Add a new memory state "nomap" to memblock. This can be used to truncate
the usable memory in the system without forgetting about what is really
installed.
Signed-off-by: Philipp Hachtmann <phacht@xxxxxxxxxxxxxxxxxx>
---
include/linux/memblock.h | 50 ++++++--
mm/memblock.c | 307 +++++++++++++++++++++++++++++++++--------------
mm/nobootmem.c | 9 ++
3 files changed, 267 insertions(+), 99 deletions(-)
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 1ef6636..2333d3f 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -18,6 +18,7 @@
#include <linux/mm.h>
#define INIT_MEMBLOCK_REGIONS 128
+#define INIT_MEMBLOCK_NOMAP_REGIONS 4
/* Definition of memblock flags. */
#define MEMBLOCK_HOTPLUG 0x1 /* hotpluggable region */
@@ -43,6 +44,9 @@ struct memblock {
phys_addr_t current_limit;
struct memblock_type memory;
struct memblock_type reserved;
+#ifdef CONFIG_ARCH_MEMBLOCK_NOMAP
+ struct memblock_type nomap;
+#endif
};
extern struct memblock memblock;
@@ -68,6 +72,10 @@ int memblock_add(phys_addr_t base, phys_addr_t size);
int memblock_remove(phys_addr_t base, phys_addr_t size);
int memblock_free(phys_addr_t base, phys_addr_t size);
int memblock_reserve(phys_addr_t base, phys_addr_t size);
+#ifdef CONFIG_ARCH_MEMBLOCK_NOMAP
+int memblock_nomap(phys_addr_t base, phys_addr_t size);
+int memblock_remap(phys_addr_t base, phys_addr_t size);
+#endif
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);
@@ -113,8 +121,9 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn,
i >= 0; __next_mem_pfn_range(&i, nid, p_start, p_end, p_nid))
#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
-void __next_free_mem_range(u64 *idx, int nid, phys_addr_t *out_start,
- phys_addr_t *out_end, int *out_nid);
+void __next_mem_range(u64 *idx, int nid, struct memblock_type *type_a,
+ struct memblock_type *type_b, phys_addr_t *out_start,
+ phys_addr_t *out_end, int *out_nid);
/**
* for_each_free_mem_range - iterate through free memblock areas
@@ -129,12 +138,31 @@ void __next_free_mem_range(u64 *idx, int nid, phys_addr_t *out_start,
*/
#define for_each_free_mem_range(i, nid, p_start, p_end, p_nid) \
for (i = 0, \
- __next_free_mem_range(&i, nid, p_start, p_end, p_nid); \
+ __next_mem_range(&i, nid, &memblock.memory, \
+ &memblock.reserved, p_start, \
+ p_end, p_nid); \
+ i != (u64)ULLONG_MAX; \
+ __next_mem_range(&i, nid, &memblock.memory, \
+ &memblock.reserved, \
+ p_start, p_end, p_nid))
+
+#ifdef CONFIG_ARCH_MEMBLOCK_NOMAP
+#define for_each_mapped_mem_range(i, nid, p_start, p_end, p_nid) \
+ for (i = 0, \
+ __next_mem_range(&i, nid, &memblock.memory, \
+ &memblock.nomap, p_start, \
+ p_end, p_nid); \
i != (u64)ULLONG_MAX; \
- __next_free_mem_range(&i, nid, p_start, p_end, p_nid))
+ __next_mem_range(&i, nid, &memblock.memory, \
+ &memblock.nomap, \
+ p_start, p_end, p_nid))
+#endif
-void __next_free_mem_range_rev(u64 *idx, int nid, phys_addr_t *out_start,
- phys_addr_t *out_end, int *out_nid);
+void __next_mem_range_rev(u64 *idx, int nid,
+ struct memblock_type *type_a,
+ struct memblock_type *type_b,
+ phys_addr_t *out_start,
+ phys_addr_t *out_end, int *out_nid);
/**
* for_each_free_mem_range_reverse - rev-iterate through free memblock areas
@@ -149,9 +177,15 @@ void __next_free_mem_range_rev(u64 *idx, int nid, phys_addr_t *out_start,
*/
#define for_each_free_mem_range_reverse(i, nid, p_start, p_end, p_nid) \
for (i = (u64)ULLONG_MAX, \
- __next_free_mem_range_rev(&i, nid, p_start, p_end, p_nid); \
+ __next_mem_range_rev(&i, nid, \
+ &memblock.memory, \
+ &memblock.reserved, \
+ p_start, p_end, p_nid); \
i != (u64)ULLONG_MAX; \
- __next_free_mem_range_rev(&i, nid, p_start, p_end, p_nid))
+ __next_mem_range_rev(&i, nid, \
+ &memblock.memory, \
+ &memblock.reserved, \
+ p_start, p_end, p_nid))
static inline void memblock_set_region_flags(struct memblock_region *r,
unsigned long flags)
diff --git a/mm/memblock.c b/mm/memblock.c
index 9c0aeef..dba3252 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -28,6 +28,11 @@
static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock;
static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock;
+#ifdef CONFIG_ARCH_MEMBLOCK_NOMAP
+static struct memblock_region
+memblock_nomap_init_regions[INIT_MEMBLOCK_NOMAP_REGIONS] __initdata_memblock;
+#endif
+
struct memblock memblock __initdata_memblock = {
.memory.regions = memblock_memory_init_regions,
.memory.cnt = 1, /* empty dummy entry */
@@ -37,6 +42,11 @@ struct memblock memblock __initdata_memblock = {
.reserved.cnt = 1, /* empty dummy entry */
.reserved.max = INIT_MEMBLOCK_REGIONS,
+#ifdef CONFIG_ARCH_MEMBLOCK_NOMAP
+ .nomap.regions = memblock_nomap_init_regions,
+ .nomap.cnt = 1, /* empty dummy entry */
+ .nomap.max = INIT_MEMBLOCK_NOMAP_REGIONS,
+#endif
.bottom_up = false,
.current_limit = MEMBLOCK_ALLOC_ANYWHERE,
};
@@ -292,7 +302,21 @@ phys_addr_t __init_memblock get_allocated_memblock_memory_regions_info(
memblock.memory.max);
}
-#endif
+#ifdef CONFIG_ARCH_MEMBLOCK_NOMAP
+phys_addr_t __init_memblock get_allocated_memblock_nomap_regions_info(
+ phys_addr_t *addr)
+{
+ if (memblock.memory.regions == memblock_memory_init_regions)
+ return 0;
+
+ *addr = __pa(memblock.memory.regions);
+
+ return PAGE_ALIGN(sizeof(struct memblock_region) *
+ memblock.memory.max);
+}
+
+#endif /* CONFIG_ARCH_MEMBLOCK_NOMAP */
+#endif /* CONFIG_ARCH_DISCARD_MEMBLOCK */
/**
* memblock_double_array - double the size of the memblock regions array
@@ -757,18 +781,76 @@ int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size)
return 0;
}
+#ifdef CONFIG_ARCH_MEMBLOCK_NOMAP
+/*
+ * memblock_nomap() - mark a memory range as completely unusable
+ *
+ * This can be used to exclude memory regions from every further treatment
+ * in the running system. Ranges which are added to the nomap list will
+ * also be marked as reserved. So they won't either be allocated by memblock
+ * nor freed to the page allocator.
+ *
+ * The usable (i.e. not in nomap list) memory can be iterated
+ * via for_each_mapped_mem_range().
+ *
+ * memblock_start_of_DRAM() and memblock_end_of_DRAM() still refer to the
+ * whole system memory.
+ */
+int __init_memblock memblock_nomap(phys_addr_t base, phys_addr_t size)
+{
+ int ret;
+ memblock_dbg("memblock_nomap: [%#016llx-%#016llx] %pF\n",
+ (unsigned long long)base,
+ (unsigned long long)base + size,
+ (void *)_RET_IP_);
+
+ ret = memblock_add_region(&memblock.reserved, base, size, MAX_NUMNODES);
+ if (ret)
+ return ret;
+
+ return memblock_add_region(&memblock.nomap, base, size, MAX_NUMNODES);
+}
+
+/*
+ * memblock_remap() - remove a memory range from the nomap list
+ *
+ * This is the inverse function to memblock_nomap().
+ */
+int __init_memblock memblock_remap(phys_addr_t base, phys_addr_t size)
+{
+ int ret;
+ memblock_dbg("memblock_remap: [%#016llx-%#016llx] %pF\n",
+ (unsigned long long)base,
+ (unsigned long long)base + size,
+ (void *)_RET_IP_);
+
+ ret = __memblock_remove(&memblock.reserved, base, size);
+ if (ret)
+ return ret;
+
+ return __memblock_remove(&memblock.nomap, base, size);
+}
+
+#endif
+
/**
- * __next_free_mem_range - next function for for_each_free_mem_range()
+ * __next_mem_range - generic next function for for_each_*_range()
+ *
+ * Finds the next range from type_a which is not marked as unsuitable
+ * in type_b.
+ *
* @idx: pointer to u64 loop variable
- * @nid: node selector, %NUMA_NO_NODE for all nodes
+ * @nid: node selector, %MAX_NUMNODES for all nodes
+ * @type_a: pointer to memblock_type from where the range is taken
+ * @type_b: pointer to memblock_type which excludes memory from being taken
* @out_start: ptr to phys_addr_t for start address of the range, can be %NULL
* @out_end: ptr to phys_addr_t for end address of the range, can be %NULL
* @out_nid: ptr to int for nid of the range, can be %NULL
*
- * Find the first free area from *@idx which matches @nid, fill the out
+ * Find the first present area from *@idx which matches @nid, fill the out
* parameters, and update *@idx for the next iteration. The lower 32bit of
- * *@idx contains index into memory region and the upper 32bit indexes the
- * areas before each reserved region. For example, if reserved regions
+ * *@idx contains index into type_a region and the upper 32bit indexes the
+ * areas before each type_b region. For example, if type_a regions
* look like the following,
*
* 0:[0-16), 1:[32-48), 2:[128-130)
@@ -780,135 +862,178 @@ int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size)
* As both region arrays are sorted, the function advances the two indices
* in lockstep and returns each intersection.
*/
-void __init_memblock __next_free_mem_range(u64 *idx, int nid,
- phys_addr_t *out_start,
- phys_addr_t *out_end, int *out_nid)
+void __init_memblock __next_mem_range(u64 *idx, int nid,
+ struct memblock_type *type_a,
+ struct memblock_type *type_b,
+ phys_addr_t *out_start,
+ phys_addr_t *out_end, int *out_nid)
{
- struct memblock_type *mem = &memblock.memory;
- struct memblock_type *rsv = &memblock.reserved;
- int mi = *idx & 0xffffffff;
- int ri = *idx >> 32;
+ int idx_a = *idx & 0xffffffff;
+ int idx_b = *idx >> 32;
if (WARN_ONCE(nid == MAX_NUMNODES, "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n"))
nid = NUMA_NO_NODE;
- for ( ; mi < mem->cnt; mi++) {
- struct memblock_region *m = &mem->regions[mi];
+ for (; idx_a < type_a->cnt; idx_a++) {
+ struct memblock_region *m = &type_a->regions[idx_a];
phys_addr_t m_start = m->base;
phys_addr_t m_end = m->base + m->size;
+ int m_nid = memblock_get_region_node(m);
/* only memory regions are associated with nodes, check it */
- if (nid != NUMA_NO_NODE && nid != memblock_get_region_node(m))
+ if (nid != MAX_NUMNODES && nid != memblock_get_region_node(m))
continue;
- /* scan areas before each reservation for intersection */
- for ( ; ri < rsv->cnt + 1; ri++) {
- struct memblock_region *r = &rsv->regions[ri];
- phys_addr_t r_start = ri ? r[-1].base + r[-1].size : 0;
- phys_addr_t r_end = ri < rsv->cnt ? r->base : ULLONG_MAX;
-
- /* if ri advanced past mi, break out to advance mi */
- if (r_start >= m_end)
- break;
- /* if the two regions intersect, we're done */
- if (m_start < r_end) {
- if (out_start)
- *out_start = max(m_start, r_start);
- if (out_end)
- *out_end = min(m_end, r_end);
- if (out_nid)
- *out_nid = memblock_get_region_node(m);
+ /* With type_b NULL we only iterate through type_a */
+ if (type_b == NULL) {
+ if (out_start)
+ *out_start = m_start;
+ if (out_end)
+ *out_end = m_end;
+ if (out_nid)
+ *out_nid = m_nid;
+ idx_a++;
+ *idx = (u32)idx_a;
+ return;
+ } else {
+ /* scan areas before each reservation */
+ for (; idx_b < type_b->cnt + 1; idx_b++) {
+ struct memblock_region *r;
+ phys_addr_t r_start;
+ phys_addr_t r_end;
+
+ r = &type_b->regions[idx_b];
+ r_start = idx_b ? r[-1].base + r[-1].size : 0;
+ r_end = idx_b < type_b->cnt ?
+ r->base : ULLONG_MAX;
+
/*
- * The region which ends first is advanced
- * for the next iteration.
+ *if idx_b advanced past idx_a,
+ * break out to advance idx_a
*/
- if (m_end <= r_end)
- mi++;
- else
- ri++;
- *idx = (u32)mi | (u64)ri << 32;
- return;
+ if (r_start >= m_end)
+ break;
+ /* if the two regions intersect, we're done */
+ if (m_start < r_end) {
+ if (out_start)
+ *out_start =
+ max(m_start, r_start);
+ if (out_end)
+ *out_end = min(m_end, r_end);
+ if (out_nid)
+ *out_nid = m_nid;
+
+ /*
+ * The region which ends first is
+ * advanced for the next iteration.
+ */
+ if (m_end <= r_end)
+ idx_a++;
+ else
+ idx_b++;
+ *idx = (u32)idx_a | (u64)idx_b << 32;
+ return;
+ }
}
}
}
-
/* signal end of iteration */
*idx = ULLONG_MAX;
}
/**
- * __next_free_mem_range_rev - next function for for_each_free_mem_range_reverse()
+ * __next_mem_range_rev - generic next function for for_each_*_range_rev()
+ *
+ * Finds the next range from type_a which is not marked as unsuitable
+ * in type_b.
+ *
* @idx: pointer to u64 loop variable
- * @nid: nid: node selector, %NUMA_NO_NODE for all nodes
+ * @nid: nid: node selector, %MAX_NUMNODES for all nodes
+ * @type_a: pointer to memblock_type from where the range is taken
+ * @type_b: pointer to memblock_type which excludes memory from being taken
* @out_start: ptr to phys_addr_t for start address of the range, can be %NULL
* @out_end: ptr to phys_addr_t for end address of the range, can be %NULL
* @out_nid: ptr to int for nid of the range, can be %NULL
*
- * Reverse of __next_free_mem_range().
- *
- * Linux kernel cannot migrate pages used by itself. Memory hotplug users won't
- * be able to hot-remove hotpluggable memory used by the kernel. So this
- * function skip hotpluggable regions if needed when allocating memory for the
- * kernel.
+ * Reverse of __next_mem_range().
*/
-void __init_memblock __next_free_mem_range_rev(u64 *idx, int nid,
- phys_addr_t *out_start,
- phys_addr_t *out_end, int *out_nid)
+void __init_memblock __next_mem_range_rev(u64 *idx, int nid,
+ struct memblock_type *type_a,
+ struct memblock_type *type_b,
+ phys_addr_t *out_start,
+ phys_addr_t *out_end, int *out_nid)
{
- struct memblock_type *mem = &memblock.memory;
- struct memblock_type *rsv = &memblock.reserved;
- int mi = *idx & 0xffffffff;
- int ri = *idx >> 32;
+ int idx_a = *idx & 0xffffffff;
+ int idx_b = *idx >> 32;
if (WARN_ONCE(nid == MAX_NUMNODES, "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n"))
nid = NUMA_NO_NODE;
if (*idx == (u64)ULLONG_MAX) {
- mi = mem->cnt - 1;
- ri = rsv->cnt;
+ idx_a = type_a->cnt - 1;
+ idx_b = type_b->cnt;
}
- for ( ; mi >= 0; mi--) {
- struct memblock_region *m = &mem->regions[mi];
+ for (; idx_a >= 0; idx_a--) {
+ struct memblock_region *m = &type_a->regions[idx_a];
phys_addr_t m_start = m->base;
phys_addr_t m_end = m->base + m->size;
/* only memory regions are associated with nodes, check it */
- if (nid != NUMA_NO_NODE && nid != memblock_get_region_node(m))
+ if (nid != MAX_NUMNODES && nid != memblock_get_region_node(m))
continue;
- /* skip hotpluggable memory regions if needed */
- if (movable_node_is_enabled() && memblock_is_hotpluggable(m))
- continue;
-
- /* scan areas before each reservation for intersection */
- for ( ; ri >= 0; ri--) {
- struct memblock_region *r = &rsv->regions[ri];
- phys_addr_t r_start = ri ? r[-1].base + r[-1].size : 0;
- phys_addr_t r_end = ri < rsv->cnt ? r->base : ULLONG_MAX;
-
- /* if ri advanced past mi, break out to advance mi */
- if (r_end <= m_start)
- break;
- /* if the two regions intersect, we're done */
- if (m_end > r_start) {
- if (out_start)
- *out_start = max(m_start, r_start);
- if (out_end)
- *out_end = min(m_end, r_end);
- if (out_nid)
- *out_nid = memblock_get_region_node(m);
-
- if (m_start >= r_start)
- mi--;
- else
- ri--;
- *idx = (u32)mi | (u64)ri << 32;
- return;
+ /* With type_b NULL we only iterate through type_a */
+ if (type_b == NULL) {
+ if (out_start)
+ *out_start = m_start;
+ if (out_end)
+ *out_end = m_end;
+ if (out_nid)
+ *out_nid = memblock_get_region_node(m);
+ idx_a--;
+ *idx = (u32)idx_a;
+ return;
+ } else {
+ /* scan areas before each reservation */
+ for (; idx_b >= 0; idx_b--) {
+ struct memblock_region *r;
+ phys_addr_t r_start;
+ phys_addr_t r_end;
+ int m_nid = memblock_get_region_node(m);
+
+ r = &type_b->regions[idx_b];
+ r_start = idx_b ? r[-1].base + r[-1].size : 0;
+ r_end = idx_b < type_b->cnt ?
+ r->base : ULLONG_MAX;
+ /*
+ * if idx_b advanced past idx_a,
+ * break out to advance idx_a
+ */
+ if (r_end <= m_start)
+ break;
+ /* if the two regions intersect, we're done */
+ if (m_end > r_start) {
+ if (out_start)
+ *out_start =
+ max(m_start, r_start);
+ if (out_end)
+ *out_end =
+ min(m_end, r_end);
+ if (out_nid)
+ *out_nid = m_nid;
+
+ if (m_start >= r_start)
+ idx_a--;
+ else
+ idx_b--;
+ *idx = (u32)idx_a | (u64)idx_b << 32;
+ return;
+ }
}
}
}
-
+ /* signal end of iteration */
*idx = ULLONG_MAX;
}
diff --git a/mm/nobootmem.c b/mm/nobootmem.c
index e2906a5..c57d5e3 100644
--- a/mm/nobootmem.c
+++ b/mm/nobootmem.c
@@ -133,6 +133,15 @@ static unsigned long __init free_low_memory_core_early(void)
size = get_allocated_memblock_memory_regions_info(&start);
if (size)
count += __free_memory_core(start, start + size);
+
+#ifdef CONFIG_ARCH_MEMBLOCK_NOMAP
+
+ /* Free memblock.nomap array if it was allocated */
+ size = get_allocated_memblock_memory_regions_info(&start);
+ if (size)
+ count += __free_memory_core(start, start + size);
+
+#endif
#endif
return count;
--
1.8.4.5
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>