LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	stable@vger.kernel.org, Vitaly Wool <vitaly.vul@sony.com>,
	Guenter Roeck <linux@roeck-us.net>,
	Oleksiy.Avramchenko@sony.com,
	Matthew Wilcox <mawilcox@microsoft.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Linus Torvalds <torvalds@linux-foundation.org>
Subject: [PATCH 4.16 31/72] z3fold: fix reclaim lock-ups
Date: Mon, 14 May 2018 08:48:48 +0200	[thread overview]
Message-ID: <20180514064824.416301035@linuxfoundation.org> (raw)
In-Reply-To: <20180514064823.033169170@linuxfoundation.org>

4.16-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Vitaly Wool <vitalywool@gmail.com>

commit 6098d7e136692f9c6e23ae362c62ec822343e4d5 upstream.

Do not try to optimize in-page object layout while the page is under
reclaim.  This fixes lock-ups on reclaim and improves reclaim
performance at the same time.

[akpm@linux-foundation.org: coding-style fixes]
Link: http://lkml.kernel.org/r/20180430125800.444cae9706489f412ad12621@gmail.com
Signed-off-by: Vitaly Wool <vitaly.vul@sony.com>
Reported-by: Guenter Roeck <linux@roeck-us.net>
Tested-by: Guenter Roeck <linux@roeck-us.net>
Cc: <Oleksiy.Avramchenko@sony.com>
Cc: Matthew Wilcox <mawilcox@microsoft.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

---
 mm/z3fold.c |   42 ++++++++++++++++++++++++++++++------------
 1 file changed, 30 insertions(+), 12 deletions(-)

--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -144,7 +144,8 @@ enum z3fold_page_flags {
 	PAGE_HEADLESS = 0,
 	MIDDLE_CHUNK_MAPPED,
 	NEEDS_COMPACTING,
-	PAGE_STALE
+	PAGE_STALE,
+	UNDER_RECLAIM
 };
 
 /*****************
@@ -173,6 +174,7 @@ static struct z3fold_header *init_z3fold
 	clear_bit(MIDDLE_CHUNK_MAPPED, &page->private);
 	clear_bit(NEEDS_COMPACTING, &page->private);
 	clear_bit(PAGE_STALE, &page->private);
+	clear_bit(UNDER_RECLAIM, &page->private);
 
 	spin_lock_init(&zhdr->page_lock);
 	kref_init(&zhdr->refcount);
@@ -748,6 +750,10 @@ static void z3fold_free(struct z3fold_po
 		atomic64_dec(&pool->pages_nr);
 		return;
 	}
+	if (test_bit(UNDER_RECLAIM, &page->private)) {
+		z3fold_page_unlock(zhdr);
+		return;
+	}
 	if (test_and_set_bit(NEEDS_COMPACTING, &page->private)) {
 		z3fold_page_unlock(zhdr);
 		return;
@@ -832,6 +838,8 @@ static int z3fold_reclaim_page(struct z3
 			kref_get(&zhdr->refcount);
 			list_del_init(&zhdr->buddy);
 			zhdr->cpu = -1;
+			set_bit(UNDER_RECLAIM, &page->private);
+			break;
 		}
 
 		list_del_init(&page->lru);
@@ -879,25 +887,35 @@ static int z3fold_reclaim_page(struct z3
 				goto next;
 		}
 next:
-		spin_lock(&pool->lock);
 		if (test_bit(PAGE_HEADLESS, &page->private)) {
 			if (ret == 0) {
-				spin_unlock(&pool->lock);
 				free_z3fold_page(page);
 				return 0;
 			}
-		} else if (kref_put(&zhdr->refcount, release_z3fold_page)) {
-			atomic64_dec(&pool->pages_nr);
+			spin_lock(&pool->lock);
+			list_add(&page->lru, &pool->lru);
+			spin_unlock(&pool->lock);
+		} else {
+			z3fold_page_lock(zhdr);
+			clear_bit(UNDER_RECLAIM, &page->private);
+			if (kref_put(&zhdr->refcount,
+					release_z3fold_page_locked)) {
+				atomic64_dec(&pool->pages_nr);
+				return 0;
+			}
+			/*
+			 * if we are here, the page is still not completely
+			 * free. Take the global pool lock then to be able
+			 * to add it back to the lru list
+			 */
+			spin_lock(&pool->lock);
+			list_add(&page->lru, &pool->lru);
 			spin_unlock(&pool->lock);
-			return 0;
+			z3fold_page_unlock(zhdr);
 		}
 
-		/*
-		 * Add to the beginning of LRU.
-		 * Pool lock has to be kept here to ensure the page has
-		 * not already been released
-		 */
-		list_add(&page->lru, &pool->lru);
+		/* We started off locked to we need to lock the pool back */
+		spin_lock(&pool->lock);
 	}
 	spin_unlock(&pool->lock);
 	return -EAGAIN;

  parent reply	other threads:[~2018-05-14  7:00 UTC|newest]

Thread overview: 86+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-05-14  6:48 [PATCH 4.16 00/72] 4.16.9-stable review Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 01/72] ipvs: fix rtnl_lock lockups caused by start_sync_thread Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 02/72] netfilter: ebtables: dont attempt to allocate 0-sized compat array Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 03/72] clk: ti: fix flag space conflict with clkctrl clocks Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 04/72] kcm: Call strp_stop before strp_done in kcm_attach Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 05/72] rds: tcp: must use spin_lock_irq* and not spin_lock_bh with rds_tcp_conn_lock Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 06/72] crypto: af_alg - fix possible uninit-value in alg_bind() Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 07/72] netlink: fix uninit-value in netlink_sendmsg Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 08/72] net: fix rtnh_ok() Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 09/72] net: initialize skb->peeked when cloning Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 10/72] net: fix uninit-value in __hw_addr_add_ex() Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 11/72] dccp: initialize ireq->ir_mark Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 12/72] ipv4: fix uninit-value in ip_route_output_key_hash_rcu() Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 13/72] soreuseport: initialise timewait reuseport field Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 14/72] inetpeer: fix uninit-value in inet_getpeer Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 15/72] bpf/tracing: fix a deadlock in perf_event_detach_bpf_prog Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 16/72] memcg: fix per_node_info cleanup Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 17/72] perf: Remove superfluous allocation error check Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 18/72] i2c: dev: prevent ZERO_SIZE_PTR deref in i2cdev_ioctl_rdwr() Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 19/72] tcp: fix TCP_REPAIR_QUEUE bound checking Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 20/72] bdi: wake up concurrent wb_shutdown() callers Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 21/72] bdi: Fix use after free bug in debugfs_remove() Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 22/72] bdi: Fix oops in wb_workfn() Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 23/72] compat: fix 4-byte infoleak via uninitialized struct field Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 24/72] gpioib: do not free unrequested descriptors Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 25/72] gpio: fix aspeed_gpio unmask irq Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 26/72] gpio: fix error path in lineevent_create Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 27/72] rfkill: gpio: fix memory leak in probe error path Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 28/72] libata: Apply NOLPM quirk for SanDisk SD7UB3Q*G1001 SSDs Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 29/72] dm integrity: use kvfree for kvmallocd memory Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 30/72] tracing: Fix regex_match_front() to not over compare the test string Greg Kroah-Hartman
2018-05-14  6:48 ` Greg Kroah-Hartman [this message]
2018-05-14  6:48 ` [PATCH 4.16 32/72] mm: sections are not offlined during memory hotremove Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 33/72] mm, oom: fix concurrent munlock and oom reaper unmap, v3 Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 34/72] ceph: fix rsize/wsize capping in ceph_direct_read_write() Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 35/72] can: flexcan: fix endianess detection Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 36/72] can: kvaser_usb: Increase correct stats counter in kvaser_usb_rx_can_msg() Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 37/72] can: hi311x: Acquire SPI lock on ->do_get_berr_counter Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 38/72] can: hi311x: Work around TX complete interrupt erratum Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 39/72] mtd: rawnand: marvell: pass ms delay to wait_op Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 40/72] mtd: rawnand: marvell: fix command xtype in BCH write hook Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 41/72] mtd: rawnand: Make sure we wait tWB before polling the STATUS reg Greg Kroah-Hartman
2018-05-14  7:32   ` Geert Uytterhoeven
2018-05-14  9:04     ` Greg Kroah-Hartman
2018-05-14  9:09       ` Boris Brezillon
2018-05-14 10:54         ` Geert Uytterhoeven
2018-05-14  9:32       ` Geert Uytterhoeven
2018-05-14 16:50       ` Greg Kroah-Hartman
2018-05-14  6:48 ` [PATCH 4.16 42/72] drm/vc4: Fix scaling of uni-planar formats Greg Kroah-Hartman
2018-05-14  6:49 ` [PATCH 4.16 43/72] drm/ttm: Use GFP_TRANSHUGE_LIGHT for allocating huge pages Greg Kroah-Hartman
2018-05-14  6:49 ` [PATCH 4.16 44/72] drm/i915: Fix drm:intel_enable_lvds ERROR message in kernel log Greg Kroah-Hartman
2018-05-14  6:49 ` [PATCH 4.16 45/72] drm/i915: Adjust eDPs logical vco in a reliable place Greg Kroah-Hartman
2018-05-14  6:49 ` [PATCH 4.16 46/72] drm/nouveau: Fix deadlock in nv50_mstm_register_connector() Greg Kroah-Hartman
2018-05-14  6:49 ` [PATCH 4.16 47/72] drm/nouveau/ttm: dont dereference nvbo::cli, it can outlive client Greg Kroah-Hartman
2018-05-14  6:49 ` [PATCH 4.16 48/72] drm/atomic: Clean old_state/new_state in drm_atomic_state_default_clear() Greg Kroah-Hartman
2018-05-14  6:49 ` [PATCH 4.16 49/72] drm/atomic: Clean private obj " Greg Kroah-Hartman
2018-05-14  6:49 ` [PATCH 4.16 50/72] net: atm: Fix potential Spectre v1 Greg Kroah-Hartman
2018-05-14  6:49 ` [PATCH 4.16 51/72] atm: zatm: " Greg Kroah-Hartman
2018-05-14  6:49 ` [PATCH 4.16 52/72] PCI / PM: Always check PME wakeup capability for runtime wakeup support Greg Kroah-Hartman
2018-05-14  6:49 ` [PATCH 4.16 53/72] PCI / PM: Check device_may_wakeup() in pci_enable_wake() Greg Kroah-Hartman
2018-05-14  6:49 ` [PATCH 4.16 54/72] cpufreq: schedutil: Avoid using invalid next_freq Greg Kroah-Hartman
2018-05-14  6:49 ` [PATCH 4.16 55/72] arm: dts: imx[35]*: declare flexcan devices to be compatible to imx25s flexcan Greg Kroah-Hartman
2018-05-14  6:49 ` [PATCH 4.16 56/72] Revert "Bluetooth: btusb: Fix quirk for Atheros 1525/QCA6174" Greg Kroah-Hartman
2018-05-14  6:49 ` [PATCH 4.16 57/72] Bluetooth: btusb: Add Dell XPS 13 9360 to btusb_needs_reset_resume_table Greg Kroah-Hartman
2018-05-14  6:49 ` [PATCH 4.16 58/72] Bluetooth: btusb: Only check needs_reset_resume DMI table for QCA rome chipsets Greg Kroah-Hartman
2018-05-14  6:49 ` [PATCH 4.16 59/72] thermal: exynos: Reading temperature makes sense only when TMU is turned on Greg Kroah-Hartman
2018-05-14  6:49 ` [PATCH 4.16 60/72] thermal: exynos: Propagate error value from tmu_read() Greg Kroah-Hartman
2018-05-14  6:49 ` [PATCH 4.16 61/72] nvme: add quirk to force medium priority for SQ creation Greg Kroah-Hartman
2018-05-14  6:49 ` [PATCH 4.16 62/72] nvme: Fix sync controller reset return Greg Kroah-Hartman
2018-05-14  6:49 ` [PATCH 4.16 63/72] smb3: directory sync should not return an error Greg Kroah-Hartman
2018-05-14  6:49 ` [PATCH 4.16 64/72] swiotlb: silent unwanted warning "buffer is full" Greg Kroah-Hartman
2018-05-14  6:49 ` [PATCH 4.16 65/72] sched/core: Fix possible Spectre-v1 indexing for sched_prio_to_weight[] Greg Kroah-Hartman
2018-05-14  6:49 ` [PATCH 4.16 66/72] sched/autogroup: " Greg Kroah-Hartman
2018-05-14  6:49 ` [PATCH 4.16 67/72] tracing/uprobe_event: Fix strncpy corner case Greg Kroah-Hartman
2018-05-14  6:49 ` [PATCH 4.16 68/72] perf/x86: Fix possible Spectre-v1 indexing for hw_perf_event cache_* Greg Kroah-Hartman
2018-05-14  6:49 ` [PATCH 4.16 69/72] perf/x86/cstate: Fix possible Spectre-v1 indexing for pkg_msr Greg Kroah-Hartman
2018-05-14  6:49 ` [PATCH 4.16 70/72] perf/x86/msr: Fix possible Spectre-v1 indexing in the MSR driver Greg Kroah-Hartman
2018-05-14  6:49 ` [PATCH 4.16 71/72] perf/core: Fix possible Spectre-v1 indexing for ->aux_pages[] Greg Kroah-Hartman
2018-05-14  6:49 ` [PATCH 4.16 72/72] perf/x86: Fix possible Spectre-v1 indexing for x86_pmu::event_map() Greg Kroah-Hartman
2018-05-14 13:45 ` [PATCH 4.16 00/72] 4.16.9-stable review kernelci.org bot
2018-05-14 16:27 ` Guenter Roeck
2018-05-14 16:51   ` Greg Kroah-Hartman
2018-05-14 22:01 ` Shuah Khan
2018-05-15  6:47   ` Greg Kroah-Hartman
2018-05-15  5:31 ` Naresh Kamboju
2018-05-15  6:47   ` Greg Kroah-Hartman

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=20180514064824.416301035@linuxfoundation.org \
    --to=gregkh@linuxfoundation.org \
    --cc=Oleksiy.Avramchenko@sony.com \
    --cc=akpm@linux-foundation.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux@roeck-us.net \
    --cc=mawilcox@microsoft.com \
    --cc=stable@vger.kernel.org \
    --cc=torvalds@linux-foundation.org \
    --cc=vitaly.vul@sony.com \
    --subject='Re: [PATCH 4.16 31/72] z3fold: fix reclaim lock-ups' \
    /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

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).