From: David Woodhouse <dwmw@amazon.co.uk>
Date: Wed, 23 Apr 2025 13:33:39 +0000 (+0100)
Subject: mm: implement for_each_valid_pfn() for CONFIG_SPARSEMEM
X-Git-Tag: v6.16-rc1~92^2~90
X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=037926316c9ded1194927ee56b862e3a1450aaf3;p=thirdparty%2Flinux.git

mm: implement for_each_valid_pfn() for CONFIG_SPARSEMEM

Implement for_each_valid_pfn() based on two helper functions.

The first_valid_pfn() function largely mirrors pfn_valid(), calling into a
pfn_section_first_valid() helper which is trivial for the !VMEMMAP case,
and in the VMEMMAP case will skip to the next subsection as needed.

Since next_valid_pfn() knows that its argument *is* a valid PFN, it
doesn't need to do any checking at all while iterating over the low bits
within a (sub)section mask; the whole (sub)section is either present or
not.

Note that the VMEMMAP version of pfn_section_first_valid() may return a
value *higher* than end_pfn when skipping to the next subsection, and
first_valid_pfn() happily returns that higher value.  This is fine.

[dwmw2@infradead.org: fix next_valid_pfn() for sparsemem]
  Link: https://lkml.kernel.org/r/c15100fcf6781a60b852c4dbb43bdc98a678fcf0.camel@infradead.org
Link: https://lkml.kernel.org/r/20250423133821.789413-4-dwmw2@infradead.org
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Reviewed-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Marc Rutland <mark.rutland@arm.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Ruihan Li <lrh2000@pku.edu.cn>
Cc: Will Deacon <will@kernel.org>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 230a29c2ed1a9..b19a98c20de8a 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -2075,11 +2075,37 @@ static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn)
 
 	return usage ? test_bit(idx, usage->subsection_map) : 0;
 }
+
+static inline bool pfn_section_first_valid(struct mem_section *ms, unsigned long *pfn)
+{
+	struct mem_section_usage *usage = READ_ONCE(ms->usage);
+	int idx = subsection_map_index(*pfn);
+	unsigned long bit;
+
+	if (!usage)
+		return false;
+
+	if (test_bit(idx, usage->subsection_map))
+		return true;
+
+	/* Find the next subsection that exists */
+	bit = find_next_bit(usage->subsection_map, SUBSECTIONS_PER_SECTION, idx);
+	if (bit == SUBSECTIONS_PER_SECTION)
+		return false;
+
+	*pfn = (*pfn & PAGE_SECTION_MASK) + (bit * PAGES_PER_SUBSECTION);
+	return true;
+}
 #else
 static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn)
 {
 	return 1;
 }
+
+static inline bool pfn_section_first_valid(struct mem_section *ms, unsigned long *pfn)
+{
+	return true;
+}
 #endif
 
 void sparse_init_early_section(int nid, struct page *map, unsigned long pnum,
@@ -2128,6 +2154,58 @@ static inline int pfn_valid(unsigned long pfn)
 
 	return ret;
 }
+
+/* Returns end_pfn or higher if no valid PFN remaining in range */
+static inline unsigned long first_valid_pfn(unsigned long pfn, unsigned long end_pfn)
+{
+	unsigned long nr = pfn_to_section_nr(pfn);
+
+	rcu_read_lock_sched();
+
+	while (nr <= __highest_present_section_nr && pfn < end_pfn) {
+		struct mem_section *ms = __pfn_to_section(pfn);
+
+		if (valid_section(ms) &&
+		    (early_section(ms) || pfn_section_first_valid(ms, &pfn))) {
+			rcu_read_unlock_sched();
+			return pfn;
+		}
+
+		/* Nothing left in this section? Skip to next section */
+		nr++;
+		pfn = section_nr_to_pfn(nr);
+	}
+
+	rcu_read_unlock_sched();
+	return end_pfn;
+}
+
+static inline unsigned long next_valid_pfn(unsigned long pfn, unsigned long end_pfn)
+{
+	pfn++;
+
+	if (pfn >= end_pfn)
+		return end_pfn;
+
+	/*
+	 * Either every PFN within the section (or subsection for VMEMMAP) is
+	 * valid, or none of them are. So there's no point repeating the check
+	 * for every PFN; only call first_valid_pfn() again when crossing a
+	 * (sub)section boundary (i.e. !(pfn & ~PAGE_{SUB,}SECTION_MASK)).
+	 */
+	if (pfn & ~(IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP) ?
+		   PAGE_SUBSECTION_MASK : PAGE_SECTION_MASK))
+		return pfn;
+
+	return first_valid_pfn(pfn, end_pfn);
+}
+
+
+#define for_each_valid_pfn(_pfn, _start_pfn, _end_pfn)			\
+	for ((_pfn) = first_valid_pfn((_start_pfn), (_end_pfn));	\
+	     (_pfn) < (_end_pfn);					\
+	     (_pfn) = next_valid_pfn((_pfn), (_end_pfn)))
+
 #endif
 
 static inline int pfn_in_present_section(unsigned long pfn)