| Message ID | 20210324230759.2213957-1-minchan@kernel.org (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | [v8] mm: cma: support sysfs | expand |
On Thu, 25 Mar 2021 at 00:09, Minchan Kim <minchan@kernel.org> wrote: > > Since CMA is getting used more widely, it's more important to > keep monitoring CMA statistics for system health since it's > directly related to user experience. > > This patch introduces sysfs statistics for CMA, in order to provide > some basic monitoring of the CMA allocator. > > * the number of CMA page successful allocations > * the number of CMA page allocation failures > > These two values allow the user to calcuate the allocation > failure rate for each CMA area. > > e.g.) > /sys/kernel/mm/cma/WIFI/alloc_pages_[success|fail] > /sys/kernel/mm/cma/SENSOR/alloc_pages_[success|fail] > /sys/kernel/mm/cma/BLUETOOTH/alloc_pages_[success|fail] > > The cma_stat was intentionally allocated by dynamic allocation > to harmonize with kobject lifetime management. > https://lore.kernel.org/linux-mm/YCOAmXqt6dZkCQYs@kroah.com/ > > Tested-by: Dmitry Osipenko <digetx@gmail.com> > Reviewed-by: Dmitry Osipenko <digetx@gmail.com> > Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> > Reviewed-by: John Hubbard <jhubbard@nvidia.com> > Link: https://lore.kernel.org/linux-mm/20210316100433.17665-1-colin.king@canonical.com/ > Addresses-Coverity: ("Dereference after null check") > Signed-off-by: Colin Ian King <colin.king@canonical.com> > Signed-off-by: Minchan Kim <minchan@kernel.org> When I build an arm64 kernel (allmodconfig - boot selftest) on today's next tag: next-20210326, I see this issue when I'm booting in qemu. [ 0.985891][ T9] Callback from call_rcu_tasks() invoked. [ 1.008860][ T1] smp: Bringing up secondary CPUs ... [ 1.012655][ T1] smp: Brought up 1 node, 1 CPU [ 1.015194][ T1] SMP: Total of 1 processors activated. [ 1.018987][ T1] CPU features: detected: 32-bit EL0 Support [ 1.021995][ T1] CPU features: detected: CRC32 instructions [ 1.026047][ T1] CPU features: detected: 32-bit EL1 Support [ 1.033728][ T1] CPU features: emulated: Privileged Access Never (PAN) using TTBR0_EL1 switching [ 2.140828][ T1] CPU: All CPU(s) started at EL1 [ 2.144773][ T17] alternatives: patching kernel code [ 132.866390][ C0] watchdog: BUG: soft lockup - CPU#0 stuck for 25s! [pgdatinit0:20] [ 132.870865][ C0] Modules linked in: [ 132.873037][ C0] irq event stamp: 739758 [ 132.875308][ C0] hardirqs last enabled at (739757): [<ffff8000126fb3d0>] _raw_spin_unlock_irqrestore+0x90/0x100 [ 132.880740][ C0] hardirqs last disabled at (739758): [<ffff8000126e30a4>] enter_el1_irq_or_nmi+0xa4/0xc0 [ 132.885801][ C0] softirqs last enabled at (739056): [<ffff800010010f98>] __do_softirq+0x8b8/0x9ac [ 132.890571][ C0] softirqs last disabled at (739051): [<ffff80001013742c>] __irq_exit_rcu+0x1ac/0x240 [ 132.895560][ C0] CPU: 0 PID: 20 Comm: pgdatinit0 Not tainted 5.12.0-rc4-next-20210326-00008-g23921ff47279 #1 [ 132.900759][ C0] Hardware name: linux,dummy-virt (DT) [ 132.903637][ C0] pstate: 40400005 (nZcv daif +PAN -UAO -TCO BTYPE=--) [ 132.907212][ C0] pc : _raw_spin_unlock_irqrestore+0xa4/0x100 [ 132.910432][ C0] lr : _raw_spin_unlock_irqrestore+0x90/0x100 [ 132.913647][ C0] sp : ffff000007b9f640 [ 132.915832][ C0] x29: ffff000007b9f640 x28: ffff800016954518 [ 132.919237][ C0] x27: 000000000000000e x26: dead000000000100 [ 132.922689][ C0] x25: dead000000000122 x24: 00000000000559b0 [ 132.926098][ C0] x23: ffff80001550e000 x22: ffff800016954530 [ 132.929479][ C0] x21: ffff800016954518 x20: 0000000000000000 [ 132.932901][ C0] x19: ffff800010f662f4 x18: 0000000000001530 [ 132.936312][ C0] x17: 0000000000001470 x16: 0000000000005518 [ 132.939723][ C0] x15: 0000000000001578 x14: ffff800010189520 [ 132.943107][ C0] x13: ffff8000107592e0 x12: ffff600000f73eb1 [ 132.946520][ C0] x11: 1fffe00000f73eb0 x10: ffff600000f73eb0 [ 132.949914][ C0] x9 : dfff800000000000 x8 : ffff000007b9f587 [ 132.953312][ C0] x7 : 0000000000000001 x6 : 00009fffff08c150 [ 132.956713][ C0] x5 : 0000000000000000 x4 : 0000000000000000 [ 132.960117][ C0] x3 : ffff000007b90040 x2 : 000000000005e6fd [ 132.963521][ C0] x1 : 00000000000000c0 x0 : 0000000000000080 [ 132.966889][ C0] Call trace: [ 132.968667][ C0] _raw_spin_unlock_irqrestore+0xa4/0x100 [ 132.971754][ C0] __debug_check_no_obj_freed+0x1d4/0x2a0 [ 132.974890][ C0] debug_check_no_obj_freed+0x20/0x80 [ 132.977813][ C0] __free_pages_ok+0x5a0/0x740 [ 132.980384][ C0] __free_pages_core+0x24c/0x280 [ 132.983091][ C0] deferred_free_range+0x6c/0xbc [ 132.985826][ C0] deferred_init_maxorder+0x2d0/0x350 [ 132.988735][ C0] deferred_init_memmap_chunk+0xc8/0x124 [ 132.991784][ C0] padata_do_multithreaded+0x15c/0x578 [ 132.994723][ C0] deferred_init_memmap+0x26c/0x364 [ 132.997560][ C0] kthread+0x23c/0x260 [ 132.999851][ C0] ret_from_fork+0x10/0x18 [ 133.002324][ C0] Kernel panic - not syncing: softlockup: hung tasks [ 133.005767][ C0] CPU: 0 PID: 20 Comm: pgdatinit0 Tainted: G L 5.12.0-rc4-next-20210326-00008-g23921ff47279 #1 [ 133.011613][ C0] Hardware name: linux,dummy-virt (DT) [ 133.014435][ C0] Call trace: [ 133.016143][ C0] dump_backtrace+0x0/0x420 [ 133.018617][ C0] show_stack+0x38/0x60 [ 133.020882][ C0] dump_stack+0x1fc/0x2c8 [ 133.023343][ C0] panic+0x304/0x5d8 [ 133.025567][ C0] watchdog_timer_fn+0x4ac/0x500 [ 133.028209][ C0] __run_hrtimer+0x770/0xba0 [ 133.030734][ C0] __hrtimer_run_queues+0x1a0/0x220 [ 133.033537][ C0] hrtimer_run_queues+0x20c/0x240 [ 133.036202][ C0] update_process_times+0xbc/0x1a0 [ 133.038997][ C0] tick_periodic+0x27c/0x2c0 [ 133.041510][ C0] tick_handle_periodic+0x44/0x120 [ 133.044267][ C0] arch_timer_handler_virt+0x68/0xa0 [ 133.047226][ C0] handle_percpu_devid_irq+0x118/0x2a0 [ 133.050229][ C0] __handle_domain_irq+0x150/0x1c0 [ 133.052959][ C0] gic_handle_irq+0x130/0x180 [ 133.055505][ C0] el1_irq+0xc0/0x15c [ 133.057723][ C0] _raw_spin_unlock_irqrestore+0xa4/0x100 [ 133.060792][ C0] __debug_check_no_obj_freed+0x1d4/0x2a0 [ 133.063869][ C0] debug_check_no_obj_freed+0x20/0x80 [ 133.066813][ C0] __free_pages_ok+0x5a0/0x740 [ 133.069409][ C0] __free_pages_core+0x24c/0x280 [ 133.072127][ C0] deferred_free_range+0x6c/0xbc [ 133.074847][ C0] deferred_init_maxorder+0x2d0/0x350 [ 133.077803][ C0] deferred_init_memmap_chunk+0xc8/0x124 [ 133.080834][ C0] padata_do_multithreaded+0x15c/0x578 [ 133.083791][ C0] deferred_init_memmap+0x26c/0x364 [ 133.086614][ C0] kthread+0x23c/0x260 [ 133.088879][ C0] ret_from_fork+0x10/0x18 [ 133.092092][ C0] ---[ end Kernel panic - not syncing: softlockup: hung tasks ]--- Full log [1], and my .config [2]. I bisected down to patch 799815f497e2 ("mm: cma: support sysfs"). When I revert 799815f497e2 ("mm: cma: support sysfs") 7af97692f30d ("mm: cma: fix potential null dereference on pointer cma") The kernel boots fine. Any idea whats happening? Cheers, Anders [1] http://ix.io/2U9S [2] http://ix.io/2Ua3
On Fri, Mar 26, 2021 at 02:59:30PM +0100, Anders Roxell wrote: > On Thu, 25 Mar 2021 at 00:09, Minchan Kim <minchan@kernel.org> wrote: > > > > Since CMA is getting used more widely, it's more important to > > keep monitoring CMA statistics for system health since it's > > directly related to user experience. > > > > This patch introduces sysfs statistics for CMA, in order to provide > > some basic monitoring of the CMA allocator. > > > > * the number of CMA page successful allocations > > * the number of CMA page allocation failures > > > > These two values allow the user to calcuate the allocation > > failure rate for each CMA area. > > > > e.g.) > > /sys/kernel/mm/cma/WIFI/alloc_pages_[success|fail] > > /sys/kernel/mm/cma/SENSOR/alloc_pages_[success|fail] > > /sys/kernel/mm/cma/BLUETOOTH/alloc_pages_[success|fail] > > > > The cma_stat was intentionally allocated by dynamic allocation > > to harmonize with kobject lifetime management. > > https://lore.kernel.org/linux-mm/YCOAmXqt6dZkCQYs@kroah.com/ > > > > Tested-by: Dmitry Osipenko <digetx@gmail.com> > > Reviewed-by: Dmitry Osipenko <digetx@gmail.com> > > Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> > > Reviewed-by: John Hubbard <jhubbard@nvidia.com> > > Link: https://lore.kernel.org/linux-mm/20210316100433.17665-1-colin.king@canonical.com/ > > Addresses-Coverity: ("Dereference after null check") > > Signed-off-by: Colin Ian King <colin.king@canonical.com> > > Signed-off-by: Minchan Kim <minchan@kernel.org> > > When I build an arm64 kernel (allmodconfig - boot selftest) on today's > next tag: next-20210326, I see this issue when I'm booting in qemu. > > [ 0.985891][ T9] Callback from call_rcu_tasks() invoked. > [ 1.008860][ T1] smp: Bringing up secondary CPUs ... > [ 1.012655][ T1] smp: Brought up 1 node, 1 CPU > [ 1.015194][ T1] SMP: Total of 1 processors activated. > [ 1.018987][ T1] CPU features: detected: 32-bit EL0 Support > [ 1.021995][ T1] CPU features: detected: CRC32 instructions > [ 1.026047][ T1] CPU features: detected: 32-bit EL1 Support > [ 1.033728][ T1] CPU features: emulated: Privileged Access Never > (PAN) using TTBR0_EL1 switching > [ 2.140828][ T1] CPU: All CPU(s) started at EL1 > [ 2.144773][ T17] alternatives: patching kernel code > [ 132.866390][ C0] watchdog: BUG: soft lockup - CPU#0 stuck for > 25s! [pgdatinit0:20] > [ 132.870865][ C0] Modules linked in: > [ 132.873037][ C0] irq event stamp: 739758 > [ 132.875308][ C0] hardirqs last enabled at (739757): > [<ffff8000126fb3d0>] _raw_spin_unlock_irqrestore+0x90/0x100 > [ 132.880740][ C0] hardirqs last disabled at (739758): > [<ffff8000126e30a4>] enter_el1_irq_or_nmi+0xa4/0xc0 > [ 132.885801][ C0] softirqs last enabled at (739056): > [<ffff800010010f98>] __do_softirq+0x8b8/0x9ac > [ 132.890571][ C0] softirqs last disabled at (739051): > [<ffff80001013742c>] __irq_exit_rcu+0x1ac/0x240 > [ 132.895560][ C0] CPU: 0 PID: 20 Comm: pgdatinit0 Not tainted > 5.12.0-rc4-next-20210326-00008-g23921ff47279 #1 > [ 132.900759][ C0] Hardware name: linux,dummy-virt (DT) > [ 132.903637][ C0] pstate: 40400005 (nZcv daif +PAN -UAO -TCO BTYPE=--) > [ 132.907212][ C0] pc : _raw_spin_unlock_irqrestore+0xa4/0x100 > [ 132.910432][ C0] lr : _raw_spin_unlock_irqrestore+0x90/0x100 > [ 132.913647][ C0] sp : ffff000007b9f640 > [ 132.915832][ C0] x29: ffff000007b9f640 x28: ffff800016954518 > [ 132.919237][ C0] x27: 000000000000000e x26: dead000000000100 > [ 132.922689][ C0] x25: dead000000000122 x24: 00000000000559b0 > [ 132.926098][ C0] x23: ffff80001550e000 x22: ffff800016954530 > [ 132.929479][ C0] x21: ffff800016954518 x20: 0000000000000000 > [ 132.932901][ C0] x19: ffff800010f662f4 x18: 0000000000001530 > [ 132.936312][ C0] x17: 0000000000001470 x16: 0000000000005518 > [ 132.939723][ C0] x15: 0000000000001578 x14: ffff800010189520 > [ 132.943107][ C0] x13: ffff8000107592e0 x12: ffff600000f73eb1 > [ 132.946520][ C0] x11: 1fffe00000f73eb0 x10: ffff600000f73eb0 > [ 132.949914][ C0] x9 : dfff800000000000 x8 : ffff000007b9f587 > [ 132.953312][ C0] x7 : 0000000000000001 x6 : 00009fffff08c150 > [ 132.956713][ C0] x5 : 0000000000000000 x4 : 0000000000000000 > [ 132.960117][ C0] x3 : ffff000007b90040 x2 : 000000000005e6fd > [ 132.963521][ C0] x1 : 00000000000000c0 x0 : 0000000000000080 > [ 132.966889][ C0] Call trace: > [ 132.968667][ C0] _raw_spin_unlock_irqrestore+0xa4/0x100 > [ 132.971754][ C0] __debug_check_no_obj_freed+0x1d4/0x2a0 > [ 132.974890][ C0] debug_check_no_obj_freed+0x20/0x80 > [ 132.977813][ C0] __free_pages_ok+0x5a0/0x740 > [ 132.980384][ C0] __free_pages_core+0x24c/0x280 > [ 132.983091][ C0] deferred_free_range+0x6c/0xbc > [ 132.985826][ C0] deferred_init_maxorder+0x2d0/0x350 > [ 132.988735][ C0] deferred_init_memmap_chunk+0xc8/0x124 > [ 132.991784][ C0] padata_do_multithreaded+0x15c/0x578 > [ 132.994723][ C0] deferred_init_memmap+0x26c/0x364 > [ 132.997560][ C0] kthread+0x23c/0x260 > [ 132.999851][ C0] ret_from_fork+0x10/0x18 > [ 133.002324][ C0] Kernel panic - not syncing: softlockup: hung tasks > [ 133.005767][ C0] CPU: 0 PID: 20 Comm: pgdatinit0 Tainted: G > L 5.12.0-rc4-next-20210326-00008-g23921ff47279 #1 > [ 133.011613][ C0] Hardware name: linux,dummy-virt (DT) > [ 133.014435][ C0] Call trace: > [ 133.016143][ C0] dump_backtrace+0x0/0x420 > [ 133.018617][ C0] show_stack+0x38/0x60 > [ 133.020882][ C0] dump_stack+0x1fc/0x2c8 > [ 133.023343][ C0] panic+0x304/0x5d8 > [ 133.025567][ C0] watchdog_timer_fn+0x4ac/0x500 > [ 133.028209][ C0] __run_hrtimer+0x770/0xba0 > [ 133.030734][ C0] __hrtimer_run_queues+0x1a0/0x220 > [ 133.033537][ C0] hrtimer_run_queues+0x20c/0x240 > [ 133.036202][ C0] update_process_times+0xbc/0x1a0 > [ 133.038997][ C0] tick_periodic+0x27c/0x2c0 > [ 133.041510][ C0] tick_handle_periodic+0x44/0x120 > [ 133.044267][ C0] arch_timer_handler_virt+0x68/0xa0 > [ 133.047226][ C0] handle_percpu_devid_irq+0x118/0x2a0 > [ 133.050229][ C0] __handle_domain_irq+0x150/0x1c0 > [ 133.052959][ C0] gic_handle_irq+0x130/0x180 > [ 133.055505][ C0] el1_irq+0xc0/0x15c > [ 133.057723][ C0] _raw_spin_unlock_irqrestore+0xa4/0x100 > [ 133.060792][ C0] __debug_check_no_obj_freed+0x1d4/0x2a0 > [ 133.063869][ C0] debug_check_no_obj_freed+0x20/0x80 > [ 133.066813][ C0] __free_pages_ok+0x5a0/0x740 > [ 133.069409][ C0] __free_pages_core+0x24c/0x280 > [ 133.072127][ C0] deferred_free_range+0x6c/0xbc > [ 133.074847][ C0] deferred_init_maxorder+0x2d0/0x350 > [ 133.077803][ C0] deferred_init_memmap_chunk+0xc8/0x124 > [ 133.080834][ C0] padata_do_multithreaded+0x15c/0x578 > [ 133.083791][ C0] deferred_init_memmap+0x26c/0x364 > [ 133.086614][ C0] kthread+0x23c/0x260 > [ 133.088879][ C0] ret_from_fork+0x10/0x18 > [ 133.092092][ C0] ---[ end Kernel panic - not syncing: > softlockup: hung tasks ]--- > > Full log [1], and my .config [2]. > > I bisected down to patch 799815f497e2 ("mm: cma: support sysfs"). > > When I revert > 799815f497e2 ("mm: cma: support sysfs") > 7af97692f30d ("mm: cma: fix potential null dereference on pointer cma") > > The kernel boots fine. > > Any idea whats happening? Hi Anders, Dmitry reported the crash(However, your callstack is not the same and didn't show any CMA stuffs so I am not sure it's same crash) and posted the fix. https://lore.kernel.org/linux-mm/20210324192044.1505747-1-minchan@kernel.org/ However, in the end, it was folded into original patchset to replace it. That is an this v8 patch. So, could you try it? 1. revert 7af97692f30d ("mm: cma: fix potential null dereference on pointer cma") 2. revert 799815f497e2 ("mm: cma: support sysfs") 3. apply this v8 patch. Thank you. > > Cheers, > Anders > [1] http://ix.io/2U9S > [2] http://ix.io/2Ua3
On Fri, 26 Mar 2021 at 16:51, Minchan Kim <minchan@kernel.org> wrote: > > On Fri, Mar 26, 2021 at 02:59:30PM +0100, Anders Roxell wrote: > > On Thu, 25 Mar 2021 at 00:09, Minchan Kim <minchan@kernel.org> wrote: > > > > > > Since CMA is getting used more widely, it's more important to > > > keep monitoring CMA statistics for system health since it's > > > directly related to user experience. > > > > > > This patch introduces sysfs statistics for CMA, in order to provide > > > some basic monitoring of the CMA allocator. > > > > > > * the number of CMA page successful allocations > > > * the number of CMA page allocation failures > > > > > > These two values allow the user to calcuate the allocation > > > failure rate for each CMA area. > > > > > > e.g.) > > > /sys/kernel/mm/cma/WIFI/alloc_pages_[success|fail] > > > /sys/kernel/mm/cma/SENSOR/alloc_pages_[success|fail] > > > /sys/kernel/mm/cma/BLUETOOTH/alloc_pages_[success|fail] > > > > > > The cma_stat was intentionally allocated by dynamic allocation > > > to harmonize with kobject lifetime management. > > > https://lore.kernel.org/linux-mm/YCOAmXqt6dZkCQYs@kroah.com/ > > > > > > Tested-by: Dmitry Osipenko <digetx@gmail.com> > > > Reviewed-by: Dmitry Osipenko <digetx@gmail.com> > > > Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> > > > Reviewed-by: John Hubbard <jhubbard@nvidia.com> > > > Link: https://lore.kernel.org/linux-mm/20210316100433.17665-1-colin.king@canonical.com/ > > > Addresses-Coverity: ("Dereference after null check") > > > Signed-off-by: Colin Ian King <colin.king@canonical.com> > > > Signed-off-by: Minchan Kim <minchan@kernel.org> > > > > When I build an arm64 kernel (allmodconfig - boot selftest) on today's > > next tag: next-20210326, I see this issue when I'm booting in qemu. > > > > [ 0.985891][ T9] Callback from call_rcu_tasks() invoked. > > [ 1.008860][ T1] smp: Bringing up secondary CPUs ... > > [ 1.012655][ T1] smp: Brought up 1 node, 1 CPU > > [ 1.015194][ T1] SMP: Total of 1 processors activated. > > [ 1.018987][ T1] CPU features: detected: 32-bit EL0 Support > > [ 1.021995][ T1] CPU features: detected: CRC32 instructions > > [ 1.026047][ T1] CPU features: detected: 32-bit EL1 Support > > [ 1.033728][ T1] CPU features: emulated: Privileged Access Never > > (PAN) using TTBR0_EL1 switching > > [ 2.140828][ T1] CPU: All CPU(s) started at EL1 > > [ 2.144773][ T17] alternatives: patching kernel code > > [ 132.866390][ C0] watchdog: BUG: soft lockup - CPU#0 stuck for > > 25s! [pgdatinit0:20] > > [ 132.870865][ C0] Modules linked in: > > [ 132.873037][ C0] irq event stamp: 739758 > > [ 132.875308][ C0] hardirqs last enabled at (739757): > > [<ffff8000126fb3d0>] _raw_spin_unlock_irqrestore+0x90/0x100 > > [ 132.880740][ C0] hardirqs last disabled at (739758): > > [<ffff8000126e30a4>] enter_el1_irq_or_nmi+0xa4/0xc0 > > [ 132.885801][ C0] softirqs last enabled at (739056): > > [<ffff800010010f98>] __do_softirq+0x8b8/0x9ac > > [ 132.890571][ C0] softirqs last disabled at (739051): > > [<ffff80001013742c>] __irq_exit_rcu+0x1ac/0x240 > > [ 132.895560][ C0] CPU: 0 PID: 20 Comm: pgdatinit0 Not tainted > > 5.12.0-rc4-next-20210326-00008-g23921ff47279 #1 > > [ 132.900759][ C0] Hardware name: linux,dummy-virt (DT) > > [ 132.903637][ C0] pstate: 40400005 (nZcv daif +PAN -UAO -TCO BTYPE=--) > > [ 132.907212][ C0] pc : _raw_spin_unlock_irqrestore+0xa4/0x100 > > [ 132.910432][ C0] lr : _raw_spin_unlock_irqrestore+0x90/0x100 > > [ 132.913647][ C0] sp : ffff000007b9f640 > > [ 132.915832][ C0] x29: ffff000007b9f640 x28: ffff800016954518 > > [ 132.919237][ C0] x27: 000000000000000e x26: dead000000000100 > > [ 132.922689][ C0] x25: dead000000000122 x24: 00000000000559b0 > > [ 132.926098][ C0] x23: ffff80001550e000 x22: ffff800016954530 > > [ 132.929479][ C0] x21: ffff800016954518 x20: 0000000000000000 > > [ 132.932901][ C0] x19: ffff800010f662f4 x18: 0000000000001530 > > [ 132.936312][ C0] x17: 0000000000001470 x16: 0000000000005518 > > [ 132.939723][ C0] x15: 0000000000001578 x14: ffff800010189520 > > [ 132.943107][ C0] x13: ffff8000107592e0 x12: ffff600000f73eb1 > > [ 132.946520][ C0] x11: 1fffe00000f73eb0 x10: ffff600000f73eb0 > > [ 132.949914][ C0] x9 : dfff800000000000 x8 : ffff000007b9f587 > > [ 132.953312][ C0] x7 : 0000000000000001 x6 : 00009fffff08c150 > > [ 132.956713][ C0] x5 : 0000000000000000 x4 : 0000000000000000 > > [ 132.960117][ C0] x3 : ffff000007b90040 x2 : 000000000005e6fd > > [ 132.963521][ C0] x1 : 00000000000000c0 x0 : 0000000000000080 > > [ 132.966889][ C0] Call trace: > > [ 132.968667][ C0] _raw_spin_unlock_irqrestore+0xa4/0x100 > > [ 132.971754][ C0] __debug_check_no_obj_freed+0x1d4/0x2a0 > > [ 132.974890][ C0] debug_check_no_obj_freed+0x20/0x80 > > [ 132.977813][ C0] __free_pages_ok+0x5a0/0x740 > > [ 132.980384][ C0] __free_pages_core+0x24c/0x280 > > [ 132.983091][ C0] deferred_free_range+0x6c/0xbc > > [ 132.985826][ C0] deferred_init_maxorder+0x2d0/0x350 > > [ 132.988735][ C0] deferred_init_memmap_chunk+0xc8/0x124 > > [ 132.991784][ C0] padata_do_multithreaded+0x15c/0x578 > > [ 132.994723][ C0] deferred_init_memmap+0x26c/0x364 > > [ 132.997560][ C0] kthread+0x23c/0x260 > > [ 132.999851][ C0] ret_from_fork+0x10/0x18 > > [ 133.002324][ C0] Kernel panic - not syncing: softlockup: hung tasks > > [ 133.005767][ C0] CPU: 0 PID: 20 Comm: pgdatinit0 Tainted: G > > L 5.12.0-rc4-next-20210326-00008-g23921ff47279 #1 > > [ 133.011613][ C0] Hardware name: linux,dummy-virt (DT) > > [ 133.014435][ C0] Call trace: > > [ 133.016143][ C0] dump_backtrace+0x0/0x420 > > [ 133.018617][ C0] show_stack+0x38/0x60 > > [ 133.020882][ C0] dump_stack+0x1fc/0x2c8 > > [ 133.023343][ C0] panic+0x304/0x5d8 > > [ 133.025567][ C0] watchdog_timer_fn+0x4ac/0x500 > > [ 133.028209][ C0] __run_hrtimer+0x770/0xba0 > > [ 133.030734][ C0] __hrtimer_run_queues+0x1a0/0x220 > > [ 133.033537][ C0] hrtimer_run_queues+0x20c/0x240 > > [ 133.036202][ C0] update_process_times+0xbc/0x1a0 > > [ 133.038997][ C0] tick_periodic+0x27c/0x2c0 > > [ 133.041510][ C0] tick_handle_periodic+0x44/0x120 > > [ 133.044267][ C0] arch_timer_handler_virt+0x68/0xa0 > > [ 133.047226][ C0] handle_percpu_devid_irq+0x118/0x2a0 > > [ 133.050229][ C0] __handle_domain_irq+0x150/0x1c0 > > [ 133.052959][ C0] gic_handle_irq+0x130/0x180 > > [ 133.055505][ C0] el1_irq+0xc0/0x15c > > [ 133.057723][ C0] _raw_spin_unlock_irqrestore+0xa4/0x100 > > [ 133.060792][ C0] __debug_check_no_obj_freed+0x1d4/0x2a0 > > [ 133.063869][ C0] debug_check_no_obj_freed+0x20/0x80 > > [ 133.066813][ C0] __free_pages_ok+0x5a0/0x740 > > [ 133.069409][ C0] __free_pages_core+0x24c/0x280 > > [ 133.072127][ C0] deferred_free_range+0x6c/0xbc > > [ 133.074847][ C0] deferred_init_maxorder+0x2d0/0x350 > > [ 133.077803][ C0] deferred_init_memmap_chunk+0xc8/0x124 > > [ 133.080834][ C0] padata_do_multithreaded+0x15c/0x578 > > [ 133.083791][ C0] deferred_init_memmap+0x26c/0x364 > > [ 133.086614][ C0] kthread+0x23c/0x260 > > [ 133.088879][ C0] ret_from_fork+0x10/0x18 > > [ 133.092092][ C0] ---[ end Kernel panic - not syncing: > > softlockup: hung tasks ]--- > > > > Full log [1], and my .config [2]. > > > > I bisected down to patch 799815f497e2 ("mm: cma: support sysfs"). > > > > When I revert > > 799815f497e2 ("mm: cma: support sysfs") > > 7af97692f30d ("mm: cma: fix potential null dereference on pointer cma") > > > > The kernel boots fine. > > > > Any idea whats happening? > > Hi Anders, > > Dmitry reported the crash(However, your callstack is not the same > and didn't show any CMA stuffs so I am not sure it's same crash) > and posted the fix. > > https://lore.kernel.org/linux-mm/20210324192044.1505747-1-minchan@kernel.org/ > > However, in the end, it was folded into original patchset to replace it. Oh, thank you for letting me know, sorry that I reported on the wrong one. > That is an this v8 patch. So, could you try it? I was able to boot the kernel. Cheers, Anders
diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-cma b/Documentation/ABI/testing/sysfs-kernel-mm-cma new file mode 100644 index 000000000000..02b2bb60c296 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-kernel-mm-cma @@ -0,0 +1,25 @@ +What: /sys/kernel/mm/cma/ +Date: Feb 2021 +Contact: Minchan Kim <minchan@kernel.org> +Description: + /sys/kernel/mm/cma/ contains a subdirectory for each CMA + heap name (also sometimes called CMA areas). + + Each CMA heap subdirectory (that is, each + /sys/kernel/mm/cma/<cma-heap-name> directory) contains the + following items: + + alloc_pages_success + alloc_pages_fail + +What: /sys/kernel/mm/cma/<cma-heap-name>/alloc_pages_success +Date: Feb 2021 +Contact: Minchan Kim <minchan@kernel.org> +Description: + the number of pages CMA API succeeded to allocate + +What: /sys/kernel/mm/cma/<cma-heap-name>/alloc_pages_fail +Date: Feb 2021 +Contact: Minchan Kim <minchan@kernel.org> +Description: + the number of pages CMA API failed to allocate diff --git a/mm/Kconfig b/mm/Kconfig index 23a0e3c98ff0..3823a2314256 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -524,6 +524,13 @@ config CMA_DEBUGFS help Turns on the DebugFS interface for CMA. +config CMA_SYSFS + bool "CMA information through sysfs interface" + depends on CMA && SYSFS + help + This option exposes some sysfs attributes to get information + from CMA. + config CMA_AREAS int "Maximum count of the CMA areas" depends on CMA diff --git a/mm/Makefile b/mm/Makefile index 9e284dba50ef..788c5ce5c0ef 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -112,6 +112,7 @@ obj-$(CONFIG_CMA) += cma.o obj-$(CONFIG_MEMORY_BALLOON) += balloon_compaction.o obj-$(CONFIG_PAGE_EXTENSION) += page_ext.o obj-$(CONFIG_CMA_DEBUGFS) += cma_debug.o +obj-$(CONFIG_CMA_SYSFS) += cma_sysfs.o obj-$(CONFIG_USERFAULTFD) += userfaultfd.o obj-$(CONFIG_IDLE_PAGE_TRACKING) += page_idle.o obj-$(CONFIG_DEBUG_PAGE_REF) += debug_page_ref.o diff --git a/mm/cma.c b/mm/cma.c index 0361e289c31a..08c45157911a 100644 --- a/mm/cma.c +++ b/mm/cma.c @@ -507,10 +507,14 @@ struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align, pr_debug("%s(): returned %p\n", __func__, page); out: - if (page) + if (page) { count_vm_event(CMA_ALLOC_SUCCESS); - else + cma_sysfs_account_success_pages(cma, count); + } else { count_vm_event(CMA_ALLOC_FAIL); + if (cma) + cma_sysfs_account_fail_pages(cma, count); + } return page; } diff --git a/mm/cma.h b/mm/cma.h index 42ae082cb067..68ffad4e430d 100644 --- a/mm/cma.h +++ b/mm/cma.h @@ -3,6 +3,12 @@ #define __MM_CMA_H__ #include <linux/debugfs.h> +#include <linux/kobject.h> + +struct cma_kobject { + struct kobject kobj; + struct cma *cma; +}; struct cma { unsigned long base_pfn; @@ -16,6 +22,14 @@ struct cma { struct debugfs_u32_array dfs_bitmap; #endif char name[CMA_MAX_NAME]; +#ifdef CONFIG_CMA_SYSFS + /* the number of CMA page successful allocations */ + atomic64_t nr_pages_succeeded; + /* the number of CMA page allocation failures */ + atomic64_t nr_pages_failed; + /* kobject requires dynamic object */ + struct cma_kobject *cma_kobj; +#endif }; extern struct cma cma_areas[MAX_CMA_AREAS]; @@ -26,4 +40,13 @@ static inline unsigned long cma_bitmap_maxno(struct cma *cma) return cma->count >> cma->order_per_bit; } +#ifdef CONFIG_CMA_SYSFS +void cma_sysfs_account_success_pages(struct cma *cma, unsigned long nr_pages); +void cma_sysfs_account_fail_pages(struct cma *cma, unsigned long nr_pages); +#else +static inline void cma_sysfs_account_success_pages(struct cma *cma, + unsigned long nr_pages) {}; +static inline void cma_sysfs_account_fail_pages(struct cma *cma, + unsigned long nr_pages) {}; +#endif #endif diff --git a/mm/cma_sysfs.c b/mm/cma_sysfs.c new file mode 100644 index 000000000000..eb2f39caff59 --- /dev/null +++ b/mm/cma_sysfs.c @@ -0,0 +1,112 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * CMA SysFS Interface + * + * Copyright (c) 2021 Minchan Kim <minchan@kernel.org> + */ + +#include <linux/cma.h> +#include <linux/kernel.h> +#include <linux/slab.h> + +#include "cma.h" + +#define CMA_ATTR_RO(_name) \ + static struct kobj_attribute _name##_attr = __ATTR_RO(_name) + +void cma_sysfs_account_success_pages(struct cma *cma, unsigned long nr_pages) +{ + atomic64_add(nr_pages, &cma->nr_pages_succeeded); +} + +void cma_sysfs_account_fail_pages(struct cma *cma, unsigned long nr_pages) +{ + atomic64_add(nr_pages, &cma->nr_pages_failed); +} + +static inline struct cma *cma_from_kobj(struct kobject *kobj) +{ + return container_of(kobj, struct cma_kobject, kobj)->cma; +} + +static ssize_t alloc_pages_success_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct cma *cma = cma_from_kobj(kobj); + + return sysfs_emit(buf, "%llu\n", + atomic64_read(&cma->nr_pages_succeeded)); +} +CMA_ATTR_RO(alloc_pages_success); + +static ssize_t alloc_pages_fail_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct cma *cma = cma_from_kobj(kobj); + + return sysfs_emit(buf, "%llu\n", atomic64_read(&cma->nr_pages_failed)); +} +CMA_ATTR_RO(alloc_pages_fail); + +static void cma_kobj_release(struct kobject *kobj) +{ + struct cma *cma = cma_from_kobj(kobj); + struct cma_kobject *cma_kobj = cma->cma_kobj; + + kfree(cma_kobj); + cma->cma_kobj = NULL; +} + +static struct attribute *cma_attrs[] = { + &alloc_pages_success_attr.attr, + &alloc_pages_fail_attr.attr, + NULL, +}; +ATTRIBUTE_GROUPS(cma); + +static struct kobj_type cma_ktype = { + .release = cma_kobj_release, + .sysfs_ops = &kobj_sysfs_ops, + .default_groups = cma_groups, +}; + +static int __init cma_sysfs_init(void) +{ + struct kobject *cma_kobj_root; + struct cma_kobject *cma_kobj; + struct cma *cma; + int i, err; + + cma_kobj_root = kobject_create_and_add("cma", mm_kobj); + if (!cma_kobj_root) + return -ENOMEM; + + for (i = 0; i < cma_area_count; i++) { + cma_kobj = kzalloc(sizeof(*cma_kobj), GFP_KERNEL); + if (!cma_kobj) { + err = -ENOMEM; + goto out; + } + + cma = &cma_areas[i]; + cma->cma_kobj = cma_kobj; + cma_kobj->cma = cma; + err = kobject_init_and_add(&cma_kobj->kobj, &cma_ktype, + cma_kobj_root, "%s", cma->name); + if (err) { + kobject_put(&cma_kobj->kobj); + goto out; + } + } + + return 0; +out: + while (--i >= 0) { + cma = &cma_areas[i]; + kobject_put(&cma->cma_kobj->kobj); + } + kobject_put(cma_kobj_root); + + return err; +} +subsys_initcall(cma_sysfs_init);