16 files changed, 113 insertions, 49 deletions

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 128192e14ff2..3230c1d48562 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -23,6 +23,8 @@ config RISCV
 	select ARCH_HAS_SET_DIRECT_MAP
 	select ARCH_HAS_SET_MEMORY
 	select ARCH_HAS_STRICT_KERNEL_RWX if MMU
+	select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX
+	select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT
 	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU
 	select ARCH_WANT_FRAME_POINTERS
 	select ARCH_WANT_HUGE_PMD_SHARE if 64BIT
diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h
index 3f1737f301cc..d0e24aaa2aa0 100644
--- a/arch/riscv/include/asm/barrier.h
+++ b/arch/riscv/include/asm/barrier.h
@@ -58,8 +58,16 @@ do {									\
  * The AQ/RL pair provides a RCpc critical section, but there's not really any
  * way we can take advantage of that here because the ordering is only enforced
  * on that one lock.  Thus, we're just doing a full fence.
+ *
+ * Since we allow writeX to be called from preemptive regions we need at least
+ * an "o" in the predecessor set to ensure device writes are visible before the
+ * task is marked as available for scheduling on a new hart.  While I don't see
+ * any concrete reason we need a full IO fence, it seems safer to just upgrade
+ * this in order to avoid any IO crossing a scheduling boundary.  In both
+ * instances the scheduler pairs this with an mb(), so nothing is necessary on
+ * the new hart.
  */
-#define smp_mb__after_spinlock()	RISCV_FENCE(rw,rw)
+#define smp_mb__after_spinlock()	RISCV_FENCE(iorw,iorw)
 
 #include <asm-generic/barrier.h>
 
diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index d969bab4a26b..262e5bbb2776 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -179,7 +179,7 @@
 			"	bnez %1, 0b\n"				\
 			"1:\n"						\
 			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
-			: "rJ" (__old), "rJ" (__new)			\
+			: "rJ" ((long)__old), "rJ" (__new)		\
 			: "memory");					\
 		break;							\
 	case 8:								\
@@ -224,7 +224,7 @@
 			RISCV_ACQUIRE_BARRIER				\
 			"1:\n"						\
 			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
-			: "rJ" (__old), "rJ" (__new)			\
+			: "rJ" ((long)__old), "rJ" (__new)		\
 			: "memory");					\
 		break;							\
 	case 8:								\
@@ -270,7 +270,7 @@
 			"	bnez %1, 0b\n"				\
 			"1:\n"						\
 			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
-			: "rJ" (__old), "rJ" (__new)			\
+			: "rJ" ((long)__old), "rJ" (__new)		\
 			: "memory");					\
 		break;							\
 	case 8:								\
@@ -316,7 +316,7 @@
 			"	fence rw, rw\n"				\
 			"1:\n"						\
 			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
-			: "rJ" (__old), "rJ" (__new)			\
+			: "rJ" ((long)__old), "rJ" (__new)		\
 			: "memory");					\
 		break;							\
 	case 8:								\
diff --git a/arch/riscv/include/asm/gdb_xml.h b/arch/riscv/include/asm/gdb_xml.h
index 041b45f5b997..09342111f227 100644
--- a/arch/riscv/include/asm/gdb_xml.h
+++ b/arch/riscv/include/asm/gdb_xml.h
@@ -3,8 +3,7 @@
 #ifndef __ASM_GDB_XML_H_
 #define __ASM_GDB_XML_H_
 
-#define kgdb_arch_gdb_stub_feature riscv_gdb_stub_feature
-static const char riscv_gdb_stub_feature[64] =
+const char riscv_gdb_stub_feature[64] =
 			"PacketSize=800;qXfer:features:read+;";
 
 static const char gdb_xfer_read_target[31] = "qXfer:features:read:target.xml:";
diff --git a/arch/riscv/include/asm/kgdb.h b/arch/riscv/include/asm/kgdb.h
index 8177a457caff..46677daf708b 100644
--- a/arch/riscv/include/asm/kgdb.h
+++ b/arch/riscv/include/asm/kgdb.h
@@ -19,7 +19,6 @@
 
 #ifndef	__ASSEMBLY__
 
-extern int kgdb_has_hit_break(unsigned long addr);
 extern unsigned long kgdb_compiled_break;
 
 static inline void arch_kgdb_breakpoint(void)
@@ -106,7 +105,9 @@ static inline void arch_kgdb_breakpoint(void)
 #define DBG_REG_BADADDR_OFF 34
 #define DBG_REG_CAUSE_OFF 35
 
-#include <asm/gdb_xml.h>
+extern const char riscv_gdb_stub_feature[64];
+
+#define kgdb_arch_gdb_stub_feature riscv_gdb_stub_feature
 
 #endif
 #endif
diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h
index 1dd12a0cbb2b..464a2bbc97ea 100644
--- a/arch/riscv/include/asm/thread_info.h
+++ b/arch/riscv/include/asm/thread_info.h
@@ -12,7 +12,11 @@
 #include <linux/const.h>
 
 /* thread information allocation */
+#ifdef CONFIG_64BIT
+#define THREAD_SIZE_ORDER	(2)
+#else
 #define THREAD_SIZE_ORDER	(1)
+#endif
 #define THREAD_SIZE		(PAGE_SIZE << THREAD_SIZE_ORDER)
 
 #ifndef __ASSEMBLY__
diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
index 08396614d6f4..2ff63d0cbb50 100644
--- a/arch/riscv/kernel/ftrace.c
+++ b/arch/riscv/kernel/ftrace.c
@@ -38,7 +38,8 @@ static int ftrace_check_current_call(unsigned long hook_pos,
 	 * Read the text we want to modify;
 	 * return must be -EFAULT on read error
 	 */
-	if (probe_kernel_read(replaced, (void *)hook_pos, MCOUNT_INSN_SIZE))
+	if (copy_from_kernel_nofault(replaced, (void *)hook_pos,
+			MCOUNT_INSN_SIZE))
 		return -EFAULT;
 
 	/*
diff --git a/arch/riscv/kernel/kgdb.c b/arch/riscv/kernel/kgdb.c
index f16ade84a11f..963ed7edcff2 100644
--- a/arch/riscv/kernel/kgdb.c
+++ b/arch/riscv/kernel/kgdb.c
@@ -44,25 +44,25 @@ DECLARE_INSN(c_beqz, MATCH_C_BEQZ, MASK_C_BEQZ)
 DECLARE_INSN(c_bnez, MATCH_C_BNEZ, MASK_C_BNEZ)
 DECLARE_INSN(sret, MATCH_SRET, MASK_SRET)
 
-int decode_register_index(unsigned long opcode, int offset)
+static int decode_register_index(unsigned long opcode, int offset)
 {
 	return (opcode >> offset) & 0x1F;
 }
 
-int decode_register_index_short(unsigned long opcode, int offset)
+static int decode_register_index_short(unsigned long opcode, int offset)
 {
 	return ((opcode >> offset) & 0x7) + 8;
 }
 
 /* Calculate the new address for after a step */
-int get_step_address(struct pt_regs *regs, unsigned long *next_addr)
+static int get_step_address(struct pt_regs *regs, unsigned long *next_addr)
 {
 	unsigned long pc = regs->epc;
 	unsigned long *regs_ptr = (unsigned long *)regs;
 	unsigned int rs1_num, rs2_num;
 	int op_code;
 
-	if (probe_kernel_address((void *)pc, op_code))
+	if (get_kernel_nofault(op_code, (void *)pc))
 		return -EINVAL;
 	if ((op_code & __INSN_LENGTH_MASK) != __INSN_LENGTH_GE_32) {
 		if (is_c_jalr_insn(op_code) || is_c_jr_insn(op_code)) {
@@ -136,7 +136,7 @@ int get_step_address(struct pt_regs *regs, unsigned long *next_addr)
 	return 0;
 }
 
-int do_single_step(struct pt_regs *regs)
+static int do_single_step(struct pt_regs *regs)
 {
 	/* Determine where the target instruction will send us to */
 	unsigned long addr = 0;
@@ -146,14 +146,14 @@ int do_single_step(struct pt_regs *regs)
 		return error;
 
 	/* Store the op code in the stepped address */
-	error = probe_kernel_address((void *)addr, stepped_opcode);
+	error = get_kernel_nofault(stepped_opcode, (void *)addr);
 	if (error)
 		return error;
 
 	stepped_address = addr;
 
 	/* Replace the op code with the break instruction */
-	error = probe_kernel_write((void *)stepped_address,
+	error = copy_to_kernel_nofault((void *)stepped_address,
 				   arch_kgdb_ops.gdb_bpt_instr,
 				   BREAK_INSTR_SIZE);
 	/* Flush and return */
@@ -173,7 +173,7 @@ int do_single_step(struct pt_regs *regs)
 static void undo_single_step(struct pt_regs *regs)
 {
 	if (stepped_opcode != 0) {
-		probe_kernel_write((void *)stepped_address,
+		copy_to_kernel_nofault((void *)stepped_address,
 				   (void *)&stepped_opcode, BREAK_INSTR_SIZE);
 		flush_icache_range(stepped_address,
 				   stepped_address + BREAK_INSTR_SIZE);
@@ -320,7 +320,7 @@ int kgdb_arch_handle_exception(int vector, int signo, int err_code,
 	return err;
 }
 
-int kgdb_riscv_kgdbbreak(unsigned long addr)
+static int kgdb_riscv_kgdbbreak(unsigned long addr)
 {
 	if (stepped_address == addr)
 		return KGDB_SW_SINGLE_STEP;
diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c
index d4a64dfed342..3fe7a5296aa5 100644
--- a/arch/riscv/kernel/patch.c
+++ b/arch/riscv/kernel/patch.c
@@ -63,7 +63,7 @@ static int patch_insn_write(void *addr, const void *insn, size_t len)
 
 	waddr = patch_map(addr, FIX_TEXT_POKE0);
 
-	ret = probe_kernel_write(waddr, insn, len);
+	ret = copy_to_kernel_nofault(waddr, insn, len);
 
 	patch_unmap(FIX_TEXT_POKE0);
 
@@ -76,7 +76,7 @@ NOKPROBE_SYMBOL(patch_insn_write);
 #else
 static int patch_insn_write(void *addr, const void *insn, size_t len)
 {
-	return probe_kernel_write(addr, insn, len);
+	return copy_to_kernel_nofault(addr, insn, len);
 }
 NOKPROBE_SYMBOL(patch_insn_write);
 #endif /* CONFIG_MMU */
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
index f3619f59d85c..12f8a7fce78b 100644
--- a/arch/riscv/kernel/sys_riscv.c
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -8,6 +8,7 @@
 #include <linux/syscalls.h>
 #include <asm/unistd.h>
 #include <asm/cacheflush.h>
+#include <asm-generic/mman-common.h>
 
 static long riscv_sys_mmap(unsigned long addr, unsigned long len,
 			   unsigned long prot, unsigned long flags,
@@ -16,6 +17,11 @@ static long riscv_sys_mmap(unsigned long addr, unsigned long len,
 {
 	if (unlikely(offset & (~PAGE_MASK >> page_shift_offset)))
 		return -EINVAL;
+
+	if ((prot & PROT_WRITE) && (prot & PROT_EXEC))
+		if (unlikely(!(prot & PROT_READ)))
+			return -EINVAL;
+
 	return ksys_mmap_pgoff(addr, len, prot, flags, fd,
 			       offset >> (PAGE_SHIFT - page_shift_offset));
 }
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index ecec1778e3a4..7d95cce5e47c 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -137,7 +137,7 @@ static inline unsigned long get_break_insn_length(unsigned long pc)
 {
 	bug_insn_t insn;
 
-	if (probe_kernel_address((bug_insn_t *)pc, insn))
+	if (get_kernel_nofault(insn, (bug_insn_t *)pc))
 		return 0;
 
 	return GET_INSN_LENGTH(insn);
@@ -165,7 +165,7 @@ int is_valid_bugaddr(unsigned long pc)
 
 	if (pc < VMALLOC_START)
 		return 0;
-	if (probe_kernel_address((bug_insn_t *)pc, insn))
+	if (get_kernel_nofault(insn, (bug_insn_t *)pc))
 		return 0;
 	if ((insn & __INSN_LENGTH_MASK) == __INSN_LENGTH_32)
 		return (insn == __BUG_INSN_32);
diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile
index 38ba55b0eb9d..e4c7c2c8a02f 100644
--- a/arch/riscv/kernel/vdso/Makefile
+++ b/arch/riscv/kernel/vdso/Makefile
@@ -17,7 +17,7 @@ vdso-syms += flush_icache
 obj-vdso = $(patsubst %, %.o, $(vdso-syms)) note.o
 
 ifneq ($(c-gettimeofday-y),)
-  CFLAGS_vgettimeofday.o += -include $(c-gettimeofday-y)
+  CFLAGS_vgettimeofday.o += -fPIC -include $(c-gettimeofday-y)
 endif
 
 # Build rules
@@ -27,6 +27,9 @@ obj-vdso := $(addprefix $(obj)/, $(obj-vdso))
 obj-y += vdso.o vdso-syms.o
 CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
 
+# Disable -pg to prevent insert call site
+CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os
+
 # Disable gcov profiling for VDSO code
 GCOV_PROFILE := n
 
diff --git a/arch/riscv/kernel/vdso/vgettimeofday.c b/arch/riscv/kernel/vdso/vgettimeofday.c
index d264943e2e47..cc0d80699c31 100644
--- a/arch/riscv/kernel/vdso/vgettimeofday.c
+++ b/arch/riscv/kernel/vdso/vgettimeofday.c
@@ -9,16 +9,22 @@
 #include <linux/time.h>
 #include <linux/types.h>
 
+extern
+int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts);
 int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts)
 {
 	return __cvdso_clock_gettime(clock, ts);
 }
 
+extern
+int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz);
 int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
 {
 	return __cvdso_gettimeofday(tv, tz);
 }
 
+extern
+int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res);
 int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res)
 {
 	return __cvdso_clock_getres(clock_id, res);
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index f4adb3684f3d..79e9d55bdf1a 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -95,19 +95,40 @@ void __init mem_init(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 static void __init setup_initrd(void)
 {
+	phys_addr_t start;
 	unsigned long size;
 
-	if (initrd_start >= initrd_end) {
-		pr_info("initrd not found or empty");
+	/* Ignore the virtul address computed during device tree parsing */
+	initrd_start = initrd_end = 0;
+
+	if (!phys_initrd_size)
+		return;
+	/*
+	 * Round the memory region to page boundaries as per free_initrd_mem()
+	 * This allows us to detect whether the pages overlapping the initrd
+	 * are in use, but more importantly, reserves the entire set of pages
+	 * as we don't want these pages allocated for other purposes.
+	 */
+	start = round_down(phys_initrd_start, PAGE_SIZE);
+	size = phys_initrd_size + (phys_initrd_start - start);
+	size = round_up(size, PAGE_SIZE);
+
+	if (!memblock_is_region_memory(start, size)) {
+		pr_err("INITRD: 0x%08llx+0x%08lx is not a memory region",
+		       (u64)start, size);
 		goto disable;
 	}
-	if (__pa_symbol(initrd_end) > PFN_PHYS(max_low_pfn)) {
-		pr_err("initrd extends beyond end of memory");
+
+	if (memblock_is_region_reserved(start, size)) {
+		pr_err("INITRD: 0x%08llx+0x%08lx overlaps in-use memory region\n",
+		       (u64)start, size);
 		goto disable;
 	}
 
-	size = initrd_end - initrd_start;
-	memblock_reserve(__pa_symbol(initrd_start), size);
+	memblock_reserve(start, size);
+	/* Now convert initrd to virtual addresses */
+	initrd_start = (unsigned long)__va(phys_initrd_start);
+	initrd_end = initrd_start + phys_initrd_size;
 	initrd_below_start_ok = 1;
 
 	pr_info("Initial ramdisk at: 0x%p (%lu bytes)\n",
@@ -126,33 +147,36 @@ void __init setup_bootmem(void)
 {
 	struct memblock_region *reg;
 	phys_addr_t mem_size = 0;
+	phys_addr_t total_mem = 0;
+	phys_addr_t mem_start, end = 0;
 	phys_addr_t vmlinux_end = __pa_symbol(&_end);
 	phys_addr_t vmlinux_start = __pa_symbol(&_start);
 
 	/* Find the memory region containing the kernel */
 	for_each_memblock(memory, reg) {
-		phys_addr_t end = reg->base + reg->size;
-
-		if (reg->base <= vmlinux_start && vmlinux_end <= end) {
-			mem_size = min(reg->size, (phys_addr_t)-PAGE_OFFSET);
-
-			/*
-			 * Remove memblock from the end of usable area to the
-			 * end of region
-			 */
-			if (reg->base + mem_size < end)
-				memblock_remove(reg->base + mem_size,
-						end - reg->base - mem_size);
-		}
+		end = reg->base + reg->size;
+		if (!total_mem)
+			mem_start = reg->base;
+		if (reg->base <= vmlinux_start && vmlinux_end <= end)
+			BUG_ON(reg->size == 0);
+		total_mem = total_mem + reg->size;
 	}
-	BUG_ON(mem_size == 0);
+
+	/*
+	 * Remove memblock from the end of usable area to the
+	 * end of region
+	 */
+	mem_size = min(total_mem, (phys_addr_t)-PAGE_OFFSET);
+	if (mem_start + mem_size < end)
+		memblock_remove(mem_start + mem_size,
+				end - mem_start - mem_size);
 
 	/* Reserve from the start of the kernel to the end of the kernel */
 	memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start);
 
-	set_max_mapnr(PFN_DOWN(mem_size));
 	max_pfn = PFN_DOWN(memblock_end_of_DRAM());
 	max_low_pfn = max_pfn;
+	set_max_mapnr(max_low_pfn);
 
 #ifdef CONFIG_BLK_DEV_INITRD
 	setup_initrd();
diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c
index 4a8b61806633..87b4ab3d3c77 100644
--- a/arch/riscv/mm/kasan_init.c
+++ b/arch/riscv/mm/kasan_init.c
@@ -44,7 +44,7 @@ asmlinkage void __init kasan_early_init(void)
 				(__pa(((uintptr_t) kasan_early_shadow_pmd))),
 				__pgprot(_PAGE_TABLE)));
 
-	flush_tlb_all();
+	local_flush_tlb_all();
 }
 
 static void __init populate(void *start, void *end)
@@ -79,7 +79,7 @@ static void __init populate(void *start, void *end)
 			pfn_pgd(PFN_DOWN(__pa(&pmd[offset])),
 				__pgprot(_PAGE_TABLE)));
 
-	flush_tlb_all();
+	local_flush_tlb_all();
 	memset(start, 0, end - start);
 }
 
diff --git a/arch/riscv/mm/pageattr.c b/arch/riscv/mm/pageattr.c
index ec2c70f84994..289a9a5ea5b5 100644
--- a/arch/riscv/mm/pageattr.c
+++ b/arch/riscv/mm/pageattr.c
@@ -151,6 +151,7 @@ int set_memory_nx(unsigned long addr, int numpages)
 
 int set_direct_map_invalid_noflush(struct page *page)
 {
+	int ret;
 	unsigned long start = (unsigned long)page_address(page);
 	unsigned long end = start + PAGE_SIZE;
 	struct pageattr_masks masks = {
@@ -158,11 +159,16 @@ int set_direct_map_invalid_noflush(struct page *page)
 		.clear_mask = __pgprot(_PAGE_PRESENT)
 	};
 
-	return walk_page_range(&init_mm, start, end, &pageattr_ops, &masks);
+	mmap_read_lock(&init_mm);
+	ret = walk_page_range(&init_mm, start, end, &pageattr_ops, &masks);
+	mmap_read_unlock(&init_mm);
+
+	return ret;
 }
 
 int set_direct_map_default_noflush(struct page *page)
 {
+	int ret;
 	unsigned long start = (unsigned long)page_address(page);
 	unsigned long end = start + PAGE_SIZE;
 	struct pageattr_masks masks = {
@@ -170,7 +176,11 @@ int set_direct_map_default_noflush(struct page *page)
 		.clear_mask = __pgprot(0)
 	};
 
-	return walk_page_range(&init_mm, start, end, &pageattr_ops, &masks);
+	mmap_read_lock(&init_mm);
+	ret = walk_page_range(&init_mm, start, end, &pageattr_ops, &masks);
+	mmap_read_unlock(&init_mm);
+
+	return ret;
 }
 
 void __kernel_map_pages(struct page *page, int numpages, int enable)