From 66f0dc481e5b802ab363b979fc1753410c7d82b5 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Wed, 30 Dec 2009 20:17:34 +0000 Subject: mm: move sys_mmap_pgoff from util.c Move sys_mmap_pgoff() from mm/util.c to mm/mmap.c and mm/nommu.c, where we'd expect to find such code: especially now that it contains the MAP_HUGETLB handling. Revert mm/util.c to how it was in 2.6.32. This patch just ignores MAP_HUGETLB in the nommu case, as in 2.6.32, whereas 2.6.33-rc2 reported -ENOSYS. Perhaps validate_mmap_request() should reject it with -EINVAL? Add that later if necessary. Signed-off-by: Hugh Dickins Signed-off-by: Linus Torvalds --- mm/nommu.c | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'mm/nommu.c') diff --git a/mm/nommu.c b/mm/nommu.c index 8687973462bb..6f9248f89bde 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1398,6 +1398,31 @@ error_getting_region: } EXPORT_SYMBOL(do_mmap_pgoff); +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; + + if (!(flags & MAP_ANONYMOUS)) { + file = fget(fd); + if (!file) + goto out; + } + + flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE); + + down_write(¤t->mm->mmap_sem); + retval = do_mmap_pgoff(file, addr, len, prot, flags, pgoff); + up_write(¤t->mm->mmap_sem); + + if (file) + fput(file); +out: + return retval; +} + /* * split a vma into two pieces at address 'addr', a new vma is allocated either * for the first part or the tail. -- cgit v1.2.2 From cfe79c00a2f4f687eed8b7534d1d3d3d35540c29 Mon Sep 17 00:00:00 2001 From: Mike Frysinger Date: Wed, 6 Jan 2010 17:23:23 +0000 Subject: NOMMU: Avoiding duplicate icache flushes of shared maps When working with FDPIC, there are many shared mappings of read-only code regions between applications (the C library, applet packages like busybox, etc.), but the current do_mmap_pgoff() function will issue an icache flush whenever a VMA is added to an MM instead of only doing it when the map is initially created. The flush can instead be done when a region is first mmapped PROT_EXEC. Note that we may not rely on the first mapping of a region being executable - it's possible for it to be PROT_READ only, so we have to remember whether we've flushed the region or not, and then flush the entire region when a bit of it is made executable. However, this also affects the brk area. That will no longer be executable. We can mprotect() it to PROT_EXEC on MPU-mode kernels, but for NOMMU mode kernels, when it increases the brk allocation, making sys_brk() flush the extra from the icache should suffice. The brk area probably isn't used by NOMMU programs since the brk area can only use up the leavings from the stack allocation, where the stack allocation is larger than requested. Signed-off-by: David Howells Signed-off-by: Mike Frysinger Signed-off-by: Linus Torvalds --- mm/nommu.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'mm/nommu.c') diff --git a/mm/nommu.c b/mm/nommu.c index 6f9248f89bde..a8d17521624a 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -432,6 +432,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) /* * Ok, looks good - let it rip. */ + flush_icache_range(mm->brk, brk); return mm->brk = brk; } @@ -1353,10 +1354,14 @@ unsigned long do_mmap_pgoff(struct file *file, share: add_vma_to_mm(current->mm, vma); - up_write(&nommu_region_sem); + /* 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; + } - if (prot & PROT_EXEC) - flush_icache_range(result, result + len); + up_write(&nommu_region_sem); kleave(" = %lx", result); return result; -- cgit v1.2.2 From 7959722b951cffcd61a0a35229d007deeed8c2dd Mon Sep 17 00:00:00 2001 From: Jie Zhang Date: Wed, 6 Jan 2010 17:23:28 +0000 Subject: NOMMU: Use copy_*_user_page() in access_process_vm() The MMU code uses the copy_*_user_page() variants in access_process_vm() rather than copy_*_user() as the former includes an icache flush. This is important when doing things like setting software breakpoints with gdb. So switch the NOMMU code over to do the same. This patch makes the reasonable assumption that copy_from_user_page() won't fail - which is probably fine, as we've checked the VMA from which we're copying is usable, and the copy is not allowed to cross VMAs. The one case where it might go wrong is if the VMA is a device rather than RAM, and that device returns an error which - in which case rubbish will be returned rather than EIO. Signed-off-by: Jie Zhang Signed-off-by: Mike Frysinger Signed-off-by: David Howells Acked-by: David McCullough Acked-by: Paul Mundt Acked-by: Greg Ungerer Signed-off-by: Linus Torvalds --- mm/nommu.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'mm/nommu.c') diff --git a/mm/nommu.c b/mm/nommu.c index a8d17521624a..17773862619b 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1921,9 +1921,11 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, in /* only read or write mappings where it is permitted */ if (write && vma->vm_flags & VM_MAYWRITE) - len -= copy_to_user((void *) addr, buf, len); + copy_to_user_page(vma, NULL, addr, + (void *) addr, buf, len); else if (!write && vma->vm_flags & VM_MAYREAD) - len -= copy_from_user(buf, (void *) addr, len); + copy_from_user_page(vma, NULL, addr, + buf, (void *) addr, len); else len = 0; } else { -- cgit v1.2.2