From 552e066f2f8bf441d9e65c2b9163b781a882f284 Mon Sep 17 00:00:00 2001 From: =?utf8?q?Arkadiusz=20Mi=C5=9Bkiewicz?= Date: Sun, 20 Dec 2015 09:49:12 +0100 Subject: [PATCH] - raid10 resync corruption fix --- kernel-small_fixes.patch | 75 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 75 insertions(+) diff --git a/kernel-small_fixes.patch b/kernel-small_fixes.patch index 01eef92f..d5200d51 100644 --- a/kernel-small_fixes.patch +++ b/kernel-small_fixes.patch @@ -709,3 +709,78 @@ index fc69e41..597c53e 100644 -- cgit v0.11.2 +commit cc57858831e3e9678291de730c4b4d2e52a19f59 +Author: Artur Paszkiewicz +Date: Fri Dec 18 15:19:16 2015 +1100 + + md/raid10: fix data corruption and crash during resync + + The commit c31df25f20e3 ("md/raid10: make sync_request_write() call + bio_copy_data()") replaced manual data copying with bio_copy_data() but + it doesn't work as intended. The source bio (fbio) is already processed, + so its bvec_iter has bi_size == 0 and bi_idx == bi_vcnt. Because of + this, bio_copy_data() either does not copy anything, or worse, copies + data from the ->bi_next bio if it is set. This causes wrong data to be + written to drives during resync and sometimes lockups/crashes in + bio_copy_data(): + + [ 517.338478] NMI watchdog: BUG: soft lockup - CPU#0 stuck for 22s! [md126_raid10:3319] + [ 517.347324] Modules linked in: raid10 xt_CHECKSUM ipt_MASQUERADE nf_nat_masquerade_ipv4 tun ip6t_rpfilter ip6t_REJECT nf_reject_ipv6 ipt_REJECT nf_reject_ipv4 xt_conntrack ebtable_nat ebtable_broute bridge stp llc ebtable_filter ebtables ip6table_nat nf_conntrack_ipv6 nf_defrag_ipv6 nf_nat_ipv6 ip6table_mangle ip6table_security ip6table_raw ip6table_filter ip6_tables iptable_nat nf_conntrack_ipv4 nf_defrag_ipv4 nf_nat_ipv4 nf_nat nf_conntrack iptable_mangle iptable_security iptable_raw iptable_filter ip_tables x86_pkg_temp_thermal coretemp kvm_intel kvm crct10dif_pclmul crc32_pclmul cryptd shpchp pcspkr ipmi_si ipmi_msghandler tpm_crb acpi_power_meter acpi_cpufreq ext4 mbcache jbd2 sr_mod cdrom sd_mod e1000e ax88179_178a usbnet mii ahci ata_generic crc32c_intel libahci ptp pata_acpi libata pps_core wmi sunrpc dm_mirror dm_region_hash dm_log dm_mod + [ 517.440555] CPU: 0 PID: 3319 Comm: md126_raid10 Not tainted 4.3.0-rc6+ #1 + [ 517.448384] Hardware name: Intel Corporation PURLEY/PURLEY, BIOS PLYDCRB1.86B.0055.D14.1509221924 09/22/2015 + [ 517.459768] task: ffff880153773980 ti: ffff880150df8000 task.ti: ffff880150df8000 + [ 517.468529] RIP: 0010:[] [] bio_copy_data+0xc8/0x3c0 + [ 517.478164] RSP: 0018:ffff880150dfbc98 EFLAGS: 00000246 + [ 517.484341] RAX: ffff880169356688 RBX: 0000000000001000 RCX: 0000000000000000 + [ 517.492558] RDX: 0000000000000000 RSI: ffffea0001ac2980 RDI: ffffea0000d835c0 + [ 517.500773] RBP: ffff880150dfbd08 R08: 0000000000000001 R09: ffff880153773980 + [ 517.508987] R10: ffff880169356600 R11: 0000000000001000 R12: 0000000000010000 + [ 517.517199] R13: 000000000000e000 R14: 0000000000000000 R15: 0000000000001000 + [ 517.525412] FS: 0000000000000000(0000) GS:ffff880174a00000(0000) knlGS:0000000000000000 + [ 517.534844] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 + [ 517.541507] CR2: 00007f8a044d5fed CR3: 0000000169504000 CR4: 00000000001406f0 + [ 517.549722] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 + [ 517.557929] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 + [ 517.566144] Stack: + [ 517.568626] ffff880174a16bc0 ffff880153773980 ffff880169356600 0000000000000000 + [ 517.577659] 0000000000000001 0000000000000001 ffff880153773980 ffff88016a61a800 + [ 517.586715] ffff880150dfbcf8 0000000000000001 ffff88016dd209e0 0000000000001000 + [ 517.595773] Call Trace: + [ 517.598747] [] raid10d+0xfc5/0x1690 [raid10] + [ 517.605610] [] ? __schedule+0x29e/0x8e2 + [ 517.611987] [] md_thread+0x106/0x140 + [ 517.618072] [] ? wait_woken+0x80/0x80 + [ 517.624252] [] ? super_1_load+0x520/0x520 + [ 517.630817] [] kthread+0xc9/0xe0 + [ 517.636506] [] ? flush_kthread_worker+0x70/0x70 + [ 517.643653] [] ret_from_fork+0x3f/0x70 + [ 517.649929] [] ? flush_kthread_worker+0x70/0x70 + + Signed-off-by: Artur Paszkiewicz + Reviewed-by: Shaohua Li + Cc: stable@vger.kernel.org (v4.2+) + Fixes: c31df25f20e3 ("md/raid10: make sync_request_write() call bio_copy_data()") + Signed-off-by: NeilBrown + +diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c +index 41d70bc..84e597e 100644 +--- a/drivers/md/raid10.c ++++ b/drivers/md/raid10.c +@@ -1946,6 +1946,8 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio) + + first = i; + fbio = r10_bio->devs[i].bio; ++ fbio->bi_iter.bi_size = r10_bio->sectors << 9; ++ fbio->bi_iter.bi_idx = 0; + + vcnt = (r10_bio->sectors + (PAGE_SIZE >> 9) - 1) >> (PAGE_SHIFT - 9); + /* now find blocks with errors */ +@@ -1989,7 +1991,7 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio) + bio_reset(tbio); + + tbio->bi_vcnt = vcnt; +- tbio->bi_iter.bi_size = r10_bio->sectors << 9; ++ tbio->bi_iter.bi_size = fbio->bi_iter.bi_size; + tbio->bi_rw = WRITE; + tbio->bi_private = r10_bio; + tbio->bi_iter.bi_sector = r10_bio->devs[i].addr; -- 2.44.0