diff options
author | Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com> | 2016-10-08 12:42:38 -0700 |
---|---|---|
committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2016-10-28 03:01:26 -0400 |
commit | d756b52c8bbe7735cc881dab46378518d2d4b1f1 (patch) | |
tree | 8ddd6af74941552a985785fbb480ad2525fb32f8 /drivers/cpufreq | |
parent | 3fc96b9e2bd08f730df18b079a2036cddab021b7 (diff) |
cpufreq: intel_pstate: Fix unsafe HWP MSR access
commit f9f4872df6e1801572949f8a370c886122d4b6da upstream.
This is a requirement that MSR MSR_PM_ENABLE must be set to 0x01 before
reading MSR_HWP_CAPABILITIES on a given CPU. If cpufreq init() is
scheduled on a CPU which is not same as policy->cpu or migrates to a
different CPU before calling msr read for MSR_HWP_CAPABILITIES, it
is possible that MSR_PM_ENABLE was not to set to 0x01 on that CPU.
This will cause GP fault. So like other places in this path
rdmsrl_on_cpu should be used instead of rdmsrl.
Moreover the scope of MSR_HWP_CAPABILITIES is on per thread basis, so it
should be read from the same CPU, for which MSR MSR_HWP_REQUEST is
getting set.
dmesg dump or warning:
[ 22.014488] WARNING: CPU: 139 PID: 1 at arch/x86/mm/extable.c:50 ex_handler_rdmsr_unsafe+0x68/0x70
[ 22.014492] unchecked MSR access error: RDMSR from 0x771
[ 22.014493] Modules linked in:
[ 22.014507] CPU: 139 PID: 1 Comm: swapper/0 Not tainted 4.7.5+ #1
...
...
[ 22.014516] Call Trace:
[ 22.014542] [<ffffffff813d7dd1>] dump_stack+0x63/0x82
[ 22.014558] [<ffffffff8107bc8b>] __warn+0xcb/0xf0
[ 22.014561] [<ffffffff8107bcff>] warn_slowpath_fmt+0x4f/0x60
[ 22.014563] [<ffffffff810676f8>] ex_handler_rdmsr_unsafe+0x68/0x70
[ 22.014564] [<ffffffff810677d9>] fixup_exception+0x39/0x50
[ 22.014604] [<ffffffff8102e400>] do_general_protection+0x80/0x150
[ 22.014610] [<ffffffff817f9ec8>] general_protection+0x28/0x30
[ 22.014635] [<ffffffff81687940>] ? get_target_pstate_use_performance+0xb0/0xb0
[ 22.014642] [<ffffffff810600c7>] ? native_read_msr+0x7/0x40
[ 22.014657] [<ffffffff81688123>] intel_pstate_hwp_set+0x23/0x130
[ 22.014660] [<ffffffff81688406>] intel_pstate_set_policy+0x1b6/0x340
[ 22.014662] [<ffffffff816829bb>] cpufreq_set_policy+0xeb/0x2c0
[ 22.014664] [<ffffffff81682f39>] cpufreq_init_policy+0x79/0xe0
[ 22.014666] [<ffffffff81682cb0>] ? cpufreq_update_policy+0x120/0x120
[ 22.014669] [<ffffffff816833a6>] cpufreq_online+0x406/0x820
[ 22.014671] [<ffffffff8168381f>] cpufreq_add_dev+0x5f/0x90
[ 22.014717] [<ffffffff81530ac8>] subsys_interface_register+0xb8/0x100
[ 22.014719] [<ffffffff816821bc>] cpufreq_register_driver+0x14c/0x210
[ 22.014749] [<ffffffff81fe1d90>] intel_pstate_init+0x39d/0x4d5
[ 22.014751] [<ffffffff81fe13f2>] ? cpufreq_gov_dbs_init+0x12/0x12
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'drivers/cpufreq')
-rw-r--r-- | drivers/cpufreq/intel_pstate.c | 10 |
1 files changed, 5 insertions, 5 deletions
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 6e80e4298274..7ff8b15a3422 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -285,14 +285,14 @@ static void intel_pstate_hwp_set(void) int min, hw_min, max, hw_max, cpu, range, adj_range; u64 value, cap; - rdmsrl(MSR_HWP_CAPABILITIES, cap); - hw_min = HWP_LOWEST_PERF(cap); - hw_max = HWP_HIGHEST_PERF(cap); - range = hw_max - hw_min; - get_online_cpus(); for_each_online_cpu(cpu) { + rdmsrl_on_cpu(cpu, MSR_HWP_CAPABILITIES, &cap); + hw_min = HWP_LOWEST_PERF(cap); + hw_max = HWP_HIGHEST_PERF(cap); + range = hw_max - hw_min; + rdmsrl_on_cpu(cpu, MSR_HWP_REQUEST, &value); adj_range = limits->min_perf_pct * range / 100; min = hw_min + adj_range; |