From 034dd340b08be1f2f0477ad16131d609f9dbd53c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 30 Aug 2026 09:22:00 -0700 Subject: Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace Pull tracing fixes from Steven Rostedt: - Fix error output of boot instance creation failure Currently if a boot instance creation fails, instead of printing out the name of the instance that failed, it prints "(null)". That is because it prints "cur_str" that had already been processed by strsep(). Print the saved name instead. While at it, print the error code of the failure. - Fix use-after-free for same named historgrams Histograms can be named so that they can be used in multiple events. But if the named histogram has a variable attached, the second event that uses the named histogram which duplicates it and needs to free the original after duplication leaves the old variable in place and still visible. If another histogram uses than variable, it will use the stale one which will try to reference the freed duplicate histogram and crash the kernel. Free the duplicate variables along with the duplicated histogram data. - Check return value of kthread_run() in event self test The events self tests uses a kthread for testing but does not check if it succeeded in creating a kthread. If the kthread creation were to fail, the code will still try to call kthread_stop() on the error returned. - Fix race between reading trace_pipe and updating subbuffer size If a user is reading the trace_pipe file at the same time they update the ring buffer sub-buffer size, can cause the trace_pipe read to read stale data. Add trace_access_lock() around updating the ring buffer sub-buffer size. - Fix eventfs_inode on failure path in creation of the events directory In the creation of the "events" directory, if after allocating the eventfs_inode a failure is detected, it calls cleanup_ei() which calls free_ei(). The free_ei() will test if eventfs_inode being freed has no children. It is a bug if it does. But on the failure case of the creation of the "events" directory, the children lists have not yet been initialized and the free will trigger a warning because list_empty() on an uninitialized list returns false. Move the initialization into init_ei() where it makes more sense and makes sure that a created eventfs_inode has its lists initialized upon creation. - Check return value of kthread_run() in ftrace direct sample code The sample code that shows how to use the ftrace direct calls does not test the return of kthread_run() to see if it succeeds. Return a failure if the kthread_run() doesn't succeed. - Clear user events state on fork in case of alloc failure On fork, the child gets a pointer to the parent's user events state. It makes a copy of it then updates the child's pointer to it. But if the allocation fails, the duplication function leaves the child with a pointer to its parent's descriptor. When the child cleans up its data, it will free the parent's descriptor while the parent is still using it. In the duplication function, set the child's user_event_mm to NULL before testing if the allocation succeeded, and when it exits it will not free the parent's descriptor. - Fix retry exhaustion in simple ring buffer reader swap simple_ring_buffer_swap_reader_page() starts with retry set to 8 and post-decrements it only after a failed link replacement. On the final attempt, a successful replacement leaves retry at zero, while a failed replacement leaves it at -1. But the check for success expects the retry value to be non-zero and exits with an error on zero. This is the opposite result. Fix it. - Fail nicely when the remote swap_reader_page() returns an error Currently, if the swap_reader_page() of a remote buffer fails, it triggers a WARN_ON_ONCE() and continues normally. Instead, have it exit with an error and a pr_warn() print instead of a full WARNING. * tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: ring-buffer: Stop remote reader update when page swap fails tracing: Fix retry exhaustion in simple ring buffer reader swap tracing/user_events: Clear copied tracing state before fork duplication samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify eventfs: Initialize ei->children and ei->list in init_ei() tracing: Fix use-after-free in trace_pipe read on sub-buffer order change tracing: Fix crash passing ERR_PTR to kthread_stop() tracing: Fix use-after-free with same-name named triggers tracing: Fix logged instance name on creation failure --- drivers/mtd/mtdblock.c | 361 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 361 insertions(+) create mode 100644 drivers/mtd/mtdblock.c (limited to 'drivers/mtd/mtdblock.c') diff --git a/drivers/mtd/mtdblock.c b/drivers/mtd/mtdblock.c new file mode 100644 index 000000000..c9143711f --- /dev/null +++ b/drivers/mtd/mtdblock.c @@ -0,0 +1,361 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Direct MTD block device access + * + * Copyright © 1999-2010 David Woodhouse + * Copyright © 2000-2003 Nicolas Pitre + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include + + +struct mtdblk_dev { + struct mtd_blktrans_dev mbd; + int count; + struct mutex cache_mutex; + unsigned char *cache_data; + unsigned long cache_offset; + unsigned int cache_size; + enum { STATE_EMPTY, STATE_CLEAN, STATE_DIRTY } cache_state; +}; + +/* + * Cache stuff... + * + * Since typical flash erasable sectors are much larger than what Linux's + * buffer cache can handle, we must implement read-modify-write on flash + * sectors for each block write requests. To avoid over-erasing flash sectors + * and to speed things up, we locally cache a whole flash sector while it is + * being written to until a different sector is required. + */ + +static int erase_write (struct mtd_info *mtd, unsigned long pos, + unsigned int len, const char *buf) +{ + struct erase_info erase; + size_t retlen; + int ret; + + /* + * First, let's erase the flash block. + */ + erase.addr = pos; + erase.len = len; + + ret = mtd_erase(mtd, &erase); + if (ret) { + printk (KERN_WARNING "mtdblock: erase of region [0x%lx, 0x%x] " + "on \"%s\" failed\n", + pos, len, mtd->name); + return ret; + } + + /* + * Next, write the data to flash. + */ + + ret = mtd_write(mtd, pos, len, &retlen, buf); + if (ret) + return ret; + if (retlen != len) + return -EIO; + return 0; +} + + +static int write_cached_data (struct mtdblk_dev *mtdblk) +{ + struct mtd_info *mtd = mtdblk->mbd.mtd; + int ret; + + if (mtdblk->cache_state != STATE_DIRTY) + return 0; + + pr_debug("mtdblock: writing cached data for \"%s\" " + "at 0x%lx, size 0x%x\n", mtd->name, + mtdblk->cache_offset, mtdblk->cache_size); + + ret = erase_write (mtd, mtdblk->cache_offset, + mtdblk->cache_size, mtdblk->cache_data); + + /* + * Here we could arguably set the cache state to STATE_CLEAN. + * However this could lead to inconsistency since we will not + * be notified if this content is altered on the flash by other + * means. Let's declare it empty and leave buffering tasks to + * the buffer cache instead. + * + * If this cache_offset points to a bad block, data cannot be + * written to the device. Clear cache_state to avoid writing to + * bad blocks repeatedly. + */ + if (ret == 0 || ret == -EIO) + mtdblk->cache_state = STATE_EMPTY; + return ret; +} + + +static int do_cached_write (struct mtdblk_dev *mtdblk, unsigned long pos, + int len, const char *buf) +{ + struct mtd_info *mtd = mtdblk->mbd.mtd; + unsigned int sect_size = mtdblk->cache_size; + size_t retlen; + int ret; + + pr_debug("mtdblock: write on \"%s\" at 0x%lx, size 0x%x\n", + mtd->name, pos, len); + + if (!sect_size) + return mtd_write(mtd, pos, len, &retlen, buf); + + while (len > 0) { + unsigned long sect_start = (pos/sect_size)*sect_size; + unsigned int offset = pos - sect_start; + unsigned int size = sect_size - offset; + if( size > len ) + size = len; + + if (size == sect_size) { + /* + * We are covering a whole sector. Thus there is no + * need to bother with the cache while it may still be + * useful for other partial writes. + */ + ret = erase_write (mtd, pos, size, buf); + if (ret) + return ret; + } else { + /* Partial sector: need to use the cache */ + + if (mtdblk->cache_state == STATE_DIRTY && + mtdblk->cache_offset != sect_start) { + ret = write_cached_data(mtdblk); + if (ret) + return ret; + } + + if (mtdblk->cache_state == STATE_EMPTY || + mtdblk->cache_offset != sect_start) { + /* fill the cache with the current sector */ + mtdblk->cache_state = STATE_EMPTY; + ret = mtd_read(mtd, sect_start, sect_size, + &retlen, mtdblk->cache_data); + if (ret && !mtd_is_bitflip(ret)) + return ret; + if (retlen != sect_size) + return -EIO; + + mtdblk->cache_offset = sect_start; + mtdblk->cache_size = sect_size; + mtdblk->cache_state = STATE_CLEAN; + } + + /* write data to our local cache */ + memcpy (mtdblk->cache_data + offset, buf, size); + mtdblk->cache_state = STATE_DIRTY; + } + + buf += size; + pos += size; + len -= size; + } + + return 0; +} + + +static int do_cached_read (struct mtdblk_dev *mtdblk, unsigned long pos, + int len, char *buf) +{ + struct mtd_info *mtd = mtdblk->mbd.mtd; + unsigned int sect_size = mtdblk->cache_size; + size_t retlen; + int ret; + + pr_debug("mtdblock: read on \"%s\" at 0x%lx, size 0x%x\n", + mtd->name, pos, len); + + if (!sect_size) { + ret = mtd_read(mtd, pos, len, &retlen, buf); + if (ret && !mtd_is_bitflip(ret)) + return ret; + return 0; + } + + while (len > 0) { + unsigned long sect_start = (pos/sect_size)*sect_size; + unsigned int offset = pos - sect_start; + unsigned int size = sect_size - offset; + if (size > len) + size = len; + + /* + * Check if the requested data is already cached + * Read the requested amount of data from our internal cache if it + * contains what we want, otherwise we read the data directly + * from flash. + */ + if (mtdblk->cache_state != STATE_EMPTY && + mtdblk->cache_offset == sect_start) { + memcpy (buf, mtdblk->cache_data + offset, size); + } else { + ret = mtd_read(mtd, pos, size, &retlen, buf); + if (ret && !mtd_is_bitflip(ret)) + return ret; + if (retlen != size) + return -EIO; + } + + buf += size; + pos += size; + len -= size; + } + + return 0; +} + +static int mtdblock_readsect(struct mtd_blktrans_dev *dev, + unsigned long block, char *buf) +{ + struct mtdblk_dev *mtdblk = container_of(dev, struct mtdblk_dev, mbd); + return do_cached_read(mtdblk, block<<9, 512, buf); +} + +static int mtdblock_writesect(struct mtd_blktrans_dev *dev, + unsigned long block, char *buf) +{ + struct mtdblk_dev *mtdblk = container_of(dev, struct mtdblk_dev, mbd); + if (unlikely(!mtdblk->cache_data && mtdblk->cache_size)) { + mtdblk->cache_data = vmalloc(mtdblk->mbd.mtd->erasesize); + if (!mtdblk->cache_data) + return -EINTR; + /* -EINTR is not really correct, but it is the best match + * documented in man 2 write for all cases. We could also + * return -EAGAIN sometimes, but why bother? + */ + } + return do_cached_write(mtdblk, block<<9, 512, buf); +} + +static int mtdblock_open(struct mtd_blktrans_dev *mbd) +{ + struct mtdblk_dev *mtdblk = container_of(mbd, struct mtdblk_dev, mbd); + + pr_debug("mtdblock_open\n"); + + if (mtdblk->count) { + mtdblk->count++; + return 0; + } + + if (mtd_type_is_nand(mbd->mtd)) + pr_warn_ratelimited("%s: MTD device '%s' is NAND, please consider using UBI block devices instead.\n", + mbd->tr->name, mbd->mtd->name); + + /* OK, it's not open. Create cache info for it */ + mtdblk->count = 1; + mutex_init(&mtdblk->cache_mutex); + mtdblk->cache_state = STATE_EMPTY; + if (!(mbd->mtd->flags & MTD_NO_ERASE) && mbd->mtd->erasesize) { + mtdblk->cache_size = mbd->mtd->erasesize; + mtdblk->cache_data = NULL; + } + + pr_debug("ok\n"); + + return 0; +} + +static void mtdblock_release(struct mtd_blktrans_dev *mbd) +{ + struct mtdblk_dev *mtdblk = container_of(mbd, struct mtdblk_dev, mbd); + + pr_debug("mtdblock_release\n"); + + mutex_lock(&mtdblk->cache_mutex); + write_cached_data(mtdblk); + mutex_unlock(&mtdblk->cache_mutex); + + if (!--mtdblk->count) { + /* + * It was the last usage. Free the cache, but only sync if + * opened for writing. + */ + if (mbd->writable) + mtd_sync(mbd->mtd); + vfree(mtdblk->cache_data); + } + + pr_debug("ok\n"); +} + +static int mtdblock_flush(struct mtd_blktrans_dev *dev) +{ + struct mtdblk_dev *mtdblk = container_of(dev, struct mtdblk_dev, mbd); + int ret; + + mutex_lock(&mtdblk->cache_mutex); + ret = write_cached_data(mtdblk); + mutex_unlock(&mtdblk->cache_mutex); + mtd_sync(dev->mtd); + return ret; +} + +static void mtdblock_add_mtd(struct mtd_blktrans_ops *tr, struct mtd_info *mtd) +{ + struct mtdblk_dev *dev = kzalloc_obj(*dev); + + if (!dev) + return; + + dev->mbd.mtd = mtd; + dev->mbd.devnum = mtd->index; + + dev->mbd.size = mtd->size >> 9; + dev->mbd.tr = tr; + + if (!(mtd->flags & MTD_WRITEABLE)) + dev->mbd.readonly = 1; + + if (add_mtd_blktrans_dev(&dev->mbd)) + kfree(dev); +} + +static void mtdblock_remove_dev(struct mtd_blktrans_dev *dev) +{ + del_mtd_blktrans_dev(dev); +} + +static struct mtd_blktrans_ops mtdblock_tr = { + .name = "mtdblock", + .major = MTD_BLOCK_MAJOR, + .part_bits = 0, + .blksize = 512, + .open = mtdblock_open, + .flush = mtdblock_flush, + .release = mtdblock_release, + .readsect = mtdblock_readsect, + .writesect = mtdblock_writesect, + .add_mtd = mtdblock_add_mtd, + .remove_dev = mtdblock_remove_dev, + .owner = THIS_MODULE, +}; + +module_mtd_blktrans(mtdblock_tr); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Nicolas Pitre et al."); +MODULE_DESCRIPTION("Caching read/erase/writeback block device emulation access to MTD devices"); -- cgit v1.3.1