1. Patchew
  2. linux
  3. View series

[PATCH] sched/topology: Provide arch_llc_mask for cache aware scheduling

Shrikanth Hegde posted 1 patch 1 week, 3 days ago
There is a newer version of this series
arch/powerpc/include/asm/topology.h |  6 ++++++
kernel/sched/topology.c             | 13 +++++++++++--
2 files changed, 17 insertions(+), 2 deletions(-)
[PATCH] sched/topology: Provide arch_llc_mask for cache aware scheduling
Posted by Shrikanth Hegde 1 week, 3 days ago 
Venkat Reported a boot kernel panic next-20260522. Git bisect pointed to
b5ea300a17e3 ("sched/cache: Make LLC id continuous")

Stacktrace points to llc_mask being null.

NIP [c000000000e58504] _find_first_bit+0x44/0x130
LR [c000000000e58500] _find_first_bit+0x40/0x130
Call Trace:
build_sched_domains+0xad8/0xe50
sched_init_smp+0xa8/0x164
kernel_init_freeable+0x250/0x370
ret_from_kernel_user_thread+0x14/0x1c

On powerpc, cpu_coregroup_mask is available only when the underlying
hardware support coregroup. In shared LPAR, QEMU guest or power9 etc
coregroup isn't supported. In such cases llc_mask was being referenced
when it was null leading to panic.

On powerpc, LLC is at SMT core level. So assumption that coregroup(MC)
domain point to LLC is wrong. Provide a way for archs to say where its
LLC is if it not at MC domain. 

Based on tip/master at 5c89783224e9 ("Merge branch into tip/master: 'x86/tdx'")
Cc: stable@vger.kernel.org

Fixes: b5ea300a17e3 ("sched/cache: Make LLC id continuous")
Reported-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Closes: https://lore.kernel.org/all/51154de7-3700-4cb4-82f2-1b3a8fa427f7@linux.ibm.com/
Reviewed-by: Chen Yu <yu.c.chen@intel.com>
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com> 
Tested-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
Co-developed-by: Chen, Yu C <yu.c.chen@intel.com>
Signed-off-by: Shrikanth Hegde <sshegde@linux.ibm.com>
---
 arch/powerpc/include/asm/topology.h |  6 ++++++
 kernel/sched/topology.c             | 13 +++++++++++--
 2 files changed, 17 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index 66ed5fe1b718..e3de0f3d8b86 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -135,6 +135,12 @@ struct cpumask *cpu_coregroup_mask(int cpu);
 const struct cpumask *cpu_die_mask(int cpu);
 int cpu_die_id(int cpu);
 
+/* Points to where the LLC is. On power9 this will point at CACHE
+ * domain, On others it will point to SMT domain. In all cases
+ * cpu_l2_cache_mask points to where LLC is
+ */
+#define arch_llc_mask(cpu)     cpu_l2_cache_mask(cpu)
+
 #ifdef CONFIG_PPC64
 #include <asm/smp.h>
 
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index df2ceb54c970..622e2e01974c 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -2063,12 +2063,21 @@ const struct cpumask *tl_mc_mask(struct sched_domain_topology_level *tl, int cpu
 	return cpu_coregroup_mask(cpu);
 }
 
-#define llc_mask(cpu) cpu_coregroup_mask(cpu)
+/*
+ * Majority of architectures have LLC at MC domain level with exception
+ * such as powerpc. Provide a way for arch to specify where its LLC is
+ * if it falls in exception category
+ */
+# ifndef arch_llc_mask
+#define arch_llc_mask(cpu) cpu_coregroup_mask(cpu)
+# endif
 
 #else
-#define llc_mask(cpu) cpumask_of(cpu)
+#define arch_llc_mask(cpu) cpumask_of(cpu)
 #endif
 
+#define llc_mask(cpu) arch_llc_mask(cpu)
+
 const struct cpumask *tl_pkg_mask(struct sched_domain_topology_level *tl, int cpu)
 {
 	return cpu_node_mask(cpu);
-- 
2.47.3
Re: [PATCH] sched/topology: Provide arch_llc_mask for cache aware scheduling
Posted by Srikar Dronamraju 1 week, 3 days ago 
* Shrikanth Hegde <sshegde@linux.ibm.com> [2026-05-29 13:27:12]:

> Venkat Reported a boot kernel panic next-20260522. Git bisect pointed to
> b5ea300a17e3 ("sched/cache: Make LLC id continuous")
> 
> Stacktrace points to llc_mask being null.
> 
> NIP [c000000000e58504] _find_first_bit+0x44/0x130
> LR [c000000000e58500] _find_first_bit+0x40/0x130
> Call Trace:
> build_sched_domains+0xad8/0xe50
> sched_init_smp+0xa8/0x164
> kernel_init_freeable+0x250/0x370
> ret_from_kernel_user_thread+0x14/0x1c
> 
> On powerpc, cpu_coregroup_mask is available only when the underlying
> hardware support coregroup. In shared LPAR, QEMU guest or power9 etc
> coregroup isn't supported. In such cases llc_mask was being referenced
> when it was null leading to panic.
> 
> On powerpc, LLC is at SMT core level. So assumption that coregroup(MC)
> domain point to LLC is wrong. Provide a way for archs to say where its
> LLC is if it not at MC domain. 
> 
> Based on tip/master at 5c89783224e9 ("Merge branch into tip/master: 'x86/tdx'")
> Cc: stable@vger.kernel.org
> 
> Fixes: b5ea300a17e3 ("sched/cache: Make LLC id continuous")
> Reported-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
> Closes: https://lore.kernel.org/all/51154de7-3700-4cb4-82f2-1b3a8fa427f7@linux.ibm.com/
> Reviewed-by: Chen Yu <yu.c.chen@intel.com>
> Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com> 
> Tested-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
> Co-developed-by: Chen, Yu C <yu.c.chen@intel.com>
> Signed-off-by: Shrikanth Hegde <sshegde@linux.ibm.com>
> ---
>  arch/powerpc/include/asm/topology.h |  6 ++++++
>  kernel/sched/topology.c             | 13 +++++++++++--
>  2 files changed, 17 insertions(+), 2 deletions(-)
> 
> diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
> index 66ed5fe1b718..e3de0f3d8b86 100644
> --- a/arch/powerpc/include/asm/topology.h
> +++ b/arch/powerpc/include/asm/topology.h
> @@ -135,6 +135,12 @@ struct cpumask *cpu_coregroup_mask(int cpu);
>  const struct cpumask *cpu_die_mask(int cpu);
>  int cpu_die_id(int cpu);
>  
> +/* Points to where the LLC is. On power9 this will point at CACHE
> + * domain, On others it will point to SMT domain. In all cases
> + * cpu_l2_cache_mask points to where LLC is
> + */

Nit: Regular comment style could have been better.

> +#define arch_llc_mask(cpu)     cpu_l2_cache_mask(cpu)
> +
>  #ifdef CONFIG_PPC64
>  #include <asm/smp.h>
>  
> diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
> index df2ceb54c970..622e2e01974c 100644
> --- a/kernel/sched/topology.c
> +++ b/kernel/sched/topology.c
> @@ -2063,12 +2063,21 @@ const struct cpumask *tl_mc_mask(struct sched_domain_topology_level *tl, int cpu
>  	return cpu_coregroup_mask(cpu);
>  }
>  
> -#define llc_mask(cpu) cpu_coregroup_mask(cpu)
> +/*
> + * Majority of architectures have LLC at MC domain level with exception
> + * such as powerpc. Provide a way for arch to specify where its LLC is
> + * if it falls in exception category
> + */
> +# ifndef arch_llc_mask
> +#define arch_llc_mask(cpu) cpu_coregroup_mask(cpu)
> +# endif
>  
>  #else
> -#define llc_mask(cpu) cpumask_of(cpu)
> +#define arch_llc_mask(cpu) cpumask_of(cpu)
>  #endif
>  
> +#define llc_mask(cpu) arch_llc_mask(cpu)
> +

Instead of having another define, could we have modified current users of
llc_mask() to arch_llc_mask()? Again its not a problem, but why have 2
defines since both point to the same thing.

>  const struct cpumask *tl_pkg_mask(struct sched_domain_topology_level *tl, int cpu)
>  {
>  	return cpu_node_mask(cpu);
> -- 
> 2.47.3
> 

Otherwise, looks good to me.

Reviewed-by: Srikar Dronamraju <srikar@linux.ibm.com>

-- 
Thanks and Regards
Srikar Dronamraju
Re: [PATCH] sched/topology: Provide arch_llc_mask for cache aware scheduling
Posted by Peter Zijlstra 1 week, 3 days ago 
On Fri, May 29, 2026 at 01:27:12PM +0530, Shrikanth Hegde wrote:
> Venkat Reported a boot kernel panic next-20260522. Git bisect pointed to
> b5ea300a17e3 ("sched/cache: Make LLC id continuous")
> 
> Stacktrace points to llc_mask being null.
> 
> NIP [c000000000e58504] _find_first_bit+0x44/0x130
> LR [c000000000e58500] _find_first_bit+0x40/0x130
> Call Trace:
> build_sched_domains+0xad8/0xe50
> sched_init_smp+0xa8/0x164
> kernel_init_freeable+0x250/0x370
> ret_from_kernel_user_thread+0x14/0x1c
> 
> On powerpc, cpu_coregroup_mask is available only when the underlying
> hardware support coregroup. In shared LPAR, QEMU guest or power9 etc
> coregroup isn't supported. In such cases llc_mask was being referenced
> when it was null leading to panic.
> 
> On powerpc, LLC is at SMT core level. So assumption that coregroup(MC)
> domain point to LLC is wrong. Provide a way for archs to say where its
> LLC is if it not at MC domain. 
> 
> Based on tip/master at 5c89783224e9 ("Merge branch into tip/master: 'x86/tdx'")
> Cc: stable@vger.kernel.org

This seems unwarranted, the patch breaking stuff is in tip:sched/core.

> Fixes: b5ea300a17e3 ("sched/cache: Make LLC id continuous")
> Reported-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
> Closes: https://lore.kernel.org/all/51154de7-3700-4cb4-82f2-1b3a8fa427f7@linux.ibm.com/
> Reviewed-by: Chen Yu <yu.c.chen@intel.com>
> Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com> 
> Tested-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
> Co-developed-by: Chen, Yu C <yu.c.chen@intel.com>
> Signed-off-by: Shrikanth Hegde <sshegde@linux.ibm.com>

Thanks all! I'll stick this in tip:sched/core to go along with the
patches that broke stuff.
[tip: sched/core] sched/topology: Provide arch_llc_mask for cache aware scheduling
Posted by tip-bot2 for Shrikanth Hegde 1 week, 3 days ago 
The following commit has been merged into the sched/core branch of tip:

Commit-ID:     1eae219ea0e80eed83c129e8cae0f007843f1893
Gitweb:        https://git.kernel.org/tip/1eae219ea0e80eed83c129e8cae0f007843f1893
Author:        Shrikanth Hegde <sshegde@linux.ibm.com>
AuthorDate:    Fri, 29 May 2026 13:27:12 +05:30
Committer:     Peter Zijlstra <peterz@infradead.org>
CommitterDate: Fri, 29 May 2026 12:43:15 +02:00

sched/topology: Provide arch_llc_mask for cache aware scheduling

Venkat Reported a boot kernel panic next-20260522. Git bisect pointed to
b5ea300a17e3 ("sched/cache: Make LLC id continuous")

Stacktrace points to llc_mask being null.

  NIP [c000000000e58504] _find_first_bit+0x44/0x130
  LR [c000000000e58500] _find_first_bit+0x40/0x130
  Call Trace:
  build_sched_domains+0xad8/0xe50
  sched_init_smp+0xa8/0x164
  kernel_init_freeable+0x250/0x370
  ret_from_kernel_user_thread+0x14/0x1c

On powerpc, cpu_coregroup_mask is available only when the underlying
hardware support coregroup. In shared LPAR, QEMU guest or power9 etc
coregroup isn't supported. In such cases llc_mask was being referenced
when it was null leading to panic.

On powerpc, LLC is at SMT core level. So assumption that coregroup(MC)
domain point to LLC is wrong. Provide a way for archs to say where its
LLC is if it not at MC domain.

Fixes: b5ea300a17e3 ("sched/cache: Make LLC id continuous")
Closes: https://lore.kernel.org/all/51154de7-3700-4cb4-82f2-1b3a8fa427f7@linux.ibm.com/
Reported-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Co-developed-by: Chen, Yu C <yu.c.chen@intel.com>
Signed-off-by: Shrikanth Hegde <sshegde@linux.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Chen Yu <yu.c.chen@intel.com>
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Tested-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
Link: https://patch.msgid.link/20260529075712.1181039-1-sshegde@linux.ibm.com
---
 arch/powerpc/include/asm/topology.h |  7 +++++++
 kernel/sched/topology.c             | 13 +++++++++++--
 2 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index 66ed5fe..44ec416 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -135,6 +135,13 @@ struct cpumask *cpu_coregroup_mask(int cpu);
 const struct cpumask *cpu_die_mask(int cpu);
 int cpu_die_id(int cpu);
 
+/*
+ * Points to where the LLC is. On power9 this will point at CACHE
+ * domain, On others it will point to SMT domain. In all cases
+ * cpu_l2_cache_mask points to where LLC is
+ */
+#define arch_llc_mask(cpu)     cpu_l2_cache_mask(cpu)
+
 #ifdef CONFIG_PPC64
 #include <asm/smp.h>
 
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index df2ceb5..622e2e0 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -2063,12 +2063,21 @@ const struct cpumask *tl_mc_mask(struct sched_domain_topology_level *tl, int cpu
 	return cpu_coregroup_mask(cpu);
 }
 
-#define llc_mask(cpu) cpu_coregroup_mask(cpu)
+/*
+ * Majority of architectures have LLC at MC domain level with exception
+ * such as powerpc. Provide a way for arch to specify where its LLC is
+ * if it falls in exception category
+ */
+# ifndef arch_llc_mask
+#define arch_llc_mask(cpu) cpu_coregroup_mask(cpu)
+# endif
 
 #else
-#define llc_mask(cpu) cpumask_of(cpu)
+#define arch_llc_mask(cpu) cpumask_of(cpu)
 #endif
 
+#define llc_mask(cpu) arch_llc_mask(cpu)
+
 const struct cpumask *tl_pkg_mask(struct sched_domain_topology_level *tl, int cpu)
 {
 	return cpu_node_mask(cpu);

Patchew 2.1-devel-ea86937

© 2016 - 2026 Red Hat, Inc.