1 files changed, 213 insertions, 129 deletions

diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 6032f3e3056a..c6daaf6c6f97 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -26,6 +26,8 @@
 #include <linux/memblock.h>
 #include <linux/fs.h>
 #include <linux/io.h>
+#include <linux/slab.h>
+#include <linux/stop_machine.h>
 
 #include <asm/cputype.h>
 #include <asm/fixmap.h>
@@ -45,80 +47,6 @@
 struct page *empty_zero_page;
 EXPORT_SYMBOL(empty_zero_page);
 
-struct cachepolicy {
-	const char	policy[16];
-	u64		mair;
-	u64		tcr;
-};
-
-static struct cachepolicy cache_policies[] __initdata = {
-	{
-		.policy		= "uncached",
-		.mair		= 0x44,			/* inner, outer non-cacheable */
-		.tcr		= TCR_IRGN_NC | TCR_ORGN_NC,
-	}, {
-		.policy		= "writethrough",
-		.mair		= 0xaa,			/* inner, outer write-through, read-allocate */
-		.tcr		= TCR_IRGN_WT | TCR_ORGN_WT,
-	}, {
-		.policy		= "writeback",
-		.mair		= 0xee,			/* inner, outer write-back, read-allocate */
-		.tcr		= TCR_IRGN_WBnWA | TCR_ORGN_WBnWA,
-	}
-};
-
-/*
- * These are useful for identifying cache coherency problems by allowing the
- * cache or the cache and writebuffer to be turned off. It changes the Normal
- * memory caching attributes in the MAIR_EL1 register.
- */
-static int __init early_cachepolicy(char *p)
-{
-	int i;
-	u64 tmp;
-
-	for (i = 0; i < ARRAY_SIZE(cache_policies); i++) {
-		int len = strlen(cache_policies[i].policy);
-
-		if (memcmp(p, cache_policies[i].policy, len) == 0)
-			break;
-	}
-	if (i == ARRAY_SIZE(cache_policies)) {
-		pr_err("ERROR: unknown or unsupported cache policy: %s\n", p);
-		return 0;
-	}
-
-	flush_cache_all();
-
-	/*
-	 * Modify MT_NORMAL attributes in MAIR_EL1.
-	 */
-	asm volatile(
-	"	mrs	%0, mair_el1\n"
-	"	bfi	%0, %1, %2, #8\n"
-	"	msr	mair_el1, %0\n"
-	"	isb\n"
-	: "=&r" (tmp)
-	: "r" (cache_policies[i].mair), "i" (MT_NORMAL * 8));
-
-	/*
-	 * Modify TCR PTW cacheability attributes.
-	 */
-	asm volatile(
-	"	mrs	%0, tcr_el1\n"
-	"	bic	%0, %0, %2\n"
-	"	orr	%0, %0, %1\n"
-	"	msr	tcr_el1, %0\n"
-	"	isb\n"
-	: "=&r" (tmp)
-	: "r" (cache_policies[i].tcr), "r" (TCR_IRGN_MASK | TCR_ORGN_MASK));
-
-	flush_cache_all();
-
-	return 0;
-}
-early_param("cachepolicy", early_cachepolicy);
-
 pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 			      unsigned long size, pgprot_t vma_prot)
 {
@@ -133,19 +61,42 @@ EXPORT_SYMBOL(phys_mem_access_prot);
 static void __init *early_alloc(unsigned long sz)
 {
 	void *ptr = __va(memblock_alloc(sz, sz));
+	BUG_ON(!ptr);
 	memset(ptr, 0, sz);
 	return ptr;
 }
 
-static void __init alloc_init_pte(pmd_t *pmd, unsigned long addr,
+/*
+ * remap a PMD into pages
+ */
+static void split_pmd(pmd_t *pmd, pte_t *pte)
+{
+	unsigned long pfn = pmd_pfn(*pmd);
+	int i = 0;
+
+	do {
+		/*
+		 * Need to have the least restrictive permissions available
+		 * permissions will be fixed up later
+		 */
+		set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC));
+		pfn++;
+	} while (pte++, i++, i < PTRS_PER_PTE);
+}
+
+static void alloc_init_pte(pmd_t *pmd, unsigned long addr,
 				  unsigned long end, unsigned long pfn,
-				  pgprot_t prot)
+				  pgprot_t prot,
+				  void *(*alloc)(unsigned long size))
 {
 	pte_t *pte;
 
-	if (pmd_none(*pmd)) {
-		pte = early_alloc(PTRS_PER_PTE * sizeof(pte_t));
+	if (pmd_none(*pmd) || pmd_sect(*pmd)) {
+		pte = alloc(PTRS_PER_PTE * sizeof(pte_t));
+		if (pmd_sect(*pmd))
+			split_pmd(pmd, pte);
 		__pmd_populate(pmd, __pa(pte), PMD_TYPE_TABLE);
+		flush_tlb_all();
 	}
 	BUG_ON(pmd_bad(*pmd));
 
@@ -156,30 +107,42 @@ static void __init alloc_init_pte(pmd_t *pmd, unsigned long addr,
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 }
 
-static void __init alloc_init_pmd(pud_t *pud, unsigned long addr,
-				  unsigned long end, phys_addr_t phys,
-				  int map_io)
+void split_pud(pud_t *old_pud, pmd_t *pmd)
+{
+	unsigned long addr = pud_pfn(*old_pud) << PAGE_SHIFT;
+	pgprot_t prot = __pgprot(pud_val(*old_pud) ^ addr);
+	int i = 0;
+
+	do {
+		set_pmd(pmd, __pmd(addr | prot));
+		addr += PMD_SIZE;
+	} while (pmd++, i++, i < PTRS_PER_PMD);
+}
+
+static void alloc_init_pmd(struct mm_struct *mm, pud_t *pud,
+				  unsigned long addr, unsigned long end,
+				  phys_addr_t phys, pgprot_t prot,
+				  void *(*alloc)(unsigned long size))
 {
 	pmd_t *pmd;
 	unsigned long next;
-	pmdval_t prot_sect;
-	pgprot_t prot_pte;
-
-	if (map_io) {
-		prot_sect = PROT_SECT_DEVICE_nGnRE;
-		prot_pte = __pgprot(PROT_DEVICE_nGnRE);
-	} else {
-		prot_sect = PROT_SECT_NORMAL_EXEC;
-		prot_pte = PAGE_KERNEL_EXEC;
-	}
 
 	/*
 	 * Check for initial section mappings in the pgd/pud and remove them.
 	 */
-	if (pud_none(*pud) || pud_bad(*pud)) {
-		pmd = early_alloc(PTRS_PER_PMD * sizeof(pmd_t));
-		pud_populate(&init_mm, pud, pmd);
+	if (pud_none(*pud) || pud_sect(*pud)) {
+		pmd = alloc(PTRS_PER_PMD * sizeof(pmd_t));
+		if (pud_sect(*pud)) {
+			/*
+			 * need to have the 1G of mappings continue to be
+			 * present
+			 */
+			split_pud(pud, pmd);
+		}
+		pud_populate(mm, pud, pmd);
+		flush_tlb_all();
 	}
+	BUG_ON(pud_bad(*pud));
 
 	pmd = pmd_offset(pud, addr);
 	do {
@@ -187,31 +150,51 @@ static void __init alloc_init_pmd(pud_t *pud, unsigned long addr,
 		/* try section mapping first */
 		if (((addr | next | phys) & ~SECTION_MASK) == 0) {
 			pmd_t old_pmd =*pmd;
-			set_pmd(pmd, __pmd(phys | prot_sect));
+			set_pmd(pmd, __pmd(phys |
+					   pgprot_val(mk_sect_prot(prot))));
 			/*
 			 * Check for previous table entries created during
 			 * boot (__create_page_tables) and flush them.
 			 */
-			if (!pmd_none(old_pmd))
+			if (!pmd_none(old_pmd)) {
 				flush_tlb_all();
+				if (pmd_table(old_pmd)) {
+					phys_addr_t table = __pa(pte_offset_map(&old_pmd, 0));
+					if (!WARN_ON_ONCE(slab_is_available()))
+						memblock_free(table, PAGE_SIZE);
+				}
+			}
 		} else {
 			alloc_init_pte(pmd, addr, next, __phys_to_pfn(phys),
-				       prot_pte);
+				       prot, alloc);
 		}
 		phys += next - addr;
 	} while (pmd++, addr = next, addr != end);
 }
 
-static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr,
-				  unsigned long end, phys_addr_t phys,
-				  int map_io)
+static inline bool use_1G_block(unsigned long addr, unsigned long next,
+			unsigned long phys)
+{
+	if (PAGE_SHIFT != 12)
+		return false;
+
+	if (((addr | next | phys) & ~PUD_MASK) != 0)
+		return false;
+
+	return true;
+}
+
+static void alloc_init_pud(struct mm_struct *mm, pgd_t *pgd,
+				  unsigned long addr, unsigned long end,
+				  phys_addr_t phys, pgprot_t prot,
+				  void *(*alloc)(unsigned long size))
 {
 	pud_t *pud;
 	unsigned long next;
 
 	if (pgd_none(*pgd)) {
-		pud = early_alloc(PTRS_PER_PUD * sizeof(pud_t));
-		pgd_populate(&init_mm, pgd, pud);
+		pud = alloc(PTRS_PER_PUD * sizeof(pud_t));
+		pgd_populate(mm, pgd, pud);
 	}
 	BUG_ON(pgd_bad(*pgd));
 
@@ -222,10 +205,10 @@ static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr,
 		/*
 		 * For 4K granule only, attempt to put down a 1GB block
 		 */
-		if (!map_io && (PAGE_SHIFT == 12) &&
-		    ((addr | next | phys) & ~PUD_MASK) == 0) {
+		if (use_1G_block(addr, next, phys)) {
 			pud_t old_pud = *pud;
-			set_pud(pud, __pud(phys | PROT_SECT_NORMAL_EXEC));
+			set_pud(pud, __pud(phys |
+					   pgprot_val(mk_sect_prot(prot))));
 
 			/*
 			 * If we have an old value for a pud, it will
@@ -235,12 +218,15 @@ static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr,
 			 * Look up the old pmd table and free it.
 			 */
 			if (!pud_none(old_pud)) {
-				phys_addr_t table = __pa(pmd_offset(&old_pud, 0));
-				memblock_free(table, PAGE_SIZE);
 				flush_tlb_all();
+				if (pud_table(old_pud)) {
+					phys_addr_t table = __pa(pmd_offset(&old_pud, 0));
+					if (!WARN_ON_ONCE(slab_is_available()))
+						memblock_free(table, PAGE_SIZE);
+				}
 			}
 		} else {
-			alloc_init_pmd(pud, addr, next, phys, map_io);
+			alloc_init_pmd(mm, pud, addr, next, phys, prot, alloc);
 		}
 		phys += next - addr;
 	} while (pud++, addr = next, addr != end);
@@ -250,9 +236,10 @@ static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr,
  * Create the page directory entries and any necessary page tables for the
  * mapping specified by 'md'.
  */
-static void __init __create_mapping(pgd_t *pgd, phys_addr_t phys,
-				    unsigned long virt, phys_addr_t size,
-				    int map_io)
+static void  __create_mapping(struct mm_struct *mm, pgd_t *pgd,
+				    phys_addr_t phys, unsigned long virt,
+				    phys_addr_t size, pgprot_t prot,
+				    void *(*alloc)(unsigned long size))
 {
 	unsigned long addr, length, end, next;
 
@@ -262,31 +249,95 @@ static void __init __create_mapping(pgd_t *pgd, phys_addr_t phys,
 	end = addr + length;
 	do {
 		next = pgd_addr_end(addr, end);
-		alloc_init_pud(pgd, addr, next, phys, map_io);
+		alloc_init_pud(mm, pgd, addr, next, phys, prot, alloc);
 		phys += next - addr;
 	} while (pgd++, addr = next, addr != end);
 }
 
-static void __init create_mapping(phys_addr_t phys, unsigned long virt,
-				  phys_addr_t size)
+static void *late_alloc(unsigned long size)
+{
+	void *ptr;
+
+	BUG_ON(size > PAGE_SIZE);
+	ptr = (void *)__get_free_page(PGALLOC_GFP);
+	BUG_ON(!ptr);
+	return ptr;
+}
+
+static void __ref create_mapping(phys_addr_t phys, unsigned long virt,
+				  phys_addr_t size, pgprot_t prot)
 {
 	if (virt < VMALLOC_START) {
 		pr_warn("BUG: not creating mapping for %pa at 0x%016lx - outside kernel range\n",
 			&phys, virt);
 		return;
 	}
-	__create_mapping(pgd_offset_k(virt & PAGE_MASK), phys, virt, size, 0);
+	__create_mapping(&init_mm, pgd_offset_k(virt & PAGE_MASK), phys, virt,
+			 size, prot, early_alloc);
+}
+
+void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
+			       unsigned long virt, phys_addr_t size,
+			       pgprot_t prot)
+{
+	__create_mapping(mm, pgd_offset(mm, virt), phys, virt, size, prot,
+				late_alloc);
 }
 
-void __init create_id_mapping(phys_addr_t addr, phys_addr_t size, int map_io)
+static void create_mapping_late(phys_addr_t phys, unsigned long virt,
+				  phys_addr_t size, pgprot_t prot)
 {
-	if ((addr >> PGDIR_SHIFT) >= ARRAY_SIZE(idmap_pg_dir)) {
-		pr_warn("BUG: not creating id mapping for %pa\n", &addr);
+	if (virt < VMALLOC_START) {
+		pr_warn("BUG: not creating mapping for %pa at 0x%016lx - outside kernel range\n",
+			&phys, virt);
 		return;
 	}
-	__create_mapping(&idmap_pg_dir[pgd_index(addr)],
-			 addr, addr, size, map_io);
+
+	return __create_mapping(&init_mm, pgd_offset_k(virt & PAGE_MASK),
+				phys, virt, size, prot, late_alloc);
+}
+
+#ifdef CONFIG_DEBUG_RODATA
+static void __init __map_memblock(phys_addr_t start, phys_addr_t end)
+{
+	/*
+	 * Set up the executable regions using the existing section mappings
+	 * for now. This will get more fine grained later once all memory
+	 * is mapped
+	 */
+	unsigned long kernel_x_start = round_down(__pa(_stext), SECTION_SIZE);
+	unsigned long kernel_x_end = round_up(__pa(__init_end), SECTION_SIZE);
+
+	if (end < kernel_x_start) {
+		create_mapping(start, __phys_to_virt(start),
+			end - start, PAGE_KERNEL);
+	} else if (start >= kernel_x_end) {
+		create_mapping(start, __phys_to_virt(start),
+			end - start, PAGE_KERNEL);
+	} else {
+		if (start < kernel_x_start)
+			create_mapping(start, __phys_to_virt(start),
+				kernel_x_start - start,
+				PAGE_KERNEL);
+		create_mapping(kernel_x_start,
+				__phys_to_virt(kernel_x_start),
+				kernel_x_end - kernel_x_start,
+				PAGE_KERNEL_EXEC);
+		if (kernel_x_end < end)
+			create_mapping(kernel_x_end,
+				__phys_to_virt(kernel_x_end),
+				end - kernel_x_end,
+				PAGE_KERNEL);
+	}
+
 }
+#else
+static void __init __map_memblock(phys_addr_t start, phys_addr_t end)
+{
+	create_mapping(start, __phys_to_virt(start), end - start,
+			PAGE_KERNEL_EXEC);
+}
+#endif
 
 static void __init map_mem(void)
 {
@@ -332,14 +383,53 @@ static void __init map_mem(void)
 			memblock_set_current_limit(limit);
 		}
 #endif
-
-		create_mapping(start, __phys_to_virt(start), end - start);
+		__map_memblock(start, end);
 	}
 
 	/* Limit no longer required. */
 	memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE);
 }
 
+void __init fixup_executable(void)
+{
+#ifdef CONFIG_DEBUG_RODATA
+	/* now that we are actually fully mapped, make the start/end more fine grained */
+	if (!IS_ALIGNED((unsigned long)_stext, SECTION_SIZE)) {
+		unsigned long aligned_start = round_down(__pa(_stext),
+							SECTION_SIZE);
+
+		create_mapping(aligned_start, __phys_to_virt(aligned_start),
+				__pa(_stext) - aligned_start,
+				PAGE_KERNEL);
+	}
+
+	if (!IS_ALIGNED((unsigned long)__init_end, SECTION_SIZE)) {
+		unsigned long aligned_end = round_up(__pa(__init_end),
+							SECTION_SIZE);
+		create_mapping(__pa(__init_end), (unsigned long)__init_end,
+				aligned_end - __pa(__init_end),
+				PAGE_KERNEL);
+	}
+#endif
+}
+
+#ifdef CONFIG_DEBUG_RODATA
+void mark_rodata_ro(void)
+{
+	create_mapping_late(__pa(_stext), (unsigned long)_stext,
+				(unsigned long)_etext - (unsigned long)_stext,
+				PAGE_KERNEL_EXEC | PTE_RDONLY);
+
+}
+#endif
+
+void fixup_init(void)
+{
+	create_mapping_late(__pa(__init_begin), (unsigned long)__init_begin,
+			(unsigned long)__init_end - (unsigned long)__init_begin,
+			PAGE_KERNEL);
+}
+
 /*
  * paging_init() sets up the page tables, initialises the zone memory
  * maps and sets up the zero page.
@@ -349,13 +439,7 @@ void __init paging_init(void)
 	void *zero_page;
 
 	map_mem();
-
-	/*
-	 * Finally flush the caches and tlb to ensure that we're in a
-	 * consistent state.
-	 */
-	flush_cache_all();
-	flush_tlb_all();
+	fixup_executable();
 
 	/* allocate the zero page. */
 	zero_page = early_alloc(PAGE_SIZE);