Merging upstream version 6.9.7.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

1 files changed, 130 insertions, 35 deletions

diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c
index 4c7ad574b9..b65a29440a 100644
--- a/arch/arm64/mm/kasan_init.c
+++ b/arch/arm64/mm/kasan_init.c
@@ -23,7 +23,7 @@
 
 #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 
-static pgd_t tmp_pg_dir[PTRS_PER_PGD] __initdata __aligned(PGD_SIZE);
+static pgd_t tmp_pg_dir[PTRS_PER_PTE] __initdata __aligned(PAGE_SIZE);
 
 /*
  * The p*d_populate functions call virt_to_phys implicitly so they can't be used
@@ -99,6 +99,19 @@ static pud_t *__init kasan_pud_offset(p4d_t *p4dp, unsigned long addr, int node,
 	return early ? pud_offset_kimg(p4dp, addr) : pud_offset(p4dp, addr);
 }
 
+static p4d_t *__init kasan_p4d_offset(pgd_t *pgdp, unsigned long addr, int node,
+				      bool early)
+{
+	if (pgd_none(READ_ONCE(*pgdp))) {
+		phys_addr_t p4d_phys = early ?
+				__pa_symbol(kasan_early_shadow_p4d)
+					: kasan_alloc_zeroed_page(node);
+		__pgd_populate(pgdp, p4d_phys, PGD_TYPE_TABLE);
+	}
+
+	return early ? p4d_offset_kimg(pgdp, addr) : p4d_offset(pgdp, addr);
+}
+
 static void __init kasan_pte_populate(pmd_t *pmdp, unsigned long addr,
 				      unsigned long end, int node, bool early)
 {
@@ -112,8 +125,8 @@ static void __init kasan_pte_populate(pmd_t *pmdp, unsigned long addr,
 		if (!early)
 			memset(__va(page_phys), KASAN_SHADOW_INIT, PAGE_SIZE);
 		next = addr + PAGE_SIZE;
-		set_pte(ptep, pfn_pte(__phys_to_pfn(page_phys), PAGE_KERNEL));
-	} while (ptep++, addr = next, addr != end && pte_none(READ_ONCE(*ptep)));
+		__set_pte(ptep, pfn_pte(__phys_to_pfn(page_phys), PAGE_KERNEL));
+	} while (ptep++, addr = next, addr != end && pte_none(__ptep_get(ptep)));
 }
 
 static void __init kasan_pmd_populate(pud_t *pudp, unsigned long addr,
@@ -144,12 +157,12 @@ static void __init kasan_p4d_populate(pgd_t *pgdp, unsigned long addr,
 				      unsigned long end, int node, bool early)
 {
 	unsigned long next;
-	p4d_t *p4dp = p4d_offset(pgdp, addr);
+	p4d_t *p4dp = kasan_p4d_offset(pgdp, addr, node, early);
 
 	do {
 		next = p4d_addr_end(addr, end);
 		kasan_pud_populate(p4dp, addr, next, node, early);
-	} while (p4dp++, addr = next, addr != end);
+	} while (p4dp++, addr = next, addr != end && p4d_none(READ_ONCE(*p4dp)));
 }
 
 static void __init kasan_pgd_populate(unsigned long addr, unsigned long end,
@@ -165,19 +178,48 @@ static void __init kasan_pgd_populate(unsigned long addr, unsigned long end,
 	} while (pgdp++, addr = next, addr != end);
 }
 
+#if defined(CONFIG_ARM64_64K_PAGES) || CONFIG_PGTABLE_LEVELS > 4
+#define SHADOW_ALIGN	P4D_SIZE
+#else
+#define SHADOW_ALIGN	PUD_SIZE
+#endif
+
+/*
+ * Return whether 'addr' is aligned to the size covered by a root level
+ * descriptor.
+ */
+static bool __init root_level_aligned(u64 addr)
+{
+	int shift = (ARM64_HW_PGTABLE_LEVELS(vabits_actual) - 1) * (PAGE_SHIFT - 3);
+
+	return (addr % (PAGE_SIZE << shift)) == 0;
+}
+
 /* The early shadow maps everything to a single page of zeroes */
 asmlinkage void __init kasan_early_init(void)
 {
 	BUILD_BUG_ON(KASAN_SHADOW_OFFSET !=
 		KASAN_SHADOW_END - (1UL << (64 - KASAN_SHADOW_SCALE_SHIFT)));
-	/*
-	 * We cannot check the actual value of KASAN_SHADOW_START during build,
-	 * as it depends on vabits_actual. As a best-effort approach, check
-	 * potential values calculated based on VA_BITS and VA_BITS_MIN.
-	 */
-	BUILD_BUG_ON(!IS_ALIGNED(_KASAN_SHADOW_START(VA_BITS), PGDIR_SIZE));
-	BUILD_BUG_ON(!IS_ALIGNED(_KASAN_SHADOW_START(VA_BITS_MIN), PGDIR_SIZE));
-	BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END, PGDIR_SIZE));
+	BUILD_BUG_ON(!IS_ALIGNED(_KASAN_SHADOW_START(VA_BITS), SHADOW_ALIGN));
+	BUILD_BUG_ON(!IS_ALIGNED(_KASAN_SHADOW_START(VA_BITS_MIN), SHADOW_ALIGN));
+	BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END, SHADOW_ALIGN));
+
+	if (!root_level_aligned(KASAN_SHADOW_START)) {
+		/*
+		 * The start address is misaligned, and so the next level table
+		 * will be shared with the linear region. This can happen with
+		 * 4 or 5 level paging, so install a generic pte_t[] as the
+		 * next level. This prevents the kasan_pgd_populate call below
+		 * from inserting an entry that refers to the shared KASAN zero
+		 * shadow pud_t[]/p4d_t[], which could end up getting corrupted
+		 * when the linear region is mapped.
+		 */
+		static pte_t tbl[PTRS_PER_PTE] __page_aligned_bss;
+		pgd_t *pgdp = pgd_offset_k(KASAN_SHADOW_START);
+
+		set_pgd(pgdp, __pgd(__pa_symbol(tbl) | PGD_TYPE_TABLE));
+	}
+
 	kasan_pgd_populate(KASAN_SHADOW_START, KASAN_SHADOW_END, NUMA_NO_NODE,
 			   true);
 }
@@ -190,34 +232,74 @@ static void __init kasan_map_populate(unsigned long start, unsigned long end,
 }
 
 /*
- * Copy the current shadow region into a new pgdir.
+ * Return the descriptor index of 'addr' in the root level table
  */
-void __init kasan_copy_shadow(pgd_t *pgdir)
+static int __init root_level_idx(u64 addr)
 {
-	pgd_t *pgdp, *pgdp_new, *pgdp_end;
+	/*
+	 * On 64k pages, the TTBR1 range root tables are extended for 52-bit
+	 * virtual addressing, and TTBR1 will simply point to the pgd_t entry
+	 * that covers the start of the 48-bit addressable VA space if LVA is
+	 * not implemented. This means we need to index the table as usual,
+	 * instead of masking off bits based on vabits_actual.
+	 */
+	u64 vabits = IS_ENABLED(CONFIG_ARM64_64K_PAGES) ? VA_BITS
+							: vabits_actual;
+	int shift = (ARM64_HW_PGTABLE_LEVELS(vabits) - 1) * (PAGE_SHIFT - 3);
 
-	pgdp = pgd_offset_k(KASAN_SHADOW_START);
-	pgdp_end = pgd_offset_k(KASAN_SHADOW_END);
-	pgdp_new = pgd_offset_pgd(pgdir, KASAN_SHADOW_START);
-	do {
-		set_pgd(pgdp_new, READ_ONCE(*pgdp));
-	} while (pgdp++, pgdp_new++, pgdp != pgdp_end);
+	return (addr & ~_PAGE_OFFSET(vabits)) >> (shift + PAGE_SHIFT);
+}
+
+/*
+ * Clone a next level table from swapper_pg_dir into tmp_pg_dir
+ */
+static void __init clone_next_level(u64 addr, pgd_t *tmp_pg_dir, pud_t *pud)
+{
+	int idx = root_level_idx(addr);
+	pgd_t pgd = READ_ONCE(swapper_pg_dir[idx]);
+	pud_t *pudp = (pud_t *)__phys_to_kimg(__pgd_to_phys(pgd));
+
+	memcpy(pud, pudp, PAGE_SIZE);
+	tmp_pg_dir[idx] = __pgd(__phys_to_pgd_val(__pa_symbol(pud)) |
+				PUD_TYPE_TABLE);
 }
 
-static void __init clear_pgds(unsigned long start,
-			unsigned long end)
+/*
+ * Return the descriptor index of 'addr' in the next level table
+ */
+static int __init next_level_idx(u64 addr)
 {
-	/*
-	 * Remove references to kasan page tables from
-	 * swapper_pg_dir. pgd_clear() can't be used
-	 * here because it's nop on 2,3-level pagetable setups
-	 */
-	for (; start < end; start += PGDIR_SIZE)
-		set_pgd(pgd_offset_k(start), __pgd(0));
+	int shift = (ARM64_HW_PGTABLE_LEVELS(vabits_actual) - 2) * (PAGE_SHIFT - 3);
+
+	return (addr >> (shift + PAGE_SHIFT)) % PTRS_PER_PTE;
+}
+
+/*
+ * Dereference the table descriptor at 'pgd_idx' and clear the entries from
+ * 'start' to 'end' (exclusive) from the table.
+ */
+static void __init clear_next_level(int pgd_idx, int start, int end)
+{
+	pgd_t pgd = READ_ONCE(swapper_pg_dir[pgd_idx]);
+	pud_t *pudp = (pud_t *)__phys_to_kimg(__pgd_to_phys(pgd));
+
+	memset(&pudp[start], 0, (end - start) * sizeof(pud_t));
+}
+
+static void __init clear_shadow(u64 start, u64 end)
+{
+	int l = root_level_idx(start), m = root_level_idx(end);
+
+	if (!root_level_aligned(start))
+		clear_next_level(l++, next_level_idx(start), PTRS_PER_PTE);
+	if (!root_level_aligned(end))
+		clear_next_level(m, 0, next_level_idx(end));
+	memset(&swapper_pg_dir[l], 0, (m - l) * sizeof(pgd_t));
 }
 
 static void __init kasan_init_shadow(void)
 {
+	static pud_t pud[2][PTRS_PER_PUD] __initdata __aligned(PAGE_SIZE);
 	u64 kimg_shadow_start, kimg_shadow_end;
 	u64 mod_shadow_start;
 	u64 vmalloc_shadow_end;
@@ -239,10 +321,23 @@ static void __init kasan_init_shadow(void)
 	 * setup will be finished.
 	 */
 	memcpy(tmp_pg_dir, swapper_pg_dir, sizeof(tmp_pg_dir));
+
+	/*
+	 * If the start or end address of the shadow region is not aligned to
+	 * the root level size, we have to allocate a temporary next-level table
+	 * in each case, clone the next level of descriptors, and install the
+	 * table into tmp_pg_dir. Note that with 5 levels of paging, the next
+	 * level will in fact be p4d_t, but that makes no difference in this
+	 * case.
+	 */
+	if (!root_level_aligned(KASAN_SHADOW_START))
+		clone_next_level(KASAN_SHADOW_START, tmp_pg_dir, pud[0]);
+	if (!root_level_aligned(KASAN_SHADOW_END))
+		clone_next_level(KASAN_SHADOW_END, tmp_pg_dir, pud[1]);
 	dsb(ishst);
-	cpu_replace_ttbr1(lm_alias(tmp_pg_dir), idmap_pg_dir);
+	cpu_replace_ttbr1(lm_alias(tmp_pg_dir));
 
-	clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END);
+	clear_shadow(KASAN_SHADOW_START, KASAN_SHADOW_END);
 
 	kasan_map_populate(kimg_shadow_start, kimg_shadow_end,
 			   early_pfn_to_nid(virt_to_pfn(lm_alias(KERNEL_START))));
@@ -271,12 +366,12 @@ static void __init kasan_init_shadow(void)
 	 * so we should make sure that it maps the zero page read-only.
 	 */
 	for (i = 0; i < PTRS_PER_PTE; i++)
-		set_pte(&kasan_early_shadow_pte[i],
+		__set_pte(&kasan_early_shadow_pte[i],
 			pfn_pte(sym_to_pfn(kasan_early_shadow_page),
 				PAGE_KERNEL_RO));
 
 	memset(kasan_early_shadow_page, KASAN_SHADOW_INIT, PAGE_SIZE);
-	cpu_replace_ttbr1(lm_alias(swapper_pg_dir), idmap_pg_dir);
+	cpu_replace_ttbr1(lm_alias(swapper_pg_dir));
 }
 
 static void __init kasan_init_depth(void)