From 072de836f53be56a70cecf70b43ae43b7ce17376 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Mon, 11 Dec 2023 10:08:36 +0000
Subject: [PATCH] mk-rootfs.sh
---
kernel/drivers/nvdimm/pmem.c | 282 ++++++++++++++++++++++++++++++++------------------------
1 files changed, 162 insertions(+), 120 deletions(-)
diff --git a/kernel/drivers/nvdimm/pmem.c b/kernel/drivers/nvdimm/pmem.c
index 18e1042..d5dd79b 100644
--- a/kernel/drivers/nvdimm/pmem.c
+++ b/kernel/drivers/nvdimm/pmem.c
@@ -1,21 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Persistent Memory Driver
*
* Copyright (c) 2014-2015, Intel Corporation.
* Copyright (c) 2015, Christoph Hellwig <hch@lst.de>.
* Copyright (c) 2015, Boaz Harrosh <boaz@plexistor.com>.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
*/
-#include <asm/cacheflush.h>
#include <linux/blkdev.h>
#include <linux/hdreg.h>
#include <linux/init.h>
@@ -33,10 +24,11 @@
#include <linux/dax.h>
#include <linux/nd.h>
#include <linux/backing-dev.h>
+#include <linux/mm.h>
+#include <asm/cacheflush.h>
#include "pmem.h"
#include "pfn.h"
#include "nd.h"
-#include "nd-core.h"
static struct device *to_dev(struct pmem_device *pmem)
{
@@ -133,7 +125,7 @@
while (len) {
mem = kmap_atomic(page);
chunk = min_t(unsigned int, len, PAGE_SIZE - off);
- rem = memcpy_mcsafe(mem + off, pmem_addr, chunk);
+ rem = copy_mc_to_kernel(mem + off, pmem_addr, chunk);
kunmap_atomic(mem);
if (rem)
return BLK_STS_IOERR;
@@ -145,9 +137,25 @@
return BLK_STS_OK;
}
-static blk_status_t pmem_do_bvec(struct pmem_device *pmem, struct page *page,
- unsigned int len, unsigned int off, unsigned int op,
- sector_t sector)
+static blk_status_t pmem_do_read(struct pmem_device *pmem,
+ struct page *page, unsigned int page_off,
+ sector_t sector, unsigned int len)
+{
+ blk_status_t rc;
+ phys_addr_t pmem_off = sector * 512 + pmem->data_offset;
+ void *pmem_addr = pmem->virt_addr + pmem_off;
+
+ if (unlikely(is_bad_pmem(&pmem->bb, sector, len)))
+ return BLK_STS_IOERR;
+
+ rc = read_pmem(page, page_off, pmem_addr, len);
+ flush_dcache_page(page);
+ return rc;
+}
+
+static blk_status_t pmem_do_write(struct pmem_device *pmem,
+ struct page *page, unsigned int page_off,
+ sector_t sector, unsigned int len)
{
blk_status_t rc = BLK_STS_OK;
bool bad_pmem = false;
@@ -157,40 +165,31 @@
if (unlikely(is_bad_pmem(&pmem->bb, sector, len)))
bad_pmem = true;
- if (!op_is_write(op)) {
- if (unlikely(bad_pmem))
- rc = BLK_STS_IOERR;
- else {
- rc = read_pmem(page, off, pmem_addr, len);
- flush_dcache_page(page);
- }
- } else {
- /*
- * Note that we write the data both before and after
- * clearing poison. The write before clear poison
- * handles situations where the latest written data is
- * preserved and the clear poison operation simply marks
- * the address range as valid without changing the data.
- * In this case application software can assume that an
- * interrupted write will either return the new good
- * data or an error.
- *
- * However, if pmem_clear_poison() leaves the data in an
- * indeterminate state we need to perform the write
- * after clear poison.
- */
- flush_dcache_page(page);
- write_pmem(pmem_addr, page, off, len);
- if (unlikely(bad_pmem)) {
- rc = pmem_clear_poison(pmem, pmem_off, len);
- write_pmem(pmem_addr, page, off, len);
- }
+ /*
+ * Note that we write the data both before and after
+ * clearing poison. The write before clear poison
+ * handles situations where the latest written data is
+ * preserved and the clear poison operation simply marks
+ * the address range as valid without changing the data.
+ * In this case application software can assume that an
+ * interrupted write will either return the new good
+ * data or an error.
+ *
+ * However, if pmem_clear_poison() leaves the data in an
+ * indeterminate state we need to perform the write
+ * after clear poison.
+ */
+ flush_dcache_page(page);
+ write_pmem(pmem_addr, page, page_off, len);
+ if (unlikely(bad_pmem)) {
+ rc = pmem_clear_poison(pmem, pmem_off, len);
+ write_pmem(pmem_addr, page, page_off, len);
}
return rc;
}
-static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
+static blk_qc_t pmem_submit_bio(struct bio *bio)
{
int ret = 0;
blk_status_t rc = 0;
@@ -198,23 +197,29 @@
unsigned long start;
struct bio_vec bvec;
struct bvec_iter iter;
- struct pmem_device *pmem = q->queuedata;
+ struct pmem_device *pmem = bio->bi_disk->private_data;
struct nd_region *nd_region = to_region(pmem);
if (bio->bi_opf & REQ_PREFLUSH)
ret = nvdimm_flush(nd_region, bio);
- do_acct = nd_iostat_start(bio, &start);
+ do_acct = blk_queue_io_stat(bio->bi_disk->queue);
+ if (do_acct)
+ start = bio_start_io_acct(bio);
bio_for_each_segment(bvec, bio, iter) {
- rc = pmem_do_bvec(pmem, bvec.bv_page, bvec.bv_len,
- bvec.bv_offset, bio_op(bio), iter.bi_sector);
+ if (op_is_write(bio_op(bio)))
+ rc = pmem_do_write(pmem, bvec.bv_page, bvec.bv_offset,
+ iter.bi_sector, bvec.bv_len);
+ else
+ rc = pmem_do_read(pmem, bvec.bv_page, bvec.bv_offset,
+ iter.bi_sector, bvec.bv_len);
if (rc) {
bio->bi_status = rc;
break;
}
}
if (do_acct)
- nd_iostat_end(bio, start);
+ bio_end_io_acct(bio, start);
if (bio->bi_opf & REQ_FUA)
ret = nvdimm_flush(nd_region, bio);
@@ -229,12 +234,13 @@
static int pmem_rw_page(struct block_device *bdev, sector_t sector,
struct page *page, unsigned int op)
{
- struct pmem_device *pmem = bdev->bd_queue->queuedata;
+ struct pmem_device *pmem = bdev->bd_disk->private_data;
blk_status_t rc;
- rc = pmem_do_bvec(pmem, page, hpage_nr_pages(page) * PAGE_SIZE,
- 0, op, sector);
-
+ if (op_is_write(op))
+ rc = pmem_do_write(pmem, page, 0, sector, thp_size(page));
+ else
+ rc = pmem_do_read(pmem, page, 0, sector, thp_size(page));
/*
* The ->rw_page interface is subtle and tricky. The core
* retries on any error, so we can only invoke page_endio() in
@@ -273,9 +279,19 @@
static const struct block_device_operations pmem_fops = {
.owner = THIS_MODULE,
+ .submit_bio = pmem_submit_bio,
.rw_page = pmem_rw_page,
- .revalidate_disk = nvdimm_revalidate_disk,
};
+
+static int pmem_dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
+ size_t nr_pages)
+{
+ struct pmem_device *pmem = dax_get_private(dax_dev);
+
+ return blk_status_to_errno(pmem_do_write(pmem, ZERO_PAGE(0), 0,
+ PFN_PHYS(pgoff) >> SECTOR_SHIFT,
+ PAGE_SIZE));
+}
static long pmem_dax_direct_access(struct dax_device *dax_dev,
pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn)
@@ -287,7 +303,7 @@
/*
* Use the 'no check' versions of copy_from_iter_flushcache() and
- * copy_to_iter_mcsafe() to bypass HARDENED_USERCOPY overhead. Bounds
+ * copy_mc_to_iter() to bypass HARDENED_USERCOPY overhead. Bounds
* checking, both file offset and device offset, is handled by
* dax_iomap_actor()
*/
@@ -300,13 +316,15 @@
static size_t pmem_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff,
void *addr, size_t bytes, struct iov_iter *i)
{
- return _copy_to_iter_mcsafe(addr, bytes, i);
+ return _copy_mc_to_iter(addr, bytes, i);
}
static const struct dax_operations pmem_dax_ops = {
.direct_access = pmem_dax_direct_access,
+ .dax_supported = generic_fsdax_supported,
.copy_from_iter = pmem_copy_from_iter,
.copy_to_iter = pmem_copy_to_iter,
+ .zero_page_range = pmem_dax_zero_page_range,
};
static const struct attribute_group *pmem_attribute_groups[] = {
@@ -314,16 +332,24 @@
NULL,
};
-static void pmem_release_queue(void *q)
+static void pmem_pagemap_cleanup(struct dev_pagemap *pgmap)
{
+ struct request_queue *q =
+ container_of(pgmap->ref, struct request_queue, q_usage_counter);
+
blk_cleanup_queue(q);
}
-static void pmem_freeze_queue(struct percpu_ref *ref)
+static void pmem_release_queue(void *pgmap)
{
- struct request_queue *q;
+ pmem_pagemap_cleanup(pgmap);
+}
- q = container_of(ref, typeof(*q), q_usage_counter);
+static void pmem_pagemap_kill(struct dev_pagemap *pgmap)
+{
+ struct request_queue *q =
+ container_of(pgmap->ref, struct request_queue, q_usage_counter);
+
blk_freeze_queue_start(q);
}
@@ -337,26 +363,10 @@
put_disk(pmem->disk);
}
-static void pmem_release_pgmap_ops(void *__pgmap)
-{
- dev_pagemap_put_ops();
-}
-
-static void fsdax_pagefree(struct page *page, void *data)
-{
- wake_up_var(&page->_refcount);
-}
-
-static int setup_pagemap_fsdax(struct device *dev, struct dev_pagemap *pgmap)
-{
- dev_pagemap_get_ops();
- if (devm_add_action_or_reset(dev, pmem_release_pgmap_ops, pgmap))
- return -ENOMEM;
- pgmap->type = MEMORY_DEVICE_FS_DAX;
- pgmap->page_free = fsdax_pagefree;
-
- return 0;
-}
+static const struct dev_pagemap_ops fsdax_pagemap_ops = {
+ .kill = pmem_pagemap_kill,
+ .cleanup = pmem_pagemap_cleanup,
+};
static int pmem_attach_disk(struct device *dev,
struct nd_namespace_common *ndns)
@@ -365,7 +375,7 @@
struct nd_region *nd_region = to_nd_region(dev->parent);
int nid = dev_to_node(dev), fua;
struct resource *res = &nsio->res;
- struct resource bb_res;
+ struct range bb_range;
struct nd_pfn *nd_pfn = NULL;
struct dax_device *dax_dev;
struct nd_pfn_sb *pfn_sb;
@@ -375,10 +385,15 @@
struct gendisk *disk;
void *addr;
int rc;
+ unsigned long flags = 0UL;
pmem = devm_kzalloc(dev, sizeof(*pmem), GFP_KERNEL);
if (!pmem)
return -ENOMEM;
+
+ rc = devm_namespace_enable(dev, ndns, nd_info_block_reserve());
+ if (rc)
+ return rc;
/* while nsio_rw_bytes is active, parse a pfn info block if present */
if (is_nd_pfn(dev)) {
@@ -389,7 +404,7 @@
}
/* we're attaching a block device, disable raw namespace access */
- devm_nsio_disable(dev, nsio);
+ devm_namespace_disable(dev, ndns);
dev_set_drvdata(dev, pmem);
pmem->phys_addr = res->start;
@@ -406,39 +421,40 @@
return -EBUSY;
}
- q = blk_alloc_queue_node(GFP_KERNEL, dev_to_node(dev), NULL);
+ q = blk_alloc_queue(dev_to_node(dev));
if (!q)
- return -ENOMEM;
-
- if (devm_add_action_or_reset(dev, pmem_release_queue, q))
return -ENOMEM;
pmem->pfn_flags = PFN_DEV;
pmem->pgmap.ref = &q->q_usage_counter;
- pmem->pgmap.kill = pmem_freeze_queue;
if (is_nd_pfn(dev)) {
- if (setup_pagemap_fsdax(dev, &pmem->pgmap))
- return -ENOMEM;
+ pmem->pgmap.type = MEMORY_DEVICE_FS_DAX;
+ pmem->pgmap.ops = &fsdax_pagemap_ops;
addr = devm_memremap_pages(dev, &pmem->pgmap);
pfn_sb = nd_pfn->pfn_sb;
pmem->data_offset = le64_to_cpu(pfn_sb->dataoff);
pmem->pfn_pad = resource_size(res) -
- resource_size(&pmem->pgmap.res);
+ range_len(&pmem->pgmap.range);
pmem->pfn_flags |= PFN_MAP;
- memcpy(&bb_res, &pmem->pgmap.res, sizeof(bb_res));
- bb_res.start += pmem->data_offset;
+ bb_range = pmem->pgmap.range;
+ bb_range.start += pmem->data_offset;
} else if (pmem_should_map_pages(dev)) {
- memcpy(&pmem->pgmap.res, &nsio->res, sizeof(pmem->pgmap.res));
- pmem->pgmap.altmap_valid = false;
- if (setup_pagemap_fsdax(dev, &pmem->pgmap))
- return -ENOMEM;
+ pmem->pgmap.range.start = res->start;
+ pmem->pgmap.range.end = res->end;
+ pmem->pgmap.nr_range = 1;
+ pmem->pgmap.type = MEMORY_DEVICE_FS_DAX;
+ pmem->pgmap.ops = &fsdax_pagemap_ops;
addr = devm_memremap_pages(dev, &pmem->pgmap);
pmem->pfn_flags |= PFN_MAP;
- memcpy(&bb_res, &pmem->pgmap.res, sizeof(bb_res));
+ bb_range = pmem->pgmap.range;
} else {
addr = devm_memremap(dev, pmem->phys_addr,
pmem->size, ARCH_MEMREMAP_PMEM);
- memcpy(&bb_res, &nsio->res, sizeof(bb_res));
+ if (devm_add_action_or_reset(dev, pmem_release_queue,
+ &pmem->pgmap))
+ return -ENOMEM;
+ bb_range.start = res->start;
+ bb_range.end = res->end;
}
if (IS_ERR(addr))
@@ -446,14 +462,12 @@
pmem->virt_addr = addr;
blk_queue_write_cache(q, true, fua);
- blk_queue_make_request(q, pmem_make_request);
blk_queue_physical_block_size(q, PAGE_SIZE);
blk_queue_logical_block_size(q, pmem_sector_size(ndns));
blk_queue_max_hw_sectors(q, UINT_MAX);
blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
if (pmem->pfn_flags & PFN_MAP)
blk_queue_flag_set(QUEUE_FLAG_DAX, q);
- q->queuedata = pmem;
disk = alloc_disk_node(0, nid);
if (!disk)
@@ -463,30 +477,32 @@
disk->fops = &pmem_fops;
disk->queue = q;
disk->flags = GENHD_FL_EXT_DEVT;
- disk->queue->backing_dev_info->capabilities |= BDI_CAP_SYNCHRONOUS_IO;
+ disk->private_data = pmem;
nvdimm_namespace_disk_name(ndns, disk->disk_name);
set_capacity(disk, (pmem->size - pmem->pfn_pad - pmem->data_offset)
/ 512);
if (devm_init_badblocks(dev, &pmem->bb))
return -ENOMEM;
- nvdimm_badblocks_populate(nd_region, &pmem->bb, &bb_res);
+ nvdimm_badblocks_populate(nd_region, &pmem->bb, &bb_range);
disk->bb = &pmem->bb;
- dax_dev = alloc_dax(pmem, disk->disk_name, &pmem_dax_ops);
- if (!dax_dev) {
+ if (is_nvdimm_sync(nd_region))
+ flags = DAXDEV_F_SYNC;
+ dax_dev = alloc_dax(pmem, disk->disk_name, &pmem_dax_ops, flags);
+ if (IS_ERR(dax_dev)) {
put_disk(disk);
- return -ENOMEM;
+ return PTR_ERR(dax_dev);
}
dax_write_cache(dax_dev, nvdimm_has_cache(nd_region));
pmem->dax_dev = dax_dev;
gendev = disk_to_dev(disk);
gendev->groups = pmem_attribute_groups;
- device_add_disk(dev, disk);
+ device_add_disk(dev, disk, NULL);
if (devm_add_action_or_reset(dev, pmem_release_disk, pmem))
return -ENOMEM;
- revalidate_disk(disk);
+ nvdimm_check_and_set_ro(disk);
pmem->bb_state = sysfs_get_dirent(disk_to_dev(disk)->kobj.sd,
"badblocks");
@@ -498,14 +514,12 @@
static int nd_pmem_probe(struct device *dev)
{
+ int ret;
struct nd_namespace_common *ndns;
ndns = nvdimm_namespace_common_probe(dev);
if (IS_ERR(ndns))
return PTR_ERR(ndns);
-
- if (devm_nsio_enable(dev, to_nd_namespace_io(&ndns->dev)))
- return -ENXIO;
if (is_nd_btt(dev))
return nvdimm_namespace_attach_btt(ndns);
@@ -513,12 +527,40 @@
if (is_nd_pfn(dev))
return pmem_attach_disk(dev, ndns);
- /* if we find a valid info-block we'll come back as that personality */
- if (nd_btt_probe(dev, ndns) == 0 || nd_pfn_probe(dev, ndns) == 0
- || nd_dax_probe(dev, ndns) == 0)
+ ret = devm_namespace_enable(dev, ndns, nd_info_block_reserve());
+ if (ret)
+ return ret;
+
+ ret = nd_btt_probe(dev, ndns);
+ if (ret == 0)
return -ENXIO;
- /* ...otherwise we're just a raw pmem device */
+ /*
+ * We have two failure conditions here, there is no
+ * info reserver block or we found a valid info reserve block
+ * but failed to initialize the pfn superblock.
+ *
+ * For the first case consider namespace as a raw pmem namespace
+ * and attach a disk.
+ *
+ * For the latter, consider this a success and advance the namespace
+ * seed.
+ */
+ ret = nd_pfn_probe(dev, ndns);
+ if (ret == 0)
+ return -ENXIO;
+ else if (ret == -EOPNOTSUPP)
+ return ret;
+
+ ret = nd_dax_probe(dev, ndns);
+ if (ret == 0)
+ return -ENXIO;
+ else if (ret == -EOPNOTSUPP)
+ return ret;
+
+ /* probe complete, attach handles namespace enabling */
+ devm_namespace_disable(dev, ndns);
+
return pmem_attach_disk(dev, ndns);
}
@@ -530,8 +572,8 @@
nvdimm_namespace_detach_btt(to_nd_btt(dev));
else {
/*
- * Note, this assumes device_lock() context to not race
- * nd_pmem_notify()
+ * Note, this assumes nd_device_lock() context to not
+ * race nd_pmem_notify()
*/
sysfs_put(pmem->bb_state);
pmem->bb_state = NULL;
@@ -552,8 +594,8 @@
resource_size_t offset = 0, end_trunc = 0;
struct nd_namespace_common *ndns;
struct nd_namespace_io *nsio;
- struct resource res;
struct badblocks *bb;
+ struct range range;
struct kernfs_node *bb_state;
if (event != NVDIMM_REVALIDATE_POISON)
@@ -589,9 +631,9 @@
nsio = to_nd_namespace_io(&ndns->dev);
}
- res.start = nsio->res.start + offset;
- res.end = nsio->res.end - end_trunc;
- nvdimm_badblocks_populate(nd_region, bb, &res);
+ range.start = nsio->res.start + offset;
+ range.end = nsio->res.end - end_trunc;
+ nvdimm_badblocks_populate(nd_region, bb, &range);
if (bb_state)
sysfs_notify_dirent(bb_state);
}
--
Gitblit v1.6.2