Merge tag 'riscv-for-linus-4.16-merge_window' of...

Merge tag 'riscv-for-linus-4.16-merge_window' of git://git.kernel.org/pub/scm/linux/kernel/git/palmer/riscv-linux

Pull RISC-V updates from Palmer Dabbelt:
 "This contains the fixes we'd like to target for the 4.16 merge window.
  It's not as much as I was originally hoping to do but between glibc,
  the chip, and FOSDEM there just wasn't enough time to get everything
  put together. As such, this merge window is essentially just going to
  be small changes. This includes mostly cleanups:

   - A build fix failure to the audit test cases.

     RISC-V doesn't have renameat because the generic syscall ABI moved
     to renameat2 by the time of our port. The syscall audit test cases
     don't understand this, so I added a trivial fix. This went through
     mailing list review during the 4.15 merge window, but nobody has
     picked it up so I think it's best to just do this here.

   - The removal of our command-line argument processing code. The
     "mem_end" stuff was broken and the rest duplicated generic device
     tree code. The generic code was already being called.

   - Some unused/redundant code has been removed, including
     __ARCH_HAVE_MMU, current_pgdir, and the initialization of
     init_mm.pgd.

   - SUM is disabled upon taking a trap, which means that user memory is
     protected during traps taking inside copy_{to,from}_user().

   - The sptbr CSR has been renamed to satp in C code. We haven't
     changed the assembly code in order to maintain compatibility with
     binutils 2.29, which doesn't understand the new name.

  Additionally, we're adding some new features:

   - Basic ftrace support, thanks to Alan Kao!

   - Support for ZONE_DMA32.

     This is necessary for all the normal reasons, but also to deal with
     a deficiency in the Xilinx PCIe controller we're using on our
     FPGA-based systems. While the ZONE_DMA32 addition should be
     sufficient for most uses, it doesn't complete the fix for the
     Xilinx controller.

   - TLB shootdowns now only target the harts where they're necessary,
     instead of applying to all harts in the system.

  These patches have all been sitting on our linux-next branch for a
  while now. Due to time constraints this is all I feel comfortable
  submitting during the 4.16 merge window, hopefully we'll do better
  next time!"

[ Note to self: "harts" is RISC-V speak for "hardware threads".  I had
  to look that up.    - Linus ]

* tag 'riscv-for-linus-4.16-merge_window' of git://git.kernel.org/pub/scm/linux/kernel/git/palmer/riscv-linux:
  riscv: inline set_pgdir into its only caller
  riscv: rename sptbr to satp
  riscv: don't read back satp in paging_init
  riscv: remove the unused current_pgdir function
  riscv: add ZONE_DMA32
  RISC-V: Limit the scope of TLB shootdowns
  riscv: disable SUM in the exception handler
  riscv: remove redundant unlikely()
  riscv: remove unused __ARCH_HAVE_MMU define
  riscv/ftrace: Add basic support
  RISC-V: Remove mem_end command line processing
  RISC-V: Remove duplicate command-line parsing logic
  audit: Avoid build failures on systems without renameat

arch/riscv/Kconfig

@@ -22,6 +22,7 @@ config RISCV
 	select GENERIC_ATOMIC64 if !64BIT || !RISCV_ISA_A
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select HAVE_MEMBLOCK
+	select HAVE_MEMBLOCK_NODE_MAP
 	select HAVE_DMA_API_DEBUG
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_GENERIC_DMA_COHERENT
@@ -43,6 +44,10 @@ config MMU
 config ARCH_PHYS_ADDR_T_64BIT
 	def_bool y
 
+config ZONE_DMA32
+	bool
+	default y
+
 config ARCH_DMA_ADDR_T_64BIT
 	def_bool y
 
@@ -55,6 +60,9 @@ config PAGE_OFFSET
 config STACKTRACE_SUPPORT
 	def_bool y
 
+config TRACE_IRQFLAGS_SUPPORT
+	def_bool y
+
 config RWSEM_GENERIC_SPINLOCK
 	def_bool y
 
@@ -107,6 +115,8 @@ config ARCH_RV64I
 	bool "RV64I"
 	select CPU_SUPPORTS_64BIT_KERNEL
 	select 64BIT
+	select HAVE_FUNCTION_TRACER
+	select HAVE_FUNCTION_GRAPH_TRACER
 
 endchoice
 

arch/riscv/include/asm/Kbuild

@@ -12,7 +12,6 @@ generic-y += errno.h
 generic-y += exec.h
 generic-y += fb.h
 generic-y += fcntl.h
-generic-y += ftrace.h
 generic-y += futex.h
 generic-y += hardirq.h
 generic-y += hash.h

arch/riscv/include/asm/csr.h

@@ -40,15 +40,15 @@
 #define SR_SD   _AC(0x8000000000000000, UL) /* FS/XS dirty */
 #endif
 
-/* SPTBR flags */
+/* SATP flags */
 #if __riscv_xlen == 32
-#define SPTBR_PPN     _AC(0x003FFFFF, UL)
-#define SPTBR_MODE_32 _AC(0x80000000, UL)
-#define SPTBR_MODE    SPTBR_MODE_32
+#define SATP_PPN     _AC(0x003FFFFF, UL)
+#define SATP_MODE_32 _AC(0x80000000, UL)
+#define SATP_MODE    SATP_MODE_32
 #else
-#define SPTBR_PPN     _AC(0x00000FFFFFFFFFFF, UL)
-#define SPTBR_MODE_39 _AC(0x8000000000000000, UL)
-#define SPTBR_MODE    SPTBR_MODE_39
+#define SATP_PPN     _AC(0x00000FFFFFFFFFFF, UL)
+#define SATP_MODE_39 _AC(0x8000000000000000, UL)
+#define SATP_MODE    SATP_MODE_39
 #endif
 
 /* Interrupt Enable and Interrupt Pending flags */

arch/riscv/include/asm/ftrace.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2017 Andes Technology Corporation */
+
+/*
+ * The graph frame test is not possible if CONFIG_FRAME_POINTER is not enabled.
+ * Check arch/riscv/kernel/mcount.S for detail.
+ */
+#if defined(CONFIG_FUNCTION_GRAPH_TRACER) && defined(CONFIG_FRAME_POINTER)
+#define HAVE_FUNCTION_GRAPH_FP_TEST
+#endif

arch/riscv/include/asm/mmu_context.h

@@ -39,16 +39,6 @@ static inline void destroy_context(struct mm_struct *mm)
 {
 }
 
-static inline pgd_t *current_pgdir(void)
-{
-	return pfn_to_virt(csr_read(sptbr) & SPTBR_PPN);
-}
-
-static inline void set_pgdir(pgd_t *pgd)
-{
-	csr_write(sptbr, virt_to_pfn(pgd) | SPTBR_MODE);
-}
-
 /*
  * When necessary, performs a deferred icache flush for the given MM context,
  * on the local CPU.  RISC-V has no direct mechanism for instruction cache
@@ -93,7 +83,12 @@ static inline void switch_mm(struct mm_struct *prev,
 		cpumask_clear_cpu(cpu, mm_cpumask(prev));
 		cpumask_set_cpu(cpu, mm_cpumask(next));
 
-		set_pgdir(next->pgd);
+		/*
+		 * Use the old spbtr name instead of using the current satp
+		 * name to support binutils 2.29 which doesn't know about the
+		 * privileged ISA 1.10 yet.
+		 */
+		csr_write(sptbr, virt_to_pfn(next->pgd) | SATP_MODE);
 		local_flush_tlb_all();
 
 		flush_icache_deferred(next);

arch/riscv/include/asm/tlbflush.h

@@ -36,7 +36,14 @@ static inline void local_flush_tlb_page(unsigned long addr)
 
 #define flush_tlb_all() local_flush_tlb_all()
 #define flush_tlb_page(vma, addr) local_flush_tlb_page(addr)
-#define flush_tlb_range(vma, start, end) local_flush_tlb_all()
+
+static inline void flush_tlb_range(struct vm_area_struct *vma,
+		unsigned long start, unsigned long end)
+{
+	local_flush_tlb_all();
+}
+
+#define flush_tlb_mm(mm) flush_tlb_all()
 
 #else /* CONFIG_SMP */
 
@@ -45,16 +52,13 @@ static inline void local_flush_tlb_page(unsigned long addr)
 #define flush_tlb_all() sbi_remote_sfence_vma(0, 0, -1)
 #define flush_tlb_page(vma, addr) flush_tlb_range(vma, addr, 0)
 #define flush_tlb_range(vma, start, end) \
-	sbi_remote_sfence_vma(0, start, (end) - (start))
+	sbi_remote_sfence_vma(mm_cpumask((vma)->vm_mm)->bits, \
+			      start, (end) - (start))
+#define flush_tlb_mm(mm) \
+	sbi_remote_sfence_vma(mm_cpumask(mm)->bits, 0, -1)
 
 #endif /* CONFIG_SMP */
 
-/* Flush the TLB entries of the specified mm context */
-static inline void flush_tlb_mm(struct mm_struct *mm)
-{
-	flush_tlb_all();
-}
-
 /* Flush a range of kernel pages */
 static inline void flush_tlb_kernel_range(unsigned long start,
 	unsigned long end)

arch/riscv/include/asm/unistd.h

@@ -11,7 +11,6 @@
  *   GNU General Public License for more details.
  */
 
-#define __ARCH_HAVE_MMU
 #define __ARCH_WANT_SYS_CLONE
 #include <uapi/asm/unistd.h>
 #include <uapi/asm/syscalls.h>

arch/riscv/kernel/Makefile

@@ -2,6 +2,11 @@
 # Makefile for the RISC-V Linux kernel
 #
 
+ifdef CONFIG_FTRACE
+CFLAGS_REMOVE_ftrace.o = -pg
+CFLAGS_REMOVE_setup.o = -pg
+endif
+
 extra-y += head.o
 extra-y += vmlinux.lds
 
@@ -29,5 +34,7 @@ CFLAGS_setup.o := -mcmodel=medany
 obj-$(CONFIG_SMP)		+= smpboot.o
 obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_MODULES)		+= module.o
+obj-$(CONFIG_FUNCTION_TRACER)	+= mcount.o
+obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o
 
 clean:

arch/riscv/kernel/entry.S

@@ -78,10 +78,13 @@ _save_context:
 	REG_S x31, PT_T6(sp)
 
 	/*
-	 * Disable FPU to detect illegal usage of
-	 * floating point in kernel space
+	 * Disable user-mode memory access as it should only be set in the
+	 * actual user copy routines.
+	 *
+	 * Disable the FPU to detect illegal usage of floating point in kernel
+	 * space.
 	 */
-	li t0, SR_FS
+	li t0, SR_SUM | SR_FS
 
 	REG_L s0, TASK_TI_USER_SP(tp)
 	csrrc s1, sstatus, t0

arch/riscv/kernel/ftrace.c

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2013 Linaro Limited
+ * Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
+ * Copyright (C) 2017 Andes Technology Corporation
+ */
+
+#include <linux/ftrace.h>
+
+/*
+ * Most of this file is copied from arm64.
+ */
+void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
+			   unsigned long frame_pointer)
+{
+	unsigned long return_hooker = (unsigned long)&return_to_handler;
+	unsigned long old;
+	struct ftrace_graph_ent trace;
+	int err;
+
+	if (unlikely(atomic_read(&current->tracing_graph_pause)))
+		return;
+
+	/*
+	 * We don't suffer access faults, so no extra fault-recovery assembly
+	 * is needed here.
+	 */
+	old = *parent;
+
+	trace.func = self_addr;
+	trace.depth = current->curr_ret_stack + 1;
+
+	if (!ftrace_graph_entry(&trace))
+		return;
+
+	err = ftrace_push_return_trace(old, self_addr, &trace.depth,
+				       frame_pointer, NULL);
+	if (err == -EBUSY)
+		return;
+	*parent = return_hooker;
+}

arch/riscv/kernel/head.S

@@ -74,15 +74,15 @@ relocate:
 	sub a1, a1, a0
 	add ra, ra, a1
 
-	/* Point stvec to virtual address of intruction after sptbr write */
+	/* Point stvec to virtual address of intruction after satp write */
 	la a0, 1f
 	add a0, a0, a1
 	csrw stvec, a0
 
-	/* Compute sptbr for kernel page tables, but don't load it yet */
+	/* Compute satp for kernel page tables, but don't load it yet */
 	la a2, swapper_pg_dir
 	srl a2, a2, PAGE_SHIFT
-	li a1, SPTBR_MODE
+	li a1, SATP_MODE
 	or a2, a2, a1
 
 	/*

arch/riscv/kernel/mcount.S

+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2017 Andes Technology Corporation */
+
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <asm/asm.h>
+#include <asm/csr.h>
+#include <asm/unistd.h>
+#include <asm/thread_info.h>
+#include <asm/asm-offsets.h>
+#include <asm-generic/export.h>
+#include <asm/ftrace.h>
+
+	.text
+
+	.macro SAVE_ABI_STATE
+	addi	sp, sp, -16
+	sd	s0, 0(sp)
+	sd	ra, 8(sp)
+	addi	s0, sp, 16
+	.endm
+
+	/*
+	 * The call to ftrace_return_to_handler would overwrite the return
+	 * register if a0 was not saved.
+	 */
+	.macro SAVE_RET_ABI_STATE
+	addi	sp, sp, -32
+	sd	s0, 16(sp)
+	sd	ra, 24(sp)
+	sd	a0, 8(sp)
+	addi	s0, sp, 32
+	.endm
+
+	.macro STORE_ABI_STATE
+	ld	ra, 8(sp)
+	ld	s0, 0(sp)
+	addi	sp, sp, 16
+	.endm
+
+	.macro STORE_RET_ABI_STATE
+	ld	ra, 24(sp)
+	ld	s0, 16(sp)
+	ld	a0, 8(sp)
+	addi	sp, sp, 32
+	.endm
+
+ENTRY(ftrace_stub)
+	ret
+ENDPROC(ftrace_stub)
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ENTRY(return_to_handler)
+/*
+ * On implementing the frame point test, the ideal way is to compare the
+ * s0 (frame pointer, if enabled) on entry and the sp (stack pointer) on return.
+ * However, the psABI of variable-length-argument functions does not allow this.
+ *
+ * So alternatively we check the *old* frame pointer position, that is, the
+ * value stored in -16(s0) on entry, and the s0 on return.
+ */
+#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
+	mv	t6, s0
+#endif
+	SAVE_RET_ABI_STATE
+#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
+	mv	a0, t6
+#endif
+	la	t0, ftrace_return_to_handler
+	jalr	t0
+	mv	a1, a0
+	STORE_RET_ABI_STATE
+	jalr	a1
+ENDPROC(return_to_handler)
+EXPORT_SYMBOL(return_to_handler)
+#endif
+
+ENTRY(_mcount)
+	la	t4, ftrace_stub
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	la	t0, ftrace_graph_return
+	ld	t1, 0(t0)
+	bne	t1, t4, do_ftrace_graph_caller
+
+	la	t3, ftrace_graph_entry
+	ld	t2, 0(t3)
+	la	t6, ftrace_graph_entry_stub
+	bne	t2, t6, do_ftrace_graph_caller
+#endif
+	la	t3, ftrace_trace_function
+	ld	t5, 0(t3)
+	bne	t5, t4, do_trace
+	ret
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+/*
+ * A pseudo representation for the function graph tracer:
+ * prepare_to_return(&ra_to_caller_of_caller, ra_to_caller)
+ */
+do_ftrace_graph_caller:
+	addi	a0, s0, -8
+	mv	a1, ra
+#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
+	ld	a2, -16(s0)
+#endif
+	SAVE_ABI_STATE
+	la	t0, prepare_ftrace_return
+	jalr	t0
+	STORE_ABI_STATE
+	ret
+#endif
+
+/*
+ * A pseudo representation for the function tracer:
+ * (*ftrace_trace_function)(ra_to_caller, ra_to_caller_of_caller)
+ */
+do_trace:
+	ld	a1, -8(s0)
+	mv	a0, ra
+
+	SAVE_ABI_STATE
+	jalr	t5
+	STORE_ABI_STATE
+	ret
+ENDPROC(_mcount)
+EXPORT_SYMBOL(_mcount)

arch/riscv/kernel/setup.c

@@ -49,10 +49,6 @@ struct screen_info screen_info = {
 };
 #endif
 
-#ifdef CONFIG_CMDLINE_BOOL
-static char __initdata builtin_cmdline[COMMAND_LINE_SIZE] = CONFIG_CMDLINE;
-#endif /* CONFIG_CMDLINE_BOOL */
-
 unsigned long va_pa_offset;
 EXPORT_SYMBOL(va_pa_offset);
 unsigned long pfn_base;
@@ -153,25 +149,6 @@ void __init sbi_save(unsigned int hartid, void *dtb)
 	early_init_dt_scan(__va(dtb));
 }
 
-/*
- * Allow the user to manually add a memory region (in case DTS is broken);
- * "mem_end=nn[KkMmGg]"
- */
-static int __init mem_end_override(char *p)
-{
-	resource_size_t base, end;
-
-	if (!p)
-		return -EINVAL;
-	base = (uintptr_t) __pa(PAGE_OFFSET);
-	end = memparse(p, &p) & PMD_MASK;
-	if (end == 0)
-		return -EINVAL;
-	memblock_add(base, end - base);
-	return 0;
-}
-early_param("mem_end", mem_end_override);
-
 static void __init setup_bootmem(void)
 {
 	struct memblock_region *reg;
@@ -204,22 +181,19 @@ static void __init setup_bootmem(void)
 	early_init_fdt_scan_reserved_mem();
 	memblock_allow_resize();
 	memblock_dump_all();
+
+	for_each_memblock(memory, reg) {
+		unsigned long start_pfn = memblock_region_memory_base_pfn(reg);
+		unsigned long end_pfn = memblock_region_memory_end_pfn(reg);
+
+		memblock_set_node(PFN_PHYS(start_pfn),
+		                  PFN_PHYS(end_pfn - start_pfn),
+		                  &memblock.memory, 0);
+	}
 }
 
 void __init setup_arch(char **cmdline_p)
 {
-#ifdef CONFIG_CMDLINE_BOOL
-#ifdef CONFIG_CMDLINE_OVERRIDE
-	strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
-#else
-	if (builtin_cmdline[0] != '\0') {
-		/* Append bootloader command line to built-in */
-		strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE);
-		strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE);
-		strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
-	}
-#endif /* CONFIG_CMDLINE_OVERRIDE */
-#endif /* CONFIG_CMDLINE_BOOL */
 	*cmdline_p = boot_command_line;
 
 	parse_early_param();

arch/riscv/kernel/vdso.c

@@ -74,7 +74,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm,
 
 	down_write(&mm->mmap_sem);
 	vdso_base = get_unmapped_area(NULL, 0, vdso_len, 0, 0);
-	if (unlikely(IS_ERR_VALUE(vdso_base))) {
+	if (IS_ERR_VALUE(vdso_base)) {
 		ret = vdso_base;
 		goto end;
 	}

arch/riscv/mm/fault.c

@@ -238,6 +238,10 @@ asmlinkage void do_page_fault(struct pt_regs *regs)
 		 * Do _not_ use "tsk->active_mm->pgd" here.
 		 * We might be inside an interrupt in the middle
 		 * of a task switch.
+		 *
+		 * Note: Use the old spbtr name instead of using the current
+		 * satp name to support binutils 2.29 which doesn't know about
+		 * the privileged ISA 1.10 yet.
 		 */
 		index = pgd_index(addr);
 		pgd = (pgd_t *)pfn_to_virt(csr_read(sptbr)) + index;

arch/riscv/mm/init.c

@@ -17,6 +17,7 @@
 #include <linux/initrd.h>
 #include <linux/memblock.h>
 #include <linux/swap.h>
+#include <linux/sizes.h>
 
 #include <asm/tlbflush.h>
 #include <asm/sections.h>
@@ -25,11 +26,12 @@
 
 static void __init zone_sizes_init(void)
 {
-	unsigned long zones_size[MAX_NR_ZONES];
+	unsigned long max_zone_pfns[MAX_NR_ZONES] = { 0, };
 
-	memset(zones_size, 0, sizeof(zones_size));
-	zones_size[ZONE_NORMAL] = max_mapnr;
-	free_area_init_node(0, zones_size, pfn_base, NULL);
+	max_zone_pfns[ZONE_DMA32] = PFN_DOWN(min(4UL * SZ_1G, max_low_pfn));
+	max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
+
+	free_area_init_nodes(max_zone_pfns);
 }
 
 void setup_zero_page(void)
@@ -39,8 +41,6 @@ void setup_zero_page(void)
 
 void __init paging_init(void)
 {
-	init_mm.pgd = (pgd_t *)pfn_to_virt(csr_read(sptbr));
-
 	setup_zero_page();
 	local_flush_tlb_all();
 	zone_sizes_init();

include/asm-generic/audit_dir_write.h

@@ -27,7 +27,9 @@ __NR_mknod,
 __NR_mkdirat,
 __NR_mknodat,
 __NR_unlinkat,
+#ifdef __NR_renameat
 __NR_renameat,
+#endif
 __NR_linkat,
 __NR_symlinkat,
 #endif