Merge tag 'powerpc-4.12-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Highlights include:

   - Larger virtual address space on 64-bit server CPUs. By default we
     use a 128TB virtual address space, but a process can request access
     to the full 512TB by passing a hint to mmap().

   - Support for the new Power9 "XIVE" interrupt controller.

   - TLB flushing optimisations for the radix MMU on Power9.

   - Support for CAPI cards on Power9, using the "Coherent Accelerator
     Interface Architecture 2.0".

   - The ability to configure the mmap randomisation limits at build and
     runtime.

   - Several small fixes and cleanups to the kprobes code, as well as
     support for KPROBES_ON_FTRACE.

   - Major improvements to handling of system reset interrupts,
     correctly treating them as NMIs, giving them a dedicated stack and
     using a new hypervisor call to trigger them, all of which should
     aid debugging and robustness.

   - Many fixes and other minor enhancements.

  Thanks to: Alastair D'Silva, Alexey Kardashevskiy, Alistair Popple,
  Andrew Donnellan, Aneesh Kumar K.V, Anshuman Khandual, Anton
  Blanchard, Balbir Singh, Ben Hutchings, Benjamin Herrenschmidt,
  Bhupesh Sharma, Chris Packham, Christian Zigotzky, Christophe Leroy,
  Christophe Lombard, Daniel Axtens, David Gibson, Gautham R. Shenoy,
  Gavin Shan, Geert Uytterhoeven, Guilherme G. Piccoli, Hamish Martin,
  Hari Bathini, Kees Cook, Laurent Dufour, Madhavan Srinivasan, Mahesh J
  Salgaonkar, Mahesh Salgaonkar, Masami Hiramatsu, Matt Brown, Matthew
  R. Ochs, Michael Neuling, Naveen N. Rao, Nicholas Piggin, Oliver
  O'Halloran, Pan Xinhui, Paul Mackerras, Rashmica Gupta, Russell
  Currey, Sukadev Bhattiprolu, Thadeu Lima de Souza Cascardo, Tobin C.
  Harding, Tyrel Datwyler, Uma Krishnan, Vaibhav Jain, Vipin K Parashar,
  Yang Shi"

* tag 'powerpc-4.12-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (214 commits)
  powerpc/64s: Power9 has no LPCR[VRMASD] field so don't set it
  powerpc/powernv: Fix TCE kill on NVLink2
  powerpc/mm/radix: Drop support for CPUs without lockless tlbie
  powerpc/book3s/mce: Move add_taint() later in virtual mode
  powerpc/sysfs: Move #ifdef CONFIG_HOTPLUG_CPU out of the function body
  powerpc/smp: Document irq enable/disable after migrating IRQs
  powerpc/mpc52xx: Don't select user-visible RTAS_PROC
  powerpc/powernv: Document cxl dependency on special case in pnv_eeh_reset()
  powerpc/eeh: Clean up and document event handling functions
  powerpc/eeh: Avoid use after free in eeh_handle_special_event()
  cxl: Mask slice error interrupts after first occurrence
  cxl: Route eeh events to all drivers in cxl_pci_error_detected()
  cxl: Force context lock during EEH flow
  powerpc/64: Allow CONFIG_RELOCATABLE if COMPILE_TEST
  powerpc/xmon: Teach xmon oops about radix vectors
  powerpc/mm/hash: Fix off-by-one in comment about kernel contexts ids
  powerpc/pseries: Enable VFIO
  powerpc/powernv: Fix iommu table size calculation hook for small tables
  powerpc/powernv: Check kzalloc() return value in pnv_pci_table_alloc
  powerpc: Add arch/powerpc/tools directory
  ...

1 files changed, 41 insertions, 43 deletions

diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 51def8a515be..3a7d580fdc59 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -120,8 +120,6 @@ static int do_sigbus(struct pt_regs *regs, unsigned long address,
 	siginfo_t info;
 	unsigned int lsb = 0;
 
-	up_read(&current->mm->mmap_sem);
-
 	if (!user_mode(regs))
 		return MM_FAULT_ERR(SIGBUS);
 
@@ -154,13 +152,6 @@ static int mm_fault_error(struct pt_regs *regs, unsigned long addr, int fault)
 	 * continue the pagefault.
 	 */
 	if (fatal_signal_pending(current)) {
-		/*
-		 * If we have retry set, the mmap semaphore will have
-		 * alrady been released in __lock_page_or_retry(). Else
-		 * we release it now.
-		 */
-		if (!(fault & VM_FAULT_RETRY))
-			up_read(&current->mm->mmap_sem);
 		/* Coming from kernel, we need to deal with uaccess fixups */
 		if (user_mode(regs))
 			return MM_FAULT_RETURN;
@@ -173,8 +164,6 @@ static int mm_fault_error(struct pt_regs *regs, unsigned long addr, int fault)
 
 	/* Out of memory */
 	if (fault & VM_FAULT_OOM) {
-		up_read(&current->mm->mmap_sem);
-
 		/*
 		 * We ran out of memory, or some other thing happened to us that
 		 * made us unable to handle the page fault gracefully.
@@ -298,7 +287,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
 	 * can result in fault, which will cause a deadlock when called with
 	 * mmap_sem held
 	 */
-	if (user_mode(regs))
+	if (!is_exec && user_mode(regs))
 		store_update_sp = store_updates_sp(regs);
 
 	if (user_mode(regs))
@@ -458,9 +447,30 @@ good_area:
 	 * the fault.
 	 */
 	fault = handle_mm_fault(vma, address, flags);
+
+	/*
+	 * Handle the retry right now, the mmap_sem has been released in that
+	 * case.
+	 */
+	if (unlikely(fault & VM_FAULT_RETRY)) {
+		/* We retry only once */
+		if (flags & FAULT_FLAG_ALLOW_RETRY) {
+			/*
+			 * Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
+			 * of starvation.
+			 */
+			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+			flags |= FAULT_FLAG_TRIED;
+			if (!fatal_signal_pending(current))
+				goto retry;
+		}
+		/* We will enter mm_fault_error() below */
+	} else
+		up_read(&current->mm->mmap_sem);
+
 	if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) {
 		if (fault & VM_FAULT_SIGSEGV)
-			goto bad_area;
+			goto bad_area_nosemaphore;
 		rc = mm_fault_error(regs, address, fault);
 		if (rc >= MM_FAULT_RETURN)
 			goto bail;
@@ -469,41 +479,29 @@ good_area:
 	}
 
 	/*
-	 * Major/minor page fault accounting is only done on the
-	 * initial attempt. If we go through a retry, it is extremely
-	 * likely that the page will be found in page cache at that point.
+	 * Major/minor page fault accounting.
 	 */
-	if (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR) {
-			current->maj_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
-				      regs, address);
+	if (fault & VM_FAULT_MAJOR) {
+		current->maj_flt++;
+		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
+			      regs, address);
 #ifdef CONFIG_PPC_SMLPAR
-			if (firmware_has_feature(FW_FEATURE_CMO)) {
-				u32 page_ins;
-
-				preempt_disable();
-				page_ins = be32_to_cpu(get_lppaca()->page_ins);
-				page_ins += 1 << PAGE_FACTOR;
-				get_lppaca()->page_ins = cpu_to_be32(page_ins);
-				preempt_enable();
-			}
-#endif /* CONFIG_PPC_SMLPAR */
-		} else {
-			current->min_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
-				      regs, address);
-		}
-		if (fault & VM_FAULT_RETRY) {
-			/* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
-			 * of starvation. */
-			flags &= ~FAULT_FLAG_ALLOW_RETRY;
-			flags |= FAULT_FLAG_TRIED;
-			goto retry;
+		if (firmware_has_feature(FW_FEATURE_CMO)) {
+			u32 page_ins;
+
+			preempt_disable();
+			page_ins = be32_to_cpu(get_lppaca()->page_ins);
+			page_ins += 1 << PAGE_FACTOR;
+			get_lppaca()->page_ins = cpu_to_be32(page_ins);
+			preempt_enable();
 		}
+#endif /* CONFIG_PPC_SMLPAR */
+	} else {
+		current->min_flt++;
+		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
+			      regs, address);
 	}
 
-	up_read(&mm->mmap_sem);
 	goto bail;
 
 bad_area: