mm/zswap: Do not disable preemption in zswap_frontswap_store()

[ Upstream commit 4e4cf4be79635e67144632d9135286381acbc95a ]

Zswap causes "BUG: scheduling while atomic" by blocking on a rt_spin_lock() with
preemption disabled. The preemption is disabled by get_cpu_var() in
zswap_frontswap_store() to protect the access of the zswap_dstmem percpu variable.

Use get_locked_var() to protect the percpu zswap_dstmem variable, making the
code preemptive.

As get_cpu_ptr() also disables preemption, replace it by this_cpu_ptr() and
remove the counterpart put_cpu_ptr().

Steps to Reproduce:

    1. # grubby --args "zswap.enabled=1" --update-kernel DEFAULT
    2. # reboot
    3. Calculate the amount o memory to be used by the test:
       ---> grep MemAvailable /proc/meminfo
       ---> Add 25% ~ 50% to that value
    4. # stress --vm 1 --vm-bytes ${MemAvailable+25%} --timeout 240s

Usually, in less than 5 minutes the backtrace listed below appears, followed
by a kernel panic:

| BUG: scheduling while atomic: kswapd1/181/0x00000002
|
| Preemption disabled at:
| [<ffffffff8b2a6cda>] zswap_frontswap_store+0x21a/0x6e1
|
| Kernel panic - not syncing: scheduling while atomic
| CPU: 14 PID: 181 Comm: kswapd1 Kdump: loaded Not tainted 5.0.14-rt9 #1
| Hardware name: AMD Pence/Pence, BIOS WPN2321X_Weekly_12_03_21 03/19/2012
| Call Trace:
|  panic+0x106/0x2a7
|  __schedule_bug.cold+0x3f/0x51
|  __schedule+0x5cb/0x6f0
|  schedule+0x43/0xd0
|  rt_spin_lock_slowlock_locked+0x114/0x2b0
|  rt_spin_lock_slowlock+0x51/0x80
|  zbud_alloc+0x1da/0x2d0
|  zswap_frontswap_store+0x31a/0x6e1
|  __frontswap_store+0xab/0x130
|  swap_writepage+0x39/0x70
|  pageout.isra.0+0xe3/0x320
|  shrink_page_list+0xa8e/0xd10
|  shrink_inactive_list+0x251/0x840
|  shrink_node_memcg+0x213/0x770
|  shrink_node+0xd9/0x450
|  balance_pgdat+0x2d5/0x510
|  kswapd+0x218/0x470
|  kthread+0xfb/0x130
|  ret_from_fork+0x27/0x50

Cc: stable-rt@vger.kernel.org
Reported-by: Ping Fang <pifang@redhat.com>
Signed-off-by: Luis Claudio R. Goncalves <lgoncalv@redhat.com>
Reviewed-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>

1 files changed, 7 insertions, 5 deletions

diff --git a/mm/zswap.c b/mm/zswap.c
index cd91fd9d96b8..420225d3ff0b 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -27,6 +27,7 @@
 #include <linux/highmem.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/locallock.h>
 #include <linux/types.h>
 #include <linux/atomic.h>
 #include <linux/frontswap.h>
@@ -990,6 +991,8 @@ static void zswap_fill_page(void *ptr, unsigned long value)
 	memset_l(page, value, PAGE_SIZE / sizeof(unsigned long));
 }
 
+/* protect zswap_dstmem from concurrency */
+static DEFINE_LOCAL_IRQ_LOCK(zswap_dstmem_lock);
 /*********************************
 * frontswap hooks
 **********************************/
@@ -1066,12 +1069,11 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
 	}
 
 	/* compress */
-	dst = get_cpu_var(zswap_dstmem);
-	tfm = *get_cpu_ptr(entry->pool->tfm);
+	dst = get_locked_var(zswap_dstmem_lock, zswap_dstmem);
+	tfm = *this_cpu_ptr(entry->pool->tfm);
 	src = kmap_atomic(page);
 	ret = crypto_comp_compress(tfm, src, PAGE_SIZE, dst, &dlen);
 	kunmap_atomic(src);
-	put_cpu_ptr(entry->pool->tfm);
 	if (ret) {
 		ret = -EINVAL;
 		goto put_dstmem;
@@ -1094,7 +1096,7 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
 	memcpy(buf, &zhdr, hlen);
 	memcpy(buf + hlen, dst, dlen);
 	zpool_unmap_handle(entry->pool->zpool, handle);
-	put_cpu_var(zswap_dstmem);
+	put_locked_var(zswap_dstmem_lock, zswap_dstmem);
 
 	/* populate entry */
 	entry->offset = offset;
@@ -1122,7 +1124,7 @@ insert_entry:
 	return 0;
 
 put_dstmem:
-	put_cpu_var(zswap_dstmem);
+	put_locked_var(zswap_dstmem_lock, zswap_dstmem);
 	zswap_pool_put(entry->pool);
 freepage:
 	zswap_entry_cache_free(entry);