mm/cma: introduce interface for early reservations

It can be desirable to reserve memory in a CMA area before it is
activated, early in boot.  Such reservations would effectively be memblock
allocations, but they can be returned to the CMA area later.  This
functionality can be used to allow hugetlb bootmem allocations from a
hugetlb CMA area.

A new interface, cma_reserve_early is introduced.  This allows for
pageblock-aligned reservations.  These reservations are skipped during the
initial handoff of pages in a CMA area to the buddy allocator.  The caller
is responsible for making sure that the page structures are set up, and
that the migrate type is set correctly, as with other memblock allocations
that stick around.  If the CMA area fails to activate (because it
intersects with multiple zones), the reserved memory is not given to the
buddy allocator, the caller needs to take care of that.

Link: https://lkml.kernel.org/r/20250228182928.2645936-25-fvdl@google.com
Signed-off-by: Frank van der Linden <fvdl@google.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Dan Carpenter <dan.carpenter@linaro.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Joao Martins <joao.m.martins@oracle.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin (Cruise) <roman.gushchin@linux.dev>
Cc: Usama Arif <usamaarif642@gmail.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Yu Zhao <yuzhao@google.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 76 insertions, 7 deletions

diff --git a/mm/cma.c b/mm/cma.c
index 5e1d169e24fa..09322b8284bd 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -144,9 +144,10 @@ bool cma_validate_zones(struct cma *cma)
 
 static void __init cma_activate_area(struct cma *cma)
 {
-	unsigned long pfn, base_pfn;
+	unsigned long pfn, end_pfn;
 	int allocrange, r;
 	struct cma_memrange *cmr;
+	unsigned long bitmap_count, count;
 
 	for (allocrange = 0; allocrange < cma->nranges; allocrange++) {
 		cmr = &cma->ranges[allocrange];
@@ -161,8 +162,13 @@ static void __init cma_activate_area(struct cma *cma)
 
 	for (r = 0; r < cma->nranges; r++) {
 		cmr = &cma->ranges[r];
-		base_pfn = cmr->base_pfn;
-		for (pfn = base_pfn; pfn < base_pfn + cmr->count;
+		if (cmr->early_pfn != cmr->base_pfn) {
+			count = cmr->early_pfn - cmr->base_pfn;
+			bitmap_count = cma_bitmap_pages_to_bits(cma, count);
+			bitmap_set(cmr->bitmap, 0, bitmap_count);
+		}
+
+		for (pfn = cmr->early_pfn; pfn < cmr->base_pfn + cmr->count;
 		     pfn += pageblock_nr_pages)
 			init_cma_reserved_pageblock(pfn_to_page(pfn));
 	}
@@ -173,6 +179,7 @@ static void __init cma_activate_area(struct cma *cma)
 	INIT_HLIST_HEAD(&cma->mem_head);
 	spin_lock_init(&cma->mem_head_lock);
 #endif
+	set_bit(CMA_ACTIVATED, &cma->flags);
 
 	return;
 
@@ -184,9 +191,8 @@ cleanup:
 	if (!test_bit(CMA_RESERVE_PAGES_ON_ERROR, &cma->flags)) {
 		for (r = 0; r < allocrange; r++) {
 			cmr = &cma->ranges[r];
-			for (pfn = cmr->base_pfn;
-			     pfn < cmr->base_pfn + cmr->count;
-			     pfn++)
+			end_pfn = cmr->base_pfn + cmr->count;
+			for (pfn = cmr->early_pfn; pfn < end_pfn; pfn++)
 				free_reserved_page(pfn_to_page(pfn));
 		}
 	}
@@ -290,6 +296,7 @@ int __init cma_init_reserved_mem(phys_addr_t base, phys_addr_t size,
 		return ret;
 
 	cma->ranges[0].base_pfn = PFN_DOWN(base);
+	cma->ranges[0].early_pfn = PFN_DOWN(base);
 	cma->ranges[0].count = cma->count;
 	cma->nranges = 1;
 	cma->nid = NUMA_NO_NODE;
@@ -509,6 +516,7 @@ int __init cma_declare_contiguous_multi(phys_addr_t total_size,
 		    nr, (u64)mlp->base, (u64)mlp->base + size);
 		cmrp = &cma->ranges[nr++];
 		cmrp->base_pfn = PHYS_PFN(mlp->base);
+		cmrp->early_pfn = cmrp->base_pfn;
 		cmrp->count = size >> PAGE_SHIFT;
 
 		sizeleft -= size;
@@ -540,7 +548,6 @@ out:
 		pr_info("Reserved %lu MiB in %d range%s\n",
 			(unsigned long)total_size / SZ_1M, nr,
 			nr > 1 ? "s" : "");
-
 	return ret;
 }
 
@@ -1034,3 +1041,65 @@ bool cma_intersects(struct cma *cma, unsigned long start, unsigned long end)
 
 	return false;
 }
+
+/*
+ * Very basic function to reserve memory from a CMA area that has not
+ * yet been activated. This is expected to be called early, when the
+ * system is single-threaded, so there is no locking. The alignment
+ * checking is restrictive - only pageblock-aligned areas
+ * (CMA_MIN_ALIGNMENT_BYTES) may be reserved through this function.
+ * This keeps things simple, and is enough for the current use case.
+ *
+ * The CMA bitmaps have not yet been allocated, so just start
+ * reserving from the bottom up, using a PFN to keep track
+ * of what has been reserved. Unreserving is not possible.
+ *
+ * The caller is responsible for initializing the page structures
+ * in the area properly, since this just points to memblock-allocated
+ * memory. The caller should subsequently use init_cma_pageblock to
+ * set the migrate type and CMA stats  the pageblocks that were reserved.
+ *
+ * If the CMA area fails to activate later, memory obtained through
+ * this interface is not handed to the page allocator, this is
+ * the responsibility of the caller (e.g. like normal memblock-allocated
+ * memory).
+ */
+void __init *cma_reserve_early(struct cma *cma, unsigned long size)
+{
+	int r;
+	struct cma_memrange *cmr;
+	unsigned long available;
+	void *ret = NULL;
+
+	if (!cma || !cma->count)
+		return NULL;
+	/*
+	 * Can only be called early in init.
+	 */
+	if (test_bit(CMA_ACTIVATED, &cma->flags))
+		return NULL;
+
+	if (!IS_ALIGNED(size, CMA_MIN_ALIGNMENT_BYTES))
+		return NULL;
+
+	if (!IS_ALIGNED(size, (PAGE_SIZE << cma->order_per_bit)))
+		return NULL;
+
+	size >>= PAGE_SHIFT;
+
+	if (size > cma->available_count)
+		return NULL;
+
+	for (r = 0; r < cma->nranges; r++) {
+		cmr = &cma->ranges[r];
+		available = cmr->count - (cmr->early_pfn - cmr->base_pfn);
+		if (size <= available) {
+			ret = phys_to_virt(PFN_PHYS(cmr->early_pfn));
+			cmr->early_pfn += size;
+			cma->available_count -= size;
+			return ret;
+		}
+	}
+
+	return ret;
+}