1 files changed, 196 insertions, 76 deletions

diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 478d6763a01a..747e5b1ef02d 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -20,6 +20,9 @@
 #include <linux/dma-map-ops.h>
 #include <linux/crash_dump.h>
 #include <linux/hugetlb.h>
+#ifdef CONFIG_RELOCATABLE
+#include <linux/elf.h>
+#endif
 
 #include <asm/fixmap.h>
 #include <asm/tlbflush.h>
@@ -57,7 +60,6 @@ unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]
 EXPORT_SYMBOL(empty_zero_page);
 
 extern char _start[];
-#define DTB_EARLY_BASE_VA      PGDIR_SIZE
 void *_dtb_early_va __initdata;
 uintptr_t _dtb_early_pa __initdata;
 
@@ -146,7 +148,7 @@ static void __init print_vm_layout(void)
 		print_ml("kasan", KASAN_SHADOW_START, KASAN_SHADOW_END);
 #endif
 
-		print_ml("kernel", (unsigned long)KERNEL_LINK_ADDR,
+		print_ml("kernel", (unsigned long)kernel_map.virt_addr,
 			 (unsigned long)ADDRESS_SPACE_END);
 	}
 }
@@ -213,6 +215,14 @@ static void __init setup_bootmem(void)
 	phys_ram_end = memblock_end_of_DRAM();
 	if (!IS_ENABLED(CONFIG_XIP_KERNEL))
 		phys_ram_base = memblock_start_of_DRAM();
+
+	/*
+	 * In 64-bit, any use of __va/__pa before this point is wrong as we
+	 * did not know the start of DRAM before.
+	 */
+	if (IS_ENABLED(CONFIG_64BIT))
+		kernel_map.va_pa_offset = PAGE_OFFSET - phys_ram_base;
+
 	/*
 	 * memblock allocator is not aware of the fact that last 4K bytes of
 	 * the addressable memory can not be mapped because of IS_ERR_VALUE
@@ -236,31 +246,22 @@ static void __init setup_bootmem(void)
 	set_max_mapnr(max_low_pfn - ARCH_PFN_OFFSET);
 
 	reserve_initrd_mem();
+
+	/*
+	 * No allocation should be done before reserving the memory as defined
+	 * in the device tree, otherwise the allocation could end up in a
+	 * reserved region.
+	 */
+	early_init_fdt_scan_reserved_mem();
+
 	/*
 	 * If DTB is built in, no need to reserve its memblock.
 	 * Otherwise, do reserve it but avoid using
 	 * early_init_fdt_reserve_self() since __pa() does
 	 * not work for DTB pointers that are fixmap addresses
 	 */
-	if (!IS_ENABLED(CONFIG_BUILTIN_DTB)) {
-		/*
-		 * In case the DTB is not located in a memory region we won't
-		 * be able to locate it later on via the linear mapping and
-		 * get a segfault when accessing it via __va(dtb_early_pa).
-		 * To avoid this situation copy DTB to a memory region.
-		 * Note that memblock_phys_alloc will also reserve DTB region.
-		 */
-		if (!memblock_is_memory(dtb_early_pa)) {
-			size_t fdt_size = fdt_totalsize(dtb_early_va);
-			phys_addr_t new_dtb_early_pa = memblock_phys_alloc(fdt_size, PAGE_SIZE);
-			void *new_dtb_early_va = early_memremap(new_dtb_early_pa, fdt_size);
-
-			memcpy(new_dtb_early_va, dtb_early_va, fdt_size);
-			early_memunmap(new_dtb_early_va, fdt_size);
-			_dtb_early_pa = new_dtb_early_pa;
-		} else
-			memblock_reserve(dtb_early_pa, fdt_totalsize(dtb_early_va));
-	}
+	if (!IS_ENABLED(CONFIG_BUILTIN_DTB))
+		memblock_reserve(dtb_early_pa, fdt_totalsize(dtb_early_va));
 
 	dma_contiguous_reserve(dma32_phys_limit);
 	if (IS_ENABLED(CONFIG_64BIT))
@@ -271,21 +272,14 @@ static void __init setup_bootmem(void)
 #ifdef CONFIG_MMU
 struct pt_alloc_ops pt_ops __initdata;
 
-unsigned long riscv_pfn_base __ro_after_init;
-EXPORT_SYMBOL(riscv_pfn_base);
-
 pgd_t swapper_pg_dir[PTRS_PER_PGD] __page_aligned_bss;
 pgd_t trampoline_pg_dir[PTRS_PER_PGD] __page_aligned_bss;
 static pte_t fixmap_pte[PTRS_PER_PTE] __page_aligned_bss;
 
 pgd_t early_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE);
-static p4d_t __maybe_unused early_dtb_p4d[PTRS_PER_P4D] __initdata __aligned(PAGE_SIZE);
-static pud_t __maybe_unused early_dtb_pud[PTRS_PER_PUD] __initdata __aligned(PAGE_SIZE);
-static pmd_t __maybe_unused early_dtb_pmd[PTRS_PER_PMD] __initdata __aligned(PAGE_SIZE);
 
 #ifdef CONFIG_XIP_KERNEL
 #define pt_ops			(*(struct pt_alloc_ops *)XIP_FIXUP(&pt_ops))
-#define riscv_pfn_base         (*(unsigned long  *)XIP_FIXUP(&riscv_pfn_base))
 #define trampoline_pg_dir      ((pgd_t *)XIP_FIXUP(trampoline_pg_dir))
 #define fixmap_pte             ((pte_t *)XIP_FIXUP(fixmap_pte))
 #define early_pg_dir           ((pgd_t *)XIP_FIXUP(early_pg_dir))
@@ -626,9 +620,6 @@ static void __init create_p4d_mapping(p4d_t *p4dp,
 #define trampoline_pgd_next	(pgtable_l5_enabled ?			\
 		(uintptr_t)trampoline_p4d : (pgtable_l4_enabled ?	\
 		(uintptr_t)trampoline_pud : (uintptr_t)trampoline_pmd))
-#define early_dtb_pgd_next	(pgtable_l5_enabled ?			\
-		(uintptr_t)early_dtb_p4d : (pgtable_l4_enabled ?	\
-		(uintptr_t)early_dtb_pud : (uintptr_t)early_dtb_pmd))
 #else
 #define pgd_next_t		pte_t
 #define alloc_pgd_next(__va)	pt_ops.alloc_pte(__va)
@@ -636,7 +627,6 @@ static void __init create_p4d_mapping(p4d_t *p4dp,
 #define create_pgd_next_mapping(__nextp, __va, __pa, __sz, __prot)	\
 	create_pte_mapping(__nextp, __va, __pa, __sz, __prot)
 #define fixmap_pgd_next		((uintptr_t)fixmap_pte)
-#define early_dtb_pgd_next	((uintptr_t)early_dtb_pmd)
 #define create_p4d_mapping(__pmdp, __va, __pa, __sz, __prot) do {} while(0)
 #define create_pud_mapping(__pmdp, __va, __pa, __sz, __prot) do {} while(0)
 #define create_pmd_mapping(__pmdp, __va, __pa, __sz, __prot) do {} while(0)
@@ -671,9 +661,16 @@ void __init create_pgd_mapping(pgd_t *pgdp,
 
 static uintptr_t __init best_map_size(phys_addr_t base, phys_addr_t size)
 {
-	/* Upgrade to PMD_SIZE mappings whenever possible */
-	base &= PMD_SIZE - 1;
-	if (!base && size >= PMD_SIZE)
+	if (!(base & (PGDIR_SIZE - 1)) && size >= PGDIR_SIZE)
+		return PGDIR_SIZE;
+
+	if (!(base & (P4D_SIZE - 1)) && size >= P4D_SIZE)
+		return P4D_SIZE;
+
+	if (!(base & (PUD_SIZE - 1)) && size >= PUD_SIZE)
+		return PUD_SIZE;
+
+	if (!(base & (PMD_SIZE - 1)) && size >= PMD_SIZE)
 		return PMD_SIZE;
 
 	return PAGE_SIZE;
@@ -732,6 +729,8 @@ static __init pgprot_t pgprot_from_va(uintptr_t va)
 #endif /* CONFIG_STRICT_KERNEL_RWX */
 
 #if defined(CONFIG_64BIT) && !defined(CONFIG_XIP_KERNEL)
+u64 __pi_set_satp_mode_from_cmdline(uintptr_t dtb_pa);
+
 static void __init disable_pgtable_l5(void)
 {
 	pgtable_l5_enabled = false;
@@ -746,17 +745,39 @@ static void __init disable_pgtable_l4(void)
 	satp_mode = SATP_MODE_39;
 }
 
+static int __init print_no4lvl(char *p)
+{
+	pr_info("Disabled 4-level and 5-level paging");
+	return 0;
+}
+early_param("no4lvl", print_no4lvl);
+
+static int __init print_no5lvl(char *p)
+{
+	pr_info("Disabled 5-level paging");
+	return 0;
+}
+early_param("no5lvl", print_no5lvl);
+
 /*
  * There is a simple way to determine if 4-level is supported by the
  * underlying hardware: establish 1:1 mapping in 4-level page table mode
  * then read SATP to see if the configuration was taken into account
  * meaning sv48 is supported.
  */
-static __init void set_satp_mode(void)
+static __init void set_satp_mode(uintptr_t dtb_pa)
 {
 	u64 identity_satp, hw_satp;
 	uintptr_t set_satp_mode_pmd = ((unsigned long)set_satp_mode) & PMD_MASK;
-	bool check_l4 = false;
+	u64 satp_mode_cmdline = __pi_set_satp_mode_from_cmdline(dtb_pa);
+
+	if (satp_mode_cmdline == SATP_MODE_57) {
+		disable_pgtable_l5();
+	} else if (satp_mode_cmdline == SATP_MODE_48) {
+		disable_pgtable_l5();
+		disable_pgtable_l4();
+		return;
+	}
 
 	create_p4d_mapping(early_p4d,
 			set_satp_mode_pmd, (uintptr_t)early_pud,
@@ -775,7 +796,8 @@ static __init void set_satp_mode(void)
 retry:
 	create_pgd_mapping(early_pg_dir,
 			   set_satp_mode_pmd,
-			   check_l4 ? (uintptr_t)early_pud : (uintptr_t)early_p4d,
+			   pgtable_l5_enabled ?
+				(uintptr_t)early_p4d : (uintptr_t)early_pud,
 			   PGDIR_SIZE, PAGE_TABLE);
 
 	identity_satp = PFN_DOWN((uintptr_t)&early_pg_dir) | satp_mode;
@@ -786,9 +808,8 @@ retry:
 	local_flush_tlb_all();
 
 	if (hw_satp != identity_satp) {
-		if (!check_l4) {
+		if (pgtable_l5_enabled) {
 			disable_pgtable_l5();
-			check_l4 = true;
 			memset(early_pg_dir, 0, PAGE_SIZE);
 			goto retry;
 		}
@@ -820,6 +841,44 @@ retry:
 #error "setup_vm() is called from head.S before relocate so it should not use absolute addressing."
 #endif
 
+#ifdef CONFIG_RELOCATABLE
+extern unsigned long __rela_dyn_start, __rela_dyn_end;
+
+static void __init relocate_kernel(void)
+{
+	Elf64_Rela *rela = (Elf64_Rela *)&__rela_dyn_start;
+	/*
+	 * This holds the offset between the linked virtual address and the
+	 * relocated virtual address.
+	 */
+	uintptr_t reloc_offset = kernel_map.virt_addr - KERNEL_LINK_ADDR;
+	/*
+	 * This holds the offset between kernel linked virtual address and
+	 * physical address.
+	 */
+	uintptr_t va_kernel_link_pa_offset = KERNEL_LINK_ADDR - kernel_map.phys_addr;
+
+	for ( ; rela < (Elf64_Rela *)&__rela_dyn_end; rela++) {
+		Elf64_Addr addr = (rela->r_offset - va_kernel_link_pa_offset);
+		Elf64_Addr relocated_addr = rela->r_addend;
+
+		if (rela->r_info != R_RISCV_RELATIVE)
+			continue;
+
+		/*
+		 * Make sure to not relocate vdso symbols like rt_sigreturn
+		 * which are linked from the address 0 in vmlinux since
+		 * vdso symbol addresses are actually used as an offset from
+		 * mm->context.vdso in VDSO_OFFSET macro.
+		 */
+		if (relocated_addr >= KERNEL_LINK_ADDR)
+			relocated_addr += reloc_offset;
+
+		*(Elf64_Addr *)addr = relocated_addr;
+	}
+}
+#endif /* CONFIG_RELOCATABLE */
+
 #ifdef CONFIG_XIP_KERNEL
 static void __init create_kernel_page_table(pgd_t *pgdir,
 					    __always_unused bool early)
@@ -860,32 +919,27 @@ static void __init create_kernel_page_table(pgd_t *pgdir, bool early)
  * this means 2 PMD entries whereas for 32-bit kernel, this is only 1 PGDIR
  * entry.
  */
-static void __init create_fdt_early_page_table(pgd_t *pgdir, uintptr_t dtb_pa)
+static void __init create_fdt_early_page_table(uintptr_t fix_fdt_va,
+					       uintptr_t dtb_pa)
 {
-#ifndef CONFIG_BUILTIN_DTB
 	uintptr_t pa = dtb_pa & ~(PMD_SIZE - 1);
 
-	create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA,
-			   IS_ENABLED(CONFIG_64BIT) ? early_dtb_pgd_next : pa,
-			   PGDIR_SIZE,
-			   IS_ENABLED(CONFIG_64BIT) ? PAGE_TABLE : PAGE_KERNEL);
-
-	if (pgtable_l5_enabled)
-		create_p4d_mapping(early_dtb_p4d, DTB_EARLY_BASE_VA,
-				   (uintptr_t)early_dtb_pud, P4D_SIZE, PAGE_TABLE);
-
-	if (pgtable_l4_enabled)
-		create_pud_mapping(early_dtb_pud, DTB_EARLY_BASE_VA,
-				   (uintptr_t)early_dtb_pmd, PUD_SIZE, PAGE_TABLE);
+#ifndef CONFIG_BUILTIN_DTB
+	/* Make sure the fdt fixmap address is always aligned on PMD size */
+	BUILD_BUG_ON(FIX_FDT % (PMD_SIZE / PAGE_SIZE));
 
-	if (IS_ENABLED(CONFIG_64BIT)) {
-		create_pmd_mapping(early_dtb_pmd, DTB_EARLY_BASE_VA,
+	/* In 32-bit only, the fdt lies in its own PGD */
+	if (!IS_ENABLED(CONFIG_64BIT)) {
+		create_pgd_mapping(early_pg_dir, fix_fdt_va,
+				   pa, MAX_FDT_SIZE, PAGE_KERNEL);
+	} else {
+		create_pmd_mapping(fixmap_pmd, fix_fdt_va,
 				   pa, PMD_SIZE, PAGE_KERNEL);
-		create_pmd_mapping(early_dtb_pmd, DTB_EARLY_BASE_VA + PMD_SIZE,
+		create_pmd_mapping(fixmap_pmd, fix_fdt_va + PMD_SIZE,
 				   pa + PMD_SIZE, PMD_SIZE, PAGE_KERNEL);
 	}
 
-	dtb_early_va = (void *)DTB_EARLY_BASE_VA + (dtb_pa & (PMD_SIZE - 1));
+	dtb_early_va = (void *)fix_fdt_va + (dtb_pa & (PMD_SIZE - 1));
 #else
 	/*
 	 * For 64-bit kernel, __va can't be used since it would return a linear
@@ -979,14 +1033,25 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 #endif
 
 #if defined(CONFIG_64BIT) && !defined(CONFIG_XIP_KERNEL)
-	set_satp_mode();
+	set_satp_mode(dtb_pa);
 #endif
 
-	kernel_map.va_pa_offset = PAGE_OFFSET - kernel_map.phys_addr;
+	/*
+	 * In 64-bit, we defer the setup of va_pa_offset to setup_bootmem,
+	 * where we have the system memory layout: this allows us to align
+	 * the physical and virtual mappings and then make use of PUD/P4D/PGD
+	 * for the linear mapping. This is only possible because the kernel
+	 * mapping lies outside the linear mapping.
+	 * In 32-bit however, as the kernel resides in the linear mapping,
+	 * setup_vm_final can not change the mapping established here,
+	 * otherwise the same kernel addresses would get mapped to different
+	 * physical addresses (if the start of dram is different from the
+	 * kernel physical address start).
+	 */
+	kernel_map.va_pa_offset = IS_ENABLED(CONFIG_64BIT) ?
+				0UL : PAGE_OFFSET - kernel_map.phys_addr;
 	kernel_map.va_kernel_pa_offset = kernel_map.virt_addr - kernel_map.phys_addr;
 
-	riscv_pfn_base = PFN_DOWN(kernel_map.phys_addr);
-
 	/*
 	 * The default maximal physical memory size is KERN_VIRT_SIZE for 32-bit
 	 * kernel, whereas for 64-bit kernel, the end of the virtual address
@@ -1007,6 +1072,17 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 	BUG_ON((kernel_map.virt_addr + kernel_map.size) > ADDRESS_SPACE_END - SZ_4K);
 #endif
 
+#ifdef CONFIG_RELOCATABLE
+	/*
+	 * Early page table uses only one PUD, which makes it possible
+	 * to map PUD_SIZE aligned on PUD_SIZE: if the relocation offset
+	 * makes the kernel cross over a PUD_SIZE boundary, raise a bug
+	 * since a part of the kernel would not get mapped.
+	 */
+	BUG_ON(PUD_SIZE - (kernel_map.virt_addr & (PUD_SIZE - 1)) < kernel_map.size);
+	relocate_kernel();
+#endif
+
 	apply_early_boot_alternatives();
 	pt_ops_set_early();
 
@@ -1055,7 +1131,7 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 	create_kernel_page_table(early_pg_dir, true);
 
 	/* Setup early mapping for FDT early scan */
-	create_fdt_early_page_table(early_pg_dir, dtb_pa);
+	create_fdt_early_page_table(__fix_to_virt(FIX_FDT), dtb_pa);
 
 	/*
 	 * Bootime fixmap only can handle PMD_SIZE mapping. Thus, boot-ioremap
@@ -1090,16 +1166,36 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 	pt_ops_set_fixmap();
 }
 
-static void __init setup_vm_final(void)
+static void __init create_linear_mapping_range(phys_addr_t start,
+					       phys_addr_t end)
 {
+	phys_addr_t pa;
 	uintptr_t va, map_size;
-	phys_addr_t pa, start, end;
+
+	for (pa = start; pa < end; pa += map_size) {
+		va = (uintptr_t)__va(pa);
+		map_size = best_map_size(pa, end - pa);
+
+		create_pgd_mapping(swapper_pg_dir, va, pa, map_size,
+				   pgprot_from_va(va));
+	}
+}
+
+static void __init create_linear_mapping_page_table(void)
+{
+	phys_addr_t start, end;
 	u64 i;
 
-	/* Setup swapper PGD for fixmap */
-	create_pgd_mapping(swapper_pg_dir, FIXADDR_START,
-			   __pa_symbol(fixmap_pgd_next),
-			   PGDIR_SIZE, PAGE_TABLE);
+#ifdef CONFIG_STRICT_KERNEL_RWX
+	phys_addr_t ktext_start = __pa_symbol(_start);
+	phys_addr_t ktext_size = __init_data_begin - _start;
+	phys_addr_t krodata_start = __pa_symbol(__start_rodata);
+	phys_addr_t krodata_size = _data - __start_rodata;
+
+	/* Isolate kernel text and rodata so they don't get mapped with a PUD */
+	memblock_mark_nomap(ktext_start,  ktext_size);
+	memblock_mark_nomap(krodata_start, krodata_size);
+#endif
 
 	/* Map all memory banks in the linear mapping */
 	for_each_mem_range(i, &start, &end) {
@@ -1111,15 +1207,39 @@ static void __init setup_vm_final(void)
 		if (end >= __pa(PAGE_OFFSET) + memory_limit)
 			end = __pa(PAGE_OFFSET) + memory_limit;
 
-		for (pa = start; pa < end; pa += map_size) {
-			va = (uintptr_t)__va(pa);
-			map_size = best_map_size(pa, end - pa);
-
-			create_pgd_mapping(swapper_pg_dir, va, pa, map_size,
-					   pgprot_from_va(va));
-		}
+		create_linear_mapping_range(start, end);
 	}
 
+#ifdef CONFIG_STRICT_KERNEL_RWX
+	create_linear_mapping_range(ktext_start, ktext_start + ktext_size);
+	create_linear_mapping_range(krodata_start,
+				    krodata_start + krodata_size);
+
+	memblock_clear_nomap(ktext_start,  ktext_size);
+	memblock_clear_nomap(krodata_start, krodata_size);
+#endif
+}
+
+static void __init setup_vm_final(void)
+{
+	/* Setup swapper PGD for fixmap */
+#if !defined(CONFIG_64BIT)
+	/*
+	 * In 32-bit, the device tree lies in a pgd entry, so it must be copied
+	 * directly in swapper_pg_dir in addition to the pgd entry that points
+	 * to fixmap_pte.
+	 */
+	unsigned long idx = pgd_index(__fix_to_virt(FIX_FDT));
+
+	set_pgd(&swapper_pg_dir[idx], early_pg_dir[idx]);
+#endif
+	create_pgd_mapping(swapper_pg_dir, FIXADDR_START,
+			   __pa_symbol(fixmap_pgd_next),
+			   PGDIR_SIZE, PAGE_TABLE);
+
+	/* Map the linear mapping */
+	create_linear_mapping_page_table();
+
 	/* Map the kernel */
 	if (IS_ENABLED(CONFIG_64BIT))
 		create_kernel_page_table(swapper_pg_dir, false);