Merge branch 'errata/tx2-219' into for-next/fixes

Workaround for Cavium/Marvell ThunderX2 erratum #219.

* errata/tx2-219:
  arm64: Allow CAVIUM_TX2_ERRATUM_219 to be selected
  arm64: Avoid Cavium TX2 erratum 219 when switching TTBR
  arm64: Enable workaround for Cavium TX2 erratum 219 when running SMT
  arm64: KVM: Trap VM ops when ARM64_WORKAROUND_CAVIUM_TX2_219_TVM is set

7 files changed, 69 insertions, 138 deletions

diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c
index ca4e5d44b571..c00b9258fa6a 100644
--- a/kernel/dma/remap.c
+++ b/kernel/dma/remap.c
@@ -87,9 +87,9 @@ void *dma_common_contiguous_remap(struct page *page, size_t size,
  */
 void dma_common_free_remap(void *cpu_addr, size_t size)
 {
-	struct page **pages = dma_common_find_pages(cpu_addr);
+	struct vm_struct *area = find_vm_area(cpu_addr);
 
-	if (!pages) {
+	if (!area || area->flags != VM_DMA_COHERENT) {
 		WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr);
 		return;
 	}
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4655adbbae10..3f0cb82e4fbc 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -10586,55 +10586,26 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
 	u32 size;
 	int ret;
 
-	if (!access_ok(uattr, PERF_ATTR_SIZE_VER0))
-		return -EFAULT;
-
-	/*
-	 * zero the full structure, so that a short copy will be nice.
-	 */
+	/* Zero the full structure, so that a short copy will be nice. */
 	memset(attr, 0, sizeof(*attr));
 
 	ret = get_user(size, &uattr->size);
 	if (ret)
 		return ret;
 
-	if (size > PAGE_SIZE)	/* silly large */
-		goto err_size;
-
-	if (!size)		/* abi compat */
+	/* ABI compatibility quirk: */
+	if (!size)
 		size = PERF_ATTR_SIZE_VER0;
-
-	if (size < PERF_ATTR_SIZE_VER0)
+	if (size < PERF_ATTR_SIZE_VER0 || size > PAGE_SIZE)
 		goto err_size;
 
-	/*
-	 * If we're handed a bigger struct than we know of,
-	 * ensure all the unknown bits are 0 - i.e. new
-	 * user-space does not rely on any kernel feature
-	 * extensions we dont know about yet.
-	 */
-	if (size > sizeof(*attr)) {
-		unsigned char __user *addr;
-		unsigned char __user *end;
-		unsigned char val;
-
-		addr = (void __user *)uattr + sizeof(*attr);
-		end  = (void __user *)uattr + size;
-
-		for (; addr < end; addr++) {
-			ret = get_user(val, addr);
-			if (ret)
-				return ret;
-			if (val)
-				goto err_size;
-		}
-		size = sizeof(*attr);
+	ret = copy_struct_from_user(attr, sizeof(*attr), uattr, size);
+	if (ret) {
+		if (ret == -E2BIG)
+			goto err_size;
+		return ret;
 	}
 
-	ret = copy_from_user(attr, uattr, size);
-	if (ret)
-		return -EFAULT;
-
 	attr->size = size;
 
 	if (attr->__reserved_1)
diff --git a/kernel/fork.c b/kernel/fork.c
index f9572f416126..1f6c45f6a734 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2525,39 +2525,19 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
 #ifdef __ARCH_WANT_SYS_CLONE3
 noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs,
 					      struct clone_args __user *uargs,
-					      size_t size)
+					      size_t usize)
 {
+	int err;
 	struct clone_args args;
 
-	if (unlikely(size > PAGE_SIZE))
+	if (unlikely(usize > PAGE_SIZE))
 		return -E2BIG;
-
-	if (unlikely(size < sizeof(struct clone_args)))
+	if (unlikely(usize < CLONE_ARGS_SIZE_VER0))
 		return -EINVAL;
 
-	if (unlikely(!access_ok(uargs, size)))
-		return -EFAULT;
-
-	if (size > sizeof(struct clone_args)) {
-		unsigned char __user *addr;
-		unsigned char __user *end;
-		unsigned char val;
-
-		addr = (void __user *)uargs + sizeof(struct clone_args);
-		end = (void __user *)uargs + size;
-
-		for (; addr < end; addr++) {
-			if (get_user(val, addr))
-				return -EFAULT;
-			if (val)
-				return -E2BIG;
-		}
-
-		size = sizeof(struct clone_args);
-	}
-
-	if (copy_from_user(&args, uargs, size))
-		return -EFAULT;
+	err = copy_struct_from_user(&args, sizeof(args), uargs, usize);
+	if (err)
+		return err;
 
 	/*
 	 * Verify that higher 32bits of exit_signal are unset and that
@@ -2604,6 +2584,17 @@ static bool clone3_args_valid(const struct kernel_clone_args *kargs)
 	return true;
 }
 
+/**
+ * clone3 - create a new process with specific properties
+ * @uargs: argument structure
+ * @size:  size of @uargs
+ *
+ * clone3() is the extensible successor to clone()/clone2().
+ * It takes a struct as argument that is versioned by its size.
+ *
+ * Return: On success, a positive PID for the child process.
+ *         On error, a negative errno number.
+ */
 SYSCALL_DEFINE2(clone3, struct clone_args __user *, uargs, size_t, size)
 {
 	int err;
diff --git a/kernel/gen_kheaders.sh b/kernel/gen_kheaders.sh
index 9ff449888d9c..aff79e461fc9 100755
--- a/kernel/gen_kheaders.sh
+++ b/kernel/gen_kheaders.sh
@@ -71,7 +71,10 @@ done | cpio --quiet -pd $cpio_dir >/dev/null 2>&1
 find $cpio_dir -type f -print0 |
 	xargs -0 -P8 -n1 perl -pi -e 'BEGIN {undef $/;}; s/\/\*((?!SPDX).)*?\*\///smg;'
 
-tar -Jcf $tarfile -C $cpio_dir/ . > /dev/null
+# Create archive and try to normalize metadata for reproducibility
+tar "${KBUILD_BUILD_TIMESTAMP:+--mtime=$KBUILD_BUILD_TIMESTAMP}" \
+    --owner=0 --group=0 --sort=name --numeric-owner \
+    -Jcf $tarfile -C $cpio_dir/ . > /dev/null
 
 echo "$src_files_md5" >  kernel/kheaders.md5
 echo "$obj_files_md5" >> kernel/kheaders.md5
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 7880f4f64d0e..dd05a378631a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5106,9 +5106,6 @@ static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *a
 	u32 size;
 	int ret;
 
-	if (!access_ok(uattr, SCHED_ATTR_SIZE_VER0))
-		return -EFAULT;
-
 	/* Zero the full structure, so that a short copy will be nice: */
 	memset(attr, 0, sizeof(*attr));
 
@@ -5116,45 +5113,19 @@ static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *a
 	if (ret)
 		return ret;
 
-	/* Bail out on silly large: */
-	if (size > PAGE_SIZE)
-		goto err_size;
-
 	/* ABI compatibility quirk: */
 	if (!size)
 		size = SCHED_ATTR_SIZE_VER0;
-
-	if (size < SCHED_ATTR_SIZE_VER0)
+	if (size < SCHED_ATTR_SIZE_VER0 || size > PAGE_SIZE)
 		goto err_size;
 
-	/*
-	 * If we're handed a bigger struct than we know of,
-	 * ensure all the unknown bits are 0 - i.e. new
-	 * user-space does not rely on any kernel feature
-	 * extensions we dont know about yet.
-	 */
-	if (size > sizeof(*attr)) {
-		unsigned char __user *addr;
-		unsigned char __user *end;
-		unsigned char val;
-
-		addr = (void __user *)uattr + sizeof(*attr);
-		end  = (void __user *)uattr + size;
-
-		for (; addr < end; addr++) {
-			ret = get_user(val, addr);
-			if (ret)
-				return ret;
-			if (val)
-				goto err_size;
-		}
-		size = sizeof(*attr);
+	ret = copy_struct_from_user(attr, sizeof(*attr), uattr, size);
+	if (ret) {
+		if (ret == -E2BIG)
+			goto err_size;
+		return ret;
 	}
 
-	ret = copy_from_user(attr, uattr, size);
-	if (ret)
-		return -EFAULT;
-
 	if ((attr->sched_flags & SCHED_FLAG_UTIL_CLAMP) &&
 	    size < SCHED_ATTR_SIZE_VER1)
 		return -EINVAL;
@@ -5354,7 +5325,7 @@ sched_attr_copy_to_user(struct sched_attr __user *uattr,
  * sys_sched_getattr - similar to sched_getparam, but with sched_attr
  * @pid: the pid in question.
  * @uattr: structure containing the extended parameters.
- * @usize: sizeof(attr) that user-space knows about, for forwards and backwards compatibility.
+ * @usize: sizeof(attr) for fwd/bwd comp.
  * @flags: for future extension.
  */
 SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c
index a39bed2c784f..168479a7d61b 100644
--- a/kernel/sched/membarrier.c
+++ b/kernel/sched/membarrier.c
@@ -174,7 +174,6 @@ static int membarrier_private_expedited(int flags)
 		 */
 		if (cpu == raw_smp_processor_id())
 			continue;
-		rcu_read_lock();
 		p = rcu_dereference(cpu_rq(cpu)->curr);
 		if (p && p->mm == mm)
 			__cpumask_set_cpu(cpu, tmpmask);
diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c
index c1f5bb590b5e..b5a65e212df2 100644
--- a/kernel/time/tick-broadcast-hrtimer.c
+++ b/kernel/time/tick-broadcast-hrtimer.c
@@ -42,39 +42,39 @@ static int bc_shutdown(struct clock_event_device *evt)
  */
 static int bc_set_next(ktime_t expires, struct clock_event_device *bc)
 {
-	int bc_moved;
 	/*
-	 * We try to cancel the timer first. If the callback is on
-	 * flight on some other cpu then we let it handle it. If we
-	 * were able to cancel the timer nothing can rearm it as we
-	 * own broadcast_lock.
+	 * This is called either from enter/exit idle code or from the
+	 * broadcast handler. In all cases tick_broadcast_lock is held.
 	 *
-	 * However we can also be called from the event handler of
-	 * ce_broadcast_hrtimer itself when it expires. We cannot
-	 * restart the timer because we are in the callback, but we
-	 * can set the expiry time and let the callback return
-	 * HRTIMER_RESTART.
+	 * hrtimer_cancel() cannot be called here neither from the
+	 * broadcast handler nor from the enter/exit idle code. The idle
+	 * code can run into the problem described in bc_shutdown() and the
+	 * broadcast handler cannot wait for itself to complete for obvious
+	 * reasons.
 	 *
-	 * Since we are in the idle loop at this point and because
-	 * hrtimer_{start/cancel} functions call into tracing,
-	 * calls to these functions must be bound within RCU_NONIDLE.
+	 * Each caller tries to arm the hrtimer on its own CPU, but if the
+	 * hrtimer callbback function is currently running, then
+	 * hrtimer_start() cannot move it and the timer stays on the CPU on
+	 * which it is assigned at the moment.
+	 *
+	 * As this can be called from idle code, the hrtimer_start()
+	 * invocation has to be wrapped with RCU_NONIDLE() as
+	 * hrtimer_start() can call into tracing.
 	 */
-	RCU_NONIDLE(
-		{
-			bc_moved = hrtimer_try_to_cancel(&bctimer) >= 0;
-			if (bc_moved) {
-				hrtimer_start(&bctimer, expires,
-					      HRTIMER_MODE_ABS_PINNED_HARD);
-			}
-		}
-	);
-
-	if (bc_moved) {
-		/* Bind the "device" to the cpu */
-		bc->bound_on = smp_processor_id();
-	} else if (bc->bound_on == smp_processor_id()) {
-		hrtimer_set_expires(&bctimer, expires);
-	}
+	RCU_NONIDLE( {
+		hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED_HARD);
+		/*
+		 * The core tick broadcast mode expects bc->bound_on to be set
+		 * correctly to prevent a CPU which has the broadcast hrtimer
+		 * armed from going deep idle.
+		 *
+		 * As tick_broadcast_lock is held, nothing can change the cpu
+		 * base which was just established in hrtimer_start() above. So
+		 * the below access is safe even without holding the hrtimer
+		 * base lock.
+		 */
+		bc->bound_on = bctimer.base->cpu_base->cpu;
+	} );
 	return 0;
 }
 
@@ -100,10 +100,6 @@ static enum hrtimer_restart bc_handler(struct hrtimer *t)
 {
 	ce_broadcast_hrtimer.event_handler(&ce_broadcast_hrtimer);
 
-	if (clockevent_state_oneshot(&ce_broadcast_hrtimer))
-		if (ce_broadcast_hrtimer.next_event != KTIME_MAX)
-			return HRTIMER_RESTART;
-
 	return HRTIMER_NORESTART;
 }