--- /dev/null
+From 03f25d53b145bc2f7ccc82fc04e4482ed734f524 Mon Sep 17 00:00:00 2001
+From: Alain Volmat <alain.volmat@foss.st.com>
+Date: Mon, 9 Oct 2023 10:24:50 +0200
+Subject: dmaengine: stm32-mdma: correct desc prep when channel running
+
+From: Alain Volmat <alain.volmat@foss.st.com>
+
+commit 03f25d53b145bc2f7ccc82fc04e4482ed734f524 upstream.
+
+In case of the prep descriptor while the channel is already running, the
+CCR register value stored into the channel could already have its EN bit
+set. This would lead to a bad transfer since, at start transfer time,
+enabling the channel while other registers aren't yet properly set.
+To avoid this, ensure to mask the CCR_EN bit when storing the ccr value
+into the mdma channel structure.
+
+Fixes: a4ffb13c8946 ("dmaengine: Add STM32 MDMA driver")
+Signed-off-by: Alain Volmat <alain.volmat@foss.st.com>
+Signed-off-by: Amelie Delaunay <amelie.delaunay@foss.st.com>
+Cc: stable@vger.kernel.org
+Tested-by: Alain Volmat <alain.volmat@foss.st.com>
+Link: https://lore.kernel.org/r/20231009082450.452877-1-amelie.delaunay@foss.st.com
+Signed-off-by: Vinod Koul <vkoul@kernel.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ drivers/dma/stm32-mdma.c | 4 ++--
+ 1 file changed, 2 insertions(+), 2 deletions(-)
+
+--- a/drivers/dma/stm32-mdma.c
++++ b/drivers/dma/stm32-mdma.c
+@@ -510,7 +510,7 @@ static int stm32_mdma_set_xfer_param(str
+ src_maxburst = chan->dma_config.src_maxburst;
+ dst_maxburst = chan->dma_config.dst_maxburst;
+
+- ccr = stm32_mdma_read(dmadev, STM32_MDMA_CCR(chan->id));
++ ccr = stm32_mdma_read(dmadev, STM32_MDMA_CCR(chan->id)) & ~STM32_MDMA_CCR_EN;
+ ctcr = stm32_mdma_read(dmadev, STM32_MDMA_CTCR(chan->id));
+ ctbr = stm32_mdma_read(dmadev, STM32_MDMA_CTBR(chan->id));
+
+@@ -938,7 +938,7 @@ stm32_mdma_prep_dma_memcpy(struct dma_ch
+ if (!desc)
+ return NULL;
+
+- ccr = stm32_mdma_read(dmadev, STM32_MDMA_CCR(chan->id));
++ ccr = stm32_mdma_read(dmadev, STM32_MDMA_CCR(chan->id)) & ~STM32_MDMA_CCR_EN;
+ ctcr = stm32_mdma_read(dmadev, STM32_MDMA_CTCR(chan->id));
+ ctbr = stm32_mdma_read(dmadev, STM32_MDMA_CTBR(chan->id));
+ cbndtr = stm32_mdma_read(dmadev, STM32_MDMA_CBNDTR(chan->id));
--- /dev/null
+From aa49c90894d06e18a1ee7c095edbd2f37c232d02 Mon Sep 17 00:00:00 2001
+From: Benjamin Bara <benjamin.bara@skidata.com>
+Date: Sat, 15 Jul 2023 09:53:24 +0200
+Subject: i2c: core: Run atomic i2c xfer when !preemptible
+
+From: Benjamin Bara <benjamin.bara@skidata.com>
+
+commit aa49c90894d06e18a1ee7c095edbd2f37c232d02 upstream.
+
+Since bae1d3a05a8b, i2c transfers are non-atomic if preemption is
+disabled. However, non-atomic i2c transfers require preemption (e.g. in
+wait_for_completion() while waiting for the DMA).
+
+panic() calls preempt_disable_notrace() before calling
+emergency_restart(). Therefore, if an i2c device is used for the
+restart, the xfer should be atomic. This avoids warnings like:
+
+[ 12.667612] WARNING: CPU: 1 PID: 1 at kernel/rcu/tree_plugin.h:318 rcu_note_context_switch+0x33c/0x6b0
+[ 12.676926] Voluntary context switch within RCU read-side critical section!
+...
+[ 12.742376] schedule_timeout from wait_for_completion_timeout+0x90/0x114
+[ 12.749179] wait_for_completion_timeout from tegra_i2c_wait_completion+0x40/0x70
+...
+[ 12.994527] atomic_notifier_call_chain from machine_restart+0x34/0x58
+[ 13.001050] machine_restart from panic+0x2a8/0x32c
+
+Use !preemptible() instead, which is basically the same check as
+pre-v5.2.
+
+Fixes: bae1d3a05a8b ("i2c: core: remove use of in_atomic()")
+Cc: stable@vger.kernel.org # v5.2+
+Suggested-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
+Acked-by: Wolfram Sang <wsa@kernel.org>
+Reviewed-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
+Tested-by: Nishanth Menon <nm@ti.com>
+Signed-off-by: Benjamin Bara <benjamin.bara@skidata.com>
+Link: https://lore.kernel.org/r/20230327-tegra-pmic-reboot-v7-2-18699d5dcd76@skidata.com
+Signed-off-by: Lee Jones <lee@kernel.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ drivers/i2c/i2c-core.h | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+--- a/drivers/i2c/i2c-core.h
++++ b/drivers/i2c/i2c-core.h
+@@ -29,7 +29,7 @@ int i2c_dev_irq_from_resources(const str
+ */
+ static inline bool i2c_in_atomic_xfer_mode(void)
+ {
+- return system_state > SYSTEM_RUNNING && irqs_disabled();
++ return system_state > SYSTEM_RUNNING && !preemptible();
+ }
+
+ static inline int __i2c_lock_bus_helper(struct i2c_adapter *adap)
--- /dev/null
+From 4bd8405257da717cd556f99e5fb68693d12c9766 Mon Sep 17 00:00:00 2001
+From: Joshua Yeong <joshua.yeong@starfivetech.com>
+Date: Wed, 13 Sep 2023 11:17:45 +0800
+Subject: i3c: master: cdns: Fix reading status register
+
+From: Joshua Yeong <joshua.yeong@starfivetech.com>
+
+commit 4bd8405257da717cd556f99e5fb68693d12c9766 upstream.
+
+IBIR_DEPTH and CMDR_DEPTH should read from status0 instead of status1.
+
+Cc: stable@vger.kernel.org
+Fixes: 603f2bee2c54 ("i3c: master: Add driver for Cadence IP")
+Signed-off-by: Joshua Yeong <joshua.yeong@starfivetech.com>
+Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
+Link: https://lore.kernel.org/r/20230913031743.11439-2-joshua.yeong@starfivetech.com
+Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ drivers/i3c/master/i3c-master-cdns.c | 6 +++---
+ 1 file changed, 3 insertions(+), 3 deletions(-)
+
+--- a/drivers/i3c/master/i3c-master-cdns.c
++++ b/drivers/i3c/master/i3c-master-cdns.c
+@@ -189,7 +189,7 @@
+ #define SLV_STATUS1_HJ_DIS BIT(18)
+ #define SLV_STATUS1_MR_DIS BIT(17)
+ #define SLV_STATUS1_PROT_ERR BIT(16)
+-#define SLV_STATUS1_DA(x) (((s) & GENMASK(15, 9)) >> 9)
++#define SLV_STATUS1_DA(s) (((s) & GENMASK(15, 9)) >> 9)
+ #define SLV_STATUS1_HAS_DA BIT(8)
+ #define SLV_STATUS1_DDR_RX_FULL BIT(7)
+ #define SLV_STATUS1_DDR_TX_FULL BIT(6)
+@@ -1580,13 +1580,13 @@ static int cdns_i3c_master_probe(struct
+ /* Device ID0 is reserved to describe this master. */
+ master->maxdevs = CONF_STATUS0_DEVS_NUM(val);
+ master->free_rr_slots = GENMASK(master->maxdevs, 1);
++ master->caps.ibirfifodepth = CONF_STATUS0_IBIR_DEPTH(val);
++ master->caps.cmdrfifodepth = CONF_STATUS0_CMDR_DEPTH(val);
+
+ val = readl(master->regs + CONF_STATUS1);
+ master->caps.cmdfifodepth = CONF_STATUS1_CMD_DEPTH(val);
+ master->caps.rxfifodepth = CONF_STATUS1_RX_DEPTH(val);
+ master->caps.txfifodepth = CONF_STATUS1_TX_DEPTH(val);
+- master->caps.ibirfifodepth = CONF_STATUS0_IBIR_DEPTH(val);
+- master->caps.cmdrfifodepth = CONF_STATUS0_CMDR_DEPTH(val);
+
+ spin_lock_init(&master->ibi.lock);
+ master->ibi.num_slots = CONF_STATUS1_IBI_HW_RES(val);
--- /dev/null
+From 61187fce8600e8ef90e601be84f9d0f3222c1206 Mon Sep 17 00:00:00 2001
+From: Zhihao Cheng <chengzhihao1@huawei.com>
+Date: Tue, 19 Sep 2023 09:25:25 +0800
+Subject: jbd2: fix potential data lost in recovering journal raced with synchronizing fs bdev
+
+From: Zhihao Cheng <chengzhihao1@huawei.com>
+
+commit 61187fce8600e8ef90e601be84f9d0f3222c1206 upstream.
+
+JBD2 makes sure journal data is fallen on fs device by sync_blockdev(),
+however, other process could intercept the EIO information from bdev's
+mapping, which leads journal recovering successful even EIO occurs during
+data written back to fs device.
+
+We found this problem in our product, iscsi + multipath is chosen for block
+device of ext4. Unstable network may trigger kpartx to rescan partitions in
+device mapper layer. Detailed process is shown as following:
+
+ mount kpartx irq
+jbd2_journal_recover
+ do_one_pass
+ memcpy(nbh->b_data, obh->b_data) // copy data to fs dev from journal
+ mark_buffer_dirty // mark bh dirty
+ vfs_read
+ generic_file_read_iter // dio
+ filemap_write_and_wait_range
+ __filemap_fdatawrite_range
+ do_writepages
+ block_write_full_folio
+ submit_bh_wbc
+ >> EIO occurs in disk <<
+ end_buffer_async_write
+ mark_buffer_write_io_error
+ mapping_set_error
+ set_bit(AS_EIO, &mapping->flags) // set!
+ filemap_check_errors
+ test_and_clear_bit(AS_EIO, &mapping->flags) // clear!
+ err2 = sync_blockdev
+ filemap_write_and_wait
+ filemap_check_errors
+ test_and_clear_bit(AS_EIO, &mapping->flags) // false
+ err2 = 0
+
+Filesystem is mounted successfully even data from journal is failed written
+into disk, and ext4/ocfs2 could become corrupted.
+
+Fix it by comparing the wb_err state in fs block device before recovering
+and after recovering.
+
+A reproducer can be found in the kernel bugzilla referenced below.
+
+Link: https://bugzilla.kernel.org/show_bug.cgi?id=217888
+Cc: stable@vger.kernel.org
+Signed-off-by: Zhihao Cheng <chengzhihao1@huawei.com>
+Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
+Reviewed-by: Jan Kara <jack@suse.cz>
+Link: https://lore.kernel.org/r/20230919012525.1783108-1-chengzhihao1@huawei.com
+Signed-off-by: Theodore Ts'o <tytso@mit.edu>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ fs/jbd2/recovery.c | 8 ++++++++
+ 1 file changed, 8 insertions(+)
+
+--- a/fs/jbd2/recovery.c
++++ b/fs/jbd2/recovery.c
+@@ -247,6 +247,8 @@ int jbd2_journal_recover(journal_t *jour
+ journal_superblock_t * sb;
+
+ struct recovery_info info;
++ errseq_t wb_err;
++ struct address_space *mapping;
+
+ memset(&info, 0, sizeof(info));
+ sb = journal->j_superblock;
+@@ -264,6 +266,9 @@ int jbd2_journal_recover(journal_t *jour
+ return 0;
+ }
+
++ wb_err = 0;
++ mapping = journal->j_fs_dev->bd_inode->i_mapping;
++ errseq_check_and_advance(&mapping->wb_err, &wb_err);
+ err = do_one_pass(journal, &info, PASS_SCAN);
+ if (!err)
+ err = do_one_pass(journal, &info, PASS_REVOKE);
+@@ -284,6 +289,9 @@ int jbd2_journal_recover(journal_t *jour
+ err2 = sync_blockdev(journal->j_fs_dev);
+ if (!err)
+ err = err2;
++ err2 = errseq_check_and_advance(&mapping->wb_err, &wb_err);
++ if (!err)
++ err = err2;
+ /* Make sure all replayed data is on permanent storage */
+ if (journal->j_flags & JBD2_BARRIER) {
+ err2 = blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL);
--- /dev/null
+From 60466c067927abbcaff299845abd4b7069963139 Mon Sep 17 00:00:00 2001
+From: Benjamin Bara <benjamin.bara@skidata.com>
+Date: Sat, 15 Jul 2023 09:53:23 +0200
+Subject: kernel/reboot: emergency_restart: Set correct system_state
+
+From: Benjamin Bara <benjamin.bara@skidata.com>
+
+commit 60466c067927abbcaff299845abd4b7069963139 upstream.
+
+As the emergency restart does not call kernel_restart_prepare(), the
+system_state stays in SYSTEM_RUNNING.
+
+Since bae1d3a05a8b, this hinders i2c_in_atomic_xfer_mode() from becoming
+active, and therefore might lead to avoidable warnings in the restart
+handlers, e.g.:
+
+[ 12.667612] WARNING: CPU: 1 PID: 1 at kernel/rcu/tree_plugin.h:318 rcu_note_context_switch+0x33c/0x6b0
+[ 12.676926] Voluntary context switch within RCU read-side critical section!
+...
+[ 12.742376] schedule_timeout from wait_for_completion_timeout+0x90/0x114
+[ 12.749179] wait_for_completion_timeout from tegra_i2c_wait_completion+0x40/0x70
+...
+[ 12.994527] atomic_notifier_call_chain from machine_restart+0x34/0x58
+[ 13.001050] machine_restart from panic+0x2a8/0x32c
+
+Avoid these by setting the correct system_state.
+
+Fixes: bae1d3a05a8b ("i2c: core: remove use of in_atomic()")
+Cc: stable@vger.kernel.org # v5.2+
+Reviewed-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
+Tested-by: Nishanth Menon <nm@ti.com>
+Signed-off-by: Benjamin Bara <benjamin.bara@skidata.com>
+Link: https://lore.kernel.org/r/20230327-tegra-pmic-reboot-v7-1-18699d5dcd76@skidata.com
+Signed-off-by: Lee Jones <lee@kernel.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ kernel/reboot.c | 1 +
+ 1 file changed, 1 insertion(+)
+
+--- a/kernel/reboot.c
++++ b/kernel/reboot.c
+@@ -64,6 +64,7 @@ EXPORT_SYMBOL_GPL(pm_power_off_prepare);
+ void emergency_restart(void)
+ {
+ kmsg_dump(KMSG_DUMP_EMERG);
++ system_state = SYSTEM_RESTART;
+ machine_emergency_restart();
+ }
+ EXPORT_SYMBOL_GPL(emergency_restart);
--- /dev/null
+From 63ba2d07b4be72b94216d20561f43e1150b25d98 Mon Sep 17 00:00:00 2001
+From: =?UTF-8?q?Sanju=C3=A1n=20Garc=C3=ADa=2C=20Jorge?=
+ <Jorge.SanjuanGarcia@duagon.com>
+Date: Thu, 19 Oct 2023 14:15:34 +0000
+Subject: mcb: fix error handling for different scenarios when parsing
+
+From: Sanjuán García, Jorge <Jorge.SanjuanGarcia@duagon.com>
+
+commit 63ba2d07b4be72b94216d20561f43e1150b25d98 upstream.
+
+chameleon_parse_gdd() may fail for different reasons and end up
+in the err tag. Make sure we at least always free the mcb_device
+allocated with mcb_alloc_dev().
+
+If mcb_device_register() fails, make sure to give up the reference
+in the same place the device was added.
+
+Fixes: 728ac3389296 ("mcb: mcb-parse: fix error handing in chameleon_parse_gdd()")
+Cc: stable <stable@kernel.org>
+Reviewed-by: Jose Javier Rodriguez Barbarin <JoseJavier.Rodriguez@duagon.com>
+Signed-off-by: Jorge Sanjuan Garcia <jorge.sanjuangarcia@duagon.com>
+Link: https://lore.kernel.org/r/20231019141434.57971-2-jorge.sanjuangarcia@duagon.com
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ drivers/mcb/mcb-core.c | 1 +
+ drivers/mcb/mcb-parse.c | 2 +-
+ 2 files changed, 2 insertions(+), 1 deletion(-)
+
+--- a/drivers/mcb/mcb-core.c
++++ b/drivers/mcb/mcb-core.c
+@@ -248,6 +248,7 @@ int mcb_device_register(struct mcb_bus *
+ return 0;
+
+ out:
++ put_device(&dev->dev);
+
+ return ret;
+ }
+--- a/drivers/mcb/mcb-parse.c
++++ b/drivers/mcb/mcb-parse.c
+@@ -106,7 +106,7 @@ static int chameleon_parse_gdd(struct mc
+ return 0;
+
+ err:
+- put_device(&mdev->dev);
++ mcb_free_dev(mdev);
+
+ return ret;
+ }
--- /dev/null
+From 2e7cfe5cd5b6b0b98abf57a3074885979e187c1c Mon Sep 17 00:00:00 2001
+From: Zi Yan <ziy@nvidia.com>
+Date: Wed, 13 Sep 2023 16:12:44 -0400
+Subject: mm/cma: use nth_page() in place of direct struct page manipulation
+
+From: Zi Yan <ziy@nvidia.com>
+
+commit 2e7cfe5cd5b6b0b98abf57a3074885979e187c1c upstream.
+
+Patch series "Use nth_page() in place of direct struct page manipulation",
+v3.
+
+On SPARSEMEM without VMEMMAP, struct page is not guaranteed to be
+contiguous, since each memory section's memmap might be allocated
+independently. hugetlb pages can go beyond a memory section size, thus
+direct struct page manipulation on hugetlb pages/subpages might give wrong
+struct page. Kernel provides nth_page() to do the manipulation properly.
+Use that whenever code can see hugetlb pages.
+
+
+This patch (of 5):
+
+When dealing with hugetlb pages, manipulating struct page pointers
+directly can get to wrong struct page, since struct page is not guaranteed
+to be contiguous on SPARSEMEM without VMEMMAP. Use nth_page() to handle
+it properly.
+
+Without the fix, page_kasan_tag_reset() could reset wrong page tags,
+causing a wrong kasan result. No related bug is reported. The fix
+comes from code inspection.
+
+Link: https://lkml.kernel.org/r/20230913201248.452081-1-zi.yan@sent.com
+Link: https://lkml.kernel.org/r/20230913201248.452081-2-zi.yan@sent.com
+Fixes: 2813b9c02962 ("kasan, mm, arm64: tag non slab memory allocated via pagealloc")
+Signed-off-by: Zi Yan <ziy@nvidia.com>
+Reviewed-by: Muchun Song <songmuchun@bytedance.com>
+Cc: David Hildenbrand <david@redhat.com>
+Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
+Cc: Mike Kravetz <mike.kravetz@oracle.com>
+Cc: Mike Rapoport (IBM) <rppt@kernel.org>
+Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
+Cc: <stable@vger.kernel.org>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ mm/cma.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+--- a/mm/cma.c
++++ b/mm/cma.c
+@@ -481,7 +481,7 @@ struct page *cma_alloc(struct cma *cma,
+ */
+ if (page) {
+ for (i = 0; i < count; i++)
+- page_kasan_tag_reset(page + i);
++ page_kasan_tag_reset(nth_page(page, i));
+ }
+
+ if (ret && !no_warn) {
--- /dev/null
+From d3cc1b0be258191d6360c82ea158c2972f8d3991 Mon Sep 17 00:00:00 2001
+From: Eric Biggers <ebiggers@google.com>
+Date: Mon, 4 Sep 2023 17:32:27 -0700
+Subject: quota: explicitly forbid quota files from being encrypted
+
+From: Eric Biggers <ebiggers@google.com>
+
+commit d3cc1b0be258191d6360c82ea158c2972f8d3991 upstream.
+
+Since commit d7e7b9af104c ("fscrypt: stop using keyrings subsystem for
+fscrypt_master_key"), xfstest generic/270 causes a WARNING when run on
+f2fs with test_dummy_encryption in the mount options:
+
+$ kvm-xfstests -c f2fs/encrypt generic/270
+[...]
+WARNING: CPU: 1 PID: 2453 at fs/crypto/keyring.c:240 fscrypt_destroy_keyring+0x1f5/0x260
+
+The cause of the WARNING is that not all encrypted inodes have been
+evicted before fscrypt_destroy_keyring() is called, which violates an
+assumption. This happens because the test uses an external quota file,
+which gets automatically encrypted due to test_dummy_encryption.
+
+Encryption of quota files has never really been supported. On ext4,
+ext4_quota_read() does not decrypt the data, so encrypted quota files
+are always considered invalid on ext4. On f2fs, f2fs_quota_read() uses
+the pagecache, so trying to use an encrypted quota file gets farther,
+resulting in the issue described above being possible. But this was
+never intended to be possible, and there is no use case for it.
+
+Therefore, make the quota support layer explicitly reject using
+IS_ENCRYPTED inodes when quotaon is attempted.
+
+Cc: stable@vger.kernel.org
+Signed-off-by: Eric Biggers <ebiggers@google.com>
+Signed-off-by: Jan Kara <jack@suse.cz>
+Message-Id: <20230905003227.326998-1-ebiggers@kernel.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ fs/quota/dquot.c | 14 ++++++++++++++
+ 1 file changed, 14 insertions(+)
+
+--- a/fs/quota/dquot.c
++++ b/fs/quota/dquot.c
+@@ -2388,6 +2388,20 @@ static int vfs_setup_quota_inode(struct
+ if (sb_has_quota_loaded(sb, type))
+ return -EBUSY;
+
++ /*
++ * Quota files should never be encrypted. They should be thought of as
++ * filesystem metadata, not user data. New-style internal quota files
++ * cannot be encrypted by users anyway, but old-style external quota
++ * files could potentially be incorrectly created in an encrypted
++ * directory, hence this explicit check. Some reasons why encrypted
++ * quota files don't work include: (1) some filesystems that support
++ * encryption don't handle it in their quota_read and quota_write, and
++ * (2) cleaning up encrypted quota files at unmount would need special
++ * consideration, as quota files are cleaned up later than user files.
++ */
++ if (IS_ENCRYPTED(inode))
++ return -EINVAL;
++
+ dqopt->files[type] = igrab(inode);
+ if (!dqopt->files[type])
+ return -EIO;
--- /dev/null
+From 84bb41d5df48868055d159d9247b80927f1f70f9 Mon Sep 17 00:00:00 2001
+From: Heiko Carstens <hca@linux.ibm.com>
+Date: Tue, 24 Oct 2023 10:15:20 +0200
+Subject: s390/cmma: fix handling of swapper_pg_dir and invalid_pg_dir
+
+From: Heiko Carstens <hca@linux.ibm.com>
+
+commit 84bb41d5df48868055d159d9247b80927f1f70f9 upstream.
+
+If the cmma no-dat feature is available the kernel page tables are walked
+to identify and mark all pages which are used for address translation (all
+region, segment, and page tables). In a subsequent loop all other pages are
+marked as "no-dat" pages with the ESSA instruction.
+
+This information is visible to the hypervisor, so that the hypervisor can
+optimize purging of guest TLB entries. All pages used for swapper_pg_dir
+and invalid_pg_dir are incorrectly marked as no-dat, which in turn can
+result in incorrect guest TLB flushes.
+
+Fix this by marking those pages correctly as being used for DAT.
+
+Cc: <stable@vger.kernel.org>
+Reviewed-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
+Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
+Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ arch/s390/mm/page-states.c | 6 ++++++
+ 1 file changed, 6 insertions(+)
+
+--- a/arch/s390/mm/page-states.c
++++ b/arch/s390/mm/page-states.c
+@@ -198,6 +198,12 @@ void __init cmma_init_nodat(void)
+ return;
+ /* Mark pages used in kernel page tables */
+ mark_kernel_pgd();
++ page = virt_to_page(&swapper_pg_dir);
++ for (i = 0; i < 4; i++)
++ set_bit(PG_arch_1, &page[i].flags);
++ page = virt_to_page(&invalid_pg_dir);
++ for (i = 0; i < 4; i++)
++ set_bit(PG_arch_1, &page[i].flags);
+
+ /* Set all kernel pages not used for page tables to stable/no-dat */
+ for_each_memblock(memory, reg) {
--- /dev/null
+From 16ba44826a04834d3eeeda4b731c2ea3481062b7 Mon Sep 17 00:00:00 2001
+From: Heiko Carstens <hca@linux.ibm.com>
+Date: Tue, 17 Oct 2023 21:07:03 +0200
+Subject: s390/cmma: fix initial kernel address space page table walk
+
+From: Heiko Carstens <hca@linux.ibm.com>
+
+commit 16ba44826a04834d3eeeda4b731c2ea3481062b7 upstream.
+
+If the cmma no-dat feature is available the kernel page tables are walked
+to identify and mark all pages which are used for address translation (all
+region, segment, and page tables). In a subsequent loop all other pages are
+marked as "no-dat" pages with the ESSA instruction.
+
+This information is visible to the hypervisor, so that the hypervisor can
+optimize purging of guest TLB entries. The initial loop however does not
+cover the complete kernel address space. This can result in pages being
+marked as not being used for dynamic address translation, even though they
+are. In turn guest TLB entries incorrectly may not be purged.
+
+Fix this by adjusting the end address of the kernel address range being
+walked.
+
+Cc: <stable@vger.kernel.org>
+Reviewed-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
+Reviewed-by: Alexander Gordeev <agordeev@linux.ibm.com>
+Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
+Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ arch/s390/mm/page-states.c | 13 ++++++++++---
+ 1 file changed, 10 insertions(+), 3 deletions(-)
+
+--- a/arch/s390/mm/page-states.c
++++ b/arch/s390/mm/page-states.c
+@@ -161,15 +161,22 @@ static void mark_kernel_p4d(pgd_t *pgd,
+
+ static void mark_kernel_pgd(void)
+ {
+- unsigned long addr, next;
++ unsigned long addr, next, max_addr;
+ struct page *page;
+ pgd_t *pgd;
+ int i;
+
+ addr = 0;
++ /*
++ * Figure out maximum virtual address accessible with the
++ * kernel ASCE. This is required to keep the page table walker
++ * from accessing non-existent entries.
++ */
++ max_addr = (S390_lowcore.kernel_asce.val & _ASCE_TYPE_MASK) >> 2;
++ max_addr = 1UL << (max_addr * 11 + 31);
+ pgd = pgd_offset_k(addr);
+ do {
+- next = pgd_addr_end(addr, MODULES_END);
++ next = pgd_addr_end(addr, max_addr);
+ if (pgd_none(*pgd))
+ continue;
+ if (!pgd_folded(*pgd)) {
+@@ -178,7 +185,7 @@ static void mark_kernel_pgd(void)
+ set_bit(PG_arch_1, &page[i].flags);
+ }
+ mark_kernel_p4d(pgd, addr, next);
+- } while (pgd++, addr = next, addr != MODULES_END);
++ } while (pgd++, addr = next, addr != max_addr);
+ }
+
+ void __init cmma_init_nodat(void)
pm-hibernate-use-__get_safe_page-rather-than-touching-the-list.patch
pm-hibernate-clean-up-sync_read-handling-in-snapshot_write_next.patch
btrfs-don-t-arbitrarily-slow-down-delalloc-if-we-re-committing.patch
+jbd2-fix-potential-data-lost-in-recovering-journal-raced-with-synchronizing-fs-bdev.patch
+quota-explicitly-forbid-quota-files-from-being-encrypted.patch
+kernel-reboot-emergency_restart-set-correct-system_state.patch
+i2c-core-run-atomic-i2c-xfer-when-preemptible.patch
+mcb-fix-error-handling-for-different-scenarios-when-parsing.patch
+dmaengine-stm32-mdma-correct-desc-prep-when-channel-running.patch
+s390-cmma-fix-initial-kernel-address-space-page-table-walk.patch
+s390-cmma-fix-handling-of-swapper_pg_dir-and-invalid_pg_dir.patch
+mm-cma-use-nth_page-in-place-of-direct-struct-page-manipulation.patch
+i3c-master-cdns-fix-reading-status-register.patch
projects / thirdparty / kernel / stable-queue.git / commitdiff
