mm/memory_hotplug: prevalidate the address range being added with platform

Patch series "mm/memory_hotplug: Pre-validate the address range with platform", v5.

This series adds a mechanism allowing platforms to weigh in and
prevalidate incoming address range before proceeding further with the
memory hotplug.  This helps prevent potential platform errors for the
given address range, down the hotplug call chain, which inevitably fails
the hotplug itself.

This mechanism was suggested by David Hildenbrand during another
discussion with respect to a memory hotplug fix on arm64 platform.

https://lore.kernel.org/linux-arm-kernel/[email protected]/

This mechanism focuses on the addressibility aspect and not [sub] section
alignment aspect.  Hence check_hotplug_memory_range() and check_pfn_span()
have been left unchanged.

This patch (of 4):

This introduces mhp_range_allowed() which can be called in various memory
hotplug paths to prevalidate the address range which is being added, with
the platform.  Then mhp_range_allowed() calls mhp_get_pluggable_range()
which provides applicable address range depending on whether linear
mapping is required or not.  For ranges that require linear mapping, it
calls a new arch callback arch_get_mappable_range() which the platform can
override.  So the new callback, in turn provides the platform an
opportunity to configure acceptable memory hotplug address ranges in case
there are constraints.

This mechanism will help prevent platform specific errors deep down during
hotplug calls.  This drops now redundant
check_hotplug_memory_addressable() check in __add_pages() but instead adds
a VM_BUG_ON() check which would ensure that the range has been validated
with mhp_range_allowed() earlier in the call chain.  Besides
mhp_get_pluggable_range() also can be used by potential memory hotplug
callers to avail the allowed physical range which would go through on a
given platform.

This does not really add any new range check in generic memory hotplug but
instead compensates for lost checks in arch_add_memory() where applicable
and check_hotplug_memory_addressable(), with unified mhp_range_allowed().

[[email protected]: make pagemap_range() return -EINVAL when mhp_range_allowed() fails]

Link: https://lkml.kernel.org/r/[email protected]
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Anshuman Khandual <[email protected]>
Suggested-by: David Hildenbrand <[email protected]>
Reviewed-by: David Hildenbrand <[email protected]>
Reviewed-by: Oscar Salvador <[email protected]>
Cc: Heiko Carstens <[email protected]>
Cc: Catalin Marinas <[email protected]>
Cc: Vasily Gorbik <[email protected]> # s390
Cc: Will Deacon <[email protected]>
Cc: Ard Biesheuvel <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Jason Wang <[email protected]>
Cc: Jonathan Cameron <[email protected]>
Cc: "Michael S. Tsirkin" <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Pankaj Gupta <[email protected]>
Cc: Pankaj Gupta <[email protected]>
Cc: teawater <[email protected]>
Cc: Wei Yang <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

Author: Anshuman Khandual

include/linux/memory_hotplug.h

@@ -66,6 +66,9 @@ struct mhp_params {
 	pgprot_t pgprot;
 };
 
+bool mhp_range_allowed(u64 start, u64 size, bool need_mapping);
+struct range mhp_get_pluggable_range(bool need_mapping);
+
 /*
  * Zone resizing functions
  *
@@ -266,6 +269,13 @@ static inline bool movable_node_is_enabled(void)
 }
 #endif /* ! CONFIG_MEMORY_HOTPLUG */
 
+/*
+ * Keep this declaration outside CONFIG_MEMORY_HOTPLUG as some
+ * platforms might override and use arch_get_mappable_range()
+ * for internal non memory hotplug purposes.
+ */
+struct range arch_get_mappable_range(void);
+
 #if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT)
 /*
  * pgdat resizing functions

mm/memory_hotplug.c

@@ -107,6 +107,9 @@ static struct resource *register_memory_resource(u64 start, u64 size,
 	if (strcmp(resource_name, "System RAM"))
 		flags |= IORESOURCE_SYSRAM_DRIVER_MANAGED;
 
+	if (!mhp_range_allowed(start, size, true))
+		return ERR_PTR(-E2BIG);
+
 	/*
 	 * Make sure value parsed from 'mem=' only restricts memory adding
 	 * while booting, so that memory hotplug won't be impacted. Please
@@ -284,22 +287,6 @@ static int check_pfn_span(unsigned long pfn, unsigned long nr_pages,
 	return 0;
 }
 
-static int check_hotplug_memory_addressable(unsigned long pfn,
-					    unsigned long nr_pages)
-{
-	const u64 max_addr = PFN_PHYS(pfn + nr_pages) - 1;
-
-	if (max_addr >> MAX_PHYSMEM_BITS) {
-		const u64 max_allowed = (1ull << (MAX_PHYSMEM_BITS + 1)) - 1;
-		WARN(1,
-		     "Hotplugged memory exceeds maximum addressable address, range=%#llx-%#llx, maximum=%#llx\n",
-		     (u64)PFN_PHYS(pfn), max_addr, max_allowed);
-		return -E2BIG;
-	}
-
-	return 0;
-}
-
 /*
  * Return page for the valid pfn only if the page is online. All pfn
  * walkers which rely on the fully initialized page->flags and others
@@ -365,9 +352,7 @@ int __ref __add_pages(int nid, unsigned long pfn, unsigned long nr_pages,
 	if (WARN_ON_ONCE(!params->pgprot.pgprot))
 		return -EINVAL;
 
-	err = check_hotplug_memory_addressable(pfn, nr_pages);
-	if (err)
-		return err;
+	VM_BUG_ON(!mhp_range_allowed(PFN_PHYS(pfn), nr_pages * PAGE_SIZE, false));
 
 	if (altmap) {
 		/*
@@ -1248,6 +1233,61 @@ int add_memory_driver_managed(int nid, u64 start, u64 size,
 }
 EXPORT_SYMBOL_GPL(add_memory_driver_managed);
 
+/*
+ * Platforms should define arch_get_mappable_range() that provides
+ * maximum possible addressable physical memory range for which the
+ * linear mapping could be created. The platform returned address
+ * range must adhere to these following semantics.
+ *
+ * - range.start <= range.end
+ * - Range includes both end points [range.start..range.end]
+ *
+ * There is also a fallback definition provided here, allowing the
+ * entire possible physical address range in case any platform does
+ * not define arch_get_mappable_range().
+ */
+struct range __weak arch_get_mappable_range(void)
+{
+	struct range mhp_range = {
+		.start = 0UL,
+		.end = -1ULL,
+	};
+	return mhp_range;
+}
+
+struct range mhp_get_pluggable_range(bool need_mapping)
+{
+	const u64 max_phys = (1ULL << MAX_PHYSMEM_BITS) - 1;
+	struct range mhp_range;
+
+	if (need_mapping) {
+		mhp_range = arch_get_mappable_range();
+		if (mhp_range.start > max_phys) {
+			mhp_range.start = 0;
+			mhp_range.end = 0;
+		}
+		mhp_range.end = min_t(u64, mhp_range.end, max_phys);
+	} else {
+		mhp_range.start = 0;
+		mhp_range.end = max_phys;
+	}
+	return mhp_range;
+}
+EXPORT_SYMBOL_GPL(mhp_get_pluggable_range);
+
+bool mhp_range_allowed(u64 start, u64 size, bool need_mapping)
+{
+	struct range mhp_range = mhp_get_pluggable_range(need_mapping);
+	u64 end = start + size;
+
+	if (start < end && start >= mhp_range.start && (end - 1) <= mhp_range.end)
+		return true;
+
+	pr_warn("Hotplug memory [%#llx-%#llx] exceeds maximum addressable range [%#llx-%#llx]\n",
+		start, end, mhp_range.start, mhp_range.end);
+	return false;
+}
+
 #ifdef CONFIG_MEMORY_HOTREMOVE
 /*
  * Confirm all pages in a range [start, end) belong to the same zone (skipping

mm/memremap.c

@@ -200,6 +200,7 @@ static void dev_pagemap_percpu_release(struct percpu_ref *ref)
 static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params,
 		int range_id, int nid)
 {
+	const bool is_private = pgmap->type == MEMORY_DEVICE_PRIVATE;
 	struct range *range = &pgmap->ranges[range_id];
 	struct dev_pagemap *conflict_pgmap;
 	int error, is_ram;
@@ -245,6 +246,11 @@ static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params,
 	if (error)
 		goto err_pfn_remap;
 
+	if (!mhp_range_allowed(range->start, range_len(range), !is_private)) {
+		error = -EINVAL;
+		goto err_pfn_remap;
+	}
+
 	mem_hotplug_begin();
 
 	/*
@@ -258,7 +264,7 @@ static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params,
 	 * the CPU, we do want the linear mapping and thus use
 	 * arch_add_memory().
 	 */
-	if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
+	if (is_private) {
 		error = add_pages(nid, PHYS_PFN(range->start),
 				PHYS_PFN(range_len(range)), params);
 	} else {