From 40d6366e9d86d9a67b5642040e76082fdb5bdcf9 Mon Sep 17 00:00:00 2001 From: Miles Chen Date: Fri, 11 Dec 2020 13:36:31 -0800 Subject: proc: use untagged_addr() for pagemap_read addresses When we try to visit the pagemap of a tagged userspace pointer, we find that the start_vaddr is not correct because of the tag. To fix it, we should untag the userspace pointers in pagemap_read(). I tested with 5.10-rc4 and the issue remains. Explanation from Catalin in [1]: "Arguably, that's a user-space bug since tagged file offsets were never supported. In this case it's not even a tag at bit 56 as per the arm64 tagged address ABI but rather down to bit 47. You could say that the problem is caused by the C library (malloc()) or whoever created the tagged vaddr and passed it to this function. It's not a kernel regression as we've never supported it. Now, pagemap is a special case where the offset is usually not generated as a classic file offset but rather derived by shifting a user virtual address. I guess we can make a concession for pagemap (only) and allow such offset with the tag at bit (56 - PAGE_SHIFT + 3)" My test code is based on [2]: A userspace pointer which has been tagged by 0xb4: 0xb400007662f541c8 userspace program: uint64 OsLayer::VirtualToPhysical(void *vaddr) { uint64 frame, paddr, pfnmask, pagemask; int pagesize = sysconf(_SC_PAGESIZE); off64_t off = ((uintptr_t)vaddr) / pagesize * 8; // off = 0xb400007662f541c8 / pagesize * 8 = 0x5a00003b317aa0 int fd = open(kPagemapPath, O_RDONLY); ... if (lseek64(fd, off, SEEK_SET) != off || read(fd, &frame, 8) != 8) { int err = errno; string errtxt = ErrorString(err); if (fd >= 0) close(fd); return 0; } ... } kernel fs/proc/task_mmu.c: static ssize_t pagemap_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { ... src = *ppos; svpfn = src / PM_ENTRY_BYTES; // svpfn == 0xb400007662f54 start_vaddr = svpfn << PAGE_SHIFT; // start_vaddr == 0xb400007662f54000 end_vaddr = mm->task_size; /* watch out for wraparound */ // svpfn == 0xb400007662f54 // (mm->task_size >> PAGE) == 0x8000000 if (svpfn > mm->task_size >> PAGE_SHIFT) // the condition is true because of the tag 0xb4 start_vaddr = end_vaddr; ret = 0; while (count && (start_vaddr < end_vaddr)) { // we cannot visit correct entry because start_vaddr is set to end_vaddr int len; unsigned long end; ... } ... } [1] https://lore.kernel.org/patchwork/patch/1343258/ [2] https://github.com/stressapptest/stressapptest/blob/master/src/os.cc#L158 Link: https://lkml.kernel.org/r/20201204024347.8295-1-miles.chen@mediatek.com Signed-off-by: Miles Chen Reviewed-by: Vincenzo Frascino Reviewed-by: Catalin Marinas Cc: Alexey Dobriyan Cc: Andrey Konovalov Cc: Alexander Potapenko Cc: Vincenzo Frascino Cc: Andrey Ryabinin Cc: Catalin Marinas Cc: Dmitry Vyukov Cc: Marco Elver Cc: Will Deacon Cc: Eric W. Biederman Cc: Song Bao Hua (Barry Song) Cc: [5.4-] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/task_mmu.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 217aa2705d5d..ee5a235b3056 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1599,11 +1599,15 @@ static ssize_t pagemap_read(struct file *file, char __user *buf, src = *ppos; svpfn = src / PM_ENTRY_BYTES; - start_vaddr = svpfn << PAGE_SHIFT; end_vaddr = mm->task_size; /* watch out for wraparound */ - if (svpfn > mm->task_size >> PAGE_SHIFT) + start_vaddr = end_vaddr; + if (svpfn <= (ULONG_MAX >> PAGE_SHIFT)) + start_vaddr = untagged_addr(svpfn << PAGE_SHIFT); + + /* Ensure the address is inside the task */ + if (start_vaddr > mm->task_size) start_vaddr = end_vaddr; /* -- cgit v1.2.3