diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 962451e54fdda..786d0e8d1d317 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -43,6 +43,7 @@ config ARM
 	select ARCH_SUPPORTS_CFI_CLANG
 	select ARCH_SUPPORTS_HUGETLBFS if ARM_LPAE
 	select ARCH_SUPPORTS_PER_VMA_LOCK
+	select ARCH_SUPPORTS_RT if HAVE_POSIX_CPU_TIMERS_TASK_WORK
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_USE_MEMTEST
@@ -82,7 +83,7 @@ config ARM
 	select HAS_IOPORT
 	select HAVE_ARCH_AUDITSYSCALL if AEABI && !OABI_COMPAT
 	select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
-	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU
+	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU && !PREEMPT_RT
 	select HAVE_ARCH_KFENCE if MMU && !XIP_KERNEL
 	select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU
 	select HAVE_ARCH_KASAN if MMU && !XIP_KERNEL
@@ -106,7 +107,7 @@ config ARM
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS if HAVE_DYNAMIC_FTRACE
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && MMU
 	select HAVE_EXIT_THREAD
-	select HAVE_GUP_FAST if ARM_LPAE
+	select HAVE_GUP_FAST if ARM_LPAE && !(PREEMPT_RT && HIGHPTE)
 	select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL
 	select HAVE_FUNCTION_ERROR_INJECTION
 	select HAVE_FUNCTION_GRAPH_TRACER
@@ -130,6 +131,7 @@ config ARM
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
+	select HAVE_POSIX_CPU_TIMERS_TASK_WORK if !KVM
 	select MMU_GATHER_RCU_TABLE_FREE if SMP && ARM_LPAE
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RSEQ
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index ab01b51de5590..cd030e2734e5d 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -474,6 +474,9 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
 	if (addr < TASK_SIZE)
 		return do_page_fault(addr, fsr, regs);
 
+	if (interrupts_enabled(regs))
+		local_irq_enable();
+
 	if (user_mode(regs))
 		goto bad_area;
 
@@ -544,6 +547,9 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
 static int
 do_sect_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 {
+	if (interrupts_enabled(regs))
+		local_irq_enable();
+
 	do_bad_area(addr, fsr, regs);
 	return 0;
 }
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index c3e0cc83f1205..ab52b5fa756ba 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -173,6 +173,7 @@ config PPC
 	select ARCH_STACKWALK
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_SUPPORTS_DEBUG_PAGEALLOC	if PPC_BOOK3S || PPC_8xx
+	select ARCH_SUPPORTS_RT			if HAVE_POSIX_CPU_TIMERS_TASK_WORK
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF		if PPC64
 	select ARCH_USE_MEMTEST
@@ -277,6 +278,7 @@ config PPC
 	select HAVE_PERF_EVENTS_NMI		if PPC64
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
+	select HAVE_POSIX_CPU_TIMERS_TASK_WORK	if !KVM
 	select HAVE_PREEMPT_DYNAMIC_KEY
 	select HAVE_RETHOOK			if KPROBES
 	select HAVE_REGS_AND_STACK_ACCESS_API
diff --git a/arch/powerpc/include/asm/stackprotector.h b/arch/powerpc/include/asm/stackprotector.h
index 283c346478565..4727f40052ddd 100644
--- a/arch/powerpc/include/asm/stackprotector.h
+++ b/arch/powerpc/include/asm/stackprotector.h
@@ -19,8 +19,13 @@
  */
 static __always_inline void boot_init_stack_canary(void)
 {
-	unsigned long canary = get_random_canary();
+	unsigned long canary;
 
+#ifndef CONFIG_PREEMPT_RT
+	canary = get_random_canary();
+#else
+	canary = ((unsigned long)&canary) & CANARY_MASK;
+#endif
 	current->stack_canary = canary;
 #ifdef CONFIG_PPC64
 	get_paca()->canary = canary;
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 2f2702c867f76..8e5a7bab208ab 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -234,6 +234,7 @@ config KVM_E500MC
 config KVM_MPIC
 	bool "KVM in-kernel MPIC emulation"
 	depends on KVM && PPC_E500
+	depends on !PREEMPT_RT
 	select HAVE_KVM_IRQCHIP
 	select HAVE_KVM_IRQ_ROUTING
 	select HAVE_KVM_MSI
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index fa3c2fff082a8..ea4f42cfe825e 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -2,6 +2,7 @@
 config PPC_PSERIES
 	depends on PPC64 && PPC_BOOK3S
 	bool "IBM pSeries & new (POWER5-based) iSeries"
+	select GENERIC_ALLOCATOR
 	select HAVE_PCSPKR_PLATFORM
 	select MPIC
 	select OF_DYNAMIC
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index eec333dd2e598..0b952ad638f9c 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -26,6 +26,7 @@
 #include <linux/of_address.h>
 #include <linux/iommu.h>
 #include <linux/rculist.h>
+#include <linux/local_lock.h>
 #include <asm/io.h>
 #include <asm/prom.h>
 #include <asm/rtas.h>
@@ -245,7 +246,13 @@ static int tce_build_pSeriesLP(unsigned long liobn, long tcenum, long tceshift,
 	return ret;
 }
 
-static DEFINE_PER_CPU(__be64 *, tce_page);
+struct tce_page {
+	__be64 * page;
+	local_lock_t lock;
+};
+static DEFINE_PER_CPU(struct tce_page, tce_page) = {
+	.lock = INIT_LOCAL_LOCK(lock),
+};
 
 static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 				     long npages, unsigned long uaddr,
@@ -268,9 +275,10 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 		                           direction, attrs);
 	}
 
-	local_irq_save(flags);	/* to protect tcep and the page behind it */
+	/* to protect tcep and the page behind it */
+	local_lock_irqsave(&tce_page.lock, flags);
 
-	tcep = __this_cpu_read(tce_page);
+	tcep = __this_cpu_read(tce_page.page);
 
 	/* This is safe to do since interrupts are off when we're called
 	 * from iommu_alloc{,_sg}()
@@ -279,12 +287,12 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 		tcep = (__be64 *)__get_free_page(GFP_ATOMIC);
 		/* If allocation fails, fall back to the loop implementation */
 		if (!tcep) {
-			local_irq_restore(flags);
+			local_unlock_irqrestore(&tce_page.lock, flags);
 			return tce_build_pSeriesLP(tbl->it_index, tcenum,
 					tceshift,
 					npages, uaddr, direction, attrs);
 		}
-		__this_cpu_write(tce_page, tcep);
+		__this_cpu_write(tce_page.page, tcep);
 	}
 
 	rpn = __pa(uaddr) >> tceshift;
@@ -314,7 +322,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 		tcenum += limit;
 	} while (npages > 0 && !rc);
 
-	local_irq_restore(flags);
+	local_unlock_irqrestore(&tce_page.lock, flags);
 
 	if (unlikely(rc == H_NOT_ENOUGH_RESOURCES)) {
 		ret = (int)rc;
@@ -498,16 +506,17 @@ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn,
 				DMA_BIDIRECTIONAL, 0);
 	}
 
-	local_irq_disable();	/* to protect tcep and the page behind it */
-	tcep = __this_cpu_read(tce_page);
+	/* to protect tcep and the page behind it */
+	local_lock_irq(&tce_page.lock);
+	tcep = __this_cpu_read(tce_page.page);
 
 	if (!tcep) {
 		tcep = (__be64 *)__get_free_page(GFP_ATOMIC);
 		if (!tcep) {
-			local_irq_enable();
+			local_unlock_irq(&tce_page.lock);
 			return -ENOMEM;
 		}
-		__this_cpu_write(tce_page, tcep);
+		__this_cpu_write(tce_page.page, tcep);
 	}
 
 	proto_tce = TCE_PCI_READ | TCE_PCI_WRITE;
@@ -550,7 +559,7 @@ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn,
 
 	/* error cleanup: caller will clear whole range */
 
-	local_irq_enable();
+	local_unlock_irq(&tce_page.lock);
 	return rc;
 }
 
diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index 5e939004b6463..40a9234e6e5dc 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -3,7 +3,6 @@ config DRM_I915
 	tristate "Intel 8xx/9xx/G3x/G4x/HD Graphics"
 	depends on DRM
 	depends on X86 && PCI
-	depends on !PREEMPT_RT
 	select INTEL_GTT if X86
 	select INTERVAL_TREE
 	# we need shmfs for the swappable backing store, and in particular
diff --git a/drivers/gpu/drm/i915/display/intel_crtc.c b/drivers/gpu/drm/i915/display/intel_crtc.c
index 29cfc38f12e04..5cfe6ecf1c115 100644
--- a/drivers/gpu/drm/i915/display/intel_crtc.c
+++ b/drivers/gpu/drm/i915/display/intel_crtc.c
@@ -559,7 +559,8 @@ void intel_pipe_update_start(struct intel_atomic_state *state,
 	 */
 	intel_psr_wait_for_idle_locked(new_crtc_state);
 
-	local_irq_disable();
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		local_irq_disable();
 
 	crtc->debug.min_vbl = evade.min;
 	crtc->debug.max_vbl = evade.max;
@@ -577,7 +578,8 @@ void intel_pipe_update_start(struct intel_atomic_state *state,
 	return;
 
 irq_disable:
-	local_irq_disable();
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		local_irq_disable();
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_DEBUG_VBLANK_EVADE)
@@ -723,7 +725,8 @@ void intel_pipe_update_end(struct intel_atomic_state *state,
 	if (!state->base.legacy_cursor_update)
 		intel_vrr_send_push(NULL, new_crtc_state);
 
-	local_irq_enable();
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		local_irq_enable();
 
 	if (intel_vgpu_active(dev_priv))
 		goto out;
diff --git a/drivers/gpu/drm/i915/display/intel_cursor.c b/drivers/gpu/drm/i915/display/intel_cursor.c
index 2fec5ba58373a..d3cfc20f866f5 100644
--- a/drivers/gpu/drm/i915/display/intel_cursor.c
+++ b/drivers/gpu/drm/i915/display/intel_cursor.c
@@ -930,13 +930,15 @@ intel_legacy_cursor_update(struct drm_plane *_plane,
 		 */
 		intel_psr_wait_for_idle_locked(crtc_state);
 
-		local_irq_disable();
+		if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+			local_irq_disable();
 
 		intel_vblank_evade(&evade);
 
 		drm_crtc_vblank_put(&crtc->base);
 	} else {
-		local_irq_disable();
+		if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+			local_irq_disable();
 	}
 
 	if (new_plane_state->uapi.visible) {
@@ -946,7 +948,8 @@ intel_legacy_cursor_update(struct drm_plane *_plane,
 		intel_plane_disable_arm(NULL, plane, crtc_state);
 	}
 
-	local_irq_enable();
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		local_irq_enable();
 
 	intel_psr_unlock(crtc_state);
 
diff --git a/drivers/gpu/drm/i915/display/intel_display_trace.h b/drivers/gpu/drm/i915/display/intel_display_trace.h
index 27ebc32cb61a5..a519d94700c36 100644
--- a/drivers/gpu/drm/i915/display/intel_display_trace.h
+++ b/drivers/gpu/drm/i915/display/intel_display_trace.h
@@ -13,6 +13,10 @@
 #if !defined(__INTEL_DISPLAY_TRACE_H__) || defined(TRACE_HEADER_MULTI_READ)
 #define __INTEL_DISPLAY_TRACE_H__
 
+#if defined(CONFIG_PREEMPT_RT) && !defined(NOTRACE)
+#define NOTRACE
+#endif
+
 #include <linux/string.h>
 #include <linux/string_helpers.h>
 #include <linux/types.h>
diff --git a/drivers/gpu/drm/i915/display/intel_vblank.c b/drivers/gpu/drm/i915/display/intel_vblank.c
index 139fa5deba805..0c29ca3bb5e32 100644
--- a/drivers/gpu/drm/i915/display/intel_vblank.c
+++ b/drivers/gpu/drm/i915/display/intel_vblank.c
@@ -312,6 +312,20 @@ static void intel_vblank_section_exit(struct intel_display *display)
 	struct drm_i915_private *i915 = to_i915(display->drm);
 	spin_unlock(&i915->uncore.lock);
 }
+
+static void intel_vblank_section_enter_irqf(struct intel_display *display, unsigned long *flags)
+	__acquires(i915->uncore.lock)
+{
+	struct drm_i915_private *i915 = to_i915(display->drm);
+	spin_lock_irqsave(&i915->uncore.lock, *flags);
+}
+
+static void intel_vblank_section_exit_irqf(struct intel_display *display, unsigned long flags)
+	__releases(i915->uncore.lock)
+{
+	struct drm_i915_private *i915 = to_i915(display->drm);
+	spin_unlock_irqrestore(&i915->uncore.lock, flags);
+}
 #else
 static void intel_vblank_section_enter(struct intel_display *display)
 {
@@ -320,6 +334,17 @@ static void intel_vblank_section_enter(struct intel_display *display)
 static void intel_vblank_section_exit(struct intel_display *display)
 {
 }
+
+static void intel_vblank_section_enter_irqf(struct intel_display *display, unsigned long *flags)
+{
+	*flags = 0;
+}
+
+static void intel_vblank_section_exit_irqf(struct intel_display *display, unsigned long flags)
+{
+	if (flags)
+		return;
+}
 #endif
 
 static bool i915_get_crtc_scanoutpos(struct drm_crtc *_crtc,
@@ -356,10 +381,10 @@ static bool i915_get_crtc_scanoutpos(struct drm_crtc *_crtc,
 	 * timing critical raw register reads, potentially with
 	 * preemption disabled, so the following code must not block.
 	 */
-	local_irq_save(irqflags);
-	intel_vblank_section_enter(display);
+	intel_vblank_section_enter_irqf(display, &irqflags);
 
-	/* preempt_disable_rt() should go right here in PREEMPT_RT patchset. */
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		preempt_disable();
 
 	/* Get optional system timestamp before query. */
 	if (stime)
@@ -423,10 +448,10 @@ static bool i915_get_crtc_scanoutpos(struct drm_crtc *_crtc,
 	if (etime)
 		*etime = ktime_get();
 
-	/* preempt_enable_rt() should go right here in PREEMPT_RT patchset. */
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		preempt_enable();
 
-	intel_vblank_section_exit(display);
-	local_irq_restore(irqflags);
+	intel_vblank_section_exit_irqf(display, irqflags);
 
 	/*
 	 * While in vblank, position will be negative
@@ -464,13 +489,11 @@ int intel_get_crtc_scanline(struct intel_crtc *crtc)
 	unsigned long irqflags;
 	int position;
 
-	local_irq_save(irqflags);
-	intel_vblank_section_enter(display);
+	intel_vblank_section_enter_irqf(display, &irqflags);
 
 	position = __intel_get_crtc_scanline(crtc);
 
-	intel_vblank_section_exit(display);
-	local_irq_restore(irqflags);
+	intel_vblank_section_exit_irqf(display, irqflags);
 
 	return position;
 }
@@ -730,11 +753,13 @@ int intel_vblank_evade(struct intel_vblank_evade_ctx *evade)
 			break;
 		}
 
-		local_irq_enable();
+		if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+			local_irq_enable();
 
 		timeout = schedule_timeout(timeout);
 
-		local_irq_disable();
+		if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+			local_irq_disable();
 	}
 
 	finish_wait(wq, &wait);
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index b721bbd233567..f5a6143ea8a24 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1609,7 +1609,7 @@ u64 intel_engine_get_last_batch_head(const struct intel_engine_cs *engine)
 
 static unsigned long stop_timeout(const struct intel_engine_cs *engine)
 {
-	if (in_atomic() || irqs_disabled()) /* inside atomic preempt-reset? */
+	if (in_atomic() || irqs_disabled() || rcu_preempt_depth()) /* inside atomic preempt-reset? */
 		return 0;
 
 	/*
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index 03baa7fa0a27c..799e943d9facb 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -1294,7 +1294,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	 * and context switches) submission.
 	 */
 
-	spin_lock(&sched_engine->lock);
+	spin_lock_irq(&sched_engine->lock);
 
 	/*
 	 * If the queue is higher priority than the last
@@ -1394,7 +1394,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				 * Even if ELSP[1] is occupied and not worthy
 				 * of timeslices, our queue might be.
 				 */
-				spin_unlock(&sched_engine->lock);
+				spin_unlock_irq(&sched_engine->lock);
 				return;
 			}
 		}
@@ -1420,7 +1420,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 
 		if (last && !can_merge_rq(last, rq)) {
 			spin_unlock(&ve->base.sched_engine->lock);
-			spin_unlock(&engine->sched_engine->lock);
+			spin_unlock_irq(&engine->sched_engine->lock);
 			return; /* leave this for another sibling */
 		}
 
@@ -1582,7 +1582,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	 */
 	sched_engine->queue_priority_hint = queue_prio(sched_engine);
 	i915_sched_engine_reset_on_empty(sched_engine);
-	spin_unlock(&sched_engine->lock);
+	spin_unlock_irq(&sched_engine->lock);
 
 	/*
 	 * We can skip poking the HW if we ended up with exactly the same set
@@ -1608,13 +1608,6 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	}
 }
 
-static void execlists_dequeue_irq(struct intel_engine_cs *engine)
-{
-	local_irq_disable(); /* Suspend interrupts across request submission */
-	execlists_dequeue(engine);
-	local_irq_enable(); /* flush irq_work (e.g. breadcrumb enabling) */
-}
-
 static void clear_ports(struct i915_request **ports, int count)
 {
 	memset_p((void **)ports, NULL, count);
@@ -2469,7 +2462,7 @@ static void execlists_submission_tasklet(struct tasklet_struct *t)
 	}
 
 	if (!engine->execlists.pending[0]) {
-		execlists_dequeue_irq(engine);
+		execlists_dequeue(engine);
 		start_timeslice(engine);
 	}
 
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
index 053780f562c1a..b25fa8f4dc4bd 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
@@ -362,7 +362,7 @@ static inline int intel_guc_send_busy_loop(struct intel_guc *guc,
 {
 	int err;
 	unsigned int sleep_period_ms = 1;
-	bool not_atomic = !in_atomic() && !irqs_disabled();
+	bool not_atomic = !in_atomic() && !irqs_disabled() && !rcu_preempt_depth();
 
 	/*
 	 * FIXME: Have caller pass in if we are in an atomic context to avoid
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index c3d27eadc0a7e..4705d6d6db141 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -608,7 +608,6 @@ bool __i915_request_submit(struct i915_request *request)
 
 	RQ_TRACE(request, "\n");
 
-	GEM_BUG_ON(!irqs_disabled());
 	lockdep_assert_held(&engine->sched_engine->lock);
 
 	/*
@@ -717,7 +716,6 @@ void __i915_request_unsubmit(struct i915_request *request)
 	 */
 	RQ_TRACE(request, "\n");
 
-	GEM_BUG_ON(!irqs_disabled());
 	lockdep_assert_held(&engine->sched_engine->lock);
 
 	/*
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index 7ed41ce9b7085..6b87ef6005c69 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -6,6 +6,10 @@
 #if !defined(_I915_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ)
 #define _I915_TRACE_H_
 
+#if defined(CONFIG_PREEMPT_RT) && !defined(NOTRACE)
+#define NOTRACE
+#endif
+
 #include <linux/stringify.h>
 #include <linux/types.h>
 #include <linux/tracepoint.h>
diff --git a/drivers/gpu/drm/i915/i915_utils.h b/drivers/gpu/drm/i915/i915_utils.h
index f7fb40cfdb705..9cb40c2c4b124 100644
--- a/drivers/gpu/drm/i915/i915_utils.h
+++ b/drivers/gpu/drm/i915/i915_utils.h
@@ -267,8 +267,13 @@ wait_remaining_ms_from_jiffies(unsigned long timestamp_jiffies, int to_wait_ms)
 						   (Wmax))
 #define wait_for(COND, MS)		_wait_for((COND), (MS) * 1000, 10, 1000)
 
-/* If CONFIG_PREEMPT_COUNT is disabled, in_atomic() always reports false. */
-#if IS_ENABLED(CONFIG_DRM_I915_DEBUG) && IS_ENABLED(CONFIG_PREEMPT_COUNT)
+/*
+ * If CONFIG_PREEMPT_COUNT is disabled, in_atomic() always reports false.
+ * On PREEMPT_RT the context isn't becoming atomic because it is used in an
+ * interrupt handler or because a spinlock_t is acquired. This leads to
+ * warnings which don't occur otherwise and therefore the check is disabled.
+ */
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG) && IS_ENABLED(CONFIG_PREEMPT_COUNT) && !defined(CONFIG_PREEMPT_RT)
 # define _WAIT_FOR_ATOMIC_CHECK(ATOMIC) WARN_ON_ONCE((ATOMIC) && !in_atomic())
 #else
 # define _WAIT_FOR_ATOMIC_CHECK(ATOMIC) do { } while (0)
diff --git a/drivers/gpu/drm/i915/intel_uncore_trace.h b/drivers/gpu/drm/i915/intel_uncore_trace.h
index f13ff71edf2db..3c67e267fb602 100644
--- a/drivers/gpu/drm/i915/intel_uncore_trace.h
+++ b/drivers/gpu/drm/i915/intel_uncore_trace.h
@@ -7,6 +7,10 @@
 #if !defined(__INTEL_UNCORE_TRACE_H__) || defined(TRACE_HEADER_MULTI_READ)
 #define __INTEL_UNCORE_TRACE_H__
 
+#if defined(CONFIG_PREEMPT_RT) && !defined(NOTRACE)
+#define NOTRACE
+#endif
+
 #include "i915_reg_defs.h"
 
 #include <linux/types.h>
diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c
index 7a6050f1c094b..d237f3e278b06 100644
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c
@@ -388,12 +388,34 @@ void __init serial8250_register_ports(struct uart_driver *drv, struct device *de
 
 #ifdef CONFIG_SERIAL_8250_CONSOLE
 
-static void univ8250_console_write(struct console *co, const char *s,
-				   unsigned int count)
+static void univ8250_console_write_atomic(struct console *co,
+					  struct nbcon_write_context *wctxt)
 {
 	struct uart_8250_port *up = &serial8250_ports[co->index];
 
-	serial8250_console_write(up, s, count);
+	serial8250_console_write(up, wctxt, true);
+}
+
+static void univ8250_console_write_thread(struct console *co,
+					  struct nbcon_write_context *wctxt)
+{
+	struct uart_8250_port *up = &serial8250_ports[co->index];
+
+	serial8250_console_write(up, wctxt, false);
+}
+
+static void univ8250_console_device_lock(struct console *co, unsigned long *flags)
+{
+	struct uart_port *up = &serial8250_ports[co->index].port;
+
+	__uart_port_lock_irqsave(up, flags);
+}
+
+static void univ8250_console_device_unlock(struct console *co, unsigned long flags)
+{
+	struct uart_port *up = &serial8250_ports[co->index].port;
+
+	__uart_port_unlock_irqrestore(up, flags);
 }
 
 static int univ8250_console_setup(struct console *co, char *options)
@@ -494,12 +516,15 @@ static int univ8250_console_match(struct console *co, char *name, int idx,
 
 static struct console univ8250_console = {
 	.name		= "ttyS",
-	.write		= univ8250_console_write,
+	.write_atomic	= univ8250_console_write_atomic,
+	.write_thread	= univ8250_console_write_thread,
+	.device_lock	= univ8250_console_device_lock,
+	.device_unlock	= univ8250_console_device_unlock,
 	.device		= uart_console_device,
 	.setup		= univ8250_console_setup,
 	.exit		= univ8250_console_exit,
 	.match		= univ8250_console_match,
-	.flags		= CON_PRINTBUFFER | CON_ANYTIME,
+	.flags		= CON_PRINTBUFFER | CON_ANYTIME | CON_NBCON,
 	.index		= -1,
 	.data		= &serial8250_reg,
 };
diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index 6d7b8c4667c9c..9537e44a4226f 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -705,7 +705,12 @@ static void serial8250_set_sleep(struct uart_8250_port *p, int sleep)
 	serial8250_rpm_put(p);
 }
 
-static void serial8250_clear_IER(struct uart_8250_port *up)
+/*
+ * Only to be used directly by the callback helper serial8250_console_write(),
+ * which may not require the port lock. Use serial8250_clear_IER() instead for
+ * all other cases.
+ */
+static void __serial8250_clear_IER(struct uart_8250_port *up)
 {
 	if (up->capabilities & UART_CAP_UUE)
 		serial_out(up, UART_IER, UART_IER_UUE);
@@ -713,6 +718,14 @@ static void serial8250_clear_IER(struct uart_8250_port *up)
 		serial_out(up, UART_IER, 0);
 }
 
+static inline void serial8250_clear_IER(struct uart_8250_port *up)
+{
+	/* Port locked to synchronize UART_IER access against the console */
+	lockdep_assert_held_once(&up->port.lock);
+
+	__serial8250_clear_IER(up);
+}
+
 #ifdef CONFIG_SERIAL_8250_RSA
 /*
  * Attempts to turn on the RSA FIFO.  Returns zero on failure.
@@ -1400,9 +1413,6 @@ void serial8250_em485_stop_tx(struct uart_8250_port *p, bool toggle_ier)
 {
 	unsigned char mcr = serial8250_in_MCR(p);
 
-	/* Port locked to synchronize UART_IER access against the console. */
-	lockdep_assert_held_once(&p->port.lock);
-
 	if (p->port.rs485.flags & SER_RS485_RTS_AFTER_SEND)
 		mcr |= UART_MCR_RTS;
 	else
@@ -1418,6 +1428,16 @@ void serial8250_em485_stop_tx(struct uart_8250_port *p, bool toggle_ier)
 		serial8250_clear_and_reinit_fifos(p);
 
 		if (toggle_ier) {
+			/*
+			 * Port locked to synchronize UART_IER access against
+			 * the console. The lockdep_assert must be restricted
+			 * to this condition because only here is it
+			 * guaranteed that the port lock is held. The other
+			 * hardware access in this function is synchronized
+			 * by console ownership.
+			 */
+			lockdep_assert_held_once(&p->port.lock);
+
 			p->ier |= UART_IER_RLSI | UART_IER_RDI;
 			serial_port_out(&p->port, UART_IER, p->ier);
 		}
@@ -3303,7 +3323,11 @@ EXPORT_SYMBOL_GPL(serial8250_set_defaults);
 
 static void serial8250_console_putchar(struct uart_port *port, unsigned char ch)
 {
+	struct uart_8250_port *up = up_to_u8250p(port);
+
 	serial_port_out(port, UART_TX, ch);
+
+	up->console_line_ended = (ch == '\n');
 }
 
 static void serial8250_console_wait_putchar(struct uart_port *port, unsigned char ch)
@@ -3340,11 +3364,22 @@ static void serial8250_console_restore(struct uart_8250_port *up)
 	serial8250_out_MCR(up, up->mcr | UART_MCR_DTR | UART_MCR_RTS);
 }
 
-static void fifo_wait_for_lsr(struct uart_8250_port *up, unsigned int count)
+static void fifo_wait_for_lsr(struct uart_8250_port *up,
+			      struct nbcon_write_context *wctxt,
+			      unsigned int count)
 {
 	unsigned int i;
 
 	for (i = 0; i < count; i++) {
+		/*
+		 * Pass the ownership as quickly as possible to a higher
+		 * priority context. Otherwise, its attempt to take over
+		 * the ownership might timeout. The new owner will wait
+		 * for UART_LSR_THRE before reusing the fifo.
+		 */
+		if (!nbcon_can_proceed(wctxt))
+			return;
+
 		if (wait_for_lsr(up, UART_LSR_THRE))
 			return;
 	}
@@ -3357,20 +3392,29 @@ static void fifo_wait_for_lsr(struct uart_8250_port *up, unsigned int count)
  * to get empty.
  */
 static void serial8250_console_fifo_write(struct uart_8250_port *up,
-					  const char *s, unsigned int count)
+					  struct nbcon_write_context *wctxt)
 {
-	const char *end = s + count;
 	unsigned int fifosize = up->tx_loadsz;
 	struct uart_port *port = &up->port;
+	const char *s = wctxt->outbuf;
+	const char *end = s + wctxt->len;
 	unsigned int tx_count = 0;
 	bool cr_sent = false;
 	unsigned int i;
 
 	while (s != end) {
 		/* Allow timeout for each byte of a possibly full FIFO */
-		fifo_wait_for_lsr(up, fifosize);
+		fifo_wait_for_lsr(up, wctxt, fifosize);
 
+		/*
+		 * Fill the FIFO. If a handover or takeover occurs, writing
+		 * must be aborted since wctxt->outbuf and wctxt->len are no
+		 * longer valid.
+		 */
 		for (i = 0; i < fifosize && s != end; ++i) {
+			if (!nbcon_enter_unsafe(wctxt))
+				return;
+
 			if (*s == '\n' && !cr_sent) {
 				serial8250_console_putchar(port, '\r');
 				cr_sent = true;
@@ -3378,6 +3422,8 @@ static void serial8250_console_fifo_write(struct uart_8250_port *up,
 				serial8250_console_putchar(port, *s++);
 				cr_sent = false;
 			}
+
+			nbcon_exit_unsafe(wctxt);
 		}
 		tx_count = i;
 	}
@@ -3386,39 +3432,57 @@ static void serial8250_console_fifo_write(struct uart_8250_port *up,
 	 * Allow timeout for each byte written since the caller will only wait
 	 * for UART_LSR_BOTH_EMPTY using the timeout of a single character
 	 */
-	fifo_wait_for_lsr(up, tx_count);
+	fifo_wait_for_lsr(up, wctxt, tx_count);
+}
+
+static void serial8250_console_byte_write(struct uart_8250_port *up,
+					  struct nbcon_write_context *wctxt)
+{
+	struct uart_port *port = &up->port;
+	const char *s = wctxt->outbuf;
+	const char *end = s + wctxt->len;
+
+	/*
+	 * Write out the message. If a handover or takeover occurs, writing
+	 * must be aborted since wctxt->outbuf and wctxt->len are no longer
+	 * valid.
+	 */
+	while (s != end) {
+		if (!nbcon_enter_unsafe(wctxt))
+			return;
+
+		uart_console_write(port, s++, 1, serial8250_console_wait_putchar);
+
+		nbcon_exit_unsafe(wctxt);
+	}
 }
 
 /*
- *	Print a string to the serial port trying not to disturb
- *	any possible real use of the port...
+ * Print a string to the serial port trying not to disturb
+ * any possible real use of the port...
  *
- *	The console_lock must be held when we get here.
- *
- *	Doing runtime PM is really a bad idea for the kernel console.
- *	Thus, we assume the function is called when device is powered up.
+ * Doing runtime PM is really a bad idea for the kernel console.
+ * Thus, assume it is called when device is powered up.
  */
-void serial8250_console_write(struct uart_8250_port *up, const char *s,
-			      unsigned int count)
+void serial8250_console_write(struct uart_8250_port *up,
+			      struct nbcon_write_context *wctxt,
+			      bool is_atomic)
 {
 	struct uart_8250_em485 *em485 = up->em485;
 	struct uart_port *port = &up->port;
-	unsigned long flags;
-	unsigned int ier, use_fifo;
-	int locked = 1;
+	unsigned int ier;
+	bool use_fifo;
 
-	touch_nmi_watchdog();
-
-	if (oops_in_progress)
-		locked = uart_port_trylock_irqsave(port, &flags);
-	else
-		uart_port_lock_irqsave(port, &flags);
+	if (!nbcon_enter_unsafe(wctxt))
+		return;
 
 	/*
-	 *	First save the IER then disable the interrupts
+	 * First, save the IER, then disable the interrupts. The special
+	 * variant to clear the IER is used because console printing may
+	 * occur without holding the port lock.
 	 */
 	ier = serial_port_in(port, UART_IER);
-	serial8250_clear_IER(up);
+	__serial8250_clear_IER(up);
 
 	/* check scratch reg to see if port powered off during system sleep */
 	if (up->canary && (up->canary != serial_port_in(port, UART_SCR))) {
@@ -3432,6 +3496,18 @@ void serial8250_console_write(struct uart_8250_port *up, const char *s,
 		mdelay(port->rs485.delay_rts_before_send);
 	}
 
+	/* If ownership was lost, no writing is allowed */
+	if (!nbcon_can_proceed(wctxt))
+		goto skip_write;
+
+	/*
+	 * If console printer did not fully output the previous line, it must
+	 * have been handed or taken over. Insert a newline in order to
+	 * maintain clean output.
+	 */
+	if (!up->console_line_ended)
+		uart_console_write(port, "\n", 1, serial8250_console_wait_putchar);
+
 	use_fifo = (up->capabilities & UART_CAP_FIFO) &&
 		/*
 		 * BCM283x requires to check the fifo
@@ -3452,10 +3528,23 @@ void serial8250_console_write(struct uart_8250_port *up, const char *s,
 		 */
 		!(up->port.flags & UPF_CONS_FLOW);
 
+	nbcon_exit_unsafe(wctxt);
+
 	if (likely(use_fifo))
-		serial8250_console_fifo_write(up, s, count);
+		serial8250_console_fifo_write(up, wctxt);
 	else
-		uart_console_write(port, s, count, serial8250_console_wait_putchar);
+		serial8250_console_byte_write(up, wctxt);
+skip_write:
+	/*
+	 * If ownership was lost, this context must reacquire ownership and
+	 * re-enter the unsafe section in order to perform final actions
+	 * (such as re-enabling interrupts).
+	 */
+	if (!nbcon_can_proceed(wctxt)) {
+		do {
+			nbcon_reacquire_nobuf(wctxt);
+		} while (!nbcon_enter_unsafe(wctxt));
+	}
 
 	/*
 	 *	Finally, wait for transmitter to become empty
@@ -3478,11 +3567,18 @@ void serial8250_console_write(struct uart_8250_port *up, const char *s,
 	 *	call it if we have saved something in the saved flags
 	 *	while processing with interrupts off.
 	 */
-	if (up->msr_saved_flags)
-		serial8250_modem_status(up);
+	if (up->msr_saved_flags) {
+		/*
+		 * For atomic, it must be deferred to irq_work because this
+		 * may be a context that does not permit waking up tasks.
+		 */
+		if (is_atomic)
+			irq_work_queue(&up->modem_status_work);
+		else
+			serial8250_modem_status(up);
+	}
 
-	if (locked)
-		uart_port_unlock_irqrestore(port, flags);
+	nbcon_exit_unsafe(wctxt);
 }
 
 static unsigned int probe_baud(struct uart_port *port)
@@ -3500,8 +3596,24 @@ static unsigned int probe_baud(struct uart_port *port)
 	return (port->uartclk / 16) / quot;
 }
 
+/*
+ * irq_work handler to perform modem control. Only triggered via
+ * ->write_atomic() callback because it may be in a scheduler or
+ * NMI context, unable to wake tasks.
+ */
+static void modem_status_handler(struct irq_work *iwp)
+{
+	struct uart_8250_port *up = container_of(iwp, struct uart_8250_port, modem_status_work);
+	struct uart_port *port = &up->port;
+
+	uart_port_lock(port);
+	serial8250_modem_status(up);
+	uart_port_unlock(port);
+}
+
 int serial8250_console_setup(struct uart_port *port, char *options, bool probe)
 {
+	struct uart_8250_port *up = up_to_u8250p(port);
 	int baud = 9600;
 	int bits = 8;
 	int parity = 'n';
@@ -3511,6 +3623,9 @@ int serial8250_console_setup(struct uart_port *port, char *options, bool probe)
 	if (!port->iobase && !port->membase)
 		return -ENODEV;
 
+	up->console_line_ended = true;
+	init_irq_work(&up->modem_status_work, modem_status_handler);
+
 	if (options)
 		uart_parse_options(options, &baud, &parity, &bits, &flow);
 	else if (probe)
diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h
index 144de7a7948de..57875c37023af 100644
--- a/include/linux/serial_8250.h
+++ b/include/linux/serial_8250.h
@@ -150,8 +150,17 @@ struct uart_8250_port {
 #define LSR_SAVE_FLAGS UART_LSR_BRK_ERROR_BITS
 	u16			lsr_saved_flags;
 	u16			lsr_save_mask;
+
+	/*
+	 * Track when a console line has been fully written to the
+	 * hardware, i.e. true when the most recent byte written to
+	 * UART_TX by the console was '\n'.
+	 */
+	bool			console_line_ended;
+
 #define MSR_SAVE_FLAGS UART_MSR_ANY_DELTA
 	unsigned char		msr_saved_flags;
+	struct irq_work		modem_status_work;
 
 	struct uart_8250_dma	*dma;
 	const struct uart_8250_ops *ops;
@@ -202,8 +211,8 @@ void serial8250_tx_chars(struct uart_8250_port *up);
 unsigned int serial8250_modem_status(struct uart_8250_port *up);
 void serial8250_init_port(struct uart_8250_port *up);
 void serial8250_set_defaults(struct uart_8250_port *up);
-void serial8250_console_write(struct uart_8250_port *up, const char *s,
-			      unsigned int count);
+void serial8250_console_write(struct uart_8250_port *up,
+			      struct nbcon_write_context *wctxt, bool in_atomic);
 int serial8250_console_setup(struct uart_port *port, char *options, bool probe);
 int serial8250_console_exit(struct uart_port *port);
 
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index eefb67d9883c2..20ac8a5ac27d7 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -188,6 +188,15 @@ KERNEL_ATTR_RO(crash_elfcorehdr_size);
 
 #endif /* CONFIG_VMCORE_INFO */
 
+#if defined(CONFIG_PREEMPT_RT)
+static ssize_t realtime_show(struct kobject *kobj,
+			     struct kobj_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%d\n", 1);
+}
+KERNEL_ATTR_RO(realtime);
+#endif
+
 /* whether file capabilities are enabled */
 static ssize_t fscaps_show(struct kobject *kobj,
 				  struct kobj_attribute *attr, char *buf)
@@ -271,6 +280,9 @@ static struct attribute * kernel_attrs[] = {
 #ifndef CONFIG_TINY_RCU
 	&rcu_expedited_attr.attr,
 	&rcu_normal_attr.attr,
+#endif
+#ifdef CONFIG_PREEMPT_RT
+	&realtime_attr.attr,
 #endif
 	NULL
 };
diff --git a/localversion-rt b/localversion-rt
new file mode 100644
index 0000000000000..1445cd65885cd
--- /dev/null
+++ b/localversion-rt
@@ -0,0 +1 @@
+-rt3