--- /dev/null
+From ee11b93f95eabdf8198edd4668bf9102e7248270 Mon Sep 17 00:00:00 2001
+From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
+Date: Thu, 29 Oct 2020 17:31:45 -0400
+Subject: ftrace: Fix recursion check for NMI test
+
+From: Steven Rostedt (VMware) <rostedt@goodmis.org>
+
+commit ee11b93f95eabdf8198edd4668bf9102e7248270 upstream.
+
+The code that checks recursion will work to only do the recursion check once
+if there's nested checks. The top one will do the check, the other nested
+checks will see recursion was already checked and return zero for its "bit".
+On the return side, nothing will be done if the "bit" is zero.
+
+The problem is that zero is returned for the "good" bit when in NMI context.
+This will set the bit for NMIs making it look like *all* NMI tracing is
+recursing, and prevent tracing of anything in NMI context!
+
+The simple fix is to return "bit + 1" and subtract that bit on the end to
+get the real bit.
+
+Cc: stable@vger.kernel.org
+Fixes: edc15cafcbfa3 ("tracing: Avoid unnecessary multiple recursion checks")
+Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ kernel/trace/trace.h | 3 ++-
+ 1 file changed, 2 insertions(+), 1 deletion(-)
+
+--- a/kernel/trace/trace.h
++++ b/kernel/trace/trace.h
+@@ -587,7 +587,7 @@ static __always_inline int trace_test_an
+ current->trace_recursion = val;
+ barrier();
+
+- return bit;
++ return bit + 1;
+ }
+
+ static __always_inline void trace_clear_recursion(int bit)
+@@ -597,6 +597,7 @@ static __always_inline void trace_clear_
+ if (!bit)
+ return;
+
++ bit--;
+ bit = 1 << bit;
+ val &= ~bit;
+
--- /dev/null
+From 726b3d3f141fba6f841d715fc4d8a4a84f02c02a Mon Sep 17 00:00:00 2001
+From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
+Date: Thu, 29 Oct 2020 19:35:08 -0400
+Subject: ftrace: Handle tracing when switching between context
+
+From: Steven Rostedt (VMware) <rostedt@goodmis.org>
+
+commit 726b3d3f141fba6f841d715fc4d8a4a84f02c02a upstream.
+
+When an interrupt or NMI comes in and switches the context, there's a delay
+from when the preempt_count() shows the update. As the preempt_count() is
+used to detect recursion having each context have its own bit get set when
+tracing starts, and if that bit is already set, it is considered a recursion
+and the function exits. But if this happens in that section where context
+has changed but preempt_count() has not been updated, this will be
+incorrectly flagged as a recursion.
+
+To handle this case, create another bit call TRANSITION and test it if the
+current context bit is already set. Flag the call as a recursion if the
+TRANSITION bit is already set, and if not, set it and continue. The
+TRANSITION bit will be cleared normally on the return of the function that
+set it, or if the current context bit is clear, set it and clear the
+TRANSITION bit to allow for another transition between the current context
+and an even higher one.
+
+Cc: stable@vger.kernel.org
+Fixes: edc15cafcbfa3 ("tracing: Avoid unnecessary multiple recursion checks")
+Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ kernel/trace/trace.h | 23 +++++++++++++++++++++--
+ kernel/trace/trace_selftest.c | 9 +++++++--
+ 2 files changed, 28 insertions(+), 4 deletions(-)
+
+--- a/kernel/trace/trace.h
++++ b/kernel/trace/trace.h
+@@ -526,6 +526,12 @@ enum {
+
+ TRACE_GRAPH_DEPTH_START_BIT,
+ TRACE_GRAPH_DEPTH_END_BIT,
++
++ /*
++ * When transitioning between context, the preempt_count() may
++ * not be correct. Allow for a single recursion to cover this case.
++ */
++ TRACE_TRANSITION_BIT,
+ };
+
+ #define trace_recursion_set(bit) do { (current)->trace_recursion |= (1<<(bit)); } while (0)
+@@ -580,8 +586,21 @@ static __always_inline int trace_test_an
+ return 0;
+
+ bit = trace_get_context_bit() + start;
+- if (unlikely(val & (1 << bit)))
+- return -1;
++ if (unlikely(val & (1 << bit))) {
++ /*
++ * It could be that preempt_count has not been updated during
++ * a switch between contexts. Allow for a single recursion.
++ */
++ bit = TRACE_TRANSITION_BIT;
++ if (trace_recursion_test(bit))
++ return -1;
++ trace_recursion_set(bit);
++ barrier();
++ return bit + 1;
++ }
++
++ /* Normal check passed, clear the transition to allow it again */
++ trace_recursion_clear(TRACE_TRANSITION_BIT);
+
+ val |= 1 << bit;
+ current->trace_recursion = val;
+--- a/kernel/trace/trace_selftest.c
++++ b/kernel/trace/trace_selftest.c
+@@ -492,8 +492,13 @@ trace_selftest_function_recursion(void)
+ unregister_ftrace_function(&test_rec_probe);
+
+ ret = -1;
+- if (trace_selftest_recursion_cnt != 1) {
+- pr_cont("*callback not called once (%d)* ",
++ /*
++ * Recursion allows for transitions between context,
++ * and may call the callback twice.
++ */
++ if (trace_selftest_recursion_cnt != 1 &&
++ trace_selftest_recursion_cnt != 2) {
++ pr_cont("*callback not called once (or twice) (%d)* ",
+ trace_selftest_recursion_cnt);
+ goto out;
+ }
--- /dev/null
+From 9f5d1c336a10c0d24e83e40b4c1b9539f7dba627 Mon Sep 17 00:00:00 2001
+From: Mike Galbraith <efault@gmx.de>
+Date: Wed, 4 Nov 2020 16:12:44 +0100
+Subject: futex: Handle transient "ownerless" rtmutex state correctly
+
+From: Mike Galbraith <efault@gmx.de>
+
+commit 9f5d1c336a10c0d24e83e40b4c1b9539f7dba627 upstream.
+
+Gratian managed to trigger the BUG_ON(!newowner) in fixup_pi_state_owner().
+This is one possible chain of events leading to this:
+
+Task Prio Operation
+T1 120 lock(F)
+T2 120 lock(F) -> blocks (top waiter)
+T3 50 (RT) lock(F) -> boosts T1 and blocks (new top waiter)
+XX timeout/ -> wakes T2
+ signal
+T1 50 unlock(F) -> wakes T3 (rtmutex->owner == NULL, waiter bit is set)
+T2 120 cleanup -> try_to_take_mutex() fails because T3 is the top waiter
+ and the lower priority T2 cannot steal the lock.
+ -> fixup_pi_state_owner() sees newowner == NULL -> BUG_ON()
+
+The comment states that this is invalid and rt_mutex_real_owner() must
+return a non NULL owner when the trylock failed, but in case of a queued
+and woken up waiter rt_mutex_real_owner() == NULL is a valid transient
+state. The higher priority waiter has simply not yet managed to take over
+the rtmutex.
+
+The BUG_ON() is therefore wrong and this is just another retry condition in
+fixup_pi_state_owner().
+
+Drop the locks, so that T3 can make progress, and then try the fixup again.
+
+Gratian provided a great analysis, traces and a reproducer. The analysis is
+to the point, but it confused the hell out of that tglx dude who had to
+page in all the futex horrors again. Condensed version is above.
+
+[ tglx: Wrote comment and changelog ]
+
+Fixes: c1e2f0eaf015 ("futex: Avoid violating the 10th rule of futex")
+Reported-by: Gratian Crisan <gratian.crisan@ni.com>
+Signed-off-by: Mike Galbraith <efault@gmx.de>
+Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
+Cc: stable@vger.kernel.org
+Link: https://lore.kernel.org/r/87a6w6x7bb.fsf@ni.com
+Link: https://lore.kernel.org/r/87sg9pkvf7.fsf@nanos.tec.linutronix.de
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ kernel/futex.c | 16 ++++++++++++++--
+ 1 file changed, 14 insertions(+), 2 deletions(-)
+
+--- a/kernel/futex.c
++++ b/kernel/futex.c
+@@ -2512,10 +2512,22 @@ retry:
+ }
+
+ /*
+- * Since we just failed the trylock; there must be an owner.
++ * The trylock just failed, so either there is an owner or
++ * there is a higher priority waiter than this one.
+ */
+ newowner = rt_mutex_owner(&pi_state->pi_mutex);
+- BUG_ON(!newowner);
++ /*
++ * If the higher priority waiter has not yet taken over the
++ * rtmutex then newowner is NULL. We can't return here with
++ * that state because it's inconsistent vs. the user space
++ * state. So drop the locks and try again. It's a valid
++ * situation and not any different from the other retry
++ * conditions.
++ */
++ if (unlikely(!newowner)) {
++ err = -EAGAIN;
++ goto handle_err;
++ }
+ } else {
+ WARN_ON_ONCE(argowner != current);
+ if (oldowner == current) {
kthread_worker-prevent-queuing-delayed-work-from-timer_fn-when-it-is-being-canceled.patch
mm-always-have-io_remap_pfn_range-set-pgprot_decrypted.patch
gfs2-wake-up-when-sd_glock_disposal-becomes-zero.patch
+ftrace-fix-recursion-check-for-nmi-test.patch
+ftrace-handle-tracing-when-switching-between-context.patch
+tracing-fix-out-of-bounds-write-in-get_trace_buf.patch
+futex-handle-transient-ownerless-rtmutex-state-correctly.patch
--- /dev/null
+From c1acb4ac1a892cf08d27efcb964ad281728b0545 Mon Sep 17 00:00:00 2001
+From: Qiujun Huang <hqjagain@gmail.com>
+Date: Fri, 30 Oct 2020 00:19:05 +0800
+Subject: tracing: Fix out of bounds write in get_trace_buf
+
+From: Qiujun Huang <hqjagain@gmail.com>
+
+commit c1acb4ac1a892cf08d27efcb964ad281728b0545 upstream.
+
+The nesting count of trace_printk allows for 4 levels of nesting. The
+nesting counter starts at zero and is incremented before being used to
+retrieve the current context's buffer. But the index to the buffer uses the
+nesting counter after it was incremented, and not its original number,
+which in needs to do.
+
+Link: https://lkml.kernel.org/r/20201029161905.4269-1-hqjagain@gmail.com
+
+Cc: stable@vger.kernel.org
+Fixes: 3d9622c12c887 ("tracing: Add barrier to trace_printk() buffer nesting modification")
+Signed-off-by: Qiujun Huang <hqjagain@gmail.com>
+Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ kernel/trace/trace.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+--- a/kernel/trace/trace.c
++++ b/kernel/trace/trace.c
+@@ -2817,7 +2817,7 @@ static char *get_trace_buf(void)
+
+ /* Interrupts must see nesting incremented before we use the buffer */
+ barrier();
+- return &buffer->buffer[buffer->nesting][0];
++ return &buffer->buffer[buffer->nesting - 1][0];
+ }
+
+ static void put_trace_buf(void)
projects / thirdparty / kernel / stable-queue.git / commitdiff
