Re: [PATCH v2 1/2] fsx: support reads/writes from buffers backed by hugepages

[Nirjhar Roy <nirjhar@linux.ibm.com>]

On 12/28/24 01:03, 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>
> ---
>   ltp/fsx.c | 108 ++++++++++++++++++++++++++++++++++++++++++++++++------
>   1 file changed, 97 insertions(+), 11 deletions(-)
>
> diff --git a/ltp/fsx.c b/ltp/fsx.c
> index 41933354..fb6a9b31 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\
>   	-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 +2858,95 @@ 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;
Thanks for the change.
> +}
> +
> +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)) {
> +		prterr("madvise collapse for buf");
> +		free(buf);
> +		return NULL;
> +	}
> +
> +	return buf;
> +}
> +
> +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(100);
> +		}
> +		good_buf = init_hugepages_buf(maxfilelen, hugepage_size, writebdy);
> +		if (!good_buf) {
> +			prterr("init_hugepages_buf failed for good_buf");
> +			exit(101);
> +		}
> +
> +		temp_buf = init_hugepages_buf(maxoplen, hugepage_size, readbdy);
> +		if (!temp_buf) {
> +			prterr("init_hugepages_buf failed for temp_buf");
> +			exit(101);
> +		}
> +	} else {
> +		unsigned long good_buf_len = maxfilelen + writebdy;
> +		unsigned long temp_buf_len = maxoplen + readbdy;
> +
> +		good_buf = (char *) malloc(good_buf_len);
> +		memset(good_buf, '\0', good_buf_len);
minor:  maybe good_buf = (char *)calloc(1, good_buf_len); So we don't 
need to use memset.
> +		temp_buf = (char *) malloc(temp_buf_len);
> +		memset(temp_buf, '\0', 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 +2974,7 @@ 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 +3007,9 @@ main(int argc, char **argv)
>   		case 'g':
>   			filldata = *optarg;
>   			break;
> +		case 'h':
> +			hugepages = 1;
> +			break;
>   		case 'i':
>   			integrity = 1;
>   			logdev = strdup(optarg);
> @@ -3229,15 +3323,7 @@ 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;
>   

-- 
Nirjhar Roy
Linux Kernel Developer
IBM, Bangalore