[PATCH v2 1/8] memblock: Introduce MEMBLOCK_PTEMAP

[Vincent Donnefort]

Keeping PTE-level mappings is interesting on some architectures as it
allows mapping/unmapping pages from the kernel direct map without the
risk of splitting blocks which, under the break-before-make rule, may
trigger page-faults the kernel can't handle.

However, mapping the entire direct map at PTE-level is costly. So
instead, create a new memblock flag MEMBLOCK_PTEMAP to selectively apply
a PTE-level mapping.

Signed-off-by: Vincent Donnefort <vdonnefort at google.com>
---
 include/linux/memblock.h | 18 ++++++++++++++++++
 mm/memblock.c            | 30 ++++++++++++++++++++++++++++++
 2 files changed, 48 insertions(+)

diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index aa845f488327..13263055996d 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -52,6 +52,7 @@ extern unsigned long long max_possible_pfn;
  * kernel that we know is good to use. It is the only memory that
  * allocations may happen from in this phase.
  * @MEMBLOCK_RSRV_HUGETLB: memory is reserved for hugetlb pages
+ * @MEMBLOCK_PTEMAP: memory region to be mapped using PTE-level mapping
  */
 enum memblock_flags {
 	MEMBLOCK_NONE		= 0x0,	/* No special request */
@@ -63,6 +64,7 @@ enum memblock_flags {
 	MEMBLOCK_RSRV_KERN	= 0x20,	/* memory reserved for kernel use */
 	MEMBLOCK_KHO_SCRATCH	= 0x40,	/* scratch memory for kexec handover */
 	MEMBLOCK_RSRV_HUGETLB	= 0x80, /* memory reserved for hugetlb pages */
+	MEMBLOCK_PTEMAP		= 0x100,/* PTE-level mapping */
 };
 
 /**
@@ -160,6 +162,8 @@ int memblock_reserved_mark_noinit(phys_addr_t base, phys_addr_t size);
 int memblock_reserved_mark_kern(phys_addr_t base, phys_addr_t size);
 int memblock_mark_kho_scratch(phys_addr_t base, phys_addr_t size);
 int memblock_clear_kho_scratch(phys_addr_t base, phys_addr_t size);
+int memblock_mark_ptemap(phys_addr_t base, phys_addr_t size);
+int memblock_clear_ptemap(phys_addr_t base, phys_addr_t size);
 
 void memblock_free(void *ptr, size_t size);
 
@@ -285,8 +289,16 @@ static inline bool memblock_is_mirror(struct memblock_region *m)
 	return m->flags & MEMBLOCK_MIRROR;
 }
 
+static inline void memblock_warn_invalid_map_flags(struct memblock_region *m)
+{
+	enum memblock_flags map_flags = MEMBLOCK_NOMAP | MEMBLOCK_PTEMAP;
+
+	WARN_ON_ONCE((m->flags & map_flags) == map_flags);
+}
+
 static inline bool memblock_is_nomap(struct memblock_region *m)
 {
+	memblock_warn_invalid_map_flags(m);
 	return m->flags & MEMBLOCK_NOMAP;
 }
 
@@ -305,6 +317,12 @@ static inline bool memblock_is_kho_scratch(struct memblock_region *m)
 	return m->flags & MEMBLOCK_KHO_SCRATCH;
 }
 
+static inline bool memblock_is_ptemap(struct memblock_region *m)
+{
+	memblock_warn_invalid_map_flags(m);
+	return m->flags & MEMBLOCK_PTEMAP;
+}
+
 int memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn,
 			    unsigned long  *end_pfn);
 void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn,
diff --git a/mm/memblock.c b/mm/memblock.c
index ea0de4b5f356..8a87d4d2516d 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1204,6 +1204,35 @@ __init int memblock_clear_kho_scratch(phys_addr_t base, phys_addr_t size)
 				    MEMBLOCK_KHO_SCRATCH);
 }
 
+/**
+ * memblock_mark_ptemap - Mark a memory region with flag MEMBLOCK_PTEMAP.
+ * @base: the base phys addr of the region
+ * @size: the size of the region
+ *
+ * If supported by the architecture, such region is mapped using PTE-level
+ * mappings in the kernel direct map.
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+int __init_memblock memblock_mark_ptemap(phys_addr_t base, phys_addr_t size)
+{
+	return memblock_setclr_flag(&memblock.memory, base, size, 1,
+				    MEMBLOCK_PTEMAP);
+}
+
+/**
+ * memblock_clear_ptemap - Clear flag MEMBLOCK_PTEMAP for a specified region.
+ * @base: the base phys addr of the region
+ * @size: the size of the region
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+int __init_memblock memblock_clear_ptemap(phys_addr_t base, phys_addr_t size)
+{
+	return memblock_setclr_flag(&memblock.memory, base, size, 0,
+				    MEMBLOCK_PTEMAP);
+}
+
 static bool should_skip_region(struct memblock_type *type,
 			       struct memblock_region *m,
 			       int nid, int flags)
@@ -2880,6 +2909,7 @@ static const char * const flagname[] = {
 	[ilog2(MEMBLOCK_RSRV_KERN)] = "RSV_KERN",
 	[ilog2(MEMBLOCK_KHO_SCRATCH)] = "KHO_SCRATCH",
 	[ilog2(MEMBLOCK_RSRV_HUGETLB)] = "RSV_HUGETLB",
+	[ilog2(MEMBLOCK_PTEMAP)] = "PTEMAP",
 };
 
 static int memblock_debug_show(struct seq_file *m, void *private)
-- 
2.55.0.1082.g2b9226bbc0-goog