloc - allocate virtually continguos memory with zero fill
|
|
*
|
|
* @size: allocation size
|
|
*
|
|
* Allocate enough pages to cover @size from the page level
|
|
* allocator and map them into continguos kernel virtual space.
|
|
* The memory allocated is set to zero.
|
|
*
|
|
* For tight control over page level allocator and protection flags
|
|
* use __vmalloc() instead.
|
|
*/
|
|
void *vzalloc(unsigned long size)
|
|
{
|
|
return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO,
|
|
PAGE_KERNEL);
|
|
}
|
|
EXPORT_SYMBOL(vzalloc);
|
|
|
|
/**
|
|
* vmalloc_node - allocate memory on a specific node
|
|
* @size: allocation size
|
|
* @node: numa node
|
|
*
|
|
* Allocate enough pages to cover @size from the page level
|
|
* allocator and map them into contiguous kernel virtual space.
|
|
*
|
|
* For tight control over page level allocator and protection flags
|
|
* use __vmalloc() instead.
|
|
*/
|
|
void *vmalloc_node(unsigned long size, int node)
|
|
{
|
|
return vmalloc(size);
|
|
}
|
|
EXPORT_SYMBOL(vmalloc_node);
|
|
|
|
/**
|
|
* vzalloc_node - allocate memory on a specific node with zero fill
|
|
* @size: allocation size
|
|
* @node: numa node
|
|
*
|
|
* Allocate enough pages to cover @size from the page level
|
|
* allocator and map them into contiguous kernel virtual space.
|
|
* The memory allocated is set to zero.
|
|
*
|
|
* For tight control over page level allocator and protection flags
|
|
* use __vmalloc() instead.
|
|
*/
|
|
void *vzalloc_node(unsigned long size, int node)
|
|
{
|
|
return vzalloc(size);
|
|
}
|
|
EXPORT_SYMBOL(vzalloc_node);
|
|
|
|
#ifndef PAGE_KERNEL_EXEC
|
|
# define PAGE_KERNEL_EXEC PAGE_KERNEL
|
|
#endif
|
|
|
|
/**
|
|
* vmalloc_exec - allocate virtually contiguous, executable memory
|
|
* @size: allocation size
|
|
*
|
|
* Kernel-internal function to allocate enough pages to cover @size
|
|
* the page level allocator and map them into contiguous and
|
|
* executable kernel virtual space.
|
|
*
|
|
* For tight control over page level allocator and protection flags
|
|
* use __vmalloc() instead.
|
|
*/
|
|
|
|
void *vmalloc_exec(unsigned long size)
|
|
{
|
|
return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC);
|
|
}
|
|
|
|
/**
|
|
* vmalloc_32 - allocate virtually contiguous memory (32bit addressable)
|
|
* @size: allocation size
|
|
*
|
|
* Allocate enough 32bit PA addressable pages to cover @size from the
|
|
* page level allocator and map them into continguos kernel virtual space.
|
|
*/
|
|
void *vmalloc_32(unsigned long size)
|
|
{
|
|
return __vmalloc(size, GFP_KERNEL, PAGE_KERNEL);
|
|
}
|
|
EXPORT_SYMBOL(vmalloc_32);
|
|
|
|
/**
|
|
* vmalloc_32_user - allocate zeroed virtually contiguous 32bit memory
|
|
* @size: allocation size
|
|
*
|
|
* The resulting memory area is 32bit addressable and zeroed so it can be
|
|
* mapped to userspace without leaking data.
|
|
*
|
|
* VM_USERMAP is set on the corresponding VMA so that subsequent calls to
|
|
* remap_vmalloc_range() are permissible.
|
|
*/
|
|
void *vmalloc_32_user(unsigned long size)
|
|
{
|
|
/*
|
|
* We'll have to sort out the ZONE_DMA bits for 64-bit,
|
|
* but for now this can simply use vmalloc_user() directly.
|
|
*/
|
|
return vmalloc_user(size);
|
|
}
|
|
EXPORT_SYMBOL(vmalloc_32_user);
|
|
|
|
void *vmap(struct page **pages, unsigned int count, unsigned long flags, pgprot_t prot)
|
|
{
|
|
BUG();
|
|
return NULL;
|
|
}
|
|
EXPORT_SYMBOL(vmap);
|
|
|
|
void vunmap(const void *addr)
|
|
{
|
|
BUG();
|
|
}
|
|
EXPORT_SYMBOL(vunmap);
|
|
|
|
void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t prot)
|
|
{
|
|
BUG();
|
|
return NULL;
|
|
}
|
|
EXPORT_SYMBOL(vm_map_ram);
|
|
|
|
void vm_unmap_ram(const void *mem, unsigned int count)
|
|
{
|
|
BUG();
|
|
}
|
|
EXPORT_SYMBOL(vm_unmap_ram);
|
|
|
|
void vm_unmap_aliases(void)
|
|
{
|
|
}
|
|
EXPORT_SYMBOL_GPL(vm_unmap_aliases);
|
|
|
|
/*
|
|
* Implement a stub for vmalloc_sync_all() if the architecture chose not to
|
|
* have one.
|
|
*/
|
|
void __weak vmalloc_sync_all(void)
|
|
{
|
|
}
|
|
|
|
/**
|
|
* alloc_vm_area - allocate a range of kernel address space
|
|
* @size: size of the area
|
|
*
|
|
* Returns: NULL on failure, vm_struct on success
|
|
*
|
|
* This function reserves a range of kernel address space, and
|
|
* allocates pagetables to map that range. No actual mappings
|
|
* are created. If the kernel address space is not shared
|
|
* between processes, it syncs the pagetable across all
|
|
* processes.
|
|
*/
|
|
struct vm_struct *alloc_vm_area(size_t size, pte_t **ptes)
|
|
{
|
|
BUG();
|
|
return NULL;
|
|
}
|
|
EXPORT_SYMBOL_GPL(alloc_vm_area);
|
|
|
|
void free_vm_area(struct vm_struct *area)
|
|
{
|
|
BUG();
|
|
}
|
|
EXPORT_SYMBOL_GPL(free_vm_area);
|
|
|
|
int vm_insert_page(struct vm_area_struct *vma, unsigned long addr,
|
|
struct page *page)
|
|
{
|
|
return -EINVAL;
|
|
}
|
|
EXPORT_SYMBOL(vm_insert_page);
|
|
|
|
/*
|
|
* sys_brk() for the most part doesn't need the global kernel
|
|
* lock, except when an application is doing something nasty
|
|
* like trying to un-brk an area that has already been mapped
|
|
* to a regular file. in this case, the unmapping will need
|
|
* to invoke file system routines that need the global lock.
|
|
*/
|
|
SYSCALL_DEFINE1(brk, unsigned long, brk)
|
|
{
|
|
struct mm_struct *mm = current->mm;
|
|
|
|
if (brk < mm->start_brk || brk > mm->context.end_brk)
|
|
return mm->brk;
|
|
|
|
if (mm->brk == brk)
|
|
return mm->brk;
|
|
|
|
/*
|
|
* Always allow shrinking brk
|
|
*/
|
|
if (brk <= mm->brk) {
|
|
mm->brk = brk;
|
|
return brk;
|
|
}
|
|
|
|
/*
|
|
* Ok, looks good - let it rip.
|
|
*/
|
|
flush_icache_range(mm->brk, brk);
|
|
return mm->brk = brk;
|
|
}
|
|
|
|
/*
|
|
* initialise the VMA and region record slabs
|
|
*/
|
|
void __init mmap_init(void)
|
|
{
|
|
int ret;
|
|
|
|
ret = percpu_counter_init(&vm_committed_as, 0);
|
|
VM_BUG_ON(ret);
|
|
vm_region_jar = KMEM_CACHE(vm_region, SLAB_PANIC);
|
|
}
|
|
|
|
/*
|
|
* validate the region tree
|
|
* - the caller must hold the region lock
|
|
*/
|
|
#ifdef CONFIG_DEBUG_NOMMU_REGIONS
|
|
static noinline void validate_nommu_regions(void)
|
|
{
|
|
struct vm_region *region, *last;
|
|
struct rb_node *p, *lastp;
|
|
|
|
lastp = rb_first(&nommu_region_tree);
|
|
if (!lastp)
|
|
return;
|
|
|
|
last = rb_entry(lastp, struct vm_region, vm_rb);
|
|
BUG_ON(unlikely(last->vm_end <= last->vm_start));
|
|
BUG_ON(unlikely(last->vm_top < last->vm_end));
|
|
|
|
while ((p = rb_next(lastp))) {
|
|
region = rb_entry(p, struct vm_region, vm_rb);
|
|
last = rb_entry(lastp, struct vm_region, vm_rb);
|
|
|
|
BUG_ON(unlikely(region->vm_end <= region->vm_start));
|
|
BUG_ON(unlikely(region->vm_top < region->vm_end));
|
|
BUG_ON(unlikely(region->vm_start < last->vm_top));
|
|
|
|
lastp = p;
|
|
}
|
|
}
|
|
#else
|
|
static void validate_nommu_regions(void)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* add a region into the global tree
|
|
*/
|
|
static void add_nommu_region(struct vm_region *region)
|
|
{
|
|
struct vm_region *pregion;
|
|
struct rb_node **p, *parent;
|
|
|
|
validate_nommu_regions();
|
|
|
|
parent = NULL;
|
|
p = &nommu_region_tree.rb_node;
|
|
while (*p) {
|
|
parent = *p;
|
|
pregion = rb_entry(parent, struct vm_region, vm_rb);
|
|
if (region->vm_start < pregion->vm_start)
|
|
p = &(*p)->rb_left;
|
|
else if (region->vm_start > pregion->vm_start)
|
|
p = &(*p)->rb_right;
|
|
else if (pregion == region)
|
|
return;
|
|
else
|
|
BUG();
|
|
}
|
|
|
|
rb_link_node(®ion->vm_rb, parent, p);
|
|
rb_insert_color(®ion->vm_rb, &nommu_region_tree);
|
|
|
|
validate_nommu_regions();
|
|
}
|
|
|
|
/*
|
|
* delete a region from the global tree
|
|
*/
|
|
static void delete_nommu_region(struct vm_region *region)
|
|
{
|
|
BUG_ON(!nommu_region_tree.rb_node);
|
|
|
|
validate_nommu_regions();
|
|
rb_erase(®ion->vm_rb, &nommu_region_tree);
|
|
validate_nommu_regions();
|
|
}
|
|
|
|
/*
|
|
* free a contiguous series of pages
|
|
*/
|
|
static void free_page_series(unsigned long from, unsigned long to)
|
|
{
|
|
for (; from < to; from += PAGE_SIZE) {
|
|
struct page *page = virt_to_page(from);
|
|
|
|
kdebug("- free %lx", from);
|
|
atomic_long_dec(&mmap_pages_allocated);
|
|
if (page_count(page) != 1)
|
|
kdebug("free page %p: refcount not one: %d",
|
|
page, page_count(page));
|
|
put_page(page);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* release a reference to a region
|
|
* - the caller must hold the region semaphore for writing, which this releases
|
|
* - the region may not have been added to the tree yet, in which case vm_top
|
|
* will equal vm_start
|
|
*/
|
|
static void __put_nommu_region(struct vm_region *region)
|
|
__releases(nommu_region_sem)
|
|
{
|
|
kenter("%p{%d}", region, region->vm_usage);
|
|
|
|
BUG_ON(!nommu_region_tree.rb_node);
|
|
|
|
if (--region->vm_usage == 0) {
|
|
if (region->vm_top > region->vm_start)
|
|
delete_nommu_region(region);
|
|
up_write(&nommu_region_sem);
|
|
|
|
if (region->vm_file)
|
|
fput(region->vm_file);
|
|
|
|
/* IO memory and memory shared directly out of the pagecache
|
|
* from ramfs/tmpfs mustn't be released here */
|
|
if (region->vm_flags & VM_MAPPED_COPY) {
|
|
kdebug("free series");
|
|
free_page_series(region->vm_start, region->vm_top);
|
|
}
|
|
kmem_cache_free(vm_region_jar, region);
|
|
} else {
|
|
up_write(&nommu_region_sem);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* release a reference to a region
|
|
*/
|
|
static void put_nommu_region(struct vm_region *region)
|
|
{
|
|
down_write(&nommu_region_sem);
|
|
__put_nommu_region(region);
|
|
}
|
|
|
|
/*
|
|
* update protection on a vma
|
|
*/
|
|
static void protect_vma(struct vm_area_struct *vma, unsigned long flags)
|
|
{
|
|
#ifdef CONFIG_MPU
|
|
struct mm_struct *mm = vma->vm_mm;
|
|
long start = vma->vm_start & PAGE_MASK;
|
|
while (start < vma->vm_end) {
|
|
protect_page(mm, start, flags);
|
|
start += PAGE_SIZE;
|
|
}
|
|
update_protections(mm);
|
|
#endif
|
|
}
|
|
|
|
/*
|
|
* add a VMA into a process's mm_struct in the appropriate place in the list
|
|
* and tree and add to the address space's page tree also if not an anonymous
|
|
* page
|
|
* - should be called with mm->mmap_sem held writelocked
|
|
*/
|
|
static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma)
|
|
{
|
|
struct vm_area_struct *pvma, *prev;
|
|
struct address_space *mapping;
|
|
struct rb_node **p, *parent, *rb_prev;
|
|
|
|
kenter(",%p", vma);
|
|
|
|
BUG_ON(!vma->vm_region);
|
|
|
|
mm->map_count++;
|
|
vma->vm_mm = mm;
|
|
|
|
protect_vma(vma, vma->vm_flags);
|
|
|
|
/* add the VMA to the mapping */
|
|
if (vma->vm_file) {
|
|
mapping = vma->vm_file->f_mapping;
|
|
|
|
mutex_lock(&mapping->i_mmap_mutex);
|
|
flush_dcache_mmap_lock(mapping);
|
|
vma_interval_tree_insert(vma, &mapping->i_mmap);
|
|
flush_dcache_mmap_unlock(mapping);
|
|
mutex_unlock(&mapping->i_mmap_mutex);
|
|
}
|
|
|
|
/* add the VMA to the tree */
|
|
parent = rb_prev = NULL;
|
|
p = &mm->mm_rb.rb_node;
|
|
while (*p) {
|
|
parent = *p;
|
|
pvma = rb_entry(parent, struct vm_area_struct, vm_rb);
|
|
|
|
/* sort by: start addr, end addr, VMA struct addr in that order
|
|
* (the latter is necessary as we may get identical VMAs) */
|
|
if (vma->vm_start < pvma->vm_start)
|
|
p = &(*p)->rb_left;
|
|
else if (vma->vm_start > pvma->vm_start) {
|
|
rb_prev = parent;
|
|
p = &(*p)->rb_right;
|
|
} else if (vma->vm_end < pvma->vm_end)
|
|
p = &(*p)->rb_left;
|
|
else if (vma->vm_end > pvma->vm_end) {
|
|
rb_prev = parent;
|
|
p = &(*p)->rb_right;
|
|
} else if (vma < pvma)
|
|
p = &(*p)->rb_left;
|
|
else if (vma > pvma) {
|
|
rb_prev = parent;
|
|
p = &(*p)->rb_right;
|
|
} else
|
|
BUG();
|
|
}
|
|
|
|
rb_link_node(&vma->vm_rb, parent, p);
|
|
rb_insert_color(&vma->vm_rb, &mm->mm_rb);
|
|
|
|
/* add VMA to the VMA list also */
|
|
prev = NULL;
|
|
if (rb_prev)
|
|
prev = rb_entry(rb_prev, struct vm_area_struct, vm_rb);
|
|
|
|
__vma_link_list(mm, vma, prev, parent);
|
|
}
|
|
|
|
/*
|
|
* delete a VMA from its owning mm_struct and address space
|
|
*/
|
|
static void delete_vma_from_mm(struct vm_area_struct *vma)
|
|
{
|
|
int i;
|
|
struct address_space *mapping;
|
|
struct mm_struct *mm = vma->vm_mm;
|
|
struct task_struct *curr = current;
|
|
|
|
kenter("%p", vma);
|
|
|
|
protect_vma(vma, 0);
|
|
|
|
mm->map_count--;
|
|
for (i = 0; i < VMACACHE_SIZE; i++) {
|
|
/* if the vma is cached, invalidate the entire cache */
|
|
if (curr->vmacache[i] == vma) {
|
|
vmacache_invalidate(mm);
|
|
break;
|
|
}
|
|
}
|
|
|
|
/* remove the VMA from the mapping */
|
|
if (vma->vm_file) {
|
|
mapping = vma->vm_file->f_mapping;
|
|
|
|
mutex_lock(&mapping->i_mmap_mutex);
|
|
flush_dcache_mmap_lock(mapping);
|
|
vma_interval_tree_remove(vma, &mapping->i_mmap);
|
|
flush_dcache_mmap_unlock(mapping);
|
|
mutex_unlock(&mapping->i_mmap_mutex);
|
|
}
|
|
|
|
/* remove from the MM's tree and list */
|
|
rb_erase(&vma->vm_rb, &mm->mm_rb);
|
|
|
|
if (vma->vm_prev)
|
|
vma->vm_prev->vm_next = vma->vm_next;
|
|
else
|
|
mm->mmap = vma->vm_next;
|
|
|
|
if (vma->vm_next)
|
|
vma->vm_next->vm_prev = vma->vm_prev;
|
|
}
|
|
|
|
/*
|
|
* destroy a VMA record
|
|
*/
|
|
static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma)
|
|
{
|
|
kenter("%p", vma);
|
|
if (vma->vm_ops && vma->vm_ops->close)
|
|
vma->vm_ops->close(vma);
|
|
if (vma->vm_file)
|
|
fput(vma->vm_file);
|
|
put_nommu_region(vma->vm_region);
|
|
kmem_cache_free(vm_area_cachep, vma);
|
|
}
|
|
|
|
/*
|
|
* look up the first VMA in which addr resides, NULL if none
|
|
* - should be called with mm->mmap_sem at least held readlocked
|
|
*/
|
|
struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
|
|
{
|
|
struct vm_area_struct *vma;
|
|
|
|
/* check the cache first */
|
|
vma = vmacache_find(mm, addr);
|
|
if (likely(vma))
|
|
return vma;
|
|
|
|
/* trawl the list (there may be multiple mappings in which addr
|
|
* resides) */
|
|
for (vma = mm->mmap; vma; vma = vma->vm_next) {
|
|
if (vma->vm_start > addr)
|
|
return NULL;
|
|
if (vma->vm_end > addr) {
|
|
vmacache_update(addr, vma);
|
|
return vma;
|
|
}
|
|
}
|
|
|
|
return NULL;
|
|
}
|
|
EXPORT_SYMBOL(find_vma);
|
|
|
|
/*
|
|
* find a VMA
|
|
* - we don't extend stack VMAs under NOMMU conditions
|
|
*/
|
|
struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned long addr)
|
|
{
|
|
return find_vma(mm, addr);
|
|
}
|
|
|
|
/*
|
|
* expand a stack to a given address
|
|
* - not supported under NOMMU conditions
|
|
*/
|
|
int expand_stack(struct vm_area_struct *vma, unsigned long address)
|
|
{
|
|
return -ENOMEM;
|
|
}
|
|
|
|
/*
|
|
* look up the first VMA exactly that exactly matches addr
|
|
* - should be called with mm->mmap_sem at least held readlocked
|
|
*/
|
|
static struct vm_area_struct *find_vma_exact(struct mm_struct *mm,
|
|
unsigned long addr,
|
|
unsigned long len)
|
|
{
|
|
struct vm_area_struct *vma;
|
|
unsigned long end = addr + len;
|
|
|
|
/* check the cache first */
|
|
vma = vmacache_find_exact(mm, addr, end);
|
|
if (vma)
|
|
return vma;
|
|
|
|
/* trawl the list (there may be multiple mappings in which addr
|
|
* resides) */
|
|
for (vma = mm->mmap; vma; vma = vma->vm_next) {
|
|
if (vma->vm_start < addr)
|
|
continue;
|
|
if (vma->vm_start > addr)
|
|
return NULL;
|
|
if (vma->vm_end == end) {
|
|
vmacache_update(addr, vma);
|
|
return vma;
|
|
}
|
|
}
|
|
|
|
return NULL;
|
|
}
|
|
|
|
/*
|
|
* determine whether a mapping should be permitted and, if so, what sort of
|
|
* mapping we're capable of supporting
|
|
*/
|
|
static int validate_mmap_request(struct file *file,
|
|
unsigned long addr,
|
|
unsigned long len,
|
|
unsigned long prot,
|
|
unsigned long flags,
|
|
unsigned long pgoff,
|
|
unsigned long *_capabilities)
|
|
{
|
|
unsigned long capabilities, rlen;
|
|
int ret;
|
|
|
|
/* do the simple checks first */
|
|
if (flags & MAP_FIXED) {
|
|
printk(KERN_DEBUG
|
|
"%d: Can't do fixed-address/overlay mmap of RAM\n",
|
|
current->pid);
|
|
return -EINVAL;
|
|
}
|
|
|
|
if ((flags & MAP_TYPE) != MAP_PRIVATE &&
|
|
(flags & MAP_TYPE) != MAP_SHARED)
|
|
return -EINVAL;
|
|
|
|
if (!len)
|
|
return -EINVAL;
|
|
|
|
/* Careful about overflows.. */
|
|
rlen = PAGE_ALIGN(len);
|
|
if (!rlen || rlen > TASK_SIZE)
|
|
return -ENOMEM;
|
|
|
|
/* offset overflow? */
|
|
if ((pgoff + (rlen >> PAGE_SHIFT)) < pgoff)
|
|
return -EOVERFLOW;
|
|
|
|
if (file) {
|
|
/* validate file mapping requests */
|
|
struct address_space *mapping;
|
|
|
|
/* files must support mmap */
|
|
if (!file->f_op->mmap)
|
|
return -ENODEV;
|
|
|
|
/* work out if what we've got could possibly be shared
|
|
* - we support chardevs that provide their own "memory"
|
|
* - we support files/blockdevs that are memory backed
|
|
*/
|
|
mapping = file->f_mapping;
|
|
if (!mapping)
|
|
mapping = file_inode(file)->i_mapping;
|
|
|
|
capabilities = 0;
|
|
if (mapping && mapping->backing_dev_info)
|
|
capabilities = mapping->backing_dev_info->capabilities;
|
|
|
|
if (!capabilities) {
|
|
/* no explicit capabilities set, so assume some
|
|
* defaults */
|
|
switch (file_inode(file)->i_mode & S_IFMT) {
|
|
case S_IFREG:
|
|
case S_IFBLK:
|
|
capabilities = BDI_CAP_MAP_COPY;
|
|
break;
|
|
|
|
case S_IFCHR:
|
|
capabilities =
|
|
BDI_CAP_MAP_DIRECT |
|
|
BDI_CAP_READ_MAP |
|
|
BDI_CAP_WRITE_MAP;
|
|
break;
|
|
|
|
default:
|
|
return -EINVAL;
|
|
}
|
|
}
|
|
|
|
/* eliminate any capabilities that we can't support on this
|
|
* device */
|
|
if (!file->f_op->get_unmapped_area)
|
|
capabilities &= ~BDI_CAP_MAP_DIRECT;
|
|
if (!file->f_op->read)
|
|
capabilities &= ~BDI_CAP_MAP_COPY;
|
|
|
|
/* The file shall have been opened with read permission. */
|
|
if (!(file->f_mode & FMODE_READ))
|
|
return -EACCES;
|
|
|
|
if (flags & MAP_SHARED) {
|
|
/* do checks for writing, appending and locking */
|
|
if ((prot & PROT_WRITE) &&
|
|
!(file->f_mode & FMODE_WRITE))
|
|
return -EACCES;
|
|
|
|
if (IS_APPEND(file_inode(file)) &&
|
|
(file->f_mode & FMODE_WRITE))
|
|
return -EACCES;
|
|
|
|
if (locks_verify_locked(file))
|
|
return -EAGAIN;
|
|
|
|
if (!(capabilities & BDI_CAP_MAP_DIRECT))
|
|
return -ENODEV;
|
|
|
|
/* we mustn't privatise shared mappings */
|
|
capabilities &= ~BDI_CAP_MAP_COPY;
|
|
} else {
|
|
/* we're going to read the file into private memory we
|
|
* allocate */
|
|
if (!(capabilities & BDI_CAP_MAP_COPY))
|
|
return -ENODEV;
|
|
|
|
/* we don't permit a private writable mapping to be
|
|
* shared with the backing device */
|
|
if (prot & PROT_WRITE)
|
|
capabilities &= ~BDI_CAP_MAP_DIRECT;
|
|
}
|
|
|
|
if (capabilities & BDI_CAP_MAP_DIRECT) {
|
|
if (((prot & PROT_READ) && !(capabilities & BDI_CAP_READ_MAP)) ||
|
|
((prot & PROT_WRITE) && !(capabilities & BDI_CAP_WRITE_MAP)) ||
|
|
((prot & PROT_EXEC) && !(capabilities & BDI_CAP_EXEC_MAP))
|
|
) {
|
|
capabilities &= ~BDI_CAP_MAP_DIRECT;
|
|
if (flags & MAP_SHARED) {
|
|
printk(KERN_WARNING
|
|
"MAP_SHARED not completely supported on !MMU\n");
|
|
return -EINVAL;
|
|
}
|
|
}
|
|
}
|
|
|
|
/* handle executable mappings and implied executable
|
|
* mappings */
|
|
if (file->f_path.mnt->mnt_flags & MNT_NOEXEC) {
|
|
if (prot & PROT_EXEC)
|
|
return -EPERM;
|
|
} else if ((prot & PROT_READ) && !(prot & PROT_EXEC)) {
|
|
/* handle implication of PROT_EXEC by PROT_READ */
|
|
if (current->personality & READ_IMPLIES_EXEC) {
|
|
if (capabilities & BDI_CAP_EXEC_MAP)
|
|
prot |= PROT_EXEC;
|
|
}
|
|
} else if ((prot & PROT_READ) &&
|
|
(prot & PROT_EXEC) &&
|
|
!(capabilities & BDI_CAP_EXEC_MAP)
|
|
) {
|
|
/* backing file is not executable, try to copy */
|
|
capabilities &= ~BDI_CAP_MAP_DIRECT;
|
|
}
|
|
} else {
|
|
/* anonymous mappings are always memory backed and can be
|
|
* privately mapped
|
|
*/
|
|
capabilities = BDI_CAP_MAP_COPY;
|
|
|
|
/* handle PROT_EXEC implication by PROT_READ */
|
|
if ((prot & PROT_READ) &&
|
|
(current->personality & READ_IMPLIES_EXEC))
|
|
prot |= PROT_EXEC;
|
|
}
|
|
|
|
/* allow the security API to have its say */
|
|
ret = security_mmap_addr(addr);
|
|
if (ret < 0)
|
|
return ret;
|
|
|
|
/* looks okay */
|
|
*_capabilities = capabilities;
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* we've determined that we can make the mapping, now translate what we
|
|
* now know into VMA flags
|
|
*/
|
|
static unsigned long determine_vm_flags(struct file *file,
|
|
unsigned long prot,
|
|
unsigned long flags,
|
|
unsigned long capabilities)
|
|
{
|
|
unsigned long vm_flags;
|
|
|
|
vm_flags = calc_vm_prot_bits(prot) | calc_vm_flag_bits(flags);
|
|
/* vm_flags |= mm->def_flags; */
|
|
|
|
if (!(capabilities & BDI_CAP_MAP_DIRECT)) {
|
|
/* attempt to share read-only copies of mapped file chunks */
|
|
vm_flags |= VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;
|
|
if (file && !(prot & PROT_WRITE))
|
|
vm_flags |= VM_MAYSHARE;
|
|
} else {
|
|
/* overlay a shareable mapping on the backing device or inode
|
|
* if possible - used for chardevs, ramfs/tmpfs/shmfs and
|
|
* romfs/cramfs */
|
|
vm_flags |= VM_MAYSHARE | (capabilities & BDI_CAP_VMFLAGS);
|
|
if (flags & MAP_SHARED)
|
|
vm_flags |= VM_SHARED;
|
|
}
|
|
|
|
/* refuse to let anyone share private mappings with this process if
|
|
* it's being traced - otherwise breakpoints set in it may interfere
|
|
* with another untraced process
|
|
*/
|
|
if ((flags & MAP_PRIVATE) && current->ptrace)
|
|
vm_flags &= ~VM_MAYSHARE;
|
|
|
|
return vm_flags;
|
|
}
|
|
|
|
/*
|
|
* set up a shared mapping on a file (the driver or filesystem provides and
|
|
* pins the storage)
|
|
*/
|
|
static int do_mmap_shared_file(struct vm_area_struct *vma)
|
|
{
|
|
int ret;
|
|
|
|
ret = vma->vm_file->f_op->mmap(vma->vm_file, vma);
|
|
if (ret == 0) {
|
|
vma->vm_region->vm_top = vma->vm_region->vm_end;
|
|
return 0;
|
|
}
|
|
if (ret != -ENOSYS)
|
|
return ret;
|
|
|
|
/* getting -ENOSYS indicates that direct mmap isn't possible (as
|
|
* opposed to tried but failed) so we can only give a suitable error as
|
|
* it's not possible to make a private copy if MAP_SHARED was given */
|
|
return -ENODEV;
|
|
}
|
|
|
|
/*
|
|
* set up a private mapping or an anonymous shared mapping
|
|
*/
|
|
static int do_mmap_private(struct vm_area_struct *vma,
|
|
struct vm_region *region,
|
|
unsigned long len,
|
|
unsigned long capabilities)
|
|
{
|
|
struct page *pages;
|
|
unsigned long total, point, n;
|
|
void *base;
|
|
int ret, order;
|
|
|
|
/* invoke the file's mapping function so that it can keep track of
|
|
* shared mappings on devices or memory
|
|
* - VM_MAYSHARE will be set if it may attempt to share
|
|
*/
|
|
if (capabilities & BDI_CAP_MAP_DIRECT) {
|
|
ret = vma->vm_file->f_op->mmap(vma->vm_file, vma);
|
|
if (ret == 0) {
|
|
/* shouldn't return success if we're not sharing */
|
|
BUG_ON(!(vma->vm_flags & VM_MAYSHARE));
|
|
vma->vm_region->vm_top = vma->vm_region->vm_end;
|
|
return 0;
|
|
}
|
|
if (ret != -ENOSYS)
|
|
return ret;
|
|
|
|
/* getting an ENOSYS error indicates that direct mmap isn't
|
|
* possible (as opposed to tried but failed) so we'll try to
|
|
* make a private copy of the data and map that instead */
|
|
}
|
|
|
|
|
|
/* allocate some memory to hold the mapping
|
|
* - note that this may not return a page-aligned address if the object
|
|
* we're allocating is smaller than a page
|
|
*/
|
|
order = get_order(len);
|
|
kdebug("alloc order %d for %lx", order, len);
|
|
|
|
pages = alloc_pages(GFP_KERNEL, order);
|
|
if (!pages)
|
|
goto enomem;
|
|
|
|
total = 1 << order;
|
|
atomic_long_add(total, &mmap_pages_allocated);
|
|
|
|
point = len >> PAGE_SHIFT;
|
|
|
|
/* we allocated a power-of-2 sized page set, so we may want to trim off
|
|
* the excess */
|
|
if (sysctl_nr_trim_pages && total - point >= sysctl_nr_trim_pages) {
|
|
while (total > point) {
|
|
order = ilog2(total - point);
|
|
n = 1 << order;
|
|
kdebug("shave %lu/%lu @%lu", n, total - point, total);
|
|
atomic_long_sub(n, &mmap_pages_allocated);
|
|
total -= n;
|
|
set_page_refcounted(pages + total);
|
|
__free_pages(pages + total, order);
|
|
}
|
|
}
|
|
|
|
for (point = 1; point < total; point++)
|
|
set_page_refcounted(&pages[point]);
|
|
|
|
base = page_address(pages);
|
|
region->vm_flags = vma->vm_flags |= VM_MAPPED_COPY;
|
|
region->vm_start = (unsigned long) base;
|
|
region->vm_end = region->vm_start + len;
|
|
region->vm_top = region->vm_start + (total << PAGE_SHIFT);
|
|
|
|
vma->vm_start = region->vm_start;
|
|
vma->vm_end = region->vm_start + len;
|
|
|
|
if (vma->vm_file) {
|
|
/* read the contents of a file into the copy */
|
|
mm_segment_t old_fs;
|
|
loff_t fpos;
|
|
|
|
fpos = vma->vm_pgoff;
|
|
fpos <<= PAGE_SHIFT;
|
|
|
|
old_fs = get_fs();
|
|
set_fs(KERNEL_DS);
|
|
ret = vma->vm_file->f_op->read(vma->vm_file, base, len, &fpos);
|
|
set_fs(old_fs);
|
|
|
|
if (ret < 0)
|
|
goto error_free;
|
|
|
|
/* clear the last little bit */
|
|
if (ret < len)
|
|
memset(base + ret, 0, len - ret);
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
error_free:
|
|
free_page_series(region->vm_start, region->vm_top);
|
|
region->vm_start = vma->vm_start = 0;
|
|
region->vm_end = vma->vm_end = 0;
|
|
region->vm_top = 0;
|
|
return ret;
|
|
|
|
enomem:
|
|
pr_err("Allocation of length %lu from process %d (%s) failed\n",
|
|
len, current->pid, current->comm);
|
|
show_free_areas(0);
|
|
return -ENOMEM;
|
|
}
|
|
|
|
/*
|
|
* handle mapping creation for uClinux
|
|
*/
|
|
unsigned long do_mmap_pgoff(struct file *file,
|
|
unsigned long addr,
|
|
unsigned long len,
|
|
unsigned long prot,
|
|
unsigned long flags,
|
|
unsigned long pgoff,
|
|
unsigned long *populate)
|
|
{
|
|
struct vm_area_struct *vma;
|
|
struct vm_region *region;
|
|
struct rb_node *rb;
|
|
unsigned long capabilities, vm_flags, result;
|
|
int ret;
|
|
|
|
kenter(",%lx,%lx,%lx,%lx,%lx", addr, len, prot, flags, pgoff);
|
|
|
|
*populate = 0;
|
|
|
|
/* decide whether we should attempt the mapping, and if so what sort of
|
|
* mapping */
|
|
ret = validate_mmap_request(file, addr, len, prot, flags, pgoff,
|
|
&capabilities);
|
|
if (ret < 0) {
|
|
kleave(" = %d [val]", ret);
|
|
return ret;
|
|
}
|
|
|
|
/* we ignore the address hint */
|
|
addr = 0;
|
|
len = PAGE_ALIGN(len);
|
|
|
|
/* we've determined that we can make the mapping, now translate what we
|
|
* now know into VMA flags */
|
|
vm_flags = determine_vm_flags(file, prot, flags, capabilities);
|
|
|
|
/* we're going to need to record the mapping */
|
|
region = kmem_cache_zalloc(vm_region_jar, GFP_KERNEL);
|
|
if (!region)
|
|
goto error_getting_region;
|
|
|
|
vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
|
|
if (!vma)
|
|
goto error_getting_vma;
|
|
|
|
region->vm_usage = 1;
|
|
region->vm_flags = vm_flags;
|
|
region->vm_pgoff = pgoff;
|
|
|
|
INIT_LIST_HEAD(&vma->anon_vma_chain);
|
|
vma->vm_flags = vm_flags;
|
|
vma->vm_pgoff = pgoff;
|
|
|
|
if (file) {
|
|
region->vm_file = get_file(file);
|
|
vma->vm_file = get_file(file);
|
|
}
|
|
|
|
down_write(&nommu_region_sem);
|
|
|
|
/* if we want to share, we need to check for regions created by other
|
|
* mmap() calls that overlap with our proposed mapping
|
|
* - we can only share with a superset match on most regular files
|
|
* - shared mappings on character devices and memory backed files are
|
|
* permitted to overlap inexactly as far as we are concerned for in
|
|
* these cases, sharing is handled in the driver or filesystem rather
|
|
* than here
|
|
*/
|
|
if (vm_flags & VM_MAYSHARE) {
|
|
struct vm_region *pregion;
|
|
unsigned long pglen, rpglen, pgend, rpgend, start;
|
|
|
|
pglen = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
|
|
pgend = pgoff + pglen;
|
|
|
|
for (rb = rb_first(&nommu_region_tree); rb; rb = rb_next(rb)) {
|
|
pregion = rb_entry(rb, struct vm_region, vm_rb);
|
|
|
|
if (!(pregion->vm_flags & VM_MAYSHARE))
|
|
continue;
|
|
|
|
/* search for overlapping mappings on the same file */
|
|
if (file_inode(pregion->vm_file) !=
|
|
file_inode(file))
|
|
continue;
|
|
|
|
if (pregion->vm_pgoff >= pgend)
|
|
continue;
|
|
|
|
rpglen = pregion->vm_end - pregion->vm_start;
|
|
rpglen = (rpglen + PAGE_SIZE - 1) >> PAGE_SHIFT;
|
|
rpgend = pregion->vm_pgoff + rpglen;
|
|
if (pgoff >= rpgend)
|
|
continue;
|
|
|
|
/* handle inexactly overlapping matches between
|
|
* mappings */
|
|
if ((pregion->vm_pgoff != pgoff || rpglen != pglen) &&
|
|
!(pgoff >= pregion->vm_pgoff && pgend <= rpgend)) {
|
|
/* new mapping is not a subset of the region */
|
|
if (!(capabilities & BDI_CAP_MAP_DIRECT))
|
|
goto sharing_violation;
|
|
continue;
|
|
}
|
|
|
|
/* we've found a region we can share */
|
|
pregion->vm_usage++;
|
|
vma->vm_region = pregion;
|
|
start = pregion->vm_start;
|
|
start += (pgoff - pregion->vm_pgoff) << PAGE_SHIFT;
|
|
vma->vm_start = start;
|
|
vma->vm_end = start + len;
|
|
|
|
if (pregion->vm_flags & VM_MAPPED_COPY) {
|
|
kdebug("share copy");
|
|
vma->vm_flags |= VM_MAPPED_COPY;
|
|
} else {
|
|
kdebug("share mmap");
|
|
ret = do_mmap_shared_file(vma);
|
|
if (ret < 0) {
|
|
vma->vm_region = NULL;
|
|
vma->vm_start = 0;
|
|
vma->vm_end = 0;
|
|
pregion->vm_usage--;
|
|
pregion = NULL;
|
|
goto error_just_free;
|
|
}
|
|
}
|
|
fput(region->vm_file);
|
|
kmem_cache_free(vm_region_jar, region);
|
|
region = pregion;
|
|
result = start;
|
|
goto share;
|
|
}
|
|
|
|
/* obtain the address at which to make a shared mapping
|
|
* - this is the hook for quasi-memory character devices to
|
|
* tell us the location of a shared mapping
|
|
*/
|
|
if (capabilities & BDI_CAP_MAP_DIRECT) {
|
|
addr = file->f_op->get_unmapped_area(file, addr, len,
|
|
pgoff, flags);
|
|
if (IS_ERR_VALUE(addr)) {
|
|
ret = addr;
|
|
if (ret != -ENOSYS)
|
|
goto error_just_free;
|
|
|
|
/* the driver refused to tell us where to site
|
|
* the mapping so we'll have to attempt to copy
|
|
* it */
|
|
ret = -ENODEV;
|
|
if (!(capabilities & BDI_CAP_MAP_COPY))
|
|
goto error_just_free;
|
|
|
|
capabilities &= ~BDI_CAP_MAP_DIRECT;
|
|
} else {
|
|
vma->vm_start = region->vm_start = addr;
|
|
vma->vm_end = region->vm_end = addr + len;
|
|
}
|
|
}
|
|
}
|
|
|
|
vma->vm_region = region;
|
|
|
|
/* set up the mapping
|
|
* - the region is filled in if BDI_CAP_MAP_DIRECT is still set
|
|
*/
|
|
if (file && vma->vm_flags & VM_SHARED)
|
|
ret = do_mmap_shared_file(vma);
|
|
else
|
|
ret = do_mmap_private(vma, region, len, capabilities);
|
|
if (ret < 0)
|
|
goto error_just_free;
|
|
add_nommu_region(region);
|
|
|
|
/* clear anonymous mappings that don't ask for uninitialized data */
|
|
if (!vma->vm_file && !(flags & MAP_UNINITIALIZED))
|
|
memset((void *)region->vm_start, 0,
|
|
region->vm_end - region->vm_start);
|
|
|
|
/* okay... we have a mapping; now we have to register it */
|
|
result = vma->vm_start;
|
|
|
|
current->mm->total_vm += len >> PAGE_SHIFT;
|
|
|
|
share:
|
|
add_vma_to_mm(current->mm, vma);
|
|
|
|
/* we flush the region from the icache only when the first executable
|
|
* mapping of it is made */
|
|
if (vma->vm_flags & VM_EXEC && !region->vm_icache_flushed) {
|
|
flush_icache_range(region->vm_start, region->vm_end);
|
|
region->vm_icache_flushed = true;
|
|
}
|
|
|
|
up_write(&nommu_region_sem);
|
|
|
|
kleave(" = %lx", result);
|
|
return result;
|
|
|
|
error_just_free:
|
|
up_write(&nommu_region_sem);
|
|
error:
|
|
if (region->vm_file)
|
|
fput(region->vm_file);
|
|
kmem_cache_free(vm_region_jar, region);
|
|
if (vma->vm_file)
|
|
fput(vma->vm_file);
|
|
kmem_cache_free(vm_area_cachep, vma);
|
|
kleave(" = %d", ret);
|
|
return ret;
|
|
|
|
sharing_violation:
|
|
up_write(&nommu_region_sem);
|
|
printk(KERN_WARNING "Attempt to share mismatched mappings\n");
|
|
ret = -EINVAL;
|
|
goto error;
|
|
|
|
error_getting_vma:
|
|
kmem_cache_free(vm_region_jar, region);
|
|
printk(KERN_WARNING "Allocation of vma for %lu byte allocation"
|
|
" from process %d failed\n",
|
|
len, current->pid);
|
|
show_free_areas(0);
|
|
return -ENOMEM;
|
|
|
|
error_getting_region:
|
|
printk(KERN_WARNING "Allocation of vm region for %lu byte allocation"
|
|
" from process %d failed\n",
|
|
len, current->pid);
|
|
show_free_areas(0);
|
|
return -ENOMEM;
|
|
}
|
|
|
|
SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
|
|
unsigned long, prot, unsigned long, flags,
|
|
unsigned long, fd, unsigned long, pgoff)
|
|
{
|
|
struct file *file = NULL;
|
|
unsigned long retval = -EBADF;
|
|
|
|
audit_mmap_fd(fd, flags);
|
|
if (!(flags & MAP_ANONYMOUS)) {
|
|
file = fget(fd);
|
|
if (!file)
|
|
goto out;
|
|
}
|
|
|
|
flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
|
|
|
|
retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff);
|
|
|
|
if (file)
|
|
fput(file);
|
|
out:
|
|
return retval;
|
|
}
|
|
|
|
#ifdef __ARCH_WANT_SYS_OLD_MMAP
|
|
struct mmap_arg_struct {
|
|
unsigned long addr;
|
|
unsigned long len;
|
|
unsigned long prot;
|
|
unsigned long flags;
|
|
unsigned long fd;
|
|
unsigned long offset;
|
|
};
|
|
|
|
SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg)
|
|
{
|
|
struct mmap_arg_struct a;
|
|
|
|
if (copy_from_user(&a, arg, sizeof(a)))
|
|
return -EFAULT;
|
|
if (a.offset & ~PAGE_MASK)
|
|
return -EINVAL;
|
|
|
|
return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd,
|
|
a.offset >> PAGE_SHIFT);
|
|
}
|
|
#endif /* __ARCH_WANT_SYS_OLD_MMAP */
|
|
|
|
/*
|
|
* split a vma into two pieces at address 'addr', a new vma is allocated either
|
|
* for the first part or the tail.
|
|
*/
|
|
int split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
|
|
unsigned long addr, int new_below)
|
|
{
|
|
struct vm_area_struct *new;
|
|
struct vm_region *region;
|
|
unsigned long npages;
|
|
|
|
kenter("");
|
|
|
|
/* we're only permitted to split anonymous regions (these should have
|
|
* only a single usage on the region) */
|
|
if (vma->vm_file)
|
|
return -ENOMEM;
|
|
|
|
if (mm->map_count >= sysctl_max_map_count)
|
|
return -ENOMEM;
|
|
|
|
region = kmem_cache_alloc(vm_region_jar, GFP_KERNEL);
|
|
if (!region)
|
|
return -ENOMEM;
|
|
|
|
new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
|
|
if (!new) {
|
|
kmem_cache_free(vm_region_jar, region);
|
|
return -ENOMEM;
|
|
}
|
|
|
|
/* most fields are the same, copy all, and then fixup */
|
|
*new = *vma;
|
|
*region = *vma->vm_region;
|
|
new->vm_region = region;
|
|
|
|
npages = (addr - vma->vm_start) >> PAGE_SHIFT;
|
|
|
|
if (new_below) {
|
|
region->vm_top = region->vm_end = new->vm_end = addr;
|
|
} else {
|
|
region->vm_start = new->vm_start = addr;
|
|
region->vm_pgoff = new->vm_pgoff += npages;
|
|
}
|
|
|
|
if (new->vm_ops && new->vm_ops->open)
|
|
new->vm_ops->open(new);
|
|
|
|
delete_vma_from_mm(vma);
|
|
down_write(&nommu_region_sem);
|
|
delete_nommu_region(vma->vm_region);
|
|
if (new_below) {
|
|
vma->vm_region->vm_start = vma->vm_start = addr;
|
|
vma->vm_region->vm_pgoff = vma->vm_pgoff += npages;
|
|
} else {
|
|
vma->vm_region->vm_end = vma->vm_end = addr;
|
|
vma->vm_region->vm_top = addr;
|
|
}
|
|
add_nommu_region(vma->vm_region);
|
|
add_nommu_region(new->vm_region);
|
|
up_write(&nommu_region_sem);
|
|
add_vma_to_mm(mm, vma);
|
|
add_vma_to_mm(mm, new);
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* shrink a VMA by removing the specified chunk from either the beginning or
|
|
* the end
|
|
*/
|
|
static int shrink_vma(struct mm_struct *mm,
|
|
struct vm_area_struct *vma,
|
|
unsigned long from, unsigned long to)
|
|
{
|
|
struct vm_region *region;
|
|
|
|
kenter("");
|
|
|
|
/* adjust the VMA's pointers, which may reposition it in the MM's tree
|
|
* and list */
|
|
delete_vma_from_mm(vma);
|
|
if (from > vma->vm_start)
|
|
vma->vm_end = from;
|
|
else
|
|
vma->vm_start = to;
|
|
add_vma_to_mm(mm, vma);
|
|
|
|
/* cut the backing region down to size */
|
|
region = vma->vm_region;
|
|
BUG_ON(region->vm_usage != 1);
|
|
|
|
down_write(&nommu_region_sem);
|
|
delete_nommu_region(region);
|
|
if (from > region->vm_start) {
|
|
to = region->vm_top;
|
|
region->vm_top = region->vm_end = from;
|
|
} else {
|
|
region->vm_start = to;
|
|
}
|
|
add_nommu_region(region);
|
|
up_write(&nommu_region_sem);
|
|
|
|
free_page_series(from, to);
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* release a mapping
|
|
* - under NOMMU conditions the chunk to be unmapped must be backed by a single
|
|
* VMA, though it need not cover the whole VMA
|
|
*/
|
|
int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
|
|
{
|
|
struct vm_area_struct *vma;
|
|
unsigned long end;
|
|
int ret;
|
|
|
|
kenter(",%lx,%zx", start, len);
|
|
|
|
len = PAGE_ALIGN(len);
|
|
if (len == 0)
|
|
return -EINVAL;
|
|
|
|
end = start + len;
|
|
|
|
/* find the first potentially overlapping VMA */
|
|
vma = find_vma(mm, start);
|
|
if (!vma) {
|
|
static int limit;
|
|
if (limit < 5) {
|
|
printk(KERN_WARNING
|
|
"munmap of memory not mmapped by process %d"
|
|
" (%s): 0x%lx-0x%lx\n",
|
|
current->pid, current->comm,
|
|
start, start + len - 1);
|
|
limit++;
|
|
}
|
|
return -EINVAL;
|
|
}
|
|
|
|
/* we're allowed to split an anonymous VMA but not a file-backed one */
|
|
if (vma->vm_file) {
|
|
do {
|
|
if (start > vma->vm_start) {
|
|
kleave(" = -EINVAL [miss]");
|
|
return -EINVAL;
|
|
}
|
|
if (end == vma->vm_end)
|
|
goto erase_whole_vma;
|
|
vma = vma->vm_next;
|
|
} while (vma);
|
|
kleave(" = -EINVAL [split file]");
|
|
return -EINVAL;
|
|
} else {
|
|
/* the chunk must be a subset of the VMA found */
|
|
if (start == vma->vm_start && end == vma->vm_end)
|
|
goto erase_whole_vma;
|
|
if (start < vma->vm_start || end > vma->vm_end) {
|
|
kleave(" = -EINVAL [superset]");
|
|
return -EINVAL;
|
|
}
|
|
if (start & ~PAGE_MASK) {
|
|
kleave(" = -EINVAL [unaligned start]");
|
|
return -EINVAL;
|
|
}
|
|
if (end != vma->vm_end && end & ~PAGE_MASK) {
|
|
kleave(" = -EINVAL [unaligned split]");
|
|
return -EINVAL;
|
|
}
|
|
if (start != vma->vm_start && end != vma->vm_end) {
|
|
ret = split_vma(mm, vma, start, 1);
|
|
if (ret < 0) {
|
|
kleave(" = %d [split]", ret);
|
|
return ret;
|
|
}
|
|
}
|
|
return shrink_vma(mm, vma, start, end);
|
|
}
|
|
|
|
erase_whole_vma:
|
|
delete_vma_from_mm(vma);
|
|
delete_vma(mm, vma);
|
|
kleave(" = 0");
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL(do_munmap);
|
|
|
|
int vm_munmap(unsigned long addr, size_t len)
|
|
{
|
|
struct mm_struct *mm = current->mm;
|
|
int ret;
|
|
|
|
down_write(&mm->mmap_sem);
|
|
ret = do_munmap(mm, addr, len);
|
|
up_write(&mm->mmap_sem);
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL(vm_munmap);
|
|
|
|
SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len)
|
|
{
|
|
return vm_munmap(addr, len);
|
|
}
|
|
|
|
/*
|
|
* release all the mappings made in a process's VM space
|
|
*/
|
|
void exit_mmap(struct mm_struct *mm)
|
|
{
|
|
struct vm_area_struct *vma;
|
|
|
|
if (!mm)
|
|
return;
|
|
|
|
kenter("");
|
|
|
|
mm->total_vm = 0;
|
|
|
|
while ((vma = mm->mmap)) {
|
|
mm->mmap = vma->vm_next;
|
|
delete_vma_from_mm(vma);
|
|
delete_vma(mm, vma);
|
|
cond_resched();
|
|
}
|
|
|
|
kleave("");
|
|
}
|
|
|
|
unsigned long vm_brk(unsigned long addr, unsigned long len)
|
|
{
|
|
return -ENOMEM;
|
|
}
|
|
|
|
/*
|
|
* expand (or shrink) an existing mapping, potentially moving it at the same
|
|
* time (controlled by the MREMAP_MAYMOVE flag and available VM space)
|
|
*
|
|
* under NOMMU conditions, we only permit changing a mapping's size, and only
|
|
* as long as it stays within the region allocated by do_mmap_private() and the
|
|
* block is not shareable
|
|
*
|
|
* MREMAP_FIXED is not supported under NOMMU conditions
|
|
*/
|
|
static unsigned long do_mremap(unsigned long addr,
|
|
unsigned long old_len, unsigned long new_len,
|
|
unsigned long flags, unsigned long new_addr)
|
|
{
|
|
struct vm_area_struct *vma;
|
|
|
|
/* insanity checks first */
|
|
old_len = PAGE_ALIGN(old_len);
|
|
new_len = PAGE_ALIGN(new_len);
|
|
if (old_len == 0 || new_len == 0)
|
|
return (unsigned long) -EINVAL;
|
|
|
|
if (addr & ~PAGE_MASK)
|
|
return -EINVAL;
|
|
|
|
if (flags & MREMAP_FIXED && new_addr != addr)
|
|
return (unsigned long) -EINVAL;
|
|
|
|
vma = find_vma_exact(current->mm, addr, old_len);
|
|
if (!vma)
|
|
return (unsigned long) -EINVAL;
|
|
|
|
if (vma->vm_end != vma->vm_start + old_len)
|
|
return (unsigned long) -EFAULT;
|
|
|
|
if (vma->vm_flags & VM_MAYSHARE)
|
|
return (unsigned long) -EPERM;
|
|
|
|
if (new_len > vma->vm_region->vm_end - vma->vm_region->vm_start)
|
|
return (unsigned long) -ENOMEM;
|
|
|
|
/* all checks complete - do it */
|
|
vma->vm_end = vma->vm_start + new_len;
|
|
return vma->vm_start;
|
|
}
|
|
|
|
SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
|
|
unsigned long, new_len, unsigned long, flags,
|
|
unsigned long, new_addr)
|
|
{
|
|
unsigned long ret;
|
|
|
|
down_write(¤t->mm->mmap_sem);
|
|
ret = do_mremap(addr, old_len, new_len, flags, new_addr);
|
|
up_write(¤t->mm->mmap_sem);
|
|
return ret;
|
|
}
|
|
|
|
struct page *follow_page_mask(struct vm_area_struct *vma,
|
|
unsigned long address, unsigned int flags,
|
|
unsigned int *page_mask)
|
|
{
|
|
*page_mask = 0;
|
|
return NULL;
|
|
}
|
|
|
|
int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
|
|
unsigned long pfn, unsigned long size, pgprot_t prot)
|
|
{
|
|
if (addr != (pfn << PAGE_SHIFT))
|
|
return -EINVAL;
|
|
|
|
vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP;
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL(remap_pfn_range);
|
|
|
|
int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len)
|
|
{
|
|
unsigned long pfn = start >> PAGE_SHIFT;
|
|
unsigned long vm_len = vma->vm_end - vma->vm_start;
|
|
|
|
pfn += vma->vm_pgoff;
|
|
return io_remap_pfn_range(vma, vma->vm_start, pfn, vm_len, vma->vm_page_prot);
|
|
}
|
|
EXPORT_SYMBOL(vm_iomap_memory);
|
|
|
|
int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
|
|
unsigned long pgoff)
|
|
{
|
|
unsigned int size = vma->vm_end - vma->vm_start;
|
|
|
|
if (!(vma->vm_flags & VM_USERMAP))
|
|
return -EINVAL;
|
|
|
|
vma->vm_start = (unsigned long)(addr + (pgoff << PAGE_SHIFT));
|
|
vma->vm_end = vma->vm_start + size;
|
|
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL(remap_vmalloc_range);
|
|
|
|
unsigned long arch_get_unmapped_area(struct file *file, unsigned long addr,
|
|
unsigned long len, unsigned long pgoff, unsigned long flags)
|
|
{
|
|
return -ENOMEM;
|
|
}
|
|
|
|
void unmap_mapping_range(struct address_space *mapping,
|
|
loff_t const holebegin, loff_t const holelen,
|
|
int even_cows)
|
|
{
|
|
}
|
|
EXPORT_SYMBOL(unmap_mapping_range);
|
|
|
|
/*
|
|
* Check that a process has enough memory to allocate a new virtual
|
|
* mapping. 0 means there is enough memory for the allocation to
|
|
* succeed and -ENOMEM implies there is not.
|
|
*
|
|
* We currently support three overcommit policies, which are set via the
|
|
* vm.overcommit_memory sysctl. See Documentation/vm/overcommit-accounting
|
|
*
|
|
* Strict overcommit modes added 2002 Feb 26 by Alan Cox.
|
|
* Additional code 2002 Jul 20 by Robert Love.
|
|
*
|
|
* cap_sys_admin is 1 if the process has admin privileges, 0 otherwise.
|
|
*
|
|
* Note this is a helper function intended to be used by LSMs which
|
|
* wish to use this logic.
|
|
*/
|
|
int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
|
|
{
|
|
unsigned long free, allowed, reserve;
|
|
|
|
vm_acct_memory(pages);
|
|
|
|
/*
|
|
* Sometimes we want to use more memory than we have
|
|
*/
|
|
if (sysctl_overcommit_memory == OVERCOMMIT_ALWAYS)
|
|
return 0;
|
|
|
|
if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) {
|
|
free = global_page_state(NR_FREE_PAGES);
|
|
free += global_page_state(NR_FILE_PAGES);
|
|
|
|
/*
|
|
* shmem pages shouldn't be counted as free in this
|
|
* case, they can't be purged, only swapped out, and
|
|
* that won't affect the overall amount of available
|
|
* memory in the system.
|
|
*/
|
|
free -= global_page_state(NR_SHMEM);
|
|
|
|
free += get_nr_swap_pages();
|
|
|
|
/*
|
|
* Any slabs which are created with the
|
|
* SLAB_RECLAIM_ACCOUNT flag claim to have contents
|
|
* which are reclaimable, under pressure. The dentry
|
|
* cache and most inode caches should fall into this
|
|
*/
|
|
free += global_page_state(NR_SLAB_RECLAIMABLE);
|
|
|
|
/*
|
|
* Leave reserved pages. The pages are not for anonymous pages.
|
|
*/
|
|
if (free <= totalreserve_pages)
|
|
goto error;
|
|
else
|
|
free -= totalreserve_pages;
|
|
|
|
/*
|
|
* Reserve some for root
|
|
*/
|
|
if (!cap_sys_admin)
|
|
free -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10);
|
|
|
|
if (free > pages)
|
|
return 0;
|
|
|
|
goto error;
|
|
}
|
|
|
|
allowed = vm_commit_limit();
|
|
/*
|
|
* Reserve some 3% for root
|
|
*/
|
|
if (!cap_sys_admin)
|
|
allowed -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10);
|
|
|
|
/*
|
|
* Don't let a single process grow so big a user can't recover
|
|
*/
|
|
if (mm) {
|
|
reserve = sysctl_user_reserve_kbytes >> (PAGE_SHIFT - 10);
|
|
allowed -= min(mm->total_vm / 32, reserve);
|
|
}
|
|
|
|
if (percpu_counter_read_positive(&vm_committed_as) < allowed)
|
|
return 0;
|
|
|
|
error:
|
|
vm_unacct_memory(pages);
|
|
|
|
return -ENOMEM;
|
|
}
|
|
|
|
int in_gate_area_no_mm(unsigned long addr)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
|
|
{
|
|
BUG();
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL(filemap_fault);
|
|
|
|
void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf)
|
|
{
|
|
BUG();
|
|
}
|
|
EXPORT_SYMBOL(filemap_map_pages);
|
|
|
|
int generic_file_remap_pages(struct vm_area_struct *vma, unsigned long addr,
|
|
unsigned long size, pgoff_t pgoff)
|
|
{
|
|
BUG();
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL(generic_file_remap_pages);
|
|
|
|
static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
|
|
unsigned long addr, void *buf, int len, int write)
|
|
{
|
|
struct vm_area_struct *vma;
|
|
|
|
down_read(&mm->mmap_sem);
|
|
|
|
/* the access must start within one of the target process's mappings */
|
|
vma = find_vma(mm, addr);
|
|
if (vma) {
|
|
/* don't overrun this mapping */
|
|
if (addr + len >= vma->vm_end)
|
|
len = vma->vm_end - addr;
|
|
|
|
/* only read or write mappings where it is permitted */
|
|
if (write && vma->vm_flags & VM_MAYWRITE)
|
|
copy_to_user_page(vma, NULL, addr,
|
|
(void *) addr, buf, len);
|
|
else if (!write && vma->vm_flags & VM_MAYREAD)
|
|
copy_from_user_page(vma, NULL, addr,
|
|
buf, (void *) addr, len);
|
|
else
|
|
len = 0;
|
|
} else {
|
|
len = 0;
|
|
}
|
|
|
|
up_read(&mm->mmap_sem);
|
|
|
|
return len;
|
|
}
|
|
|
|
/**
|
|
* @access_remote_vm - access another process' address space
|
|
* @mm: the mm_struct of the target address space
|
|
* @addr: start address to access
|
|
* @buf: source or destination buffer
|
|
* @len: number of bytes to transfer
|
|
* @write: whether the access is a write
|
|
*
|
|
* The caller must hold a reference on @mm.
|
|
*/
|
|
int access_remote_vm(struct mm_struct *mm, unsigned long addr,
|
|
void *buf, int len, int write)
|
|
{
|
|
return __access_remote_vm(NULL, mm, addr, buf, len, write);
|
|
}
|
|
|
|
/*
|
|
* Access another process' address space.
|
|
* - source/target buffer must be kernel space
|
|
*/
|
|
int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write)
|
|
{
|
|
struct mm_struct *mm;
|
|
|
|
if (addr + len < addr)
|
|
return 0;
|
|
|
|
mm = get_task_mm(tsk);
|
|
if (!mm)
|
|
return 0;
|
|
|
|
len = __access_remote_vm(tsk, mm, addr, buf, len, write);
|
|
|
|
mmput(mm);
|
|
return len;
|
|
}
|
|
|
|
/**
|
|
* nommu_shrink_inode_mappings - Shrink the shared mappings on an inode
|
|
* @inode: The inode to check
|
|
* @size: The current filesize of the inode
|
|
* @newsize: The proposed filesize of the inode
|
|
*
|
|
* Check the shared mappings on an inode on behalf of a shrinking truncate to
|
|
* make sure that that any outstanding VMAs aren't broken and then shrink the
|
|
* vm_regions that extend that beyond so that do_mmap_pgoff() doesn't
|
|
* automatically grant mappings that are too large.
|
|
*/
|
|
int nommu_shrink_inode_mappings(struct inode *inode, size_t size,
|
|
size_t newsize)
|
|
{
|
|
struct vm_area_struct *vma;
|
|
struct vm_region *region;
|
|
pgoff_t low, high;
|
|
size_t r_size, r_top;
|
|
|
|
low = newsize >> PAGE_SHIFT;
|
|
high = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
|
|
|
|
down_write(&nommu_region_sem);
|
|
mutex_lock(&inode->i_mapping->i_mmap_mutex);
|
|
|
|
/* search for VMAs that fall within the dead zone */
|
|
vma_interval_tree_foreach(vma, &inode->i_mapping->i_mmap, low, high) {
|
|
/* found one - only interested if it's shared out of the page
|
|
* cache */
|
|
if (vma->vm_flags & VM_SHARED) {
|
|
mutex_unlock(&inode->i_mapping->i_mmap_mutex);
|
|
up_write(&nommu_region_sem);
|
|
return -ETXTBSY; /* not quite true, but near enough */
|
|
}
|
|
}
|
|
|
|
/* reduce any regions that overlap the dead zone - if in existence,
|
|
* these will be pointed to by VMAs that don't overlap the dead zone
|
|
*
|
|
* we don't check for any regions that start beyond the EOF as there
|
|
* shouldn't be any
|
|
*/
|
|
vma_interval_tree_foreach(vma, &inode->i_mapping->i_mmap,
|
|
0, ULONG_MAX) {
|
|
if (!(vma->vm_flags & VM_SHARED))
|
|
continue;
|
|
|
|
region = vma->vm_region;
|
|
r_size = region->vm_top - region->vm_start;
|
|
r_top = (region->vm_pgoff << PAGE_SHIFT) + r_size;
|
|
|
|
if (r_top > newsize) {
|
|
region->vm_top -= r_top - newsize;
|
|
if (region->vm_end > region->vm_top)
|
|
region->vm_end = region->vm_top;
|
|
}
|
|
}
|
|
|
|
mutex_unlock(&inode->i_mapping->i_mmap_mutex);
|
|
up_write(&nommu_region_sem);
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Initialise sysctl_user_reserve_kbytes.
|
|
*
|
|
* This is intended to prevent a user from starting a single memory hogging
|
|
* process, such that they cannot recover (kill the hog) in OVERCOMMIT_NEVER
|
|
* mode.
|
|
*
|
|
* The default value is min(3% of free memory, 128MB)
|
|
* 128MB is enough to recover with sshd/login, bash, and top/kill.
|
|
*/
|
|
static int __meminit init_user_reserve(void)
|
|
{
|
|
unsigned long free_kbytes;
|
|
|
|
free_kbytes = global_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10);
|
|
|
|
sysctl_user_reserve_kbytes = min(free_kbytes / 32, 1UL << 17);
|
|
return 0;
|
|
}
|
|
module_init(init_user_reserve)
|
|
|
|
/*
|
|
* Initialise sysctl_admin_reserve_kbytes.
|
|
*
|
|
* The purpose of sysctl_admin_reserve_kbytes is to allow the sys admin
|
|
* to log in and kill a memory hogging process.
|
|
*
|
|
* Systems with more than 256MB will reserve 8MB, enough to recover
|
|
* with sshd, bash, and top in OVERCOMMIT_GUESS. Smaller systems will
|
|
* only reserve 3% of free pages by default.
|
|
*/
|
|
static int __meminit init_admin_reserve(void)
|
|
{
|
|
unsigned long free_kbytes;
|
|
|
|
free_kbytes = global_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10);
|
|
|
|
sysctl_admin_reserve_kbytes = min(free_kbytes / 32, 1UL << 13);
|
|
return 0;
|
|
}
|
|
module_init(init_admin_reserve)
|