[PATCH v7 5/9] memblock: introduce MEMBLOCK_NODUMP flag

[Wandun Chen]

From: Wandun Chen <chenwandun at lixiang.com>

Add MEMBLOCK_NODUMP to mark regions that should be excluded from
kdump vmcores.

The flag is meant for reserved memory that carries no data useful for
crash analysis. Reusable reserved regions such as CMA may hold useful
data, so these regions must not be marked MEMBLOCK_NODUMP. Subsequent
patches wire this up for /reserved-memory and /memreserve/ entries.

Regions in /memreserve/ (such as the initrd) may be reserved at the
beginning and freed later, so we also need to clear the flag when
freeing reserved memory.

Suggested-by: Rob Herring <robh at kernel.org>
Signed-off-by: Wandun Chen <chenwandun at lixiang.com>
Tested-by: Meijing Zhao <zhaomeijing at lixiang.com>
---
 include/linux/memblock.h |  9 +++++++++
 mm/memblock.c            | 43 ++++++++++++++++++++++++++++++++++++++--
 2 files changed, 50 insertions(+), 2 deletions(-)

diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index aa845f488327..0126b47bc3c4 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -52,6 +52,8 @@ 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_NODUMP: exclude from kdump vmcore. It carries no data useful
+ * for crash analysis (e.g. firmware carveouts).
  */
 enum memblock_flags {
 	MEMBLOCK_NONE		= 0x0,	/* No special request */
@@ -63,6 +65,7 @@ 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_NODUMP		= 0x100,/* exclude from kdump vmcore */
 };
 
 /**
@@ -160,6 +163,7 @@ 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_nodump(phys_addr_t base, phys_addr_t size);
 
 void memblock_free(void *ptr, size_t size);
 
@@ -305,6 +309,11 @@ static inline bool memblock_is_kho_scratch(struct memblock_region *m)
 	return m->flags & MEMBLOCK_KHO_SCRATCH;
 }
 
+static inline bool memblock_is_nodump(struct memblock_region *m)
+{
+	return m->flags & MEMBLOCK_NODUMP;
+}
+
 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..48cabfe5cdf1 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -929,6 +929,8 @@ static unsigned long __free_reserved_area(phys_addr_t start, phys_addr_t end,
 	return pages;
 }
 
+static int memblock_clear_nodump(phys_addr_t base, phys_addr_t size);
+
 unsigned long free_reserved_area(void *start, void *end, int poison, const char *s)
 {
 	phys_addr_t start_pa, end_pa;
@@ -949,9 +951,13 @@ unsigned long free_reserved_area(void *start, void *end, int poison, const char
 	}
 
 	if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) {
-		if (start_pa < end_pa)
+		if (start_pa < end_pa) {
 			memblock_remove_range(&memblock.reserved,
 					      start_pa, end_pa - start_pa);
+
+			if (IS_ENABLED(CONFIG_CRASH_DUMP))
+				memblock_clear_nodump(start_pa, end_pa - start_pa);
+		}
 	}
 
 	pages = __free_reserved_area(start_pa, end_pa, poison);
@@ -995,8 +1001,11 @@ int __init_memblock memblock_phys_free(phys_addr_t base, phys_addr_t size)
 
 	kmemleak_free_part_phys(base, size);
 
-	if (!slab_is_available() || IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK))
+	if (!slab_is_available() || IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) {
 		ret = memblock_remove_range(&memblock.reserved, base, size);
+		if (IS_ENABLED(CONFIG_CRASH_DUMP))
+			memblock_clear_nodump(base, size);
+	}
 
 	if (slab_is_available())
 		__free_reserved_area(base, base + size, -1);
@@ -1204,6 +1213,35 @@ __init int memblock_clear_kho_scratch(phys_addr_t base, phys_addr_t size)
 				    MEMBLOCK_KHO_SCRATCH);
 }
 
+/**
+ * memblock_mark_nodump - Mark a memory region with flag MEMBLOCK_NODUMP.
+ * @base: the base phys addr of the region
+ * @size: the size of the region
+ *
+ * Mark the region as not to be included in crash dumps.
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+int __init_memblock memblock_mark_nodump(phys_addr_t base, phys_addr_t size)
+{
+	return memblock_setclr_flag(&memblock.memory, base, size, 1,
+				    MEMBLOCK_NODUMP);
+}
+
+/**
+ * memblock_clear_nodump - Clear a memory region with flag MEMBLOCK_NODUMP.
+ * @base: the base phys addr of the region
+ * @size: the size of the region
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+static int __init_memblock memblock_clear_nodump(phys_addr_t base,
+						 phys_addr_t size)
+{
+	return memblock_setclr_flag(&memblock.memory, base, size, 0,
+				    MEMBLOCK_NODUMP);
+}
+
 static bool should_skip_region(struct memblock_type *type,
 			       struct memblock_region *m,
 			       int nid, int flags)
@@ -2880,6 +2918,7 @@ 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_NODUMP)] = "NODUMP",
 };
 
 static int memblock_debug_show(struct seq_file *m, void *private)
-- 
2.43.0