* [PATCH v4 01/10] powerpc/smp: Fix a warning under !NEED_MULTIPLE_NODES
From: Srikar Dronamraju @ 2020-07-27 5:32 UTC (permalink / raw)
To: Michael Ellerman
Cc: Nathan Lynch, Gautham R Shenoy, Michael Neuling,
Srikar Dronamraju, Peter Zijlstra, Jordan Niethe, LKML,
Nicholas Piggin, Valentin Schneider, Oliver O'Halloran,
linuxppc-dev, Ingo Molnar
In-Reply-To: <20200727053230.19753-1-srikar@linux.vnet.ibm.com>
Fix a build warning in a non CONFIG_NEED_MULTIPLE_NODES
"error: _numa_cpu_lookup_table_ undeclared"
Cc: linuxppc-dev <linuxppc-dev@lists.ozlabs.org>
Cc: LKML <linux-kernel@vger.kernel.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Oliver O'Halloran <oohall@gmail.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: Michael Neuling <mikey@neuling.org>
Cc: Gautham R Shenoy <ego@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Valentin Schneider <valentin.schneider@arm.com>
Cc: Jordan Niethe <jniethe5@gmail.com>
Reviewed-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
---
Changelog v2 -> v3:
Removed node caching part. Rewrote the Commit msg (Michael Ellerman)
Renamed to powerpc/smp: Fix a warning under !NEED_MULTIPLE_NODES
arch/powerpc/kernel/smp.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 73199470c265..edf94ca64eea 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -860,6 +860,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
GFP_KERNEL, cpu_to_node(cpu));
zalloc_cpumask_var_node(&per_cpu(cpu_core_map, cpu),
GFP_KERNEL, cpu_to_node(cpu));
+#ifdef CONFIG_NEED_MULTIPLE_NODES
/*
* numa_node_id() works after this.
*/
@@ -868,6 +869,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
set_cpu_numa_mem(cpu,
local_memory_node(numa_cpu_lookup_table[cpu]));
}
+#endif
}
/* Init the cpumasks so the boot CPU is related to itself */
--
2.17.1
^ permalink raw reply related
* [PATCH v4 03/10] powerpc/smp: Move powerpc_topology above
From: Srikar Dronamraju @ 2020-07-27 5:17 UTC (permalink / raw)
To: Michael Ellerman
Cc: Nathan Lynch, Gautham R Shenoy, Michael Neuling,
Srikar Dronamraju, Peter Zijlstra, Jordan Niethe, LKML,
Nicholas Piggin, Valentin Schneider, Oliver O'Halloran,
linuxppc-dev, Ingo Molnar
In-Reply-To: <20200727051805.16728-1-srikar@linux.vnet.ibm.com>
Just moving the powerpc_topology description above.
This will help in using functions in this file and avoid declarations.
No other functional changes
Cc: linuxppc-dev <linuxppc-dev@lists.ozlabs.org>
Cc: LKML <linux-kernel@vger.kernel.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Oliver O'Halloran <oohall@gmail.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: Michael Neuling <mikey@neuling.org>
Cc: Gautham R Shenoy <ego@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Valentin Schneider <valentin.schneider@arm.com>
Cc: Jordan Niethe <jniethe5@gmail.com>
Reviewed-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
---
arch/powerpc/kernel/smp.c | 116 +++++++++++++++++++-------------------
1 file changed, 58 insertions(+), 58 deletions(-)
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 283a04e54f52..a685915e5941 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -818,6 +818,64 @@ static int init_cpu_l1_cache_map(int cpu)
return err;
}
+static bool shared_caches;
+
+#ifdef CONFIG_SCHED_SMT
+/* cpumask of CPUs with asymmetric SMT dependency */
+static int powerpc_smt_flags(void)
+{
+ int flags = SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES;
+
+ if (cpu_has_feature(CPU_FTR_ASYM_SMT)) {
+ printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n");
+ flags |= SD_ASYM_PACKING;
+ }
+ return flags;
+}
+#endif
+
+/*
+ * P9 has a slightly odd architecture where pairs of cores share an L2 cache.
+ * This topology makes it *much* cheaper to migrate tasks between adjacent cores
+ * since the migrated task remains cache hot. We want to take advantage of this
+ * at the scheduler level so an extra topology level is required.
+ */
+static int powerpc_shared_cache_flags(void)
+{
+ return SD_SHARE_PKG_RESOURCES;
+}
+
+/*
+ * We can't just pass cpu_l2_cache_mask() directly because
+ * returns a non-const pointer and the compiler barfs on that.
+ */
+static const struct cpumask *shared_cache_mask(int cpu)
+{
+ if (shared_caches)
+ return cpu_l2_cache_mask(cpu);
+
+ if (has_big_cores)
+ return cpu_smallcore_mask(cpu);
+
+ return per_cpu(cpu_sibling_map, cpu);
+}
+
+#ifdef CONFIG_SCHED_SMT
+static const struct cpumask *smallcore_smt_mask(int cpu)
+{
+ return cpu_smallcore_mask(cpu);
+}
+#endif
+
+static struct sched_domain_topology_level powerpc_topology[] = {
+#ifdef CONFIG_SCHED_SMT
+ { cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) },
+#endif
+ { shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE) },
+ { cpu_cpu_mask, SD_INIT_NAME(DIE) },
+ { NULL, },
+};
+
static int init_big_cores(void)
{
int cpu;
@@ -1247,8 +1305,6 @@ static void add_cpu_to_masks(int cpu)
set_cpus_related(cpu, i, cpu_core_mask);
}
-static bool shared_caches;
-
/* Activate a secondary processor. */
void start_secondary(void *unused)
{
@@ -1312,62 +1368,6 @@ int setup_profiling_timer(unsigned int multiplier)
return 0;
}
-#ifdef CONFIG_SCHED_SMT
-/* cpumask of CPUs with asymmetric SMT dependency */
-static int powerpc_smt_flags(void)
-{
- int flags = SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES;
-
- if (cpu_has_feature(CPU_FTR_ASYM_SMT)) {
- printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n");
- flags |= SD_ASYM_PACKING;
- }
- return flags;
-}
-#endif
-
-/*
- * P9 has a slightly odd architecture where pairs of cores share an L2 cache.
- * This topology makes it *much* cheaper to migrate tasks between adjacent cores
- * since the migrated task remains cache hot. We want to take advantage of this
- * at the scheduler level so an extra topology level is required.
- */
-static int powerpc_shared_cache_flags(void)
-{
- return SD_SHARE_PKG_RESOURCES;
-}
-
-/*
- * We can't just pass cpu_l2_cache_mask() directly because
- * returns a non-const pointer and the compiler barfs on that.
- */
-static const struct cpumask *shared_cache_mask(int cpu)
-{
- if (shared_caches)
- return cpu_l2_cache_mask(cpu);
-
- if (has_big_cores)
- return cpu_smallcore_mask(cpu);
-
- return per_cpu(cpu_sibling_map, cpu);
-}
-
-#ifdef CONFIG_SCHED_SMT
-static const struct cpumask *smallcore_smt_mask(int cpu)
-{
- return cpu_smallcore_mask(cpu);
-}
-#endif
-
-static struct sched_domain_topology_level powerpc_topology[] = {
-#ifdef CONFIG_SCHED_SMT
- { cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) },
-#endif
- { shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE) },
- { cpu_cpu_mask, SD_INIT_NAME(DIE) },
- { NULL, },
-};
-
void __init smp_cpus_done(unsigned int max_cpus)
{
/*
--
2.17.1
^ permalink raw reply related
* [PATCH v4 01/10] powerpc/smp: Fix a warning under !NEED_MULTIPLE_NODES
From: Srikar Dronamraju @ 2020-07-27 5:17 UTC (permalink / raw)
To: Michael Ellerman
Cc: Nathan Lynch, Gautham R Shenoy, Michael Neuling,
Srikar Dronamraju, Peter Zijlstra, Jordan Niethe, LKML,
Nicholas Piggin, Valentin Schneider, Oliver O'Halloran,
linuxppc-dev, Ingo Molnar
In-Reply-To: <20200727051805.16728-1-srikar@linux.vnet.ibm.com>
Fix a build warning in a non CONFIG_NEED_MULTIPLE_NODES
"error: _numa_cpu_lookup_table_ undeclared"
Cc: linuxppc-dev <linuxppc-dev@lists.ozlabs.org>
Cc: LKML <linux-kernel@vger.kernel.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Oliver O'Halloran <oohall@gmail.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: Michael Neuling <mikey@neuling.org>
Cc: Gautham R Shenoy <ego@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Valentin Schneider <valentin.schneider@arm.com>
Cc: Jordan Niethe <jniethe5@gmail.com>
Reviewed-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
---
Changelog v2 -> v3:
Removed node caching part. Rewrote the Commit msg (Michael Ellerman)
Renamed to powerpc/smp: Fix a warning under !NEED_MULTIPLE_NODES
arch/powerpc/kernel/smp.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 73199470c265..edf94ca64eea 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -860,6 +860,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
GFP_KERNEL, cpu_to_node(cpu));
zalloc_cpumask_var_node(&per_cpu(cpu_core_map, cpu),
GFP_KERNEL, cpu_to_node(cpu));
+#ifdef CONFIG_NEED_MULTIPLE_NODES
/*
* numa_node_id() works after this.
*/
@@ -868,6 +869,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
set_cpu_numa_mem(cpu,
local_memory_node(numa_cpu_lookup_table[cpu]));
}
+#endif
}
/* Init the cpumasks so the boot CPU is related to itself */
--
2.17.1
^ permalink raw reply related
* [PATCH v4 10/10] powerpc/smp: Implement cpu_to_coregroup_id
From: Srikar Dronamraju @ 2020-07-27 5:18 UTC (permalink / raw)
To: Michael Ellerman
Cc: Nathan Lynch, Gautham R Shenoy, Michael Neuling,
Srikar Dronamraju, Peter Zijlstra, Jordan Niethe, LKML,
Nicholas Piggin, Valentin Schneider, Oliver O'Halloran,
linuxppc-dev, Ingo Molnar
In-Reply-To: <20200727051805.16728-1-srikar@linux.vnet.ibm.com>
Lookup the coregroup id from the associativity array.
If unable to detect the coregroup id, fallback on the core id.
This way, ensure sched_domain degenerates and an extra sched domain is
not created.
Ideally this function should have been implemented in
arch/powerpc/kernel/smp.c. However if its implemented in mm/numa.c, we
don't need to find the primary domain again.
If the device-tree mentions more than one coregroup, then kernel
implements only the last or the smallest coregroup, which currently
corresponds to the penultimate domain in the device-tree.
Cc: linuxppc-dev <linuxppc-dev@lists.ozlabs.org>
Cc: LKML <linux-kernel@vger.kernel.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Oliver O'Halloran <oohall@gmail.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: Michael Neuling <mikey@neuling.org>
Cc: Gautham R Shenoy <ego@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Valentin Schneider <valentin.schneider@arm.com>
Cc: Jordan Niethe <jniethe5@gmail.com>
Reviewed-by : Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
---
Changelog v1 -> v2:
Move coregroup_enabled before getting associativity (Gautham)
arch/powerpc/mm/numa.c | 20 ++++++++++++++++++++
1 file changed, 20 insertions(+)
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 0d57779e7942..8b3b3ec7fcc4 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -1218,6 +1218,26 @@ int find_and_online_cpu_nid(int cpu)
int cpu_to_coregroup_id(int cpu)
{
+ __be32 associativity[VPHN_ASSOC_BUFSIZE] = {0};
+ int index;
+
+ if (cpu < 0 || cpu > nr_cpu_ids)
+ return -1;
+
+ if (!coregroup_enabled)
+ goto out;
+
+ if (!firmware_has_feature(FW_FEATURE_VPHN))
+ goto out;
+
+ if (vphn_get_associativity(cpu, associativity))
+ goto out;
+
+ index = of_read_number(associativity, 1);
+ if (index > min_common_depth + 1)
+ return of_read_number(&associativity[index - 1], 1);
+
+out:
return cpu_to_core_id(cpu);
}
--
2.17.1
^ permalink raw reply related
* [PATCH v4 09/10] Powerpc/smp: Create coregroup domain
From: Srikar Dronamraju @ 2020-07-27 5:18 UTC (permalink / raw)
To: Michael Ellerman
Cc: Nathan Lynch, Gautham R Shenoy, Michael Neuling,
Srikar Dronamraju, Peter Zijlstra, Jordan Niethe, LKML,
Nicholas Piggin, Valentin Schneider, Oliver O'Halloran,
linuxppc-dev, Ingo Molnar
In-Reply-To: <20200727051805.16728-1-srikar@linux.vnet.ibm.com>
Add percpu coregroup maps and masks to create coregroup domain.
If a coregroup doesn't exist, the coregroup domain will be degenerated
in favour of SMT/CACHE domain.
Cc: linuxppc-dev <linuxppc-dev@lists.ozlabs.org>
Cc: LKML <linux-kernel@vger.kernel.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Oliver O'Halloran <oohall@gmail.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: Michael Neuling <mikey@neuling.org>
Cc: Gautham R Shenoy <ego@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Valentin Schneider <valentin.schneider@arm.com>
Cc: Jordan Niethe <jniethe5@gmail.com>
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
---
Changelog v3 ->v4:
if coregroup_support doesn't exist, update MC mask to the next
smaller domain mask.
Changelog v2 -> v3:
Add optimization for mask updation under coregroup_support
Changelog v1 -> v2:
Moved coregroup topology fixup to fixup_topology (Gautham)
arch/powerpc/include/asm/topology.h | 10 ++++++
arch/powerpc/kernel/smp.c | 48 +++++++++++++++++++++++++++++
arch/powerpc/mm/numa.c | 5 +++
3 files changed, 63 insertions(+)
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index f0b6300e7dd3..6609174918ab 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -88,12 +88,22 @@ static inline int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
#if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR)
extern int find_and_online_cpu_nid(int cpu);
+extern int cpu_to_coregroup_id(int cpu);
#else
static inline int find_and_online_cpu_nid(int cpu)
{
return 0;
}
+static inline int cpu_to_coregroup_id(int cpu)
+{
+#ifdef CONFIG_SMP
+ return cpu_to_core_id(cpu);
+#else
+ return 0;
+#endif
+}
+
#endif /* CONFIG_NUMA && CONFIG_PPC_SPLPAR */
#include <asm-generic/topology.h>
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index dab96a1203ec..95f0bf72e283 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -80,6 +80,7 @@ DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map);
DEFINE_PER_CPU(cpumask_var_t, cpu_smallcore_map);
DEFINE_PER_CPU(cpumask_var_t, cpu_l2_cache_map);
DEFINE_PER_CPU(cpumask_var_t, cpu_core_map);
+DEFINE_PER_CPU(cpumask_var_t, cpu_coregroup_map);
EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
EXPORT_PER_CPU_SYMBOL(cpu_l2_cache_map);
@@ -91,6 +92,7 @@ enum {
smt_idx,
#endif
bigcore_idx,
+ mc_idx,
die_idx,
};
@@ -869,6 +871,21 @@ static const struct cpumask *smallcore_smt_mask(int cpu)
}
#endif
+static struct cpumask *cpu_coregroup_mask(int cpu)
+{
+ return per_cpu(cpu_coregroup_map, cpu);
+}
+
+static bool has_coregroup_support(void)
+{
+ return coregroup_enabled;
+}
+
+static const struct cpumask *cpu_mc_mask(int cpu)
+{
+ return cpu_coregroup_mask(cpu);
+}
+
static const struct cpumask *cpu_bigcore_mask(int cpu)
{
return per_cpu(cpu_sibling_map, cpu);
@@ -879,6 +896,7 @@ static struct sched_domain_topology_level powerpc_topology[] = {
{ cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) },
#endif
{ cpu_bigcore_mask, SD_INIT_NAME(BIGCORE) },
+ { cpu_mc_mask, SD_INIT_NAME(MC) },
{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
{ NULL, },
};
@@ -925,6 +943,10 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
GFP_KERNEL, cpu_to_node(cpu));
zalloc_cpumask_var_node(&per_cpu(cpu_core_map, cpu),
GFP_KERNEL, cpu_to_node(cpu));
+ if (has_coregroup_support())
+ zalloc_cpumask_var_node(&per_cpu(cpu_coregroup_map, cpu),
+ GFP_KERNEL, cpu_to_node(cpu));
+
#ifdef CONFIG_NEED_MULTIPLE_NODES
/*
* numa_node_id() works after this.
@@ -942,6 +964,9 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
cpumask_set_cpu(boot_cpuid, cpu_l2_cache_mask(boot_cpuid));
cpumask_set_cpu(boot_cpuid, cpu_core_mask(boot_cpuid));
+ if (has_coregroup_support())
+ cpumask_set_cpu(boot_cpuid, cpu_coregroup_mask(boot_cpuid));
+
init_big_cores();
if (has_big_cores) {
cpumask_set_cpu(boot_cpuid,
@@ -1233,6 +1258,8 @@ static void remove_cpu_from_masks(int cpu)
set_cpus_unrelated(cpu, i, cpu_sibling_mask);
if (has_big_cores)
set_cpus_unrelated(cpu, i, cpu_smallcore_mask);
+ if (has_coregroup_support())
+ set_cpus_unrelated(cpu, i, cpu_coregroup_mask);
}
}
#endif
@@ -1293,6 +1320,20 @@ static void add_cpu_to_masks(int cpu)
add_cpu_to_smallcore_masks(cpu);
update_mask_by_l2(cpu, cpu_l2_cache_mask);
+ if (has_coregroup_support()) {
+ int coregroup_id = cpu_to_coregroup_id(cpu);
+
+ cpumask_set_cpu(cpu, cpu_coregroup_mask(cpu));
+ for_each_cpu_and(i, cpu_online_mask, cpu_cpu_mask(cpu)) {
+ int fcpu = cpu_first_thread_sibling(i);
+
+ if (fcpu == first_thread)
+ set_cpus_related(cpu, i, cpu_coregroup_mask);
+ else if (coregroup_id == cpu_to_coregroup_id(i))
+ set_cpus_related(cpu, i, cpu_coregroup_mask);
+ }
+ }
+
if (pkg_id == -1) {
struct cpumask *(*mask)(int) = cpu_sibling_mask;
@@ -1398,6 +1439,9 @@ static void fixup_topology(void)
powerpc_topology[bigcore_idx].name = "CACHE";
#endif
}
+
+ if (!has_coregroup_support())
+ powerpc_topology[mc_idx].mask = powerpc_topology[bigcore_idx].mask;
}
void __init smp_cpus_done(unsigned int max_cpus)
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 51cb672f113b..0d57779e7942 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -1216,6 +1216,11 @@ int find_and_online_cpu_nid(int cpu)
return new_nid;
}
+int cpu_to_coregroup_id(int cpu)
+{
+ return cpu_to_core_id(cpu);
+}
+
static int topology_update_init(void)
{
topology_inited = 1;
--
2.17.1
^ permalink raw reply related
* [PATCH v4 08/10] powerpc/smp: Allocate cpumask only after searching thread group
From: Srikar Dronamraju @ 2020-07-27 5:18 UTC (permalink / raw)
To: Michael Ellerman
Cc: Nathan Lynch, Gautham R Shenoy, Michael Neuling,
Srikar Dronamraju, Peter Zijlstra, Jordan Niethe, LKML,
Nicholas Piggin, Valentin Schneider, Oliver O'Halloran,
linuxppc-dev, Ingo Molnar
In-Reply-To: <20200727051805.16728-1-srikar@linux.vnet.ibm.com>
If allocated earlier and the search fails, then cpumask need to be
freed. However cpu_l1_cache_map can be allocated after we search thread
group.
Cc: linuxppc-dev <linuxppc-dev@lists.ozlabs.org>
Cc: LKML <linux-kernel@vger.kernel.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Oliver O'Halloran <oohall@gmail.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: Michael Neuling <mikey@neuling.org>
Cc: Gautham R Shenoy <ego@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Valentin Schneider <valentin.schneider@arm.com>
Cc: Jordan Niethe <jniethe5@gmail.com>
Reviewed-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
---
arch/powerpc/kernel/smp.c | 7 +++----
1 file changed, 3 insertions(+), 4 deletions(-)
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 698000c7f76f..dab96a1203ec 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -797,10 +797,6 @@ static int init_cpu_l1_cache_map(int cpu)
if (err)
goto out;
- zalloc_cpumask_var_node(&per_cpu(cpu_l1_cache_map, cpu),
- GFP_KERNEL,
- cpu_to_node(cpu));
-
cpu_group_start = get_cpu_thread_group_start(cpu, &tg);
if (unlikely(cpu_group_start == -1)) {
@@ -809,6 +805,9 @@ static int init_cpu_l1_cache_map(int cpu)
goto out;
}
+ zalloc_cpumask_var_node(&per_cpu(cpu_l1_cache_map, cpu),
+ GFP_KERNEL, cpu_to_node(cpu));
+
for (i = first_thread; i < first_thread + threads_per_core; i++) {
int i_group_start = get_cpu_thread_group_start(i, &tg);
--
2.17.1
^ permalink raw reply related
* [PATCH v4 07/10] Powerpc/numa: Detect support for coregroup
From: Srikar Dronamraju @ 2020-07-27 5:18 UTC (permalink / raw)
To: Michael Ellerman
Cc: Nathan Lynch, Gautham R Shenoy, Michael Neuling,
Srikar Dronamraju, Peter Zijlstra, Jordan Niethe, LKML,
Nicholas Piggin, Valentin Schneider, Oliver O'Halloran,
linuxppc-dev, Ingo Molnar
In-Reply-To: <20200727051805.16728-1-srikar@linux.vnet.ibm.com>
Add support for grouping cores based on the device-tree classification.
- The last domain in the associativity domains always refers to the
core.
- If primary reference domain happens to be the penultimate domain in
the associativity domains device-tree property, then there are no
coregroups. However if its not a penultimate domain, then there are
coregroups. There can be more than one coregroup. For now we would be
interested in the last or the smallest coregroups.
Cc: linuxppc-dev <linuxppc-dev@lists.ozlabs.org>
Cc: LKML <linux-kernel@vger.kernel.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Oliver O'Halloran <oohall@gmail.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: Michael Neuling <mikey@neuling.org>
Cc: Gautham R Shenoy <ego@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Valentin Schneider <valentin.schneider@arm.com>
Cc: Jordan Niethe <jniethe5@gmail.com>
Reviewed-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
---
Changelog v1 -> v2:
Explained Coregroup in commit msg (Michael Ellerman)
arch/powerpc/include/asm/smp.h | 1 +
arch/powerpc/kernel/smp.c | 1 +
arch/powerpc/mm/numa.c | 34 +++++++++++++++++++++-------------
3 files changed, 23 insertions(+), 13 deletions(-)
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index 49a25e2400f2..5bdc17a7049f 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -28,6 +28,7 @@
extern int boot_cpuid;
extern int spinning_secondaries;
extern u32 *cpu_to_phys_id;
+extern bool coregroup_enabled;
extern void cpu_die(void);
extern int cpu_to_chip_id(int cpu);
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 3c5ccf6d2b1c..698000c7f76f 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -74,6 +74,7 @@ static DEFINE_PER_CPU(int, cpu_state) = { 0 };
struct task_struct *secondary_current;
bool has_big_cores;
+bool coregroup_enabled;
DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map);
DEFINE_PER_CPU(cpumask_var_t, cpu_smallcore_map);
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 2298899a0f0a..51cb672f113b 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -886,7 +886,9 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
static void __init find_possible_nodes(void)
{
struct device_node *rtas;
- u32 numnodes, i;
+ const __be32 *domains;
+ int prop_length, max_nodes;
+ u32 i;
if (!numa_enabled)
return;
@@ -895,25 +897,31 @@ static void __init find_possible_nodes(void)
if (!rtas)
return;
- if (of_property_read_u32_index(rtas, "ibm,current-associativity-domains",
- min_common_depth, &numnodes)) {
- /*
- * ibm,current-associativity-domains is a fairly recent
- * property. If it doesn't exist, then fallback on
- * ibm,max-associativity-domains. Current denotes what the
- * platform can support compared to max which denotes what the
- * Hypervisor can support.
- */
- if (of_property_read_u32_index(rtas, "ibm,max-associativity-domains",
- min_common_depth, &numnodes))
+ /*
+ * ibm,current-associativity-domains is a fairly recent property. If
+ * it doesn't exist, then fallback on ibm,max-associativity-domains.
+ * Current denotes what the platform can support compared to max
+ * which denotes what the Hypervisor can support.
+ */
+ domains = of_get_property(rtas, "ibm,current-associativity-domains",
+ &prop_length);
+ if (!domains) {
+ domains = of_get_property(rtas, "ibm,max-associativity-domains",
+ &prop_length);
+ if (!domains)
goto out;
}
- for (i = 0; i < numnodes; i++) {
+ max_nodes = of_read_number(&domains[min_common_depth], 1);
+ for (i = 0; i < max_nodes; i++) {
if (!node_possible(i))
node_set(i, node_possible_map);
}
+ prop_length /= sizeof(int);
+ if (prop_length > min_common_depth + 2)
+ coregroup_enabled = 1;
+
out:
of_node_put(rtas);
}
--
2.17.1
^ permalink raw reply related
* [PATCH v4 06/10] powerpc/smp: Generalize 2nd sched domain
From: Srikar Dronamraju @ 2020-07-27 5:18 UTC (permalink / raw)
To: Michael Ellerman
Cc: Nathan Lynch, Gautham R Shenoy, Michael Neuling,
Srikar Dronamraju, Peter Zijlstra, Jordan Niethe, LKML,
Nicholas Piggin, Valentin Schneider, Oliver O'Halloran,
linuxppc-dev, Ingo Molnar
In-Reply-To: <20200727051805.16728-1-srikar@linux.vnet.ibm.com>
Currently "CACHE" domain happens to be the 2nd sched domain as per
powerpc_topology. This domain will collapse if cpumask of l2-cache is
same as SMT domain. However we could generalize this domain such that it
could mean either be a "CACHE" domain or a "BIGCORE" domain.
While setting up the "CACHE" domain, check if shared_cache is already
set.
Cc: linuxppc-dev <linuxppc-dev@lists.ozlabs.org>
Cc: LKML <linux-kernel@vger.kernel.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Oliver O'Halloran <oohall@gmail.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: Michael Neuling <mikey@neuling.org>
Cc: Gautham R Shenoy <ego@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Valentin Schneider <valentin.schneider@arm.com>
Cc: Jordan Niethe <jniethe5@gmail.com>
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
---
Changelog v1 -> v2:
Moved shared_cache topology fixup to fixup_topology (Gautham)
arch/powerpc/kernel/smp.c | 49 ++++++++++++++++++++++++++++-----------
1 file changed, 35 insertions(+), 14 deletions(-)
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index d997c7411664..3c5ccf6d2b1c 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -85,6 +85,14 @@ EXPORT_PER_CPU_SYMBOL(cpu_l2_cache_map);
EXPORT_PER_CPU_SYMBOL(cpu_core_map);
EXPORT_SYMBOL_GPL(has_big_cores);
+enum {
+#ifdef CONFIG_SCHED_SMT
+ smt_idx,
+#endif
+ bigcore_idx,
+ die_idx,
+};
+
#define MAX_THREAD_LIST_SIZE 8
#define THREAD_GROUP_SHARE_L1 1
struct thread_groups {
@@ -851,13 +859,7 @@ static int powerpc_shared_cache_flags(void)
*/
static const struct cpumask *shared_cache_mask(int cpu)
{
- if (shared_caches)
- return cpu_l2_cache_mask(cpu);
-
- if (has_big_cores)
- return cpu_smallcore_mask(cpu);
-
- return per_cpu(cpu_sibling_map, cpu);
+ return per_cpu(cpu_l2_cache_map, cpu);
}
#ifdef CONFIG_SCHED_SMT
@@ -867,11 +869,16 @@ static const struct cpumask *smallcore_smt_mask(int cpu)
}
#endif
+static const struct cpumask *cpu_bigcore_mask(int cpu)
+{
+ return per_cpu(cpu_sibling_map, cpu);
+}
+
static struct sched_domain_topology_level powerpc_topology[] = {
#ifdef CONFIG_SCHED_SMT
{ cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) },
#endif
- { shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE) },
+ { cpu_bigcore_mask, SD_INIT_NAME(BIGCORE) },
{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
{ NULL, },
};
@@ -1311,7 +1318,6 @@ static void add_cpu_to_masks(int cpu)
void start_secondary(void *unused)
{
unsigned int cpu = smp_processor_id();
- struct cpumask *(*sibling_mask)(int) = cpu_sibling_mask;
mmgrab(&init_mm);
current->active_mm = &init_mm;
@@ -1337,14 +1343,20 @@ void start_secondary(void *unused)
/* Update topology CPU masks */
add_cpu_to_masks(cpu);
- if (has_big_cores)
- sibling_mask = cpu_smallcore_mask;
/*
* Check for any shared caches. Note that this must be done on a
* per-core basis because one core in the pair might be disabled.
*/
- if (!cpumask_equal(cpu_l2_cache_mask(cpu), sibling_mask(cpu)))
- shared_caches = true;
+ if (!shared_caches) {
+ struct cpumask *(*sibling_mask)(int) = cpu_sibling_mask;
+ struct cpumask *mask = cpu_l2_cache_mask(cpu);
+
+ if (has_big_cores)
+ sibling_mask = cpu_smallcore_mask;
+
+ if (cpumask_weight(mask) > cpumask_weight(sibling_mask(cpu)))
+ shared_caches = true;
+ }
set_numa_node(numa_cpu_lookup_table[cpu]);
set_numa_mem(local_memory_node(numa_cpu_lookup_table[cpu]));
@@ -1375,9 +1387,17 @@ static void fixup_topology(void)
#ifdef CONFIG_SCHED_SMT
if (has_big_cores) {
pr_info("Big cores detected but using small core scheduling\n");
- powerpc_topology[0].mask = smallcore_smt_mask;
+ powerpc_topology[smt_idx].mask = smallcore_smt_mask;
}
#endif
+ if (shared_caches) {
+ pr_info("Using shared cache scheduler topology\n");
+ powerpc_topology[bigcore_idx].mask = shared_cache_mask;
+ powerpc_topology[bigcore_idx].sd_flags = powerpc_shared_cache_flags;
+#ifdef CONFIG_SCHED_DEBUG
+ powerpc_topology[bigcore_idx].name = "CACHE";
+#endif
+ }
}
void __init smp_cpus_done(unsigned int max_cpus)
--
2.17.1
^ permalink raw reply related
* [PATCH v4 05/10] powerpc/smp: Dont assume l2-cache to be superset of sibling
From: Srikar Dronamraju @ 2020-07-27 5:18 UTC (permalink / raw)
To: Michael Ellerman
Cc: Nathan Lynch, Gautham R Shenoy, Michael Neuling,
Srikar Dronamraju, Peter Zijlstra, Jordan Niethe, LKML,
Nicholas Piggin, Valentin Schneider, Oliver O'Halloran,
linuxppc-dev, Ingo Molnar
In-Reply-To: <20200727051805.16728-1-srikar@linux.vnet.ibm.com>
Current code assumes that cpumask of cpus sharing a l2-cache mask will
always be a superset of cpu_sibling_mask.
Lets stop that assumption. cpu_l2_cache_mask is a superset of
cpu_sibling_mask if and only if shared_caches is set.
Cc: linuxppc-dev <linuxppc-dev@lists.ozlabs.org>
Cc: LKML <linux-kernel@vger.kernel.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Oliver O'Halloran <oohall@gmail.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: Michael Neuling <mikey@neuling.org>
Cc: Gautham R Shenoy <ego@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Valentin Schneider <valentin.schneider@arm.com>
Cc: Jordan Niethe <jniethe5@gmail.com>
Reviewed-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
---
Changelog v1 -> v2:
Set cpumask after verifying l2-cache. (Gautham)
arch/powerpc/kernel/smp.c | 28 +++++++++++++++-------------
1 file changed, 15 insertions(+), 13 deletions(-)
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index da27f6909be1..d997c7411664 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -1194,6 +1194,7 @@ static bool update_mask_by_l2(int cpu, struct cpumask *(*mask_fn)(int))
if (!l2_cache)
return false;
+ cpumask_set_cpu(cpu, mask_fn(cpu));
for_each_cpu(i, cpu_online_mask) {
/*
* when updating the marks the current CPU has not been marked
@@ -1276,29 +1277,30 @@ static void add_cpu_to_masks(int cpu)
* add it to it's own thread sibling mask.
*/
cpumask_set_cpu(cpu, cpu_sibling_mask(cpu));
+ cpumask_set_cpu(cpu, cpu_core_mask(cpu));
for (i = first_thread; i < first_thread + threads_per_core; i++)
if (cpu_online(i))
set_cpus_related(i, cpu, cpu_sibling_mask);
add_cpu_to_smallcore_masks(cpu);
- /*
- * Copy the thread sibling mask into the cache sibling mask
- * and mark any CPUs that share an L2 with this CPU.
- */
- for_each_cpu(i, cpu_sibling_mask(cpu))
- set_cpus_related(cpu, i, cpu_l2_cache_mask);
update_mask_by_l2(cpu, cpu_l2_cache_mask);
- /*
- * Copy the cache sibling mask into core sibling mask and mark
- * any CPUs on the same chip as this CPU.
- */
- for_each_cpu(i, cpu_l2_cache_mask(cpu))
- set_cpus_related(cpu, i, cpu_core_mask);
+ if (pkg_id == -1) {
+ struct cpumask *(*mask)(int) = cpu_sibling_mask;
+
+ /*
+ * Copy the sibling mask into core sibling mask and
+ * mark any CPUs on the same chip as this CPU.
+ */
+ if (shared_caches)
+ mask = cpu_l2_cache_mask;
+
+ for_each_cpu(i, mask(cpu))
+ set_cpus_related(cpu, i, cpu_core_mask);
- if (pkg_id == -1)
return;
+ }
for_each_cpu(i, cpu_online_mask)
if (get_physical_package_id(i) == pkg_id)
--
2.17.1
^ permalink raw reply related
* [PATCH v4 04/10] powerpc/smp: Move topology fixups into a new function
From: Srikar Dronamraju @ 2020-07-27 5:17 UTC (permalink / raw)
To: Michael Ellerman
Cc: Nathan Lynch, Gautham R Shenoy, Michael Neuling,
Srikar Dronamraju, Peter Zijlstra, Jordan Niethe, LKML,
Nicholas Piggin, Valentin Schneider, Oliver O'Halloran,
linuxppc-dev, Ingo Molnar
In-Reply-To: <20200727051805.16728-1-srikar@linux.vnet.ibm.com>
Move topology fixup based on the platform attributes into its own
function which is called just before set_sched_topology.
Cc: linuxppc-dev <linuxppc-dev@lists.ozlabs.org>
Cc: LKML <linux-kernel@vger.kernel.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Oliver O'Halloran <oohall@gmail.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: Michael Neuling <mikey@neuling.org>
Cc: Gautham R Shenoy <ego@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Valentin Schneider <valentin.schneider@arm.com>
Cc: Jordan Niethe <jniethe5@gmail.com>
Reviewed-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
---
Changelog v2 -> v3:
Rewrote changelog (Gautham)
Renamed to powerpc/smp: Move topology fixups into a new function
arch/powerpc/kernel/smp.c | 17 +++++++++++------
1 file changed, 11 insertions(+), 6 deletions(-)
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index a685915e5941..da27f6909be1 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -1368,6 +1368,16 @@ int setup_profiling_timer(unsigned int multiplier)
return 0;
}
+static void fixup_topology(void)
+{
+#ifdef CONFIG_SCHED_SMT
+ if (has_big_cores) {
+ pr_info("Big cores detected but using small core scheduling\n");
+ powerpc_topology[0].mask = smallcore_smt_mask;
+ }
+#endif
+}
+
void __init smp_cpus_done(unsigned int max_cpus)
{
/*
@@ -1381,12 +1391,7 @@ void __init smp_cpus_done(unsigned int max_cpus)
dump_numa_cpu_topology();
-#ifdef CONFIG_SCHED_SMT
- if (has_big_cores) {
- pr_info("Big cores detected but using small core scheduling\n");
- powerpc_topology[0].mask = smallcore_smt_mask;
- }
-#endif
+ fixup_topology();
set_sched_topology(powerpc_topology);
}
--
2.17.1
^ permalink raw reply related
* [PATCH v4 02/10] powerpc/smp: Merge Power9 topology with Power topology
From: Srikar Dronamraju @ 2020-07-27 5:17 UTC (permalink / raw)
To: Michael Ellerman
Cc: Nathan Lynch, Gautham R Shenoy, Michael Neuling,
Srikar Dronamraju, Peter Zijlstra, Jordan Niethe, LKML,
Nicholas Piggin, Valentin Schneider, Oliver O'Halloran,
linuxppc-dev, Ingo Molnar
In-Reply-To: <20200727051805.16728-1-srikar@linux.vnet.ibm.com>
A new sched_domain_topology_level was added just for Power9. However the
same can be achieved by merging powerpc_topology with power9_topology
and makes the code more simpler especially when adding a new sched
domain.
Cc: linuxppc-dev <linuxppc-dev@lists.ozlabs.org>
Cc: LKML <linux-kernel@vger.kernel.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Oliver O'Halloran <oohall@gmail.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: Michael Neuling <mikey@neuling.org>
Cc: Gautham R Shenoy <ego@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Valentin Schneider <valentin.schneider@arm.com>
Cc: Jordan Niethe <jniethe5@gmail.com>
Reviewed-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
---
Changelog v1 -> v2:
Replaced a reference to cpu_smt_mask with per_cpu(cpu_sibling_map, cpu)
since cpu_smt_mask is only defined under CONFIG_SCHED_SMT
arch/powerpc/kernel/smp.c | 33 ++++++++++-----------------------
1 file changed, 10 insertions(+), 23 deletions(-)
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index edf94ca64eea..283a04e54f52 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -1313,7 +1313,7 @@ int setup_profiling_timer(unsigned int multiplier)
}
#ifdef CONFIG_SCHED_SMT
-/* cpumask of CPUs with asymetric SMT dependancy */
+/* cpumask of CPUs with asymmetric SMT dependency */
static int powerpc_smt_flags(void)
{
int flags = SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES;
@@ -1326,14 +1326,6 @@ static int powerpc_smt_flags(void)
}
#endif
-static struct sched_domain_topology_level powerpc_topology[] = {
-#ifdef CONFIG_SCHED_SMT
- { cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) },
-#endif
- { cpu_cpu_mask, SD_INIT_NAME(DIE) },
- { NULL, },
-};
-
/*
* P9 has a slightly odd architecture where pairs of cores share an L2 cache.
* This topology makes it *much* cheaper to migrate tasks between adjacent cores
@@ -1351,7 +1343,13 @@ static int powerpc_shared_cache_flags(void)
*/
static const struct cpumask *shared_cache_mask(int cpu)
{
- return cpu_l2_cache_mask(cpu);
+ if (shared_caches)
+ return cpu_l2_cache_mask(cpu);
+
+ if (has_big_cores)
+ return cpu_smallcore_mask(cpu);
+
+ return per_cpu(cpu_sibling_map, cpu);
}
#ifdef CONFIG_SCHED_SMT
@@ -1361,7 +1359,7 @@ static const struct cpumask *smallcore_smt_mask(int cpu)
}
#endif
-static struct sched_domain_topology_level power9_topology[] = {
+static struct sched_domain_topology_level powerpc_topology[] = {
#ifdef CONFIG_SCHED_SMT
{ cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) },
#endif
@@ -1386,21 +1384,10 @@ void __init smp_cpus_done(unsigned int max_cpus)
#ifdef CONFIG_SCHED_SMT
if (has_big_cores) {
pr_info("Big cores detected but using small core scheduling\n");
- power9_topology[0].mask = smallcore_smt_mask;
powerpc_topology[0].mask = smallcore_smt_mask;
}
#endif
- /*
- * If any CPU detects that it's sharing a cache with another CPU then
- * use the deeper topology that is aware of this sharing.
- */
- if (shared_caches) {
- pr_info("Using shared cache scheduler topology\n");
- set_sched_topology(power9_topology);
- } else {
- pr_info("Using standard scheduler topology\n");
- set_sched_topology(powerpc_topology);
- }
+ set_sched_topology(powerpc_topology);
}
#ifdef CONFIG_HOTPLUG_CPU
--
2.17.1
^ permalink raw reply related
* [PATCH v4 00/10] Coregroup support on Powerpc
From: Srikar Dronamraju @ 2020-07-27 5:17 UTC (permalink / raw)
To: Michael Ellerman
Cc: Nathan Lynch, Gautham R Shenoy, Oliver OHalloran, Michael Neuling,
Srikar Dronamraju, Michael Ellerman, Peter Zijlstra,
Jordan Niethe, Anton Blanchard, LKML, Valentin Schneider,
Nick Piggin, linuxppc-dev, Ingo Molnar
Changelog v3 ->v4:
v3: https://lore.kernel.org/lkml/20200723085116.4731-1-srikar@linux.vnet.ibm.com/t/#u
powerpc/smp: Create coregroup domain
if coregroup_support doesn't exist, update MC mask to the next
smaller domain mask.
Changelog v2 -> v3:
v2: https://lore.kernel.org/linuxppc-dev/20200721113814.32284-1-srikar@linux.vnet.ibm.com/t/#u
powerpc/smp: Cache node for reuse
Removed node caching part. Rewrote the Commit msg (Michael Ellerman)
Renamed to powerpc/smp: Fix a warning under !NEED_MULTIPLE_NODES
powerpc/smp: Enable small core scheduling sooner
Rewrote changelog (Gautham)
Renamed to powerpc/smp: Move topology fixups into a new function
powerpc/smp: Create coregroup domain
Add optimization for mask updation under coregroup_support
Changelog v1 -> v2:
v1: https://lore.kernel.org/linuxppc-dev/20200714043624.5648-1-srikar@linux.vnet.ibm.com/t/#u
powerpc/smp: Merge Power9 topology with Power topology
Replaced a reference to cpu_smt_mask with per_cpu(cpu_sibling_map, cpu)
since cpu_smt_mask is only defined under CONFIG_SCHED_SMT
powerpc/smp: Enable small core scheduling sooner
Restored the previous info msg (Jordan)
Moved big core topology fixup to fixup_topology (Gautham)
powerpc/smp: Dont assume l2-cache to be superset of sibling
Set cpumask after verifying l2-cache. (Gautham)
powerpc/smp: Generalize 2nd sched domain
Moved shared_cache topology fixup to fixup_topology (Gautham)
Powerpc/numa: Detect support for coregroup
Explained Coregroup in commit msg (Michael Ellerman)
Powerpc/smp: Create coregroup domain
Moved coregroup topology fixup to fixup_topology (Gautham)
powerpc/smp: Implement cpu_to_coregroup_id
Move coregroup_enabled before getting associativity (Gautham)
powerpc/smp: Provide an ability to disable coregroup
Patch dropped (Michael Ellerman)
Cleanup of existing powerpc topologies and add coregroup support on
Powerpc. Coregroup is a group of (subset of) cores of a DIE that share
a resource.
Patch 7 of this patch series: "Powerpc/numa: Detect support for coregroup"
depends on
https://lore.kernel.org/linuxppc-dev/20200707140644.7241-1-srikar@linux.vnet.ibm.com/t/#u
However it should be easy to rebase the patch without the above patch.
This patch series is based on top of current powerpc/next tree + the
above patch.
On Power 8 Systems
------------------
$ tail /proc/cpuinfo
processor : 255
cpu : POWER8 (architected), altivec supported
clock : 3724.000000MHz
revision : 2.1 (pvr 004b 0201)
timebase : 512000000
platform : pSeries
model : IBM,8408-E8E
machine : CHRP IBM,8408-E8E
MMU : Hash
Before the patchset
-------------------
$ cat /proc/sys/kernel/sched_domain/cpu0/domain*/name
SMT
DIE
NUMA
NUMA
$ head /proc/schedstat
version 15
timestamp 4295534931
cpu0 0 0 0 0 0 0 41389823338 17682779896 14117
domain0 00000000,00000000,00000000,00000000,00000000,00000000,00000000,000000ff 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
domain1 00000000,00000000,00000000,00000000,00000000,00000000,00000000,ffffffff 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
domain2 00000000,00000000,00000000,00000000,00000000,00000000,ffffffff,ffffffff 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
domain3 ffffffff,ffffffff,ffffffff,ffffffff,ffffffff,ffffffff,ffffffff,ffffffff 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
cpu1 0 0 0 0 0 0 27087859050 152273672 10396
domain0 00000000,00000000,00000000,00000000,00000000,00000000,00000000,000000ff 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
domain1 00000000,00000000,00000000,00000000,00000000,00000000,00000000,ffffffff 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
After the patchset
------------------
$ cat /proc/sys/kernel/sched_domain/cpu0/domain*/name
SMT
DIE
NUMA
NUMA
$ head /proc/schedstat
version 15
timestamp 4295534931
cpu0 0 0 0 0 0 0 41389823338 17682779896 14117
domain0 00000000,00000000,00000000,00000000,00000000,00000000,00000000,000000ff 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
domain1 00000000,00000000,00000000,00000000,00000000,00000000,00000000,ffffffff 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
domain2 00000000,00000000,00000000,00000000,00000000,00000000,ffffffff,ffffffff 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
domain3 ffffffff,ffffffff,ffffffff,ffffffff,ffffffff,ffffffff,ffffffff,ffffffff 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
cpu1 0 0 0 0 0 0 27087859050 152273672 10396
domain0 00000000,00000000,00000000,00000000,00000000,00000000,00000000,000000ff 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
domain1 00000000,00000000,00000000,00000000,00000000,00000000,00000000,ffffffff 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
On Power 9 (with device-tree enablement to show coregroups).
(hunks for mimicing a coregroup was posted at
https://lore.kernel.org/linuxppc-dev/20200714043624.5648-1-srikar@linux.vnet.ibm.com/t/#m2cb09bb11c7a93257d6123d1d27edb8212f8af21)
-----------------------------------------------------------
$ tail /proc/cpuinfo
processor : 127
cpu : POWER9 (architected), altivec supported
clock : 3000.000000MHz
revision : 2.2 (pvr 004e 0202)
timebase : 512000000
platform : pSeries
model : IBM,9008-22L
machine : CHRP IBM,9008-22L
MMU : Hash
Before patchset
--------------
$ cat /proc/sys/kernel/sched_domain/cpu0/domain*/name
SMT
CACHE
DIE
NUMA
$ head /proc/schedstat
version 15
timestamp 4318242208
cpu0 0 0 0 0 0 0 28077107004 4773387362 78205
domain0 00000000,00000000,00000000,00000055 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
domain1 00000000,00000000,00000000,000000ff 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
domain2 00000000,00000000,ffffffff,ffffffff 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
domain3 ffffffff,ffffffff,ffffffff,ffffffff 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
cpu1 0 0 0 0 0 0 24177439200 413887604 75393
domain0 00000000,00000000,00000000,000000aa 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
domain1 00000000,00000000,00000000,000000ff 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
After patchset
--------------
$ cat /proc/sys/kernel/sched_domain/cpu0/domain*/name
SMT
CACHE
MC
DIE
NUMA
$ head /proc/schedstat
version 15
timestamp 4318242208
cpu0 0 0 0 0 0 0 28077107004 4773387362 78205
domain0 00000000,00000000,00000000,00000055 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
domain1 00000000,00000000,00000000,000000ff 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
domain2 00000000,00000000,00000000,ffffffff 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
domain3 00000000,00000000,ffffffff,ffffffff 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
domain4 ffffffff,ffffffff,ffffffff,ffffffff 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
cpu1 0 0 0 0 0 0 24177439200 413887604 75393
domain0 00000000,00000000,00000000,000000aa 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
Cc: linuxppc-dev <linuxppc-dev@lists.ozlabs.org>
Cc: LKML <linux-kernel@vger.kernel.org>
Cc: Michael Ellerman <michaele@au1.ibm.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Valentin Schneider <valentin.schneider@arm.com>
Cc: Nick Piggin <npiggin@au1.ibm.com>
Cc: Oliver OHalloran <oliveroh@au1.ibm.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: Michael Neuling <mikey@linux.ibm.com>
Cc: Anton Blanchard <anton@au1.ibm.com>
Cc: Gautham R Shenoy <ego@linux.vnet.ibm.com>
Cc: Vaidyanathan Srinivasan <svaidy@linux.ibm.com>
Cc: Jordan Niethe <jniethe5@gmail.com>
Srikar Dronamraju (10):
powerpc/smp: Fix a warning under !NEED_MULTIPLE_NODES
powerpc/smp: Merge Power9 topology with Power topology
powerpc/smp: Move powerpc_topology above
powerpc/smp: Move topology fixups into a new function
powerpc/smp: Dont assume l2-cache to be superset of sibling
powerpc/smp: Generalize 2nd sched domain
powerpc/numa: Detect support for coregroup
powerpc/smp: Allocate cpumask only after searching thread group
powerpc/smp: Create coregroup domain
powerpc/smp: Implement cpu_to_coregroup_id
arch/powerpc/include/asm/smp.h | 1 +
arch/powerpc/include/asm/topology.h | 10 ++
arch/powerpc/kernel/smp.c | 246 +++++++++++++++++-----------
arch/powerpc/mm/numa.c | 59 +++++--
4 files changed, 210 insertions(+), 106 deletions(-)
--
2.17.1
^ permalink raw reply
* Re: [PATCH v3 09/10] powerpc/smp: Create coregroup domain
From: Gautham R Shenoy @ 2020-07-27 4:39 UTC (permalink / raw)
To: Srikar Dronamraju
Cc: Nathan Lynch, Gautham R Shenoy, Michael Neuling, Peter Zijlstra,
LKML, Nicholas Piggin, Valentin Schneider, Oliver O'Halloran,
Jordan Niethe, linuxppc-dev, Ingo Molnar
In-Reply-To: <20200723085116.4731-10-srikar@linux.vnet.ibm.com>
On Thu, Jul 23, 2020 at 02:21:15PM +0530, Srikar Dronamraju wrote:
> Add percpu coregroup maps and masks to create coregroup domain.
> If a coregroup doesn't exist, the coregroup domain will be degenerated
> in favour of SMT/CACHE domain.
>
> Cc: linuxppc-dev <linuxppc-dev@lists.ozlabs.org>
> Cc: LKML <linux-kernel@vger.kernel.org>
> Cc: Michael Ellerman <mpe@ellerman.id.au>
> Cc: Nicholas Piggin <npiggin@gmail.com>
> Cc: Anton Blanchard <anton@ozlabs.org>
> Cc: Oliver O'Halloran <oohall@gmail.com>
> Cc: Nathan Lynch <nathanl@linux.ibm.com>
> Cc: Michael Neuling <mikey@neuling.org>
> Cc: Gautham R Shenoy <ego@linux.vnet.ibm.com>
> Cc: Ingo Molnar <mingo@kernel.org>
> Cc: Peter Zijlstra <peterz@infradead.org>
> Cc: Valentin Schneider <valentin.schneider@arm.com>
> Cc: Jordan Niethe <jniethe5@gmail.com>
> Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
> ---
> Changelog v2 -> v3:
> Add optimization for mask updation under coregroup_support
>
> Changelog v1 -> v2:
> Moved coregroup topology fixup to fixup_topology (Gautham)
>
> arch/powerpc/include/asm/topology.h | 10 +++++++
> arch/powerpc/kernel/smp.c | 44 +++++++++++++++++++++++++++++
> arch/powerpc/mm/numa.c | 5 ++++
> 3 files changed, 59 insertions(+)
>
> diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
> index f0b6300e7dd3..6609174918ab 100644
> --- a/arch/powerpc/include/asm/topology.h
> +++ b/arch/powerpc/include/asm/topology.h
> @@ -88,12 +88,22 @@ static inline int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
>
> #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR)
> extern int find_and_online_cpu_nid(int cpu);
> +extern int cpu_to_coregroup_id(int cpu);
> #else
> static inline int find_and_online_cpu_nid(int cpu)
> {
> return 0;
> }
>
> +static inline int cpu_to_coregroup_id(int cpu)
> +{
> +#ifdef CONFIG_SMP
> + return cpu_to_core_id(cpu);
> +#else
> + return 0;
> +#endif
> +}
> +
> #endif /* CONFIG_NUMA && CONFIG_PPC_SPLPAR */
>
> #include <asm-generic/topology.h>
> diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
> index 7d8d44cbab11..1faedde3e406 100644
> --- a/arch/powerpc/kernel/smp.c
> +++ b/arch/powerpc/kernel/smp.c
> @@ -80,6 +80,7 @@ DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map);
> DEFINE_PER_CPU(cpumask_var_t, cpu_smallcore_map);
> DEFINE_PER_CPU(cpumask_var_t, cpu_l2_cache_map);
> DEFINE_PER_CPU(cpumask_var_t, cpu_core_map);
> +DEFINE_PER_CPU(cpumask_var_t, cpu_coregroup_map);
>
> EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
> EXPORT_PER_CPU_SYMBOL(cpu_l2_cache_map);
> @@ -91,6 +92,7 @@ enum {
> smt_idx,
> #endif
> bigcore_idx,
> + mc_idx,
> die_idx,
> };
>
> @@ -869,6 +871,21 @@ static const struct cpumask *smallcore_smt_mask(int cpu)
> }
> #endif
>
> +static struct cpumask *cpu_coregroup_mask(int cpu)
> +{
> + return per_cpu(cpu_coregroup_map, cpu);
> +}
> +
> +static bool has_coregroup_support(void)
> +{
> + return coregroup_enabled;
> +}
> +
> +static const struct cpumask *cpu_mc_mask(int cpu)
> +{
> + return cpu_coregroup_mask(cpu);
> +}
> +
> static const struct cpumask *cpu_bigcore_mask(int cpu)
> {
> return per_cpu(cpu_sibling_map, cpu);
> @@ -879,6 +896,7 @@ static struct sched_domain_topology_level powerpc_topology[] = {
> { cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) },
> #endif
> { cpu_bigcore_mask, SD_INIT_NAME(BIGCORE) },
> + { cpu_mc_mask, SD_INIT_NAME(MC) },
> { cpu_cpu_mask, SD_INIT_NAME(DIE) },
> { NULL, },
> };
[..snip..]
> @@ -1384,6 +1425,9 @@ int setup_profiling_timer(unsigned int multiplier)
>
> static void fixup_topology(void)
> {
> + if (!has_coregroup_support())
> + powerpc_topology[mc_idx].mask = cpu_bigcore_mask;
> +
> if (shared_caches) {
> pr_info("Using shared cache scheduler topology\n");
> powerpc_topology[bigcore_idx].mask = shared_cache_mask;
Suppose we consider a topology which does not have coregroup_support,
but has shared_caches. In that case, we would want our coregroup
domain to degenerate.
From the above code, after the fixup, our topology will look as
follows:
static struct sched_domain_topology_level powerpc_topology[] = {
{ cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) },
{ shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE) },
{ cpu_bigcore_mask, SD_INIT_NAME(MC) },
{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
{ NULL, },
So, in this case, the core-group domain (identified by MC) will
degenerate only if cpu_bigcore_mask() and shared_cache_mask() return
the same value. This may work for existing platforms, because either
shared_caches don't exist, or when they do, cpu_bigcore_mask and
shared_cache_mask return the same set of CPUs. But this may or may not
continue to hold good in the future.
Furthermore, if that is always going to be the case that in the
presence of shared_caches the cpu_bigcore_mask() and
shared_cache_mask() will always be the same, then why even define two
separate masks and not just have only the cpu_bigcore_mask() ?
The correct way would be to set the powerpc_topology[mc_idx].mask to
powerpc_topology[bigcore_idx].mask *after* we have fixedup the
big_core level.
--
Thanks and Regards
gautham.
^ permalink raw reply
* [PATCH v2 6/6] selftests/powerpc: Add test for pkey siginfo verification
From: Sandipan Das @ 2020-07-27 4:00 UTC (permalink / raw)
To: mpe; +Cc: fweimer, aneesh.kumar, linuxram, linuxppc-dev, bauerman
In-Reply-To: <cover.1595821792.git.sandipan@linux.ibm.com>
Commit c46241a370a61 ("powerpc/pkeys: Check vma before
returning key fault error to the user") fixes a bug which
causes the kernel to set the wrong pkey in siginfo when a
pkey fault occurs after two competing threads that have
allocated different pkeys, one fully permissive and the
other restrictive, attempt to protect a common page at the
same time. This adds a test to detect the bug.
Signed-off-by: Sandipan Das <sandipan@linux.ibm.com>
---
tools/testing/selftests/powerpc/mm/.gitignore | 1 +
tools/testing/selftests/powerpc/mm/Makefile | 5 +-
.../selftests/powerpc/mm/pkey_siginfo.c | 332 ++++++++++++++++++
3 files changed, 337 insertions(+), 1 deletion(-)
create mode 100644 tools/testing/selftests/powerpc/mm/pkey_siginfo.c
diff --git a/tools/testing/selftests/powerpc/mm/.gitignore b/tools/testing/selftests/powerpc/mm/.gitignore
index 8f841f925baa5..36ec2c4ccdea4 100644
--- a/tools/testing/selftests/powerpc/mm/.gitignore
+++ b/tools/testing/selftests/powerpc/mm/.gitignore
@@ -9,3 +9,4 @@ large_vm_fork_separation
bad_accesses
tlbie_test
pkey_exec_prot
+pkey_siginfo
diff --git a/tools/testing/selftests/powerpc/mm/Makefile b/tools/testing/selftests/powerpc/mm/Makefile
index f9fa0ba7435c4..558b7ccc93932 100644
--- a/tools/testing/selftests/powerpc/mm/Makefile
+++ b/tools/testing/selftests/powerpc/mm/Makefile
@@ -3,7 +3,8 @@ noarg:
$(MAKE) -C ../
TEST_GEN_PROGS := hugetlb_vs_thp_test subpage_prot prot_sao segv_errors wild_bctr \
- large_vm_fork_separation bad_accesses pkey_exec_prot
+ large_vm_fork_separation bad_accesses pkey_exec_prot \
+ pkey_siginfo
TEST_GEN_PROGS_EXTENDED := tlbie_test
TEST_GEN_FILES := tempfile
@@ -18,8 +19,10 @@ $(OUTPUT)/wild_bctr: CFLAGS += -m64
$(OUTPUT)/large_vm_fork_separation: CFLAGS += -m64
$(OUTPUT)/bad_accesses: CFLAGS += -m64
$(OUTPUT)/pkey_exec_prot: CFLAGS += -m64
+$(OUTPUT)/pkey_siginfo: CFLAGS += -m64
$(OUTPUT)/tempfile:
dd if=/dev/zero of=$@ bs=64k count=1
$(OUTPUT)/tlbie_test: LDLIBS += -lpthread
+$(OUTPUT)/pkey_siginfo: LDLIBS += -lpthread
diff --git a/tools/testing/selftests/powerpc/mm/pkey_siginfo.c b/tools/testing/selftests/powerpc/mm/pkey_siginfo.c
new file mode 100644
index 0000000000000..0c57f88f7f01a
--- /dev/null
+++ b/tools/testing/selftests/powerpc/mm/pkey_siginfo.c
@@ -0,0 +1,332 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright 2020, Sandipan Das, IBM Corp.
+ *
+ * Test if the signal information reports the correct memory protection
+ * key upon getting a key access violation fault for a page that was
+ * attempted to be protected by two different keys from two competing
+ * threads at the same time.
+ */
+
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <signal.h>
+
+#include <unistd.h>
+#include <pthread.h>
+#include <sys/mman.h>
+
+#include "pkeys.h"
+
+#define PPC_INST_NOP 0x60000000
+#define PPC_INST_BLR 0x4e800020
+#define PROT_RWX (PROT_READ | PROT_WRITE | PROT_EXEC)
+
+#define NUM_ITERATIONS 1000000
+
+static volatile sig_atomic_t perm_pkey, rest_pkey;
+static volatile sig_atomic_t rights, fault_count;
+static volatile unsigned int *volatile fault_addr;
+static pthread_barrier_t iteration_barrier;
+
+static void segv_handler(int signum, siginfo_t *sinfo, void *ctx)
+{
+ void *pgstart;
+ size_t pgsize;
+ int pkey;
+
+ pkey = siginfo_pkey(sinfo);
+
+ /* Check if this fault originated from a pkey access violation */
+ if (sinfo->si_code != SEGV_PKUERR) {
+ sigsafe_err("got a fault for an unexpected reason\n");
+ _exit(1);
+ }
+
+ /* Check if this fault originated from the expected address */
+ if (sinfo->si_addr != (void *) fault_addr) {
+ sigsafe_err("got a fault for an unexpected address\n");
+ _exit(1);
+ }
+
+ /* Check if this fault originated from the restrictive pkey */
+ if (pkey != rest_pkey) {
+ sigsafe_err("got a fault for an unexpected pkey\n");
+ _exit(1);
+ }
+
+ /* Check if too many faults have occurred for the same iteration */
+ if (fault_count > 0) {
+ sigsafe_err("got too many faults for the same address\n");
+ _exit(1);
+ }
+
+ pgsize = getpagesize();
+ pgstart = (void *) ((unsigned long) fault_addr & ~(pgsize - 1));
+
+ /*
+ * If the current fault occurred due to lack of execute rights,
+ * reassociate the page with the exec-only pkey since execute
+ * rights cannot be changed directly for the faulting pkey as
+ * IAMR is inaccessible from userspace.
+ *
+ * Otherwise, if the current fault occurred due to lack of
+ * read-write rights, change the AMR permission bits for the
+ * pkey.
+ *
+ * This will let the test continue.
+ */
+ if (rights == PKEY_DISABLE_EXECUTE &&
+ mprotect(pgstart, pgsize, PROT_EXEC))
+ _exit(1);
+ else
+ pkey_set_rights(pkey, 0);
+
+ fault_count++;
+}
+
+struct region {
+ unsigned long rights;
+ unsigned int *base;
+ size_t size;
+};
+
+static void *protect(void *p)
+{
+ unsigned long rights;
+ unsigned int *base;
+ size_t size;
+ int tid, i;
+
+ tid = gettid();
+ base = ((struct region *) p)->base;
+ size = ((struct region *) p)->size;
+ FAIL_IF_EXIT(!base);
+
+ /* No read, write and execute restrictions */
+ rights = 0;
+
+ printf("tid %d, pkey permissions are %s\n", tid, pkey_rights(rights));
+
+ /* Allocate the permissive pkey */
+ perm_pkey = sys_pkey_alloc(0, rights);
+ FAIL_IF_EXIT(perm_pkey < 0);
+
+ /*
+ * Repeatedly try to protect the common region with a permissive
+ * pkey
+ */
+ for (i = 0; i < NUM_ITERATIONS; i++) {
+ /*
+ * Wait until the other thread has finished allocating the
+ * restrictive pkey or until the next iteration has begun
+ */
+ pthread_barrier_wait(&iteration_barrier);
+
+ /* Try to associate the permissive pkey with the region */
+ FAIL_IF_EXIT(sys_pkey_mprotect(base, size, PROT_RWX,
+ perm_pkey));
+ }
+
+ /* Free the permissive pkey */
+ sys_pkey_free(perm_pkey);
+
+ return NULL;
+}
+
+static void *protect_access(void *p)
+{
+ size_t size, numinsns;
+ unsigned int *base;
+ int tid, i;
+
+ tid = gettid();
+ base = ((struct region *) p)->base;
+ size = ((struct region *) p)->size;
+ rights = ((struct region *) p)->rights;
+ numinsns = size / sizeof(base[0]);
+ FAIL_IF_EXIT(!base);
+
+ /* Allocate the restrictive pkey */
+ rest_pkey = sys_pkey_alloc(0, rights);
+ FAIL_IF_EXIT(rest_pkey < 0);
+
+ printf("tid %d, pkey permissions are %s\n", tid, pkey_rights(rights));
+ printf("tid %d, %s randomly in range [%p, %p]\n", tid,
+ (rights == PKEY_DISABLE_EXECUTE) ? "execute" :
+ (rights == PKEY_DISABLE_WRITE) ? "write" : "read",
+ base, base + numinsns);
+
+ /*
+ * Repeatedly try to protect the common region with a restrictive
+ * pkey and read, write or execute from it
+ */
+ for (i = 0; i < NUM_ITERATIONS; i++) {
+ /*
+ * Wait until the other thread has finished allocating the
+ * permissive pkey or until the next iteration has begun
+ */
+ pthread_barrier_wait(&iteration_barrier);
+
+ /* Try to associate the restrictive pkey with the region */
+ FAIL_IF_EXIT(sys_pkey_mprotect(base, size, PROT_RWX,
+ rest_pkey));
+
+ /* Choose a random instruction word address from the region */
+ fault_addr = base + (rand() % numinsns);
+ fault_count = 0;
+
+ switch (rights) {
+ /* Read protection test */
+ case PKEY_DISABLE_ACCESS:
+ /*
+ * Read an instruction word from the region and
+ * verify if it has not been overwritten to
+ * something unexpected
+ */
+ FAIL_IF_EXIT(*fault_addr != PPC_INST_NOP &&
+ *fault_addr != PPC_INST_BLR);
+ break;
+
+ /* Write protection test */
+ case PKEY_DISABLE_WRITE:
+ /*
+ * Write an instruction word to the region and
+ * verify if the overwrite has succeeded
+ */
+ *fault_addr = PPC_INST_BLR;
+ FAIL_IF_EXIT(*fault_addr != PPC_INST_BLR);
+ break;
+
+ /* Execute protection test */
+ case PKEY_DISABLE_EXECUTE:
+ /* Jump to the region and execute instructions */
+ asm volatile(
+ "mtctr %0; bctrl"
+ : : "r"(fault_addr) : "ctr", "lr");
+ break;
+ }
+
+ /*
+ * Restore the restrictions originally imposed by the
+ * restrictive pkey as the signal handler would have
+ * cleared out the corresponding AMR bits
+ */
+ pkey_set_rights(rest_pkey, rights);
+ }
+
+ /* Free restrictive pkey */
+ sys_pkey_free(rest_pkey);
+
+ return NULL;
+}
+
+static void reset_pkeys(unsigned long rights)
+{
+ int pkeys[NR_PKEYS], i;
+
+ /* Exhaustively allocate all available pkeys */
+ for (i = 0; i < NR_PKEYS; i++)
+ pkeys[i] = sys_pkey_alloc(0, rights);
+
+ /* Free all allocated pkeys */
+ for (i = 0; i < NR_PKEYS; i++)
+ sys_pkey_free(pkeys[i]);
+}
+
+static int test(void)
+{
+ pthread_t prot_thread, pacc_thread;
+ struct sigaction act;
+ pthread_attr_t attr;
+ size_t numinsns;
+ struct region r;
+ int ret, i;
+
+ srand(time(NULL));
+ ret = pkeys_unsupported();
+ if (ret)
+ return ret;
+
+ /* Allocate the region */
+ r.size = getpagesize();
+ r.base = mmap(NULL, r.size, PROT_RWX,
+ MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+ FAIL_IF(r.base == MAP_FAILED);
+
+ /*
+ * Fill the region with no-ops with a branch at the end
+ * for returning to the caller
+ */
+ numinsns = r.size / sizeof(r.base[0]);
+ for (i = 0; i < numinsns - 1; i++)
+ r.base[i] = PPC_INST_NOP;
+ r.base[i] = PPC_INST_BLR;
+
+ /* Setup SIGSEGV handler */
+ act.sa_handler = 0;
+ act.sa_sigaction = segv_handler;
+ FAIL_IF(sigprocmask(SIG_SETMASK, 0, &act.sa_mask) != 0);
+ act.sa_flags = SA_SIGINFO;
+ act.sa_restorer = 0;
+ FAIL_IF(sigaction(SIGSEGV, &act, NULL) != 0);
+
+ /*
+ * For these tests, the parent process should clear all bits of
+ * AMR and IAMR, i.e. impose no restrictions, for all available
+ * pkeys. This will be the base for the initial AMR and IAMR
+ * values for all the test thread pairs.
+ *
+ * If the AMR and IAMR bits of all available pkeys are cleared
+ * before running the tests and a fault is generated when
+ * attempting to read, write or execute instructions from a
+ * pkey protected region, the pkey responsible for this must be
+ * the one from the protect-and-access thread since the other
+ * one is fully permissive. Despite that, if the pkey reported
+ * by siginfo is not the restrictive pkey, then there must be a
+ * kernel bug.
+ */
+ reset_pkeys(0);
+
+ /* Setup barrier for protect and protect-and-access threads */
+ FAIL_IF(pthread_attr_init(&attr) != 0);
+ FAIL_IF(pthread_barrier_init(&iteration_barrier, NULL, 2) != 0);
+
+ /* Setup and start protect and protect-and-read threads */
+ puts("starting thread pair (protect, protect-and-read)");
+ r.rights = PKEY_DISABLE_ACCESS;
+ FAIL_IF(pthread_create(&prot_thread, &attr, &protect, &r) != 0);
+ FAIL_IF(pthread_create(&pacc_thread, &attr, &protect_access, &r) != 0);
+ FAIL_IF(pthread_join(prot_thread, NULL) != 0);
+ FAIL_IF(pthread_join(pacc_thread, NULL) != 0);
+
+ /* Setup and start protect and protect-and-write threads */
+ puts("starting thread pair (protect, protect-and-write)");
+ r.rights = PKEY_DISABLE_WRITE;
+ FAIL_IF(pthread_create(&prot_thread, &attr, &protect, &r) != 0);
+ FAIL_IF(pthread_create(&pacc_thread, &attr, &protect_access, &r) != 0);
+ FAIL_IF(pthread_join(prot_thread, NULL) != 0);
+ FAIL_IF(pthread_join(pacc_thread, NULL) != 0);
+
+ /* Setup and start protect and protect-and-execute threads */
+ puts("starting thread pair (protect, protect-and-execute)");
+ r.rights = PKEY_DISABLE_EXECUTE;
+ FAIL_IF(pthread_create(&prot_thread, &attr, &protect, &r) != 0);
+ FAIL_IF(pthread_create(&pacc_thread, &attr, &protect_access, &r) != 0);
+ FAIL_IF(pthread_join(prot_thread, NULL) != 0);
+ FAIL_IF(pthread_join(pacc_thread, NULL) != 0);
+
+ /* Cleanup */
+ FAIL_IF(pthread_attr_destroy(&attr) != 0);
+ FAIL_IF(pthread_barrier_destroy(&iteration_barrier) != 0);
+ munmap(r.base, r.size);
+
+ return 0;
+}
+
+int main(void)
+{
+ test_harness(test, "pkey_siginfo");
+}
--
2.25.1
^ permalink raw reply related
* [PATCH v2 4/6] selftests/powerpc: Add helper to exit on failure
From: Sandipan Das @ 2020-07-27 4:00 UTC (permalink / raw)
To: mpe; +Cc: fweimer, aneesh.kumar, linuxram, linuxppc-dev, bauerman
In-Reply-To: <cover.1595821792.git.sandipan@linux.ibm.com>
This adds a helper similar to FAIL_IF() which lets a
program exit with code 1 (to indicate failure) when
the given condition is true.
Signed-off-by: Sandipan Das <sandipan@linux.ibm.com>
---
tools/testing/selftests/powerpc/include/utils.h | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/tools/testing/selftests/powerpc/include/utils.h b/tools/testing/selftests/powerpc/include/utils.h
index 7f259f36e23bc..69d16875802da 100644
--- a/tools/testing/selftests/powerpc/include/utils.h
+++ b/tools/testing/selftests/powerpc/include/utils.h
@@ -72,6 +72,15 @@ do { \
} \
} while (0)
+#define FAIL_IF_EXIT(x) \
+do { \
+ if ((x)) { \
+ fprintf(stderr, \
+ "[FAIL] Test FAILED on line %d\n", __LINE__); \
+ _exit(1); \
+ } \
+} while (0)
+
/* The test harness uses this, yes it's gross */
#define MAGIC_SKIP_RETURN_VALUE 99
--
2.25.1
^ permalink raw reply related
* [PATCH v2 3/6] selftests/powerpc: Harden test for execute-disabled pkeys
From: Sandipan Das @ 2020-07-27 4:00 UTC (permalink / raw)
To: mpe; +Cc: fweimer, aneesh.kumar, linuxram, linuxppc-dev, bauerman
In-Reply-To: <cover.1595821792.git.sandipan@linux.ibm.com>
Commit 192b6a7805989 ("powerpc/book3s64/pkeys: Fix
pkey_access_permitted() for execute disable pkey") fixed a
bug that caused repetitive faults for pkeys with no execute
rights alongside some combination of read and write rights.
This removes the last two cases of the test, which check
the behaviour of pkeys with read, write but no execute
rights and all the rights, in favour of checking all the
possible combinations of read, write and execute rights
to be able to detect bugs like the one mentioned above.
Signed-off-by: Sandipan Das <sandipan@linux.ibm.com>
---
.../selftests/powerpc/mm/pkey_exec_prot.c | 84 +++++++++----------
1 file changed, 41 insertions(+), 43 deletions(-)
diff --git a/tools/testing/selftests/powerpc/mm/pkey_exec_prot.c b/tools/testing/selftests/powerpc/mm/pkey_exec_prot.c
index 18ebfe6bae1c9..9e5c7f3f498a7 100644
--- a/tools/testing/selftests/powerpc/mm/pkey_exec_prot.c
+++ b/tools/testing/selftests/powerpc/mm/pkey_exec_prot.c
@@ -237,55 +237,53 @@ static int test(void)
*fault_addr = PPC_INST_NOP;
FAIL_IF(remaining_faults != 0 || fault_code != SEGV_ACCERR);
- /*
- * Jump to the executable region when AMR bits are set i.e.
- * the pkey permits neither read nor write access.
- *
- * This should generate a pkey fault based on IAMR bits which
- * are set to not permit execution. AMR bits should not affect
- * execution.
- *
- * This also checks if the overwrite of the first instruction
- * word from a trap to a no-op succeeded.
- */
- fault_addr = insns;
- fault_type = PKEY_DISABLE_EXECUTE;
- fault_pkey = pkey;
- remaining_faults = 1;
- FAIL_IF(sys_pkey_mprotect(insns, pgsize, PROT_EXEC, pkey) != 0);
- pkey_set_rights(pkey, PKEY_DISABLE_ACCESS);
- printf("execute at %p, pkey permissions are %s\n", fault_addr,
- pkey_rights(rights));
- asm volatile("mtctr %0; bctrl" : : "r"(insns));
- FAIL_IF(remaining_faults != 0 || fault_code != SEGV_PKUERR);
-
- /*
- * Free the current pkey and allocate a new one that is
- * fully permissive.
- */
+ /* Free the current pkey */
sys_pkey_free(pkey);
+
rights = 0;
- pkey = sys_pkey_alloc(0, rights);
+ do {
+ /*
+ * Allocate pkeys with all valid combinations of read,
+ * write and execute restrictions.
+ */
+ pkey = sys_pkey_alloc(0, rights);
+ FAIL_IF(pkey < 0);
+
+ /*
+ * Jump to the executable region. AMR bits may or may not
+ * be set but they should not affect execution.
+ *
+ * This should generate pkey faults based on IAMR bits which
+ * may be set to restrict execution.
+ *
+ * The first iteration also checks if the overwrite of the
+ * first instruction word from a trap to a no-op succeeded.
+ */
+ fault_pkey = pkey;
+ fault_type = -1;
+ remaining_faults = 0;
+ if (rights & PKEY_DISABLE_EXECUTE) {
+ fault_type = PKEY_DISABLE_EXECUTE;
+ remaining_faults = 1;
+ }
- /*
- * Jump to the executable region when AMR bits are not set
- * i.e. the pkey permits read and write access.
- *
- * This should not generate any faults as the IAMR bits are
- * also not set and hence will the pkey will not restrict
- * execution.
- */
- fault_pkey = pkey;
- remaining_faults = 0;
- FAIL_IF(sys_pkey_mprotect(insns, pgsize, PROT_EXEC, pkey) != 0);
- printf("execute at %p, pkey permissions are %s\n", fault_addr,
- pkey_rights(rights));
- asm volatile("mtctr %0; bctrl" : : "r"(insns));
- FAIL_IF(remaining_faults != 0);
+ FAIL_IF(sys_pkey_mprotect(insns, pgsize, PROT_EXEC, pkey) != 0);
+ printf("execute at %p, pkey permissions are %s\n", fault_addr,
+ pkey_rights(rights));
+ asm volatile("mtctr %0; bctrl" : : "r"(insns));
+ FAIL_IF(remaining_faults != 0);
+ if (rights & PKEY_DISABLE_EXECUTE)
+ FAIL_IF(fault_code != SEGV_PKUERR);
+
+ /* Free the current pkey */
+ sys_pkey_free(pkey);
+
+ /* Find next valid combination of pkey rights */
+ rights = next_pkey_rights(rights);
+ } while (rights);
/* Cleanup */
munmap((void *) insns, pgsize);
- sys_pkey_free(pkey);
return 0;
}
--
2.25.1
^ permalink raw reply related
* [PATCH v2 5/6] selftests/powerpc: Add wrapper for gettid
From: Sandipan Das @ 2020-07-27 4:00 UTC (permalink / raw)
To: mpe; +Cc: fweimer, aneesh.kumar, linuxram, linuxppc-dev, bauerman
In-Reply-To: <cover.1595821792.git.sandipan@linux.ibm.com>
The gettid() syscall wrapper was first introduced in
glibc 2.30. This adds a wrapper for use in distros
running older versions.
Suggested-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Suggested-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Sandipan Das <sandipan@linux.ibm.com>
---
tools/testing/selftests/powerpc/include/utils.h | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/tools/testing/selftests/powerpc/include/utils.h b/tools/testing/selftests/powerpc/include/utils.h
index 69d16875802da..71d2924f5b8b3 100644
--- a/tools/testing/selftests/powerpc/include/utils.h
+++ b/tools/testing/selftests/powerpc/include/utils.h
@@ -42,6 +42,16 @@ int perf_event_enable(int fd);
int perf_event_disable(int fd);
int perf_event_reset(int fd);
+#if !defined(__GLIBC_PREREQ) || !__GLIBC_PREREQ(2, 30)
+#include <unistd.h>
+#include <sys/syscall.h>
+
+static inline pid_t gettid(void)
+{
+ return syscall(SYS_gettid);
+}
+#endif
+
static inline bool have_hwcap(unsigned long ftr)
{
return ((unsigned long)get_auxv_entry(AT_HWCAP) & ftr) == ftr;
--
2.25.1
^ permalink raw reply related
* [PATCH v2 2/6] selftests/powerpc: Add pkey helpers for rights
From: Sandipan Das @ 2020-07-27 4:00 UTC (permalink / raw)
To: mpe; +Cc: fweimer, aneesh.kumar, linuxram, linuxppc-dev, bauerman
In-Reply-To: <cover.1595821792.git.sandipan@linux.ibm.com>
This adds some new pkey-related helper to print
access rights of a pkey in the "rwx" format and
to generate different valid combinations of pkey
rights starting from a given combination.
Signed-off-by: Sandipan Das <sandipan@linux.ibm.com>
---
.../testing/selftests/powerpc/include/pkeys.h | 28 +++++++++++++++
.../selftests/powerpc/mm/pkey_exec_prot.c | 36 ++++++++++---------
2 files changed, 48 insertions(+), 16 deletions(-)
diff --git a/tools/testing/selftests/powerpc/include/pkeys.h b/tools/testing/selftests/powerpc/include/pkeys.h
index 9b53a97e664ea..6ba95039a0343 100644
--- a/tools/testing/selftests/powerpc/include/pkeys.h
+++ b/tools/testing/selftests/powerpc/include/pkeys.h
@@ -105,4 +105,32 @@ int siginfo_pkey(siginfo_t *si)
#endif
}
+#define pkey_rights(r) ({ \
+ static char buf[4] = "rwx"; \
+ unsigned int amr_bits; \
+ if ((r) & PKEY_DISABLE_EXECUTE) \
+ buf[2] = '-'; \
+ amr_bits = (r) & PKEY_BITS_MASK; \
+ if (amr_bits & PKEY_DISABLE_WRITE) \
+ buf[1] = '-'; \
+ if (amr_bits & PKEY_DISABLE_ACCESS & ~PKEY_DISABLE_WRITE) \
+ buf[0] = '-'; \
+ buf; \
+})
+
+unsigned long next_pkey_rights(unsigned long rights)
+{
+ if (rights == PKEY_DISABLE_ACCESS)
+ return PKEY_DISABLE_EXECUTE;
+ else if (rights == (PKEY_DISABLE_ACCESS | PKEY_DISABLE_EXECUTE))
+ return 0;
+
+ if ((rights & PKEY_BITS_MASK) == 0)
+ rights |= PKEY_DISABLE_WRITE;
+ else if ((rights & PKEY_BITS_MASK) == PKEY_DISABLE_WRITE)
+ rights |= PKEY_DISABLE_ACCESS;
+
+ return rights;
+}
+
#endif /* _SELFTESTS_POWERPC_PKEYS_H */
diff --git a/tools/testing/selftests/powerpc/mm/pkey_exec_prot.c b/tools/testing/selftests/powerpc/mm/pkey_exec_prot.c
index 1253ad6afba24..18ebfe6bae1c9 100644
--- a/tools/testing/selftests/powerpc/mm/pkey_exec_prot.c
+++ b/tools/testing/selftests/powerpc/mm/pkey_exec_prot.c
@@ -102,6 +102,7 @@ static void segv_handler(int signum, siginfo_t *sinfo, void *ctx)
static int test(void)
{
struct sigaction segv_act, trap_act;
+ unsigned long rights;
int pkey, ret, i;
ret = pkeys_unsupported();
@@ -150,7 +151,8 @@ static int test(void)
insns[numinsns - 1] = PPC_INST_BLR;
/* Allocate a pkey that restricts execution */
- pkey = sys_pkey_alloc(0, PKEY_DISABLE_EXECUTE);
+ rights = PKEY_DISABLE_EXECUTE;
+ pkey = sys_pkey_alloc(0, rights);
FAIL_IF(pkey < 0);
/*
@@ -175,8 +177,8 @@ static int test(void)
*/
remaining_faults = 0;
FAIL_IF(sys_pkey_mprotect(insns, pgsize, PROT_EXEC, pkey) != 0);
- printf("read from %p, pkey is execute-disabled, access-enabled\n",
- (void *) fault_addr);
+ printf("read from %p, pkey permissions are %s\n", fault_addr,
+ pkey_rights(rights));
i = *fault_addr;
FAIL_IF(remaining_faults != 0);
@@ -192,12 +194,13 @@ static int test(void)
*/
remaining_faults = 1;
FAIL_IF(sys_pkey_mprotect(insns, pgsize, PROT_EXEC, pkey) != 0);
- printf("write to %p, pkey is execute-disabled, access-enabled\n",
- (void *) fault_addr);
+ printf("write to %p, pkey permissions are %s\n", fault_addr,
+ pkey_rights(rights));
*fault_addr = PPC_INST_TRAP;
FAIL_IF(remaining_faults != 0 || fault_code != SEGV_ACCERR);
/* The following three cases will generate SEGV_PKUERR */
+ rights |= PKEY_DISABLE_ACCESS;
fault_type = PKEY_DISABLE_ACCESS;
fault_pkey = pkey;
@@ -211,9 +214,9 @@ static int test(void)
*/
remaining_faults = 1;
FAIL_IF(sys_pkey_mprotect(insns, pgsize, PROT_EXEC, pkey) != 0);
- printf("read from %p, pkey is execute-disabled, access-disabled\n",
- (void *) fault_addr);
- pkey_set_rights(pkey, PKEY_DISABLE_ACCESS);
+ pkey_set_rights(pkey, rights);
+ printf("read from %p, pkey permissions are %s\n", fault_addr,
+ pkey_rights(rights));
i = *fault_addr;
FAIL_IF(remaining_faults != 0 || fault_code != SEGV_PKUERR);
@@ -228,9 +231,9 @@ static int test(void)
*/
remaining_faults = 2;
FAIL_IF(sys_pkey_mprotect(insns, pgsize, PROT_EXEC, pkey) != 0);
- printf("write to %p, pkey is execute-disabled, access-disabled\n",
- (void *) fault_addr);
- pkey_set_rights(pkey, PKEY_DISABLE_ACCESS);
+ pkey_set_rights(pkey, rights);
+ printf("write to %p, pkey permissions are %s\n", fault_addr,
+ pkey_rights(rights));
*fault_addr = PPC_INST_NOP;
FAIL_IF(remaining_faults != 0 || fault_code != SEGV_ACCERR);
@@ -251,8 +254,8 @@ static int test(void)
remaining_faults = 1;
FAIL_IF(sys_pkey_mprotect(insns, pgsize, PROT_EXEC, pkey) != 0);
pkey_set_rights(pkey, PKEY_DISABLE_ACCESS);
- printf("execute at %p, pkey is execute-disabled, access-disabled\n",
- (void *) fault_addr);
+ printf("execute at %p, pkey permissions are %s\n", fault_addr,
+ pkey_rights(rights));
asm volatile("mtctr %0; bctrl" : : "r"(insns));
FAIL_IF(remaining_faults != 0 || fault_code != SEGV_PKUERR);
@@ -261,7 +264,8 @@ static int test(void)
* fully permissive.
*/
sys_pkey_free(pkey);
- pkey = sys_pkey_alloc(0, 0);
+ rights = 0;
+ pkey = sys_pkey_alloc(0, rights);
/*
* Jump to the executable region when AMR bits are not set
@@ -274,8 +278,8 @@ static int test(void)
fault_pkey = pkey;
remaining_faults = 0;
FAIL_IF(sys_pkey_mprotect(insns, pgsize, PROT_EXEC, pkey) != 0);
- printf("execute at %p, pkey is execute-enabled, access-enabled\n",
- (void *) fault_addr);
+ printf("execute at %p, pkey permissions are %s\n", fault_addr,
+ pkey_rights(rights));
asm volatile("mtctr %0; bctrl" : : "r"(insns));
FAIL_IF(remaining_faults != 0);
--
2.25.1
^ permalink raw reply related
* [PATCH v2 1/6] selftests/powerpc: Move pkey helpers to headers
From: Sandipan Das @ 2020-07-27 4:00 UTC (permalink / raw)
To: mpe; +Cc: fweimer, aneesh.kumar, linuxram, linuxppc-dev, bauerman
In-Reply-To: <cover.1595821792.git.sandipan@linux.ibm.com>
This moves all the pkey-related helpers to a new header
file and also a helper to print error messages in signal
handlers to the existing utils header file.
Signed-off-by: Sandipan Das <sandipan@linux.ibm.com>
---
.../testing/selftests/powerpc/include/pkeys.h | 108 ++++++++++++++++++
.../testing/selftests/powerpc/include/utils.h | 4 +
.../selftests/powerpc/mm/pkey_exec_prot.c | 100 +---------------
3 files changed, 114 insertions(+), 98 deletions(-)
create mode 100644 tools/testing/selftests/powerpc/include/pkeys.h
diff --git a/tools/testing/selftests/powerpc/include/pkeys.h b/tools/testing/selftests/powerpc/include/pkeys.h
new file mode 100644
index 0000000000000..9b53a97e664ea
--- /dev/null
+++ b/tools/testing/selftests/powerpc/include/pkeys.h
@@ -0,0 +1,108 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright 2020, Sandipan Das, IBM Corp.
+ */
+
+#ifndef _SELFTESTS_POWERPC_PKEYS_H
+#define _SELFTESTS_POWERPC_PKEYS_H
+
+#include <sys/mman.h>
+
+#include "reg.h"
+#include "utils.h"
+
+/*
+ * Older versions of libc use the Intel-specific access rights.
+ * Hence, override the definitions as they might be incorrect.
+ */
+#undef PKEY_DISABLE_ACCESS
+#define PKEY_DISABLE_ACCESS 0x3
+
+#undef PKEY_DISABLE_WRITE
+#define PKEY_DISABLE_WRITE 0x2
+
+#undef PKEY_DISABLE_EXECUTE
+#define PKEY_DISABLE_EXECUTE 0x4
+
+/* Older versions of libc do not not define this */
+#ifndef SEGV_PKUERR
+#define SEGV_PKUERR 4
+#endif
+
+#define SI_PKEY_OFFSET 0x20
+
+#define SYS_pkey_mprotect 386
+#define SYS_pkey_alloc 384
+#define SYS_pkey_free 385
+
+#define PKEY_BITS_PER_PKEY 2
+#define NR_PKEYS 32
+#define PKEY_BITS_MASK ((1UL << PKEY_BITS_PER_PKEY) - 1)
+
+inline unsigned long pkeyreg_get(void)
+{
+ return mfspr(SPRN_AMR);
+}
+
+inline void pkeyreg_set(unsigned long amr)
+{
+ set_amr(amr);
+}
+
+void pkey_set_rights(int pkey, unsigned long rights)
+{
+ unsigned long amr, shift;
+
+ shift = (NR_PKEYS - pkey - 1) * PKEY_BITS_PER_PKEY;
+ amr = pkeyreg_get();
+ amr &= ~(PKEY_BITS_MASK << shift);
+ amr |= (rights & PKEY_BITS_MASK) << shift;
+ pkeyreg_set(amr);
+}
+
+int sys_pkey_mprotect(void *addr, size_t len, int prot, int pkey)
+{
+ return syscall(SYS_pkey_mprotect, addr, len, prot, pkey);
+}
+
+int sys_pkey_alloc(unsigned long flags, unsigned long rights)
+{
+ return syscall(SYS_pkey_alloc, flags, rights);
+}
+
+int sys_pkey_free(int pkey)
+{
+ return syscall(SYS_pkey_free, pkey);
+}
+
+int pkeys_unsupported(void)
+{
+ bool hash_mmu = false;
+ int pkey;
+
+ /* Protection keys are currently supported on Hash MMU only */
+ FAIL_IF(using_hash_mmu(&hash_mmu));
+ SKIP_IF(!hash_mmu);
+
+ /* Check if the system call is supported */
+ pkey = sys_pkey_alloc(0, 0);
+ SKIP_IF(pkey < 0);
+ sys_pkey_free(pkey);
+
+ return 0;
+}
+
+int siginfo_pkey(siginfo_t *si)
+{
+ /*
+ * In older versions of libc, siginfo_t does not have si_pkey as
+ * a member.
+ */
+#ifdef si_pkey
+ return si->si_pkey;
+#else
+ return *((int *)(((char *) si) + SI_PKEY_OFFSET));
+#endif
+}
+
+#endif /* _SELFTESTS_POWERPC_PKEYS_H */
diff --git a/tools/testing/selftests/powerpc/include/utils.h b/tools/testing/selftests/powerpc/include/utils.h
index 9dbe607cc5ec3..7f259f36e23bc 100644
--- a/tools/testing/selftests/powerpc/include/utils.h
+++ b/tools/testing/selftests/powerpc/include/utils.h
@@ -97,6 +97,10 @@ do { \
#define _str(s) #s
#define str(s) _str(s)
+#define sigsafe_err(msg) ({ \
+ ssize_t nbytes __attribute__((unused)); \
+ nbytes = write(STDERR_FILENO, msg, strlen(msg)); })
+
/* POWER9 feature */
#ifndef PPC_FEATURE2_ARCH_3_00
#define PPC_FEATURE2_ARCH_3_00 0x00800000
diff --git a/tools/testing/selftests/powerpc/mm/pkey_exec_prot.c b/tools/testing/selftests/powerpc/mm/pkey_exec_prot.c
index 7c7c93425c5e9..1253ad6afba24 100644
--- a/tools/testing/selftests/powerpc/mm/pkey_exec_prot.c
+++ b/tools/testing/selftests/powerpc/mm/pkey_exec_prot.c
@@ -14,83 +14,13 @@
#include <signal.h>
#include <unistd.h>
-#include <sys/mman.h>
-#include "reg.h"
-#include "utils.h"
-
-/*
- * Older versions of libc use the Intel-specific access rights.
- * Hence, override the definitions as they might be incorrect.
- */
-#undef PKEY_DISABLE_ACCESS
-#define PKEY_DISABLE_ACCESS 0x3
-
-#undef PKEY_DISABLE_WRITE
-#define PKEY_DISABLE_WRITE 0x2
-
-#undef PKEY_DISABLE_EXECUTE
-#define PKEY_DISABLE_EXECUTE 0x4
-
-/* Older versions of libc do not not define this */
-#ifndef SEGV_PKUERR
-#define SEGV_PKUERR 4
-#endif
-
-#define SI_PKEY_OFFSET 0x20
-
-#define SYS_pkey_mprotect 386
-#define SYS_pkey_alloc 384
-#define SYS_pkey_free 385
-
-#define PKEY_BITS_PER_PKEY 2
-#define NR_PKEYS 32
-#define PKEY_BITS_MASK ((1UL << PKEY_BITS_PER_PKEY) - 1)
+#include "pkeys.h"
#define PPC_INST_NOP 0x60000000
#define PPC_INST_TRAP 0x7fe00008
#define PPC_INST_BLR 0x4e800020
-#define sigsafe_err(msg) ({ \
- ssize_t nbytes __attribute__((unused)); \
- nbytes = write(STDERR_FILENO, msg, strlen(msg)); })
-
-static inline unsigned long pkeyreg_get(void)
-{
- return mfspr(SPRN_AMR);
-}
-
-static inline void pkeyreg_set(unsigned long amr)
-{
- set_amr(amr);
-}
-
-static void pkey_set_rights(int pkey, unsigned long rights)
-{
- unsigned long amr, shift;
-
- shift = (NR_PKEYS - pkey - 1) * PKEY_BITS_PER_PKEY;
- amr = pkeyreg_get();
- amr &= ~(PKEY_BITS_MASK << shift);
- amr |= (rights & PKEY_BITS_MASK) << shift;
- pkeyreg_set(amr);
-}
-
-static int sys_pkey_mprotect(void *addr, size_t len, int prot, int pkey)
-{
- return syscall(SYS_pkey_mprotect, addr, len, prot, pkey);
-}
-
-static int sys_pkey_alloc(unsigned long flags, unsigned long rights)
-{
- return syscall(SYS_pkey_alloc, flags, rights);
-}
-
-static int sys_pkey_free(int pkey)
-{
- return syscall(SYS_pkey_free, pkey);
-}
-
static volatile sig_atomic_t fault_pkey, fault_code, fault_type;
static volatile sig_atomic_t remaining_faults;
static volatile unsigned int *fault_addr;
@@ -110,16 +40,7 @@ static void segv_handler(int signum, siginfo_t *sinfo, void *ctx)
{
int signal_pkey;
- /*
- * In older versions of libc, siginfo_t does not have si_pkey as
- * a member.
- */
-#ifdef si_pkey
- signal_pkey = sinfo->si_pkey;
-#else
- signal_pkey = *((int *)(((char *) sinfo) + SI_PKEY_OFFSET));
-#endif
-
+ signal_pkey = siginfo_pkey(sinfo);
fault_code = sinfo->si_code;
/* Check if this fault originated from the expected address */
@@ -178,23 +99,6 @@ static void segv_handler(int signum, siginfo_t *sinfo, void *ctx)
remaining_faults--;
}
-static int pkeys_unsupported(void)
-{
- bool hash_mmu = false;
- int pkey;
-
- /* Protection keys are currently supported on Hash MMU only */
- FAIL_IF(using_hash_mmu(&hash_mmu));
- SKIP_IF(!hash_mmu);
-
- /* Check if the system call is supported */
- pkey = sys_pkey_alloc(0, 0);
- SKIP_IF(pkey < 0);
- sys_pkey_free(pkey);
-
- return 0;
-}
-
static int test(void)
{
struct sigaction segv_act, trap_act;
--
2.25.1
^ permalink raw reply related
* [PATCH v2 0/6] Improvements to pkey tests
From: Sandipan Das @ 2020-07-27 4:00 UTC (permalink / raw)
To: mpe; +Cc: fweimer, aneesh.kumar, linuxram, linuxppc-dev, bauerman
Based on recent bugs found in the pkey infrastructure, this
improves the test for execute-disabled pkeys and adds a new
test for detecting inconsistencies with the pkey reported by
the signal information upon getting a fault.
Previous versions can be found at:
v1: https://lore.kernel.org/linuxppc-dev/cover.1594897099.git.sandipan@linux.ibm.com/
Changes in v2:
- Added a wrapper for the gettid syscall based on suggestions
from Michael and Christophe.
Sandipan Das (6):
selftests/powerpc: Move pkey helpers to headers
selftests/powerpc: Add pkey helpers for rights
selftests/powerpc: Harden test for execute-disabled pkeys
selftests/powerpc: Add helper to exit on failure
selftests/powerpc: Add wrapper for gettid
selftests/powerpc: Add test for pkey siginfo verification
.../testing/selftests/powerpc/include/pkeys.h | 136 +++++++
.../testing/selftests/powerpc/include/utils.h | 23 ++
tools/testing/selftests/powerpc/mm/.gitignore | 1 +
tools/testing/selftests/powerpc/mm/Makefile | 5 +-
.../selftests/powerpc/mm/pkey_exec_prot.c | 210 +++--------
.../selftests/powerpc/mm/pkey_siginfo.c | 332 ++++++++++++++++++
6 files changed, 554 insertions(+), 153 deletions(-)
create mode 100644 tools/testing/selftests/powerpc/include/pkeys.h
create mode 100644 tools/testing/selftests/powerpc/mm/pkey_siginfo.c
--
2.25.1
^ permalink raw reply
* Re: [PATCH v5 5/7] KVM: PPC: Book3S HV: migrate hot plugged memory
From: Bharata B Rao @ 2020-07-27 3:55 UTC (permalink / raw)
To: Ram Pai
Cc: ldufour, cclaudio, kvm-ppc, sathnaga, aneesh.kumar, sukadev,
linuxppc-dev, bauerman, david
In-Reply-To: <1595534844-16188-6-git-send-email-linuxram@us.ibm.com>
On Thu, Jul 23, 2020 at 01:07:22PM -0700, Ram Pai wrote:
> From: Laurent Dufour <ldufour@linux.ibm.com>
>
> When a memory slot is hot plugged to a SVM, PFNs associated with the
> GFNs in that slot must be migrated to the secure-PFNs, aka device-PFNs.
>
> Call kvmppc_uv_migrate_mem_slot() to accomplish this.
> Disable page-merge for all pages in the memory slot.
>
> Signed-off-by: Ram Pai <linuxram@us.ibm.com>
> [rearranged the code, and modified the commit log]
> Signed-off-by: Laurent Dufour <ldufour@linux.ibm.com>
> ---
> arch/powerpc/include/asm/kvm_book3s_uvmem.h | 14 ++++++++++++++
> arch/powerpc/kvm/book3s_hv.c | 10 ++--------
> arch/powerpc/kvm/book3s_hv_uvmem.c | 23 +++++++++++++++++++----
> 3 files changed, 35 insertions(+), 12 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/kvm_book3s_uvmem.h b/arch/powerpc/include/asm/kvm_book3s_uvmem.h
> index f229ab5..59c17ca 100644
> --- a/arch/powerpc/include/asm/kvm_book3s_uvmem.h
> +++ b/arch/powerpc/include/asm/kvm_book3s_uvmem.h
> @@ -25,6 +25,10 @@ void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free,
> struct kvm *kvm, bool skip_page_out);
> int kvmppc_uv_migrate_mem_slot(struct kvm *kvm,
> const struct kvm_memory_slot *memslot);
> +int kvmppc_uvmem_memslot_create(struct kvm *kvm,
> + const struct kvm_memory_slot *new);
> +void kvmppc_uvmem_memslot_delete(struct kvm *kvm,
> + const struct kvm_memory_slot *old);
> #else
> static inline int kvmppc_uvmem_init(void)
> {
> @@ -84,5 +88,15 @@ static inline int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn)
> static inline void
> kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free,
> struct kvm *kvm, bool skip_page_out) { }
> +
> +static inline int kvmppc_uvmem_memslot_create(struct kvm *kvm,
> + const struct kvm_memory_slot *new)
> +{
> + return H_UNSUPPORTED;
> +}
> +
> +static inline void kvmppc_uvmem_memslot_delete(struct kvm *kvm,
> + const struct kvm_memory_slot *old) { }
> +
> #endif /* CONFIG_PPC_UV */
> #endif /* __ASM_KVM_BOOK3S_UVMEM_H__ */
> diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
> index d331b46..b1485ca 100644
> --- a/arch/powerpc/kvm/book3s_hv.c
> +++ b/arch/powerpc/kvm/book3s_hv.c
> @@ -4515,16 +4515,10 @@ static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm,
>
> switch (change) {
> case KVM_MR_CREATE:
> - if (kvmppc_uvmem_slot_init(kvm, new))
> - return;
> - uv_register_mem_slot(kvm->arch.lpid,
> - new->base_gfn << PAGE_SHIFT,
> - new->npages * PAGE_SIZE,
> - 0, new->id);
> + kvmppc_uvmem_memslot_create(kvm, new);
Only concern is that kvmppc_uvmem_memslot_create() can fail due
to multiple reasons but we ignore them and go ahead with memory
hotplug.
May be this hasn't been observed in reality but if we can note this
as a TODO in the comments to dig further and explore the possibility
of recovering from here, then
Reviewed-by: Bharata B Rao <bharata@linux.ibm.com>
Regards,
Bharata.
^ permalink raw reply
* Re: [PATCH v5 6/7] KVM: PPC: Book3S HV: move kvmppc_svm_page_out up
From: Bharata B Rao @ 2020-07-27 3:49 UTC (permalink / raw)
To: Ram Pai
Cc: ldufour, cclaudio, kvm-ppc, sathnaga, aneesh.kumar, sukadev,
linuxppc-dev, bauerman, david
In-Reply-To: <1595534844-16188-7-git-send-email-linuxram@us.ibm.com>
On Thu, Jul 23, 2020 at 01:07:23PM -0700, Ram Pai wrote:
> From: Laurent Dufour <ldufour@linux.ibm.com>
>
> kvmppc_svm_page_out() will need to be called by kvmppc_uvmem_drop_pages()
> so move it upper in this file.
>
> Furthermore it will be interesting to call this function when already
> holding the kvm->arch.uvmem_lock, so prefix the original function with __
> and remove the locking in it, and introduce a wrapper which call that
> function with the lock held.
>
> There is no functional change.
>
> Cc: Ram Pai <linuxram@us.ibm.com>
> Cc: Bharata B Rao <bharata@linux.ibm.com>
> Cc: Paul Mackerras <paulus@ozlabs.org>
> Signed-off-by: Ram Pai <linuxram@us.ibm.com>
> Signed-off-by: Laurent Dufour <ldufour@linux.ibm.com>
Reviewed-by: Bharata B Rao <bharata@linux.ibm.com>
Regards,
Bharata.
^ permalink raw reply
* Re: [PATCH] KVM: PPC: Book3S HV: rework secure mem slot dropping
From: Bharata B Rao @ 2020-07-27 3:49 UTC (permalink / raw)
To: Laurent Dufour
Cc: aneesh.kumar, linuxram, cclaudio, kvm-ppc, sathnaga, sukadev,
linuxppc-dev, bauerman, david
In-Reply-To: <20200724083527.28027-1-ldufour@linux.ibm.com>
On Fri, Jul 24, 2020 at 10:35:27AM +0200, Laurent Dufour wrote:
> When a secure memslot is dropped, all the pages backed in the secure
> device (aka really backed by secure memory by the Ultravisor)
> should be paged out to a normal page. Previously, this was
> achieved by triggering the page fault mechanism which is calling
> kvmppc_svm_page_out() on each pages.
>
> This can't work when hot unplugging a memory slot because the memory
> slot is flagged as invalid and gfn_to_pfn() is then not trying to access
> the page, so the page fault mechanism is not triggered.
>
> Since the final goal is to make a call to kvmppc_svm_page_out() it seems
> simpler to call directly instead of triggering such a mechanism. This
> way kvmppc_uvmem_drop_pages() can be called even when hot unplugging a
> memslot.
>
> Since kvmppc_uvmem_drop_pages() is already holding kvm->arch.uvmem_lock,
> the call to __kvmppc_svm_page_out() is made. As
> __kvmppc_svm_page_out needs the vma pointer to migrate the pages,
> the VMA is fetched in a lazy way, to not trigger find_vma() all
> the time. In addition, the mmap_sem is held in read mode during
> that time, not in write mode since the virual memory layout is not
> impacted, and kvm->arch.uvmem_lock prevents concurrent operation
> on the secure device.
>
> Cc: Ram Pai <linuxram@us.ibm.com>
> Cc: Bharata B Rao <bharata@linux.ibm.com>
> Cc: Paul Mackerras <paulus@ozlabs.org>
> Signed-off-by: Ram Pai <linuxram@us.ibm.com>
> [modified the changelog description]
> Signed-off-by: Laurent Dufour <ldufour@linux.ibm.com>
> [modified check on the VMA in kvmppc_uvmem_drop_pages]
Reviewed-by: Bharata B Rao <bharata@linux.ibm.com>
Regards,
Bharata.
^ permalink raw reply
* Re: [PATCH 5/5] selftests/powerpc: Add test for pkey siginfo verification
From: Sandipan Das @ 2020-07-27 3:27 UTC (permalink / raw)
To: Michael Ellerman, Christophe Leroy
Cc: fweimer, aneesh.kumar, linuxram, linuxppc-dev, bauerman
In-Reply-To: <87zh7lg7g5.fsf@mpe.ellerman.id.au>
On 27/07/20 5:22 am, Michael Ellerman wrote:
> Christophe Leroy <christophe.leroy@csgroup.eu> writes:
>> Michael Ellerman <mpe@ellerman.id.au> a écrit :
>>> Sandipan Das <sandipan@linux.ibm.com> writes:
>>>> diff --git a/tools/testing/selftests/powerpc/mm/pkey_siginfo.c
>>>> b/tools/testing/selftests/powerpc/mm/pkey_siginfo.c
>>>> new file mode 100644
>>>> index 0000000000000..58605c53d495d
>>>> --- /dev/null
>>>> +++ b/tools/testing/selftests/powerpc/mm/pkey_siginfo.c
>>>> @@ -0,0 +1,332 @@
>>> ...
>>>> +
>>>> +static void *protect(void *p)
>>>> +{
>>>> + unsigned long rights;
>>>> + unsigned int *base;
>>>> + size_t size;
>>>> + int tid, i;
>>>> +
>>>> + tid = gettid();
>>>
>>> pkey_siginfo.c: In function 'protect':
>>> pkey_siginfo.c:103:8: error: implicit declaration of function
>>> 'gettid' [-Werror=implicit-function-declaration]
>>> tid = gettid();
>>> ^
>>>
>>>
>>> On Ubuntu 18.04 at least.
>>
>> See https://man7.org/linux/man-pages/man2/gettid.2.html
>>
>> Added in glibc 2.30
>
> Thanks, this seems to work:
>
> diff --git a/tools/testing/selftests/powerpc/include/utils.h b/tools/testing/selftests/powerpc/include/utils.h
> index 69d16875802d..71d2924f5b8b 100644
> --- a/tools/testing/selftests/powerpc/include/utils.h
> +++ b/tools/testing/selftests/powerpc/include/utils.h
> @@ -42,6 +42,16 @@ int perf_event_enable(int fd);
> int perf_event_disable(int fd);
> int perf_event_reset(int fd);
>
> +#if !defined(__GLIBC_PREREQ) || !__GLIBC_PREREQ(2, 30)
> +#include <unistd.h>
> +#include <sys/syscall.h>
> +
> +static inline pid_t gettid(void)
> +{
> + return syscall(SYS_gettid);
> +}
> +#endif
> +
> static inline bool have_hwcap(unsigned long ftr)
> {
> return ((unsigned long)get_auxv_entry(AT_HWCAP) & ftr) == ftr;
>
>
> cheers
>
Thanks for catching this. Will add these changes to v2.
- Sandipan
^ permalink raw reply
* linux-next: manual merge of the vfs tree with the powerpc tree
From: Stephen Rothwell @ 2020-07-27 1:32 UTC (permalink / raw)
To: Al Viro, Michael Ellerman
Cc: Aneesh Kumar K.V, Linux Next Mailing List, PowerPC,
Linux Kernel Mailing List
[-- Attachment #1: Type: text/plain, Size: 2065 bytes --]
Hi all,
Today's linux-next merge of the vfs tree got a conflict in:
arch/powerpc/kernel/ptrace/ptrace-view.c
between commit:
e0d8e991be64 ("powerpc/book3s64/kuap: Move UAMOR setup to key init function")
from the powerpc tree and commit:
5e39a71bddb3 ("powerpc: switch to ->regset_get()")
from the vfs tree.
I fixed it up (I thnk - see below) and can carry the fix as necessary.
This is now fixed as far as linux-next is concerned, but any non trivial
conflicts should be mentioned to your upstream maintainer when your tree
is submitted for merging. You may also want to consider cooperating
with the maintainer of the conflicting tree to minimise any particularly
complex conflicts.
--
Cheers,
Stephen Rothwell
diff --cc arch/powerpc/kernel/ptrace/ptrace-view.c
index ac7d480cb9c1,13208a9a02ca..000000000000
--- a/arch/powerpc/kernel/ptrace/ptrace-view.c
+++ b/arch/powerpc/kernel/ptrace/ptrace-view.c
@@@ -486,23 -468,15 +468,15 @@@ static int pkey_active(struct task_stru
}
static int pkey_get(struct task_struct *target, const struct user_regset *regset,
- unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf)
+ struct membuf to)
{
- int ret;
-
BUILD_BUG_ON(TSO(amr) + sizeof(unsigned long) != TSO(iamr));
- BUILD_BUG_ON(TSO(iamr) + sizeof(unsigned long) != TSO(uamor));
if (!arch_pkeys_enabled())
return -ENODEV;
- ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &target->thread.amr,
- 0, 2 * sizeof(unsigned long));
- if (ret)
- return ret;
-
- ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &default_uamor,
- 2 * sizeof(unsigned long), 3 * sizeof(unsigned long));
- return ret;
- return membuf_write(&to, &target->thread.amr, ELF_NPKEY * sizeof(unsigned long));
++ membuf_write(&to, &target->thread.amr, 2 * sizeof(unsigned long));
++ return membuf_write(&to, &default_uamor, sizeof(unsigned long));
}
static int pkey_set(struct task_struct *target, const struct user_regset *regset,
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox