Merge branch 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus

Pull MIPS fixes from Ralf Baechle:
 "Here's a final round of fixes for 4.12:

   - Fix misordered instructions in assembly code making kenel startup
     via UHB unreliable.

   - Fix special case of MADDF and MADDF emulation.

   - Fix alignment issue in address calculation in pm-cps on 64 bit.

   - Fix IRQ tracing & lockdep when rescheduling

   - Systems with MAARs require post-DMA cache flushes.

  The reordering fix and the MADDF/MSUBF fix have sat in linux-next for
  a number of days. The others haven't propagated from my pull tree to
  linux-next yet but all have survived manual testing and Imagination's
  automated test system and there are no pending bug reports"

* 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus:
  MIPS: Avoid accidental raw backtrace
  MIPS: Perform post-DMA cache flushes on systems with MAARs
  MIPS: Fix IRQ tracing & lockdep when rescheduling
  MIPS: pm-cps: Drop manual cache-line alignment of ready_count
  MIPS: math-emu: Handle zero accumulator case in MADDF and MSUBF separately
  MIPS: head: Reorder instructions missing a delay slot

arch/mips/kernel/entry.S

@@ -11,6 +11,7 @@
 #include <asm/asm.h>
 #include <asm/asmmacro.h>
 #include <asm/compiler.h>
+#include <asm/irqflags.h>
 #include <asm/regdef.h>
 #include <asm/mipsregs.h>
 #include <asm/stackframe.h>
@@ -119,6 +120,7 @@ work_pending:
 	andi	t0, a2, _TIF_NEED_RESCHED # a2 is preloaded with TI_FLAGS
 	beqz	t0, work_notifysig
 work_resched:
+	TRACE_IRQS_OFF
 	jal	schedule
 
 	local_irq_disable		# make sure need_resched and
@@ -155,6 +157,7 @@ syscall_exit_work:
 	beqz	t0, work_pending	# trace bit set?
 	local_irq_enable		# could let syscall_trace_leave()
 					# call schedule() instead
+	TRACE_IRQS_ON
 	move	a0, sp
 	jal	syscall_trace_leave
 	b	resume_userspace

arch/mips/kernel/head.S

@@ -106,8 +106,8 @@ NESTED(kernel_entry, 16, sp)			# kernel entry point
 	beq		t0, t1, dtb_found
 #endif
 	li		t1, -2
-	beq		a0, t1, dtb_found
 	move		t2, a1
+	beq		a0, t1, dtb_found
 
 	li		t2, 0
 dtb_found:

arch/mips/kernel/pm-cps.c

@@ -56,7 +56,6 @@ DECLARE_BITMAP(state_support, CPS_PM_STATE_COUNT);
  * state. Actually per-core rather than per-CPU.
  */
 static DEFINE_PER_CPU_ALIGNED(u32*, ready_count);
-static DEFINE_PER_CPU_ALIGNED(void*, ready_count_alloc);
 
 /* Indicates online CPUs coupled with the current CPU */
 static DEFINE_PER_CPU_ALIGNED(cpumask_t, online_coupled);
@@ -642,7 +641,6 @@ static int cps_pm_online_cpu(unsigned int cpu)
 {
 	enum cps_pm_state state;
 	unsigned core = cpu_data[cpu].core;
-	unsigned dlinesz = cpu_data[cpu].dcache.linesz;
 	void *entry_fn, *core_rc;
 
 	for (state = CPS_PM_NC_WAIT; state < CPS_PM_STATE_COUNT; state++) {
@@ -662,16 +660,11 @@ static int cps_pm_online_cpu(unsigned int cpu)
 	}
 
 	if (!per_cpu(ready_count, core)) {
-		core_rc = kmalloc(dlinesz * 2, GFP_KERNEL);
+		core_rc = kmalloc(sizeof(u32), GFP_KERNEL);
 		if (!core_rc) {
 			pr_err("Failed allocate core %u ready_count\n", core);
 			return -ENOMEM;
 		}
-		per_cpu(ready_count_alloc, core) = core_rc;
-
-		/* Ensure ready_count is aligned to a cacheline boundary */
-		core_rc += dlinesz - 1;
-		core_rc = (void *)((unsigned long)core_rc & ~(dlinesz - 1));
 		per_cpu(ready_count, core) = core_rc;
 	}
 

arch/mips/kernel/traps.c

@@ -201,6 +201,8 @@ void show_stack(struct task_struct *task, unsigned long *sp)
 {
 	struct pt_regs regs;
 	mm_segment_t old_fs = get_fs();
+
+	regs.cp0_status = KSU_KERNEL;
 	if (sp) {
 		regs.regs[29] = (unsigned long)sp;
 		regs.regs[31] = 0;

arch/mips/math-emu/dp_maddf.c

@@ -54,7 +54,7 @@ static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x,
 		return ieee754dp_nanxcpt(z);
 	case IEEE754_CLASS_DNORM:
 		DPDNORMZ;
-	/* QNAN is handled separately below */
+	/* QNAN and ZERO cases are handled separately below */
 	}
 
 	switch (CLPAIR(xc, yc)) {
@@ -210,6 +210,9 @@ static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x,
 	}
 	assert(rm & (DP_HIDDEN_BIT << 3));
 
+	if (zc == IEEE754_CLASS_ZERO)
+		return ieee754dp_format(rs, re, rm);
+
 	/* And now the addition */
 	assert(zm & DP_HIDDEN_BIT);
 

arch/mips/math-emu/sp_maddf.c

@@ -54,7 +54,7 @@ static union ieee754sp _sp_maddf(union ieee754sp z, union ieee754sp x,
 		return ieee754sp_nanxcpt(z);
 	case IEEE754_CLASS_DNORM:
 		SPDNORMZ;
-	/* QNAN is handled separately below */
+	/* QNAN and ZERO cases are handled separately below */
 	}
 
 	switch (CLPAIR(xc, yc)) {
@@ -203,6 +203,9 @@ static union ieee754sp _sp_maddf(union ieee754sp z, union ieee754sp x,
 	}
 	assert(rm & (SP_HIDDEN_BIT << 3));
 
+	if (zc == IEEE754_CLASS_ZERO)
+		return ieee754sp_format(rs, re, rm);
+
 	/* And now the addition */
 
 	assert(zm & SP_HIDDEN_BIT);

arch/mips/mm/dma-default.c

@@ -68,12 +68,25 @@ static inline struct page *dma_addr_to_page(struct device *dev,
  * systems and only the R10000 and R12000 are used in such systems, the
  * SGI IP28 Indigo² rsp. SGI IP32 aka O2.
  */
-static inline int cpu_needs_post_dma_flush(struct device *dev)
+static inline bool cpu_needs_post_dma_flush(struct device *dev)
 {
-	return !plat_device_is_coherent(dev) &&
+	if (plat_device_is_coherent(dev))
-	       (boot_cpu_type() == CPU_R10000 ||
+		return false;
-		boot_cpu_type() == CPU_R12000 ||
+
-		boot_cpu_type() == CPU_BMIPS5000);
+	switch (boot_cpu_type()) {
+	case CPU_R10000:
+	case CPU_R12000:
+	case CPU_BMIPS5000:
+		return true;
+
+	default:
+		/*
+		 * Presence of MAARs suggests that the CPU supports
+		 * speculatively prefetching data, and therefore requires
+		 * the post-DMA flush/invalidate.
+		 */
+		return cpu_has_maar;
+	}
 }
 
 static gfp_t massage_gfp_flags(const struct device *dev, gfp_t gfp)