Merge tag 'powerpc-4.10-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Highlights include:

   - Support for the kexec_file_load() syscall, which is a prereq for
     secure and trusted boot.

   - Prevent kernel execution of userspace on P9 Radix (similar to
     SMEP/PXN).

   - Sort the exception tables at build time, to save time at boot, and
     store them as relative offsets to save space in the kernel image &
     memory.

   - Allow building the kernel with thin archives, which should allow us
     to build an allyesconfig once some other fixes land.

   - Build fixes to allow us to correctly rebuild when changing the
     kernel endian from big to little or vice versa.

   - Plumbing so that we can avoid doing a full mm TLB flush on P9
     Radix.

   - Initial stack protector support (-fstack-protector).

   - Support for dumping the radix (aka. Linux) and hash page tables via
     debugfs.

   - Fix an oops in cxl coredump generation when cxl_get_fd() is used.

   - Freescale updates from Scott: "Highlights include 8xx hugepage
     support, qbman fixes/cleanup, device tree updates, and some misc
     cleanup."

   - Many and varied fixes and minor enhancements as always.

  Thanks to:
    Alexey Kardashevskiy, Andrew Donnellan, Aneesh Kumar K.V, Anshuman
    Khandual, Anton Blanchard, Balbir Singh, Bartlomiej Zolnierkiewicz,
    Christophe Jaillet, Christophe Leroy, Denis Kirjanov, Elimar
    Riesebieter, Frederic Barrat, Gautham R. Shenoy, Geliang Tang, Geoff
    Levand, Jack Miller, Johan Hovold, Lars-Peter Clausen, Libin,
    Madhavan Srinivasan, Michael Neuling, Nathan Fontenot, Naveen N.
    Rao, Nicholas Piggin, Pan Xinhui, Peter Senna Tschudin, Rashmica
    Gupta, Rui Teng, Russell Currey, Scott Wood, Simon Guo, Suraj
    Jitindar Singh, Thiago Jung Bauermann, Tobias Klauser, Vaibhav Jain"

[ And thanks to Michael, who took time off from a new baby to get this
  pull request done.   - Linus ]

* tag 'powerpc-4.10-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (174 commits)
  powerpc/fsl/dts: add FMan node for t1042d4rdb
  powerpc/fsl/dts: add sg_2500_aqr105_phy4 alias on t1024rdb
  powerpc/fsl/dts: add QMan and BMan nodes on t1024
  powerpc/fsl/dts: add QMan and BMan nodes on t1023
  soc/fsl/qman: test: use DEFINE_SPINLOCK()
  powerpc/fsl-lbc: use DEFINE_SPINLOCK()
  powerpc/8xx: Implement support of hugepages
  powerpc: get hugetlbpage handling more generic
  powerpc: port 64 bits pgtable_cache to 32 bits
  powerpc/boot: Request no dynamic linker for boot wrapper
  soc/fsl/bman: Use resource_size instead of computation
  soc/fsl/qe: use builtin_platform_driver
  powerpc/fsl_pmc: use builtin_platform_driver
  powerpc/83xx/suspend: use builtin_platform_driver
  powerpc/ftrace: Fix the comments for ftrace_modify_code
  powerpc/perf: macros for power9 format encoding
  powerpc/perf: power9 raw event format encoding
  powerpc/perf: update attribute_group data structure
  powerpc/perf: factor out the event format field
  powerpc/mm/iommu, vfio/spapr: Put pages on VFIO container shutdown
  ...

7 files changed, 68 insertions, 51 deletions

diff --git a/arch/powerpc/include/asm/nohash/32/pgalloc.h b/arch/powerpc/include/asm/nohash/32/pgalloc.h
index 76d6b9e0c8a9..633139291a48 100644
--- a/arch/powerpc/include/asm/nohash/32/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/32/pgalloc.h
@@ -2,14 +2,42 @@
 #define _ASM_POWERPC_PGALLOC_32_H
 
 #include <linux/threads.h>
+#include <linux/slab.h>
 
-/* For 32-bit, all levels of page tables are just drawn from get_free_page() */
-#define MAX_PGTABLE_INDEX_SIZE	0
+/*
+ * Functions that deal with pagetables that could be at any level of
+ * the table need to be passed an "index_size" so they know how to
+ * handle allocation.  For PTE pages (which are linked to a struct
+ * page for now, and drawn from the main get_free_pages() pool), the
+ * allocation size will be (2^index_size * sizeof(pointer)) and
+ * allocations are drawn from the kmem_cache in PGT_CACHE(index_size).
+ *
+ * The maximum index size needs to be big enough to allow any
+ * pagetable sizes we need, but small enough to fit in the low bits of
+ * any page table pointer.  In other words all pagetables, even tiny
+ * ones, must be aligned to allow at least enough low 0 bits to
+ * contain this value.  This value is also used as a mask, so it must
+ * be one less than a power of two.
+ */
+#define MAX_PGTABLE_INDEX_SIZE	0xf
 
 extern void __bad_pte(pmd_t *pmd);
 
-extern pgd_t *pgd_alloc(struct mm_struct *mm);
-extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
+extern struct kmem_cache *pgtable_cache[];
+#define PGT_CACHE(shift) ({				\
+			BUG_ON(!(shift));		\
+			pgtable_cache[(shift) - 1];	\
+		})
+
+static inline pgd_t *pgd_alloc(struct mm_struct *mm)
+{
+	return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE), GFP_KERNEL);
+}
+
+static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+	kmem_cache_free(PGT_CACHE(PGD_INDEX_SIZE), pgd);
+}
 
 /*
  * We don't have any real pmd's, and this code never triggers because
@@ -68,8 +96,12 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
 
 static inline void pgtable_free(void *table, unsigned index_size)
 {
-	BUG_ON(index_size); /* 32-bit doesn't use this */
-	free_page((unsigned long)table);
+	if (!index_size) {
+		free_page((unsigned long)table);
+	} else {
+		BUG_ON(index_size > MAX_PGTABLE_INDEX_SIZE);
+		kmem_cache_free(PGT_CACHE(index_size), table);
+	}
 }
 
 #define check_pgt_cache()	do { } while (0)
diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index c219ef7be53b..ba9921bf202e 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -16,6 +16,23 @@ extern int icache_44x_need_flush;
 
 #endif /* __ASSEMBLY__ */
 
+#define PTE_INDEX_SIZE	PTE_SHIFT
+#define PMD_INDEX_SIZE	0
+#define PUD_INDEX_SIZE	0
+#define PGD_INDEX_SIZE	(32 - PGDIR_SHIFT)
+
+#define PMD_CACHE_INDEX	PMD_INDEX_SIZE
+
+#ifndef __ASSEMBLY__
+#define PTE_TABLE_SIZE	(sizeof(pte_t) << PTE_INDEX_SIZE)
+#define PMD_TABLE_SIZE	0
+#define PUD_TABLE_SIZE	0
+#define PGD_TABLE_SIZE	(sizeof(pgd_t) << PGD_INDEX_SIZE)
+#endif	/* __ASSEMBLY__ */
+
+#define PTRS_PER_PTE	(1 << PTE_INDEX_SIZE)
+#define PTRS_PER_PGD	(1 << PGD_INDEX_SIZE)
+
 /*
  * The normal case is that PTEs are 32-bits and we have a 1-page
  * 1024-entry pgdir pointing to 1-page 1024-entry PTE pages.  -- paulus
@@ -27,22 +44,12 @@ extern int icache_44x_need_flush;
  * -Matt
  */
 /* PGDIR_SHIFT determines what a top-level page table entry can map */
-#define PGDIR_SHIFT	(PAGE_SHIFT + PTE_SHIFT)
+#define PGDIR_SHIFT	(PAGE_SHIFT + PTE_INDEX_SIZE)
 #define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
 #define PGDIR_MASK	(~(PGDIR_SIZE-1))
 
-/*
- * entries per page directory level: our page-table tree is two-level, so
- * we don't really have any PMD directory.
- */
-#ifndef __ASSEMBLY__
-#define PTE_TABLE_SIZE	(sizeof(pte_t) << PTE_SHIFT)
-#define PGD_TABLE_SIZE	(sizeof(pgd_t) << (32 - PGDIR_SHIFT))
-#endif	/* __ASSEMBLY__ */
-
-#define PTRS_PER_PTE	(1 << PTE_SHIFT)
-#define PTRS_PER_PMD	1
-#define PTRS_PER_PGD	(1 << (32 - PGDIR_SHIFT))
+/* Bits to mask out from a PGD to get to the PUD page */
+#define PGD_MASKED_BITS		0
 
 #define USER_PTRS_PER_PGD	(TASK_SIZE / PGDIR_SIZE)
 #define FIRST_USER_ADDRESS	0UL
@@ -268,7 +275,8 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 
 
 static inline void __ptep_set_access_flags(struct mm_struct *mm,
-					   pte_t *ptep, pte_t entry)
+					   pte_t *ptep, pte_t entry,
+					   unsigned long address)
 {
 	unsigned long set = pte_val(entry) &
 		(_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC);
@@ -328,15 +336,6 @@ static inline void __ptep_set_access_flags(struct mm_struct *mm,
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val(pte) >> 3 })
 #define __swp_entry_to_pte(x)		((pte_t) { (x).val << 3 })
 
-#ifndef CONFIG_PPC_4K_PAGES
-void pgtable_cache_init(void);
-#else
-/*
- * No page table caches to initialise
- */
-#define pgtable_cache_init()	do { } while (0)
-#endif
-
 extern int get_pteptr(struct mm_struct *mm, unsigned long addr, pte_t **ptep,
 		      pmd_t **pmdp);
 
diff --git a/arch/powerpc/include/asm/nohash/32/pte-8xx.h b/arch/powerpc/include/asm/nohash/32/pte-8xx.h
index 3742b1919661..b4df2734c078 100644
--- a/arch/powerpc/include/asm/nohash/32/pte-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/pte-8xx.h
@@ -49,6 +49,7 @@
 #define _PMD_BAD	0x0ff0
 #define _PMD_PAGE_MASK	0x000c
 #define _PMD_PAGE_8M	0x000c
+#define _PMD_PAGE_512K	0x0004
 
 /* Until my rework is finished, 8xx still needs atomic PTE updates */
 #define PTE_ATOMIC_UPDATES	1
diff --git a/arch/powerpc/include/asm/nohash/64/pgtable-4k.h b/arch/powerpc/include/asm/nohash/64/pgtable-4k.h
index fc7d51753f81..d0db98793dd8 100644
--- a/arch/powerpc/include/asm/nohash/64/pgtable-4k.h
+++ b/arch/powerpc/include/asm/nohash/64/pgtable-4k.h
@@ -27,9 +27,6 @@
 #define PMD_SIZE	(1UL << PMD_SHIFT)
 #define PMD_MASK	(~(PMD_SIZE-1))
 
-/* With 4k base page size, hugepage PTEs go at the PMD level */
-#define MIN_HUGEPTE_SHIFT	PMD_SHIFT
-
 /* PUD_SHIFT determines what a third-level page table entry can map */
 #define PUD_SHIFT	(PMD_SHIFT + PMD_INDEX_SIZE)
 #define PUD_SIZE	(1UL << PUD_SHIFT)
diff --git a/arch/powerpc/include/asm/nohash/64/pgtable-64k.h b/arch/powerpc/include/asm/nohash/64/pgtable-64k.h
index 908324574f77..55b28ef3409a 100644
--- a/arch/powerpc/include/asm/nohash/64/pgtable-64k.h
+++ b/arch/powerpc/include/asm/nohash/64/pgtable-64k.h
@@ -31,9 +31,6 @@
 #define PTRS_PER_PMD	(1 << PMD_INDEX_SIZE)
 #define PTRS_PER_PGD	(1 << PGD_INDEX_SIZE)
 
-/* With 4k base page size, hugepage PTEs go at the PMD level */
-#define MIN_HUGEPTE_SHIFT	PAGE_SHIFT
-
 /* PMD_SHIFT determines what a second-level page table entry can map */
 #define PMD_SHIFT	(PAGE_SHIFT + PTE_INDEX_SIZE)
 #define PMD_SIZE	(1UL << PMD_SHIFT)
diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h
index 653a1838469d..c7f927e67d14 100644
--- a/arch/powerpc/include/asm/nohash/64/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/64/pgtable.h
@@ -26,15 +26,11 @@
 #else
 #define PMD_CACHE_INDEX	PMD_INDEX_SIZE
 #endif
+
 /*
  * Define the address range of the kernel non-linear virtual area
  */
-
-#ifdef CONFIG_PPC_BOOK3E
 #define KERN_VIRT_START ASM_CONST(0x8000000000000000)
-#else
-#define KERN_VIRT_START ASM_CONST(0xD000000000000000)
-#endif
 #define KERN_VIRT_SIZE	ASM_CONST(0x0000100000000000)
 
 /*
@@ -43,11 +39,7 @@
  * (we keep a quarter for the virtual memmap)
  */
 #define VMALLOC_START	KERN_VIRT_START
-#ifdef CONFIG_PPC_BOOK3E
 #define VMALLOC_SIZE	(KERN_VIRT_SIZE >> 2)
-#else
-#define VMALLOC_SIZE	(KERN_VIRT_SIZE >> 1)
-#endif
 #define VMALLOC_END	(VMALLOC_START + VMALLOC_SIZE)
 
 /*
@@ -85,12 +77,8 @@
  * Defines the address of the vmemap area, in its own region on
  * hash table CPUs and after the vmalloc space on Book3E
  */
-#ifdef CONFIG_PPC_BOOK3E
 #define VMEMMAP_BASE		VMALLOC_END
 #define VMEMMAP_END		KERN_IO_START
-#else
-#define VMEMMAP_BASE		(VMEMMAP_REGION_ID << REGION_SHIFT)
-#endif
 #define vmemmap			((struct page *)VMEMMAP_BASE)
 
 
@@ -301,7 +289,8 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
  * function doesn't need to flush the hash entry
  */
 static inline void __ptep_set_access_flags(struct mm_struct *mm,
-					   pte_t *ptep, pte_t entry)
+					   pte_t *ptep, pte_t entry,
+					   unsigned long address)
 {
 	unsigned long bits = pte_val(entry) &
 		(_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC);
@@ -358,8 +347,6 @@ static inline void __ptep_set_access_flags(struct mm_struct *mm,
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val((pte)) })
 #define __swp_entry_to_pte(x)		__pte((x).val)
 
-void pgtable_cache_add(unsigned shift, void (*ctor)(void *));
-void pgtable_cache_init(void);
 extern int map_kernel_page(unsigned long ea, unsigned long pa,
 			   unsigned long flags);
 extern int __meminit vmemmap_create_mapping(unsigned long start,
diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h
index 1263c22d60d8..172849727054 100644
--- a/arch/powerpc/include/asm/nohash/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/pgtable.h
@@ -226,7 +226,11 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 #ifdef CONFIG_HUGETLB_PAGE
 static inline int hugepd_ok(hugepd_t hpd)
 {
+#ifdef CONFIG_PPC_8xx
+	return ((hpd.pd & 0x4) != 0);
+#else
 	return (hpd.pd > 0);
+#endif
 }
 
 static inline int pmd_huge(pmd_t pmd)