From: yulei.kernel@gmail.com
To: linux-mm@kvack.org, akpm@linux-foundation.org,
linux-fsdevel@vger.kernel.org, kvm@vger.kernel.org,
linux-kernel@vger.kernel.org, naoya.horiguchi@nec.com,
viro@zeniv.linux.org.uk, pbonzini@redhat.com
Cc: joao.m.martins@oracle.com, rdunlap@infradead.org,
sean.j.christopherson@intel.com, xiaoguangrong.eric@gmail.com,
kernellwp@gmail.com, lihaiwei.kernel@gmail.com,
Yulei Zhang <yuleixzhang@tencent.com>,
Haiwei Li <lihaiwei@tencent.com>
Subject: [RFC V2 31/37] dmem: introduce mce handler
Date: Mon, 7 Dec 2020 19:31:24 +0800 [thread overview]
Message-ID: <6a5471107b81ee999f776547f2fccb045967701e.1607332046.git.yuleixzhang@tencent.com> (raw)
In-Reply-To: <cover.1607332046.git.yuleixzhang@tencent.com>
From: Yulei Zhang <yuleixzhang@tencent.com>
dmem handle the mce if the pfn belongs to dmem when mce occurs.
1. check whether the pfn is handled by dmem. return if true.
2. mark the pfn in a new error bitmap defined in page.
3. a series of mechanism to ensure that the mce pfn is not allocated.
Signed-off-by: Haiwei Li <lihaiwei@tencent.com>
Signed-off-by: Yulei Zhang <yuleixzhang@tencent.com>
---
include/linux/dmem.h | 6 +++
include/trace/events/dmem.h | 17 ++++++++
mm/dmem.c | 103 +++++++++++++++++++++++++++++++-------------
mm/memory-failure.c | 6 +++
4 files changed, 102 insertions(+), 30 deletions(-)
diff --git a/include/linux/dmem.h b/include/linux/dmem.h
index 59d3ef14..cd17a91 100644
--- a/include/linux/dmem.h
+++ b/include/linux/dmem.h
@@ -21,6 +21,8 @@
void dmem_free_pages(phys_addr_t addr, unsigned int dpages_nr);
bool is_dmem_pfn(unsigned long pfn);
#define dmem_free_page(addr) dmem_free_pages(addr, 1)
+
+bool dmem_memory_failure(unsigned long pfn, int flags);
#else
static inline int dmem_reserve_init(void)
{
@@ -32,5 +34,9 @@ static inline bool is_dmem_pfn(unsigned long pfn)
return 0;
}
+static inline bool dmem_memory_failure(unsigned long pfn, int flags)
+{
+ return false;
+}
#endif
#endif /* _LINUX_DMEM_H */
diff --git a/include/trace/events/dmem.h b/include/trace/events/dmem.h
index 10d1b90..f8eeb3c 100644
--- a/include/trace/events/dmem.h
+++ b/include/trace/events/dmem.h
@@ -62,6 +62,23 @@
TP_printk("addr %#lx dpages_nr %d", (unsigned long)__entry->addr,
__entry->dpages_nr)
);
+
+TRACE_EVENT(dmem_memory_failure,
+ TP_PROTO(unsigned long pfn, bool used),
+ TP_ARGS(pfn, used),
+
+ TP_STRUCT__entry(
+ __field(unsigned long, pfn)
+ __field(bool, used)
+ ),
+
+ TP_fast_assign(
+ __entry->pfn = pfn;
+ __entry->used = used;
+ ),
+
+ TP_printk("pfn=%#lx used=%d", __entry->pfn, __entry->used)
+);
#endif
/* This part must be outside protection */
diff --git a/mm/dmem.c b/mm/dmem.c
index 50cdff9..16438db 100644
--- a/mm/dmem.c
+++ b/mm/dmem.c
@@ -431,6 +431,41 @@ static void __init dmem_uinit(void)
dmem_pool.registered_pages = 0;
}
+/* set or clear corresponding bit on allocation bitmap based on error bitmap */
+static unsigned long dregion_alloc_bitmap_set_clear(struct dmem_region *dregion,
+ bool set)
+{
+ unsigned long pos_pfn, pos_offset;
+ unsigned long valid_pages, mce_dpages = 0;
+ phys_addr_t dpage, reserved_start_pfn;
+
+ reserved_start_pfn = __phys_to_pfn(dregion->reserved_start_addr);
+
+ valid_pages = dpage_to_pfn(dregion->dpage_end_pfn) - reserved_start_pfn;
+ pos_offset = dpage_to_pfn(dregion->dpage_start_pfn)
+ - reserved_start_pfn;
+try_set:
+ pos_pfn = find_next_bit(dregion->error_bitmap, valid_pages, pos_offset);
+
+ if (pos_pfn >= valid_pages)
+ return mce_dpages;
+ mce_dpages++;
+ dpage = pfn_to_dpage(pos_pfn + reserved_start_pfn);
+ if (set)
+ WARN_ON(__test_and_set_bit(dpage - dregion->dpage_start_pfn,
+ dregion->bitmap));
+ else
+ WARN_ON(!__test_and_clear_bit(dpage - dregion->dpage_start_pfn,
+ dregion->bitmap));
+ pos_offset = dpage_to_pfn(dpage + 1) - reserved_start_pfn;
+ goto try_set;
+}
+
+static unsigned long dmem_region_mark_mce_dpages(struct dmem_region *dregion)
+{
+ return dregion_alloc_bitmap_set_clear(dregion, true);
+}
+
static int __init dmem_region_init(struct dmem_region *dregion)
{
unsigned long *bitmap, nr_pages;
@@ -514,6 +549,8 @@ static int dmem_alloc_region_init(struct dmem_region *dregion,
dregion->dpage_start_pfn = start;
dregion->dpage_end_pfn = end;
+ *dpages -= dmem_region_mark_mce_dpages(dregion);
+
dmem_pool.unaligned_pages += __phys_to_pfn((dpage_to_phys(start)
- dregion->reserved_start_addr));
dmem_pool.unaligned_pages += __phys_to_pfn(dregion->reserved_end_addr
@@ -558,36 +595,6 @@ static bool dmem_dpage_is_error(struct dmem_region *dregion, phys_addr_t dpage)
return err_num;
}
-/* set or clear corresponding bit on allocation bitmap based on error bitmap */
-static unsigned long dregion_alloc_bitmap_set_clear(struct dmem_region *dregion,
- bool set)
-{
- unsigned long pos_pfn, pos_offset;
- unsigned long valid_pages, mce_dpages = 0;
- phys_addr_t dpage, reserved_start_pfn;
-
- reserved_start_pfn = __phys_to_pfn(dregion->reserved_start_addr);
-
- valid_pages = dpage_to_pfn(dregion->dpage_end_pfn) - reserved_start_pfn;
- pos_offset = dpage_to_pfn(dregion->dpage_start_pfn)
- - reserved_start_pfn;
-try_set:
- pos_pfn = find_next_bit(dregion->error_bitmap, valid_pages, pos_offset);
-
- if (pos_pfn >= valid_pages)
- return mce_dpages;
- mce_dpages++;
- dpage = pfn_to_dpage(pos_pfn + reserved_start_pfn);
- if (set)
- WARN_ON(__test_and_set_bit(dpage - dregion->dpage_start_pfn,
- dregion->bitmap));
- else
- WARN_ON(!__test_and_clear_bit(dpage - dregion->dpage_start_pfn,
- dregion->bitmap));
- pos_offset = dpage_to_pfn(dpage + 1) - reserved_start_pfn;
- goto try_set;
-}
-
static void dmem_uinit_check_alloc_bitmap(struct dmem_region *dregion)
{
unsigned long dpages, size;
@@ -989,6 +996,42 @@ void dmem_free_pages(phys_addr_t addr, unsigned int dpages_nr)
}
EXPORT_SYMBOL(dmem_free_pages);
+bool dmem_memory_failure(unsigned long pfn, int flags)
+{
+ struct dmem_region *dregion;
+ struct dmem_node *pdnode = NULL;
+ u64 pos;
+ phys_addr_t addr = __pfn_to_phys(pfn);
+ bool used = false;
+
+ dregion = find_dmem_region(addr, &pdnode);
+ if (!dregion)
+ return false;
+
+ WARN_ON(!pdnode || !dregion->error_bitmap);
+
+ mutex_lock(&dmem_pool.lock);
+ pos = pfn - __phys_to_pfn(dregion->reserved_start_addr);
+ if (__test_and_set_bit(pos, dregion->error_bitmap))
+ goto out;
+
+ if (!dregion->bitmap || pfn < dpage_to_pfn(dregion->dpage_start_pfn) ||
+ pfn >= dpage_to_pfn(dregion->dpage_end_pfn))
+ goto out;
+
+ pos = phys_to_dpage(addr) - dregion->dpage_start_pfn;
+ if (__test_and_set_bit(pos, dregion->bitmap)) {
+ used = true;
+ } else {
+ pr_info("MCE: free dpage, mark %#lx disabled in dmem\n", pfn);
+ dnode_count_free_dpages(pdnode, -1);
+ }
+out:
+ trace_dmem_memory_failure(pfn, used);
+ mutex_unlock(&dmem_pool.lock);
+ return true;
+}
+
bool is_dmem_pfn(unsigned long pfn)
{
struct dmem_node *dnode;
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 5d880d4..dda45d2 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -35,6 +35,7 @@
*/
#include <linux/kernel.h>
#include <linux/mm.h>
+#include <linux/dmem.h>
#include <linux/page-flags.h>
#include <linux/kernel-page-flags.h>
#include <linux/sched/signal.h>
@@ -1323,6 +1324,11 @@ int memory_failure(unsigned long pfn, int flags)
if (!sysctl_memory_failure_recovery)
panic("Memory failure on page %lx", pfn);
+ if (dmem_memory_failure(pfn, flags)) {
+ pr_info("MCE %#lx: handled by dmem\n", pfn);
+ return 0;
+ }
+
p = pfn_to_online_page(pfn);
if (!p) {
if (pfn_valid(pfn)) {
--
1.8.3.1
next prev parent reply other threads:[~2020-12-07 11:35 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-12-07 11:30 [RFC V2 00/37] Enhance memory utilization with DMEMFS yulei.kernel
2020-12-07 11:30 ` [RFC V2 01/37] fs: introduce dmemfs module yulei.kernel
2020-12-07 11:30 ` [RFC V2 02/37] mm: support direct memory reservation yulei.kernel
2020-12-07 11:30 ` [RFC V2 03/37] dmem: implement dmem memory management yulei.kernel
2020-12-07 11:30 ` [RFC V2 04/37] dmem: let pat recognize dmem yulei.kernel
2020-12-07 11:30 ` [RFC V2 05/37] dmemfs: support mmap for dmemfs yulei.kernel
2020-12-07 11:30 ` [RFC V2 06/37] dmemfs: support truncating inode down yulei.kernel
2020-12-07 11:31 ` [RFC V2 07/37] dmem: trace core functions yulei.kernel
2020-12-07 11:31 ` [RFC V2 08/37] dmem: show some statistic in debugfs yulei.kernel
2020-12-07 11:31 ` [RFC V2 09/37] dmemfs: support remote access yulei.kernel
2020-12-07 11:31 ` [RFC V2 10/37] dmemfs: introduce max_alloc_try_dpages parameter yulei.kernel
2020-12-07 11:31 ` [RFC V2 11/37] mm: export mempolicy interfaces to serve dmem allocator yulei.kernel
2020-12-07 11:31 ` [RFC V2 12/37] dmem: introduce mempolicy support yulei.kernel
2020-12-07 11:31 ` [RFC V2 13/37] mm, dmem: introduce PFN_DMEM and pfn_t_dmem yulei.kernel
2020-12-07 11:31 ` [RFC V2 14/37] mm, dmem: differentiate dmem-pmd and thp-pmd yulei.kernel
2020-12-07 11:31 ` [RFC V2 15/37] mm: add pmd_special() check for pmd_trans_huge_lock() yulei.kernel
2020-12-07 11:31 ` [RFC V2 16/37] dmemfs: introduce ->split() to dmemfs_vm_ops yulei.kernel
2020-12-07 11:31 ` [RFC V2 17/37] mm, dmemfs: support unmap_page_range() for dmemfs pmd yulei.kernel
2020-12-07 11:31 ` [RFC V2 18/37] mm: follow_pmd_mask() for dmem huge pmd yulei.kernel
2020-12-07 11:31 ` [RFC V2 19/37] mm: gup_huge_pmd() " yulei.kernel
2020-12-07 11:31 ` [RFC V2 20/37] mm: support dmem huge pmd for vmf_insert_pfn_pmd() yulei.kernel
2020-12-07 11:31 ` [RFC V2 21/37] mm: support dmem huge pmd for follow_pfn() yulei.kernel
2020-12-07 11:31 ` [RFC V2 22/37] kvm, x86: Distinguish dmemfs page from mmio page yulei.kernel
2020-12-07 11:31 ` [RFC V2 23/37] kvm, x86: introduce VM_DMEM for syscall support usage yulei.kernel
2020-12-07 11:31 ` [RFC V2 24/37] dmemfs: support hugepage for dmemfs yulei.kernel
2020-12-07 11:31 ` [RFC V2 25/37] mm, x86, dmem: fix estimation of reserved page for vaddr_get_pfn() yulei.kernel
2020-12-07 11:31 ` [RFC V2 26/37] mm, dmem: introduce pud_special() for dmem huge pud support yulei.kernel
2020-12-07 11:31 ` [RFC V2 27/37] mm: add pud_special() check to support dmem huge pud yulei.kernel
2020-12-07 11:31 ` [RFC V2 28/37] mm, dmemfs: support huge_fault() for dmemfs yulei.kernel
2020-12-07 11:31 ` [RFC V2 29/37] mm: add follow_pte_pud() to support huge pud look up yulei.kernel
2020-12-07 11:31 ` [RFC V2 30/37] dmem: introduce dmem_bitmap_alloc() and dmem_bitmap_free() yulei.kernel
2020-12-07 11:31 ` yulei.kernel [this message]
2020-12-07 11:31 ` [RFC V2 32/37] mm, dmemfs: register and handle the dmem mce yulei.kernel
2020-12-07 11:31 ` [RFC V2 33/37] kvm, x86: enable record_steal_time for dmem yulei.kernel
2020-12-07 11:31 ` [RFC V2 34/37] dmem: add dmem unit tests yulei.kernel
2020-12-07 11:31 ` [RFC V2 35/37] mm, dmem: introduce dregion->memmap for dmem yulei.kernel
2020-12-07 11:31 ` [RFC V2 36/37] vfio: support dmempage refcount for vfio yulei.kernel
2020-12-07 11:31 ` [RFC V2 37/37] Add documentation for dmemfs yulei.kernel
2020-12-24 18:27 ` Randy Dunlap
2020-12-07 12:02 ` [RFC V2 00/37] Enhance memory utilization with DMEMFS David Hildenbrand
2020-12-07 19:32 ` Dan Williams
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=6a5471107b81ee999f776547f2fccb045967701e.1607332046.git.yuleixzhang@tencent.com \
--to=yulei.kernel@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=joao.m.martins@oracle.com \
--cc=kernellwp@gmail.com \
--cc=kvm@vger.kernel.org \
--cc=lihaiwei.kernel@gmail.com \
--cc=lihaiwei@tencent.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=naoya.horiguchi@nec.com \
--cc=pbonzini@redhat.com \
--cc=rdunlap@infradead.org \
--cc=sean.j.christopherson@intel.com \
--cc=viro@zeniv.linux.org.uk \
--cc=xiaoguangrong.eric@gmail.com \
--cc=yuleixzhang@tencent.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox