kernel BUG at include/linux/swapops.h:204!
Subsystems (2)
Hello,
I've seen one weird bug on 5.12.14 that happened a couple of times when I started a bunch of VMs on a server.
I've briefly googled this problem but could not find any relevant commit that would fix this issue.
Do you have any hint how to debug this further or know the fix by any chance?
Thanks in advance. Stack trace following:
[ 376.876610] ------------[ cut here ]------------
[ 376.881274] kernel BUG at include/linux/swapops.h:204!
[ 376.886455] invalid opcode: 0000 [#1] SMP NOPTI
[ 376.891014] CPU: 40 PID: 11775 Comm: rpc-worker Tainted: G E
5.12.14-1.gdc.el8.x86_64 #1
[ 376.900464] Hardware name: HPE ProLiant DL380 Gen10/ProLiant DL380
Gen10, BIOS U30 05/24/2021
[ 376.909038] RIP: 0010:pmd_migration_entry_wait+0x132/0x140
[ 376.914562] Code: 02 00 00 00 5b 4c 89 c7 5d e9 8a e4 f6 ff 48 81 e2 00
f0 ff ff 48 f7 d2 48 21 c2 89 d1 f7 c2 81 01 00 00 75 80 e9 44 ff ff ff
<0f> 0b 48 8b 2d 75 bd 30 01 e9 ef fe ff ff 0f 1f 44 00 00 41 55 48
[ 376.933443] RSP: 0000:ffffb65a5e1cfdc8 EFLAGS: 00010246
[ 376.938701] RAX: 0017ffffc0000000 RBX: ffff908b8ecabaf8 RCX:
ffffffffffffffff
[ 376.945878] RDX: 0000000000000000 RSI: ffff908b8ecabaf8 RDI:
fffff497473b2ae8
[ 376.953055] RBP: fffff497473b2ae8 R08: fffff49747fa8080 R09:
0000000000000000
[ 376.960230] R10: 0000000000000000 R11: 0000000000000000 R12:
0000000000000af8
[ 376.967407] R13: 0400000000000000 R14: 0400000000000080 R15:
ffff908bbef7b6a8
[ 376.974582] FS: 00007f5bb1f81700(0000) GS:ffff90e87fd80000(0000)
knlGS:0000000000000000
[ 376.982718] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 376.988497] CR2: 00007f5b2bfffd98 CR3: 00000001f793e006 CR4:
00000000007726e0
[ 376.995673] DR0: 0000000000000000 DR1: 0000000000000000 DR2:
0000000000000000
[ 377.002849] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7:
0000000000000400
[ 377.010026] PKRU: 55555554
[ 377.012745] Call Trace:
[ 377.015207] __handle_mm_fault+0x5ad/0x6e0
[ 377.019335] handle_mm_fault+0xc5/0x290
[ 377.023194] do_user_addr_fault+0x1cd/0x740
[ 377.027406] exc_page_fault+0x54/0x110
[ 377.031182] ? asm_exc_page_fault+0x8/0x30
[ 377.035307] asm_exc_page_fault+0x1e/0x30
[ 377.039340] RIP: 0033:0x7f5bb91d6734
[ 377.042937] Code: 89 08 48 8b 35 dd 3b 21 00 4c 8d 0d d6 3b 21 00 31 c0
4c 39 ce 74 73 0f 1f 80 00 00 00 00 48 8d 96 40 fd ff ff 49 39 d2 74 22
<48> 8b 96 d8 03 00 00 48 01 15 4e 7c 21 00 80 be 50 03 00 00 00 c7
[ 377.061820] RSP: 002b:00007f5bb1f7ff58 EFLAGS: 00010206
[ 377.067076] RAX: 0000000000000000 RBX: 0000000000000000 RCX:
00007f5ba0000020
[ 377.074255] RDX: 00007f5b2bfff700 RSI: 00007f5b2bfff9c0 RDI:
0000000000000001
[ 377.081429] RBP: 0000000000000001 R08: 0000000000000000 R09:
00007f5bb93ea2f0
[ 377.088606] R10: 00007f5bb1f81700 R11: 0000000000000202 R12:
0000000000000001
[ 377.095782] R13: 0000000000000006 R14: 0000000000000cb4 R15:
00007f5bb1f801f0
[ 377.102958] Modules linked in: ebt_arp(E) nft_meta_bridge(E)ip6_tables(E) xt_CT(E) nf_log_ipv4(E) nf_log_common(E) nft_limit(E) nft_counter(E) xt_LOG(E) xt_limit(E) xt_mac(E) xt_set(E) xt_multiport(E) xt_state(E) xt_conntrack(E) xt_comment(E) xt_physdev(E) nft_compat(E) ip_set_hash_net(E) ip_set(E) vhost_net(E) vhost(E) vhost_iotlb(E) tap(E) tun(E) tcp_diag(E) udp_diag(E) inet_diag(E) netconsole(E) nf_tables(E) vxlan(E) ip6_udp_tunnel(E) udp_tunnel(E) nfnetlink(E) binfmt_misc(E) iscsi_tcp(E) libiscsi_tcp(E) 8021q(E) garp(E) mrp(E) bonding(E) tls(E) vfat(E) fat(E) dm_service_time(E) dm_multipath(E) rpcrdma(E) sunrpc(E) rdma_ucm(E) ib_srpt(E) ib_isert(E) iscsi_target_mod(E) target_core_mod(E) ib_iser(E) rdma_cm(E) iw_cm(E) ib_cm(E) libiscsi(E) scsi_transport_iscsi(E) intel_rapl_msr(E) qedr(E) intel_rapl_common(E) ib_uverbs(E) isst_if_common(E) ib_core(E) nfit(E) libnvdimm(E) x86_pkg_temp_thermal(E) intel_powerclamp(E) coretemp(E) kvm_intel(E) kvm(E) irqbypass(E) crct10dif_pclmul(E)
[ 377.102999] crc32_pclmul(E) ghash_clmulni_intel(E) rapl(E)
intel_cstate(E) ipmi_ssif(E) acpi_ipmi(E) ipmi_si(E) mei_me(E) ioatdma(E) ipmi_devintf(E) dm_mod(E) ses(E) intel_uncore(E) pcspkr(E) qede(E) enclosure(E) tg3(E) mei(E) lpc_ich(E) hpilo(E) hpwdt(E) intel_pch_thermal(E) dca(E) ipmi_msghandler(E) acpi_power_meter(E) ext4(E) mbcache(E) jbd2(E) sd_mod(E) t10_pi(E) sg(E) qedf(E) qed(E) crc8(E) libfcoe(E) libfc(E) smartpqi(E) scsi_transport_fc(E) scsi_transport_sas(E) wmi(E) nf_conntrack(E) nf_defrag_ipv6(E) libcrc32c(E) crc32c_intel(E) nf_defrag_ipv4(E) br_netfilter(E) bridge(E) stp(E) llc(E)
[ 377.243468] ---[ end trace 04bce3bb051f7620 ]--- [ 377.385645] RIP: 0010:pmd_migration_entry_wait+0x132/0x140 [ 377.391194] Code: 02 00 00 00 5b 4c 89 c7 5d e9 8a e4 f6 ff 48 81 e2 00 f0 ff ff 48 f7 d2 48 21 c2 89 d1 f7 c2 81 01 00 00 75 80 e9 44 ff ff ff <0f> 0b 48 8b 2d 75 bd 30 01 e9 ef fe ff ff 0f 1f 44 00 00 41 55 48 [ 377.410091] RSP: 0000:ffffb65a5e1cfdc8 EFLAGS: 00010246 [ 377.415355] RAX: 0017ffffc0000000 RBX: ffff908b8ecabaf8 RCX: ffffffffffffffff [ 377.422540] RDX: 0000000000000000 RSI: ffff908b8ecabaf8 RDI: fffff497473b2ae8 [ 377.429721] RBP: fffff497473b2ae8 R08: fffff49747fa8080 R09: 0000000000000000 [ 377.436902] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000af8 [ 377.444086] R13: 0400000000000000 R14: 0400000000000080 R15: ffff908bbef7b6a8 [ 377.451272] FS: 00007f5bb1f81700(0000) GS:ffff90e87fd80000(0000) knlGS:0000000000000000 [ 377.459415] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 377.465196] CR2: 00007f5b2bfffd98 CR3: 00000001f793e006 CR4: 00000000007726e0 [ 377.472377] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 377.479556] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 377.486738] PKRU: 55555554 [ 377.489465] Kernel panic - not syncing: Fatal exception [ 377.573911] Kernel Offset: 0xa000000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) [ 377.716482] ---[ end Kernel panic - not syncing: Fatal exception ]---
Quoted 4 lines · On Sat, 10 Jul 2021 09:33:26 +0200 Igor Raits wrote:
Hello,
I've seen one weird bug on 5.12.14 that happened a couple of times when I started a bunch of VMs on a server.
Thanks for your report.
Quoted 3 lines
I've briefly googled this problem but could not find any relevant commit that would fix this issue.
Not sure this is the first report - a similar one [0] from syzbot.
[0] https://lore.kernel.org/linux-mm/[email protected]/
Quoted 3 lines
Do you have any hint how to debug this further or know the fix by any chance?
This report has more info about the BUG - in pmd_migration_entry_wait() huge migration entry is checked under page table lock. And on the updater side, hme should be set and removed also with ptl held, see below diff.
Quoted 34 lines
Thanks in advance. Stack trace following:
[ 376.876610] ------------[ cut here ]------------ [ 376.881274] kernel BUG at include/linux/swapops.h:204! [ 376.886455] invalid opcode: 0000 [#1] SMP NOPTI [ 376.891014] CPU: 40 PID: 11775 Comm: rpc-worker Tainted: G E 5.12.14-1.gdc.el8.x86_64 #1 [ 376.900464] Hardware name: HPE ProLiant DL380 Gen10/ProLiant DL380 Gen10, BIOS U30 05/24/2021 [ 376.909038] RIP: 0010:pmd_migration_entry_wait+0x132/0x140 [ 376.914562] Code: 02 00 00 00 5b 4c 89 c7 5d e9 8a e4 f6 ff 48 81 e2 00 f0 ff ff 48 f7 d2 48 21 c2 89 d1 f7 c2 81 01 00 00 75 80 e9 44 ff ff ff <0f> 0b 48 8b 2d 75 bd 30 01 e9 ef fe ff ff 0f 1f 44 00 00 41 55 48 [ 376.933443] RSP: 0000:ffffb65a5e1cfdc8 EFLAGS: 00010246 [ 376.938701] RAX: 0017ffffc0000000 RBX: ffff908b8ecabaf8 RCX: ffffffffffffffff [ 376.945878] RDX: 0000000000000000 RSI: ffff908b8ecabaf8 RDI: fffff497473b2ae8 [ 376.953055] RBP: fffff497473b2ae8 R08: fffff49747fa8080 R09: 0000000000000000 [ 376.960230] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000af8 [ 376.967407] R13: 0400000000000000 R14: 0400000000000080 R15: ffff908bbef7b6a8 [ 376.974582] FS: 00007f5bb1f81700(0000) GS:ffff90e87fd80000(0000) knlGS:0000000000000000 [ 376.982718] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 376.988497] CR2: 00007f5b2bfffd98 CR3: 00000001f793e006 CR4: 00000000007726e0 [ 376.995673] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 377.002849] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7:0000000000000400
Quoted 8 lines
[ 377.010026] PKRU: 55555554 [ 377.012745] Call Trace: [ 377.015207] __handle_mm_fault+0x5ad/0x6e0 [ 377.019335] handle_mm_fault+0xc5/0x290 [ 377.023194] do_user_addr_fault+0x1cd/0x740 [ 377.027406] exc_page_fault+0x54/0x110 [ 377.031182] ? asm_exc_page_fault+0x8/0x30 [ 377.035307] asm_exc_page_fault+0x1e/0x30
+++ x/mm/huge_memory.c
@@ -2983,6 +2983,7 @@ void set_pmd_migration_entry(struct page
struct vm_area_struct *vma = pvmw->vma; struct mm_struct *mm = vma->vm_mm;
unsigned long address = pvmw->address;
+ spinlock_t *ptl;
pmd_t pmdval;
swp_entry_t entry;
pmd_t pmdswp;
@@ -2998,7 +2999,9 @@ void set_pmd_migration_entry(struct page
pmdswp = swp_entry_to_pmd(entry);
if (pmd_soft_dirty(pmdval))
pmdswp = pmd_swp_mksoft_dirty(pmdswp);
+ ptl = pmd_lock(mm, pvmw->pmd);
set_pmd_at(mm, address, pvmw->pmd, pmdswp);
+ spin_unlock(ptl);
page_remove_rmap(page, true); put_page(page);
}
@@ -3009,6 +3012,7 @@ void remove_migration_pmd(struct page_vm
struct mm_struct *mm = vma->vm_mm;
unsigned long address = pvmw->address; unsigned long mmun_start = address & HPAGE_PMD_MASK;
+ spinlock_t *ptl;
pmd_t pmde;
swp_entry_t entry;
@@ -3028,7 +3032,9 @@ void remove_migration_pmd(struct page_vm
page_add_anon_rmap(new, vma, mmun_start, true);
else
page_add_file_rmap(new, true);
+ ptl = pmd_lock(mm, pvmw->pmd);
set_pmd_at(mm, mmun_start, pvmw->pmd, pmde);
+ spin_unlock(ptl);
if ((vma->vm_flags & VM_LOCKED) && !PageDoubleMap(new))
mlock_vma_page(new);
update_mmu_cache_pmd(vma, address, pvmw->pmd);
Quoted 4 lines · Igor Raits
Hello,
I've seen one weird bug on 5.12.14 that happened a couple of times when I started a bunch of VMs on a server.
Would it be possible for you to try the same on a 5.12.13 kernel? Perhaps by reverting the diff between 5.12.13 and 5.12.14 temporarily. Enough to form an impression of whether the issue is new in 5.12.14.
I ask because 5.12.14 did include several fixes and cleanups from me to page_vma_mapped_walk(), and that is involved in inserting and removing pmd migration entries. I am not aware of introducing any bug there, but your report has got me worried. If it's happening in 5.12.14 but not in 5.12.13, then I must look again at my changes.
I don't expect Hillf's patch to help at at all: the pmd_lock() is supposed to be taken by page_vma_mapped_walk(), before set_pmd_migration_entry() and remove_migration_pmd() are called.
Thanks,
Hugh
Quoted 118 lines
I've briefly googled this problem but could not find any relevant commit that would fix this issue.
Do you have any hint how to debug this further or know the fix by any chance?
Thanks in advance. Stack trace following:
[ 376.876610] ------------[ cut here ]------------ [ 376.881274] kernel BUG at include/linux/swapops.h:204! [ 376.886455] invalid opcode: 0000 [#1] SMP NOPTI [ 376.891014] CPU: 40 PID: 11775 Comm: rpc-worker Tainted: G E 5.12.14-1.gdc.el8.x86_64 #1 [ 376.900464] Hardware name: HPE ProLiant DL380 Gen10/ProLiant DL380 Gen10, BIOS U30 05/24/2021 [ 376.909038] RIP: 0010:pmd_migration_entry_wait+0x132/0x140 [ 376.914562] Code: 02 00 00 00 5b 4c 89 c7 5d e9 8a e4 f6 ff 48 81 e2 00 f0 ff ff 48 f7 d2 48 21 c2 89 d1 f7 c2 81 01 00 00 75 80 e9 44 ff ff ff <0f> 0b 48 8b 2d 75 bd 30 01 e9 ef fe ff ff 0f 1f 44 00 00 41 55 48 [ 376.933443] RSP: 0000:ffffb65a5e1cfdc8 EFLAGS: 00010246 [ 376.938701] RAX: 0017ffffc0000000 RBX: ffff908b8ecabaf8 RCX: ffffffffffffffff [ 376.945878] RDX: 0000000000000000 RSI: ffff908b8ecabaf8 RDI: fffff497473b2ae8 [ 376.953055] RBP: fffff497473b2ae8 R08: fffff49747fa8080 R09: 0000000000000000 [ 376.960230] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000af8 [ 376.967407] R13: 0400000000000000 R14: 0400000000000080 R15: ffff908bbef7b6a8 [ 376.974582] FS: 00007f5bb1f81700(0000) GS:ffff90e87fd80000(0000) knlGS:0000000000000000 [ 376.982718] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 376.988497] CR2: 00007f5b2bfffd98 CR3: 00000001f793e006 CR4: 00000000007726e0 [ 376.995673] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 377.002849] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 377.010026] PKRU: 55555554 [ 377.012745] Call Trace: [ 377.015207] __handle_mm_fault+0x5ad/0x6e0 [ 377.019335] handle_mm_fault+0xc5/0x290 [ 377.023194] do_user_addr_fault+0x1cd/0x740 [ 377.027406] exc_page_fault+0x54/0x110 [ 377.031182] ? asm_exc_page_fault+0x8/0x30 [ 377.035307] asm_exc_page_fault+0x1e/0x30 [ 377.039340] RIP: 0033:0x7f5bb91d6734 [ 377.042937] Code: 89 08 48 8b 35 dd 3b 21 00 4c 8d 0d d6 3b 21 00 31 c0 4c 39 ce 74 73 0f 1f 80 00 00 00 00 48 8d 96 40 fd ff ff 49 39 d2 74 22 <48> 8b 96 d8 03 00 00 48 01 15 4e 7c 21 00 80 be 50 03 00 00 00 c7 [ 377.061820] RSP: 002b:00007f5bb1f7ff58 EFLAGS: 00010206 [ 377.067076] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 00007f5ba0000020 [ 377.074255] RDX: 00007f5b2bfff700 RSI: 00007f5b2bfff9c0 RDI: 0000000000000001 [ 377.081429] RBP: 0000000000000001 R08: 0000000000000000 R09: 00007f5bb93ea2f0 [ 377.088606] R10: 00007f5bb1f81700 R11: 0000000000000202 R12: 0000000000000001 [ 377.095782] R13: 0000000000000006 R14: 0000000000000cb4 R15: 00007f5bb1f801f0 [ 377.102958] Modules linked in: ebt_arp(E) nft_meta_bridge(E)
ip6_tables(E)xt_CT(E)nf_log_ipv4(E)nf_log_common(E)nft_limit(E)nft_counter(E)xt_LOG(E)xt_limit(E)xt_mac(E)xt_set(E)xt_multiport(E)xt_state(E)xt_conntrack(E)xt_comment(E)xt_physdev(E)nft_compat(E)ip_set_hash_net(E)ip_set(E)vhost_net(E)vhost(E)vhost_iotlb(E)tap(E) tun(E)tcp_diag(E)udp_diag(E)inet_diag(E)netconsole(E)nf_tables(E)vxlan(E)ip6_udp_tunnel(E)udp_tunnel(E)nfnetlink(E)binfmt_misc(E)iscsi_tcp(E)libiscsi_tcp(E)8021q(E) garp(E) mrp(E) bonding(E) tls(E) vfat(E) fat(E)dm_service_time(E)dm_multipath(E)rpcrdma(E) sunrpc(E)rdma_ucm(E)ib_srpt(E)ib_isert(E)iscsi_target_mod(E)target_core_mod(E)ib_iser(E)rdma_cm(E)iw_cm(E)ib_cm(E)libiscsi(E)scsi_transport_iscsi(E)intel_rapl_msr(E)qedr(E)intel_rapl_common(E)ib_uverbs(E)isst_if_common(E)ib_core(E)nfit(E) libnvdimm(E)x86_pkg_temp_thermal(E)intel_powerclamp(E)coretemp(E)kvm_intel(E)kvm(E) irqbypass(E)crct10dif_pclmul(E)[ 377.102999] crc32_pclmul(E) ghash_clmulni_intel(E) rapl(E)
intel_cstate(E)ipmi_ssif(E)acpi_ipmi(E)ipmi_si(E)mei_me(E)ioatdma(E)ipmi_devintf(E)dm_mod(E)ses(E)intel_uncore(E)pcspkr(E) qede(E) enclosure(E) tg3(E) mei(E)lpc_ich(E)hpilo(E) hpwdt(E)intel_pch_thermal(E)dca(E)ipmi_msghandler(E)acpi_power_meter(E)ext4(E) mbcache(E) jbd2(E)sd_mod(E)t10_pi(E)sg(E) qedf(E) qed(E) crc8(E) libfcoe(E) libfc(E) smartpqi(E)scsi_transport_fc(E)scsi_transport_sas(E)wmi(E)nf_conntrack(E)nf_defrag_ipv6(E)libcrc32c(E)crc32c_intel(E)nf_defrag_ipv4(E)br_netfilter(E)bridge(E) stp(E) llc(E)[ 377.243468] ---[ end trace 04bce3bb051f7620 ]--- [ 377.385645] RIP: 0010:pmd_migration_entry_wait+0x132/0x140 [ 377.391194] Code: 02 00 00 00 5b 4c 89 c7 5d e9 8a e4 f6 ff 48 81 e2 00 f0 ff ff 48 f7 d2 48 21 c2 89 d1 f7 c2 81 01 00 00 75 80 e9 44 ff ff ff <0f> 0b 48 8b 2d 75 bd 30 01 e9 ef fe ff ff 0f 1f 44 00 00 41 55 48 [ 377.410091] RSP: 0000:ffffb65a5e1cfdc8 EFLAGS: 00010246 [ 377.415355] RAX: 0017ffffc0000000 RBX: ffff908b8ecabaf8 RCX: ffffffffffffffff [ 377.422540] RDX: 0000000000000000 RSI: ffff908b8ecabaf8 RDI: fffff497473b2ae8 [ 377.429721] RBP: fffff497473b2ae8 R08: fffff49747fa8080 R09: 0000000000000000 [ 377.436902] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000af8 [ 377.444086] R13: 0400000000000000 R14: 0400000000000080 R15: ffff908bbef7b6a8 [ 377.451272] FS: 00007f5bb1f81700(0000) GS:ffff90e87fd80000(0000) knlGS:0000000000000000 [ 377.459415] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 377.465196] CR2: 00007f5b2bfffd98 CR3: 00000001f793e006 CR4: 00000000007726e0 [ 377.472377] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 377.479556] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 377.486738] PKRU: 55555554 [ 377.489465] Kernel panic - not syncing: Fatal exception [ 377.573911] Kernel Offset: 0xa000000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) [ 377.716482] ---[ end Kernel panic - not syncing: Fatal exception ]---
Hi Hugh,
Quoted 11 lines · Hugh Dickins
Quoted 4 lines · Igor Raits
Hello,
I've seen one weird bug on 5.12.14 that happened a couple of times when I started a bunch of VMs on a server.
Would it be possible for you to try the same on a 5.12.13 kernel? Perhaps by reverting the diff between 5.12.13 and 5.12.14 temporarily. Enough to form an impression of whether the issue is new in 5.12.14.
We've been using 5.12.12 for quite some time (~ a month) and I never saw it there.
But I have to admit that I don't really have a reproducer. For example, on servers where it happened,
I just rebooted them and panic did not happen anymore (so I saw it only only once,
only on 2 servers out of 32 that we have on 5.12.14).
Quoted 140 lines
I ask because 5.12.14 did include several fixes and cleanups from me to
page_vma_mapped_walk(), and that is involved in inserting and removing pmd migration entries. I am not aware of introducing any bug there, but your report has got me worried. If it's happening in 5.12.14 but not in 5.12.13, then I must look again at my changes.I don't expect Hillf's patch to help at at all: the
pmd_lock()is supposed to be taken bypage_vma_mapped_walk(), beforeset_pmd_migration_entry()andremove_migration_pmd()are called.Thanks,
HughQuoted 7 lines
I've briefly googled this problem but could not find any relevant commit that would fix this issue.
Do you have any hint how to debug this further or know the fix by any chance?
Quoted 6 lines
Thanks in advance. Stack trace following:
[ 376.876610] ------------[ cut here ]------------ [ 376.881274] kernel BUG at include/linux/swapops.h:204! [ 376.886455] invalid opcode: 0000 [#1] SMP NOPTI [ 376.891014] CPU: 40 PID: 11775 Comm: rpc-worker Tainted: GE
Quoted 5 lines
5.12.14-1.gdc.el8.x86_64 #1 [ 376.900464] Hardware name: HPE ProLiant DL380 Gen10/ProLiant DL380 Gen10, BIOS U30 05/24/2021 [ 376.909038] RIP: 0010:pmd_migration_entry_wait+0x132/0x140 [ 376.914562] Code: 02 00 00 00 5b 4c 89 c7 5d e9 8a e4 f6 ff 48 81 e200
Quoted 24 lines
f0 ff ff 48 f7 d2 48 21 c2 89 d1 f7 c2 81 01 00 00 75 80 e9 44 ff ff ff <0f> 0b 48 8b 2d 75 bd 30 01 e9 ef fe ff ff 0f 1f 44 00 00 41 55 48
[ 376.933443] RSP: 0000:ffffb65a5e1cfdc8 EFLAGS: 00010246 [ 376.938701] RAX: 0017ffffc0000000 RBX: ffff908b8ecabaf8 RCX: ffffffffffffffff [ 376.945878] RDX: 0000000000000000 RSI: ffff908b8ecabaf8 RDI: fffff497473b2ae8 [ 376.953055] RBP: fffff497473b2ae8 R08: fffff49747fa8080 R09: 0000000000000000 [ 376.960230] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000af8 [ 376.967407] R13: 0400000000000000 R14: 0400000000000080 R15: ffff908bbef7b6a8 [ 376.974582] FS: 00007f5bb1f81700(0000) GS:ffff90e87fd80000(0000) knlGS:0000000000000000 [ 376.982718] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 376.988497] CR2: 00007f5b2bfffd98 CR3: 00000001f793e006 CR4: 00000000007726e0 [ 376.995673] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 377.002849] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 377.010026] PKRU: 55555554 [ 377.012745] Call Trace:Quoted 8 lines
[ 377.015207] __handle_mm_fault+0x5ad/0x6e0 [ 377.019335] handle_mm_fault+0xc5/0x290 [ 377.023194] do_user_addr_fault+0x1cd/0x740 [ 377.027406] exc_page_fault+0x54/0x110 [ 377.031182] ? asm_exc_page_fault+0x8/0x30 [ 377.035307] asm_exc_page_fault+0x1e/0x30 [ 377.039340] RIP: 0033:0x7f5bb91d6734 [ 377.042937] Code: 89 08 48 8b 35 dd 3b 21 00 4c 8d 0d d6 3b 21 00 31c0
Quoted 14 lines
4c 39 ce 74 73 0f 1f 80 00 00 00 00 48 8d 96 40 fd ff ff 49 39 d2 74 22 <48> 8b 96 d8 03 00 00 48 01 15 4e 7c 21 00 80 be 50 03 00 00 00 c7
[ 377.061820] RSP: 002b:00007f5bb1f7ff58 EFLAGS: 00010206 [ 377.067076] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 00007f5ba0000020 [ 377.074255] RDX: 00007f5b2bfff700 RSI: 00007f5b2bfff9c0 RDI: 0000000000000001 [ 377.081429] RBP: 0000000000000001 R08: 0000000000000000 R09: 00007f5bb93ea2f0 [ 377.088606] R10: 00007f5bb1f81700 R11: 0000000000000202 R12: 0000000000000001 [ 377.095782] R13: 0000000000000006 R14: 0000000000000cb4 R15: 00007f5bb1f801f0 [ 377.102958] Modules linked in: ebt_arp(E) nft_meta_bridge(E)Quoted 10 lines
ip6_tables(E)xt_CT(E)nf_log_ipv4(E)nf_log_common(E)nft_limit(E)nft_counter(E)xt_LOG(E)xt_limit(E)xt_mac(E)xt_set(E)xt_multiport(E)xt_state(E)xt_conntrack(E)xt_comment(E)xt_physdev(E)nft_compat(E)ip_set_hash_net(E)ip_set(E)vhost_net(E)vhost(E)vhost_iotlb(E)tap(E) tun(E)tcp_diag(E)udp_diag(E)inet_diag(E)netconsole(E)nf_tables(E)vxlan(E)ip6_udp_tunnel(E)udp_tunnel(E)nfnetlink(E)binfmt_misc(E)iscsi_tcp(E)libiscsi_tcp(E)8021q(E) garp(E) mrp(E) bonding(E) tls(E) vfat(E) fat(E)dm_service_time(E)dm_multipath(E)rpcrdma(E) sunrpc(E)rdma_ucm(E)ib_srpt(E)ib_isert(E)iscsi_target_mod(E)target_core_mod(E)ib_iser(E)rdma_cm(E)iw_cm(E)ib_cm(E)libiscsi(E)
scsi_transport_iscsi(E)Quoted 9 lines
intel_rapl_msr(E)qedr(E)intel_rapl_common(E)ib_uverbs(E)isst_if_common(E)ib_core(E)nfit(E) libnvdimm(E)x86_pkg_temp_thermal(E)intel_powerclamp(E)coretemp(E)kvm_intel(E)kvm(E) irqbypass(E)crct10dif_pclmul(E)[ 377.102999] crc32_pclmul(E) ghash_clmulni_intel(E) rapl(E)
intel_cstate(E)ipmi_ssif(E)acpi_ipmi(E)ipmi_si(E)mei_me(E)ioatdma(E)ipmi_devintf(E)dm_mod(E)ses(E)intel_uncore(E)pcspkr(E) qede(E) enclosure(E) tg3(E) mei(E)lpc_ich(E)hpilo(E) hpwdt(E)intel_pch_thermal(E)dca(E)ipmi_msghandler(E)acpi_power_meter(E)ext4(E)
Quoted 2 lines
mbcache(E) jbd2(E)
sd_mod(E)t10_pi(E)sg(E) qedf(E) qed(E) crc8(E) libfcoe(E) libfc(E) smartpqi(E)scsi_transport_fc(E)
scsi_transport_sas(E)Quoted 5 lines
wmi(E)
nf_conntrack(E)nf_defrag_ipv6(E)libcrc32c(E)crc32c_intel(E)nf_defrag_ipv4(E)br_netfilter(E)bridge(E) stp(E) llc(E)[ 377.243468] ---[ end trace 04bce3bb051f7620 ]--- [ 377.385645] RIP: 0010:pmd_migration_entry_wait+0x132/0x140 [ 377.391194] Code: 02 00 00 00 5b 4c 89 c7 5d e9 8a e4 f6 ff 48 81 e200
Quoted 17 lines
f0 ff ff 48 f7 d2 48 21 c2 89 d1 f7 c2 81 01 00 00 75 80 e9 44 ff ff ff <0f> 0b 48 8b 2d 75 bd 30 01 e9 ef fe ff ff 0f 1f 44 00 00 41 55 48
[ 377.410091] RSP: 0000:ffffb65a5e1cfdc8 EFLAGS: 00010246 [ 377.415355] RAX: 0017ffffc0000000 RBX: ffff908b8ecabaf8 RCX: ffffffffffffffff [ 377.422540] RDX: 0000000000000000 RSI: ffff908b8ecabaf8 RDI: fffff497473b2ae8 [ 377.429721] RBP: fffff497473b2ae8 R08: fffff49747fa8080 R09: 0000000000000000 [ 377.436902] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000af8 [ 377.444086] R13: 0400000000000000 R14: 0400000000000080 R15: ffff908bbef7b6a8 [ 377.451272] FS: 00007f5bb1f81700(0000) GS:ffff90e87fd80000(0000) knlGS:0000000000000000 [ 377.459415] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 377.465196] CR2: 00007f5b2bfffd98 CR3: 00000001f793e006 CR4:Quoted 8 lines
00000000007726e0[ 377.472377] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 377.479556] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 377.486738] PKRU: 55555554 [ 377.489465] Kernel panic - not syncing: Fatal exception [ 377.573911] Kernel Offset: 0xa000000 from 0xffffffff81000000(relocation
Quoted 3 lines
range: 0xffffffff80000000-0xffffffffbfffffff)
[ 377.716482] ---[ end Kernel panic - not syncing: Fatal exception ]---
Signature · 19 lines
Igor Raits Sr. SW Engineer [email protected] +420 775 117 817 Moravske namesti 1007/14 602 00 Brno-Veveri, Czech Republic Twitter <https://twitter.com/gooddata> | Facebook <https://www.facebook.com/gooddata> | LinkedIn <http://www.linkedin.com/company/gooddata> | Blog <http://www.gooddata.com/blog> <https://www.gooddata.com/>
Hi everyone again,
I've been trying to reproduce this issue but still can't find a consistent pattern.
However, it did happen once more and this time on 5.13.1:
[ 222.068216] ------------[ cut here ]------------ [ 222.072884] kernel BUG at include/linux/swapops.h:204! [ 222.078062] invalid opcode: 0000 [#1] SMP NOPTI [ 222.082618] CPU: 38 PID: 9828 Comm: rpc-worker Tainted: G E 5.13.1-1.gdc.el8.x86_64 #1 [ 222.091894] Hardware name: HPE ProLiant DL380 Gen10/ProLiant DL380 Gen10, BIOS U30 05/24/2021 [ 222.100468] RIP: 0010:pmd_migration_entry_wait+0x132/0x140 [ 222.105994] Code: 02 00 00 00 5b 4c 89 c7 5d e9 ca c5 f6 ff 48 81 e2 00 f0 ff ff 48 f7 d2 48 21 c2 89 d1 f7 c2 81 01 00 00 75 80 e9 44 ff ff ff <0f> 0b 48 8b 2d 65 48 30 01 e9 ef fe ff ff 0f 1f 44 00 00 41 55 48 [ 222.124878] RSP: 0000:ffffbcfe9eb7bdd8 EFLAGS: 00010246 [ 222.130134] RAX: 0057ffffc0000000 RBX: ffff9eec4b3cdbf8 RCX: ffffffffffffffff [ 222.137309] RDX: 0000000000000000 RSI: ffff9eec4b3cdbf8 RDI: ffffdf55c52cf368 [ 222.144485] RBP: ffffdf55c52cf368 R08: ffffdf57428d8080 R09: 0000000000000000 [ 222.151661] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000bf8 [ 222.158837] R13: 0400000000000000 R14: 0400000000000080 R15: ffff9eec2825b1f8 [ 222.166015] FS: 00007f6754aeb700(0000) GS:ffff9f49bfd00000(0000) knlGS:0000000000000000 [ 222.174153] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 222.179932] CR2: 00007f676ffffd98 CR3: 000000012bf6a002 CR4: 00000000007726e0 [ 222.187109] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 222.194283] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 222.201457] PKRU: 55555554 [ 222.204178] Call Trace: [ 222.206638] __handle_mm_fault+0x5ad/0x6e0 [ 222.210760] ? sysvec_call_function_single+0xb/0x90 [ 222.215672] handle_mm_fault+0xc5/0x290 [ 222.219529] do_user_addr_fault+0x1a9/0x660 [ 222.223740] ? sched_clock_cpu+0xc/0xa0 [ 222.227602] exc_page_fault+0x68/0x130 [ 222.231373] ? asm_exc_page_fault+0x8/0x30 [ 222.235495] asm_exc_page_fault+0x1e/0x30 [ 222.239526] RIP: 0033:0x7f67baaed734 [ 222.243120] Code: 89 08 48 8b 35 dd 3b 21 00 4c 8d 0d d6 3b 21 00 31 c0 4c 39 ce 74 73 0f 1f 80 00 00 00 00 48 8d 96 40 fd ff ff 49 39 d2 74 22 <48> 8b 96 d8 03 00 00 48 01 15 4e 7c 21 00 80 be 50 03 00 00 00 c7 [ 222.262002] RSP: 002b:00007f6754aea298 EFLAGS: 00010287 [ 222.267257] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 [ 222.274432] RDX: 00007f676ffff700 RSI: 00007f676ffff9c0 RDI: 00007f676f7fec10 [ 222.281609] RBP: 0000000000000001 R08: 00007f676f7fed10 R09: 00007f67bad012f0 [ 222.288785] R10: 00007f6754aeb700 R11: 0000000000000202 R12: 0000000000000001 [ 222.295961] R13: 0000000000000006 R14: 0000000000000e28 R15: 00007f674006e1f0 [ 222.303137] Modules linked in: vhost_net(E) vhost(E) vhost_iotlb(E)
tap(E) tun(E) tcp_diag(E) udp_diag(E) inet_diag(E) netconsole(E) nf_tables(E) vxlan(E) ip6_udp_tunnel(E) udp_tunnel(E) nfnetlink(E) binfmt_misc(E) iscsi_tcp(E) libiscsi_tcp(E) 8021q(E) garp(E) mrp(E) bonding(E) tls(E) vfat(E) fat(E) dm_service_time(E) dm_multipath(E) rpcrdma(E) sunrpc(E) rdma_ucm(E) ib_srpt(E) ib_isert(E) iscsi_target_mod(E) target_core_mod(E) ib_iser(E) rdma_cm(E) iw_cm(E) ib_cm(E) libiscsi(E) intel_rapl_msr(E) intel_rapl_common(E) scsi_transport_iscsi(E) isst_if_common(E) ipmi_ssif(E) nfit(E) libnvdimm(E) x86_pkg_temp_thermal(E) intel_powerclamp(E) coretemp(E) kvm_intel(E) kvm(E) irqbypass(E) crct10dif_pclmul(E) crc32_pclmul(E) ghash_clmulni_intel(E) rapl(E) qedr(E) mei_me(E) acpi_ipmi(E) ib_uverbs(E) intel_cstate(E) ipmi_si(E) ib_core(E) ipmi_devintf(E) dm_mod(E) ioatdma(E) ses(E) intel_uncore(E) pcspkr(E) enclosure(E) mei(E) hpwdt(E) hpilo(E) lpc_ich(E) intel_pch_thermal(E) dca(E) ipmi_msghandler(E)
[ 222.303181] acpi_power_meter(E) ext4(E) mbcache(E) jbd2(E) sd_mod(E)
t10_pi(E) sg(E) qedf(E) qede(E) libfcoe(E) qed(E) libfc(E) smartpqi(E) scsi_transport_fc(E) tg3(E) scsi_transport_sas(E) crc8(E) wmi(E) nf_conntrack(E) libcrc32c(E) crc32c_intel(E) nf_defrag_ipv6(E) nf_defrag_ipv4(E) br_netfilter(E) bridge(E) stp(E) llc(E)
[ 222.420050] ---[ end trace bcf7b6d1610cc21f ]--- [ 222.572925] RIP: 0010:pmd_migration_entry_wait+0x132/0x140 [ 222.578469] Code: 02 00 00 00 5b 4c 89 c7 5d e9 ca c5 f6 ff 48 81 e2 00 f0 ff ff 48 f7 d2 48 21 c2 89 d1 f7 c2 81 01 00 00 75 80 e9 44 ff ff ff <0f> 0b 48 8b 2d 65 48 30 01 e9 ef fe ff ff 0f 1f 44 00 00 41 55 48 [ 222.597359] RSP: 0000:ffffbcfe9eb7bdd8 EFLAGS: 00010246 [ 222.602620] RAX: 0057ffffc0000000 RBX: ffff9eec4b3cdbf8 RCX: ffffffffffffffff [ 222.609807] RDX: 0000000000000000 RSI: ffff9eec4b3cdbf8 RDI: ffffdf55c52cf368 [ 222.616990] RBP: ffffdf55c52cf368 R08: ffffdf57428d8080 R09: 0000000000000000 [ 222.624177] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000bf8 [ 222.631361] R13: 0400000000000000 R14: 0400000000000080 R15: ffff9eec2825b1f8 [ 222.638548] FS: 00007f6754aeb700(0000) GS:ffff9f49bfd00000(0000) knlGS:0000000000000000 [ 222.646694] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 222.652481] CR2: 00007f676ffffd98 CR3: 000000012bf6a002 CR4: 00000000007726e0 [ 222.659665] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 222.666850] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 222.674031] PKRU: 55555554 [ 222.676758] Kernel panic - not syncing: Fatal exception [ 222.817538] Kernel Offset: 0x16000000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) [ 222.965540] ---[ end Kernel panic - not syncing: Fatal exception ]---
Quoted 194 lines · Igor Raits
Hi Hugh,
Quoted 4 lines · Hugh Dickins
Quoted 2 lines · Igor Raits
Hello,
Quoted 8 lines
Quoted 1 line
I've seen one weird bug on 5.12.14 that happened a couple of times when
I
Quoted 1 line
started a bunch of VMs on a server.
Would it be possible for you to try the same on a 5.12.13 kernel? Perhaps by reverting the diff between 5.12.13 and 5.12.14 temporarily. Enough to form an impression of whether the issue is new in 5.12.14.
We've been using 5.12.12 for quite some time (~ a month) and I never saw it there.
But I have to admit that I don't really have a reproducer. For example, on servers where it happened,
I just rebooted them and panic did not happen anymore (so I saw it only only once,
only on 2 servers out of 32 that we have on 5.12.14).Quoted 138 lines
I ask because 5.12.14 did include several fixes and cleanups from me to
page_vma_mapped_walk(), and that is involved in inserting and removing pmd migration entries. I am not aware of introducing any bug there, but your report has got me worried. If it's happening in 5.12.14 but not in 5.12.13, then I must look again at my changes.I don't expect Hillf's patch to help at at all: the
pmd_lock()is supposed to be taken bypage_vma_mapped_walk(), beforeset_pmd_migration_entry()andremove_migration_pmd()are called.Thanks,
HughQuoted 7 lines
I've briefly googled this problem but could not find any relevant commit that would fix this issue.
Do you have any hint how to debug this further or know the fix by any chance?
Quoted 6 lines
Thanks in advance. Stack trace following:
[ 376.876610] ------------[ cut here ]------------ [ 376.881274] kernel BUG at include/linux/swapops.h:204! [ 376.886455] invalid opcode: 0000 [#1] SMP NOPTI [ 376.891014] CPU: 40 PID: 11775 Comm: rpc-worker Tainted: GE
Quoted 5 lines
5.12.14-1.gdc.el8.x86_64 #1 [ 376.900464] Hardware name: HPE ProLiant DL380 Gen10/ProLiant DL380 Gen10, BIOS U30 05/24/2021 [ 376.909038] RIP: 0010:pmd_migration_entry_wait+0x132/0x140 [ 376.914562] Code: 02 00 00 00 5b 4c 89 c7 5d e9 8a e4 f6 ff 48 81 e200
Quoted 24 lines
f0 ff ff 48 f7 d2 48 21 c2 89 d1 f7 c2 81 01 00 00 75 80 e9 44 ff ff ff <0f> 0b 48 8b 2d 75 bd 30 01 e9 ef fe ff ff 0f 1f 44 00 00 41 55 48
[ 376.933443] RSP: 0000:ffffb65a5e1cfdc8 EFLAGS: 00010246 [ 376.938701] RAX: 0017ffffc0000000 RBX: ffff908b8ecabaf8 RCX: ffffffffffffffff [ 376.945878] RDX: 0000000000000000 RSI: ffff908b8ecabaf8 RDI: fffff497473b2ae8 [ 376.953055] RBP: fffff497473b2ae8 R08: fffff49747fa8080 R09: 0000000000000000 [ 376.960230] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000af8 [ 376.967407] R13: 0400000000000000 R14: 0400000000000080 R15: ffff908bbef7b6a8 [ 376.974582] FS: 00007f5bb1f81700(0000) GS:ffff90e87fd80000(0000) knlGS:0000000000000000 [ 376.982718] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 376.988497] CR2: 00007f5b2bfffd98 CR3: 00000001f793e006 CR4: 00000000007726e0 [ 376.995673] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 377.002849] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 377.010026] PKRU: 55555554 [ 377.012745] Call Trace:Quoted 8 lines
[ 377.015207] __handle_mm_fault+0x5ad/0x6e0 [ 377.019335] handle_mm_fault+0xc5/0x290 [ 377.023194] do_user_addr_fault+0x1cd/0x740 [ 377.027406] exc_page_fault+0x54/0x110 [ 377.031182] ? asm_exc_page_fault+0x8/0x30 [ 377.035307] asm_exc_page_fault+0x1e/0x30 [ 377.039340] RIP: 0033:0x7f5bb91d6734 [ 377.042937] Code: 89 08 48 8b 35 dd 3b 21 00 4c 8d 0d d6 3b 21 00 31c0
Quoted 14 lines
4c 39 ce 74 73 0f 1f 80 00 00 00 00 48 8d 96 40 fd ff ff 49 39 d2 74 22 <48> 8b 96 d8 03 00 00 48 01 15 4e 7c 21 00 80 be 50 03 00 00 00 c7
[ 377.061820] RSP: 002b:00007f5bb1f7ff58 EFLAGS: 00010206 [ 377.067076] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 00007f5ba0000020 [ 377.074255] RDX: 00007f5b2bfff700 RSI: 00007f5b2bfff9c0 RDI: 0000000000000001 [ 377.081429] RBP: 0000000000000001 R08: 0000000000000000 R09: 00007f5bb93ea2f0 [ 377.088606] R10: 00007f5bb1f81700 R11: 0000000000000202 R12: 0000000000000001 [ 377.095782] R13: 0000000000000006 R14: 0000000000000cb4 R15: 00007f5bb1f801f0 [ 377.102958] Modules linked in: ebt_arp(E) nft_meta_bridge(E)Quoted 9 lines
ip6_tables(E)xt_CT(E)nf_log_ipv4(E)nf_log_common(E)nft_limit(E)nft_counter(E)xt_LOG(E)xt_limit(E)xt_mac(E)xt_set(E)xt_multiport(E)xt_state(E)xt_conntrack(E)xt_comment(E)xt_physdev(E)nft_compat(E)ip_set_hash_net(E)ip_set(E)vhost_net(E)vhost(E)vhost_iotlb(E)tap(E) tun(E)tcp_diag(E)udp_diag(E)inet_diag(E)netconsole(E)nf_tables(E)vxlan(E)ip6_udp_tunnel(E)udp_tunnel(E)nfnetlink(E)binfmt_misc(E)iscsi_tcp(E)libiscsi_tcp(E)8021q(E) garp(E) mrp(E) bonding(E) tls(E) vfat(E) fat(E)dm_service_time(E)dm_multipath(E)rpcrdma(E) sunrpc(E)rdma_ucm(E)ib_srpt(E)ib_isert(E)iscsi_target_mod(E)
target_core_mod(E)Quoted 1 line
ib_iser(E)rdma_cm(E)iw_cm(E)ib_cm(E)libiscsi(E)
scsi_transport_iscsi(E)Quoted 2 lines
intel_rapl_msr(E)qedr(E)intel_rapl_common(E)ib_uverbs(E)isst_if_common(E)ib_core(E)nfit(E) libnvdimm(E)
x86_pkg_temp_thermal(E)Quoted 4 lines
intel_powerclamp(E)coretemp(E)kvm_intel(E)kvm(E) irqbypass(E)crct10dif_pclmul(E)[ 377.102999] crc32_pclmul(E) ghash_clmulni_intel(E) rapl(E)
intel_cstate(E)ipmi_ssif(E)acpi_ipmi(E)ipmi_si(E)mei_me(E)ioatdma(E)
Quoted 3 lines
ipmi_devintf(E)dm_mod(E)ses(E)intel_uncore(E)pcspkr(E) qede(E) enclosure(E) tg3(E) mei(E)lpc_ich(E)hpilo(E) hpwdt(E)intel_pch_thermal(E)dca(E)ipmi_msghandler(E)acpi_power_meter(E)ext4(E)
Quoted 2 lines
mbcache(E) jbd2(E)
sd_mod(E)t10_pi(E)sg(E) qedf(E) qed(E) crc8(E) libfcoe(E) libfc(E) smartpqi(E)scsi_transport_fc(E)
scsi_transport_sas(E)Quoted 5 lines
wmi(E)
nf_conntrack(E)nf_defrag_ipv6(E)libcrc32c(E)crc32c_intel(E)nf_defrag_ipv4(E)br_netfilter(E)bridge(E) stp(E) llc(E)[ 377.243468] ---[ end trace 04bce3bb051f7620 ]--- [ 377.385645] RIP: 0010:pmd_migration_entry_wait+0x132/0x140 [ 377.391194] Code: 02 00 00 00 5b 4c 89 c7 5d e9 8a e4 f6 ff 48 81 e200
Quoted 17 lines
f0 ff ff 48 f7 d2 48 21 c2 89 d1 f7 c2 81 01 00 00 75 80 e9 44 ff ff ff <0f> 0b 48 8b 2d 75 bd 30 01 e9 ef fe ff ff 0f 1f 44 00 00 41 55 48
[ 377.410091] RSP: 0000:ffffb65a5e1cfdc8 EFLAGS: 00010246 [ 377.415355] RAX: 0017ffffc0000000 RBX: ffff908b8ecabaf8 RCX: ffffffffffffffff [ 377.422540] RDX: 0000000000000000 RSI: ffff908b8ecabaf8 RDI: fffff497473b2ae8 [ 377.429721] RBP: fffff497473b2ae8 R08: fffff49747fa8080 R09: 0000000000000000 [ 377.436902] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000af8 [ 377.444086] R13: 0400000000000000 R14: 0400000000000080 R15: ffff908bbef7b6a8 [ 377.451272] FS: 00007f5bb1f81700(0000) GS:ffff90e87fd80000(0000) knlGS:0000000000000000 [ 377.459415] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 377.465196] CR2: 00007f5b2bfffd98 CR3: 00000001f793e006 CR4:Quoted 8 lines
00000000007726e0[ 377.472377] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 377.479556] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 377.486738] PKRU: 55555554 [ 377.489465] Kernel panic - not syncing: Fatal exception [ 377.573911] Kernel Offset: 0xa000000 from 0xffffffff81000000Quoted 5 lines
(relocation
Quoted 3 lines
range: 0xffffffff80000000-0xffffffffbfffffff)
[ 377.716482] ---[ end Kernel panic - not syncing: Fatal exception ]-----
Igor Raits
Sr. SW Engineer
+420 775 117 817
Moravske namesti 1007/14
602 00 Brno-Veveri, Czech Republic
Twitter <https://twitter.com/gooddata> | Facebook
<https://www.facebook.com/gooddata> | LinkedIn
<http://www.linkedin.com/company/gooddata> | Blog
<http://www.gooddata.com/blog>
Signature · 19 lines
Igor Raits Sr. SW Engineer [email protected] +420 775 117 817 Moravske namesti 1007/14 602 00 Brno-Veveri, Czech Republic Twitter <https://twitter.com/gooddata> | Facebook <https://www.facebook.com/gooddata> | LinkedIn <http://www.linkedin.com/company/gooddata> | Blog <http://www.gooddata.com/blog> <https://www.gooddata.com/>
Quoted 6 lines · Igor Raits
Hi everyone again,
I've been trying to reproduce this issue but still can't find a consistent pattern.
However, it did happen once more and this time on 5.13.1:
Thanks for the updates, Igor.
I have to admit that what you have reported confirms the suspicion that it's a bug introduced by one of my "stable" patches in 5.12.14 (which are also in 5.13): nothing else between 5.12.12 and 5.12.14 seems likely to be relevant.
But I've gone back and forth and not been able to spot the problem.
Please would you send (either privately to me, or to the list) your 5.13.1 kernel's .config, and disassembly of pmd_migration_entry_wait() from its vmlinux (with line numbers if available; or just send the whole vmlinux if that's easier, and I'll disassemble).
I am hoping that the disassembly, together with the register contents that you've shown, will help guide towards an answer.
Thanks,
Hugh
Quoted 328 lines
[ 222.068216] ------------[ cut here ]------------ [ 222.072884] kernel BUG at include/linux/swapops.h:204! [ 222.078062] invalid opcode: 0000 [#1] SMP NOPTI [ 222.082618] CPU: 38 PID: 9828 Comm: rpc-worker Tainted: G E 5.13.1-1.gdc.el8.x86_64 #1 [ 222.091894] Hardware name: HPE ProLiant DL380 Gen10/ProLiant DL380 Gen10, BIOS U30 05/24/2021 [ 222.100468] RIP: 0010:pmd_migration_entry_wait+0x132/0x140 [ 222.105994] Code: 02 00 00 00 5b 4c 89 c7 5d e9 ca c5 f6 ff 48 81 e2 00 f0 ff ff 48 f7 d2 48 21 c2 89 d1 f7 c2 81 01 00 00 75 80 e9 44 ff ff ff <0f> 0b 48 8b 2d 65 48 30 01 e9 ef fe ff ff 0f 1f 44 00 00 41 55 48 [ 222.124878] RSP: 0000:ffffbcfe9eb7bdd8 EFLAGS: 00010246 [ 222.130134] RAX: 0057ffffc0000000 RBX: ffff9eec4b3cdbf8 RCX: ffffffffffffffff [ 222.137309] RDX: 0000000000000000 RSI: ffff9eec4b3cdbf8 RDI: ffffdf55c52cf368 [ 222.144485] RBP: ffffdf55c52cf368 R08: ffffdf57428d8080 R09: 0000000000000000 [ 222.151661] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000bf8 [ 222.158837] R13: 0400000000000000 R14: 0400000000000080 R15: ffff9eec2825b1f8 [ 222.166015] FS: 00007f6754aeb700(0000) GS:ffff9f49bfd00000(0000) knlGS:0000000000000000 [ 222.174153] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 222.179932] CR2: 00007f676ffffd98 CR3: 000000012bf6a002 CR4: 00000000007726e0 [ 222.187109] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 222.194283] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 222.201457] PKRU: 55555554 [ 222.204178] Call Trace: [ 222.206638] __handle_mm_fault+0x5ad/0x6e0 [ 222.210760] ? sysvec_call_function_single+0xb/0x90 [ 222.215672] handle_mm_fault+0xc5/0x290 [ 222.219529] do_user_addr_fault+0x1a9/0x660 [ 222.223740] ? sched_clock_cpu+0xc/0xa0 [ 222.227602] exc_page_fault+0x68/0x130 [ 222.231373] ? asm_exc_page_fault+0x8/0x30 [ 222.235495] asm_exc_page_fault+0x1e/0x30 [ 222.239526] RIP: 0033:0x7f67baaed734 [ 222.243120] Code: 89 08 48 8b 35 dd 3b 21 00 4c 8d 0d d6 3b 21 00 31 c0 4c 39 ce 74 73 0f 1f 80 00 00 00 00 48 8d 96 40 fd ff ff 49 39 d2 74 22 <48> 8b 96 d8 03 00 00 48 01 15 4e 7c 21 00 80 be 50 03 00 00 00 c7 [ 222.262002] RSP: 002b:00007f6754aea298 EFLAGS: 00010287 [ 222.267257] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 [ 222.274432] RDX: 00007f676ffff700 RSI: 00007f676ffff9c0 RDI: 00007f676f7fec10 [ 222.281609] RBP: 0000000000000001 R08: 00007f676f7fed10 R09: 00007f67bad012f0 [ 222.288785] R10: 00007f6754aeb700 R11: 0000000000000202 R12: 0000000000000001 [ 222.295961] R13: 0000000000000006 R14: 0000000000000e28 R15: 00007f674006e1f0 [ 222.303137] Modules linked in: vhost_net(E) vhost(E) vhost_iotlb(E)tap(E) tun(E)
tcp_diag(E)udp_diag(E)inet_diag(E)netconsole(E)nf_tables(E)vxlan(E)ip6_udp_tunnel(E)udp_tunnel(E)nfnetlink(E)binfmt_misc(E)iscsi_tcp(E)libiscsi_tcp(E)8021q(E) garp(E) mrp(E) bonding(E) tls(E) vfat(E) fat(E)dm_service_time(E)dm_multipath(E)rpcrdma(E) sunrpc(E)rdma_ucm(E)ib_srpt(E)ib_isert(E)iscsi_target_mod(E)target_core_mod(E)ib_iser(E)rdma_cm(E)iw_cm(E)ib_cm(E)libiscsi(E)intel_rapl_msr(E)intel_rapl_common(E)scsi_transport_iscsi(E)isst_if_common(E)ipmi_ssif(E)nfit(E) libnvdimm(E)x86_pkg_temp_thermal(E)intel_powerclamp(E)coretemp(E)kvm_intel(E)kvm(E) irqbypass(E)crct10dif_pclmul(E)crc32_pclmul(E)ghash_clmulni_intel(E)rapl(E) qedr(E)mei_me(E)acpi_ipmi(E)ib_uverbs(E)intel_cstate(E)ipmi_si(E)ib_core(E)ipmi_devintf(E)dm_mod(E)ioatdma(E) ses(E)intel_uncore(E)pcspkr(E) enclosure(E) mei(E) hpwdt(E) hpilo(E)lpc_ich(E)intel_pch_thermal(E)dca(E)ipmi_msghandler(E)[ 222.303181] acpi_power_meter(E) ext4(E) mbcache(E) jbd2(E) sd_mod(E)
t10_pi(E)sg(E) qedf(E) qede(E) libfcoe(E) qed(E) libfc(E) smartpqi(E)scsi_transport_fc(E)tg3(E)scsi_transport_sas(E)crc8(E) wmi(E)nf_conntrack(E)libcrc32c(E)crc32c_intel(E)nf_defrag_ipv6(E)nf_defrag_ipv4(E)br_netfilter(E)bridge(E) stp(E) llc(E)[ 222.420050] ---[ end trace bcf7b6d1610cc21f ]--- [ 222.572925] RIP: 0010:pmd_migration_entry_wait+0x132/0x140 [ 222.578469] Code: 02 00 00 00 5b 4c 89 c7 5d e9 ca c5 f6 ff 48 81 e2 00 f0 ff ff 48 f7 d2 48 21 c2 89 d1 f7 c2 81 01 00 00 75 80 e9 44 ff ff ff <0f> 0b 48 8b 2d 65 48 30 01 e9 ef fe ff ff 0f 1f 44 00 00 41 55 48 [ 222.597359] RSP: 0000:ffffbcfe9eb7bdd8 EFLAGS: 00010246 [ 222.602620] RAX: 0057ffffc0000000 RBX: ffff9eec4b3cdbf8 RCX: ffffffffffffffff [ 222.609807] RDX: 0000000000000000 RSI: ffff9eec4b3cdbf8 RDI: ffffdf55c52cf368 [ 222.616990] RBP: ffffdf55c52cf368 R08: ffffdf57428d8080 R09: 0000000000000000 [ 222.624177] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000bf8 [ 222.631361] R13: 0400000000000000 R14: 0400000000000080 R15: ffff9eec2825b1f8 [ 222.638548] FS: 00007f6754aeb700(0000) GS:ffff9f49bfd00000(0000) knlGS:0000000000000000 [ 222.646694] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 222.652481] CR2: 00007f676ffffd98 CR3: 000000012bf6a002 CR4: 00000000007726e0 [ 222.659665] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 222.666850] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 222.674031] PKRU: 55555554 [ 222.676758] Kernel panic - not syncing: Fatal exception [ 222.817538] Kernel Offset: 0x16000000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) [ 222.965540] ---[ end Kernel panic - not syncing: Fatal exception ]---Quoted 194 lines · Igor Raits
Hi Hugh,
Quoted 4 lines · Hugh Dickins
Quoted 2 lines · Igor Raits
Hello,
Quoted 8 lines
Quoted 1 line
I've seen one weird bug on 5.12.14 that happened a couple of times when
I
Quoted 1 line
started a bunch of VMs on a server.
Would it be possible for you to try the same on a 5.12.13 kernel? Perhaps by reverting the diff between 5.12.13 and 5.12.14 temporarily. Enough to form an impression of whether the issue is new in 5.12.14.
We've been using 5.12.12 for quite some time (~ a month) and I never saw it there.
But I have to admit that I don't really have a reproducer. For example, on servers where it happened,
I just rebooted them and panic did not happen anymore (so I saw it only only once,
only on 2 servers out of 32 that we have on 5.12.14).Quoted 138 lines
I ask because 5.12.14 did include several fixes and cleanups from me to
page_vma_mapped_walk(), and that is involved in inserting and removing pmd migration entries. I am not aware of introducing any bug there, but your report has got me worried. If it's happening in 5.12.14 but not in 5.12.13, then I must look again at my changes.I don't expect Hillf's patch to help at at all: the
pmd_lock()is supposed to be taken bypage_vma_mapped_walk(), beforeset_pmd_migration_entry()andremove_migration_pmd()are called.Thanks,
HughQuoted 7 lines
I've briefly googled this problem but could not find any relevant commit that would fix this issue.
Do you have any hint how to debug this further or know the fix by any chance?
Quoted 6 lines
Thanks in advance. Stack trace following:
[ 376.876610] ------------[ cut here ]------------ [ 376.881274] kernel BUG at include/linux/swapops.h:204! [ 376.886455] invalid opcode: 0000 [#1] SMP NOPTI [ 376.891014] CPU: 40 PID: 11775 Comm: rpc-worker Tainted: GE
Quoted 5 lines
5.12.14-1.gdc.el8.x86_64 #1 [ 376.900464] Hardware name: HPE ProLiant DL380 Gen10/ProLiant DL380 Gen10, BIOS U30 05/24/2021 [ 376.909038] RIP: 0010:pmd_migration_entry_wait+0x132/0x140 [ 376.914562] Code: 02 00 00 00 5b 4c 89 c7 5d e9 8a e4 f6 ff 48 81 e200
Quoted 24 lines
f0 ff ff 48 f7 d2 48 21 c2 89 d1 f7 c2 81 01 00 00 75 80 e9 44 ff ff ff <0f> 0b 48 8b 2d 75 bd 30 01 e9 ef fe ff ff 0f 1f 44 00 00 41 55 48
[ 376.933443] RSP: 0000:ffffb65a5e1cfdc8 EFLAGS: 00010246 [ 376.938701] RAX: 0017ffffc0000000 RBX: ffff908b8ecabaf8 RCX: ffffffffffffffff [ 376.945878] RDX: 0000000000000000 RSI: ffff908b8ecabaf8 RDI: fffff497473b2ae8 [ 376.953055] RBP: fffff497473b2ae8 R08: fffff49747fa8080 R09: 0000000000000000 [ 376.960230] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000af8 [ 376.967407] R13: 0400000000000000 R14: 0400000000000080 R15: ffff908bbef7b6a8 [ 376.974582] FS: 00007f5bb1f81700(0000) GS:ffff90e87fd80000(0000) knlGS:0000000000000000 [ 376.982718] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 376.988497] CR2: 00007f5b2bfffd98 CR3: 00000001f793e006 CR4: 00000000007726e0 [ 376.995673] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 377.002849] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 377.010026] PKRU: 55555554 [ 377.012745] Call Trace:Quoted 8 lines
[ 377.015207] __handle_mm_fault+0x5ad/0x6e0 [ 377.019335] handle_mm_fault+0xc5/0x290 [ 377.023194] do_user_addr_fault+0x1cd/0x740 [ 377.027406] exc_page_fault+0x54/0x110 [ 377.031182] ? asm_exc_page_fault+0x8/0x30 [ 377.035307] asm_exc_page_fault+0x1e/0x30 [ 377.039340] RIP: 0033:0x7f5bb91d6734 [ 377.042937] Code: 89 08 48 8b 35 dd 3b 21 00 4c 8d 0d d6 3b 21 00 31c0
Quoted 14 lines
4c 39 ce 74 73 0f 1f 80 00 00 00 00 48 8d 96 40 fd ff ff 49 39 d2 74 22 <48> 8b 96 d8 03 00 00 48 01 15 4e 7c 21 00 80 be 50 03 00 00 00 c7
[ 377.061820] RSP: 002b:00007f5bb1f7ff58 EFLAGS: 00010206 [ 377.067076] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 00007f5ba0000020 [ 377.074255] RDX: 00007f5b2bfff700 RSI: 00007f5b2bfff9c0 RDI: 0000000000000001 [ 377.081429] RBP: 0000000000000001 R08: 0000000000000000 R09: 00007f5bb93ea2f0 [ 377.088606] R10: 00007f5bb1f81700 R11: 0000000000000202 R12: 0000000000000001 [ 377.095782] R13: 0000000000000006 R14: 0000000000000cb4 R15: 00007f5bb1f801f0 [ 377.102958] Modules linked in: ebt_arp(E) nft_meta_bridge(E)Quoted 9 lines
ip6_tables(E)xt_CT(E)nf_log_ipv4(E)nf_log_common(E)nft_limit(E)nft_counter(E)xt_LOG(E)xt_limit(E)xt_mac(E)xt_set(E)xt_multiport(E)xt_state(E)xt_conntrack(E)xt_comment(E)xt_physdev(E)nft_compat(E)ip_set_hash_net(E)ip_set(E)vhost_net(E)vhost(E)vhost_iotlb(E)tap(E) tun(E)tcp_diag(E)udp_diag(E)inet_diag(E)netconsole(E)nf_tables(E)vxlan(E)ip6_udp_tunnel(E)udp_tunnel(E)nfnetlink(E)binfmt_misc(E)iscsi_tcp(E)libiscsi_tcp(E)8021q(E) garp(E) mrp(E) bonding(E) tls(E) vfat(E) fat(E)dm_service_time(E)dm_multipath(E)rpcrdma(E) sunrpc(E)rdma_ucm(E)ib_srpt(E)ib_isert(E)iscsi_target_mod(E)
target_core_mod(E)Quoted 1 line
ib_iser(E)rdma_cm(E)iw_cm(E)ib_cm(E)libiscsi(E)
scsi_transport_iscsi(E)Quoted 2 lines
intel_rapl_msr(E)qedr(E)intel_rapl_common(E)ib_uverbs(E)isst_if_common(E)ib_core(E)nfit(E) libnvdimm(E)
x86_pkg_temp_thermal(E)Quoted 4 lines
intel_powerclamp(E)coretemp(E)kvm_intel(E)kvm(E) irqbypass(E)crct10dif_pclmul(E)[ 377.102999] crc32_pclmul(E) ghash_clmulni_intel(E) rapl(E)
intel_cstate(E)ipmi_ssif(E)acpi_ipmi(E)ipmi_si(E)mei_me(E)ioatdma(E)
Quoted 3 lines
ipmi_devintf(E)dm_mod(E)ses(E)intel_uncore(E)pcspkr(E) qede(E) enclosure(E) tg3(E) mei(E)lpc_ich(E)hpilo(E) hpwdt(E)intel_pch_thermal(E)dca(E)ipmi_msghandler(E)acpi_power_meter(E)ext4(E)
Quoted 2 lines
mbcache(E) jbd2(E)
sd_mod(E)t10_pi(E)sg(E) qedf(E) qed(E) crc8(E) libfcoe(E) libfc(E) smartpqi(E)scsi_transport_fc(E)
scsi_transport_sas(E)Quoted 5 lines
wmi(E)
nf_conntrack(E)nf_defrag_ipv6(E)libcrc32c(E)crc32c_intel(E)nf_defrag_ipv4(E)br_netfilter(E)bridge(E) stp(E) llc(E)[ 377.243468] ---[ end trace 04bce3bb051f7620 ]--- [ 377.385645] RIP: 0010:pmd_migration_entry_wait+0x132/0x140 [ 377.391194] Code: 02 00 00 00 5b 4c 89 c7 5d e9 8a e4 f6 ff 48 81 e200
Quoted 17 lines
f0 ff ff 48 f7 d2 48 21 c2 89 d1 f7 c2 81 01 00 00 75 80 e9 44 ff ff ff <0f> 0b 48 8b 2d 75 bd 30 01 e9 ef fe ff ff 0f 1f 44 00 00 41 55 48
[ 377.410091] RSP: 0000:ffffb65a5e1cfdc8 EFLAGS: 00010246 [ 377.415355] RAX: 0017ffffc0000000 RBX: ffff908b8ecabaf8 RCX: ffffffffffffffff [ 377.422540] RDX: 0000000000000000 RSI: ffff908b8ecabaf8 RDI: fffff497473b2ae8 [ 377.429721] RBP: fffff497473b2ae8 R08: fffff49747fa8080 R09: 0000000000000000 [ 377.436902] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000af8 [ 377.444086] R13: 0400000000000000 R14: 0400000000000080 R15: ffff908bbef7b6a8 [ 377.451272] FS: 00007f5bb1f81700(0000) GS:ffff90e87fd80000(0000) knlGS:0000000000000000 [ 377.459415] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 377.465196] CR2: 00007f5b2bfffd98 CR3: 00000001f793e006 CR4:Quoted 8 lines
00000000007726e0[ 377.472377] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 377.479556] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 377.486738] PKRU: 55555554 [ 377.489465] Kernel panic - not syncing: Fatal exception [ 377.573911] Kernel Offset: 0xa000000 from 0xffffffff81000000Quoted 5 lines
(relocation
Quoted 3 lines
range: 0xffffffff80000000-0xffffffffbfffffff)
[ 377.716482] ---[ end Kernel panic - not syncing: Fatal exception ]-----
Igor Raits
Sr. SW Engineer
+420 775 117 817
Moravske namesti 1007/14
602 00 Brno-Veveri, Czech Republic
Twitter <https://twitter.com/gooddata> | Facebook
<https://www.facebook.com/gooddata> | LinkedIn
<http://www.linkedin.com/company/gooddata> | Blog
<http://www.gooddata.com/blog>Signature · 19 lines
Igor Raits Sr. SW Engineer [email protected] +420 775 117 817 Moravske namesti 1007/14 602 00 Brno-Veveri, Czech Republic Twitter <https://twitter.com/gooddata> | Facebook <https://www.facebook.com/gooddata> | LinkedIn <http://www.linkedin.com/company/gooddata> | Blog <http://www.gooddata.com/blog> <https://www.gooddata.com/>
Hi Peter,
I believe you have already fixed this, but the fix needs to go to stable. Sorry, the messages below are a muddle of top and middle posting, I'll resume at the bottom.
Quoted 23 lines · Hugh Dickins
Quoted 6 lines · Igor Raits
Hi everyone again,
I've been trying to reproduce this issue but still can't find a consistent pattern.
However, it did happen once more and this time on 5.13.1:
Thanks for the updates, Igor.
I have to admit that what you have reported confirms the suspicion that it's a bug introduced by one of my "stable" patches in 5.12.14 (which are also in 5.13): nothing else between 5.12.12 and 5.12.14 seems likely to be relevant.
But I've gone back and forth and not been able to spot the problem.
Please would you send (either privately to me, or to the list) your 5.13.1 kernel's .config, and disassembly of
pmd_migration_entry_wait()from its vmlinux (with line numbers if available; or just send the whole vmlinux if that's easier, and I'll disassemble).
Quoted 284 lines
I am hoping that the disassembly, together with the register contents that you've shown, will help guide towards an answer.
Thanks,
HughQuoted 278 lines
[ 222.068216] ------------[ cut here ]------------ [ 222.072884] kernel BUG at include/linux/swapops.h:204! [ 222.078062] invalid opcode: 0000 [#1] SMP NOPTI [ 222.082618] CPU: 38 PID: 9828 Comm: rpc-worker Tainted: G E 5.13.1-1.gdc.el8.x86_64 #1 [ 222.091894] Hardware name: HPE ProLiant DL380 Gen10/ProLiant DL380 Gen10, BIOS U30 05/24/2021 [ 222.100468] RIP: 0010:pmd_migration_entry_wait+0x132/0x140 [ 222.105994] Code: 02 00 00 00 5b 4c 89 c7 5d e9 ca c5 f6 ff 48 81 e2 00 f0 ff ff 48 f7 d2 48 21 c2 89 d1 f7 c2 81 01 00 00 75 80 e9 44 ff ff ff <0f> 0b 48 8b 2d 65 48 30 01 e9 ef fe ff ff 0f 1f 44 00 00 41 55 48 [ 222.124878] RSP: 0000:ffffbcfe9eb7bdd8 EFLAGS: 00010246 [ 222.130134] RAX: 0057ffffc0000000 RBX: ffff9eec4b3cdbf8 RCX: ffffffffffffffff [ 222.137309] RDX: 0000000000000000 RSI: ffff9eec4b3cdbf8 RDI: ffffdf55c52cf368 [ 222.144485] RBP: ffffdf55c52cf368 R08: ffffdf57428d8080 R09: 0000000000000000 [ 222.151661] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000bf8 [ 222.158837] R13: 0400000000000000 R14: 0400000000000080 R15: ffff9eec2825b1f8 [ 222.166015] FS: 00007f6754aeb700(0000) GS:ffff9f49bfd00000(0000) knlGS:0000000000000000 [ 222.174153] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 222.179932] CR2: 00007f676ffffd98 CR3: 000000012bf6a002 CR4: 00000000007726e0 [ 222.187109] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 222.194283] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 222.201457] PKRU: 55555554 [ 222.204178] Call Trace: [ 222.206638] __handle_mm_fault+0x5ad/0x6e0 [ 222.210760] ? sysvec_call_function_single+0xb/0x90 [ 222.215672] handle_mm_fault+0xc5/0x290 [ 222.219529] do_user_addr_fault+0x1a9/0x660 [ 222.223740] ? sched_clock_cpu+0xc/0xa0 [ 222.227602] exc_page_fault+0x68/0x130 [ 222.231373] ? asm_exc_page_fault+0x8/0x30 [ 222.235495] asm_exc_page_fault+0x1e/0x30 [ 222.239526] RIP: 0033:0x7f67baaed734 [ 222.243120] Code: 89 08 48 8b 35 dd 3b 21 00 4c 8d 0d d6 3b 21 00 31 c0 4c 39 ce 74 73 0f 1f 80 00 00 00 00 48 8d 96 40 fd ff ff 49 39 d2 74 22 <48> 8b 96 d8 03 00 00 48 01 15 4e 7c 21 00 80 be 50 03 00 00 00 c7 [ 222.262002] RSP: 002b:00007f6754aea298 EFLAGS: 00010287 [ 222.267257] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 [ 222.274432] RDX: 00007f676ffff700 RSI: 00007f676ffff9c0 RDI: 00007f676f7fec10 [ 222.281609] RBP: 0000000000000001 R08: 00007f676f7fed10 R09: 00007f67bad012f0 [ 222.288785] R10: 00007f6754aeb700 R11: 0000000000000202 R12: 0000000000000001 [ 222.295961] R13: 0000000000000006 R14: 0000000000000e28 R15: 00007f674006e1f0 [ 222.303137] Modules linked in: vhost_net(E) vhost(E) vhost_iotlb(E)tap(E) tun(E)
tcp_diag(E)udp_diag(E)inet_diag(E)netconsole(E)nf_tables(E)vxlan(E)ip6_udp_tunnel(E)udp_tunnel(E)nfnetlink(E)binfmt_misc(E)iscsi_tcp(E)libiscsi_tcp(E)8021q(E) garp(E) mrp(E) bonding(E) tls(E) vfat(E) fat(E)dm_service_time(E)dm_multipath(E)rpcrdma(E) sunrpc(E)rdma_ucm(E)ib_srpt(E)ib_isert(E)iscsi_target_mod(E)target_core_mod(E)ib_iser(E)rdma_cm(E)iw_cm(E)ib_cm(E)libiscsi(E)intel_rapl_msr(E)intel_rapl_common(E)scsi_transport_iscsi(E)isst_if_common(E)ipmi_ssif(E)nfit(E) libnvdimm(E)x86_pkg_temp_thermal(E)intel_powerclamp(E)coretemp(E)kvm_intel(E)kvm(E) irqbypass(E)crct10dif_pclmul(E)crc32_pclmul(E)ghash_clmulni_intel(E)rapl(E) qedr(E)mei_me(E)acpi_ipmi(E)ib_uverbs(E)intel_cstate(E)ipmi_si(E)ib_core(E)ipmi_devintf(E)dm_mod(E)ioatdma(E) ses(E)intel_uncore(E)pcspkr(E) enclosure(E) mei(E) hpwdt(E) hpilo(E)lpc_ich(E)intel_pch_thermal(E)dca(E)ipmi_msghandler(E)[ 222.303181] acpi_power_meter(E) ext4(E) mbcache(E) jbd2(E) sd_mod(E)
t10_pi(E)sg(E) qedf(E) qede(E) libfcoe(E) qed(E) libfc(E) smartpqi(E)scsi_transport_fc(E)tg3(E)scsi_transport_sas(E)crc8(E) wmi(E)nf_conntrack(E)libcrc32c(E)crc32c_intel(E)nf_defrag_ipv6(E)nf_defrag_ipv4(E)br_netfilter(E)bridge(E) stp(E) llc(E)[ 222.420050] ---[ end trace bcf7b6d1610cc21f ]--- [ 222.572925] RIP: 0010:pmd_migration_entry_wait+0x132/0x140 [ 222.578469] Code: 02 00 00 00 5b 4c 89 c7 5d e9 ca c5 f6 ff 48 81 e2 00 f0 ff ff 48 f7 d2 48 21 c2 89 d1 f7 c2 81 01 00 00 75 80 e9 44 ff ff ff <0f> 0b 48 8b 2d 65 48 30 01 e9 ef fe ff ff 0f 1f 44 00 00 41 55 48 [ 222.597359] RSP: 0000:ffffbcfe9eb7bdd8 EFLAGS: 00010246 [ 222.602620] RAX: 0057ffffc0000000 RBX: ffff9eec4b3cdbf8 RCX: ffffffffffffffff [ 222.609807] RDX: 0000000000000000 RSI: ffff9eec4b3cdbf8 RDI: ffffdf55c52cf368 [ 222.616990] RBP: ffffdf55c52cf368 R08: ffffdf57428d8080 R09: 0000000000000000 [ 222.624177] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000bf8 [ 222.631361] R13: 0400000000000000 R14: 0400000000000080 R15: ffff9eec2825b1f8 [ 222.638548] FS: 00007f6754aeb700(0000) GS:ffff9f49bfd00000(0000) knlGS:0000000000000000 [ 222.646694] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 222.652481] CR2: 00007f676ffffd98 CR3: 000000012bf6a002 CR4: 00000000007726e0 [ 222.659665] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 222.666850] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 222.674031] PKRU: 55555554 [ 222.676758] Kernel panic - not syncing: Fatal exception [ 222.817538] Kernel Offset: 0x16000000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) [ 222.965540] ---[ end Kernel panic - not syncing: Fatal exception ]---Quoted 168 lines · Igor Raits
Hi Hugh,
Quoted 4 lines · Hugh Dickins
Quoted 2 lines · Igor Raits
Hello,
Quoted 8 lines
Quoted 1 line
I've seen one weird bug on 5.12.14 that happened a couple of times when
I
Quoted 1 line
started a bunch of VMs on a server.
Would it be possible for you to try the same on a 5.12.13 kernel? Perhaps by reverting the diff between 5.12.13 and 5.12.14 temporarily. Enough to form an impression of whether the issue is new in 5.12.14.
We've been using 5.12.12 for quite some time (~ a month) and I never saw it there.
But I have to admit that I don't really have a reproducer. For example, on servers where it happened,
I just rebooted them and panic did not happen anymore (so I saw it only only once,
only on 2 servers out of 32 that we have on 5.12.14).Quoted 141 lines
I ask because 5.12.14 did include several fixes and cleanups from me to
page_vma_mapped_walk(), and that is involved in inserting and removing pmd migration entries. I am not aware of introducing any bug there, but your report has got me worried. If it's happening in 5.12.14 but not in 5.12.13, then I must look again at my changes.I don't expect Hillf's patch to help at at all: the
pmd_lock()is supposed to be taken bypage_vma_mapped_walk(), beforeset_pmd_migration_entry()andremove_migration_pmd()are called.Thanks,
HughQuoted 7 lines
I've briefly googled this problem but could not find any relevant commit that would fix this issue.
Do you have any hint how to debug this further or know the fix by any chance?
Quoted 6 lines
Thanks in advance. Stack trace following:
[ 376.876610] ------------[ cut here ]------------ [ 376.881274] kernel BUG at include/linux/swapops.h:204! [ 376.886455] invalid opcode: 0000 [#1] SMP NOPTI [ 376.891014] CPU: 40 PID: 11775 Comm: rpc-worker Tainted: GE
Quoted 5 lines
5.12.14-1.gdc.el8.x86_64 #1 [ 376.900464] Hardware name: HPE ProLiant DL380 Gen10/ProLiant DL380 Gen10, BIOS U30 05/24/2021 [ 376.909038] RIP: 0010:pmd_migration_entry_wait+0x132/0x140 [ 376.914562] Code: 02 00 00 00 5b 4c 89 c7 5d e9 8a e4 f6 ff 48 81 e200
Quoted 24 lines
f0 ff ff 48 f7 d2 48 21 c2 89 d1 f7 c2 81 01 00 00 75 80 e9 44 ff ff ff <0f> 0b 48 8b 2d 75 bd 30 01 e9 ef fe ff ff 0f 1f 44 00 00 41 55 48
[ 376.933443] RSP: 0000:ffffb65a5e1cfdc8 EFLAGS: 00010246 [ 376.938701] RAX: 0017ffffc0000000 RBX: ffff908b8ecabaf8 RCX: ffffffffffffffff [ 376.945878] RDX: 0000000000000000 RSI: ffff908b8ecabaf8 RDI: fffff497473b2ae8 [ 376.953055] RBP: fffff497473b2ae8 R08: fffff49747fa8080 R09: 0000000000000000 [ 376.960230] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000af8 [ 376.967407] R13: 0400000000000000 R14: 0400000000000080 R15: ffff908bbef7b6a8 [ 376.974582] FS: 00007f5bb1f81700(0000) GS:ffff90e87fd80000(0000) knlGS:0000000000000000 [ 376.982718] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 376.988497] CR2: 00007f5b2bfffd98 CR3: 00000001f793e006 CR4: 00000000007726e0 [ 376.995673] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 377.002849] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 377.010026] PKRU: 55555554 [ 377.012745] Call Trace:Quoted 8 lines
[ 377.015207] __handle_mm_fault+0x5ad/0x6e0 [ 377.019335] handle_mm_fault+0xc5/0x290 [ 377.023194] do_user_addr_fault+0x1cd/0x740 [ 377.027406] exc_page_fault+0x54/0x110 [ 377.031182] ? asm_exc_page_fault+0x8/0x30 [ 377.035307] asm_exc_page_fault+0x1e/0x30 [ 377.039340] RIP: 0033:0x7f5bb91d6734 [ 377.042937] Code: 89 08 48 8b 35 dd 3b 21 00 4c 8d 0d d6 3b 21 00 31c0
Quoted 14 lines
4c 39 ce 74 73 0f 1f 80 00 00 00 00 48 8d 96 40 fd ff ff 49 39 d2 74 22 <48> 8b 96 d8 03 00 00 48 01 15 4e 7c 21 00 80 be 50 03 00 00 00 c7
[ 377.061820] RSP: 002b:00007f5bb1f7ff58 EFLAGS: 00010206 [ 377.067076] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 00007f5ba0000020 [ 377.074255] RDX: 00007f5b2bfff700 RSI: 00007f5b2bfff9c0 RDI: 0000000000000001 [ 377.081429] RBP: 0000000000000001 R08: 0000000000000000 R09: 00007f5bb93ea2f0 [ 377.088606] R10: 00007f5bb1f81700 R11: 0000000000000202 R12: 0000000000000001 [ 377.095782] R13: 0000000000000006 R14: 0000000000000cb4 R15: 00007f5bb1f801f0 [ 377.102958] Modules linked in: ebt_arp(E) nft_meta_bridge(E)Quoted 9 lines
ip6_tables(E)xt_CT(E)nf_log_ipv4(E)nf_log_common(E)nft_limit(E)nft_counter(E)xt_LOG(E)xt_limit(E)xt_mac(E)xt_set(E)xt_multiport(E)xt_state(E)xt_conntrack(E)xt_comment(E)xt_physdev(E)nft_compat(E)ip_set_hash_net(E)ip_set(E)vhost_net(E)vhost(E)vhost_iotlb(E)tap(E) tun(E)tcp_diag(E)udp_diag(E)inet_diag(E)netconsole(E)nf_tables(E)vxlan(E)ip6_udp_tunnel(E)udp_tunnel(E)nfnetlink(E)binfmt_misc(E)iscsi_tcp(E)libiscsi_tcp(E)8021q(E) garp(E) mrp(E) bonding(E) tls(E) vfat(E) fat(E)dm_service_time(E)dm_multipath(E)rpcrdma(E) sunrpc(E)rdma_ucm(E)ib_srpt(E)ib_isert(E)iscsi_target_mod(E)
target_core_mod(E)Quoted 1 line
ib_iser(E)rdma_cm(E)iw_cm(E)ib_cm(E)libiscsi(E)
scsi_transport_iscsi(E)Quoted 2 lines
intel_rapl_msr(E)qedr(E)intel_rapl_common(E)ib_uverbs(E)isst_if_common(E)ib_core(E)nfit(E) libnvdimm(E)
x86_pkg_temp_thermal(E)Quoted 4 lines
intel_powerclamp(E)coretemp(E)kvm_intel(E)kvm(E) irqbypass(E)crct10dif_pclmul(E)[ 377.102999] crc32_pclmul(E) ghash_clmulni_intel(E) rapl(E)
intel_cstate(E)ipmi_ssif(E)acpi_ipmi(E)ipmi_si(E)mei_me(E)ioatdma(E)
Quoted 3 lines
ipmi_devintf(E)dm_mod(E)ses(E)intel_uncore(E)pcspkr(E) qede(E) enclosure(E) tg3(E) mei(E)lpc_ich(E)hpilo(E) hpwdt(E)intel_pch_thermal(E)dca(E)ipmi_msghandler(E)acpi_power_meter(E)ext4(E)
Quoted 2 lines
mbcache(E) jbd2(E)
sd_mod(E)t10_pi(E)sg(E) qedf(E) qed(E) crc8(E) libfcoe(E) libfc(E) smartpqi(E)scsi_transport_fc(E)
scsi_transport_sas(E)Quoted 5 lines
wmi(E)
nf_conntrack(E)nf_defrag_ipv6(E)libcrc32c(E)crc32c_intel(E)nf_defrag_ipv4(E)br_netfilter(E)bridge(E) stp(E) llc(E)[ 377.243468] ---[ end trace 04bce3bb051f7620 ]--- [ 377.385645] RIP: 0010:pmd_migration_entry_wait+0x132/0x140 [ 377.391194] Code: 02 00 00 00 5b 4c 89 c7 5d e9 8a e4 f6 ff 48 81 e200
Quoted 17 lines
f0 ff ff 48 f7 d2 48 21 c2 89 d1 f7 c2 81 01 00 00 75 80 e9 44 ff ff ff <0f> 0b 48 8b 2d 75 bd 30 01 e9 ef fe ff ff 0f 1f 44 00 00 41 55 48
[ 377.410091] RSP: 0000:ffffb65a5e1cfdc8 EFLAGS: 00010246 [ 377.415355] RAX: 0017ffffc0000000 RBX: ffff908b8ecabaf8 RCX: ffffffffffffffff [ 377.422540] RDX: 0000000000000000 RSI: ffff908b8ecabaf8 RDI: fffff497473b2ae8 [ 377.429721] RBP: fffff497473b2ae8 R08: fffff49747fa8080 R09: 0000000000000000 [ 377.436902] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000af8 [ 377.444086] R13: 0400000000000000 R14: 0400000000000080 R15: ffff908bbef7b6a8 [ 377.451272] FS: 00007f5bb1f81700(0000) GS:ffff90e87fd80000(0000) knlGS:0000000000000000 [ 377.459415] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 377.465196] CR2: 00007f5b2bfffd98 CR3: 00000001f793e006 CR4:Quoted 8 lines
00000000007726e0[ 377.472377] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 377.479556] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 377.486738] PKRU: 55555554 [ 377.489465] Kernel panic - not syncing: Fatal exception [ 377.573911] Kernel Offset: 0xa000000 from 0xffffffff81000000(relocation
Quoted 2 lines
range: 0xffffffff80000000-0xffffffffbfffffff)
[ 377.716482] ---[ end Kernel panic - not syncing: Fatal exception ]---
Disassembly of the vmlinux Igor sent (along with other info) confirmed something I suspected, that R08: fffff49747fa8080 in one of the dumps,
R08: ffffdf57428d8080 in the other, is the relevant struct page pointer (and RAX the page->flags, which look like it was pointing at a good page).
A page pointer ....8080 in pmd_migration_entry_wait() is interesting:
normally I'd expect that to be ....0000 or ....8000, pointing to the head of a huge page. But instead it's pointing to the second tail (though by now that compound page has been freed, and head pointers in the tails reset to 0): as if the pfn has been incremented by 2 somehow.
And if the pfn (swp_offset) in the migration entry has got corrupted, then it's no surprise that when removing migration entries, page_vma_mapped_walk() would see migration_entry_to_page(entry) != page, so be unable to replace that migration entry, leaving it behind for the user to hit BUG_ON(!PageLocked) in pmd_migration_entry_wait() when faulting on it later.
So, what might increment the swp_offset by 2? Hunt around the encodings. Hmm, _PAGE_BIT_UFFD_WP is _PAGE_BIT_SOFTW2 which is bit 10, whereas _PAGE_BIT_PROTNONE (top bit to be avoided in pte encoding of swap) is _PAGE_BIT_GLOBAL is bit 8. After overcoming off-by-one confusions, it looks like if something somewhere were to set _PAGE_BIT_UFFD_WP in a migration pmd (whereas it's only suitable for a present pmd), it would indeed increment the swp_offset by 2.
Hunt for uffd_wps, and run across copy_huge_pmd() in mm/huge_memory.c:
in Igor's 5.13.1 and 5.12.14 and many others, that says
if (!(vma->vm_flags & VM_UFFD_WP)) pmd = pmd_clear_uffd_wp(pmd);
just *before* checking is_swap_pmd(). Fixed in 5.14-rc1 in commit 8f34f1eac382 ("mm/userfaultfd: fix uffd-wp special cases for fork()").
But clearing the bit would be harmless, wouldn't it? Because it wouldn't be set anyway. Waste a day before remembering what I never forgot but somehow blanked out: the L1TF "feature" forced us to invert the offset bits in the pte encoding of a swap entry, so there really is a bit set there in the pmd entry, and clearing it has the effect of setting it in the corresponding swap entry, so incrementing the migration pfn by 2.
I cannot explain why Igor never saw this crash on 5.12.12: maybe something else in the environment changed around that time. And it will take several days for it to be confirmed as the fix in practice.
But I'm confident that 8f34f1eac382 will prove to be the fix, so Peter please prepare some backports of that for the various stable/longterm kernels that need it - I've not looked into whether it applies cleanly, or depends on other commits too. You fixed several related but different things in that commit: but this one is the worst, because it can corrupt even those who are not using UFFD_WP at all.
Many thans for reporting and helping, Igor.
Hugh
p.s. Peter, unrelated to this particular bug, and should not divert from fixing it: but looking again at those swap encodings, and particularly the soft_dirty manipulations: they look very fragile. I think uffd_wp was wrong to follow that bad example, and your upcoming new encoding (that I have previously called elegant) takes it a worse step further.
I think we should change to a rule where the architecture-independent swp_entry_t contains *all* the info, including bits for soft_dirty and uffd_wp, so that swap entry cases can move immediately to decoding from arch-dependent pte to arch-independent swp_entry_t, and do all the manipulations on that. But I don't have time to make that change, and probably neither do you, and making the change is liable to introduce errors itself. So, no immediate plans, but please keep in mind.
Quoted 1 line · Hugh Dickins
Hi Peter,
Hi, Hugh,
Quoted 358 lines
I believe you have already fixed this, but the fix needs to go to stable. Sorry, the messages below are a muddle of top and middle posting, I'll resume at the bottom.
Quoted 23 lines · Hugh Dickins
Quoted 6 lines · Igor Raits
Hi everyone again,
I've been trying to reproduce this issue but still can't find a consistent pattern.
However, it did happen once more and this time on 5.13.1:
Thanks for the updates, Igor.
I have to admit that what you have reported confirms the suspicion that it's a bug introduced by one of my "stable" patches in 5.12.14 (which are also in 5.13): nothing else between 5.12.12 and 5.12.14 seems likely to be relevant.
But I've gone back and forth and not been able to spot the problem.
Please would you send (either privately to me, or to the list) your 5.13.1 kernel's .config, and disassembly of
pmd_migration_entry_wait()from its vmlinux (with line numbers if available; or just send the whole vmlinux if that's easier, and I'll disassemble).Quoted 284 lines
I am hoping that the disassembly, together with the register contents that you've shown, will help guide towards an answer.
Thanks,
HughQuoted 278 lines
[ 222.068216] ------------[ cut here ]------------ [ 222.072884] kernel BUG at include/linux/swapops.h:204! [ 222.078062] invalid opcode: 0000 [#1] SMP NOPTI [ 222.082618] CPU: 38 PID: 9828 Comm: rpc-worker Tainted: G E 5.13.1-1.gdc.el8.x86_64 #1 [ 222.091894] Hardware name: HPE ProLiant DL380 Gen10/ProLiant DL380 Gen10, BIOS U30 05/24/2021 [ 222.100468] RIP: 0010:pmd_migration_entry_wait+0x132/0x140 [ 222.105994] Code: 02 00 00 00 5b 4c 89 c7 5d e9 ca c5 f6 ff 48 81 e2 00 f0 ff ff 48 f7 d2 48 21 c2 89 d1 f7 c2 81 01 00 00 75 80 e9 44 ff ff ff <0f> 0b 48 8b 2d 65 48 30 01 e9 ef fe ff ff 0f 1f 44 00 00 41 55 48 [ 222.124878] RSP: 0000:ffffbcfe9eb7bdd8 EFLAGS: 00010246 [ 222.130134] RAX: 0057ffffc0000000 RBX: ffff9eec4b3cdbf8 RCX: ffffffffffffffff [ 222.137309] RDX: 0000000000000000 RSI: ffff9eec4b3cdbf8 RDI: ffffdf55c52cf368 [ 222.144485] RBP: ffffdf55c52cf368 R08: ffffdf57428d8080 R09: 0000000000000000 [ 222.151661] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000bf8 [ 222.158837] R13: 0400000000000000 R14: 0400000000000080 R15: ffff9eec2825b1f8 [ 222.166015] FS: 00007f6754aeb700(0000) GS:ffff9f49bfd00000(0000) knlGS:0000000000000000 [ 222.174153] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 222.179932] CR2: 00007f676ffffd98 CR3: 000000012bf6a002 CR4: 00000000007726e0 [ 222.187109] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 222.194283] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 222.201457] PKRU: 55555554 [ 222.204178] Call Trace: [ 222.206638] __handle_mm_fault+0x5ad/0x6e0 [ 222.210760] ? sysvec_call_function_single+0xb/0x90 [ 222.215672] handle_mm_fault+0xc5/0x290 [ 222.219529] do_user_addr_fault+0x1a9/0x660 [ 222.223740] ? sched_clock_cpu+0xc/0xa0 [ 222.227602] exc_page_fault+0x68/0x130 [ 222.231373] ? asm_exc_page_fault+0x8/0x30 [ 222.235495] asm_exc_page_fault+0x1e/0x30 [ 222.239526] RIP: 0033:0x7f67baaed734 [ 222.243120] Code: 89 08 48 8b 35 dd 3b 21 00 4c 8d 0d d6 3b 21 00 31 c0 4c 39 ce 74 73 0f 1f 80 00 00 00 00 48 8d 96 40 fd ff ff 49 39 d2 74 22 <48> 8b 96 d8 03 00 00 48 01 15 4e 7c 21 00 80 be 50 03 00 00 00 c7 [ 222.262002] RSP: 002b:00007f6754aea298 EFLAGS: 00010287 [ 222.267257] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 [ 222.274432] RDX: 00007f676ffff700 RSI: 00007f676ffff9c0 RDI: 00007f676f7fec10 [ 222.281609] RBP: 0000000000000001 R08: 00007f676f7fed10 R09: 00007f67bad012f0 [ 222.288785] R10: 00007f6754aeb700 R11: 0000000000000202 R12: 0000000000000001 [ 222.295961] R13: 0000000000000006 R14: 0000000000000e28 R15: 00007f674006e1f0 [ 222.303137] Modules linked in: vhost_net(E) vhost(E) vhost_iotlb(E)tap(E) tun(E)
tcp_diag(E)udp_diag(E)inet_diag(E)netconsole(E)nf_tables(E)vxlan(E)ip6_udp_tunnel(E)udp_tunnel(E)nfnetlink(E)binfmt_misc(E)iscsi_tcp(E)libiscsi_tcp(E)8021q(E) garp(E) mrp(E) bonding(E) tls(E) vfat(E) fat(E)dm_service_time(E)dm_multipath(E)rpcrdma(E) sunrpc(E)rdma_ucm(E)ib_srpt(E)ib_isert(E)iscsi_target_mod(E)target_core_mod(E)ib_iser(E)rdma_cm(E)iw_cm(E)ib_cm(E)libiscsi(E)intel_rapl_msr(E)intel_rapl_common(E)scsi_transport_iscsi(E)isst_if_common(E)ipmi_ssif(E)nfit(E) libnvdimm(E)x86_pkg_temp_thermal(E)intel_powerclamp(E)coretemp(E)kvm_intel(E)kvm(E) irqbypass(E)crct10dif_pclmul(E)crc32_pclmul(E)ghash_clmulni_intel(E)rapl(E) qedr(E)mei_me(E)acpi_ipmi(E)ib_uverbs(E)intel_cstate(E)ipmi_si(E)ib_core(E)ipmi_devintf(E)dm_mod(E)ioatdma(E) ses(E)intel_uncore(E)pcspkr(E) enclosure(E) mei(E) hpwdt(E) hpilo(E)lpc_ich(E)intel_pch_thermal(E)dca(E)ipmi_msghandler(E)[ 222.303181] acpi_power_meter(E) ext4(E) mbcache(E) jbd2(E) sd_mod(E)
t10_pi(E)sg(E) qedf(E) qede(E) libfcoe(E) qed(E) libfc(E) smartpqi(E)scsi_transport_fc(E)tg3(E)scsi_transport_sas(E)crc8(E) wmi(E)nf_conntrack(E)libcrc32c(E)crc32c_intel(E)nf_defrag_ipv6(E)nf_defrag_ipv4(E)br_netfilter(E)bridge(E) stp(E) llc(E)[ 222.420050] ---[ end trace bcf7b6d1610cc21f ]--- [ 222.572925] RIP: 0010:pmd_migration_entry_wait+0x132/0x140 [ 222.578469] Code: 02 00 00 00 5b 4c 89 c7 5d e9 ca c5 f6 ff 48 81 e2 00 f0 ff ff 48 f7 d2 48 21 c2 89 d1 f7 c2 81 01 00 00 75 80 e9 44 ff ff ff <0f> 0b 48 8b 2d 65 48 30 01 e9 ef fe ff ff 0f 1f 44 00 00 41 55 48 [ 222.597359] RSP: 0000:ffffbcfe9eb7bdd8 EFLAGS: 00010246 [ 222.602620] RAX: 0057ffffc0000000 RBX: ffff9eec4b3cdbf8 RCX: ffffffffffffffff [ 222.609807] RDX: 0000000000000000 RSI: ffff9eec4b3cdbf8 RDI: ffffdf55c52cf368 [ 222.616990] RBP: ffffdf55c52cf368 R08: ffffdf57428d8080 R09: 0000000000000000 [ 222.624177] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000bf8 [ 222.631361] R13: 0400000000000000 R14: 0400000000000080 R15: ffff9eec2825b1f8 [ 222.638548] FS: 00007f6754aeb700(0000) GS:ffff9f49bfd00000(0000) knlGS:0000000000000000 [ 222.646694] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 222.652481] CR2: 00007f676ffffd98 CR3: 000000012bf6a002 CR4: 00000000007726e0 [ 222.659665] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 222.666850] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 222.674031] PKRU: 55555554 [ 222.676758] Kernel panic - not syncing: Fatal exception [ 222.817538] Kernel Offset: 0x16000000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) [ 222.965540] ---[ end Kernel panic - not syncing: Fatal exception ]---Quoted 168 lines · Igor Raits
Hi Hugh,
Quoted 4 lines · Hugh Dickins
Quoted 2 lines · Igor Raits
Hello,
Quoted 8 lines
Quoted 1 line
I've seen one weird bug on 5.12.14 that happened a couple of times when
I
Quoted 1 line
started a bunch of VMs on a server.
Would it be possible for you to try the same on a 5.12.13 kernel? Perhaps by reverting the diff between 5.12.13 and 5.12.14 temporarily. Enough to form an impression of whether the issue is new in 5.12.14.
We've been using 5.12.12 for quite some time (~ a month) and I never saw it there.
But I have to admit that I don't really have a reproducer. For example, on servers where it happened,
I just rebooted them and panic did not happen anymore (so I saw it only only once,
only on 2 servers out of 32 that we have on 5.12.14).Quoted 141 lines
I ask because 5.12.14 did include several fixes and cleanups from me to
page_vma_mapped_walk(), and that is involved in inserting and removing pmd migration entries. I am not aware of introducing any bug there, but your report has got me worried. If it's happening in 5.12.14 but not in 5.12.13, then I must look again at my changes.I don't expect Hillf's patch to help at at all: the
pmd_lock()is supposed to be taken bypage_vma_mapped_walk(), beforeset_pmd_migration_entry()andremove_migration_pmd()are called.Thanks,
HughQuoted 7 lines
I've briefly googled this problem but could not find any relevant commit that would fix this issue.
Do you have any hint how to debug this further or know the fix by any chance?
Quoted 6 lines
Thanks in advance. Stack trace following:
[ 376.876610] ------------[ cut here ]------------ [ 376.881274] kernel BUG at include/linux/swapops.h:204! [ 376.886455] invalid opcode: 0000 [#1] SMP NOPTI [ 376.891014] CPU: 40 PID: 11775 Comm: rpc-worker Tainted: GE
Quoted 5 lines
5.12.14-1.gdc.el8.x86_64 #1 [ 376.900464] Hardware name: HPE ProLiant DL380 Gen10/ProLiant DL380 Gen10, BIOS U30 05/24/2021 [ 376.909038] RIP: 0010:pmd_migration_entry_wait+0x132/0x140 [ 376.914562] Code: 02 00 00 00 5b 4c 89 c7 5d e9 8a e4 f6 ff 48 81 e200
Quoted 24 lines
f0 ff ff 48 f7 d2 48 21 c2 89 d1 f7 c2 81 01 00 00 75 80 e9 44 ff ff ff <0f> 0b 48 8b 2d 75 bd 30 01 e9 ef fe ff ff 0f 1f 44 00 00 41 55 48
[ 376.933443] RSP: 0000:ffffb65a5e1cfdc8 EFLAGS: 00010246 [ 376.938701] RAX: 0017ffffc0000000 RBX: ffff908b8ecabaf8 RCX: ffffffffffffffff [ 376.945878] RDX: 0000000000000000 RSI: ffff908b8ecabaf8 RDI: fffff497473b2ae8 [ 376.953055] RBP: fffff497473b2ae8 R08: fffff49747fa8080 R09: 0000000000000000 [ 376.960230] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000af8 [ 376.967407] R13: 0400000000000000 R14: 0400000000000080 R15: ffff908bbef7b6a8 [ 376.974582] FS: 00007f5bb1f81700(0000) GS:ffff90e87fd80000(0000) knlGS:0000000000000000 [ 376.982718] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 376.988497] CR2: 00007f5b2bfffd98 CR3: 00000001f793e006 CR4: 00000000007726e0 [ 376.995673] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 377.002849] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 377.010026] PKRU: 55555554 [ 377.012745] Call Trace:Quoted 8 lines
[ 377.015207] __handle_mm_fault+0x5ad/0x6e0 [ 377.019335] handle_mm_fault+0xc5/0x290 [ 377.023194] do_user_addr_fault+0x1cd/0x740 [ 377.027406] exc_page_fault+0x54/0x110 [ 377.031182] ? asm_exc_page_fault+0x8/0x30 [ 377.035307] asm_exc_page_fault+0x1e/0x30 [ 377.039340] RIP: 0033:0x7f5bb91d6734 [ 377.042937] Code: 89 08 48 8b 35 dd 3b 21 00 4c 8d 0d d6 3b 21 00 31c0
Quoted 14 lines
4c 39 ce 74 73 0f 1f 80 00 00 00 00 48 8d 96 40 fd ff ff 49 39 d2 74 22 <48> 8b 96 d8 03 00 00 48 01 15 4e 7c 21 00 80 be 50 03 00 00 00 c7
[ 377.061820] RSP: 002b:00007f5bb1f7ff58 EFLAGS: 00010206 [ 377.067076] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 00007f5ba0000020 [ 377.074255] RDX: 00007f5b2bfff700 RSI: 00007f5b2bfff9c0 RDI: 0000000000000001 [ 377.081429] RBP: 0000000000000001 R08: 0000000000000000 R09: 00007f5bb93ea2f0 [ 377.088606] R10: 00007f5bb1f81700 R11: 0000000000000202 R12: 0000000000000001 [ 377.095782] R13: 0000000000000006 R14: 0000000000000cb4 R15: 00007f5bb1f801f0 [ 377.102958] Modules linked in: ebt_arp(E) nft_meta_bridge(E)Quoted 9 lines
ip6_tables(E)xt_CT(E)nf_log_ipv4(E)nf_log_common(E)nft_limit(E)nft_counter(E)xt_LOG(E)xt_limit(E)xt_mac(E)xt_set(E)xt_multiport(E)xt_state(E)xt_conntrack(E)xt_comment(E)xt_physdev(E)nft_compat(E)ip_set_hash_net(E)ip_set(E)vhost_net(E)vhost(E)vhost_iotlb(E)tap(E) tun(E)tcp_diag(E)udp_diag(E)inet_diag(E)netconsole(E)nf_tables(E)vxlan(E)ip6_udp_tunnel(E)udp_tunnel(E)nfnetlink(E)binfmt_misc(E)iscsi_tcp(E)libiscsi_tcp(E)8021q(E) garp(E) mrp(E) bonding(E) tls(E) vfat(E) fat(E)dm_service_time(E)dm_multipath(E)rpcrdma(E) sunrpc(E)rdma_ucm(E)ib_srpt(E)ib_isert(E)iscsi_target_mod(E)
target_core_mod(E)Quoted 1 line
ib_iser(E)rdma_cm(E)iw_cm(E)ib_cm(E)libiscsi(E)
scsi_transport_iscsi(E)Quoted 2 lines
intel_rapl_msr(E)qedr(E)intel_rapl_common(E)ib_uverbs(E)isst_if_common(E)ib_core(E)nfit(E) libnvdimm(E)
x86_pkg_temp_thermal(E)Quoted 4 lines
intel_powerclamp(E)coretemp(E)kvm_intel(E)kvm(E) irqbypass(E)crct10dif_pclmul(E)[ 377.102999] crc32_pclmul(E) ghash_clmulni_intel(E) rapl(E)
intel_cstate(E)ipmi_ssif(E)acpi_ipmi(E)ipmi_si(E)mei_me(E)ioatdma(E)
Quoted 3 lines
ipmi_devintf(E)dm_mod(E)ses(E)intel_uncore(E)pcspkr(E) qede(E) enclosure(E) tg3(E) mei(E)lpc_ich(E)hpilo(E) hpwdt(E)intel_pch_thermal(E)dca(E)ipmi_msghandler(E)acpi_power_meter(E)ext4(E)
Quoted 2 lines
mbcache(E) jbd2(E)
sd_mod(E)t10_pi(E)sg(E) qedf(E) qed(E) crc8(E) libfcoe(E) libfc(E) smartpqi(E)scsi_transport_fc(E)
scsi_transport_sas(E)Quoted 5 lines
wmi(E)
nf_conntrack(E)nf_defrag_ipv6(E)libcrc32c(E)crc32c_intel(E)nf_defrag_ipv4(E)br_netfilter(E)bridge(E) stp(E) llc(E)[ 377.243468] ---[ end trace 04bce3bb051f7620 ]--- [ 377.385645] RIP: 0010:pmd_migration_entry_wait+0x132/0x140 [ 377.391194] Code: 02 00 00 00 5b 4c 89 c7 5d e9 8a e4 f6 ff 48 81 e200
Quoted 17 lines
f0 ff ff 48 f7 d2 48 21 c2 89 d1 f7 c2 81 01 00 00 75 80 e9 44 ff ff ff <0f> 0b 48 8b 2d 75 bd 30 01 e9 ef fe ff ff 0f 1f 44 00 00 41 55 48
[ 377.410091] RSP: 0000:ffffb65a5e1cfdc8 EFLAGS: 00010246 [ 377.415355] RAX: 0017ffffc0000000 RBX: ffff908b8ecabaf8 RCX: ffffffffffffffff [ 377.422540] RDX: 0000000000000000 RSI: ffff908b8ecabaf8 RDI: fffff497473b2ae8 [ 377.429721] RBP: fffff497473b2ae8 R08: fffff49747fa8080 R09: 0000000000000000 [ 377.436902] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000af8 [ 377.444086] R13: 0400000000000000 R14: 0400000000000080 R15: ffff908bbef7b6a8 [ 377.451272] FS: 00007f5bb1f81700(0000) GS:ffff90e87fd80000(0000) knlGS:0000000000000000 [ 377.459415] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 377.465196] CR2: 00007f5b2bfffd98 CR3: 00000001f793e006 CR4:Quoted 8 lines
00000000007726e0[ 377.472377] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 377.479556] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 377.486738] PKRU: 55555554 [ 377.489465] Kernel panic - not syncing: Fatal exception [ 377.573911] Kernel Offset: 0xa000000 from 0xffffffff81000000(relocation
Quoted 2 lines
range: 0xffffffff80000000-0xffffffffbfffffff)
[ 377.716482] ---[ end Kernel panic - not syncing: Fatal exception ]---Disassembly of the vmlinux Igor sent (along with other info) confirmed something I suspected, that R08:
fffff49747fa8080in one of the dumps,
R08:ffffdf57428d8080in the other, is the relevant struct page pointer (and RAX thepage->flags, which look like it was pointing at a good page).A page pointer ....8080 in
pmd_migration_entry_wait()is interesting:
normally I'd expect that to be ....0000 or ....8000, pointing to the head of a huge page. But instead it's pointing to the second tail (though by now that compound page has been freed, and head pointers in the tails reset to 0): as if the pfn has been incremented by 2 somehow.And if the pfn (
swp_offset) in the migration entry has got corrupted, then it's no surprise that when removing migration entries,page_vma_mapped_walk()would seemigration_entry_to_page(entry)!= page, so be unable to replace that migration entry, leaving it behind for the user to hitBUG_ON(!PageLocked)inpmd_migration_entry_wait()when faulting on it later.So, what might increment the
swp_offsetby 2? Hunt around the encodings. Hmm,_PAGE_BIT_UFFD_WPis_PAGE_BIT_SOFTW2which is bit 10, whereas_PAGE_BIT_PROTNONE(top bit to be avoided in pte encoding of swap) is_PAGE_BIT_GLOBALis bit 8. After overcoming off-by-one confusions, it looks like if something somewhere were to set_PAGE_BIT_UFFD_WPin a migration pmd (whereas it's only suitable for a present pmd), it would indeed increment theswp_offsetby 2.Hunt for
uffd_wps, and run acrosscopy_huge_pmd()inmm/huge_memory.c:
in Igor's 5.13.1 and 5.12.14 and many others, that saysif (!(vma->vm_flags & VM_UFFD_WP)) pmd = pmd_clear_uffd_wp(pmd);just *before* checking
is_swap_pmd(). Fixed in 5.14-rc1 in commit8f34f1eac382("mm/userfaultfd: fix uffd-wp special cases forfork()").But clearing the bit would be harmless, wouldn't it? Because it wouldn't be set anyway. Waste a day before remembering what I never forgot but somehow blanked out: the L1TF "feature" forced us to invert the offset bits in the pte encoding of a swap entry, so there really is a bit set there in the pmd entry, and clearing it has the effect of setting it in the corresponding swap entry, so incrementing the migration pfn by 2.
I cannot explain why Igor never saw this crash on 5.12.12: maybe something else in the environment changed around that time. And it will take several days for it to be confirmed as the fix in practice.
Quoted 6 lines
But I'm confident that
8f34f1eac382will prove to be the fix, so Peter please prepare some backports of that for the various stable/longterm kernels that need it - I've not looked into whether it applies cleanly, or depends on other commits too. You fixed several related but different things in that commit: but this one is the worst, because it can corrupt even those who are not usingUFFD_WPat all.
Looks right to me, b569a1760782 ("userfaultfd: wp: drop _PAGE_UFFD_WP properly when fork", 2020-04-07) seems to be the culprit. I didn't notice the side effect in the bug or in the fix, or it should have already land stables. I am very sorry for such a preliminary bug that caused this fallout - I really can't tell why I completely didn't look at is_swap_pte() that's so obvious indeed.
I checked it up, 5.6.y doesn't have the issue commit yet as it's not marked as "fixes". It started to show up in 5.7.y~5.13.y. 5.14-rc1 has 8f34f1eac382 which is the fix. So I think we need the fix or equivalent fix for 5.7.y~5.13.y.
5.12.y & 5.13.y can pick up the fix 8f34f1eac382 cleanly. For the olders (5.7.y~5.11.y) they can't. I plan to revert b569a1760782 instead.
Quoted 10 lines
Many thans for reporting and helping, Igor.
Hughp.s. Peter, unrelated to this particular bug, and should not divert from fixing it: but looking again at those swap encodings, and particularly the
soft_dirtymanipulations: they look very fragile. I thinkuffd_wpwas wrong to follow that bad example, and your upcoming new encoding (that I have previously called elegant) takes it a worse step further.
Quoted 7 lines
I think we should change to a rule where the architecture-independent
swp_entry_tcontains *all* the info, including bits forsoft_dirtyanduffd_wp, so that swap entry cases can move immediately to decoding from arch-dependent pte to arch-independentswp_entry_t, and do all the manipulations on that. But I don't have time to make that change, and probably neither do you, and making the change is liable to introduce errors itself. So, no immediate plans, but please keep in mind.
Curious: did we encounter similar issue previously where soft dirty bit is applied wrongly so causing hard-to-debug issues?
If this is destined to be the best solution, I can work on both of them. I am just worried that's too big a change as you said so we don't know what's the most efficient considering total time we use to develop, review and debug them.
The other alternative is we fix bugs; I know that's so cheap a word when I said it, however we still can't deny it as an option yet.
We can definitely discuss this out of this thread and I'll prepare the backport first. For all the cases, this bug definitely brings some alert, and I'll keep that in mind.
Please let me know if there's any comment on the backport plan above, or I'll prepare the patches for all the branches before tomorrow.
Thanks,
Signature · 1 line
Peter Xu
Quoted 22 lines · Peter Xu
Quoted 7 lines · Hugh Dickins
But I'm confident that
8f34f1eac382will prove to be the fix, so Peter please prepare some backports of that for the various stable/longterm kernels that need it - I've not looked into whether it applies cleanly, or depends on other commits too. You fixed several related but different things in that commit: but this one is the worst, because it can corrupt even those who are not usingUFFD_WPat all.Looks right to me,
b569a1760782("userfaultfd: wp: drop_PAGE_UFFD_WPproperly when fork", 2020-04-07) seems to be the culprit. I didn't notice the side effect in the bug or in the fix, or it should have already land stables. I am very sorry for such a preliminary bug that caused this fallout - I really can't tell why I completely didn't look atis_swap_pte()that's so obvious indeed.I checked it up, 5.6.y doesn't have the issue commit yet as it's not marked as "fixes". It started to show up in 5.7.y~5.13.y. 5.14-rc1 has
8f34f1eac382which is the fix. So I think we need the fix or equivalent fix for 5.7.y~5.13.y.5.12.y & 5.13.y can pick up the fix
8f34f1eac382cleanly. For the olders (5.7.y~5.11.y) they can't. I plan to revertb569a1760782instead.
...
Quoted 3 lines
Please let me know if there's any comment on the backport plan above, or I'll prepare the patches for all the branches before tomorrow.
Thanks for getting on to it so quickly, Peter.
The only non-EOL stable/longterm releases are then 5.13, 5.12 and 5.10.
I have no appreciation of the importance of UFFD_EVENT_FORK support for uffd-wp. And no appreciation of the importance of the other bugs you fixed in 8f34f1eac382, and other uffd-wp fixes you may have made recently, some backported, some not.
But I think it is worth giving 5.10, the longterm, a little more
consideration: don't be driven by whether 8f34f1eac382 applies cleanly (all 5.13 and 5.12 would require then is a mail to GregKH Cc stable asking him to add that commit), but by how important the support is to users of 5.10, and how far away from working safely it is - maybe a 5.10-specific patch would be worthwhile, maybe not, I cannot judge.
Hugh
Quoted 23 lines · Hugh Dickins
Quoted 15 lines · Peter Xu
Quoted 7 lines · Hugh Dickins
But I'm confident that
8f34f1eac382will prove to be the fix, so Peter please prepare some backports of that for the various stable/longterm kernels that need it - I've not looked into whether it applies cleanly, or depends on other commits too. You fixed several related but different things in that commit: but this one is the worst, because it can corrupt even those who are not usingUFFD_WPat all.Looks right to me,
b569a1760782("userfaultfd: wp: drop_PAGE_UFFD_WPproperly when fork", 2020-04-07) seems to be the culprit. I didn't notice the side effect in the bug or in the fix, or it should have already land stables. I am very sorry for such a preliminary bug that caused this fallout - I really can't tell why I completely didn't look atis_swap_pte()that's so obvious indeed.Quoted 7 lines
I checked it up, 5.6.y doesn't have the issue commit yet as it's not marked as "fixes". It started to show up in 5.7.y~5.13.y. 5.14-rc1 has
8f34f1eac382which is the fix. So I think we need the fix or equivalent fix for 5.7.y~5.13.y.5.12.y & 5.13.y can pick up the fix
8f34f1eac382cleanly. For the olders (5.7.y~5.11.y) they can't. I plan to revertb569a1760782instead.
Quoted 8 lines
...
Quoted 3 lines
Please let me know if there's any comment on the backport plan above, or I'll prepare the patches for all the branches before tomorrow.
Thanks for getting on to it so quickly, Peter.
The only non-EOL stable/longterm releases are then 5.13, 5.12 and 5.10.
I see, thanks. I haven't explicitly backported patches to stable; it's a good chance to learn about the bits, though.
Quoted 6 lines
I have no appreciation of the importance of
UFFD_EVENT_FORKsupport for uffd-wp. And no appreciation of the importance of the other bugs you fixed in8f34f1eac382, and other uffd-wp fixes you may have made recently, some backported, some not.
Quoted 6 lines
But I think it is worth giving 5.10, the longterm, a little more
consideration: don't be driven by whether8f34f1eac382applies cleanly (all 5.13 and 5.12 would require then is a mail to GregKH Cc stable asking him to add that commit), but by how important the support is to users of 5.10, and how far away from working safely it is - maybe a 5.10-specific patch would be worthwhile, maybe not, I cannot judge.
I am not aware of anyone who's using fork with uffd-wp. CRIU is the major user per my knowledge that uses uffd fork, but still it shouldn't be using uffd-wp. I know other users that use uffd-wp, but never with fork event.
Per my understanding, if above is true then it's probably not a good candidate for such patches that fixing uffd-wp + fork to be backported to stable, as in stable tree rules there's one entry:
- It must fix a real bug that bothers people (not a, “This could be a problem…” type thing).
https://www.kernel.org/doc/html/v5.13/process/stable-kernel-rules.html
That's also one reason I didn't add Fixes for some patches because I am not sure whether that'll help anyone, and the worst case is if someone hit some issue we can backport explicitly.
There're a few other things that made me a bit worried before backporting the full patch, even for 5.12/5.13, as there're requirements on the patch:
- It cannot be bigger than 100 lines, with context.
- It must fix only one thing.
The full patch (after squashed) contains ~200 LOC with context, and it does fix a few more things... Do you know whether that would be a problem?
I'm not sure how strict would stable branches be, but if that's one blocker then we'll only be able to either pick up the real fix for copy_pmd_range() or just revert the issue commit which is just a few more lines; that should also keep the tree cleaner. From that sense, maybe it's easier to just revert for all the branches (5.10/5.12/5.13). Then if someone broke with uffd-wp+fork, I can backport the full patch with better reasoning.
Thoughts?
Thanks,
Signature · 1 line
Peter Xu
Quoted 49 lines · Peter Xu
Quoted 23 lines · Hugh Dickins
Quoted 15 lines · Peter Xu
Quoted 7 lines · Hugh Dickins
But I'm confident that
8f34f1eac382will prove to be the fix, so Peter please prepare some backports of that for the various stable/longterm kernels that need it - I've not looked into whether it applies cleanly, or depends on other commits too. You fixed several related but different things in that commit: but this one is the worst, because it can corrupt even those who are not usingUFFD_WPat all.Looks right to me,
b569a1760782("userfaultfd: wp: drop_PAGE_UFFD_WPproperly when fork", 2020-04-07) seems to be the culprit. I didn't notice the side effect in the bug or in the fix, or it should have already land stables. I am very sorry for such a preliminary bug that caused this fallout - I really can't tell why I completely didn't look atis_swap_pte()that's so obvious indeed.Quoted 7 lines
I checked it up, 5.6.y doesn't have the issue commit yet as it's not marked as "fixes". It started to show up in 5.7.y~5.13.y. 5.14-rc1 has
8f34f1eac382which is the fix. So I think we need the fix or equivalent fix for 5.7.y~5.13.y.5.12.y & 5.13.y can pick up the fix
8f34f1eac382cleanly. For the olders (5.7.y~5.11.y) they can't. I plan to revertb569a1760782instead.Quoted 8 lines
...
Quoted 3 lines
Please let me know if there's any comment on the backport plan above, or I'll prepare the patches for all the branches before tomorrow.
Thanks for getting on to it so quickly, Peter.
The only non-EOL stable/longterm releases are then 5.13, 5.12 and 5.10.
I see, thanks. I haven't explicitly backported patches to stable; it's a good chance to learn about the bits, though.
Quoted 6 lines
I have no appreciation of the importance of
UFFD_EVENT_FORKsupport for uffd-wp. And no appreciation of the importance of the other bugs you fixed in8f34f1eac382, and other uffd-wp fixes you may have made recently, some backported, some not.Quoted 6 lines
But I think it is worth giving 5.10, the longterm, a little more
consideration: don't be driven by whether8f34f1eac382applies cleanly (all 5.13 and 5.12 would require then is a mail to GregKH Cc stable asking him to add that commit), but by how important the support is to users of 5.10, and how far away from working safely it is - maybe a 5.10-specific patch would be worthwhile, maybe not, I cannot judge.
Quoted 3 lines
I am not aware of anyone who's using fork with uffd-wp. CRIU is the major user per my knowledge that uses uffd fork, but still it shouldn't be using uffd-wp. I know other users that use uffd-wp, but never with fork event.
Okay. It does run a risk, that an unknown 5.10 longterm user is relying on uffd-wp with uffd-fork, and the revert will break their usage in what is supposed to be a stable kernel. But I'll let you be the judge of that.
Quoted 7 lines
Per my understanding, if above is true then it's probably not a good candidate for such patches that fixing uffd-wp + fork to be backported to stable, as in stable tree rules there's one entry:
- It must fix a real bug that bothers people (not a, “This could be a problem…” type thing).
BUG_ON(!PageLocked) is a real bug that bothered Igor (thougn not on 5.10). I cannot estimate the seriousness of the other fixes in that commit.
I have not re-read those rules recently, but last time I questioned them, the conclusion seemed to be that they're reasons the stable guys can give for refusing a patch, but generally nowadays they put in much more than fits those rules; to the extent that akpm has to restrain them from time to time, insisting that mm patches for stable be his decision.
Quoted 4 lines
That's also one reason I didn't add Fixes for some patches because I am not sure whether that'll help anyone, and the worst case is if someone hit some issue we can backport explicitly.
Putting in Fixes generally helps, but whether then to Cc stable will usually be akpm's decision based on our input. In the case of a BUG that hit a real user, I feel fairly confident predicting his decision.
Quoted 9 lines
There're a few other things that made me a bit worried before backporting the full patch, even for 5.12/5.13, as there're requirements on the patch:
- It cannot be bigger than 100 lines, with context.
- It must fix only one thing.The full patch (after squashed) contains ~200 LOC with context, and it does fix a few more things... Do you know whether that would be a problem?
I doubt it. But I'd have to spend too long reading the git-log man-page to learn what options to give it to find an example in stable.git to reassure you.
I'd worry much more about the quality of your commit than its size. If you're uneasy about that now, then it should not have gone into 5.14-rc. If you're confident in it, then I'd say it's good for stable:
unless you suspect interdependent fixes, some of which may already be there in 5.10.y (not always by akpm's choice), some of which not: that can get messy. Applying cleanly is not the most important criterion.
Quoted 7 lines
I'm not sure how strict would stable branches be, but if that's one blocker then we'll only be able to either pick up the real fix for
copy_pmd_range()or just revert the issue commit which is just a few more lines; that should also keep the tree cleaner. From that sense, maybe it's easier to just revert for all the branches (5.10/5.12/5.13). Then if someone broke with uffd-wp+fork, I can backport the full patch with better reasoning.
5.10 is a long-lasting foundation for many, considerably more important than 5.12 and 5.13 which will likely reach EOL soon: so yes, if you have any doubts about 8f34f1eac382, or the way it will fit into earlier releases, and think a revert of uffd-wp+fork is safer, that may be the right thing for all those releases.
I feel like I've used a lot of words to say nothing: back to patches!
Hugh
Quoted 435 lines · Peter Xu
Quoted 1 line · Hugh Dickins
Hi Peter,
Hi, Hugh,
Quoted 11 lines
I believe you have already fixed this, but the fix needs to go to stable. Sorry, the messages below are a muddle of top and middle posting, I'll resume at the bottom.
Quoted 5 lines · Hugh Dickins
Quoted 3 lines · Igor Raits
Hi everyone again,
I've been trying to reproduce this issue but still can't find a
consistent
Quoted 21 lines
Quoted 21 lines
Quoted 3 lines
pattern.
However, it did happen once more and this time on 5.13.1:
Thanks for the updates, Igor.
I have to admit that what you have reported confirms the suspicion that it's a bug introduced by one of my "stable" patches in 5.12.14 (which are also in 5.13): nothing else between 5.12.12 and 5.12.14 seems likely to be relevant.
But I've gone back and forth and not been able to spot the problem.
Please would you send (either privately to me, or to the list) your 5.13.1 kernel's .config, and disassembly of
pmd_migration_entry_wait()from its vmlinux (with line numbers if available; or just send the whole vmlinux if that's easier, and I'll disassemble).I am hoping that the disassembly, together with the register contents that you've shown, will help guide towards an answer.
Quoted 8 lines
Quoted 8 lines
Thanks,
HughQuoted 5 lines
[ 222.068216] ------------[ cut here ]------------ [ 222.072884] kernel BUG at include/linux/swapops.h:204! [ 222.078062] invalid opcode: 0000 [#1] SMP NOPTI [ 222.082618] CPU: 38 PID: 9828 Comm: rpc-worker Tainted: GE
Quoted 5 lines
Quoted 5 lines
Quoted 5 lines
5.13.1-1.gdc.el8.x86_64 #1
[ 222.091894] Hardware name: HPE ProLiant DL380 Gen10/ProLiant DL380 Gen10, BIOS U30 05/24/2021 [ 222.100468] RIP: 0010:pmd_migration_entry_wait+0x132/0x140 [ 222.105994] Code: 02 00 00 00 5b 4c 89 c7 5d e9 ca c5 f6 ff 48 81e2 00
Quoted 1 line
Quoted 1 line
Quoted 1 line
f0 ff ff 48 f7 d2 48 21 c2 89 d1 f7 c2 81 01 00 00 75 80 e9 44 ff ff
ff
Quoted 25 lines
Quoted 25 lines
Quoted 25 lines
<0f> 0b 48 8b 2d 65 48 30 01 e9 ef fe ff ff 0f 1f 44 00 00 41 55 48
[ 222.124878] RSP: 0000:ffffbcfe9eb7bdd8 EFLAGS: 00010246 [ 222.130134] RAX: 0057ffffc0000000 RBX: ffff9eec4b3cdbf8 RCX: ffffffffffffffff [ 222.137309] RDX: 0000000000000000 RSI: ffff9eec4b3cdbf8 RDI: ffffdf55c52cf368 [ 222.144485] RBP: ffffdf55c52cf368 R08: ffffdf57428d8080 R09: 0000000000000000 [ 222.151661] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000bf8 [ 222.158837] R13: 0400000000000000 R14: 0400000000000080 R15: ffff9eec2825b1f8 [ 222.166015] FS: 00007f6754aeb700(0000) GS:ffff9f49bfd00000(0000) knlGS:0000000000000000 [ 222.174153] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 222.179932] CR2: 00007f676ffffd98 CR3: 000000012bf6a002 CR4: 00000000007726e0 [ 222.187109] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 222.194283] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 222.201457] PKRU: 55555554 [ 222.204178] Call Trace: [ 222.206638] __handle_mm_fault+0x5ad/0x6e0 [ 222.210760] ? sysvec_call_function_single+0xb/0x90Quoted 8 lines
Quoted 8 lines
Quoted 8 lines
[ 222.215672] handle_mm_fault+0xc5/0x290 [ 222.219529] do_user_addr_fault+0x1a9/0x660 [ 222.223740] ? sched_clock_cpu+0xc/0xa0 [ 222.227602] exc_page_fault+0x68/0x130 [ 222.231373] ? asm_exc_page_fault+0x8/0x30 [ 222.235495] asm_exc_page_fault+0x1e/0x30 [ 222.239526] RIP: 0033:0x7f67baaed734 [ 222.243120] Code: 89 08 48 8b 35 dd 3b 21 00 4c 8d 0d d6 3b 21 0031 c0
Quoted 1 line
Quoted 1 line
Quoted 1 line
4c 39 ce 74 73 0f 1f 80 00 00 00 00 48 8d 96 40 fd ff ff 49 39 d2 74
22
Quoted 5 lines
Quoted 5 lines
Quoted 5 lines
<48> 8b 96 d8 03 00 00 48 01 15 4e 7c 21 00 80 be 50 03 00 00 00 c7
[ 222.262002] RSP: 002b:00007f6754aea298 EFLAGS: 00010287 [ 222.267257] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 [ 222.274432] RDX: 00007f676ffff700 RSI: 00007f676ffff9c0 RDI:Quoted 8 lines
Quoted 8 lines
Quoted 8 lines
00007f676f7fec10[ 222.281609] RBP: 0000000000000001 R08: 00007f676f7fed10 R09: 00007f67bad012f0 [ 222.288785] R10: 00007f6754aeb700 R11: 0000000000000202 R12: 0000000000000001 [ 222.295961] R13: 0000000000000006 R14: 0000000000000e28 R15: 00007f674006e1f0 [ 222.303137] Modules linked in: vhost_net(E) vhost(E)
vhost_iotlb(E)Quoted 5 lines
Quoted 5 lines
Quoted 5 lines
tap(E) tun(E)
tcp_diag(E)udp_diag(E)inet_diag(E)netconsole(E)nf_tables(E)vxlan(E)ip6_udp_tunnel(E)udp_tunnel(E)nfnetlink(E)binfmt_misc(E)iscsi_tcp(E)libiscsi_tcp(E)8021q(E) garp(E) mrp(E) bonding(E) tls(E) vfat(E) fat(E)dm_service_time(E)dm_multipath(E)rpcrdma(E) sunrpc(E)rdma_ucm(E)ib_srpt(E)ib_isert(E)
iscsi_target_mod(E)Quoted 1 line
Quoted 1 line
Quoted 1 line
target_core_mod(E)ib_iser(E)rdma_cm(E)iw_cm(E)ib_cm(E)libiscsi(E)
Quoted 2 lines
Quoted 2 lines
Quoted 2 lines
intel_rapl_msr(E)intel_rapl_common(E)scsi_transport_iscsi(E)isst_if_common(E)ipmi_ssif(E)nfit(E) libnvdimm(E)
x86_pkg_temp_thermal(E)Quoted 2 lines
Quoted 2 lines
Quoted 2 lines
intel_powerclamp(E)coretemp(E)kvm_intel(E)kvm(E) irqbypass(E)crct10dif_pclmul(E)crc32_pclmul(E)ghash_clmulni_intel(E)rapl(E)qedr(E)
Quoted 1 line
Quoted 1 line
Quoted 1 line
mei_me(E)acpi_ipmi(E)ib_uverbs(E)intel_cstate(E)ipmi_si(E)
ib_core(E)Quoted 4 lines
Quoted 4 lines
Quoted 4 lines
ipmi_devintf(E)dm_mod(E)ioatdma(E) ses(E)intel_uncore(E)pcspkr(E) enclosure(E) mei(E) hpwdt(E) hpilo(E)lpc_ich(E)intel_pch_thermal(E)dca(E)ipmi_msghandler(E)[ 222.303181] acpi_power_meter(E) ext4(E) mbcache(E) jbd2(E)
sd_mod(E)Quoted 1 line
Quoted 1 line
Quoted 1 line
t10_pi(E)sg(E) qedf(E) qede(E) libfcoe(E) qed(E) libfc(E)smartpqi(E)
Quoted 6 lines
Quoted 6 lines
Quoted 6 lines
scsi_transport_fc(E)tg3(E)scsi_transport_sas(E)crc8(E) wmi(E)nf_conntrack(E)libcrc32c(E)crc32c_intel(E)nf_defrag_ipv6(E)nf_defrag_ipv4(E)br_netfilter(E)bridge(E) stp(E) llc(E)[ 222.420050] ---[ end trace bcf7b6d1610cc21f ]--- [ 222.572925] RIP: 0010:pmd_migration_entry_wait+0x132/0x140 [ 222.578469] Code: 02 00 00 00 5b 4c 89 c7 5d e9 ca c5 f6 ff 48 81e2 00
Quoted 1 line
Quoted 1 line
Quoted 1 line
f0 ff ff 48 f7 d2 48 21 c2 89 d1 f7 c2 81 01 00 00 75 80 e9 44 ff ff
ff
Quoted 18 lines
Quoted 18 lines
Quoted 18 lines
<0f> 0b 48 8b 2d 65 48 30 01 e9 ef fe ff ff 0f 1f 44 00 00 41 55 48
[ 222.597359] RSP: 0000:ffffbcfe9eb7bdd8 EFLAGS: 00010246 [ 222.602620] RAX: 0057ffffc0000000 RBX: ffff9eec4b3cdbf8 RCX: ffffffffffffffff [ 222.609807] RDX: 0000000000000000 RSI: ffff9eec4b3cdbf8 RDI: ffffdf55c52cf368 [ 222.616990] RBP: ffffdf55c52cf368 R08: ffffdf57428d8080 R09: 0000000000000000 [ 222.624177] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000bf8 [ 222.631361] R13: 0400000000000000 R14: 0400000000000080 R15: ffff9eec2825b1f8 [ 222.638548] FS: 00007f6754aeb700(0000) GS:ffff9f49bfd00000(0000) knlGS:0000000000000000 [ 222.646694] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 222.652481] CR2: 00007f676ffffd98 CR3: 000000012bf6a002 CR4: 00000000007726e0 [ 222.659665] DR0: 0000000000000000 DR1: 0000000000000000 DR2:Quoted 8 lines
Quoted 8 lines
Quoted 8 lines
0000000000000000
[ 222.666850] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 222.674031] PKRU: 55555554 [ 222.676758] Kernel panic - not syncing: Fatal exception [ 222.817538] Kernel Offset: 0x16000000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) [ 222.965540] ---[ end Kernel panic - not syncing: Fatal exception]---
Quoted 2 lines
Quoted 2 lines
Quoted 2 lines
On Sun, Jul 11, 2021 at 8:06 AM Igor Raits <[email protected]>
Quoted 4 lines · wrote:
Quoted 4 lines
Quoted 4 lines
Quoted 4 lines
Hi Hugh,
On Sun, Jul 11, 2021 at 6:17 AM Hugh Dickins <[email protected]>
Quoted 6 lines · wrote:
Quoted 6 lines
Quoted 6 lines
Quoted 6 lines
Quoted 6 lines · Igor Raits
Quoted 4 lines
Hello,
I've seen one weird bug on 5.12.14 that happened a couple of
times when
Quoted 5 lines
Quoted 5 lines
Quoted 5 lines
Quoted 5 lines
Quoted 5 lines
I
Quoted 1 line
started a bunch of VMs on a server.
Would it be possible for you to try the same on a 5.12.13 kernel? Perhaps by reverting the diff between 5.12.13 and 5.12.14
temporarily.
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Enough to form an impression of whether the issue is new in
5.12.14.
Quoted 3 lines
Quoted 3 lines
Quoted 3 lines
Quoted 3 lines
Quoted 1 line
We've been using 5.12.12 for quite some time (~ a month) and I
never saw
Quoted 3 lines
Quoted 3 lines
Quoted 3 lines
Quoted 3 lines
it there.
But I have to admit that I don't really have a reproducer. For
example, on
Quoted 2 lines
Quoted 2 lines
Quoted 2 lines
Quoted 2 lines
servers where it happened,
I just rebooted them and panic did not happen anymore (so I saw itonly
Quoted 5 lines
Quoted 5 lines
Quoted 5 lines
Quoted 5 lines
only once,
only on 2 servers out of 32 that we have on 5.12.14).Quoted 1 line
I ask because 5.12.14 did include several fixes and cleanups from
me
Quoted 3 lines
Quoted 3 lines
Quoted 3 lines
Quoted 3 lines
Quoted 3 lines
to
page_vma_mapped_walk(), and that is involved in inserting and removing pmd migration entries. I am not aware of introducing any bug there, but your report has got me worried. If it's happeningin
Quoted 11 lines
Quoted 11 lines
Quoted 11 lines
Quoted 11 lines
Quoted 11 lines
5.12.14 but not in 5.12.13, then I must look again at my changes.
I don't expect Hillf's patch to help at at all: the
pmd_lock()is supposed to be taken bypage_vma_mapped_walk(), beforeset_pmd_migration_entry()andremove_migration_pmd()are called.Thanks,
HughQuoted 2 lines
I've briefly googled this problem but could not find any
relevant commit
Quoted 3 lines
Quoted 3 lines
Quoted 3 lines
Quoted 3 lines
Quoted 3 lines
Quoted 3 lines
that would fix this issue.
Do you have any hint how to debug this further or know the fix
by any
Quoted 11 lines
Quoted 11 lines
Quoted 11 lines
Quoted 11 lines
Quoted 11 lines
Quoted 8 lines
chance?
Thanks in advance. Stack trace following:
[ 376.876610] ------------[ cut here ]------------ [ 376.881274] kernel BUG at include/linux/swapops.h:204! [ 376.886455] invalid opcode: 0000 [#1] SMP NOPTI [ 376.891014] CPU: 40 PID: 11775 Comm: rpc-worker Tainted: GE
Quoted 2 lines
5.12.14-1.gdc.el8.x86_64 #1 [ 376.900464] Hardware name: HPE ProLiant DL380 Gen10/ProLiantDL380
Quoted 3 lines
Quoted 3 lines
Quoted 3 lines
Quoted 3 lines
Quoted 3 lines
Quoted 3 lines
Gen10, BIOS U30 05/24/2021
[ 376.909038] RIP: 0010:pmd_migration_entry_wait+0x132/0x140 [ 376.914562] Code: 02 00 00 00 5b 4c 89 c7 5d e9 8a e4 f6 ff48 81 e2
Quoted 2 lines
Quoted 2 lines
Quoted 2 lines
Quoted 2 lines
Quoted 2 lines
00
Quoted 1 line
f0 ff ff 48 f7 d2 48 21 c2 89 d1 f7 c2 81 01 00 00 75 80 e9 44
ff ff ff
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
<0f> 0b 48 8b 2d 75 bd 30 01 e9 ef fe ff ff 0f 1f 44 00 00 41
55 48
Quoted 4 lines
Quoted 4 lines
Quoted 4 lines
Quoted 4 lines
Quoted 4 lines
Quoted 4 lines
[ 376.933443] RSP: 0000:ffffb65a5e1cfdc8 EFLAGS: 00010246 [ 376.938701] RAX: 0017ffffc0000000 RBX: ffff908b8ecabaf8 RCX: ffffffffffffffff [ 376.945878] RDX: 0000000000000000 RSI: ffff908b8ecabaf8 RDI:Quoted 8 lines
Quoted 8 lines
Quoted 8 lines
Quoted 8 lines
Quoted 8 lines
Quoted 8 lines
fffff497473b2ae8[ 376.953055] RBP: fffff497473b2ae8 R08: fffff49747fa8080 R09: 0000000000000000 [ 376.960230] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000af8 [ 376.967407] R13: 0400000000000000 R14: 0400000000000080 R15: ffff908bbef7b6a8 [ 376.974582] FS: 00007f5bb1f81700(0000)GS:ffff90e87fd80000(0000)
Quoted 10 lines
Quoted 10 lines
Quoted 10 lines
Quoted 10 lines
Quoted 10 lines
Quoted 10 lines
knlGS:0000000000000000
[ 376.982718] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 376.988497] CR2: 00007f5b2bfffd98 CR3: 00000001f793e006 CR4: 00000000007726e0 [ 376.995673] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 377.002849] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 377.010026] PKRU: 55555554 [ 377.012745] Call Trace:Quoted 8 lines
Quoted 8 lines
Quoted 8 lines
Quoted 8 lines
Quoted 8 lines
Quoted 8 lines
[ 377.015207] __handle_mm_fault+0x5ad/0x6e0 [ 377.019335] handle_mm_fault+0xc5/0x290 [ 377.023194] do_user_addr_fault+0x1cd/0x740 [ 377.027406] exc_page_fault+0x54/0x110 [ 377.031182] ? asm_exc_page_fault+0x8/0x30 [ 377.035307] asm_exc_page_fault+0x1e/0x30 [ 377.039340] RIP: 0033:0x7f5bb91d6734 [ 377.042937] Code: 89 08 48 8b 35 dd 3b 21 00 4c 8d 0d d6 3b21 00 31
Quoted 2 lines
Quoted 2 lines
Quoted 2 lines
Quoted 2 lines
Quoted 2 lines
c0
Quoted 1 line
4c 39 ce 74 73 0f 1f 80 00 00 00 00 48 8d 96 40 fd ff ff 49 39
d2 74 22
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
<48> 8b 96 d8 03 00 00 48 01 15 4e 7c 21 00 80 be 50 03 00 00
00 c7
Quoted 5 lines
Quoted 5 lines
Quoted 5 lines
Quoted 5 lines
Quoted 5 lines
Quoted 5 lines
[ 377.061820] RSP: 002b:00007f5bb1f7ff58 EFLAGS: 00010206 [ 377.067076] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 00007f5ba0000020 [ 377.074255] RDX: 00007f5b2bfff700 RSI: 00007f5b2bfff9c0 RDI:0000000000000001
Quoted 8 lines
Quoted 8 lines
Quoted 8 lines
Quoted 8 lines
Quoted 8 lines
Quoted 8 lines
[ 377.081429] RBP: 0000000000000001 R08: 0000000000000000 R09: 00007f5bb93ea2f0 [ 377.088606] R10: 00007f5bb1f81700 R11: 0000000000000202 R12: 0000000000000001 [ 377.095782] R13: 0000000000000006 R14: 0000000000000cb4 R15: 00007f5bb1f801f0 [ 377.102958] Modules linked in: ebt_arp(E) nft_meta_bridge(E)
ip6_tables(E)xt_CT(E)nf_log_ipv4(E)nf_log_common(E)
nft_limit(E)Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
nft_counter(E)xt_LOG(E)xt_limit(E)xt_mac(E)xt_set(E)
xt_multiport(E)Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
xt_state(E)xt_conntrack(E)xt_comment(E)xt_physdev(E)
nft_compat(E)Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
ip_set_hash_net(E)ip_set(E)vhost_net(E)vhost(E)
vhost_iotlb(E)tap(E)Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
tun(E)
tcp_diag(E)udp_diag(E)inet_diag(E)netconsole(E)
nf_tables(E)Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
vxlan(E)
ip6_udp_tunnel(E)udp_tunnel(E)nfnetlink(E)
binfmt_misc(E)Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
iscsi_tcp(E)libiscsi_tcp(E)8021q(E) garp(E) mrp(E) bonding(E)tls(E)
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
vfat(E) fat(E)
dm_service_time(E)dm_multipath(E)rpcrdma(E)sunrpc(E)
Quoted 6 lines
Quoted 6 lines
Quoted 6 lines
Quoted 6 lines
Quoted 6 lines
Quoted 1 line
rdma_ucm(E)ib_srpt(E)ib_isert(E)iscsi_target_mod(E)
target_core_mod(E)Quoted 1 line
ib_iser(E)rdma_cm(E)iw_cm(E)ib_cm(E)libiscsi(E)
scsi_transport_iscsi(E)Quoted 2 lines
intel_rapl_msr(E)qedr(E)intel_rapl_common(E)ib_uverbs(E)isst_if_common(E)ib_core(E)nfit(E) libnvdimm(E)Quoted 7 lines
Quoted 7 lines
Quoted 7 lines
Quoted 7 lines
Quoted 7 lines
x86_pkg_temp_thermal(E)Quoted 4 lines
intel_powerclamp(E)coretemp(E)kvm_intel(E)kvm(E) irqbypass(E)crct10dif_pclmul(E)[ 377.102999] crc32_pclmul(E) ghash_clmulni_intel(E) rapl(E)
intel_cstate(E)ipmi_ssif(E)acpi_ipmi(E)ipmi_si(E)mei_me(E)ioatdma(E)
Quoted 1 line
ipmi_devintf(E)dm_mod(E)ses(E)intel_uncore(E)pcspkr(E)qede(E)
Quoted 2 lines
Quoted 2 lines
Quoted 2 lines
Quoted 2 lines
Quoted 2 lines
Quoted 2 lines
enclosure(E) tg3(E) mei(E)
lpc_ich(E)hpilo(E) hpwdt(E)intel_pch_thermal(E)dca(E)ipmi_msghandler(E)
acpi_power_meter(E)Quoted 2 lines
Quoted 2 lines
Quoted 2 lines
Quoted 2 lines
Quoted 2 lines
ext4(E)
Quoted 1 line
mbcache(E) jbd2(E)
sd_mod(E)t10_pi(E)sg(E) qedf(E) qed(E)crc8(E)
Quoted 3 lines
Quoted 3 lines
Quoted 3 lines
Quoted 3 lines
Quoted 3 lines
Quoted 1 line
libfcoe(E) libfc(E) smartpqi(E)
scsi_transport_fc(E)
scsi_transport_sas(E)Quoted 1 line
wmi(E)
nf_conntrack(E)nf_defrag_ipv6(E)libcrc32c(E)
crc32c_intel(E)Quoted 4 lines
Quoted 4 lines
Quoted 4 lines
Quoted 4 lines
Quoted 4 lines
Quoted 4 lines
nf_defrag_ipv4(E)br_netfilter(E)bridge(E) stp(E) llc(E)[ 377.243468] ---[ end trace 04bce3bb051f7620 ]--- [ 377.385645] RIP: 0010:pmd_migration_entry_wait+0x132/0x140 [ 377.391194] Code: 02 00 00 00 5b 4c 89 c7 5d e9 8a e4 f6 ff48 81 e2
Quoted 2 lines
Quoted 2 lines
Quoted 2 lines
Quoted 2 lines
Quoted 2 lines
00
Quoted 1 line
f0 ff ff 48 f7 d2 48 21 c2 89 d1 f7 c2 81 01 00 00 75 80 e9 44
ff ff ff
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
Quoted 1 line
<0f> 0b 48 8b 2d 75 bd 30 01 e9 ef fe ff ff 0f 1f 44 00 00 41
55 48
Quoted 4 lines
Quoted 4 lines
Quoted 4 lines
Quoted 4 lines
Quoted 4 lines
Quoted 4 lines
[ 377.410091] RSP: 0000:ffffb65a5e1cfdc8 EFLAGS: 00010246 [ 377.415355] RAX: 0017ffffc0000000 RBX: ffff908b8ecabaf8 RCX: ffffffffffffffff [ 377.422540] RDX: 0000000000000000 RSI: ffff908b8ecabaf8 RDI:Quoted 8 lines
Quoted 8 lines
Quoted 8 lines
Quoted 8 lines
Quoted 8 lines
Quoted 8 lines
fffff497473b2ae8[ 377.429721] RBP: fffff497473b2ae8 R08: fffff49747fa8080 R09: 0000000000000000 [ 377.436902] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000af8 [ 377.444086] R13: 0400000000000000 R14: 0400000000000080 R15: ffff908bbef7b6a8 [ 377.451272] FS: 00007f5bb1f81700(0000)GS:ffff90e87fd80000(0000)
Quoted 11 lines
Quoted 11 lines
Quoted 11 lines
Quoted 11 lines
Quoted 11 lines
Quoted 11 lines
knlGS:0000000000000000
[ 377.459415] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 377.465196] CR2: 00007f5b2bfffd98 CR3: 00000001f793e006 CR4: 00000000007726e0 [ 377.472377] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 377.479556] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 377.486738] PKRU: 55555554 [ 377.489465] Kernel panic - not syncing: Fatal exception [ 377.573911] Kernel Offset: 0xa000000 from 0xffffffff81000000Quoted 3 lines
Quoted 3 lines
Quoted 3 lines
Quoted 3 lines
Quoted 3 lines
(relocation
Quoted 2 lines
range: 0xffffffff80000000-0xffffffffbfffffff)
[ 377.716482] ---[ end Kernel panic - not syncing: Fatalexception ]---
Quoted 5 lines
Disassembly of the vmlinux Igor sent (along with other info) confirmed something I suspected, that R08:
fffff49747fa8080in one of the dumps,
R08:ffffdf57428d8080in the other, is the relevant struct page pointer (and RAX thepage->flags, which look like it was pointing at a goodpage).
Quoted 40 lines
A page pointer ....8080 in
pmd_migration_entry_wait()is interesting:
normally I'd expect that to be ....0000 or ....8000, pointing to the head of a huge page. But instead it's pointing to the second tail (though by now that compound page has been freed, and head pointers in the tails reset to 0): as if the pfn has been incremented by 2 somehow.And if the pfn (
swp_offset) in the migration entry has got corrupted, then it's no surprise that when removing migration entries,page_vma_mapped_walk()would seemigration_entry_to_page(entry)!= page, so be unable to replace that migration entry, leaving it behind for the user to hitBUG_ON(!PageLocked)inpmd_migration_entry_wait()when faulting on it later.So, what might increment the
swp_offsetby 2? Hunt around the encodings. Hmm,_PAGE_BIT_UFFD_WPis_PAGE_BIT_SOFTW2which is bit 10, whereas_PAGE_BIT_PROTNONE(top bit to be avoided in pte encoding of swap) is_PAGE_BIT_GLOBALis bit 8. After overcoming off-by-one confusions, it looks like if something somewhere were to set_PAGE_BIT_UFFD_WPin a migration pmd (whereas it's only suitable for a present pmd), it would indeed increment theswp_offsetby 2.Hunt for
uffd_wps, and run acrosscopy_huge_pmd()inmm/huge_memory.c:
in Igor's 5.13.1 and 5.12.14 and many others, that saysif (!(vma->vm_flags & VM_UFFD_WP)) pmd = pmd_clear_uffd_wp(pmd);just *before* checking
is_swap_pmd(). Fixed in 5.14-rc1 in commit8f34f1eac382("mm/userfaultfd: fix uffd-wp special cases forfork()").But clearing the bit would be harmless, wouldn't it? Because it wouldn't be set anyway. Waste a day before remembering what I never forgot but somehow blanked out: the L1TF "feature" forced us to invert the offset bits in the pte encoding of a swap entry, so there really is a bit set there in the pmd entry, and clearing it has the effect of setting it in the corresponding swap entry, so incrementing the migration pfn by 2.
I cannot explain why Igor never saw this crash on 5.12.12: maybe something else in the environment changed around that time. And it will take several days for it to be confirmed as the fix in practice.
Quoted 6 lines
But I'm confident that
8f34f1eac382will prove to be the fix, so Peter please prepare some backports of that for the various stable/longterm kernels that need it - I've not looked into whether it applies cleanly, or depends on other commits too. You fixed several related but different things in that commit: but this one is the worst, because it can corrupt even those who are not usingUFFD_WPat all.Looks right to me,
b569a1760782("userfaultfd: wp: drop_PAGE_UFFD_WPproperly
when fork", 2020-04-07) seems to be the culprit. I didn't notice the side effect in the bug or in the fix, or it should have already land stables. I am
very sorry for such a preliminary bug that caused this fallout - I really can't
tell why I completely didn't look atis_swap_pte()that's so obvious indeed.
Quoted 9 lines
I checked it up, 5.6.y doesn't have the issue commit yet as it's not marked as
"fixes". It started to show up in 5.7.y~5.13.y. 5.14-rc1 has8f34f1eac382which
is the fix. So I think we need the fix or equivalent fix for 5.7.y~5.13.y.5.12.y & 5.13.y can pick up the fix
8f34f1eac382cleanly. For the olders (5.7.y~5.11.y) they can't. I plan to revertb569a1760782instead.
FTR, even though 8f34f1eac382 applies cleanly it does not compile. The 1st patch of that series is also required (5fc7a5f6fd04) - it removes use of
*vma, which is later removed by the patch that fixes the actual problem.
Quoted 49 lines
Quoted 11 lines
Many thans for reporting and helping, Igor.
Hughp.s. Peter, unrelated to this particular bug, and should not divert from fixing it: but looking again at those swap encodings, and particularly the
soft_dirtymanipulations: they look very fragile. I thinkuffd_wpwas wrong to follow that bad example, and your upcoming new encoding (that I have previously called elegant) takes it a worse step further.Quoted 7 lines
I think we should change to a rule where the architecture-independent
swp_entry_tcontains *all* the info, including bits forsoft_dirtyanduffd_wp, so that swap entry cases can move immediately to decoding from arch-dependent pte to arch-independentswp_entry_t, and do all the manipulations on that. But I don't have time to make that change, and probably neither do you, and making the change is liable to introduce errors itself. So, no immediate plans, but please keep in mind.Curious: did we encounter similar issue previously where soft dirty bit is applied wrongly so causing hard-to-debug issues?
If this is destined to be the best solution, I can work on both of them. I am
just worried that's too big a change as you said so we don't know what's the
most efficient considering total time we use to develop, review and debug them.The other alternative is we fix bugs; I know that's so cheap a word when I said
it, however we still can't deny it as an option yet.We can definitely discuss this out of this thread and I'll prepare the backport
first. For all the cases, this bug definitely brings some alert, and I'll keep
that in mind.Please let me know if there's any comment on the backport plan above, or I'll
prepare the patches for all the branches before tomorrow.Thanks,
--
Peter Xu
Signature · 19 lines
Igor Raits Sr. SW Engineer [email protected] +420 775 117 817 Moravske namesti 1007/14 602 00 Brno-Veveri, Czech Republic Twitter <https://twitter.com/gooddata> | Facebook <https://www.facebook.com/gooddata> | LinkedIn <http://www.linkedin.com/company/gooddata> | Blog <http://www.gooddata.com/blog> <https://www.gooddata.com/>
Hi, Igor,
Quoted 4 lines · Igor Raits
FTR, even though
8f34f1eac382applies cleanly it does not compile. The 1st patch of that series is also required (5fc7a5f6fd04) - it removes use of
*vma, which is later removed by the patch that fixes the actual problem.
Please feel free to give it a shot with the two backport series to see whether you spot any issue with it so far.
5.13/5.12: https://lore.kernel.org/linux-mm/[email protected]
5.10: https://lore.kernel.org/linux-mm/[email protected]
Sorry for the trouble.
Signature · 1 line
Peter Xu
Hi Peter,
Quoted 8 lines · Peter Xu
Hi, Igor,
Quoted 4 lines · Igor Raits
FTR, even though
8f34f1eac382applies cleanly it does not compile. The 1st patch of that series is also required (5fc7a5f6fd04) - it removes use of
*vma, which is later removed by the patch that fixes the actual problem.
Quoted 7 lines
Please feel free to give it a shot with the two backport series to see whether
you spot any issue with it so far.5.13/5.12:
https://lore.kernel.org/linux-mm/[email protected]
It seems like a normal cherry-pick without any extra changes around (please correct me if I'm wrong),
so I've already added that to our internal kernel builds and so far I did not spot any issues
(but as the issue does not happen frequently, I can't confirm if it is really fixed but I trust Hugh
that he identified that as the commit that should fix it).
Anyhow, I'll keep looking around and let you know if I spot anything :)
5.10:
Quoted 4 lines
https://lore.kernel.org/linux-mm/[email protected]
Sorry for the trouble.
Thanks for providing fixes!
Quoted 3 lines
Peter Xu
Signature · 19 lines
Igor Raits Sr. SW Engineer [email protected] +420 775 117 817 Moravske namesti 1007/14 602 00 Brno-Veveri, Czech Republic Twitter <https://twitter.com/gooddata> | Facebook <https://www.facebook.com/gooddata> | LinkedIn <http://www.linkedin.com/company/gooddata> | Blog <http://www.gooddata.com/blog> <https://www.gooddata.com/>
cover mm/thp: Fix uffd-wp with fork(); crash on pmd migration entry on fork
In reply to Hugh DickinsIn summary: this series should be needed for 5.10/5.12/5.13. This is the 5.13.y/5.12.y backport of the series, and it should be able to be applied on both of the branches. Patch 1 is a dependency of patch 2, while patch 2 should be the real fix.
This series should be able to fix a rare race that mentioned in thread:
https://lore.kernel.org/linux-mm/[email protected]/
This fact wasn't discovered when the fix got proposed and merged, because the fix was originally about uffd-wp and its fork event. However it turns out that the problematic commit b569a1760782f3d is also causing crashing on fork() of pmd migration entries which is even more severe than the original uffd-wp problem.
Stable kernels at least on 5.12.y has the crash reproduced, and it's possible 5.13.y and 5.10.y could hit it due to having the problematic commit b569a1760782f3d but lacking of the uffd-wp fix patch (8f34f1eac382, which is also patch 2 of this series).
The pmd entry crash problem was reported by Igor Raits <[email protected]> and debugged by Hugh Dickins <[email protected]>.
Please review, thanks.
Peter Xu (2):
mm/thp: simplify copying of huge zero page pmd when fork mm/userfaultfd: fix uffd-wp special cases for fork()
include/linux/huge_mm.h | 2 +- include/linux/swapops.h | 2 ++ mm/huge_memory.c | 36 +++++++++++++++++------------------- mm/memory.c | 25 +++++++++++++------------ 4 files changed, 33 insertions(+), 32 deletions(-)
Signature · 1 line
2.31.1
PATCH 1/2 mm/thp: simplify copying of huge zero page pmd when fork
Patch series "mm/uffd: Misc fix for uffd-wp and one more test".
This series tries to fix some corner case bugs for uffd-wp on either thp or fork(). Then it introduced a new test with pagemap/pageout.
Patch layout:
Patch 1: cleanup for THP, it'll slightly simplify the follow up patches Patch 2-4: misc fixes for uffd-wp here and there; please refer to each patch Patch 5: add pagemap support for uffd-wp Patch 6: add pagemap/pageout test for uffd-wp
The last test introduced can also verify some of the fixes in previous patches, as the test will fail without the fixes. However it's not easy to verify all the changes in patch 2-4, but hopefully they can still be properly reviewed.
Note that if considering the ongoing uffd-wp shmem & hugetlbfs work, patch 5 will be incomplete as it's missing e.g. hugetlbfs part or the special swap pte detection. However that's not needed in this series, and since that series is still during review, this series does not depend on that one (the last test only runs with anonymous memory, not file-backed). So this series can be merged even before that series.
This patch (of 6):
Huge zero page is handled in a special path in copy_huge_pmd(), however it should share most codes with a normal thp page. Trying to share more code with it by removing the special path. The only leftover so far is the huge zero page refcounting (mm_get_huge_zero_page()), because that's separately done with a global counter.
This prepares for a future patch to modify the huge pmd to be installed, so that we don't need to duplicate it explicitly into huge zero page case too.
--- mm/huge_memory.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-)
mm/huge_memory.c +3 -6
@@ -1088,17 +1088,13 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,* a page table. */ if (is_huge_zero_pmd (pmd)) { -struct page *zero_page;/* * get_huge_zero_page() will never allocate a new page here, * since we already have a zero page to copy. It just takes a * reference. */ - zero_page =mm_get_huge_zero_page (dst_mm); -set_huge_zero_page (pgtable, dst_mm, vma, addr, dst_pmd, - zero_page); - ret =0 ; - goto out_unlock; +mm_get_huge_zero_page (dst_mm); + goto out_zero_page; } src_page =pmd_page (pmd);
@@ -1122,6 +1118,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,get_page (src_page);page_dup_rmap (src_page, true);add_mm_counter (dst_mm,MM_ANONPAGES ,HPAGE_PMD_NR ); +out_zero_page:mm_inc_nr_ptes (dst_mm);pgtable_trans_huge_deposit (dst_mm, dst_pmd, pgtable);
Signature · 1 line
2.31.1
PATCH 2/2 mm/userfaultfd: fix uffd-wp special cases for fork()
In reply to Peter XuWe tried to do something similar in b569a1760782 ("userfaultfd: wp: drop _PAGE_UFFD_WP properly when fork") previously, but it's not doing it all right.. A few fixes around the code path:
1. We were referencing VM_UFFD_WP vm_flags on the _old_ vma rather than the new vma. That's overlooked in b569a1760782, so it won't work as expected. Thanks to the recent rework on fork code (7a4830c380f3a8b3), we can easily get the new vma now, so switch the checks to that.
2. Dropping the uffd-wp bit in copy_huge_pmd() could be wrong if the huge pmd is a migration huge pmd. When it happens, instead of using pmd_uffd_wp(), we should use pmd_swp_uffd_wp(). The fix is simply to handle them separately.
3. Forget to carry over uffd-wp bit for a write migration huge pmd entry. This also happens in copy_huge_pmd(), where we converted a write huge migration entry into a read one.
4. In copy_nonpresent_pte(), drop uffd-wp if necessary for swap ptes.
5. In copy_present_page() when COW is enforced when fork(), we also need to pass over the uffd-wp bit if VM_UFFD_WP is armed on the new vma, and when the pte to be copied has uffd-wp bit set.
Remove the comment in copy_present_pte() about this. It won't help a huge lot to only comment there, but comment everywhere would be an overkill. Let's assume the commit messages would help.
--- include/linux/huge_mm.h | 2 +- include/linux/swapops.h | 2 ++ mm/huge_memory.c | 27 ++++++++++++++------------- mm/memory.c | 25 +++++++++++++------------ 4 files changed, 30 insertions(+), 26 deletions(-)
include/linux/huge_mm.h +1 -1
@@ -10,7 +10,7 @@vm_fault_t do_huge_pmd_anonymous_page (struct vm_fault *vmf);int copy_huge_pmd (struct mm_struct *dst_mm,struct mm_struct *src_mm,pmd_t *dst_pmd,pmd_t *src_pmd,unsigned long addr, -struct vm_area_struct *vma); +struct vm_area_struct *dst_vma,struct vm_area_struct *src_vma);void huge_pmd_set_accessed (struct vm_fault *vmf,pmd_t orig_pmd); int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm, pud_t *dst_pud, pud_t *src_pud, unsigned long addr,
include/linux/swapops.h +2 -0
@@ -265,6 +265,8 @@ static inline swp_entry_t pmd_to_swp_entry(pmd_t pmd)if (pmd_swp_soft_dirty (pmd)) pmd =pmd_swp_clear_soft_dirty (pmd); +if (pmd_swp_uffd_wp (pmd)) + pmd =pmd_swp_clear_uffd_wp (pmd); arch_entry =__pmd_to_swp_entry (pmd);return swp_entry (__swp_type (arch_entry),__swp_offset (arch_entry)); }
mm/huge_memory.c +14 -13
@@ -1026,7 +1026,7 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,int copy_huge_pmd (struct mm_struct *dst_mm,struct mm_struct *src_mm,pmd_t *dst_pmd,pmd_t *src_pmd,unsigned long addr, -struct vm_area_struct *vma) +struct vm_area_struct *dst_vma,struct vm_area_struct *src_vma) {spinlock_t *dst_ptl, *src_ptl;struct page *src_page;
@@ -1035,7 +1035,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,int ret = -ENOMEM ;/* Skip if can be re-fill on fault */ -if (!vma_is_anonymous (vma)) +if (!vma_is_anonymous (dst_vma))return 0 ; pgtable =pte_alloc_one (dst_mm);
@@ -1049,14 +1049,6 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, ret = -EAGAIN ; pmd = *src_pmd; -/* -* Make sure the _PAGE_UFFD_WP bit is cleared if the new VMA -* does not have the VM_UFFD_WP, which means that the uffd -* fork event is not enabled. -*/ -if (!(vma->vm_flags &VM_UFFD_WP )) - pmd =pmd_clear_uffd_wp (pmd); -#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION if (unlikely (is_swap_pmd (pmd))) {swp_entry_t entry =pmd_to_swp_entry (pmd);
@@ -1067,11 +1059,15 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd =swp_entry_to_pmd (entry);if (pmd_swp_soft_dirty (*src_pmd)) pmd =pmd_swp_mksoft_dirty (pmd); +if (pmd_swp_uffd_wp (*src_pmd)) + pmd =pmd_swp_mkuffd_wp (pmd);set_pmd_at (src_mm, addr, src_pmd, pmd); }add_mm_counter (dst_mm,MM_ANONPAGES ,HPAGE_PMD_NR );mm_inc_nr_ptes (dst_mm);pgtable_trans_huge_deposit (dst_mm, dst_pmd, pgtable); +if (!userfaultfd_wp (dst_vma)) + pmd =pmd_swp_clear_uffd_wp (pmd);set_pmd_at (dst_mm, addr, dst_pmd, pmd); ret =0 ; goto out_unlock;
@@ -1107,11 +1103,11 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,* best effort that the pinned pages won't be replaced by another * random page during the coming copy-on-write. */ -if (unlikely (page_needs_cow_for_dma (vma, src_page))) { +if (unlikely (page_needs_cow_for_dma (src_vma, src_page))) {pte_free (dst_mm, pgtable);spin_unlock (src_ptl);spin_unlock (dst_ptl); -__split_huge_pmd (vma, src_pmd, addr, false,NULL ); +__split_huge_pmd (src_vma, src_pmd, addr, false,NULL );return -EAGAIN ; }
@@ -1121,8 +1117,9 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, out_zero_page:mm_inc_nr_ptes (dst_mm);pgtable_trans_huge_deposit (dst_mm, dst_pmd, pgtable); -pmdp_set_wrprotect (src_mm, addr, src_pmd); +if (!userfaultfd_wp (dst_vma)) + pmd =pmd_clear_uffd_wp (pmd); pmd =pmd_mkold (pmd_wrprotect (pmd));set_pmd_at (dst_mm, addr, dst_pmd, pmd);
@@ -1838,6 +1835,8 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, newpmd =swp_entry_to_pmd (entry);if (pmd_swp_soft_dirty (*pmd)) newpmd =pmd_swp_mksoft_dirty (newpmd); +if (pmd_swp_uffd_wp (*pmd)) + newpmd =pmd_swp_mkuffd_wp (newpmd);set_pmd_at (mm, addr, pmd, newpmd); } goto unlock;
@@ -3248,6 +3247,8 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) pmde =pmd_mksoft_dirty (pmde);if (is_write_migration_entry (entry)) pmde =maybe_pmd_mkwrite (pmde, vma); +if (pmd_swp_uffd_wp (*pvmw->pmd)) + pmde =pmd_wrprotect (pmd_mkuffd_wp (pmde));flush_cache_range (vma, mmun_start, mmun_start +HPAGE_PMD_SIZE );if (PageAnon (new))
mm/memory.c +13 -12
@@ -708,10 +708,10 @@ struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr,static unsigned long copy_nonpresent_pte (struct mm_struct *dst_mm,struct mm_struct *src_mm, -pte_t *dst_pte,pte_t *src_pte,struct vm_area_struct *vma, -unsigned long addr,int *rss) +pte_t *dst_pte,pte_t *src_pte,struct vm_area_struct *dst_vma, +struct vm_area_struct *src_vma,unsigned long addr,int *rss) { -unsigned long vm_flags = vma->vm_flags; +unsigned long vm_flags = dst_vma->vm_flags;pte_t pte = *src_pte;struct page *page;swp_entry_t entry =pte_to_swp_entry (pte);
@@ -780,6 +780,8 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,set_pte_at (src_mm, addr, src_pte, pte); } } +if (!userfaultfd_wp (dst_vma)) + pte =pte_swp_clear_uffd_wp (pte);set_pte_at (dst_mm, addr, dst_pte, pte);return 0 ; }
@@ -845,6 +847,9 @@ copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma/* All done, just insert the new page copy in the child */ pte =mk_pte (new_page, dst_vma->vm_page_prot); pte =maybe_mkwrite (pte_mkdirty (pte), dst_vma); +if (userfaultfd_pte_wp (dst_vma, *src_pte)) +/* Uffd-wp needs to be delivered to dest pte as well */ + pte =pte_wrprotect (pte_mkuffd_wp (pte));set_pte_at (dst_vma->vm_mm, addr, dst_pte, pte);return 0 ; }
@@ -894,12 +899,7 @@ copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pte =pte_mkclean (pte); pte =pte_mkold (pte); -/* -* Make sure the _PAGE_UFFD_WP bit is cleared if the new VMA -* does not have the VM_UFFD_WP, which means that the uffd -* fork event is not enabled. -*/ -if (!(vm_flags &VM_UFFD_WP )) +if (!userfaultfd_wp (dst_vma)) pte =pte_clear_uffd_wp (pte);set_pte_at (dst_vma->vm_mm, addr, dst_pte, pte);
@@ -974,7 +974,8 @@ copy_pte_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,if (unlikely (!pte_present (*src_pte))) { entry.val =copy_nonpresent_pte (dst_mm, src_mm, dst_pte, src_pte, - src_vma, addr, rss); + dst_vma, src_vma, + addr, rss);if (entry.val)break ; progress +=8 ;
@@ -1051,8 +1052,8 @@ copy_pmd_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, || pmd_devmap(*src_pmd)) {int err;VM_BUG_ON_VMA (next-addr !=HPAGE_PMD_SIZE , src_vma); - err =copy_huge_pmd (dst_mm, src_mm, - dst_pmd, src_pmd, addr, src_vma); + err =copy_huge_pmd (dst_mm, src_mm, dst_pmd, src_pmd, + addr, dst_vma, src_vma);if (err == -ENOMEM )return -ENOMEM ;if (!err)
Signature · 1 line
2.31.1
Re: [PATCH stable 5.13.y/5.12.y 0/2] mm/thp: Fix uffd-wp with fork(); crash on pmd migration entry on fork
In reply to Peter XuQuoted 21 lines · Peter Xu
In summary: this series should be needed for 5.10/5.12/5.13. This is the 5.13.y/5.12.y backport of the series, and it should be able to be applied on both of the branches. Patch 1 is a dependency of patch 2, while patch 2 should be the real fix.
This series should be able to fix a rare race that mentioned in thread:
https://lore.kernel.org/linux-mm/[email protected]/
This fact wasn't discovered when the fix got proposed and merged, because the fix was originally about uffd-wp and its fork event. However it turns out that the problematic commit
b569a1760782f3dis also causing crashing onfork()of pmd migration entries which is even more severe than the original uffd-wp problem.Stable kernels at least on 5.12.y has the crash reproduced, and it's possible 5.13.y and 5.10.y could hit it due to having the problematic commit
b569a1760782f3dbut lacking of the uffd-wp fix patch (8f34f1eac382, which is also patch 2 of this series).
Quoted 4 lines
The pmd entry crash problem was reported by Igor Raits <[email protected]> and debugged by Hugh Dickins <[email protected]>.
Please review, thanks.
These two 5.13.y patches look just right to me, thank you Peter (and 5.12.19 announced EOL overnight, so nothing more wanted for that).
But these do just amount to asking [email protected] to cherry-pick the two commits 5fc7a5f6fd04bc18f309d9f979b32ef7d1d0a997 8f34f1eac3820fc2722e5159acceb22545b30b0d
Hugh
(I'd usually reply with alpine rather than gmail, but I see extra blank lines on these 0/2s that way; but the patches themselves are good.)
Quoted 15 lines
Peter Xu (2):
mm/thp: simplify copying of huge zero page pmd when fork mm/userfaultfd: fix uffd-wp special cases forfork()include/linux/huge_mm.h | 2 +- include/linux/swapops.h | 2 ++ mm/huge_memory.c | 36 +++++++++++++++++------------------- mm/memory.c | 25 +++++++++++++------------ 4 files changed, 33 insertions(+), 32 deletions(-)--
2.31.1
Re: [PATCH stable 5.13.y/5.12.y 0/2] mm/thp: Fix uffd-wp with fork(); crash on pmd migration entry on fork
Quoted 27 lines · Hugh Dickins
Quoted 21 lines · Peter Xu
In summary: this series should be needed for 5.10/5.12/5.13. This is the 5.13.y/5.12.y backport of the series, and it should be able to be applied on both of the branches. Patch 1 is a dependency of patch 2, while patch 2 should be the real fix.
This series should be able to fix a rare race that mentioned in thread:
https://lore.kernel.org/linux-mm/[email protected]/
This fact wasn't discovered when the fix got proposed and merged, because the fix was originally about uffd-wp and its fork event. However it turns out that the problematic commit
b569a1760782f3dis also causing crashing onfork()of pmd migration entries which is even more severe than the original uffd-wp problem.Stable kernels at least on 5.12.y has the crash reproduced, and it's possible 5.13.y and 5.10.y could hit it due to having the problematic commit
b569a1760782f3dbut lacking of the uffd-wp fix patch (8f34f1eac382, which is also patch 2 of this series).Quoted 4 lines
The pmd entry crash problem was reported by Igor Raits <[email protected]> and debugged by Hugh Dickins <[email protected]>.
Please review, thanks.
Quoted 7 lines
These two 5.13.y patches look just right to me, thank you Peter (and 5.12.19 announced EOL overnight, so nothing more wanted for that).
But these do just amount to asking [email protected] to cherry-pick the two commits
5fc7a5f6fd04bc18f309d9f979b32ef7d1d0a9978f34f1eac3820fc2722e5159acceb22545b30b0d
Thanks for the review, both now queued up to 5.13.y.
greg k-h
cover mm/thp: Fix uffd-wp with fork(); crash on pmd migration entry on fork
In reply to Hugh DickinsIn summary, this series should be needed for 5.10/5.12/5.13. This is the 5.10.y backport of the series. Patch 1 is a dependency of patch 2, while patch 2 should be the real fix.
There's a minor conflict on patch 2 when cherry pick due to not having the new helper called page_needs_cow_for_dma(). It's also mentioned at the entry of patch 2.
This series should be able to fix a rare race that mentioned in thread:
https://lore.kernel.org/linux-mm/[email protected]/
This fact wasn't discovered when the fix got proposed and merged, because the fix was originally about uffd-wp and its fork event. However it turns out that the problematic commit b569a1760782f3d is also causing crashing on fork() of pmd migration entries which is even more severe than the original uffd-wp problem.
Stable kernels at least on 5.12.y has the crash reproduced, and it's possible 5.13.y and 5.10.y could hit it due to having the problematic commit b569a1760782f3d but lacking of the uffd-wp fix patch (8f34f1eac382, which is also patch 2 of this series).
The pmd entry crash problem was reported by Igor Raits <[email protected]> and debugged by Hugh Dickins <[email protected]>.
Please review, thanks.
Peter Xu (2):
mm/thp: simplify copying of huge zero page pmd when fork mm/userfaultfd: fix uffd-wp special cases for fork()
include/linux/huge_mm.h | 2 +- include/linux/swapops.h | 2 ++ mm/huge_memory.c | 36 +++++++++++++++++------------------- mm/memory.c | 25 +++++++++++++------------ 4 files changed, 33 insertions(+), 32 deletions(-)
Signature · 1 line
2.31.1
PATCH 1/2 mm/thp: simplify copying of huge zero page pmd when fork
Patch series "mm/uffd: Misc fix for uffd-wp and one more test".
This series tries to fix some corner case bugs for uffd-wp on either thp or fork(). Then it introduced a new test with pagemap/pageout.
Patch layout:
Patch 1: cleanup for THP, it'll slightly simplify the follow up patches Patch 2-4: misc fixes for uffd-wp here and there; please refer to each patch Patch 5: add pagemap support for uffd-wp Patch 6: add pagemap/pageout test for uffd-wp
The last test introduced can also verify some of the fixes in previous patches, as the test will fail without the fixes. However it's not easy to verify all the changes in patch 2-4, but hopefully they can still be properly reviewed.
Note that if considering the ongoing uffd-wp shmem & hugetlbfs work, patch 5 will be incomplete as it's missing e.g. hugetlbfs part or the special swap pte detection. However that's not needed in this series, and since that series is still during review, this series does not depend on that one (the last test only runs with anonymous memory, not file-backed). So this series can be merged even before that series.
This patch (of 6):
Huge zero page is handled in a special path in copy_huge_pmd(), however it should share most codes with a normal thp page. Trying to share more code with it by removing the special path. The only leftover so far is the huge zero page refcounting (mm_get_huge_zero_page()), because that's separately done with a global counter.
This prepares for a future patch to modify the huge pmd to be installed, so that we don't need to duplicate it explicitly into huge zero page case too.
--- mm/huge_memory.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-)
mm/huge_memory.c +3 -6
@@ -1074,17 +1074,13 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,* a page table. */ if (is_huge_zero_pmd (pmd)) { -struct page *zero_page;/* * get_huge_zero_page() will never allocate a new page here, * since we already have a zero page to copy. It just takes a * reference. */ - zero_page =mm_get_huge_zero_page (dst_mm); -set_huge_zero_page (pgtable, dst_mm, vma, addr, dst_pmd, - zero_page); - ret =0 ; - goto out_unlock; +mm_get_huge_zero_page (dst_mm); + goto out_zero_page; } src_page =pmd_page (pmd);
@@ -1110,6 +1106,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,get_page (src_page);page_dup_rmap (src_page, true);add_mm_counter (dst_mm,MM_ANONPAGES ,HPAGE_PMD_NR ); +out_zero_page:mm_inc_nr_ptes (dst_mm);pgtable_trans_huge_deposit (dst_mm, dst_pmd, pgtable);
Signature · 1 line
2.31.1
PATCH 2/2 mm/userfaultfd: fix uffd-wp special cases for fork()
In reply to Peter Xu[Conflict: copy_huge_pmd() hasn't introduced helper page_needs_cow_for_dma()]
We tried to do something similar in b569a1760782 ("userfaultfd: wp: drop _PAGE_UFFD_WP properly when fork") previously, but it's not doing it all right.. A few fixes around the code path:
1. We were referencing VM_UFFD_WP vm_flags on the _old_ vma rather than the new vma. That's overlooked in b569a1760782, so it won't work as expected. Thanks to the recent rework on fork code (7a4830c380f3a8b3), we can easily get the new vma now, so switch the checks to that.
2. Dropping the uffd-wp bit in copy_huge_pmd() could be wrong if the huge pmd is a migration huge pmd. When it happens, instead of using pmd_uffd_wp(), we should use pmd_swp_uffd_wp(). The fix is simply to handle them separately.
3. Forget to carry over uffd-wp bit for a write migration huge pmd entry. This also happens in copy_huge_pmd(), where we converted a write huge migration entry into a read one.
4. In copy_nonpresent_pte(), drop uffd-wp if necessary for swap ptes.
5. In copy_present_page() when COW is enforced when fork(), we also need to pass over the uffd-wp bit if VM_UFFD_WP is armed on the new vma, and when the pte to be copied has uffd-wp bit set.
Remove the comment in copy_present_pte() about this. It won't help a huge lot to only comment there, but comment everywhere would be an overkill. Let's assume the commit messages would help.
--- include/linux/huge_mm.h | 2 +- include/linux/swapops.h | 2 ++ mm/huge_memory.c | 27 ++++++++++++++------------- mm/memory.c | 25 +++++++++++++------------ 4 files changed, 30 insertions(+), 26 deletions(-)
include/linux/huge_mm.h +1 -1
@@ -10,7 +10,7 @@vm_fault_t do_huge_pmd_anonymous_page (struct vm_fault *vmf);int copy_huge_pmd (struct mm_struct *dst_mm,struct mm_struct *src_mm,pmd_t *dst_pmd,pmd_t *src_pmd,unsigned long addr, -struct vm_area_struct *vma); +struct vm_area_struct *dst_vma,struct vm_area_struct *src_vma);void huge_pmd_set_accessed (struct vm_fault *vmf,pmd_t orig_pmd); int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm, pud_t *dst_pud, pud_t *src_pud, unsigned long addr,
include/linux/swapops.h +2 -0
@@ -265,6 +265,8 @@ static inline swp_entry_t pmd_to_swp_entry(pmd_t pmd)if (pmd_swp_soft_dirty (pmd)) pmd =pmd_swp_clear_soft_dirty (pmd); +if (pmd_swp_uffd_wp (pmd)) + pmd =pmd_swp_clear_uffd_wp (pmd); arch_entry =__pmd_to_swp_entry (pmd);return swp_entry (__swp_type (arch_entry),__swp_offset (arch_entry)); }
mm/huge_memory.c +14 -13
@@ -1012,7 +1012,7 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,int copy_huge_pmd (struct mm_struct *dst_mm,struct mm_struct *src_mm,pmd_t *dst_pmd,pmd_t *src_pmd,unsigned long addr, -struct vm_area_struct *vma) +struct vm_area_struct *dst_vma,struct vm_area_struct *src_vma) {spinlock_t *dst_ptl, *src_ptl;struct page *src_page;
@@ -1021,7 +1021,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,int ret = -ENOMEM ;/* Skip if can be re-fill on fault */ -if (!vma_is_anonymous (vma)) +if (!vma_is_anonymous (dst_vma))return 0 ; pgtable =pte_alloc_one (dst_mm);
@@ -1035,14 +1035,6 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, ret = -EAGAIN ; pmd = *src_pmd; -/* -* Make sure the _PAGE_UFFD_WP bit is cleared if the new VMA -* does not have the VM_UFFD_WP, which means that the uffd -* fork event is not enabled. -*/ -if (!(vma->vm_flags &VM_UFFD_WP )) - pmd =pmd_clear_uffd_wp (pmd); -#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION if (unlikely (is_swap_pmd (pmd))) {swp_entry_t entry =pmd_to_swp_entry (pmd);
@@ -1053,11 +1045,15 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd =swp_entry_to_pmd (entry);if (pmd_swp_soft_dirty (*src_pmd)) pmd =pmd_swp_mksoft_dirty (pmd); +if (pmd_swp_uffd_wp (*src_pmd)) + pmd =pmd_swp_mkuffd_wp (pmd);set_pmd_at (src_mm, addr, src_pmd, pmd); }add_mm_counter (dst_mm,MM_ANONPAGES ,HPAGE_PMD_NR );mm_inc_nr_ptes (dst_mm);pgtable_trans_huge_deposit (dst_mm, dst_pmd, pgtable); +if (!userfaultfd_wp (dst_vma)) + pmd =pmd_swp_clear_uffd_wp (pmd);set_pmd_at (dst_mm, addr, dst_pmd, pmd); ret =0 ; goto out_unlock;
@@ -1093,13 +1089,13 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,* best effort that the pinned pages won't be replaced by another * random page during the coming copy-on-write. */ -if (unlikely (is_cow_mapping (vma->vm_flags) && +if (unlikely (is_cow_mapping (src_vma->vm_flags) &&atomic_read (&src_mm->has_pinned) &&page_maybe_dma_pinned (src_page))) {pte_free (dst_mm, pgtable);spin_unlock (src_ptl);spin_unlock (dst_ptl); -__split_huge_pmd (vma, src_pmd, addr, false,NULL ); +__split_huge_pmd (src_vma, src_pmd, addr, false,NULL );return -EAGAIN ; }
@@ -1109,8 +1105,9 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, out_zero_page:mm_inc_nr_ptes (dst_mm);pgtable_trans_huge_deposit (dst_mm, dst_pmd, pgtable); -pmdp_set_wrprotect (src_mm, addr, src_pmd); +if (!userfaultfd_wp (dst_vma)) + pmd =pmd_clear_uffd_wp (pmd); pmd =pmd_mkold (pmd_wrprotect (pmd));set_pmd_at (dst_mm, addr, dst_pmd, pmd);
@@ -1829,6 +1826,8 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, newpmd =swp_entry_to_pmd (entry);if (pmd_swp_soft_dirty (*pmd)) newpmd =pmd_swp_mksoft_dirty (newpmd); +if (pmd_swp_uffd_wp (*pmd)) + newpmd =pmd_swp_mkuffd_wp (newpmd);set_pmd_at (mm, addr, pmd, newpmd); } goto unlock;
@@ -2995,6 +2994,8 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) pmde =pmd_mksoft_dirty (pmde);if (is_write_migration_entry (entry)) pmde =maybe_pmd_mkwrite (pmde, vma); +if (pmd_swp_uffd_wp (*pvmw->pmd)) + pmde =pmd_wrprotect (pmd_mkuffd_wp (pmde));flush_cache_range (vma, mmun_start, mmun_start +HPAGE_PMD_SIZE );if (PageAnon (new))
mm/memory.c +13 -12
@@ -696,10 +696,10 @@ struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr,static unsigned long copy_nonpresent_pte (struct mm_struct *dst_mm,struct mm_struct *src_mm, -pte_t *dst_pte,pte_t *src_pte,struct vm_area_struct *vma, -unsigned long addr,int *rss) +pte_t *dst_pte,pte_t *src_pte,struct vm_area_struct *dst_vma, +struct vm_area_struct *src_vma,unsigned long addr,int *rss) { -unsigned long vm_flags = vma->vm_flags; +unsigned long vm_flags = dst_vma->vm_flags;pte_t pte = *src_pte;struct page *page;swp_entry_t entry =pte_to_swp_entry (pte);
@@ -768,6 +768,8 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,set_pte_at (src_mm, addr, src_pte, pte); } } +if (!userfaultfd_wp (dst_vma)) + pte =pte_swp_clear_uffd_wp (pte);set_pte_at (dst_mm, addr, dst_pte, pte);return 0 ; }
@@ -839,6 +841,9 @@ copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma/* All done, just insert the new page copy in the child */ pte =mk_pte (new_page, dst_vma->vm_page_prot); pte =maybe_mkwrite (pte_mkdirty (pte), dst_vma); +if (userfaultfd_pte_wp (dst_vma, *src_pte)) +/* Uffd-wp needs to be delivered to dest pte as well */ + pte =pte_wrprotect (pte_mkuffd_wp (pte));set_pte_at (dst_vma->vm_mm, addr, dst_pte, pte);return 0 ; }
@@ -888,12 +893,7 @@ copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pte =pte_mkclean (pte); pte =pte_mkold (pte); -/* -* Make sure the _PAGE_UFFD_WP bit is cleared if the new VMA -* does not have the VM_UFFD_WP, which means that the uffd -* fork event is not enabled. -*/ -if (!(vm_flags &VM_UFFD_WP )) +if (!userfaultfd_wp (dst_vma)) pte =pte_clear_uffd_wp (pte);set_pte_at (dst_vma->vm_mm, addr, dst_pte, pte);
@@ -968,7 +968,8 @@ copy_pte_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,if (unlikely (!pte_present (*src_pte))) { entry.val =copy_nonpresent_pte (dst_mm, src_mm, dst_pte, src_pte, - src_vma, addr, rss); + dst_vma, src_vma, + addr, rss);if (entry.val)break ; progress +=8 ;
@@ -1045,8 +1046,8 @@ copy_pmd_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, || pmd_devmap(*src_pmd)) {int err;VM_BUG_ON_VMA (next-addr !=HPAGE_PMD_SIZE , src_vma); - err =copy_huge_pmd (dst_mm, src_mm, - dst_pmd, src_pmd, addr, src_vma); + err =copy_huge_pmd (dst_mm, src_mm, dst_pmd, src_pmd, + addr, dst_vma, src_vma);if (err == -ENOMEM )return -ENOMEM ;if (!err)
Signature · 1 line
2.31.1
Re: [PATCH stable 5.10.y 0/2] mm/thp: Fix uffd-wp with fork(); crash on pmd migration entry on fork
In reply to Peter XuQuoted 24 lines · Peter Xu
In summary, this series should be needed for 5.10/5.12/5.13. This is the 5.10.y backport of the series. Patch 1 is a dependency of patch 2, while patch 2 should be the real fix.
There's a minor conflict on patch 2 when cherry pick due to not having the new helper called
page_needs_cow_for_dma(). It's also mentioned at the entry of patch 2.This series should be able to fix a rare race that mentioned in thread:
https://lore.kernel.org/linux-mm/[email protected]/
This fact wasn't discovered when the fix got proposed and merged, because the fix was originally about uffd-wp and its fork event. However it turns out that the problematic commit
b569a1760782f3dis also causing crashing onfork()of pmd migration entries which is even more severe than the original uffd-wp problem.Stable kernels at least on 5.12.y has the crash reproduced, and it's possible 5.13.y and 5.10.y could hit it due to having the problematic commit
b569a1760782f3dbut lacking of the uffd-wp fix patch (8f34f1eac382, which is also patch 2 of this series).
Quoted 4 lines
The pmd entry crash problem was reported by Igor Raits <[email protected]> and debugged by Hugh Dickins <[email protected]>.
Please review, thanks.
And these two for 5.10.y look good to me also: I'm glad you decided in the end to keep 5.10's support for uffd-wp-fork.
The first is just a straight cherry-pick of 5fc7a5f6fd04bc18f309d9f979b32ef7d1d0a997, but as you noted above, 8f34f1eac3820fc2722e5159acceb22545b30b0d needed one line of fixup for that tree.
Thank you Peter,
Hugh
Quoted 15 lines
Peter Xu (2):
mm/thp: simplify copying of huge zero page pmd when fork mm/userfaultfd: fix uffd-wp special cases forfork()include/linux/huge_mm.h | 2 +- include/linux/swapops.h | 2 ++ mm/huge_memory.c | 36 +++++++++++++++++------------------- mm/memory.c | 25 +++++++++++++------------ 4 files changed, 33 insertions(+), 32 deletions(-)--
2.31.1
Greg KH
maintainerRe: [PATCH stable 5.10.y 0/2] mm/thp: Fix uffd-wp with fork(); crash on pmd migration entry on fork
Quoted 28 lines · Hugh Dickins
Quoted 27 lines · Peter Xu
In summary, this series should be needed for 5.10/5.12/5.13. This is the 5.10.y backport of the series. Patch 1 is a dependency of patch 2, while patch 2 should be the real fix.
There's a minor conflict on patch 2 when cherry pick due to not having the new helper called
page_needs_cow_for_dma(). It's also mentioned at the entry of patch 2.This series should be able to fix a rare race that mentioned in thread:
https://lore.kernel.org/linux-mm/[email protected]/
This fact wasn't discovered when the fix got proposed and merged, because the fix was originally about uffd-wp and its fork event. However it turns out that the problematic commit
b569a1760782f3dis also causing crashing onfork()of pmd migration entries which is even more severe than the original uffd-wp problem.Stable kernels at least on 5.12.y has the crash reproduced, and it's possible 5.13.y and 5.10.y could hit it due to having the problematic commit
b569a1760782f3dbut lacking of the uffd-wp fix patch (8f34f1eac382, which is also patch 2 of this series).The pmd entry crash problem was reported by Igor Raits <[email protected]> and debugged by Hugh Dickins <[email protected]>.
Quoted 8 lines
Quoted 1 line
Please review, thanks.
And these two for 5.10.y look good to me also: I'm glad you decided in the end to keep 5.10's support for uffd-wp-fork.
The first is just a straight cherry-pick of5fc7a5f6fd04bc18f309d9f979b32ef7d1d0a997, but as you noted above,8f34f1eac3820fc2722e5159acceb22545b30b0dneeded one line of fixup for that tree.
All now queued up, thanks.
greg k-h