Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Subject: [PATCH v5 03/10] mm/sparsemem: Add helpers track active portions of
 a section at boot
From:   Dan Williams <dan.j.williams@intel.com>
To:     akpm@linux-foundation.org
Cc:     Michal Hocko <mhocko@suse.com>, Vlastimil Babka <vbabka@suse.cz>,
        Logan Gunthorpe <logang@deltatee.com>, linux-mm@kvack.org,
        linux-nvdimm@lists.01.org, linux-kernel@vger.kernel.org
Date:   Fri, 22 Mar 2019 09:58:10 -0700
Message-ID: <155327389029.225273.1972826189687261996.stgit@dwillia2-desk3.amr.corp.intel.com>
In-Reply-To: <155327387405.225273.9325594075351253804.stgit@dwillia2-desk3.amr.corp.intel.com>
References: <155327387405.225273.9325594075351253804.stgit@dwillia2-desk3.amr.corp.intel.com>
User-Agent: StGit/0.18-2-gc94f
MIME-Version: 1.0
Content-Type: text/plain; charset="utf-8"
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

Prepare for hot{plug,remove} of sub-ranges of a section by tracking a
section active bitmask, each bit representing 2MB (SECTION_SIZE (128M) /
map_active bitmask length (64)). If it turns out that 2MB is too large
of an active tracking granularity it is trivial to increase the size of
the map_active bitmap.

The implications of a partially populated section is that pfn_valid()
needs to go beyond a valid_section() check and read the sub-section
active ranges from the bitmask.

Cc: Michal Hocko <mhocko@suse.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 include/linux/mmzone.h |   29 ++++++++++++++++++++++++++++-
 mm/page_alloc.c        |    4 +++-
 mm/sparse.c            |   48 ++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 79 insertions(+), 2 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 69b9cb9cb2ed..ae4aa7f63d2e 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1122,6 +1122,8 @@ struct mem_section_usage {
 	unsigned long pageblock_flags[0];
 };
 
+void section_active_init(unsigned long pfn, unsigned long nr_pages);
+
 struct page;
 struct page_ext;
 struct mem_section {
@@ -1259,12 +1261,36 @@ static inline struct mem_section *__pfn_to_section(unsigned long pfn)
 
 extern int __highest_present_section_nr;
 
+static inline int section_active_index(phys_addr_t phys)
+{
+	return (phys & ~(PA_SECTION_MASK)) / SECTION_ACTIVE_SIZE;
+}
+
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn)
+{
+	int idx = section_active_index(PFN_PHYS(pfn));
+
+	return !!(ms->usage->map_active & (1UL << idx));
+}
+#else
+static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn)
+{
+	return 1;
+}
+#endif
+
 #ifndef CONFIG_HAVE_ARCH_PFN_VALID
 static inline int pfn_valid(unsigned long pfn)
 {
+	struct mem_section *ms;
+
 	if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
 		return 0;
-	return valid_section(__nr_to_section(pfn_to_section_nr(pfn)));
+	ms = __nr_to_section(pfn_to_section_nr(pfn));
+	if (!valid_section(ms))
+		return 0;
+	return pfn_section_valid(ms, pfn);
 }
 #endif
 
@@ -1295,6 +1321,7 @@ void sparse_init(void);
 #else
 #define sparse_init()	do {} while (0)
 #define sparse_index_init(_sec, _nid)  do {} while (0)
+#define section_active_init(_pfn, _nr_pages) do {} while (0)
 #endif /* CONFIG_SPARSEMEM */
 
 /*
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index bf23bc0b8399..508a810fd514 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -7221,10 +7221,12 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
 
 	/* Print out the early node map */
 	pr_info("Early memory node ranges\n");
-	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid)
+	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) {
 		pr_info("  node %3d: [mem %#018Lx-%#018Lx]\n", nid,
 			(u64)start_pfn << PAGE_SHIFT,
 			((u64)end_pfn << PAGE_SHIFT) - 1);
+		section_active_init(start_pfn, end_pfn - start_pfn);
+	}
 
 	/* Initialise every node */
 	mminit_verify_pageflags_layout();
diff --git a/mm/sparse.c b/mm/sparse.c
index cdd2978d0ffe..3cd7ce46e749 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -210,6 +210,54 @@ static inline unsigned long first_present_section_nr(void)
 	return next_present_section_nr(-1);
 }
 
+static unsigned long section_active_mask(unsigned long pfn,
+		unsigned long nr_pages)
+{
+	int idx_start, idx_size;
+	phys_addr_t start, size;
+
+	if (!nr_pages)
+		return 0;
+
+	start = PFN_PHYS(pfn);
+	size = PFN_PHYS(min(nr_pages, PAGES_PER_SECTION
+				- (pfn & ~PAGE_SECTION_MASK)));
+	size = ALIGN(size, SECTION_ACTIVE_SIZE);
+
+	idx_start = section_active_index(start);
+	idx_size = section_active_index(size);
+
+	if (idx_size == 0)
+		return -1;
+	return ((1UL << idx_size) - 1) << idx_start;
+}
+
+void section_active_init(unsigned long pfn, unsigned long nr_pages)
+{
+	int end_sec = pfn_to_section_nr(pfn + nr_pages - 1);
+	int i, start_sec = pfn_to_section_nr(pfn);
+
+	if (!nr_pages)
+		return;
+
+	for (i = start_sec; i <= end_sec; i++) {
+		struct mem_section *ms;
+		unsigned long mask;
+		unsigned long pfns;
+
+		pfns = min(nr_pages, PAGES_PER_SECTION
+				- (pfn & ~PAGE_SECTION_MASK));
+		mask = section_active_mask(pfn, pfns);
+
+		ms = __nr_to_section(i);
+		pr_debug("%s: sec: %d mask: %#018lx\n", __func__, i, mask);
+		ms->usage->map_active = mask;
+
+		pfn += pfns;
+		nr_pages -= pfns;
+	}
+}
+
 /* Record a memory area against a node. */
 void __init memory_present(int nid, unsigned long start, unsigned long end)
 {