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 a63c357b9fd56ad5fe64616f5b22835252c6a76a
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024012226-unmanned-marshy-5819@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^..
Possible dependencies:
a63c357b9fd5 ("iommu/dma: Trace bounce buffer usage when mapping buffers")
f316ba0a8814 ("dma-iommu: Check that swiotlb is active before trying to use it")
a17e3026bc4d ("iommu: Move flush queue data into iommu_dma_cookie")
f7f07484542f ("iommu/iova: Move flush queue code to iommu-dma")
ea4d71bb5e3f ("iommu/iova: Consolidate flush queue code")
87f60cc65d24 ("iommu/vt-d: Use put_pages_list")
649ad9835a37 ("iommu/iova: Squash flush_cb abstraction")
d5c383f2c98a ("iommu/iova: Squash entry_dtor abstraction")
d7061627d701 ("iommu/iova: Fix race between FQ timeout and teardown")
2e727bffbe93 ("iommu/dma: Check CONFIG_SWIOTLB more broadly")
9b49bbc2c4df ("iommu/dma: Fold _swiotlb helpers into callers")
ee9d4097cc14 ("iommu/dma: Skip extra sync during unmap w/swiotlb")
06e620345d54 ("iommu/dma: Fix arch_sync_dma for map")
08ae5d4a1ae9 ("iommu/dma: Fix sync_sg with swiotlb")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From a63c357b9fd56ad5fe64616f5b22835252c6a76a Mon Sep 17 00:00:00 2001
From: "Isaac J. Manjarres" <isaacmanjarres(a)google.com>
Date: Fri, 8 Dec 2023 15:41:40 -0800
Subject: [PATCH] iommu/dma: Trace bounce buffer usage when mapping buffers
When commit 82612d66d51d ("iommu: Allow the dma-iommu api to
use bounce buffers") was introduced, it did not add the logic
for tracing the bounce buffer usage from iommu_dma_map_page().
All of the users of swiotlb_tbl_map_single() trace their bounce
buffer usage, except iommu_dma_map_page(). This makes it difficult
to track SWIOTLB usage from that function. Thus, trace bounce buffer
usage from iommu_dma_map_page().
Fixes: 82612d66d51d ("iommu: Allow the dma-iommu api to use bounce buffers")
Cc: stable(a)vger.kernel.org # v5.15+
Cc: Tom Murphy <murphyt7(a)tcd.ie>
Cc: Lu Baolu <baolu.lu(a)linux.intel.com>
Cc: Saravana Kannan <saravanak(a)google.com>
Signed-off-by: Isaac J. Manjarres <isaacmanjarres(a)google.com>
Link: https://lore.kernel.org/r/20231208234141.2356157-1-isaacmanjarres@google.com
Signed-off-by: Joerg Roedel <jroedel(a)suse.de>
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 85163a83df2f..037fcf826407 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -29,6 +29,7 @@
#include <linux/spinlock.h>
#include <linux/swiotlb.h>
#include <linux/vmalloc.h>
+#include <trace/events/swiotlb.h>
#include "dma-iommu.h"
@@ -1156,6 +1157,8 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
return DMA_MAPPING_ERROR;
}
+ trace_swiotlb_bounced(dev, phys, size);
+
aligned_size = iova_align(iovad, size);
phys = swiotlb_tbl_map_single(dev, phys, size, aligned_size,
iova_mask(iovad), dir, attrs);
The patch below does not apply to the 6.1-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-6.1.y
git checkout FETCH_HEAD
git cherry-pick -x 8e0545c83d672750632f46e3f9ad95c48c91a0fc
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024061303-heap-catalyst-0a58@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^..
Possible dependencies:
8e0545c83d67 ("mm/vmalloc: fix vmalloc which may return null if called with __GFP_NOFAIL")
e9c3cda4d86e ("mm, vmalloc: fix high order __GFP_NOFAIL allocations")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 8e0545c83d672750632f46e3f9ad95c48c91a0fc Mon Sep 17 00:00:00 2001
From: "Hailong.Liu" <hailong.liu(a)oppo.com>
Date: Fri, 10 May 2024 18:01:31 +0800
Subject: [PATCH] mm/vmalloc: fix vmalloc which may return null if called with
__GFP_NOFAIL
commit a421ef303008 ("mm: allow !GFP_KERNEL allocations for kvmalloc")
includes support for __GFP_NOFAIL, but it presents a conflict with commit
dd544141b9eb ("vmalloc: back off when the current task is OOM-killed"). A
possible scenario is as follows:
process-a
__vmalloc_node_range(GFP_KERNEL | __GFP_NOFAIL)
__vmalloc_area_node()
vm_area_alloc_pages()
--> oom-killer send SIGKILL to process-a
if (fatal_signal_pending(current)) break;
--> return NULL;
To fix this, do not check fatal_signal_pending() in vm_area_alloc_pages()
if __GFP_NOFAIL set.
This issue occurred during OPLUS KASAN TEST. Below is part of the log
-> oom-killer sends signal to process
[65731.222840] [ T1308] oom-kill:constraint=CONSTRAINT_NONE,nodemask=(null),cpuset=/,mems_allowed=0,global_oom,task_memcg=/apps/uid_10198,task=gs.intelligence,pid=32454,uid=10198
[65731.259685] [T32454] Call trace:
[65731.259698] [T32454] dump_backtrace+0xf4/0x118
[65731.259734] [T32454] show_stack+0x18/0x24
[65731.259756] [T32454] dump_stack_lvl+0x60/0x7c
[65731.259781] [T32454] dump_stack+0x18/0x38
[65731.259800] [T32454] mrdump_common_die+0x250/0x39c [mrdump]
[65731.259936] [T32454] ipanic_die+0x20/0x34 [mrdump]
[65731.260019] [T32454] atomic_notifier_call_chain+0xb4/0xfc
[65731.260047] [T32454] notify_die+0x114/0x198
[65731.260073] [T32454] die+0xf4/0x5b4
[65731.260098] [T32454] die_kernel_fault+0x80/0x98
[65731.260124] [T32454] __do_kernel_fault+0x160/0x2a8
[65731.260146] [T32454] do_bad_area+0x68/0x148
[65731.260174] [T32454] do_mem_abort+0x151c/0x1b34
[65731.260204] [T32454] el1_abort+0x3c/0x5c
[65731.260227] [T32454] el1h_64_sync_handler+0x54/0x90
[65731.260248] [T32454] el1h_64_sync+0x68/0x6c
[65731.260269] [T32454] z_erofs_decompress_queue+0x7f0/0x2258
--> be->decompressed_pages = kvcalloc(be->nr_pages, sizeof(struct page *), GFP_KERNEL | __GFP_NOFAIL);
kernel panic by NULL pointer dereference.
erofs assume kvmalloc with __GFP_NOFAIL never return NULL.
[65731.260293] [T32454] z_erofs_runqueue+0xf30/0x104c
[65731.260314] [T32454] z_erofs_readahead+0x4f0/0x968
[65731.260339] [T32454] read_pages+0x170/0xadc
[65731.260364] [T32454] page_cache_ra_unbounded+0x874/0xf30
[65731.260388] [T32454] page_cache_ra_order+0x24c/0x714
[65731.260411] [T32454] filemap_fault+0xbf0/0x1a74
[65731.260437] [T32454] __do_fault+0xd0/0x33c
[65731.260462] [T32454] handle_mm_fault+0xf74/0x3fe0
[65731.260486] [T32454] do_mem_abort+0x54c/0x1b34
[65731.260509] [T32454] el0_da+0x44/0x94
[65731.260531] [T32454] el0t_64_sync_handler+0x98/0xb4
[65731.260553] [T32454] el0t_64_sync+0x198/0x19c
Link: https://lkml.kernel.org/r/20240510100131.1865-1-hailong.liu@oppo.com
Fixes: 9376130c390a ("mm/vmalloc: add support for __GFP_NOFAIL")
Signed-off-by: Hailong.Liu <hailong.liu(a)oppo.com>
Acked-by: Michal Hocko <mhocko(a)suse.com>
Suggested-by: Barry Song <21cnbao(a)gmail.com>
Reported-by: Oven <liyangouwen1(a)oppo.com>
Reviewed-by: Barry Song <baohua(a)kernel.org>
Reviewed-by: Uladzislau Rezki (Sony) <urezki(a)gmail.com>
Cc: Chao Yu <chao(a)kernel.org>
Cc: Christoph Hellwig <hch(a)infradead.org>
Cc: Gao Xiang <xiang(a)kernel.org>
Cc: Lorenzo Stoakes <lstoakes(a)gmail.com>
Cc: Michal Hocko <mhocko(a)suse.com>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 6641be0ca80b..5d3aa2dc88a8 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -3498,7 +3498,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
{
unsigned int nr_allocated = 0;
gfp_t alloc_gfp = gfp;
- bool nofail = false;
+ bool nofail = gfp & __GFP_NOFAIL;
struct page *page;
int i;
@@ -3555,12 +3555,11 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
* and compaction etc.
*/
alloc_gfp &= ~__GFP_NOFAIL;
- nofail = true;
}
/* High-order pages or fallback path if "bulk" fails. */
while (nr_allocated < nr_pages) {
- if (fatal_signal_pending(current))
+ if (!nofail && fatal_signal_pending(current))
break;
if (nid == NUMA_NO_NODE)
The patch titled
Subject: mm: fix incorrect vbq reference in purge_fragmented_block
has been added to the -mm mm-hotfixes-stable branch. Its filename is
mm-fix-incorrect-vbq-reference-in-purge_fragmented_block.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche…
This patch will later appear in the mm-hotfixes-stable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Zhaoyang Huang <zhaoyang.huang(a)unisoc.com>
Subject: mm: fix incorrect vbq reference in purge_fragmented_block
Date: Fri, 7 Jun 2024 10:31:16 +0800
xa_for_each() in _vm_unmap_aliases() loops through all vbs. However,
since commit 062eacf57ad9 ("mm: vmalloc: remove a global vmap_blocks
xarray") the vb from xarray may not be on the corresponding CPU
vmap_block_queue. Consequently, purge_fragmented_block() might use the
wrong vbq->lock to protect the free list, leading to vbq->free breakage.
Incorrect lock protection can exhaust all vmalloc space as follows:
CPU0 CPU1
+--------------------------------------------+
| +--------------------+ +-----+ |
+--> | |---->| |------+
| CPU1:vbq free_list | | vb1 |
+--- | |<----| |<-----+
| +--------------------+ +-----+ |
+--------------------------------------------+
_vm_unmap_aliases() vb_alloc()
new_vmap_block()
xa_for_each(&vbq->vmap_blocks, idx, vb)
--> vb in CPU1:vbq->freelist
purge_fragmented_block(vb)
spin_lock(&vbq->lock) spin_lock(&vbq->lock)
--> use CPU0:vbq->lock --> use CPU1:vbq->lock
list_del_rcu(&vb->free_list) list_add_tail_rcu(&vb->free_list, &vbq->free)
__list_del(vb->prev, vb->next)
next->prev = prev
+--------------------+
| |
| CPU1:vbq free_list |
+---| |<--+
| +--------------------+ |
+----------------------------+
__list_add(new, head->prev, head)
+--------------------------------------------+
| +--------------------+ +-----+ |
+--> | |---->| |------+
| CPU1:vbq free_list | | vb2 |
+--- | |<----| |<-----+
| +--------------------+ +-----+ |
+--------------------------------------------+
prev->next = next
+--------------------------------------------+
|----------------------------+ |
| +--------------------+ | +-----+ |
+--> | |--+ | |------+
| CPU1:vbq free_list | | vb2 |
+--- | |<----| |<-----+
| +--------------------+ +-----+ |
+--------------------------------------------+
Here���s a list breakdown. All vbs, which were to be added to
���prev���, cannot be used by list_for_each_entry_rcu(vb, &vbq->free,
free_list) in vb_alloc(). Thus, vmalloc space is exhausted.
This issue affects both erofs and f2fs, the stacktrace is as follows:
erofs:
[<ffffffd4ffb93ad4>] __switch_to+0x174
[<ffffffd4ffb942f0>] __schedule+0x624
[<ffffffd4ffb946f4>] schedule+0x7c
[<ffffffd4ffb947cc>] schedule_preempt_disabled+0x24
[<ffffffd4ffb962ec>] __mutex_lock+0x374
[<ffffffd4ffb95998>] __mutex_lock_slowpath+0x14
[<ffffffd4ffb95954>] mutex_lock+0x24
[<ffffffd4fef2900c>] reclaim_and_purge_vmap_areas+0x44
[<ffffffd4fef25908>] alloc_vmap_area+0x2e0
[<ffffffd4fef24ea0>] vm_map_ram+0x1b0
[<ffffffd4ff1b46f4>] z_erofs_lz4_decompress+0x278
[<ffffffd4ff1b8ac4>] z_erofs_decompress_queue+0x650
[<ffffffd4ff1b8328>] z_erofs_runqueue+0x7f4
[<ffffffd4ff1b66a8>] z_erofs_read_folio+0x104
[<ffffffd4feeb6fec>] filemap_read_folio+0x6c
[<ffffffd4feeb68c4>] filemap_fault+0x300
[<ffffffd4fef0ecac>] __do_fault+0xc8
[<ffffffd4fef0c908>] handle_mm_fault+0xb38
[<ffffffd4ffb9f008>] do_page_fault+0x288
[<ffffffd4ffb9ed64>] do_translation_fault[jt]+0x40
[<ffffffd4fec39c78>] do_mem_abort+0x58
[<ffffffd4ffb8c3e4>] el0_ia+0x70
[<ffffffd4ffb8c260>] el0t_64_sync_handler[jt]+0xb0
[<ffffffd4fec11588>] ret_to_user[jt]+0x0
f2fs:
[<ffffffd4ffb93ad4>] __switch_to+0x174
[<ffffffd4ffb942f0>] __schedule+0x624
[<ffffffd4ffb946f4>] schedule+0x7c
[<ffffffd4ffb947cc>] schedule_preempt_disabled+0x24
[<ffffffd4ffb962ec>] __mutex_lock+0x374
[<ffffffd4ffb95998>] __mutex_lock_slowpath+0x14
[<ffffffd4ffb95954>] mutex_lock+0x24
[<ffffffd4fef2900c>] reclaim_and_purge_vmap_areas+0x44
[<ffffffd4fef25908>] alloc_vmap_area+0x2e0
[<ffffffd4fef24ea0>] vm_map_ram+0x1b0
[<ffffffd4ff1a3b60>] f2fs_prepare_decomp_mem+0x144
[<ffffffd4ff1a6c24>] f2fs_alloc_dic+0x264
[<ffffffd4ff175468>] f2fs_read_multi_pages+0x428
[<ffffffd4ff17b46c>] f2fs_mpage_readpages+0x314
[<ffffffd4ff1785c4>] f2fs_readahead+0x50
[<ffffffd4feec3384>] read_pages+0x80
[<ffffffd4feec32c0>] page_cache_ra_unbounded+0x1a0
[<ffffffd4feec39e8>] page_cache_ra_order+0x274
[<ffffffd4feeb6cec>] do_sync_mmap_readahead+0x11c
[<ffffffd4feeb6764>] filemap_fault+0x1a0
[<ffffffd4ff1423bc>] f2fs_filemap_fault+0x28
[<ffffffd4fef0ecac>] __do_fault+0xc8
[<ffffffd4fef0c908>] handle_mm_fault+0xb38
[<ffffffd4ffb9f008>] do_page_fault+0x288
[<ffffffd4ffb9ed64>] do_translation_fault[jt]+0x40
[<ffffffd4fec39c78>] do_mem_abort+0x58
[<ffffffd4ffb8c3e4>] el0_ia+0x70
[<ffffffd4ffb8c260>] el0t_64_sync_handler[jt]+0xb0
[<ffffffd4fec11588>] ret_to_user[jt]+0x0
To fix this, introducee cpu within vmap_block to record which this vb
belongs to.
Link: https://lkml.kernel.org/r/20240607023116.1720640-1-zhaoyang.huang@unisoc.com
Fixes: fc1e0d980037 ("mm/vmalloc: prevent stale TLBs in fully utilized blocks")
Signed-off-by: Zhaoyang Huang <zhaoyang.huang(a)unisoc.com>
Suggested-by: Hailong.Liu <hailong.liu(a)oppo.com>
Reviewed-by: Uladzislau Rezki (Sony) <urezki(a)gmail.com>
Cc: Baoquan He <bhe(a)redhat.com>
Cc: Christoph Hellwig <hch(a)infradead.org>
Cc: Lorenzo Stoakes <lstoakes(a)gmail.com>
Cc: Thomas Gleixner <tglx(a)linutronix.de>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
mm/vmalloc.c | 21 +++++++++++++++------
1 file changed, 15 insertions(+), 6 deletions(-)
--- a/mm/vmalloc.c~mm-fix-incorrect-vbq-reference-in-purge_fragmented_block
+++ a/mm/vmalloc.c
@@ -2498,6 +2498,7 @@ struct vmap_block {
struct list_head free_list;
struct rcu_head rcu_head;
struct list_head purge;
+ unsigned int cpu;
};
/* Queue of free and dirty vmap blocks, for allocation and flushing purposes */
@@ -2625,8 +2626,15 @@ static void *new_vmap_block(unsigned int
free_vmap_area(va);
return ERR_PTR(err);
}
-
- vbq = raw_cpu_ptr(&vmap_block_queue);
+ /*
+ * list_add_tail_rcu could happened in another core
+ * rather than vb->cpu due to task migration, which
+ * is safe as list_add_tail_rcu will ensure the list's
+ * integrity together with list_for_each_rcu from read
+ * side.
+ */
+ vb->cpu = raw_smp_processor_id();
+ vbq = per_cpu_ptr(&vmap_block_queue, vb->cpu);
spin_lock(&vbq->lock);
list_add_tail_rcu(&vb->free_list, &vbq->free);
spin_unlock(&vbq->lock);
@@ -2654,9 +2662,10 @@ static void free_vmap_block(struct vmap_
}
static bool purge_fragmented_block(struct vmap_block *vb,
- struct vmap_block_queue *vbq, struct list_head *purge_list,
- bool force_purge)
+ struct list_head *purge_list, bool force_purge)
{
+ struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, vb->cpu);
+
if (vb->free + vb->dirty != VMAP_BBMAP_BITS ||
vb->dirty == VMAP_BBMAP_BITS)
return false;
@@ -2704,7 +2713,7 @@ static void purge_fragmented_blocks(int
continue;
spin_lock(&vb->lock);
- purge_fragmented_block(vb, vbq, &purge, true);
+ purge_fragmented_block(vb, &purge, true);
spin_unlock(&vb->lock);
}
rcu_read_unlock();
@@ -2841,7 +2850,7 @@ static void _vm_unmap_aliases(unsigned l
* not purgeable, check whether there is dirty
* space to be flushed.
*/
- if (!purge_fragmented_block(vb, vbq, &purge_list, false) &&
+ if (!purge_fragmented_block(vb, &purge_list, false) &&
vb->dirty_max && vb->dirty != VMAP_BBMAP_BITS) {
unsigned long va_start = vb->va->va_start;
unsigned long s, e;
_
Patches currently in -mm which might be from zhaoyang.huang(a)unisoc.com are
mm-fix-incorrect-vbq-reference-in-purge_fragmented_block.patch
mm-optimization-on-page-allocation-when-cma-enabled.patch
From: Zhaoyang Huang <zhaoyang.huang(a)unisoc.com>
vmalloc area runs out in our ARM64 system during an erofs test as
vm_map_ram failed[1]. By following the debug log, we find that
vm_map_ram()->vb_alloc() will allocate new vb->va which corresponding
to 4MB vmalloc area as list_for_each_entry_rcu returns immediately
when vbq->free->next points to vbq->free. That is to say, 65536 times
of page fault after the list's broken will run out of the whole
vmalloc area. This should be introduced by one vbq->free->next point to
vbq->free which makes list_for_each_entry_rcu can not iterate the list
and find the BUG.
[1]
PID: 1 TASK: ffffff80802b4e00 CPU: 6 COMMAND: "init"
#0 [ffffffc08006afe0] __switch_to at ffffffc08111d5cc
#1 [ffffffc08006b040] __schedule at ffffffc08111dde0
#2 [ffffffc08006b0a0] schedule at ffffffc08111e294
#3 [ffffffc08006b0d0] schedule_preempt_disabled at ffffffc08111e3f0
#4 [ffffffc08006b140] __mutex_lock at ffffffc08112068c
#5 [ffffffc08006b180] __mutex_lock_slowpath at ffffffc08111f8f8
#6 [ffffffc08006b1a0] mutex_lock at ffffffc08111f834
#7 [ffffffc08006b1d0] reclaim_and_purge_vmap_areas at ffffffc0803ebc3c
#8 [ffffffc08006b290] alloc_vmap_area at ffffffc0803e83fc
#9 [ffffffc08006b300] vm_map_ram at ffffffc0803e78c0
Fixes: fc1e0d980037 ("mm/vmalloc: prevent stale TLBs in fully utilized blocks")
For detailed reason of broken list, please refer to below URL
https://lore.kernel.org/all/20240531024820.5507-1-hailong.liu@oppo.com/
Suggested-by: Hailong.Liu <hailong.liu(a)oppo.com>
Signed-off-by: Zhaoyang Huang <zhaoyang.huang(a)unisoc.com>
---
v2: introduce cpu in vmap_block to record the right CPU number
v3: use get_cpu/put_cpu to prevent schedule between core
v4: replace get_cpu/put_cpu by another API to avoid disabling preemption
---
---
mm/vmalloc.c | 21 +++++++++++++++------
1 file changed, 15 insertions(+), 6 deletions(-)
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 22aa63f4ef63..89eb034f4ac6 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2458,6 +2458,7 @@ struct vmap_block {
struct list_head free_list;
struct rcu_head rcu_head;
struct list_head purge;
+ unsigned int cpu;
};
/* Queue of free and dirty vmap blocks, for allocation and flushing purposes */
@@ -2585,8 +2586,15 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask)
free_vmap_area(va);
return ERR_PTR(err);
}
-
- vbq = raw_cpu_ptr(&vmap_block_queue);
+ /*
+ * list_add_tail_rcu could happened in another core
+ * rather than vb->cpu due to task migration, which
+ * is safe as list_add_tail_rcu will ensure the list's
+ * integrity together with list_for_each_rcu from read
+ * side.
+ */
+ vb->cpu = raw_smp_processor_id();
+ vbq = per_cpu_ptr(&vmap_block_queue, vb->cpu);
spin_lock(&vbq->lock);
list_add_tail_rcu(&vb->free_list, &vbq->free);
spin_unlock(&vbq->lock);
@@ -2614,9 +2622,10 @@ static void free_vmap_block(struct vmap_block *vb)
}
static bool purge_fragmented_block(struct vmap_block *vb,
- struct vmap_block_queue *vbq, struct list_head *purge_list,
- bool force_purge)
+ struct list_head *purge_list, bool force_purge)
{
+ struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, vb->cpu);
+
if (vb->free + vb->dirty != VMAP_BBMAP_BITS ||
vb->dirty == VMAP_BBMAP_BITS)
return false;
@@ -2664,7 +2673,7 @@ static void purge_fragmented_blocks(int cpu)
continue;
spin_lock(&vb->lock);
- purge_fragmented_block(vb, vbq, &purge, true);
+ purge_fragmented_block(vb, &purge, true);
spin_unlock(&vb->lock);
}
rcu_read_unlock();
@@ -2801,7 +2810,7 @@ static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush)
* not purgeable, check whether there is dirty
* space to be flushed.
*/
- if (!purge_fragmented_block(vb, vbq, &purge_list, false) &&
+ if (!purge_fragmented_block(vb, &purge_list, false) &&
vb->dirty_max && vb->dirty != VMAP_BBMAP_BITS) {
unsigned long va_start = vb->va->va_start;
unsigned long s, e;
--
2.25.1
The patch titled
Subject: mm: shmem: fix getting incorrect lruvec when replacing a shmem folio
has been added to the -mm mm-hotfixes-unstable branch. Its filename is
mm-shmem-fix-getting-incorrect-lruvec-when-replacing-a-shmem-folio.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche…
This patch will later appear in the mm-hotfixes-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Baolin Wang <baolin.wang(a)linux.alibaba.com>
Subject: mm: shmem: fix getting incorrect lruvec when replacing a shmem folio
Date: Thu, 13 Jun 2024 16:21:19 +0800
When testing shmem swapin, I encountered the warning below on my machine.
The reason is that replacing an old shmem folio with a new one causes
mem_cgroup_migrate() to clear the old folio's memcg data. As a result,
the old folio cannot get the correct memcg's lruvec needed to remove
itself from the LRU list when it is being freed. This could lead to
possible serious problems, such as LRU list crashes due to holding the
wrong LRU lock, and incorrect LRU statistics.
To fix this issue, we can fallback to use the mem_cgroup_replace_folio()
to replace the old shmem folio.
[ 5241.100311] page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x5d9960
[ 5241.100317] head: order:4 mapcount:0 entire_mapcount:0 nr_pages_mapped:0 pincount:0
[ 5241.100319] flags: 0x17fffe0000040068(uptodate|lru|head|swapbacked|node=0|zone=2|lastcpupid=0x3ffff)
[ 5241.100323] raw: 17fffe0000040068 fffffdffd6687948 fffffdffd69ae008 0000000000000000
[ 5241.100325] raw: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000
[ 5241.100326] head: 17fffe0000040068 fffffdffd6687948 fffffdffd69ae008 0000000000000000
[ 5241.100327] head: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000
[ 5241.100328] head: 17fffe0000000204 fffffdffd6665801 ffffffffffffffff 0000000000000000
[ 5241.100329] head: 0000000a00000010 0000000000000000 00000000ffffffff 0000000000000000
[ 5241.100330] page dumped because: VM_WARN_ON_ONCE_FOLIO(!memcg && !mem_cgroup_disabled())
[ 5241.100338] ------------[ cut here ]------------
[ 5241.100339] WARNING: CPU: 19 PID: 78402 at include/linux/memcontrol.h:775 folio_lruvec_lock_irqsave+0x140/0x150
[...]
[ 5241.100374] pc : folio_lruvec_lock_irqsave+0x140/0x150
[ 5241.100375] lr : folio_lruvec_lock_irqsave+0x138/0x150
[ 5241.100376] sp : ffff80008b38b930
[...]
[ 5241.100398] Call trace:
[ 5241.100399] folio_lruvec_lock_irqsave+0x140/0x150
[ 5241.100401] __page_cache_release+0x90/0x300
[ 5241.100404] __folio_put+0x50/0x108
[ 5241.100406] shmem_replace_folio+0x1b4/0x240
[ 5241.100409] shmem_swapin_folio+0x314/0x528
[ 5241.100411] shmem_get_folio_gfp+0x3b4/0x930
[ 5241.100412] shmem_fault+0x74/0x160
[ 5241.100414] __do_fault+0x40/0x218
[ 5241.100417] do_shared_fault+0x34/0x1b0
[ 5241.100419] do_fault+0x40/0x168
[ 5241.100420] handle_pte_fault+0x80/0x228
[ 5241.100422] __handle_mm_fault+0x1c4/0x440
[ 5241.100424] handle_mm_fault+0x60/0x1f0
[ 5241.100426] do_page_fault+0x120/0x488
[ 5241.100429] do_translation_fault+0x4c/0x68
[ 5241.100431] do_mem_abort+0x48/0xa0
[ 5241.100434] el0_da+0x38/0xc0
[ 5241.100436] el0t_64_sync_handler+0x68/0xc0
[ 5241.100437] el0t_64_sync+0x14c/0x150
[ 5241.100439] ---[ end trace 0000000000000000 ]---
Link: https://lkml.kernel.org/r/3c11000dd6c1df83015a8321a859e9775ebbc23e.17182661…
Fixes: 85ce2c517ade ("memcontrol: only transfer the memcg data for migration")
Signed-off-by: Baolin Wang <baolin.wang(a)linux.alibaba.com>
Cc: Hugh Dickins <hughd(a)google.com>
Cc: Johannes Weiner <hannes(a)cmpxchg.org>
Cc: Nhat Pham <nphamcs(a)gmail.com>
Cc: Shakeel Butt <shakeel.butt(a)linux.dev>
Cc: Michal Hocko <mhocko(a)suse.com>
Cc: Roman Gushchin <roman.gushchin(a)linux.dev>
Cc: Muchun Song <songmuchun(a)bytedance.com>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
mm/shmem.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/mm/shmem.c~mm-shmem-fix-getting-incorrect-lruvec-when-replacing-a-shmem-folio
+++ a/mm/shmem.c
@@ -1786,7 +1786,7 @@ static int shmem_replace_folio(struct fo
xa_lock_irq(&swap_mapping->i_pages);
error = shmem_replace_entry(swap_mapping, swap_index, old, new);
if (!error) {
- mem_cgroup_migrate(old, new);
+ mem_cgroup_replace_folio(old, new);
__lruvec_stat_mod_folio(new, NR_FILE_PAGES, 1);
__lruvec_stat_mod_folio(new, NR_SHMEM, 1);
__lruvec_stat_mod_folio(old, NR_FILE_PAGES, -1);
_
Patches currently in -mm which might be from baolin.wang(a)linux.alibaba.com are
mm-shmem-fix-getting-incorrect-lruvec-when-replacing-a-shmem-folio.patch
mm-memory-extend-finish_fault-to-support-large-folio.patch
mm-memory-extend-finish_fault-to-support-large-folio-fix.patch
mm-shmem-add-thp-validation-for-pmd-mapped-thp-related-statistics.patch
mm-shmem-add-multi-size-thp-sysfs-interface-for-anonymous-shmem.patch
mm-shmem-add-multi-size-thp-sysfs-interface-for-anonymous-shmem-fix.patch
mm-shmem-add-mthp-support-for-anonymous-shmem.patch
mm-shmem-add-mthp-size-alignment-in-shmem_get_unmapped_area.patch
mm-shmem-add-mthp-counters-for-anonymous-shmem.patch
The patch titled
Subject: mm: fix incorrect vbq reference in purge_fragmented_block
has been added to the -mm mm-hotfixes-unstable branch. Its filename is
mm-fix-incorrect-vbq-reference-in-purge_fragmented_block.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche…
This patch will later appear in the mm-hotfixes-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Zhaoyang Huang <zhaoyang.huang(a)unisoc.com>
Subject: mm: fix incorrect vbq reference in purge_fragmented_block
Date: Fri, 7 Jun 2024 10:31:16 +0800
vmalloc area runs out in our ARM64 system during an erofs test as
vm_map_ram failed[1]. By following the debug log, we find that
vm_map_ram()->vb_alloc() will allocate new vb->va which corresponding to
4MB vmalloc area as list_for_each_entry_rcu returns immediately when
vbq->free->next points to vbq->free. That is to say, 65536 times of page
fault after the list's broken will run out of the whole vmalloc area.
This should be introduced by one vbq->free->next point to vbq->free which
makes list_for_each_entry_rcu can not iterate the list and find the BUG.
[1]
PID: 1 TASK: ffffff80802b4e00 CPU: 6 COMMAND: "init"
#0 [ffffffc08006afe0] __switch_to at ffffffc08111d5cc
#1 [ffffffc08006b040] __schedule at ffffffc08111dde0
#2 [ffffffc08006b0a0] schedule at ffffffc08111e294
#3 [ffffffc08006b0d0] schedule_preempt_disabled at ffffffc08111e3f0
#4 [ffffffc08006b140] __mutex_lock at ffffffc08112068c
#5 [ffffffc08006b180] __mutex_lock_slowpath at ffffffc08111f8f8
#6 [ffffffc08006b1a0] mutex_lock at ffffffc08111f834
#7 [ffffffc08006b1d0] reclaim_and_purge_vmap_areas at ffffffc0803ebc3c
#8 [ffffffc08006b290] alloc_vmap_area at ffffffc0803e83fc
#9 [ffffffc08006b300] vm_map_ram at ffffffc0803e78c0
For detailed descri[ption of the broken list, please see
https://lore.kernel.org/all/20240531024820.5507-1-hailong.liu@oppo.com/
Link: https://lkml.kernel.org/r/20240607023116.1720640-1-zhaoyang.huang@unisoc.com
Fixes: fc1e0d980037 ("mm/vmalloc: prevent stale TLBs in fully utilized blocks")
Signed-off-by: Zhaoyang Huang <zhaoyang.huang(a)unisoc.com>
Suggested-by: Hailong.Liu <hailong.liu(a)oppo.com>
Reviewed-by: Uladzislau Rezki (Sony) <urezki(a)gmail.com>
Cc: Baoquan He <bhe(a)redhat.com>
Cc: Christoph Hellwig <hch(a)infradead.org>
Cc: Lorenzo Stoakes <lstoakes(a)gmail.com>
Cc: Thomas Gleixner <tglx(a)linutronix.de>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
mm/vmalloc.c | 21 +++++++++++++++------
1 file changed, 15 insertions(+), 6 deletions(-)
--- a/mm/vmalloc.c~mm-fix-incorrect-vbq-reference-in-purge_fragmented_block
+++ a/mm/vmalloc.c
@@ -2498,6 +2498,7 @@ struct vmap_block {
struct list_head free_list;
struct rcu_head rcu_head;
struct list_head purge;
+ unsigned int cpu;
};
/* Queue of free and dirty vmap blocks, for allocation and flushing purposes */
@@ -2625,8 +2626,15 @@ static void *new_vmap_block(unsigned int
free_vmap_area(va);
return ERR_PTR(err);
}
-
- vbq = raw_cpu_ptr(&vmap_block_queue);
+ /*
+ * list_add_tail_rcu could happened in another core
+ * rather than vb->cpu due to task migration, which
+ * is safe as list_add_tail_rcu will ensure the list's
+ * integrity together with list_for_each_rcu from read
+ * side.
+ */
+ vb->cpu = raw_smp_processor_id();
+ vbq = per_cpu_ptr(&vmap_block_queue, vb->cpu);
spin_lock(&vbq->lock);
list_add_tail_rcu(&vb->free_list, &vbq->free);
spin_unlock(&vbq->lock);
@@ -2654,9 +2662,10 @@ static void free_vmap_block(struct vmap_
}
static bool purge_fragmented_block(struct vmap_block *vb,
- struct vmap_block_queue *vbq, struct list_head *purge_list,
- bool force_purge)
+ struct list_head *purge_list, bool force_purge)
{
+ struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, vb->cpu);
+
if (vb->free + vb->dirty != VMAP_BBMAP_BITS ||
vb->dirty == VMAP_BBMAP_BITS)
return false;
@@ -2704,7 +2713,7 @@ static void purge_fragmented_blocks(int
continue;
spin_lock(&vb->lock);
- purge_fragmented_block(vb, vbq, &purge, true);
+ purge_fragmented_block(vb, &purge, true);
spin_unlock(&vb->lock);
}
rcu_read_unlock();
@@ -2841,7 +2850,7 @@ static void _vm_unmap_aliases(unsigned l
* not purgeable, check whether there is dirty
* space to be flushed.
*/
- if (!purge_fragmented_block(vb, vbq, &purge_list, false) &&
+ if (!purge_fragmented_block(vb, &purge_list, false) &&
vb->dirty_max && vb->dirty != VMAP_BBMAP_BITS) {
unsigned long va_start = vb->va->va_start;
unsigned long s, e;
_
Patches currently in -mm which might be from zhaoyang.huang(a)unisoc.com are
mm-fix-incorrect-vbq-reference-in-purge_fragmented_block.patch
mm-optimization-on-page-allocation-when-cma-enabled.patch