#include <linux/bootmem.h>
#include <linux/splice.h>
#include <linux/pfn.h>
+#include <linux/smp_lock.h>
#include <asm/uaccess.h>
#include <asm/io.h>
*/
static inline int uncached_access(struct file *file, unsigned long addr)
{
-#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)
+#if defined(CONFIG_IA64)
/*
* On ia64, we ignore O_SYNC because we cannot tolerate memory attribute aliases.
*/
}
#endif
+#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 __attribute__((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.
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
*/
ptr = xlate_dev_mem_ptr(p);
+ if (!ptr)
+ return -EFAULT;
- if (copy_to_user(buf, ptr, sz))
+ if (copy_to_user(buf, ptr, sz)) {
+ unxlate_dev_mem_ptr(p, ptr);
return -EFAULT;
+ }
+
+ unxlate_dev_mem_ptr(p, ptr);
+
buf += sz;
p += sz;
count -= sz;
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
*/
ptr = xlate_dev_mem_ptr(p);
+ if (!ptr) {
+ if (written)
+ break;
+ return -EFAULT;
+ }
copied = copy_from_user(ptr, buf, sz);
if (copied) {
written += sz - copied;
+ unxlate_dev_mem_ptr(p, ptr);
if (written)
break;
return -EFAULT;
}
+
+ unxlate_dev_mem_ptr(p, ptr);
+
buf += sz;
p += sz;
count -= sz;
return written;
}
+int __attribute__((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
static pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
unsigned long size, pgprot_t vma_prot)
}
#endif
+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;
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);
+ vma->vm_ops = &mmap_mem_ops;
+
/* Remap-pfn-range will mark the range VM_IO and VM_RESERVED */
if (remap_pfn_range(vma,
vma->vm_start,
vma->vm_pgoff,
size,
- vma->vm_page_prot))
+ vma->vm_page_prot)) {
return -EAGAIN;
+ }
return 0;
}
+#ifdef CONFIG_DEVKMEM
static int mmap_kmem(struct file * file, struct vm_area_struct * vma)
{
unsigned long pfn;
vma->vm_pgoff = pfn;
return mmap_mem(file, vma);
}
+#endif
#ifdef CONFIG_CRASH_DUMP
/*
}
#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.
*/
*ppos = p;
return virtr + wrote;
}
+#endif
#ifdef CONFIG_DEVPORT
static ssize_t read_port(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();
.get_unmapped_area = get_unmapped_area_mem,
};
+#ifdef CONFIG_DEVKMEM
static const struct file_operations kmem_fops = {
.llseek = memory_lseek,
.read = read_kmem,
.open = open_kmem,
.get_unmapped_area = get_unmapped_area_mem,
};
+#endif
static const struct file_operations null_fops = {
.llseek = null_lseek,
* - permits private mappings, "copies" are taken of the source of zeros
*/
static struct backing_dev_info zero_bdi = {
+ .name = "char/mem",
.capabilities = BDI_CAP_MAP_COPY,
};
.write = kmsg_write,
};
-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;
+static const struct memdev {
+ const char *name;
+ mode_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
- case 4:
- filp->f_op = &port_fops;
- break;
+ [4] = { "port", 0, &port_fops, NULL },
#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;
+ [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 },
+ [11] = { "kmsg", 0, &kmsg_fops, NULL },
#ifdef CONFIG_CRASH_DUMP
- case 12:
- filp->f_op = &oldmem_fops;
- break;
+ [12] = { "oldmem", 0, &oldmem_fops, NULL },
#endif
- default:
- return -ENXIO;
- }
- if (filp->f_op && filp->f_op->open)
- return filp->f_op->open(inode,filp);
- return 0;
+};
+
+static int memory_open(struct inode *inode, struct file *filp)
+{
+ int minor;
+ const struct memdev *dev;
+ int ret = -ENXIO;
+
+ lock_kernel();
+
+ minor = iminor(inode);
+ if (minor >= ARRAY_SIZE(devlist))
+ goto out;
+
+ dev = &devlist[minor];
+ if (!dev->fops)
+ goto out;
+
+ filp->f_op = dev->fops;
+ if (dev->dev_info)
+ filp->f_mapping->backing_dev_info = dev->dev_info;
+
+ if (dev->fops->open)
+ ret = dev->fops->open(inode, filp);
+ else
+ ret = 0;
+out:
+ unlock_kernel();
+ return ret;
}
static const struct file_operations memory_fops = {
- .open = memory_open, /* just a selector for the real open */
+ .open = memory_open,
};
-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, mode_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);
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);
+ mem_class->devnode = mem_devnode;
+ for (minor = 1; minor < ARRAY_SIZE(devlist); minor++) {
+ if (!devlist[minor].name)
+ continue;
+ device_create(mem_class, NULL, MKDEV(MEM_MAJOR, minor),
+ NULL, devlist[minor].name);
+ }
return 0;
}