All of lore.kernel.org
 help / color / mirror / Atom feed
From: Hannes Reinecke <hare@suse.de>
To: Matthew Wilcox <willy@infradead.org>
Cc: Luis Chamberlain <mcgrof@kernel.org>,
	Christoph Hellwig <hch@lst.de>, Jens Axboe <axboe@kernel.dk>,
	Pankaj Raghav <p.raghav@samsung.com>,
	linux-block@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	Hannes Reinecke <hare@suse.de>
Subject: [PATCH 15/18] brd: make sector size configurable
Date: Mon, 18 Sep 2023 13:05:07 +0200	[thread overview]
Message-ID: <20230918110510.66470-16-hare@suse.de> (raw)
In-Reply-To: <20230918110510.66470-1-hare@suse.de>

Add a module option 'rd_blksize' to allow the user to change
the sector size of the RAM disks.

Signed-off-by: Hannes Reinecke <hare@suse.de>
---
 drivers/block/brd.c | 50 +++++++++++++++++++++++++++++++--------------
 1 file changed, 35 insertions(+), 15 deletions(-)

diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 90e1b6c4fbc8..0c5f3dbbb77c 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -30,7 +30,7 @@
 /*
  * Each block ramdisk device has a xarray of folios that stores the folios
  * containing the block device's contents. A brd folio's ->index is its offset
- * in PAGE_SIZE units. This is similar to, but in no way connected with,
+ * in brd_sector_size units. This is similar to, but in no way connected with,
  * the kernel's pagecache or buffer cache (which sit above our block device).
  */
 struct brd_device {
@@ -43,9 +43,11 @@ struct brd_device {
 	 */
 	struct xarray	        brd_folios;
 	u64			brd_nr_folios;
+	unsigned int		brd_sector_shift;
+	unsigned int		brd_sector_size;
 };
 
-#define BRD_SECTOR_SHIFT(b) (PAGE_SHIFT - SECTOR_SHIFT)
+#define BRD_SECTOR_SHIFT(b) ((b)->brd_sector_shift - SECTOR_SHIFT)
 
 static pgoff_t brd_sector_index(struct brd_device *brd, sector_t sector)
 {
@@ -85,7 +87,7 @@ static int brd_insert_folio(struct brd_device *brd, sector_t sector, gfp_t gfp)
 {
 	pgoff_t idx;
 	struct folio *folio, *cur;
-	unsigned int rd_sector_order = get_order(PAGE_SIZE);
+	unsigned int rd_sector_order = get_order(brd->brd_sector_size);
 	int ret = 0;
 
 	folio = brd_lookup_folio(brd, sector);
@@ -140,7 +142,7 @@ static void brd_free_folios(struct brd_device *brd)
 static int copy_to_brd_setup(struct brd_device *brd, sector_t sector, size_t n,
 			     gfp_t gfp)
 {
-	unsigned int rd_sector_size = PAGE_SIZE;
+	unsigned int rd_sector_size = brd->brd_sector_size;
 	unsigned int offset = brd_sector_offset(brd, sector);
 	size_t copy;
 	int ret;
@@ -163,7 +165,7 @@ static void copy_to_brd(struct brd_device *brd, const void *src,
 			sector_t sector, size_t n)
 {
 	struct folio *folio;
-	unsigned int rd_sector_size = PAGE_SIZE;
+	unsigned int rd_sector_size = brd->brd_sector_size;
 	unsigned int offset = brd_sector_offset(brd, sector);
 	size_t copy;
 
@@ -181,7 +183,7 @@ static void copy_from_brd(void *dst, struct brd_device *brd,
 			sector_t sector, size_t n)
 {
 	struct folio *folio;
-	unsigned int rd_sector_size = PAGE_SIZE;
+	unsigned int rd_sector_size = brd->brd_sector_size;
 	unsigned int offset = brd_sector_offset(brd, sector);
 	size_t copy;
 
@@ -279,6 +281,10 @@ static int max_part = 1;
 module_param(max_part, int, 0444);
 MODULE_PARM_DESC(max_part, "Num Minors to reserve between devices");
 
+static unsigned int rd_blksize = PAGE_SIZE;
+module_param(rd_blksize, uint, 0444);
+MODULE_PARM_DESC(rd_blksize, "Blocksize of each RAM disk in bytes.");
+
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_BLOCKDEV_MAJOR(RAMDISK_MAJOR);
 MODULE_ALIAS("rd");
@@ -305,6 +311,7 @@ static int brd_alloc(int i)
 	struct brd_device *brd;
 	struct gendisk *disk;
 	char buf[DISK_NAME_LEN];
+	unsigned int rd_max_sectors;
 	int err = -ENOMEM;
 
 	list_for_each_entry(brd, &brd_devices, brd_list)
@@ -315,6 +322,25 @@ static int brd_alloc(int i)
 		return -ENOMEM;
 	brd->brd_number		= i;
 	list_add_tail(&brd->brd_list, &brd_devices);
+	if (!is_power_of_2(rd_blksize)) {
+		pr_err("rd_blksize %d is not supported\n", rd_blksize);
+		err = -EINVAL;
+		goto out_free_dev;
+	}
+	if (rd_blksize < SECTOR_SIZE) {
+		pr_err("rd_blksize must be at least 512 bytes\n");
+		err = -EINVAL;
+		goto out_free_dev;
+	}
+	/* We can't allocate more than MAX_ORDER pages */
+	rd_max_sectors = (1ULL << MAX_ORDER) << PAGE_SECTORS_SHIFT;
+	if ((rd_blksize >> SECTOR_SHIFT) > rd_max_sectors) {
+		pr_err("rd_blocksize too large\n");
+		err = -EINVAL;
+		goto out_free_dev;
+	}
+	brd->brd_sector_shift = ilog2(rd_blksize);
+	brd->brd_sector_size = rd_blksize;
 
 	xa_init(&brd->brd_folios);
 
@@ -334,15 +360,9 @@ static int brd_alloc(int i)
 	disk->private_data	= brd;
 	strscpy(disk->disk_name, buf, DISK_NAME_LEN);
 	set_capacity(disk, rd_size * 2);
-	
-	/*
-	 * This is so fdisk will align partitions on 4k, because of
-	 * direct_access API needing 4k alignment, returning a PFN
-	 * (This is only a problem on very small devices <= 4M,
-	 *  otherwise fdisk will align on 1M. Regardless this call
-	 *  is harmless)
-	 */
-	blk_queue_physical_block_size(disk->queue, PAGE_SIZE);
+
+	blk_queue_physical_block_size(disk->queue, rd_blksize);
+	blk_queue_max_hw_sectors(disk->queue, rd_max_sectors);
 
 	/* Tell the block layer that this is not a rotational device */
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue);
-- 
2.35.3


  parent reply	other threads:[~2023-09-18 11:06 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-09-18 11:04 [RFC PATCH 00/18] block: update buffer_head for Large-block I/O Hannes Reinecke
2023-09-18 11:04 ` [PATCH 01/18] mm/readahead: rework loop in page_cache_ra_unbounded() Hannes Reinecke
     [not found]   ` <CGME20230920115645eucas1p1c8ed9bf515c4532b3e6995f8078a863b@eucas1p1.samsung.com>
2023-09-20 11:56     ` Pankaj Raghav
2023-09-20 14:13       ` Hannes Reinecke
2023-09-21  9:06         ` Pankaj Raghav
2023-09-20 14:18       ` Matthew Wilcox
2023-09-18 11:04 ` [PATCH 02/18] fs/mpage: use blocks_per_folio instead of blocks_per_page Hannes Reinecke
2023-09-18 13:15   ` Matthew Wilcox
2023-09-18 17:45     ` Hannes Reinecke
2023-09-18 11:04 ` [PATCH 03/18] block/buffer_head: introduce block_{index_to_sector,sector_to_index} Hannes Reinecke
2023-09-18 16:36   ` Matthew Wilcox
2023-09-18 17:42     ` Hannes Reinecke
2023-09-18 21:01       ` Matthew Wilcox
2023-09-18 11:04 ` [PATCH 04/18] fs/buffer.c: use accessor function to translate page index to sectors Hannes Reinecke
2023-10-20 19:37   ` Matthew Wilcox
2023-10-21  5:08     ` Matthew Wilcox
2023-10-23  5:03     ` Hannes Reinecke
2023-09-18 11:04 ` [PATCH 05/18] fs/mpage: " Hannes Reinecke
2023-09-18 11:04 ` [PATCH 06/18] fs: Allow fine-grained control of folio sizes Hannes Reinecke
2023-09-18 12:29   ` [lkp] [+550 bytes kernel size regression] [i386-tinyconfig] [8558b2228d] " kernel test robot
2023-09-18 11:04 ` [PATCH 07/18] mm/filemap: allocate folios with mapping order preference Hannes Reinecke
2023-09-18 13:41   ` Matthew Wilcox
2023-09-18 17:34     ` Hannes Reinecke
2023-09-18 11:05 ` [PATCH 08/18] mm/readahead: " Hannes Reinecke
2023-09-18 13:11   ` kernel test robot
2023-09-18 20:46   ` kernel test robot
2023-09-18 11:05 ` [PATCH 09/18] fs/buffer: use mapping order in grow_dev_page() Hannes Reinecke
2023-09-18 14:00   ` Matthew Wilcox
2023-09-18 17:38     ` Hannes Reinecke
2023-09-18 11:05 ` [PATCH 10/18] block/bdev: lift restrictions on supported blocksize Hannes Reinecke
2023-09-18 11:05 ` [PATCH 11/18] block/bdev: enable large folio support for large logical block sizes Hannes Reinecke
2023-09-18 11:05 ` [PATCH 12/18] brd: convert to folios Hannes Reinecke
2023-09-18 11:05 ` [PATCH 13/18] brd: abstract page_size conventions Hannes Reinecke
2023-09-18 11:05 ` [PATCH 14/18] brd: use memcpy_{to,from}_folio() Hannes Reinecke
2023-09-18 11:05 ` Hannes Reinecke [this message]
2023-09-18 11:05 ` [PATCH 16/18] brd: make logical sector size configurable Hannes Reinecke
2023-09-18 11:05 ` [PATCH 17/18] xfs: remove check for block sizes smaller than PAGE_SIZE Hannes Reinecke
2023-09-20  2:13   ` Dave Chinner
2023-09-18 11:05 ` [PATCH 18/18] nvme: enable logical block size > PAGE_SIZE Hannes Reinecke

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=20230918110510.66470-16-hare@suse.de \
    --to=hare@suse.de \
    --cc=axboe@kernel.dk \
    --cc=hch@lst.de \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=mcgrof@kernel.org \
    --cc=p.raghav@samsung.com \
    --cc=willy@infradead.org \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.