memblock: add MEMBLOCK_DRIVER_MANAGED to mimic IORESOURCE_SYSRAM_DRIVER_MANAGED

Let's add a flag that corresponds to IORESOURCE_SYSRAM_DRIVER_MANAGED,
indicating that we're dealing with a memory region that is never
indicated in the firmware-provided memory map, but always detected and
added by a driver.

Similar to MEMBLOCK_HOTPLUG, most infrastructure has to treat such
memory regions like ordinary MEMBLOCK_NONE memory regions -- for
example, when selecting memory regions to add to the vmcore for dumping
in the crashkernel via for_each_mem_range().

However, especially kexec_file is not supposed to select such memblocks
via for_each_free_mem_range() / for_each_free_mem_range_reverse() to
place kexec images, similar to how we handle
IORESOURCE_SYSRAM_DRIVER_MANAGED without CONFIG_ARCH_KEEP_MEMBLOCK.

We'll make sure that memory hotplug code sets the flag where applicable
(IORESOURCE_SYSRAM_DRIVER_MANAGED) next.  This prepares architectures
that need CONFIG_ARCH_KEEP_MEMBLOCK, such as arm64, for virtio-mem
support.

Note that kexec *must not* indicate this memory to the second kernel and
*must not* place kexec-images on this memory.  Let's add a comment to
kexec_walk_memblock(), documenting how we handle MEMBLOCK_DRIVER_MANAGED
now just like using IORESOURCE_SYSRAM_DRIVER_MANAGED in
locate_mem_hole_callback() for kexec_walk_resources().

Also note that MEMBLOCK_HOTPLUG cannot be reused due to different
semantics:
	MEMBLOCK_HOTPLUG: memory is indicated as "System RAM" in the
	firmware-provided memory map and added to the system early during
	boot; kexec *has to* indicate this memory to the second kernel and
	can place kexec-images on this memory. After memory hotunplug,
	kexec has to be re-armed. We mostly ignore this flag when
	"movable_node" is not set on the kernel command line, because
	then we're told to not care about hotunpluggability of such
	memory regions.

	MEMBLOCK_DRIVER_MANAGED: memory is not indicated as "System RAM" in
	the firmware-provided memory map; this memory is always detected
	and added to the system by a driver; memory might not actually be
	physically hotunpluggable. kexec *must not* indicate this memory to
	the second kernel and *must not* place kexec-images on this memory.

Link: https://lkml.kernel.org/r/20211004093605.5830-5-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>
Cc: "Aneesh Kumar K . V" <aneesh.kumar@linux.ibm.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Jianyong Wu <Jianyong.Wu@arm.com>
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Shahab Vahedi <shahab@synopsys.com>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vineet Gupta <vgupta@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 8b6560dc7a9ed356a109c21ab1166064db0d8623..7df557b16c1e83294add2fb8d5925f20f6253c9e 100644 (file)
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -37,12 +37,17 @@ extern unsigned long long max_possible_pfn;
  * @MEMBLOCK_NOMAP: don't add to kernel direct mapping and treat as
  * reserved in the memory map; refer to memblock_mark_nomap() description
  * for further details
+ * @MEMBLOCK_DRIVER_MANAGED: memory region that is always detected and added
+ * via a driver, and never indicated in the firmware-provided memory map as
+ * system RAM. This corresponds to IORESOURCE_SYSRAM_DRIVER_MANAGED in the
+ * kernel resource tree.
  */
 enum memblock_flags {
        MEMBLOCK_NONE           = 0x0,  /* No special request */
        MEMBLOCK_HOTPLUG        = 0x1,  /* hotpluggable region */
        MEMBLOCK_MIRROR         = 0x2,  /* mirrored region */
        MEMBLOCK_NOMAP          = 0x4,  /* don't add to kernel direct mapping */
+       MEMBLOCK_DRIVER_MANAGED = 0x8,  /* always detected via a driver */
 };
 
 /**
@@ -213,7 +218,8 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type,
  */
 #define for_each_mem_range(i, p_start, p_end) \
        __for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE,   \
-                            MEMBLOCK_HOTPLUG, p_start, p_end, NULL)
+                            MEMBLOCK_HOTPLUG | MEMBLOCK_DRIVER_MANAGED, \
+                            p_start, p_end, NULL)
 
 /**
  * for_each_mem_range_rev - reverse iterate through memblock areas from
@@ -224,7 +230,8 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type,
  */
 #define for_each_mem_range_rev(i, p_start, p_end)                      \
        __for_each_mem_range_rev(i, &memblock.memory, NULL, NUMA_NO_NODE, \
-                                MEMBLOCK_HOTPLUG, p_start, p_end, NULL)
+                                MEMBLOCK_HOTPLUG | MEMBLOCK_DRIVER_MANAGED,\
+                                p_start, p_end, NULL)
 
 /**
  * for_each_reserved_mem_range - iterate over all reserved memblock areas
@@ -254,6 +261,11 @@ static inline bool memblock_is_nomap(struct memblock_region *m)
        return m->flags & MEMBLOCK_NOMAP;
 }
 
+static inline bool memblock_is_driver_managed(struct memblock_region *m)
+{
+       return m->flags & MEMBLOCK_DRIVER_MANAGED;
+}
+
 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/kernel/kexec_file.c b/kernel/kexec_file.c
index 33400ff051a848b05989b82753358451bfb4c53b..8347fc158d2b96ff2169389cd79ef42d4f513cf9 100644 (file)
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -556,6 +556,11 @@ static int kexec_walk_memblock(struct kexec_buf *kbuf,
        if (kbuf->image->type == KEXEC_TYPE_CRASH)
                return func(&crashk_res, kbuf);
 
+       /*
+        * Using MEMBLOCK_NONE will properly skip MEMBLOCK_DRIVER_MANAGED. See
+        * IORESOURCE_SYSRAM_DRIVER_MANAGED handling in
+        * locate_mem_hole_callback().
+        */
        if (kbuf->top_down) {
                for_each_free_mem_range_reverse(i, NUMA_NO_NODE, MEMBLOCK_NONE,
                                                &mstart, &mend, NULL) {

diff --git a/mm/memblock.c b/mm/memblock.c
index 1b0cd8a52a13a237216de5e7d9344fe30eaddff4..659bf0ffb0867308e23b6baf203988cbd0e30544 100644 (file)
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -982,6 +982,10 @@ static bool should_skip_region(struct memblock_type *type,
        if (!(flags & MEMBLOCK_NOMAP) && memblock_is_nomap(m))
                return true;
 
+       /* skip driver-managed memory unless we were asked for it explicitly */
+       if (!(flags & MEMBLOCK_DRIVER_MANAGED) && memblock_is_driver_managed(m))
+               return true;
+
        return false;
 }