linux_dsm_epyc7002/arch
Matt Fleming d7a702f0b1 perf/x86/intel/cqm: Do not access cpu_data() from CPU_UP_PREPARE handler
Tony reports that booting his 144-cpu machine with maxcpus=10 triggers
the following WARN_ON():

[   21.045727] WARNING: CPU: 8 PID: 647 at arch/x86/kernel/cpu/perf_event_intel_cqm.c:1267 intel_cqm_cpu_prepare+0x75/0x90()
[   21.045744] CPU: 8 PID: 647 Comm: systemd-udevd Not tainted 4.2.0-rc4 #1
[   21.045745] Hardware name: Intel Corporation BRICKLAND/BRICKLAND, BIOS BRHSXSD1.86B.0066.R00.1506021730 06/02/2015
[   21.045747]  0000000000000000 0000000082771b09 ffff880856333ba8 ffffffff81669b67
[   21.045748]  0000000000000000 0000000000000000 ffff880856333be8 ffffffff8107b02a
[   21.045750]  ffff88085b789800 ffff88085f68a020 ffffffff819e2470 000000000000000a
[   21.045750] Call Trace:
[   21.045757]  [<ffffffff81669b67>] dump_stack+0x45/0x57
[   21.045759]  [<ffffffff8107b02a>] warn_slowpath_common+0x8a/0xc0
[   21.045761]  [<ffffffff8107b15a>] warn_slowpath_null+0x1a/0x20
[   21.045762]  [<ffffffff81036725>] intel_cqm_cpu_prepare+0x75/0x90
[   21.045764]  [<ffffffff81036872>] intel_cqm_cpu_notifier+0x42/0x160
[   21.045767]  [<ffffffff8109a33d>] notifier_call_chain+0x4d/0x80
[   21.045769]  [<ffffffff8109a44e>] __raw_notifier_call_chain+0xe/0x10
[   21.045770]  [<ffffffff8107b538>] _cpu_up+0xe8/0x190
[   21.045771]  [<ffffffff8107b65a>] cpu_up+0x7a/0xa0
[   21.045774]  [<ffffffff8165e920>] cpu_subsys_online+0x40/0x90
[   21.045777]  [<ffffffff81433b37>] device_online+0x67/0x90
[   21.045778]  [<ffffffff81433bea>] online_store+0x8a/0xa0
[   21.045782]  [<ffffffff81430e78>] dev_attr_store+0x18/0x30
[   21.045785]  [<ffffffff8126b6ba>] sysfs_kf_write+0x3a/0x50
[   21.045786]  [<ffffffff8126ad40>] kernfs_fop_write+0x120/0x170
[   21.045789]  [<ffffffff811f0b77>] __vfs_write+0x37/0x100
[   21.045791]  [<ffffffff811f38b8>] ? __sb_start_write+0x58/0x110
[   21.045795]  [<ffffffff81296d2d>] ? security_file_permission+0x3d/0xc0
[   21.045796]  [<ffffffff811f1279>] vfs_write+0xa9/0x190
[   21.045797]  [<ffffffff811f2075>] SyS_write+0x55/0xc0
[   21.045800]  [<ffffffff81067300>] ? do_page_fault+0x30/0x80
[   21.045804]  [<ffffffff816709ae>] entry_SYSCALL_64_fastpath+0x12/0x71
[   21.045805] ---[ end trace fe228b836d8af405 ]---

The root cause is that CPU_UP_PREPARE is completely the wrong notifier
action from which to access cpu_data(), because smp_store_cpu_info()
won't have been executed by the target CPU at that point, which in turn
means that ->x86_cache_max_rmid and ->x86_cache_occ_scale haven't been
filled out.

Instead let's invoke our handler from CPU_STARTING and rename it
appropriately.

Reported-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Ashok Raj <ashok.raj@intel.com>
Cc: Kanaka Juvva <kanaka.d.juvva@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vikas Shivappa <vikas.shivappa@intel.com>
Link: http://lkml.kernel.org/r/1438863163-14083-1-git-send-email-matt@codeblueprint.co.uk
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-08-12 11:37:23 +02:00
..
alpha mm: clean up per architecture MM hook header files 2015-07-17 16:39:53 -07:00
arc mm: clean up per architecture MM hook header files 2015-07-17 16:39:53 -07:00
arm MMC core: 2015-07-24 16:43:16 -07:00
arm64 ARM64/irq: Use access helper irq_data_get_affinity_mask() 2015-07-22 10:57:09 +01:00
avr32 AVR32/time: Migrate to new 'set-state' interface 2015-07-20 12:19:10 +02:00
blackfin mm: clean up per architecture MM hook header files 2015-07-17 16:39:53 -07:00
c6x mm: clean up per architecture MM hook header files 2015-07-17 16:39:53 -07:00
cris mm: clean up per architecture MM hook header files 2015-07-17 16:39:53 -07:00
frv mm: clean up per architecture MM hook header files 2015-07-17 16:39:53 -07:00
h8300 mm: clean up per architecture MM hook header files 2015-07-17 16:39:53 -07:00
hexagon mm: clean up per architecture MM hook header files 2015-07-17 16:39:53 -07:00
ia64 mm: clean up per architecture MM hook header files 2015-07-17 16:39:53 -07:00
m32r m32r: Add ioreadXX/iowriteXX big-endian mmio accessors 2015-07-23 18:08:28 -07:00
m68k mm: clean up per architecture MM hook header files 2015-07-17 16:39:53 -07:00
metag mm: clean up per architecture MM hook header files 2015-07-17 16:39:53 -07:00
microblaze mm: clean up per architecture MM hook header files 2015-07-17 16:39:53 -07:00
mips Merge branch 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus 2015-07-19 14:12:22 -07:00
mn10300 mm: clean up per architecture MM hook header files 2015-07-17 16:39:53 -07:00
nios2 mm: clean up per architecture MM hook header files 2015-07-17 16:39:53 -07:00
openrisc mm: clean up per architecture MM hook header files 2015-07-17 16:39:53 -07:00
parisc parisc: mm: Fix a memory leak related to pmd not attached to the pgd 2015-07-19 08:56:14 +02:00
powerpc powerpc/perf/24x7: Fix lockdep warning 2015-07-08 15:18:04 +10:00
s390 s390: adapt entry.S to the move of thread_struct 2015-07-20 13:22:18 +02:00
score mm: clean up per architecture MM hook header files 2015-07-17 16:39:53 -07:00
sh mm: clean up per architecture MM hook header files 2015-07-17 16:39:53 -07:00
sparc mm: clean up per architecture MM hook header files 2015-07-17 16:39:53 -07:00
tile tile: use free_bootmem_late() for initrd 2015-07-23 14:11:09 -04:00
um mm: clean up per architecture MM hook header files 2015-07-17 16:39:53 -07:00
unicore32 mm: clean up per architecture MM hook header files 2015-07-17 16:39:53 -07:00
x86 perf/x86/intel/cqm: Do not access cpu_data() from CPU_UP_PREPARE handler 2015-08-12 11:37:23 +02:00
xtensa mm: clean up per architecture MM hook header files 2015-07-17 16:39:53 -07:00
.gitignore
Kconfig x86/fpu, sched: Introduce CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT and use it on x86 2015-07-18 03:42:51 +02:00