x86: unify x86_32 and 64 NUMA init paths, take#2
Subsystems (4)
PATCH 1/1 x86: unify x86_32 and 64 NUMA init paths, take#2
Hello,
This is the second take of unify-x86_32-and-64-NUMA-init-paths patchset. Changes from the last take[L] are,
* As suggested by Ingo, 0004 from the previous series is further split into 0004-0011.
* Comment noting the ugliness of x86_32 logical apicid mapping difference added.
This patchset started as an attempt to fix percpu setup problem on x86_32 NUMA configurations reported by Eric Dumazet. On x86_32, NUMA configuration is initialized during SMP bringup which happens way later than percpu setup. As percpu setup code doesn't have access to NUMA configuration, it gets set up as if the system is UMA.
The NUMA init paths differ subtly yet significantly between x86_32 and 64 making it quite difficult to follow. Custom apic configurations on x86_32 worsens the problem.
There is no fundamental reason why x86_32 can't be initialized in the same steps as x86_64. They just were written differently and just weren't unified during x86_32/64 code merge. This patchset unifies them and in the process fixes percpu setup problem on 32bit NUMA.
This patchset contains the following sixteen patches.
0001-x86-Kill-unused-static-boot_cpu_logical_apicid-in-sm.patch 0002-x86-Rename-x86_32-MAX_APICID-to-MAX_LOCAL_APIC.patch 0003-x86-Make-default_send_IPI_mask_sequence-allbutself_l.patch 0004-x86-Use-local-variable-to-cache-smp_processor_id-in-.patch 0005-x86-Replace-cpu_2_logical_apicid-with-early-percpu-v.patch 0006-x86-Always-use-x86_cpu_to_logical_apicid-for-cpu-log.patch 0007-x86-Remove-custom-apic-cpu_to_logical_apicid-impleme.patch 0008-x86-Use-apic-cpu_to_logical_apicid-to-find-out-logic.patch 0009-x86-Implement-cpu_to_logical_apicid-for-bigsmp_32.patch 0010-x86-Implement-cpu_to_logical_apicid-for-summit_32.patch 0011-x86-Implement-cpu_to_logical_apicid-for-numaq_32.patch 0012-x86-Replace-apic-apicid_to_node-with-numa_cpu_node.patch 0013-x86-Unify-cpu-apicid-NUMA-node-mapping-between-32-an.patch 0014-x86-Unify-CPU-NUMA-node-mapping-between-32-and-64bit.patch 0015-x86-Unify-node_to_cpumask_map-handling-between-32-an.patch 0016-x86-Unify-NUMA-initialization-between-32-and-64bit.patch
0001-0004 are small preparation patches.
0005-0011 change the role of apic->cpu_to_logical_apicid(). It's now called once for each cpu early during boot and the output is recorded. apic works fine but I couldn't test other apic configurations.
I couldn't figure out how to determine logical_apicid early for numaq and it still has the stub cpu_to_logical_apicid() implementation which would result in suboptimal percpu configuration. NUMA configuration is still updated during SMP bringup, so the situation is the same as before the series, but if someone knows how to convert this one, please go ahead.
0005 replaces apic->apicid_to_node() with ->numa_cpu_node() as some need physical apicid while others logical and both can be easily found from cpu.
0006-0009 unify different parts of NUMA initialization/handling step by step. Afterwards, x86_32 and 64 behave mostly the same regarding NUMA initialization making the whole thing much easier to understand and percpu setup works correctly on x86_32 too.
This patchset is on top of the current mainline (19650e8580987c0ffabc2fe2cbc16b944789df8b) and also avaialbe in the following git branch,
git://git.kernel.org/pub/scm/linux/kernel/git/tj/misc.git x86_32-numa
and contains the following changes.
arch/x86/Kconfig | 2 arch/x86/include/asm/apic.h | 22 ++- arch/x86/include/asm/apicdef.h | 1 arch/x86/include/asm/ipi.h | 8 - arch/x86/include/asm/mpspec.h | 3 arch/x86/include/asm/numa.h | 61 ++++++++++ arch/x86/include/asm/numa_32.h | 7 - arch/x86/include/asm/numa_64.h | 16 -- arch/x86/include/asm/smp.h | 3 arch/x86/include/asm/topology.h | 17 -- arch/x86/kernel/acpi/boot.c | 8 - arch/x86/kernel/apic/apic.c | 52 ++++++-- arch/x86/kernel/apic/apic_flat_64.c | 4 arch/x86/kernel/apic/apic_noop.c | 4 arch/x86/kernel/apic/bigsmp_32.c | 33 ++--- arch/x86/kernel/apic/es7000_32.c | 33 ++--- arch/x86/kernel/apic/ipi.c | 12 - arch/x86/kernel/apic/numaq_32.c | 29 +++- arch/x86/kernel/apic/probe_32.c | 2 arch/x86/kernel/apic/summit_32.c | 46 ++----- arch/x86/kernel/apic/x2apic_cluster.c | 2 arch/x86/kernel/apic/x2apic_phys.c | 2 arch/x86/kernel/apic/x2apic_uv_x.c | 2 arch/x86/kernel/cpu/amd.c | 18 +- arch/x86/kernel/cpu/common.c | 2 arch/x86/kernel/cpu/intel.c | 5 arch/x86/kernel/setup.c | 2 arch/x86/kernel/setup_percpu.c | 11 + arch/x86/kernel/smpboot.c | 68 ----------- arch/x86/mm/k8topology_64.c | 2 arch/x86/mm/numa.c | 179 +++++++++++++++++++++++++++++ arch/x86/mm/numa_32.c | 7 + arch/x86/mm/numa_64.c | 205 ---------------------------------- arch/x86/mm/srat_32.c | 6 arch/x86/mm/srat_64.c | 10 - 35 files changed, 433 insertions(+), 451 deletions(-)
Thanks.
--
tejun
PATCH 1/16 x86: Kill unused static boot_cpu_logical_apicid in smpboot.c
--- arch/x86/kernel/smpboot.c | 6 +----- 1 files changed, 1 insertions(+), 5 deletions(-)
arch/x86/kernel/smpboot.c +1 -5
@@ -165,8 +165,6 @@ static void unmap_cpu_to_node(int cpu)#endif #ifdef CONFIG_X86_32 -static int boot_cpu_logical_apicid; -u8 cpu_2_logical_apicid[NR_CPUS ]__read_mostly = { [0 ...NR_CPUS -1 ] =BAD_APICID };
@@ -1101,9 +1099,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)* Setup boot CPU information */ smp_store_cpu_info (0 );/* Final full version of the data */ -#ifdef CONFIG_X86_32 - boot_cpu_logical_apicid =logical_smp_processor_id (); -#endif +current_thread_info ()->cpu =0 ;/* needed? */ for_each_possible_cpu (i) {zalloc_cpumask_var (&per_cpu (cpu_sibling_map, i),GFP_KERNEL );
Signature · 1 line
1.7.1
PATCH 2/16 x86: Rename x86_32 MAX_APICID to MAX_LOCAL_APIC
In reply to Tejun HeoReplace x86_32 MAX_APICID in include/asm/mpspec.h with MAX_LOCAL_APIC in include/asm/apicdef.h to make it consistent with x86_64.
--- arch/x86/include/asm/apicdef.h | 1 + arch/x86/include/asm/mpspec.h | 2 -- arch/x86/kernel/smpboot.c | 2 +- arch/x86/mm/srat_32.c | 4 ++-- 4 files changed, 4 insertions(+), 5 deletions(-)
arch/x86/include/asm/apicdef.h +1 -0
@@ -145,6 +145,7 @@#ifdef CONFIG_X86_32 # define MAX_IO_APICS 64 +# define MAX_LOCAL_APIC 256#else # define MAX_IO_APICS 128# define MAX_LOCAL_APIC 32768
arch/x86/include/asm/mpspec.h +0 -2
@@ -32,8 +32,6 @@ extern int mp_bus_id_to_local[MAX_MP_BUSSES];extern int quad_local_to_mp_bus_id [NR_CPUS /4 ][4 ];#endif -#define MAX_APICID 256 -#else /* CONFIG_X86_64: */ #define MAX_MP_BUSSES 256
arch/x86/kernel/smpboot.c +1 -1
@@ -72,7 +72,7 @@#include <asm/i8259.h> #ifdef CONFIG_X86_32 -u8 apicid_2_node[MAX_APICID ]; +u8 apicid_2_node[MAX_LOCAL_APIC ];#endif /* State of each CPU */
arch/x86/mm/srat_32.c +2 -2
@@ -57,7 +57,7 @@ struct node_memory_chunk_s {static struct node_memory_chunk_s __initdata node_memory_chunk[MAXCHUNKS ];static int __initdata num_memory_chunks;/* total number of memory chunks */ -static u8 __initdata apicid_to_pxm[MAX_APICID ]; +static u8 __initdata apicid_to_pxm[MAX_LOCAL_APIC ];int numa_off__initdata ;int acpi_numa__initdata ;
@@ -254,7 +254,7 @@ int __init get_memcfg_from_srat(void)printk (KERN_DEBUG "Number of memory chunks in system = %d\n" , num_memory_chunks); -for (i =0 ; i <MAX_APICID ; i++) +for (i =0 ; i <MAX_LOCAL_APIC ; i++) apicid_2_node[i] =pxm_to_node (apicid_to_pxm[i]);for (j =0 ; j < num_memory_chunks; j++){
Signature · 1 line
1.7.1
PATCH 3/16 x86: Make default_send_IPI_mask_sequence/allbutself_logical() 32bit only
In reply to Tejun HeoBoth functions are used only in 32bit. Put them inside CONFIG_X86_32. This is to prepare for logical apicid handling update.
- Cyrill Gorcunov spotted that I forgot to move declarations in ipi.h under CONFIG_X86_32. Fixed.
--- arch/x86/include/asm/ipi.h | 8 ++++---- arch/x86/kernel/apic/ipi.c | 4 ++-- 2 files changed, 6 insertions(+), 6 deletions(-)
arch/x86/include/asm/ipi.h +4 -4
@@ -123,10 +123,6 @@ extern void default_send_IPI_mask_sequence_phys(const struct cpumask *mask, int vector);extern void default_send_IPI_mask_allbutself_phys (const struct cpumask *mask,int vector); -extern void default_send_IPI_mask_sequence_logical (const struct cpumask *mask, -int vector); -extern void default_send_IPI_mask_allbutself_logical (const struct cpumask *mask, -int vector);/* Avoid include hell */ #define NMI_VECTOR 0x02
@@ -150,6 +146,10 @@ static inline void __default_local_send_IPI_all(int vector) }#ifdef CONFIG_X86_32 +extern void default_send_IPI_mask_sequence_logical (const struct cpumask *mask, +int vector); +extern void default_send_IPI_mask_allbutself_logical (const struct cpumask *mask, +int vector);extern void default_send_IPI_mask_logical (const struct cpumask *mask,int vector);extern void default_send_IPI_allbutself (int vector);
arch/x86/kernel/apic/ipi.c +2 -2
@@ -56,6 +56,8 @@ void default_send_IPI_mask_allbutself_phys(const struct cpumask *mask,local_irq_restore (flags); } +#ifdef CONFIG_X86_32 +void default_send_IPI_mask_sequence_logical (const struct cpumask *mask,int vector) {
@@ -96,8 +98,6 @@ void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask,local_irq_restore (flags); } -#ifdef CONFIG_X86_32 -/* * This is only used on smaller machines. */
Signature · 1 line
1.7.1
PATCH 4/16 x86: Use local variable to cache smp_processor_id() in setup_local_APIC()
In reply to Tejun HeoThis is a trivial clean up.
--- arch/x86/kernel/apic/apic.c | 13 ++++++------- 1 files changed, 6 insertions(+), 7 deletions(-)
arch/x86/kernel/apic/apic.c +6 -7
@@ -1201,6 +1201,7 @@ static void __cpuinit lapic_setup_esr(void)*/ void __cpuinit setup_local_APIC (void ) { +int cpu =smp_processor_id ();unsigned int value, queued;int i, j, acked =0 ;unsigned long long tsc =0 , ntsc;
@@ -1342,21 +1343,19 @@ void __cpuinit setup_local_APIC(void)* TODO: set up through-local-APIC from through-I/O-APIC? --macro */ value =apic_read (APIC_LVT0 ) &APIC_LVT_MASKED ; -if (!smp_processor_id () && (pic_mode || !value)) { +if (!cpu && (pic_mode || !value)) { value =APIC_DM_EXTINT ; -apic_printk (APIC_VERBOSE ,"enabled ExtINT on CPU#%d\n" , -smp_processor_id ()); +apic_printk (APIC_VERBOSE ,"enabled ExtINT on CPU#%d\n" , cpu); }else { value =APIC_DM_EXTINT |APIC_LVT_MASKED ; -apic_printk (APIC_VERBOSE ,"masked ExtINT on CPU#%d\n" , -smp_processor_id ()); +apic_printk (APIC_VERBOSE ,"masked ExtINT on CPU#%d\n" , cpu); }apic_write (APIC_LVT0 , value);/* * only the BP should see the LINT1 NMI signal, obviously. */ -if (!smp_processor_id ()) +if (!cpu) value =APIC_DM_NMI ;else value =APIC_DM_NMI |APIC_LVT_MASKED ;
@@ -1368,7 +1367,7 @@ void __cpuinit setup_local_APIC(void)#ifdef CONFIG_X86_MCE_INTEL /* Recheck CMCI information after local APIC is up on CPU #0 */ -if (smp_processor_id () ==0 ) +if (cpu ==0 )cmci_recheck ();#endif }
Signature · 1 line
1.7.1
Re: [PATCH 04/16] x86: Use local variable to cache smp_processor_id() in setup_local_APIC()
Quoted 8 lines · Tejun Heo
This is a trivial clean up.
Signed-off-by Tejun Heo <[email protected]>Cc Yinghai Lu <[email protected]>--- arch/x86/kernel/apic/apic.c | 13 ++++++------- 1 files changed, 6 insertions(+), 7 deletions(-)
Hi Tejun, I belive we should put in change log that it's
not a trivial change. The cpu gets cached before preemption disabled and used after preemption enabled, which is not 1:1 like it was before.
Though at moment all setup_local_APIC callers have preemption
disabled this might be changed in future and heck knows what side effect we would have :)
Perhaps the easiest would be to make cpu = smp_processor_id()
after preempt_disable() call and leave the last snippet in this function
#ifdef CONFIG_X86_MCE_INTEL /* Recheck CMCI information after local APIC is up on CPU #0 */ if (smp_processor_id() == 0) cmci_recheck();
#endif
untouched.
On the other hands I might be too paranoid ;)
Cyrill
PATCH 4/16 x86: Use local variable to cache smp_processor_id() in setup_local_APIC()
In reply to Tejun HeoSubject: x86: Use local variable to cache smp_processor_id() in setup_local_APIC()
This is a trivial clean up.
* Move initialization of @cpu inside preemption disabled region as suggested by Cyrill Gorcunov.
---
Updated as suggested. Git tree updated too.
Thanks.
arch/x86/kernel/apic/apic.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-)
arch/x86/kernel/apic/apic.c +7 -8
@@ -1202,7 +1202,7 @@ static void __cpuinit lapic_setup_esr(vovoid __cpuinit setup_local_APIC (void ) {unsigned int value, queued; -int i, j, acked =0 ; +int cpu, i, j, acked =0 ;unsigned long long tsc =0 , ntsc;long long max_loops = cpu_khz;
@@ -1226,6 +1226,7 @@ void __cpuinit setup_local_APIC(void)perf_events_lapic_init ();preempt_disable (); + cpu =smp_processor_id ();/* * Double-check whether this APIC is really registered.
@@ -1342,21 +1343,19 @@ void __cpuinit setup_local_APIC(void)* TODO: set up through-local-APIC from through-I/O-APIC? --macro */ value =apic_read (APIC_LVT0 ) &APIC_LVT_MASKED ; -if (!smp_processor_id () && (pic_mode || !value)) { +if (!cpu && (pic_mode || !value)) { value =APIC_DM_EXTINT ; -apic_printk (APIC_VERBOSE ,"enabled ExtINT on CPU#%d\n" , -smp_processor_id ()); +apic_printk (APIC_VERBOSE ,"enabled ExtINT on CPU#%d\n" , cpu); }else { value =APIC_DM_EXTINT |APIC_LVT_MASKED ; -apic_printk (APIC_VERBOSE ,"masked ExtINT on CPU#%d\n" , -smp_processor_id ()); +apic_printk (APIC_VERBOSE ,"masked ExtINT on CPU#%d\n" , cpu); }apic_write (APIC_LVT0 , value);/* * only the BP should see the LINT1 NMI signal, obviously. */ -if (!smp_processor_id ()) +if (!cpu) value =APIC_DM_NMI ;else value =APIC_DM_NMI |APIC_LVT_MASKED ;
@@ -1368,7 +1367,7 @@ void __cpuinit setup_local_APIC(void)#ifdef CONFIG_X86_MCE_INTEL /* Recheck CMCI information after local APIC is up on CPU #0 */ -if (smp_processor_id () ==0 ) +if (cpu ==0 )cmci_recheck ();#endif }
PATCH 4/16 x86: Use local variable to cache smp_processor_id() in setup_local_APIC()
In reply to Tejun HeoThis is a trivial clean up.
* Move initialization of @cpu inside preemption disabled region as suggested by Cyrill Gorcunov.
---
Alright, updated yet again, but I frankly don't see the point in these changes. If setup_local_APIC() is being run from a different CPU, we have a much larger problem. We're already accessing cpu local resources (tsc, lapic) outside of preemption disabled area. But, anyways, I don't think it matters one way or the other.
Thanks.
arch/x86/kernel/apic/apic.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-)
arch/x86/kernel/apic/apic.c +6 -7
@@ -1202,7 +1202,7 @@ static void __cpuinit lapic_setup_esr(vovoid __cpuinit setup_local_APIC (void ) {unsigned int value, queued; -int i, j, acked =0 ; +int cpu, i, j, acked =0 ;unsigned long long tsc =0 , ntsc;long long max_loops = cpu_khz;
@@ -1226,6 +1226,7 @@ void __cpuinit setup_local_APIC(void)perf_events_lapic_init ();preempt_disable (); + cpu =smp_processor_id ();/* * Double-check whether this APIC is really registered.
@@ -1342,21 +1343,19 @@ void __cpuinit setup_local_APIC(void)* TODO: set up through-local-APIC from through-I/O-APIC? --macro */ value =apic_read (APIC_LVT0 ) &APIC_LVT_MASKED ; -if (!smp_processor_id () && (pic_mode || !value)) { +if (!cpu && (pic_mode || !value)) { value =APIC_DM_EXTINT ; -apic_printk (APIC_VERBOSE ,"enabled ExtINT on CPU#%d\n" , -smp_processor_id ()); +apic_printk (APIC_VERBOSE ,"enabled ExtINT on CPU#%d\n" , cpu); }else { value =APIC_DM_EXTINT |APIC_LVT_MASKED ; -apic_printk (APIC_VERBOSE ,"masked ExtINT on CPU#%d\n" , -smp_processor_id ()); +apic_printk (APIC_VERBOSE ,"masked ExtINT on CPU#%d\n" , cpu); }apic_write (APIC_LVT0 , value);/* * only the BP should see the LINT1 NMI signal, obviously. */ -if (!smp_processor_id ()) +if (!cpu) value =APIC_DM_NMI ;else value =APIC_DM_NMI |APIC_LVT_MASKED ;
Re: [PATCH UPDATED#2 04/16] x86: Use local variable to cache smp_processor_id() in setup_local_APIC()
Quoted 10 lines · Tejun Heo
This is a trivial clean up.
* Move initialization of @cpu inside preemption disabled region as suggested by Cyrill Gorcunov.
Signed-off-by Tejun Heo <[email protected]>Cc Yinghai Lu <[email protected]>Cc Cyrill Gorcunov <[email protected]>---
Alright, updated yet again, but I frankly don't see the point in these
code structure, if we would be referring variable taken inside preempt off this always look suspicious, i think you agree with me :)
Quoted 7 lines
changes. If
setup_local_APIC()is being run from a different CPU, we have a much larger problem. We're already accessing cpu local resources (tsc, lapic) outside of preemption disabled area. But, anyways, I don't think it matters one way or the other.Thanks.
Re: [PATCH UPDATED#2 04/16] x86: Use local variable to cache smp_processor_id() in setup_local_APIC()
Quoted 6 lines · Cyrill Gorcunov
Quoted 5 lines · Tejun Heo
This is a trivial clean up.
* Move initialization of @cpu inside preemption disabled region as suggested by Cyrill Gorcunov.
Quoted 8 lines
Quoted 5 lines
Signed-off-by Tejun Heo <[email protected]>Cc Yinghai Lu <[email protected]>Cc Cyrill Gorcunov <[email protected]>---
Alright, updated yet again, but I frankly don't see the point in thesecode structure, if we would be referring variable taken inside preempt off this always look suspicious, i think you agree with me :)
Not really. smp_processor_id() outside of preemption/irq disabled area is suspicious exactly the same and having @cpu initialized at the head of the function has the advantage of making it clear that the function as a whole is special w.r.t. which cpu it runs on. In fact, I think it's actually worse to put it inside preemption disabled area as it gives the wrong impression that the function isn't special and might be able to handle being called from another cpu. In fact, caching smp_processor_id() in @cpu is better than calling it every time as it makes it clear that the function is bound to that cpu.
That said, I really don't think this matters one way or the other. This function is called during smp bring up to initialize the CPU. Things don't get much more arch/cpu dependent than this and the code is thoroughly tested on each and every boot and power management operations. How @cpu is cached and used just doesn't matter, which is why I didn't really care about it and changed as suggested. So, let's just let it go.
Thanks.
Signature · 1 line
tejun
Re: [PATCH UPDATED#2 04/16] x86: Use local variable to cache smp_processor_id() in setup_local_APIC()
On Tue, Nov 30, 2010 at 08:42:27PM +0100, Tejun Heo wrote:
...
Quoted 6 lines
Not really.
smp_processor_id()outside of preemption/irq disabled area is suspicious exactly the same and having @cpu initialized at the head of the function has the advantage of making it clear that the function as a whole is special w.r.t. which cpu it runs on. In fact, I think it's actually worse to put it inside preemption disabled area as it gives the wrong impression that the function isn't special and
well, i take the opposite, if function is not ever supposed to be called outside of cpu it runs on there should not be references even in local variables outside of preempt scope (even if we know that it is safe to cache 'cpu' early), but I think this is a question of habbit :)
Quoted 11 lines
might be able to handle being called from another cpu. In fact, caching
smp_processor_id()in @cpu is better than calling it every time as it makes it clear that the function is bound to that cpu.That said, I really don't think this matters one way or the other. This function is called during smp bring up to initialize the CPU. Things don't get much more
arch/cpudependent than this and the code is thoroughly tested on each and every boot and power management operations. How @cpu is cached and used just doesn't matter, which is why I didn't really care about it and changed as suggested. So, let's just let it go.
*sure*, as one Ingo merge it we would be able to clean it a bit on top
[ in particular I believe we should preempt disable at the very beginning
on the function and use cached cpu then until the preemption gets on at the end, and we would cover cmci_recheck with cached cpu as well. this would eliminate all the questions I believe ]
Quoted 6 lines
Thanks.
Signature · 1 line
tejun
Cyrill
Re: [PATCH UPDATED#2 04/16] x86: Use local variable to cache smp_processor_id() in setup_local_APIC()
In reply to Tejun HeoQuoted 8 lines · Tejun Heo
This is a trivial clean up.
* Move initialization of @cpu inside preemption disabled region as suggested by Cyrill Gorcunov.
Signed-off-by Tejun Heo <[email protected]>Cc Yinghai Lu <[email protected]>Cc Cyrill Gorcunov <[email protected]>
PATCH 4/16 x86: setup_local_APIC() must always be called with preemption disabled
In reply to Tejun Heosetup_local_APIC() is used to setup local APIC early during CPU initialization and already assumes that preemption is disabled on entry. However, The function unnecessarily disables and enables preemption and uses smp_processor_id() multiple times in and out of the nested preemption disabled section. This gives the wrong impression that the function might be able to handle being called with preemption enabled and/or migrated to another processor in the middle.
Make it clear that the function is always called with preemption disabled, drop the confusing preemption disable block and call smp_processor_id() once at the beginning of the function.
---
As this function is causing undue confusion, let's go one step further and make clear that it can't handle and was never meant to be called with preemption enabled or migrated to another CPU in the middle.
The rest of series applies fine with this change and the git tree is updated accordingly.
git://git.kernel.org/pub/scm/linux/kernel/git/tj/misc.git x86_32-numa
Thanks.
arch/x86/kernel/apic/apic.c | 21 +++++++++------------ 1 file changed, 9 insertions(+), 12 deletions(-)
arch/x86/kernel/apic/apic.c +9 -12
@@ -1195,12 +1195,15 @@ static void __cpuinit lapic_setup_esr(vo oldvalue, value); } -/** * setup_local_APIC - setup the local APIC +* +* Used to setup local APIC while initializing BSP or bringin up APs. +* Always called with preemption disabled. */ void __cpuinit setup_local_APIC (void ) { +int cpu =smp_processor_id ();unsigned int value, queued;int i, j, acked =0 ;unsigned long long tsc =0 , ntsc;
@@ -1225,8 +1228,6 @@ void __cpuinit setup_local_APIC(void)#endif perf_events_lapic_init (); -preempt_disable (); -/* * Double-check whether this APIC is really registered. * This is meaningless in clustered apic mode, so we skip it.
@@ -1342,21 +1343,19 @@ void __cpuinit setup_local_APIC(void)* TODO: set up through-local-APIC from through-I/O-APIC? --macro */ value =apic_read (APIC_LVT0 ) &APIC_LVT_MASKED ; -if (!smp_processor_id () && (pic_mode || !value)) { +if (!cpu && (pic_mode || !value)) { value =APIC_DM_EXTINT ; -apic_printk (APIC_VERBOSE ,"enabled ExtINT on CPU#%d\n" , -smp_processor_id ()); +apic_printk (APIC_VERBOSE ,"enabled ExtINT on CPU#%d\n" , cpu); }else { value =APIC_DM_EXTINT |APIC_LVT_MASKED ; -apic_printk (APIC_VERBOSE ,"masked ExtINT on CPU#%d\n" , -smp_processor_id ()); +apic_printk (APIC_VERBOSE ,"masked ExtINT on CPU#%d\n" , cpu); }apic_write (APIC_LVT0 , value);/* * only the BP should see the LINT1 NMI signal, obviously. */ -if (!smp_processor_id ()) +if (!cpu) value =APIC_DM_NMI ;else value =APIC_DM_NMI |APIC_LVT_MASKED ;
@@ -1364,11 +1363,9 @@ void __cpuinit setup_local_APIC(void) value |=APIC_LVT_LEVEL_TRIGGER ;apic_write (APIC_LVT1 , value); -preempt_enable (); -#ifdef CONFIG_X86_MCE_INTEL /* Recheck CMCI information after local APIC is up on CPU #0 */ -if (smp_processor_id () ==0 ) +if (!cpu)cmci_recheck ();#endif }
Re: [PATCH UPDATED#3 04/16] x86: setup_local_APIC() must always be called with preemption disabled
Quoted 12 lines · Tejun Heo
setup_local_APIC()is used to setup local APIC early during CPU initialization and already assumes that preemption is disabled on entry. However, The function unnecessarily disables and enables preemption and usessmp_processor_id()multiple times in and out of the nested preemption disabled section. This gives the wrong impression that the function might be able to handle being called with preemption enabled and/or migrated to another processor in the middle.Make it clear that the function is always called with preemption disabled, drop the confusing preemption disable block and call
smp_processor_id()once at the beginning of the function.
Quoted 5 lines
Signed-off-by Tejun Heo <[email protected]>Cc Yinghai Lu <[email protected]>Cc Cyrill Gorcunov <[email protected]>Cc Pekka Enberg <[email protected]>---
Thanks a lot, Tejun!
FWIW
Re: [PATCH UPDATED#3 04/16] x86: setup_local_APIC() must always be called with preemption disabled
In reply to Tejun HeoQuoted 8 lines · Tejun Heo
setup_local_APIC()is used to setup local APIC early during CPU initialization and already assumes that preemption is disabled on entry. However, The function unnecessarily disables and enables preemption and usessmp_processor_id()multiple times in and out of the nested preemption disabled section. This gives the wrong impression that the function might be able to handle being called with preemption enabled and/or migrated to another processor in the middle.
Quoted 8 lines
Make it clear that the function is always called with preemption disabled, drop the confusing preemption disable block and call
smp_processor_id()once at the beginning of the function.Signed-off-by Tejun Heo <[email protected]>Cc Yinghai Lu <[email protected]>Cc Cyrill Gorcunov <[email protected]>Cc Pekka Enberg <[email protected]>
Re: [PATCH UPDATED#3 04/16] x86: setup_local_APIC() must always be called with preemption disabled
In reply to Tejun HeoQuoted 11 lines · Tejun Heo
setup_local_APIC()is used to setup local APIC early during CPU initialization and already assumes that preemption is disabled on entry. However, The function unnecessarily disables and enables preemption and usessmp_processor_id()multiple times in and out of the nested preemption disabled section. This gives the wrong impression that the function might be able to handle being called with preemption enabled and/or migrated to another processor in the middle.Make it clear that the function is always called with preemption disabled, drop the confusing preemption disable block and call
smp_processor_id()once at the beginning of the function.
AFAICT, this one is completely unrelated to that NUMA cleanup, right ?
So this can be applied independent and should never have been part of that NUMA series in the first place.
Thanks,
tglx
Re: [PATCH UPDATED#3 04/16] x86: setup_local_APIC() must always be called with preemption disabled
Quoted 10 lines · Thomas Gleixner
Quoted 8 lines · Tejun Heo
setup_local_APIC()is used to setup local APIC early during CPU initialization and already assumes that preemption is disabled on entry. However, The function unnecessarily disables and enables preemption and usessmp_processor_id()multiple times in and out of the nested preemption disabled section. This gives the wrong impression that the function might be able to handle being called with preemption enabled and/or migrated to another processor in the middle.
Quoted 8 lines
Quoted 3 lines
Make it clear that the function is always called with preemption disabled, drop the confusing preemption disable block and call
smp_processor_id()once at the beginning of the function.AFAICT, this one is completely unrelated to that NUMA cleanup, right ?
So this can be applied independent and should never have been part of that NUMA series in the first place.
Originally, it was a trivial prep patch. Anyways, I'll push it to the top of the series so that it can be taken separately.
Thanks.
Signature · 1 line
tejun
Re: [PATCH UPDATED#3 04/16] x86: setup_local_APIC() must always be called with preemption disabled
Quoted 15 lines · Tejun Heo
Quoted 14 lines · Thomas Gleixner
Quoted 11 lines · Tejun Heo
setup_local_APIC()is used to setup local APIC early during CPU initialization and already assumes that preemption is disabled on entry. However, The function unnecessarily disables and enables preemption and usessmp_processor_id()multiple times in and out of the nested preemption disabled section. This gives the wrong impression that the function might be able to handle being called with preemption enabled and/or migrated to another processor in the middle.Make it clear that the function is always called with preemption disabled, drop the confusing preemption disable block and call
smp_processor_id()once at the beginning of the function.
Quoted 7 lines
Quoted 4 lines
AFAICT, this one is completely unrelated to that NUMA cleanup, right ?
So this can be applied independent and should never have been part of that NUMA series in the first place.
Originally, it was a trivial prep patch. Anyways, I'll push it to the top of the series so that it can be taken separately.
I pick it up from mail.
Thanks,
tglx
[tip:x86/apic-cleanups] x86: apic: Cleanup and simplify setup_local_APIC()
In reply to Tejun HeoCommit-ID: 0aa002fe602939370e9476e5ec32b562000a0425 Gitweb: http://git.kernel.org/tip/0aa002fe602939370e9476e5ec32b562000a0425 Author: Tejun Heo <[email protected]> AuthorDate: Thu, 9 Dec 2010 11:47:21 +0100 Committer: Thomas Gleixner <[email protected]> CommitDate: Fri, 10 Dec 2010 13:46:26 +0100
x86: apic: Cleanup and simplify setup_local_APIC()
setup_local_APIC() is used to setup local APIC early during CPU initialization and already assumes that preemption is disabled on entry. However, The function unnecessarily disables and enables preemption and uses smp_processor_id() multiple times in and out of the nested preemption disabled section. This gives the wrong impression that the function might be able to handle being called with preemption enabled and/or migrated to another processor in the middle.
Make it clear that the function is always called with preemption disabled, drop the confusing preemption disable block and call smp_processor_id() once at the beginning of the function.
LKML-Reference: <[email protected]>
--- arch/x86/kernel/apic/apic.c | 21 +++++++++------------ 1 files changed, 9 insertions(+), 12 deletions(-)
arch/x86/kernel/apic/apic.c +9 -12
@@ -1195,12 +1195,15 @@ static void __cpuinit lapic_setup_esr(void) oldvalue, value); } -/** * setup_local_APIC - setup the local APIC +* +* Used to setup local APIC while initializing BSP or bringin up APs. +* Always called with preemption disabled. */ void __cpuinit setup_local_APIC (void ) { +int cpu =smp_processor_id ();unsigned int value, queued;int i, j, acked =0 ;unsigned long long tsc =0 , ntsc;
@@ -1225,8 +1228,6 @@ void __cpuinit setup_local_APIC(void)#endif perf_events_lapic_init (); -preempt_disable (); -/* * Double-check whether this APIC is really registered. * This is meaningless in clustered apic mode, so we skip it.
@@ -1342,21 +1343,19 @@ void __cpuinit setup_local_APIC(void)* TODO: set up through-local-APIC from through-I/O-APIC? --macro */ value =apic_read (APIC_LVT0 ) &APIC_LVT_MASKED ; -if (!smp_processor_id () && (pic_mode || !value)) { +if (!cpu && (pic_mode || !value)) { value =APIC_DM_EXTINT ; -apic_printk (APIC_VERBOSE ,"enabled ExtINT on CPU#%d\n" , -smp_processor_id ()); +apic_printk (APIC_VERBOSE ,"enabled ExtINT on CPU#%d\n" , cpu); }else { value =APIC_DM_EXTINT |APIC_LVT_MASKED ; -apic_printk (APIC_VERBOSE ,"masked ExtINT on CPU#%d\n" , -smp_processor_id ()); +apic_printk (APIC_VERBOSE ,"masked ExtINT on CPU#%d\n" , cpu); }apic_write (APIC_LVT0 , value);/* * only the BP should see the LINT1 NMI signal, obviously. */ -if (!smp_processor_id ()) +if (!cpu) value =APIC_DM_NMI ;else value =APIC_DM_NMI |APIC_LVT_MASKED ;
@@ -1364,11 +1363,9 @@ void __cpuinit setup_local_APIC(void) value |=APIC_LVT_LEVEL_TRIGGER ;apic_write (APIC_LVT1 , value); -preempt_enable (); -#ifdef CONFIG_X86_MCE_INTEL /* Recheck CMCI information after local APIC is up on CPU #0 */ -if (smp_processor_id () ==0 ) +if (!cpu)cmci_recheck ();#endif }
PATCH 5/16 x86: Replace cpu_2_logical_apicid[] with early percpu variable
In reply to Tejun HeoUnlike x86_64, on x86_32, the mapping from cpu to logical apicid may vary depending on apic in use. cpu_2_logical_apicid[] array is used for this mapping. Replace it with early percpu variable x86_cpu_to_logical_apicid to make it better aligned with other mappings.
--- arch/x86/include/asm/apic.h | 4 ---- arch/x86/include/asm/smp.h | 3 +++ arch/x86/kernel/apic/apic.c | 11 +++++++++++ arch/x86/kernel/apic/es7000_32.c | 2 +- arch/x86/kernel/apic/numaq_32.c | 2 +- arch/x86/kernel/apic/summit_32.c | 4 ++-- arch/x86/kernel/setup_percpu.c | 7 +++++++ arch/x86/kernel/smpboot.c | 7 ++----- 8 files changed, 27 insertions(+), 13 deletions(-)
arch/x86/include/asm/apic.h +0 -4
@@ -594,8 +594,4 @@ extern int default_check_phys_apicid_present(int phys_apicid);#endif /* CONFIG_X86_LOCAL_APIC */ -#ifdef CONFIG_X86_32 -extern u8 cpu_2_logical_apicid[NR_CPUS ]; -#endif -#endif /* _ASM_X86_APIC_H */
arch/x86/include/asm/smp.h +3 -0
@@ -38,6 +38,9 @@ static inline struct cpumask *cpu_core_mask(int cpu)DECLARE_EARLY_PER_CPU (u16, x86_cpu_to_apicid);DECLARE_EARLY_PER_CPU (u16, x86_bios_cpu_apicid); +#if defined(CONFIG_SMP ) && defined(CONFIG_X86_32 ) +DECLARE_EARLY_PER_CPU (int, x86_cpu_to_logical_apicid); +#endif /* Static state in head.S used to set up a CPU */ extern struct {
arch/x86/kernel/apic/apic.c +11 -0
@@ -79,6 +79,17 @@ EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_apicid);EXPORT_EARLY_PER_CPU_SYMBOL (x86_bios_cpu_apicid);#ifdef CONFIG_X86_32 + +#ifdef CONFIG_SMP +/* +* On x86_32, the mapping between cpu and logical apicid may vary +* depending on apic in use. The following early percpu variable is +* used for the mapping. This is where the behaviors of x86_64 and 32 +* actually diverge. Let's keep it ugly for now. +*/ +DEFINE_EARLY_PER_CPU (int, x86_cpu_to_logical_apicid,BAD_APICID ); +#endif +/* * Knob to control our willingness to enable the local APIC. *
arch/x86/kernel/apic/es7000_32.c +1 -1
@@ -534,7 +534,7 @@ static int es7000_cpu_to_logical_apicid(int cpu)#ifdef CONFIG_SMP if (cpu >= nr_cpu_ids)return BAD_APICID ; -return cpu_2_logical_apicid[cpu]; +return early_per_cpu (x86_cpu_to_logical_apicid, cpu);#else return logical_smp_processor_id ();#endif
arch/x86/kernel/apic/numaq_32.c +1 -1
@@ -377,7 +377,7 @@ static inline int numaq_cpu_to_logical_apicid(int cpu) {if (cpu >= nr_cpu_ids)return BAD_APICID ; -return cpu_2_logical_apicid[cpu]; +return early_per_cpu (x86_cpu_to_logical_apicid, cpu); }/*
arch/x86/kernel/apic/summit_32.c +2 -2
@@ -206,7 +206,7 @@ static void summit_init_apic_ldr(void)/* Create logical APIC IDs by counting CPUs already in cluster. */ for (count =0 , i = nr_cpu_ids; --i >=0 ; ) { - lid = cpu_2_logical_apicid[i]; + lid =early_per_cpu (x86_cpu_to_logical_apicid, i);if (lid !=BAD_APICID &&APIC_CLUSTER (lid) == my_cluster) ++count; }
@@ -247,7 +247,7 @@ static inline int summit_cpu_to_logical_apicid(int cpu)#ifdef CONFIG_SMP if (cpu >= nr_cpu_ids)return BAD_APICID ; -return cpu_2_logical_apicid[cpu]; +return early_per_cpu (x86_cpu_to_logical_apicid, cpu);#else return logical_smp_processor_id ();#endif
arch/x86/kernel/setup_percpu.c +7 -0
@@ -225,6 +225,10 @@ void __init setup_per_cpu_areas(void)per_cpu (x86_bios_cpu_apicid, cpu) =early_per_cpu_map (x86_bios_cpu_apicid, cpu);#endif +#ifdef CONFIG_X86_32 +per_cpu (x86_cpu_to_logical_apicid, cpu) = +early_per_cpu_map (x86_cpu_to_logical_apicid, cpu); +#endif #ifdef CONFIG_X86_64 per_cpu (irq_stack_ptr, cpu) = per_cpu(irq_stack_union.irq_stack, cpu) +
@@ -256,6 +260,9 @@ void __init setup_per_cpu_areas(void)early_per_cpu_ptr (x86_cpu_to_apicid) =NULL ;early_per_cpu_ptr (x86_bios_cpu_apicid) =NULL ;#endif +#ifdef CONFIG_X86_32 +early_per_cpu_ptr (x86_cpu_to_logical_apicid) =NULL ; +#endif #if defined(CONFIG_X86_64 ) && defined(CONFIG_NUMA )early_per_cpu_ptr (x86_cpu_to_node_map) =NULL ;#endif
arch/x86/kernel/smpboot.c +2 -5
@@ -165,9 +165,6 @@ static void unmap_cpu_to_node(int cpu)#endif #ifdef CONFIG_X86_32 -u8 cpu_2_logical_apicid[NR_CPUS ]__read_mostly = - { [0 ...NR_CPUS -1 ] =BAD_APICID }; -static void map_cpu_to_logical_apicid (void ) {int cpu =smp_processor_id ();
@@ -177,13 +174,13 @@ static void map_cpu_to_logical_apicid(void)if (!node_online (node)) node = first_online_node; - cpu_2_logical_apicid[cpu] = apicid; +early_per_cpu (x86_cpu_to_logical_apicid, cpu) = apicid; map_cpu_to_node(cpu, node); }void numa_remove_cpu (int cpu) { - cpu_2_logical_apicid[cpu] =BAD_APICID ; +early_per_cpu (x86_cpu_to_logical_apicid, cpu) =BAD_APICID ;unmap_cpu_to_node (cpu); }#else
Signature · 1 line
1.7.1
PATCH 6/16 x86: Always use x86_cpu_to_logical_apicid for cpu -> logical apic id
In reply to Tejun HeoCurrently, cpu -> logical apic id translation is done by apic->cpu_to_logical_apicid() callback which may or may not use x86_cpu_to_logical_apicid. This is unnecessary as it should always equal logical_smp_processor_id() which is known early during CPU bring up.
Initialize x86_cpu_to_logical_apicid after apic->init_apic_ldr() in setup_local_APIC() and always use x86_cpu_to_logical_apicid for cpu -> logical apic id mapping.
--- arch/x86/kernel/apic/apic.c | 8 ++++++++ arch/x86/kernel/apic/ipi.c | 8 ++++---- arch/x86/kernel/smpboot.c | 7 +++---- 3 files changed, 15 insertions(+), 8 deletions(-)
arch/x86/kernel/apic/apic.c +8 -0
@@ -1252,6 +1252,14 @@ void __cpuinit setup_local_APIC(void)*/ apic->init_apic_ldr (); +#ifdef CONFIG_X86_32 +/* +* APIC LDR is initialized. Fetch and store logical_apic_id. +*/ +early_per_cpu (x86_cpu_to_logical_apicid, cpu) = +logical_smp_processor_id (); +#endif +/* * Set Task Priority to 'accept all'. We never change this * later on.
arch/x86/kernel/apic/ipi.c +4 -4
@@ -73,8 +73,8 @@ void default_send_IPI_mask_sequence_logical(const struct cpumask *mask,local_irq_save (flags);for_each_cpu (query_cpu, mask)__default_send_IPI_dest_field ( - apic->cpu_to_logical_apicid (query_cpu), vector, - apic->dest_logical); +early_per_cpu (x86_cpu_to_logical_apicid, query_cpu), + vector, apic->dest_logical);local_irq_restore (flags); }
@@ -92,8 +92,8 @@ void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask,if (query_cpu == this_cpu)continue ;__default_send_IPI_dest_field ( - apic->cpu_to_logical_apicid (query_cpu), vector, - apic->dest_logical); +early_per_cpu (x86_cpu_to_logical_apicid, query_cpu), + vector, apic->dest_logical); }local_irq_restore (flags); }
arch/x86/kernel/smpboot.c +3 -4
@@ -168,19 +168,18 @@ static void unmap_cpu_to_node(int cpu)static void map_cpu_to_logical_apicid (void ) {int cpu =smp_processor_id (); -int apicid =logical_smp_processor_id (); -int node = apic->apicid_to_node (apicid); +int logical_apicid =early_per_cpu (x86_cpu_to_logical_apicid, cpu); +int node; + node = apic->apicid_to_node (logical_apicid);if (!node_online (node)) node = first_online_node; -early_per_cpu (x86_cpu_to_logical_apicid, cpu) = apicid;map_cpu_to_node (cpu, node); }void numa_remove_cpu (int cpu) { -early_per_cpu (x86_cpu_to_logical_apicid, cpu) =BAD_APICID ;unmap_cpu_to_node (cpu); }#else
Signature · 1 line
1.7.1
PATCH 7/16 x86: Remove custom apic->cpu_to_logical_apicid() implementations
In reply to Tejun HeoAfter the previous patch, apic->cpu_to_logical_apicid() is no longer used. The callback will be repurposed. Remove all the custom implementations from bigsmp_32, es7000_32, numaq_32 and summit_32.
The removals are straight forward. The function is removed and if it's used elsewhere in the apic implementation, its users are modified to do the mapping directly.
#ifdef's on CONFIG_SMP in es7000_32 summit_32 are ignored during conversion as they are not used for UP kernels.
--- arch/x86/kernel/apic/bigsmp_32.c | 19 +++++++------------ arch/x86/kernel/apic/es7000_32.c | 18 ++---------------- arch/x86/kernel/apic/numaq_32.c | 8 -------- arch/x86/kernel/apic/summit_32.c | 17 ++--------------- 4 files changed, 11 insertions(+), 51 deletions(-)
arch/x86/kernel/apic/bigsmp_32.c +7 -12
@@ -93,14 +93,6 @@ static int bigsmp_cpu_present_to_apicid(int mps_cpu)return BAD_APICID ; } -/* Mapping from cpu number to logical apicid */ -static inline int bigsmp_cpu_to_logical_apicid (int cpu) -{ -if (cpu >= nr_cpu_ids) -return BAD_APICID ; -return cpu_physical_id (cpu); -} -static void bigsmp_ioapic_phys_id_map (physid_mask_t *phys_map,physid_mask_t *retmap) {/* For clustered we don't have a good way to do this yet - hack */
@@ -115,7 +107,11 @@ static int bigsmp_check_phys_apicid_present(int phys_apicid)/* As we are using single CPU as destination, pick only one CPU here */ static unsigned int bigsmp_cpu_mask_to_apicid (const struct cpumask *cpumask) { -return bigsmp_cpu_to_logical_apicid (cpumask_first (cpumask)); +int cpu =cpumask_first (cpumask); + +if (cpu < nr_cpu_ids) +return cpu_physical_id (cpu); +return BAD_APICID ; } static unsigned int bigsmp_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
@@ -129,9 +125,9 @@ static unsigned int bigsmp_cpu_mask_to_apicid_and(const struct cpumask *cpumask,*/ for_each_cpu_and (cpu, cpumask, andmask) {if (cpumask_test_cpu (cpu, cpu_online_mask)) -break ; +return cpu_physical_id (cpu); } -return bigsmp_cpu_to_logical_apicid (cpu); +return BAD_APICID ; }static int bigsmp_phys_pkg_id (int cpuid_apic,int index_msb)
@@ -220,7 +216,6 @@ struct apic apic_bigsmp = { .setup_apic_routing = bigsmp_setup_apic_routing, .multi_timer_check = NULL, .apicid_to_node = bigsmp_apicid_to_node, - .cpu_to_logical_apicid = bigsmp_cpu_to_logical_apicid, .cpu_present_to_apicid = bigsmp_cpu_present_to_apicid, .apicid_to_cpu_present = physid_set_mask_of_physid, .setup_portio_remap = NULL,
arch/x86/kernel/apic/es7000_32.c +2 -16
@@ -528,18 +528,6 @@ static void es7000_apicid_to_cpu_present(int phys_apicid, physid_mask_t *retmap) ++cpu_id; } -/* Mapping from cpu number to logical apicid */ -static int es7000_cpu_to_logical_apicid (int cpu) -{ -#ifdef CONFIG_SMP -if (cpu >= nr_cpu_ids) -return BAD_APICID ; -return early_per_cpu (x86_cpu_to_logical_apicid, cpu); -#else -return logical_smp_processor_id (); -#endif -} -static void es7000_ioapic_phys_id_map (physid_mask_t *phys_map,physid_mask_t *retmap) {/* For clustered we don't have a good way to do this yet - hack */
@@ -561,7 +549,7 @@ static unsigned int es7000_cpu_mask_to_apicid(const struct cpumask *cpumask)* The cpus in the mask must all be on the apic cluster. */ for_each_cpu (cpu, cpumask) { -int new_apicid =es7000_cpu_to_logical_apicid (cpu); +int new_apicid =early_per_cpu (x86_cpu_to_logical_apicid, cpu);if (round &&APIC_CLUSTER (apicid) !=APIC_CLUSTER (new_apicid)) {WARN (1 ,"Not a valid mask!" );
@@ -578,7 +566,7 @@ static unsigned int es7000_cpu_mask_to_apicid_and(const struct cpumask *inmask, const struct cpumask *andmask) { - int apicid = es7000_cpu_to_logical_apicid(0); + int apicid = early_per_cpu(x86_cpu_to_logical_apicid, 0);cpumask_var_t cpumask;if (!alloc_cpumask_var (&cpumask,GFP_ATOMIC ))
@@ -656,7 +644,6 @@ struct apic __refdata apic_es7000_cluster = { .setup_apic_routing = es7000_setup_apic_routing, .multi_timer_check = NULL, .apicid_to_node = es7000_apicid_to_node, - .cpu_to_logical_apicid = es7000_cpu_to_logical_apicid, .cpu_present_to_apicid = es7000_cpu_present_to_apicid, .apicid_to_cpu_present = es7000_apicid_to_cpu_present, .setup_portio_remap = NULL,
@@ -721,7 +708,6 @@ struct apic __refdata apic_es7000 = { .setup_apic_routing = es7000_setup_apic_routing, .multi_timer_check = NULL, .apicid_to_node = es7000_apicid_to_node, - .cpu_to_logical_apicid = es7000_cpu_to_logical_apicid, .cpu_present_to_apicid = es7000_cpu_present_to_apicid, .apicid_to_cpu_present = es7000_apicid_to_cpu_present, .setup_portio_remap = NULL,
arch/x86/kernel/apic/numaq_32.c +0 -8
@@ -373,13 +373,6 @@ static inline void numaq_ioapic_phys_id_map(physid_mask_t *phys_map, physid_maskreturn physids_promote (0xFUL , retmap); } -static inline int numaq_cpu_to_logical_apicid (int cpu) -{ -if (cpu >= nr_cpu_ids) -return BAD_APICID ; -return early_per_cpu (x86_cpu_to_logical_apicid, cpu); -} -/* * Supporting over 60 cpus on NUMA-Q requires a locality-dependent * cpu to APIC ID relation to properly interact with the intelligent
@@ -509,7 +502,6 @@ struct apic __refdata apic_numaq = { .setup_apic_routing = numaq_setup_apic_routing, .multi_timer_check = numaq_multi_timer_check, .apicid_to_node = numaq_apicid_to_node, - .cpu_to_logical_apicid = numaq_cpu_to_logical_apicid, .cpu_present_to_apicid = numaq_cpu_present_to_apicid, .apicid_to_cpu_present = numaq_apicid_to_cpu_present, .setup_portio_remap = numaq_setup_portio_remap,
arch/x86/kernel/apic/summit_32.c +2 -15
@@ -241,18 +241,6 @@ static int summit_apicid_to_node(int logical_apicid)#endif } -/* Mapping from cpu number to logical apicid */ -static inline int summit_cpu_to_logical_apicid (int cpu) -{ -#ifdef CONFIG_SMP -if (cpu >= nr_cpu_ids) -return BAD_APICID ; -return early_per_cpu (x86_cpu_to_logical_apicid, cpu); -#else -return logical_smp_processor_id (); -#endif -} -static int summit_cpu_present_to_apicid (int mps_cpu) {if (mps_cpu < nr_cpu_ids)
@@ -286,7 +274,7 @@ static unsigned int summit_cpu_mask_to_apicid(const struct cpumask *cpumask)* The cpus in the mask must all be on the apic cluster. */ for_each_cpu (cpu, cpumask) { -int new_apicid =summit_cpu_to_logical_apicid (cpu); +int new_apicid =early_per_cpu (x86_cpu_to_logical_apicid, cpu);if (round &&APIC_CLUSTER (apicid) !=APIC_CLUSTER (new_apicid)) {printk ("%s: Not a valid mask!\n" , __func__);
@@ -301,7 +289,7 @@ static unsigned int summit_cpu_mask_to_apicid(const struct cpumask *cpumask)static unsigned int summit_cpu_mask_to_apicid_and (const struct cpumask *inmask,const struct cpumask *andmask) { -int apicid =summit_cpu_to_logical_apicid (0 ); +int apicid =early_per_cpu (x86_cpu_to_logical_apicid,0 );cpumask_var_t cpumask;if (!alloc_cpumask_var (&cpumask,GFP_ATOMIC ))
@@ -529,7 +517,6 @@ struct apic apic_summit = { .setup_apic_routing = summit_setup_apic_routing, .multi_timer_check = NULL, .apicid_to_node = summit_apicid_to_node, - .cpu_to_logical_apicid = summit_cpu_to_logical_apicid, .cpu_present_to_apicid = summit_cpu_present_to_apicid, .apicid_to_cpu_present = summit_apicid_to_cpu_present, .setup_portio_remap = NULL,
Signature · 1 line
1.7.1
Re: [PATCH 07/16] x86: Remove custom apic->cpu_to_logical_apicid() implementations
Quoted 2 lines · Tejun Heo
After the previous patch,
apic->cpu_to_logical_apicid()is no longer used. The callback will be repurposed. Remove all the custom
That's a very bad idea. You remove the callbacks from the esoteric platforms, but you keep the other implementation in the tree.
It's not longer used now, so remove all incarnations and get rid of all those useless = NULL initializations at the same time. Then implement a new callback with a different name.
It's slightly more work and code churn, but it makes the change entirely clear. It'd be also nice to annotate in the function name that this is 32bit only or even make it 32bit dependent if it's not too much ifdeffery
Thanks,
tglx
Re: [PATCH 07/16] x86: Remove custom apic->cpu_to_logical_apicid() implementations
Hello, Thomas.
Quoted 9 lines · Thomas Gleixner
Quoted 2 lines
After the previous patch,
apic->cpu_to_logical_apicid()is no longer used. The callback will be repurposed. Remove all the customThat's a very bad idea. You remove the callbacks from the esoteric platforms, but you keep the other implementation in the tree.
It's not longer used now, so remove all incarnations and get rid of all those useless = NULL initializations at the same time. Then implement a new callback with a different name.
Yeah, that would be cleaner. I wasn't very sure about clearing unimplemented apic ops. Currently the rule seems to be always setting them to NULL and I didn't want to re-do that with a new callback.
Quoted 4 lines
It's slightly more work and code churn, but it makes the change entirely clear. It'd be also nice to annotate in the function name that this is 32bit only or even make it 32bit dependent if it's not too much ifdeffery
Yeah, sure, if the silly NULL assignments aren't necessary, I don't think it would be much more churn anyway.
Thanks.
Signature · 1 line
tejun
Re: [PATCH 07/16] x86: Remove custom apic->cpu_to_logical_apicid() implementations
Quoted 17 lines · Tejun Heo
Hello, Thomas.
Quoted 9 lines · Thomas Gleixner
Quoted 2 lines
After the previous patch,
apic->cpu_to_logical_apicid()is no longer used. The callback will be repurposed. Remove all the customThat's a very bad idea. You remove the callbacks from the esoteric platforms, but you keep the other implementation in the tree.
It's not longer used now, so remove all incarnations and get rid of all those useless = NULL initializations at the same time. Then implement a new callback with a different name.
Yeah, that would be cleaner. I wasn't very sure about clearing unimplemented apic ops. Currently the rule seems to be always setting them to NULL and I didn't want to re-do that with a new callback.
Quoted 7 lines
Quoted 4 lines
It's slightly more work and code churn, but it makes the change entirely clear. It'd be also nice to annotate in the function name that this is 32bit only or even make it 32bit dependent if it's not too much ifdeffery
Yeah, sure, if the silly NULL assignments aren't necessary, I don't think it would be much more churn anyway.
I don't see much point in them, as static struct initializing fills all unset members with zero anyway. And we have no way to check with the compiler that every instance has really initialized all members, which would make sense to ensure that people look at all instances when they add new members.
Thanks,
tglx
PATCH 8/16 x86: Use apic->cpu_to_logical_apicid() to find out logical apic id mapping early during boot
In reply to Tejun HeoOn x86_32, non-standard logical apicid mapping can be used by different NUMA setups. The mapping can be determined while bringing up each CPU after apic->init_apic_ldr(). The logical apicid is then used to deliver IPIs and determine NUMA configuration.
Unfortunately, initializing at SMP bring up is too late for percpu setup making static percpu variables setup w/o considering NUMA. This also is different from how x86_64 is configured making the code difficult to follow and maintain.
Use the unused apic->cpu_to_logical_apicid() to find out the logical apic id mapping before SMP bring up. The callback is called once during get_smp_config() and the output is recorded in x86_cpu_to_logical_apicid. apic implementation is free to return BAD_APICID from the callback if it can't be determined at the time. The early mapping is later verified and reinitialized during SMP bring up.
A stub implementation for apic->cpu_to_logical_apicid() is added for each non-standard apic.
--- arch/x86/include/asm/apic.h | 14 +++++++++++++- arch/x86/kernel/apic/apic.c | 12 ++++++++++-- arch/x86/kernel/apic/bigsmp_32.c | 10 ++++++++++ arch/x86/kernel/apic/es7000_32.c | 11 +++++++++++ arch/x86/kernel/apic/numaq_32.c | 10 ++++++++++ arch/x86/kernel/apic/summit_32.c | 10 ++++++++++ 6 files changed, 64 insertions(+), 3 deletions(-)
arch/x86/include/asm/apic.h +13 -1
@@ -299,6 +299,19 @@ struct apic {unsigned long (*check_apicid_present)(int apicid);void (*vector_allocation_domain)(int cpu,struct cpumask *retmask); +/* +* x86_32 specific method called very early during boot from +* get_smp_config(). It should return the logical apicid. +* x86_[bios]_cpu_to_apicid is initialized before this +* function is called. +* +* If logical apicid can't be determined that early, the +* function may return BAD_APICID. Logical apicid will be +* automatically configured after init_apic_ldr() while +* bringing up CPUs. Note that NUMA affinity won't work +* properly during early boot in this case. +*/ +int (*cpu_to_logical_apicid)(int cpu);void (*init_apic_ldr)(void );void (*ioapic_phys_id_map)(physid_mask_t *phys_map,physid_mask_t *retmap);
@@ -306,7 +319,6 @@ struct apic {void (*setup_apic_routing)(void );int (*multi_timer_check)(int apic,int irq);int (*apicid_to_node)(int logical_apicid); -int (*cpu_to_logical_apicid)(int cpu);int (*cpu_present_to_apicid)(int mps_cpu);void (*apicid_to_cpu_present)(int phys_apicid,physid_mask_t *retmap);void (*setup_portio_remap)(void );
arch/x86/kernel/apic/apic.c +10 -2
@@ -1254,8 +1254,13 @@ void __cpuinit setup_local_APIC(void)#ifdef CONFIG_X86_32 /* -* APIC LDR is initialized. Fetch and store logical_apic_id. +* APIC LDR is initialized. If logical_apicid mapping was +* initialized during get_smp_config(), make sure it matches +* the actual value. */ + i =early_per_cpu (x86_cpu_to_logical_apicid, cpu); +WARN_ON (i !=BAD_APICID && i !=logical_smp_processor_id ()); +/* always use the value from LDR */ early_per_cpu (x86_cpu_to_logical_apicid, cpu) =logical_smp_processor_id ();#endif
@@ -1984,7 +1989,10 @@ void __cpuinit generic_processor_info(int apicid, int version)early_per_cpu (x86_cpu_to_apicid, cpu) = apicid;early_per_cpu (x86_bios_cpu_apicid, cpu) = apicid;#endif - +#ifdef CONFIG_X86_32 +early_per_cpu (x86_cpu_to_logical_apicid, cpu) = + apic->cpu_to_logical_apicid (cpu); +#endif set_cpu_possible (cpu, true);set_cpu_present (cpu, true); }
arch/x86/kernel/apic/bigsmp_32.c +10 -0
@@ -45,6 +45,15 @@ static unsigned long bigsmp_check_apicid_present(int bit)return 1 ; } +static int bigsmp_cpu_to_logical_apicid (int cpu) +{ +/* +* This is stub implementation which causes static percpu area +* layout to ignore NUMA affinity. +*/ +return BAD_APICID ; +} +static inline unsigned long calculate_ldr (int cpu) {unsigned long val, id;
@@ -210,6 +219,7 @@ struct apic apic_bigsmp = { .check_apicid_present = bigsmp_check_apicid_present, .vector_allocation_domain = bigsmp_vector_allocation_domain, + .cpu_to_logical_apicid = bigsmp_cpu_to_logical_apicid, .init_apic_ldr = bigsmp_init_apic_ldr, .ioapic_phys_id_map = bigsmp_ioapic_phys_id_map,
arch/x86/kernel/apic/es7000_32.c +11 -0
@@ -460,6 +460,15 @@ static unsigned long es7000_check_apicid_present(int bit)return physid_isset (bit, phys_cpu_present_map); } +static int es7000_cpu_to_logical_apicid (int cpu) +{ +/* +* This is stub implementation which causes static percpu area +* layout to ignore NUMA affinity. +*/ +return BAD_APICID ; +} +static unsigned long calculate_ldr (int cpu) {unsigned long id =per_cpu (x86_bios_cpu_apicid, cpu);
@@ -638,6 +647,7 @@ struct apic __refdata apic_es7000_cluster = { .check_apicid_present = es7000_check_apicid_present, .vector_allocation_domain = es7000_vector_allocation_domain, + .cpu_to_logical_apicid = es7000_cpu_to_logical_apicid, .init_apic_ldr = es7000_init_apic_ldr_cluster, .ioapic_phys_id_map = es7000_ioapic_phys_id_map,
@@ -702,6 +712,7 @@ struct apic __refdata apic_es7000 = { .check_apicid_present = es7000_check_apicid_present, .vector_allocation_domain = es7000_vector_allocation_domain, + .cpu_to_logical_apicid = es7000_cpu_to_logical_apicid, .init_apic_ldr = es7000_init_apic_ldr, .ioapic_phys_id_map = es7000_ioapic_phys_id_map,
arch/x86/kernel/apic/numaq_32.c +10 -0
@@ -346,6 +346,15 @@ static inline int numaq_apic_id_registered(void)return 1 ; } +static int numaq_cpu_to_logical_apicid (int cpu) +{ +/* +* This is stub implementation which causes static percpu area +* layout to ignore NUMA affinity. +*/ +return BAD_APICID ; +} +static inline void numaq_init_apic_ldr (void ) {/* Already done in NUMA-Q firmware */
@@ -496,6 +505,7 @@ struct apic __refdata apic_numaq = { .check_apicid_present = numaq_check_apicid_present, .vector_allocation_domain = numaq_vector_allocation_domain, + .cpu_to_logical_apicid = numaq_cpu_to_logical_apicid, .init_apic_ldr = numaq_init_apic_ldr, .ioapic_phys_id_map = numaq_ioapic_phys_id_map,
arch/x86/kernel/apic/summit_32.c +10 -0
@@ -194,6 +194,15 @@ static unsigned long summit_check_apicid_present(int bit)return 1 ; } +static int summit_cpu_to_logical_apicid (int cpu) +{ +/* +* This is stub implementation which causes static percpu area +* layout to ignore NUMA affinity. +*/ +return BAD_APICID ; +} +static void summit_init_apic_ldr (void ) {unsigned long val, id;
@@ -511,6 +520,7 @@ struct apic apic_summit = { .check_apicid_present = summit_check_apicid_present, .vector_allocation_domain = summit_vector_allocation_domain, + .cpu_to_logical_apicid = summit_cpu_to_logical_apicid, .init_apic_ldr = summit_init_apic_ldr, .ioapic_phys_id_map = summit_ioapic_phys_id_map,
Signature · 1 line
1.7.1
PATCH 9/16 x86: Implement cpu_to_logical_apicid() for bigsmp_32
In reply to Tejun Heo--- arch/x86/kernel/apic/bigsmp_32.c | 7 ++----- 1 files changed, 2 insertions(+), 5 deletions(-)
arch/x86/kernel/apic/bigsmp_32.c +2 -5
@@ -47,11 +47,8 @@ static unsigned long bigsmp_check_apicid_present(int bit)static int bigsmp_cpu_to_logical_apicid (int cpu) { -/* -* This is stub implementation which causes static percpu area -* layout to ignore NUMA affinity. -*/ -return BAD_APICID ; +/* on bigsmp, logical apicid is the same as physical */ +return early_per_cpu (x86_cpu_to_apicid, cpu); }static inline unsigned long calculate_ldr (int cpu)
Signature · 1 line
1.7.1
PATCH 10/16 x86: Implement cpu_to_logical_apicid() for summit_32
In reply to Tejun HeoFactor out logical apic id calculation from summit_init_apic_ldr() and use it for the cpu_to_logical_apicid() callback.
--- arch/x86/kernel/apic/summit_32.c | 22 ++++++++++------------ 1 files changed, 10 insertions(+), 12 deletions(-)
arch/x86/kernel/apic/summit_32.c +10 -12
@@ -196,18 +196,8 @@ static unsigned long summit_check_apicid_present(int bit)static int summit_cpu_to_logical_apicid (int cpu) { -/* -* This is stub implementation which causes static percpu area -* layout to ignore NUMA affinity. -*/ -return BAD_APICID ; -} - -static void summit_init_apic_ldr (void ) -{ -unsigned long val, id;int count =0 ; -u8 my_id = (u8 )hard_smp_processor_id (); +u8 my_id =early_per_cpu (x86_cpu_to_apicid, cpu);u8 my_cluster =APIC_CLUSTER (my_id);#ifdef CONFIG_SMP u8 lid;
@@ -223,7 +213,15 @@ static void summit_init_apic_ldr(void)/* We only have a 4 wide bitmap in cluster mode. If a deranged * BIOS puts 5 CPUs in one APIC cluster, we're hosed. */ BUG_ON (count >=XAPIC_DEST_CPUS_SHIFT ); - id = my_cluster | (1UL << count); +return my_cluster | (1UL << count); +} + +static void summit_init_apic_ldr (void ) +{ +int cpu =smp_processor_id (); +unsigned long id =early_per_cpu (x86_cpu_to_logical_apicid, cpu); +unsigned long val; +apic_write (APIC_DFR ,SUMMIT_APIC_DFR_VALUE ); val =apic_read (APIC_LDR ) & ~APIC_LDR_MASK ; val |=SET_APIC_LOGICAL_ID (id);
Signature · 1 line
1.7.1
PATCH 11/16 x86: Implement cpu_to_logical_apicid() for numaq_32
In reply to Tejun Heo--- arch/x86/kernel/apic/es7000_32.c | 7 ++----- 1 files changed, 2 insertions(+), 5 deletions(-)
arch/x86/kernel/apic/es7000_32.c +2 -5
@@ -462,11 +462,8 @@ static unsigned long es7000_check_apicid_present(int bit)static int es7000_cpu_to_logical_apicid (int cpu) { -/* -* This is stub implementation which causes static percpu area -* layout to ignore NUMA affinity. -*/ -return BAD_APICID ; +/* on bigsmp, logical apicid is the same as physical */ +return early_per_cpu (x86_bios_cpu_apicid, cpu); }static unsigned long calculate_ldr (int cpu)
Signature · 1 line
1.7.1
PATCH 12/16 x86: Replace apic->apicid_to_node() with ->numa_cpu_node()
In reply to Tejun Heoapic->apicid_to_node() is 32bit specific apic operation which determines NUMA node for a CPU. Depending on the APIC implementation, it can be easier to determine NUMA node from either physical or logical apicid. Currently, ->apicid_to_node() takes @logical_apicid and calls hard_smp_processor_id() if the physical apicid is needed.
This prevents NUMA mapping from being queried from a different CPU, which in turn makes it impossible to initialize NUMA mapping before SMP bringup.
This patch replaces apic->apicid_to_node() with ->numa_cpu_node() which takes @cpu, from which both logical and physical apicids can easily be determined. While at it, drop duplicate implementations from bigsmp_32 and summit_32, and use the default.
--- arch/x86/include/asm/apic.h | 4 ++-- arch/x86/kernel/apic/apic.c | 6 +++--- arch/x86/kernel/apic/apic_flat_64.c | 4 ++-- arch/x86/kernel/apic/apic_noop.c | 4 ++-- arch/x86/kernel/apic/bigsmp_32.c | 7 +------ arch/x86/kernel/apic/es7000_32.c | 7 +++---- arch/x86/kernel/apic/numaq_32.c | 11 ++++++++++- arch/x86/kernel/apic/probe_32.c | 2 +- arch/x86/kernel/apic/summit_32.c | 11 +---------- arch/x86/kernel/apic/x2apic_cluster.c | 2 +- arch/x86/kernel/apic/x2apic_phys.c | 2 +- arch/x86/kernel/apic/x2apic_uv_x.c | 2 +- arch/x86/kernel/smpboot.c | 3 +-- 13 files changed, 29 insertions(+), 36 deletions(-)
arch/x86/include/asm/apic.h +2 -2
@@ -318,7 +318,7 @@ struct apic {void (*setup_apic_routing)(void );int (*multi_timer_check)(int apic,int irq); -int (*apicid_to_node)(int logical_apicid); +int (*numa_cpu_node)(int cpu);int (*cpu_present_to_apicid)(int mps_cpu);void (*apicid_to_cpu_present)(int phys_apicid,physid_mask_t *retmap);void (*setup_portio_remap)(void );
@@ -532,7 +532,7 @@ static inline int default_phys_pkg_id(int cpuid_apic, int index_msb) return cpuid_apic >> index_msb; } -extern int default_apicid_to_node (int logical_apicid); +extern int default_numa_cpu_node (int cpu);#endif
arch/x86/kernel/apic/apic.c +3 -3
@@ -2013,10 +2013,10 @@ void default_init_apic_ldr(void) }#ifdef CONFIG_X86_32 -int default_apicid_to_node (int logical_apicid) +int default_numa_cpu_node (int cpu) { -#ifdef CONFIG_SMP -return apicid_2_node[hard_smp_processor_id ()]; +#ifdef CONFIG_NUMA +return apicid_2_node[early_per_cpu (x86_cpu_to_apicid, cpu)];#else return 0 ;#endif
arch/x86/kernel/apic/apic_flat_64.c +2 -2
@@ -185,7 +185,7 @@ struct apic apic_flat = { .ioapic_phys_id_map = NULL, .setup_apic_routing = NULL, .multi_timer_check = NULL, - .apicid_to_node = NULL, + .numa_cpu_node = NULL, .cpu_to_logical_apicid = NULL, .cpu_present_to_apicid = default_cpu_present_to_apicid, .apicid_to_cpu_present = NULL,
@@ -337,7 +337,7 @@ struct apic apic_physflat = { .ioapic_phys_id_map = NULL, .setup_apic_routing = NULL, .multi_timer_check = NULL, - .apicid_to_node = NULL, + .numa_cpu_node = NULL, .cpu_to_logical_apicid = NULL, .cpu_present_to_apicid = default_cpu_present_to_apicid, .apicid_to_cpu_present = NULL,
arch/x86/kernel/apic/apic_noop.c +2 -2
@@ -113,7 +113,7 @@ static void noop_vector_allocation_domain(int cpu, struct cpumask *retmask)cpumask_set_cpu (cpu, retmask); } -int noop_apicid_to_node (int logical_apicid) +int noop_numa_cpu_node (int cpu) {/* we're always on node 0 */ return 0 ;
@@ -153,7 +153,7 @@ struct apic apic_noop = { .ioapic_phys_id_map = default_ioapic_phys_id_map, .setup_apic_routing = NULL, .multi_timer_check = NULL, - .apicid_to_node = noop_apicid_to_node, + .numa_cpu_node = noop_numa_cpu_node, .cpu_to_logical_apicid = noop_cpu_to_logical_apicid, .cpu_present_to_apicid = default_cpu_present_to_apicid,
arch/x86/kernel/apic/bigsmp_32.c +1 -6
@@ -86,11 +86,6 @@ static void bigsmp_setup_apic_routing(void) nr_ioapics); } -static int bigsmp_apicid_to_node (int logical_apicid) -{ -return apicid_2_node[hard_smp_processor_id ()]; -} -static int bigsmp_cpu_present_to_apicid (int mps_cpu) {if (mps_cpu < nr_cpu_ids)
@@ -222,7 +217,7 @@ struct apic apic_bigsmp = { .ioapic_phys_id_map = bigsmp_ioapic_phys_id_map, .setup_apic_routing = bigsmp_setup_apic_routing, .multi_timer_check = NULL, - .apicid_to_node = bigsmp_apicid_to_node, + .numa_cpu_node = default_numa_cpu_node, .cpu_present_to_apicid = bigsmp_cpu_present_to_apicid, .apicid_to_cpu_present = physid_set_mask_of_physid, .setup_portio_remap = NULL,
arch/x86/kernel/apic/es7000_32.c +3 -4
@@ -510,12 +510,11 @@ static void es7000_setup_apic_routing(void) nr_ioapics, cpumask_bits(es7000_target_cpus())[0]); } -static int es7000_apicid_to_node (int logical_apicid) +static int es7000_numa_cpu_node (int cpu) {return 0 ; } -static int es7000_cpu_present_to_apicid (int mps_cpu) {if (!mps_cpu)
@@ -650,7 +649,7 @@ struct apic __refdata apic_es7000_cluster = { .ioapic_phys_id_map = es7000_ioapic_phys_id_map, .setup_apic_routing = es7000_setup_apic_routing, .multi_timer_check = NULL, - .apicid_to_node = es7000_apicid_to_node, + .numa_cpu_node = es7000_numa_cpu_node, .cpu_present_to_apicid = es7000_cpu_present_to_apicid, .apicid_to_cpu_present = es7000_apicid_to_cpu_present, .setup_portio_remap = NULL,
@@ -715,7 +714,7 @@ struct apic __refdata apic_es7000 = { .ioapic_phys_id_map = es7000_ioapic_phys_id_map, .setup_apic_routing = es7000_setup_apic_routing, .multi_timer_check = NULL, - .apicid_to_node = es7000_apicid_to_node, + .numa_cpu_node = es7000_numa_cpu_node, .cpu_present_to_apicid = es7000_cpu_present_to_apicid, .apicid_to_cpu_present = es7000_apicid_to_cpu_present, .setup_portio_remap = NULL,
arch/x86/kernel/apic/numaq_32.c +10 -1
@@ -400,6 +400,15 @@ static inline int numaq_apicid_to_node(int logical_apicid)return logical_apicid >>4 ; } +static int numaq_numa_cpu_node (int cpu) +{ +int logical_apicid =early_per_cpu (x86_cpu_to_logical_apicid, cpu); + +if (logical_apicid !=BAD_APICID ) +return numaq_apicid_to_node (logical_apicid); +return NUMA_NO_NODE ; +} +static void numaq_apicid_to_cpu_present (int logical_apicid,physid_mask_t *retmap) {int node =numaq_apicid_to_node (logical_apicid);
@@ -511,7 +520,7 @@ struct apic __refdata apic_numaq = { .ioapic_phys_id_map = numaq_ioapic_phys_id_map, .setup_apic_routing = numaq_setup_apic_routing, .multi_timer_check = numaq_multi_timer_check, - .apicid_to_node = numaq_apicid_to_node, + .numa_cpu_node = numaq_numa_cpu_node, .cpu_present_to_apicid = numaq_cpu_present_to_apicid, .apicid_to_cpu_present = numaq_apicid_to_cpu_present, .setup_portio_remap = numaq_setup_portio_remap,
arch/x86/kernel/apic/probe_32.c +1 -1
@@ -130,7 +130,7 @@ struct apic apic_default = { .ioapic_phys_id_map = default_ioapic_phys_id_map, .setup_apic_routing = setup_apic_flat_routing, .multi_timer_check = NULL, - .apicid_to_node = default_apicid_to_node, + .numa_cpu_node = default_numa_cpu_node, .cpu_to_logical_apicid = default_cpu_to_logical_apicid, .cpu_present_to_apicid = default_cpu_present_to_apicid, .apicid_to_cpu_present = physid_set_mask_of_physid,
arch/x86/kernel/apic/summit_32.c +1 -10
@@ -239,15 +239,6 @@ static void summit_setup_apic_routing(void) nr_ioapics); } -static int summit_apicid_to_node (int logical_apicid) -{ -#ifdef CONFIG_SMP -return apicid_2_node[hard_smp_processor_id ()]; -#else -return 0 ; -#endif -} -static int summit_cpu_present_to_apicid (int mps_cpu) {if (mps_cpu < nr_cpu_ids)
@@ -524,7 +515,7 @@ struct apic apic_summit = { .ioapic_phys_id_map = summit_ioapic_phys_id_map, .setup_apic_routing = summit_setup_apic_routing, .multi_timer_check = NULL, - .apicid_to_node = summit_apicid_to_node, + .numa_cpu_node = default_numa_cpu_node, .cpu_present_to_apicid = summit_cpu_present_to_apicid, .apicid_to_cpu_present = summit_apicid_to_cpu_present, .setup_portio_remap = NULL,
arch/x86/kernel/apic/x2apic_cluster.c +1 -1
@@ -206,7 +206,7 @@ struct apic apic_x2apic_cluster = { .ioapic_phys_id_map = NULL, .setup_apic_routing = NULL, .multi_timer_check = NULL, - .apicid_to_node = NULL, + .numa_cpu_node = NULL, .cpu_to_logical_apicid = NULL, .cpu_present_to_apicid = default_cpu_present_to_apicid, .apicid_to_cpu_present = NULL,
arch/x86/kernel/apic/x2apic_phys.c +1 -1
@@ -195,7 +195,7 @@ struct apic apic_x2apic_phys = { .ioapic_phys_id_map = NULL, .setup_apic_routing = NULL, .multi_timer_check = NULL, - .apicid_to_node = NULL, + .numa_cpu_node = NULL, .cpu_to_logical_apicid = NULL, .cpu_present_to_apicid = default_cpu_present_to_apicid, .apicid_to_cpu_present = NULL,
arch/x86/kernel/apic/x2apic_uv_x.c +1 -1
@@ -336,7 +336,7 @@ struct apic __refdata apic_x2apic_uv_x = { .ioapic_phys_id_map = NULL, .setup_apic_routing = NULL, .multi_timer_check = NULL, - .apicid_to_node = NULL, + .numa_cpu_node = NULL, .cpu_to_logical_apicid = NULL, .cpu_present_to_apicid = default_cpu_present_to_apicid, .apicid_to_cpu_present = NULL,
arch/x86/kernel/smpboot.c +1 -2
@@ -168,10 +168,9 @@ static void unmap_cpu_to_node(int cpu)static void map_cpu_to_logical_apicid (void ) {int cpu =smp_processor_id (); -int logical_apicid =early_per_cpu (x86_cpu_to_logical_apicid, cpu);int node; - node = apic->apicid_to_node (logical_apicid); + node = apic->numa_cpu_node (cpu);if (!node_online (node)) node = first_online_node;
Signature · 1 line
1.7.1
PATCH 13/16 x86: Unify cpu/apicid <-> NUMA node mapping between 32 and 64bit
In reply to Tejun HeoThe mapping between cpu/apicid and node is done via apicid_to_node[] on 64bit and apicid_2_node[] + apic->numa_cpu_node() on 32bit. This difference makes it difficult to further unify 32 and 64bit NUMA hanlding.
This patch unifies it by replacing both apicid_to_node[] and apicid_2_node[] with __apicid_to_node[] array, which is accessed by two accessors - set_apicid_to_node() and numa_cpu_node(). On 64bit, numa_cpu_node() always consults __apicid_to_node[] directly while 32bit goes through apic->numa_cpu_node() method to allow apic implementation to override it.
There are several places where using numa_cpu_node() is awkward and the override doesn't matter. In those places, __apicid_to_node[] are used directly.
--- arch/x86/include/asm/mpspec.h | 1 - arch/x86/include/asm/numa.h | 31 +++++++++++++++++++++++++++++++ arch/x86/include/asm/numa_32.h | 6 ++++++ arch/x86/include/asm/numa_64.h | 5 ++--- arch/x86/kernel/acpi/boot.c | 3 +-- arch/x86/kernel/apic/apic.c | 6 +++++- arch/x86/kernel/cpu/amd.c | 14 +++++++------- arch/x86/kernel/cpu/intel.c | 3 +-- arch/x86/kernel/smpboot.c | 6 +----- arch/x86/mm/k8topology_64.c | 2 +- arch/x86/mm/numa.c | 6 +++++- arch/x86/mm/numa_32.c | 6 ++++++ arch/x86/mm/numa_64.c | 18 +++++++++--------- arch/x86/mm/srat_32.c | 2 +- arch/x86/mm/srat_64.c | 10 +++++----- 15 files changed, 81 insertions(+), 38 deletions(-)
arch/x86/include/asm/mpspec.h +0 -1
@@ -24,7 +24,6 @@ extern int pic_mode;#define MAX_IRQ_SOURCES 256extern unsigned int def_to_bigsmp; -extern u8 apicid_2_node[];#ifdef CONFIG_X86_NUMAQ extern int mp_bus_id_to_node[MAX_MP_BUSSES ];
arch/x86/include/asm/numa.h +31 -0
@@ -1,5 +1,36 @@ +#ifndef _ASM_X86_NUMA_H +#define _ASM_X86_NUMA_H + +#include <asm/apicdef.h> + +#ifdef CONFIG_NUMA +/* +* __apicid_to_node[] stores the raw mapping between physical apicid +* and node and is used to initialize cpu_to_node mapping. +* +* The mapping may be overridden by apic->numa_cpu_node() on 32bit and +* thus should be accessed by the accessors - set_apicid_to_node() and +* numa_cpu_node(). +* +* If the user knows that it doesn't care about 32bit APIC-specific +* overrides, __apicid_to_node[] may be used directly. +*/ +extern s16 __apicid_to_node[MAX_LOCAL_APIC ]; + +static inline void set_apicid_to_node (int apicid,s16 node) +{ + __apicid_to_node[apicid] = node; +} +#else /* CONFIG_NUMA */ +static inline void set_apicid_to_node (int apicid,s16 node) +{ +} +#endif /* CONFIG_NUMA */ +#ifdef CONFIG_X86_32 # include "numa_32.h" #else # include "numa_64.h" #endif + +#endif /* _ASM_X86_NUMA_H */
arch/x86/include/asm/numa_32.h +6 -0
@@ -4,6 +4,12 @@extern int pxm_to_nid (int pxm);extern void numa_remove_cpu (int cpu); +#ifdef CONFIG_NUMA +extern int __cpuinit numa_cpu_node (int apicid); +#else /* CONFIG_NUMA */ +static inline int numa_cpu_node (int cpu) {return NUMA_NO_NODE ; } +#endif /* CONFIG_NUMA */ +#ifdef CONFIG_HIGHMEM extern void set_highmem_pages_init (void );#else
arch/x86/include/asm/numa_64.h +2 -3
@@ -2,7 +2,6 @@#define _ASM_X86_NUMA_64_H#include <linux/nodemask.h> -#include <asm/apicdef.h> struct bootnode {u64 start;
@@ -17,8 +16,6 @@ extern int compute_hash_shift(struct bootnode *nodes, int numblks,extern void numa_init_array (void );extern int numa_off; -extern s16 apicid_to_node[MAX_LOCAL_APIC ]; -extern unsigned long numa_free_all_bootmem (void );extern void setup_node_bootmem (int nodeid,unsigned long start,unsigned long end);
@@ -32,6 +29,7 @@ extern void setup_node_bootmem(int nodeid, unsigned long start,#define NODE_MIN_SIZE (4*1024*1024)extern void __init init_cpu_to_node (void ); +extern int __cpuinit numa_cpu_node (int cpu);extern void __cpuinit numa_set_node (int cpu,int node);extern void __cpuinit numa_clear_node (int cpu);extern void __cpuinit numa_add_cpu (int cpu);
@@ -43,6 +41,7 @@ extern void __cpuinit numa_remove_cpu(int cpu);#endif /* CONFIG_NUMA_EMU */ #else static inline void init_cpu_to_node (void ) { } +static inline int numa_cpu_node (int cpu) {return NUMA_NO_NODE ; }static inline void numa_set_node (int cpu,int node) { }static inline void numa_clear_node (int cpu) { }static inline void numa_add_cpu (int cpu,int node) { }
arch/x86/kernel/acpi/boot.c +1 -2
@@ -583,11 +583,10 @@ static void acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) nid =acpi_get_node (handle);if (nid ==-1 || !node_online (nid))return ; +set_apicid_to_node (physid, nid);#ifdef CONFIG_X86_64 - apicid_to_node[physid] = nid;numa_set_node (cpu, nid);#else /* CONFIG_X86_32 */ - apicid_2_node[physid] = nid; cpu_to_node_map[cpu] = nid;#endif
arch/x86/kernel/apic/apic.c +5 -1
@@ -2016,7 +2016,11 @@ void default_init_apic_ldr(void)int default_numa_cpu_node (int cpu) {#ifdef CONFIG_NUMA -return apicid_2_node[early_per_cpu (x86_cpu_to_apicid, cpu)]; +int apicid =early_per_cpu (x86_cpu_to_apicid, cpu); + +if (apicid !=BAD_APICID ) +return __apicid_to_node[apicid]; +return NUMA_NO_NODE ;#else return 0 ;#endif
arch/x86/kernel/cpu/amd.c +7 -7
@@ -239,12 +239,12 @@ static int __cpuinit nearby_node(int apicid)int i, node;for (i = apicid -1 ; i >=0 ; i--) { - node = apicid_to_node[i]; + node = __apicid_to_node[i];if (node !=NUMA_NO_NODE &&node_online (node))return node; }for (i = apicid +1 ; i <MAX_LOCAL_APIC ; i++) { - node = apicid_to_node[i]; + node = __apicid_to_node[i];if (node !=NUMA_NO_NODE &&node_online (node))return node; }
@@ -339,10 +339,10 @@ static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)int node;unsigned apicid = c->apicid; - node =per_cpu (cpu_llc_id, cpu); + node =numa_cpu_node (cpu); +if (node ==NUMA_NO_NODE ) + node =per_cpu (cpu_llc_id, cpu); -if (apicid_to_node[apicid] !=NUMA_NO_NODE ) - node = apicid_to_node[apicid];if (!node_online (node)) {/* Two possibilities here: - The CPU is missing memory and no node was created.
@@ -357,8 +357,8 @@ static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)int ht_nodeid = c->initial_apicid;if (ht_nodeid >=0 && - apicid_to_node[ht_nodeid] !=NUMA_NO_NODE ) - node = apicid_to_node[ht_nodeid]; + __apicid_to_node[ht_nodeid] !=NUMA_NO_NODE ) + node = __apicid_to_node[ht_nodeid];/* Pick a nearby node */ if (!node_online (node)) node =nearby_node (apicid);
arch/x86/kernel/cpu/intel.c +1 -2
@@ -279,11 +279,10 @@ static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)#if defined(CONFIG_NUMA ) && defined(CONFIG_X86_64 )unsigned node;int cpu =smp_processor_id (); -int apicid = cpu_has_apic ?hard_smp_processor_id () : c->apicid;/* Don't do the funky fallback heuristics the AMD version employs for now. */ - node = apicid_to_node[apicid]; + node =numa_cpu_node (cpu);if (node ==NUMA_NO_NODE || !node_online (node)) {/* reuse the value from init_cpu_to_node() */ node =cpu_to_node (cpu);
arch/x86/kernel/smpboot.c +1 -5
@@ -71,10 +71,6 @@#include <asm/smpboot_hooks.h> #include <asm/i8259.h> -#ifdef CONFIG_X86_32 -u8 apicid_2_node[MAX_LOCAL_APIC ]; -#endif -/* State of each CPU */ DEFINE_PER_CPU(int, cpu_state) = { 0 };
@@ -170,7 +166,7 @@ static void map_cpu_to_logical_apicid(void)int cpu =smp_processor_id ();int node; - node = apic->numa_cpu_node (cpu); + node =numa_cpu_node (cpu);if (!node_online (node)) node = first_online_node;
arch/x86/mm/k8topology_64.c +1 -1
@@ -228,7 +228,7 @@ int __init k8_scan_nodes(void) nodes[i].start >>PAGE_SHIFT , nodes[i].end >> PAGE_SHIFT);for (j = apicid_base; j < cores + apicid_base; j++) - apicid_to_node[(i << bits) + j] = i; +set_apicid_to_node ((i << bits) + j, i);setup_node_bootmem (i, nodes[i].start, nodes[i].end); }
arch/x86/mm/numa.c +5 -1
@@ -4,8 +4,12 @@#include <linux/bootmem.h> /* -* Which logical CPUs are on which nodes +* apicid, cpu, node mappings */ +s16 __apicid_to_node[MAX_LOCAL_APIC ]__cpuinitdata = { + [0 ...MAX_LOCAL_APIC -1 ] =NUMA_NO_NODE +}; +cpumask_var_t node_to_cpumask_map[MAX_NUMNODES ];EXPORT_SYMBOL (node_to_cpumask_map);
arch/x86/mm/numa_32.c +6 -0
@@ -110,6 +110,12 @@ void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags);static unsigned long kva_start_pfn;static unsigned long kva_pages; + +int __cpuinit numa_cpu_node (int cpu) +{ +return apic->numa_cpu_node (cpu); +} +/* * FLAT - support for basic PC memory model with discontig enabled, essentially * a single node with all available processors in it with a flat
arch/x86/mm/numa_64.c +9 -9
@@ -26,10 +26,6 @@ EXPORT_SYMBOL(node_data);struct memnode memnode; -s16 apicid_to_node[MAX_LOCAL_APIC ]__cpuinitdata = { - [0 ...MAX_LOCAL_APIC -1 ] =NUMA_NO_NODE -}; -int numa_off__initdata ;static unsigned long __initdata nodemap_addr;static unsigned long __initdata nodemap_size;
@@ -721,12 +717,8 @@ void __init init_cpu_to_node(void)BUG_ON (cpu_to_apicid ==NULL );for_each_possible_cpu (cpu) { -int node; -u16 apicid = cpu_to_apicid[cpu]; +int node =numa_cpu_node (cpu); -if (apicid ==BAD_APICID ) -continue ; - node = apicid_to_node[apicid];if (node ==NUMA_NO_NODE )continue ;if (!node_online (node))
@@ -736,6 +728,14 @@ void __init init_cpu_to_node(void) }#endif +int __cpuinit numa_cpu_node (int cpu) +{ +int apicid =early_per_cpu (x86_cpu_to_apicid, cpu); + +if (apicid !=BAD_APICID ) +return __apicid_to_node[apicid]; +return NUMA_NO_NODE ; +}void __cpuinit numa_set_node (int cpu,int node) {
arch/x86/mm/srat_32.c +1 -1
@@ -255,7 +255,7 @@ int __init get_memcfg_from_srat(void) num_memory_chunks);for (i =0 ; i <MAX_LOCAL_APIC ; i++) - apicid_2_node[i] =pxm_to_node (apicid_to_pxm[i]); +set_apicid_to_node (i,pxm_to_node (apicid_to_pxm[i]));for (j =0 ; j < num_memory_chunks; j++){struct node_memory_chunk_s * chunk = &node_memory_chunk[j];
arch/x86/mm/srat_64.c +5 -5
@@ -79,7 +79,7 @@ static __init void bad_srat(void)printk (KERN_ERR "SRAT: SRAT not used.\n" ); acpi_numa =-1 ;for (i =0 ; i <MAX_LOCAL_APIC ; i++) - apicid_to_node[i] =NUMA_NO_NODE ; +set_apicid_to_node (i,NUMA_NO_NODE );for (i =0 ; i <MAX_NUMNODES ; i++) { nodes[i].start = nodes[i].end =0 ; nodes_add[i].start = nodes_add[i].end =0 ;
@@ -134,7 +134,7 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa) } apic_id = pa->apic_id; - apicid_to_node[apic_id] = node; +set_apicid_to_node (apic_id, node);node_set (node, cpu_nodes_parsed); acpi_numa =1 ; printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%04x -> Node %u\n",
@@ -168,7 +168,7 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) apic_id = (pa->apic_id <<8 ) | pa->local_sapic_eid; else apic_id = pa->apic_id; - apicid_to_node[apic_id] = node; +set_apicid_to_node (apic_id, node);node_set (node, cpu_nodes_parsed); acpi_numa =1 ; printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%02x -> Node %u\n",
@@ -512,13 +512,13 @@ void __init acpi_fake_nodes(const struct bootnode *fake_nodes, int num_nodes)* node, it must now point to the fake node ID. */ for (j =0 ; j <MAX_LOCAL_APIC ; j++) -if (apicid_to_node[j] == nid && +if (__apicid_to_node[j] == nid && fake_apicid_to_node[j] ==NUMA_NO_NODE ) fake_apicid_to_node[j] = i; }for (i =0 ; i < num_nodes; i++)__acpi_map_pxm_to_node (fake_node_to_pxm_map[i], i); -memcpy (apicid_to_node, fake_apicid_to_node,sizeof (apicid_to_node)); +memcpy (__apicid_to_node, fake_apicid_to_node,sizeof (__apicid_to_node));nodes_clear (nodes_parsed);for (i =0 ; i < num_nodes; i++)
Signature · 1 line
1.7.1
Re: [PATCH 13/16] x86: Unify cpu/apicid <-> NUMA node mapping between 32 and 64bit
Quoted 12 lines · Tejun Heo
The mapping between cpu/apicid and node is done via apicid_to_node[] on 64bit and apicid_2_node[] +
apic->numa_cpu_node()on 32bit. This difference makes it difficult to further unify 32 and 64bit NUMA hanlding.This patch unifies it by replacing both apicid_to_node[] and apicid_2_node[] with __apicid_to_node[] array, which is accessed by two accessors -
set_apicid_to_node()andnuma_cpu_node(). On 64bit,numa_cpu_node()always consults __apicid_to_node[] directly while 32bit goes throughapic->numa_cpu_node()method to allow apic implementation to override it.
Quoted 3 lines
There are several places where using
numa_cpu_node()is awkward and the override doesn't matter. In those places, __apicid_to_node[] are used directly.
Why is it awkward? Anything outside the accessor functions or specialized setup code using it is awkward, inconsistent and sloppy.
Thanks,
tglx
Re: [PATCH 13/16] x86: Unify cpu/apicid <-> NUMA node mapping between 32 and 64bit
Hello, Thomas.
Quoted 6 lines · Thomas Gleixner
Quoted 3 lines
There are several places where using
numa_cpu_node()is awkward and the override doesn't matter. In those places, __apicid_to_node[] are used directly.Why is it awkward? Anything outside the accessor functions or specialized setup code using it is awkward, inconsistent and sloppy.
There are two places which index the mapping by apicid instead of cpu. One is acpi_fake_nodes() - this sets up the table, so it doesn't constitute violation of accessors.
The problematic one is the nearby detection workaround in kernel/cpu/amd.c. This is rather hacky and looks like added to deal with early AMD NUMAs which had broken BIOS. The intel counterpart omits this workaround and simply ignore NUMA configuration in those cases.
I can change srat_detect_node() and nearby_node() to index by cpu but as I have no idea what kind of broken configurations this is supposed to deal with, I'm concerned that this may lead to different outcome by walking the table in a different order. I can implement an apicid -> numa node mapping function for this but this is something which is inherently ugly, so maybe it's best to leave it ugly.
For now, how about adding a big fat comment explaining the ugliness in amd.c?
Thanks.
Signature · 1 line
tejun
Re: [PATCH 13/16] x86: Unify cpu/apicid <-> NUMA node mapping between 32 and 64bit
Quoted 6 lines · Tejun Heo
I can change
srat_detect_node()andnearby_node()to index by cpu but as I have no idea what kind of broken configurations this is supposed to deal with, I'm concerned that this may lead to different outcome by walking the table in a different order. I can implement an apicid -> numa node mapping function for this but this is something which is inherently ugly, so maybe it's best to leave it ugly.
Oh, right, another problem. It's possible that apicid <-> numa mapping exists when apicid <-> cpu doesn't. Again, this is a corner case which might not matter but I have no idea what kind of brokeness is being worked around and it would also be difficult to test whether the change is okay.
If someone can tell me that this workaround can go away, it would be awesome.
Signature · 1 line
tejun
Re: [PATCH 13/16] x86: Unify cpu/apicid <-> NUMA node mapping between 32 and 64bit
Quoted 8 lines · Tejun Heo
Quoted 6 lines · Tejun Heo
I can change
srat_detect_node()andnearby_node()to index by cpu but as I have no idea what kind of broken configurations this is supposed to deal with, I'm concerned that this may lead to different outcome by walking the table in a different order. I can implement an apicid -> numa node mapping function for this but this is something which is inherently ugly, so maybe it's best to leave it ugly.
Quoted 6 lines
Oh, right, another problem. It's possible that apicid <-> numa mapping exists when apicid <-> cpu doesn't. Again, this is a corner case which might not matter but I have no idea what kind of brokeness is being worked around and it would also be difficult to test whether the change is okay.
that could happen...when SRAT and MADT is in different order. and your are booting nr_cpus=<less....> in SRAT...
should be fixed in
https://lkml.org/lkml/2010/11/22/5
Thanks
Yinghai
PATCH 14/16 x86: Unify CPU -> NUMA node mapping between 32 and 64bit
In reply to Tejun HeoUnlike 64bit, 32bit has been using its own cpu_to_node_map[] for CPU -> NUMA node mapping. Replace it with early_percpu variable x86_cpu_to_node_map and share the mapping code with 64bit.
* USE_PERCPU_NUMA_NODE_ID is now enabled for 32bit too.
* x86_cpu_to_node_map and numa_set/clear_node() are moved from numa_64 to numa. For now, x86_cpu_to_node_map is initialized with 0 instead of NUMA_NO_NODE. This is to avoid introducing unexpected behavior change and will be updated once init path is unified.
* srat_detect_node() is now enabled for x86_32 too. It calls numa_set_node() and initializes the mapping making explicit cpu_to_node_map[] updates from map/unmap_cpu_to_node() unnecessary.
--- arch/x86/Kconfig | 2 +- arch/x86/include/asm/numa.h | 8 ++++ arch/x86/include/asm/numa_64.h | 4 -- arch/x86/include/asm/topology.h | 17 --------- arch/x86/kernel/acpi/boot.c | 5 --- arch/x86/kernel/cpu/amd.c | 4 +- arch/x86/kernel/cpu/intel.c | 2 +- arch/x86/kernel/setup_percpu.c | 4 +- arch/x86/kernel/smpboot.c | 6 --- arch/x86/mm/numa.c | 72 ++++++++++++++++++++++++++++++++++++++- arch/x86/mm/numa_64.c | 65 ----------------------------------- 11 files changed, 85 insertions(+), 104 deletions(-)
arch/x86/Kconfig +1 -1
@@ -1678,7 +1678,7 @@ config HAVE_ARCH_EARLY_PFN_TO_NID depends on NUMA config USE_PERCPU_NUMA_NODE_ID - def_bool X86_64 + def_bool y depends on NUMA menu "Power management and ACPI options"
arch/x86/include/asm/numa.h +8 -0
@@ -33,4 +33,12 @@ static inline void set_apicid_to_node(int apicid, s16 node)# include "numa_64.h" #endif +#ifdef CONFIG_NUMA +extern void __cpuinit numa_set_node (int cpu,int node); +extern void __cpuinit numa_clear_node (int cpu); +#else /* CONFIG_NUMA */ +static inline void numa_set_node (int cpu,int node) { } +static inline void numa_clear_node (int cpu) { } +#endif /* CONFIG_NUMA */ +#endif /* _ASM_X86_NUMA_H */
arch/x86/include/asm/numa_64.h +0 -4
@@ -30,8 +30,6 @@ extern void setup_node_bootmem(int nodeid, unsigned long start,extern void __init init_cpu_to_node (void );extern int __cpuinit numa_cpu_node (int cpu); -extern void __cpuinit numa_set_node (int cpu,int node); -extern void __cpuinit numa_clear_node (int cpu);extern void __cpuinit numa_add_cpu (int cpu);extern void __cpuinit numa_remove_cpu (int cpu);
@@ -42,8 +40,6 @@ extern void __cpuinit numa_remove_cpu(int cpu);#else static inline void init_cpu_to_node (void ) { }static inline int numa_cpu_node (int cpu) {return NUMA_NO_NODE ; } -static inline void numa_set_node (int cpu,int node) { } -static inline void numa_clear_node (int cpu) { }static inline void numa_add_cpu (int cpu,int node) { }static inline void numa_remove_cpu (int cpu) { }#endif
arch/x86/include/asm/topology.h +0 -17
@@ -47,21 +47,6 @@#include <asm/mpspec.h> -#ifdef CONFIG_X86_32 - -/* Mappings between logical cpu number and node number */ -extern int cpu_to_node_map[]; - -/* Returns the number of the node containing CPU 'cpu' */ -static inline int __cpu_to_node (int cpu) -{ -return cpu_to_node_map[cpu]; -} -#define early_cpu_to_node __cpu_to_node -#define cpu_to_node __cpu_to_node - -#else /* CONFIG_X86_64 */ -/* Mappings between logical cpu number and node number */ DECLARE_EARLY_PER_CPU (int, x86_cpu_to_node_map);
@@ -84,8 +69,6 @@ static inline int early_cpu_to_node(int cpu)#endif /* !CONFIG_DEBUG_PER_CPU_MAPS */ -#endif /* CONFIG_X86_64 */ -/* Mappings between node number and cpus on that node. */ extern cpumask_var_t node_to_cpumask_map[MAX_NUMNODES ];
arch/x86/kernel/acpi/boot.c +0 -5
@@ -584,12 +584,7 @@ static void acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)if (nid ==-1 || !node_online (nid))return ;set_apicid_to_node (physid, nid); -#ifdef CONFIG_X86_64 numa_set_node (cpu, nid); -#else /* CONFIG_X86_32 */ - cpu_to_node_map[cpu] = nid; -#endif -#endif }
arch/x86/kernel/cpu/amd.c +2 -2
@@ -233,7 +233,7 @@ static void __cpuinit init_amd_k7(struct cpuinfo_x86 *c) }#endif -#if defined(CONFIG_NUMA ) && defined(CONFIG_X86_64 ) +#ifdef CONFIG_NUMA static int __cpuinit nearby_node (int apicid) {int i, node;
@@ -334,7 +334,7 @@ EXPORT_SYMBOL_GPL(amd_get_nb_id);static void __cpuinit srat_detect_node (struct cpuinfo_x86 *c) { -#if defined(CONFIG_NUMA ) && defined(CONFIG_X86_64 ) +#ifdef CONFIG_NUMA int cpu =smp_processor_id ();int node;unsigned apicid = c->apicid;
arch/x86/kernel/cpu/intel.c +1 -1
@@ -276,7 +276,7 @@ static void __cpuinit intel_workarounds(struct cpuinfo_x86 *c)static void __cpuinit srat_detect_node (struct cpuinfo_x86 *c) { -#if defined(CONFIG_NUMA ) && defined(CONFIG_X86_64 ) +#ifdef CONFIG_NUMA unsigned node;int cpu =smp_processor_id ();
arch/x86/kernel/setup_percpu.c +2 -2
@@ -233,6 +233,7 @@ void __init setup_per_cpu_areas(void)per_cpu (irq_stack_ptr, cpu) =per_cpu (irq_stack_union.irq_stack, cpu) +IRQ_STACK_SIZE -64 ; +#endif #ifdef CONFIG_NUMA per_cpu (x86_cpu_to_node_map, cpu) =early_per_cpu_map (x86_cpu_to_node_map, cpu);
@@ -246,7 +247,6 @@ void __init setup_per_cpu_areas(void)*/ set_cpu_numa_node (cpu,early_cpu_to_node (cpu));#endif -#endif /* * Up to this point, the boot CPU has been using .init.data * area. Reload any changed state for the boot CPU.
@@ -263,7 +263,7 @@ void __init setup_per_cpu_areas(void)#ifdef CONFIG_X86_32 early_per_cpu_ptr (x86_cpu_to_logical_apicid) =NULL ;#endif -#if defined(CONFIG_X86_64 ) && defined(CONFIG_NUMA ) +#ifdef CONFIG_NUMA early_per_cpu_ptr (x86_cpu_to_node_map) =NULL ;#endif
arch/x86/kernel/smpboot.c +0 -6
@@ -133,16 +133,11 @@ EXPORT_PER_CPU_SYMBOL(cpu_info);atomic_t init_deasserted;#if defined(CONFIG_NUMA ) && defined(CONFIG_X86_32 ) -/* which node each logical CPU is on */ -int cpu_to_node_map[NR_CPUS ]__read_mostly = { [0 ...NR_CPUS -1 ] =0 }; -EXPORT_SYMBOL (cpu_to_node_map); -/* set up a mapping between cpu and node. */ static void map_cpu_to_node (int cpu,int node) {printk (KERN_INFO "Mapping cpu %d to node %d\n" , cpu, node);cpumask_set_cpu (cpu, node_to_cpumask_map[node]); - cpu_to_node_map[cpu] = node; }/* undo a mapping between cpu and node. */
@@ -153,7 +148,6 @@ static void unmap_cpu_to_node(int cpu)printk (KERN_INFO "Unmapping cpu %d from all nodes\n" , cpu);for (node =0 ; node <MAX_NUMNODES ; node++) cpumask_clear_cpu(cpu, node_to_cpumask_map[node]); - cpu_to_node_map[cpu] = 0; }#else /* !(CONFIG_NUMA && CONFIG_X86_32) */ #define map_cpu_to_node (cpu, node) ({})
arch/x86/mm/numa.c +71 -1
87 lines not on this page · raw message
arch/x86/mm/numa_64.c +0 -65
83 lines not on this page · raw message
Signature · 1 line
1.7.1
Re: [PATCH 14/16] x86: Unify CPU -> NUMA node mapping between 32 and 64bit
Quoted 9 lines · Tejun Heo
Unlike 64bit, 32bit has been using its own cpu_to_node_map[] for CPU -> NUMA node mapping. Replace it with
early_percpuvariablex86_cpu_to_node_mapand share the mapping code with 64bit.*
USE_PERCPU_NUMA_NODE_IDis now enabled for 32bit too.*
x86_cpu_to_node_mapand numa_set/clear_node() are moved fromnuma_64to numa. For now,x86_cpu_to_node_mapis initialized with 0 instead ofNUMA_NO_NODE. This is to avoid introducing unexpected behavior
That's true for 32bit only, right? I actually had to dig into the code to verify this. Please make this clear for the casual reader.
Thanks,
tglx
Re: [PATCH 14/16] x86: Unify CPU -> NUMA node mapping between 32 and 64bit
Quoted 6 lines · Thomas Gleixner
Quoted 4 lines · Tejun Heo
Unlike 64bit, 32bit has been using its own cpu_to_node_map[] for CPU -> NUMA node mapping. Replace it with
early_percpuvariablex86_cpu_to_node_mapand share the mapping code with 64bit.
Quoted 8 lines
Quoted 5 lines
*
USE_PERCPU_NUMA_NODE_IDis now enabled for 32bit too.*
x86_cpu_to_node_mapand numa_set/clear_node() are moved fromnuma_64to numa. For now,x86_cpu_to_node_mapis initialized with 0 instead ofNUMA_NO_NODE. This is to avoid introducing unexpected behaviorThat's true for 32bit only, right? I actually had to dig into the code to verify this. Please make this clear for the casual reader.
Will do so.
Thanks.
Signature · 1 line
tejun
PATCH 15/16 x86: Unify node_to_cpumask_map handling between 32 and 64bit
In reply to Tejun Heox86_32 has been managing node_to_cpumask_map explicitly from map_cpu_to_node() and friends in a rather ugly way. With previous changes, it's now possible to simply share the code with 64bit.
* numa_add/remove_cpu() are moved from numa_64 to numa.
* identify_cpu() now calls numa_add_cpu() for 32bit too. This makes the explicit mask management from map_cpu_to_node() unnecessary.
* The whole x86_32 specific map_cpu_to_node() chunk is no longer necessary. Dropped.
--- arch/x86/include/asm/numa.h | 18 +++++++++++++ arch/x86/include/asm/numa_32.h | 1 - arch/x86/include/asm/numa_64.h | 4 --- arch/x86/kernel/cpu/common.c | 2 +- arch/x86/kernel/smpboot.c | 47 ---------------------------------- arch/x86/mm/numa.c | 33 ++++++++++++++++++++++++ arch/x86/mm/numa_64.c | 55 ---------------------------------------- 7 files changed, 52 insertions(+), 108 deletions(-)
arch/x86/include/asm/numa.h +18 -0
@@ -1,6 +1,7 @@#ifndef _ASM_X86_NUMA_H#define _ASM_X86_NUMA_H +#include <asm/topology.h> #include <asm/apicdef.h> #ifdef CONFIG_NUMA
@@ -36,9 +37,26 @@ static inline void set_apicid_to_node(int apicid, s16 node)#ifdef CONFIG_NUMA extern void __cpuinit numa_set_node (int cpu,int node);extern void __cpuinit numa_clear_node (int cpu); + +# ifdef CONFIG_DEBUG_PER_CPU_MAPS +extern void __cpuinit numa_add_cpu (int cpu); +extern void __cpuinit numa_remove_cpu (int cpu); +# else /* CONFIG_DEBUG_PER_CPU_MAPS */ +static inline void __cpuinit numa_add_cpu (int cpu) +{ +cpumask_set_cpu (cpu, node_to_cpumask_map[early_cpu_to_node (cpu)]); +} +static inline void __cpuinit numa_remove_cpu (int cpu) +{ +cpumask_clear_cpu (cpu, node_to_cpumask_map[early_cpu_to_node (cpu)]); +} +# endif /* CONFIG_DEBUG_PER_CPU_MAPS */ +#else /* CONFIG_NUMA */ static inline void numa_set_node (int cpu,int node) { }static inline void numa_clear_node (int cpu) { } +static inline void numa_add_cpu (int cpu) { } +static inline void numa_remove_cpu (int cpu) { }#endif /* CONFIG_NUMA */ #endif /* _ASM_X86_NUMA_H */
arch/x86/include/asm/numa_32.h +0 -1
@@ -2,7 +2,6 @@#define _ASM_X86_NUMA_32_Hextern int pxm_to_nid (int pxm); -extern void numa_remove_cpu (int cpu);#ifdef CONFIG_NUMA extern int __cpuinit numa_cpu_node (int apicid);
arch/x86/include/asm/numa_64.h +0 -4
@@ -30,8 +30,6 @@ extern void setup_node_bootmem(int nodeid, unsigned long start,extern void __init init_cpu_to_node (void );extern int __cpuinit numa_cpu_node (int cpu); -extern void __cpuinit numa_add_cpu (int cpu); -extern void __cpuinit numa_remove_cpu (int cpu);#ifdef CONFIG_NUMA_EMU #define FAKE_NODE_MIN_SIZE ((u64)64 << 20)
@@ -40,8 +38,6 @@ extern void __cpuinit numa_remove_cpu(int cpu);#else static inline void init_cpu_to_node (void ) { }static inline int numa_cpu_node (int cpu) {return NUMA_NO_NODE ; } -static inline void numa_add_cpu (int cpu,int node) { } -static inline void numa_remove_cpu (int cpu) { }#endif #endif /* _ASM_X86_NUMA_64_H */
arch/x86/kernel/cpu/common.c +1 -1
@@ -869,7 +869,7 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)select_idle_routine (c); -#if defined(CONFIG_NUMA ) && defined(CONFIG_X86_64 ) +#ifdef CONFIG_NUMA numa_add_cpu (smp_processor_id ());#endif }
arch/x86/kernel/smpboot.c +0 -47
71 lines not on this page · raw message
arch/x86/mm/numa.c +33 -0
@@ -109,6 +109,39 @@ int early_cpu_to_node(int cpu)return per_cpu (x86_cpu_to_node_map, cpu); } +static void __cpuinit numa_set_cpumask (int cpu,int enable) +{ +int node =early_cpu_to_node (cpu); +struct cpumask *mask; +char buf[64 ]; + + mask = node_to_cpumask_map[node]; +if (mask ==NULL ) { +printk (KERN_ERR "node_to_cpumask_map[%i] NULL\n" , node); +dump_stack (); +return ; + } + +if (enable) +cpumask_set_cpu (cpu, mask); +else +cpumask_clear_cpu (cpu, mask); + +cpulist_scnprintf (buf,sizeof (buf), mask); +printk (KERN_DEBUG "%s cpu %d node %d: mask now %s\n" , + enable ?"numa_add_cpu" :"numa_remove_cpu" , cpu, node, buf); +} + +void __cpuinit numa_add_cpu (int cpu) +{ +numa_set_cpumask (cpu,1 ); +} + +void __cpuinit numa_remove_cpu (int cpu) +{ +numa_set_cpumask (cpu,0 ); +} +/* * Returns a pointer to the bitmask of CPUs on Node 'node'. */
arch/x86/mm/numa_64.c +0 -55
58 lines not on this page · raw message
Signature · 1 line
1.7.1
PATCH 16/16 x86: Unify NUMA initialization between 32 and 64bit
In reply to Tejun HeoNow that everything else is unified, NUMA initialization can be unified too.
* numa_init_array() and init_cpu_to_node() are moved from numa_64 to numa.
* numa_32::initmem_init() is updated to call numa_init_array() and setup_arch() to call init_cpu_to_node() on 32bit too.
* x86_cpu_to_node_map is now initialized to NUMA_NO_NODE on 32bit too. This is safe now as numa_init_array() will initialize it early during boot.
This makes NUMA mapping fully initialized before setup_per_cpu_areas() on 32bit too and thus makes the first percpu chunk which contains all the static variables and some of dynamic area allocated with NUMA affinity correctly considered.
--- arch/x86/include/asm/numa.h | 4 ++ arch/x86/include/asm/numa_64.h | 3 -- arch/x86/kernel/setup.c | 2 - arch/x86/mm/numa.c | 76 +++++++++++++++++++++++++++++++++++++-- arch/x86/mm/numa_32.c | 1 + arch/x86/mm/numa_64.c | 75 --------------------------------------- 6 files changed, 77 insertions(+), 84 deletions(-)
arch/x86/include/asm/numa.h +4 -0
@@ -37,6 +37,8 @@ static inline void set_apicid_to_node(int apicid, s16 node)#ifdef CONFIG_NUMA extern void __cpuinit numa_set_node (int cpu,int node);extern void __cpuinit numa_clear_node (int cpu); +extern void __init numa_init_array (void ); +extern void __init init_cpu_to_node (void );# ifdef CONFIG_DEBUG_PER_CPU_MAPS extern void __cpuinit numa_add_cpu (int cpu);
@@ -55,6 +57,8 @@ static inline void __cpuinit numa_remove_cpu(int cpu)#else /* CONFIG_NUMA */ static inline void numa_set_node (int cpu,int node) { }static inline void numa_clear_node (int cpu) { } +static inline void numa_init_array (void ) { } +static inline void init_cpu_to_node (void ) { }static inline void numa_add_cpu (int cpu) { }static inline void numa_remove_cpu (int cpu) { }#endif /* CONFIG_NUMA */
arch/x86/include/asm/numa_64.h +0 -3
@@ -13,7 +13,6 @@ extern int compute_hash_shift(struct bootnode *nodes, int numblks,#define ZONE_ALIGN (1UL << (MAX_ORDER+PAGE_SHIFT)) -extern void numa_init_array (void );extern int numa_off;extern unsigned long numa_free_all_bootmem (void );
@@ -28,7 +27,6 @@ extern void setup_node_bootmem(int nodeid, unsigned long start,*/ #define NODE_MIN_SIZE (4*1024*1024) -extern void __init init_cpu_to_node (void );extern int __cpuinit numa_cpu_node (int cpu);#ifdef CONFIG_NUMA_EMU
@@ -36,7 +34,6 @@ extern int __cpuinit numa_cpu_node(int cpu);#define FAKE_NODE_MIN_HASH_MASK (~(FAKE_NODE_MIN_SIZE - 1UL))#endif /* CONFIG_NUMA_EMU */ #else -static inline void init_cpu_to_node (void ) { }static inline int numa_cpu_node (int cpu) {return NUMA_NO_NODE ; }#endif
arch/x86/kernel/setup.c +0 -2
@@ -1030,9 +1030,7 @@ void __init setup_arch(char **cmdline_p)prefill_possible_map (); -#ifdef CONFIG_X86_64 init_cpu_to_node (); -#endif init_apic_mappings ();ioapic_init_mappings ();
arch/x86/mm/numa.c +72 -4
89 lines not on this page · raw message
arch/x86/mm/numa_32.c +1 -0
@@ -367,6 +367,7 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,*/ get_memcfg_numa (); +numa_init_array (); kva_pages =roundup (calculate_numa_remap_pages (),PTRS_PER_PTE );
arch/x86/mm/numa_64.c +0 -75
87 lines not on this page · raw message
Signature · 1 line
1.7.1
Quoted 10 lines · Tejun Heo
Hello,
This is the second take of unify-x86_32-and-64-NUMA-init-paths patchset. Changes from the last take[L] are,
* As suggested by Ingo, 0004 from the previous series is further split into 0004-0011.
* Comment noting the ugliness of
x86_32logical apicid mapping difference added.
Ingo, ping?
Thanks.
Signature · 1 line
tejun