[PATCH AUTOSEL 5.15 04/21] powerpc/hw_breakpoint: Avoid relying on caller synchronization

[PATCH AUTOSEL 5.15 04/21] powerpc/hw_breakpoint: Avoid relying on caller synchronization

[Sasha Levin]

From: Marco Elver <elver@google.com>

[ Upstream commit f95e5a3d59011eec1257d0e76de1e1f8969d426f ]

Internal data structures (cpu_bps, task_bps) of powerpc's hw_breakpoint
implementation have relied on nr_bp_mutex serializing access to them.

Before overhauling synchronization of kernel/events/hw_breakpoint.c,
introduce 2 spinlocks to synchronize cpu_bps and task_bps respectively,
thus avoiding reliance on callers synchronizing powerpc's hw_breakpoint.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Marco Elver <elver@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Dmitry Vyukov <dvyukov@google.com>
Acked-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20220829124719.675715-10-elver@google.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/kernel/hw_breakpoint.c | 53 ++++++++++++++++++++++-------
 1 file changed, 40 insertions(+), 13 deletions(-)

diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index 91a3be14808b..4d99c6523b6d 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -15,6 +15,7 @@
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
+#include <linux/spinlock.h>
 #include <linux/debugfs.h>
 #include <linux/init.h>
 
@@ -129,7 +130,14 @@ struct breakpoint {
 	bool ptrace_bp;
 };
 
+/*
+ * While kernel/events/hw_breakpoint.c does its own synchronization, we cannot
+ * rely on it safely synchronizing internals here; however, we can rely on it
+ * not requesting more breakpoints than available.
+ */
+static DEFINE_SPINLOCK(cpu_bps_lock);
 static DEFINE_PER_CPU(struct breakpoint *, cpu_bps[HBP_NUM_MAX]);
+static DEFINE_SPINLOCK(task_bps_lock);
 static LIST_HEAD(task_bps);
 
 static struct breakpoint *alloc_breakpoint(struct perf_event *bp)
@@ -174,7 +182,9 @@ static int task_bps_add(struct perf_event *bp)
 	if (IS_ERR(tmp))
 		return PTR_ERR(tmp);
 
+	spin_lock(&task_bps_lock);
 	list_add(&tmp->list, &task_bps);
+	spin_unlock(&task_bps_lock);
 	return 0;
 }
 
@@ -182,6 +192,7 @@ static void task_bps_remove(struct perf_event *bp)
 {
 	struct list_head *pos, *q;
 
+	spin_lock(&task_bps_lock);
 	list_for_each_safe(pos, q, &task_bps) {
 		struct breakpoint *tmp = list_entry(pos, struct breakpoint, list);
 
@@ -191,6 +202,7 @@ static void task_bps_remove(struct perf_event *bp)
 			break;
 		}
 	}
+	spin_unlock(&task_bps_lock);
 }
 
 /*
@@ -200,12 +212,17 @@ static void task_bps_remove(struct perf_event *bp)
 static bool all_task_bps_check(struct perf_event *bp)
 {
 	struct breakpoint *tmp;
+	bool ret = false;
 
+	spin_lock(&task_bps_lock);
 	list_for_each_entry(tmp, &task_bps, list) {
-		if (!can_co_exist(tmp, bp))
-			return true;
+		if (!can_co_exist(tmp, bp)) {
+			ret = true;
+			break;
+		}
 	}
-	return false;
+	spin_unlock(&task_bps_lock);
+	return ret;
 }
 
 /*
@@ -215,13 +232,18 @@ static bool all_task_bps_check(struct perf_event *bp)
 static bool same_task_bps_check(struct perf_event *bp)
 {
 	struct breakpoint *tmp;
+	bool ret = false;
 
+	spin_lock(&task_bps_lock);
 	list_for_each_entry(tmp, &task_bps, list) {
 		if (tmp->bp->hw.target == bp->hw.target &&
-		    !can_co_exist(tmp, bp))
-			return true;
+		    !can_co_exist(tmp, bp)) {
+			ret = true;
+			break;
+		}
 	}
-	return false;
+	spin_unlock(&task_bps_lock);
+	return ret;
 }
 
 static int cpu_bps_add(struct perf_event *bp)
@@ -234,6 +256,7 @@ static int cpu_bps_add(struct perf_event *bp)
 	if (IS_ERR(tmp))
 		return PTR_ERR(tmp);
 
+	spin_lock(&cpu_bps_lock);
 	cpu_bp = per_cpu_ptr(cpu_bps, bp->cpu);
 	for (i = 0; i < nr_wp_slots(); i++) {
 		if (!cpu_bp[i]) {
@@ -241,6 +264,7 @@ static int cpu_bps_add(struct perf_event *bp)
 			break;
 		}
 	}
+	spin_unlock(&cpu_bps_lock);
 	return 0;
 }
 
@@ -249,6 +273,7 @@ static void cpu_bps_remove(struct perf_event *bp)
 	struct breakpoint **cpu_bp;
 	int i = 0;
 
+	spin_lock(&cpu_bps_lock);
 	cpu_bp = per_cpu_ptr(cpu_bps, bp->cpu);
 	for (i = 0; i < nr_wp_slots(); i++) {
 		if (!cpu_bp[i])
@@ -260,19 +285,25 @@ static void cpu_bps_remove(struct perf_event *bp)
 			break;
 		}
 	}
+	spin_unlock(&cpu_bps_lock);
 }
 
 static bool cpu_bps_check(int cpu, struct perf_event *bp)
 {
 	struct breakpoint **cpu_bp;
+	bool ret = false;
 	int i;
 
+	spin_lock(&cpu_bps_lock);
 	cpu_bp = per_cpu_ptr(cpu_bps, cpu);
 	for (i = 0; i < nr_wp_slots(); i++) {
-		if (cpu_bp[i] && !can_co_exist(cpu_bp[i], bp))
-			return true;
+		if (cpu_bp[i] && !can_co_exist(cpu_bp[i], bp)) {
+			ret = true;
+			break;
+		}
 	}
-	return false;
+	spin_unlock(&cpu_bps_lock);
+	return ret;
 }
 
 static bool all_cpu_bps_check(struct perf_event *bp)
@@ -286,10 +317,6 @@ static bool all_cpu_bps_check(struct perf_event *bp)
 	return false;
 }
 
-/*
- * We don't use any locks to serialize accesses to cpu_bps or task_bps
- * because are already inside nr_bp_mutex.
- */
 int arch_reserve_bp_slot(struct perf_event *bp)
 {
 	int ret;
-- 
2.35.1

[PATCH AUTOSEL 5.15 10/21] powerpc/64: don't refer nr_cpu_ids in asm code when it's undefined

[Sasha Levin]

From: Yury Norov <yury.norov@gmail.com>

[ Upstream commit 546a073d628111e3338af689938407e77d5dc38f ]

generic_secondary_common_init() calls LOAD_REG_ADDR(r7, nr_cpu_ids)
conditionally on CONFIG_SMP. However, if 'NR_CPUS == 1', kernel doesn't
use the nr_cpu_ids, and in C code, it's just:
  #if NR_CPUS == 1
  #define nr_cpu_ids
  ...

This series makes declaration of nr_cpu_ids conditional on NR_CPUS == 1,
and that reveals the issue, because compiler can't link the
LOAD_REG_ADDR(r7, nr_cpu_ids) against nonexisting symbol.

Current code looks unsafe for those who build kernel with CONFIG_SMP=y and
NR_CPUS == 1. This is weird configuration, but not disallowed.

Fix the linker error by replacing LOAD_REG_ADDR() with LOAD_REG_IMMEDIATE()
conditionally on NR_CPUS == 1.

As the following patch adds CONFIG_FORCE_NR_CPUS option that has the
similar effect on nr_cpu_ids, make the generic_secondary_common_init()
conditional on it too.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Yury Norov <yury.norov@gmail.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/kernel/head_64.S | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index f17ae2083733..1cfb9be1ca9b 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -400,8 +400,12 @@ generic_secondary_common_init:
 #else
 	LOAD_REG_ADDR(r8, paca_ptrs)	/* Load paca_ptrs pointe	 */
 	ld	r8,0(r8)		/* Get base vaddr of array	 */
+#if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS)
+	LOAD_REG_IMMEDIATE(r7, NR_CPUS)
+#else
 	LOAD_REG_ADDR(r7, nr_cpu_ids)	/* Load nr_cpu_ids address       */
 	lwz	r7,0(r7)		/* also the max paca allocated 	 */
+#endif
 	li	r5,0			/* logical cpu id                */
 1:
 	sldi	r9,r5,3			/* get paca_ptrs[] index from cpu id */
-- 
2.35.1