[PATCH 5.15 128/230] mm/hwpoison: avoid the impact of hwpoison_filter() return value on mce handler

From: Greg Kroah-Hartman
Date: Mon Jul 11 2022 - 05:52:35 EST


From: luofei <luofei@xxxxxxxxxxxx>

[ Upstream commit d1fe111fb62a1cf0446a2919f5effbb33ad0702c ]

When the hwpoison page meets the filter conditions, it should not be
regarded as successful memory_failure() processing for mce handler, but
should return a distinct value, otherwise mce handler regards the error
page has been identified and isolated, which may lead to calling
set_mce_nospec() to change page attribute, etc.

Here memory_failure() return -EOPNOTSUPP to indicate that the error
event is filtered, mce handler should not take any action for this
situation and hwpoison injector should treat as correct.

Link: https://lkml.kernel.org/r/20220223082135.2769649-1-luofei@xxxxxxxxxxxx
Signed-off-by: luofei <luofei@xxxxxxxxxxxx>
Acked-by: Borislav Petkov <bp@xxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: H. Peter Anvin <hpa@xxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Miaohe Lin <linmiaohe@xxxxxxxxxx>
Cc: Naoya Horiguchi <naoya.horiguchi@xxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Tony Luck <tony.luck@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
arch/x86/kernel/cpu/mce/core.c | 8 +++++---
drivers/base/memory.c | 2 ++
mm/hwpoison-inject.c | 3 ++-
mm/madvise.c | 2 ++
mm/memory-failure.c | 9 +++++++--
5 files changed, 18 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index e23e74e2f928..848cfb013f58 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1297,10 +1297,12 @@ static void kill_me_maybe(struct callback_head *cb)

/*
* -EHWPOISON from memory_failure() means that it already sent SIGBUS
- * to the current process with the proper error info, so no need to
- * send SIGBUS here again.
+ * to the current process with the proper error info,
+ * -EOPNOTSUPP means hwpoison_filter() filtered the error event,
+ *
+ * In both cases, no further processing is required.
*/
- if (ret == -EHWPOISON)
+ if (ret == -EHWPOISON || ret == -EOPNOTSUPP)
return;

if (p->mce_vaddr != (void __user *)-1l) {
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index c0d501a3a714..c778d1df7455 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -555,6 +555,8 @@ static ssize_t hard_offline_page_store(struct device *dev,
return -EINVAL;
pfn >>= PAGE_SHIFT;
ret = memory_failure(pfn, 0);
+ if (ret == -EOPNOTSUPP)
+ ret = 0;
return ret ? ret : count;
}

diff --git a/mm/hwpoison-inject.c b/mm/hwpoison-inject.c
index aff4d27ec235..a1d6fc3c78b9 100644
--- a/mm/hwpoison-inject.c
+++ b/mm/hwpoison-inject.c
@@ -48,7 +48,8 @@ static int hwpoison_inject(void *data, u64 val)

inject:
pr_info("Injecting memory failure at pfn %#lx\n", pfn);
- return memory_failure(pfn, 0);
+ err = memory_failure(pfn, 0);
+ return (err == -EOPNOTSUPP) ? 0 : err;
}

static int hwpoison_unpoison(void *data, u64 val)
diff --git a/mm/madvise.c b/mm/madvise.c
index 8e5ca01a6cc0..882767d58c27 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -968,6 +968,8 @@ static int madvise_inject_error(int behavior,
pr_info("Injecting memory failure for pfn %#lx at process virtual address %#lx\n",
pfn, start);
ret = memory_failure(pfn, MF_COUNT_INCREASED);
+ if (ret == -EOPNOTSUPP)
+ ret = 0;
}

if (ret)
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index e6425d959fa9..5664bafd5e77 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1444,7 +1444,7 @@ static int memory_failure_hugetlb(unsigned long pfn, int flags)
if (TestClearPageHWPoison(head))
num_poisoned_pages_dec();
unlock_page(head);
- return 0;
+ return -EOPNOTSUPP;
}
unlock_page(head);
res = MF_FAILED;
@@ -1525,7 +1525,7 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
goto out;

if (hwpoison_filter(page)) {
- rc = 0;
+ rc = -EOPNOTSUPP;
goto unlock;
}

@@ -1594,6 +1594,10 @@ static DEFINE_MUTEX(mf_mutex);
*
* Must run in process context (e.g. a work queue) with interrupts
* enabled and no spinlocks hold.
+ *
+ * Return: 0 for successfully handled the memory error,
+ * -EOPNOTSUPP for memory_filter() filtered the error event,
+ * < 0(except -EOPNOTSUPP) on failure.
*/
int memory_failure(unsigned long pfn, int flags)
{
@@ -1742,6 +1746,7 @@ int memory_failure(unsigned long pfn, int flags)
num_poisoned_pages_dec();
unlock_page(p);
put_page(p);
+ res = -EOPNOTSUPP;
goto unlock_mutex;
}

--
2.35.1