Merge tag 'powerpc-4.5-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Core:
   - Ground work for the new Power9 MMU from Aneesh Kumar K.V
   - Optimise FP/VMX/VSX context switching from Anton Blanchard

  Misc:
   - Various cleanups from Krzysztof Kozlowski, John Ogness, Rashmica
     Gupta, Russell Currey, Gavin Shan, Daniel Axtens, Michael Neuling,
     Andrew Donnellan
   - Allow wrapper to work on non-english system from Laurent Vivier
   - Add rN aliases to the pt_regs_offset table from Rashmica Gupta
   - Fix module autoload for rackmeter & axonram drivers from Luis de
     Bethencourt
   - Include KVM guest test in all interrupt vectors from Paul Mackerras
   - Fix DSCR inheritance over fork() from Anton Blanchard
   - Make value-returning atomics & {cmp}xchg* & their atomic_ versions
     fully ordered from Boqun Feng
   - Print MSR TM bits in oops messages from Michael Neuling
   - Add TM signal return & invalid stack selftests from Michael Neuling
   - Limit EPOW reset event warnings from Vipin K Parashar
   - Remove the Cell QPACE code from Rashmica Gupta
   - Append linux_banner to exception information in xmon from Rashmica
     Gupta
   - Add selftest to check if VSRs are corrupted from Rashmica Gupta
   - Remove broken GregorianDay() from Daniel Axtens
   - Import Anton's context_switch2 benchmark into selftests from
     Michael Ellerman
   - Add selftest script to test HMI functionality from Daniel Axtens
   - Remove obsolete OPAL v2 support from Stewart Smith
   - Make enter_rtas() private from Michael Ellerman
   - PPR exception cleanups from Michael Ellerman
   - Add page soft dirty tracking from Laurent Dufour
   - Add support for Nvlink NPUs from Alistair Popple
   - Add support for kexec on 476fpe from Alistair Popple
   - Enable kernel CPU dlpar from sysfs from Nathan Fontenot
   - Copy only required pieces of the mm_context_t to the paca from
     Michael Neuling
   - Add a kmsg_dumper that flushes OPAL console output on panic from
     Russell Currey
   - Implement save_stack_trace_regs() to enable kprobe stack tracing
     from Steven Rostedt
   - Add HWCAP bits for Power9 from Michael Ellerman
   - Fix _PAGE_PTE breaking swapoff from Aneesh Kumar K.V
   - Fix _PAGE_SWP_SOFT_DIRTY breaking swapoff from Hugh Dickins
   - scripts/recordmcount.pl: support data in text section on powerpc
     from Ulrich Weigand
   - Handle R_PPC64_ENTRY relocations in modules from Ulrich Weigand

  cxl:
   - cxl: Fix possible idr warning when contexts are released from
     Vaibhav Jain
   - cxl: use correct operator when writing pcie config space values
     from Andrew Donnellan
   - cxl: Fix DSI misses when the context owning task exits from Vaibhav
     Jain
   - cxl: fix build for GCC 4.6.x from Brian Norris
   - cxl: use -Werror only with CONFIG_PPC_WERROR from Brian Norris
   - cxl: Enable PCI device ID for future IBM CXL adapter from Uma
     Krishnan

  Freescale:
   - Freescale updates from Scott: Highlights include moving QE code out
     of arch/powerpc (to be shared with arm), device tree updates, and
     minor fixes"

* tag 'powerpc-4.5-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (149 commits)
  powerpc/module: Handle R_PPC64_ENTRY relocations
  scripts/recordmcount.pl: support data in text section on powerpc
  powerpc/powernv: Fix OPAL_CONSOLE_FLUSH prototype and usages
  powerpc/mm: fix _PAGE_SWP_SOFT_DIRTY breaking swapoff
  powerpc/mm: Fix _PAGE_PTE breaking swapoff
  cxl: Enable PCI device ID for future IBM CXL adapter
  cxl: use -Werror only with CONFIG_PPC_WERROR
  cxl: fix build for GCC 4.6.x
  powerpc: Add HWCAP bits for Power9
  powerpc/powernv: Reserve PE#0 on NPU
  powerpc/powernv: Change NPU PE# assignment
  powerpc/powernv: Fix update of NVLink DMA mask
  powerpc/powernv: Remove misleading comment in pci.c
  powerpc: Implement save_stack_trace_regs() to enable kprobe stack tracing
  powerpc: Fix build break due to paca mm_context_t changes
  cxl: Fix DSI misses when the context owning task exits
  MAINTAINERS: Update Scott Wood's e-mail address
  powerpc/powernv: Fix minor off-by-one error in opal_mce_check_early_recovery()
  powerpc: Fix style of self-test config prompts
  powerpc/powernv: Only delay opal_rtc_read() retry when necessary
  ...

1 files changed, 95 insertions, 34 deletions

diff --git a/drivers/misc/cxl/fault.c b/drivers/misc/cxl/fault.c
index 25a5418c55cb..81c3f75b7330 100644
--- a/drivers/misc/cxl/fault.c
+++ b/drivers/misc/cxl/fault.c
@@ -166,13 +166,92 @@ static void cxl_handle_page_fault(struct cxl_context *ctx,
 	cxl_ack_irq(ctx, CXL_PSL_TFC_An_R, 0);
 }
 
+/*
+ * Returns the mm_struct corresponding to the context ctx via ctx->pid
+ * In case the task has exited we use the task group leader accessible
+ * via ctx->glpid to find the next task in the thread group that has a
+ * valid  mm_struct associated with it. If a task with valid mm_struct
+ * is found the ctx->pid is updated to use the task struct for subsequent
+ * translations. In case no valid mm_struct is found in the task group to
+ * service the fault a NULL is returned.
+ */
+static struct mm_struct *get_mem_context(struct cxl_context *ctx)
+{
+	struct task_struct *task = NULL;
+	struct mm_struct *mm = NULL;
+	struct pid *old_pid = ctx->pid;
+
+	if (old_pid == NULL) {
+		pr_warn("%s: Invalid context for pe=%d\n",
+			 __func__, ctx->pe);
+		return NULL;
+	}
+
+	task = get_pid_task(old_pid, PIDTYPE_PID);
+
+	/*
+	 * pid_alive may look racy but this saves us from costly
+	 * get_task_mm when the task is a zombie. In worst case
+	 * we may think a task is alive, which is about to die
+	 * but get_task_mm will return NULL.
+	 */
+	if (task != NULL && pid_alive(task))
+		mm = get_task_mm(task);
+
+	/* release the task struct that was taken earlier */
+	if (task)
+		put_task_struct(task);
+	else
+		pr_devel("%s: Context owning pid=%i for pe=%i dead\n",
+			__func__, pid_nr(old_pid), ctx->pe);
+
+	/*
+	 * If we couldn't find the mm context then use the group
+	 * leader to iterate over the task group and find a task
+	 * that gives us mm_struct.
+	 */
+	if (unlikely(mm == NULL && ctx->glpid != NULL)) {
+
+		rcu_read_lock();
+		task = pid_task(ctx->glpid, PIDTYPE_PID);
+		if (task)
+			do {
+				mm = get_task_mm(task);
+				if (mm) {
+					ctx->pid = get_task_pid(task,
+								PIDTYPE_PID);
+					break;
+				}
+				task = next_thread(task);
+			} while (task && !thread_group_leader(task));
+		rcu_read_unlock();
+
+		/* check if we switched pid */
+		if (ctx->pid != old_pid) {
+			if (mm)
+				pr_devel("%s:pe=%i switch pid %i->%i\n",
+					 __func__, ctx->pe, pid_nr(old_pid),
+					 pid_nr(ctx->pid));
+			else
+				pr_devel("%s:Cannot find mm for pid=%i\n",
+					 __func__, pid_nr(old_pid));
+
+			/* drop the reference to older pid */
+			put_pid(old_pid);
+		}
+	}
+
+	return mm;
+}
+
+
+
 void cxl_handle_fault(struct work_struct *fault_work)
 {
 	struct cxl_context *ctx =
 		container_of(fault_work, struct cxl_context, fault_work);
 	u64 dsisr = ctx->dsisr;
 	u64 dar = ctx->dar;
-	struct task_struct *task = NULL;
 	struct mm_struct *mm = NULL;
 
 	if (cxl_p2n_read(ctx->afu, CXL_PSL_DSISR_An) != dsisr ||
@@ -195,17 +274,17 @@ void cxl_handle_fault(struct work_struct *fault_work)
 		"DSISR: %#llx DAR: %#llx\n", ctx->pe, dsisr, dar);
 
 	if (!ctx->kernel) {
-		if (!(task = get_pid_task(ctx->pid, PIDTYPE_PID))) {
-			pr_devel("cxl_handle_fault unable to get task %i\n",
-				 pid_nr(ctx->pid));
+
+		mm = get_mem_context(ctx);
+		/* indicates all the thread in task group have exited */
+		if (mm == NULL) {
+			pr_devel("%s: unable to get mm for pe=%d pid=%i\n",
+				 __func__, ctx->pe, pid_nr(ctx->pid));
 			cxl_ack_ae(ctx);
 			return;
-		}
-		if (!(mm = get_task_mm(task))) {
-			pr_devel("cxl_handle_fault unable to get mm %i\n",
-				 pid_nr(ctx->pid));
-			cxl_ack_ae(ctx);
-			goto out;
+		} else {
+			pr_devel("Handling page fault for pe=%d pid=%i\n",
+				 ctx->pe, pid_nr(ctx->pid));
 		}
 	}
 
@@ -218,33 +297,22 @@ void cxl_handle_fault(struct work_struct *fault_work)
 
 	if (mm)
 		mmput(mm);
-out:
-	if (task)
-		put_task_struct(task);
 }
 
 static void cxl_prefault_one(struct cxl_context *ctx, u64 ea)
 {
-	int rc;
-	struct task_struct *task;
 	struct mm_struct *mm;
 
-	if (!(task = get_pid_task(ctx->pid, PIDTYPE_PID))) {
-		pr_devel("cxl_prefault_one unable to get task %i\n",
-			 pid_nr(ctx->pid));
-		return;
-	}
-	if (!(mm = get_task_mm(task))) {
+	mm = get_mem_context(ctx);
+	if (mm == NULL) {
 		pr_devel("cxl_prefault_one unable to get mm %i\n",
 			 pid_nr(ctx->pid));
-		put_task_struct(task);
 		return;
 	}
 
-	rc = cxl_fault_segment(ctx, mm, ea);
+	cxl_fault_segment(ctx, mm, ea);
 
 	mmput(mm);
-	put_task_struct(task);
 }
 
 static u64 next_segment(u64 ea, u64 vsid)
@@ -263,18 +331,13 @@ static void cxl_prefault_vma(struct cxl_context *ctx)
 	struct copro_slb slb;
 	struct vm_area_struct *vma;
 	int rc;
-	struct task_struct *task;
 	struct mm_struct *mm;
 
-	if (!(task = get_pid_task(ctx->pid, PIDTYPE_PID))) {
-		pr_devel("cxl_prefault_vma unable to get task %i\n",
-			 pid_nr(ctx->pid));
-		return;
-	}
-	if (!(mm = get_task_mm(task))) {
+	mm = get_mem_context(ctx);
+	if (mm == NULL) {
 		pr_devel("cxl_prefault_vm unable to get mm %i\n",
 			 pid_nr(ctx->pid));
-		goto out1;
+		return;
 	}
 
 	down_read(&mm->mmap_sem);
@@ -295,8 +358,6 @@ static void cxl_prefault_vma(struct cxl_context *ctx)
 	up_read(&mm->mmap_sem);
 
 	mmput(mm);
-out1:
-	put_task_struct(task);
 }
 
 void cxl_prefault(struct cxl_context *ctx, u64 wed)