From: Andrew Jones <drjo...@redhat.com>
commit 75df529bec9110dad43ab30e2d9490242529e8b8 upstream.
Steal time initialization requires mapping a memory region which
invokes a memory allocation. Doing this at CPU starting time results
in the following trace when CONFIG_DEBUG_ATOMIC_SLEEP is enabled:
BUG: sleeping function called from invalid context at mm/slab.h:498
in_atomic(): 1, irqs_disabled(): 128, non_block: 0, pid: 0, name: swapper/1
CPU: 1 PID: 0 Comm: swapper/1 Not tainted 5.9.0-rc5+ #1
Call trace:
dump_backtrace+0x0/0x208
show_stack+0x1c/0x28
dump_stack+0xc4/0x11c
___might_sleep+0xf8/0x130
__might_sleep+0x58/0x90
slab_pre_alloc_hook.constprop.101+0xd0/0x118
kmem_cache_alloc_node_trace+0x84/0x270
__get_vm_area_node+0x88/0x210
get_vm_area_caller+0x38/0x40
__ioremap_caller+0x70/0xf8
ioremap_cache+0x78/0xb0
memremap+0x9c/0x1a8
init_stolen_time_cpu+0x54/0xf0
cpuhp_invoke_callback+0xa8/0x720
notify_cpu_starting+0xc8/0xd8
secondary_start_kernel+0x114/0x180
CPU1: Booted secondary processor 0x0000000001 [0x431f0a11]
However we don't need to initialize steal time at CPU starting time.
We can simply wait until CPU online time, just sacrificing a bit of
accuracy by returning zero for steal time until we know better.
While at it, add __init to the functions that are only called by
pv_time_init() which is __init.
Signed-off-by: Andrew Jones <drjo...@redhat.com>
Fixes: e0685fa228fd ("arm64: Retrieve stolen time as paravirtualized guest")
Cc: sta...@vger.kernel.org
Reviewed-by: Steven Price <steven.pr...@arm.com>
Link: https://lore.kernel.org/r/20200916154530.40809-1-drjo...@redhat.com
Signed-off-by: Catalin Marinas <catalin.mari...@arm.com>
Signed-off-by: Greg Kroah-Hartman <gre...@linuxfoundation.org>
---
arch/arm64/kernel/paravirt.c | 26 +++++++++++++++-----------
include/linux/cpuhotplug.h | 1 -
2 files changed, 15 insertions(+), 12 deletions(-)
--- a/arch/arm64/kernel/paravirt.c
+++ b/arch/arm64/kernel/paravirt.c
@@ -50,16 +50,19 @@ static u64 pv_steal_clock(int cpu)
struct pv_time_stolen_time_region *reg;
reg = per_cpu_ptr(&stolen_time_region, cpu);
- if (!reg->kaddr) {
- pr_warn_once("stolen time enabled but not configured for cpu
%d\n",
- cpu);
+
+ /*
+ * paravirt_steal_clock() may be called before the CPU
+ * online notification callback runs. Until the callback
+ * has run we just return zero.
+ */
+ if (!reg->kaddr)
return 0;
- }
return le64_to_cpu(READ_ONCE(reg->kaddr->stolen_time));
}
-static int stolen_time_dying_cpu(unsigned int cpu)
+static int stolen_time_cpu_down_prepare(unsigned int cpu)
{
struct pv_time_stolen_time_region *reg;
@@ -73,7 +76,7 @@ static int stolen_time_dying_cpu(unsigne
return 0;
}
-static int init_stolen_time_cpu(unsigned int cpu)
+static int stolen_time_cpu_online(unsigned int cpu)
{
struct pv_time_stolen_time_region *reg;
struct arm_smccc_res res;
@@ -103,19 +106,20 @@ static int init_stolen_time_cpu(unsigned
return 0;
}
-static int pv_time_init_stolen_time(void)
+static int __init pv_time_init_stolen_time(void)
{
int ret;
- ret = cpuhp_setup_state(CPUHP_AP_ARM_KVMPV_STARTING,
- "hypervisor/arm/pvtime:starting",
- init_stolen_time_cpu, stolen_time_dying_cpu);
+ ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
+ "hypervisor/arm/pvtime:online",
+ stolen_time_cpu_online,
+ stolen_time_cpu_down_prepare);
if (ret < 0)
return ret;
return 0;
}
-static bool has_pv_steal_clock(void)
+static bool __init has_pv_steal_clock(void)
{
struct arm_smccc_res res;
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -141,7 +141,6 @@ enum cpuhp_state {
/* Must be the last timer callback */
CPUHP_AP_DUMMY_TIMER_STARTING,
CPUHP_AP_ARM_XEN_STARTING,
- CPUHP_AP_ARM_KVMPV_STARTING,
CPUHP_AP_ARM_CORESIGHT_STARTING,
CPUHP_AP_ARM_CORESIGHT_CTI_STARTING,
CPUHP_AP_ARM64_ISNDEP_STARTING,
