mm/memblock: allocate boot time data structures from mirrored memory

Try to allocate all boot time kernel data structures from mirrored
memory.

If we run out of mirrored memory print warnings, but fall back to using
non-mirrored memory to make sure that we still boot.

By number of bytes, most of what we allocate at boot time is the page
structures.  64 bytes per 4K page on x86_64 ...  or about 1.5% of total
system memory.  For workloads where the bulk of memory is allocated to
applications this may represent a useful improvement to system
availability since 1.5% of total memory might be a third of the memory
allocated to the kernel.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Cc: Xishi Qiu <qiuxishi@huawei.com>
Cc: Hanjun Guo <guohanjun@huawei.com>
Cc: Xiexiuqi <xiexiuqi@huawei.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/memblock.h

@@ -24,6 +24,7 @@
 enum {
 	MEMBLOCK_NONE		= 0x0,	/* No special request */
 	MEMBLOCK_HOTPLUG	= 0x1,	/* hotpluggable region */
+	MEMBLOCK_MIRROR		= 0x2,	/* mirrored region */
 };
 
 struct memblock_region {
@@ -78,6 +79,8 @@ int memblock_reserve(phys_addr_t base, phys_addr_t size);
 void memblock_trim_memory(phys_addr_t align);
 int memblock_mark_hotplug(phys_addr_t base, phys_addr_t size);
 int memblock_clear_hotplug(phys_addr_t base, phys_addr_t size);
+int memblock_mark_mirror(phys_addr_t base, phys_addr_t size);
+ulong choose_memblock_flags(void);
 
 /* Low level functions */
 int memblock_add_range(struct memblock_type *type,
@@ -160,6 +163,11 @@ static inline bool movable_node_is_enabled(void)
 }
 #endif
 
+static inline bool memblock_is_mirror(struct memblock_region *m)
+{
+	return m->flags & MEMBLOCK_MIRROR;
+}
+
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 int memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn,
 			    unsigned long  *end_pfn);

mm/memblock.c

@@ -54,10 +54,16 @@ int memblock_debug __initdata_memblock;
 #ifdef CONFIG_MOVABLE_NODE
 bool movable_node_enabled __initdata_memblock = false;
 #endif
+static bool system_has_some_mirror __initdata_memblock = false;
 static int memblock_can_resize __initdata_memblock;
 static int memblock_memory_in_slab __initdata_memblock = 0;
 static int memblock_reserved_in_slab __initdata_memblock = 0;
 
+ulong __init_memblock choose_memblock_flags(void)
+{
+	return system_has_some_mirror ? MEMBLOCK_MIRROR : MEMBLOCK_NONE;
+}
+
 /* inline so we don't get a warning when pr_debug is compiled out */
 static __init_memblock const char *
 memblock_type_name(struct memblock_type *type)
@@ -259,8 +265,21 @@ phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start,
 					phys_addr_t end, phys_addr_t size,
 					phys_addr_t align)
 {
-	return memblock_find_in_range_node(size, align, start, end,
-					    NUMA_NO_NODE, MEMBLOCK_NONE);
+	phys_addr_t ret;
+	ulong flags = choose_memblock_flags();
+
+again:
+	ret = memblock_find_in_range_node(size, align, start, end,
+					    NUMA_NO_NODE, flags);
+
+	if (!ret && (flags & MEMBLOCK_MIRROR)) {
+		pr_warn("Could not allocate %pap bytes of mirrored memory\n",
+			&size);
+		flags &= ~MEMBLOCK_MIRROR;
+		goto again;
+	}
+
+	return ret;
 }
 
 static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r)
@@ -785,6 +804,21 @@ int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size)
 	return memblock_setclr_flag(base, size, 0, MEMBLOCK_HOTPLUG);
 }
 
+/**
+ * memblock_mark_mirror - Mark mirrored memory with flag MEMBLOCK_MIRROR.
+ * @base: the base phys addr of the region
+ * @size: the size of the region
+ *
+ * Return 0 on succees, -errno on failure.
+ */
+int __init_memblock memblock_mark_mirror(phys_addr_t base, phys_addr_t size)
+{
+	system_has_some_mirror = true;
+
+	return memblock_setclr_flag(base, size, 1, MEMBLOCK_MIRROR);
+}
+
+
 /**
  * __next__mem_range - next function for for_each_free_mem_range() etc.
  * @idx: pointer to u64 loop variable
@@ -839,6 +873,10 @@ void __init_memblock __next_mem_range(u64 *idx, int nid, ulong flags,
 		if (movable_node_is_enabled() && memblock_is_hotpluggable(m))
 			continue;
 
+		/* if we want mirror memory skip non-mirror memory regions */
+		if ((flags & MEMBLOCK_MIRROR) && !memblock_is_mirror(m))
+			continue;
+
 		if (!type_b) {
 			if (out_start)
 				*out_start = m_start;
@@ -944,6 +982,10 @@ void __init_memblock __next_mem_range_rev(u64 *idx, int nid, ulong flags,
 		if (movable_node_is_enabled() && memblock_is_hotpluggable(m))
 			continue;
 
+		/* if we want mirror memory skip non-mirror memory regions */
+		if ((flags & MEMBLOCK_MIRROR) && !memblock_is_mirror(m))
+			continue;
+
 		if (!type_b) {
 			if (out_start)
 				*out_start = m_start;
@@ -1096,8 +1138,18 @@ static phys_addr_t __init memblock_alloc_base_nid(phys_addr_t size,
 
 phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid)
 {
-	return memblock_alloc_base_nid(size, align, MEMBLOCK_ALLOC_ACCESSIBLE,
-				       nid, MEMBLOCK_NONE);
+	ulong flags = choose_memblock_flags();
+	phys_addr_t ret;
+
+again:
+	ret = memblock_alloc_base_nid(size, align, MEMBLOCK_ALLOC_ACCESSIBLE,
+				      nid, flags);
+
+	if (!ret && (flags & MEMBLOCK_MIRROR)) {
+		flags &= ~MEMBLOCK_MIRROR;
+		goto again;
+	}
+	return ret;
 }
 
 phys_addr_t __init __memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
@@ -1167,6 +1219,7 @@ static void * __init memblock_virt_alloc_internal(
 {
 	phys_addr_t alloc;
 	void *ptr;
+	ulong flags = choose_memblock_flags();
 
 	if (WARN_ONCE(nid == MAX_NUMNODES, "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n"))
 		nid = NUMA_NO_NODE;
@@ -1187,14 +1240,14 @@ static void * __init memblock_virt_alloc_internal(
 
 again:
 	alloc = memblock_find_in_range_node(size, align, min_addr, max_addr,
-					    nid, MEMBLOCK_NONE);
+					    nid, flags);
 	if (alloc)
 		goto done;
 
 	if (nid != NUMA_NO_NODE) {
 		alloc = memblock_find_in_range_node(size, align, min_addr,
 						    max_addr, NUMA_NO_NODE,
-						    MEMBLOCK_NONE);
+						    flags);
 		if (alloc)
 			goto done;
 	}
@@ -1202,10 +1255,16 @@ again:
 	if (min_addr) {
 		min_addr = 0;
 		goto again;
-	} else {
-		goto error;
 	}
 
+	if (flags & MEMBLOCK_MIRROR) {
+		flags &= ~MEMBLOCK_MIRROR;
+		pr_warn("Could not allocate %pap bytes of mirrored memory\n",
+			&size);
+		goto again;
+	}
+
+	return NULL;
 done:
 	memblock_reserve(alloc, size);
 	ptr = phys_to_virt(alloc);
@@ -1220,9 +1279,6 @@ done:
 	kmemleak_alloc(ptr, size, 0, 0);
 
 	return ptr;
-
-error:
-	return NULL;
 }
 
 /**

mm/nobootmem.c

@@ -37,12 +37,20 @@ static void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
 {
 	void *ptr;
 	u64 addr;
+	ulong flags = choose_memblock_flags();
 
 	if (limit > memblock.current_limit)
 		limit = memblock.current_limit;
 
+again:
 	addr = memblock_find_in_range_node(size, align, goal, limit, nid,
-					   MEMBLOCK_NONE);
+					   flags);
+	if (!addr && (flags & MEMBLOCK_MIRROR)) {
+		flags &= ~MEMBLOCK_MIRROR;
+		pr_warn("Could not allocate %pap bytes of mirrored memory\n",
+			&size);
+		goto again;
+	}
 	if (!addr)
 		return NULL;