[PATCH AUTOSEL 6.6 02/13] rcu: Dump memory object info if callback function is invalid

[PATCH AUTOSEL 6.6 02/13] rcu: Dump memory object info if callback function is invalid

[Sasha Levin]

From: Zhen Lei <thunder.leizhen@huawei.com>

[ Upstream commit 2cbc482d325ee58001472c4359b311958c4efdd1 ]

When a structure containing an RCU callback rhp is (incorrectly) freed
and reallocated after rhp is passed to call_rcu(), it is not unusual for
rhp->func to be set to NULL. This defeats the debugging prints used by
__call_rcu_common() in kernels built with CONFIG_DEBUG_OBJECTS_RCU_HEAD=y,
which expect to identify the offending code using the identity of this
function.

And in kernels build without CONFIG_DEBUG_OBJECTS_RCU_HEAD=y, things
are even worse, as can be seen from this splat:

Unable to handle kernel NULL pointer dereference at virtual address 0
... ...
PC is at 0x0
LR is at rcu_do_batch+0x1c0/0x3b8
... ...
 (rcu_do_batch) from (rcu_core+0x1d4/0x284)
 (rcu_core) from (__do_softirq+0x24c/0x344)
 (__do_softirq) from (__irq_exit_rcu+0x64/0x108)
 (__irq_exit_rcu) from (irq_exit+0x8/0x10)
 (irq_exit) from (__handle_domain_irq+0x74/0x9c)
 (__handle_domain_irq) from (gic_handle_irq+0x8c/0x98)
 (gic_handle_irq) from (__irq_svc+0x5c/0x94)
 (__irq_svc) from (arch_cpu_idle+0x20/0x3c)
 (arch_cpu_idle) from (default_idle_call+0x4c/0x78)
 (default_idle_call) from (do_idle+0xf8/0x150)
 (do_idle) from (cpu_startup_entry+0x18/0x20)
 (cpu_startup_entry) from (0xc01530)

This commit therefore adds calls to mem_dump_obj(rhp) to output some
information, for example:

  slab kmalloc-256 start ffff410c45019900 pointer offset 0 size 256

This provides the rough size of the memory block and the offset of the
rcu_head structure, which as least provides at least a few clues to help
locate the problem. If the problem is reproducible, additional slab
debugging can be enabled, for example, CONFIG_DEBUG_SLAB=y, which can
provide significantly more information.

Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/rcu/rcu.h      | 7 +++++++
 kernel/rcu/srcutiny.c | 1 +
 kernel/rcu/srcutree.c | 1 +
 kernel/rcu/tasks.h    | 1 +
 kernel/rcu/tiny.c     | 1 +
 kernel/rcu/tree.c     | 1 +
 6 files changed, 12 insertions(+)

diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 98e13be411afd..d612731feea48 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -10,6 +10,7 @@
 #ifndef __LINUX_RCU_H
 #define __LINUX_RCU_H
 
+#include <linux/slab.h>
 #include <trace/events/rcu.h>
 
 /*
@@ -248,6 +249,12 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head)
 }
 #endif	/* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
 
+static inline void debug_rcu_head_callback(struct rcu_head *rhp)
+{
+	if (unlikely(!rhp->func))
+		kmem_dump_obj(rhp);
+}
+
 extern int rcu_cpu_stall_suppress_at_boot;
 
 static inline bool rcu_stall_is_suppressed_at_boot(void)
diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c
index 336af24e0fe35..c38e5933a5d69 100644
--- a/kernel/rcu/srcutiny.c
+++ b/kernel/rcu/srcutiny.c
@@ -138,6 +138,7 @@ void srcu_drive_gp(struct work_struct *wp)
 	while (lh) {
 		rhp = lh;
 		lh = lh->next;
+		debug_rcu_head_callback(rhp);
 		local_bh_disable();
 		rhp->func(rhp);
 		local_bh_enable();
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 20d7a238d675a..b3e9bc3b60f0b 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -1708,6 +1708,7 @@ static void srcu_invoke_callbacks(struct work_struct *work)
 	rhp = rcu_cblist_dequeue(&ready_cbs);
 	for (; rhp != NULL; rhp = rcu_cblist_dequeue(&ready_cbs)) {
 		debug_rcu_head_unqueue(rhp);
+		debug_rcu_head_callback(rhp);
 		local_bh_disable();
 		rhp->func(rhp);
 		local_bh_enable();
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index 8d65f7d576a34..7c845532a50ac 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -538,6 +538,7 @@ static void rcu_tasks_invoke_cbs(struct rcu_tasks *rtp, struct rcu_tasks_percpu
 	raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
 	len = rcl.len;
 	for (rhp = rcu_cblist_dequeue(&rcl); rhp; rhp = rcu_cblist_dequeue(&rcl)) {
+		debug_rcu_head_callback(rhp);
 		local_bh_disable();
 		rhp->func(rhp);
 		local_bh_enable();
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index 42f7589e51e09..fec804b790803 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -97,6 +97,7 @@ static inline bool rcu_reclaim_tiny(struct rcu_head *head)
 
 	trace_rcu_invoke_callback("", head);
 	f = head->func;
+	debug_rcu_head_callback(head);
 	WRITE_ONCE(head->func, (rcu_callback_t)0L);
 	f(head);
 	rcu_lock_release(&rcu_callback_map);
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index cb1caefa8bd07..29e4acbafefda 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2135,6 +2135,7 @@ static void rcu_do_batch(struct rcu_data *rdp)
 		trace_rcu_invoke_callback(rcu_state.name, rhp);
 
 		f = rhp->func;
+		debug_rcu_head_callback(rhp);
 		WRITE_ONCE(rhp->func, (rcu_callback_t)0L);
 		f(rhp);
 
-- 
2.42.0

[PATCH AUTOSEL 6.6 03/13] srcu: Fix srcu_struct node grpmask overflow on 64-bit systems

[Sasha Levin]

From: Denis Arefev <arefev@swemel.ru>

[ Upstream commit d8d5b7bf6f2105883bbd91bbd4d5b67e4e3dff71 ]

The value of a bitwise expression 1 << (cpu - sdp->mynode->grplo)
is subject to overflow due to a failure to cast operands to a larger
data type before performing the bitwise operation.

The maximum result of this subtraction is defined by the RCU_FANOUT_LEAF
Kconfig option, which on 64-bit systems defaults to 16 (resulting in a
maximum shift of 15), but which can be set up as high as 64 (resulting
in a maximum shift of 63).  A value of 31 can result in sign extension,
resulting in 0xffffffff80000000 instead of the desired 0x80000000.
A value of 32 or greater triggers undefined behavior per the C standard.

This bug has not been known to cause issues because almost all kernels
take the default CONFIG_RCU_FANOUT_LEAF=16.  Furthermore, as long as a
given compiler gives a deterministic non-zero result for 1<<N for N>=32,
the code correctly invokes all SRCU callbacks, albeit wasting CPU time
along the way.

This commit therefore substitutes the correct 1UL for the buggy 1.

Found by Linux Verification Center (linuxtesting.org) with SVACE.

Signed-off-by: Denis Arefev <arefev@swemel.ru>
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Cc: David Laight <David.Laight@aculab.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/rcu/srcutree.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index b3e9bc3b60f0b..a1fcb8566b2e3 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -223,7 +223,7 @@ static bool init_srcu_struct_nodes(struct srcu_struct *ssp, gfp_t gfp_flags)
 				snp->grplo = cpu;
 			snp->grphi = cpu;
 		}
-		sdp->grpmask = 1 << (cpu - sdp->mynode->grplo);
+		sdp->grpmask = 1UL << (cpu - sdp->mynode->grplo);
 	}
 	smp_store_release(&ssp->srcu_sup->srcu_size_state, SRCU_SIZE_WAIT_BARRIER);
 	return true;
@@ -833,7 +833,7 @@ static void srcu_schedule_cbs_snp(struct srcu_struct *ssp, struct srcu_node *snp
 	int cpu;
 
 	for (cpu = snp->grplo; cpu <= snp->grphi; cpu++) {
-		if (!(mask & (1 << (cpu - snp->grplo))))
+		if (!(mask & (1UL << (cpu - snp->grplo))))
 			continue;
 		srcu_schedule_cbs_sdp(per_cpu_ptr(ssp->sda, cpu), delay);
 	}
-- 
2.42.0

[PATCH AUTOSEL 6.6 09/13] srcu: Only accelerate on enqueue time

[Sasha Levin]

From: Frederic Weisbecker <frederic@kernel.org>

[ Upstream commit 8a77f38bcd28d3c22ab7dd8eff3f299d43c00411 ]

Acceleration in SRCU happens on enqueue time for each new callback. This
operation is expected not to fail and therefore any similar attempt
from other places shouldn't find any remaining callbacks to accelerate.

Moreover accelerations performed beyond enqueue time are error prone
because rcu_seq_snap() then may return the snapshot for a new grace
period that is not going to be started.

Remove these dangerous and needless accelerations and introduce instead
assertions reporting leaking unaccelerated callbacks beyond enqueue
time.

Co-developed-by: Yong He <alexyonghe@tencent.com>
Signed-off-by: Yong He <alexyonghe@tencent.com>
Co-developed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Co-developed-by: Neeraj upadhyay <Neeraj.Upadhyay@amd.com>
Signed-off-by: Neeraj upadhyay <Neeraj.Upadhyay@amd.com>
Reviewed-by: Like Xu <likexu@tencent.com>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/rcu/srcutree.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index a1fcb8566b2e3..dbb5116bb0200 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -782,8 +782,7 @@ static void srcu_gp_start(struct srcu_struct *ssp)
 	spin_lock_rcu_node(sdp);  /* Interrupts already disabled. */
 	rcu_segcblist_advance(&sdp->srcu_cblist,
 			      rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq));
-	(void)rcu_segcblist_accelerate(&sdp->srcu_cblist,
-				       rcu_seq_snap(&ssp->srcu_sup->srcu_gp_seq));
+	WARN_ON_ONCE(!rcu_segcblist_segempty(&sdp->srcu_cblist, RCU_NEXT_TAIL));
 	spin_unlock_rcu_node(sdp);  /* Interrupts remain disabled. */
 	WRITE_ONCE(ssp->srcu_sup->srcu_gp_start, jiffies);
 	WRITE_ONCE(ssp->srcu_sup->srcu_n_exp_nodelay, 0);
@@ -1692,6 +1691,7 @@ static void srcu_invoke_callbacks(struct work_struct *work)
 	ssp = sdp->ssp;
 	rcu_cblist_init(&ready_cbs);
 	spin_lock_irq_rcu_node(sdp);
+	WARN_ON_ONCE(!rcu_segcblist_segempty(&sdp->srcu_cblist, RCU_NEXT_TAIL));
 	rcu_segcblist_advance(&sdp->srcu_cblist,
 			      rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq));
 	if (sdp->srcu_cblist_invoking ||
@@ -1721,8 +1721,6 @@ static void srcu_invoke_callbacks(struct work_struct *work)
 	 */
 	spin_lock_irq_rcu_node(sdp);
 	rcu_segcblist_add_len(&sdp->srcu_cblist, -len);
-	(void)rcu_segcblist_accelerate(&sdp->srcu_cblist,
-				       rcu_seq_snap(&ssp->srcu_sup->srcu_gp_seq));
 	sdp->srcu_cblist_invoking = false;
 	more = rcu_segcblist_ready_cbs(&sdp->srcu_cblist);
 	spin_unlock_irq_rcu_node(sdp);
-- 
2.42.0