Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

Pull powerpc merge from Benjamin Herrenschmidt:
 "Here's the powerpc batch for this merge window.  It is going to be a
  bit more nasty than usual as in touching things outside of
  arch/powerpc mostly due to the big iSeriesectomy :-) We finally got
  rid of the bugger (legacy iSeries support) which was a PITA to
  maintain and that nobody really used anymore.

  Here are some of the highlights:

   - Legacy iSeries is gone.  Thanks Stephen ! There's still some bits
     and pieces remaining if you do a grep -ir series arch/powerpc but
     they are harmless and will be removed in the next few weeks
     hopefully.

   - The 'fadump' functionality (Firmware Assisted Dump) replaces the
     previous (equivalent) "pHyp assisted dump"...  it's a rewrite of a
     mechanism to get the hypervisor to do crash dumps on pSeries, the
     new implementation hopefully being much more reliable.  Thanks
     Mahesh Salgaonkar.

   - The "EEH" code (pSeries PCI error handling & recovery) got a big
     spring cleaning, motivated by the need to be able to implement a
     new backend for it on top of some new different type of firwmare.

     The work isn't complete yet, but a good chunk of the cleanups is
     there.  Note that this adds a field to struct device_node which is
     not very nice and which Grant objects to.  I will have a patch soon
     that moves that to a powerpc private data structure (hopefully
     before rc1) and we'll improve things further later on (hopefully
     getting rid of the need for that pointer completely).  Thanks Gavin
     Shan.

   - I dug into our exception & interrupt handling code to improve the
     way we do lazy interrupt handling (and make it work properly with
     "edge" triggered interrupt sources), and while at it found & fixed
     a wagon of issues in those areas, including adding support for page
     fault retry & fatal signals on page faults.

   - Your usual random batch of small fixes & updates, including a bunch
     of new embedded boards, both Freescale and APM based ones, etc..."

I fixed up some conflicts with the generalized irq-domain changes from
Grant Likely, hopefully correctly.

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (141 commits)
  powerpc/ps3: Do not adjust the wrapper load address
  powerpc: Remove the rest of the legacy iSeries include files
  powerpc: Remove the remaining CONFIG_PPC_ISERIES pieces
  init: Remove CONFIG_PPC_ISERIES
  powerpc: Remove FW_FEATURE ISERIES from arch code
  tty/hvc_vio: FW_FEATURE_ISERIES is no longer selectable
  powerpc/spufs: Fix double unlocks
  powerpc/5200: convert mpc5200 to use of_platform_populate()
  powerpc/mpc5200: add options to mpc5200_defconfig
  powerpc/mpc52xx: add a4m072 board support
  powerpc/mpc5200: update mpc5200_defconfig to fit for charon board
  Documentation/powerpc/mpc52xx.txt: Checkpatch cleanup
  powerpc/44x: Add additional device support for APM821xx SoC and Bluestone board
  powerpc/44x: Add support PCI-E for APM821xx SoC and Bluestone board
  MAINTAINERS: Update PowerPC 4xx tree
  powerpc/44x: The bug fixed support for APM821xx SoC and Bluestone board
  powerpc: document the FSL MPIC message register binding
  powerpc: add support for MPIC message register API
  powerpc/fsl: Added aliased MSIIR register address to MSI node in dts
  powerpc/85xx: mpc8548cds - add 36-bit dts
  ...

1 files changed, 131 insertions, 50 deletions

diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 2f0d1b032a8..19f2f9498b2 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -105,6 +105,82 @@ static int store_updates_sp(struct pt_regs *regs)
 	}
 	return 0;
 }
+/*
+ * do_page_fault error handling helpers
+ */
+
+#define MM_FAULT_RETURN		0
+#define MM_FAULT_CONTINUE	-1
+#define MM_FAULT_ERR(sig)	(sig)
+
+static int out_of_memory(struct pt_regs *regs)
+{
+	/*
+	 * We ran out of memory, or some other thing happened to us that made
+	 * us unable to handle the page fault gracefully.
+	 */
+	up_read(&current->mm->mmap_sem);
+	if (!user_mode(regs))
+		return MM_FAULT_ERR(SIGKILL);
+	pagefault_out_of_memory();
+	return MM_FAULT_RETURN;
+}
+
+static int do_sigbus(struct pt_regs *regs, unsigned long address)
+{
+	siginfo_t info;
+
+	up_read(&current->mm->mmap_sem);
+
+	if (user_mode(regs)) {
+		info.si_signo = SIGBUS;
+		info.si_errno = 0;
+		info.si_code = BUS_ADRERR;
+		info.si_addr = (void __user *)address;
+		force_sig_info(SIGBUS, &info, current);
+		return MM_FAULT_RETURN;
+	}
+	return MM_FAULT_ERR(SIGBUS);
+}
+
+static int mm_fault_error(struct pt_regs *regs, unsigned long addr, int fault)
+{
+	/*
+	 * Pagefault was interrupted by SIGKILL. We have no reason to
+	 * 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;
+		return MM_FAULT_ERR(SIGKILL);
+	}
+
+	/* No fault: be happy */
+	if (!(fault & VM_FAULT_ERROR))
+		return MM_FAULT_CONTINUE;
+
+	/* Out of memory */
+	if (fault & VM_FAULT_OOM)
+		return out_of_memory(regs);
+
+	/* Bus error. x86 handles HWPOISON here, we'll add this if/when
+	 * we support the feature in HW
+	 */
+	if (fault & VM_FAULT_SIGBUS)
+		return do_sigbus(regs, addr);
+
+	/* We don't understand the fault code, this is fatal */
+	BUG();
+	return MM_FAULT_CONTINUE;
+}
 
 /*
  * For 600- and 800-family processors, the error_code parameter is DSISR
@@ -124,11 +200,12 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 {
 	struct vm_area_struct * vma;
 	struct mm_struct *mm = current->mm;
-	siginfo_t info;
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 	int code = SEGV_MAPERR;
-	int is_write = 0, ret;
+	int is_write = 0;
 	int trap = TRAP(regs);
  	int is_exec = trap == 0x400;
+	int fault;
 
 #if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE))
 	/*
@@ -145,6 +222,9 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 	is_write = error_code & ESR_DST;
 #endif /* CONFIG_4xx || CONFIG_BOOKE */
 
+	if (is_write)
+		flags |= FAULT_FLAG_WRITE;
+
 #ifdef CONFIG_PPC_ICSWX
 	/*
 	 * we need to do this early because this "data storage
@@ -152,13 +232,11 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 	 * look at it
 	 */
 	if (error_code & ICSWX_DSI_UCT) {
-		int ret;
-
-		ret = acop_handle_fault(regs, address, error_code);
-		if (ret)
-			return ret;
+		int rc = acop_handle_fault(regs, address, error_code);
+		if (rc)
+			return rc;
 	}
-#endif
+#endif /* CONFIG_PPC_ICSWX */
 
 	if (notify_page_fault(regs))
 		return 0;
@@ -179,6 +257,10 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 	}
 #endif
 
+	/* We restore the interrupt state now */
+	if (!arch_irq_disabled_regs(regs))
+		local_irq_enable();
+
 	if (in_atomic() || mm == NULL) {
 		if (!user_mode(regs))
 			return SIGSEGV;
@@ -212,7 +294,15 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 		if (!user_mode(regs) && !search_exception_tables(regs->nip))
 			goto bad_area_nosemaphore;
 
+retry:
 		down_read(&mm->mmap_sem);
+	} else {
+		/*
+		 * The above down_read_trylock() might have succeeded in
+		 * which case we'll have missed the might_sleep() from
+		 * down_read():
+		 */
+		might_sleep();
 	}
 
 	vma = find_vma(mm, address);
@@ -327,30 +417,43 @@ good_area:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	ret = handle_mm_fault(mm, vma, address, is_write ? FAULT_FLAG_WRITE : 0);
-	if (unlikely(ret & VM_FAULT_ERROR)) {
-		if (ret & VM_FAULT_OOM)
-			goto out_of_memory;
-		else if (ret & VM_FAULT_SIGBUS)
-			goto do_sigbus;
-		BUG();
+	fault = handle_mm_fault(mm, vma, address, flags);
+	if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) {
+		int rc = mm_fault_error(regs, address, fault);
+		if (rc >= MM_FAULT_RETURN)
+			return rc;
 	}
-	if (ret & VM_FAULT_MAJOR) {
-		current->maj_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
-				     regs, address);
+
+	/*
+	 * 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.
+	 */
+	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);
 #ifdef CONFIG_PPC_SMLPAR
-		if (firmware_has_feature(FW_FEATURE_CMO)) {
-			preempt_disable();
-			get_lppaca()->page_ins += (1 << PAGE_FACTOR);
-			preempt_enable();
+			if (firmware_has_feature(FW_FEATURE_CMO)) {
+				preempt_disable();
+				get_lppaca()->page_ins += (1 << PAGE_FACTOR);
+				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;
+			goto retry;
 		}
-#endif
-	} else {
-		current->min_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
-				     regs, address);
 	}
+
 	up_read(&mm->mmap_sem);
 	return 0;
 
@@ -371,28 +474,6 @@ bad_area_nosemaphore:
 
 	return SIGSEGV;
 
-/*
- * We ran out of memory, or some other thing happened to us that made
- * us unable to handle the page fault gracefully.
- */
-out_of_memory:
-	up_read(&mm->mmap_sem);
-	if (!user_mode(regs))
-		return SIGKILL;
-	pagefault_out_of_memory();
-	return 0;
-
-do_sigbus:
-	up_read(&mm->mmap_sem);
-	if (user_mode(regs)) {
-		info.si_signo = SIGBUS;
-		info.si_errno = 0;
-		info.si_code = BUS_ADRERR;
-		info.si_addr = (void __user *)address;
-		force_sig_info(SIGBUS, &info, current);
-		return 0;
-	}
-	return SIGBUS;
 }
 
 /*