x86 - irq vector assignment
PATCH 1/1 x86 - irq vector assignment
Try to assign irq vectors to cpus on the correct node & fall back to global assignment only if node-local fails. This reduces the chances of using all of the interrupt vectors of a single cpu.
---
Note: this is a fix for a problem we saw on systems with a large number of IOHs. The IOHs are distributed across 10's of nodes.
Early in boot, the IO infrastructure assigns interrupts for the DMA engines. Currently, all interrupts are targeted to cpu 0. This uses all interrupt vectors on cpu 0. Later, some drivers try to create irqs targeted to cpu 0. The assignment fails because all vectors are assigned.
This is a repost of a patch sent earlier. See
http://marc.info/?l=linux-kernel&m=127740806705617&w=2 http://marc.info/?l=linux-kernel&m=127791052828867&w=2
arch/x86/kernel/apic/io_apic.c | 5 +++++ 1 file changed, 5 insertions(+)
arch/x86/kernel/apic/io_apic.c +5 -0
@@ -3253,6 +3253,11 @@ unsigned int create_irq_nr(unsigned int desc_new =move_irq_desc (desc_new, node); cfg_new = desc_new->chip_data; +#ifdef CONFIG_NUMA +if (node >=0 &&__assign_irq_vector (new, cfg_new, node_to_cpumask_map[node]) ==0 ) + irq = new; + else +#endif if (__assign_irq_vector (new, cfg_new, apic->target_cpus ()) ==0 ) irq = new;break ;
Quoted 31 lines · Jack Steiner
Try to assign irq vectors to cpus on the correct node & fall back to global assignment only if node-local fails. This reduces the chances of using all of the interrupt vectors of a single cpu.
Signed-off-by Jack Steiner <[email protected]>---
Note: this is a fix for a problem we saw on systems with a large number of IOHs. The IOHs are distributed across 10's of nodes.Early in boot, the IO infrastructure assigns interrupts for the DMA engines. Currently, all interrupts are targeted to cpu 0. This uses all interrupt vectors on cpu 0. Later, some drivers try to create irqs targeted to cpu 0. The assignment fails because all vectors are assigned.
This is a repost of a patch sent earlier. See
http://marc.info/?l=linux-kernel&m=127740806705617&w=2
http://marc.info/?l=linux-kernel&m=127791052828867&w=2arch/x86/kernel/apic/io_apic.c | 5 +++++
1 file changed, 5 insertions(+)Index:
linux/arch/x86/kernel/apic/io_apic.c
===================================================================arch/x86/kernel/apic/io_apic.c 2010-09-17 13:00:23.448595373 -0500 renamed from arch/x86/kernel/apic/io_apic.c 2010-09-17 13:00:19.164638447 -0500 +0
-0@@ -3253,6 +3253,11 @@ unsigned int create_irq_nr(unsigned int desc_new = move_irq_desc(desc_new, node);
arch/x86/kernel/apic/io_apic.c 2010-09-17 13:00:23.448595373 -0500 unsigned int create_irq_nr(unsigned int · line 3263
Quoted 10 lines
arch/x86/kernel/apic/io_apic.c 2010-09-17 13:00:23.448595373 -0500 renamed from arch/x86/kernel/apic/io_apic.c 2010-09-17 13:00:19.164638447 -0500 +5
-0cfg_new = desc_new->chip_data; +#ifdef CONFIG_NUMA + if (node >= 0 && __assign_irq_vector(new, cfg_new, node_to_cpumask_map[node]) == 0) + irq = new; + else +#endif if (__assign_irq_vector(new, cfg_new, apic->target_cpus()) == 0) irq = new; break;
target_cpus() for uv_x and x2apic phys mode all have cpu_online_mask()
so we should get the vector for other cpus. aka __assign_irq_vector() should not fail. unless you have so many irq > nr_irqs.
current code we only make sure irq_desc on device local node.
for the vectors, user can set irq smp_affinity move the device local cpus if needed.
Thanks
Yinghai
Quoted 22 lines · Yinghai Lu
Quoted 9 lines
arch/x86/kernel/apic/io_apic.c | 5 +++++
1 file changed, 5 insertions(+)Index:
linux/arch/x86/kernel/apic/io_apic.c
===================================================================arch/x86/kernel/apic/io_apic.c 2010-09-17 13:00:23.448595373 -0500 renamed from arch/x86/kernel/apic/io_apic.c 2010-09-17 13:00:19.164638447 -0500 +0
-0@@ -3253,6 +3253,11 @@ unsigned int create_irq_nr(unsigned int desc_new = move_irq_desc(desc_new, node);arch/x86/kernel/apic/io_apic.c 2010-09-17 13:00:23.448595373 -0500 unsigned int create_irq_nr(unsigned int · line 3263
Quoted 10 lines
arch/x86/kernel/apic/io_apic.c 2010-09-17 13:00:23.448595373 -0500 renamed from arch/x86/kernel/apic/io_apic.c 2010-09-17 13:00:19.164638447 -0500 +5
-0cfg_new = desc_new->chip_data; +#ifdef CONFIG_NUMA + if (node >= 0 && __assign_irq_vector(new, cfg_new, node_to_cpumask_map[node]) == 0) + irq = new; + else +#endif if (__assign_irq_vector(new, cfg_new, apic->target_cpus()) == 0) irq = new; break;
target_cpus()foruv_xand x2apic phys mode all havecpu_online_mask()
Quoted 2 lines
so we should get the vector for other cpus. aka
__assign_irq_vector()should not fail. unless you have so many irq >nr_irqs.
Did you even read the changelog ? It's not about "should".
All CPU0 vectors are assigned already just because the current code takes the first cpu in the target_cpus mask regardless of the node on which the irq_desc is allocated. That's crap. Why do we allocate irq_desc on node and leave the vector assigned to node(cpu0) ?
Quoted 1 line
current code we only make sure
irq_descon device local node.
Brilliant.
Quoted 2 lines
for the vectors, user can set irq
smp_affinitymove the device local cpus if needed.
What a nonsense. If we allocate irq_desc on a target node it does not make any sense to target the vector to whatever random node/cpu in the first place and wait for user space to fix it up. What about running into that situation _before_ we hit user space ?
Thanks,
tglx
Quoted 26 lines · Thomas Gleixner
Quoted 22 lines · Yinghai Lu
Quoted 9 lines
arch/x86/kernel/apic/io_apic.c | 5 +++++ 1 file changed, 5 insertions(+)Index:
linux/arch/x86/kernel/apic/io_apic.c
===================================================================arch/x86/kernel/apic/io_apic.c 2010-09-17 13:00:23.448595373 -0500 renamed from arch/x86/kernel/apic/io_apic.c 2010-09-17 13:00:19.164638447 -0500 +0
-0@@ -3253,6 +3253,11 @@ unsigned int create_irq_nr(unsigned int desc_new = move_irq_desc(desc_new, node);arch/x86/kernel/apic/io_apic.c 2010-09-17 13:00:23.448595373 -0500 unsigned int create_irq_nr(unsigned int · line 3263
Quoted 10 lines
arch/x86/kernel/apic/io_apic.c 2010-09-17 13:00:23.448595373 -0500 renamed from arch/x86/kernel/apic/io_apic.c 2010-09-17 13:00:19.164638447 -0500 +5
-0cfg_new = desc_new->chip_data; +#ifdef CONFIG_NUMA + if (node >= 0 && __assign_irq_vector(new, cfg_new, node_to_cpumask_map[node]) == 0) + irq = new; + else +#endif if (__assign_irq_vector(new, cfg_new, apic->target_cpus()) == 0) irq = new; break;
target_cpus()foruv_xand x2apic phys mode all havecpu_online_mask()Quoted 2 lines
so we should get the vector for other cpus. aka
__assign_irq_vector()should not fail. unless you have so many irq >nr_irqs.
Quoted 6 lines
Did you even read the changelog ? It's not about "should".
All CPU0 vectors are assigned already just because the current code takes the first cpu in the
target_cpusmask regardless of the node on which theirq_descis allocated. That's crap. Why do we allocateirq_descon node and leave the vector assigned to node(cpu0) ?
ok, i got it. vectors from cpus on node0 are used by devices from others nodes.
later devices from node0 can not get vector from node0.
Yinghai
Quoted 29 lines · Yinghai Lu
Quoted 28 lines · Thomas Gleixner
Quoted 22 lines · Yinghai Lu
Quoted 9 lines
arch/x86/kernel/apic/io_apic.c | 5 +++++ 1 file changed, 5 insertions(+)Index:
linux/arch/x86/kernel/apic/io_apic.c
===================================================================arch/x86/kernel/apic/io_apic.c 2010-09-17 13:00:23.448595373 -0500 renamed from arch/x86/kernel/apic/io_apic.c 2010-09-17 13:00:19.164638447 -0500 +0
-0@@ -3253,6 +3253,11 @@ unsigned int create_irq_nr(unsigned int desc_new = move_irq_desc(desc_new, node);arch/x86/kernel/apic/io_apic.c 2010-09-17 13:00:23.448595373 -0500 unsigned int create_irq_nr(unsigned int · line 3263
Quoted 10 lines
arch/x86/kernel/apic/io_apic.c 2010-09-17 13:00:23.448595373 -0500 renamed from arch/x86/kernel/apic/io_apic.c 2010-09-17 13:00:19.164638447 -0500 +5
-0cfg_new = desc_new->chip_data; +#ifdef CONFIG_NUMA + if (node >= 0 && __assign_irq_vector(new, cfg_new, node_to_cpumask_map[node]) == 0) + irq = new; + else +#endif if (__assign_irq_vector(new, cfg_new, apic->target_cpus()) == 0) irq = new; break;
target_cpus()foruv_xand x2apic phys mode all havecpu_online_mask()Quoted 2 lines
so we should get the vector for other cpus. aka
__assign_irq_vector()should not fail. unless you have so many irq >nr_irqs.Did you even read the changelog ? It's not about "should".
Quoted 7 lines
Quoted 4 lines
All CPU0 vectors are assigned already just because the current code takes the first cpu in the
target_cpusmask regardless of the node on which theirq_descis allocated. That's crap. Why do we allocateirq_descon node and leave the vector assigned to node(cpu0) ?ok, i got it. vectors from cpus on node0 are used by devices from others nodes.
later devices from node0 can not get vector from node0.
Does that resolve all of your questions or are there still other issues.