Merge tag 'powerpc-5.1-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Notable changes:

   - Enable THREAD_INFO_IN_TASK to move thread_info off the stack.

   - A big series from Christoph reworking our DMA code to use more of
     the generic infrastructure, as he said:
       "This series switches the powerpc port to use the generic swiotlb
        and noncoherent dma ops, and to use more generic code for the
        coherent direct mapping, as well as removing a lot of dead
        code."

   - Increase our vmalloc space to 512T with the Hash MMU on modern
     CPUs, allowing us to support machines with larger amounts of total
     RAM or distance between nodes.

   - Two series from Christophe, one to optimise TLB miss handlers on
     6xx, and another to optimise the way STRICT_KERNEL_RWX is
     implemented on some 32-bit CPUs.

   - Support for KCOV coverage instrumentation which means we can run
     syzkaller and discover even more bugs in our code.

  And as always many clean-ups, reworks and minor fixes etc.

  Thanks to: Alan Modra, Alexey Kardashevskiy, Alistair Popple, Andrea
  Arcangeli, Andrew Donnellan, Aneesh Kumar K.V, Aravinda Prasad, Balbir
  Singh, Brajeswar Ghosh, Breno Leitao, Christian Lamparter, Christian
  Zigotzky, Christophe Leroy, Christoph Hellwig, Corentin Labbe, Daniel
  Axtens, David Gibson, Diana Craciun, Firoz Khan, Gustavo A. R. Silva,
  Igor Stoppa, Joe Lawrence, Joel Stanley, Jonathan Neuschäfer, Jordan
  Niethe, Laurent Dufour, Madhavan Srinivasan, Mahesh Salgaonkar, Mark
  Cave-Ayland, Masahiro Yamada, Mathieu Malaterre, Matteo Croce, Meelis
  Roos, Michael W. Bringmann, Nathan Chancellor, Nathan Fontenot,
  Nicholas Piggin, Nick Desaulniers, Nicolai Stange, Oliver O'Halloran,
  Paul Mackerras, Peter Xu, PrasannaKumar Muralidharan, Qian Cai,
  Rashmica Gupta, Reza Arbab, Robert P. J. Day, Russell Currey,
  Sabyasachi Gupta, Sam Bobroff, Sandipan Das, Sergey Senozhatsky,
  Souptick Joarder, Stewart Smith, Tyrel Datwyler, Vaibhav Jain,
  YueHaibing"

* tag 'powerpc-5.1-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (200 commits)
  powerpc/32: Clear on-stack exception marker upon exception return
  powerpc: Remove export of save_stack_trace_tsk_reliable()
  powerpc/mm: fix "section_base" set but not used
  powerpc/mm: Fix "sz" set but not used warning
  powerpc/mm: Check secondary hash page table
  powerpc: remove nargs from __SYSCALL
  powerpc/64s: Fix unrelocated interrupt trampoline address test
  powerpc/powernv/ioda: Fix locked_vm counting for memory used by IOMMU tables
  powerpc/fsl: Fix the flush of branch predictor.
  powerpc/powernv: Make opal log only readable by root
  powerpc/xmon: Fix opcode being uninitialized in print_insn_powerpc
  powerpc/powernv: move OPAL call wrapper tracing and interrupt handling to C
  powerpc/64s: Fix data interrupts vs d-side MCE reentrancy
  powerpc/64s: Prepare to handle data interrupts vs d-side MCE reentrancy
  powerpc/64s: system reset interrupt preserve HSRRs
  powerpc/64s: Fix HV NMI vs HV interrupt recoverability test
  powerpc/mm/hash: Handle mmap_min_addr correctly in get_unmapped_area topdown search
  powerpc/hugetlb: Handle mmap_min_addr correctly in get_unmapped_area callback
  selftests/powerpc: Remove duplicate header
  powerpc sstep: Add support for modsd, modud instructions
  ...

1 files changed, 38 insertions, 71 deletions

diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 3f15edf25a0d..e784342bdaa1 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -20,6 +20,7 @@
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/task_stack.h>
 #include <linux/sched/topology.h>
 #include <linux/smp.h>
 #include <linux/interrupt.h>
@@ -75,7 +76,7 @@
 static DEFINE_PER_CPU(int, cpu_state) = { 0 };
 #endif
 
-struct thread_info *secondary_ti;
+struct task_struct *secondary_current;
 bool has_big_cores;
 
 DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map);
@@ -358,13 +359,12 @@ void arch_send_call_function_ipi_mask(const struct cpumask *mask)
  * NMI IPIs may not be recoverable, so should not be used as ongoing part of
  * a running system. They can be used for crash, debug, halt/reboot, etc.
  *
- * NMI IPIs are globally single threaded. No more than one in progress at
- * any time.
- *
  * The IPI call waits with interrupts disabled until all targets enter the
- * NMI handler, then the call returns.
+ * NMI handler, then returns. Subsequent IPIs can be issued before targets
+ * have returned from their handlers, so there is no guarantee about
+ * concurrency or re-entrancy.
  *
- * No new NMI can be initiated until targets exit the handler.
+ * A new NMI can be issued before all targets exit the handler.
  *
  * The IPI call may time out without all targets entering the NMI handler.
  * In that case, there is some logic to recover (and ignore subsequent
@@ -375,7 +375,7 @@ void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 
 static atomic_t __nmi_ipi_lock = ATOMIC_INIT(0);
 static struct cpumask nmi_ipi_pending_mask;
-static int nmi_ipi_busy_count = 0;
+static bool nmi_ipi_busy = false;
 static void (*nmi_ipi_function)(struct pt_regs *) = NULL;
 
 static void nmi_ipi_lock_start(unsigned long *flags)
@@ -414,7 +414,7 @@ static void nmi_ipi_unlock_end(unsigned long *flags)
  */
 int smp_handle_nmi_ipi(struct pt_regs *regs)
 {
-	void (*fn)(struct pt_regs *);
+	void (*fn)(struct pt_regs *) = NULL;
 	unsigned long flags;
 	int me = raw_smp_processor_id();
 	int ret = 0;
@@ -425,29 +425,17 @@ int smp_handle_nmi_ipi(struct pt_regs *regs)
 	 * because the caller may have timed out.
 	 */
 	nmi_ipi_lock_start(&flags);
-	if (!nmi_ipi_busy_count)
-		goto out;
-	if (!cpumask_test_cpu(me, &nmi_ipi_pending_mask))
-		goto out;
-
-	fn = nmi_ipi_function;
-	if (!fn)
-		goto out;
-
-	cpumask_clear_cpu(me, &nmi_ipi_pending_mask);
-	nmi_ipi_busy_count++;
-	nmi_ipi_unlock();
-
-	ret = 1;
-
-	fn(regs);
-
-	nmi_ipi_lock();
-	if (nmi_ipi_busy_count > 1) /* Can race with caller time-out */
-		nmi_ipi_busy_count--;
-out:
+	if (cpumask_test_cpu(me, &nmi_ipi_pending_mask)) {
+		cpumask_clear_cpu(me, &nmi_ipi_pending_mask);
+		fn = READ_ONCE(nmi_ipi_function);
+		WARN_ON_ONCE(!fn);
+		ret = 1;
+	}
 	nmi_ipi_unlock_end(&flags);
 
+	if (fn)
+		fn(regs);
+
 	return ret;
 }
 
@@ -473,9 +461,10 @@ static void do_smp_send_nmi_ipi(int cpu, bool safe)
  * - cpu is the target CPU (must not be this CPU), or NMI_IPI_ALL_OTHERS.
  * - fn is the target callback function.
  * - delay_us > 0 is the delay before giving up waiting for targets to
- *   complete executing the handler, == 0 specifies indefinite delay.
+ *   begin executing the handler, == 0 specifies indefinite delay.
  */
-int __smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us, bool safe)
+static int __smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *),
+				u64 delay_us, bool safe)
 {
 	unsigned long flags;
 	int me = raw_smp_processor_id();
@@ -487,31 +476,33 @@ int __smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us, bool
 	if (unlikely(!smp_ops))
 		return 0;
 
-	/* Take the nmi_ipi_busy count/lock with interrupts hard disabled */
 	nmi_ipi_lock_start(&flags);
-	while (nmi_ipi_busy_count) {
+	while (nmi_ipi_busy) {
 		nmi_ipi_unlock_end(&flags);
-		spin_until_cond(nmi_ipi_busy_count == 0);
+		spin_until_cond(!nmi_ipi_busy);
 		nmi_ipi_lock_start(&flags);
 	}
-
+	nmi_ipi_busy = true;
 	nmi_ipi_function = fn;
 
+	WARN_ON_ONCE(!cpumask_empty(&nmi_ipi_pending_mask));
+
 	if (cpu < 0) {
 		/* ALL_OTHERS */
 		cpumask_copy(&nmi_ipi_pending_mask, cpu_online_mask);
 		cpumask_clear_cpu(me, &nmi_ipi_pending_mask);
 	} else {
-		/* cpumask starts clear */
 		cpumask_set_cpu(cpu, &nmi_ipi_pending_mask);
 	}
-	nmi_ipi_busy_count++;
+
 	nmi_ipi_unlock();
 
+	/* Interrupts remain hard disabled */
+
 	do_smp_send_nmi_ipi(cpu, safe);
 
 	nmi_ipi_lock();
-	/* nmi_ipi_busy_count is held here, so unlock/lock is okay */
+	/* nmi_ipi_busy is set here, so unlock/lock is okay */
 	while (!cpumask_empty(&nmi_ipi_pending_mask)) {
 		nmi_ipi_unlock();
 		udelay(1);
@@ -523,29 +514,15 @@ int __smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us, bool
 		}
 	}
 
-	while (nmi_ipi_busy_count > 1) {
-		nmi_ipi_unlock();
-		udelay(1);
-		nmi_ipi_lock();
-		if (delay_us) {
-			delay_us--;
-			if (!delay_us)
-				break;
-		}
-	}
-
 	if (!cpumask_empty(&nmi_ipi_pending_mask)) {
 		/* Timeout waiting for CPUs to call smp_handle_nmi_ipi */
 		ret = 0;
 		cpumask_clear(&nmi_ipi_pending_mask);
 	}
-	if (nmi_ipi_busy_count > 1) {
-		/* Timeout waiting for CPUs to execute fn */
-		ret = 0;
-		nmi_ipi_busy_count = 1;
-	}
 
-	nmi_ipi_busy_count--;
+	nmi_ipi_function = NULL;
+	nmi_ipi_busy = false;
+
 	nmi_ipi_unlock_end(&flags);
 
 	return ret;
@@ -613,17 +590,8 @@ void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *))
 static void nmi_stop_this_cpu(struct pt_regs *regs)
 {
 	/*
-	 * This is a special case because it never returns, so the NMI IPI
-	 * handling would never mark it as done, which makes any later
-	 * smp_send_nmi_ipi() call spin forever. Mark it done now.
-	 *
 	 * IRQs are already hard disabled by the smp_handle_nmi_ipi.
 	 */
-	nmi_ipi_lock();
-	if (nmi_ipi_busy_count > 1)
-		nmi_ipi_busy_count--;
-	nmi_ipi_unlock();
-
 	spin_begin();
 	while (1)
 		spin_cpu_relax();
@@ -663,7 +631,7 @@ void smp_send_stop(void)
 }
 #endif /* CONFIG_NMI_IPI */
 
-struct thread_info *current_set[NR_CPUS];
+struct task_struct *current_set[NR_CPUS];
 
 static void smp_store_cpu_info(int id)
 {
@@ -928,7 +896,7 @@ void smp_prepare_boot_cpu(void)
 	paca_ptrs[boot_cpuid]->__current = current;
 #endif
 	set_numa_node(numa_cpu_lookup_table[boot_cpuid]);
-	current_set[boot_cpuid] = task_thread_info(current);
+	current_set[boot_cpuid] = current;
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -1013,14 +981,13 @@ static bool secondaries_inhibited(void)
 
 static void cpu_idle_thread_init(unsigned int cpu, struct task_struct *idle)
 {
-	struct thread_info *ti = task_thread_info(idle);
-
 #ifdef CONFIG_PPC64
 	paca_ptrs[cpu]->__current = idle;
-	paca_ptrs[cpu]->kstack = (unsigned long)ti + THREAD_SIZE - STACK_FRAME_OVERHEAD;
+	paca_ptrs[cpu]->kstack = (unsigned long)task_stack_page(idle) +
+				 THREAD_SIZE - STACK_FRAME_OVERHEAD;
 #endif
-	ti->cpu = cpu;
-	secondary_ti = current_set[cpu] = ti;
+	idle->cpu = cpu;
+	secondary_current = current_set[cpu] = idle;
 }
 
 int __cpu_up(unsigned int cpu, struct task_struct *tidle)