mm: hwpoison: coredump: support recovery from dump_user_range()

dump_user_range() is used to copy the user page to a coredump file, but if
a hardware memory error occurred during copy, which called from
__kernel_write_iter() in dump_user_range(), it crashes,

  CPU: 112 PID: 7014 Comm: mca-recover Not tainted 6.3.0-rc2 #425

  pc : __memcpy+0x110/0x260
  lr : _copy_from_iter+0x3bc/0x4c8
  ...
  Call trace:
   __memcpy+0x110/0x260
   copy_page_from_iter+0xcc/0x130
   pipe_write+0x164/0x6d8
   __kernel_write_iter+0x9c/0x210
   dump_user_range+0xc8/0x1d8
   elf_core_dump+0x308/0x368
   do_coredump+0x2e8/0xa40
   get_signal+0x59c/0x788
   do_signal+0x118/0x1f8
   do_notify_resume+0xf0/0x280
   el0_da+0x130/0x138
   el0t_64_sync_handler+0x68/0xc0
   el0t_64_sync+0x188/0x190

Generally, the '->write_iter' of file ops will use copy_page_from_iter()
and copy_page_from_iter_atomic(), change memcpy() to copy_mc_to_kernel()
in both of them to handle #MC during source read, which stop coredump
processing and kill the task instead of kernel panic, but the source
address may not always a user address, so introduce a new copy_mc flag in
struct iov_iter{} to indicate that the iter could do a safe memory copy,
also introduce the helpers to set/cleck the flag, for now, it's only used
in coredump's dump_user_range(), but it could expand to any other
scenarios to fix the similar issue.

Link: https://lkml.kernel.org/r/20230417045323.11054-1-wangkefeng.wang@huawei.com
Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Tong Tiangen <tongtiangen@huawei.com>
Cc: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

3 files changed, 32 insertions, 2 deletions

diff --git a/fs/coredump.c b/fs/coredump.c
index 5df1e6e1eb2b..ece7badf701b 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -882,6 +882,7 @@ static int dump_emit_page(struct coredump_params *cprm, struct page *page)
 	pos = file->f_pos;
 	bvec_set_page(&bvec, page, PAGE_SIZE, 0);
 	iov_iter_bvec(&iter, ITER_SOURCE, &bvec, 1, PAGE_SIZE);
+	iov_iter_set_copy_mc(&iter);
 	n = __kernel_write_iter(cprm->file, &iter, &pos);
 	if (n != PAGE_SIZE)
 		return 0;
diff --git a/include/linux/uio.h b/include/linux/uio.h
index 3d386849a758..044c1d8c230c 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -42,6 +42,7 @@ struct iov_iter_state {
 
 struct iov_iter {
 	u8 iter_type;
+	bool copy_mc;
 	bool nofault;
 	bool data_source;
 	bool user_backed;
@@ -256,8 +257,22 @@ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i);
 
 #ifdef CONFIG_ARCH_HAS_COPY_MC
 size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i);
+static inline void iov_iter_set_copy_mc(struct iov_iter *i)
+{
+	i->copy_mc = true;
+}
+
+static inline bool iov_iter_is_copy_mc(const struct iov_iter *i)
+{
+	return i->copy_mc;
+}
 #else
 #define _copy_mc_to_iter _copy_to_iter
+static inline void iov_iter_set_copy_mc(struct iov_iter *i) { }
+static inline bool iov_iter_is_copy_mc(const struct iov_iter *i)
+{
+	return false;
+}
 #endif
 
 size_t iov_iter_zero(size_t bytes, struct iov_iter *);
@@ -380,6 +395,7 @@ static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction,
 	WARN_ON(direction & ~(READ | WRITE));
 	*i = (struct iov_iter) {
 		.iter_type = ITER_UBUF,
+		.copy_mc = false,
 		.user_backed = true,
 		.data_source = direction,
 		.ubuf = buf,
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index c3dbe994112c..960223ed9199 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -434,6 +434,7 @@ void iov_iter_init(struct iov_iter *i, unsigned int direction,
 	WARN_ON(direction & ~(READ | WRITE));
 	*i = (struct iov_iter) {
 		.iter_type = ITER_IOVEC,
+		.copy_mc = false,
 		.nofault = false,
 		.user_backed = true,
 		.data_source = direction,
@@ -630,6 +631,14 @@ size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
 EXPORT_SYMBOL_GPL(_copy_mc_to_iter);
 #endif /* CONFIG_ARCH_HAS_COPY_MC */
 
+static void *memcpy_from_iter(struct iov_iter *i, void *to, const void *from,
+				 size_t size)
+{
+	if (iov_iter_is_copy_mc(i))
+		return (void *)copy_mc_to_kernel(to, from, size);
+	return memcpy(to, from, size);
+}
+
 size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
 {
 	if (WARN_ON_ONCE(!i->data_source))
@@ -639,7 +648,7 @@ size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
 		might_fault();
 	iterate_and_advance(i, bytes, base, len, off,
 		copyin(addr + off, base, len),
-		memcpy(addr + off, base, len)
+		memcpy_from_iter(i, addr + off, base, len)
 	)
 
 	return bytes;
@@ -862,7 +871,7 @@ size_t copy_page_from_iter_atomic(struct page *page, unsigned offset, size_t byt
 	}
 	iterate_and_advance(i, bytes, base, len, off,
 		copyin(p + off, base, len),
-		memcpy(p + off, base, len)
+		memcpy_from_iter(i, p + off, base, len)
 	)
 	kunmap_atomic(kaddr);
 	return bytes;
@@ -1043,6 +1052,7 @@ void iov_iter_kvec(struct iov_iter *i, unsigned int direction,
 	WARN_ON(direction & ~(READ | WRITE));
 	*i = (struct iov_iter){
 		.iter_type = ITER_KVEC,
+		.copy_mc = false,
 		.data_source = direction,
 		.kvec = kvec,
 		.nr_segs = nr_segs,
@@ -1059,6 +1069,7 @@ void iov_iter_bvec(struct iov_iter *i, unsigned int direction,
 	WARN_ON(direction & ~(READ | WRITE));
 	*i = (struct iov_iter){
 		.iter_type = ITER_BVEC,
+		.copy_mc = false,
 		.data_source = direction,
 		.bvec = bvec,
 		.nr_segs = nr_segs,
@@ -1105,6 +1116,7 @@ void iov_iter_xarray(struct iov_iter *i, unsigned int direction,
 	BUG_ON(direction & ~1);
 	*i = (struct iov_iter) {
 		.iter_type = ITER_XARRAY,
+		.copy_mc = false,
 		.data_source = direction,
 		.xarray = xarray,
 		.xarray_start = start,
@@ -1128,6 +1140,7 @@ void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count)
 	BUG_ON(direction != READ);
 	*i = (struct iov_iter){
 		.iter_type = ITER_DISCARD,
+		.copy_mc = false,
 		.data_source = false,
 		.count = count,
 		.iov_offset = 0