[PATCH v3 1/6] mm, x86: Add ARCH_HAS_ZONE_DEVICE to Kconfig

[PATCH v3 1/6] mm, x86: Add ARCH_HAS_ZONE_DEVICE to Kconfig

[Oliver O'Halloran]

Currently ZONE_DEVICE depends on X86_64 and this will get unwieldly as
new architectures (and platforms) get ZONE_DEVICE support. Move to an
arch selected Kconfig option to save us the trouble.

Cc: linux-mm@kvack.org
Acked-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Balbir Singh <bsingharora@gmail.com>
Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
---
v2: Added missing hunk.
v3: No changes
---
 arch/x86/Kconfig | 1 +
 mm/Kconfig       | 6 +++++-
 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 0efb4c9497bc..325429a3f32f 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -59,6 +59,7 @@ config X86
 	select ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_HAS_STRICT_MODULE_RWX
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
+	select ARCH_HAS_ZONE_DEVICE		if X86_64
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_MIGHT_HAVE_ACPI_PDC		if ACPI
 	select ARCH_MIGHT_HAVE_PC_PARPORT
diff --git a/mm/Kconfig b/mm/Kconfig
index beb7a455915d..790e52a8a486 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -683,12 +683,16 @@ config IDLE_PAGE_TRACKING
 
 	  See Documentation/vm/idle_page_tracking.txt for more details.
 
+# arch_add_memory() comprehends device memory
+config ARCH_HAS_ZONE_DEVICE
+	bool
+
 config ZONE_DEVICE
 	bool "Device memory (pmem, etc...) hotplug support"
 	depends on MEMORY_HOTPLUG
 	depends on MEMORY_HOTREMOVE
 	depends on SPARSEMEM_VMEMMAP
-	depends on X86_64 #arch_add_memory() comprehends device memory
+	depends on ARCH_HAS_ZONE_DEVICE
 
 	help
 	  Device memory hotplug support allows for establishing pmem,
-- 
2.9.4

[PATCH v3 2/6] powerpc/vmemmap: Reshuffle vmemmap_free()

[Oliver O'Halloran]

Removes an indentation level and shuffles some code around to make the
following patch cleaner. No functional changes.

Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
---
v1 -> v2: Remove broken initialiser
---
 arch/powerpc/mm/init_64.c | 48 ++++++++++++++++++++++++-----------------------
 1 file changed, 25 insertions(+), 23 deletions(-)

diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index ec84b31c6c86..8851e4f5dbab 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -234,13 +234,15 @@ static unsigned long vmemmap_list_free(unsigned long start)
 void __ref vmemmap_free(unsigned long start, unsigned long end)
 {
 	unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift;
+	unsigned long page_order = get_order(page_size);
 
 	start = _ALIGN_DOWN(start, page_size);
 
 	pr_debug("vmemmap_free %lx...%lx\n", start, end);
 
 	for (; start < end; start += page_size) {
-		unsigned long addr;
+		unsigned long nr_pages, addr;
+		struct page *page;
 
 		/*
 		 * the section has already be marked as invalid, so
@@ -251,29 +253,29 @@ void __ref vmemmap_free(unsigned long start, unsigned long end)
 			continue;
 
 		addr = vmemmap_list_free(start);
-		if (addr) {
-			struct page *page = pfn_to_page(addr >> PAGE_SHIFT);
-
-			if (PageReserved(page)) {
-				/* allocated from bootmem */
-				if (page_size < PAGE_SIZE) {
-					/*
-					 * this shouldn't happen, but if it is
-					 * the case, leave the memory there
-					 */
-					WARN_ON_ONCE(1);
-				} else {
-					unsigned int nr_pages =
-						1 << get_order(page_size);
-					while (nr_pages--)
-						free_reserved_page(page++);
-				}
-			} else
-				free_pages((unsigned long)(__va(addr)),
-							get_order(page_size));
-
-			vmemmap_remove_mapping(start, page_size);
+		if (!addr)
+			continue;
+
+		page = pfn_to_page(addr >> PAGE_SHIFT);
+		nr_pages = 1 << page_order;
+
+		if (PageReserved(page)) {
+			/* allocated from bootmem */
+			if (page_size < PAGE_SIZE) {
+				/*
+				 * this shouldn't happen, but if it is
+				 * the case, leave the memory there
+				 */
+				WARN_ON_ONCE(1);
+			} else {
+				while (nr_pages--)
+					free_reserved_page(page++);
+			}
+		} else {
+			free_pages((unsigned long)(__va(addr)), page_order);
 		}
+
+		vmemmap_remove_mapping(start, page_size);
 	}
 }
 #endif
-- 
2.9.4

Re: [PATCH v3 2/6] powerpc/vmemmap: Reshuffle vmemmap_free()

[Balbir Singh]

On Fri, 23 Jun 2017 18:31:18 +1000
Oliver O'Halloran <oohall@gmail.com> wrote:

> Removes an indentation level and shuffles some code around to make the
> following patch cleaner. No functional changes.
> 
> Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
> ---
> v1 -> v2: Remove broken initialiser
> ---
>  arch/powerpc/mm/init_64.c | 48 ++++++++++++++++++++++++-----------------------
>  1 file changed, 25 insertions(+), 23 deletions(-)
> 
> diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
> index ec84b31c6c86..8851e4f5dbab 100644
> --- a/arch/powerpc/mm/init_64.c
> +++ b/arch/powerpc/mm/init_64.c
> @@ -234,13 +234,15 @@ static unsigned long vmemmap_list_free(unsigned long start)
>  void __ref vmemmap_free(unsigned long start, unsigned long end)
>  {
>  	unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift;
> +	unsigned long page_order = get_order(page_size);
>  
>  	start = _ALIGN_DOWN(start, page_size);
>  
>  	pr_debug("vmemmap_free %lx...%lx\n", start, end);
>  
>  	for (; start < end; start += page_size) {
> -		unsigned long addr;
> +		unsigned long nr_pages, addr;
> +		struct page *page;
>  
>  		/*
>  		 * the section has already be marked as invalid, so
> @@ -251,29 +253,29 @@ void __ref vmemmap_free(unsigned long start, unsigned long end)
>  			continue;
>  
>  		addr = vmemmap_list_free(start);
> -		if (addr) {
> -			struct page *page = pfn_to_page(addr >> PAGE_SHIFT);
> -
> -			if (PageReserved(page)) {
> -				/* allocated from bootmem */
> -				if (page_size < PAGE_SIZE) {
> -					/*
> -					 * this shouldn't happen, but if it is
> -					 * the case, leave the memory there
> -					 */
> -					WARN_ON_ONCE(1);
> -				} else {
> -					unsigned int nr_pages =
> -						1 << get_order(page_size);
> -					while (nr_pages--)
> -						free_reserved_page(page++);
> -				}
> -			} else
> -				free_pages((unsigned long)(__va(addr)),
> -							get_order(page_size));
> -
> -			vmemmap_remove_mapping(start, page_size);
> +		if (!addr)
> +			continue;
> +
> +		page = pfn_to_page(addr >> PAGE_SHIFT);
> +		nr_pages = 1 << page_order;
> +
> +		if (PageReserved(page)) {
> +			/* allocated from bootmem */
> +			if (page_size < PAGE_SIZE) {
> +				/*
> +				 * this shouldn't happen, but if it is
> +				 * the case, leave the memory there
> +				 */
> +				WARN_ON_ONCE(1);
> +			} else {
> +				while (nr_pages--)
> +					free_reserved_page(page++);
> +			}
> +		} else {
> +			free_pages((unsigned long)(__va(addr)), page_order);
>  		}
> +
> +		vmemmap_remove_mapping(start, page_size);
>  	}
>  }
>  #endif

Reviewed-by: Balbir Singh <bsingharora@gmail.com>

Balbir Singh.

[PATCH v3 3/6] powerpc/vmemmap: Add altmap support

[Oliver O'Halloran]

Adds support to powerpc for the altmap feature of ZONE_DEVICE memory. An
altmap is a driver provided region that is used to provide the backing
storage for the struct pages of ZONE_DEVICE memory. In situations where
large amount of ZONE_DEVICE memory is being added to the system the
altmap reduces pressure on main system memory by allowing the mm/
metadata to be stored on the device itself rather in main memory.

Reviewed-by: Balbir Singh <bsingharora@gmail.com>
Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
---
 arch/powerpc/mm/init_64.c | 15 +++++++++++++--
 arch/powerpc/mm/mem.c     | 16 +++++++++++++---
 2 files changed, 26 insertions(+), 5 deletions(-)

diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 8851e4f5dbab..225fbb8034e6 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -44,6 +44,7 @@
 #include <linux/slab.h>
 #include <linux/of_fdt.h>
 #include <linux/libfdt.h>
+#include <linux/memremap.h>
 
 #include <asm/pgalloc.h>
 #include <asm/page.h>
@@ -171,13 +172,17 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
 	pr_debug("vmemmap_populate %lx..%lx, node %d\n", start, end, node);
 
 	for (; start < end; start += page_size) {
+		struct vmem_altmap *altmap;
 		void *p;
 		int rc;
 
 		if (vmemmap_populated(start, page_size))
 			continue;
 
-		p = vmemmap_alloc_block(page_size, node);
+		/* altmap lookups only work at section boundaries */
+		altmap = to_vmem_altmap(SECTION_ALIGN_DOWN(start));
+
+		p =  __vmemmap_alloc_block_buf(page_size, node, altmap);
 		if (!p)
 			return -ENOMEM;
 
@@ -242,6 +247,8 @@ void __ref vmemmap_free(unsigned long start, unsigned long end)
 
 	for (; start < end; start += page_size) {
 		unsigned long nr_pages, addr;
+		struct vmem_altmap *altmap;
+		struct page *section_base;
 		struct page *page;
 
 		/*
@@ -257,9 +264,13 @@ void __ref vmemmap_free(unsigned long start, unsigned long end)
 			continue;
 
 		page = pfn_to_page(addr >> PAGE_SHIFT);
+		section_base = pfn_to_page(vmemmap_section_start(start));
 		nr_pages = 1 << page_order;
 
-		if (PageReserved(page)) {
+		altmap = to_vmem_altmap((unsigned long) section_base);
+		if (altmap) {
+			vmem_altmap_free(altmap, nr_pages);
+		} else if (PageReserved(page)) {
 			/* allocated from bootmem */
 			if (page_size < PAGE_SIZE) {
 				/*
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 9ee536ec0739..2c0c16f11eee 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -36,6 +36,7 @@
 #include <linux/hugetlb.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
+#include <linux/memremap.h>
 
 #include <asm/pgalloc.h>
 #include <asm/prom.h>
@@ -159,11 +160,20 @@ int arch_remove_memory(u64 start, u64 size)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
-	struct zone *zone;
+	struct vmem_altmap *altmap;
+	struct page *page;
 	int ret;
 
-	zone = page_zone(pfn_to_page(start_pfn));
-	ret = __remove_pages(zone, start_pfn, nr_pages);
+	/*
+	 * If we have an altmap then we need to skip over any reserved PFNs
+	 * when querying the zone.
+	 */
+	page = pfn_to_page(start_pfn);
+	altmap = to_vmem_altmap((unsigned long) page);
+	if (altmap)
+		page += vmem_altmap_offset(altmap);
+
+	ret = __remove_pages(page_zone(page), start_pfn, nr_pages);
 	if (ret)
 		return ret;
 
-- 
2.9.4

[PATCH v3 4/6] powerpc/mm: Add devmap support for ppc64

[Oliver O'Halloran]

Add support for the devmap bit on PTEs and PMDs for PPC64 Book3S.  This
is used to differentiate device backed memory from transparent huge
pages since they are handled in more or less the same manner by the core
mm code.

Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
---
v1 -> v2: Properly differentiate THP and PMD Devmap entries. The
mm core assumes that pmd_trans_huge() and pmd_devmap() are mutually
exclusive and v1 had pmd_trans_huge() being true on a devmap pmd.

v2 -> v3:
	Remove setting of _PAGE_SPECIAL in pmd_mkdevmap()
	Make pud_pfn() a BUILD_BUG()
	Remove unnecessary _PAGE_DEVMAP check in hash__pmd_trans_huge()
---
 arch/powerpc/include/asm/book3s/64/pgtable.h | 46 +++++++++++++++++++++++++++-
 arch/powerpc/include/asm/book3s/64/radix.h   |  2 +-
 arch/powerpc/include/asm/string.h            |  1 +
 arch/powerpc/mm/hugetlbpage.c                |  2 +-
 arch/powerpc/mm/pgtable-book3s64.c           |  4 +--
 arch/powerpc/mm/pgtable-hash64.c             |  4 ++-
 arch/powerpc/mm/pgtable-radix.c              |  3 +-
 arch/powerpc/mm/pgtable_64.c                 |  2 +-
 8 files changed, 56 insertions(+), 8 deletions(-)

diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 85bc9875c3be..54b51e0fbe85 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -5,6 +5,7 @@
 
 #ifndef __ASSEMBLY__
 #include <linux/mmdebug.h>
+#include <linux/bug.h>
 #endif
 
 /*
@@ -79,6 +80,9 @@
 
 #define _PAGE_SOFT_DIRTY	_RPAGE_SW3 /* software: software dirty tracking */
 #define _PAGE_SPECIAL		_RPAGE_SW2 /* software: special page */
+#define _PAGE_DEVMAP		_RPAGE_SW1
+#define __HAVE_ARCH_PTE_DEVMAP
+
 /*
  * Drivers request for cache inhibited pte mapping using _PAGE_NO_CACHE
  * Instead of fixing all of them, add an alternate define which
@@ -599,6 +603,16 @@ static inline pte_t pte_mkhuge(pte_t pte)
 	return pte;
 }
 
+static inline pte_t pte_mkdevmap(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_SPECIAL|_PAGE_DEVMAP);
+}
+
+static inline int pte_devmap(pte_t pte)
+{
+	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_DEVMAP));
+}
+
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
 	/* FIXME!! check whether this need to be a conditional */
@@ -1137,7 +1151,6 @@ static inline int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl,
 	return true;
 }
 
-
 #define arch_needs_pgtable_deposit arch_needs_pgtable_deposit
 static inline bool arch_needs_pgtable_deposit(void)
 {
@@ -1146,6 +1159,37 @@ static inline bool arch_needs_pgtable_deposit(void)
 	return true;
 }
 
+static inline pmd_t pmd_mkdevmap(pmd_t pmd)
+{
+	return __pmd(pmd_val(pmd) | (_PAGE_PTE | _PAGE_DEVMAP));
+}
+
+static inline int pmd_devmap(pmd_t pmd)
+{
+	return pte_devmap(pmd_pte(pmd));
+}
+
+static inline int pud_devmap(pud_t pud)
+{
+	return 0;
+}
+
+static inline const int pud_pfn(pud_t pud)
+{
+	/*
+	 * Calls to pud_pfn() are gated around a pud_devmap() check
+	 * so this should never be used. If it grows another user we
+	 * want to know about it.
+	 */
+	BUILD_BUG();
+	return 0;
+}
+
+static inline int pgd_devmap(pgd_t pgd)
+{
+	return 0;
+}
+
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ */
diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h
index ac16d1943022..ba43754e96d2 100644
--- a/arch/powerpc/include/asm/book3s/64/radix.h
+++ b/arch/powerpc/include/asm/book3s/64/radix.h
@@ -252,7 +252,7 @@ static inline int radix__pgd_bad(pgd_t pgd)
 
 static inline int radix__pmd_trans_huge(pmd_t pmd)
 {
-	return !!(pmd_val(pmd) & _PAGE_PTE);
+	return (pmd_val(pmd) & (_PAGE_PTE | _PAGE_DEVMAP)) == _PAGE_PTE;
 }
 
 static inline pmd_t radix__pmd_mkhuge(pmd_t pmd)
diff --git a/arch/powerpc/include/asm/string.h b/arch/powerpc/include/asm/string.h
index da3cdffca440..ef7c73cf7288 100644
--- a/arch/powerpc/include/asm/string.h
+++ b/arch/powerpc/include/asm/string.h
@@ -10,6 +10,7 @@
 #define __HAVE_ARCH_MEMMOVE
 #define __HAVE_ARCH_MEMCMP
 #define __HAVE_ARCH_MEMCHR
+#define __HAVE_ARCH_MEMCPY_FLUSHCACHE
 
 extern char * strcpy(char *,const char *);
 extern char * strncpy(char *,const char *, __kernel_size_t);
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index a4f33de4008e..d9958af5c98e 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -963,7 +963,7 @@ pte_t *__find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
 			if (pmd_none(pmd))
 				return NULL;
 
-			if (pmd_trans_huge(pmd)) {
+			if (pmd_trans_huge(pmd) || pmd_devmap(pmd)) {
 				if (is_thp)
 					*is_thp = true;
 				ret_pte = (pte_t *) pmdp;
diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c
index 5fcb3dd74c13..31eed8fa8e99 100644
--- a/arch/powerpc/mm/pgtable-book3s64.c
+++ b/arch/powerpc/mm/pgtable-book3s64.c
@@ -32,7 +32,7 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address,
 {
 	int changed;
 #ifdef CONFIG_DEBUG_VM
-	WARN_ON(!pmd_trans_huge(*pmdp));
+	WARN_ON(!pmd_trans_huge(*pmdp) && !pmd_devmap(*pmdp));
 	assert_spin_locked(&vma->vm_mm->page_table_lock);
 #endif
 	changed = !pmd_same(*(pmdp), entry);
@@ -59,7 +59,7 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 #ifdef CONFIG_DEBUG_VM
 	WARN_ON(pte_present(pmd_pte(*pmdp)) && !pte_protnone(pmd_pte(*pmdp)));
 	assert_spin_locked(&mm->page_table_lock);
-	WARN_ON(!pmd_trans_huge(pmd));
+	WARN_ON(!(pmd_trans_huge(pmd) || pmd_devmap(pmd)));
 #endif
 	trace_hugepage_set_pmd(addr, pmd_val(pmd));
 	return set_pte_at(mm, addr, pmdp_ptep(pmdp), pmd_pte(pmd));
diff --git a/arch/powerpc/mm/pgtable-hash64.c b/arch/powerpc/mm/pgtable-hash64.c
index 8b85a14b08ea..7456cde4dbce 100644
--- a/arch/powerpc/mm/pgtable-hash64.c
+++ b/arch/powerpc/mm/pgtable-hash64.c
@@ -109,7 +109,7 @@ unsigned long hash__pmd_hugepage_update(struct mm_struct *mm, unsigned long addr
 	unsigned long old;
 
 #ifdef CONFIG_DEBUG_VM
-	WARN_ON(!pmd_trans_huge(*pmdp));
+	WARN_ON(!hash__pmd_trans_huge(*pmdp) && !pmd_devmap(*pmdp));
 	assert_spin_locked(&mm->page_table_lock);
 #endif
 
@@ -141,6 +141,7 @@ pmd_t hash__pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long addres
 
 	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
 	VM_BUG_ON(pmd_trans_huge(*pmdp));
+	VM_BUG_ON(pmd_devmap(*pmdp));
 
 	pmd = *pmdp;
 	pmd_clear(pmdp);
@@ -221,6 +222,7 @@ void hash__pmdp_huge_split_prepare(struct vm_area_struct *vma,
 {
 	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
 	VM_BUG_ON(REGION_ID(address) != USER_REGION_ID);
+	VM_BUG_ON(pmd_devmap(*pmdp));
 
 	/*
 	 * We can't mark the pmd none here, because that will cause a race
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index c28165d8970b..69e28dda81f2 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -683,7 +683,7 @@ unsigned long radix__pmd_hugepage_update(struct mm_struct *mm, unsigned long add
 	unsigned long old;
 
 #ifdef CONFIG_DEBUG_VM
-	WARN_ON(!radix__pmd_trans_huge(*pmdp));
+	WARN_ON(!radix__pmd_trans_huge(*pmdp) && !pmd_devmap(*pmdp));
 	assert_spin_locked(&mm->page_table_lock);
 #endif
 
@@ -701,6 +701,7 @@ pmd_t radix__pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long addre
 
 	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
 	VM_BUG_ON(radix__pmd_trans_huge(*pmdp));
+	VM_BUG_ON(pmd_devmap(*pmdp));
 	/*
 	 * khugepaged calls this for normal pmd
 	 */
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index db93cf747a03..aefde9bd3110 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -323,7 +323,7 @@ struct page *pud_page(pud_t pud)
  */
 struct page *pmd_page(pmd_t pmd)
 {
-	if (pmd_trans_huge(pmd) || pmd_huge(pmd))
+	if (pmd_trans_huge(pmd) || pmd_huge(pmd) || pmd_devmap(pmd))
 		return pte_page(pmd_pte(pmd));
 	return virt_to_page(pmd_page_vaddr(pmd));
 }
-- 
2.9.4

Re: [PATCH v3 4/6] powerpc/mm: Add devmap support for ppc64

[kbuild test robot]

[-- Attachment #1: Type: text/plain, Size: 2335 bytes --]

Hi Oliver,

[auto build test ERROR on powerpc/next]
[also build test ERROR on v4.12-rc6 next-20170623]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]

url:    https://github.com/0day-ci/linux/commits/Oliver-O-Halloran/mm-x86-Add-ARCH_HAS_ZONE_DEVICE-to-Kconfig/20170625-102522
base:   https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git next
config: powerpc-defconfig (attached as .config)
compiler: powerpc64-linux-gnu-gcc (Debian 6.1.1-9) 6.1.1 20160705
reproduce:
        wget https://raw.githubusercontent.com/01org/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # save the attached .config to linux build tree
        make.cross ARCH=powerpc 

All errors (new ones prefixed by >>):

   mm/gup.c: In function '__gup_device_huge_pud':
>> mm/gup.c:1329:14: error: implicit declaration of function 'pud_pfn' [-Werror=implicit-function-declaration]
     fault_pfn = pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
                 ^~~~~~~
   cc1: some warnings being treated as errors

vim +/pud_pfn +1329 mm/gup.c

b59f65fa Kirill A. Shutemov 2017-03-16  1323  
b59f65fa Kirill A. Shutemov 2017-03-16  1324  static int __gup_device_huge_pud(pud_t pud, unsigned long addr,
b59f65fa Kirill A. Shutemov 2017-03-16  1325  		unsigned long end, struct page **pages, int *nr)
b59f65fa Kirill A. Shutemov 2017-03-16  1326  {
b59f65fa Kirill A. Shutemov 2017-03-16  1327  	unsigned long fault_pfn;
b59f65fa Kirill A. Shutemov 2017-03-16  1328  
b59f65fa Kirill A. Shutemov 2017-03-16 @1329  	fault_pfn = pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
b59f65fa Kirill A. Shutemov 2017-03-16  1330  	return __gup_device_huge(fault_pfn, addr, end, pages, nr);
b59f65fa Kirill A. Shutemov 2017-03-16  1331  }
b59f65fa Kirill A. Shutemov 2017-03-16  1332  #else

:::::: The code at line 1329 was first introduced by commit
:::::: b59f65fa076a8eac2ff3a8ab7f8e1705b9fa86cb mm/gup: Implement the dev_pagemap() logic in the generic get_user_pages_fast() function

:::::: TO: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
:::::: CC: Ingo Molnar <mingo@kernel.org>

---
0-DAY kernel test infrastructure                Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all                   Intel Corporation

[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 23373 bytes --]

Re: [PATCH v3 4/6] powerpc/mm: Add devmap support for ppc64

[Michael Ellerman]

kbuild test robot <lkp@intel.com> writes:

> Hi Oliver,
>
> [auto build test ERROR on powerpc/next]
> [also build test ERROR on v4.12-rc6 next-20170623]
> [if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
>
> url:    https://github.com/0day-ci/linux/commits/Oliver-O-Halloran/mm-x86-Add-ARCH_HAS_ZONE_DEVICE-to-Kconfig/20170625-102522
> base:   https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git next
> config: powerpc-defconfig (attached as .config)
> compiler: powerpc64-linux-gnu-gcc (Debian 6.1.1-9) 6.1.1 20160705
> reproduce:
>         wget https://raw.githubusercontent.com/01org/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
>         chmod +x ~/bin/make.cross
>         # save the attached .config to linux build tree
>         make.cross ARCH=powerpc 
>
> All errors (new ones prefixed by >>):
>
>    mm/gup.c: In function '__gup_device_huge_pud':
>>> mm/gup.c:1329:14: error: implicit declaration of function 'pud_pfn' [-Werror=implicit-function-declaration]
>      fault_pfn = pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
>                  ^~~~~~~
>    cc1: some warnings being treated as errors

The key here is that CONFIG_TRANSPARENT_HUGEPAGE=n.

So this needs to be fixed before I can merge this.

I think the problem is just that pud_pfn() is inside #ifdef
CONFIG_TRANSPARENT_HUGEPAGE but shouldn't be.

cheers

Re: [PATCH v3 4/6] powerpc/mm: Add devmap support for ppc64

[Oliver]

On Tue, Jun 27, 2017 at 12:33 PM, Michael Ellerman <mpe@ellerman.id.au> wrote:
> kbuild test robot <lkp@intel.com> writes:
>
>> Hi Oliver,
>>
>> [auto build test ERROR on powerpc/next]
>> [also build test ERROR on v4.12-rc6 next-20170623]
>> [if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
>>
>> url:    https://github.com/0day-ci/linux/commits/Oliver-O-Halloran/mm-x86-Add-ARCH_HAS_ZONE_DEVICE-to-Kconfig/20170625-102522
>> base:   https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git next
>> config: powerpc-defconfig (attached as .config)
>> compiler: powerpc64-linux-gnu-gcc (Debian 6.1.1-9) 6.1.1 20160705
>> reproduce:
>>         wget https://raw.githubusercontent.com/01org/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
>>         chmod +x ~/bin/make.cross
>>         # save the attached .config to linux build tree
>>         make.cross ARCH=powerpc
>>
>> All errors (new ones prefixed by >>):
>>
>>    mm/gup.c: In function '__gup_device_huge_pud':
>>>> mm/gup.c:1329:14: error: implicit declaration of function 'pud_pfn' [-Werror=implicit-function-declaration]
>>      fault_pfn = pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
>>                  ^~~~~~~
>>    cc1: some warnings being treated as errors
>
> The key here is that CONFIG_TRANSPARENT_HUGEPAGE=n.
>
> So this needs to be fixed before I can merge this.
>
> I think the problem is just that pud_pfn() is inside #ifdef
> CONFIG_TRANSPARENT_HUGEPAGE but shouldn't be.

I'm not 100% sold on making pud_pfn() independent of THP. pmd_pfn() is
used a few times in generic code, but the usages are always gated by a
#ifdef CONFIG_TRANSPARENT_HUGEPAGE so I think we should be doing the
same here. I sent a patch[1] yesterday to fix the usage in gup.c, but
I'll do a respin if you want.

Thanks,
Oliver

[1] http://marc.info/?l=linux-mm&m=149845912612363&w=4

[PATCH v3 5/6] powerpc/mm: Wire up hpte_removebolted for powernv

[Oliver O'Halloran]

From: Anton Blanchard <anton@samba.org>

Adds support for removing bolted (i.e kernel linear mapping) mappings on
powernv. This is needed to support memory hot unplug operations which
are required for the teardown of DAX/PMEM devices.

Reviewed-by: Balbir Singh <bsingharora@gmail.com>
Reviewed-by: Rashmica Gupta <rashmica.g@gmail.com>
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
---
v1 -> v2: Fixed the commit author
          Added VM_WARN_ON() if we attempt to remove an unbolted hpte
---
 arch/powerpc/mm/hash_native_64.c | 33 +++++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 65bb8f33b399..b534d041cfe8 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -407,6 +407,38 @@ static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
 	tlbie(vpn, psize, psize, ssize, 0);
 }
 
+/*
+ * Remove a bolted kernel entry. Memory hotplug uses this.
+ *
+ * No need to lock here because we should be the only user.
+ */
+static int native_hpte_removebolted(unsigned long ea, int psize, int ssize)
+{
+	unsigned long vpn;
+	unsigned long vsid;
+	long slot;
+	struct hash_pte *hptep;
+
+	vsid = get_kernel_vsid(ea, ssize);
+	vpn = hpt_vpn(ea, vsid, ssize);
+
+	slot = native_hpte_find(vpn, psize, ssize);
+	if (slot == -1)
+		return -ENOENT;
+
+	hptep = htab_address + slot;
+
+	VM_WARN_ON(!(be64_to_cpu(hptep->v) & HPTE_V_BOLTED));
+
+	/* Invalidate the hpte */
+	hptep->v = 0;
+
+	/* Invalidate the TLB */
+	tlbie(vpn, psize, psize, ssize, 0);
+	return 0;
+}
+
+
 static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
 				   int bpsize, int apsize, int ssize, int local)
 {
@@ -725,6 +757,7 @@ void __init hpte_init_native(void)
 	mmu_hash_ops.hpte_invalidate	= native_hpte_invalidate;
 	mmu_hash_ops.hpte_updatepp	= native_hpte_updatepp;
 	mmu_hash_ops.hpte_updateboltedpp = native_hpte_updateboltedpp;
+	mmu_hash_ops.hpte_removebolted = native_hpte_removebolted;
 	mmu_hash_ops.hpte_insert	= native_hpte_insert;
 	mmu_hash_ops.hpte_remove	= native_hpte_remove;
 	mmu_hash_ops.hpte_clear_all	= native_hpte_clear;
-- 
2.9.4

[PATCH v3 6/6] powerpc/mm: Enable ZONE_DEVICE on powerpc

[Oliver O'Halloran]

Flip the switch. Running around and screaming "IT'S ALIVE" is optional,
but recommended.

Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
---
v3: Only select when building for 64bit Book3-S
---
 arch/powerpc/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index bf4391d18923..978f371bb103 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -138,6 +138,7 @@ config PPC
 	select ARCH_HAS_SG_CHAIN
 	select ARCH_HAS_TICK_BROADCAST		if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
+	select ARCH_HAS_ZONE_DEVICE		if PPC_BOOK3S_64
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
-- 
2.9.4

Re: [PATCH v3 1/6] mm, x86: Add ARCH_HAS_ZONE_DEVICE to Kconfig

[John Hubbard]

On 06/23/2017 01:31 AM, Oliver O'Halloran wrote:
> Currently ZONE_DEVICE depends on X86_64 and this will get unwieldly as
> new architectures (and platforms) get ZONE_DEVICE support. Move to an
> arch selected Kconfig option to save us the trouble.
> 
> Cc: linux-mm@kvack.org
> Acked-by: Ingo Molnar <mingo@kernel.org>
> Acked-by: Balbir Singh <bsingharora@gmail.com>
> Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
> ---
> v2: Added missing hunk.
> v3: No changes
> ---
>   arch/x86/Kconfig | 1 +
>   mm/Kconfig       | 6 +++++-
>   2 files changed, 6 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
> index 0efb4c9497bc..325429a3f32f 100644
> --- a/arch/x86/Kconfig
> +++ b/arch/x86/Kconfig
> @@ -59,6 +59,7 @@ config X86
>   	select ARCH_HAS_STRICT_KERNEL_RWX
>   	select ARCH_HAS_STRICT_MODULE_RWX
>   	select ARCH_HAS_UBSAN_SANITIZE_ALL
> +	select ARCH_HAS_ZONE_DEVICE		if X86_64
>   	select ARCH_HAVE_NMI_SAFE_CMPXCHG
>   	select ARCH_MIGHT_HAVE_ACPI_PDC		if ACPI
>   	select ARCH_MIGHT_HAVE_PC_PARPORT
> diff --git a/mm/Kconfig b/mm/Kconfig
> index beb7a455915d..790e52a8a486 100644
> --- a/mm/Kconfig
> +++ b/mm/Kconfig
> @@ -683,12 +683,16 @@ config IDLE_PAGE_TRACKING
>   
>   	  See Documentation/vm/idle_page_tracking.txt for more details.
>   
> +# arch_add_memory() comprehends device memory
> +config ARCH_HAS_ZONE_DEVICE
> +	bool
> +
>   config ZONE_DEVICE
>   	bool "Device memory (pmem, etc...) hotplug support"
>   	depends on MEMORY_HOTPLUG
>   	depends on MEMORY_HOTREMOVE
>   	depends on SPARSEMEM_VMEMMAP
> -	depends on X86_64 #arch_add_memory() comprehends device memory
> +	depends on ARCH_HAS_ZONE_DEVICE
>   
>   	help
>   	  Device memory hotplug support allows for establishing pmem,
> 

Hi Oliver,

+1, this is nice to have, and it behaves as expected on x86_64 with and without HMM, at 
least with the small bit of Kconfig dependency testing I did here.

thanks,
john h