On Mon, 3 Nov 2014, Ilya Dryomov wrote:
> Large (greater than 32k, the value of PAGE_ALLOC_COSTLY_ORDER) auth
> tickets will have their buffers vmalloc'ed, which leads to the
> following crash in crypto:
>
> [ 28.685082] BUG: unable to handle kernel paging request at ffffeb04000032c0
> [ 28.686032] IP: [<ffffffff81392b42>] scatterwalk_pagedone+0x22/0x80
> [ 28.686032] PGD 0
> [ 28.688088] Oops: 0000 [#1] PREEMPT SMP
> [ 28.688088] Modules linked in:
> [ 28.688088] CPU: 0 PID: 878 Comm: kworker/0:2 Not tainted 3.17.0-vm+ #305
> [ 28.688088] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2007
> [ 28.688088] Workqueue: ceph-msgr con_work
> [ 28.688088] task: ffff88011a7f9030 ti: ffff8800d903c000 task.ti: ffff8800d903c000
> [ 28.688088] RIP: 0010:[<ffffffff81392b42>] [<ffffffff81392b42>] scatterwalk_pagedone+0x22/0x80
> [ 28.688088] RSP: 0018:ffff8800d903f688 EFLAGS: 00010286
> [ 28.688088] RAX: ffffeb04000032c0 RBX: ffff8800d903f718 RCX: ffffeb04000032c0
> [ 28.688088] RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff8800d903f750
> [ 28.688088] RBP: ffff8800d903f688 R08: 00000000000007de R09: ffff8800d903f880
> [ 28.688088] R10: 18df467c72d6257b R11: 0000000000000000 R12: 0000000000000010
> [ 28.688088] R13: ffff8800d903f750 R14: ffff8800d903f8a0 R15: 0000000000000000
> [ 28.688088] FS: 00007f50a41c7700(0000) GS:ffff88011fc00000(0000) knlGS:0000000000000000
> [ 28.688088] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
> [ 28.688088] CR2: ffffeb04000032c0 CR3: 00000000da3f3000 CR4: 00000000000006b0
> [ 28.688088] Stack:
> [ 28.688088] ffff8800d903f698 ffffffff81392ca8 ffff8800d903f6e8 ffffffff81395d32
> [ 28.688088] ffff8800dac96000 ffff880000000000 ffff8800d903f980 ffff880119b7e020
> [ 28.688088] ffff880119b7e010 0000000000000000 0000000000000010 0000000000000010
> [ 28.688088] Call Trace:
> [ 28.688088] [<ffffffff81392ca8>] scatterwalk_done+0x38/0x40
> [ 28.688088] [<ffffffff81392ca8>] scatterwalk_done+0x38/0x40
> [ 28.688088] [<ffffffff81395d32>] blkcipher_walk_done+0x182/0x220
> [ 28.688088] [<ffffffff813990bf>] crypto_cbc_encrypt+0x15f/0x180
> [ 28.688088] [<ffffffff81399780>] ? crypto_aes_set_key+0x30/0x30
> [ 28.688088] [<ffffffff8156c40c>] ceph_aes_encrypt2+0x29c/0x2e0
> [ 28.688088] [<ffffffff8156d2a3>] ceph_encrypt2+0x93/0xb0
> [ 28.688088] [<ffffffff8156d7da>] ceph_x_encrypt+0x4a/0x60
> [ 28.688088] [<ffffffff8155b39d>] ? ceph_buffer_new+0x5d/0xf0
> [ 28.688088] [<ffffffff8156e837>] ceph_x_build_authorizer.isra.6+0x297/0x360
> [ 28.688088] [<ffffffff8112089b>] ? kmem_cache_alloc_trace+0x11b/0x1c0
> [ 28.688088] [<ffffffff8156b496>] ? ceph_auth_create_authorizer+0x36/0x80
> [ 28.688088] [<ffffffff8156ed83>] ceph_x_create_authorizer+0x63/0xd0
> [ 28.688088] [<ffffffff8156b4b4>] ceph_auth_create_authorizer+0x54/0x80
> [ 28.688088] [<ffffffff8155f7c0>] get_authorizer+0x80/0xd0
> [ 28.688088] [<ffffffff81555a8b>] prepare_write_connect+0x18b/0x2b0
> [ 28.688088] [<ffffffff81559289>] try_read+0x1e59/0x1f10
>
> This is because we set up crypto scatterlists as if all buffers were
> kmalloc'ed. Fix it.
>
> Cc: stable@xxxxxxxxxxxxxxx
> Signed-off-by: Ilya Dryomov <idryomov@xxxxxxxxxx>
Looks good!
Reviewed-by: Sage Weil <sage@xxxxxxxxxx>
> ---
> v2:
> - no single page limit
>
> net/ceph/crypto.c | 169 +++++++++++++++++++++++++++++++++++++++++------------
> 1 file changed, 132 insertions(+), 37 deletions(-)
>
> diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c
> index 62fc5e7a9acf..e809e6067f5d 100644
> --- a/net/ceph/crypto.c
> +++ b/net/ceph/crypto.c
> @@ -90,11 +90,82 @@ static struct crypto_blkcipher *ceph_crypto_alloc_cipher(void)
>
> static const u8 *aes_iv = (u8 *)CEPH_AES_IV;
>
> +/*
> + * Should be used for buffers allocated with ceph_kvmalloc().
> + * Currently these are encrypt out-buffer (ceph_buffer) and decrypt
> + * in-buffer (msg front).
> + *
> + * Dispose of @sgt with teardown_sgtable().
> + *
> + * @prealloc_sg is to avoid memory allocation inside sg_alloc_table()
> + * in cases where a single sg is sufficient. No attempt to reduce the
> + * number of sgs by squeezing physically contiguous pages together is
> + * made though, for simplicity.
> + */
> +static int setup_sgtable(struct sg_table *sgt, struct scatterlist *prealloc_sg,
> + const void *buf, unsigned int buf_len)
> +{
> + struct scatterlist *sg;
> + const bool is_vmalloc = is_vmalloc_addr(buf);
> + unsigned int off = offset_in_page(buf);
> + unsigned int chunk_cnt = 1;
> + unsigned int chunk_len = PAGE_ALIGN(off + buf_len);
> + int i;
> + int ret;
> +
> + if (buf_len == 0) {
> + memset(sgt, 0, sizeof(*sgt));
> + return -EINVAL;
> + }
> +
> + if (is_vmalloc) {
> + chunk_cnt = chunk_len >> PAGE_SHIFT;
> + chunk_len = PAGE_SIZE;
> + }
> +
> + if (chunk_cnt > 1) {
> + ret = sg_alloc_table(sgt, chunk_cnt, GFP_NOFS);
> + if (ret)
> + return ret;
> + } else {
> + BUG_ON(chunk_cnt != 1);
> + sg_init_table(prealloc_sg, 1);
> + sgt->sgl = prealloc_sg;
> + sgt->nents = sgt->orig_nents = 1;
> + }
> +
> + for_each_sg(sgt->sgl, sg, sgt->orig_nents, i) {
> + struct page *page;
> + unsigned int len = min(chunk_len - off, buf_len);
> +
> + if (is_vmalloc)
> + page = vmalloc_to_page(buf);
> + else
> + page = virt_to_page(buf);
> +
> + sg_set_page(sg, page, len, off);
> +
> + off = 0;
> + buf += len;
> + buf_len -= len;
> + }
> + BUG_ON(buf_len != 0);
> +
> + return 0;
> +}
> +
> +static void teardown_sgtable(struct sg_table *sgt)
> +{
> + if (sgt->orig_nents > 1)
> + sg_free_table(sgt);
> +}
> +
> static int ceph_aes_encrypt(const void *key, int key_len,
> void *dst, size_t *dst_len,
> const void *src, size_t src_len)
> {
> - struct scatterlist sg_in[2], sg_out[1];
> + struct scatterlist sg_in[2], prealloc_sg;
> + struct sg_table sg_out;
> struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher();
> struct blkcipher_desc desc = { .tfm = tfm, .flags = 0 };
> int ret;
> @@ -110,16 +181,18 @@ static int ceph_aes_encrypt(const void *key, int key_len,
>
> *dst_len = src_len + zero_padding;
>
> - crypto_blkcipher_setkey((void *)tfm, key, key_len);
> sg_init_table(sg_in, 2);
> sg_set_buf(&sg_in[0], src, src_len);
> sg_set_buf(&sg_in[1], pad, zero_padding);
> - sg_init_table(sg_out, 1);
> - sg_set_buf(sg_out, dst, *dst_len);
> + ret = setup_sgtable(&sg_out, &prealloc_sg, dst, *dst_len);
> + if (ret)
> + goto out_tfm;
> +
> + crypto_blkcipher_setkey((void *)tfm, key, key_len);
> iv = crypto_blkcipher_crt(tfm)->iv;
> ivsize = crypto_blkcipher_ivsize(tfm);
> -
> memcpy(iv, aes_iv, ivsize);
> +
> /*
> print_hex_dump(KERN_ERR, "enc key: ", DUMP_PREFIX_NONE, 16, 1,
> key, key_len, 1);
> @@ -128,16 +201,22 @@ static int ceph_aes_encrypt(const void *key, int key_len,
> print_hex_dump(KERN_ERR, "enc pad: ", DUMP_PREFIX_NONE, 16, 1,
> pad, zero_padding, 1);
> */
> - ret = crypto_blkcipher_encrypt(&desc, sg_out, sg_in,
> + ret = crypto_blkcipher_encrypt(&desc, sg_out.sgl, sg_in,
> src_len + zero_padding);
> - crypto_free_blkcipher(tfm);
> - if (ret < 0)
> + if (ret < 0) {
> pr_err("ceph_aes_crypt failed %d\n", ret);
> + goto out_sg;
> + }
> /*
> print_hex_dump(KERN_ERR, "enc out: ", DUMP_PREFIX_NONE, 16, 1,
> dst, *dst_len, 1);
> */
> - return 0;
> +
> +out_sg:
> + teardown_sgtable(&sg_out);
> +out_tfm:
> + crypto_free_blkcipher(tfm);
> + return ret;
> }
>
> static int ceph_aes_encrypt2(const void *key, int key_len, void *dst,
> @@ -145,7 +224,8 @@ static int ceph_aes_encrypt2(const void *key, int key_len, void *dst,
> const void *src1, size_t src1_len,
> const void *src2, size_t src2_len)
> {
> - struct scatterlist sg_in[3], sg_out[1];
> + struct scatterlist sg_in[3], prealloc_sg;
> + struct sg_table sg_out;
> struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher();
> struct blkcipher_desc desc = { .tfm = tfm, .flags = 0 };
> int ret;
> @@ -161,17 +241,19 @@ static int ceph_aes_encrypt2(const void *key, int key_len, void *dst,
>
> *dst_len = src1_len + src2_len + zero_padding;
>
> - crypto_blkcipher_setkey((void *)tfm, key, key_len);
> sg_init_table(sg_in, 3);
> sg_set_buf(&sg_in[0], src1, src1_len);
> sg_set_buf(&sg_in[1], src2, src2_len);
> sg_set_buf(&sg_in[2], pad, zero_padding);
> - sg_init_table(sg_out, 1);
> - sg_set_buf(sg_out, dst, *dst_len);
> + ret = setup_sgtable(&sg_out, &prealloc_sg, dst, *dst_len);
> + if (ret)
> + goto out_tfm;
> +
> + crypto_blkcipher_setkey((void *)tfm, key, key_len);
> iv = crypto_blkcipher_crt(tfm)->iv;
> ivsize = crypto_blkcipher_ivsize(tfm);
> -
> memcpy(iv, aes_iv, ivsize);
> +
> /*
> print_hex_dump(KERN_ERR, "enc key: ", DUMP_PREFIX_NONE, 16, 1,
> key, key_len, 1);
> @@ -182,23 +264,30 @@ static int ceph_aes_encrypt2(const void *key, int key_len, void *dst,
> print_hex_dump(KERN_ERR, "enc pad: ", DUMP_PREFIX_NONE, 16, 1,
> pad, zero_padding, 1);
> */
> - ret = crypto_blkcipher_encrypt(&desc, sg_out, sg_in,
> + ret = crypto_blkcipher_encrypt(&desc, sg_out.sgl, sg_in,
> src1_len + src2_len + zero_padding);
> - crypto_free_blkcipher(tfm);
> - if (ret < 0)
> + if (ret < 0) {
> pr_err("ceph_aes_crypt2 failed %d\n", ret);
> + goto out_sg;
> + }
> /*
> print_hex_dump(KERN_ERR, "enc out: ", DUMP_PREFIX_NONE, 16, 1,
> dst, *dst_len, 1);
> */
> - return 0;
> +
> +out_sg:
> + teardown_sgtable(&sg_out);
> +out_tfm:
> + crypto_free_blkcipher(tfm);
> + return ret;
> }
>
> static int ceph_aes_decrypt(const void *key, int key_len,
> void *dst, size_t *dst_len,
> const void *src, size_t src_len)
> {
> - struct scatterlist sg_in[1], sg_out[2];
> + struct sg_table sg_in;
> + struct scatterlist sg_out[2], prealloc_sg;
> struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher();
> struct blkcipher_desc desc = { .tfm = tfm };
> char pad[16];
> @@ -210,16 +299,16 @@ static int ceph_aes_decrypt(const void *key, int key_len,
> if (IS_ERR(tfm))
> return PTR_ERR(tfm);
>
> - crypto_blkcipher_setkey((void *)tfm, key, key_len);
> - sg_init_table(sg_in, 1);
> sg_init_table(sg_out, 2);
> - sg_set_buf(sg_in, src, src_len);
> sg_set_buf(&sg_out[0], dst, *dst_len);
> sg_set_buf(&sg_out[1], pad, sizeof(pad));
> + ret = setup_sgtable(&sg_in, &prealloc_sg, src, src_len);
> + if (ret)
> + goto out_tfm;
>
> + crypto_blkcipher_setkey((void *)tfm, key, key_len);
> iv = crypto_blkcipher_crt(tfm)->iv;
> ivsize = crypto_blkcipher_ivsize(tfm);
> -
> memcpy(iv, aes_iv, ivsize);
>
> /*
> @@ -228,12 +317,10 @@ static int ceph_aes_decrypt(const void *key, int key_len,
> print_hex_dump(KERN_ERR, "dec in: ", DUMP_PREFIX_NONE, 16, 1,
> src, src_len, 1);
> */
> -
> - ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in, src_len);
> - crypto_free_blkcipher(tfm);
> + ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in.sgl, src_len);
> if (ret < 0) {
> pr_err("ceph_aes_decrypt failed %d\n", ret);
> - return ret;
> + goto out_sg;
> }
>
> if (src_len <= *dst_len)
> @@ -251,7 +338,12 @@ static int ceph_aes_decrypt(const void *key, int key_len,
> print_hex_dump(KERN_ERR, "dec out: ", DUMP_PREFIX_NONE, 16, 1,
> dst, *dst_len, 1);
> */
> - return 0;
> +
> +out_sg:
> + teardown_sgtable(&sg_in);
> +out_tfm:
> + crypto_free_blkcipher(tfm);
> + return ret;
> }
>
> static int ceph_aes_decrypt2(const void *key, int key_len,
> @@ -259,7 +351,8 @@ static int ceph_aes_decrypt2(const void *key, int key_len,
> void *dst2, size_t *dst2_len,
> const void *src, size_t src_len)
> {
> - struct scatterlist sg_in[1], sg_out[3];
> + struct sg_table sg_in;
> + struct scatterlist sg_out[3], prealloc_sg;
> struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher();
> struct blkcipher_desc desc = { .tfm = tfm };
> char pad[16];
> @@ -271,17 +364,17 @@ static int ceph_aes_decrypt2(const void *key, int key_len,
> if (IS_ERR(tfm))
> return PTR_ERR(tfm);
>
> - sg_init_table(sg_in, 1);
> - sg_set_buf(sg_in, src, src_len);
> sg_init_table(sg_out, 3);
> sg_set_buf(&sg_out[0], dst1, *dst1_len);
> sg_set_buf(&sg_out[1], dst2, *dst2_len);
> sg_set_buf(&sg_out[2], pad, sizeof(pad));
> + ret = setup_sgtable(&sg_in, &prealloc_sg, src, src_len);
> + if (ret)
> + goto out_tfm;
>
> crypto_blkcipher_setkey((void *)tfm, key, key_len);
> iv = crypto_blkcipher_crt(tfm)->iv;
> ivsize = crypto_blkcipher_ivsize(tfm);
> -
> memcpy(iv, aes_iv, ivsize);
>
> /*
> @@ -290,12 +383,10 @@ static int ceph_aes_decrypt2(const void *key, int key_len,
> print_hex_dump(KERN_ERR, "dec in: ", DUMP_PREFIX_NONE, 16, 1,
> src, src_len, 1);
> */
> -
> - ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in, src_len);
> - crypto_free_blkcipher(tfm);
> + ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in.sgl, src_len);
> if (ret < 0) {
> pr_err("ceph_aes_decrypt failed %d\n", ret);
> - return ret;
> + goto out_sg;
> }
>
> if (src_len <= *dst1_len)
> @@ -325,7 +416,11 @@ static int ceph_aes_decrypt2(const void *key, int key_len,
> dst2, *dst2_len, 1);
> */
>
> - return 0;
> +out_sg:
> + teardown_sgtable(&sg_in);
> +out_tfm:
> + crypto_free_blkcipher(tfm);
> + return ret;
> }
>
>
> --
> 1.7.10.4
>
> --
> To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
> the body of a message to majordomo@xxxxxxxxxxxxxxx
> More majordomo info at http://vger.kernel.org/majordomo-info.html
>
>
--
To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
