Merge branch 'parisc-4.16-1' of git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux

Pull parisc fixes from Helge Deller:

 - a patch to change the ordering of cache and TLB flushes to hopefully
   fix the random segfaults we very rarely face (by Dave Anglin).

 - a patch to hide the virtual kernel memory layout due to security
   reasons.

 - two small patches to make the kernel run more smoothly under qemu.

* 'parisc-4.16-1' of git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux:
  parisc: Reduce irq overhead when run in qemu
  parisc: Use cr16 interval timers unconditionally on qemu
  parisc: Check if secondary CPUs want own PDC calls
  parisc: Hide virtual kernel memory layout
  parisc: Fix ordering of cache and TLB flushes

5 files changed, 77 insertions, 38 deletions

diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index 19c0c14..7908977 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -465,10 +465,10 @@ EXPORT_SYMBOL(copy_user_page);
 int __flush_tlb_range(unsigned long sid, unsigned long start,
 		      unsigned long end)
 {
-	unsigned long flags, size;
+	unsigned long flags;
 
-	size = (end - start);
-	if (size >= parisc_tlb_flush_threshold) {
+	if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) &&
+	    end - start >= parisc_tlb_flush_threshold) {
 		flush_tlb_all();
 		return 1;
 	}
@@ -539,13 +539,11 @@ void flush_cache_mm(struct mm_struct *mm)
 	struct vm_area_struct *vma;
 	pgd_t *pgd;
 
-	/* Flush the TLB to avoid speculation if coherency is required. */
-	if (parisc_requires_coherency())
-		flush_tlb_all();
-
 	/* Flushing the whole cache on each cpu takes forever on
 	   rp3440, etc.  So, avoid it if the mm isn't too big.  */
-	if (mm_total_size(mm) >= parisc_cache_flush_threshold) {
+	if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) &&
+	    mm_total_size(mm) >= parisc_cache_flush_threshold) {
+		flush_tlb_all();
 		flush_cache_all();
 		return;
 	}
@@ -553,9 +551,9 @@ void flush_cache_mm(struct mm_struct *mm)
 	if (mm->context == mfsp(3)) {
 		for (vma = mm->mmap; vma; vma = vma->vm_next) {
 			flush_user_dcache_range_asm(vma->vm_start, vma->vm_end);
-			if ((vma->vm_flags & VM_EXEC) == 0)
-				continue;
-			flush_user_icache_range_asm(vma->vm_start, vma->vm_end);
+			if (vma->vm_flags & VM_EXEC)
+				flush_user_icache_range_asm(vma->vm_start, vma->vm_end);
+			flush_tlb_range(vma, vma->vm_start, vma->vm_end);
 		}
 		return;
 	}
@@ -581,14 +579,9 @@ void flush_cache_mm(struct mm_struct *mm)
 void flush_cache_range(struct vm_area_struct *vma,
 		unsigned long start, unsigned long end)
 {
-	BUG_ON(!vma->vm_mm->context);
-
-	/* Flush the TLB to avoid speculation if coherency is required. */
-	if (parisc_requires_coherency())
+	if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) &&
+	    end - start >= parisc_cache_flush_threshold) {
 		flush_tlb_range(vma, start, end);
-
-	if ((end - start) >= parisc_cache_flush_threshold
-	    || vma->vm_mm->context != mfsp(3)) {
 		flush_cache_all();
 		return;
 	}
@@ -596,6 +589,7 @@ void flush_cache_range(struct vm_area_struct *vma,
 	flush_user_dcache_range_asm(start, end);
 	if (vma->vm_flags & VM_EXEC)
 		flush_user_icache_range_asm(start, end);
+	flush_tlb_range(vma, start, end);
 }
 
 void
@@ -604,8 +598,7 @@ flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long
 	BUG_ON(!vma->vm_mm->context);
 
 	if (pfn_valid(pfn)) {
-		if (parisc_requires_coherency())
-			flush_tlb_page(vma, vmaddr);
+		flush_tlb_page(vma, vmaddr);
 		__flush_cache_page(vma, vmaddr, PFN_PHYS(pfn));
 	}
 }
@@ -613,21 +606,33 @@ flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long
 void flush_kernel_vmap_range(void *vaddr, int size)
 {
 	unsigned long start = (unsigned long)vaddr;
+	unsigned long end = start + size;
 
-	if ((unsigned long)size > parisc_cache_flush_threshold)
+	if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) &&
+	    (unsigned long)size >= parisc_cache_flush_threshold) {
+		flush_tlb_kernel_range(start, end);
 		flush_data_cache();
-	else
-		flush_kernel_dcache_range_asm(start, start + size);
+		return;
+	}
+
+	flush_kernel_dcache_range_asm(start, end);
+	flush_tlb_kernel_range(start, end);
 }
 EXPORT_SYMBOL(flush_kernel_vmap_range);
 
 void invalidate_kernel_vmap_range(void *vaddr, int size)
 {
 	unsigned long start = (unsigned long)vaddr;
+	unsigned long end = start + size;
 
-	if ((unsigned long)size > parisc_cache_flush_threshold)
+	if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) &&
+	    (unsigned long)size >= parisc_cache_flush_threshold) {
+		flush_tlb_kernel_range(start, end);
 		flush_data_cache();
-	else
-		flush_kernel_dcache_range_asm(start, start + size);
+		return;
+	}
+
+	purge_kernel_dcache_range_asm(start, end);
+	flush_tlb_kernel_range(start, end);
 }
 EXPORT_SYMBOL(invalidate_kernel_vmap_range);
diff --git a/arch/parisc/kernel/head.S b/arch/parisc/kernel/head.S
index bbbe360..fbb4e43 100644
--- a/arch/parisc/kernel/head.S
+++ b/arch/parisc/kernel/head.S
@@ -138,6 +138,16 @@ $pgt_fill_loop:
 	std		%dp,0x18(%r10)
 #endif
 
+#ifdef CONFIG_64BIT
+	/* Get PDCE_PROC for monarch CPU. */
+#define MEM_PDC_LO 0x388
+#define MEM_PDC_HI 0x35C
+	ldw             MEM_PDC_LO(%r0),%r3
+	ldw             MEM_PDC_HI(%r0),%r10
+	depd            %r10, 31, 32, %r3        /* move to upper word */
+#endif
+
+
 #ifdef CONFIG_SMP
 	/* Set the smp rendezvous address into page zero.
 	** It would be safer to do this in init_smp_config() but
@@ -196,12 +206,6 @@ common_stext:
         ** Someday, palo might not do this for the Monarch either.
         */
 2:
-#define MEM_PDC_LO 0x388
-#define MEM_PDC_HI 0x35C
-	ldw             MEM_PDC_LO(%r0),%r3
-	ldw             MEM_PDC_HI(%r0),%r6
-	depd            %r6, 31, 32, %r3        /* move to upper word */
-
 	mfctl		%cr30,%r6		/* PCX-W2 firmware bug */
 
 	ldo             PDC_PSW(%r0),%arg0              /* 21 */
@@ -268,6 +272,8 @@ $install_iva:
 aligned_rfi:
 	pcxt_ssm_bug
 
+	copy		%r3, %arg0	/* PDCE_PROC for smp_callin() */
+
 	rsm		PSW_SM_QUIET,%r0	/* off troublesome PSW bits */
 	/* Don't need NOPs, have 8 compliant insn before rfi */
 
diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S
index 2d40c4f..67b0f75 100644
--- a/arch/parisc/kernel/pacache.S
+++ b/arch/parisc/kernel/pacache.S
@@ -1110,6 +1110,28 @@ ENTRY_CFI(flush_kernel_dcache_range_asm)
 	.procend
 ENDPROC_CFI(flush_kernel_dcache_range_asm)
 
+ENTRY_CFI(purge_kernel_dcache_range_asm)
+	.proc
+	.callinfo NO_CALLS
+	.entry
+
+	ldil		L%dcache_stride, %r1
+	ldw		R%dcache_stride(%r1), %r23
+	ldo		-1(%r23), %r21
+	ANDCM		%r26, %r21, %r26
+
+1:      cmpb,COND(<<),n	%r26, %r25,1b
+	pdc,m		%r23(%r26)
+
+	sync
+	syncdma
+	bv		%r0(%r2)
+	nop
+	.exit
+
+	.procend
+ENDPROC_CFI(purge_kernel_dcache_range_asm)
+
 ENTRY_CFI(flush_user_icache_range_asm)
 	.proc
 	.callinfo NO_CALLS
diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c
index 30c28ab..4065b5e 100644
--- a/arch/parisc/kernel/smp.c
+++ b/arch/parisc/kernel/smp.c
@@ -292,10 +292,15 @@ smp_cpu_init(int cpunum)
  * Slaves start using C here. Indirectly called from smp_slave_stext.
  * Do what start_kernel() and main() do for boot strap processor (aka monarch)
  */
-void __init smp_callin(void)
+void __init smp_callin(unsigned long pdce_proc)
 {
 	int slave_id = cpu_now_booting;
 
+#ifdef CONFIG_64BIT
+	WARN_ON(((unsigned long)(PAGE0->mem_pdc_hi) << 32
+			| PAGE0->mem_pdc) != pdce_proc);
+#endif
+
 	smp_cpu_init(slave_id);
 	preempt_disable();
 
diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c
index 4b8fd6d..f7e6845 100644
--- a/arch/parisc/kernel/time.c
+++ b/arch/parisc/kernel/time.c
@@ -76,10 +76,10 @@ irqreturn_t __irq_entry timer_interrupt(int irq, void *dev_id)
 	next_tick = cpuinfo->it_value;
 
 	/* Calculate how many ticks have elapsed. */
+	now = mfctl(16);
 	do {
 		++ticks_elapsed;
 		next_tick += cpt;
-		now = mfctl(16);
 	} while (next_tick - now > cpt);
 
 	/* Store (in CR16 cycles) up to when we are accounting right now. */
@@ -103,16 +103,17 @@ irqreturn_t __irq_entry timer_interrupt(int irq, void *dev_id)
 	 * if one or the other wrapped. If "now" is "bigger" we'll end up
 	 * with a very large unsigned number.
 	 */
-	while (next_tick - mfctl(16) > cpt)
+	now = mfctl(16);
+	while (next_tick - now > cpt)
 		next_tick += cpt;
 
 	/* Program the IT when to deliver the next interrupt.
 	 * Only bottom 32-bits of next_tick are writable in CR16!
 	 * Timer interrupt will be delivered at least a few hundred cycles
-	 * after the IT fires, so if we are too close (<= 500 cycles) to the
+	 * after the IT fires, so if we are too close (<= 8000 cycles) to the
 	 * next cycle, simply skip it.
 	 */
-	if (next_tick - mfctl(16) <= 500)
+	if (next_tick - now <= 8000)
 		next_tick += cpt;
 	mtctl(next_tick, 16);
 
@@ -248,7 +249,7 @@ static int __init init_cr16_clocksource(void)
 	 * different sockets, so mark them unstable and lower rating on
 	 * multi-socket SMP systems.
 	 */
-	if (num_online_cpus() > 1) {
+	if (num_online_cpus() > 1 && !running_on_qemu) {
 		int cpu;
 		unsigned long cpu0_loc;
 		cpu0_loc = per_cpu(cpu_data, 0).cpu_loc;