path: root/drivers/block/drbd/drbd_actlog.c

// SPDX-License-Identifier: GPL-2.0-or-later
/*
   drbd_actlog.c

   This file is part of DRBD by Philipp Reisner and Lars Ellenberg.

   Copyright (C) 2003-2008, LINBIT Information Technologies GmbH.
   Copyright (C) 2003-2008, Philipp Reisner <philipp.reisner@linbit.com>.
   Copyright (C) 2003-2008, Lars Ellenberg <lars.ellenberg@linbit.com>.


 */

#include <linux/slab.h>
#include <linux/crc32c.h>
#include <linux/drbd.h>
#include <linux/drbd_limits.h>
#include "drbd_int.h"


enum al_transaction_types {
	AL_TR_UPDATE = 0,
	AL_TR_INITIALIZED = 0xffff
};
/* all fields on disc in big endian */
struct __packed al_transaction_on_disk {
	/* don't we all like magic */
	__be32	magic;

	/* to identify the most recent transaction block
	 * in the on disk ring buffer */
	__be32	tr_number;

	/* checksum on the full 4k block, with this field set to 0. */
	__be32	crc32c;

	/* type of transaction, special transaction types like:
	 * purge-all, set-all-idle, set-all-active, ... to-be-defined
	 * see also enum al_transaction_types */
	__be16	transaction_type;

	/* we currently allow only a few thousand extents,
	 * so 16bit will be enough for the slot number. */

	/* how many updates in this transaction */
	__be16	n_updates;

	/* maximum slot number, "al-extents" in drbd.conf speak.
	 * Having this in each transaction should make reconfiguration
	 * of that parameter easier. */
	__be16	context_size;

	/* slot number the context starts with */
	__be16	context_start_slot_nr;

	/* Some reserved bytes.  Expected usage is a 64bit counter of
	 * sectors-written since device creation, and other data generation tag
	 * supporting usage */
	__be32	__reserved[4];

	/* --- 36 byte used --- */

	/* Reserve space for up to AL_UPDATES_PER_TRANSACTION changes
	 * in one transaction, then use the remaining byte in the 4k block for
	 * context information.  "Flexible" number of updates per transaction
	 * does not help, as we have to account for the case when all update
	 * slots are used anyways, so it would only complicate code without
	 * additional benefit.
	 */
	__be16	update_slot_nr[AL_UPDATES_PER_TRANSACTION];

	/* but the extent number is 32bit, which at an extent size of 4 MiB
	 * allows to cover device sizes of up to 2**54 Byte (16 PiB) */
	__be32	update_extent_nr[AL_UPDATES_PER_TRANSACTION];

	/* --- 420 bytes used (36 + 64*6) --- */

	/* 4096 - 420 = 3676 = 919 * 4 */
	__be32	context[AL_CONTEXT_PER_TRANSACTION];
};

void *drbd_md_get_buffer(struct drbd_device *device, const char *intent)
{
	int r;

	wait_event(device->misc_wait,
		   (r = atomic_cmpxchg(&device->md_io.in_use, 0, 1)) == 0 ||
		   device->state.disk <= D_FAILED);

	if (r)
		return NULL;

	device->md_io.current_use = intent;
	device->md_io.start_jif = jiffies;
	device->md_io.submit_jif = device->md_io.start_jif - 1;
	return page_address(device->md_io.page);
}

void drbd_md_put_buffer(struct drbd_device *device)
{
	if (atomic_dec_and_test(&device->md_io.in_use))
		wake_up(&device->misc_wait);
}

void wait_until_done_or_force_detached(struct drbd_device *device, struct drbd_backing_dev *bdev,
				     unsigned int *done)
{
	long dt;

	rcu_read_lock();
	dt = rcu_dereference(bdev->disk_conf)->disk_timeout;
	rcu_read_unlock();
	dt = dt * HZ / 10;
	if (dt == 0)
		dt = MAX_SCHEDULE_TIMEOUT;

	dt = wait_event_timeout(device->misc_wait,
			*done || test_bit(FORCE_DETACH, &device->flags), dt);
	if (dt == 0) {
		drbd_err(device, "meta-data IO operation timed out\n");
		drbd_chk_io_error(device, 1, DRBD_FORCE_DETACH);
	}
}

static int _drbd_md_sync_page_io(struct drbd_device *device,
				 struct drbd_backing_dev *bdev,
				 sector_t sector, enum req_op op)
{
	struct bio *bio;
	/* we do all our meta data IO in aligned 4k blocks. */
	const int size = 4096;
	int err;
	blk_opf_t op_flags = 0;

	device->md_io.done = 0;
	device->md_io.error = -ENODEV;

	if ((op == REQ_OP_WRITE) && !test_bit(MD_NO_FUA, &device->flags))
		op_flags |= REQ_FUA | REQ_PREFLUSH;
	op_flags