public inbox for linux-fsdevel@vger.kernel.org
 help / color / mirror / Atom feed
From: "Darrick J. Wong" <djwong@kernel.org>
To: Joanne Koong <joannelkoong@gmail.com>
Cc: fstests@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	bfoster@redhat.com, nirjhar@linux.ibm.com, zlang@redhat.com,
	kernel-team@meta.com
Subject: Re: [PATCH v3 1/2] fsx: support reads/writes from buffers backed by hugepages
Date: Wed, 15 Jan 2025 13:37:13 -0800	[thread overview]
Message-ID: <20250115213713.GE3557695@frogsfrogsfrogs> (raw)
In-Reply-To: <20250115183107.3124743-2-joannelkoong@gmail.com>

On Wed, Jan 15, 2025 at 10:31:06AM -0800, Joanne Koong wrote:
> Add support for reads/writes from buffers backed by hugepages.
> This can be enabled through the '-h' flag. This flag should only be used
> on systems where THP capabilities are enabled.
> 
> This is motivated by a recent bug that was due to faulty handling of
> userspace buffers backed by hugepages. This patch is a mitigation
> against problems like this in the future.
> 
> Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
> Reviewed-by: Brian Foster <bfoster@redhat.com>
> ---
>  ltp/fsx.c | 119 +++++++++++++++++++++++++++++++++++++++++++++++++-----
>  1 file changed, 108 insertions(+), 11 deletions(-)
> 
> diff --git a/ltp/fsx.c b/ltp/fsx.c
> index 41933354..8d3a2e2c 100644
> --- a/ltp/fsx.c
> +++ b/ltp/fsx.c
> @@ -190,6 +190,7 @@ int	o_direct;			/* -Z */
>  int	aio = 0;
>  int	uring = 0;
>  int	mark_nr = 0;
> +int	hugepages = 0;                  /* -h flag */
>  
>  int page_size;
>  int page_mask;
> @@ -2471,7 +2472,7 @@ void
>  usage(void)
>  {
>  	fprintf(stdout, "usage: %s",
> -		"fsx [-dfknqxyzBEFHIJKLORWXZ0]\n\
> +		"fsx [-dfhknqxyzBEFHIJKLORWXZ0]\n\
>  	   [-b opnum] [-c Prob] [-g filldata] [-i logdev] [-j logid]\n\
>  	   [-l flen] [-m start:end] [-o oplen] [-p progressinterval]\n\
>  	   [-r readbdy] [-s style] [-t truncbdy] [-w writebdy]\n\
> @@ -2484,6 +2485,7 @@ usage(void)
>  	-e: pollute post-eof on size changes (default 0)\n\
>  	-f: flush and invalidate cache after I/O\n\
>  	-g X: write character X instead of random generated data\n\
> +	-h hugepages: use buffers backed by hugepages for reads/writes\n\

If this requires MADV_COLLAPSE, then perhaps the help text shouldn't
describe the switch if the support wasn't compiled in?

e.g.

	-g X: write character X instead of random generated data\n"
#ifdef MADV_COLLAPSE
"	-h hugepages: use buffers backed by hugepages for reads/writes\n"
#endif
"	-i logdev: do integrity testing, logdev is the dm log writes device\n\

(assuming I got the preprocessor and string construction goo right; I
might be a few cards short of a deck due to zombie attack earlier)

>  	-i logdev: do integrity testing, logdev is the dm log writes device\n\
>  	-j logid: prefix debug log messsages with this id\n\
>  	-k: do not truncate existing file and use its size as upper bound on file size\n\
> @@ -2856,6 +2858,101 @@ keep_running(void)
>  	return numops-- != 0;
>  }
>  
> +static long
> +get_hugepage_size(void)
> +{
> +	const char str[] = "Hugepagesize:";
> +	size_t str_len =  sizeof(str) - 1;
> +	unsigned int hugepage_size = 0;
> +	char buffer[64];
> +	FILE *file;
> +
> +	file = fopen("/proc/meminfo", "r");
> +	if (!file) {
> +		prterr("get_hugepage_size: fopen /proc/meminfo");
> +		return -1;
> +	}
> +	while (fgets(buffer, sizeof(buffer), file)) {
> +		if (strncmp(buffer, str, str_len) == 0) {
> +			sscanf(buffer + str_len, "%u", &hugepage_size);
> +			break;
> +		}
> +	}
> +	fclose(file);
> +	if (!hugepage_size) {
> +		prterr("get_hugepage_size: failed to find "
> +			"hugepage size in /proc/meminfo\n");
> +		return -1;
> +	}
> +
> +	/* convert from KiB to bytes */
> +	return hugepage_size << 10;
> +}
> +
> +#ifdef MADV_COLLAPSE
> +static void *
> +init_hugepages_buf(unsigned len, int hugepage_size, int alignment)
> +{
> +	void *buf;
> +	long buf_size = roundup(len, hugepage_size) + alignment;
> +
> +	if (posix_memalign(&buf, hugepage_size, buf_size)) {
> +		prterr("posix_memalign for buf");
> +		return NULL;
> +	}
> +	memset(buf, '\0', buf_size);
> +	if (madvise(buf, buf_size, MADV_COLLAPSE)) {

If the fsx runs for a long period of time, will it be necessary to call
MADV_COLLAPSE periodically to ensure that reclaim doesn't break up the
hugepage?

> +		prterr("madvise collapse for buf");
> +		free(buf);
> +		return NULL;
> +	}
> +
> +	return buf;
> +}
> +#else
> +static void *
> +init_hugepages_buf(unsigned len, int hugepage_size, int alignment)
> +{
> +	return NULL;
> +}
> +#endif
> +
> +static void
> +init_buffers(void)
> +{
> +	int i;
> +
> +	original_buf = (char *) malloc(maxfilelen);
> +	for (i = 0; i < maxfilelen; i++)
> +		original_buf[i] = random() % 256;
> +	if (hugepages) {
> +		long hugepage_size = get_hugepage_size();
> +		if (hugepage_size == -1) {
> +			prterr("get_hugepage_size()");
> +			exit(102);
> +		}
> +		good_buf = init_hugepages_buf(maxfilelen, hugepage_size, writebdy);
> +		if (!good_buf) {
> +			prterr("init_hugepages_buf failed for good_buf");
> +			exit(103);
> +		}
> +
> +		temp_buf = init_hugepages_buf(maxoplen, hugepage_size, readbdy);
> +		if (!temp_buf) {
> +			prterr("init_hugepages_buf failed for temp_buf");
> +			exit(103);
> +		}
> +	} else {
> +		unsigned long good_buf_len = maxfilelen + writebdy;
> +		unsigned long temp_buf_len = maxoplen + readbdy;
> +
> +		good_buf = calloc(1, good_buf_len);
> +		temp_buf = calloc(1, temp_buf_len);
> +	}
> +	good_buf = round_ptr_up(good_buf, writebdy, 0);
> +	temp_buf = round_ptr_up(temp_buf, readbdy, 0);
> +}
> +
>  static struct option longopts[] = {
>  	{"replay-ops", required_argument, 0, 256},
>  	{"record-ops", optional_argument, 0, 255},
> @@ -2883,7 +2980,7 @@ main(int argc, char **argv)
>  	setvbuf(stdout, (char *)0, _IOLBF, 0); /* line buffered stdout */
>  
>  	while ((ch = getopt_long(argc, argv,
> -				 "0b:c:de:fg:i:j:kl:m:no:p:qr:s:t:uw:xyABD:EFJKHzCILN:OP:RS:UWXZ",
> +				 "0b:c:de:fg:hi:j:kl:m:no:p:qr:s:t:uw:xyABD:EFJKHzCILN:OP:RS:UWXZ",
>  				 longopts, NULL)) != EOF)
>  		switch (ch) {
>  		case 'b':
> @@ -2916,6 +3013,14 @@ main(int argc, char **argv)
>  		case 'g':
>  			filldata = *optarg;
>  			break;
> +		case 'h':
> +			#ifndef MADV_COLLAPSE

Preprocessor directives should start at column 0, like most of the rest
of fstests.

--D

> +				fprintf(stderr, "MADV_COLLAPSE not supported. "
> +					"Can't support -h\n");
> +				exit(86);
> +			#endif
> +			hugepages = 1;
> +			break;
>  		case 'i':
>  			integrity = 1;
>  			logdev = strdup(optarg);
> @@ -3229,15 +3334,7 @@ main(int argc, char **argv)
>  			exit(95);
>  		}
>  	}
> -	original_buf = (char *) malloc(maxfilelen);
> -	for (i = 0; i < maxfilelen; i++)
> -		original_buf[i] = random() % 256;
> -	good_buf = (char *) malloc(maxfilelen + writebdy);
> -	good_buf = round_ptr_up(good_buf, writebdy, 0);
> -	memset(good_buf, '\0', maxfilelen);
> -	temp_buf = (char *) malloc(maxoplen + readbdy);
> -	temp_buf = round_ptr_up(temp_buf, readbdy, 0);
> -	memset(temp_buf, '\0', maxoplen);
> +	init_buffers();
>  	if (lite) {	/* zero entire existing file */
>  		ssize_t written;
>  
> -- 
> 2.47.1
> 
> 

  reply	other threads:[~2025-01-15 21:37 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-01-15 18:31 [PATCH v3 0/2] fstests: test reads/writes from hugepages-backed buffers Joanne Koong
2025-01-15 18:31 ` [PATCH v3 1/2] fsx: support reads/writes from buffers backed by hugepages Joanne Koong
2025-01-15 21:37   ` Darrick J. Wong [this message]
2025-01-16  0:47     ` Joanne Koong
2025-01-16  0:59       ` Darrick J. Wong
2025-01-16 12:53         ` Brian Foster
2025-01-17  1:26           ` Joanne Koong
2025-01-17 13:27             ` Brian Foster
2025-01-17 17:43               ` Darrick J. Wong
2025-01-17 21:18               ` Joanne Koong
2025-01-17  1:03         ` Joanne Koong
2025-01-17  1:57           ` Darrick J. Wong
2025-01-17 21:48             ` Joanne Koong
2025-01-15 18:31 ` [PATCH v3 2/2] generic: add tests for read/writes from hugepages-backed buffers Joanne Koong
2025-01-15 21:40   ` Darrick J. Wong

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20250115213713.GE3557695@frogsfrogsfrogs \
    --to=djwong@kernel.org \
    --cc=bfoster@redhat.com \
    --cc=fstests@vger.kernel.org \
    --cc=joannelkoong@gmail.com \
    --cc=kernel-team@meta.com \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=nirjhar@linux.ibm.com \
    --cc=zlang@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox