Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

Pull powerpc updates from Ben Herrenschmidt:
 "Here is the bulk of the powerpc changes for this merge window.  It got
  a bit delayed in part because I wasn't paying attention, and in part
  because I discovered I had a core PCI change without a PCI maintainer
  ack in it.  Bjorn eventually agreed it was ok to merge it though we'll
  probably improve it later and I didn't want to rebase to add his ack.

  There is going to be a bit more next week, essentially fixes that I
  still want to sort through and test.

  The biggest item this time is the support to build the ppc64 LE kernel
  with our new v2 ABI.  We previously supported v2 userspace but the
  kernel itself was a tougher nut to crack.  This is now sorted mostly
  thanks to Anton and Rusty.

  We also have a fairly big series from Cedric that add support for
  64-bit LE zImage boot wrapper.  This was made harder by the fact that
  traditionally our zImage wrapper was always 32-bit, but our new LE
  toolchains don't really support 32-bit anymore (it's somewhat there
  but not really "supported") so we didn't want to rely on it.  This
  meant more churn that just endian fixes.

  This brings some more LE bits as well, such as the ability to run in
  LE mode without a hypervisor (ie. under OPAL firmware) by doing the
  right OPAL call to reinitialize the CPU to take HV interrupts in the
  right mode and the usual pile of endian fixes.

  There's another series from Gavin adding EEH improvements (one day we
  *will* have a release with less than 20 EEH patches, I promise!).

  Another highlight is the support for the "Split core" functionality on
  P8 by Michael.  This allows a P8 core to be split into "sub cores" of
  4 threads which allows the subcores to run different guests under KVM
  (the HW still doesn't support a partition per thread).

  And then the usual misc bits and fixes ..."

[ Further delayed by gmail deciding that BenH is a dirty spammer.
  Google knows.  ]

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (155 commits)
  powerpc/powernv: Add missing include to LPC code
  selftests/powerpc: Test the THP bug we fixed in the previous commit
  powerpc/mm: Check paca psize is up to date for huge mappings
  powerpc/powernv: Pass buffer size to OPAL validate flash call
  powerpc/pseries: hcall functions are exported to modules, need _GLOBAL_TOC()
  powerpc: Exported functions __clear_user and copy_page use r2 so need _GLOBAL_TOC()
  powerpc/powernv: Set memory_block_size_bytes to 256MB
  powerpc: Allow ppc_md platform hook to override memory_block_size_bytes
  powerpc/powernv: Fix endian issues in memory error handling code
  powerpc/eeh: Skip eeh sysfs when eeh is disabled
  powerpc: 64bit sendfile is capped at 2GB
  powerpc/powernv: Provide debugfs access to the LPC bus via OPAL
  powerpc/serial: Use saner flags when creating legacy ports
  powerpc: Add cpu family documentation
  powerpc/xmon: Fix up xmon format strings
  powerpc/powernv: Add calls to support little endian host
  powerpc: Document sysfs DSCR interface
  powerpc: Fix regression of per-CPU DSCR setting
  powerpc: Split __SYSFS_SPRSETUP macro
  arch: powerpc/fadump: Cleaning up inconsistent NULL checks
  ...

5 files changed, 107 insertions, 62 deletions

diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S
index 1136d26a95ae..057cbbb4c576 100644
--- a/arch/powerpc/mm/hash_low_64.S
+++ b/arch/powerpc/mm/hash_low_64.S
@@ -159,7 +159,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 BEGIN_FTR_SECTION
 	mr	r4,r30
 	mr	r5,r7
-	bl	.hash_page_do_lazy_icache
+	bl	hash_page_do_lazy_icache
 END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE)
 
 	/* At this point, r3 contains new PP bits, save them in
@@ -201,7 +201,8 @@ htab_insert_pte:
 	li	r8,MMU_PAGE_4K		/* page size */
 	li	r9,MMU_PAGE_4K		/* actual page size */
 	ld	r10,STK_PARAM(R9)(r1)	/* segment size */
-_GLOBAL(htab_call_hpte_insert1)
+.globl htab_call_hpte_insert1
+htab_call_hpte_insert1:
 	bl	.			/* Patched by htab_finish_init() */
 	cmpdi	0,r3,0
 	bge	htab_pte_insert_ok	/* Insertion successful */
@@ -225,7 +226,8 @@ _GLOBAL(htab_call_hpte_insert1)
 	li	r8,MMU_PAGE_4K		/* page size */
 	li	r9,MMU_PAGE_4K		/* actual page size */
 	ld	r10,STK_PARAM(R9)(r1)	/* segment size */
-_GLOBAL(htab_call_hpte_insert2)
+.globl htab_call_hpte_insert2
+htab_call_hpte_insert2:
 	bl	.			/* Patched by htab_finish_init() */
 	cmpdi	0,r3,0
 	bge+	htab_pte_insert_ok	/* Insertion successful */
@@ -242,7 +244,8 @@ _GLOBAL(htab_call_hpte_insert2)
 2:	and	r0,r5,r27
 	rldicr	r3,r0,3,63-3	/* r0 = (hash & mask) << 3 */	
 	/* Call ppc_md.hpte_remove */
-_GLOBAL(htab_call_hpte_remove)
+.globl htab_call_hpte_remove
+htab_call_hpte_remove:
 	bl	.			/* Patched by htab_finish_init() */
 
 	/* Try all again */
@@ -296,7 +299,8 @@ htab_modify_pte:
 	li	r7,MMU_PAGE_4K		/* actual page size */
 	ld	r8,STK_PARAM(R9)(r1)	/* segment size */
 	ld	r9,STK_PARAM(R8)(r1)	/* get "local" param */
-_GLOBAL(htab_call_hpte_updatepp)
+.globl htab_call_hpte_updatepp
+htab_call_hpte_updatepp:
 	bl	.			/* Patched by htab_finish_init() */
 
 	/* if we failed because typically the HPTE wasn't really here
@@ -471,7 +475,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 BEGIN_FTR_SECTION
 	mr	r4,r30
 	mr	r5,r7
-	bl	.hash_page_do_lazy_icache
+	bl	hash_page_do_lazy_icache
 END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE)
 
 	/* At this point, r3 contains new PP bits, save them in
@@ -526,7 +530,8 @@ htab_special_pfn:
 	li	r8,MMU_PAGE_4K		/* page size */
 	li	r9,MMU_PAGE_4K		/* actual page size */
 	ld	r10,STK_PARAM(R9)(r1)	/* segment size */
-_GLOBAL(htab_call_hpte_insert1)
+.globl htab_call_hpte_insert1
+htab_call_hpte_insert1:
 	bl	.			/* patched by htab_finish_init() */
 	cmpdi	0,r3,0
 	bge	htab_pte_insert_ok	/* Insertion successful */
@@ -554,7 +559,8 @@ _GLOBAL(htab_call_hpte_insert1)
 	li	r8,MMU_PAGE_4K		/* page size */
 	li	r9,MMU_PAGE_4K		/* actual page size */
 	ld	r10,STK_PARAM(R9)(r1)	/* segment size */
-_GLOBAL(htab_call_hpte_insert2)
+.globl htab_call_hpte_insert2
+htab_call_hpte_insert2:
 	bl	.			/* patched by htab_finish_init() */
 	cmpdi	0,r3,0
 	bge+	htab_pte_insert_ok	/* Insertion successful */
@@ -571,7 +577,8 @@ _GLOBAL(htab_call_hpte_insert2)
 2:	and	r0,r5,r27
 	rldicr	r3,r0,3,63-3		/* r0 = (hash & mask) << 3 */
 	/* Call ppc_md.hpte_remove */
-_GLOBAL(htab_call_hpte_remove)
+.globl htab_call_hpte_remove
+htab_call_hpte_remove:
 	bl	.			/* patched by htab_finish_init() */
 
 	/* Try all again */
@@ -588,7 +595,7 @@ htab_inval_old_hpte:
 	li	r6,MMU_PAGE_64K		/* psize */
 	ld	r7,STK_PARAM(R9)(r1)	/* ssize */
 	ld	r8,STK_PARAM(R8)(r1)	/* local */
-	bl	.flush_hash_page
+	bl	flush_hash_page
 	/* Clear out _PAGE_HPTE_SUB bits in the new linux PTE */
 	lis	r0,_PAGE_HPTE_SUB@h
 	ori	r0,r0,_PAGE_HPTE_SUB@l
@@ -660,7 +667,8 @@ htab_modify_pte:
 	li	r7,MMU_PAGE_4K		/* actual page size */
 	ld	r8,STK_PARAM(R9)(r1)	/* segment size */
 	ld	r9,STK_PARAM(R8)(r1)	/* get "local" param */
-_GLOBAL(htab_call_hpte_updatepp)
+.globl htab_call_hpte_updatepp
+htab_call_hpte_updatepp:
 	bl	.			/* patched by htab_finish_init() */
 
 	/* if we failed because typically the HPTE wasn't really here
@@ -812,7 +820,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 BEGIN_FTR_SECTION
 	mr	r4,r30
 	mr	r5,r7
-	bl	.hash_page_do_lazy_icache
+	bl	hash_page_do_lazy_icache
 END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE)
 
 	/* At this point, r3 contains new PP bits, save them in
@@ -857,7 +865,8 @@ ht64_insert_pte:
 	li	r8,MMU_PAGE_64K
 	li	r9,MMU_PAGE_64K		/* actual page size */
 	ld	r10,STK_PARAM(R9)(r1)	/* segment size */
-_GLOBAL(ht64_call_hpte_insert1)
+.globl ht64_call_hpte_insert1
+ht64_call_hpte_insert1:
 	bl	.			/* patched by htab_finish_init() */
 	cmpdi	0,r3,0
 	bge	ht64_pte_insert_ok	/* Insertion successful */
@@ -881,7 +890,8 @@ _GLOBAL(ht64_call_hpte_insert1)
 	li	r8,MMU_PAGE_64K
 	li	r9,MMU_PAGE_64K		/* actual page size */
 	ld	r10,STK_PARAM(R9)(r1)	/* segment size */
-_GLOBAL(ht64_call_hpte_insert2)
+.globl ht64_call_hpte_insert2
+ht64_call_hpte_insert2:
 	bl	.			/* patched by htab_finish_init() */
 	cmpdi	0,r3,0
 	bge+	ht64_pte_insert_ok	/* Insertion successful */
@@ -898,7 +908,8 @@ _GLOBAL(ht64_call_hpte_insert2)
 2:	and	r0,r5,r27
 	rldicr	r3,r0,3,63-3	/* r0 = (hash & mask) << 3 */
 	/* Call ppc_md.hpte_remove */
-_GLOBAL(ht64_call_hpte_remove)
+.globl ht64_call_hpte_remove
+ht64_call_hpte_remove:
 	bl	.			/* patched by htab_finish_init() */
 
 	/* Try all again */
@@ -952,7 +963,8 @@ ht64_modify_pte:
 	li	r7,MMU_PAGE_64K		/* actual page size */
 	ld	r8,STK_PARAM(R9)(r1)	/* segment size */
 	ld	r9,STK_PARAM(R8)(r1)	/* get "local" param */
-_GLOBAL(ht64_call_hpte_updatepp)
+.globl ht64_call_hpte_updatepp
+ht64_call_hpte_updatepp:
 	bl	.			/* patched by htab_finish_init() */
 
 	/* if we failed because typically the HPTE wasn't really here
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 350aa58a6f95..88fdd9d25077 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -449,6 +449,24 @@ static void mmu_psize_set_default_penc(void)
 			mmu_psize_defs[bpsize].penc[apsize] = -1;
 }
 
+#ifdef CONFIG_PPC_64K_PAGES
+
+static bool might_have_hea(void)
+{
+	/*
+	 * The HEA ethernet adapter requires awareness of the
+	 * GX bus. Without that awareness we can easily assume
+	 * we will never see an HEA ethernet device.
+	 */
+#ifdef CONFIG_IBMEBUS
+	return !cpu_has_feature(CPU_FTR_ARCH_207S);
+#else
+	return false;
+#endif
+}
+
+#endif /* #ifdef CONFIG_PPC_64K_PAGES */
+
 static void __init htab_init_page_sizes(void)
 {
 	int rc;
@@ -503,10 +521,11 @@ static void __init htab_init_page_sizes(void)
 			mmu_linear_psize = MMU_PAGE_64K;
 		if (mmu_has_feature(MMU_FTR_CI_LARGE_PAGE)) {
 			/*
-			 * Don't use 64k pages for ioremap on pSeries, since
-			 * that would stop us accessing the HEA ethernet.
+			 * When running on pSeries using 64k pages for ioremap
+			 * would stop us accessing the HEA ethernet. So if we
+			 * have the chance of ever seeing one, stay at 4k.
 			 */
-			if (!machine_is(pseries))
+			if (!might_have_hea() || !machine_is(pseries))
 				mmu_io_psize = MMU_PAGE_64K;
 		} else
 			mmu_ci_restrictions = 1;
@@ -607,47 +626,43 @@ int remove_section_mapping(unsigned long start, unsigned long end)
 }
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
-#define FUNCTION_TEXT(A)	((*(unsigned long *)(A)))
+extern u32 htab_call_hpte_insert1[];
+extern u32 htab_call_hpte_insert2[];
+extern u32 htab_call_hpte_remove[];
+extern u32 htab_call_hpte_updatepp[];
+extern u32 ht64_call_hpte_insert1[];
+extern u32 ht64_call_hpte_insert2[];
+extern u32 ht64_call_hpte_remove[];
+extern u32 ht64_call_hpte_updatepp[];
 
 static void __init htab_finish_init(void)
 {
-	extern unsigned int *htab_call_hpte_insert1;
-	extern unsigned int *htab_call_hpte_insert2;
-	extern unsigned int *htab_call_hpte_remove;
-	extern unsigned int *htab_call_hpte_updatepp;
-
 #ifdef CONFIG_PPC_HAS_HASH_64K
-	extern unsigned int *ht64_call_hpte_insert1;
-	extern unsigned int *ht64_call_hpte_insert2;
-	extern unsigned int *ht64_call_hpte_remove;
-	extern unsigned int *ht64_call_hpte_updatepp;
-
 	patch_branch(ht64_call_hpte_insert1,
-		FUNCTION_TEXT(ppc_md.hpte_insert),
+		ppc_function_entry(ppc_md.hpte_insert),
 		BRANCH_SET_LINK);
 	patch_branch(ht64_call_hpte_insert2,
-		FUNCTION_TEXT(ppc_md.hpte_insert),
+		ppc_function_entry(ppc_md.hpte_insert),
 		BRANCH_SET_LINK);
 	patch_branch(ht64_call_hpte_remove,
-		FUNCTION_TEXT(ppc_md.hpte_remove),
+		ppc_function_entry(ppc_md.hpte_remove),
 		BRANCH_SET_LINK);
 	patch_branch(ht64_call_hpte_updatepp,
-		FUNCTION_TEXT(ppc_md.hpte_updatepp),
+		ppc_function_entry(ppc_md.hpte_updatepp),
 		BRANCH_SET_LINK);
-
 #endif /* CONFIG_PPC_HAS_HASH_64K */
 
 	patch_branch(htab_call_hpte_insert1,
-		FUNCTION_TEXT(ppc_md.hpte_insert),
+		ppc_function_entry(ppc_md.hpte_insert),
 		BRANCH_SET_LINK);
 	patch_branch(htab_call_hpte_insert2,
-		FUNCTION_TEXT(ppc_md.hpte_insert),
+		ppc_function_entry(ppc_md.hpte_insert),
 		BRANCH_SET_LINK);
 	patch_branch(htab_call_hpte_remove,
-		FUNCTION_TEXT(ppc_md.hpte_remove),
+		ppc_function_entry(ppc_md.hpte_remove),
 		BRANCH_SET_LINK);
 	patch_branch(htab_call_hpte_updatepp,
-		FUNCTION_TEXT(ppc_md.hpte_updatepp),
+		ppc_function_entry(ppc_md.hpte_updatepp),
 		BRANCH_SET_LINK);
 }
 
@@ -964,6 +979,22 @@ void hash_failure_debug(unsigned long ea, unsigned long access,
 		trap, vsid, ssize, psize, lpsize, pte);
 }
 
+static void check_paca_psize(unsigned long ea, struct mm_struct *mm,
+			     int psize, bool user_region)
+{
+	if (user_region) {
+		if (psize != get_paca_psize(ea)) {
+			get_paca()->context = mm->context;
+			slb_flush_and_rebolt();
+		}
+	} else if (get_paca()->vmalloc_sllp !=
+		   mmu_psize_defs[mmu_vmalloc_psize].sllp) {
+		get_paca()->vmalloc_sllp =
+			mmu_psize_defs[mmu_vmalloc_psize].sllp;
+		slb_vmalloc_update();
+	}
+}
+
 /* Result code is:
  *  0 - handled
  *  1 - normal page fault
@@ -1085,6 +1116,8 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 			WARN_ON(1);
 		}
 #endif
+		check_paca_psize(ea, mm, psize, user_region);
+
 		goto bail;
 	}
 
@@ -1125,17 +1158,8 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 #endif
 		}
 	}
-	if (user_region) {
-		if (psize != get_paca_psize(ea)) {
-			get_paca()->context = mm->context;
-			slb_flush_and_rebolt();
-		}
-	} else if (get_paca()->vmalloc_sllp !=
-		   mmu_psize_defs[mmu_vmalloc_psize].sllp) {
-		get_paca()->vmalloc_sllp =
-			mmu_psize_defs[mmu_vmalloc_psize].sllp;
-		slb_vmalloc_update();
-	}
+
+	check_paca_psize(ea, mm, psize, user_region);
 #endif /* CONFIG_PPC_64K_PAGES */
 
 #ifdef CONFIG_PPC_HAS_HASH_64K
diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c
index 964a5f61488a..0399a6702958 100644
--- a/arch/powerpc/mm/slb.c
+++ b/arch/powerpc/mm/slb.c
@@ -256,10 +256,14 @@ static inline void patch_slb_encoding(unsigned int *insn_addr,
 	patch_instruction(insn_addr, insn);
 }
 
+extern u32 slb_compare_rr_to_size[];
+extern u32 slb_miss_kernel_load_linear[];
+extern u32 slb_miss_kernel_load_io[];
+extern u32 slb_compare_rr_to_size[];
+extern u32 slb_miss_kernel_load_vmemmap[];
+
 void slb_set_size(u16 size)
 {
-	extern unsigned int *slb_compare_rr_to_size;
-
 	if (mmu_slb_size == size)
 		return;
 
@@ -272,11 +276,7 @@ void slb_initialize(void)
 	unsigned long linear_llp, vmalloc_llp, io_llp;
 	unsigned long lflags, vflags;
 	static int slb_encoding_inited;
-	extern unsigned int *slb_miss_kernel_load_linear;
-	extern unsigned int *slb_miss_kernel_load_io;
-	extern unsigned int *slb_compare_rr_to_size;
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
-	extern unsigned int *slb_miss_kernel_load_vmemmap;
 	unsigned long vmemmap_llp;
 #endif
 
diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S
index 17aa6dfceb34..736d18b3cefd 100644
--- a/arch/powerpc/mm/slb_low.S
+++ b/arch/powerpc/mm/slb_low.S
@@ -35,7 +35,7 @@ _GLOBAL(slb_allocate_realmode)
 	 * check for bad kernel/user address
 	 * (ea & ~REGION_MASK) >= PGTABLE_RANGE
 	 */
-	rldicr. r9,r3,4,(63 - 46 - 4)
+	rldicr. r9,r3,4,(63 - PGTABLE_EADDR_SIZE - 4)
 	bne-	8f
 
 	srdi	r9,r3,60		/* get region */
@@ -59,7 +59,8 @@ _GLOBAL(slb_allocate_realmode)
 	/* Linear mapping encoding bits, the "li" instruction below will
 	 * be patched by the kernel at boot
 	 */
-_GLOBAL(slb_miss_kernel_load_linear)
+.globl slb_miss_kernel_load_linear
+slb_miss_kernel_load_linear:
 	li	r11,0
 	/*
 	 * context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1
@@ -79,7 +80,8 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT)
 	/* Check virtual memmap region. To be patches at kernel boot */
 	cmpldi	cr0,r9,0xf
 	bne	1f
-_GLOBAL(slb_miss_kernel_load_vmemmap)
+.globl slb_miss_kernel_load_vmemmap
+slb_miss_kernel_load_vmemmap:
 	li	r11,0
 	b	6f
 1:
@@ -95,7 +97,8 @@ _GLOBAL(slb_miss_kernel_load_vmemmap)
 	b	6f
 5:
 	/* IO mapping */
-	_GLOBAL(slb_miss_kernel_load_io)
+.globl slb_miss_kernel_load_io
+slb_miss_kernel_load_io:
 	li	r11,0
 6:
 	/*
@@ -250,7 +253,8 @@ slb_finish_load:
 7:	ld	r10,PACASTABRR(r13)
 	addi	r10,r10,1
 	/* This gets soft patched on boot. */
-_GLOBAL(slb_compare_rr_to_size)
+.globl slb_compare_rr_to_size
+slb_compare_rr_to_size:
 	cmpldi	r10,0
 
 	blt+	4f
diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c
index ae3d5b799b90..92cb18d52ea8 100644
--- a/arch/powerpc/mm/tlb_nohash.c
+++ b/arch/powerpc/mm/tlb_nohash.c
@@ -596,8 +596,13 @@ static void __early_init_mmu(int boot_cpu)
 	/* XXX This should be decided at runtime based on supported
 	 * page sizes in the TLB, but for now let's assume 16M is
 	 * always there and a good fit (which it probably is)
+	 *
+	 * Freescale booke only supports 4K pages in TLB0, so use that.
 	 */
-	mmu_vmemmap_psize = MMU_PAGE_16M;
+	if (mmu_has_feature(MMU_FTR_TYPE_FSL_E))
+		mmu_vmemmap_psize = MMU_PAGE_4K;
+	else
+		mmu_vmemmap_psize = MMU_PAGE_16M;
 
 	/* XXX This code only checks for TLB 0 capabilities and doesn't
 	 *     check what page size combos are supported by the HW. It