This is a note to let you know that I've just added the patch titled
device-dax: switch to srcu, fix rcu_read_lock() vs pte allocation
to the 4.10-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
device-dax-switch-to-srcu-fix-rcu_read_lock-vs-pte-allocation.patch
and it can be found in the queue-4.10 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From 956a4cd2c957acf638ff29951aabaa9d8e92bbc2 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@xxxxxxxxx>
Date: Fri, 7 Apr 2017 16:42:08 -0700
Subject: device-dax: switch to srcu, fix rcu_read_lock() vs pte allocation
From: Dan Williams <dan.j.williams@xxxxxxxxx>
commit 956a4cd2c957acf638ff29951aabaa9d8e92bbc2 upstream.
The following warning triggers with a new unit test that stresses the
device-dax interface.
===============================
[ ERR: suspicious RCU usage. ]
4.11.0-rc4+ #1049 Tainted: G O
-------------------------------
./include/linux/rcupdate.h:521 Illegal context switch in RCU read-side critical section!
other info that might help us debug this:
rcu_scheduler_active = 2, debug_locks = 0
2 locks held by fio/9070:
#0: (&mm->mmap_sem){++++++}, at: [<ffffffff8d0739d7>] __do_page_fault+0x167/0x4f0
#1: (rcu_read_lock){......}, at: [<ffffffffc03fbd02>] dax_dev_huge_fault+0x32/0x620 [dax]
Call Trace:
dump_stack+0x86/0xc3
lockdep_rcu_suspicious+0xd7/0x110
___might_sleep+0xac/0x250
__might_sleep+0x4a/0x80
__alloc_pages_nodemask+0x23a/0x360
alloc_pages_current+0xa1/0x1f0
pte_alloc_one+0x17/0x80
__pte_alloc+0x1e/0x120
__get_locked_pte+0x1bf/0x1d0
insert_pfn.isra.70+0x3a/0x100
? lookup_memtype+0xa6/0xd0
vm_insert_mixed+0x64/0x90
dax_dev_huge_fault+0x520/0x620 [dax]
? dax_dev_huge_fault+0x32/0x620 [dax]
dax_dev_fault+0x10/0x20 [dax]
__do_fault+0x1e/0x140
__handle_mm_fault+0x9af/0x10d0
handle_mm_fault+0x16d/0x370
? handle_mm_fault+0x47/0x370
__do_page_fault+0x28c/0x4f0
trace_do_page_fault+0x58/0x2a0
do_async_page_fault+0x1a/0xa0
async_page_fault+0x28/0x30
Inserting a page table entry may trigger an allocation while we are
holding a read lock to keep the device instance alive for the duration
of the fault. Use srcu for this keep-alive protection.
Fixes: dee410792419 ("/dev/dax, core: file operations and dax-mmap")
Signed-off-by: Dan Williams <dan.j.williams@xxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
drivers/dax/Kconfig | 1 +
drivers/dax/dax.c | 13 +++++++------
2 files changed, 8 insertions(+), 6 deletions(-)
--- a/drivers/dax/Kconfig
+++ b/drivers/dax/Kconfig
@@ -2,6 +2,7 @@ menuconfig DEV_DAX
tristate "DAX: direct access to differentiated memory"
default m if NVDIMM_DAX
depends on TRANSPARENT_HUGEPAGE
+ select SRCU
help
Support raw access to differentiated (persistence, bandwidth,
latency...) memory via an mmap(2) capable character
--- a/drivers/dax/dax.c
+++ b/drivers/dax/dax.c
@@ -24,6 +24,7 @@
#include "dax.h"
static dev_t dax_devt;
+DEFINE_STATIC_SRCU(dax_srcu);
static struct class *dax_class;
static DEFINE_IDA(dax_minor_ida);
static int nr_dax = CONFIG_NR_DEV_DAX;
@@ -59,7 +60,7 @@ struct dax_region {
* @region - parent region
* @dev - device backing the character device
* @cdev - core chardev data
- * @alive - !alive + rcu grace period == no new mappings can be established
+ * @alive - !alive + srcu grace period == no new mappings can be established
* @id - child id in the region
* @num_resources - number of physical address extents in this device
* @res - array of physical address ranges
@@ -530,7 +531,7 @@ static int __dax_dev_pmd_fault(struct da
static int dax_dev_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
pmd_t *pmd, unsigned int flags)
{
- int rc;
+ int rc, id;
struct file *filp = vma->vm_file;
struct dax_dev *dax_dev = filp->private_data;
@@ -538,9 +539,9 @@ static int dax_dev_pmd_fault(struct vm_a
current->comm, (flags & FAULT_FLAG_WRITE)
? "write" : "read", vma->vm_start, vma->vm_end);
- rcu_read_lock();
+ id = srcu_read_lock(&dax_srcu);
rc = __dax_dev_pmd_fault(dax_dev, vma, addr, pmd, flags);
- rcu_read_unlock();
+ srcu_read_unlock(&dax_srcu, id);
return rc;
}
@@ -656,11 +657,11 @@ static void unregister_dax_dev(void *dev
* Note, rcu is not protecting the liveness of dax_dev, rcu is
* ensuring that any fault handlers that might have seen
* dax_dev->alive == true, have completed. Any fault handlers
- * that start after synchronize_rcu() has started will abort
+ * that start after synchronize_srcu() has started will abort
* upon seeing dax_dev->alive == false.
*/
dax_dev->alive = false;
- synchronize_rcu();
+ synchronize_srcu(&dax_srcu);
unmap_mapping_range(dax_dev->inode->i_mapping, 0, 0, 1);
cdev_del(cdev);
device_unregister(dev);
Patches currently in stable-queue which might be from dan.j.williams@xxxxxxxxx are
queue-4.10/device-dax-switch-to-srcu-fix-rcu_read_lock-vs-pte-allocation.patch
queue-4.10/x86-mce-make-the-mce-notifier-a-blocking-one.patch