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

* 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc:
  vmlinux.lds: fix .data..init_task output section (fix popwerpc boot)
  powerpc: Fix erroneous lmb->memblock conversions
  powerpc/mm: Add some debug output when hash insertion fails
  powerpc/mm: Fix bugs in huge page hashing
  powerpc/mm: Move around testing of _PAGE_PRESENT in hash code
  powerpc/mm: Handle hypervisor pte insert failure in __hash_page_huge
  powerpc/kexec: Fix boundary case for book-e kexec memory limits

arch/powerpc/include/asm/kexec.h

@@ -8,9 +8,9 @@
  * On FSL-BookE we setup a 1:1 mapping which covers the first 2GiB of memory
  * and therefore we can only deal with memory within this range
  */
-#define KEXEC_SOURCE_MEMORY_LIMIT	(2 * 1024 * 1024 * 1024UL)
+#define KEXEC_SOURCE_MEMORY_LIMIT	(2 * 1024 * 1024 * 1024UL - 1)
-#define KEXEC_DESTINATION_MEMORY_LIMIT	(2 * 1024 * 1024 * 1024UL)
+#define KEXEC_DESTINATION_MEMORY_LIMIT	(2 * 1024 * 1024 * 1024UL - 1)
-#define KEXEC_CONTROL_MEMORY_LIMIT	(2 * 1024 * 1024 * 1024UL)
+#define KEXEC_CONTROL_MEMORY_LIMIT	(2 * 1024 * 1024 * 1024UL - 1)
 
 #else
 

arch/powerpc/include/asm/mmu-hash64.h

@@ -250,7 +250,9 @@ extern int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 		     pte_t *ptep, unsigned long trap, int local, int ssize,
 		     unsigned int shift, unsigned int mmu_psize);
-
+extern void hash_failure_debug(unsigned long ea, unsigned long access,
+			       unsigned long vsid, unsigned long trap,
+			       int ssize, int psize, unsigned long pte);
 extern int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
 			     unsigned long pstart, unsigned long prot,
 			     int psize, int ssize);

arch/powerpc/kernel/prom.c

@@ -414,7 +414,7 @@ static int __init early_init_dt_scan_drconf_memory(unsigned long node)
 	u64 base, size, memblock_size;
 	unsigned int is_kexec_kdump = 0, rngs;
 
-	ls = of_get_flat_dt_prop(node, "ibm,memblock-size", &l);
+	ls = of_get_flat_dt_prop(node, "ibm,lmb-size", &l);
 	if (ls == NULL || l < dt_root_size_cells * sizeof(__be32))
 		return 0;
 	memblock_size = dt_mem_next_cell(dt_root_size_cells, &ls);

arch/powerpc/mm/hash_low_64.S

@@ -68,9 +68,6 @@ _GLOBAL(__hash_page_4K)
 	std	r8,STK_PARM(r8)(r1)
 	std	r9,STK_PARM(r9)(r1)
 	
-	/* Add _PAGE_PRESENT to access */
-	ori	r4,r4,_PAGE_PRESENT
-
 	/* Save non-volatile registers.
 	 * r31 will hold "old PTE"
 	 * r30 is "new PTE"
@@ -347,9 +344,6 @@ _GLOBAL(__hash_page_4K)
 	std	r8,STK_PARM(r8)(r1)
 	std	r9,STK_PARM(r9)(r1)
 
-	/* Add _PAGE_PRESENT to access */
-	ori	r4,r4,_PAGE_PRESENT
-
 	/* Save non-volatile registers.
 	 * r31 will hold "old PTE"
 	 * r30 is "new PTE"
@@ -687,9 +681,6 @@ _GLOBAL(__hash_page_64K)
 	std	r8,STK_PARM(r8)(r1)
 	std	r9,STK_PARM(r9)(r1)
 
-	/* Add _PAGE_PRESENT to access */
-	ori	r4,r4,_PAGE_PRESENT
-
 	/* Save non-volatile registers.
 	 * r31 will hold "old PTE"
 	 * r30 is "new PTE"

arch/powerpc/mm/hash_utils_64.c

@@ -871,6 +871,18 @@ static inline int subpage_protection(struct mm_struct *mm, unsigned long ea)
 }
 #endif
 
+void hash_failure_debug(unsigned long ea, unsigned long access,
+			unsigned long vsid, unsigned long trap,
+			int ssize, int psize, unsigned long pte)
+{
+	if (!printk_ratelimit())
+		return;
+	pr_info("mm: Hashing failure ! EA=0x%lx access=0x%lx current=%s\n",
+		ea, access, current->comm);
+	pr_info("    trap=0x%lx vsid=0x%lx ssize=%d psize=%d pte=0x%lx\n",
+		trap, vsid, ssize, psize, pte);
+}
+
 /* Result code is:
  *  0 - handled
  *  1 - normal page fault
@@ -955,6 +967,17 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 		return 1;
 	}
 
+	/* Add _PAGE_PRESENT to the required access perm */
+	access |= _PAGE_PRESENT;
+
+	/* Pre-check access permissions (will be re-checked atomically
+	 * in __hash_page_XX but this pre-check is a fast path
+	 */
+	if (access & ~pte_val(*ptep)) {
+		DBG_LOW(" no access !\n");
+		return 1;
+	}
+
 #ifdef CONFIG_HUGETLB_PAGE
 	if (hugeshift)
 		return __hash_page_huge(ea, access, vsid, ptep, trap, local,
@@ -967,14 +990,6 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 	DBG_LOW(" i-pte: %016lx %016lx\n", pte_val(*ptep),
 		pte_val(*(ptep + PTRS_PER_PTE)));
 #endif
-	/* Pre-check access permissions (will be re-checked atomically
-	 * in __hash_page_XX but this pre-check is a fast path
-	 */
-	if (access & ~pte_val(*ptep)) {
-		DBG_LOW(" no access !\n");
-		return 1;
-	}
-
 	/* Do actual hashing */
 #ifdef CONFIG_PPC_64K_PAGES
 	/* If _PAGE_4K_PFN is set, make sure this is a 4k segment */
@@ -1033,6 +1048,12 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 					    local, ssize, spp);
 	}
 
+	/* Dump some info in case of hash insertion failure, they should
+	 * never happen so it is really useful to know if/when they do
+	 */
+	if (rc == -1)
+		hash_failure_debug(ea, access, vsid, trap, ssize, psize,
+				   pte_val(*ptep));
 #ifndef CONFIG_PPC_64K_PAGES
 	DBG_LOW(" o-pte: %016lx\n", pte_val(*ptep));
 #else
@@ -1051,8 +1072,7 @@ void hash_preload(struct mm_struct *mm, unsigned long ea,
 	void *pgdir;
 	pte_t *ptep;
 	unsigned long flags;
-	int local = 0;
+	int rc, ssize, local = 0;
-	int ssize;
 
 	BUG_ON(REGION_ID(ea) != USER_REGION_ID);
 
@@ -1098,11 +1118,18 @@ void hash_preload(struct mm_struct *mm, unsigned long ea,
 	/* Hash it in */
 #ifdef CONFIG_PPC_HAS_HASH_64K
 	if (mm->context.user_psize == MMU_PAGE_64K)
-		__hash_page_64K(ea, access, vsid, ptep, trap, local, ssize);
+		rc = __hash_page_64K(ea, access, vsid, ptep, trap, local, ssize);
 	else
 #endif /* CONFIG_PPC_HAS_HASH_64K */
-		__hash_page_4K(ea, access, vsid, ptep, trap, local, ssize,
+		rc = __hash_page_4K(ea, access, vsid, ptep, trap, local, ssize,
-			       subpage_protection(pgdir, ea));
+				    subpage_protection(pgdir, ea));
+
+	/* Dump some info in case of hash insertion failure, they should
+	 * never happen so it is really useful to know if/when they do
+	 */
+	if (rc == -1)
+		hash_failure_debug(ea, access, vsid, trap, ssize,
+				   mm->context.user_psize, pte_val(*ptep));
 
 	local_irq_restore(flags);
 }

arch/powerpc/mm/hugetlbpage-hash64.c

@@ -21,21 +21,13 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 	unsigned long old_pte, new_pte;
 	unsigned long va, rflags, pa, sz;
 	long slot;
-	int err = 1;
 
 	BUG_ON(shift != mmu_psize_defs[mmu_psize].shift);
 
 	/* Search the Linux page table for a match with va */
 	va = hpt_va(ea, vsid, ssize);
 
-	/*
+	/* At this point, we have a pte (old_pte) which can be used to build
-	 * Check the user's access rights to the page.  If access should be
-	 * prevented then send the problem up to do_page_fault.
-	 */
-	if (unlikely(access & ~pte_val(*ptep)))
-		goto out;
-	/*
-	 * At this point, we have a pte (old_pte) which can be used to build
 	 * or update an HPTE. There are 2 cases:
 	 *
 	 * 1. There is a valid (present) pte with no associated HPTE (this is
@@ -49,9 +41,17 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 
 	do {
 		old_pte = pte_val(*ptep);
-		if (old_pte & _PAGE_BUSY)
+		/* If PTE busy, retry the access */
-			goto out;
+		if (unlikely(old_pte & _PAGE_BUSY))
+			return 0;
+		/* If PTE permissions don't match, take page fault */
+		if (unlikely(access & ~old_pte))
+			return 1;
+		/* Try to lock the PTE, add ACCESSED and DIRTY if it was
+		 * a write access */
 		new_pte = old_pte | _PAGE_BUSY | _PAGE_ACCESSED;
+		if (access & _PAGE_RW)
+			new_pte |= _PAGE_DIRTY;
 	} while(old_pte != __cmpxchg_u64((unsigned long *)ptep,
 					 old_pte, new_pte));
 
@@ -121,8 +121,16 @@ repeat:
                         }
 		}
 
-		if (unlikely(slot == -2))
+		/*
-			panic("hash_huge_page: pte_insert failed\n");
+		 * Hypervisor failure. Restore old pte and return -1
+		 * similar to __hash_page_*
+		 */
+		if (unlikely(slot == -2)) {
+			*ptep = __pte(old_pte);
+			hash_failure_debug(ea, access, vsid, trap, ssize,
+					   mmu_psize, old_pte);
+			return -1;
+		}
 
 		new_pte |= (slot << 12) & (_PAGE_F_SECOND | _PAGE_F_GIX);
 	}
@@ -131,9 +139,5 @@ repeat:
 	 * No need to use ldarx/stdcx here
 	 */
 	*ptep = __pte(new_pte & ~_PAGE_BUSY);
-
+	return 0;
-	err = 0;
-
- out:
-	return err;
 }

arch/powerpc/mm/numa.c

@@ -398,15 +398,15 @@ static int of_get_drconf_memory(struct device_node *memory, const u32 **dm)
 }
 
 /*
- * Retreive and validate the ibm,memblock-size property for drconf memory
+ * Retreive and validate the ibm,lmb-size property for drconf memory
  * from the device tree.
  */
-static u64 of_get_memblock_size(struct device_node *memory)
+static u64 of_get_lmb_size(struct device_node *memory)
 {
 	const u32 *prop;
 	u32 len;
 
-	prop = of_get_property(memory, "ibm,memblock-size", &len);
+	prop = of_get_property(memory, "ibm,lmb-size", &len);
 	if (!prop || len < sizeof(unsigned int))
 		return 0;
 
@@ -562,7 +562,7 @@ static unsigned long __init numa_enforce_memory_limit(unsigned long start,
 static inline int __init read_usm_ranges(const u32 **usm)
 {
 	/*
-	 * For each memblock in ibm,dynamic-memory a corresponding
+	 * For each lmb in ibm,dynamic-memory a corresponding
 	 * entry in linux,drconf-usable-memory property contains
 	 * a counter followed by that many (base, size) duple.
 	 * read the counter from linux,drconf-usable-memory
@@ -578,7 +578,7 @@ static void __init parse_drconf_memory(struct device_node *memory)
 {
 	const u32 *dm, *usm;
 	unsigned int n, rc, ranges, is_kexec_kdump = 0;
-	unsigned long memblock_size, base, size, sz;
+	unsigned long lmb_size, base, size, sz;
 	int nid;
 	struct assoc_arrays aa;
 
@@ -586,8 +586,8 @@ static void __init parse_drconf_memory(struct device_node *memory)
 	if (!n)
 		return;
 
-	memblock_size = of_get_memblock_size(memory);
+	lmb_size = of_get_lmb_size(memory);
-	if (!memblock_size)
+	if (!lmb_size)
 		return;
 
 	rc = of_get_assoc_arrays(memory, &aa);
@@ -611,7 +611,7 @@ static void __init parse_drconf_memory(struct device_node *memory)
 			continue;
 
 		base = drmem.base_addr;
-		size = memblock_size;
+		size = lmb_size;
 		ranges = 1;
 
 		if (is_kexec_kdump) {
@@ -1072,7 +1072,7 @@ static int hot_add_drconf_scn_to_nid(struct device_node *memory,
 {
 	const u32 *dm;
 	unsigned int drconf_cell_cnt, rc;
-	unsigned long memblock_size;
+	unsigned long lmb_size;
 	struct assoc_arrays aa;
 	int nid = -1;
 
@@ -1080,8 +1080,8 @@ static int hot_add_drconf_scn_to_nid(struct device_node *memory,
 	if (!drconf_cell_cnt)
 		return -1;
 
-	memblock_size = of_get_memblock_size(memory);
+	lmb_size = of_get_lmb_size(memory);
-	if (!memblock_size)
+	if (!lmb_size)
 		return -1;
 
 	rc = of_get_assoc_arrays(memory, &aa);
@@ -1100,7 +1100,7 @@ static int hot_add_drconf_scn_to_nid(struct device_node *memory,
 			continue;
 
 		if ((scn_addr < drmem.base_addr)
-		    || (scn_addr >= (drmem.base_addr + memblock_size)))
+		    || (scn_addr >= (drmem.base_addr + lmb_size)))
 			continue;
 
 		nid = of_drconf_to_nid_single(&drmem, &aa);

arch/powerpc/platforms/pseries/hotplug-memory.c

@@ -69,7 +69,7 @@ static int pseries_remove_memory(struct device_node *np)
 	const char *type;
 	const unsigned int *regs;
 	unsigned long base;
-	unsigned int memblock_size;
+	unsigned int lmb_size;
 	int ret = -EINVAL;
 
 	/*
@@ -87,9 +87,9 @@ static int pseries_remove_memory(struct device_node *np)
 		return ret;
 
 	base = *(unsigned long *)regs;
-	memblock_size = regs[3];
+	lmb_size = regs[3];
 
-	ret = pseries_remove_memblock(base, memblock_size);
+	ret = pseries_remove_memblock(base, lmb_size);
 	return ret;
 }
 
@@ -98,7 +98,7 @@ static int pseries_add_memory(struct device_node *np)
 	const char *type;
 	const unsigned int *regs;
 	unsigned long base;
-	unsigned int memblock_size;
+	unsigned int lmb_size;
 	int ret = -EINVAL;
 
 	/*
@@ -116,36 +116,36 @@ static int pseries_add_memory(struct device_node *np)
 		return ret;
 
 	base = *(unsigned long *)regs;
-	memblock_size = regs[3];
+	lmb_size = regs[3];
 
 	/*
 	 * Update memory region to represent the memory add
 	 */
-	ret = memblock_add(base, memblock_size);
+	ret = memblock_add(base, lmb_size);
 	return (ret < 0) ? -EINVAL : 0;
 }
 
 static int pseries_drconf_memory(unsigned long *base, unsigned int action)
 {
 	struct device_node *np;
-	const unsigned long *memblock_size;
+	const unsigned long *lmb_size;
 	int rc;
 
 	np = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
 	if (!np)
 		return -EINVAL;
 
-	memblock_size = of_get_property(np, "ibm,memblock-size", NULL);
+	lmb_size = of_get_property(np, "ibm,lmb-size", NULL);
-	if (!memblock_size) {
+	if (!lmb_size) {
 		of_node_put(np);
 		return -EINVAL;
 	}
 
 	if (action == PSERIES_DRCONF_MEM_ADD) {
-		rc = memblock_add(*base, *memblock_size);
+		rc = memblock_add(*base, *lmb_size);
 		rc = (rc < 0) ? -EINVAL : 0;
 	} else if (action == PSERIES_DRCONF_MEM_REMOVE) {
-		rc = pseries_remove_memblock(*base, *memblock_size);
+		rc = pseries_remove_memblock(*base, *lmb_size);
 	} else {
 		rc = -EINVAL;
 	}

include/asm-generic/vmlinux.lds.h

@@ -445,7 +445,7 @@
  */
 #define INIT_TASK_DATA_SECTION(align)					\
 	. = ALIGN(align);						\
-	.data..init_task : {						\
+	.data..init_task :  AT(ADDR(.data..init_task) - LOAD_OFFSET) {	\
 		INIT_TASK_DATA(align)					\
 	}