dma-buf: system_heap: Set allocation orders for larger page sizes
PATCH v3 1/1 dma-buf: system_heap: Set allocation orders for larger page sizes
This change sets the allocation orders for the different page sizes (4k, 16k, 64k) based on PAGE_SHIFT. Before this change, the orders for large page sizes were calculated incorrectly, this caused system heap to allocate from 2% to 4% more memory on 16KiB page size kernels.
This change was tested on 4k/16k page size kernels.
---
Changes in v2:
- Add John's Acked-by tag.
- Add TJ's Reviewed-by tag
- Use dma-buf: system_heap: in the subject since this is specific to the system heap, as per TJ.
- Remove extra space in if statement.
Changes in v3:
- Remove defines for the orders as per Christian.
- Update the order array for 64k page sizes as per TJ
drivers/dma-buf/heaps/system_heap.c | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-)
drivers/dma-buf/heaps/system_heap.c +18 -3
@@ -18,6 +18,7 @@#include <linux/mm.h> #include <linux/module.h> #include <linux/scatterlist.h> +#include <linux/sizes.h> #include <linux/slab.h> #include <linux/vmalloc.h>
@@ -44,14 +45,28 @@ struct dma_heap_attachment {#define HIGH_ORDER_GFP (((GFP_HIGHUSER | __GFP_ZERO | __GFP_NOWARN \ | __GFP_NORETRY) & ~__GFP_RECLAIM) \ | __GFP_COMP) -static gfp_t order_flags[] = {HIGH_ORDER_GFP ,HIGH_ORDER_GFP ,LOW_ORDER_GFP };/* * The selection of the orders used for allocation (1MB, 64K, 4K) is designed * to match with the sizes often found in IOMMUs. Using order 4 pages instead * of order 0 pages can significantly improve the performance of many IOMMUs * by reducing TLB pressure and time spent updating page tables. +* +* Note: When the order is 0, the minimum allocation is PAGE_SIZE. The possible +* page sizes for ARM devices could be 4K, 16K and 64K. +*/ +#if (PAGE_SIZE ==SZ_64K ) +static gfp_t order_flags[] = {HIGH_ORDER_GFP ,LOW_ORDER_GFP }; +/* 1MiB allocs are calculated with (2 ^ (20 - PAGE_SHIFT)) * PAGE_SIZE = 1MiB */ +static const unsigned int orders[] = {20 -PAGE_SHIFT ,0 }; +#else +static gfp_t order_flags[] = {HIGH_ORDER_GFP ,HIGH_ORDER_GFP ,LOW_ORDER_GFP }; +/* +* 1MiB allocs are calculated with (2 ^ (20 - PAGE_SHIFT)) * PAGE_SIZE = 1MiB +* 64KiB allocs are calculated with (2 ^ (16 - PAGE_SHIFT)) * PAGE_SIZE = 64KiB */ -static const unsigned int orders[] = {8 ,4 ,0 }; +static const unsigned int orders[] = {20 -PAGE_SHIFT ,16 -PAGE_SHIFT ,0 }; +#endif +#define NUM_ORDERS ARRAY_SIZE(orders)static struct sg_table *dup_sg_table (struct sg_table *table)
@@ -318,7 +333,7 @@ static struct page *alloc_largest_available(unsigned long size,int i;for (i =0 ; i <NUM_ORDERS ; i++) { -if (size < (PAGE_SIZE << orders[i])) +if (size < (PAGE_SIZE << orders[i]))continue ;if (max_order < orders[i])continue ;
Signature · 1 line
2.49.0.805.g082f7c87e0-goog
Quoted 70 lines · Juan Yescas
This change sets the allocation orders for the different page sizes (4k, 16k, 64k) based on
PAGE_SHIFT. Before this change, the orders for large page sizes were calculated incorrectly, this caused system heap to allocate from 2% to 4% more memory on 16KiB page size kernels.This change was tested on 4k/16k page size kernels.
Signed-off-by Juan Yescas <[email protected]>Acked-by John Stultz <[email protected]>Reviewed-by T.J. Mercier <[email protected]>---
Changes in v2:
- Add John's Acked-by tag.
- Add TJ's Reviewed-by tag
- Use dma-buf:system_heap: in the subject since this is specific to the system heap, as per TJ.
- Remove extra space in if statement.Changes in v3:
- Remove defines for the orders as per Christian.
- Update the order array for 64k page sizes as per TJdrivers/dma-buf/heaps/system_heap.c | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-)drivers/dma-buf/heaps/system_heap.c +17
-2@@ -18,6 +18,7 @@#include <linux/mm.h> #include <linux/module.h> #include <linux/scatterlist.h> +#include <linux/sizes.h> #include <linux/slab.h> #include <linux/vmalloc.h> @@ -44,14 +45,28 @@ struct dma_heap_attachment {#define HIGH_ORDER_GFP (((GFP_HIGHUSER | __GFP_ZERO | __GFP_NOWARN \ | __GFP_NORETRY) & ~__GFP_RECLAIM) \ | __GFP_COMP) -static gfp_t order_flags[] = {HIGH_ORDER_GFP ,HIGH_ORDER_GFP ,LOW_ORDER_GFP };/* * The selection of the orders used for allocation (1MB, 64K, 4K) is designed * to match with the sizes often found in IOMMUs. Using order 4 pages instead * of order 0 pages can significantly improve the performance of many IOMMUs * by reducing TLB pressure and time spent updating page tables. +* +* Note: When the order is 0, the minimum allocation is PAGE_SIZE. The possible +* page sizes for ARM devices could be 4K, 16K and 64K. +*/ +#if (PAGE_SIZE ==SZ_64K ) +static gfp_t order_flags[] = {HIGH_ORDER_GFP ,LOW_ORDER_GFP }; +/* 1MiB allocs are calculated with (2 ^ (20 - PAGE_SHIFT)) * PAGE_SIZE = 1MiB */ +static const unsigned int orders[] = {20 -PAGE_SHIFT ,0 }; +#else +static gfp_t order_flags[] = {HIGH_ORDER_GFP ,HIGH_ORDER_GFP ,LOW_ORDER_GFP }; +/* +* 1MiB allocs are calculated with (2 ^ (20 - PAGE_SHIFT)) * PAGE_SIZE = 1MiB +* 64KiB allocs are calculated with (2 ^ (16 - PAGE_SHIFT)) * PAGE_SIZE = 64KiB */ -static const unsigned int orders[] = {8 ,4 ,0 }; +static const unsigned int orders[] = {20 -PAGE_SHIFT ,16 -PAGE_SHIFT ,0 }; +#endif +#define NUM_ORDERS ARRAY_SIZE(orders)static struct sg_table *dup_sg_table (struct sg_table *table)
drivers/dma-buf/heaps/system_heap.c static struct page *alloc_largest_available(unsigned long size, · line 339
Quoted 8 lines
drivers/dma-buf/heaps/system_heap.c +1
-1@@ -318,7 +333,7 @@ static struct page *alloc_largest_available(unsigned long size,int i;for (i =0 ; i <NUM_ORDERS ; i++) { -if (size < (PAGE_SIZE << orders[i])) +if (size < (PAGE_SIZE << orders[i]))continue ;if (max_order < orders[i])continue ;
Hello Juan,
I've posted a respin of the patch by extending upon your work, Can you please review?
Aplogies for adding signed-off by, will drop it in v2.
Quoted 86 lines · Pankaj Patil
Quoted 70 lines · Juan Yescas
This change sets the allocation orders for the different page sizes (4k, 16k, 64k) based on
PAGE_SHIFT. Before this change, the orders for large page sizes were calculated incorrectly, this caused system heap to allocate from 2% to 4% more memory on 16KiB page size kernels.This change was tested on 4k/16k page size kernels.
Signed-off-by Juan Yescas <[email protected]>Acked-by John Stultz <[email protected]>Reviewed-by T.J. Mercier <[email protected]>---
Changes in v2:
- Add John's Acked-by tag.
- Add TJ's Reviewed-by tag
- Use dma-buf:system_heap: in the subject since this is specific to the system heap, as per TJ.
- Remove extra space in if statement.Changes in v3:
- Remove defines for the orders as per Christian.
- Update the order array for 64k page sizes as per TJdrivers/dma-buf/heaps/system_heap.c | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-)drivers/dma-buf/heaps/system_heap.c +17
-2@@ -18,6 +18,7 @@#include <linux/mm.h> #include <linux/module.h> #include <linux/scatterlist.h> +#include <linux/sizes.h> #include <linux/slab.h> #include <linux/vmalloc.h> @@ -44,14 +45,28 @@ struct dma_heap_attachment {#define HIGH_ORDER_GFP (((GFP_HIGHUSER | __GFP_ZERO | __GFP_NOWARN \ | __GFP_NORETRY) & ~__GFP_RECLAIM) \ | __GFP_COMP) -static gfp_t order_flags[] = {HIGH_ORDER_GFP ,HIGH_ORDER_GFP ,LOW_ORDER_GFP };/* * The selection of the orders used for allocation (1MB, 64K, 4K) is designed * to match with the sizes often found in IOMMUs. Using order 4 pages instead * of order 0 pages can significantly improve the performance of many IOMMUs * by reducing TLB pressure and time spent updating page tables. +* +* Note: When the order is 0, the minimum allocation is PAGE_SIZE. The possible +* page sizes for ARM devices could be 4K, 16K and 64K. +*/ +#if (PAGE_SIZE ==SZ_64K ) +static gfp_t order_flags[] = {HIGH_ORDER_GFP ,LOW_ORDER_GFP }; +/* 1MiB allocs are calculated with (2 ^ (20 - PAGE_SHIFT)) * PAGE_SIZE = 1MiB */ +static const unsigned int orders[] = {20 -PAGE_SHIFT ,0 }; +#else +static gfp_t order_flags[] = {HIGH_ORDER_GFP ,HIGH_ORDER_GFP ,LOW_ORDER_GFP }; +/* +* 1MiB allocs are calculated with (2 ^ (20 - PAGE_SHIFT)) * PAGE_SIZE = 1MiB +* 64KiB allocs are calculated with (2 ^ (16 - PAGE_SHIFT)) * PAGE_SIZE = 64KiB */ -static const unsigned int orders[] = {8 ,4 ,0 }; +static const unsigned int orders[] = {20 -PAGE_SHIFT ,16 -PAGE_SHIFT ,0 }; +#endif +#define NUM_ORDERS ARRAY_SIZE(orders)static struct sg_table *dup_sg_table (struct sg_table *table)drivers/dma-buf/heaps/system_heap.c static struct page *alloc_largest_available(unsigned long size, · line 339
Quoted 8 lines
drivers/dma-buf/heaps/system_heap.c +1
-1@@ -318,7 +333,7 @@ static struct page *alloc_largest_available(unsigned long size,int i;for (i =0 ; i <NUM_ORDERS ; i++) { -if (size < (PAGE_SIZE << orders[i])) +if (size < (PAGE_SIZE << orders[i]))continue ;if (max_order < orders[i])continue ;Hello Juan,
I've posted a respin of the patch by extending upon your work, Can you please review?
Aplogies for adding signed-off by, will drop it in v2.
Quoted 3 lines
Hi Pankaj,
There is another change that fixes the problem and adds the 2MiB order. It has already been
reviewed the Christian König:
https://lore.kernel.org/all/[email protected]/