aboutsummaryrefslogtreecommitdiff
path: root/drivers/char/mem.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/char/mem.c')
-rw-r--r--drivers/char/mem.c739
1 files changed, 366 insertions, 373 deletions
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index 20070b7c573..917403fe10d 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -3,9 +3,9 @@
*
* Copyright (C) 1991, 1992 Linus Torvalds
*
- * Added devfs support.
+ * Added devfs support.
* Jan-11-1998, C. Scott Ananian <cananian@alumni.princeton.edu>
- * Shared /dev/zero mmaping support, Feb 2000, Kanoj Sarcar <kanoj@sgi.com>
+ * Shared /dev/zero mmapping support, Feb 2000, Kanoj Sarcar <kanoj@sgi.com>
*/
#include <linux/mm.h>
@@ -21,144 +21,127 @@
#include <linux/ptrace.h>
#include <linux/device.h>
#include <linux/highmem.h>
-#include <linux/crash_dump.h>
#include <linux/backing-dev.h>
-#include <linux/bootmem.h>
#include <linux/splice.h>
#include <linux/pfn.h>
+#include <linux/export.h>
+#include <linux/io.h>
+#include <linux/aio.h>
#include <asm/uaccess.h>
-#include <asm/io.h>
#ifdef CONFIG_IA64
# include <linux/efi.h>
#endif
-/*
- * Architectures vary in how they handle caching for addresses
- * outside of main memory.
- *
- */
-static inline int uncached_access(struct file *file, unsigned long addr)
+#define DEVPORT_MINOR 4
+
+static inline unsigned long size_inside_page(unsigned long start,
+ unsigned long size)
{
-#if defined(__i386__) && !defined(__arch_um__)
- /*
- * On the PPro and successors, the MTRRs are used to set
- * memory types for physical addresses outside main memory,
- * so blindly setting PCD or PWT on those pages is wrong.
- * For Pentiums and earlier, the surround logic should disable
- * caching for the high addresses through the KEN pin, but
- * we maintain the tradition of paranoia in this code.
- */
- if (file->f_flags & O_SYNC)
- return 1;
- return !( test_bit(X86_FEATURE_MTRR, boot_cpu_data.x86_capability) ||
- test_bit(X86_FEATURE_K6_MTRR, boot_cpu_data.x86_capability) ||
- test_bit(X86_FEATURE_CYRIX_ARR, boot_cpu_data.x86_capability) ||
- test_bit(X86_FEATURE_CENTAUR_MCR, boot_cpu_data.x86_capability) )
- && addr >= __pa(high_memory);
-#elif defined(__x86_64__) && !defined(__arch_um__)
- /*
- * This is broken because it can generate memory type aliases,
- * which can cause cache corruptions
- * But it is only available for root and we have to be bug-to-bug
- * compatible with i386.
- */
- if (file->f_flags & O_SYNC)
- return 1;
- /* same behaviour as i386. PAT always set to cached and MTRRs control the
- caching behaviour.
- Hopefully a full PAT implementation will fix that soon. */
- return 0;
-#elif defined(CONFIG_IA64)
- /*
- * On ia64, we ignore O_SYNC because we cannot tolerate memory attribute aliases.
- */
- return !(efi_mem_attributes(addr) & EFI_MEMORY_WB);
-#elif defined(CONFIG_MIPS)
- {
- extern int __uncached_access(struct file *file,
- unsigned long addr);
+ unsigned long sz;
- return __uncached_access(file, addr);
- }
-#else
- /*
- * Accessing memory above the top the kernel knows about or through a file pointer
- * that was marked O_SYNC will be done non-cached.
- */
- if (file->f_flags & O_SYNC)
- return 1;
- return addr >= __pa(high_memory);
-#endif
+ sz = PAGE_SIZE - (start & (PAGE_SIZE - 1));
+
+ return min(sz, size);
}
#ifndef ARCH_HAS_VALID_PHYS_ADDR_RANGE
-static inline int valid_phys_addr_range(unsigned long addr, size_t count)
+static inline int valid_phys_addr_range(phys_addr_t addr, size_t count)
{
- if (addr + count > __pa(high_memory))
- return 0;
+ return addr + count <= __pa(high_memory);
+}
+static inline int valid_mmap_phys_addr_range(unsigned long pfn, size_t size)
+{
return 1;
}
+#endif
-static inline int valid_mmap_phys_addr_range(unsigned long pfn, size_t size)
+#ifdef CONFIG_STRICT_DEVMEM
+static inline int range_is_allowed(unsigned long pfn, unsigned long size)
+{
+ u64 from = ((u64)pfn) << PAGE_SHIFT;
+ u64 to = from + size;
+ u64 cursor = from;
+
+ while (cursor < to) {
+ if (!devmem_is_allowed(pfn)) {
+ printk(KERN_INFO
+ "Program %s tried to access /dev/mem between %Lx->%Lx.\n",
+ current->comm, from, to);
+ return 0;
+ }
+ cursor += PAGE_SIZE;
+ pfn++;
+ }
+ return 1;
+}
+#else
+static inline int range_is_allowed(unsigned long pfn, unsigned long size)
{
return 1;
}
#endif
+void __weak unxlate_dev_mem_ptr(unsigned long phys, void *addr)
+{
+}
+
/*
- * This funcion reads the *physical* memory. The f_pos points directly to the
- * memory location.
+ * This funcion reads the *physical* memory. The f_pos points directly to the
+ * memory location.
*/
-static ssize_t read_mem(struct file * file, char __user * buf,
+static ssize_t read_mem(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
- unsigned long p = *ppos;
+ phys_addr_t p = *ppos;
ssize_t read, sz;
char *ptr;
+ if (p != *ppos)
+ return 0;
+
if (!valid_phys_addr_range(p, count))
return -EFAULT;
read = 0;
#ifdef __ARCH_HAS_NO_PAGE_ZERO_MAPPED
/* we don't have page 0 mapped on sparc and m68k.. */
if (p < PAGE_SIZE) {
- sz = PAGE_SIZE - p;
- if (sz > count)
- sz = count;
+ sz = size_inside_page(p, count);
if (sz > 0) {
if (clear_user(buf, sz))
return -EFAULT;
- buf += sz;
- p += sz;
- count -= sz;
- read += sz;
+ buf += sz;
+ p += sz;
+ count -= sz;
+ read += sz;
}
}
#endif
while (count > 0) {
- /*
- * Handle first page in case it's not aligned
- */
- if (-p & (PAGE_SIZE - 1))
- sz = -p & (PAGE_SIZE - 1);
- else
- sz = PAGE_SIZE;
+ unsigned long remaining;
+
+ sz = size_inside_page(p, count);
- sz = min_t(unsigned long, sz, count);
+ if (!range_is_allowed(p >> PAGE_SHIFT, count))
+ return -EPERM;
/*
- * On ia64 if a page has been mapped somewhere as
- * uncached, then it must also be accessed uncached
- * by the kernel or data corruption may occur
+ * On ia64 if a page has been mapped somewhere as uncached, then
+ * it must also be accessed uncached by the kernel or data
+ * corruption may occur.
*/
ptr = xlate_dev_mem_ptr(p);
+ if (!ptr)
+ return -EFAULT;
- if (copy_to_user(buf, ptr, sz))
+ remaining = copy_to_user(buf, ptr, sz);
+ unxlate_dev_mem_ptr(p, ptr);
+ if (remaining)
return -EFAULT;
+
buf += sz;
p += sz;
count -= sz;
@@ -169,14 +152,17 @@ static ssize_t read_mem(struct file * file, char __user * buf,
return read;
}
-static ssize_t write_mem(struct file * file, const char __user * buf,
+static ssize_t write_mem(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
- unsigned long p = *ppos;
+ phys_addr_t p = *ppos;
ssize_t written, sz;
unsigned long copied;
void *ptr;
+ if (p != *ppos)
+ return -EFBIG;
+
if (!valid_phys_addr_range(p, count))
return -EFAULT;
@@ -185,9 +171,7 @@ static ssize_t write_mem(struct file * file, const char __user * buf,
#ifdef __ARCH_HAS_NO_PAGE_ZERO_MAPPED
/* we don't have page 0 mapped on sparc and m68k.. */
if (p < PAGE_SIZE) {
- unsigned long sz = PAGE_SIZE - p;
- if (sz > count)
- sz = count;
+ sz = size_inside_page(p, count);
/* Hmm. Do something? */
buf += sz;
p += sz;
@@ -197,30 +181,32 @@ static ssize_t write_mem(struct file * file, const char __user * buf,
#endif
while (count > 0) {
- /*
- * Handle first page in case it's not aligned
- */
- if (-p & (PAGE_SIZE - 1))
- sz = -p & (PAGE_SIZE - 1);
- else
- sz = PAGE_SIZE;
+ sz = size_inside_page(p, count);
- sz = min_t(unsigned long, sz, count);
+ if (!range_is_allowed(p >> PAGE_SHIFT, sz))
+ return -EPERM;
/*
- * On ia64 if a page has been mapped somewhere as
- * uncached, then it must also be accessed uncached
- * by the kernel or data corruption may occur
+ * On ia64 if a page has been mapped somewhere as uncached, then
+ * it must also be accessed uncached by the kernel or data
+ * corruption may occur.
*/
ptr = xlate_dev_mem_ptr(p);
+ if (!ptr) {
+ if (written)
+ break;
+ return -EFAULT;
+ }
copied = copy_from_user(ptr, buf, sz);
+ unxlate_dev_mem_ptr(p, ptr);
if (copied) {
written += sz - copied;
if (written)
break;
return -EFAULT;
}
+
buf += sz;
p += sz;
count -= sz;
@@ -231,12 +217,53 @@ static ssize_t write_mem(struct file * file, const char __user * buf,
return written;
}
+int __weak phys_mem_access_prot_allowed(struct file *file,
+ unsigned long pfn, unsigned long size, pgprot_t *vma_prot)
+{
+ return 1;
+}
+
#ifndef __HAVE_PHYS_MEM_ACCESS_PROT
+
+/*
+ * Architectures vary in how they handle caching for addresses
+ * outside of main memory.
+ *
+ */
+#ifdef pgprot_noncached
+static int uncached_access(struct file *file, phys_addr_t addr)
+{
+#if defined(CONFIG_IA64)
+ /*
+ * On ia64, we ignore O_DSYNC because we cannot tolerate memory
+ * attribute aliases.
+ */
+ return !(efi_mem_attributes(addr) & EFI_MEMORY_WB);
+#elif defined(CONFIG_MIPS)
+ {
+ extern int __uncached_access(struct file *file,
+ unsigned long addr);
+
+ return __uncached_access(file, addr);
+ }
+#else
+ /*
+ * Accessing memory above the top the kernel knows about or through a
+ * file pointer
+ * that was marked O_DSYNC will be done non-cached.
+ */
+ if (file->f_flags & O_DSYNC)
+ return 1;
+ return addr >= __pa(high_memory);
+#endif
+}
+#endif
+
static pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
unsigned long size, pgprot_t vma_prot)
{
#ifdef pgprot_noncached
- unsigned long offset = pfn << PAGE_SHIFT;
+ phys_addr_t offset = pfn << PAGE_SHIFT;
if (uncached_access(file, offset))
return pgprot_noncached(vma_prot);
@@ -271,7 +298,13 @@ static inline int private_mapping_ok(struct vm_area_struct *vma)
}
#endif
-static int mmap_mem(struct file * file, struct vm_area_struct * vma)
+static const struct vm_operations_struct mmap_mem_ops = {
+#ifdef CONFIG_HAVE_IOREMAP_PROT
+ .access = generic_access_phys
+#endif
+};
+
+static int mmap_mem(struct file *file, struct vm_area_struct *vma)
{
size_t size = vma->vm_end - vma->vm_start;
@@ -281,21 +314,32 @@ static int mmap_mem(struct file * file, struct vm_area_struct * vma)
if (!private_mapping_ok(vma))
return -ENOSYS;
+ if (!range_is_allowed(vma->vm_pgoff, size))
+ return -EPERM;
+
+ if (!phys_mem_access_prot_allowed(file, vma->vm_pgoff, size,
+ &vma->vm_page_prot))
+ return -EINVAL;
+
vma->vm_page_prot = phys_mem_access_prot(file, vma->vm_pgoff,
size,
vma->vm_page_prot);
- /* Remap-pfn-range will mark the range VM_IO and VM_RESERVED */
+ vma->vm_ops = &mmap_mem_ops;
+
+ /* Remap-pfn-range will mark the range VM_IO */
if (remap_pfn_range(vma,
vma->vm_start,
vma->vm_pgoff,
size,
- vma->vm_page_prot))
+ vma->vm_page_prot)) {
return -EAGAIN;
+ }
return 0;
}
-static int mmap_kmem(struct file * file, struct vm_area_struct * vma)
+#ifdef CONFIG_DEVKMEM
+static int mmap_kmem(struct file *file, struct vm_area_struct *vma)
{
unsigned long pfn;
@@ -303,9 +347,9 @@ static int mmap_kmem(struct file * file, struct vm_area_struct * vma)
pfn = __pa((u64)vma->vm_pgoff << PAGE_SHIFT) >> PAGE_SHIFT;
/*
- * RED-PEN: on some architectures there is more mapped memory
- * than available in mem_map which pfn_valid checks
- * for. Perhaps should add a new macro here.
+ * RED-PEN: on some architectures there is more mapped memory than
+ * available in mem_map which pfn_valid checks for. Perhaps should add a
+ * new macro here.
*
* RED-PEN: vmalloc is not supported right now.
*/
@@ -315,84 +359,41 @@ static int mmap_kmem(struct file * file, struct vm_area_struct * vma)
vma->vm_pgoff = pfn;
return mmap_mem(file, vma);
}
-
-#ifdef CONFIG_CRASH_DUMP
-/*
- * Read memory corresponding to the old kernel.
- */
-static ssize_t read_oldmem(struct file *file, char __user *buf,
- size_t count, loff_t *ppos)
-{
- unsigned long pfn, offset;
- size_t read = 0, csize;
- int rc = 0;
-
- while (count) {
- pfn = *ppos / PAGE_SIZE;
- if (pfn > saved_max_pfn)
- return read;
-
- offset = (unsigned long)(*ppos % PAGE_SIZE);
- if (count > PAGE_SIZE - offset)
- csize = PAGE_SIZE - offset;
- else
- csize = count;
-
- rc = copy_oldmem_page(pfn, buf, csize, offset, 1);
- if (rc < 0)
- return rc;
- buf += csize;
- *ppos += csize;
- read += csize;
- count -= csize;
- }
- return read;
-}
#endif
-extern long vread(char *buf, char *addr, unsigned long count);
-extern long vwrite(char *buf, char *addr, unsigned long count);
-
+#ifdef CONFIG_DEVKMEM
/*
* This function reads the *virtual* memory as seen by the kernel.
*/
-static ssize_t read_kmem(struct file *file, char __user *buf,
+static ssize_t read_kmem(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
unsigned long p = *ppos;
ssize_t low_count, read, sz;
- char * kbuf; /* k-addr because vread() takes vmlist_lock rwlock */
+ char *kbuf; /* k-addr because vread() takes vmlist_lock rwlock */
+ int err = 0;
read = 0;
if (p < (unsigned long) high_memory) {
low_count = count;
- if (count > (unsigned long) high_memory - p)
- low_count = (unsigned long) high_memory - p;
+ if (count > (unsigned long)high_memory - p)
+ low_count = (unsigned long)high_memory - p;
#ifdef __ARCH_HAS_NO_PAGE_ZERO_MAPPED
/* we don't have page 0 mapped on sparc and m68k.. */
if (p < PAGE_SIZE && low_count > 0) {
- size_t tmp = PAGE_SIZE - p;
- if (tmp > low_count) tmp = low_count;
- if (clear_user(buf, tmp))
+ sz = size_inside_page(p, low_count);
+ if (clear_user(buf, sz))
return -EFAULT;
- buf += tmp;
- p += tmp;
- read += tmp;
- low_count -= tmp;
- count -= tmp;
+ buf += sz;
+ p += sz;
+ read += sz;
+ low_count -= sz;
+ count -= sz;
}
#endif
while (low_count > 0) {
- /*
- * Handle first page in case it's not aligned
- */
- if (-p & (PAGE_SIZE - 1))
- sz = -p & (PAGE_SIZE - 1);
- else
- sz = PAGE_SIZE;
-
- sz = min_t(unsigned long, sz, low_count);
+ sz = size_inside_page(p, low_count);
/*
* On ia64 if a page has been mapped somewhere as
@@ -416,32 +417,32 @@ static ssize_t read_kmem(struct file *file, char __user *buf,
if (!kbuf)
return -ENOMEM;
while (count > 0) {
- int len = count;
-
- if (len > PAGE_SIZE)
- len = PAGE_SIZE;
- len = vread(kbuf, (char *)p, len);
- if (!len)
+ sz = size_inside_page(p, count);
+ if (!is_vmalloc_or_module_addr((void *)p)) {
+ err = -ENXIO;
break;
- if (copy_to_user(buf, kbuf, len)) {
- free_page((unsigned long)kbuf);
- return -EFAULT;
}
- count -= len;
- buf += len;
- read += len;
- p += len;
+ sz = vread(kbuf, (char *)p, sz);
+ if (!sz)
+ break;
+ if (copy_to_user(buf, kbuf, sz)) {
+ err = -EFAULT;
+ break;
+ }
+ count -= sz;
+ buf += sz;
+ read += sz;
+ p += sz;
}
free_page((unsigned long)kbuf);
}
- *ppos = p;
- return read;
+ *ppos = p;
+ return read ? read : err;
}
-static inline ssize_t
-do_write_kmem(void *p, unsigned long realp, const char __user * buf,
- size_t count, loff_t *ppos)
+static ssize_t do_write_kmem(unsigned long p, const char __user *buf,
+ size_t count, loff_t *ppos)
{
ssize_t written, sz;
unsigned long copied;
@@ -449,14 +450,11 @@ do_write_kmem(void *p, unsigned long realp, const char __user * buf,
written = 0;
#ifdef __ARCH_HAS_NO_PAGE_ZERO_MAPPED
/* we don't have page 0 mapped on sparc and m68k.. */
- if (realp < PAGE_SIZE) {
- unsigned long sz = PAGE_SIZE - realp;
- if (sz > count)
- sz = count;
+ if (p < PAGE_SIZE) {
+ sz = size_inside_page(p, count);
/* Hmm. Do something? */
buf += sz;
p += sz;
- realp += sz;
count -= sz;
written += sz;
}
@@ -464,22 +462,15 @@ do_write_kmem(void *p, unsigned long realp, const char __user * buf,
while (count > 0) {
char *ptr;
- /*
- * Handle first page in case it's not aligned
- */
- if (-realp & (PAGE_SIZE - 1))
- sz = -realp & (PAGE_SIZE - 1);
- else
- sz = PAGE_SIZE;
- sz = min_t(unsigned long, sz, count);
+ sz = size_inside_page(p, count);
/*
- * On ia64 if a page has been mapped somewhere as
- * uncached, then it must also be accessed uncached
- * by the kernel or data corruption may occur
+ * On ia64 if a page has been mapped somewhere as uncached, then
+ * it must also be accessed uncached by the kernel or data
+ * corruption may occur.
*/
- ptr = xlate_dev_kmem_ptr(p);
+ ptr = xlate_dev_kmem_ptr((char *)p);
copied = copy_from_user(ptr, buf, sz);
if (copied) {
@@ -490,7 +481,6 @@ do_write_kmem(void *p, unsigned long realp, const char __user * buf,
}
buf += sz;
p += sz;
- realp += sz;
count -= sz;
written += sz;
}
@@ -499,29 +489,24 @@ do_write_kmem(void *p, unsigned long realp, const char __user * buf,
return written;
}
-
/*
* This function writes to the *virtual* memory as seen by the kernel.
*/
-static ssize_t write_kmem(struct file * file, const char __user * buf,
+static ssize_t write_kmem(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
unsigned long p = *ppos;
ssize_t wrote = 0;
ssize_t virtr = 0;
- ssize_t written;
- char * kbuf; /* k-addr because vwrite() takes vmlist_lock rwlock */
+ char *kbuf; /* k-addr because vwrite() takes vmlist_lock rwlock */
+ int err = 0;
if (p < (unsigned long) high_memory) {
-
- wrote = count;
- if (count > (unsigned long) high_memory - p)
- wrote = (unsigned long) high_memory - p;
-
- written = do_write_kmem((void*)p, p, buf, wrote, ppos);
- if (written != wrote)
- return written;
- wrote = written;
+ unsigned long to_write = min_t(unsigned long, count,
+ (unsigned long)high_memory - p);
+ wrote = do_write_kmem(p, buf, to_write, ppos);
+ if (wrote != to_write)
+ return wrote;
p += wrote;
buf += wrote;
count -= wrote;
@@ -532,44 +517,44 @@ static ssize_t write_kmem(struct file * file, const char __user * buf,
if (!kbuf)
return wrote ? wrote : -ENOMEM;
while (count > 0) {
- int len = count;
-
- if (len > PAGE_SIZE)
- len = PAGE_SIZE;
- if (len) {
- written = copy_from_user(kbuf, buf, len);
- if (written) {
- if (wrote + virtr)
- break;
- free_page((unsigned long)kbuf);
- return -EFAULT;
- }
+ unsigned long sz = size_inside_page(p, count);
+ unsigned long n;
+
+ if (!is_vmalloc_or_module_addr((void *)p)) {
+ err = -ENXIO;
+ break;
+ }
+ n = copy_from_user(kbuf, buf, sz);
+ if (n) {
+ err = -EFAULT;
+ break;
}
- len = vwrite(kbuf, (char *)p, len);
- count -= len;
- buf += len;
- virtr += len;
- p += len;
+ vwrite(kbuf, (char *)p, sz);
+ count -= sz;
+ buf += sz;
+ virtr += sz;
+ p += sz;
}
free_page((unsigned long)kbuf);
}
- *ppos = p;
- return virtr + wrote;
+ *ppos = p;
+ return virtr + wrote ? : err;
}
+#endif
#ifdef CONFIG_DEVPORT
-static ssize_t read_port(struct file * file, char __user * buf,
+static ssize_t read_port(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
unsigned long i = *ppos;
char __user *tmp = buf;
if (!access_ok(VERIFY_WRITE, buf, count))
- return -EFAULT;
+ return -EFAULT;
while (count-- > 0 && i < 65536) {
- if (__put_user(inb(i),tmp) < 0)
- return -EFAULT;
+ if (__put_user(inb(i), tmp) < 0)
+ return -EFAULT;
i++;
tmp++;
}
@@ -577,22 +562,22 @@ static ssize_t read_port(struct file * file, char __user * buf,
return tmp-buf;
}
-static ssize_t write_port(struct file * file, const char __user * buf,
+static ssize_t write_port(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
unsigned long i = *ppos;
- const char __user * tmp = buf;
+ const char __user *tmp = buf;
- if (!access_ok(VERIFY_READ,buf,count))
+ if (!access_ok(VERIFY_READ, buf, count))
return -EFAULT;
while (count-- > 0 && i < 65536) {
char c;
if (__get_user(c, tmp)) {
if (tmp > buf)
break;
- return -EFAULT;
+ return -EFAULT;
}
- outb(c,i);
+ outb(c, i);
i++;
tmp++;
}
@@ -601,31 +586,43 @@ static ssize_t write_port(struct file * file, const char __user * buf,
}
#endif
-static ssize_t read_null(struct file * file, char __user * buf,
+static ssize_t read_null(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
return 0;
}
-static ssize_t write_null(struct file * file, const char __user * buf,
+static ssize_t write_null(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
return count;
}
+static ssize_t aio_read_null(struct kiocb *iocb, const struct iovec *iov,
+ unsigned long nr_segs, loff_t pos)
+{
+ return 0;
+}
+
+static ssize_t aio_write_null(struct kiocb *iocb, const struct iovec *iov,
+ unsigned long nr_segs, loff_t pos)
+{
+ return iov_length(iov, nr_segs);
+}
+
static int pipe_to_null(struct pipe_inode_info *info, struct pipe_buffer *buf,
struct splice_desc *sd)
{
return sd->len;
}
-static ssize_t splice_write_null(struct pipe_inode_info *pipe,struct file *out,
+static ssize_t splice_write_null(struct pipe_inode_info *pipe, struct file *out,
loff_t *ppos, size_t len, unsigned int flags)
{
return splice_from_pipe(pipe, out, ppos, len, flags, pipe_to_null);
}
-static ssize_t read_zero(struct file * file, char __user * buf,
+static ssize_t read_zero(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
size_t written;
@@ -643,10 +640,12 @@ static ssize_t read_zero(struct file * file, char __user * buf,
if (chunk > PAGE_SIZE)
chunk = PAGE_SIZE; /* Just for latency reasons */
- unwritten = clear_user(buf, chunk);
+ unwritten = __clear_user(buf, chunk);
written += chunk - unwritten;
if (unwritten)
break;
+ if (signal_pending(current))
+ return written ? written : -ERESTARTSYS;
buf += chunk;
count -= chunk;
cond_resched();
@@ -654,7 +653,25 @@ static ssize_t read_zero(struct file * file, char __user * buf,
return written ? written : -EFAULT;
}
-static int mmap_zero(struct file * file, struct vm_area_struct * vma)
+static ssize_t aio_read_zero(struct kiocb *iocb, const struct iovec *iov,
+ unsigned long nr_segs, loff_t pos)
+{
+ size_t written = 0;
+ unsigned long i;
+ ssize_t ret;
+
+ for (i = 0; i < nr_segs; i++) {
+ ret = read_zero(iocb->ki_filp, iov[i].iov_base, iov[i].iov_len,
+ &pos);
+ if (ret < 0)
+ break;
+ written += ret;
+ }
+
+ return written ? written : -EFAULT;
+}
+
+static int mmap_zero(struct file *file, struct vm_area_struct *vma)
{
#ifndef CONFIG_MMU
return -ENOSYS;
@@ -664,7 +681,7 @@ static int mmap_zero(struct file * file, struct vm_area_struct * vma)
return 0;
}
-static ssize_t write_full(struct file * file, const char __user * buf,
+static ssize_t write_full(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
return -ENOSPC;
@@ -675,8 +692,7 @@ static ssize_t write_full(struct file * file, const char __user * buf,
* can fopen() both devices with "a" now. This was previously impossible.
* -- SRB.
*/
-
-static loff_t null_lseek(struct file * file, loff_t offset, int orig)
+static loff_t null_lseek(struct file *file, loff_t offset, int orig)
{
return file->f_pos = 0;
}
@@ -689,30 +705,32 @@ static loff_t null_lseek(struct file * file, loff_t offset, int orig)
* also note that seeking relative to the "end of file" isn't supported:
* it has no meaning, so it returns -EINVAL.
*/
-static loff_t memory_lseek(struct file * file, loff_t offset, int orig)
+static loff_t memory_lseek(struct file *file, loff_t offset, int orig)
{
loff_t ret;
- mutex_lock(&file->f_path.dentry->d_inode->i_mutex);
+ mutex_lock(&file_inode(file)->i_mutex);
switch (orig) {
- case 0:
- file->f_pos = offset;
- ret = file->f_pos;
- force_successful_syscall_return();
- break;
- case 1:
- file->f_pos += offset;
- ret = file->f_pos;
- force_successful_syscall_return();
+ case SEEK_CUR:
+ offset += file->f_pos;
+ case SEEK_SET:
+ /* to avoid userland mistaking f_pos=-9 as -EBADF=-9 */
+ if (IS_ERR_VALUE((unsigned long long)offset)) {
+ ret = -EOVERFLOW;
break;
- default:
- ret = -EINVAL;
+ }
+ file->f_pos = offset;
+ ret = file->f_pos;
+ force_successful_syscall_return();
+ break;
+ default:
+ ret = -EINVAL;
}
- mutex_unlock(&file->f_path.dentry->d_inode->i_mutex);
+ mutex_unlock(&file_inode(file)->i_mutex);
return ret;
}
-static int open_port(struct inode * inode, struct file * filp)
+static int open_port(struct inode *inode, struct file *filp)
{
return capable(CAP_SYS_RAWIO) ? 0 : -EPERM;
}
@@ -721,9 +739,9 @@ static int open_port(struct inode * inode, struct file * filp)
#define full_lseek null_lseek
#define write_zero write_null
#define read_full read_zero
+#define aio_write_zero aio_write_null
#define open_mem open_port
#define open_kmem open_mem
-#define open_oldmem open_mem
static const struct file_operations mem_fops = {
.llseek = memory_lseek,
@@ -734,6 +752,7 @@ static const struct file_operations mem_fops = {
.get_unmapped_area = get_unmapped_area_mem,
};
+#ifdef CONFIG_DEVKMEM
static const struct file_operations kmem_fops = {
.llseek = memory_lseek,
.read = read_kmem,
@@ -742,11 +761,14 @@ static const struct file_operations kmem_fops = {
.open = open_kmem,
.get_unmapped_area = get_unmapped_area_mem,
};
+#endif
static const struct file_operations null_fops = {
.llseek = null_lseek,
.read = read_null,
.write = write_null,
+ .aio_read = aio_read_null,
+ .aio_write = aio_write_null,
.splice_write = splice_write_null,
};
@@ -763,15 +785,19 @@ static const struct file_operations zero_fops = {
.llseek = zero_lseek,
.read = read_zero,
.write = write_zero,
+ .aio_read = aio_read_zero,
+ .aio_write = aio_write_zero,
.mmap = mmap_zero,
};
/*
* capabilities for /dev/zero
* - permits private mappings, "copies" are taken of the source of zeros
+ * - no writeback happens
*/
static struct backing_dev_info zero_bdi = {
- .capabilities = BDI_CAP_MAP_COPY,
+ .name = "char/mem",
+ .capabilities = BDI_CAP_MAP_COPY | BDI_CAP_NO_ACCT_AND_WRITEBACK,
};
static const struct file_operations full_fops = {
@@ -780,135 +806,102 @@ static const struct file_operations full_fops = {
.write = write_full,
};
-#ifdef CONFIG_CRASH_DUMP
-static const struct file_operations oldmem_fops = {
- .read = read_oldmem,
- .open = open_oldmem,
-};
+static const struct memdev {
+ const char *name;
+ umode_t mode;
+ const struct file_operations *fops;
+ struct backing_dev_info *dev_info;
+} devlist[] = {
+ [1] = { "mem", 0, &mem_fops, &directly_mappable_cdev_bdi },
+#ifdef CONFIG_DEVKMEM
+ [2] = { "kmem", 0, &kmem_fops, &directly_mappable_cdev_bdi },
+#endif
+ [3] = { "null", 0666, &null_fops, NULL },
+#ifdef CONFIG_DEVPORT
+ [4] = { "port", 0, &port_fops, NULL },
#endif
+ [5] = { "zero", 0666, &zero_fops, &zero_bdi },
+ [7] = { "full", 0666, &full_fops, NULL },
+ [8] = { "random", 0666, &random_fops, NULL },
+ [9] = { "urandom", 0666, &urandom_fops, NULL },
+#ifdef CONFIG_PRINTK
+ [11] = { "kmsg", 0644, &kmsg_fops, NULL },
+#endif
+};
-static ssize_t kmsg_write(struct file * file, const char __user * buf,
- size_t count, loff_t *ppos)
+static int memory_open(struct inode *inode, struct file *filp)
{
- char *tmp;
- ssize_t ret;
+ int minor;
+ const struct memdev *dev;
- tmp = kmalloc(count + 1, GFP_KERNEL);
- if (tmp == NULL)
- return -ENOMEM;
- ret = -EFAULT;
- if (!copy_from_user(tmp, buf, count)) {
- tmp[count] = 0;
- ret = printk("%s", tmp);
- if (ret > count)
- /* printk can add a prefix */
- ret = count;
- }
- kfree(tmp);
- return ret;
-}
+ minor = iminor(inode);
+ if (minor >= ARRAY_SIZE(devlist))
+ return -ENXIO;
-static const struct file_operations kmsg_fops = {
- .write = kmsg_write,
-};
+ dev = &devlist[minor];
+ if (!dev->fops)
+ return -ENXIO;
+
+ filp->f_op = dev->fops;
+ if (dev->dev_info)
+ filp->f_mapping->backing_dev_info = dev->dev_info;
+
+ /* Is /dev/mem or /dev/kmem ? */
+ if (dev->dev_info == &directly_mappable_cdev_bdi)
+ filp->f_mode |= FMODE_UNSIGNED_OFFSET;
+
+ if (dev->fops->open)
+ return dev->fops->open(inode, filp);
-static int memory_open(struct inode * inode, struct file * filp)
-{
- switch (iminor(inode)) {
- case 1:
- filp->f_op = &mem_fops;
- filp->f_mapping->backing_dev_info =
- &directly_mappable_cdev_bdi;
- break;
- case 2:
- filp->f_op = &kmem_fops;
- filp->f_mapping->backing_dev_info =
- &directly_mappable_cdev_bdi;
- break;
- case 3:
- filp->f_op = &null_fops;
- break;
-#ifdef CONFIG_DEVPORT
- case 4:
- filp->f_op = &port_fops;
- break;
-#endif
- case 5:
- filp->f_mapping->backing_dev_info = &zero_bdi;
- filp->f_op = &zero_fops;
- break;
- case 7:
- filp->f_op = &full_fops;
- break;
- case 8:
- filp->f_op = &random_fops;
- break;
- case 9:
- filp->f_op = &urandom_fops;
- break;
- case 11:
- filp->f_op = &kmsg_fops;
- break;
-#ifdef CONFIG_CRASH_DUMP
- case 12:
- filp->f_op = &oldmem_fops;
- break;
-#endif
- default:
- return -ENXIO;
- }
- if (filp->f_op && filp->f_op->open)
- return filp->f_op->open(inode,filp);
return 0;
}
static const struct file_operations memory_fops = {
- .open = memory_open, /* just a selector for the real open */
+ .open = memory_open,
+ .llseek = noop_llseek,
};
-static const struct {
- unsigned int minor;
- char *name;
- umode_t mode;
- const struct file_operations *fops;
-} devlist[] = { /* list of minor devices */
- {1, "mem", S_IRUSR | S_IWUSR | S_IRGRP, &mem_fops},
- {2, "kmem", S_IRUSR | S_IWUSR | S_IRGRP, &kmem_fops},
- {3, "null", S_IRUGO | S_IWUGO, &null_fops},
-#ifdef CONFIG_DEVPORT
- {4, "port", S_IRUSR | S_IWUSR | S_IRGRP, &port_fops},
-#endif
- {5, "zero", S_IRUGO | S_IWUGO, &zero_fops},
- {7, "full", S_IRUGO | S_IWUGO, &full_fops},
- {8, "random", S_IRUGO | S_IWUSR, &random_fops},
- {9, "urandom", S_IRUGO | S_IWUSR, &urandom_fops},
- {11,"kmsg", S_IRUGO | S_IWUSR, &kmsg_fops},
-#ifdef CONFIG_CRASH_DUMP
- {12,"oldmem", S_IRUSR | S_IWUSR | S_IRGRP, &oldmem_fops},
-#endif
-};
+static char *mem_devnode(struct device *dev, umode_t *mode)
+{
+ if (mode && devlist[MINOR(dev->devt)].mode)
+ *mode = devlist[MINOR(dev->devt)].mode;
+ return NULL;
+}
static struct class *mem_class;
static int __init chr_dev_init(void)
{
- int i;
+ int minor;
int err;
err = bdi_init(&zero_bdi);
if (err)
return err;
- if (register_chrdev(MEM_MAJOR,"mem",&memory_fops))
+ if (register_chrdev(MEM_MAJOR, "mem", &memory_fops))
printk("unable to get major %d for memory devs\n", MEM_MAJOR);
mem_class = class_create(THIS_MODULE, "mem");
- for (i = 0; i < ARRAY_SIZE(devlist); i++)
- device_create(mem_class, NULL,
- MKDEV(MEM_MAJOR, devlist[i].minor),
- devlist[i].name);
+ if (IS_ERR(mem_class))
+ return PTR_ERR(mem_class);
- return 0;
+ mem_class->devnode = mem_devnode;
+ for (minor = 1; minor < ARRAY_SIZE(devlist); minor++) {
+ if (!devlist[minor].name)
+ continue;
+
+ /*
+ * Create /dev/port?
+ */
+ if ((minor == DEVPORT_MINOR) && !arch_has_dev_port())
+ continue;
+
+ device_create(mem_class, NULL, MKDEV(MEM_MAJOR, minor),
+ NULL, devlist[minor].name);
+ }
+
+ return tty_init();
}
fs_initcall(chr_dev_init);
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-10 07:04:38 +0000