Patch "device-dax: switch to srcu, fix rcu_read_lock() vs pte allocation" has been added to the 4.9-stable tree

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 4.9-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-4.9 subdirectory.

If you, or anyone else, feels it should not be added to the stable tree, please let <[email protected]> know about it.

From: Dan Williams <[email protected]>
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 <[email protected]>

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.

---
 drivers/dax/Kconfig |    1 +
 drivers/dax/dax.c   |   13 +++++++------
 2 files changed, 8 insertions(+), 6 deletions(-)

@@ -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

@@ -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

@@ -437,7 +438,7 @@ 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;
 

@@ -445,9 +446,9 @@ 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;
 }

@@ -563,11 +564,11 @@ 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 [email protected] are

queue-4.9/device-dax-switch-to-srcu-fix-rcu_read_lock-vs-pte-allocation.patch queue-4.9/x86-mce-make-the-mce-notifier-a-blocking-one.patch