[PATCH v2] mm: hugetlb: don't zero 1GiB bootmem pages.

[PATCH v2] mm: hugetlb: don't zero 1GiB bootmem pages.

[Cannon Matthews]

When using 1GiB pages during early boot, use the new
memblock_virt_alloc_try_nid_raw() function to allocate memory without
zeroing it.  Zeroing out hundreds or thousands of GiB in a single core
memset() call is very slow, and can make early boot last upwards of
20-30 minutes on multi TiB machines.

The memory does not need to be zero'd as the hugetlb pages are always
zero'd on page fault.

Tested: Booted with ~3800 1G pages, and it booted successfully in
roughly the same amount of time as with 0, as opposed to the 25+
minutes it would take before.

Signed-off-by: Cannon Matthews <cannonmatthews@google.com>
---
v2: removed the memset of the huge_bootmem_page area and added
INIT_LIST_HEAD instead.

 mm/hugetlb.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 3612fbb32e9d..488330f23f04 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2101,7 +2101,7 @@ int __alloc_bootmem_huge_page(struct hstate *h)
 	for_each_node_mask_to_alloc(h, nr_nodes, node, &node_states[N_MEMORY]) {
 		void *addr;

-		addr = memblock_virt_alloc_try_nid_nopanic(
+		addr = memblock_virt_alloc_try_nid_raw(
 				huge_page_size(h), huge_page_size(h),
 				0, BOOTMEM_ALLOC_ACCESSIBLE, node);
 		if (addr) {
@@ -2119,6 +2119,7 @@ int __alloc_bootmem_huge_page(struct hstate *h)
 found:
 	BUG_ON(!IS_ALIGNED(virt_to_phys(m), huge_page_size(h)));
 	/* Put them into a private list first because mem_map is not up yet */
+	INIT_LIST_HEAD(&m->list);
 	list_add(&m->list, &huge_boot_pages);
 	m->hstate = h;
 	return 1;
--
2.18.0.203.gfac676dfb9-goog

Re: [PATCH v2] mm: hugetlb: don't zero 1GiB bootmem pages.

[Mike Kravetz]

On 07/11/2018 02:33 PM, Cannon Matthews wrote:
> When using 1GiB pages during early boot, use the new
> memblock_virt_alloc_try_nid_raw() function to allocate memory without
> zeroing it.  Zeroing out hundreds or thousands of GiB in a single core
> memset() call is very slow, and can make early boot last upwards of
> 20-30 minutes on multi TiB machines.
> 
> The memory does not need to be zero'd as the hugetlb pages are always
> zero'd on page fault.
> 
> Tested: Booted with ~3800 1G pages, and it booted successfully in
> roughly the same amount of time as with 0, as opposed to the 25+
> minutes it would take before.
> 
> Signed-off-by: Cannon Matthews <cannonmatthews@google.com>

Thanks,

Acked-by: Mike Kravetz <mike.kravetz@oracle.com>

-- 
Mike Kravetz

> ---
> v2: removed the memset of the huge_bootmem_page area and added
> INIT_LIST_HEAD instead.
> 
>  mm/hugetlb.c | 3 ++-
>  1 file changed, 2 insertions(+), 1 deletion(-)
> 
> diff --git a/mm/hugetlb.c b/mm/hugetlb.c
> index 3612fbb32e9d..488330f23f04 100644
> --- a/mm/hugetlb.c
> +++ b/mm/hugetlb.c
> @@ -2101,7 +2101,7 @@ int __alloc_bootmem_huge_page(struct hstate *h)
>  	for_each_node_mask_to_alloc(h, nr_nodes, node, &node_states[N_MEMORY]) {
>  		void *addr;
> 
> -		addr = memblock_virt_alloc_try_nid_nopanic(
> +		addr = memblock_virt_alloc_try_nid_raw(
>  				huge_page_size(h), huge_page_size(h),
>  				0, BOOTMEM_ALLOC_ACCESSIBLE, node);
>  		if (addr) {
> @@ -2119,6 +2119,7 @@ int __alloc_bootmem_huge_page(struct hstate *h)
>  found:
>  	BUG_ON(!IS_ALIGNED(virt_to_phys(m), huge_page_size(h)));
>  	/* Put them into a private list first because mem_map is not up yet */
> +	INIT_LIST_HEAD(&m->list);
>  	list_add(&m->list, &huge_boot_pages);
>  	m->hstate = h;
>  	return 1;
> --
> 2.18.0.203.gfac676dfb9-goog
> 

Re: [PATCH v2] mm: hugetlb: don't zero 1GiB bootmem pages.

[Michal Hocko]

On Wed 11-07-18 14:33:13, Cannon Matthews wrote:
> When using 1GiB pages during early boot, use the new
> memblock_virt_alloc_try_nid_raw() function to allocate memory without
> zeroing it.  Zeroing out hundreds or thousands of GiB in a single core
> memset() call is very slow, and can make early boot last upwards of
> 20-30 minutes on multi TiB machines.
> 
> The memory does not need to be zero'd as the hugetlb pages are always
> zero'd on page fault.
> 
> Tested: Booted with ~3800 1G pages, and it booted successfully in
> roughly the same amount of time as with 0, as opposed to the 25+
> minutes it would take before.
> 
> Signed-off-by: Cannon Matthews <cannonmatthews@google.com>

Thanks for the updated version.

Acked-by: Michal Hocko <mhocko@suse.com>

> ---
> v2: removed the memset of the huge_bootmem_page area and added
> INIT_LIST_HEAD instead.
> 
>  mm/hugetlb.c | 3 ++-
>  1 file changed, 2 insertions(+), 1 deletion(-)
> 
> diff --git a/mm/hugetlb.c b/mm/hugetlb.c
> index 3612fbb32e9d..488330f23f04 100644
> --- a/mm/hugetlb.c
> +++ b/mm/hugetlb.c
> @@ -2101,7 +2101,7 @@ int __alloc_bootmem_huge_page(struct hstate *h)
>  	for_each_node_mask_to_alloc(h, nr_nodes, node, &node_states[N_MEMORY]) {
>  		void *addr;
> 
> -		addr = memblock_virt_alloc_try_nid_nopanic(
> +		addr = memblock_virt_alloc_try_nid_raw(
>  				huge_page_size(h), huge_page_size(h),
>  				0, BOOTMEM_ALLOC_ACCESSIBLE, node);
>  		if (addr) {
> @@ -2119,6 +2119,7 @@ int __alloc_bootmem_huge_page(struct hstate *h)
>  found:
>  	BUG_ON(!IS_ALIGNED(virt_to_phys(m), huge_page_size(h)));
>  	/* Put them into a private list first because mem_map is not up yet */
> +	INIT_LIST_HEAD(&m->list);
>  	list_add(&m->list, &huge_boot_pages);
>  	m->hstate = h;
>  	return 1;
> --
> 2.18.0.203.gfac676dfb9-goog

-- 
Michal Hocko
SUSE Labs