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

Pull powerpc fixes from Ben Herrenschmidt:
 "Here are some more powerpc fixes for 3.14

  The main one is a nasty issue with the NUMA balancing support which
  requires a small generic change and the addition of a new accessor to
  set _PAGE_NUMA.  Both have been reviewed and acked by Mel and Rik.

  The changelog should have plenty of details but basically, without
  this fix, we get random user segfaults and/or corruptions due to
  missing TLB/hash flushes.  Aneesh series of 3 patches fixes it.

  We have some vDSO vs.  perf fixes from Anton, some small EEH fixes
  from Gavin, a ppc32 regression vs the stack overflow detector, and a
  fix for the way we handle PCIe host bridge speed settings on pseries
  (which is needed for proper operations of AMD graphics cards on
  Power8)"

* 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc:
  powerpc/eeh: Disable EEH on reboot
  powerpc/eeh: Cleanup on eeh_subsystem_enabled
  powerpc/powernv: Rework EEH reset
  powerpc: Use unstripped VDSO image for more accurate profiling data
  powerpc: Link VDSOs at 0x0
  mm: Use ptep/pmdp_set_numa() for updating _PAGE_NUMA bit
  mm: Dirty accountable change only apply to non prot numa case
  powerpc/mm: Add new "set" flag argument to pte/pmd update function
  powerpc/pseries: Add Gen3 definitions for PCIE link speed
  powerpc/pseries: Fix regression on PCI link speed
  powerpc: Set the correct ksp_limit on ppc32 when switching to irq stack

arch/powerpc/include/asm/eeh.h

@@ -172,10 +172,20 @@ struct eeh_ops {
 };
 
 extern struct eeh_ops *eeh_ops;
-extern int eeh_subsystem_enabled;
+extern bool eeh_subsystem_enabled;
 extern raw_spinlock_t confirm_error_lock;
 extern int eeh_probe_mode;
 
+static inline bool eeh_enabled(void)
+{
+	return eeh_subsystem_enabled;
+}
+
+static inline void eeh_set_enable(bool mode)
+{
+	eeh_subsystem_enabled = mode;
+}
+
 #define EEH_PROBE_MODE_DEV	(1<<0)	/* From PCI device	*/
 #define EEH_PROBE_MODE_DEVTREE	(1<<1)	/* From device tree	*/
 
@@ -246,7 +256,7 @@ void eeh_remove_device(struct pci_dev *);
  * If this macro yields TRUE, the caller relays to eeh_check_failure()
  * which does further tests out of line.
  */
-#define EEH_POSSIBLE_ERROR(val, type)	((val) == (type)~0 && eeh_subsystem_enabled)
+#define EEH_POSSIBLE_ERROR(val, type)	((val) == (type)~0 && eeh_enabled())
 
 /*
  * Reads from a device which has been isolated by EEH will return
@@ -257,6 +267,13 @@ void eeh_remove_device(struct pci_dev *);
 
 #else /* !CONFIG_EEH */
 
+static inline bool eeh_enabled(void)
+{
+        return false;
+}
+
+static inline void eeh_set_enable(bool mode) { }
+
 static inline int eeh_init(void)
 {
 	return 0;

arch/powerpc/include/asm/hugetlb.h

@@ -127,7 +127,7 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 					    unsigned long addr, pte_t *ptep)
 {
 #ifdef CONFIG_PPC64
-	return __pte(pte_update(mm, addr, ptep, ~0UL, 1));
+	return __pte(pte_update(mm, addr, ptep, ~0UL, 0, 1));
 #else
 	return __pte(pte_update(ptep, ~0UL, 0));
 #endif

arch/powerpc/include/asm/pgtable-ppc64.h

@@ -195,6 +195,7 @@ extern void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
 static inline unsigned long pte_update(struct mm_struct *mm,
 				       unsigned long addr,
 				       pte_t *ptep, unsigned long clr,
+				       unsigned long set,
 				       int huge)
 {
 #ifdef PTE_ATOMIC_UPDATES
@@ -205,14 +206,15 @@ static inline unsigned long pte_update(struct mm_struct *mm,
 	andi.	%1,%0,%6\n\
 	bne-	1b \n\
 	andc	%1,%0,%4 \n\
+	or	%1,%1,%7\n\
 	stdcx.	%1,0,%3 \n\
 	bne-	1b"
 	: "=&r" (old), "=&r" (tmp), "=m" (*ptep)
-	: "r" (ptep), "r" (clr), "m" (*ptep), "i" (_PAGE_BUSY)
+	: "r" (ptep), "r" (clr), "m" (*ptep), "i" (_PAGE_BUSY), "r" (set)
 	: "cc" );
 #else
 	unsigned long old = pte_val(*ptep);
-	*ptep = __pte(old & ~clr);
+	*ptep = __pte((old & ~clr) | set);
 #endif
 	/* huge pages use the old page table lock */
 	if (!huge)
@@ -231,9 +233,9 @@ static inline int __ptep_test_and_clear_young(struct mm_struct *mm,
 {
 	unsigned long old;
 
-       	if ((pte_val(*ptep) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0)
+	if ((pte_val(*ptep) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0)
 		return 0;
-	old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0);
+	old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0, 0);
 	return (old & _PAGE_ACCESSED) != 0;
 }
 #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
@@ -252,7 +254,7 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 	if ((pte_val(*ptep) & _PAGE_RW) == 0)
 		return;
 
-	pte_update(mm, addr, ptep, _PAGE_RW, 0);
+	pte_update(mm, addr, ptep, _PAGE_RW, 0, 0);
 }
 
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
@@ -261,7 +263,7 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 	if ((pte_val(*ptep) & _PAGE_RW) == 0)
 		return;
 
-	pte_update(mm, addr, ptep, _PAGE_RW, 1);
+	pte_update(mm, addr, ptep, _PAGE_RW, 0, 1);
 }
 
 /*
@@ -284,14 +286,14 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 				       unsigned long addr, pte_t *ptep)
 {
-	unsigned long old = pte_update(mm, addr, ptep, ~0UL, 0);
+	unsigned long old = pte_update(mm, addr, ptep, ~0UL, 0, 0);
 	return __pte(old);
 }
 
 static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
 			     pte_t * ptep)
 {
-	pte_update(mm, addr, ptep, ~0UL, 0);
+	pte_update(mm, addr, ptep, ~0UL, 0, 0);
 }
 
 
@@ -506,7 +508,9 @@ extern int pmdp_set_access_flags(struct vm_area_struct *vma,
 
 extern unsigned long pmd_hugepage_update(struct mm_struct *mm,
 					 unsigned long addr,
-					 pmd_t *pmdp, unsigned long clr);
+					 pmd_t *pmdp,
+					 unsigned long clr,
+					 unsigned long set);
 
 static inline int __pmdp_test_and_clear_young(struct mm_struct *mm,
 					      unsigned long addr, pmd_t *pmdp)
@@ -515,7 +519,7 @@ static inline int __pmdp_test_and_clear_young(struct mm_struct *mm,
 
 	if ((pmd_val(*pmdp) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0)
 		return 0;
-	old = pmd_hugepage_update(mm, addr, pmdp, _PAGE_ACCESSED);
+	old = pmd_hugepage_update(mm, addr, pmdp, _PAGE_ACCESSED, 0);
 	return ((old & _PAGE_ACCESSED) != 0);
 }
 
@@ -542,7 +546,7 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 	if ((pmd_val(*pmdp) & _PAGE_RW) == 0)
 		return;
 
-	pmd_hugepage_update(mm, addr, pmdp, _PAGE_RW);
+	pmd_hugepage_update(mm, addr, pmdp, _PAGE_RW, 0);
 }
 
 #define __HAVE_ARCH_PMDP_SPLITTING_FLUSH

arch/powerpc/include/asm/pgtable.h

@@ -75,12 +75,34 @@ static inline pte_t pte_mknuma(pte_t pte)
 	return pte;
 }
 
+#define ptep_set_numa ptep_set_numa
+static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr,
+				 pte_t *ptep)
+{
+	if ((pte_val(*ptep) & _PAGE_PRESENT) == 0)
+		VM_BUG_ON(1);
+
+	pte_update(mm, addr, ptep, _PAGE_PRESENT, _PAGE_NUMA, 0);
+	return;
+}
+
 #define pmd_numa pmd_numa
 static inline int pmd_numa(pmd_t pmd)
 {
 	return pte_numa(pmd_pte(pmd));
 }
 
+#define pmdp_set_numa pmdp_set_numa
+static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr,
+				 pmd_t *pmdp)
+{
+	if ((pmd_val(*pmdp) & _PAGE_PRESENT) == 0)
+		VM_BUG_ON(1);
+
+	pmd_hugepage_update(mm, addr, pmdp, _PAGE_PRESENT, _PAGE_NUMA);
+	return;
+}
+
 #define pmd_mknonnuma pmd_mknonnuma
 static inline pmd_t pmd_mknonnuma(pmd_t pmd)
 {

arch/powerpc/include/asm/vdso.h

@@ -4,11 +4,11 @@
 #ifdef __KERNEL__
 
 /* Default link addresses for the vDSOs */
-#define VDSO32_LBASE	0x100000
+#define VDSO32_LBASE	0x0
-#define VDSO64_LBASE	0x100000
+#define VDSO64_LBASE	0x0
 
 /* Default map addresses for 32bit vDSO */
-#define VDSO32_MBASE	VDSO32_LBASE
+#define VDSO32_MBASE	0x100000
 
 #define VDSO_VERSION_STRING	LINUX_2.6.15
 

arch/powerpc/kernel/eeh.c

@@ -28,6 +28,7 @@
 #include <linux/pci.h>
 #include <linux/proc_fs.h>
 #include <linux/rbtree.h>
+#include <linux/reboot.h>
 #include <linux/seq_file.h>
 #include <linux/spinlock.h>
 #include <linux/export.h>
@@ -89,7 +90,7 @@
 /* Platform dependent EEH operations */
 struct eeh_ops *eeh_ops = NULL;
 
-int eeh_subsystem_enabled;
+bool eeh_subsystem_enabled = false;
 EXPORT_SYMBOL(eeh_subsystem_enabled);
 
 /*
@@ -364,7 +365,7 @@ int eeh_dev_check_failure(struct eeh_dev *edev)
 
 	eeh_stats.total_mmio_ffs++;
 
-	if (!eeh_subsystem_enabled)
+	if (!eeh_enabled())
 		return 0;
 
 	if (!edev) {
@@ -747,6 +748,17 @@ int __exit eeh_ops_unregister(const char *name)
 	return -EEXIST;
 }
 
+static int eeh_reboot_notifier(struct notifier_block *nb,
+			       unsigned long action, void *unused)
+{
+	eeh_set_enable(false);
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block eeh_reboot_nb = {
+	.notifier_call = eeh_reboot_notifier,
+};
+
 /**
  * eeh_init - EEH initialization
  *
@@ -778,6 +790,14 @@ int eeh_init(void)
 	if (machine_is(powernv) && cnt++ <= 0)
 		return ret;
 
+	/* Register reboot notifier */
+	ret = register_reboot_notifier(&eeh_reboot_nb);
+	if (ret) {
+		pr_warn("%s: Failed to register notifier (%d)\n",
+			__func__, ret);
+		return ret;
+	}
+
 	/* call platform initialization function */
 	if (!eeh_ops) {
 		pr_warning("%s: Platform EEH operation not found\n",
@@ -822,7 +842,7 @@ int eeh_init(void)
 			return ret;
 	}
 
-	if (eeh_subsystem_enabled)
+	if (eeh_enabled())
 		pr_info("EEH: PCI Enhanced I/O Error Handling Enabled\n");
 	else
 		pr_warning("EEH: No capable adapters found\n");
@@ -897,7 +917,7 @@ void eeh_add_device_late(struct pci_dev *dev)
 	struct device_node *dn;
 	struct eeh_dev *edev;
 
-	if (!dev || !eeh_subsystem_enabled)
+	if (!dev || !eeh_enabled())
 		return;
 
 	pr_debug("EEH: Adding device %s\n", pci_name(dev));
@@ -1005,7 +1025,7 @@ void eeh_remove_device(struct pci_dev *dev)
 {
 	struct eeh_dev *edev;
 
-	if (!dev || !eeh_subsystem_enabled)
+	if (!dev || !eeh_enabled())
 		return;
 	edev = pci_dev_to_eeh_dev(dev);
 
@@ -1045,7 +1065,7 @@ void eeh_remove_device(struct pci_dev *dev)
 
 static int proc_eeh_show(struct seq_file *m, void *v)
 {
-	if (0 == eeh_subsystem_enabled) {
+	if (!eeh_enabled()) {
 		seq_printf(m, "EEH Subsystem is globally disabled\n");
 		seq_printf(m, "eeh_total_mmio_ffs=%llu\n", eeh_stats.total_mmio_ffs);
 	} else {

arch/powerpc/kernel/misc_32.S

@@ -57,11 +57,14 @@ _GLOBAL(call_do_softirq)
 	mtlr	r0
 	blr
 
+/*
+ * void call_do_irq(struct pt_regs *regs, struct thread_info *irqtp);
+ */
 _GLOBAL(call_do_irq)
 	mflr	r0
 	stw	r0,4(r1)
 	lwz	r10,THREAD+KSP_LIMIT(r2)
-	addi	r11,r3,THREAD_INFO_GAP
+	addi	r11,r4,THREAD_INFO_GAP
 	stwu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4)
 	mr	r1,r4
 	stw	r10,8(r1)

arch/powerpc/kernel/vdso32/vdso32_wrapper.S

@@ -6,7 +6,7 @@
 	.globl vdso32_start, vdso32_end
 	.balign PAGE_SIZE
 vdso32_start:
-	.incbin "arch/powerpc/kernel/vdso32/vdso32.so"
+	.incbin "arch/powerpc/kernel/vdso32/vdso32.so.dbg"
 	.balign PAGE_SIZE
 vdso32_end:
 

arch/powerpc/kernel/vdso64/vdso64_wrapper.S

@@ -6,7 +6,7 @@
 	.globl vdso64_start, vdso64_end
 	.balign PAGE_SIZE
 vdso64_start:
-	.incbin "arch/powerpc/kernel/vdso64/vdso64.so"
+	.incbin "arch/powerpc/kernel/vdso64/vdso64.so.dbg"
 	.balign PAGE_SIZE
 vdso64_end:
 

arch/powerpc/mm/pgtable_64.c

@@ -510,7 +510,8 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address,
 }
 
 unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr,
-				  pmd_t *pmdp, unsigned long clr)
+				  pmd_t *pmdp, unsigned long clr,
+				  unsigned long set)
 {
 
 	unsigned long old, tmp;
@@ -526,14 +527,15 @@ unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr,
 		andi.	%1,%0,%6\n\
 		bne-	1b \n\
 		andc	%1,%0,%4 \n\
+		or	%1,%1,%7\n\
 		stdcx.	%1,0,%3 \n\
 		bne-	1b"
 	: "=&r" (old), "=&r" (tmp), "=m" (*pmdp)
-	: "r" (pmdp), "r" (clr), "m" (*pmdp), "i" (_PAGE_BUSY)
+	: "r" (pmdp), "r" (clr), "m" (*pmdp), "i" (_PAGE_BUSY), "r" (set)
 	: "cc" );
 #else
 	old = pmd_val(*pmdp);
-	*pmdp = __pmd(old & ~clr);
+	*pmdp = __pmd((old & ~clr) | set);
 #endif
 	if (old & _PAGE_HASHPTE)
 		hpte_do_hugepage_flush(mm, addr, pmdp);
@@ -708,7 +710,7 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 		     pmd_t *pmdp)
 {
-	pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT);
+	pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, 0);
 }
 
 /*
@@ -835,7 +837,7 @@ pmd_t pmdp_get_and_clear(struct mm_struct *mm,
 	unsigned long old;
 	pgtable_t *pgtable_slot;
 
-	old = pmd_hugepage_update(mm, addr, pmdp, ~0UL);
+	old = pmd_hugepage_update(mm, addr, pmdp, ~0UL, 0);
 	old_pmd = __pmd(old);
 	/*
 	 * We have pmd == none and we are holding page_table_lock.

arch/powerpc/mm/subpage-prot.c

@@ -78,7 +78,7 @@ static void hpte_flush_range(struct mm_struct *mm, unsigned long addr,
 	pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
 	arch_enter_lazy_mmu_mode();
 	for (; npages > 0; --npages) {
-		pte_update(mm, addr, pte, 0, 0);
+		pte_update(mm, addr, pte, 0, 0, 0);
 		addr += PAGE_SIZE;
 		++pte;
 	}

arch/powerpc/platforms/powernv/eeh-ioda.c

@@ -44,7 +44,8 @@ static int ioda_eeh_event(struct notifier_block *nb,
 
 	/* We simply send special EEH event */
 	if ((changed_evts & OPAL_EVENT_PCI_ERROR) &&
-	    (events & OPAL_EVENT_PCI_ERROR))
+	    (events & OPAL_EVENT_PCI_ERROR) &&
+	    eeh_enabled())
 		eeh_send_failure_event(NULL);
 
 	return 0;
@@ -489,8 +490,7 @@ static int ioda_eeh_bridge_reset(struct pci_controller *hose,
 static int ioda_eeh_reset(struct eeh_pe *pe, int option)
 {
 	struct pci_controller *hose = pe->phb;
-	struct eeh_dev *edev;
+	struct pci_bus *bus;
-	struct pci_dev *dev;
 	int ret;
 
 	/*
@@ -519,31 +519,11 @@ static int ioda_eeh_reset(struct eeh_pe *pe, int option)
 	if (pe->type & EEH_PE_PHB) {
 		ret = ioda_eeh_phb_reset(hose, option);
 	} else {
-		if (pe->type & EEH_PE_DEVICE) {
+		bus = eeh_pe_bus_get(pe);
-			/*
+		if (pci_is_root_bus(bus))
-			 * If it's device PE, we didn't refer to the parent
-			 * PCI bus yet. So we have to figure it out indirectly.
-			 */
-			edev = list_first_entry(&pe->edevs,
-					struct eeh_dev, list);
-			dev = eeh_dev_to_pci_dev(edev);
-			dev = dev->bus->self;
-		} else {
-			/*
-			 * If it's bus PE, the parent PCI bus is already there
-			 * and just pick it up.
-			 */
-			dev = pe->bus->self;
-		}
-
-		/*
-		 * Do reset based on the fact that the direct upstream bridge
-		 * is root bridge (port) or not.
-		 */
-		if (dev->bus->number == 0)
 			ret = ioda_eeh_root_reset(hose, option);
 		else
-			ret = ioda_eeh_bridge_reset(hose, dev, option);
+			ret = ioda_eeh_bridge_reset(hose, bus->self, option);
 	}
 
 	return ret;

arch/powerpc/platforms/powernv/eeh-powernv.c

@@ -145,7 +145,7 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag)
 	 * Enable EEH explicitly so that we will do EEH check
 	 * while accessing I/O stuff
 	 */
-	eeh_subsystem_enabled = 1;
+	eeh_set_enable(true);
 
 	/* Save memory bars */
 	eeh_save_bars(edev);

arch/powerpc/platforms/pseries/eeh_pseries.c

@@ -265,7 +265,7 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag)
 			enable = 1;
 
 		if (enable) {
-			eeh_subsystem_enabled = 1;
+			eeh_set_enable(true);
 			eeh_add_to_parent_pe(edev);
 
 			pr_debug("%s: EEH enabled on %s PHB#%d-PE#%x, config addr#%x\n",

arch/powerpc/platforms/pseries/pci.c

@@ -113,7 +113,8 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge)
 {
 	struct device_node *dn, *pdn;
 	struct pci_bus *bus;
-	const __be32 *pcie_link_speed_stats;
+	u32 pcie_link_speed_stats[2];
+	int rc;
 
 	bus = bridge->bus;
 
@@ -122,38 +123,45 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge)
 		return 0;
 
 	for (pdn = dn; pdn != NULL; pdn = of_get_next_parent(pdn)) {
-		pcie_link_speed_stats = of_get_property(pdn,
+		rc = of_property_read_u32_array(pdn,
-			"ibm,pcie-link-speed-stats", NULL);
+				"ibm,pcie-link-speed-stats",
-		if (pcie_link_speed_stats)
+				&pcie_link_speed_stats[0], 2);
+		if (!rc)
 			break;
 	}
 
 	of_node_put(pdn);
 
-	if (!pcie_link_speed_stats) {
+	if (rc) {
 		pr_err("no ibm,pcie-link-speed-stats property\n");
 		return 0;
 	}
 
-	switch (be32_to_cpup(pcie_link_speed_stats)) {
+	switch (pcie_link_speed_stats[0]) {
 	case 0x01:
 		bus->max_bus_speed = PCIE_SPEED_2_5GT;
 		break;
 	case 0x02:
 		bus->max_bus_speed = PCIE_SPEED_5_0GT;
 		break;
+	case 0x04:
+		bus->max_bus_speed = PCIE_SPEED_8_0GT;
+		break;
 	default:
 		bus->max_bus_speed = PCI_SPEED_UNKNOWN;
 		break;
 	}
 
-	switch (be32_to_cpup(pcie_link_speed_stats)) {
+	switch (pcie_link_speed_stats[1]) {
 	case 0x01:
 		bus->cur_bus_speed = PCIE_SPEED_2_5GT;
 		break;
 	case 0x02:
 		bus->cur_bus_speed = PCIE_SPEED_5_0GT;
 		break;
+	case 0x04:
+		bus->cur_bus_speed = PCIE_SPEED_8_0GT;
+		break;
 	default:
 		bus->cur_bus_speed = PCI_SPEED_UNKNOWN;
 		break;

include/asm-generic/pgtable.h

@@ -701,6 +701,18 @@ static inline pte_t pte_mknuma(pte_t pte)
 }
 #endif
 
+#ifndef ptep_set_numa
+static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr,
+				 pte_t *ptep)
+{
+	pte_t ptent = *ptep;
+
+	ptent = pte_mknuma(ptent);
+	set_pte_at(mm, addr, ptep, ptent);
+	return;
+}
+#endif
+
 #ifndef pmd_mknuma
 static inline pmd_t pmd_mknuma(pmd_t pmd)
 {
@@ -708,6 +720,18 @@ static inline pmd_t pmd_mknuma(pmd_t pmd)
 	return pmd_clear_flags(pmd, _PAGE_PRESENT);
 }
 #endif
+
+#ifndef pmdp_set_numa
+static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr,
+				 pmd_t *pmdp)
+{
+	pmd_t pmd = *pmdp;
+
+	pmd = pmd_mknuma(pmd);
+	set_pmd_at(mm, addr, pmdp, pmd);
+	return;
+}
+#endif
 #else
 extern int pte_numa(pte_t pte);
 extern int pmd_numa(pmd_t pmd);
@@ -715,6 +739,8 @@ extern pte_t pte_mknonnuma(pte_t pte);
 extern pmd_t pmd_mknonnuma(pmd_t pmd);
 extern pte_t pte_mknuma(pte_t pte);
 extern pmd_t pmd_mknuma(pmd_t pmd);
+extern void ptep_set_numa(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
+extern void pmdp_set_numa(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp);
 #endif /* CONFIG_ARCH_USES_NUMA_PROT_NONE */
 #else
 static inline int pmd_numa(pmd_t pmd)
@@ -742,10 +768,23 @@ static inline pte_t pte_mknuma(pte_t pte)
 	return pte;
 }
 
+static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr,
+				 pte_t *ptep)
+{
+	return;
+}
+
+
 static inline pmd_t pmd_mknuma(pmd_t pmd)
 {
 	return pmd;
 }
+
+static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr,
+				 pmd_t *pmdp)
+{
+	return ;
+}
 #endif /* CONFIG_NUMA_BALANCING */
 
 #endif /* CONFIG_MMU */

mm/huge_memory.c

@@ -1545,6 +1545,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 				entry = pmd_mknonnuma(entry);
 			entry = pmd_modify(entry, newprot);
 			ret = HPAGE_PMD_NR;
+			set_pmd_at(mm, addr, pmd, entry);
 			BUG_ON(pmd_write(entry));
 		} else {
 			struct page *page = pmd_page(*pmd);
@@ -1557,16 +1558,10 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 			 */
 			if (!is_huge_zero_page(page) &&
 			    !pmd_numa(*pmd)) {
-				entry = *pmd;
+				pmdp_set_numa(mm, addr, pmd);
-				entry = pmd_mknuma(entry);
 				ret = HPAGE_PMD_NR;
 			}
 		}
-
-		/* Set PMD if cleared earlier */
-		if (ret == HPAGE_PMD_NR)
-			set_pmd_at(mm, addr, pmd, entry);
-
 		spin_unlock(ptl);
 	}
 

mm/mprotect.c

@@ -58,36 +58,27 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 				if (pte_numa(ptent))
 					ptent = pte_mknonnuma(ptent);
 				ptent = pte_modify(ptent, newprot);
+				/*
+				 * Avoid taking write faults for pages we
+				 * know to be dirty.
+				 */
+				if (dirty_accountable && pte_dirty(ptent))
+					ptent = pte_mkwrite(ptent);
+				ptep_modify_prot_commit(mm, addr, pte, ptent);
 				updated = true;
 			} else {
 				struct page *page;
 
-				ptent = *pte;
 				page = vm_normal_page(vma, addr, oldpte);
 				if (page && !PageKsm(page)) {
 					if (!pte_numa(oldpte)) {
-						ptent = pte_mknuma(ptent);
+						ptep_set_numa(mm, addr, pte);
-						set_pte_at(mm, addr, pte, ptent);
 						updated = true;
 					}
 				}
 			}
-
-			/*
-			 * Avoid taking write faults for pages we know to be
-			 * dirty.
-			 */
-			if (dirty_accountable && pte_dirty(ptent)) {
-				ptent = pte_mkwrite(ptent);
-				updated = true;
-			}
-
 			if (updated)
 				pages++;
-
-			/* Only !prot_numa always clears the pte */
-			if (!prot_numa)
-				ptep_modify_prot_commit(mm, addr, pte, ptent);
 		} else if (IS_ENABLED(CONFIG_MIGRATION) && !pte_file(oldpte)) {
 			swp_entry_t entry = pte_to_swp_entry(oldpte);