| Message ID | 20191031093909.9228-2-dja@axtens.net (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | kasan: support backing vmalloc space with real shadow memory | expand |
On Thu, 2019-10-31 at 20:39 +1100, Daniel Axtens wrote: > /* > * In this function, newly allocated vm_struct has VM_UNINITIALIZED > * flag. It means that vm_struct is not fully initialized. > @@ -3377,6 +3411,9 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, > > setup_vmalloc_vm_locked(vms[area], vas[area], VM_ALLOC, > pcpu_get_vm_areas); > + > + /* assume success here */ > + kasan_populate_vmalloc(sizes[area], vms[area]); > } > spin_unlock(&vmap_area_lock); Here it is all wrong. GFP_KERNEL with in_atomic(). [ 32.231000][ T1] BUG: sleeping function called from invalid context at mm/page_alloc.c:4681 [ 32.239934][ T1] in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 1, name: swapper/0 [ 32.248896][ T1] 2 locks held by swapper/0/1: [ 32.253580][ T1] #0: ffffffff880d6160 (pcpu_alloc_mutex){+.+.}, at: pcpu_alloc+0x707/0xbe0 [ 32.262305][ T1] #1: ffffffff88105558 (vmap_area_lock){+.+.}, at: pcpu_get_vm_areas+0xc4f/0x1e60 [ 32.271919][ T1] CPU: 4 PID: 1 Comm: swapper/0 Tainted: G W 5.4.0-rc7-next-20191115+ #6 [ 32.281555][ T1] Hardware name: HPE ProLiant DL385 Gen10/ProLiant DL385 Gen10, BIOS A40 03/09/2018 [ 32.281896][ T1] Call Trace: [ 32.281896][ T1] dump_stack+0xa0/0xea [ 32.281896][ T1] ___might_sleep.cold.89+0xd2/0x122 [ 32.301996][ T1] __might_sleep+0x73/0xe0 [ 32.301996][ T1] __alloc_pages_nodemask+0x442/0x720 [ 32.311564][ T1] ? __kasan_check_read+0x11/0x20 [ 32.311564][ T1] ? __alloc_pages_slowpath+0x1870/0x1870 [ 32.321705][ T1] ? mark_held_locks+0x86/0xb0 [ 32.321705][ T1] ? _raw_spin_unlock_irqrestore+0x44/0x50 [ 32.331563][ T1] alloc_page_interleave+0x18/0x130 [ 32.331563][ T1] alloc_pages_current+0xf6/0x110 [ 32.341979][ T1] __get_free_pages+0x12/0x60 [ 32.341979][ T1] __pte_alloc_kernel+0x1b/0xc0 [ 32.351563][ T1] apply_to_page_range+0x5b5/0x690 [ 32.351563][ T1] ? memset+0x40/0x40 [ 32.361693][ T1] kasan_populate_vmalloc+0x6d/0xa0 [ 32.361693][ T1] pcpu_get_vm_areas+0xd49/0x1e60 [ 32.371425][ T1] ? vm_map_ram+0x10d0/0x10d0 [ 32.371425][ T1] ? pcpu_mem_zalloc+0x65/0x90 [ 32.371425][ T1] pcpu_create_chunk+0x152/0x3f0 [ 32.371425][ T1] pcpu_alloc+0xa2f/0xbe0 [ 32.391423][ T1] ? pcpu_balance_workfn+0xb00/0xb00 [ 32.391423][ T1] ? __kasan_kmalloc.constprop.11+0xc1/0xd0 [ 32.391423][ T1] ? kasan_kmalloc+0x9/0x10 [ 32.391423][ T1] ? kmem_cache_alloc_trace+0x1f8/0x470 [ 32.411421][ T1] ? iommu_dma_get_resv_regions+0x10/0x10 [ 32.411421][ T1] __alloc_percpu+0x15/0x20 [ 32.411421][ T1] init_iova_flush_queue+0x79/0x230 [ 32.411421][ T1] iommu_setup_dma_ops+0x87d/0x890 [ 32.431420][ T1] ? __kasan_check_write+0x14/0x20 [ 32.431420][ T1] ? refcount_sub_and_test_checked+0xba/0x170 [ 32.431420][ T1] ? __kasan_check_write+0x14/0x20 [ 32.431420][ T1] ? iommu_dma_alloc+0x1e0/0x1e0 [ 32.451420][ T1] ? iommu_group_get_for_dev+0x153/0x450 [ 32.451420][ T1] ? refcount_dec_and_test_checked+0x11/0x20 [ 32.451420][ T1] ? kobject_put+0x36/0x270 [ 32.451420][ T1] amd_iommu_add_device+0x560/0x710 [ 32.471423][ T1] ? iommu_probe_device+0x150/0x150 [ 32.471423][ T1] iommu_probe_device+0x8c/0x150 [ 32.471423][ T1] add_iommu_group+0xe/0x20 [ 32.471423][ T1] bus_for_each_dev+0xfe/0x160 [ 32.491421][ T1] ? subsys_dev_iter_init+0x80/0x80 [ 32.491421][ T1] ? blocking_notifier_chain_register+0x4f/0x70 [ 32.491421][ T1] bus_set_iommu+0xc6/0x100 [ 32.491421][ T1] ? e820__memblock_setup+0x10e/0x10e [ 32.511571][ T1] amd_iommu_init_api+0x25/0x3e [ 32.511571][ T1] state_next+0x214/0x7ea [ 32.511571][ T1] ? check_flags.part.25+0x86/0x220 [ 32.511571][ T1] ? early_amd_iommu_init+0x10c0/0x10c0 [ 32.531421][ T1] ? e820__memblock_setup+0x10e/0x10e [ 32.531421][ T1] ? rcu_read_lock_sched_held+0xac/0xe0 [ 32.531421][ T1] ? e820__memblock_setup+0x10e/0x10e [ 32.551423][ T1] amd_iommu_init+0x25/0x57 [ 32.551423][ T1] pci_iommu_init+0x26/0x62 [ 32.551423][ T1] do_one_initcall+0xfe/0x4fa [ 32.551423][ T1] ? perf_trace_initcall_level+0x240/0x240 [ 32.571420][ T1] ? rcu_read_lock_sched_held+0xac/0xe0 [ 32.571420][ T1] ? rcu_read_lock_bh_held+0xc0/0xc0 [ 32.571420][ T1] ? __kasan_check_read+0x11/0x20 [ 32.571420][ T1] kernel_init_freeable+0x420/0x4e4 [ 32.591420][ T1] ? start_kernel+0x6a9/0x6a9 [ 32.591420][ T1] ? lockdep_hardirqs_on+0x1b0/0x2a0 [ 32.591420][ T1] ? _raw_spin_unlock_irq+0x27/0x40 [ 32.591420][ T1] ? rest_init+0x307/0x307 [ 32.611557][ T1] kernel_init+0x11/0x139 [ 32.611557][ T1] ? rest_init+0x307/0x307 [ 32.611557][ T1] ret_from_fork+0x27/0x50 [ 32.054647][ T1] BUG: sleeping function called from invalid context at mm/page_alloc.c:4681 [ 32.063814][ T1] in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 1, name: swapper/0 [ 32.072444][ T1] 2 locks held by swapper/0/1: [ 32.077104][ T1] #0: ffffffffac0d6160 (pcpu_alloc_mutex){+.+.}, at: pcpu_alloc+0x707/0xbe0 [ 32.086227][ T1] #1: ffffffffac105558 (vmap_area_lock){+.+.}, at: pcpu_get_vm_areas+0xc4f/0x1e50 [ 32.095478][ T1] CPU: 53 PID: 1 Comm: swapper/0 Tainted: G W 5.4.0-rc7-next-20191115 #5 [ 32.105115][ T1] Hardware name: HPE ProLiant DL385 Gen10/ProLiant DL385 Gen10, BIOS A40 03/09/2018 [ 32.105450][ T1] Call Trace: [ 32.105450][ T1] dump_stack+0xa0/0xea [ 32.105450][ T1] ___might_sleep.cold.89+0xd2/0x122 [ 32.105450][ T1] __might_sleep+0x73/0xe0 [ 32.105450][ T1] __alloc_pages_nodemask+0x442/0x720 [ 32.105450][ T1] ? add_iommu_group+0xe/0x20 [ 32.105450][ T1] ? bus_for_each_dev+0xfe/0x160 [ 32.105450][ T1] ? __alloc_pages_slowpath+0x1870/0x1870 [ 32.105450][ T1] ? check_chain_key+0x1df/0x2e0 [ 32.105450][ T1] alloc_page_interleave+0x18/0x130 [ 32.105450][ T1] alloc_pages_current+0xf6/0x110 [ 32.105450][ T1] __get_free_pages+0x12/0x60 [ 32.105450][ T1] kasan_populate_vmalloc_pte+0x2a/0x150 [ 32.105450][ T1] ? register_lock_class+0x940/0x940 [ 32.105450][ T1] apply_to_page_range+0x42d/0x690 [ 32.105450][ T1] ? memset+0x40/0x40 [ 32.105450][ T1] kasan_populate_vmalloc+0x69/0xa0 [ 32.105450][ T1] pcpu_get_vm_areas+0xd44/0x1e50 [ 32.105450][ T1] ? vm_map_ram+0x10d0/0x10d0 [ 32.105450][ T1] ? pcpu_mem_zalloc+0x65/0x90 [ 32.105450][ T1] pcpu_create_chunk+0x152/0x3f0 [ 32.105450][ T1] pcpu_alloc+0xa2f/0xbe0 [ 32.105450][ T1] ? pcpu_balance_workfn+0xb00/0xb00 [ 32.105450][ T1] ? __kasan_kmalloc.constprop.11+0xc1/0xd0 [ 32.105450][ T1] ? kasan_kmalloc+0x9/0x10 [ 32.105450][ T1] ? kmem_cache_alloc_trace+0x1f8/0x470 [ 32.105450][ T1] ? iommu_dma_get_resv_regions+0x10/0x10 [ 32.105450][ T1] __alloc_percpu+0x15/0x20 [ 32.105450][ T1] init_iova_flush_queue+0x79/0x230 [ 32.105450][ T1] iommu_setup_dma_ops+0x87d/0x890 [ 32.105450][ T1] ? __kasan_check_write+0x14/0x20 [ 32.105450][ T1] ? refcount_sub_and_test_checked+0xba/0x170 [ 32.105450][ T1] ? __kasan_check_write+0x14/0x20 [ 32.105450][ T1] ? iommu_dma_alloc+0x1e0/0x1e0 [ 32.105450][ T1] ? iommu_group_get_for_dev+0x153/0x450 [ 32.105450][ T1] ? refcount_dec_and_test_checked+0x11/0x20 [ 32.105450][ T1] ? kobject_put+0x36/0x270 [ 32.105450][ T1] amd_iommu_add_device+0x560/0x710 [ 32.105450][ T1] ? iommu_probe_device+0x150/0x150 [ 32.105450][ T1] iommu_probe_device+0x8c/0x150 [ 32.105450][ T1] add_iommu_group+0xe/0x20 [ 32.105450][ T1] bus_for_each_dev+0xfe/0x160 [ 32.105450][ T1] ? subsys_dev_iter_init+0x80/0x80 [ 32.105450][ T1] ? blocking_notifier_chain_register+0x4f/0x70 [ 32.105450][ T1] bus_set_iommu+0xc6/0x100 [ 32.105450][ T1] ? e820__memblock_setup+0x10e/0x10e [ 32.105450][ T1] amd_iommu_init_api+0x25/0x3e [ 32.105450][ T1] state_next+0x214/0x7ea [ 32.105450][ T1] ? check_flags.part.25+0x86/0x220 [ 32.105450][ T1] ? early_amd_iommu_init+0x10c0/0x10c0 [ 32.105450][ T1] ? e820__memblock_setup+0x10e/0x10e [ 32.105450][ T1] ? rcu_read_lock_sched_held+0xac/0xe0 [ 32.105450][ T1] ? e820__memblock_setup+0x10e/0x10e [ 32.105450][ T1] amd_iommu_init+0x25/0x57 [ 32.105450][ T1] pci_iommu_init+0x26/0x62 [ 32.105450][ T1] do_one_initcall+0xfe/0x4fa [ 32.105450][ T1].781281][ T1] pci 0000:60:08.0: Adding to iommu group 63 [ 32.831700][ T1] pci 0000:60:08.1: Adding to iommu group 64 [ 32.883138][ T1] pci 0000:63:00.0: Adding to iommu group 65 [ 32.933084][ T1] pci 0000:63:00.1: Adding to iommu group 65 [ 32.940474][ T1] pci 0000:62:00.0: Adding to iommu group 66 [ 32.991631][ T1] pci 0000:62:00.2: Adding to iommu group 67 [ 33.042553][ T1] pci 0000:61:00.0: Adding to iommu group 68
Qian Cai <cai@lca.pw> writes: > On Thu, 2019-10-31 at 20:39 +1100, Daniel Axtens wrote: >> /* >> * In this function, newly allocated vm_struct has VM_UNINITIALIZED >> * flag. It means that vm_struct is not fully initialized. >> @@ -3377,6 +3411,9 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, >> >> setup_vmalloc_vm_locked(vms[area], vas[area], VM_ALLOC, >> pcpu_get_vm_areas); >> + >> + /* assume success here */ >> + kasan_populate_vmalloc(sizes[area], vms[area]); >> } >> spin_unlock(&vmap_area_lock); > > Here it is all wrong. GFP_KERNEL with in_atomic(). I think this fix will work, I will do a v12 with it included. diff --git a/mm/vmalloc.c b/mm/vmalloc.c index a4b950a02d0b..bf030516258c 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -3417,11 +3417,14 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, setup_vmalloc_vm_locked(vms[area], vas[area], VM_ALLOC, pcpu_get_vm_areas); + } + spin_unlock(&vmap_area_lock); + /* populate the shadow space outside of the lock */ + for (area = 0; area < nr_vms; area++) { /* assume success here */ kasan_populate_vmalloc(sizes[area], vms[area]); } - spin_unlock(&vmap_area_lock); kfree(vas); return vms;
On 11/18/19 6:29 AM, Daniel Axtens wrote: > Qian Cai <cai@lca.pw> writes: > >> On Thu, 2019-10-31 at 20:39 +1100, Daniel Axtens wrote: >>> /* >>> * In this function, newly allocated vm_struct has VM_UNINITIALIZED >>> * flag. It means that vm_struct is not fully initialized. >>> @@ -3377,6 +3411,9 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, >>> >>> setup_vmalloc_vm_locked(vms[area], vas[area], VM_ALLOC, >>> pcpu_get_vm_areas); >>> + >>> + /* assume success here */ >>> + kasan_populate_vmalloc(sizes[area], vms[area]); >>> } >>> spin_unlock(&vmap_area_lock); >> >> Here it is all wrong. GFP_KERNEL with in_atomic(). > > I think this fix will work, I will do a v12 with it included. You can send just the fix. Andrew will fold it into the original patch before sending it to Linus. > diff --git a/mm/vmalloc.c b/mm/vmalloc.c > index a4b950a02d0b..bf030516258c 100644 > --- a/mm/vmalloc.c > +++ b/mm/vmalloc.c > @@ -3417,11 +3417,14 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, > > setup_vmalloc_vm_locked(vms[area], vas[area], VM_ALLOC, > pcpu_get_vm_areas); > + } > + spin_unlock(&vmap_area_lock); > > + /* populate the shadow space outside of the lock */ > + for (area = 0; area < nr_vms; area++) { > /* assume success here */ > kasan_populate_vmalloc(sizes[area], vms[area]); > } > - spin_unlock(&vmap_area_lock); > > kfree(vas); > return vms; > >
On Tue, Nov 19, 2019 at 10:54 AM Andrey Ryabinin <aryabinin@virtuozzo.com> wrote: > On 11/18/19 6:29 AM, Daniel Axtens wrote: > > Qian Cai <cai@lca.pw> writes: > > > >> On Thu, 2019-10-31 at 20:39 +1100, Daniel Axtens wrote: > >>> /* > >>> * In this function, newly allocated vm_struct has VM_UNINITIALIZED > >>> * flag. It means that vm_struct is not fully initialized. > >>> @@ -3377,6 +3411,9 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, > >>> > >>> setup_vmalloc_vm_locked(vms[area], vas[area], VM_ALLOC, > >>> pcpu_get_vm_areas); > >>> + > >>> + /* assume success here */ > >>> + kasan_populate_vmalloc(sizes[area], vms[area]); > >>> } > >>> spin_unlock(&vmap_area_lock); > >> > >> Here it is all wrong. GFP_KERNEL with in_atomic(). > > > > I think this fix will work, I will do a v12 with it included. > > You can send just the fix. Andrew will fold it into the original patch before sending it to Linus. > > > > > diff --git a/mm/vmalloc.c b/mm/vmalloc.c > > index a4b950a02d0b..bf030516258c 100644 > > --- a/mm/vmalloc.c > > +++ b/mm/vmalloc.c > > @@ -3417,11 +3417,14 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, > > > > setup_vmalloc_vm_locked(vms[area], vas[area], VM_ALLOC, > > pcpu_get_vm_areas); > > + } > > + spin_unlock(&vmap_area_lock); > > > > + /* populate the shadow space outside of the lock */ > > + for (area = 0; area < nr_vms; area++) { > > /* assume success here */ > > kasan_populate_vmalloc(sizes[area], vms[area]); > > } > > - spin_unlock(&vmap_area_lock); > > > > kfree(vas); > > return vms; Hi, I am testing this support on next-20191129 and seeing the following warnings: BUG: sleeping function called from invalid context at mm/page_alloc.c:4681 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 44, name: kworker/1:1 4 locks held by kworker/1:1/44: #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: __write_once_size include/linux/compiler.h:247 [inline] #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: arch_atomic64_set arch/x86/include/asm/atomic64_64.h:34 [inline] #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: atomic64_set include/asm-generic/atomic-instrumented.h:868 [inline] #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: atomic_long_set include/asm-generic/atomic-long.h:40 [inline] #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: set_work_data kernel/workqueue.c:615 [inline] #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: set_work_pool_and_clear_pending kernel/workqueue.c:642 [inline] #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: process_one_work+0x88b/0x1750 kernel/workqueue.c:2235 #1: ffffc900002afdf0 (pcpu_balance_work){+.+.}, at: process_one_work+0x8c0/0x1750 kernel/workqueue.c:2239 #2: ffffffff8943f080 (pcpu_alloc_mutex){+.+.}, at: pcpu_balance_workfn+0xcc/0x13e0 mm/percpu.c:1845 #3: ffffffff89450c78 (vmap_area_lock){+.+.}, at: spin_lock include/linux/spinlock.h:338 [inline] #3: ffffffff89450c78 (vmap_area_lock){+.+.}, at: pcpu_get_vm_areas+0x1449/0x3df0 mm/vmalloc.c:3431 Preemption disabled at: [<ffffffff81a84199>] spin_lock include/linux/spinlock.h:338 [inline] [<ffffffff81a84199>] pcpu_get_vm_areas+0x1449/0x3df0 mm/vmalloc.c:3431 CPU: 1 PID: 44 Comm: kworker/1:1 Not tainted 5.4.0-next-20191129+ #5 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.12.0-1 04/01/2014 Workqueue: events pcpu_balance_workfn Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x199/0x216 lib/dump_stack.c:118 ___might_sleep.cold.97+0x1f5/0x238 kernel/sched/core.c:6800 __might_sleep+0x95/0x190 kernel/sched/core.c:6753 prepare_alloc_pages mm/page_alloc.c:4681 [inline] __alloc_pages_nodemask+0x3cd/0x890 mm/page_alloc.c:4730 alloc_pages_current+0x10c/0x210 mm/mempolicy.c:2211 alloc_pages include/linux/gfp.h:532 [inline] __get_free_pages+0xc/0x40 mm/page_alloc.c:4786 kasan_populate_vmalloc_pte mm/kasan/common.c:762 [inline] kasan_populate_vmalloc_pte+0x2f/0x1b0 mm/kasan/common.c:753 apply_to_pte_range mm/memory.c:2041 [inline] apply_to_pmd_range mm/memory.c:2068 [inline] apply_to_pud_range mm/memory.c:2088 [inline] apply_to_p4d_range mm/memory.c:2108 [inline] apply_to_page_range+0x5ca/0xa00 mm/memory.c:2133 kasan_populate_vmalloc+0x69/0xa0 mm/kasan/common.c:791 pcpu_get_vm_areas+0x1596/0x3df0 mm/vmalloc.c:3439 pcpu_create_chunk+0x240/0x7f0 mm/percpu-vm.c:340 pcpu_balance_workfn+0x1033/0x13e0 mm/percpu.c:1934 process_one_work+0x9b5/0x1750 kernel/workqueue.c:2264 worker_thread+0x8b/0xd20 kernel/workqueue.c:2410 kthread+0x365/0x450 kernel/kthread.c:255 ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:352 Not sure if it's the same or not. Is it addressed by something in flight? My config: https://gist.githubusercontent.com/dvyukov/36c7be311fdec9cd51c649f7c3cb2ddb/raw/39c6f864fdd0ffc53f0822b14c354a73c1695fa1/gistfile1.txt
On Fri, Nov 29, 2019 at 11:43 AM Dmitry Vyukov <dvyukov@google.com> wrote: > > On Tue, Nov 19, 2019 at 10:54 AM Andrey Ryabinin > <aryabinin@virtuozzo.com> wrote: > > On 11/18/19 6:29 AM, Daniel Axtens wrote: > > > Qian Cai <cai@lca.pw> writes: > > > > > >> On Thu, 2019-10-31 at 20:39 +1100, Daniel Axtens wrote: > > >>> /* > > >>> * In this function, newly allocated vm_struct has VM_UNINITIALIZED > > >>> * flag. It means that vm_struct is not fully initialized. > > >>> @@ -3377,6 +3411,9 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, > > >>> > > >>> setup_vmalloc_vm_locked(vms[area], vas[area], VM_ALLOC, > > >>> pcpu_get_vm_areas); > > >>> + > > >>> + /* assume success here */ > > >>> + kasan_populate_vmalloc(sizes[area], vms[area]); > > >>> } > > >>> spin_unlock(&vmap_area_lock); > > >> > > >> Here it is all wrong. GFP_KERNEL with in_atomic(). > > > > > > I think this fix will work, I will do a v12 with it included. > > > > You can send just the fix. Andrew will fold it into the original patch before sending it to Linus. > > > > > > > > > diff --git a/mm/vmalloc.c b/mm/vmalloc.c > > > index a4b950a02d0b..bf030516258c 100644 > > > --- a/mm/vmalloc.c > > > +++ b/mm/vmalloc.c > > > @@ -3417,11 +3417,14 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, > > > > > > setup_vmalloc_vm_locked(vms[area], vas[area], VM_ALLOC, > > > pcpu_get_vm_areas); > > > + } > > > + spin_unlock(&vmap_area_lock); > > > > > > + /* populate the shadow space outside of the lock */ > > > + for (area = 0; area < nr_vms; area++) { > > > /* assume success here */ > > > kasan_populate_vmalloc(sizes[area], vms[area]); > > > } > > > - spin_unlock(&vmap_area_lock); > > > > > > kfree(vas); > > > return vms; > > Hi, > > I am testing this support on next-20191129 and seeing the following warnings: > > BUG: sleeping function called from invalid context at mm/page_alloc.c:4681 > in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 44, name: kworker/1:1 > 4 locks held by kworker/1:1/44: > #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: > __write_once_size include/linux/compiler.h:247 [inline] > #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: > arch_atomic64_set arch/x86/include/asm/atomic64_64.h:34 [inline] > #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: atomic64_set > include/asm-generic/atomic-instrumented.h:868 [inline] > #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: > atomic_long_set include/asm-generic/atomic-long.h:40 [inline] > #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: set_work_data > kernel/workqueue.c:615 [inline] > #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: > set_work_pool_and_clear_pending kernel/workqueue.c:642 [inline] > #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: > process_one_work+0x88b/0x1750 kernel/workqueue.c:2235 > #1: ffffc900002afdf0 (pcpu_balance_work){+.+.}, at: > process_one_work+0x8c0/0x1750 kernel/workqueue.c:2239 > #2: ffffffff8943f080 (pcpu_alloc_mutex){+.+.}, at: > pcpu_balance_workfn+0xcc/0x13e0 mm/percpu.c:1845 > #3: ffffffff89450c78 (vmap_area_lock){+.+.}, at: spin_lock > include/linux/spinlock.h:338 [inline] > #3: ffffffff89450c78 (vmap_area_lock){+.+.}, at: > pcpu_get_vm_areas+0x1449/0x3df0 mm/vmalloc.c:3431 > Preemption disabled at: > [<ffffffff81a84199>] spin_lock include/linux/spinlock.h:338 [inline] > [<ffffffff81a84199>] pcpu_get_vm_areas+0x1449/0x3df0 mm/vmalloc.c:3431 > CPU: 1 PID: 44 Comm: kworker/1:1 Not tainted 5.4.0-next-20191129+ #5 > Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.12.0-1 04/01/2014 > Workqueue: events pcpu_balance_workfn > Call Trace: > __dump_stack lib/dump_stack.c:77 [inline] > dump_stack+0x199/0x216 lib/dump_stack.c:118 > ___might_sleep.cold.97+0x1f5/0x238 kernel/sched/core.c:6800 > __might_sleep+0x95/0x190 kernel/sched/core.c:6753 > prepare_alloc_pages mm/page_alloc.c:4681 [inline] > __alloc_pages_nodemask+0x3cd/0x890 mm/page_alloc.c:4730 > alloc_pages_current+0x10c/0x210 mm/mempolicy.c:2211 > alloc_pages include/linux/gfp.h:532 [inline] > __get_free_pages+0xc/0x40 mm/page_alloc.c:4786 > kasan_populate_vmalloc_pte mm/kasan/common.c:762 [inline] > kasan_populate_vmalloc_pte+0x2f/0x1b0 mm/kasan/common.c:753 > apply_to_pte_range mm/memory.c:2041 [inline] > apply_to_pmd_range mm/memory.c:2068 [inline] > apply_to_pud_range mm/memory.c:2088 [inline] > apply_to_p4d_range mm/memory.c:2108 [inline] > apply_to_page_range+0x5ca/0xa00 mm/memory.c:2133 > kasan_populate_vmalloc+0x69/0xa0 mm/kasan/common.c:791 > pcpu_get_vm_areas+0x1596/0x3df0 mm/vmalloc.c:3439 > pcpu_create_chunk+0x240/0x7f0 mm/percpu-vm.c:340 > pcpu_balance_workfn+0x1033/0x13e0 mm/percpu.c:1934 > process_one_work+0x9b5/0x1750 kernel/workqueue.c:2264 > worker_thread+0x8b/0xd20 kernel/workqueue.c:2410 > kthread+0x365/0x450 kernel/kthread.c:255 > ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:352 > > > Not sure if it's the same or not. Is it addressed by something in flight? > > My config: > https://gist.githubusercontent.com/dvyukov/36c7be311fdec9cd51c649f7c3cb2ddb/raw/39c6f864fdd0ffc53f0822b14c354a73c1695fa1/gistfile1.txt I've tried this fix for pcpu_get_vm_areas: https://groups.google.com/d/msg/kasan-dev/t_F2X1MWKwk/h152Z3q2AgAJ and it helps. But this will break syzbot on linux-next soon.
On Fri, Nov 29, 2019 at 11:58 AM Dmitry Vyukov <dvyukov@google.com> wrote: > > On Fri, Nov 29, 2019 at 11:43 AM Dmitry Vyukov <dvyukov@google.com> wrote: > > > > On Tue, Nov 19, 2019 at 10:54 AM Andrey Ryabinin > > <aryabinin@virtuozzo.com> wrote: > > > On 11/18/19 6:29 AM, Daniel Axtens wrote: > > > > Qian Cai <cai@lca.pw> writes: > > > > > > > >> On Thu, 2019-10-31 at 20:39 +1100, Daniel Axtens wrote: > > > >>> /* > > > >>> * In this function, newly allocated vm_struct has VM_UNINITIALIZED > > > >>> * flag. It means that vm_struct is not fully initialized. > > > >>> @@ -3377,6 +3411,9 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, > > > >>> > > > >>> setup_vmalloc_vm_locked(vms[area], vas[area], VM_ALLOC, > > > >>> pcpu_get_vm_areas); > > > >>> + > > > >>> + /* assume success here */ > > > >>> + kasan_populate_vmalloc(sizes[area], vms[area]); > > > >>> } > > > >>> spin_unlock(&vmap_area_lock); > > > >> > > > >> Here it is all wrong. GFP_KERNEL with in_atomic(). > > > > > > > > I think this fix will work, I will do a v12 with it included. > > > > > > You can send just the fix. Andrew will fold it into the original patch before sending it to Linus. > > > > > > > > > > > > > diff --git a/mm/vmalloc.c b/mm/vmalloc.c > > > > index a4b950a02d0b..bf030516258c 100644 > > > > --- a/mm/vmalloc.c > > > > +++ b/mm/vmalloc.c > > > > @@ -3417,11 +3417,14 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, > > > > > > > > setup_vmalloc_vm_locked(vms[area], vas[area], VM_ALLOC, > > > > pcpu_get_vm_areas); > > > > + } > > > > + spin_unlock(&vmap_area_lock); > > > > > > > > + /* populate the shadow space outside of the lock */ > > > > + for (area = 0; area < nr_vms; area++) { > > > > /* assume success here */ > > > > kasan_populate_vmalloc(sizes[area], vms[area]); > > > > } > > > > - spin_unlock(&vmap_area_lock); > > > > > > > > kfree(vas); > > > > return vms; > > > > Hi, > > > > I am testing this support on next-20191129 and seeing the following warnings: > > > > BUG: sleeping function called from invalid context at mm/page_alloc.c:4681 > > in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 44, name: kworker/1:1 > > 4 locks held by kworker/1:1/44: > > #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: > > __write_once_size include/linux/compiler.h:247 [inline] > > #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: > > arch_atomic64_set arch/x86/include/asm/atomic64_64.h:34 [inline] > > #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: atomic64_set > > include/asm-generic/atomic-instrumented.h:868 [inline] > > #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: > > atomic_long_set include/asm-generic/atomic-long.h:40 [inline] > > #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: set_work_data > > kernel/workqueue.c:615 [inline] > > #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: > > set_work_pool_and_clear_pending kernel/workqueue.c:642 [inline] > > #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: > > process_one_work+0x88b/0x1750 kernel/workqueue.c:2235 > > #1: ffffc900002afdf0 (pcpu_balance_work){+.+.}, at: > > process_one_work+0x8c0/0x1750 kernel/workqueue.c:2239 > > #2: ffffffff8943f080 (pcpu_alloc_mutex){+.+.}, at: > > pcpu_balance_workfn+0xcc/0x13e0 mm/percpu.c:1845 > > #3: ffffffff89450c78 (vmap_area_lock){+.+.}, at: spin_lock > > include/linux/spinlock.h:338 [inline] > > #3: ffffffff89450c78 (vmap_area_lock){+.+.}, at: > > pcpu_get_vm_areas+0x1449/0x3df0 mm/vmalloc.c:3431 > > Preemption disabled at: > > [<ffffffff81a84199>] spin_lock include/linux/spinlock.h:338 [inline] > > [<ffffffff81a84199>] pcpu_get_vm_areas+0x1449/0x3df0 mm/vmalloc.c:3431 > > CPU: 1 PID: 44 Comm: kworker/1:1 Not tainted 5.4.0-next-20191129+ #5 > > Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.12.0-1 04/01/2014 > > Workqueue: events pcpu_balance_workfn > > Call Trace: > > __dump_stack lib/dump_stack.c:77 [inline] > > dump_stack+0x199/0x216 lib/dump_stack.c:118 > > ___might_sleep.cold.97+0x1f5/0x238 kernel/sched/core.c:6800 > > __might_sleep+0x95/0x190 kernel/sched/core.c:6753 > > prepare_alloc_pages mm/page_alloc.c:4681 [inline] > > __alloc_pages_nodemask+0x3cd/0x890 mm/page_alloc.c:4730 > > alloc_pages_current+0x10c/0x210 mm/mempolicy.c:2211 > > alloc_pages include/linux/gfp.h:532 [inline] > > __get_free_pages+0xc/0x40 mm/page_alloc.c:4786 > > kasan_populate_vmalloc_pte mm/kasan/common.c:762 [inline] > > kasan_populate_vmalloc_pte+0x2f/0x1b0 mm/kasan/common.c:753 > > apply_to_pte_range mm/memory.c:2041 [inline] > > apply_to_pmd_range mm/memory.c:2068 [inline] > > apply_to_pud_range mm/memory.c:2088 [inline] > > apply_to_p4d_range mm/memory.c:2108 [inline] > > apply_to_page_range+0x5ca/0xa00 mm/memory.c:2133 > > kasan_populate_vmalloc+0x69/0xa0 mm/kasan/common.c:791 > > pcpu_get_vm_areas+0x1596/0x3df0 mm/vmalloc.c:3439 > > pcpu_create_chunk+0x240/0x7f0 mm/percpu-vm.c:340 > > pcpu_balance_workfn+0x1033/0x13e0 mm/percpu.c:1934 > > process_one_work+0x9b5/0x1750 kernel/workqueue.c:2264 > > worker_thread+0x8b/0xd20 kernel/workqueue.c:2410 > > kthread+0x365/0x450 kernel/kthread.c:255 > > ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:352 > > > > > > Not sure if it's the same or not. Is it addressed by something in flight? > > > > My config: > > https://gist.githubusercontent.com/dvyukov/36c7be311fdec9cd51c649f7c3cb2ddb/raw/39c6f864fdd0ffc53f0822b14c354a73c1695fa1/gistfile1.txt > > > I've tried this fix for pcpu_get_vm_areas: > https://groups.google.com/d/msg/kasan-dev/t_F2X1MWKwk/h152Z3q2AgAJ > and it helps. But this will break syzbot on linux-next soon. Can this be related as well? Crashes on accesses to shadow on the ion memory... BUG: unable to handle page fault for address: fffff52006000000 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 7ffcd067 P4D 7ffcd067 PUD 2cd10067 PMD 0 Oops: 0000 [#1] PREEMPT SMP KASAN CPU: 2 PID: 3472 Comm: ion_system_heap Not tainted 5.4.0-next-20191129+ #6 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.org 04/01/2014 RIP: 0010:memory_is_nonzero mm/kasan/generic.c:121 [inline] RIP: 0010:memory_is_poisoned_n mm/kasan/generic.c:135 [inline] RIP: 0010:memory_is_poisoned mm/kasan/generic.c:166 [inline] RIP: 0010:check_memory_region_inline mm/kasan/generic.c:182 [inline] RIP: 0010:check_memory_region+0x83/0x1d0 mm/kasan/generic.c:192 Code: 83 fb 10 0f 8e a9 00 00 00 45 89 c8 41 83 e0 07 75 66 4c 8d 43 07 48 85 db 4c 0f 49 c3 49 c1 f8 03 45 85 c0 0f 84 3f 01 00 00 <48> 83 38 00 75 1c 41 83 e8 01 4e 8d 44 c0 08 48 83 c0 08 49 39 c0 RSP: 0018:ffffc900011c7b10 EFLAGS: 00010206 RAX: fffff52006000000 RBX: 0000000000004000 RCX: ffffffff85988df8 RDX: 0000000000000001 RSI: 0000000000020000 RDI: ffffc90030000000 RBP: ffffc900011c7b28 R08: 0000000000000800 R09: fffff52006000000 R10: fffff52006003fff R11: ffffc9003001ffff R12: fffff52006004000 R13: 0000000000000000 R14: dffffc0000000000 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff88802d400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: fffff52006000000 CR3: 00000000680fb004 CR4: 0000000000760ee0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: memset+0x23/0x40 mm/kasan/common.c:107 memset include/linux/string.h:410 [inline] ion_heap_clear_pages+0x48/0x70 drivers/staging/android/ion/ion_heap.c:106 ion_heap_sglist_zero+0x1f9/0x260 drivers/staging/android/ion/ion_heap.c:123 ion_heap_buffer_zero+0xf8/0x150 drivers/staging/android/ion/ion_heap.c:145 ion_system_heap_free+0x227/0x290 drivers/staging/android/ion/ion_system_heap.c:163 ion_buffer_destroy+0x15a/0x2d0 drivers/staging/android/ion/ion.c:93 ion_heap_deferred_free+0x267/0x5e0 drivers/staging/android/ion/ion_heap.c:239 kthread+0x365/0x450 kernel/kthread.c:255 ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:352 Modules linked in: Dumping ftrace buffer: (ftrace buffer empty) CR2: fffff52006000000 ---[ end trace c101f19526ce3d42 ]--- RIP: 0010:memory_is_nonzero mm/kasan/generic.c:121 [inline] RIP: 0010:memory_is_poisoned_n mm/kasan/generic.c:135 [inline] RIP: 0010:memory_is_poisoned mm/kasan/generic.c:166 [inline] RIP: 0010:check_memory_region_inline mm/kasan/generic.c:182 [inline] RIP: 0010:check_memory_region+0x83/0x1d0 mm/kasan/generic.c:192 Code: 83 fb 10 0f 8e a9 00 00 00 45 89 c8 41 83 e0 07 75 66 4c 8d 43 07 48 85 db 4c 0f 49 c3 49 c1 f8 03 45 85 c0 0f 84 3f 01 00 00 <48> 83 38 00 75 1c 41 83 e8 01 4e 8d 44 c0 08 48 83 c0 08 49 39 c0 RSP: 0018:ffffc900011c7b10 EFLAGS: 00010206 RAX: fffff52006000000 RBX: 0000000000004000 RCX: ffffffff85988df8 RDX: 0000000000000001 RSI: 0000000000020000 RDI: ffffc90030000000 RBP: ffffc900011c7b28 R08: 0000000000000800 R09: fffff52006000000 R10: fffff52006003fff R11: ffffc9003001ffff R12: fffff52006004000 R13: 0000000000000000 R14: dffffc0000000000 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff88802d400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: fffff52006000000 CR3: 00000000680fb004 CR4: 0000000000760ee0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554
On 11/29/19 2:02 PM, Dmitry Vyukov wrote: > On Fri, Nov 29, 2019 at 11:58 AM Dmitry Vyukov <dvyukov@google.com> wrote: >> >> On Fri, Nov 29, 2019 at 11:43 AM Dmitry Vyukov <dvyukov@google.com> wrote: >>> >>> On Tue, Nov 19, 2019 at 10:54 AM Andrey Ryabinin >>> <aryabinin@virtuozzo.com> wrote: >>>> On 11/18/19 6:29 AM, Daniel Axtens wrote: >>>>> Qian Cai <cai@lca.pw> writes: >>>>> >>>>>> On Thu, 2019-10-31 at 20:39 +1100, Daniel Axtens wrote: >>>>>>> /* >>>>>>> * In this function, newly allocated vm_struct has VM_UNINITIALIZED >>>>>>> * flag. It means that vm_struct is not fully initialized. >>>>>>> @@ -3377,6 +3411,9 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, >>>>>>> >>>>>>> setup_vmalloc_vm_locked(vms[area], vas[area], VM_ALLOC, >>>>>>> pcpu_get_vm_areas); >>>>>>> + >>>>>>> + /* assume success here */ >>>>>>> + kasan_populate_vmalloc(sizes[area], vms[area]); >>>>>>> } >>>>>>> spin_unlock(&vmap_area_lock); >>>>>> >>>>>> Here it is all wrong. GFP_KERNEL with in_atomic(). >>>>> >>>>> I think this fix will work, I will do a v12 with it included. >>>> >>>> You can send just the fix. Andrew will fold it into the original patch before sending it to Linus. >>>> >>>> >>>> >>>>> diff --git a/mm/vmalloc.c b/mm/vmalloc.c >>>>> index a4b950a02d0b..bf030516258c 100644 >>>>> --- a/mm/vmalloc.c >>>>> +++ b/mm/vmalloc.c >>>>> @@ -3417,11 +3417,14 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, >>>>> >>>>> setup_vmalloc_vm_locked(vms[area], vas[area], VM_ALLOC, >>>>> pcpu_get_vm_areas); >>>>> + } >>>>> + spin_unlock(&vmap_area_lock); >>>>> >>>>> + /* populate the shadow space outside of the lock */ >>>>> + for (area = 0; area < nr_vms; area++) { >>>>> /* assume success here */ >>>>> kasan_populate_vmalloc(sizes[area], vms[area]); >>>>> } >>>>> - spin_unlock(&vmap_area_lock); >>>>> >>>>> kfree(vas); >>>>> return vms; >>> >>> Hi, >>> >>> I am testing this support on next-20191129 and seeing the following warnings: >>> >>> BUG: sleeping function called from invalid context at mm/page_alloc.c:4681 >>> in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 44, name: kworker/1:1 >>> 4 locks held by kworker/1:1/44: >>> #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: >>> __write_once_size include/linux/compiler.h:247 [inline] >>> #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: >>> arch_atomic64_set arch/x86/include/asm/atomic64_64.h:34 [inline] >>> #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: atomic64_set >>> include/asm-generic/atomic-instrumented.h:868 [inline] >>> #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: >>> atomic_long_set include/asm-generic/atomic-long.h:40 [inline] >>> #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: set_work_data >>> kernel/workqueue.c:615 [inline] >>> #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: >>> set_work_pool_and_clear_pending kernel/workqueue.c:642 [inline] >>> #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: >>> process_one_work+0x88b/0x1750 kernel/workqueue.c:2235 >>> #1: ffffc900002afdf0 (pcpu_balance_work){+.+.}, at: >>> process_one_work+0x8c0/0x1750 kernel/workqueue.c:2239 >>> #2: ffffffff8943f080 (pcpu_alloc_mutex){+.+.}, at: >>> pcpu_balance_workfn+0xcc/0x13e0 mm/percpu.c:1845 >>> #3: ffffffff89450c78 (vmap_area_lock){+.+.}, at: spin_lock >>> include/linux/spinlock.h:338 [inline] >>> #3: ffffffff89450c78 (vmap_area_lock){+.+.}, at: >>> pcpu_get_vm_areas+0x1449/0x3df0 mm/vmalloc.c:3431 >>> Preemption disabled at: >>> [<ffffffff81a84199>] spin_lock include/linux/spinlock.h:338 [inline] >>> [<ffffffff81a84199>] pcpu_get_vm_areas+0x1449/0x3df0 mm/vmalloc.c:3431 >>> CPU: 1 PID: 44 Comm: kworker/1:1 Not tainted 5.4.0-next-20191129+ #5 >>> Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.12.0-1 04/01/2014 >>> Workqueue: events pcpu_balance_workfn >>> Call Trace: >>> __dump_stack lib/dump_stack.c:77 [inline] >>> dump_stack+0x199/0x216 lib/dump_stack.c:118 >>> ___might_sleep.cold.97+0x1f5/0x238 kernel/sched/core.c:6800 >>> __might_sleep+0x95/0x190 kernel/sched/core.c:6753 >>> prepare_alloc_pages mm/page_alloc.c:4681 [inline] >>> __alloc_pages_nodemask+0x3cd/0x890 mm/page_alloc.c:4730 >>> alloc_pages_current+0x10c/0x210 mm/mempolicy.c:2211 >>> alloc_pages include/linux/gfp.h:532 [inline] >>> __get_free_pages+0xc/0x40 mm/page_alloc.c:4786 >>> kasan_populate_vmalloc_pte mm/kasan/common.c:762 [inline] >>> kasan_populate_vmalloc_pte+0x2f/0x1b0 mm/kasan/common.c:753 >>> apply_to_pte_range mm/memory.c:2041 [inline] >>> apply_to_pmd_range mm/memory.c:2068 [inline] >>> apply_to_pud_range mm/memory.c:2088 [inline] >>> apply_to_p4d_range mm/memory.c:2108 [inline] >>> apply_to_page_range+0x5ca/0xa00 mm/memory.c:2133 >>> kasan_populate_vmalloc+0x69/0xa0 mm/kasan/common.c:791 >>> pcpu_get_vm_areas+0x1596/0x3df0 mm/vmalloc.c:3439 >>> pcpu_create_chunk+0x240/0x7f0 mm/percpu-vm.c:340 >>> pcpu_balance_workfn+0x1033/0x13e0 mm/percpu.c:1934 >>> process_one_work+0x9b5/0x1750 kernel/workqueue.c:2264 >>> worker_thread+0x8b/0xd20 kernel/workqueue.c:2410 >>> kthread+0x365/0x450 kernel/kthread.c:255 >>> ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:352 >>> >>> >>> Not sure if it's the same or not. Is it addressed by something in flight? >>> >>> My config: >>> https://gist.githubusercontent.com/dvyukov/36c7be311fdec9cd51c649f7c3cb2ddb/raw/39c6f864fdd0ffc53f0822b14c354a73c1695fa1/gistfile1.txt >> >> >> I've tried this fix for pcpu_get_vm_areas: >> https://groups.google.com/d/msg/kasan-dev/t_F2X1MWKwk/h152Z3q2AgAJ >> and it helps. But this will break syzbot on linux-next soon. > > > Can this be related as well? > Crashes on accesses to shadow on the ion memory... Nope, it's vm_map_ram() not being handled
On Fri, Nov 29, 2019 at 12:38 PM Andrey Ryabinin <aryabinin@virtuozzo.com> wrote: > >>> > >>> > >>> Not sure if it's the same or not. Is it addressed by something in flight? > >>> > >>> My config: > >>> https://gist.githubusercontent.com/dvyukov/36c7be311fdec9cd51c649f7c3cb2ddb/raw/39c6f864fdd0ffc53f0822b14c354a73c1695fa1/gistfile1.txt > >> > >> > >> I've tried this fix for pcpu_get_vm_areas: > >> https://groups.google.com/d/msg/kasan-dev/t_F2X1MWKwk/h152Z3q2AgAJ > >> and it helps. But this will break syzbot on linux-next soon. > > > > > > Can this be related as well? > > Crashes on accesses to shadow on the ion memory... > > Nope, it's vm_map_ram() not being handled Another suspicious one. Related to kasan/vmalloc? BUG: unable to handle page fault for address: fffff52005b80000 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 7ffcd067 P4D 7ffcd067 PUD 2cd10067 PMD 66d76067 PTE 0 Oops: 0000 [#1] PREEMPT SMP KASAN CPU: 2 PID: 9211 Comm: syz-executor.2 Not tainted 5.4.0-next-20191129+ #6 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.org 04/01/2014 RIP: 0010:xfs_sb_read_verify+0xe9/0x540 fs/xfs/libxfs/xfs_sb.c:691 Code: fc ff df 48 c1 ea 03 80 3c 02 00 0f 85 1e 04 00 00 4d 8b ac 24 30 01 00 00 48 b8 00 00 00 00 00 fc ff df 4c 89 ea 48 c1 ea 03 <0f> b6 04 02 84 c0 74 08 3c 03 0f 8e ad 03 00 00 41 8b 45 00 bf 58 RSP: 0018:ffffc9000a58f8d0 EFLAGS: 00010a06 RAX: dffffc0000000000 RBX: 1ffff920014b1f1d RCX: ffffc9000af42000 RDX: 1ffff92005b80000 RSI: ffffffff82914404 RDI: ffff88805cdb1460 RBP: ffffc9000a58fab0 R08: ffff8880610cd380 R09: ffffed1005a87045 R10: ffffed1005a87044 R11: ffff88802d438223 R12: ffff88805cdb1340 R13: ffffc9002dc00000 R14: ffffc9000a58fa88 R15: ffff888061b5c000 FS: 00007fb49bda9700(0000) GS:ffff88802d400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: fffff52005b80000 CR3: 0000000060769006 CR4: 0000000000760ee0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: xfs_buf_ioend+0x228/0xdc0 fs/xfs/xfs_buf.c:1162 __xfs_buf_submit+0x38b/0xe50 fs/xfs/xfs_buf.c:1485 xfs_buf_submit fs/xfs/xfs_buf.h:268 [inline] xfs_buf_read_uncached+0x15c/0x560 fs/xfs/xfs_buf.c:897 xfs_readsb+0x2d0/0x540 fs/xfs/xfs_mount.c:298 xfs_fc_fill_super+0x3e6/0x11f0 fs/xfs/xfs_super.c:1415 get_tree_bdev+0x444/0x620 fs/super.c:1340 xfs_fc_get_tree+0x1c/0x20 fs/xfs/xfs_super.c:1550 vfs_get_tree+0x8e/0x300 fs/super.c:1545 do_new_mount fs/namespace.c:2822 [inline] do_mount+0x152d/0x1b50 fs/namespace.c:3142 ksys_mount+0x114/0x130 fs/namespace.c:3351 __do_sys_mount fs/namespace.c:3365 [inline] __se_sys_mount fs/namespace.c:3362 [inline] __x64_sys_mount+0xbe/0x150 fs/namespace.c:3362 do_syscall_64+0xfa/0x780 arch/x86/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x46736a Code: 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007fb49bda8a78 EFLAGS: 00000202 ORIG_RAX: 00000000000000a5 RAX: ffffffffffffffda RBX: 00007fb49bda8af0 RCX: 000000000046736a RDX: 00007fb49bda8ad0 RSI: 0000000020000140 RDI: 00007fb49bda8af0 RBP: 00007fb49bda8ad0 R08: 00007fb49bda8b30 R09: 00007fb49bda8ad0 R10: 0000000000000000 R11: 0000000000000202 R12: 00007fb49bda8b30 R13: 00000000004b1c60 R14: 00000000004b006d R15: 00007fb49bda96bc Modules linked in: Dumping ftrace buffer: (ftrace buffer empty) CR2: fffff52005b80000 ---[ end trace eddd8949d4c898df ]--- RIP: 0010:xfs_sb_read_verify+0xe9/0x540 fs/xfs/libxfs/xfs_sb.c:691 Code: fc ff df 48 c1 ea 03 80 3c 02 00 0f 85 1e 04 00 00 4d 8b ac 24 30 01 00 00 48 b8 00 00 00 00 00 fc ff df 4c 89 ea 48 c1 ea 03 <0f> b6 04 02 84 c0 74 08 3c 03 0f 8e ad 03 00 00 41 8b 45 00 bf 58 RSP: 0018:ffffc9000a58f8d0 EFLAGS: 00010a06 RAX: dffffc0000000000 RBX: 1ffff920014b1f1d RCX: ffffc9000af42000 RDX: 1ffff92005b80000 RSI: ffffffff82914404 RDI: ffff88805cdb1460 RBP: ffffc9000a58fab0 R08: ffff8880610cd380 R09: ffffed1005a87045 R10: ffffed1005a87044 R11: ffff88802d438223 R12: ffff88805cdb1340 R13: ffffc9002dc00000 R14: ffffc9000a58fa88 R15: ffff888061b5c000 FS: 00007fb49bda9700(0000) GS:ffff88802d400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: fffff52005b80000 CR3: 0000000060769006 CR4: 0000000000760ee0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554
On 11/29/19 2:47 PM, Dmitry Vyukov wrote: > On Fri, Nov 29, 2019 at 12:38 PM Andrey Ryabinin > <aryabinin@virtuozzo.com> wrote: >>>>> >>>>> >>>>> Not sure if it's the same or not. Is it addressed by something in flight? >>>>> >>>>> My config: >>>>> https://gist.githubusercontent.com/dvyukov/36c7be311fdec9cd51c649f7c3cb2ddb/raw/39c6f864fdd0ffc53f0822b14c354a73c1695fa1/gistfile1.txt >>>> >>>> >>>> I've tried this fix for pcpu_get_vm_areas: >>>> https://groups.google.com/d/msg/kasan-dev/t_F2X1MWKwk/h152Z3q2AgAJ >>>> and it helps. But this will break syzbot on linux-next soon. >>> >>> >>> Can this be related as well? >>> Crashes on accesses to shadow on the ion memory... >> >> Nope, it's vm_map_ram() not being handled > > > Another suspicious one. Related to kasan/vmalloc? Very likely the same as with ion: # git grep vm_map_ram|grep xfs fs/xfs/xfs_buf.c: * vm_map_ram() will allocate auxiliary structures (e.g. fs/xfs/xfs_buf.c: bp->b_addr = vm_map_ram(bp->b_pages, bp->b_page_count, > > BUG: unable to handle page fault for address: fffff52005b80000 > #PF: supervisor read access in kernel mode > #PF: error_code(0x0000) - not-present page > PGD 7ffcd067 P4D 7ffcd067 PUD 2cd10067 PMD 66d76067 PTE 0 > Oops: 0000 [#1] PREEMPT SMP KASAN > CPU: 2 PID: 9211 Comm: syz-executor.2 Not tainted 5.4.0-next-20191129+ #6 > Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS > rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.org 04/01/2014 > RIP: 0010:xfs_sb_read_verify+0xe9/0x540 fs/xfs/libxfs/xfs_sb.c:691 > Code: fc ff df 48 c1 ea 03 80 3c 02 00 0f 85 1e 04 00 00 4d 8b ac 24 > 30 01 00 00 48 b8 00 00 00 00 00 fc ff df 4c 89 ea 48 c1 ea 03 <0f> b6 > 04 02 84 c0 74 08 3c 03 0f 8e ad 03 00 00 41 8b 45 00 bf 58 > RSP: 0018:ffffc9000a58f8d0 EFLAGS: 00010a06 > RAX: dffffc0000000000 RBX: 1ffff920014b1f1d RCX: ffffc9000af42000 > RDX: 1ffff92005b80000 RSI: ffffffff82914404 RDI: ffff88805cdb1460 > RBP: ffffc9000a58fab0 R08: ffff8880610cd380 R09: ffffed1005a87045 > R10: ffffed1005a87044 R11: ffff88802d438223 R12: ffff88805cdb1340 > R13: ffffc9002dc00000 R14: ffffc9000a58fa88 R15: ffff888061b5c000 > FS: 00007fb49bda9700(0000) GS:ffff88802d400000(0000) knlGS:0000000000000000 > CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 > CR2: fffff52005b80000 CR3: 0000000060769006 CR4: 0000000000760ee0 > DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 > DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 > PKRU: 55555554 > Call Trace: > xfs_buf_ioend+0x228/0xdc0 fs/xfs/xfs_buf.c:1162 > __xfs_buf_submit+0x38b/0xe50 fs/xfs/xfs_buf.c:1485 > xfs_buf_submit fs/xfs/xfs_buf.h:268 [inline] > xfs_buf_read_uncached+0x15c/0x560 fs/xfs/xfs_buf.c:897 > xfs_readsb+0x2d0/0x540 fs/xfs/xfs_mount.c:298 > xfs_fc_fill_super+0x3e6/0x11f0 fs/xfs/xfs_super.c:1415 > get_tree_bdev+0x444/0x620 fs/super.c:1340 > xfs_fc_get_tree+0x1c/0x20 fs/xfs/xfs_super.c:1550 > vfs_get_tree+0x8e/0x300 fs/super.c:1545 > do_new_mount fs/namespace.c:2822 [inline] > do_mount+0x152d/0x1b50 fs/namespace.c:3142 > ksys_mount+0x114/0x130 fs/namespace.c:3351 > __do_sys_mount fs/namespace.c:3365 [inline] > __se_sys_mount fs/namespace.c:3362 [inline] > __x64_sys_mount+0xbe/0x150 fs/namespace.c:3362 > do_syscall_64+0xfa/0x780 arch/x86/entry/common.c:294 > entry_SYSCALL_64_after_hwframe+0x49/0xbe > RIP: 0033:0x46736a > Code: 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f > 84 00 00 00 00 00 0f 1f 44 00 00 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d > 01 f0 ff ff 73 01 c3 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48 > RSP: 002b:00007fb49bda8a78 EFLAGS: 00000202 ORIG_RAX: 00000000000000a5 > RAX: ffffffffffffffda RBX: 00007fb49bda8af0 RCX: 000000000046736a > RDX: 00007fb49bda8ad0 RSI: 0000000020000140 RDI: 00007fb49bda8af0 > RBP: 00007fb49bda8ad0 R08: 00007fb49bda8b30 R09: 00007fb49bda8ad0 > R10: 0000000000000000 R11: 0000000000000202 R12: 00007fb49bda8b30 > R13: 00000000004b1c60 R14: 00000000004b006d R15: 00007fb49bda96bc > Modules linked in: > Dumping ftrace buffer: > (ftrace buffer empty) > CR2: fffff52005b80000 > ---[ end trace eddd8949d4c898df ]--- > RIP: 0010:xfs_sb_read_verify+0xe9/0x540 fs/xfs/libxfs/xfs_sb.c:691 > Code: fc ff df 48 c1 ea 03 80 3c 02 00 0f 85 1e 04 00 00 4d 8b ac 24 > 30 01 00 00 48 b8 00 00 00 00 00 fc ff df 4c 89 ea 48 c1 ea 03 <0f> b6 > 04 02 84 c0 74 08 3c 03 0f 8e ad 03 00 00 41 8b 45 00 bf 58 > RSP: 0018:ffffc9000a58f8d0 EFLAGS: 00010a06 > RAX: dffffc0000000000 RBX: 1ffff920014b1f1d RCX: ffffc9000af42000 > RDX: 1ffff92005b80000 RSI: ffffffff82914404 RDI: ffff88805cdb1460 > RBP: ffffc9000a58fab0 R08: ffff8880610cd380 R09: ffffed1005a87045 > R10: ffffed1005a87044 R11: ffff88802d438223 R12: ffff88805cdb1340 > R13: ffffc9002dc00000 R14: ffffc9000a58fa88 R15: ffff888061b5c000 > FS: 00007fb49bda9700(0000) GS:ffff88802d400000(0000) knlGS:0000000000000000 > CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 > CR2: fffff52005b80000 CR3: 0000000060769006 CR4: 0000000000760ee0 > DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 > DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 > PKRU: 55555554 >
Hi Dmitry, >> I am testing this support on next-20191129 and seeing the following warnings: >> >> BUG: sleeping function called from invalid context at mm/page_alloc.c:4681 >> in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 44, name: kworker/1:1 >> 4 locks held by kworker/1:1/44: >> #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: >> __write_once_size include/linux/compiler.h:247 [inline] >> #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: >> arch_atomic64_set arch/x86/include/asm/atomic64_64.h:34 [inline] >> #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: atomic64_set >> include/asm-generic/atomic-instrumented.h:868 [inline] >> #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: >> atomic_long_set include/asm-generic/atomic-long.h:40 [inline] >> #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: set_work_data >> kernel/workqueue.c:615 [inline] >> #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: >> set_work_pool_and_clear_pending kernel/workqueue.c:642 [inline] >> #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: >> process_one_work+0x88b/0x1750 kernel/workqueue.c:2235 >> #1: ffffc900002afdf0 (pcpu_balance_work){+.+.}, at: >> process_one_work+0x8c0/0x1750 kernel/workqueue.c:2239 >> #2: ffffffff8943f080 (pcpu_alloc_mutex){+.+.}, at: >> pcpu_balance_workfn+0xcc/0x13e0 mm/percpu.c:1845 >> #3: ffffffff89450c78 (vmap_area_lock){+.+.}, at: spin_lock >> include/linux/spinlock.h:338 [inline] >> #3: ffffffff89450c78 (vmap_area_lock){+.+.}, at: >> pcpu_get_vm_areas+0x1449/0x3df0 mm/vmalloc.c:3431 >> Preemption disabled at: >> [<ffffffff81a84199>] spin_lock include/linux/spinlock.h:338 [inline] >> [<ffffffff81a84199>] pcpu_get_vm_areas+0x1449/0x3df0 mm/vmalloc.c:3431 >> CPU: 1 PID: 44 Comm: kworker/1:1 Not tainted 5.4.0-next-20191129+ #5 >> Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.12.0-1 04/01/2014 >> Workqueue: events pcpu_balance_workfn >> Call Trace: >> __dump_stack lib/dump_stack.c:77 [inline] >> dump_stack+0x199/0x216 lib/dump_stack.c:118 >> ___might_sleep.cold.97+0x1f5/0x238 kernel/sched/core.c:6800 >> __might_sleep+0x95/0x190 kernel/sched/core.c:6753 >> prepare_alloc_pages mm/page_alloc.c:4681 [inline] >> __alloc_pages_nodemask+0x3cd/0x890 mm/page_alloc.c:4730 >> alloc_pages_current+0x10c/0x210 mm/mempolicy.c:2211 >> alloc_pages include/linux/gfp.h:532 [inline] >> __get_free_pages+0xc/0x40 mm/page_alloc.c:4786 >> kasan_populate_vmalloc_pte mm/kasan/common.c:762 [inline] >> kasan_populate_vmalloc_pte+0x2f/0x1b0 mm/kasan/common.c:753 >> apply_to_pte_range mm/memory.c:2041 [inline] >> apply_to_pmd_range mm/memory.c:2068 [inline] >> apply_to_pud_range mm/memory.c:2088 [inline] >> apply_to_p4d_range mm/memory.c:2108 [inline] >> apply_to_page_range+0x5ca/0xa00 mm/memory.c:2133 >> kasan_populate_vmalloc+0x69/0xa0 mm/kasan/common.c:791 >> pcpu_get_vm_areas+0x1596/0x3df0 mm/vmalloc.c:3439 >> pcpu_create_chunk+0x240/0x7f0 mm/percpu-vm.c:340 >> pcpu_balance_workfn+0x1033/0x13e0 mm/percpu.c:1934 >> process_one_work+0x9b5/0x1750 kernel/workqueue.c:2264 >> worker_thread+0x8b/0xd20 kernel/workqueue.c:2410 >> kthread+0x365/0x450 kernel/kthread.c:255 >> ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:352 >> >> >> Not sure if it's the same or not. Is it addressed by something in flight? It looks like this one is the same. There is a patch to fix it: https://lore.kernel.org/linux-mm/20191120052719.7201-1-dja@axtens.net/ Andrew said he had picked it up on the 22nd: https://marc.info/?l=linux-mm-commits&m=157438241512561&w=2 It's landed in mmots but not mmotm, so hopefully that will happen and then it will land in -next very soon! I will look into your other bug report shortly. Regards, Daniel >> >> My config: >> https://gist.githubusercontent.com/dvyukov/36c7be311fdec9cd51c649f7c3cb2ddb/raw/39c6f864fdd0ffc53f0822b14c354a73c1695fa1/gistfile1.txt > > > I've tried this fix for pcpu_get_vm_areas: > https://groups.google.com/d/msg/kasan-dev/t_F2X1MWKwk/h152Z3q2AgAJ > and it helps. But this will break syzbot on linux-next soon.
On Fri, Nov 29, 2019 at 1:09 PM Daniel Axtens <dja@axtens.net> wrote: > > Hi Dmitry, > > >> I am testing this support on next-20191129 and seeing the following warnings: > >> > >> BUG: sleeping function called from invalid context at mm/page_alloc.c:4681 > >> in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 44, name: kworker/1:1 > >> 4 locks held by kworker/1:1/44: > >> #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: > >> __write_once_size include/linux/compiler.h:247 [inline] > >> #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: > >> arch_atomic64_set arch/x86/include/asm/atomic64_64.h:34 [inline] > >> #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: atomic64_set > >> include/asm-generic/atomic-instrumented.h:868 [inline] > >> #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: > >> atomic_long_set include/asm-generic/atomic-long.h:40 [inline] > >> #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: set_work_data > >> kernel/workqueue.c:615 [inline] > >> #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: > >> set_work_pool_and_clear_pending kernel/workqueue.c:642 [inline] > >> #0: ffff888067c26d28 ((wq_completion)events){+.+.}, at: > >> process_one_work+0x88b/0x1750 kernel/workqueue.c:2235 > >> #1: ffffc900002afdf0 (pcpu_balance_work){+.+.}, at: > >> process_one_work+0x8c0/0x1750 kernel/workqueue.c:2239 > >> #2: ffffffff8943f080 (pcpu_alloc_mutex){+.+.}, at: > >> pcpu_balance_workfn+0xcc/0x13e0 mm/percpu.c:1845 > >> #3: ffffffff89450c78 (vmap_area_lock){+.+.}, at: spin_lock > >> include/linux/spinlock.h:338 [inline] > >> #3: ffffffff89450c78 (vmap_area_lock){+.+.}, at: > >> pcpu_get_vm_areas+0x1449/0x3df0 mm/vmalloc.c:3431 > >> Preemption disabled at: > >> [<ffffffff81a84199>] spin_lock include/linux/spinlock.h:338 [inline] > >> [<ffffffff81a84199>] pcpu_get_vm_areas+0x1449/0x3df0 mm/vmalloc.c:3431 > >> CPU: 1 PID: 44 Comm: kworker/1:1 Not tainted 5.4.0-next-20191129+ #5 > >> Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.12.0-1 04/01/2014 > >> Workqueue: events pcpu_balance_workfn > >> Call Trace: > >> __dump_stack lib/dump_stack.c:77 [inline] > >> dump_stack+0x199/0x216 lib/dump_stack.c:118 > >> ___might_sleep.cold.97+0x1f5/0x238 kernel/sched/core.c:6800 > >> __might_sleep+0x95/0x190 kernel/sched/core.c:6753 > >> prepare_alloc_pages mm/page_alloc.c:4681 [inline] > >> __alloc_pages_nodemask+0x3cd/0x890 mm/page_alloc.c:4730 > >> alloc_pages_current+0x10c/0x210 mm/mempolicy.c:2211 > >> alloc_pages include/linux/gfp.h:532 [inline] > >> __get_free_pages+0xc/0x40 mm/page_alloc.c:4786 > >> kasan_populate_vmalloc_pte mm/kasan/common.c:762 [inline] > >> kasan_populate_vmalloc_pte+0x2f/0x1b0 mm/kasan/common.c:753 > >> apply_to_pte_range mm/memory.c:2041 [inline] > >> apply_to_pmd_range mm/memory.c:2068 [inline] > >> apply_to_pud_range mm/memory.c:2088 [inline] > >> apply_to_p4d_range mm/memory.c:2108 [inline] > >> apply_to_page_range+0x5ca/0xa00 mm/memory.c:2133 > >> kasan_populate_vmalloc+0x69/0xa0 mm/kasan/common.c:791 > >> pcpu_get_vm_areas+0x1596/0x3df0 mm/vmalloc.c:3439 > >> pcpu_create_chunk+0x240/0x7f0 mm/percpu-vm.c:340 > >> pcpu_balance_workfn+0x1033/0x13e0 mm/percpu.c:1934 > >> process_one_work+0x9b5/0x1750 kernel/workqueue.c:2264 > >> worker_thread+0x8b/0xd20 kernel/workqueue.c:2410 > >> kthread+0x365/0x450 kernel/kthread.c:255 > >> ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:352 > >> > >> > >> Not sure if it's the same or not. Is it addressed by something in flight? > > It looks like this one is the same. > > There is a patch to fix it: > https://lore.kernel.org/linux-mm/20191120052719.7201-1-dja@axtens.net/ > > Andrew said he had picked it up on the 22nd: > https://marc.info/?l=linux-mm-commits&m=157438241512561&w=2 > It's landed in mmots but not mmotm, so hopefully that will happen and > then it will land in -next very soon! > > I will look into your other bug report shortly. Thanks for the quick responses, Andrey, Daniel. > Regards, > Daniel > > >> > >> My config: > >> https://gist.githubusercontent.com/dvyukov/36c7be311fdec9cd51c649f7c3cb2ddb/raw/39c6f864fdd0ffc53f0822b14c354a73c1695fa1/gistfile1.txt > > > > > > I've tried this fix for pcpu_get_vm_areas: > > https://groups.google.com/d/msg/kasan-dev/t_F2X1MWKwk/h152Z3q2AgAJ > > and it helps. But this will break syzbot on linux-next soon.
>>> Nope, it's vm_map_ram() not being handled >> >> >> Another suspicious one. Related to kasan/vmalloc? > > Very likely the same as with ion: > > # git grep vm_map_ram|grep xfs > fs/xfs/xfs_buf.c: * vm_map_ram() will allocate auxiliary structures (e.g. > fs/xfs/xfs_buf.c: bp->b_addr = vm_map_ram(bp->b_pages, bp->b_page_count, Aaargh, that's an embarassing miss. It's a bit intricate because kasan_vmalloc_populate function is currently set up to take a vm_struct not a vmap_area, but I'll see if I can get something simple out this evening - I'm away for the first part of next week. Do you have to do anything interesting to get it to explode with xfs? Is it as simple as mounting a drive and doing some I/O? Or do you need to do something more involved? Regards, Daniel > >> >> BUG: unable to handle page fault for address: fffff52005b80000 >> #PF: supervisor read access in kernel mode >> #PF: error_code(0x0000) - not-present page >> PGD 7ffcd067 P4D 7ffcd067 PUD 2cd10067 PMD 66d76067 PTE 0 >> Oops: 0000 [#1] PREEMPT SMP KASAN >> CPU: 2 PID: 9211 Comm: syz-executor.2 Not tainted 5.4.0-next-20191129+ #6 >> Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS >> rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.org 04/01/2014 >> RIP: 0010:xfs_sb_read_verify+0xe9/0x540 fs/xfs/libxfs/xfs_sb.c:691 >> Code: fc ff df 48 c1 ea 03 80 3c 02 00 0f 85 1e 04 00 00 4d 8b ac 24 >> 30 01 00 00 48 b8 00 00 00 00 00 fc ff df 4c 89 ea 48 c1 ea 03 <0f> b6 >> 04 02 84 c0 74 08 3c 03 0f 8e ad 03 00 00 41 8b 45 00 bf 58 >> RSP: 0018:ffffc9000a58f8d0 EFLAGS: 00010a06 >> RAX: dffffc0000000000 RBX: 1ffff920014b1f1d RCX: ffffc9000af42000 >> RDX: 1ffff92005b80000 RSI: ffffffff82914404 RDI: ffff88805cdb1460 >> RBP: ffffc9000a58fab0 R08: ffff8880610cd380 R09: ffffed1005a87045 >> R10: ffffed1005a87044 R11: ffff88802d438223 R12: ffff88805cdb1340 >> R13: ffffc9002dc00000 R14: ffffc9000a58fa88 R15: ffff888061b5c000 >> FS: 00007fb49bda9700(0000) GS:ffff88802d400000(0000) knlGS:0000000000000000 >> CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 >> CR2: fffff52005b80000 CR3: 0000000060769006 CR4: 0000000000760ee0 >> DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 >> DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 >> PKRU: 55555554 >> Call Trace: >> xfs_buf_ioend+0x228/0xdc0 fs/xfs/xfs_buf.c:1162 >> __xfs_buf_submit+0x38b/0xe50 fs/xfs/xfs_buf.c:1485 >> xfs_buf_submit fs/xfs/xfs_buf.h:268 [inline] >> xfs_buf_read_uncached+0x15c/0x560 fs/xfs/xfs_buf.c:897 >> xfs_readsb+0x2d0/0x540 fs/xfs/xfs_mount.c:298 >> xfs_fc_fill_super+0x3e6/0x11f0 fs/xfs/xfs_super.c:1415 >> get_tree_bdev+0x444/0x620 fs/super.c:1340 >> xfs_fc_get_tree+0x1c/0x20 fs/xfs/xfs_super.c:1550 >> vfs_get_tree+0x8e/0x300 fs/super.c:1545 >> do_new_mount fs/namespace.c:2822 [inline] >> do_mount+0x152d/0x1b50 fs/namespace.c:3142 >> ksys_mount+0x114/0x130 fs/namespace.c:3351 >> __do_sys_mount fs/namespace.c:3365 [inline] >> __se_sys_mount fs/namespace.c:3362 [inline] >> __x64_sys_mount+0xbe/0x150 fs/namespace.c:3362 >> do_syscall_64+0xfa/0x780 arch/x86/entry/common.c:294 >> entry_SYSCALL_64_after_hwframe+0x49/0xbe >> RIP: 0033:0x46736a >> Code: 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f >> 84 00 00 00 00 00 0f 1f 44 00 00 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d >> 01 f0 ff ff 73 01 c3 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48 >> RSP: 002b:00007fb49bda8a78 EFLAGS: 00000202 ORIG_RAX: 00000000000000a5 >> RAX: ffffffffffffffda RBX: 00007fb49bda8af0 RCX: 000000000046736a >> RDX: 00007fb49bda8ad0 RSI: 0000000020000140 RDI: 00007fb49bda8af0 >> RBP: 00007fb49bda8ad0 R08: 00007fb49bda8b30 R09: 00007fb49bda8ad0 >> R10: 0000000000000000 R11: 0000000000000202 R12: 00007fb49bda8b30 >> R13: 00000000004b1c60 R14: 00000000004b006d R15: 00007fb49bda96bc >> Modules linked in: >> Dumping ftrace buffer: >> (ftrace buffer empty) >> CR2: fffff52005b80000 >> ---[ end trace eddd8949d4c898df ]--- >> RIP: 0010:xfs_sb_read_verify+0xe9/0x540 fs/xfs/libxfs/xfs_sb.c:691 >> Code: fc ff df 48 c1 ea 03 80 3c 02 00 0f 85 1e 04 00 00 4d 8b ac 24 >> 30 01 00 00 48 b8 00 00 00 00 00 fc ff df 4c 89 ea 48 c1 ea 03 <0f> b6 >> 04 02 84 c0 74 08 3c 03 0f 8e ad 03 00 00 41 8b 45 00 bf 58 >> RSP: 0018:ffffc9000a58f8d0 EFLAGS: 00010a06 >> RAX: dffffc0000000000 RBX: 1ffff920014b1f1d RCX: ffffc9000af42000 >> RDX: 1ffff92005b80000 RSI: ffffffff82914404 RDI: ffff88805cdb1460 >> RBP: ffffc9000a58fab0 R08: ffff8880610cd380 R09: ffffed1005a87045 >> R10: ffffed1005a87044 R11: ffff88802d438223 R12: ffff88805cdb1340 >> R13: ffffc9002dc00000 R14: ffffc9000a58fa88 R15: ffff888061b5c000 >> FS: 00007fb49bda9700(0000) GS:ffff88802d400000(0000) knlGS:0000000000000000 >> CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 >> CR2: fffff52005b80000 CR3: 0000000060769006 CR4: 0000000000760ee0 >> DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 >> DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 >> PKRU: 55555554 >> > > -- > You received this message because you are subscribed to the Google Groups "kasan-dev" group. > To unsubscribe from this group and stop receiving emails from it, send an email to kasan-dev+unsubscribe@googlegroups.com. > To view this discussion on the web visit https://groups.google.com/d/msgid/kasan-dev/56cf8aab-c61b-156c-f681-d2354aed22bb%40virtuozzo.com.
On Fri, Nov 29, 2019 at 1:29 PM Daniel Axtens <dja@axtens.net> wrote: > >>> Nope, it's vm_map_ram() not being handled > >> Another suspicious one. Related to kasan/vmalloc? > > Very likely the same as with ion: > > > > # git grep vm_map_ram|grep xfs > > fs/xfs/xfs_buf.c: * vm_map_ram() will allocate auxiliary structures (e.g. > > fs/xfs/xfs_buf.c: bp->b_addr = vm_map_ram(bp->b_pages, bp->b_page_count, > > Aaargh, that's an embarassing miss. > > It's a bit intricate because kasan_vmalloc_populate function is > currently set up to take a vm_struct not a vmap_area, but I'll see if I > can get something simple out this evening - I'm away for the first part > of next week. > > Do you have to do anything interesting to get it to explode with xfs? Is > it as simple as mounting a drive and doing some I/O? Or do you need to > do something more involved? As simple as running syzkaller :) with this config https://github.com/google/syzkaller/blob/master/dashboard/config/upstream-kasan.config > Regards, > Daniel > > > > >> > >> BUG: unable to handle page fault for address: fffff52005b80000 > >> #PF: supervisor read access in kernel mode > >> #PF: error_code(0x0000) - not-present page > >> PGD 7ffcd067 P4D 7ffcd067 PUD 2cd10067 PMD 66d76067 PTE 0 > >> Oops: 0000 [#1] PREEMPT SMP KASAN > >> CPU: 2 PID: 9211 Comm: syz-executor.2 Not tainted 5.4.0-next-20191129+ #6 > >> Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS > >> rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.org 04/01/2014 > >> RIP: 0010:xfs_sb_read_verify+0xe9/0x540 fs/xfs/libxfs/xfs_sb.c:691 > >> Code: fc ff df 48 c1 ea 03 80 3c 02 00 0f 85 1e 04 00 00 4d 8b ac 24 > >> 30 01 00 00 48 b8 00 00 00 00 00 fc ff df 4c 89 ea 48 c1 ea 03 <0f> b6 > >> 04 02 84 c0 74 08 3c 03 0f 8e ad 03 00 00 41 8b 45 00 bf 58 > >> RSP: 0018:ffffc9000a58f8d0 EFLAGS: 00010a06 > >> RAX: dffffc0000000000 RBX: 1ffff920014b1f1d RCX: ffffc9000af42000 > >> RDX: 1ffff92005b80000 RSI: ffffffff82914404 RDI: ffff88805cdb1460 > >> RBP: ffffc9000a58fab0 R08: ffff8880610cd380 R09: ffffed1005a87045 > >> R10: ffffed1005a87044 R11: ffff88802d438223 R12: ffff88805cdb1340 > >> R13: ffffc9002dc00000 R14: ffffc9000a58fa88 R15: ffff888061b5c000 > >> FS: 00007fb49bda9700(0000) GS:ffff88802d400000(0000) knlGS:0000000000000000 > >> CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 > >> CR2: fffff52005b80000 CR3: 0000000060769006 CR4: 0000000000760ee0 > >> DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 > >> DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 > >> PKRU: 55555554 > >> Call Trace: > >> xfs_buf_ioend+0x228/0xdc0 fs/xfs/xfs_buf.c:1162 > >> __xfs_buf_submit+0x38b/0xe50 fs/xfs/xfs_buf.c:1485 > >> xfs_buf_submit fs/xfs/xfs_buf.h:268 [inline] > >> xfs_buf_read_uncached+0x15c/0x560 fs/xfs/xfs_buf.c:897 > >> xfs_readsb+0x2d0/0x540 fs/xfs/xfs_mount.c:298 > >> xfs_fc_fill_super+0x3e6/0x11f0 fs/xfs/xfs_super.c:1415 > >> get_tree_bdev+0x444/0x620 fs/super.c:1340 > >> xfs_fc_get_tree+0x1c/0x20 fs/xfs/xfs_super.c:1550 > >> vfs_get_tree+0x8e/0x300 fs/super.c:1545 > >> do_new_mount fs/namespace.c:2822 [inline] > >> do_mount+0x152d/0x1b50 fs/namespace.c:3142 > >> ksys_mount+0x114/0x130 fs/namespace.c:3351 > >> __do_sys_mount fs/namespace.c:3365 [inline] > >> __se_sys_mount fs/namespace.c:3362 [inline] > >> __x64_sys_mount+0xbe/0x150 fs/namespace.c:3362 > >> do_syscall_64+0xfa/0x780 arch/x86/entry/common.c:294 > >> entry_SYSCALL_64_after_hwframe+0x49/0xbe > >> RIP: 0033:0x46736a > >> Code: 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f > >> 84 00 00 00 00 00 0f 1f 44 00 00 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d > >> 01 f0 ff ff 73 01 c3 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48 > >> RSP: 002b:00007fb49bda8a78 EFLAGS: 00000202 ORIG_RAX: 00000000000000a5 > >> RAX: ffffffffffffffda RBX: 00007fb49bda8af0 RCX: 000000000046736a > >> RDX: 00007fb49bda8ad0 RSI: 0000000020000140 RDI: 00007fb49bda8af0 > >> RBP: 00007fb49bda8ad0 R08: 00007fb49bda8b30 R09: 00007fb49bda8ad0 > >> R10: 0000000000000000 R11: 0000000000000202 R12: 00007fb49bda8b30 > >> R13: 00000000004b1c60 R14: 00000000004b006d R15: 00007fb49bda96bc > >> Modules linked in: > >> Dumping ftrace buffer: > >> (ftrace buffer empty) > >> CR2: fffff52005b80000 > >> ---[ end trace eddd8949d4c898df ]--- > >> RIP: 0010:xfs_sb_read_verify+0xe9/0x540 fs/xfs/libxfs/xfs_sb.c:691 > >> Code: fc ff df 48 c1 ea 03 80 3c 02 00 0f 85 1e 04 00 00 4d 8b ac 24 > >> 30 01 00 00 48 b8 00 00 00 00 00 fc ff df 4c 89 ea 48 c1 ea 03 <0f> b6 > >> 04 02 84 c0 74 08 3c 03 0f 8e ad 03 00 00 41 8b 45 00 bf 58 > >> RSP: 0018:ffffc9000a58f8d0 EFLAGS: 00010a06 > >> RAX: dffffc0000000000 RBX: 1ffff920014b1f1d RCX: ffffc9000af42000 > >> RDX: 1ffff92005b80000 RSI: ffffffff82914404 RDI: ffff88805cdb1460 > >> RBP: ffffc9000a58fab0 R08: ffff8880610cd380 R09: ffffed1005a87045 > >> R10: ffffed1005a87044 R11: ffff88802d438223 R12: ffff88805cdb1340 > >> R13: ffffc9002dc00000 R14: ffffc9000a58fa88 R15: ffff888061b5c000 > >> FS: 00007fb49bda9700(0000) GS:ffff88802d400000(0000) knlGS:0000000000000000 > >> CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 > >> CR2: fffff52005b80000 CR3: 0000000060769006 CR4: 0000000000760ee0 > >> DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 > >> DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 > >> PKRU: 55555554 > >> > > > > -- > > You received this message because you are subscribed to the Google Groups "kasan-dev" group. > > To unsubscribe from this group and stop receiving emails from it, send an email to kasan-dev+unsubscribe@googlegroups.com. > > To view this discussion on the web visit https://groups.google.com/d/msgid/kasan-dev/56cf8aab-c61b-156c-f681-d2354aed22bb%40virtuozzo.com. > > -- > You received this message because you are subscribed to the Google Groups "kasan-dev" group. > To unsubscribe from this group and stop receiving emails from it, send an email to kasan-dev+unsubscribe@googlegroups.com. > To view this discussion on the web visit https://groups.google.com/d/msgid/kasan-dev/871rtqg91q.fsf%40dja-thinkpad.axtens.net.
On Fri, Nov 29, 2019 at 1:45 PM Dmitry Vyukov <dvyukov@google.com> wrote: > > On Fri, Nov 29, 2019 at 1:29 PM Daniel Axtens <dja@axtens.net> wrote: > > >>> Nope, it's vm_map_ram() not being handled > > >> Another suspicious one. Related to kasan/vmalloc? > > > Very likely the same as with ion: > > > > > > # git grep vm_map_ram|grep xfs > > > fs/xfs/xfs_buf.c: * vm_map_ram() will allocate auxiliary structures (e.g. > > > fs/xfs/xfs_buf.c: bp->b_addr = vm_map_ram(bp->b_pages, bp->b_page_count, > > > > Aaargh, that's an embarassing miss. > > > > It's a bit intricate because kasan_vmalloc_populate function is > > currently set up to take a vm_struct not a vmap_area, but I'll see if I > > can get something simple out this evening - I'm away for the first part > > of next week. > > > > Do you have to do anything interesting to get it to explode with xfs? Is > > it as simple as mounting a drive and doing some I/O? Or do you need to > > do something more involved? > > As simple as running syzkaller :) > with this config > https://github.com/google/syzkaller/blob/master/dashboard/config/upstream-kasan.config > > > Regards, > > Daniel > > > > > > > >> > > >> BUG: unable to handle page fault for address: fffff52005b80000 > > >> #PF: supervisor read access in kernel mode > > >> #PF: error_code(0x0000) - not-present page > > >> PGD 7ffcd067 P4D 7ffcd067 PUD 2cd10067 PMD 66d76067 PTE 0 > > >> Oops: 0000 [#1] PREEMPT SMP KASAN > > >> CPU: 2 PID: 9211 Comm: syz-executor.2 Not tainted 5.4.0-next-20191129+ #6 > > >> Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS > > >> rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.org 04/01/2014 > > >> RIP: 0010:xfs_sb_read_verify+0xe9/0x540 fs/xfs/libxfs/xfs_sb.c:691 > > >> Code: fc ff df 48 c1 ea 03 80 3c 02 00 0f 85 1e 04 00 00 4d 8b ac 24 > > >> 30 01 00 00 48 b8 00 00 00 00 00 fc ff df 4c 89 ea 48 c1 ea 03 <0f> b6 > > >> 04 02 84 c0 74 08 3c 03 0f 8e ad 03 00 00 41 8b 45 00 bf 58 > > >> RSP: 0018:ffffc9000a58f8d0 EFLAGS: 00010a06 > > >> RAX: dffffc0000000000 RBX: 1ffff920014b1f1d RCX: ffffc9000af42000 > > >> RDX: 1ffff92005b80000 RSI: ffffffff82914404 RDI: ffff88805cdb1460 > > >> RBP: ffffc9000a58fab0 R08: ffff8880610cd380 R09: ffffed1005a87045 > > >> R10: ffffed1005a87044 R11: ffff88802d438223 R12: ffff88805cdb1340 > > >> R13: ffffc9002dc00000 R14: ffffc9000a58fa88 R15: ffff888061b5c000 > > >> FS: 00007fb49bda9700(0000) GS:ffff88802d400000(0000) knlGS:0000000000000000 > > >> CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 > > >> CR2: fffff52005b80000 CR3: 0000000060769006 CR4: 0000000000760ee0 > > >> DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 > > >> DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 > > >> PKRU: 55555554 > > >> Call Trace: > > >> xfs_buf_ioend+0x228/0xdc0 fs/xfs/xfs_buf.c:1162 > > >> __xfs_buf_submit+0x38b/0xe50 fs/xfs/xfs_buf.c:1485 > > >> xfs_buf_submit fs/xfs/xfs_buf.h:268 [inline] > > >> xfs_buf_read_uncached+0x15c/0x560 fs/xfs/xfs_buf.c:897 > > >> xfs_readsb+0x2d0/0x540 fs/xfs/xfs_mount.c:298 > > >> xfs_fc_fill_super+0x3e6/0x11f0 fs/xfs/xfs_super.c:1415 > > >> get_tree_bdev+0x444/0x620 fs/super.c:1340 > > >> xfs_fc_get_tree+0x1c/0x20 fs/xfs/xfs_super.c:1550 > > >> vfs_get_tree+0x8e/0x300 fs/super.c:1545 > > >> do_new_mount fs/namespace.c:2822 [inline] > > >> do_mount+0x152d/0x1b50 fs/namespace.c:3142 > > >> ksys_mount+0x114/0x130 fs/namespace.c:3351 > > >> __do_sys_mount fs/namespace.c:3365 [inline] > > >> __se_sys_mount fs/namespace.c:3362 [inline] > > >> __x64_sys_mount+0xbe/0x150 fs/namespace.c:3362 > > >> do_syscall_64+0xfa/0x780 arch/x86/entry/common.c:294 > > >> entry_SYSCALL_64_after_hwframe+0x49/0xbe > > >> RIP: 0033:0x46736a > > >> Code: 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f > > >> 84 00 00 00 00 00 0f 1f 44 00 00 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d > > >> 01 f0 ff ff 73 01 c3 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48 > > >> RSP: 002b:00007fb49bda8a78 EFLAGS: 00000202 ORIG_RAX: 00000000000000a5 > > >> RAX: ffffffffffffffda RBX: 00007fb49bda8af0 RCX: 000000000046736a > > >> RDX: 00007fb49bda8ad0 RSI: 0000000020000140 RDI: 00007fb49bda8af0 > > >> RBP: 00007fb49bda8ad0 R08: 00007fb49bda8b30 R09: 00007fb49bda8ad0 > > >> R10: 0000000000000000 R11: 0000000000000202 R12: 00007fb49bda8b30 > > >> R13: 00000000004b1c60 R14: 00000000004b006d R15: 00007fb49bda96bc > > >> Modules linked in: > > >> Dumping ftrace buffer: > > >> (ftrace buffer empty) > > >> CR2: fffff52005b80000 > > >> ---[ end trace eddd8949d4c898df ]--- > > >> RIP: 0010:xfs_sb_read_verify+0xe9/0x540 fs/xfs/libxfs/xfs_sb.c:691 > > >> Code: fc ff df 48 c1 ea 03 80 3c 02 00 0f 85 1e 04 00 00 4d 8b ac 24 > > >> 30 01 00 00 48 b8 00 00 00 00 00 fc ff df 4c 89 ea 48 c1 ea 03 <0f> b6 > > >> 04 02 84 c0 74 08 3c 03 0f 8e ad 03 00 00 41 8b 45 00 bf 58 > > >> RSP: 0018:ffffc9000a58f8d0 EFLAGS: 00010a06 > > >> RAX: dffffc0000000000 RBX: 1ffff920014b1f1d RCX: ffffc9000af42000 > > >> RDX: 1ffff92005b80000 RSI: ffffffff82914404 RDI: ffff88805cdb1460 > > >> RBP: ffffc9000a58fab0 R08: ffff8880610cd380 R09: ffffed1005a87045 > > >> R10: ffffed1005a87044 R11: ffff88802d438223 R12: ffff88805cdb1340 > > >> R13: ffffc9002dc00000 R14: ffffc9000a58fa88 R15: ffff888061b5c000 > > >> FS: 00007fb49bda9700(0000) GS:ffff88802d400000(0000) knlGS:0000000000000000 > > >> CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 > > >> CR2: fffff52005b80000 CR3: 0000000060769006 CR4: 0000000000760ee0 > > >> DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 > > >> DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 > > >> PKRU: 55555554 Another one that looks related: BUG: sleeping function called from invalid context at mm/page_alloc.c:4681 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 15087, name: syz-executor.7 3 locks held by syz-executor.7/15087: #0: ffff888024542110 (sk_lock-AF_PACKET){+.+.}, at: lock_sock include/net/sock.h:1526 [inline] #0: ffff888024542110 (sk_lock-AF_PACKET){+.+.}, at: packet_setsockopt+0xdf1/0x2d90 net/packet/af_packet.c:3678 #1: ffffffff89850a80 (vmap_purge_lock){+.+.}, at: try_purge_vmap_area_lazy mm/vmalloc.c:1331 [inline] #1: ffffffff89850a80 (vmap_purge_lock){+.+.}, at: free_vmap_area_noflush+0x2a8/0x390 mm/vmalloc.c:1368 #2: ffffffff89850c18 (free_vmap_area_lock){+.+.}, at: spin_lock include/linux/spinlock.h:338 [inline] #2: ffffffff89850c18 (free_vmap_area_lock){+.+.}, at: __purge_vmap_area_lazy+0x19c/0x1f30 mm/vmalloc.c:1298 Preemption disabled at: [<ffffffff81a78ddc>] spin_lock include/linux/spinlock.h:338 [inline] [<ffffffff81a78ddc>] __purge_vmap_area_lazy+0x19c/0x1f30 mm/vmalloc.c:1298 CPU: 3 PID: 15087 Comm: syz-executor.7 Not tainted 5.4.0-next-20191129+ #7 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x199/0x216 lib/dump_stack.c:118 ___might_sleep.cold.97+0x1f5/0x238 kernel/sched/core.c:6800 __might_sleep+0x95/0x190 kernel/sched/core.c:6753 prepare_alloc_pages mm/page_alloc.c:4681 [inline] __alloc_pages_nodemask+0x3cd/0x890 mm/page_alloc.c:4730 alloc_pages_current+0x10c/0x210 mm/mempolicy.c:2211 alloc_pages include/linux/gfp.h:532 [inline] __get_free_pages+0xc/0x40 mm/page_alloc.c:4786 __pte_alloc_one_kernel include/asm-generic/pgalloc.h:21 [inline] pte_alloc_one_kernel include/asm-generic/pgalloc.h:33 [inline] __pte_alloc_kernel+0x1d/0x200 mm/memory.c:459 apply_to_pte_range mm/memory.c:2031 [inline] apply_to_pmd_range mm/memory.c:2068 [inline] apply_to_pud_range mm/memory.c:2088 [inline] apply_to_p4d_range mm/memory.c:2108 [inline] apply_to_page_range+0x77d/0xa00 mm/memory.c:2133 kasan_release_vmalloc+0xa7/0xc0 mm/kasan/common.c:970 __purge_vmap_area_lazy+0xcbb/0x1f30 mm/vmalloc.c:1313 try_purge_vmap_area_lazy mm/vmalloc.c:1332 [inline] free_vmap_area_noflush+0x2ca/0x390 mm/vmalloc.c:1368 free_unmap_vmap_area mm/vmalloc.c:1381 [inline] remove_vm_area+0x1cc/0x230 mm/vmalloc.c:2209 vm_remove_mappings mm/vmalloc.c:2236 [inline] __vunmap+0x223/0xa20 mm/vmalloc.c:2299 __vfree+0x3f/0xd0 mm/vmalloc.c:2356 __vmalloc_area_node mm/vmalloc.c:2507 [inline] __vmalloc_node_range+0x5d5/0x810 mm/vmalloc.c:2547 __vmalloc_node mm/vmalloc.c:2607 [inline] __vmalloc_node_flags mm/vmalloc.c:2621 [inline] vzalloc+0x6f/0x80 mm/vmalloc.c:2666 alloc_one_pg_vec_page net/packet/af_packet.c:4233 [inline] alloc_pg_vec net/packet/af_packet.c:4258 [inline] packet_set_ring+0xbc0/0x1b50 net/packet/af_packet.c:4342 packet_setsockopt+0xed7/0x2d90 net/packet/af_packet.c:3695 __sys_setsockopt+0x29b/0x4d0 net/socket.c:2117 __do_sys_setsockopt net/socket.c:2133 [inline] __se_sys_setsockopt net/socket.c:2130 [inline] __x64_sys_setsockopt+0xbe/0x150 net/socket.c:2130 do_syscall_64+0xfa/0x780 arch/x86/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x465fe9 Code: Bad RIP value. RSP: 002b:00007ff70087dc68 EFLAGS: 00000246 ORIG_RAX: 0000000000000036 RAX: ffffffffffffffda RBX: 000000000052bf00 RCX: 0000000000465fe9 RDX: 0000000000000005 RSI: 0000000000000107 RDI: 0000000000000004 RBP: 00000000ffffffff R08: 000000000000001c R09: 0000000000000000 R10: 0000000020000040 R11: 0000000000000246 R12: 00000000004a643a R13: 00000000004f2620 R14: 00000000004af7e6 R15: 00007ff70087e6bc BUG: scheduling while atomic: syz-executor.7/15087/0x00000002 3 locks held by syz-executor.7/15087: #0: ffff888024542110 (sk_lock-AF_PACKET){+.+.}, at: lock_sock include/net/sock.h:1526 [inline] #0: ffff888024542110 (sk_lock-AF_PACKET){+.+.}, at: packet_setsockopt+0xdf1/0x2d90 net/packet/af_packet.c:3678 #1: ffffffff89850a80 (vmap_purge_lock){+.+.}, at: try_purge_vmap_area_lazy mm/vmalloc.c:1331 [inline] #1: ffffffff89850a80 (vmap_purge_lock){+.+.}, at: free_vmap_area_noflush+0x2a8/0x390 mm/vmalloc.c:1368 #2: ffffffff89850c18 (free_vmap_area_lock){+.+.}, at: spin_lock include/linux/spinlock.h:338 [inline] #2: ffffffff89850c18 (free_vmap_area_lock){+.+.}, at: __purge_vmap_area_lazy+0x19c/0x1f30 mm/vmalloc.c:1298 Modules linked in: Preemption disabled at: [<ffffffff81a78ddc>] spin_lock include/linux/spinlock.h:338 [inline] [<ffffffff81a78ddc>] __purge_vmap_area_lazy+0x19c/0x1f30 mm/vmalloc.c:1298
> On Nov 29, 2019, at 7:29 AM, Daniel Axtens <dja@axtens.net> wrote: > >>>> >>>> Nope, it's vm_map_ram() not being handled >>> >>> >>> Another suspicious one. Related to kasan/vmalloc? >> >> Very likely the same as with ion: >> >> # git grep vm_map_ram|grep xfs >> fs/xfs/xfs_buf.c: * vm_map_ram() will allocate auxiliary structures (e.g. >> fs/xfs/xfs_buf.c: bp->b_addr = vm_map_ram(bp->b_pages, bp->b_page_count, > > Aaargh, that's an embarassing miss. > > It's a bit intricate because kasan_vmalloc_populate function is > currently set up to take a vm_struct not a vmap_area, but I'll see if I > can get something simple out this evening - I'm away for the first part > of next week. > > Do you have to do anything interesting to get it to explode with xfs? Is > it as simple as mounting a drive and doing some I/O? Or do you need to > do something more involved? I instead trigger something a bit different by manually triggering a crash first to make the XFS partition uncleanly shutdown. # echo c >/proc/sysrq-trigger and then reboot the same kernel where it will crash while checking the XFS. This can be workaround by rebooting to an older kernel (v4.18) first where xfs_repair will be successfully there, and then rebooting to the new linux-next kernel will be fine. [ OK ] Started File System Check on /dev/mapper/rhel_hpe--sy680gen9--01-root. Mounting /sysroot... [ 141.177726][ T1730] SGI XFS with security attributes, no debug enabled [ 141.432382][ T1720] XFS (dm-0): Mounting V5 Filesystem [** ] A start job is running for /sysroot (39s / 1min 51s)[ 158.738816][ T1720] XFS (dm-0): Starting recovery (logdev: internal) [ 158.792010][ T844] BUG: unable to handle page fault for address: fffff52001f0000c [ 158.830913][ T844] #PF: supervisor read access in kernel mode [ 158.859680][ T844] #PF: error_code(0x0000) - not-present page [ 158.886057][ T844] PGD 207ffe3067 P4D 207ffe3067 PUD 2071f2067 PMD f68e08067 PTE 0 [ 158.922065][ T844] Oops: 0000 [#1] SMP DEBUG_PAGEALLOC KASAN PTI [ 158.949620][ T844] CPU: 112 PID: 844 Comm: kworker/112:1 Not tainted 5.4.0-next-20191127+ #3 [ 158.988759][ T844] Hardware name: HP Synergy 680 Gen9/Synergy 680 Gen9 Compute Module, BIOS I40 05/23/2018 [ 159.033380][ T844] Workqueue: xfs-buf/dm-0 xfs_buf_ioend_work [xfs] [ 159.061935][ T844] RIP: 0010:__asan_load4+0x3a/0xa0 [ 159.061941][ T844] Code: 00 00 00 00 00 00 ff 48 39 f8 77 6d 48 8d 47 03 48 89 c2 83 e2 07 48 83 fa 02 76 30 48 be 00 00 00 00 00 fc ff df 48 c1 e8 03 <0f> b6 04 30 84 c0 75 3e 5d c3 48 b8 00 00 00 00 00 80 ff ff eb c7 [ 159.061944][ T844] RSP: 0018:ffffc9000a4b7cb0 EFLAGS: 00010a06 [ 159.061949][ T844] RAX: 1ffff92001f0000c RBX: ffffc9000f800000 RCX: ffffffffc06d10ae [ 159.061952][ T844] RDX: 0000000000000003 RSI: dffffc0000000000 RDI: ffffc9000f800060 [ 159.061955][ T844] RBP: ffffc9000a4b7cb0 R08: ffffed130bee89e5 R09: 0000000000000001 [ 159.061958][ T844] R10: ffffed130bee89e4 R11: ffff88985f744f23 R12: 0000000000000000 [ 159.061961][ T844] R13: ffff889724be0040 R14: ffff88836c8e5000 R15: 00000000000c8000 [ 159.061965][ T844] FS: 0000000000000000(0000) GS:ffff88985f700000(0000) knlGS:0000000000000000 [ 159.061968][ T844] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 159.061971][ T844] CR2: fffff52001f0000c CR3: 0000001f615b8004 CR4: 00000000003606e0 [ 159.061974][ T844] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 159.061976][ T844] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 159.061978][ T844] Call Trace: [ 159.062118][ T844] xfs_inode_buf_verify+0x13e/0x230 [xfs] [ 159.062264][ T844] xfs_inode_buf_readahead_verify+0x13/0x20 [xfs] [ 159.634441][ T844] xfs_buf_ioend+0x153/0x6b0 [xfs] [ 159.634455][ T844] ? trace_hardirqs_on+0x3a/0x160 [ 159.679087][ T844] xfs_buf_ioend_work+0x15/0x20 [xfs] [ 159.702689][ T844] process_one_work+0x579/0xb90 [ 159.723898][ T844] ? pwq_dec_nr_in_flight+0x170/0x170 [ 159.747499][ T844] worker_thread+0x63/0x5b0 [ 159.767531][ T844] ? process_one_work+0xb90/0xb90 [ 159.789549][ T844] kthread+0x1e6/0x210 [ 159.807166][ T844] ? kthread_create_worker_on_cpu+0xc0/0xc0 [ 159.833064][ T844] ret_from_fork+0x3a/0x50 [ 159.852200][ T844] Modules linked in: xfs sd_mod bnx2x mdio firmware_class hpsa scsi_transport_sas dm_mirror dm_region_hash dm_log dm_mod [ 159.915273][ T844] CR2: fffff52001f0000c [ 159.934029][ T844] ---[ end trace 3f3b30f5fc34bbf1 ]--- [ 159.957937][ T844] RIP: 0010:__asan_load4+0x3a/0xa0 [ 159.980316][ T844] Code: 00 00 00 00 00 00 ff 48 39 f8 77 6d 48 8d 47 03 48 89 c2 83 e2 07 48 83 fa 02 76 30 48 be 00 00 00 00 00 fc ff df 48 c1 e8 03 <0f> b6 04 30 84 c0 75 3e 5d c3 48 b8 00 00 00 00 00 80 ff ff eb c7 [ 160.068386][ T844] RSP: 0018:ffffc9000a4b7cb0 EFLAGS: 00010a06 [ 160.068389][ T844] RAX: 1ffff92001f0000c RBX: ffffc9000f800000 RCX: ffffffffc06d10ae [ 160.068391][ T844] RDX: 0000000000000003 RSI: dffffc0000000000 RDI: ffffc9000f800060 [ 160.068393][ T844] RBP: ffffc9000a4b7cb0 R08: ffffed130bee89e5 R09: 0000000000000001 [ 160.068395][ T844] R10: ffffed130bee89e4 R11: ffff88985f744f23 R12: 0000000000000000 [ 160.068397][ T844] R13: ffff889724be0040 R14: ffff88836c8e5000 R15: 00000000000c8000 [ 160.068399][ T844] FS: 0000000000000000(0000) GS:ffff88985f700000(0000) knlGS:0000000000000000 [ 160.068401][ T844] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 160.068404][ T844] CR2: fffff52001f0000c CR3: 0000001f615b8004 CR4: 00000000003606e0 [ 160.068405][ T844] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 160.068407][ T844] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 160.068410][ T844] Kernel panic - not syncing: Fatal exception [ 160.095178][ T844] Kernel Offset: 0x21c00000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) [ 160.541027][ T844] ---[ end Kernel panic - not syncing: Fatal exception ]--- > > Regards, > Daniel > >> >>> >>> BUG: unable to handle page fault for address: fffff52005b80000 >>> #PF: supervisor read access in kernel mode >>> #PF: error_code(0x0000) - not-present page >>> PGD 7ffcd067 P4D 7ffcd067 PUD 2cd10067 PMD 66d76067 PTE 0 >>> Oops: 0000 [#1] PREEMPT SMP KASAN >>> CPU: 2 PID: 9211 Comm: syz-executor.2 Not tainted 5.4.0-next-20191129+ #6 >>> Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS >>> rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.org 04/01/2014 >>> RIP: 0010:xfs_sb_read_verify+0xe9/0x540 fs/xfs/libxfs/xfs_sb.c:691 >>> Code: fc ff df 48 c1 ea 03 80 3c 02 00 0f 85 1e 04 00 00 4d 8b ac 24 >>> 30 01 00 00 48 b8 00 00 00 00 00 fc ff df 4c 89 ea 48 c1 ea 03 <0f> b6 >>> 04 02 84 c0 74 08 3c 03 0f 8e ad 03 00 00 41 8b 45 00 bf 58 >>> RSP: 0018:ffffc9000a58f8d0 EFLAGS: 00010a06 >>> RAX: dffffc0000000000 RBX: 1ffff920014b1f1d RCX: ffffc9000af42000 >>> RDX: 1ffff92005b80000 RSI: ffffffff82914404 RDI: ffff88805cdb1460 >>> RBP: ffffc9000a58fab0 R08: ffff8880610cd380 R09: ffffed1005a87045 >>> R10: ffffed1005a87044 R11: ffff88802d438223 R12: ffff88805cdb1340 >>> R13: ffffc9002dc00000 R14: ffffc9000a58fa88 R15: ffff888061b5c000 >>> FS: 00007fb49bda9700(0000) GS:ffff88802d400000(0000) knlGS:0000000000000000 >>> CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 >>> CR2: fffff52005b80000 CR3: 0000000060769006 CR4: 0000000000760ee0 >>> DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 >>> DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 >>> PKRU: 55555554 >>> Call Trace: >>> xfs_buf_ioend+0x228/0xdc0 fs/xfs/xfs_buf.c:1162 >>> __xfs_buf_submit+0x38b/0xe50 fs/xfs/xfs_buf.c:1485 >>> xfs_buf_submit fs/xfs/xfs_buf.h:268 [inline] >>> xfs_buf_read_uncached+0x15c/0x560 fs/xfs/xfs_buf.c:897 >>> xfs_readsb+0x2d0/0x540 fs/xfs/xfs_mount.c:298 >>> xfs_fc_fill_super+0x3e6/0x11f0 fs/xfs/xfs_super.c:1415 >>> get_tree_bdev+0x444/0x620 fs/super.c:1340 >>> xfs_fc_get_tree+0x1c/0x20 fs/xfs/xfs_super.c:1550 >>> vfs_get_tree+0x8e/0x300 fs/super.c:1545 >>> do_new_mount fs/namespace.c:2822 [inline] >>> do_mount+0x152d/0x1b50 fs/namespace.c:3142 >>> ksys_mount+0x114/0x130 fs/namespace.c:3351 >>> __do_sys_mount fs/namespace.c:3365 [inline] >>> __se_sys_mount fs/namespace.c:3362 [inline] >>> __x64_sys_mount+0xbe/0x150 fs/namespace.c:3362 >>> do_syscall_64+0xfa/0x780 arch/x86/entry/common.c:294 >>> entry_SYSCALL_64_after_hwframe+0x49/0xbe >>> RIP: 0033:0x46736a >>> Code: 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f >>> 84 00 00 00 00 00 0f 1f 44 00 00 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d >>> 01 f0 ff ff 73 01 c3 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48 >>> RSP: 002b:00007fb49bda8a78 EFLAGS: 00000202 ORIG_RAX: 00000000000000a5 >>> RAX: ffffffffffffffda RBX: 00007fb49bda8af0 RCX: 000000000046736a >>> RDX: 00007fb49bda8ad0 RSI: 0000000020000140 RDI: 00007fb49bda8af0 >>> RBP: 00007fb49bda8ad0 R08: 00007fb49bda8b30 R09: 00007fb49bda8ad0 >>> R10: 0000000000000000 R11: 0000000000000202 R12: 00007fb49bda8b30 >>> R13: 00000000004b1c60 R14: 00000000004b006d R15: 00007fb49bda96bc >>> Modules linked in: >>> Dumping ftrace buffer: >>> (ftrace buffer empty) >>> CR2: fffff52005b80000 >>> ---[ end trace eddd8949d4c898df ]--- >>> RIP: 0010:xfs_sb_read_verify+0xe9/0x540 fs/xfs/libxfs/xfs_sb.c:691 >>> Code: fc ff df 48 c1 ea 03 80 3c 02 00 0f 85 1e 04 00 00 4d 8b ac 24 >>> 30 01 00 00 48 b8 00 00 00 00 00 fc ff df 4c 89 ea 48 c1 ea 03 <0f> b6 >>> 04 02 84 c0 74 08 3c 03 0f 8e ad 03 00 00 41 8b 45 00 bf 58 >>> RSP: 0018:ffffc9000a58f8d0 EFLAGS: 00010a06 >>> RAX: dffffc0000000000 RBX: 1ffff920014b1f1d RCX: ffffc9000af42000 >>> RDX: 1ffff92005b80000 RSI: ffffffff82914404 RDI: ffff88805cdb1460 >>> RBP: ffffc9000a58fab0 R08: ffff8880610cd380 R09: ffffed1005a87045 >>> R10: ffffed1005a87044 R11: ffff88802d438223 R12: ffff88805cdb1340 >>> R13: ffffc9002dc00000 R14: ffffc9000a58fa88 R15: ffff888061b5c000 >>> FS: 00007fb49bda9700(0000) GS:ffff88802d400000(0000) knlGS:0000000000000000 >>> CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 >>> CR2: fffff52005b80000 CR3: 0000000060769006 CR4: 0000000000760ee0 >>> DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 >>> DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 >>> PKRU: 55555554 >>> >> >> -- >> You received this message because you are subscribed to the Google Groups "kasan-dev" group. >> To unsubscribe from this group and stop receiving emails from it, send an email to kasan-dev+unsubscribe@googlegroups.com. >> To view this discussion on the web visit https://groups.google.com/d/msgid/kasan-dev/56cf8aab-c61b-156c-f681-d2354aed22bb%40virtuozzo.com.
>>>>> >>>>> Nope, it's vm_map_ram() not being handled >>>> >>>> >>>> Another suspicious one. Related to kasan/vmalloc? >>> >>> Very likely the same as with ion: >>> >>> # git grep vm_map_ram|grep xfs >>> fs/xfs/xfs_buf.c: * vm_map_ram() will allocate auxiliary structures (e.g. >>> fs/xfs/xfs_buf.c: bp->b_addr = vm_map_ram(bp->b_pages, bp->b_page_count, >> >> Aaargh, that's an embarassing miss. >> >> It's a bit intricate because kasan_vmalloc_populate function is >> currently set up to take a vm_struct not a vmap_area, but I'll see if I >> can get something simple out this evening - I'm away for the first part >> of next week. For crashes in XFS, binder etc that implicate vm_map_ram, see: https://lore.kernel.org/linux-mm/20191129154519.30964-1-dja@axtens.net/ The easiest way I found to repro the bug is sudo modprobe i915 mock_selftest=-1 For lock warns, one that goes through the percpu alloc path, the patch is already queued in mmots. For Dmitry's latest one where there's an allocation in the purge_vmap_area_lazy path that triggers a locking warning, you'll have to wait until next week, sorry. Regards, Daniel
diff --git a/Documentation/dev-tools/kasan.rst b/Documentation/dev-tools/kasan.rst index 525296121d89..e4d66e7c50de 100644 --- a/Documentation/dev-tools/kasan.rst +++ b/Documentation/dev-tools/kasan.rst @@ -218,3 +218,66 @@ brk handler is used to print bug reports. A potential expansion of this mode is a hardware tag-based mode, which would use hardware memory tagging support instead of compiler instrumentation and manual shadow memory manipulation. + +What memory accesses are sanitised by KASAN? +-------------------------------------------- + +The kernel maps memory in a number of different parts of the address +space. This poses something of a problem for KASAN, which requires +that all addresses accessed by instrumented code have a valid shadow +region. + +The range of kernel virtual addresses is large: there is not enough +real memory to support a real shadow region for every address that +could be accessed by the kernel. + +By default +~~~~~~~~~~ + +By default, architectures only map real memory over the shadow region +for the linear mapping (and potentially other small areas). For all +other areas - such as vmalloc and vmemmap space - a single read-only +page is mapped over the shadow area. This read-only shadow page +declares all memory accesses as permitted. + +This presents a problem for modules: they do not live in the linear +mapping, but in a dedicated module space. By hooking in to the module +allocator, KASAN can temporarily map real shadow memory to cover +them. This allows detection of invalid accesses to module globals, for +example. + +This also creates an incompatibility with ``VMAP_STACK``: if the stack +lives in vmalloc space, it will be shadowed by the read-only page, and +the kernel will fault when trying to set up the shadow data for stack +variables. + +CONFIG_KASAN_VMALLOC +~~~~~~~~~~~~~~~~~~~~ + +With ``CONFIG_KASAN_VMALLOC``, KASAN can cover vmalloc space at the +cost of greater memory usage. Currently this is only supported on x86. + +This works by hooking into vmalloc and vmap, and dynamically +allocating real shadow memory to back the mappings. + +Most mappings in vmalloc space are small, requiring less than a full +page of shadow space. Allocating a full shadow page per mapping would +therefore be wasteful. Furthermore, to ensure that different mappings +use different shadow pages, mappings would have to be aligned to +``KASAN_SHADOW_SCALE_SIZE * PAGE_SIZE``. + +Instead, we share backing space across multiple mappings. We allocate +a backing page when a mapping in vmalloc space uses a particular page +of the shadow region. This page can be shared by other vmalloc +mappings later on. + +We hook in to the vmap infrastructure to lazily clean up unused shadow +memory. + +To avoid the difficulties around swapping mappings around, we expect +that the part of the shadow region that covers the vmalloc space will +not be covered by the early shadow page, but will be left +unmapped. This will require changes in arch-specific code. + +This allows ``VMAP_STACK`` support on x86, and can simplify support of +architectures that do not have a fixed module region. diff --git a/include/linux/kasan.h b/include/linux/kasan.h index cc8a03cc9674..4f404c565db1 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -70,8 +70,18 @@ struct kasan_cache { int free_meta_offset; }; +/* + * These functions provide a special case to support backing module + * allocations with real shadow memory. With KASAN vmalloc, the special + * case is unnecessary, as the work is handled in the generic case. + */ +#ifndef CONFIG_KASAN_VMALLOC int kasan_module_alloc(void *addr, size_t size); void kasan_free_shadow(const struct vm_struct *vm); +#else +static inline int kasan_module_alloc(void *addr, size_t size) { return 0; } +static inline void kasan_free_shadow(const struct vm_struct *vm) {} +#endif int kasan_add_zero_shadow(void *start, unsigned long size); void kasan_remove_zero_shadow(void *start, unsigned long size); @@ -194,4 +204,25 @@ static inline void *kasan_reset_tag(const void *addr) #endif /* CONFIG_KASAN_SW_TAGS */ +#ifdef CONFIG_KASAN_VMALLOC +int kasan_populate_vmalloc(unsigned long requested_size, + struct vm_struct *area); +void kasan_poison_vmalloc(void *start, unsigned long size); +void kasan_release_vmalloc(unsigned long start, unsigned long end, + unsigned long free_region_start, + unsigned long free_region_end); +#else +static inline int kasan_populate_vmalloc(unsigned long requested_size, + struct vm_struct *area) +{ + return 0; +} + +static inline void kasan_poison_vmalloc(void *start, unsigned long size) {} +static inline void kasan_release_vmalloc(unsigned long start, + unsigned long end, + unsigned long free_region_start, + unsigned long free_region_end) {} +#endif + #endif /* LINUX_KASAN_H */ diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h index 5229c18025e9..ca92aea8a6bd 100644 --- a/include/linux/moduleloader.h +++ b/include/linux/moduleloader.h @@ -91,7 +91,7 @@ void module_arch_cleanup(struct module *mod); /* Any cleanup before freeing mod->module_init */ void module_arch_freeing_init(struct module *mod); -#ifdef CONFIG_KASAN +#if defined(CONFIG_KASAN) && !defined(CONFIG_KASAN_VMALLOC) #include <linux/kasan.h> #define MODULE_ALIGN (PAGE_SIZE << KASAN_SHADOW_SCALE_SHIFT) #else diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 4e7809408073..61c43d1a29ca 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -22,6 +22,18 @@ struct notifier_block; /* in notifier.h */ #define VM_UNINITIALIZED 0x00000020 /* vm_struct is not fully initialized */ #define VM_NO_GUARD 0x00000040 /* don't add guard page */ #define VM_KASAN 0x00000080 /* has allocated kasan shadow memory */ + +/* + * VM_KASAN is used slighly differently depending on CONFIG_KASAN_VMALLOC. + * + * If IS_ENABLED(CONFIG_KASAN_VMALLOC), VM_KASAN is set on a vm_struct after + * shadow memory has been mapped. It's used to handle allocation errors so that + * we don't try to poision shadow on free if it was never allocated. + * + * Otherwise, VM_KASAN is set for kasan_module_alloc() allocations and used to + * determine which allocations need the module shadow freed. + */ + /* * Memory with VM_FLUSH_RESET_PERMS cannot be freed in an interrupt or with * vfree_atomic(). diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan index 6c9682ce0254..81f5464ea9e1 100644 --- a/lib/Kconfig.kasan +++ b/lib/Kconfig.kasan @@ -6,6 +6,9 @@ config HAVE_ARCH_KASAN config HAVE_ARCH_KASAN_SW_TAGS bool +config HAVE_ARCH_KASAN_VMALLOC + bool + config CC_HAS_KASAN_GENERIC def_bool $(cc-option, -fsanitize=kernel-address) @@ -142,6 +145,19 @@ config KASAN_SW_TAGS_IDENTIFY (use-after-free or out-of-bounds) at the cost of increased memory consumption. +config KASAN_VMALLOC + bool "Back mappings in vmalloc space with real shadow memory" + depends on KASAN && HAVE_ARCH_KASAN_VMALLOC + help + By default, the shadow region for vmalloc space is the read-only + zero page. This means that KASAN cannot detect errors involving + vmalloc space. + + Enabling this option will hook in to vmap/vmalloc and back those + mappings with real shadow memory allocated on demand. This allows + for KASAN to detect more sorts of errors (and to support vmapped + stacks), but at the cost of higher memory usage. + config TEST_KASAN tristate "Module for testing KASAN for bug detection" depends on m && KASAN diff --git a/mm/kasan/common.c b/mm/kasan/common.c index 6814d6d6a023..6e7bc5d3fa83 100644 --- a/mm/kasan/common.c +++ b/mm/kasan/common.c @@ -36,6 +36,8 @@ #include <linux/bug.h> #include <linux/uaccess.h> +#include <asm/tlbflush.h> + #include "kasan.h" #include "../slab.h" @@ -590,6 +592,7 @@ void kasan_kfree_large(void *ptr, unsigned long ip) /* The object will be poisoned by page_alloc. */ } +#ifndef CONFIG_KASAN_VMALLOC int kasan_module_alloc(void *addr, size_t size) { void *ret; @@ -625,6 +628,7 @@ void kasan_free_shadow(const struct vm_struct *vm) if (vm->flags & VM_KASAN) vfree(kasan_mem_to_shadow(vm->addr)); } +#endif extern void __kasan_report(unsigned long addr, size_t size, bool is_write, unsigned long ip); @@ -744,3 +748,230 @@ static int __init kasan_memhotplug_init(void) core_initcall(kasan_memhotplug_init); #endif + +#ifdef CONFIG_KASAN_VMALLOC +static int kasan_populate_vmalloc_pte(pte_t *ptep, unsigned long addr, + void *unused) +{ + unsigned long page; + pte_t pte; + + if (likely(!pte_none(*ptep))) + return 0; + + page = __get_free_page(GFP_KERNEL); + if (!page) + return -ENOMEM; + + memset((void *)page, KASAN_VMALLOC_INVALID, PAGE_SIZE); + pte = pfn_pte(PFN_DOWN(__pa(page)), PAGE_KERNEL); + + spin_lock(&init_mm.page_table_lock); + if (likely(pte_none(*ptep))) { + set_pte_at(&init_mm, addr, ptep, pte); + page = 0; + } + spin_unlock(&init_mm.page_table_lock); + if (page) + free_page(page); + return 0; +} + +int kasan_populate_vmalloc(unsigned long requested_size, struct vm_struct *area) +{ + unsigned long shadow_start, shadow_end; + int ret; + + shadow_start = (unsigned long)kasan_mem_to_shadow(area->addr); + shadow_start = ALIGN_DOWN(shadow_start, PAGE_SIZE); + shadow_end = (unsigned long)kasan_mem_to_shadow(area->addr + + area->size); + shadow_end = ALIGN(shadow_end, PAGE_SIZE); + + ret = apply_to_page_range(&init_mm, shadow_start, + shadow_end - shadow_start, + kasan_populate_vmalloc_pte, NULL); + if (ret) + return ret; + + kasan_unpoison_shadow(area->addr, requested_size); + + area->flags |= VM_KASAN; + + /* + * We need to be careful about inter-cpu effects here. Consider: + * + * CPU#0 CPU#1 + * WRITE_ONCE(p, vmalloc(100)); while (x = READ_ONCE(p)) ; + * p[99] = 1; + * + * With compiler instrumentation, that ends up looking like this: + * + * CPU#0 CPU#1 + * // vmalloc() allocates memory + * // let a = area->addr + * // we reach kasan_populate_vmalloc + * // and call kasan_unpoison_shadow: + * STORE shadow(a), unpoison_val + * ... + * STORE shadow(a+99), unpoison_val x = LOAD p + * // rest of vmalloc process <data dependency> + * STORE p, a LOAD shadow(x+99) + * + * If there is no barrier between the end of unpoisioning the shadow + * and the store of the result to p, the stores could be committed + * in a different order by CPU#0, and CPU#1 could erroneously observe + * poison in the shadow. + * + * We need some sort of barrier between the stores. + * + * In the vmalloc() case, this is provided by a smp_wmb() in + * clear_vm_uninitialized_flag(). In the per-cpu allocator and in + * get_vm_area() and friends, the caller gets shadow allocated but + * doesn't have any pages mapped into the virtual address space that + * has been reserved. Mapping those pages in will involve taking and + * releasing a page-table lock, which will provide the barrier. + */ + + return 0; +} + +/* + * Poison the shadow for a vmalloc region. Called as part of the + * freeing process at the time the region is freed. + */ +void kasan_poison_vmalloc(void *start, unsigned long size) +{ + size = round_up(size, KASAN_SHADOW_SCALE_SIZE); + kasan_poison_shadow(start, size, KASAN_VMALLOC_INVALID); +} + +static int kasan_depopulate_vmalloc_pte(pte_t *ptep, unsigned long addr, + void *unused) +{ + unsigned long page; + + page = (unsigned long)__va(pte_pfn(*ptep) << PAGE_SHIFT); + + spin_lock(&init_mm.page_table_lock); + + if (likely(!pte_none(*ptep))) { + pte_clear(&init_mm, addr, ptep); + free_page(page); + } + spin_unlock(&init_mm.page_table_lock); + + return 0; +} + +/* + * Release the backing for the vmalloc region [start, end), which + * lies within the free region [free_region_start, free_region_end). + * + * This can be run lazily, long after the region was freed. It runs + * under vmap_area_lock, so it's not safe to interact with the vmalloc/vmap + * infrastructure. + * + * How does this work? + * ------------------- + * + * We have a region that is page aligned, labelled as A. + * That might not map onto the shadow in a way that is page-aligned: + * + * start end + * v v + * |????????|????????|AAAAAAAA|AA....AA|AAAAAAAA|????????| < vmalloc + * -------- -------- -------- -------- -------- + * | | | | | + * | | | /-------/ | + * \-------\|/------/ |/---------------/ + * ||| || + * |??AAAAAA|AAAAAAAA|AA??????| < shadow + * (1) (2) (3) + * + * First we align the start upwards and the end downwards, so that the + * shadow of the region aligns with shadow page boundaries. In the + * example, this gives us the shadow page (2). This is the shadow entirely + * covered by this allocation. + * + * Then we have the tricky bits. We want to know if we can free the + * partially covered shadow pages - (1) and (3) in the example. For this, + * we are given the start and end of the free region that contains this + * allocation. Extending our previous example, we could have: + * + * free_region_start free_region_end + * | start end | + * v v v v + * |FFFFFFFF|FFFFFFFF|AAAAAAAA|AA....AA|AAAAAAAA|FFFFFFFF| < vmalloc + * -------- -------- -------- -------- -------- + * | | | | | + * | | | /-------/ | + * \-------\|/------/ |/---------------/ + * ||| || + * |FFAAAAAA|AAAAAAAA|AAF?????| < shadow + * (1) (2) (3) + * + * Once again, we align the start of the free region up, and the end of + * the free region down so that the shadow is page aligned. So we can free + * page (1) - we know no allocation currently uses anything in that page, + * because all of it is in the vmalloc free region. But we cannot free + * page (3), because we can't be sure that the rest of it is unused. + * + * We only consider pages that contain part of the original region for + * freeing: we don't try to free other pages from the free region or we'd + * end up trying to free huge chunks of virtual address space. + * + * Concurrency + * ----------- + * + * How do we know that we're not freeing a page that is simultaneously + * being used for a fresh allocation in kasan_populate_vmalloc(_pte)? + * + * We _can_ have kasan_release_vmalloc and kasan_populate_vmalloc running + * at the same time. While we run under free_vmap_area_lock, the population + * code does not. + * + * free_vmap_area_lock instead operates to ensure that the larger range + * [free_region_start, free_region_end) is safe: because __alloc_vmap_area and + * the per-cpu region-finding algorithm both run under free_vmap_area_lock, + * no space identified as free will become used while we are running. This + * means that so long as we are careful with alignment and only free shadow + * pages entirely covered by the free region, we will not run in to any + * trouble - any simultaneous allocations will be for disjoint regions. + */ +void kasan_release_vmalloc(unsigned long start, unsigned long end, + unsigned long free_region_start, + unsigned long free_region_end) +{ + void *shadow_start, *shadow_end; + unsigned long region_start, region_end; + + region_start = ALIGN(start, PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE); + region_end = ALIGN_DOWN(end, PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE); + + free_region_start = ALIGN(free_region_start, + PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE); + + if (start != region_start && + free_region_start < region_start) + region_start -= PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE; + + free_region_end = ALIGN_DOWN(free_region_end, + PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE); + + if (end != region_end && + free_region_end > region_end) + region_end += PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE; + + shadow_start = kasan_mem_to_shadow((void *)region_start); + shadow_end = kasan_mem_to_shadow((void *)region_end); + + if (shadow_end > shadow_start) { + apply_to_page_range(&init_mm, (unsigned long)shadow_start, + (unsigned long)(shadow_end - shadow_start), + kasan_depopulate_vmalloc_pte, NULL); + flush_tlb_kernel_range((unsigned long)shadow_start, + (unsigned long)shadow_end); + } +} +#endif diff --git a/mm/kasan/generic_report.c b/mm/kasan/generic_report.c index 36c645939bc9..2d97efd4954f 100644 --- a/mm/kasan/generic_report.c +++ b/mm/kasan/generic_report.c @@ -86,6 +86,9 @@ static const char *get_shadow_bug_type(struct kasan_access_info *info) case KASAN_ALLOCA_RIGHT: bug_type = "alloca-out-of-bounds"; break; + case KASAN_VMALLOC_INVALID: + bug_type = "vmalloc-out-of-bounds"; + break; } return bug_type; diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index 35cff6bbb716..3a083274628e 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -25,6 +25,7 @@ #endif #define KASAN_GLOBAL_REDZONE 0xFA /* redzone for global variable */ +#define KASAN_VMALLOC_INVALID 0xF9 /* unallocated space in vmapped page */ /* * Stack redzone shadow values diff --git a/mm/vmalloc.c b/mm/vmalloc.c index f48f64c8d200..72d0aa039e68 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -683,7 +683,7 @@ insert_vmap_area_augment(struct vmap_area *va, * free area is inserted. If VA has been merged, it is * freed. */ -static __always_inline void +static __always_inline struct vmap_area * merge_or_add_vmap_area(struct vmap_area *va, struct rb_root *root, struct list_head *head) { @@ -750,7 +750,10 @@ merge_or_add_vmap_area(struct vmap_area *va, /* Free vmap_area object. */ kmem_cache_free(vmap_area_cachep, va); - return; + + /* Point to the new merged area. */ + va = sibling; + merged = true; } } @@ -759,6 +762,8 @@ merge_or_add_vmap_area(struct vmap_area *va, link_va(va, root, parent, link, head); augment_tree_propagate_from(va); } + + return va; } static __always_inline bool @@ -1196,8 +1201,7 @@ static void free_vmap_area(struct vmap_area *va) * Insert/Merge it back to the free tree/list. */ spin_lock(&free_vmap_area_lock); - merge_or_add_vmap_area(va, - &free_vmap_area_root, &free_vmap_area_list); + merge_or_add_vmap_area(va, &free_vmap_area_root, &free_vmap_area_list); spin_unlock(&free_vmap_area_lock); } @@ -1294,14 +1298,20 @@ static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end) spin_lock(&free_vmap_area_lock); llist_for_each_entry_safe(va, n_va, valist, purge_list) { unsigned long nr = (va->va_end - va->va_start) >> PAGE_SHIFT; + unsigned long orig_start = va->va_start; + unsigned long orig_end = va->va_end; /* * Finally insert or merge lazily-freed area. It is * detached and there is no need to "unlink" it from * anything. */ - merge_or_add_vmap_area(va, - &free_vmap_area_root, &free_vmap_area_list); + va = merge_or_add_vmap_area(va, &free_vmap_area_root, + &free_vmap_area_list); + + if (is_vmalloc_or_module_addr((void *)orig_start)) + kasan_release_vmalloc(orig_start, orig_end, + va->va_start, va->va_end); atomic_long_sub(nr, &vmap_lazy_nr); @@ -2090,6 +2100,22 @@ static struct vm_struct *__get_vm_area_node(unsigned long size, setup_vmalloc_vm(area, va, flags, caller); + /* + * For KASAN, if we are in vmalloc space, we need to cover the shadow + * area with real memory. If we come here through VM_ALLOC, this is + * done by a higher level function that has access to the true size, + * which might not be a full page. + * + * We assume module space comes via VM_ALLOC path. + */ + if (is_vmalloc_addr(area->addr) && !(area->flags & VM_ALLOC)) { + if (kasan_populate_vmalloc(area->size, area)) { + unmap_vmap_area(va); + kfree(area); + return NULL; + } + } + return area; } @@ -2267,6 +2293,9 @@ static void __vunmap(const void *addr, int deallocate_pages) debug_check_no_locks_freed(area->addr, get_vm_area_size(area)); debug_check_no_obj_freed(area->addr, get_vm_area_size(area)); + if (area->flags & VM_KASAN) + kasan_poison_vmalloc(area->addr, area->size); + vm_remove_mappings(area, deallocate_pages); if (deallocate_pages) { @@ -2519,6 +2548,11 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align, if (!addr) return NULL; + if (is_vmalloc_or_module_addr(area->addr)) { + if (kasan_populate_vmalloc(real_size, area)) + return NULL; + } + /* * In this function, newly allocated vm_struct has VM_UNINITIALIZED * flag. It means that vm_struct is not fully initialized. @@ -3377,6 +3411,9 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, setup_vmalloc_vm_locked(vms[area], vas[area], VM_ALLOC, pcpu_get_vm_areas); + + /* assume success here */ + kasan_populate_vmalloc(sizes[area], vms[area]); } spin_unlock(&vmap_area_lock); @@ -3391,8 +3428,8 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, * and when pcpu_get_vm_areas() is success. */ while (area--) { - merge_or_add_vmap_area(vas[area], - &free_vmap_area_root, &free_vmap_area_list); + merge_or_add_vmap_area(vas[area], &free_vmap_area_root, + &free_vmap_area_list); vas[area] = NULL; }
Hook into vmalloc and vmap, and dynamically allocate real shadow memory to back the mappings. Most mappings in vmalloc space are small, requiring less than a full page of shadow space. Allocating a full shadow page per mapping would therefore be wasteful. Furthermore, to ensure that different mappings use different shadow pages, mappings would have to be aligned to KASAN_SHADOW_SCALE_SIZE * PAGE_SIZE. Instead, share backing space across multiple mappings. Allocate a backing page when a mapping in vmalloc space uses a particular page of the shadow region. This page can be shared by other vmalloc mappings later on. We hook in to the vmap infrastructure to lazily clean up unused shadow memory. To avoid the difficulties around swapping mappings around, this code expects that the part of the shadow region that covers the vmalloc space will not be covered by the early shadow page, but will be left unmapped. This will require changes in arch-specific code. This allows KASAN with VMAP_STACK, and may be helpful for architectures that do not have a separate module space (e.g. powerpc64, which I am currently working on). It also allows relaxing the module alignment back to PAGE_SIZE. Testing with test_vmalloc.sh on an x86 VM with 2 vCPUs shows that: - Turning on KASAN, inline instrumentation, without vmalloc, introuduces a 4.1x-4.2x slowdown in vmalloc operations. - Turning this on introduces the following slowdowns over KASAN: * ~1.76x slower single-threaded (test_vmalloc.sh performance) * ~2.18x slower when both cpus are performing operations simultaneously (test_vmalloc.sh sequential_test_order=1) This is unfortunate but given that this is a debug feature only, not the end of the world. Link: https://bugzilla.kernel.org/show_bug.cgi?id=202009 Acked-by: Vasily Gorbik <gor@linux.ibm.com> Reviewed-by: Andrey Ryabinin <aryabinin@virtuozzo.com> Co-developed-by: Mark Rutland <mark.rutland@arm.com> Signed-off-by: Mark Rutland <mark.rutland@arm.com> [shadow rework] Signed-off-by: Daniel Axtens <dja@axtens.net> -- v2: let kasan_unpoison_shadow deal with ranges that do not use a full shadow byte. v3: relax module alignment rename to kasan_populate_vmalloc which is a much better name deal with concurrency correctly v4: Mark's rework Poision pages on vfree Handle allocation failures v5: Per Christophe Leroy, split out test and dynamically free pages. v6: Guard freeing page properly. Drop WARN_ON_ONCE(pte_none(*ptep)), on reflection it's unnecessary debugging cruft with too high a false positive rate. v7: tlb flush, thanks Mark. explain more clearly how freeing works and is concurrency-safe. v9: - Pull in Uladzislau Rezki's changes to better line up with the design of the new vmalloc implementation. Thanks Vlad. - clarify comment explaining smp_wmb() per Mark and Andrey's discussion - tighten up the allocation of backing memory so that it only happens for vmalloc or module space allocations. Thanks Andrey Ryabinin. - A TLB flush in the freeing path, thanks Mark Rutland. v10: - rebase on next, pulling in Vlad's new work on splitting the vmalloc locks. This doesn't require changes in our behaviour but does require rechecking and rewording the explanation of why our behaviour is safe. - after much discussion of barriers, I now document where I think they are needed and why. Thanks Mark and Andrey. - clean up some TLB flushing. We were doing it twice - once after each page and once at the end of the whole process. Only do it at the end of the whole depopulate process. - checkpatch cleanups v11: Nit from Andrey, tighten up release to vmalloc/module space, thanks Vlad. Add benchmark results. The full benchmark results are: Performance No KASAN KASAN original x baseline KASAN vmalloc x baseline x KASAN fix_size_alloc_test 1697913 14229459 8.38 22981983 13.54 1.62 full_fit_alloc_test 1841601 15152633 8.23 17902922 9.72 1.18 long_busy_list_alloc_test 17874082 58856758 3.29 103925371 5.81 1.77 random_size_alloc_test 9356047 29544085 3.16 57871338 6.19 1.96 fix_align_alloc_test 3188968 19821620 6.22 37979436 11.91 1.92 random_size_align_alloc_te 3033507 17584339 5.80 32588942 10.74 1.85 align_shift_alloc_test 325 1154 3.55 7263 22.35 6.29 pcpu_alloc_test 231952 278181 1.20 318977 1.38 1.15 Total Cycles 235852824254 985040965542 4.18 1733258779416 7.35 1.76 Sequential, 2 cpus No KASAN KASAN original x baseline KASAN vmalloc x baseline x KASAN fix_size_alloc_test 2505806 17989253 7.18 39651038 15.82 2.20 full_fit_alloc_test 3579676 18829862 5.26 21142645 5.91 1.12 long_busy_list_alloc_test 21594983 74766736 3.46 140701363 6.52 1.88 random_size_alloc_test 10884695 34282077 3.15 91945108 8.45 2.68 fix_align_alloc_test 4133226 26304745 6.36 76163270 18.43 2.90 random_size_align_alloc_te 4261175 22927883 5.38 55236058 12.96 2.41 align_shift_alloc_test 948 4827 5.09 4144 4.37 0.86 pcpu_alloc_test 371789 307654 0.83 374412 1.01 1.22 Total Cycles 99965417402 412710461642 4.13 897968646378 8.98 2.18 fix_size_alloc_test 2502718 17921542 7.16 39893515 15.94 2.23 full_fit_alloc_test 3547996 18675007 5.26 21330495 6.01 1.14 long_busy_list_alloc_test 21522579 74610739 3.47 139822907 6.50 1.87 random_size_alloc_test 10881507 34317349 3.15 91110531 8.37 2.65 fix_align_alloc_test 4119755 26180887 6.35 75818927 18.40 2.90 random_size_align_alloc_te 4297708 23058344 5.37 55969004 13.02 2.43 align_shift_alloc_test 956 5574 5.83 4591 4.80 0.82 pcpu_alloc_test 306340 347014 1.13 571289 1.86 1.65 Total Cycles 99642832084 412084074628 4.14 896497227762 9.00 2.18 --- Documentation/dev-tools/kasan.rst | 63 ++++++++ include/linux/kasan.h | 31 ++++ include/linux/moduleloader.h | 2 +- include/linux/vmalloc.h | 12 ++ lib/Kconfig.kasan | 16 +++ mm/kasan/common.c | 231 ++++++++++++++++++++++++++++++ mm/kasan/generic_report.c | 3 + mm/kasan/kasan.h | 1 + mm/vmalloc.c | 53 +++++-- 9 files changed, 403 insertions(+), 9 deletions(-)