This patch fixes a bug reported from customer, who found many unreasonable error
interrupts reported on all APs during the system boot stage.
According to Chapter 10 of Intel Software Developer Manual Volume 3A, Local APIC
may signal an illegal vector error when an LVT entry is set as an illegal
vector value (0~15) under FIXED delivery mode (bits 8-11 is 0), regardless of
whether the mask bit is set or an interrupt actually happen. These errors are
seen as error interrupts.
The initial value of thermal LVT entries on all APs always reads 0x10000 because
APs are woken up by BSP issuing INIT-SIPI-SIPI sequence to them and LVT
registers are reset to 0s except for the mask bits which are set to 1s when APs
receive INIT IPI. When BIOS take over the thermal throttling interrupt, LVT
thermal deliver mode should be SMI and it is required to restore AP's LVT
thermal monitor register.
This issue happens when BIOS do not take over thermal throttling interrupt,
AP's LVT thermal monitor register will be restored to 0x10000 which means vector
0 and fixed deliver mode, so all APs will signal illegal vector error
interrupt. This patch check if interrupt delivery mode is not fixed mode before
restore AP's LVT thermal monitor register.
Signed-off-by: Youquan Song <[email protected]>
Acked-by: Suresh Siddha <[email protected]>
Acked-by: Yong Wang <[email protected]>
---
arch/x86/include/asm/apicdef.h | 1 +
arch/x86/kernel/cpu/mcheck/therm_throt.c | 12 +++++++-----
2 files changed, 8 insertions(+), 5 deletions(-)
diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h
index d87988b..34595d5 100644
--- a/arch/x86/include/asm/apicdef.h
+++ b/arch/x86/include/asm/apicdef.h
@@ -78,6 +78,7 @@
#define APIC_DEST_LOGICAL 0x00800
#define APIC_DEST_PHYSICAL 0x00000
#define APIC_DM_FIXED 0x00000
+#define APIC_DM_FIXED_MASK 0x00700
#define APIC_DM_LOWEST 0x00100
#define APIC_DM_SMI 0x00200
#define APIC_DM_REMRD 0x00300
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 6f8c5e9..22c212a 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -446,18 +446,20 @@ void intel_init_thermal(struct cpuinfo_x86 *c)
*/
rdmsr(MSR_IA32_MISC_ENABLE, l, h);
+ h = lvtthmr_init;
/*
* The initial value of thermal LVT entries on all APs always reads
* 0x10000 because APs are woken up by BSP issuing INIT-SIPI-SIPI
* sequence to them and LVT registers are reset to 0s except for
* the mask bits which are set to 1s when APs receive INIT IPI.
- * Always restore the value that BIOS has programmed on AP based on
- * BSP's info we saved since BIOS is always setting the same value
- * for all threads/cores
+ * If BIOS take over the thermal interrupt and set its interrupt
+ * delivery mode to SMI not fixed, it restore the value that BIOS has
+ * programmed on AP based on BSP's info we saved since BIOS is always
+ * setting the same value for all threads/cores.
*/
- apic_write(APIC_LVTTHMR, lvtthmr_init);
+ if ((h & APIC_DM_FIXED_MASK) != APIC_DM_FIXED)
+ apic_write(APIC_LVTTHMR, lvtthmr_init);
- h = lvtthmr_init;
if ((l & MSR_IA32_MISC_ENABLE_TM1) && (h & APIC_DM_SMI)) {
printk(KERN_DEBUG
--
1.6.4.2
Hi Ingo,
Below is the updated description. If it looks good, please take it
since the first patch "x86, apic: Print verbose error interrupt reason on
apic=debug" in the patchset already accepted in -tip.
Thanks
-Youquan
On Fri, Apr 22, 2011 at 12:22:43AM +0800, Youquan Song wrote:
> This patch fixes a bug reported from customer, who found many unreasonable error
> interrupts reported on all APs during the system boot stage.
>
> According to Chapter 10 of Intel Software Developer Manual Volume 3A, Local APIC
> may signal an illegal vector error when an LVT entry is set as an illegal
> vector value (0~15) under FIXED delivery mode (bits 8-11 is 0), regardless of
> whether the mask bit is set or an interrupt actually happen. These errors are
> seen as error interrupts.
>
> The initial value of thermal LVT entries on all APs always reads 0x10000 because
> APs are woken up by BSP issuing INIT-SIPI-SIPI sequence to them and LVT
> registers are reset to 0s except for the mask bits which are set to 1s when APs
> receive INIT IPI. When BIOS take over the thermal throttling interrupt, LVT
> thermal deliver mode should be SMI and it is required to restore AP's LVT
> thermal monitor register.
>
> This issue happens when BIOS do not take over thermal throttling interrupt,
> AP's LVT thermal monitor register will be restored to 0x10000 which means vector
> 0 and fixed deliver mode, so all APs will signal illegal vector error
> interrupt. This patch check if interrupt delivery mode is not fixed mode before
> restore AP's LVT thermal monitor register.
>
> Signed-off-by: Youquan Song <[email protected]>
> Acked-by: Suresh Siddha <[email protected]>
> Acked-by: Yong Wang <[email protected]>
> ---
> arch/x86/include/asm/apicdef.h | 1 +
> arch/x86/kernel/cpu/mcheck/therm_throt.c | 12 +++++++-----
> 2 files changed, 8 insertions(+), 5 deletions(-)
>
> diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h
> index d87988b..34595d5 100644
> --- a/arch/x86/include/asm/apicdef.h
> +++ b/arch/x86/include/asm/apicdef.h
> @@ -78,6 +78,7 @@
> #define APIC_DEST_LOGICAL 0x00800
> #define APIC_DEST_PHYSICAL 0x00000
> #define APIC_DM_FIXED 0x00000
> +#define APIC_DM_FIXED_MASK 0x00700
> #define APIC_DM_LOWEST 0x00100
> #define APIC_DM_SMI 0x00200
> #define APIC_DM_REMRD 0x00300
> diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
> index 6f8c5e9..22c212a 100644
> --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
> +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
> @@ -446,18 +446,20 @@ void intel_init_thermal(struct cpuinfo_x86 *c)
> */
> rdmsr(MSR_IA32_MISC_ENABLE, l, h);
>
> + h = lvtthmr_init;
> /*
> * The initial value of thermal LVT entries on all APs always reads
> * 0x10000 because APs are woken up by BSP issuing INIT-SIPI-SIPI
> * sequence to them and LVT registers are reset to 0s except for
> * the mask bits which are set to 1s when APs receive INIT IPI.
> - * Always restore the value that BIOS has programmed on AP based on
> - * BSP's info we saved since BIOS is always setting the same value
> - * for all threads/cores
> + * If BIOS take over the thermal interrupt and set its interrupt
> + * delivery mode to SMI not fixed, it restore the value that BIOS has
> + * programmed on AP based on BSP's info we saved since BIOS is always
> + * setting the same value for all threads/cores.
> */
> - apic_write(APIC_LVTTHMR, lvtthmr_init);
> + if ((h & APIC_DM_FIXED_MASK) != APIC_DM_FIXED)
> + apic_write(APIC_LVTTHMR, lvtthmr_init);
>
> - h = lvtthmr_init;
>
> if ((l & MSR_IA32_MISC_ENABLE_TM1) && (h & APIC_DM_SMI)) {
> printk(KERN_DEBUG
> --
> 1.6.4.2
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at http://www.tux.org/lkml/
>
Commit-ID: e503f9e4b092e2349a9477a333543de8f3c7f5d9
Gitweb: http://git.kernel.org/tip/e503f9e4b092e2349a9477a333543de8f3c7f5d9
Author: Youquan Song <[email protected]>
AuthorDate: Fri, 22 Apr 2011 00:22:43 +0800
Committer: Ingo Molnar <[email protected]>
CommitDate: Mon, 16 May 2011 13:48:25 +0200
x86, apic: Fix spurious error interrupts triggering on all non-boot APs
This patch fixes a bug reported by a customer, who found
that many unreasonable error interrupts reported on all
non-boot CPUs (APs) during the system boot stage.
According to Chapter 10 of Intel Software Developer Manual
Volume 3A, Local APIC may signal an illegal vector error when
an LVT entry is set as an illegal vector value (0~15) under
FIXED delivery mode (bits 8-11 is 0), regardless of whether
the mask bit is set or an interrupt actually happen. These
errors are seen as error interrupts.
The initial value of thermal LVT entries on all APs always reads
0x10000 because APs are woken up by BSP issuing INIT-SIPI-SIPI
sequence to them and LVT registers are reset to 0s except for
the mask bits which are set to 1s when APs receive INIT IPI.
When the BIOS takes over the thermal throttling interrupt,
the LVT thermal deliver mode should be SMI and it is required
from the kernel to keep AP's LVT thermal monitoring register
programmed as such as well.
This issue happens when BIOS does not take over thermal throttling
interrupt, AP's LVT thermal monitor register will be restored to
0x10000 which means vector 0 and fixed deliver mode, so all APs will
signal illegal vector error interrupts.
This patch check if interrupt delivery mode is not fixed mode before
restoring AP's LVT thermal monitor register.
Signed-off-by: Youquan Song <[email protected]>
Acked-by: Suresh Siddha <[email protected]>
Acked-by: Yong Wang <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: <[email protected]> # As far back as possible
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
---
arch/x86/include/asm/apicdef.h | 1 +
arch/x86/kernel/cpu/mcheck/therm_throt.c | 12 +++++++-----
2 files changed, 8 insertions(+), 5 deletions(-)
diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h
index d87988b..34595d5 100644
--- a/arch/x86/include/asm/apicdef.h
+++ b/arch/x86/include/asm/apicdef.h
@@ -78,6 +78,7 @@
#define APIC_DEST_LOGICAL 0x00800
#define APIC_DEST_PHYSICAL 0x00000
#define APIC_DM_FIXED 0x00000
+#define APIC_DM_FIXED_MASK 0x00700
#define APIC_DM_LOWEST 0x00100
#define APIC_DM_SMI 0x00200
#define APIC_DM_REMRD 0x00300
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 6f8c5e9..0f03446 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -446,18 +446,20 @@ void intel_init_thermal(struct cpuinfo_x86 *c)
*/
rdmsr(MSR_IA32_MISC_ENABLE, l, h);
+ h = lvtthmr_init;
/*
* The initial value of thermal LVT entries on all APs always reads
* 0x10000 because APs are woken up by BSP issuing INIT-SIPI-SIPI
* sequence to them and LVT registers are reset to 0s except for
* the mask bits which are set to 1s when APs receive INIT IPI.
- * Always restore the value that BIOS has programmed on AP based on
- * BSP's info we saved since BIOS is always setting the same value
- * for all threads/cores
+ * If BIOS takes over the thermal interrupt and sets its interrupt
+ * delivery mode to SMI (not fixed), it restores the value that the
+ * BIOS has programmed on AP based on BSP's info we saved since BIOS
+ * is always setting the same value for all threads/cores.
*/
- apic_write(APIC_LVTTHMR, lvtthmr_init);
+ if ((h & APIC_DM_FIXED_MASK) != APIC_DM_FIXED)
+ apic_write(APIC_LVTTHMR, lvtthmr_init);
- h = lvtthmr_init;
if ((l & MSR_IA32_MISC_ENABLE_TM1) && (h & APIC_DM_SMI)) {
printk(KERN_DEBUG