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
  ...

6 files changed, 54 insertions, 28 deletions

diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
index 1af837c561ba..1c64bc6330bc 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -16,9 +16,6 @@
 #define H_PUD_TABLE_SIZE	(sizeof(pud_t) << H_PUD_INDEX_SIZE)
 #define H_PGD_TABLE_SIZE	(sizeof(pgd_t) << H_PGD_INDEX_SIZE)
 
-/* With 4k base page size, hugepage PTEs go at the PMD level */
-#define MIN_HUGEPTE_SHIFT	PMD_SHIFT
-
 /* PTE flags to conserve for HPTE identification */
 #define _PAGE_HPTEFLAGS (H_PAGE_BUSY | H_PAGE_HASHPTE | \
 			 H_PAGE_F_SECOND | H_PAGE_F_GIX)
diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h
index 5aae4f530c21..f3dd21efa2ea 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-64k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h
@@ -6,9 +6,6 @@
 #define H_PUD_INDEX_SIZE  5
 #define H_PGD_INDEX_SIZE  12
 
-/* With 4k base page size, hugepage PTEs go at the PMD level */
-#define MIN_HUGEPTE_SHIFT	PAGE_SHIFT
-
 #define H_PAGE_COMBO	0x00001000 /* this is a combo 4k page */
 #define H_PAGE_4K_PFN	0x00002000 /* PFN is for a single 4k page */
 /*
diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb-radix.h b/arch/powerpc/include/asm/book3s/64/hugetlb.h
index c45189aa7476..c62f14d0bec1 100644
--- a/arch/powerpc/include/asm/book3s/64/hugetlb-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_POWERPC_BOOK3S_64_HUGETLB_RADIX_H
-#define _ASM_POWERPC_BOOK3S_64_HUGETLB_RADIX_H
+#ifndef _ASM_POWERPC_BOOK3S_64_HUGETLB_H
+#define _ASM_POWERPC_BOOK3S_64_HUGETLB_H
 /*
  * For radix we want generic code to handle hugetlb. But then if we want
  * both hash and radix to be enabled together we need to workaround the
@@ -21,9 +21,33 @@ static inline int hstate_get_psize(struct hstate *hstate)
 		return MMU_PAGE_2M;
 	else if (shift == mmu_psize_defs[MMU_PAGE_1G].shift)
 		return MMU_PAGE_1G;
+	else if (shift == mmu_psize_defs[MMU_PAGE_16M].shift)
+		return MMU_PAGE_16M;
+	else if (shift == mmu_psize_defs[MMU_PAGE_16G].shift)
+		return MMU_PAGE_16G;
 	else {
 		WARN(1, "Wrong huge page shift\n");
 		return mmu_virtual_psize;
 	}
 }
+
+#define arch_make_huge_pte arch_make_huge_pte
+static inline pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
+				       struct page *page, int writable)
+{
+	unsigned long page_shift;
+
+	if (!cpu_has_feature(CPU_FTR_POWER9_DD1))
+		return entry;
+
+	page_shift = huge_page_shift(hstate_vma(vma));
+	/*
+	 * We don't support 1G hugetlb pages yet.
+	 */
+	VM_WARN_ON(page_shift == mmu_psize_defs[MMU_PAGE_1G].shift);
+	if (page_shift == mmu_psize_defs[MMU_PAGE_2M].shift)
+		return __pte(pte_val(entry) | _PAGE_LARGE);
+	else
+		return entry;
+}
 #endif
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 0ebfbc8f0449..5905f0ff57d1 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -26,6 +26,11 @@
 #define _RPAGE_SW1		0x00800
 #define _RPAGE_SW2		0x00400
 #define _RPAGE_SW3		0x00200
+#define _RPAGE_RSV1		0x1000000000000000UL
+#define _RPAGE_RSV2		0x0800000000000000UL
+#define _RPAGE_RSV3		0x0400000000000000UL
+#define _RPAGE_RSV4		0x0200000000000000UL
+
 #ifdef CONFIG_MEM_SOFT_DIRTY
 #define _PAGE_SOFT_DIRTY	_RPAGE_SW3 /* software: software dirty tracking */
 #else
@@ -33,6 +38,11 @@
 #endif
 #define _PAGE_SPECIAL		_RPAGE_SW2 /* software: special page */
 
+/*
+ * For P9 DD1 only, we need to track whether the pte's huge.
+ */
+#define _PAGE_LARGE	_RPAGE_RSV1
+
 
 #define _PAGE_PTE		(1ul << 62)	/* distinguishes PTEs from pointers */
 #define _PAGE_PRESENT		(1ul << 63)	/* pte contains a translation */
@@ -568,10 +578,11 @@ static inline bool check_pte_access(unsigned long access, unsigned long ptev)
  */
 
 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)
 {
 	if (radix_enabled())
-		return radix__ptep_set_access_flags(mm, ptep, entry);
+		return radix__ptep_set_access_flags(mm, ptep, entry, address);
 	return hash__ptep_set_access_flags(ptep, entry);
 }
 
@@ -789,9 +800,6 @@ extern struct page *pgd_page(pgd_t pgd);
 #define pgd_ERROR(e) \
 	pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
 
-void pgtable_cache_add(unsigned shift, void (*ctor)(void *));
-void pgtable_cache_init(void);
-
 static inline int map_kernel_page(unsigned long ea, unsigned long pa,
 				  unsigned long flags)
 {
diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h
index 2a46dea8e1b1..b4d1302387a3 100644
--- a/arch/powerpc/include/asm/book3s/64/radix.h
+++ b/arch/powerpc/include/asm/book3s/64/radix.h
@@ -140,19 +140,20 @@ static inline unsigned long radix__pte_update(struct mm_struct *mm,
 		unsigned long new_pte;
 
 		old_pte = __radix_pte_update(ptep, ~0, 0);
-		asm volatile("ptesync" : : : "memory");
 		/*
 		 * new value of pte
 		 */
 		new_pte = (old_pte | set) & ~clr;
-
 		/*
-		 * For now let's do heavy pid flush
-		 * radix__flush_tlb_page_psize(mm, addr, mmu_virtual_psize);
+		 * If we are trying to clear the pte, we can skip
+		 * the below sequence and batch the tlb flush. The
+		 * tlb flush batching is done by mmu gather code
 		 */
-		radix__flush_tlb_mm(mm);
-
-		__radix_pte_update(ptep, 0, new_pte);
+		if (new_pte) {
+			asm volatile("ptesync" : : : "memory");
+			radix__flush_tlb_pte_p9_dd1(old_pte, mm, addr);
+			__radix_pte_update(ptep, 0, new_pte);
+		}
 	} else
 		old_pte = __radix_pte_update(ptep, clr, set);
 	asm volatile("ptesync" : : : "memory");
@@ -167,7 +168,8 @@ static inline unsigned long radix__pte_update(struct mm_struct *mm,
  * function doesn't need to invalidate tlb.
  */
 static inline void radix__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 |
@@ -183,13 +185,7 @@ static inline void radix__ptep_set_access_flags(struct mm_struct *mm,
 		 * new value of pte
 		 */
 		new_pte = old_pte | set;
-
-		/*
-		 * For now let's do heavy pid flush
-		 * radix__flush_tlb_page_psize(mm, addr, mmu_virtual_psize);
-		 */
-		radix__flush_tlb_mm(mm);
-
+		radix__flush_tlb_pte_p9_dd1(old_pte, mm, address);
 		__radix_pte_update(ptep, 0, new_pte);
 	} else
 		__radix_pte_update(ptep, 0, set);
@@ -243,6 +239,8 @@ static inline int radix__pmd_trans_huge(pmd_t pmd)
 
 static inline pmd_t radix__pmd_mkhuge(pmd_t pmd)
 {
+	if (cpu_has_feature(CPU_FTR_POWER9_DD1))
+		return __pmd(pmd_val(pmd) | _PAGE_PTE | _PAGE_LARGE);
 	return __pmd(pmd_val(pmd) | _PAGE_PTE);
 }
 static inline void radix__pmdp_huge_split_prepare(struct vm_area_struct *vma,
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
index a9e19cb2f7c5..cc7fbde4f53c 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
@@ -42,4 +42,6 @@ extern void radix__flush_tlb_lpid_va(unsigned long lpid, unsigned long gpa,
 				     unsigned long page_size);
 extern void radix__flush_tlb_lpid(unsigned long lpid);
 extern void radix__flush_tlb_all(void);
+extern void radix__flush_tlb_pte_p9_dd1(unsigned long old_pte, struct mm_struct *mm,
+					unsigned long address);
 #endif