Re: [PATCH v4 1/1] mm: initialize pages on demand during boot

[Pavel Tatashin]

Thank you Mel!

Pavel

On Thu, Feb 15, 2018 at 5:55 AM, Mel Gorman  wrote:
> On Wed, Feb 14, 2018 at 11:33:43AM -0500, Pavel Tatashin wrote:
>> Deferred page initialization allows the boot cpu to initialize a small
>> subset of the system's pages early in boot, with other cpus doing the rest
>> later on.
>>
>
> Bit late to the game but
>
> Acked-by: Mel Gorman 
>
> --
> Mel Gorman
> SUSE Labs
>
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majord...@kvack.org.  For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: mailto:"d...@kvack.org;> em...@kvack.org 

Re: [PATCH v4 1/1] mm: initialize pages on demand during boot

[Pavel Tatashin]

Thank you Mel!

Pavel

On Thu, Feb 15, 2018 at 5:55 AM, Mel Gorman  wrote:
> On Wed, Feb 14, 2018 at 11:33:43AM -0500, Pavel Tatashin wrote:
>> Deferred page initialization allows the boot cpu to initialize a small
>> subset of the system's pages early in boot, with other cpus doing the rest
>> later on.
>>
>
> Bit late to the game but
>
> Acked-by: Mel Gorman 
>
> --
> Mel Gorman
> SUSE Labs
>
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majord...@kvack.org.  For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: mailto:"d...@kvack.org;> em...@kvack.org 

Re: [PATCH v4 1/1] mm: initialize pages on demand during boot

[Mel Gorman]

On Wed, Feb 14, 2018 at 11:33:43AM -0500, Pavel Tatashin wrote:
> Deferred page initialization allows the boot cpu to initialize a small
> subset of the system's pages early in boot, with other cpus doing the rest
> later on.
> 

Bit late to the game but

Acked-by: Mel Gorman 

-- 
Mel Gorman
SUSE Labs

Re: [PATCH v4 1/1] mm: initialize pages on demand during boot

[Mel Gorman]

On Wed, Feb 14, 2018 at 11:33:43AM -0500, Pavel Tatashin wrote:
> Deferred page initialization allows the boot cpu to initialize a small
> subset of the system's pages early in boot, with other cpus doing the rest
> later on.
> 

Bit late to the game but

Acked-by: Mel Gorman 

-- 
Mel Gorman
SUSE Labs

[PATCH v4 1/1] mm: initialize pages on demand during boot

[Pavel Tatashin]

Deferred page initialization allows the boot cpu to initialize a small
subset of the system's pages early in boot, with other cpus doing the rest
later on.

It is, however, problematic to know how many pages the kernel needs during
boot.  Different modules and kernel parameters may change the requirement,
so the boot cpu either initializes too many pages or runs out of memory.

To fix that, initialize early pages on demand.  This ensures the kernel
does the minimum amount of work to initialize pages during boot and leaves
the rest to be divided in the multithreaded initialization path
(deferred_init_memmap).

The on-demand code is permanently disabled using static branching once
deferred pages are initialized.  After the static branch is changed to
false, the overhead is up-to two branch-always instructions if the zone
watermark check fails or if rmqueue fails.

Changes from Andrew Morton:
fix typo in comment, make deferred_pages static

Sergey Senozhatsky noticed that while deferred pages currently make sense
only on NUMA machines (we start one thread per latency node), CONFIG_NUMA
is not a requirement for CONFIG_DEFERRED_STRUCT_PAGE_INIT, so that is also
must be addressed in the patch.

Signed-off-by: Pavel Tatashin 
Reviewed-by: Daniel Jordan 
Reviewed-by: Steven Sistare 
Reviewed-by: Andrew Morton 
Tested-by: Masayoshi Mizuma 
---
 include/linux/memblock.h |  10 ---
 mm/memblock.c|  23 ---
 mm/page_alloc.c  | 175 ---
 3 files changed, 136 insertions(+), 72 deletions(-)

diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 8be5077efb5f..6c305afd95ab 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -417,21 +417,11 @@ static inline void early_memtest(phys_addr_t start, 
phys_addr_t end)
 {
 }
 #endif
-
-extern unsigned long memblock_reserved_memory_within(phys_addr_t start_addr,
-   phys_addr_t end_addr);
 #else
 static inline phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align)
 {
return 0;
 }
-
-static inline unsigned long memblock_reserved_memory_within(phys_addr_t 
start_addr,
-   phys_addr_t end_addr)
-{
-   return 0;
-}
-
 #endif /* CONFIG_HAVE_MEMBLOCK */
 
 #endif /* __KERNEL__ */
diff --git a/mm/memblock.c b/mm/memblock.c
index 5a9ca2a1751b..4120e9f536f7 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1778,29 +1778,6 @@ static void __init_memblock memblock_dump(struct 
memblock_type *type)
}
 }
 
-extern unsigned long __init_memblock
-memblock_reserved_memory_within(phys_addr_t start_addr, phys_addr_t end_addr)
-{
-   struct memblock_region *rgn;
-   unsigned long size = 0;
-   int idx;
-
-   for_each_memblock_type(idx, (), rgn) {
-   phys_addr_t start, end;
-
-   if (rgn->base + rgn->size < start_addr)
-   continue;
-   if (rgn->base > end_addr)
-   continue;
-
-   start = rgn->base;
-   end = start + rgn->size;
-   size += end - start;
-   }
-
-   return size;
-}
-
 void __init_memblock __memblock_dump_all(void)
 {
pr_info("MEMBLOCK configuration:\n");
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 81e18ceef579..4fc26de256f6 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -291,40 +291,6 @@ EXPORT_SYMBOL(nr_online_nodes);
 int page_group_by_mobility_disabled __read_mostly;
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
-
-/*
- * Determine how many pages need to be initialized during early boot
- * (non-deferred initialization).
- * The value of first_deferred_pfn will be set later, once non-deferred pages
- * are initialized, but for now set it ULONG_MAX.
- */
-static inline void reset_deferred_meminit(pg_data_t *pgdat)
-{
-   phys_addr_t start_addr, end_addr;
-   unsigned long max_pgcnt;
-   unsigned long reserved;
-
-   /*
-* Initialise at least 2G of a node but also take into account that
-* two large system hashes that can take up 1GB for 0.25TB/node.
-*/
-   max_pgcnt = max(2UL << (30 - PAGE_SHIFT),
-   (pgdat->node_spanned_pages >> 8));
-
-   /*
-* Compensate the all the memblock reservations (e.g. crash kernel)
-* from the initial estimation to make sure we will initialize enough
-* memory to boot.
-*/
-   start_addr = PFN_PHYS(pgdat->node_start_pfn);
-   end_addr = PFN_PHYS(pgdat->node_start_pfn + max_pgcnt);
-   reserved = memblock_reserved_memory_within(start_addr, end_addr);
-   max_pgcnt += PHYS_PFN(reserved);
-
-   pgdat->static_init_pgcnt = min(max_pgcnt, pgdat->node_spanned_pages);
-   pgdat->first_deferred_pfn = ULONG_MAX;
-}
-
 /* Returns true if the struct page for the pfn is uninitialised */
 static inline 

[PATCH v4 1/1] mm: initialize pages on demand during boot

[Pavel Tatashin]

Deferred page initialization allows the boot cpu to initialize a small
subset of the system's pages early in boot, with other cpus doing the rest
later on.

It is, however, problematic to know how many pages the kernel needs during
boot.  Different modules and kernel parameters may change the requirement,
so the boot cpu either initializes too many pages or runs out of memory.

To fix that, initialize early pages on demand.  This ensures the kernel
does the minimum amount of work to initialize pages during boot and leaves
the rest to be divided in the multithreaded initialization path
(deferred_init_memmap).

The on-demand code is permanently disabled using static branching once
deferred pages are initialized.  After the static branch is changed to
false, the overhead is up-to two branch-always instructions if the zone
watermark check fails or if rmqueue fails.

Changes from Andrew Morton:
fix typo in comment, make deferred_pages static

Sergey Senozhatsky noticed that while deferred pages currently make sense
only on NUMA machines (we start one thread per latency node), CONFIG_NUMA
is not a requirement for CONFIG_DEFERRED_STRUCT_PAGE_INIT, so that is also
must be addressed in the patch.

Signed-off-by: Pavel Tatashin 
Reviewed-by: Daniel Jordan 
Reviewed-by: Steven Sistare 
Reviewed-by: Andrew Morton 
Tested-by: Masayoshi Mizuma 
---
 include/linux/memblock.h |  10 ---
 mm/memblock.c|  23 ---
 mm/page_alloc.c  | 175 ---
 3 files changed, 136 insertions(+), 72 deletions(-)

diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 8be5077efb5f..6c305afd95ab 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -417,21 +417,11 @@ static inline void early_memtest(phys_addr_t start, 
phys_addr_t end)
 {
 }
 #endif
-
-extern unsigned long memblock_reserved_memory_within(phys_addr_t start_addr,
-   phys_addr_t end_addr);
 #else
 static inline phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align)
 {
return 0;
 }
-
-static inline unsigned long memblock_reserved_memory_within(phys_addr_t 
start_addr,
-   phys_addr_t end_addr)
-{
-   return 0;
-}
-
 #endif /* CONFIG_HAVE_MEMBLOCK */
 
 #endif /* __KERNEL__ */
diff --git a/mm/memblock.c b/mm/memblock.c
index 5a9ca2a1751b..4120e9f536f7 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1778,29 +1778,6 @@ static void __init_memblock memblock_dump(struct 
memblock_type *type)
}
 }
 
-extern unsigned long __init_memblock
-memblock_reserved_memory_within(phys_addr_t start_addr, phys_addr_t end_addr)
-{
-   struct memblock_region *rgn;
-   unsigned long size = 0;
-   int idx;
-
-   for_each_memblock_type(idx, (), rgn) {
-   phys_addr_t start, end;
-
-   if (rgn->base + rgn->size < start_addr)
-   continue;
-   if (rgn->base > end_addr)
-   continue;
-
-   start = rgn->base;
-   end = start + rgn->size;
-   size += end - start;
-   }
-
-   return size;
-}
-
 void __init_memblock __memblock_dump_all(void)
 {
pr_info("MEMBLOCK configuration:\n");
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 81e18ceef579..4fc26de256f6 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -291,40 +291,6 @@ EXPORT_SYMBOL(nr_online_nodes);
 int page_group_by_mobility_disabled __read_mostly;
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
-
-/*
- * Determine how many pages need to be initialized during early boot
- * (non-deferred initialization).
- * The value of first_deferred_pfn will be set later, once non-deferred pages
- * are initialized, but for now set it ULONG_MAX.
- */
-static inline void reset_deferred_meminit(pg_data_t *pgdat)
-{
-   phys_addr_t start_addr, end_addr;
-   unsigned long max_pgcnt;
-   unsigned long reserved;
-
-   /*
-* Initialise at least 2G of a node but also take into account that
-* two large system hashes that can take up 1GB for 0.25TB/node.
-*/
-   max_pgcnt = max(2UL << (30 - PAGE_SHIFT),
-   (pgdat->node_spanned_pages >> 8));
-
-   /*
-* Compensate the all the memblock reservations (e.g. crash kernel)
-* from the initial estimation to make sure we will initialize enough
-* memory to boot.
-*/
-   start_addr = PFN_PHYS(pgdat->node_start_pfn);
-   end_addr = PFN_PHYS(pgdat->node_start_pfn + max_pgcnt);
-   reserved = memblock_reserved_memory_within(start_addr, end_addr);
-   max_pgcnt += PHYS_PFN(reserved);
-
-   pgdat->static_init_pgcnt = min(max_pgcnt, pgdat->node_spanned_pages);
-   pgdat->first_deferred_pfn = ULONG_MAX;
-}
-
 /* Returns true if the struct page for the pfn is uninitialised */
 static inline bool __meminit early_page_uninitialised(unsigned long pfn)
 {
@@ -357,10 +323,6 @@ static inline bool update_defer_init(pg_data_t *pgdat,