Syzbot reported a BUG_ON:
==================================================================
EXT4-fs (loop0): mounted filesystem without journal. Quota mode: none.
EXT4-fs error (device loop0): ext4_mb_generate_buddy:1098: group 0, block
bitmap and bg descriptor inconsistent: 25 vs 150994969 free clusters
------------[ cut here ]------------
kernel BUG at fs/ext4/ext4_jbd2.c:53!
invalid opcode: 0000 [#1] PREEMPT SMP KASAN
CPU: 1 PID: 494 Comm: syz-executor.0 6.1.0-rc7-syzkaller-ga4412fdd49dc #0
RIP: 0010:__ext4_journal_stop+0x1b3/0x1c0
[...]
Call Trace:
ext4_write_inline_data_end+0xa39/0xdf0
ext4_da_write_end+0x1e2/0x950
generic_perform_write+0x401/0x5f0
ext4_buffered_write_iter+0x35f/0x640
ext4_file_write_iter+0x198/0x1cd0
vfs_write+0x8b5/0xef0
[...]
==================================================================
The above BUG_ON is triggered by the following race:
cpu1 cpu2
________________________|________________________
ksys_write
vfs_write
new_sync_write
ext4_file_write_iter
ext4_buffered_write_iter
generic_perform_write
ext4_da_write_begin
do_fault
do_page_mkwrite
ext4_page_mkwrite
ext4_convert_inline_data
ext4_convert_inline_data_nolock
ext4_destroy_inline_data_nolock
//clear EXT4_STATE_MAY_INLINE_DATA
ext4_map_blocks --> return error
ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)
ext4_block_write_begin
ext4_restore_inline_data
// set EXT4_STATE_MAY_INLINE_DATA
ext4_da_write_end
ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)
ext4_write_inline_data_end
handle=NULL
ext4_journal_stop(handle)
__ext4_journal_stop
ext4_put_nojournal(handle)
ref_cnt = (unsigned long)handle
BUG_ON(ref_cnt == 0) ---> BUG_ON
The root cause of this problem is that the ext4_convert_inline_data() in
ext4_page_mkwrite() does not grab i_rwsem, so it may race with
ext4_buffered_write_iter() and cause the write_begin() and write_end()
functions to be inconsistent and trigger BUG_ON.
To solve the above issue, we can not add inode_lock directly to
ext4_page_mkwrite(), which would not only cause performance degradation but
also ABBA deadlock (see Link). Hence we move ext4_convert_inline_data() to
ext4_file_mmap(), and only when inline_data is enabled and mmap a writeable
file in shared mode, we hold the lock to convert, which avoids the above
problems.
Link: https://lore.kernel.org/r/20230530102804.6t7np7om6tczscuo@quack3/
Reported-by: Jun Nie <jun.nie(a)linaro.org>
Closes: https://lore.kernel.org/lkml/63903521.5040307@huawei.com/t/
Reported-by: syzbot+a158d886ca08a3fecca4(a)syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?id=899b37f20ce4072bcdfecfe1647b39602e956e…
Fixes: 7b4cc9787fe3 ("ext4: evict inline data when writing to memory map")
CC: stable(a)vger.kernel.org # 4.12+
Signed-off-by: Baokun Li <libaokun1(a)huawei.com>
---
fs/ext4/file.c | 24 +++++++++++++++++++++++-
fs/ext4/inode.c | 4 ----
2 files changed, 23 insertions(+), 5 deletions(-)
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index d101b3b0c7da..9df82d72eb90 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -795,7 +795,8 @@ static const struct vm_operations_struct ext4_file_vm_ops = {
static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
{
struct inode *inode = file->f_mapping->host;
- struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ struct super_block *sb = inode->i_sb;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
struct dax_device *dax_dev = sbi->s_daxdev;
if (unlikely(ext4_forced_shutdown(sbi)))
@@ -808,6 +809,27 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
if (!daxdev_mapping_supported(vma, dax_dev))
return -EOPNOTSUPP;
+ /*
+ * Writing via mmap has no logic to handle inline data, so we
+ * need to call ext4_convert_inline_data() to convert the inode
+ * to normal format before doing so, otherwise a BUG_ON will be
+ * triggered in ext4_writepages() due to the
+ * EXT4_STATE_MAY_INLINE_DATA flag. Moreover, we need to grab
+ * i_rwsem during conversion, since clearing and setting the
+ * inline data flag may race with ext4_buffered_write_iter()
+ * to trigger a BUG_ON.
+ */
+ if (ext4_has_feature_inline_data(sb) &&
+ vma->vm_flags & VM_SHARED && vma->vm_flags & VM_MAYWRITE) {
+ int err;
+
+ inode_lock(inode);
+ err = ext4_convert_inline_data(inode);
+ inode_unlock(inode);
+ if (err)
+ return err;
+ }
+
file_accessed(file);
if (IS_DAX(file_inode(file))) {
vma->vm_ops = &ext4_dax_vm_ops;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index ce5f21b6c2b3..31844c4ec9fe 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -6043,10 +6043,6 @@ vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf)
filemap_invalidate_lock_shared(mapping);
- err = ext4_convert_inline_data(inode);
- if (err)
- goto out_ret;
-
/*
* On data journalling we skip straight to the transaction handle:
* there's no delalloc; page truncated will be checked later; the
--
2.31.1
Touching privately mapped GPA that is not properly converted to private
with MapGPA and accepted leads to unrecoverable exit to VMM.
load_unaligned_zeropad() can touch memory that is not owned by the
caller, but just happened to next after the owned memory.
This load_unaligned_zeropad() behaviour makes it important when kernel
asks VMM to convert a GPA from shared to private or back. Kernel must
never have a page mapped into direct mapping (and aliases) as private
when the GPA is already converted to shared or when GPA is not yet
converted to private.
guest.enc_status_change_prepare() called before adjusting direct mapping
and therefore it is responsible for converting the memory to private.
guest.enc_status_change_finish() called after adjusting direct mapping
and it converts the memory to shared.
It is okay to have a shared mapping of memory that is not converted
properly. handle_mmio() knows how to deal with load_unaligned_zeropad()
stepping on it.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com>
Fixes: 7dbde7631629 ("x86/mm/cpa: Add support for TDX shared memory")
Cc: stable(a)vger.kernel.org
---
arch/x86/coco/tdx/tdx.c | 56 ++++++++++++++++++++++++++++++++++++++---
1 file changed, 53 insertions(+), 3 deletions(-)
diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
index e146b599260f..59cc13e41aa6 100644
--- a/arch/x86/coco/tdx/tdx.c
+++ b/arch/x86/coco/tdx/tdx.c
@@ -840,6 +840,30 @@ static bool tdx_enc_status_changed(unsigned long vaddr, int numpages, bool enc)
return true;
}
+static bool tdx_enc_status_change_prepare(unsigned long vaddr, int numpages,
+ bool enc)
+{
+ /*
+ * Only handle shared->private conversion here.
+ * See the comment in tdx_early_init().
+ */
+ if (enc)
+ return tdx_enc_status_changed(vaddr, numpages, enc);
+ return true;
+}
+
+static bool tdx_enc_status_change_finish(unsigned long vaddr, int numpages,
+ bool enc)
+{
+ /*
+ * Only handle private->shared conversion here.
+ * See the comment in tdx_early_init().
+ */
+ if (!enc)
+ return tdx_enc_status_changed(vaddr, numpages, enc);
+ return true;
+}
+
void __init tdx_early_init(void)
{
u64 cc_mask;
@@ -867,9 +891,35 @@ void __init tdx_early_init(void)
*/
physical_mask &= cc_mask - 1;
- x86_platform.guest.enc_cache_flush_required = tdx_cache_flush_required;
- x86_platform.guest.enc_tlb_flush_required = tdx_tlb_flush_required;
- x86_platform.guest.enc_status_change_finish = tdx_enc_status_changed;
+ /*
+ * Touching privately mapped GPA that is not properly converted to
+ * private with MapGPA and accepted leads to unrecoverable exit
+ * to VMM.
+ *
+ * load_unaligned_zeropad() can touch memory that is not owned by
+ * the caller, but just happened to next after the owned memory.
+ * This load_unaligned_zeropad() behaviour makes it important when
+ * kernel asks VMM to convert a GPA from shared to private or back.
+ * Kernel must never have a page mapped into direct mapping (and
+ * aliases) as private when the GPA is already converted to shared or
+ * when GPA is not yet converted to private.
+ *
+ * guest.enc_status_change_prepare() called before adjusting direct
+ * mapping and therefore it is responsible for converting the memory
+ * to private.
+ *
+ * guest.enc_status_change_finish() called after adjusting direct
+ * mapping and it converts the memory to shared.
+ *
+ * It is okay to have a shared mapping of memory that is not converted
+ * properly. handle_mmio() knows how to deal with load_unaligned_zeropad()
+ * stepping on it.
+ */
+ x86_platform.guest.enc_status_change_prepare = tdx_enc_status_change_prepare;
+ x86_platform.guest.enc_status_change_finish = tdx_enc_status_change_finish;
+
+ x86_platform.guest.enc_cache_flush_required = tdx_cache_flush_required;
+ x86_platform.guest.enc_tlb_flush_required = tdx_tlb_flush_required;
pr_info("Guest detected\n");
}
--
2.39.3
The patch below does not apply to the 4.14-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.14.y
git checkout FETCH_HEAD
git cherry-pick -x 7e01c7f7046efc2c7c192c3619db43292b98e997
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023052625-mutual-punch-5c0b@gregkh' --subject-prefix 'PATCH 4.14.y' HEAD^..
Possible dependencies:
7e01c7f7046e ("net: cdc_ncm: Deal with too low values of dwNtbOutMaxSize")
2be6d4d16a08 ("net: cdc_ncm: Allow for dwNtbOutMaxSize to be unset or zero")
0fa81b304a79 ("cdc_ncm: Implement the 32-bit version of NCM Transfer Block")
49c2c3f246e2 ("cdc_ncm: avoid padding beyond end of skb")
6314dab4b8fb ("net: cdc_ncm: GetNtbFormat endian fix")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 7e01c7f7046efc2c7c192c3619db43292b98e997 Mon Sep 17 00:00:00 2001
From: Tudor Ambarus <tudor.ambarus(a)linaro.org>
Date: Wed, 17 May 2023 13:38:08 +0000
Subject: [PATCH] net: cdc_ncm: Deal with too low values of dwNtbOutMaxSize
Currently in cdc_ncm_check_tx_max(), if dwNtbOutMaxSize is lower than
the calculated "min" value, but greater than zero, the logic sets
tx_max to dwNtbOutMaxSize. This is then used to allocate a new SKB in
cdc_ncm_fill_tx_frame() where all the data is handled.
For small values of dwNtbOutMaxSize the memory allocated during
alloc_skb(dwNtbOutMaxSize, GFP_ATOMIC) will have the same size, due to
how size is aligned at alloc time:
size = SKB_DATA_ALIGN(size);
size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
Thus we hit the same bug that we tried to squash with
commit 2be6d4d16a084 ("net: cdc_ncm: Allow for dwNtbOutMaxSize to be unset or zero")
Low values of dwNtbOutMaxSize do not cause an issue presently because at
alloc_skb() time more memory (512b) is allocated than required for the
SKB headers alone (320b), leaving some space (512b - 320b = 192b)
for CDC data (172b).
However, if more elements (for example 3 x u64 = [24b]) were added to
one of the SKB header structs, say 'struct skb_shared_info',
increasing its original size (320b [320b aligned]) to something larger
(344b [384b aligned]), then suddenly the CDC data (172b) no longer
fits in the spare SKB data area (512b - 384b = 128b).
Consequently the SKB bounds checking semantics fails and panics:
skbuff: skb_over_panic: text:ffffffff831f755b len:184 put:172 head:ffff88811f1c6c00 data:ffff88811f1c6c00 tail:0xb8 end:0x80 dev:<NULL>
------------[ cut here ]------------
kernel BUG at net/core/skbuff.c:113!
invalid opcode: 0000 [#1] PREEMPT SMP KASAN
CPU: 0 PID: 57 Comm: kworker/0:2 Not tainted 5.15.106-syzkaller-00249-g19c0ed55a470 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/14/2023
Workqueue: mld mld_ifc_work
RIP: 0010:skb_panic net/core/skbuff.c:113 [inline]
RIP: 0010:skb_over_panic+0x14c/0x150 net/core/skbuff.c:118
[snip]
Call Trace:
<TASK>
skb_put+0x151/0x210 net/core/skbuff.c:2047
skb_put_zero include/linux/skbuff.h:2422 [inline]
cdc_ncm_ndp16 drivers/net/usb/cdc_ncm.c:1131 [inline]
cdc_ncm_fill_tx_frame+0x11ab/0x3da0 drivers/net/usb/cdc_ncm.c:1308
cdc_ncm_tx_fixup+0xa3/0x100
Deal with too low values of dwNtbOutMaxSize, clamp it in the range
[USB_CDC_NCM_NTB_MIN_OUT_SIZE, CDC_NCM_NTB_MAX_SIZE_TX]. We ensure
enough data space is allocated to handle CDC data by making sure
dwNtbOutMaxSize is not smaller than USB_CDC_NCM_NTB_MIN_OUT_SIZE.
Fixes: 289507d3364f ("net: cdc_ncm: use sysfs for rx/tx aggregation tuning")
Cc: stable(a)vger.kernel.org
Reported-by: syzbot+9f575a1f15fc0c01ed69(a)syzkaller.appspotmail.com
Link: https://syzkaller.appspot.com/bug?extid=b982f1059506db48409d
Link: https://lore.kernel.org/all/20211202143437.1411410-1-lee.jones@linaro.org/
Signed-off-by: Tudor Ambarus <tudor.ambarus(a)linaro.org>
Reviewed-by: Simon Horman <simon.horman(a)corigine.com>
Link: https://lore.kernel.org/r/20230517133808.1873695-2-tudor.ambarus@linaro.org
Signed-off-by: Jakub Kicinski <kuba(a)kernel.org>
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 6ce8f4f0c70e..db05622f1f70 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -181,9 +181,12 @@ static u32 cdc_ncm_check_tx_max(struct usbnet *dev, u32 new_tx)
else
min = ctx->max_datagram_size + ctx->max_ndp_size + sizeof(struct usb_cdc_ncm_nth32);
- max = min_t(u32, CDC_NCM_NTB_MAX_SIZE_TX, le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize));
- if (max == 0)
+ if (le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize) == 0)
max = CDC_NCM_NTB_MAX_SIZE_TX; /* dwNtbOutMaxSize not set */
+ else
+ max = clamp_t(u32, le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize),
+ USB_CDC_NCM_NTB_MIN_OUT_SIZE,
+ CDC_NCM_NTB_MAX_SIZE_TX);
/* some devices set dwNtbOutMaxSize too low for the above default */
min = min(min, max);
@@ -1244,6 +1247,9 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign)
* further.
*/
if (skb_out == NULL) {
+ /* If even the smallest allocation fails, abort. */
+ if (ctx->tx_curr_size == USB_CDC_NCM_NTB_MIN_OUT_SIZE)
+ goto alloc_failed;
ctx->tx_low_mem_max_cnt = min(ctx->tx_low_mem_max_cnt + 1,
(unsigned)CDC_NCM_LOW_MEM_MAX_CNT);
ctx->tx_low_mem_val = ctx->tx_low_mem_max_cnt;
@@ -1262,13 +1268,8 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign)
skb_out = alloc_skb(ctx->tx_curr_size, GFP_ATOMIC);
/* No allocation possible so we will abort */
- if (skb_out == NULL) {
- if (skb != NULL) {
- dev_kfree_skb_any(skb);
- dev->net->stats.tx_dropped++;
- }
- goto exit_no_skb;
- }
+ if (!skb_out)
+ goto alloc_failed;
ctx->tx_low_mem_val--;
}
if (ctx->is_ndp16) {
@@ -1461,6 +1462,11 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign)
return skb_out;
+alloc_failed:
+ if (skb) {
+ dev_kfree_skb_any(skb);
+ dev->net->stats.tx_dropped++;
+ }
exit_no_skb:
/* Start timer, if there is a remaining non-empty skb */
if (ctx->tx_curr_skb != NULL && n > 0)
The patch below does not apply to the 4.19-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y
git checkout FETCH_HEAD
git cherry-pick -x 7e01c7f7046efc2c7c192c3619db43292b98e997
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023052623-tricky-machinist-46c5@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^..
Possible dependencies:
7e01c7f7046e ("net: cdc_ncm: Deal with too low values of dwNtbOutMaxSize")
2be6d4d16a08 ("net: cdc_ncm: Allow for dwNtbOutMaxSize to be unset or zero")
0fa81b304a79 ("cdc_ncm: Implement the 32-bit version of NCM Transfer Block")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 7e01c7f7046efc2c7c192c3619db43292b98e997 Mon Sep 17 00:00:00 2001
From: Tudor Ambarus <tudor.ambarus(a)linaro.org>
Date: Wed, 17 May 2023 13:38:08 +0000
Subject: [PATCH] net: cdc_ncm: Deal with too low values of dwNtbOutMaxSize
Currently in cdc_ncm_check_tx_max(), if dwNtbOutMaxSize is lower than
the calculated "min" value, but greater than zero, the logic sets
tx_max to dwNtbOutMaxSize. This is then used to allocate a new SKB in
cdc_ncm_fill_tx_frame() where all the data is handled.
For small values of dwNtbOutMaxSize the memory allocated during
alloc_skb(dwNtbOutMaxSize, GFP_ATOMIC) will have the same size, due to
how size is aligned at alloc time:
size = SKB_DATA_ALIGN(size);
size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
Thus we hit the same bug that we tried to squash with
commit 2be6d4d16a084 ("net: cdc_ncm: Allow for dwNtbOutMaxSize to be unset or zero")
Low values of dwNtbOutMaxSize do not cause an issue presently because at
alloc_skb() time more memory (512b) is allocated than required for the
SKB headers alone (320b), leaving some space (512b - 320b = 192b)
for CDC data (172b).
However, if more elements (for example 3 x u64 = [24b]) were added to
one of the SKB header structs, say 'struct skb_shared_info',
increasing its original size (320b [320b aligned]) to something larger
(344b [384b aligned]), then suddenly the CDC data (172b) no longer
fits in the spare SKB data area (512b - 384b = 128b).
Consequently the SKB bounds checking semantics fails and panics:
skbuff: skb_over_panic: text:ffffffff831f755b len:184 put:172 head:ffff88811f1c6c00 data:ffff88811f1c6c00 tail:0xb8 end:0x80 dev:<NULL>
------------[ cut here ]------------
kernel BUG at net/core/skbuff.c:113!
invalid opcode: 0000 [#1] PREEMPT SMP KASAN
CPU: 0 PID: 57 Comm: kworker/0:2 Not tainted 5.15.106-syzkaller-00249-g19c0ed55a470 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/14/2023
Workqueue: mld mld_ifc_work
RIP: 0010:skb_panic net/core/skbuff.c:113 [inline]
RIP: 0010:skb_over_panic+0x14c/0x150 net/core/skbuff.c:118
[snip]
Call Trace:
<TASK>
skb_put+0x151/0x210 net/core/skbuff.c:2047
skb_put_zero include/linux/skbuff.h:2422 [inline]
cdc_ncm_ndp16 drivers/net/usb/cdc_ncm.c:1131 [inline]
cdc_ncm_fill_tx_frame+0x11ab/0x3da0 drivers/net/usb/cdc_ncm.c:1308
cdc_ncm_tx_fixup+0xa3/0x100
Deal with too low values of dwNtbOutMaxSize, clamp it in the range
[USB_CDC_NCM_NTB_MIN_OUT_SIZE, CDC_NCM_NTB_MAX_SIZE_TX]. We ensure
enough data space is allocated to handle CDC data by making sure
dwNtbOutMaxSize is not smaller than USB_CDC_NCM_NTB_MIN_OUT_SIZE.
Fixes: 289507d3364f ("net: cdc_ncm: use sysfs for rx/tx aggregation tuning")
Cc: stable(a)vger.kernel.org
Reported-by: syzbot+9f575a1f15fc0c01ed69(a)syzkaller.appspotmail.com
Link: https://syzkaller.appspot.com/bug?extid=b982f1059506db48409d
Link: https://lore.kernel.org/all/20211202143437.1411410-1-lee.jones@linaro.org/
Signed-off-by: Tudor Ambarus <tudor.ambarus(a)linaro.org>
Reviewed-by: Simon Horman <simon.horman(a)corigine.com>
Link: https://lore.kernel.org/r/20230517133808.1873695-2-tudor.ambarus@linaro.org
Signed-off-by: Jakub Kicinski <kuba(a)kernel.org>
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 6ce8f4f0c70e..db05622f1f70 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -181,9 +181,12 @@ static u32 cdc_ncm_check_tx_max(struct usbnet *dev, u32 new_tx)
else
min = ctx->max_datagram_size + ctx->max_ndp_size + sizeof(struct usb_cdc_ncm_nth32);
- max = min_t(u32, CDC_NCM_NTB_MAX_SIZE_TX, le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize));
- if (max == 0)
+ if (le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize) == 0)
max = CDC_NCM_NTB_MAX_SIZE_TX; /* dwNtbOutMaxSize not set */
+ else
+ max = clamp_t(u32, le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize),
+ USB_CDC_NCM_NTB_MIN_OUT_SIZE,
+ CDC_NCM_NTB_MAX_SIZE_TX);
/* some devices set dwNtbOutMaxSize too low for the above default */
min = min(min, max);
@@ -1244,6 +1247,9 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign)
* further.
*/
if (skb_out == NULL) {
+ /* If even the smallest allocation fails, abort. */
+ if (ctx->tx_curr_size == USB_CDC_NCM_NTB_MIN_OUT_SIZE)
+ goto alloc_failed;
ctx->tx_low_mem_max_cnt = min(ctx->tx_low_mem_max_cnt + 1,
(unsigned)CDC_NCM_LOW_MEM_MAX_CNT);
ctx->tx_low_mem_val = ctx->tx_low_mem_max_cnt;
@@ -1262,13 +1268,8 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign)
skb_out = alloc_skb(ctx->tx_curr_size, GFP_ATOMIC);
/* No allocation possible so we will abort */
- if (skb_out == NULL) {
- if (skb != NULL) {
- dev_kfree_skb_any(skb);
- dev->net->stats.tx_dropped++;
- }
- goto exit_no_skb;
- }
+ if (!skb_out)
+ goto alloc_failed;
ctx->tx_low_mem_val--;
}
if (ctx->is_ndp16) {
@@ -1461,6 +1462,11 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign)
return skb_out;
+alloc_failed:
+ if (skb) {
+ dev_kfree_skb_any(skb);
+ dev->net->stats.tx_dropped++;
+ }
exit_no_skb:
/* Start timer, if there is a remaining non-empty skb */
if (ctx->tx_curr_skb != NULL && n > 0)
The patch below does not apply to the 5.15-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y
git checkout FETCH_HEAD
git cherry-pick -x 8173cab3368a13cdc3cad0bd5cf14e9399b0f501
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023052257-kiwi-level-12a2@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^..
Possible dependencies:
8173cab3368a ("drm/amdgpu/gfx10: Disable gfxoff before disabling powergating.")
fabe1753851c ("drm/amdgpu: enable gfx power gating for GC 10.3.7")
874bfdfa4735 ("drm/amdgpu: add gc 10.3.6 support")
a65dbf7cded7 ("drm/amdgpu/gfx10: Add GC 10.3.7 Support")
35c27d957835 ("drm/amdgpu: update vcn/jpeg PG flags for VCN 3.1.1")
b67f00e06f36 ("drm/amdgpu: set new revision id for 10.3.7 GC")
dfcc3e8c24cc ("drm/amdgpu: make cyan skillfish support code more consistent")
212021297eaf ("drm/amdgpu: set APU flag based on IP discovery table")
e8a423c589a0 ("drm/amdgpu: update RLC_PG_DELAY_3 Value to 200us for yellow carp")
a61794bd2f65 ("drm/amdgpu: remove grbm cam index/data operations for gfx v10")
b05b9c591f9e ("drm/amdgpu: clean up set IP function")
1d789535a036 ("drm/amdgpu: convert IP version array to include instances")
5c3720be7d46 ("drm/amdgpu: get VCN and SDMA instances from IP discovery table")
2cbc6f4259f6 ("drm/amd/display: fix error case handling")
75a07bcd1d30 ("drm/amdgpu/soc15: convert to IP version checking")
0b64a5a85229 ("drm/amdgpu/vcn2.5: convert to IP version checking")
96b8dd4423e7 ("drm/amdgpu/amdgpu_vcn: convert to IP version checking")
50638f7dbd0b ("drm/amdgpu/pm/amdgpu_smu: convert more IP version checking")
61b396b91196 ("drm/amdgpu/pm/smu_v13.0: convert IP version checking")
6b726a0a52cc ("drm/amdgpu/pm/smu_v11.0: update IP version checking")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 8173cab3368a13cdc3cad0bd5cf14e9399b0f501 Mon Sep 17 00:00:00 2001
From: Bas Nieuwenhuizen <bas(a)basnieuwenhuizen.nl>
Date: Tue, 9 May 2023 18:49:46 +0200
Subject: [PATCH] drm/amdgpu/gfx10: Disable gfxoff before disabling
powergating.
Otherwise we get a full system lock (looks like a FW mess).
Copied the order from the GFX9 powergating code.
Fixes: 366468ff6c34 ("drm/amdgpu: Allow GfxOff on Vangogh as default")
Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2545
Signed-off-by: Bas Nieuwenhuizen <bas(a)basnieuwenhuizen.nl>
Tested-by: Guilherme G. Piccoli <gpiccoli(a)igalia.com>
Cc: Alex Deucher <alexander.deucher(a)amd.com>
Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com>
Cc: stable(a)vger.kernel.org
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index f5b5ce1051a2..1ec076517c96 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -8152,8 +8152,14 @@ static int gfx_v10_0_set_powergating_state(void *handle,
case IP_VERSION(10, 3, 3):
case IP_VERSION(10, 3, 6):
case IP_VERSION(10, 3, 7):
+ if (!enable)
+ amdgpu_gfx_off_ctrl(adev, false);
+
gfx_v10_cntl_pg(adev, enable);
- amdgpu_gfx_off_ctrl(adev, enable);
+
+ if (enable)
+ amdgpu_gfx_off_ctrl(adev, true);
+
break;
default:
break;
Hello all,
I have a HP Elite x360 1049 G9 2-in-1 notebook running fedora 38 with an Adler
Lake intel video card.
After upgrading to kernel 6.2.13 (as packaged by fedora), I started seeing
severe video glitches made of random pixels in a vertical band occupying about
20% of my screen, on the right. The glitches would happen both with X.org and
wayland.
I checked that vanilla 6.2.12 does not have the bug and that both vanilla
6.2.13 and vanilla 6.3.2 do have the bug.
I bisected the problem to commit e2b789bc3dc34edc87ffb85634967d24ed351acb (it
is a one-liner reproduced at the end of this message).
I checked that vanilla 6.3.2 with this commit reverted does not have the bug.
I am CC-ing every e-mail appearing in this commit , I hope this is ok, and I
apologize if it is not.
I have filled a fedora bug report about this, see https://bugzilla.redhat.com/
show_bug.cgi?id=2203549 . You will find there a small video (made with fedora
kernel 2.6.14) demonstrating the issue.
Some more details:
% sudo lspci -vk -s 00:02.0
00:02.0 VGA compatible controller: Intel Corporation Alder Lake-UP3 GT2 [Iris
Xe Graphics] (rev 0c) (prog-if 00 [VGA controller])
DeviceName: Onboard IGD
Subsystem: Hewlett-Packard Company Device 896d
Flags: bus master, fast devsel, latency 0, IRQ 143
Memory at 603c000000 (64-bit, non-prefetchable) [size=16M]
Memory at 4000000000 (64-bit, prefetchable) [size=256M]
I/O ports at 3000 [size=64]
Expansion ROM at 000c0000 [virtual] [disabled] [size=128K]
Capabilities: [40] Vendor Specific Information: Len=0c <?>
Capabilities: [70] Express Root Complex Integrated Endpoint, MSI 00
Capabilities: [ac] MSI: Enable+ Count=1/1 Maskable+ 64bit-
Capabilities: [d0] Power Management version 2
Capabilities: [100] Process Address Space ID (PASID)
Capabilities: [200] Address Translation Service (ATS)
Capabilities: [300] Page Request Interface (PRI)
Capabilities: [320] Single Root I/O Virtualization (SR-IOV)
Kernel driver in use: i915
Kernel modules: i915
Relevant kernel boot messages: (appart from timestamps, these lines are
identical for 6.2.12 and 6.2.14):
[ 2.790043] i915 0000:00:02.0: vgaarb: deactivate vga console
[ 2.790089] i915 0000:00:02.0: [drm] Using Transparent Hugepages
[ 2.790497] i915 0000:00:02.0: vgaarb: changed VGA decodes:
olddecodes=io+mem,decodes=io+mem:owns=io+mem
[ 2.793812] i915 0000:00:02.0: [drm] Finished loading DMC firmware i915/
adlp_dmc_ver2_16.bin (v2.16)
[ 2.825058] i915 0000:00:02.0: [drm] GuC firmware i915/adlp_guc_70.bin
version 70.5.1
[ 2.825061] i915 0000:00:02.0: [drm] HuC firmware i915/tgl_huc.bin version
7.9.3
[ 2.842906] i915 0000:00:02.0: [drm] HuC authenticated
[ 2.843778] i915 0000:00:02.0: [drm] GuC submission enabled
[ 2.843779] i915 0000:00:02.0: [drm] GuC SLPC enabled
[ 2.844200] i915 0000:00:02.0: [drm] GuC RC: enabled
[ 2.845010] i915 0000:00:02.0: [drm] Protected Xe Path (PXP) protected
content support initialized
[ 3.964766] [drm] Initialized i915 1.6.0 20201103 for 0000:00:02.0 on minor
1
[ 3.968403] ACPI: video: Video Device [GFX0] (multi-head: yes rom: no
post: no)
[ 3.968981] input: Video Bus as /devices/LNXSYSTM:00/LNXSYBUS:00/
PNP0A08:00/LNXVIDEO:00/input/input18
[ 3.977892] fbcon: i915drmfb (fb0) is primary device
[ 3.977899] fbcon: Deferring console take-over
[ 3.977904] i915 0000:00:02.0: [drm] fb0: i915drmfb frame buffer device
[ 4.026120] i915 0000:00:02.0: [drm] Selective fetch area calculation
failed in pipe A
Is there anything else I should provide? I am willing to run some tests, of
course.
Thanks for your help,
Éric Brunet
=================================================
commit e2b789bc3dc34edc87ffb85634967d24ed351acb (HEAD)
Author: Ville Syrjälä <ville.syrjala(a)linux.intel.com>
Date: Wed Mar 29 20:24:33 2023 +0300
drm/i915: Fix fast wake AUX sync len
commit e1c71f8f918047ce822dc19b42ab1261ed259fd1 upstream.
Fast wake should use 8 SYNC pulses for the preamble
and 10-16 SYNC pulses for the precharge. Reduce our
fast wake SYNC count to match the maximum value.
We also use the maximum precharge length for normal
AUX transactions.
Cc: stable(a)vger.kernel.org
Cc: Jouni Högander <jouni.hogander(a)intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala(a)linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/
20230329172434.18744-1-ville.syrjala(a)linux.intel.com
Reviewed-by: Jouni Högander <jouni.hogander(a)intel.com>
(cherry picked from commit 605f7c73133341d4b762cbd9a22174cc22d4c38b)
Signed-off-by: Jani Nikula <jani.nikula(a)intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux.c b/drivers/gpu/drm/
i915/display/intel_dp_aux.c
index 664bebdecea7..d5fed2eb66d2 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_aux.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_aux.c
@@ -166,7 +166,7 @@ static u32 skl_get_aux_send_ctl(struct intel_dp *intel_dp,
DP_AUX_CH_CTL_TIME_OUT_MAX |
DP_AUX_CH_CTL_RECEIVE_ERROR |
(send_bytes << DP_AUX_CH_CTL_MESSAGE_SIZE_SHIFT) |
- DP_AUX_CH_CTL_FW_SYNC_PULSE_SKL(32) |
+ DP_AUX_CH_CTL_FW_SYNC_PULSE_SKL(24) |
DP_AUX_CH_CTL_SYNC_PULSE_SKL(32);
if (intel_tc_port_in_tbt_alt_mode(dig_port))
In I2C_FUNC_SMBUS_BLOCK_DATA case, the I2C Designware driver does not
handle correctly when it receives the length of SMBus block data
response from SMBus slave device, which is outside the range 1-32 bytes.
Consequently, the I2C Designware bus is stuck and cannot recover.
Because if IC_EMPTYFIFO_HOLD_MASTER_EN is set, which cannot be detected
from the registers, the controller can be disabled if the STOP bit is set.
But it is only set after receiving block data response length.
Hence, to prevent the bus from stuck condition, after receiving the
invalid block data response length, the driver will read another byte
with STOP bit set.
Cc: stable(a)vger.kernel.org
Signed-off-by: Tam Nguyen <tamnguyenchi(a)os.amperecomputing.com>
---
drivers/i2c/busses/i2c-designware-master.c | 15 +++++++++++++--
1 file changed, 13 insertions(+), 2 deletions(-)
diff --git a/drivers/i2c/busses/i2c-designware-master.c b/drivers/i2c/busses/i2c-designware-master.c
index 55ea91a63382..94dadd785ed0 100644
--- a/drivers/i2c/busses/i2c-designware-master.c
+++ b/drivers/i2c/busses/i2c-designware-master.c
@@ -527,8 +527,19 @@ i2c_dw_read(struct dw_i2c_dev *dev)
regmap_read(dev->map, DW_IC_DATA_CMD, &tmp);
/* Ensure length byte is a valid value */
- if (flags & I2C_M_RECV_LEN &&
- (tmp & DW_IC_DATA_CMD_DAT) <= I2C_SMBUS_BLOCK_MAX && tmp > 0) {
+ if (flags & I2C_M_RECV_LEN) {
+ /*
+ * if IC_EMPTYFIFO_HOLD_MASTER_EN is set, which cannot be
+ * detected from the registers, the controller can be
+ * disabled if the STOP bit is set. But it is only set
+ * after receiving block data response length in
+ * I2C_FUNC_SMBUS_BLOCK_DATA case. That needs to read
+ * another byte with STOP bit set when the block data
+ * response length is invalid to complete the transaction.
+ */
+ if ((tmp & DW_IC_DATA_CMD_DAT) > I2C_SMBUS_BLOCK_MAX || tmp == 0)
+ tmp = 1;
+
len = i2c_dw_recv_len(dev, tmp);
}
*buf++ = tmp;
--
2.25.1
From: Xiubo Li <xiubli(a)redhat.com>
Blindly expanding the readahead windows will cause unneccessary
pagecache thrashing and also will introdue the network workload.
We should disable expanding the windows if the readahead is disabled
and also shouldn't expand the windows too much.
Expanding forward firstly instead of expanding backward for possible
sequential reads.
Bound `rreq->len` to the actual file size to restore the previous page
cache usage.
The posix_fadvise may change the maximum size of a file readahead.
Cc: stable(a)vger.kernel.org
Fixes: 49870056005c ("ceph: convert ceph_readpages to ceph_readahead")
URL: https://lore.kernel.org/ceph-devel/20230504082510.247-1-sehuww@mail.scut.ed…
URL: https://www.spinics.net/lists/ceph-users/msg76183.html
Cc: Hu Weiwen <sehuww(a)mail.scut.edu.cn>
Signed-off-by: Xiubo Li <xiubli(a)redhat.com>
---
fs/ceph/addr.c | 40 +++++++++++++++++++++++++++++++++-------
1 file changed, 33 insertions(+), 7 deletions(-)
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 93fff1a7373f..4b29777c01d7 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -188,16 +188,42 @@ static void ceph_netfs_expand_readahead(struct netfs_io_request *rreq)
struct inode *inode = rreq->inode;
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_file_layout *lo = &ci->i_layout;
+ unsigned long max_pages = inode->i_sb->s_bdi->ra_pages;
+ loff_t end = rreq->start + rreq->len, new_end;
+ struct ceph_netfs_request_data *priv = rreq->netfs_priv;
+ unsigned long max_len;
u32 blockoff;
- u64 blockno;
- /* Expand the start downward */
- blockno = div_u64_rem(rreq->start, lo->stripe_unit, &blockoff);
- rreq->start = blockno * lo->stripe_unit;
- rreq->len += blockoff;
+ if (priv) {
+ /* Readahead is disabled by posix_fadvise POSIX_FADV_RANDOM */
+ if (priv->file_ra_disabled)
+ max_pages = 0;
+ else
+ max_pages = priv->file_ra_pages;
+
+ }
+
+ /* Readahead is disabled */
+ if (!max_pages)
+ return;
- /* Now, round up the length to the next block */
- rreq->len = roundup(rreq->len, lo->stripe_unit);
+ max_len = max_pages << PAGE_SHIFT;
+
+ /*
+ * Try to expand the length forward by rounding up it to the next
+ * block, but do not exceed the file size, unless the original
+ * request already exceeds it.
+ */
+ new_end = min(round_up(end, lo->stripe_unit), rreq->i_size);
+ if (new_end > end && new_end <= rreq->start + max_len)
+ rreq->len = new_end - rreq->start;
+
+ /* Try to expand the start downward */
+ div_u64_rem(rreq->start, lo->stripe_unit, &blockoff);
+ if (rreq->len + blockoff <= max_len) {
+ rreq->start -= blockoff;
+ rreq->len += blockoff;
+ }
}
static bool ceph_netfs_clamp_length(struct netfs_io_subrequest *subreq)
--
2.40.1