[RFC PATCH 06/12] mm/cma: define and act on CMA_BALANCE flag

Frank van der Linden posted 12 patches 2 weeks, 2 days ago
[RFC PATCH 06/12] mm/cma: define and act on CMA_BALANCE flag
Posted by Frank van der Linden 2 weeks, 2 days ago
When the CMA_BALANCE flag is set for a CMA area, it means that
it opts in to CMA balancing. This means two things:

1) It allows movable allocations to be migrated in to it in
   the case of a CMA inbalance (too much free memory in CMA
   pageblocks as compared to other pageblocks).
2) It is allocated top-down, so that compaction will end up
   migrating pages in to it. Doing this will make sure that
   compaction doesn't aggrevate a CMA imbalance, and that it
   won't fight with CMA balance migration from non-CMA to
   CMA.

Signed-off-by: Frank van der Linden <fvdl@google.com>
---
 include/linux/cma.h |  4 +++-
 mm/cma.c            | 33 ++++++++++++++++++++++++++-------
 2 files changed, 29 insertions(+), 8 deletions(-)

diff --git a/include/linux/cma.h b/include/linux/cma.h
index 0504580d61d0..6e98a516b336 100644
--- a/include/linux/cma.h
+++ b/include/linux/cma.h
@@ -26,6 +26,7 @@ enum cma_flags {
 	__CMA_ZONES_INVALID,
 	__CMA_ACTIVATED,
 	__CMA_FIXED,
+	__CMA_BALANCE,
 };
 
 #define CMA_RESERVE_PAGES_ON_ERROR	BIT(__CMA_RESERVE_PAGES_ON_ERROR)
@@ -33,8 +34,9 @@ enum cma_flags {
 #define CMA_ZONES_INVALID		BIT(__CMA_ZONES_INVALID)
 #define CMA_ACTIVATED			BIT(__CMA_ACTIVATED)
 #define CMA_FIXED			BIT(__CMA_FIXED)
+#define CMA_BALANCE			BIT(__CMA_BALANCE)
 
-#define CMA_INIT_FLAGS (CMA_FIXED|CMA_RESERVE_PAGES_ON_ERROR)
+#define CMA_INIT_FLAGS (CMA_FIXED|CMA_RESERVE_PAGES_ON_ERROR|CMA_BALANCE)
 
 struct cma;
 struct zone;
diff --git a/mm/cma.c b/mm/cma.c
index 53cb1833407b..6050d57f3c2e 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -272,6 +272,9 @@ static bool cma_next_free_range(struct cma_memrange *cmr,
 static inline bool cma_should_balance_range(struct zone *zone,
 				      struct cma_memrange *cmr)
 {
+	if (!(cmr->cma->flags & CMA_BALANCE))
+		return false;
+
 	if (page_zone(pfn_to_page(cmr->base_pfn)) != zone)
 		return false;
 
@@ -527,6 +530,12 @@ static bool __init basecmp(struct cma_init_memrange *mlp,
 	return mlp->base < mrp->base;
 }
 
+static bool __init revbasecmp(struct cma_init_memrange *mlp,
+			   struct cma_init_memrange *mrp)
+{
+	return mlp->base > mrp->base;
+}
+
 /*
  * Helper function to create sorted lists.
  */
@@ -575,7 +584,8 @@ static int __init cma_fixed_reserve(phys_addr_t base, phys_addr_t size)
 }
 
 static phys_addr_t __init cma_alloc_mem(phys_addr_t base, phys_addr_t size,
-			phys_addr_t align, phys_addr_t limit, int nid)
+			phys_addr_t align, phys_addr_t limit, int nid,
+			unsigned long flags)
 {
 	phys_addr_t addr = 0;
 
@@ -588,7 +598,8 @@ static phys_addr_t __init cma_alloc_mem(phys_addr_t base, phys_addr_t size,
 	 * like DMA/DMA32.
 	 */
 #ifdef CONFIG_PHYS_ADDR_T_64BIT
-	if (!memblock_bottom_up() && limit >= SZ_4G + size) {
+	if (!(flags & CMA_BALANCE) && !memblock_bottom_up()
+			&& limit >= SZ_4G + size) {
 		memblock_set_bottom_up(true);
 		addr = memblock_alloc_range_nid(size, align, SZ_4G, limit,
 						nid, true);
@@ -695,7 +706,7 @@ static int __init __cma_declare_contiguous_nid(phys_addr_t *basep,
 		if (ret)
 			return ret;
 	} else {
-		base = cma_alloc_mem(base, size, alignment, limit, nid);
+		base = cma_alloc_mem(base, size, alignment, limit, nid, flags);
 		if (!base)
 			return -ENOMEM;
 
@@ -851,7 +862,10 @@ int __init cma_declare_contiguous_multi(phys_addr_t total_size,
 	list_for_each_safe(mp, next, &ranges) {
 		mlp = list_entry(mp, struct cma_init_memrange, list);
 		list_del(mp);
-		list_insert_sorted(&final_ranges, mlp, basecmp);
+		if (flags & CMA_BALANCE)
+			list_insert_sorted(&final_ranges, mlp, revbasecmp);
+		else
+			list_insert_sorted(&final_ranges, mlp, basecmp);
 		sizesum += mlp->size;
 		if (sizesum >= total_size)
 			break;
@@ -866,7 +880,12 @@ int __init cma_declare_contiguous_multi(phys_addr_t total_size,
 	list_for_each(mp, &final_ranges) {
 		mlp = list_entry(mp, struct cma_init_memrange, list);
 		size = min(sizeleft, mlp->size);
-		if (memblock_reserve(mlp->base, size)) {
+		if (flags & CMA_BALANCE)
+			start = (mlp->base + mlp->size - size);
+		else
+			start = mlp->base;
+
+		if (memblock_reserve(start, size)) {
 			/*
 			 * Unexpected error. Could go on to
 			 * the next one, but just abort to
@@ -877,9 +896,9 @@ int __init cma_declare_contiguous_multi(phys_addr_t total_size,
 		}
 
 		pr_debug("created region %d: %016llx - %016llx\n",
-		    nr, (u64)mlp->base, (u64)mlp->base + size);
+		    nr, (u64)start, (u64)start + size);
 		cmrp = &cma->ranges[nr++];
-		cmrp->base_pfn = PHYS_PFN(mlp->base);
+		cmrp->base_pfn = PHYS_PFN(start);
 		cmrp->early_pfn = cmrp->base_pfn;
 		cmrp->count = size >> PAGE_SHIFT;
 		cmrp->cma = cma;
-- 
2.51.0.384.g4c02a37b29-goog
Re: [RFC PATCH 06/12] mm/cma: define and act on CMA_BALANCE flag
Posted by Rik van Riel 2 weeks, 1 day ago
On Mon, 2025-09-15 at 19:51 +0000, Frank van der Linden wrote:
> 
> @@ -851,7 +862,10 @@ int __init
> cma_declare_contiguous_multi(phys_addr_t total_size,
>  	list_for_each_safe(mp, next, &ranges) {
>  		mlp = list_entry(mp, struct cma_init_memrange,
> list);
>  		list_del(mp);
> -		list_insert_sorted(&final_ranges, mlp, basecmp);
> +		if (flags & CMA_BALANCE)
> +			list_insert_sorted(&final_ranges, mlp,
> revbasecmp);
> +		else
> +			list_insert_sorted(&final_ranges, mlp,
> basecmp);
>  		sizesum += mlp->size;
>  		if (sizesum >= total_size)
>  			break;

Wait, what is this supposed to do when presented
with a mix of CMA_BALANCE and !CMA_BALANCE ranges?

I can't convince myself this would always keep
the CMA_BALANCE range near the top of the list,
and the others near the bottom.

Also, does the regular compaction code pay any
attention to the order of this list?

I have the feeling I am overlooking something big
in how this patch is supposed to work, but I am
not sure what that would be...

> @@ -866,7 +880,12 @@ int __init
> cma_declare_contiguous_multi(phys_addr_t total_size,
>  	list_for_each(mp, &final_ranges) {
>  		mlp = list_entry(mp, struct cma_init_memrange,
> list);
>  		size = min(sizeleft, mlp->size);
> -		if (memblock_reserve(mlp->base, size)) {
> +		if (flags & CMA_BALANCE)
> +			start = (mlp->base + mlp->size - size);
> +		else
> +			start = mlp->base;
> +
> +		if (memblock_reserve(start, size)) {
>  			/*
>  			 * Unexpected error. Could go on to
>  			 * the next one, but just abort to
> 

-- 
All Rights Reversed.