Merge tag 'powerpc-5.17-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:

 - Optimise radix KVM guest entry/exit by 2x on Power9/Power10.

 - Allow firmware to tell us whether to disable the entry and uaccess
   flushes on Power10 or later CPUs.

 - Add BPF_PROBE_MEM support for 32 and 64-bit BPF jits.

 - Several fixes and improvements to our hard lockup watchdog.

 - Activate HAVE_DYNAMIC_FTRACE_WITH_REGS on 32-bit.

 - Allow building the 64-bit Book3S kernel without hash MMU support, ie.
   Radix only.

 - Add KUAP (SMAP) support for 40x, 44x, 8xx, Book3E (64-bit).

 - Add new encodings for perf_mem_data_src.mem_hops field, and use them
   on Power10.

 - A series of small performance improvements to 64-bit interrupt entry.

 - Several commits fixing issues when building with the clang integrated
   assembler.

 - Many other small features and fixes.

Thanks to Alan Modra, Alexey Kardashevskiy, Ammar Faizi, Anders Roxell,
Arnd Bergmann, Athira Rajeev, Cédric Le Goater, Christophe JAILLET,
Christophe Leroy, Christoph Hellwig, Daniel Axtens, David Yang, Erhard
Furtner, Fabiano Rosas, Greg Kroah-Hartman, Guo Ren, Hari Bathini, Jason
Wang, Joel Stanley, Julia Lawall, Kajol Jain, Kees Cook, Laurent Dufour,
Madhavan Srinivasan, Mark Brown, Minghao Chi, Nageswara R Sastry, Naresh
Kamboju, Nathan Chancellor, Nathan Lynch, Nicholas Piggin, Nick Child,
Oliver O'Halloran, Peiwei Hu, Randy Dunlap, Ravi Bangoria, Rob Herring,
Russell Currey, Sachin Sant, Sean Christopherson, Segher Boessenkool,
Thadeu Lima de Souza Cascardo, Tyrel Datwyler, Xiang wangx, and Yang
Guang.

* tag 'powerpc-5.17-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (240 commits)
  powerpc/xmon: Dump XIVE information for online-only processors.
  powerpc/opal: use default_groups in kobj_type
  powerpc/cacheinfo: use default_groups in kobj_type
  powerpc/sched: Remove unused TASK_SIZE_OF
  powerpc/xive: Add missing null check after calling kmalloc
  powerpc/floppy: Remove usage of the deprecated "pci-dma-compat.h" API
  selftests/powerpc: Add a test of sigreturning to an unaligned address
  powerpc/64s: Use EMIT_WARN_ENTRY for SRR debug warnings
  powerpc/64s: Mask NIP before checking against SRR0
  powerpc/perf: Fix spelling of "its"
  powerpc/32: Fix boot failure with GCC latent entropy plugin
  powerpc/code-patching: Replace patch_instruction() by ppc_inst_write() in selftests
  powerpc/code-patching: Move code patching selftests in its own file
  powerpc/code-patching: Move instr_is_branch_{i/b}form() in code-patching.h
  powerpc/code-patching: Move patch_exception() outside code-patching.c
  powerpc/code-patching: Use test_trampoline for prefixed patch test
  powerpc/code-patching: Fix patch_branch() return on out-of-range failure
  powerpc/code-patching: Reorganise do_patch_instruction() to ease error handling
  powerpc/code-patching: Fix unmap_patch_area() error handling
  powerpc/code-patching: Fix error handling in do_patch_instruction()
  ...

1 files changed, 62 insertions, 25 deletions

diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index cae8f03a44fe..62361cc7281c 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -88,6 +88,7 @@ static struct clocksource clocksource_timebase = {
 
 #define DECREMENTER_DEFAULT_MAX 0x7FFFFFFF
 u64 decrementer_max = DECREMENTER_DEFAULT_MAX;
+EXPORT_SYMBOL_GPL(decrementer_max); /* for KVM HDEC */
 
 static int decrementer_set_next_event(unsigned long evt,
 				      struct clock_event_device *dev);
@@ -107,6 +108,7 @@ struct clock_event_device decrementer_clockevent = {
 EXPORT_SYMBOL(decrementer_clockevent);
 
 DEFINE_PER_CPU(u64, decrementers_next_tb);
+EXPORT_SYMBOL_GPL(decrementers_next_tb);
 static DEFINE_PER_CPU(struct clock_event_device, decrementers);
 
 #define XSEC_PER_SEC (1024*1024)
@@ -496,6 +498,16 @@ EXPORT_SYMBOL(profile_pc);
  * 64-bit uses a byte in the PACA, 32-bit uses a per-cpu variable...
  */
 #ifdef CONFIG_PPC64
+static inline unsigned long test_irq_work_pending(void)
+{
+	unsigned long x;
+
+	asm volatile("lbz %0,%1(13)"
+		: "=r" (x)
+		: "i" (offsetof(struct paca_struct, irq_work_pending)));
+	return x;
+}
+
 static inline void set_irq_work_pending_flag(void)
 {
 	asm volatile("stb %0,%1(13)" : :
@@ -539,13 +551,44 @@ void arch_irq_work_raise(void)
 	preempt_enable();
 }
 
+static void set_dec_or_work(u64 val)
+{
+	set_dec(val);
+	/* We may have raced with new irq work */
+	if (unlikely(test_irq_work_pending()))
+		set_dec(1);
+}
+
 #else  /* CONFIG_IRQ_WORK */
 
 #define test_irq_work_pending()	0
 #define clear_irq_work_pending()
 
+static void set_dec_or_work(u64 val)
+{
+	set_dec(val);
+}
 #endif /* CONFIG_IRQ_WORK */
 
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+void timer_rearm_host_dec(u64 now)
+{
+	u64 *next_tb = this_cpu_ptr(&decrementers_next_tb);
+
+	WARN_ON_ONCE(!arch_irqs_disabled());
+	WARN_ON_ONCE(mfmsr() & MSR_EE);
+
+	if (now >= *next_tb) {
+		local_paca->irq_happened |= PACA_IRQ_DEC;
+	} else {
+		now = *next_tb - now;
+		if (now <= decrementer_max)
+			set_dec_or_work(now);
+	}
+}
+EXPORT_SYMBOL_GPL(timer_rearm_host_dec);
+#endif
+
 /*
  * timer_interrupt - gets called when the decrementer overflows,
  * with interrupts disabled.
@@ -566,22 +609,23 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt)
 		return;
 	}
 
-	/* Ensure a positive value is written to the decrementer, or else
-	 * some CPUs will continue to take decrementer exceptions. When the
-	 * PPC_WATCHDOG (decrementer based) is configured, keep this at most
-	 * 31 bits, which is about 4 seconds on most systems, which gives
-	 * the watchdog a chance of catching timer interrupt hard lockups.
-	 */
-	if (IS_ENABLED(CONFIG_PPC_WATCHDOG))
-		set_dec(0x7fffffff);
-	else
-		set_dec(decrementer_max);
-
-	/* Conditionally hard-enable interrupts now that the DEC has been
-	 * bumped to its maximum value
-	 */
-	may_hard_irq_enable();
+	/* Conditionally hard-enable interrupts. */
+	if (should_hard_irq_enable()) {
+		/*
+		 * Ensure a positive value is written to the decrementer, or
+		 * else some CPUs will continue to take decrementer exceptions.
+		 * When the PPC_WATCHDOG (decrementer based) is configured,
+		 * keep this at most 31 bits, which is about 4 seconds on most
+		 * systems, which gives the watchdog a chance of catching timer
+		 * interrupt hard lockups.
+		 */
+		if (IS_ENABLED(CONFIG_PPC_WATCHDOG))
+			set_dec(0x7fffffff);
+		else
+			set_dec(decrementer_max);
 
+		do_hard_irq_enable();
+	}
 
 #if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC)
 	if (atomic_read(&ppc_n_lost_interrupts) != 0)
@@ -606,10 +650,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt)
 	} else {
 		now = *next_tb - now;
 		if (now <= decrementer_max)
-			set_dec(now);
-		/* We may have raced with new irq work */
-		if (test_irq_work_pending())
-			set_dec(1);
+			set_dec_or_work(now);
 		__this_cpu_inc(irq_stat.timer_irqs_others);
 	}
 
@@ -730,7 +771,7 @@ static int __init get_freq(char *name, int cells, unsigned long *val)
 
 static void start_cpu_decrementer(void)
 {
-#if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
+#ifdef CONFIG_BOOKE_OR_40x
 	unsigned int tcr;
 
 	/* Clear any pending timer interrupts */
@@ -843,11 +884,7 @@ static int decrementer_set_next_event(unsigned long evt,
 				      struct clock_event_device *dev)
 {
 	__this_cpu_write(decrementers_next_tb, get_tb() + evt);
-	set_dec(evt);
-
-	/* We may have raced with new irq work */
-	if (test_irq_work_pending())
-		set_dec(1);
+	set_dec_or_work(evt);
 
 	return 0;
 }