[PATCH v6] arm64: mm: Populate vmemmap/linear at the page level for hotplugged sections

[Zhenhua Huang <quic_zhenhuah@quicinc.com>]

On the arm64 platform with 4K base page config, SECTION_SIZE_BITS is set
to 27, making one section 128M. The related page struct which vmemmap
points to is 2M then.
Commit c1cc1552616d ("arm64: MMU initialisation") optimizes the
vmemmap to populate at the PMD section level which was suitable
initially since hot plug granule is always one section(128M). However,
commit ba72b4c8cf60 ("mm/sparsemem: support sub-section hotplug")
introduced a 2M(SUBSECTION_SIZE) hot plug granule, which disrupted the
existing arm64 assumptions.

Considering the vmemmap_free -> unmap_hotplug_pmd_range path, when
pmd_sect() is true, the entire PMD section is cleared, even if there is
other effective subsection. For example page_struct_map1 and
page_strcut_map2 are part of a single PMD entry and they are hot-added
sequentially. Then page_struct_map1 is removed, vmemmap_free() will clear
the entire PMD entry freeing the struct page map for the whole section,
even though page_struct_map2 is still active. Similar problem exists
with linear mapping as well, for 16K base page(PMD size = 32M) or 64K
base page(PMD = 512M), their block mappings exceed SUBSECTION_SIZE.
Tearing down the entire PMD mapping too will leave other subsections
unmapped in the linear mapping.

To address the issue, we need to prevent PMD/PUD/CONT mappings for both
linear and vmemmap for non-boot sections if corresponding size on the
given base page exceeds SUBSECTION_SIZE(2MB now).

Cc: <stable@vger.kernel.org> # v5.4+
Fixes: ba72b4c8cf60 ("mm/sparsemem: support sub-section hotplug")
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Zhenhua Huang <quic_zhenhuah@quicinc.com>
---
 arch/arm64/mm/mmu.c | 46 ++++++++++++++++++++++++++++++++++++---------
 1 file changed, 37 insertions(+), 9 deletions(-)

diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index b4df5bc5b1b8..b1089365f3e7 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -42,9 +42,13 @@
 #include <asm/pgalloc.h>
 #include <asm/kfence.h>
 
-#define NO_BLOCK_MAPPINGS	BIT(0)
-#define NO_CONT_MAPPINGS	BIT(1)
-#define NO_EXEC_MAPPINGS	BIT(2)	/* assumes FEAT_HPDS is not used */
+#define NO_PMD_BLOCK_MAPPINGS	BIT(0)
+#define NO_PUD_BLOCK_MAPPINGS	BIT(1)  /* Hotplug case: do not want block mapping for PUD */
+#define NO_BLOCK_MAPPINGS	(NO_PMD_BLOCK_MAPPINGS | NO_PUD_BLOCK_MAPPINGS)
+#define NO_PTE_CONT_MAPPINGS	BIT(2)
+#define NO_PMD_CONT_MAPPINGS	BIT(3)  /* Hotplug case: do not want cont mapping for PMD */
+#define NO_CONT_MAPPINGS	(NO_PTE_CONT_MAPPINGS | NO_PMD_CONT_MAPPINGS)
+#define NO_EXEC_MAPPINGS	BIT(4)	/* assumes FEAT_HPDS is not used */
 
 u64 kimage_voffset __ro_after_init;
 EXPORT_SYMBOL(kimage_voffset);
@@ -224,7 +228,7 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
 
 		/* use a contiguous mapping if the range is suitably aligned */
 		if ((((addr | next | phys) & ~CONT_PTE_MASK) == 0) &&
-		    (flags & NO_CONT_MAPPINGS) == 0)
+		    (flags & NO_PTE_CONT_MAPPINGS) == 0)
 			__prot = __pgprot(pgprot_val(prot) | PTE_CONT);
 
 		init_pte(ptep, addr, next, phys, __prot);
@@ -254,7 +258,7 @@ static void init_pmd(pmd_t *pmdp, unsigned long addr, unsigned long end,
 
 		/* try section mapping first */
 		if (((addr | next | phys) & ~PMD_MASK) == 0 &&
-		    (flags & NO_BLOCK_MAPPINGS) == 0) {
+		    (flags & NO_PMD_BLOCK_MAPPINGS) == 0) {
 			pmd_set_huge(pmdp, phys, prot);
 
 			/*
@@ -311,7 +315,7 @@ static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
 
 		/* use a contiguous mapping if the range is suitably aligned */
 		if ((((addr | next | phys) & ~CONT_PMD_MASK) == 0) &&
-		    (flags & NO_CONT_MAPPINGS) == 0)
+		    (flags & NO_PMD_CONT_MAPPINGS) == 0)
 			__prot = __pgprot(pgprot_val(prot) | PTE_CONT);
 
 		init_pmd(pmdp, addr, next, phys, __prot, pgtable_alloc, flags);
@@ -358,8 +362,8 @@ static void alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end,
 		 * For 4K granule only, attempt to put down a 1GB block
 		 */
 		if (pud_sect_supported() &&
-		   ((addr | next | phys) & ~PUD_MASK) == 0 &&
-		    (flags & NO_BLOCK_MAPPINGS) == 0) {
+		    ((addr | next | phys) & ~PUD_MASK) == 0 &&
+		    (flags & NO_PUD_BLOCK_MAPPINGS) == 0) {
 			pud_set_huge(pudp, phys, prot);
 
 			/*
@@ -1178,7 +1182,13 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 {
 	WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END));
 
-	if (!IS_ENABLED(CONFIG_ARM64_4K_PAGES))
+	/*
+	 * Hotplugged section does not support hugepages as
+	 * PMD_SIZE (hence PUD_SIZE) section mapping covers
+	 * struct page range that exceeds a SUBSECTION_SIZE
+	 * i.e 2MB - for all available base page sizes.
+	 */
+	if (!IS_ENABLED(CONFIG_ARM64_4K_PAGES) || system_state != SYSTEM_BOOTING)
 		return vmemmap_populate_basepages(start, end, node, altmap);
 	else
 		return vmemmap_populate_hugepages(start, end, node, altmap);
@@ -1340,9 +1350,27 @@ int arch_add_memory(int nid, u64 start, u64 size,
 		    struct mhp_params *params)
 {
 	int ret, flags = NO_EXEC_MAPPINGS;
+	unsigned long start_pfn = PFN_DOWN(start);
+	struct mem_section *ms = __pfn_to_section(start_pfn);
 
 	VM_BUG_ON(!mhp_range_allowed(start, size, true));
 
+	/* should not be invoked by early section */
+	WARN_ON(early_section(ms));
+
+	/*
+	 * Disallow BLOCK/CONT mappings if the corresponding size exceeds
+	 * SUBSECTION_SIZE which now is 2MB.
+	 *
+	 * PUD_BLOCK or PMD_CONT should consistently exceed SUBSECTION_SIZE
+	 * across all variable page size configurations, so add them directly
+	 */
+	flags |= NO_PUD_BLOCK_MAPPINGS | NO_PMD_CONT_MAPPINGS;
+	if (SUBSECTION_SHIFT < PMD_SHIFT)
+		flags |= NO_PMD_BLOCK_MAPPINGS;
+	if (SUBSECTION_SHIFT < CONT_PTE_SHIFT)
+		flags |= NO_PTE_CONT_MAPPINGS;
+
 	if (can_set_direct_map())
 		flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
 
-- 
2.25.1