Merge branch 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm

Pull ARM updates from Russell King:
 "Included in this update:

   - perf updates from Will Deacon:

     The main changes are callchain stability fixes from Jean Pihet and
     event mapping and PMU name rework from Mark Rutland

     The latter is preparatory work for enabling some code re-use with
     arm64 in the future.

   - updates for nommu from Uwe Kleine-König:

     Two different fixes for the same problem making some ARM nommu
     configurations not boot since 3.6-rc1.  The problem is that
     user_addr_max returned the biggest available RAM address which
     makes some copy_from_user variants fail to read from XIP memory.

   - deprecate legacy OMAP DMA API, in preparation for it's removal.

     The popular drivers have been converted over, leaving a very small
     number of rarely used drivers, which hopefully can be converted
     during the next cycle with a bit more visibility (and hopefully
     people popping out of the woodwork to help test)

   - more tweaks for BE systems, particularly with the kernel image
     format.  In connection with this, I've cleaned up the way we
     generate the linker script for the decompressor.

   - removal of hard-coded assumptions of the kernel stack size, making
     everywhere depend on the value of THREAD_SIZE_ORDER.

   - MCPM updates from Nicolas Pitre.

   - Make it easier for proper CPU part number checks (which should
     always include the vendor field).

   - Assembly code optimisation - use the "bx" instruction when
     returning from a function on ARMv6+ rather than "mov pc, reg".

   - Save the last kernel misaligned fault location and report it via
     the procfs alignment file.

   - Clean up the way we create the initial stack frame, which is a
     repeated pattern in several different locations.

   - Support for 8-byte get_user(), needed for some DRM implementations.

   - mcs locking from Will Deacon.

   - Save and restore a few more Cortex-A9 registers (for errata
     workarounds)

   - Fix various aspects of the SWP emulation, and the ELF hwcap for the
     SWP instruction.

   - Update LPAE logic for pte_write and pmd_write to make it more
     correct.

   - Support for Broadcom Brahma15 CPU cores.

   - ARM assembly crypto updates from Ard Biesheuvel"

* 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm: (53 commits)
  ARM: add comments to the early page table remap code
  ARM: 8122/1: smp_scu: enable SCU standby support
  ARM: 8121/1: smp_scu: use macro for SCU enable bit
  ARM: 8120/1: crypto: sha512: add ARM NEON implementation
  ARM: 8119/1: crypto: sha1: add ARM NEON implementation
  ARM: 8118/1: crypto: sha1/make use of common SHA-1 structures
  ARM: 8113/1: remove remaining definitions of PLAT_PHYS_OFFSET from <mach/memory.h>
  ARM: 8111/1: Enable erratum 798181 for Broadcom Brahma-B15
  ARM: 8110/1: do CPU-specific init for Broadcom Brahma15 cores
  ARM: 8109/1: mm: Modify pte_write and pmd_write logic for LPAE
  ARM: 8108/1: mm: Introduce {pte,pmd}_isset and {pte,pmd}_isclear
  ARM: hwcap: disable HWCAP_SWP if the CPU advertises it has exclusives
  ARM: SWP emulation: only initialise on ARMv7 CPUs
  ARM: SWP emulation: always enable when SMP is enabled
  ARM: 8103/1: save/restore Cortex-A9 CP15 registers on suspend/resume
  ARM: 8098/1: mcs lock: implement wfe-based polling for MCS locking
  ARM: 8091/2: add get_user() support for 8 byte types
  ARM: 8097/1: unistd.h: relocate comments back to place
  ARM: 8096/1: Describe required sort order for textofs-y (TEXT_OFFSET)
  ARM: 8090/1: add revision info for PL310 errata 588369 and 727915
  ...

1 files changed, 30 insertions, 19 deletions

diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index 85c60adc8b60..06e0bc0f8b00 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -79,18 +79,19 @@
 #define L_PTE_PRESENT		(_AT(pteval_t, 3) << 0)		/* Present */
 #define L_PTE_FILE		(_AT(pteval_t, 1) << 2)		/* only when !PRESENT */
 #define L_PTE_USER		(_AT(pteval_t, 1) << 6)		/* AP[1] */
-#define L_PTE_RDONLY		(_AT(pteval_t, 1) << 7)		/* AP[2] */
 #define L_PTE_SHARED		(_AT(pteval_t, 3) << 8)		/* SH[1:0], inner shareable */
 #define L_PTE_YOUNG		(_AT(pteval_t, 1) << 10)	/* AF */
 #define L_PTE_XN		(_AT(pteval_t, 1) << 54)	/* XN */
-#define L_PTE_DIRTY		(_AT(pteval_t, 1) << 55)	/* unused */
-#define L_PTE_SPECIAL		(_AT(pteval_t, 1) << 56)	/* unused */
+#define L_PTE_DIRTY		(_AT(pteval_t, 1) << 55)
+#define L_PTE_SPECIAL		(_AT(pteval_t, 1) << 56)
 #define L_PTE_NONE		(_AT(pteval_t, 1) << 57)	/* PROT_NONE */
+#define L_PTE_RDONLY		(_AT(pteval_t, 1) << 58)	/* READ ONLY */
 
-#define PMD_SECT_VALID		(_AT(pmdval_t, 1) << 0)
-#define PMD_SECT_DIRTY		(_AT(pmdval_t, 1) << 55)
-#define PMD_SECT_SPLITTING	(_AT(pmdval_t, 1) << 56)
-#define PMD_SECT_NONE		(_AT(pmdval_t, 1) << 57)
+#define L_PMD_SECT_VALID	(_AT(pmdval_t, 1) << 0)
+#define L_PMD_SECT_DIRTY	(_AT(pmdval_t, 1) << 55)
+#define L_PMD_SECT_SPLITTING	(_AT(pmdval_t, 1) << 56)
+#define L_PMD_SECT_NONE		(_AT(pmdval_t, 1) << 57)
+#define L_PMD_SECT_RDONLY	(_AT(pteval_t, 1) << 58)
 
 /*
  * To be used in assembly code with the upper page attributes.
@@ -207,27 +208,32 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 #define pte_huge(pte)		(pte_val(pte) && !(pte_val(pte) & PTE_TABLE_BIT))
 #define pte_mkhuge(pte)		(__pte(pte_val(pte) & ~PTE_TABLE_BIT))
 
-#define pmd_young(pmd)		(pmd_val(pmd) & PMD_SECT_AF)
+#define pmd_isset(pmd, val)	((u32)(val) == (val) ? pmd_val(pmd) & (val) \
+						: !!(pmd_val(pmd) & (val)))
+#define pmd_isclear(pmd, val)	(!(pmd_val(pmd) & (val)))
+
+#define pmd_young(pmd)		(pmd_isset((pmd), PMD_SECT_AF))
 
 #define __HAVE_ARCH_PMD_WRITE
-#define pmd_write(pmd)		(!(pmd_val(pmd) & PMD_SECT_RDONLY))
+#define pmd_write(pmd)		(pmd_isclear((pmd), L_PMD_SECT_RDONLY))
+#define pmd_dirty(pmd)		(pmd_isset((pmd), L_PMD_SECT_DIRTY))
 
 #define pmd_hugewillfault(pmd)	(!pmd_young(pmd) || !pmd_write(pmd))
 #define pmd_thp_or_huge(pmd)	(pmd_huge(pmd) || pmd_trans_huge(pmd))
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-#define pmd_trans_huge(pmd)	(pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT))
-#define pmd_trans_splitting(pmd) (pmd_val(pmd) & PMD_SECT_SPLITTING)
+#define pmd_trans_huge(pmd)	(pmd_val(pmd) && !pmd_table(pmd))
+#define pmd_trans_splitting(pmd) (pmd_isset((pmd), L_PMD_SECT_SPLITTING))
 #endif
 
 #define PMD_BIT_FUNC(fn,op) \
 static inline pmd_t pmd_##fn(pmd_t pmd) { pmd_val(pmd) op; return pmd; }
 
-PMD_BIT_FUNC(wrprotect,	|= PMD_SECT_RDONLY);
+PMD_BIT_FUNC(wrprotect,	|= L_PMD_SECT_RDONLY);
 PMD_BIT_FUNC(mkold,	&= ~PMD_SECT_AF);
-PMD_BIT_FUNC(mksplitting, |= PMD_SECT_SPLITTING);
-PMD_BIT_FUNC(mkwrite,   &= ~PMD_SECT_RDONLY);
-PMD_BIT_FUNC(mkdirty,   |= PMD_SECT_DIRTY);
+PMD_BIT_FUNC(mksplitting, |= L_PMD_SECT_SPLITTING);
+PMD_BIT_FUNC(mkwrite,   &= ~L_PMD_SECT_RDONLY);
+PMD_BIT_FUNC(mkdirty,   |= L_PMD_SECT_DIRTY);
 PMD_BIT_FUNC(mkyoung,   |= PMD_SECT_AF);
 
 #define pmd_mkhuge(pmd)		(__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT))
@@ -241,8 +247,8 @@ PMD_BIT_FUNC(mkyoung,   |= PMD_SECT_AF);
 
 static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 {
-	const pmdval_t mask = PMD_SECT_USER | PMD_SECT_XN | PMD_SECT_RDONLY |
-				PMD_SECT_VALID | PMD_SECT_NONE;
+	const pmdval_t mask = PMD_SECT_USER | PMD_SECT_XN | L_PMD_SECT_RDONLY |
+				L_PMD_SECT_VALID | L_PMD_SECT_NONE;
 	pmd_val(pmd) = (pmd_val(pmd) & ~mask) | (pgprot_val(newprot) & mask);
 	return pmd;
 }
@@ -253,8 +259,13 @@ static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 	BUG_ON(addr >= TASK_SIZE);
 
 	/* create a faulting entry if PROT_NONE protected */
-	if (pmd_val(pmd) & PMD_SECT_NONE)
-		pmd_val(pmd) &= ~PMD_SECT_VALID;
+	if (pmd_val(pmd) & L_PMD_SECT_NONE)
+		pmd_val(pmd) &= ~L_PMD_SECT_VALID;
+
+	if (pmd_write(pmd) && pmd_dirty(pmd))
+		pmd_val(pmd) &= ~PMD_SECT_AP2;
+	else
+		pmd_val(pmd) |= PMD_SECT_AP2;
 
 	*pmdp = __pmd(pmd_val(pmd) | PMD_SECT_nG);
 	flush_pmd_entry(pmdp);