Merge tag 'powerpc-3.20-1' of git://git.kernel.org/pub/scm/linux/kernel/git/mpe/linux

Pull powerpc updates from Michael Ellerman:

 - Update of all defconfigs

 - Addition of a bunch of config options to modernise our defconfigs

 - Some PS3 updates from Geoff

 - Optimised memcmp for 64 bit from Anton

 - Fix for kprobes that allows 'perf probe' to work from Naveen

 - Several cxl updates from Ian & Ryan

 - Expanded support for the '24x7' PMU from Cody & Sukadev

 - Freescale updates from Scott:
    "Highlights include 8xx optimizations, some more work on datapath
     device tree content, e300 machine check support, t1040 corenet
     error reporting, and various cleanups and fixes"

* tag 'powerpc-3.20-1' of git://git.kernel.org/pub/scm/linux/kernel/git/mpe/linux: (102 commits)
  cxl: Add missing return statement after handling AFU errror
  cxl: Fail AFU initialisation if an invalid configuration record is found
  cxl: Export optional AFU configuration record in sysfs
  powerpc/mm: Warn on flushing tlb page in kernel context
  powerpc/powernv: Add OPAL soft-poweroff routine
  powerpc/perf/hv-24x7: Document sysfs event description entries
  powerpc/perf/hv-gpci: add the remaining gpci requests
  powerpc/perf/{hv-gpci, hv-common}: generate requests with counters annotated
  powerpc/perf/hv-24x7: parse catalog and populate sysfs with events
  perf: define EVENT_DEFINE_RANGE_FORMAT_LITE helper
  perf: add PMU_EVENT_ATTR_STRING() helper
  perf: provide sysfs_show for struct perf_pmu_events_attr
  powerpc/kernel: Avoid initializing device-tree pointer twice
  powerpc: Remove old compile time disabled syscall tracing code
  powerpc/kernel: Make syscall_exit a local label
  cxl: Fix device_node reference counting
  powerpc/mm: bail out early when flushing TLB page
  powerpc: defconfigs: add MTD_SPI_NOR (new dependency for M25P80)
  perf/powerpc: reset event hw state when adding it to the PMU
  powerpc/qe: Use strlcpy()
  ...

5 files changed, 65 insertions, 37 deletions

diff --git a/arch/powerpc/mm/fsl_booke_mmu.c b/arch/powerpc/mm/fsl_booke_mmu.c
index 94cd728..b46912f 100644
--- a/arch/powerpc/mm/fsl_booke_mmu.c
+++ b/arch/powerpc/mm/fsl_booke_mmu.c
@@ -67,8 +67,6 @@ struct tlbcamrange {
 	phys_addr_t phys;
 } tlbcam_addrs[NUM_TLBCAMS];
 
-extern unsigned int tlbcam_index;
-
 unsigned long tlbcam_sz(int idx)
 {
 	return tlbcam_addrs[idx].limit - tlbcam_addrs[idx].start + 1;
diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c
index 9cba6cb..986afbc 100644
--- a/arch/powerpc/mm/mmu_context_nohash.c
+++ b/arch/powerpc/mm/mmu_context_nohash.c
@@ -52,12 +52,15 @@
 #include <asm/mmu_context.h>
 #include <asm/tlbflush.h>
 
+#include "mmu_decl.h"
+
 static unsigned int first_context, last_context;
 static unsigned int next_context, nr_free_contexts;
 static unsigned long *context_map;
 static unsigned long *stale_map[NR_CPUS];
 static struct mm_struct **context_mm;
 static DEFINE_RAW_SPINLOCK(context_lock);
+static bool no_selective_tlbil;
 
 #define CTX_MAP_SIZE	\
 	(sizeof(unsigned long) * (last_context / BITS_PER_LONG + 1))
@@ -133,6 +136,38 @@ static unsigned int steal_context_smp(unsigned int id)
 }
 #endif  /* CONFIG_SMP */
 
+static unsigned int steal_all_contexts(void)
+{
+	struct mm_struct *mm;
+	int cpu = smp_processor_id();
+	unsigned int id;
+
+	for (id = first_context; id <= last_context; id++) {
+		/* Pick up the victim mm */
+		mm = context_mm[id];
+
+		pr_hardcont(" | steal %d from 0x%p", id, mm);
+
+		/* Mark this mm as having no context anymore */
+		mm->context.id = MMU_NO_CONTEXT;
+		if (id != first_context) {
+			context_mm[id] = NULL;
+			__clear_bit(id, context_map);
+#ifdef DEBUG_MAP_CONSISTENCY
+			mm->context.active = 0;
+#endif
+		}
+		__clear_bit(id, stale_map[cpu]);
+	}
+
+	/* Flush the TLB for all contexts (not to be used on SMP) */
+	_tlbil_all();
+
+	nr_free_contexts = last_context - first_context;
+
+	return first_context;
+}
+
 /* Note that this will also be called on SMP if all other CPUs are
  * offlined, which means that it may be called for cpu != 0. For
  * this to work, we somewhat assume that CPUs that are onlined
@@ -241,7 +276,10 @@ void switch_mmu_context(struct mm_struct *prev, struct mm_struct *next)
 			goto stolen;
 		}
 #endif /* CONFIG_SMP */
-		id = steal_context_up(id);
+		if (no_selective_tlbil)
+			id = steal_all_contexts();
+		else
+			id = steal_context_up(id);
 		goto stolen;
 	}
 	nr_free_contexts--;
@@ -407,12 +445,15 @@ void __init mmu_context_init(void)
 	if (mmu_has_feature(MMU_FTR_TYPE_8xx)) {
 		first_context = 0;
 		last_context = 15;
+		no_selective_tlbil = true;
 	} else if (mmu_has_feature(MMU_FTR_TYPE_47x)) {
 		first_context = 1;
 		last_context = 65535;
+		no_selective_tlbil = false;
 	} else {
 		first_context = 1;
 		last_context = 255;
+		no_selective_tlbil = false;
 	}
 
 #ifdef DEBUG_CLAMP_LAST_CONTEXT
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 50fad38..03b1a3b 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -63,7 +63,6 @@ void setbat(int index, unsigned long virt, phys_addr_t phys,
 #endif /* HAVE_BATS */
 
 #ifdef HAVE_TLBCAM
-extern unsigned int tlbcam_index;
 extern phys_addr_t v_mapped_by_tlbcam(unsigned long va);
 extern unsigned long p_mapped_by_tlbcam(phys_addr_t pa);
 #else /* !HAVE_TLBCAM */
@@ -73,13 +72,25 @@ extern unsigned long p_mapped_by_tlbcam(phys_addr_t pa);
 
 #define PGDIR_ORDER	(32 + PGD_T_LOG2 - PGDIR_SHIFT)
 
+#ifndef CONFIG_PPC_4K_PAGES
+static struct kmem_cache *pgtable_cache;
+
+void pgtable_cache_init(void)
+{
+	pgtable_cache = kmem_cache_create("PGDIR cache", 1 << PGDIR_ORDER,
+					  1 << PGDIR_ORDER, 0, NULL);
+	if (pgtable_cache == NULL)
+		panic("Couldn't allocate pgtable caches");
+}
+#endif
+
 pgd_t *pgd_alloc(struct mm_struct *mm)
 {
 	pgd_t *ret;
 
 	/* pgdir take page or two with 4K pages and a page fraction otherwise */
 #ifndef CONFIG_PPC_4K_PAGES
-	ret = kzalloc(1 << PGDIR_ORDER, GFP_KERNEL);
+	ret = kmem_cache_alloc(pgtable_cache, GFP_KERNEL | __GFP_ZERO);
 #else
 	ret = (pgd_t *)__get_free_pages(GFP_KERNEL|__GFP_ZERO,
 			PGDIR_ORDER - PAGE_SHIFT);
@@ -90,7 +101,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
 #ifndef CONFIG_PPC_4K_PAGES
-	kfree((void *)pgd);
+	kmem_cache_free(pgtable_cache, (void *)pgd);
 #else
 	free_pages((unsigned long)pgd, PGDIR_ORDER - PAGE_SHIFT);
 #endif
@@ -147,7 +158,7 @@ void __iomem *
 ioremap_prot(phys_addr_t addr, unsigned long size, unsigned long flags)
 {
 	/* writeable implies dirty for kernel addresses */
-	if (flags & _PAGE_RW)
+	if ((flags & (_PAGE_RW | _PAGE_RO)) != _PAGE_RO)
 		flags |= _PAGE_DIRTY | _PAGE_HWWRITE;
 
 	/* we don't want to let _PAGE_USER and _PAGE_EXEC leak out */
diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c
index ded0ea1..0f432a7 100644
--- a/arch/powerpc/mm/slice.c
+++ b/arch/powerpc/mm/slice.c
@@ -645,35 +645,6 @@ void slice_set_user_psize(struct mm_struct *mm, unsigned int psize)
 	spin_unlock_irqrestore(&slice_convert_lock, flags);
 }
 
-void slice_set_psize(struct mm_struct *mm, unsigned long address,
-		     unsigned int psize)
-{
-	unsigned char *hpsizes;
-	unsigned long i, flags;
-	u64 *lpsizes;
-
-	spin_lock_irqsave(&slice_convert_lock, flags);
-	if (address < SLICE_LOW_TOP) {
-		i = GET_LOW_SLICE_INDEX(address);
-		lpsizes = &mm->context.low_slices_psize;
-		*lpsizes = (*lpsizes & ~(0xful << (i * 4))) |
-			((unsigned long) psize << (i * 4));
-	} else {
-		int index, mask_index;
-		i = GET_HIGH_SLICE_INDEX(address);
-		hpsizes = mm->context.high_slices_psize;
-		mask_index = i & 0x1;
-		index = i >> 1;
-		hpsizes[index] = (hpsizes[index] &
-				  ~(0xf << (mask_index * 4))) |
-			(((unsigned long)psize) << (mask_index * 4));
-	}
-
-	spin_unlock_irqrestore(&slice_convert_lock, flags);
-
-	copro_flush_all_slbs(mm);
-}
-
 void slice_set_range_psize(struct mm_struct *mm, unsigned long start,
 			   unsigned long len, unsigned int psize)
 {
diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c
index f38ea4d..cbd3d06 100644
--- a/arch/powerpc/mm/tlb_nohash.c
+++ b/arch/powerpc/mm/tlb_nohash.c
@@ -284,8 +284,15 @@ void __flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
 	struct cpumask *cpu_mask;
 	unsigned int pid;
 
+	/*
+	 * This function as well as __local_flush_tlb_page() must only be called
+	 * for user contexts.
+	 */
+	if (unlikely(WARN_ON(!mm)))
+		return;
+
 	preempt_disable();
-	pid = mm ? mm->context.id : 0;
+	pid = mm->context.id;
 	if (unlikely(pid == MMU_NO_CONTEXT))
 		goto bail;
 	cpu_mask = mm_cpumask(mm);