[PATCH v3 0/3] Cleanup and fixups for vmemmap handling

[PATCH v3 0/3] Cleanup and fixups for vmemmap handling

[Oscar Salvador]

Hi,

this series contains cleanups to remove dead code that handles
unaligned cases for 4K and 1GB pages (patch#1 and pathc#2) when
removing the vemmmap range, and a fix (patch#3) to handle the case
when two vmemmap ranges intersect a PMD.

More details can be found in the respective changelogs.

 v2 -> v3:
 - Make sure we do not clear the PUD entry in case
   we are not removing the whole range.
 - Add Reviewed-by

 v1 -> v2:
 - Remove dead code in remove_pud_table as well
 - Addessed feedback by David
 - Place the vmemap functions that take care of unaligned PMDs
   within CONFIG_SPARSEMEM_VMEMMAP

Oscar Salvador (3):
  x86/vmemmap: Drop handling of 4K unaligned vmemmap range
  x86/vmemmap: Drop handling of 1GB vmemmap ranges
  x86/vmemmap: Handle unpopulated sub-pmd ranges

 arch/x86/mm/init_64.c | 189 ++++++++++++++++++++++++++----------------
 1 file changed, 118 insertions(+), 71 deletions(-)

-- 
2.26.2

[PATCH v3 1/3] x86/vmemmap: Drop handling of 4K unaligned vmemmap range

[Oscar Salvador]

remove_pte_table() is prepared to handle the case where either the
start or the end of the range is not PAGE aligned.
This cannot actually happen:

__populate_section_memmap enforces the range to be PMD aligned,
so as long as the size of the struct page remains multiple of 8,
the vmemmap range will be aligned to PAGE_SIZE.

Drop the dead code and place a VM_BUG_ON in vmemmap_{populate,free}
to catch nasty cases.

Signed-off-by: Oscar Salvador <osalvador@suse.de>
Suggested-by: David Hildenbrand <david@redhat.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
---
 arch/x86/mm/init_64.c | 48 ++++++++++++-------------------------------
 1 file changed, 13 insertions(+), 35 deletions(-)

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index b5a3fa4033d3..b0e1d215c83e 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -962,7 +962,6 @@ remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end,
 {
 	unsigned long next, pages = 0;
 	pte_t *pte;
-	void *page_addr;
 	phys_addr_t phys_addr;
 
 	pte = pte_start + pte_index(addr);
@@ -983,42 +982,15 @@ remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end,
 		if (phys_addr < (phys_addr_t)0x40000000)
 			return;
 
-		if (PAGE_ALIGNED(addr) && PAGE_ALIGNED(next)) {
-			/*
-			 * Do not free direct mapping pages since they were
-			 * freed when offlining, or simplely not in use.
-			 */
-			if (!direct)
-				free_pagetable(pte_page(*pte), 0);
-
-			spin_lock(&init_mm.page_table_lock);
-			pte_clear(&init_mm, addr, pte);
-			spin_unlock(&init_mm.page_table_lock);
+		if (!direct)
+			free_pagetable(pte_page(*pte), 0);
 
-			/* For non-direct mapping, pages means nothing. */
-			pages++;
-		} else {
-			/*
-			 * If we are here, we are freeing vmemmap pages since
-			 * direct mapped memory ranges to be freed are aligned.
-			 *
-			 * If we are not removing the whole page, it means
-			 * other page structs in this page are being used and
-			 * we canot remove them. So fill the unused page_structs
-			 * with 0xFD, and remove the page when it is wholly
-			 * filled with 0xFD.
-			 */
-			memset((void *)addr, PAGE_INUSE, next - addr);
-
-			page_addr = page_address(pte_page(*pte));
-			if (!memchr_inv(page_addr, PAGE_INUSE, PAGE_SIZE)) {
-				free_pagetable(pte_page(*pte), 0);
+		spin_lock(&init_mm.page_table_lock);
+		pte_clear(&init_mm, addr, pte);
+		spin_unlock(&init_mm.page_table_lock);
 
-				spin_lock(&init_mm.page_table_lock);
-				pte_clear(&init_mm, addr, pte);
-				spin_unlock(&init_mm.page_table_lock);
-			}
-		}
+		/* For non-direct mapping, pages means nothing. */
+		pages++;
 	}
 
 	/* Call free_pte_table() in remove_pmd_table(). */
@@ -1197,6 +1169,9 @@ remove_pagetable(unsigned long start, unsigned long end, bool direct,
 void __ref vmemmap_free(unsigned long start, unsigned long end,
 		struct vmem_altmap *altmap)
 {
+	VM_BUG_ON(!IS_ALIGNED(start, PAGE_SIZE));
+	VM_BUG_ON(!IS_ALIGNED(end, PAGE_SIZE));
+
 	remove_pagetable(start, end, false, altmap);
 }
 
@@ -1556,6 +1531,9 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 {
 	int err;
 
+	VM_BUG_ON(!IS_ALIGNED(start, PAGE_SIZE));
+	VM_BUG_ON(!IS_ALIGNED(end, PAGE_SIZE));
+
 	if (end - start < PAGES_PER_SECTION * sizeof(struct page))
 		err = vmemmap_populate_basepages(start, end, node, NULL);
 	else if (boot_cpu_has(X86_FEATURE_PSE))
-- 
2.26.2

[PATCH v3 2/3] x86/vmemmap: Drop handling of 1GB vmemmap ranges

[Oscar Salvador]

We never get to allocate 1GB pages when mapping the vmemmap range.
Drop the dead code both for the aligned and unaligned cases and leave
only the direct map handling.

Signed-off-by: Oscar Salvador <osalvador@suse.de>
Suggested-by: David Hildenbrand <david@redhat.com>
---
 arch/x86/mm/init_64.c | 35 +++++++----------------------------
 1 file changed, 7 insertions(+), 28 deletions(-)

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index b0e1d215c83e..9ecb3c488ac8 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1062,7 +1062,6 @@ remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end,
 	unsigned long next, pages = 0;
 	pmd_t *pmd_base;
 	pud_t *pud;
-	void *page_addr;
 
 	pud = pud_start + pud_index(addr);
 	for (; addr < end; addr = next, pud++) {
@@ -1071,33 +1070,13 @@ remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end,
 		if (!pud_present(*pud))
 			continue;
 
-		if (pud_large(*pud)) {
-			if (IS_ALIGNED(addr, PUD_SIZE) &&
-			    IS_ALIGNED(next, PUD_SIZE)) {
-				if (!direct)
-					free_pagetable(pud_page(*pud),
-						       get_order(PUD_SIZE));
-
-				spin_lock(&init_mm.page_table_lock);
-				pud_clear(pud);
-				spin_unlock(&init_mm.page_table_lock);
-				pages++;
-			} else {
-				/* If here, we are freeing vmemmap pages. */
-				memset((void *)addr, PAGE_INUSE, next - addr);
-
-				page_addr = page_address(pud_page(*pud));
-				if (!memchr_inv(page_addr, PAGE_INUSE,
-						PUD_SIZE)) {
-					free_pagetable(pud_page(*pud),
-						       get_order(PUD_SIZE));
-
-					spin_lock(&init_mm.page_table_lock);
-					pud_clear(pud);
-					spin_unlock(&init_mm.page_table_lock);
-				}
-			}
-
+		if (pud_large(*pud) &&
+		    IS_ALIGNED(addr, PUD_SIZE) &&
+		    IS_ALIGNED(next, PUD_SIZE)) {
+			spin_lock(&init_mm.page_table_lock);
+			pud_clear(pud);
+			spin_unlock(&init_mm.page_table_lock);
+			pages++;
 			continue;
 		}
 
-- 
2.26.2

[PATCH v3 3/3] x86/vmemmap: Handle unpopulated sub-pmd ranges

[Oscar Salvador]

When the size of a struct page is not multiple of 2MB, sections do
not span a PMD anymore and so when populating them some parts of the
PMD will remain unused.
Because of this, PMDs will be left behind when depopulating sections
since remove_pmd_table() thinks that those unused parts are still in
use.

Fix this by marking the unused parts with PAGE_UNUSED, so memchr_inv()
will do the right thing and will let us free the PMD when the last user
of it is gone.

This patch is based on a similar patch by David Hildenbrand:

https://lore.kernel.org/linux-mm/20200722094558.9828-9-david@redhat.com/
https://lore.kernel.org/linux-mm/20200722094558.9828-10-david@redhat.com/

Signed-off-by: Oscar Salvador <osalvador@suse.de>
---
 arch/x86/mm/init_64.c | 106 ++++++++++++++++++++++++++++++++++++++----
 1 file changed, 98 insertions(+), 8 deletions(-)

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 9ecb3c488ac8..7e8de63f02b3 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -871,7 +871,93 @@ int arch_add_memory(int nid, u64 start, u64 size,
 	return add_pages(nid, start_pfn, nr_pages, params);
 }
 
-#define PAGE_INUSE 0xFD
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+#define PAGE_UNUSED 0xFD
+
+/*
+ * The unused vmemmap range, which was not yet memset(PAGE_UNUSED) ranges
+ * from unused_pmd_start to next PMD_SIZE boundary.
+ */
+static unsigned long unused_pmd_start __meminitdata;
+
+static void __meminit vmemmap_flush_unused_pmd(void)
+{
+	if (!unused_pmd_start)
+		return;
+	/*
+	 * Clears (unused_pmd_start, PMD_END]
+	 */
+	memset((void *)unused_pmd_start, PAGE_UNUSED,
+	       ALIGN(unused_pmd_start, PMD_SIZE) - unused_pmd_start);
+	unused_pmd_start = 0;
+}
+
+/* Returns true if the PMD is completely unused and thus it can be freed */
+static bool __meminit vmemmap_unuse_sub_pmd(unsigned long addr, unsigned long end)
+{
+	unsigned long start = ALIGN_DOWN(addr, PMD_SIZE);
+
+	vmemmap_flush_unused_pmd();
+	memset((void *)addr, PAGE_UNUSED, end - addr);
+
+	return !memchr_inv((void *)start, PAGE_UNUSED, PMD_SIZE);
+}
+
+static void __meminit __vmemmap_use_sub_pmd(unsigned long start)
+{
+	/*
+	 * As we expect to add in the same granularity as we remove, it's
+	 * sufficient to mark only some piece used to block the memmap page from
+	 * getting removed when removing some other adjacent memmap (just in
+	 * case the first memmap never gets initialized e.g., because the memory
+	 * block never gets onlined).
+	 */
+	memset((void *)start, 0, sizeof(struct page));
+}
+
+static void __meminit vmemmap_use_sub_pmd(unsigned long start, unsigned long end)
+{
+	/*
+	 * We only optimize if the new used range directly follows the
+	 * previously unused range (esp., when populating consecutive sections).
+	 */
+	if (unused_pmd_start == start) {
+		if (likely(IS_ALIGNED(end, PMD_SIZE)))
+			unused_pmd_start = 0;
+		else
+			unused_pmd_start = end;
+		return;
+	}
+
+	vmemmap_flush_unused_pmd();
+	__vmemmap_use_sub_pmd(start);
+}
+
+static void __meminit vmemmap_use_new_sub_pmd(unsigned long start, unsigned long end)
+{
+	vmemmap_flush_unused_pmd();
+
+	/*
+	 * Could be our memmap page is filled with PAGE_UNUSED already from a
+	 * previous remove.
+	 */
+	__vmemmap_use_sub_pmd(start);
+
+	/*
+	 * Mark the unused parts of the new memmap range
+	 */
+	if (!IS_ALIGNED(start, PMD_SIZE))
+		memset((void *)start, PAGE_UNUSED,
+		       start - ALIGN_DOWN(start, PMD_SIZE));
+	/*
+	 * We want to avoid memset(PAGE_UNUSED) when populating the vmemmap of
+	 * consecutive sections. Remember for the last added PMD the last
+	 * unused range in the populated PMD.
+	 */
+	if (!IS_ALIGNED(end, PMD_SIZE))
+		unused_pmd_start = end;
+}
+#endif
 
 static void __meminit free_pagetable(struct page *page, int order)
 {
@@ -1006,7 +1092,6 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end,
 	unsigned long next, pages = 0;
 	pte_t *pte_base;
 	pmd_t *pmd;
-	void *page_addr;
 
 	pmd = pmd_start + pmd_index(addr);
 	for (; addr < end; addr = next, pmd++) {
@@ -1027,12 +1112,11 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end,
 				spin_unlock(&init_mm.page_table_lock);
 				pages++;
 			} else {
-				/* If here, we are freeing vmemmap pages. */
-				memset((void *)addr, PAGE_INUSE, next - addr);
-
-				page_addr = page_address(pmd_page(*pmd));
-				if (!memchr_inv(page_addr, PAGE_INUSE,
-						PMD_SIZE)) {
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+				/*
+				 * Free the PMD if the whole range is unused.
+				 */
+				if (vmemmap_unuse_sub_pmd(addr, next)) {
 					free_hugepage_table(pmd_page(*pmd),
 							    altmap);
 
@@ -1040,6 +1124,7 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end,
 					pmd_clear(pmd);
 					spin_unlock(&init_mm.page_table_lock);
 				}
+#endif
 			}
 
 			continue;
@@ -1492,11 +1577,16 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start,
 
 				addr_end = addr + PMD_SIZE;
 				p_end = p + PMD_SIZE;
+
+				if (!IS_ALIGNED(addr, PMD_SIZE) ||
+				    !IS_ALIGNED(next, PMD_SIZE))
+					vmemmap_use_new_sub_pmd(addr, next);
 				continue;
 			} else if (altmap)
 				return -ENOMEM; /* no fallback */
 		} else if (pmd_large(*pmd)) {
 			vmemmap_verify((pte_t *)pmd, node, addr, next);
+			vmemmap_use_sub_pmd(addr, next);
 			continue;
 		}
 		if (vmemmap_populate_basepages(addr, next, node, NULL))
-- 
2.26.2

Re: [PATCH v3 2/3] x86/vmemmap: Drop handling of 1GB vmemmap ranges

[David Hildenbrand]

On 04.02.21 14:43, Oscar Salvador wrote:
> We never get to allocate 1GB pages when mapping the vmemmap range.
> Drop the dead code both for the aligned and unaligned cases and leave
> only the direct map handling.
> 
> Signed-off-by: Oscar Salvador <osalvador@suse.de>
> Suggested-by: David Hildenbrand <david@redhat.com>
> ---
>   arch/x86/mm/init_64.c | 35 +++++++----------------------------
>   1 file changed, 7 insertions(+), 28 deletions(-)
> 
> diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
> index b0e1d215c83e..9ecb3c488ac8 100644
> --- a/arch/x86/mm/init_64.c
> +++ b/arch/x86/mm/init_64.c
> @@ -1062,7 +1062,6 @@ remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end,
>   	unsigned long next, pages = 0;
>   	pmd_t *pmd_base;
>   	pud_t *pud;
> -	void *page_addr;
>   
>   	pud = pud_start + pud_index(addr);
>   	for (; addr < end; addr = next, pud++) {
> @@ -1071,33 +1070,13 @@ remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end,
>   		if (!pud_present(*pud))
>   			continue;
>   
> -		if (pud_large(*pud)) {
> -			if (IS_ALIGNED(addr, PUD_SIZE) &&
> -			    IS_ALIGNED(next, PUD_SIZE)) {
> -				if (!direct)
> -					free_pagetable(pud_page(*pud),
> -						       get_order(PUD_SIZE));
> -
> -				spin_lock(&init_mm.page_table_lock);
> -				pud_clear(pud);
> -				spin_unlock(&init_mm.page_table_lock);
> -				pages++;
> -			} else {
> -				/* If here, we are freeing vmemmap pages. */
> -				memset((void *)addr, PAGE_INUSE, next - addr);
> -
> -				page_addr = page_address(pud_page(*pud));
> -				if (!memchr_inv(page_addr, PAGE_INUSE,
> -						PUD_SIZE)) {
> -					free_pagetable(pud_page(*pud),
> -						       get_order(PUD_SIZE));
> -
> -					spin_lock(&init_mm.page_table_lock);
> -					pud_clear(pud);
> -					spin_unlock(&init_mm.page_table_lock);
> -				}
> -			}
> -
> +		if (pud_large(*pud) &&
> +		    IS_ALIGNED(addr, PUD_SIZE) &&
> +		    IS_ALIGNED(next, PUD_SIZE)) {
> +			spin_lock(&init_mm.page_table_lock);
> +			pud_clear(pud);
> +			spin_unlock(&init_mm.page_table_lock);
> +			pages++;
>   			continue;
>   		}
>   
> 

Reviewed-by: David Hildenbrand <david@redhat.com>

-- 
Thanks,

David / dhildenb

Re: [PATCH v3 3/3] x86/vmemmap: Handle unpopulated sub-pmd ranges

[David Hildenbrand]

On 04.02.21 14:43, Oscar Salvador wrote:
> When the size of a struct page is not multiple of 2MB, sections do
> not span a PMD anymore and so when populating them some parts of the
> PMD will remain unused.
> Because of this, PMDs will be left behind when depopulating sections
> since remove_pmd_table() thinks that those unused parts are still in
> use.
> 
> Fix this by marking the unused parts with PAGE_UNUSED, so memchr_inv()
> will do the right thing and will let us free the PMD when the last user
> of it is gone.
> 
> This patch is based on a similar patch by David Hildenbrand:
> 
> https://lore.kernel.org/linux-mm/20200722094558.9828-9-david@redhat.com/
> https://lore.kernel.org/linux-mm/20200722094558.9828-10-david@redhat.com/
> 
> Signed-off-by: Oscar Salvador <osalvador@suse.de>
> ---
>   arch/x86/mm/init_64.c | 106 ++++++++++++++++++++++++++++++++++++++----
>   1 file changed, 98 insertions(+), 8 deletions(-)
> 
> diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
> index 9ecb3c488ac8..7e8de63f02b3 100644
> --- a/arch/x86/mm/init_64.c
> +++ b/arch/x86/mm/init_64.c
> @@ -871,7 +871,93 @@ int arch_add_memory(int nid, u64 start, u64 size,
>   	return add_pages(nid, start_pfn, nr_pages, params);
>   }
>   
> -#define PAGE_INUSE 0xFD
> +#ifdef CONFIG_SPARSEMEM_VMEMMAP
> +#define PAGE_UNUSED 0xFD
> +
> +/*
> + * The unused vmemmap range, which was not yet memset(PAGE_UNUSED) ranges
> + * from unused_pmd_start to next PMD_SIZE boundary.
> + */
> +static unsigned long unused_pmd_start __meminitdata;
> +
> +static void __meminit vmemmap_flush_unused_pmd(void)
> +{
> +	if (!unused_pmd_start)
> +		return;
> +	/*
> +	 * Clears (unused_pmd_start, PMD_END]
> +	 */
> +	memset((void *)unused_pmd_start, PAGE_UNUSED,
> +	       ALIGN(unused_pmd_start, PMD_SIZE) - unused_pmd_start);
> +	unused_pmd_start = 0;
> +}
> +
> +/* Returns true if the PMD is completely unused and thus it can be freed */
> +static bool __meminit vmemmap_unuse_sub_pmd(unsigned long addr, unsigned long end)
> +{
> +	unsigned long start = ALIGN_DOWN(addr, PMD_SIZE);
> +
> +	vmemmap_flush_unused_pmd();
> +	memset((void *)addr, PAGE_UNUSED, end - addr);
> +
> +	return !memchr_inv((void *)start, PAGE_UNUSED, PMD_SIZE);
> +}
> +
> +static void __meminit __vmemmap_use_sub_pmd(unsigned long start)
> +{
> +	/*
> +	 * As we expect to add in the same granularity as we remove, it's
> +	 * sufficient to mark only some piece used to block the memmap page from
> +	 * getting removed when removing some other adjacent memmap (just in
> +	 * case the first memmap never gets initialized e.g., because the memory
> +	 * block never gets onlined).
> +	 */
> +	memset((void *)start, 0, sizeof(struct page));
> +}
> +
> +static void __meminit vmemmap_use_sub_pmd(unsigned long start, unsigned long end)
> +{
> +	/*
> +	 * We only optimize if the new used range directly follows the
> +	 * previously unused range (esp., when populating consecutive sections).
> +	 */
> +	if (unused_pmd_start == start) {
> +		if (likely(IS_ALIGNED(end, PMD_SIZE)))
> +			unused_pmd_start = 0;
> +		else
> +			unused_pmd_start = end;
> +		return;
> +	}
> +
> +	vmemmap_flush_unused_pmd();
> +	__vmemmap_use_sub_pmd(start);
> +}
> +
> +static void __meminit vmemmap_use_new_sub_pmd(unsigned long start, unsigned long end)
> +{
> +	vmemmap_flush_unused_pmd();
> +
> +	/*
> +	 * Could be our memmap page is filled with PAGE_UNUSED already from a
> +	 * previous remove.
> +	 */
> +	__vmemmap_use_sub_pmd(start);
> +
> +	/*
> +	 * Mark the unused parts of the new memmap range
> +	 */
> +	if (!IS_ALIGNED(start, PMD_SIZE))
> +		memset((void *)start, PAGE_UNUSED,
> +		       start - ALIGN_DOWN(start, PMD_SIZE));
> +	/*
> +	 * We want to avoid memset(PAGE_UNUSED) when populating the vmemmap of
> +	 * consecutive sections. Remember for the last added PMD the last
> +	 * unused range in the populated PMD.
> +	 */
> +	if (!IS_ALIGNED(end, PMD_SIZE))
> +		unused_pmd_start = end;
> +}
> +#endif
>   
>   static void __meminit free_pagetable(struct page *page, int order)
>   {
> @@ -1006,7 +1092,6 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end,
>   	unsigned long next, pages = 0;
>   	pte_t *pte_base;
>   	pmd_t *pmd;
> -	void *page_addr;
>   
>   	pmd = pmd_start + pmd_index(addr);
>   	for (; addr < end; addr = next, pmd++) {
> @@ -1027,12 +1112,11 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end,
>   				spin_unlock(&init_mm.page_table_lock);
>   				pages++;
>   			} else {
> -				/* If here, we are freeing vmemmap pages. */
> -				memset((void *)addr, PAGE_INUSE, next - addr);
> -
> -				page_addr = page_address(pmd_page(*pmd));
> -				if (!memchr_inv(page_addr, PAGE_INUSE,
> -						PMD_SIZE)) {
> +#ifdef CONFIG_SPARSEMEM_VMEMMAP
> +				/*
> +				 * Free the PMD if the whole range is unused.
> +				 */
> +				if (vmemmap_unuse_sub_pmd(addr, next)) {
>   					free_hugepage_table(pmd_page(*pmd),
>   							    altmap);
>   
> @@ -1040,6 +1124,7 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end,
>   					pmd_clear(pmd);
>   					spin_unlock(&init_mm.page_table_lock);
>   				}
> +#endif
>   			}
>   
>   			continue;
> @@ -1492,11 +1577,16 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start,
>   
>   				addr_end = addr + PMD_SIZE;
>   				p_end = p + PMD_SIZE;
> +
> +				if (!IS_ALIGNED(addr, PMD_SIZE) ||
> +				    !IS_ALIGNED(next, PMD_SIZE))
> +					vmemmap_use_new_sub_pmd(addr, next);
>   				continue;
>   			} else if (altmap)
>   				return -ENOMEM; /* no fallback */
>   		} else if (pmd_large(*pmd)) {
>   			vmemmap_verify((pte_t *)pmd, node, addr, next);
> +			vmemmap_use_sub_pmd(addr, next);
>   			continue;
>   		}
>   		if (vmemmap_populate_basepages(addr, next, node, NULL))
> 

LGTM, thanks

Reviewed-by: David Hildenbrand <david@redhat.com>

-- 
Thanks,

David / dhildenb

Re: [PATCH v3 3/3] x86/vmemmap: Handle unpopulated sub-pmd ranges

[kernel test robot]

[-- Attachment #1: Type: text/plain, Size: 4578 bytes --]

Hi Oscar,

Thank you for the patch! Yet something to improve:

[auto build test ERROR on tip/x86/mm]
[also build test ERROR on hnaz-linux-mm/master v5.11-rc6 next-20210125]
[cannot apply to luto/next]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]

url:    https://github.com/0day-ci/linux/commits/Oscar-Salvador/Cleanup-and-fixups-for-vmemmap-handling/20210204-215019
base:   https://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git 167dcfc08b0b1f964ea95d410aa496fd78adf475
config: x86_64-randconfig-r026-20210205 (attached as .config)
compiler: clang version 12.0.0 (https://github.com/llvm/llvm-project c9439ca36342fb6013187d0a69aef92736951476)
reproduce (this is a W=1 build):
        wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # install x86_64 cross compiling tool for clang build
        # apt-get install binutils-x86-64-linux-gnu
        # https://github.com/0day-ci/linux/commit/8eed800ab9b1129124ca4af26be911f1ea800339
        git remote add linux-review https://github.com/0day-ci/linux
        git fetch --no-tags linux-review Oscar-Salvador/Cleanup-and-fixups-for-vmemmap-handling/20210204-215019
        git checkout 8eed800ab9b1129124ca4af26be911f1ea800339
        # save the attached .config to linux build tree
        COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross ARCH=x86_64 

If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>

All errors (new ones prefixed by >>):

>> arch/x86/mm/init_64.c:1583:6: error: implicit declaration of function 'vmemmap_use_new_sub_pmd' [-Werror,-Wimplicit-function-declaration]
                                           vmemmap_use_new_sub_pmd(addr, next);
                                           ^
>> arch/x86/mm/init_64.c:1589:4: error: implicit declaration of function 'vmemmap_use_sub_pmd' [-Werror,-Wimplicit-function-declaration]
                           vmemmap_use_sub_pmd(addr, next);
                           ^
   2 errors generated.


vim +/vmemmap_use_new_sub_pmd +1583 arch/x86/mm/init_64.c

  1530	
  1531	static int __meminit vmemmap_populate_hugepages(unsigned long start,
  1532			unsigned long end, int node, struct vmem_altmap *altmap)
  1533	{
  1534		unsigned long addr;
  1535		unsigned long next;
  1536		pgd_t *pgd;
  1537		p4d_t *p4d;
  1538		pud_t *pud;
  1539		pmd_t *pmd;
  1540	
  1541		for (addr = start; addr < end; addr = next) {
  1542			next = pmd_addr_end(addr, end);
  1543	
  1544			pgd = vmemmap_pgd_populate(addr, node);
  1545			if (!pgd)
  1546				return -ENOMEM;
  1547	
  1548			p4d = vmemmap_p4d_populate(pgd, addr, node);
  1549			if (!p4d)
  1550				return -ENOMEM;
  1551	
  1552			pud = vmemmap_pud_populate(p4d, addr, node);
  1553			if (!pud)
  1554				return -ENOMEM;
  1555	
  1556			pmd = pmd_offset(pud, addr);
  1557			if (pmd_none(*pmd)) {
  1558				void *p;
  1559	
  1560				p = vmemmap_alloc_block_buf(PMD_SIZE, node, altmap);
  1561				if (p) {
  1562					pte_t entry;
  1563	
  1564					entry = pfn_pte(__pa(p) >> PAGE_SHIFT,
  1565							PAGE_KERNEL_LARGE);
  1566					set_pmd(pmd, __pmd(pte_val(entry)));
  1567	
  1568					/* check to see if we have contiguous blocks */
  1569					if (p_end != p || node_start != node) {
  1570						if (p_start)
  1571							pr_debug(" [%lx-%lx] PMD -> [%p-%p] on node %d\n",
  1572							       addr_start, addr_end-1, p_start, p_end-1, node_start);
  1573						addr_start = addr;
  1574						node_start = node;
  1575						p_start = p;
  1576					}
  1577	
  1578					addr_end = addr + PMD_SIZE;
  1579					p_end = p + PMD_SIZE;
  1580	
  1581					if (!IS_ALIGNED(addr, PMD_SIZE) ||
  1582					    !IS_ALIGNED(next, PMD_SIZE))
> 1583						vmemmap_use_new_sub_pmd(addr, next);
  1584					continue;
  1585				} else if (altmap)
  1586					return -ENOMEM; /* no fallback */
  1587			} else if (pmd_large(*pmd)) {
  1588				vmemmap_verify((pte_t *)pmd, node, addr, next);
> 1589				vmemmap_use_sub_pmd(addr, next);
  1590				continue;
  1591			}
  1592			if (vmemmap_populate_basepages(addr, next, node, NULL))
  1593				return -ENOMEM;
  1594		}
  1595		return 0;
  1596	}
  1597	

---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all(a)lists.01.org

[-- Attachment #2: config.gz --]
[-- Type: application/gzip, Size: 36101 bytes --]