Messages in this thread | | | From | Stephan Mueller <> | Subject | algif_hash: splice of data > 2**16 | Date | Thu, 18 Dec 2014 13:15:28 +0100 |
| |
Hi Herbert,
While testing the vmsplice/splice interface of algif_hash I was made aware of the problem that data blobs larger than 16 pages do not seem to be hashed properly.
For testing, a file is mmap()ed and handed to vmsplice / splice. If the file is smaller than 2**16, the interface returns the proper hash. However, when the file is larger, only the first 2**16 bytes seem to be used.
When adding printk's to hash_sendpage, I see that this function is invoked exactly 16 times where the first 15 invocations have the MSG_MORE flag set and the last invocation does not have MSG_MORE.
To invoke the vmsplice/splice interface, I use my current implementation of libkcapi available at [1]. That library uses the following calls:
vmsplice(handle->pipes[1], iov, iovlen, SPLICE_F_GIFT); splice(handle->pipes[0], NULL, handle->opfd, NULL, inlen, 0); read(handle->opfd, out, outlen);
The return code of splice() is always 65536 irrespectively of the following variations:
- have one iovec pointing to the entire buffer of the mmap()ed file
- have multiple iovecs with all pointing to at most 2**16 bytes
- invoke splice/read multiple times with at most 2**16 bytes
My guess of the problem is that the maximum buffer size for the pipe is 16 pages. These 16 pages are filled with the repeated invocation of hash_sendpage.
Is there a specific way of how the splice interface is to be called so that the pages are released? Or is there a need to change hash_sendpage such that after the af_alg_wait_for_completion call, some form of "releasing/putting" of the used page needs to be added?
Note, hashing the large mmap()ed file with one iovec using the sendmsg() interface works flawlessly.
[1] http://www.chronox.de/libkcapi.html
Thanks Stephan
| |